Compare commits

...

349 Commits

Author SHA1 Message Date
Brooklyn Nicholson
d459868776 docs(analysis): map IDE coding-agent harness techniques onto Hermes
Study of the five harness subsystems that make in-editor coding agents
outperform the raw model (same models underneath), with a grounded map of
each onto the Hermes codebase: indexed semantic retrieval, retrieval-as-
accuracy-driver, decoupled apply model, ambient context, per-task routing.

Findings reference real files (tools/fuzzy_match.py, agent/auxiliary_client.py,
agent/prompt_builder.py, hermes_state.py). Identifies semantic codebase
retrieval as the one structural gap; apply-reliability and model-routing as
existing strengths.
2026-06-04 01:54:49 -05:00
kshitij
0401176c7a Merge pull request #38760 from helix4u/fix/prefill-config-compat
fix(config): align prefill messages key handling
2026-06-03 23:52:47 -07:00
Siddharth Balyan
f31c950182 refactor(supermemory): session-level ingest + kebab aliases (salvaged from #32487) (#38756)
* refactor(supermemory): session-level conversation ingest + kebab tool aliases

Salvaged from #32487 (by @MaheshtheDev), rebased onto current main.

- sync_turn now buffers cleaned turns; the full session is ingested once
  at session end / switch / shutdown via the conversations endpoint
- ingest_conversation() accepts and forwards functional document metadata
  (type, session_id, message_count, partial)
- register kebab-case tool aliases (supermemory-save/search/forget/profile)
  alongside the snake_case names
- README + docs (EN/zh-Hans) updated for the simplified session model

Source/vendor-attribution removed per project policy (no telemetry):
dropped x-sm-source header, sm_source metadata, and sm_capture_mode tags.
Preserved the post-branch atomic_json_write(mode=0o600) hardening that the
PR's stale base had reverted. Updated provider tests for the new behavior
and added maheshthedev@gmail.com to release.py AUTHOR_MAP.

Co-authored-by: alt-glitch <balyan.sid@gmail.com>

* feat(supermemory): restore x-sm-source for Spaces routing

Reinstates x-sm-source: hermes (SDK default_headers + conversations POST)
and sm_source: hermes document metadata. Per @Dhravya (Supermemory), this
is a functional routing key, not telemetry: it groups Hermes writes into a
dedicated "Hermes" Space in the Supermemory app so users can filter and
bulk-manage memories per source agent.

sm_capture_mode remains dropped (appears analytics-only; Spaces are routed
by sm_source) pending confirmation. Adds README note + a unit test covering
_merge_metadata sm_source stamping and legacy source->type migration.

---------

Co-authored-by: Mahesh Sanikommu <maheshthedev@gmail.com>
2026-06-04 11:50:02 +05:30
helix4u
ffb53767bf fix(config): align prefill messages key handling 2026-06-03 23:51:44 -06:00
brooklyn!
3c163cb035 feat(desktop): background needs-input indicator, clarify redesign, Cmd+K palette & UI consistency pass (#38631)
* fix(desktop): surface background-session clarify prompts instead of hanging

clarify.request is a one-shot blocking event: the gateway turn blocks on
clarify.respond. The desktop handler dropped it for any non-focused session
(`if (!isActiveEvent) return`) and stored at most one request in a single
global atom, so a background session that asked a clarifying question hung
forever and re-focusing it could never recover (the event was already gone).

- store/clarify.ts: key pending requests by runtime session id; expose the
  active session's request via a focus-scoped computed view (ClarifyTool is
  unchanged). clearClarifyRequest takes an optional session id for targeted
  clears, with a request-id fallback.
- use-message-stream.ts: park every session's clarify (drop the isActiveEvent
  early return); toast when one lands for a background session since the row
  otherwise just keeps spinning like normal work.
- clarify-tool.tsx: clear by session id so answering one chat can't wipe
  another's pending request.
- store/clarify.test.ts: concurrent independence, focus-scoped view,
  targeted/stale/fallback clears.

* feat(desktop): persistent needs-input indicator + icon button consolidation

Replace the background-clarify toast (expired on alt-tab, easy to miss) with a
persistent, glowing amber "needs input" dot on the session's sidebar row,
driven off a new ClientSessionState.needsInput flag mirrored into a
$attentionSessionIds store. The flag is set on clarify.request and cleared the
moment the turn resumes (tool.complete) or ends.

Also: redesign the clarify tool UI (borderless choices, pseudo-radio dots,
right-aligned checkmark, arc border, tighter padding), make Button the single
source of icon-button styling (4px radius, new icon-titlebar variant, titlebar
buttons rendered polymorphically via asChild, Codicons throughout), put the
file-tree refresh action first, and .trim() pasted composer text.

* style(desktop): padding-driven, square non-icon buttons

Default button sizing was vanilla-shadcn chunky (fixed h-9, 16px padding) and
inconsistent with the icon-button radius pass. Size text variants by
padding + line-height instead of fixed heights so they stay snug and scale
with content, and drop the radius on non-icon buttons (icon buttons keep the
shared 4px). Move the update-overlay CTAs off a hardcoded h-10 onto the
padding-based lg variant. Composer and the inline approval strip are untouched.

* style(desktop): shrink button scale, flush overlay sidebar, variant-ize stray buttons

- Buttons: smaller default font (14px -> 13px) and tighter padding-driven sizes
  across every variant; the chunky shadcn scale read as oversized in a dense
  desktop UI.
- Overlay split layout (settings / command center): the shared OverlayView top
  padding left the card surface showing as a gap above the sidebar. Move the
  titlebar clearance into each column so the sidebar background runs flush to
  the card's top edge.
- Consolidate buttons that hardcoded size/radius/font onto the proper size
  variants (tooltip-icon-button, overlay close, cron IconAction, SidebarTrigger,
  gateway system button, session-row actions radius, title chip radius, release
  notes link) so styling flows from variant props, not per-call overrides.
  Composer and the inline approval strip are intentionally left as-is.

* style(desktop): 12px button text, drop sparkle decoration + redundant settings titles

- Button base font down to 12px (text-xs) for the dense desktop scale.
- Remove the decorative Sparkles glyph from the model "Apply" button (keep the
  spinner while applying).
- Drop the page-level section titles that just restate the left nav ("Main
  model", "Appearance", "MCP servers") — the sidebar already labels the pane.
  Sub-section headings (Auxiliary models, LLM providers, etc.) stay.

* feat(desktop): add boxless `text` button variant; use for aux-model actions

New reusable `text` variant renders a button as inline label text (no
bg/border, muted -> foreground, underline-on-hover affordance). Emphasize the
actionable word by adding `font-semibold`/`underline` at the call site. Applied
to the auxiliary-model "Set to main" (plain), "Change" and "Reset all to main"
(bold + underlined) actions, replacing the boxed ghost/outline buttons.

* style(desktop): nudge button scale up + 2.5px radius on non-icon buttons

Bump default/sm vertical padding a step (the 12px pass read too small) and give
non-icon buttons a subtle 2.5px radius instead of square corners. Icon buttons
keep their 4px.

* style(desktop): unify Input/Textarea/SelectTrigger on shared controlVariants

Mirror the buttonVariants exercise for non-composer form controls: add a
single controlVariants source of truth (2.5px radius, 12px text,
padding-driven sizing, chrome via desktop-input-chrome) and consume it from
Input, Textarea, and SelectTrigger. Drop per-call radius/height/font
overrides that fought the shared look.

* style(desktop): flatten appearance settings — drop card-in-card sections

Remove the outer card chrome (border/bg/shadow/rounded) wrapping each
appearance section so they're flat headings + option grids instead of
boxes nested inside boxes, matching the other settings pages.

* style(desktop): de-box appearance options into flat rows + bare theme swatches

Color Mode and Tool Call Display become flat radio-style rows (no tile
border/fill, no inner icon box, no filled check badge — just a subtle active
bg and a check). Theme drops its outer card wrapper so only the preview
swatch shows, with a primary ring marking the active palette.

* style(desktop): primitive-level pointer cursor + borderless settings lists

Add a base-layer rule giving every interactive control (button, select,
menu item, switch, tab, summary) cursor:pointer, and strip the now-redundant
hardcoded cursor-pointer from those elements (plain clickable divs/labels
keep theirs). Remove the divide-y separators from settings list sections so
they breathe.

* style(desktop): Color Mode + Tool Call Display as one-row segmented controls

Replace the vertical option-row lists with a compact SegmentedControl
(grouped pill buttons on a single track), dropping the per-option
descriptions since the section subtitle already covers the context.

* style(desktop): drop redundant On/Off label next to boolean config switches

The switch already communicates state, so the text label was noise.

* style(desktop): add Switch xs size; move appearance controls inline-right

Add an xs size variant to the Switch primitive and use it for the provider
edit submenu toggles. In appearance settings, drop the redundant selection
Pills (the UI already shows the active choice), move the Color Mode and Tool
Call Display segmented controls into the section header's right side
(responsive: stacks under the heading on narrow widths), and shrink the
segmented control.

* feat(desktop): titlebar toggle to flip sidebar sides

Adds a top-left swap button (replacing the search icon) that mirrors the
layout: sessions sidebar ↔ file browser + preview rail. Persisted via
$panesFlipped. The left/right sidebar toggles, content inset, and pane
borders all follow the active side so the buttons stay accurate after a flip.

* feat(desktop): global Cmd+K palette + UI consistency overhaul

Builds on the clarify/needs-input work with a cross-cutting pass to make
the desktop surfaces feel like one app.

- Global Cmd+K command palette (cmdk): nav, settings deep-links, async
  API-key / MCP-server / archived-session groups, reusable theme sub-page
  (light/dark groups, stays open on pick), loop nav, fuzzy match. Replaces
  per-page settings search.
- Shared SearchField: borderless, underline-on-focus, `field-sizing`
  auto-width. Unifies sessions sidebar, pages, overlays, command center,
  cron; drops bespoke OverlaySearchInput.
- Cron & Profiles converted to OverlayView; flat token-driven panels
  (no card-in-card / divider borders) matching command center.
- `r` refresh hotkey via useRefreshHotkey; drop the visible refresh buttons.
- Button text/textStrong link variants applied across settings & views;
  shared PAGE_INSET_X content gutters.
- Math/ascii loaders replace "Loading…" text placeholders; x-icon close
  over text "Close"; cursor-pointer at the dropdown/select primitive level.

* style(desktop): tidy root error-boundary actions

Reload window → text link, Open logs pushed right (ml-auto), and the
error message box drops the oversized rounded-2xl for rounded-md.

* style(desktop): fix profiles sidebar — header + add-icon, drop text-link

The full-width `text` New-profile button drew an underline under the +
glyph on hover (text-decoration spans the icon). Replace with a proper
"PROFILES" section header + ghost add-icon button, matching the chat
sidebar's header/new-item pattern.

* style(desktop): kill focus rings globally

Tab/focus showed Tailwind's `focus-visible:ring-*` (a box-shadow) plus the
native outline. Drop both via an unlayered reset that nulls --tw-ring-*;
the composer / input soft-glow is untouched (those use direct box-shadows).

* style(desktop): shared Badge component; tidy profile metadata

Add a proper shadcn-style Badge (CVA tones, app radius — not a full pill)
and use it for the Default/.env tags instead of bespoke rounded-full spans.
Drop the oversized text-sm metadata values to text-xs.

* style(desktop): migrate bespoke pills to shared Badge; tidy cron/titlebar

- Sidebar toggles in the titlebar no longer carry an active highlight —
  they're plain show/hide affordances now.
- Replace every bespoke rounded-full status pill (cron, messaging,
  settings, skills) with the shared Badge (adds a `warn` tone). App radius,
  one component.
- Cron row actions use Codicons (play/debug-pause/zap/edit/trash) to match
  the rest of the chrome instead of stray lucide glyphs.

* style(desktop): drop active background on titlebar actions

Mute/haptics state reads from the icon glyph (and aria-pressed) — no
background highlight on any titlebar action.

* style(desktop): tighten error-boundary action gap

gap-4 → gap-2.5 between Try again / Reload window.

* style(desktop): hide search when there's nothing to search

Empty datasets no longer render a search field. Adds a `searchHidden` prop
to PageSearchShell (artifacts/skills/messaging) and gates cron + command
center sessions search on a non-empty list. The chat sidebar already did
this via showSessionSections.

* fix(desktop): composer wraps long text & expands at the real wrap point

Long unbroken input ran off horizontally and the stacked layout flipped
on a char-count guess (too early). Add wrap rules to the contentEditable
and drive expansion off the editor's actual rendered height via the
resize observer, so it stacks exactly when the text wraps to a 2nd line.

* feat(desktop): composer/intro polish + shared ErrorState

- Composer single-line row centers (was bottom-aligned); placeholder
  randomizes per session (starter vs follow-up) without mid-stream flip.
- Drop chat header on brand-new sessions (dead label + border).
- ⌘N flashes its sidebar hint; ⌘. toggles the command center.
- Intro wordmark fills width (drop 8rem fit cap).
- Unify error states on a shared ErrorState component (boundary + updates).

* style(desktop): satisfy lint across PR-touched files

* refactor(desktop): DRY/elegance pass over PR-touched files

- Shared useDeepLinkHighlight hook collapses 3 near-identical settings
  deep-link effects (keys/mcp); config kept inline (distinct bail-clear).
- command-center: table-driven SECTION_ICONS + single errorText helper.
- clarify-tool: OPTION_ROW_CLASS + RadioDot extracted from option rows.
- desktop-controller: merge Cmd+K / Cmd+. into one keydown handler.
- statusbar-controls: hoist shared action class.
- Misc: drop redundant cn()/cursor-pointer/dead fields; tidy switch.

* feat(desktop): Cmd+K jumps to sessions; drop API-key entries

Add active sessions to the palette (fuzzy jump-to-chat), remove the
low-value per-API-key entries, and move the lazy palette sources
(config/sessions/archived) to react-query instead of hand-rolled
useState + effect fetching. Hoist the shared nav helper.
2026-06-04 00:47:08 -05:00
Brooklyn Nicholson
86643d84e9 feat(desktop): Cmd+K jumps to sessions; drop API-key entries
Add active sessions to the palette (fuzzy jump-to-chat), remove the
low-value per-API-key entries, and move the lazy palette sources
(config/sessions/archived) to react-query instead of hand-rolled
useState + effect fetching. Hoist the shared nav helper.
2026-06-04 00:32:55 -05:00
Brooklyn Nicholson
bc9e33d66b refactor(desktop): DRY/elegance pass over PR-touched files
- Shared useDeepLinkHighlight hook collapses 3 near-identical settings
  deep-link effects (keys/mcp); config kept inline (distinct bail-clear).
- command-center: table-driven SECTION_ICONS + single errorText helper.
- clarify-tool: OPTION_ROW_CLASS + RadioDot extracted from option rows.
- desktop-controller: merge Cmd+K / Cmd+. into one keydown handler.
- statusbar-controls: hoist shared action class.
- Misc: drop redundant cn()/cursor-pointer/dead fields; tidy switch.
2026-06-04 00:28:57 -05:00
Brooklyn Nicholson
38acced687 style(desktop): satisfy lint across PR-touched files 2026-06-04 00:22:17 -05:00
Brooklyn Nicholson
5bb7156949 feat(desktop): composer/intro polish + shared ErrorState
- Composer single-line row centers (was bottom-aligned); placeholder
  randomizes per session (starter vs follow-up) without mid-stream flip.
- Drop chat header on brand-new sessions (dead label + border).
- ⌘N flashes its sidebar hint; ⌘. toggles the command center.
- Intro wordmark fills width (drop 8rem fit cap).
- Unify error states on a shared ErrorState component (boundary + updates).
2026-06-04 00:19:05 -05:00
Brooklyn Nicholson
3a5e36cfa5 fix(desktop): composer wraps long text & expands at the real wrap point
Long unbroken input ran off horizontally and the stacked layout flipped
on a char-count guess (too early). Add wrap rules to the contentEditable
and drive expansion off the editor's actual rendered height via the
resize observer, so it stacks exactly when the text wraps to a 2nd line.
2026-06-04 00:03:41 -05:00
Brooklyn Nicholson
aecdc75bb0 style(desktop): hide search when there's nothing to search
Empty datasets no longer render a search field. Adds a `searchHidden` prop
to PageSearchShell (artifacts/skills/messaging) and gates cron + command
center sessions search on a non-empty list. The chat sidebar already did
this via showSessionSections.
2026-06-03 23:55:04 -05:00
Brooklyn Nicholson
9e02b18828 style(desktop): tighten error-boundary action gap
gap-4 → gap-2.5 between Try again / Reload window.
2026-06-03 23:53:25 -05:00
Brooklyn Nicholson
fd68ae6331 style(desktop): drop active background on titlebar actions
Mute/haptics state reads from the icon glyph (and aria-pressed) — no
background highlight on any titlebar action.
2026-06-03 23:53:10 -05:00
Brooklyn Nicholson
e026fd88cd style(desktop): migrate bespoke pills to shared Badge; tidy cron/titlebar
- Sidebar toggles in the titlebar no longer carry an active highlight —
  they're plain show/hide affordances now.
- Replace every bespoke rounded-full status pill (cron, messaging,
  settings, skills) with the shared Badge (adds a `warn` tone). App radius,
  one component.
- Cron row actions use Codicons (play/debug-pause/zap/edit/trash) to match
  the rest of the chrome instead of stray lucide glyphs.
2026-06-03 23:52:51 -05:00
Brooklyn Nicholson
fd88d527af style(desktop): shared Badge component; tidy profile metadata
Add a proper shadcn-style Badge (CVA tones, app radius — not a full pill)
and use it for the Default/.env tags instead of bespoke rounded-full spans.
Drop the oversized text-sm metadata values to text-xs.
2026-06-03 23:49:45 -05:00
Brooklyn Nicholson
88bdb6b074 style(desktop): kill focus rings globally
Tab/focus showed Tailwind's `focus-visible:ring-*` (a box-shadow) plus the
native outline. Drop both via an unlayered reset that nulls --tw-ring-*;
the composer / input soft-glow is untouched (those use direct box-shadows).
2026-06-03 23:48:22 -05:00
Brooklyn Nicholson
ded620b711 style(desktop): fix profiles sidebar — header + add-icon, drop text-link
The full-width `text` New-profile button drew an underline under the +
glyph on hover (text-decoration spans the icon). Replace with a proper
"PROFILES" section header + ghost add-icon button, matching the chat
sidebar's header/new-item pattern.
2026-06-03 23:47:42 -05:00
Brooklyn Nicholson
311e80809f style(desktop): tidy root error-boundary actions
Reload window → text link, Open logs pushed right (ml-auto), and the
error message box drops the oversized rounded-2xl for rounded-md.
2026-06-03 23:46:49 -05:00
Brooklyn Nicholson
ac9de2e80c feat(desktop): global Cmd+K palette + UI consistency overhaul
Builds on the clarify/needs-input work with a cross-cutting pass to make
the desktop surfaces feel like one app.

- Global Cmd+K command palette (cmdk): nav, settings deep-links, async
  API-key / MCP-server / archived-session groups, reusable theme sub-page
  (light/dark groups, stays open on pick), loop nav, fuzzy match. Replaces
  per-page settings search.
- Shared SearchField: borderless, underline-on-focus, `field-sizing`
  auto-width. Unifies sessions sidebar, pages, overlays, command center,
  cron; drops bespoke OverlaySearchInput.
- Cron & Profiles converted to OverlayView; flat token-driven panels
  (no card-in-card / divider borders) matching command center.
- `r` refresh hotkey via useRefreshHotkey; drop the visible refresh buttons.
- Button text/textStrong link variants applied across settings & views;
  shared PAGE_INSET_X content gutters.
- Math/ascii loaders replace "Loading…" text placeholders; x-icon close
  over text "Close"; cursor-pointer at the dropdown/select primitive level.
2026-06-03 23:45:45 -05:00
Teknium
40420a619b fix(desktop): attachments on Enter, IME composition, scroll, fetchJson resets (salvage #38502) (#38677)
* fix(desktop): critical fixes — attachments, IME composition, scroll, fetchJson

DC2: Pass attachments to onSubmit() on direct Enter submit and call
clearComposerAttachments().  Previously attachments were silently
dropped — only text was sent while attachment pills remained visible.

DH1: Add 'open' to ThinkingDisclosure ResizeObserver effect deps.
When the disclosure toggles, refs point to new DOM but the observer
wasn't reattached, breaking live-scroll preview after expand/collapse
and leaking detached DOM nodes.

DH3+DH4: Add composition tracking via composingRef (set by
compositionstart/compositionend).  Guards handleEditorInput (skip
preedit state writes), handleEditorKeyDown (prefer composingRef over
unreliable isComposing), and form onSubmit (prevent IME Enter from
triggering submission).  Fixes IME Enter message splitting and preedit
text leaking into app state on CJK input.

DH6: Add res.on('error', reject) to fetchJson response stream.
Without this, a TCP reset mid-transfer left the promise hanging forever,
freezing the desktop UI.

All TypeScript compiles cleanly.

* chore: add copii.list@gmail.com to AUTHOR_MAP (stremtec)

* fix(desktop): prevent scroll snap-back during streaming, atomic config writes

DH2: Defer pinToBottom() in useLayoutEffect to rAF so that browser
scroll/wheel events from the current frame are processed first.
Previously an immediate pinToBottom() could snap the viewport back
to bottom against the user's trackpad scroll-up intent during
streaming — the wheel event hadn't fired yet so stickyBottomRef was
still true.

DH7: Add writeFileAtomic() helper (write to .tmp then rename) and
use it in writeDesktopConnectionConfig, writeDesktopUpdateConfig,
and writeBootstrapMarker.  Prevents partial writes on crash/power
loss that would corrupt JSON config files, requiring manual repair.

* fix(desktop): guard nativeTheme listener from duplicates, invalidate connection config cache

DM9: Guard nativeTheme.on('updated') with a one-shot flag so that
multiple createWindow() calls (e.g. macOS activate after all windows
closed) don't accumulate duplicate listeners on the process-wide
singleton.

DM3: Add mtime-based cache invalidation to readDesktopConnectionConfig.
Previously the cache was populated once and never invalidated — if an
external tool modified connection.json, the desktop ignored the change
until restart.  Now re-reads when the file's mtime differs.

* fix(desktop): widen fetchJson res.on('error') to sibling fetch + sort JSX props

Follow-up to salvaged #38502:
- resourceBufferFromUrl had the same mid-stream-reset hang class as
  fetchJson (req.on('error') present, res.on('error') missing). Add the
  response-stream error handler so a TCP reset during body read rejects
  instead of leaving the promise unsettled.
- Sort the new onComposition* JSX props to satisfy perfectionist/sort-jsx-props
  (was an introduced eslint error in the composer).

---------

Co-authored-by: asill-livestream <copii.list@gmail.com>
2026-06-03 23:38:58 -05:00
Ben Barclay
2e628ae971 fix(docker): add libolm-dev so matrix lazy-install can build python-olm (#33685)
Closes #25495 (matrix/synapse broken in the official docker image).

`tools/lazy_deps.py` routes `platform.matrix` to
`mautrix[encryption]==0.21.0`, which transitively depends on
`python-olm`. `python-olm` is a Cython extension that links against
`libolm`; without `libolm-dev` in the image's apt set the lazy-install
build fails. Add `libolm-dev` to the runtime apt install line so the
in-container source build succeeds on first matrix use.

Salvages #27795 by @konsisumer. Their PR targeted a pre-rework
Dockerfile (still had `build-essential nodejs npm` in the apt list,
no `ca-certificates`); cherry-pick conflicts on incidental apt-list
churn, so this re-applies the same one-word insert against the
current apt line plus the matching pyproject.toml comment update.

Co-authored-by: konsisumer <11262660+konsisumer@users.noreply.github.com>
2026-06-04 14:07:27 +10:00
Ben Barclay
30c7b787d1 fix(memory): fall back to pip when uv is unavailable (salvage #5954) (#38668)
`_install_dependencies` (hermes memory setup) hard-aborted with
"uv not found — cannot install dependencies" whenever `uv` was not on
PATH, even when a perfectly good `pip` was available. Slim container
images and some CI environments don't ship uv, so memory-provider
dependency installation dead-ended there for no good reason.

Now: use `uv pip install` when uv is present, otherwise fall back to
`<python> -m pip install` when pip3/pip is available, and only abort
(with the uv install hint) when neither is found. The "Run manually:"
hints reflect whichever installer was selected.

Salvages #5954 by @MustafaKara7. Their patch added redundant local
`import subprocess` / `import sys` (both are already in scope — module
-level `sys`, function-top `subprocess`); this salvage drops those and
adds a regression test (TestInstallDependenciesRunner) covering all
three paths (uv / pip-fallback / abort). Verified adversarially: the
pip-fallback test fails against origin/main's unfixed code with the
exact dead-end symptom and passes with the fix.

Closes #5954.

Co-authored-by: MustafaKara7 <186085093+MustafaKara7@users.noreply.github.com>
2026-06-04 14:03:02 +10:00
Ben Barclay
03ba06ebfb fix(docker): chown gateway install tree on UID remap (salvage #37928) (#38655)
Salvage of #37928 (@sarvesh1327), reduced to the still-needed delta.

`/opt/hermes/gateway` is a runtime-writable Python package: on first import
the supervised gateway writes `__pycache__` beneath it, and the image does
not set PYTHONDONTWRITEBYTECODE. When HERMES_UID/PUID is remapped at boot
(e.g. Unraid 99), `usermod -u` only re-chowns the hermes home dir; the build
trees under /opt/hermes keep the build-time UID (10000). main already chowns
`.venv`, `ui-tui`, and `node_modules` on remap (#38556) but missed `gateway`,
so the remapped gateway hits EACCES writing `__pycache__` (#27221).

Add `/opt/hermes/gateway` to both chown sites — the Dockerfile build-time
`chown -R hermes:hermes` line and the stage2-hook build-tree repair — so it
tracks the remapped UID like the sibling trees.

Differs from #37928 as submitted: dropped the `uid_gid_remapped` flag and the
`|| [ "$uid_gid_remapped" = true ]` chown gate. main's #38556 already solved
that half, and more correctly — it probes the actual tree ownership
(`venv_owner != actual_hermes_uid`) rather than tracking same-boot remaps,
which also catches pre-existing ownership drift and stays idempotent. Keeping
#37928's flag would regress that. The salvage is the `gateway`-tree addition
only.

Verified end-to-end against a real image build: on baseline main a remap to
UID 99 leaves `gateway` owned by 10000 and a write as uid 99 fails EACCES;
with this change `gateway` is chowned to 99:100 and the write succeeds, while
the default-uid (no-remap) path is unchanged.

Fixes #27221.

Co-authored-by: Sarvesh <sarveshagl1327@gmail.com>
2026-06-04 13:34:23 +10:00
Brooklyn Nicholson
e68fc4def2 feat(desktop): titlebar toggle to flip sidebar sides
Adds a top-left swap button (replacing the search icon) that mirrors the
layout: sessions sidebar ↔ file browser + preview rail. Persisted via
$panesFlipped. The left/right sidebar toggles, content inset, and pane
borders all follow the active side so the buttons stay accurate after a flip.
2026-06-03 22:30:47 -05:00
Teknium
e45dd2b0e7 refactor(web): unify main-slot model assignment base_url/context handling (#38593)
Both POST /api/model/set and the profile-model writer hand-rolled the same
provider/default/base_url/context_length reconciliation. Extract it into
_apply_main_model_assignment so the custom-vs-hosted base_url logic lives in
one place — removing the future-drift risk where one site learns about
custom base_url persistence and the other forgets.

Behavior unchanged; pinned with a direct helper unit test.
2026-06-03 20:25:33 -07:00
Ben Barclay
e2ea648a08 test(docker): make tty-passthrough probe robust to container boot-log noise (#38665)
`test_tty_passthrough_to_container` asserted `int(numeric_lines[0]) > 0`
where `numeric_lines` was every `.isdigit()` token in the FULL PTY stream
— but the container's s6 boot output (cont-init diagnostics, the preinit
`uid=0 ... egid=0` line, skills-sync summaries like
`Done: 90 new, 0 updated, 0 unchanged. 90 total bundled.`) is written to
the same PTY before the `tput cols` probe runs. So the test was really
asserting on "the first number anywhere in the boot log", which passed
only by luck on whatever that first digit happened to be.

Any PR that shifts boot output flips the first digit to a stray `0` and
breaks the test with `assert 0 > 0` — even when TTY passthrough is
working perfectly (`tput cols` returns the right value). This is a latent
landmine for every Docker PR that changes boot output (e.g. adding a
bundled dependency changes the skills-sync counts).

Fix: emit the probe result behind a unique marker
(`HERMES_TTY_COLS=<cols>` / `HERMES_TTY_COLS=NO_TTY`) and parse only the
marked value, ignoring all boot-log noise. The test's real intent — verify
`docker run -t` delivers a real TTY with a positive column count — is
preserved (NO_TTY and non-numeric values still fail).

Verified against a real build, adversarially:
- Built an image with extra boot output (the markdown core-dep change from
  #38649, which is what surfaced this) so the OLD logic grabs a stray `0`
  -> reproduced `assert 0 > 0` locally.
- The hardened test PASSES against that same image, and against a clean
  image. `tput cols` correctly returns 123 in both.
2026-06-04 13:19:13 +10:00
Brooklyn Nicholson
75e29f97ee style(desktop): add Switch xs size; move appearance controls inline-right
Add an xs size variant to the Switch primitive and use it for the provider
edit submenu toggles. In appearance settings, drop the redundant selection
Pills (the UI already shows the active choice), move the Color Mode and Tool
Call Display segmented controls into the section header's right side
(responsive: stacks under the heading on narrow widths), and shrink the
segmented control.
2026-06-03 22:17:26 -05:00
Brooklyn Nicholson
947f305f84 style(desktop): drop redundant On/Off label next to boolean config switches
The switch already communicates state, so the text label was noise.
2026-06-03 22:15:55 -05:00
Brooklyn Nicholson
41ede96304 style(desktop): Color Mode + Tool Call Display as one-row segmented controls
Replace the vertical option-row lists with a compact SegmentedControl
(grouped pill buttons on a single track), dropping the per-option
descriptions since the section subtitle already covers the context.
2026-06-03 22:15:27 -05:00
Brooklyn Nicholson
f15d2cb5e4 style(desktop): primitive-level pointer cursor + borderless settings lists
Add a base-layer rule giving every interactive control (button, select,
menu item, switch, tab, summary) cursor:pointer, and strip the now-redundant
hardcoded cursor-pointer from those elements (plain clickable divs/labels
keep theirs). Remove the divide-y separators from settings list sections so
they breathe.
2026-06-03 22:14:25 -05:00
Brooklyn Nicholson
2b762c5364 style(desktop): de-box appearance options into flat rows + bare theme swatches
Color Mode and Tool Call Display become flat radio-style rows (no tile
border/fill, no inner icon box, no filled check badge — just a subtle active
bg and a check). Theme drops its outer card wrapper so only the preview
swatch shows, with a primary ring marking the active palette.
2026-06-03 22:06:23 -05:00
Brooklyn Nicholson
75adf7d603 style(desktop): flatten appearance settings — drop card-in-card sections
Remove the outer card chrome (border/bg/shadow/rounded) wrapping each
appearance section so they're flat headings + option grids instead of
boxes nested inside boxes, matching the other settings pages.
2026-06-03 22:05:06 -05:00
Brooklyn Nicholson
0776d1b19c style(desktop): unify Input/Textarea/SelectTrigger on shared controlVariants
Mirror the buttonVariants exercise for non-composer form controls: add a
single controlVariants source of truth (2.5px radius, 12px text,
padding-driven sizing, chrome via desktop-input-chrome) and consume it from
Input, Textarea, and SelectTrigger. Drop per-call radius/height/font
overrides that fought the shared look.
2026-06-03 22:03:46 -05:00
Brooklyn Nicholson
d6e2c940e9 style(desktop): nudge button scale up + 2.5px radius on non-icon buttons
Bump default/sm vertical padding a step (the 12px pass read too small) and give
non-icon buttons a subtle 2.5px radius instead of square corners. Icon buttons
keep their 4px.
2026-06-03 22:00:39 -05:00
Brooklyn Nicholson
fb0250ef63 feat(desktop): add boxless text button variant; use for aux-model actions
New reusable `text` variant renders a button as inline label text (no
bg/border, muted -> foreground, underline-on-hover affordance). Emphasize the
actionable word by adding `font-semibold`/`underline` at the call site. Applied
to the auxiliary-model "Set to main" (plain), "Change" and "Reset all to main"
(bold + underlined) actions, replacing the boxed ghost/outline buttons.
2026-06-03 21:59:44 -05:00
Brooklyn Nicholson
1e1ab31ad6 style(desktop): 12px button text, drop sparkle decoration + redundant settings titles
- Button base font down to 12px (text-xs) for the dense desktop scale.
- Remove the decorative Sparkles glyph from the model "Apply" button (keep the
  spinner while applying).
- Drop the page-level section titles that just restate the left nav ("Main
  model", "Appearance", "MCP servers") — the sidebar already labels the pane.
  Sub-section headings (Auxiliary models, LLM providers, etc.) stay.
2026-06-03 21:58:47 -05:00
Brooklyn Nicholson
8c0f15478d style(desktop): shrink button scale, flush overlay sidebar, variant-ize stray buttons
- Buttons: smaller default font (14px -> 13px) and tighter padding-driven sizes
  across every variant; the chunky shadcn scale read as oversized in a dense
  desktop UI.
- Overlay split layout (settings / command center): the shared OverlayView top
  padding left the card surface showing as a gap above the sidebar. Move the
  titlebar clearance into each column so the sidebar background runs flush to
  the card's top edge.
- Consolidate buttons that hardcoded size/radius/font onto the proper size
  variants (tooltip-icon-button, overlay close, cron IconAction, SidebarTrigger,
  gateway system button, session-row actions radius, title chip radius, release
  notes link) so styling flows from variant props, not per-call overrides.
  Composer and the inline approval strip are intentionally left as-is.
2026-06-03 21:56:35 -05:00
Brooklyn Nicholson
712bf4d8e4 style(desktop): padding-driven, square non-icon buttons
Default button sizing was vanilla-shadcn chunky (fixed h-9, 16px padding) and
inconsistent with the icon-button radius pass. Size text variants by
padding + line-height instead of fixed heights so they stay snug and scale
with content, and drop the radius on non-icon buttons (icon buttons keep the
shared 4px). Move the update-overlay CTAs off a hardcoded h-10 onto the
padding-based lg variant. Composer and the inline approval strip are untouched.
2026-06-03 21:50:03 -05:00
Brooklyn Nicholson
35a750eedd feat(desktop): persistent needs-input indicator + icon button consolidation
Replace the background-clarify toast (expired on alt-tab, easy to miss) with a
persistent, glowing amber "needs input" dot on the session's sidebar row,
driven off a new ClientSessionState.needsInput flag mirrored into a
$attentionSessionIds store. The flag is set on clarify.request and cleared the
moment the turn resumes (tool.complete) or ends.

Also: redesign the clarify tool UI (borderless choices, pseudo-radio dots,
right-aligned checkmark, arc border, tighter padding), make Button the single
source of icon-button styling (4px radius, new icon-titlebar variant, titlebar
buttons rendered polymorphically via asChild, Codicons throughout), put the
file-tree refresh action first, and .trim() pasted composer text.
2026-06-03 21:44:30 -05:00
cornna
7402706c5e fix(docker): accept Unraid uid mappings (#38098)
Co-authored-by: Cornna <96944678+ymylive@users.noreply.github.com>
2026-06-04 12:38:24 +10:00
Dusk1e
2059707fce fix(gateway-windows): anchor detached/startup cwd at HERMES_HOME 2026-06-03 19:37:29 -07:00
LeonSGP43
40fbb0f3c6 fix(constants): use windows native default hermes home 2026-06-03 19:37:29 -07:00
Teknium
e3313c50a7 feat(dashboard): add Debug Share to the System page (#38600)
* Port from google-gemini/gemini-cli#21541: back up corrupted config.yaml

When config.yaml fails to parse, load_config() silently falls back to
DEFAULT_CONFIG and leaves the broken file on disk. If the user then re-runs
the setup wizard or hermes config set (both rewrite config.yaml), their
broken-but-recoverable overrides are lost for good.

Adapts the policy-file recovery from gemini-cli#21541: on the first parse
warning for a given broken file, snapshot it to config.yaml.corrupt.<ts>.bak
(best-effort, symlink-guarded, size-deduped) and tell the user where it
landed. Unlike Gemini's version we deliberately do NOT reset config.yaml to a
clean state — hermes never silently mutates user config, and leaving it means
a hand-fixed file is re-read on the next load.

Tests: 3 new cases (backup created + content preserved + original untouched;
same-size backup dedup; symlink not copied). E2E verified with isolated
HERMES_HOME and a real tab-indented broken config.

* feat(dashboard): add Debug Share to the System page

Surface `hermes debug share` in the dashboard. The System > Operations
section gets a dedicated card that uploads a redacted report + full logs
and returns the paste URLs as real, copyable links instead of a log tail.

- debug.py: factor a pure build_debug_share() returning structured
  {urls, failures, redacted, auto_delete_seconds}; run_debug_share now
  calls it (CLI output unchanged).
- web_server.py: POST /api/ops/debug-share runs the share core in a
  worker thread and returns the structured payload synchronously (the
  URLs are the whole point — not a backgrounded action).
- api.ts: runDebugShare() + DebugShareResponse.
- SystemPage.tsx: share card with a redaction toggle (on by default),
  per-link + copy-all buttons, and the 6h auto-delete countdown.
- tests: build_debug_share core + endpoint (redact toggle, failure 502,
  token gate).
2026-06-03 19:37:04 -07:00
Brooklyn Nicholson
72f556dfc4 Merge remote-tracking branch 'origin/main' into bb/desktop-background-clarify 2026-06-03 21:07:35 -05:00
Brooklyn Nicholson
58eb473baa fix(desktop): surface background-session clarify prompts instead of hanging
clarify.request is a one-shot blocking event: the gateway turn blocks on
clarify.respond. The desktop handler dropped it for any non-focused session
(`if (!isActiveEvent) return`) and stored at most one request in a single
global atom, so a background session that asked a clarifying question hung
forever and re-focusing it could never recover (the event was already gone).

- store/clarify.ts: key pending requests by runtime session id; expose the
  active session's request via a focus-scoped computed view (ClarifyTool is
  unchanged). clearClarifyRequest takes an optional session id for targeted
  clears, with a request-id fallback.
- use-message-stream.ts: park every session's clarify (drop the isActiveEvent
  early return); toast when one lands for a background session since the row
  otherwise just keeps spinning like normal work.
- clarify-tool.tsx: clear by session id so answering one chat can't wipe
  another's pending request.
- store/clarify.test.ts: concurrent independence, focus-scoped view,
  targeted/stale/fallback clears.
2026-06-03 21:07:33 -05:00
Teknium
f66a929a6b fix(desktop): render approval/sudo/secret prompts so tools stop silently timing out (#38578)
* fix(desktop): render approval/sudo/secret prompts so tools stop silently timing out

The desktop app's gateway event handler (use-message-stream.ts) handled
clarify.request but had no case for approval.request, sudo.request, or
secret.request. When a tool needed approval, the gateway emitted
approval.request and blocked the agent thread in _await_gateway_decision()
for up to 5 min (approvals.gateway_timeout); the desktop dropped the unknown
event, never showed a dialog, then the agent returned BLOCKED. No prompt,
just a stall then a block.

The Ink TUI already handles all three (createGatewayEventHandler.ts); this
brings the Electron app to parity.

- store/prompts.ts: approval/sudo/secret atoms (+ request-id-guarded clears)
- components/prompt-overlays.tsx: Radix dialogs; close/Esc maps to refusal so
  silence is never mistaken for consent (parity with TUI Esc->deny)
- use-message-stream.ts: wire the three *.request cases; clearAllPrompts on
  message.complete so an overlay can't outlive its turn
- chat-messages.ts: GatewayEventPayload gains command/description/env_var/prompt
- mount PromptOverlays in the chat shell

* feat(desktop): inline tool-call approval bar (Cursor-style "Run")

Render dangerous-command / execute_code approval inline on the pending
tool row instead of as a modal. Binding is positional: the desktop
tool.start payload carries no structured args, but approval.request only
fires from the terminal/execute_code guards and the agent blocks on one
approval at a time, so the single pending row of those tools is the one
that raised it. Command/description text comes from $approvalRequest.

Drops ApprovalDialog from PromptOverlays (sudo/secret stay modal).

* style(desktop): make inline approval bar match Cursor's command card

Drop the amber alert styling for a neutral elevated card: command on a
terminal-prefixed row up top, a divided footer with the muted description
on the left and right-aligned controls — a ghost "Reject" (Esc) plus a
split primary "Run" (⌘⏎) whose chevron opens "Allow this session" /
"Always allow" / "Reject". Wire ⌘/Ctrl+Enter → Run and Esc → Reject to
match Cursor's accept/skip bindings, guarded against double-send via the
$approvalRequest atom.

* style(desktop): shrink inline approval to a tiny Cursor-style button strip

The running tool row already shows the command, so drop the whole card +
command echo + description band. What's left is a compact strip under the
row: a small split "Run ⌘⏎" button (chevron → Allow this session / Always
allow / Reject) and a ghost "Reject Esc", indented to sit under the row's
title text.

* style(desktop): drop the loud blue Run button for a quiet outlined control

Swap the primary (blue) Run for a subtle outlined split control — neutral
border, transparent fill, hover-accent — so the approval strip reads as
quiet inline affordance rather than a big CTA. Reject stays ghost.

* style(desktop): make Run a soft primary badge

Tint the Run split control with the primary color as a badge (bg-primary/10,
primary text, primary/25 border, rounded-md, hover primary/15) instead of a
solid CTA or a neutral outline.

* style(desktop): slim the approval chevron and space out Reject

The chevron button had ballooned because dropping the size prop fell back
to the big default size (h-9 + has-svg px-3). Pin size=xs everywhere and
give the chevron a tight w-5/px-0. Bump the gap between the Run badge and
Reject (gap-2.5) and loosen Reject's internal spacing.

* feat(desktop): confirm before "Always allow" persists an approval

"Always allow" writes the matched pattern to ~/.hermes/config.yaml and
suppresses the prompt in every future session — too consequential to fire
straight from a menu click. Route it through a confirm dialog that names
the pattern + command and the file it touches. The dialog owns the
keyboard while open so Esc closes it instead of denying the approval.

* fix(gateway): make sudo + secret prompts actually fire in the desktop

Tek's PR added the sudo/secret overlays and callback wiring, but neither
reached the live path:

- Sudo: the sudo password callback is thread-local (terminal_tool
  _callback_tls), and _wire_callbacks runs on the agent-build thread, not
  the turn thread that executes tools. At command time the callback was
  missing, so terminal sudo fell through to /dev/tty and hung the headless
  gateway. Re-wire callbacks at the top of the prompt-submit turn thread.

- Secret: skills_tool short-circuited to the "secret entry unsupported"
  hint for any gateway surface, before invoking the callback. Interactive
  surfaces (desktop/TUI) register a secret-capture callback that routes to
  the secret.request overlay; only short-circuit when no callback exists,
  so messaging still gets the hint but the desktop prompts.

* docs(desktop): drop Cursor references from approval comments

* docs(desktop): drop Cursor reference from prompt-overlays comment

* fix(skills): gate in-band secret capture on HERMES_INTERACTIVE, not callback presence

The desktop/sudo PR switched the gateway secret-capture short-circuit from
"any gateway surface" to "gateway surface with no callback registered". That
made a messaging gateway (telegram/discord/...) attempt interactive in-band
secret capture whenever any callback happened to be registered, instead of
returning the safe "setup unsupported" hint — and broke
test_gateway_still_loads_skill_but_returns_setup_guidance.

Discriminate on HERMES_INTERACTIVE instead: the desktop app / TUI set it in
_enable_gateway_prompts (alongside registering the secret.request callback),
while messaging platforms never do. This is the same flag tools/approval.py
uses to tell an interactive surface from a messaging one, so messaging keeps
the hint and desktop/TUI still prompt.

---------

Co-authored-by: Brooklyn Nicholson <brooklyn.bb.nicholson@gmail.com>
2026-06-04 01:53:51 +00:00
Ben Barclay
04d620d91f fix(docker): run config migrations during container boot (salvage #35508) (#36627)
Salvage of #35508 (@dchenk), rebased onto current main. Resolved the
tests/tools/test_stage2_hook_puid_pgid.py conflict (kept both the
envdir-creation regression test on main and the new config-migration
tests).

Docker image upgrades replace code under $INSTALL_DIR but preserve
$HERMES_HOME on the mounted volume, so the persisted config.yaml never
received the schema migrations that non-Docker `hermes update` runs
(#35406). This adds scripts/docker_config_migrate.py, invoked from
stage2-hook after first-boot seeding and before gateway services start:
it backs up config.yaml + .env, runs migrate_config(interactive=False),
and honors HERMES_SKIP_CONFIG_MIGRATION=1 for manual control.

Also fixes a latent bug in check_config_version(): it called load_config()
which deep-merges DEFAULT_CONFIG, so a legacy config with no raw
_config_version falsely reported as already-current. It now reads the raw
on-disk file so legacy configs are correctly detected for migration.

Differs from #35508 as submitted (Option B cleanup): dropped the
`_config_version` line added to cli-config.yaml.example and removed the
accompanying test_cli_config_example_declares_latest_version change-detector
test. The example is a copy-template and has no business asserting a schema
version; check_config_version() reads the user's real config.yaml, not the
example. This removes a second sync point that drifts on every version bump.

Closes #35508. Fixes #35406.

Co-authored-by: Dmitriy Cherchenko <17372886+dchenk@users.noreply.github.com>
2026-06-04 11:11:27 +10:00
brooklyn!
92be989291 Merge pull request #38564 from NousResearch/bb/tui-sgr-mouse-fragment-leak
fix(hermes-ink): reassemble split SGR mouse sequences at the tokenizer (supersedes #29337)
2026-06-03 20:10:48 -05:00
Ben Barclay
343c54e35b fix(docker): reject unsupported --user <arbitrary-uid> start with clear guidance (#38579)
`docker run --user $(id -u):$(id -g)` was a tini-era trick to make
container-written files match the host user. Under s6-overlay it no longer
works: the bootstrap (UID remap, volume + build-tree chown, config seeding)
needs root, and the baked image dirs (/opt/data, /opt/hermes/.venv, ui-tui,
node_modules) are owned by the hermes build UID (10000). A pinned arbitrary
UID can't write them, so the runtime fails with EACCES on a bind mount or
hard-crashes on a named volume (Docker inits the volume from the image as
10000; the non-root start can't even `cd /opt/data`, and the profile
reconciler dies with PermissionError on gateway_state.json).

Detect that start early in both the cont-init hook (stage2-hook.sh) and the
CMD wrapper (main-wrapper.sh) and fail fast with actionable guidance pointing
at the supported path: root start + HERMES_UID/HERMES_GID (or the PUID/PGID
aliases), which remaps the hermes user and chowns the volume — the same
host-UID-matching outcome --user was used for, without breaking s6.

The guard fires only when the current UID is neither root NOR the hermes UID.
This preserves the supported non-root start from #34648/#34837 (running with
`--user 10000:10000`, i.e. pinned to the hermes UID itself), which is
unaffected — only the arbitrary-UID variant that #34837 never actually made
writable is rejected.

Verified live across five scenarios (built image, bind + named volume):
arbitrary --user on bind -> rejected with guidance, hermes does not run;
arbitrary --user on named volume -> guidance shown, no raw 'can't cd' crash;
--user 10000:10000 -> boots; root + HERMES_UID=4242 remap -> boots, guard not
tripped; default root start -> boots. Pre-fix control reproduces the raw
PermissionError + 'can't cd' crash with no guidance.
2026-06-04 10:51:51 +10:00
Teknium
b0a52d74ac fix(mcp): resolve ${ENV} in discovery probe so header auth works (#38571)
`hermes mcp add --auth header` built `Authorization: Bearer ${MCP_X_API_KEY}`
and passed it straight to the discovery probe without interpolation, so the
probe sent the literal placeholder and auth-requiring servers (e.g. n8n)
returned 401. Runtime tool loading worked because `_load_mcp_config()`
interpolates, but the four CLI probe call sites (add/test/login/configure)
all used unresolved config.

Resolve `${ENV}` inside `_probe_single_server` via a new
`_resolve_mcp_server_config()` (load_hermes_dotenv + _interpolate_env_vars),
mirroring runtime loading. This covers all four call sites, not just add.

Also strip a leading `Bearer ` from pasted tokens before saving to
`MCP_*_API_KEY`, so a token pasted with the prefix doesn't produce
`Bearer Bearer <jwt>` (also a 401).

Reported with a precise root-cause analysis in #37792.

Co-authored-by: ThyFriendlyFox <116314616+ThyFriendlyFox@users.noreply.github.com>
2026-06-03 17:49:39 -07:00
xxxigm
5a22cd427d fix(desktop): configure local/custom endpoint without an API key or UI changes
Onboarding's "Local / custom endpoint" only wrote the OPENAI_BASE_URL env
var, which runtime resolution ignores — so a self-hosted endpoint was never
wired in and setup failed with "No usable credentials found for custom" even
though local servers need no key.

Route the local option through saveOnboardingLocalEndpoint: probe the
endpoint, auto-discover a model from /v1/models, persist provider=custom +
base_url + model via /api/model/set, then verify the runtime directly
(not via completeWithModelConfirm, which would re-assign the model without
base_url and wipe it). No onboarding form/UI changes — the existing single
URL field is enough.
2026-06-03 17:48:55 -07:00
xxxigm
ca06715721 feat(web): wire local/custom endpoints into model assignment
The runtime resolver reads model.base_url from config and ignores the
OPENAI_BASE_URL env var, so a self-hosted endpoint could not be configured
from the GUI. Two changes enable it:

- POST /api/model/set accepts an optional base_url and persists it as
  model.base_url when provider=custom (still clearing stale base_url for
  hosted providers).
- POST /api/providers/validate now returns the model ids a custom endpoint
  advertises at /v1/models, so the GUI can auto-pick a default without
  asking the user to type a model name.

Refs desktop onboarding "Local / custom endpoint" bug.
2026-06-03 17:48:55 -07:00
Teknium
d50741af90 fix(onboarding): clarify Anthropic API vs OAuth provider entries and reorder (#38577)
The setup-flow provider list showed two Anthropic/Claude entries with
ambiguous labels ('Anthropic (Claude API)' and 'Claude Code (subscription)')
in no deliberate order. Relabel and reorder so the distinction and the
subscription caveat are explicit:

- 'Anthropic API Key' (PKCE, API path)
- 'Anthropic OAuth: Required Extra Usage Credits to Use Subscription' (external)
- Both Anthropic entries moved to the bottom of the list.
- 'OpenAI Codex (ChatGPT)' -> 'OpenAI OAuth (ChatGPT)', now first after Nous.

Applied consistently to the backend OAuth catalog (web_server.py) and the
desktop onboarding overlay's PROVIDER_DISPLAY title/order map; test
assertions updated to the new titles.
2026-06-03 17:46:04 -07:00
Brooklyn Nicholson
725290db63 test(hermes-ink): fuzz the tokenizer flush valve against fragment leaks
Hammer createTokenizer with the worst stalls a terminal can produce —
split + flush at every interior byte, and a 200-report byte-by-byte feed
that flushes after every single byte — and assert the two invariants that
make the SGR-leak class structurally impossible: nothing ever leaks as a
text token, and every complete report reassembles whole. A mixed
mouse+keystroke variant proves real input survives the same storm.
2026-06-03 19:38:08 -05:00
Teknium
e7bc6189cf feat(cli): resume relaunches in the directory the session was started from (#38562)
hermes -c / --resume now reopen a session in its original working
directory. The sessions table already had a cwd column; the classic CLI
just never wrote or read it.

- run_agent._ensure_db_session stamps cwd for local CLI sessions only
  (new _launch_cwd_for_session gates out gateway/cron and non-local
  terminal backends, where a host cwd is meaningless to restore).
- cli._restore_session_cwd chdir's the process AND retargets TERMINAL_CWD
  so the terminal tool, code-exec tool, and relative-path resolution all
  land in the restored dir. Called from both resume paths (interactive
  run() and the -q single-query path).
- Robust degradation: no-op when no cwd recorded, when already there, or
  when the dir is gone (single dim warning, stays put — no crash).
2026-06-03 17:37:27 -07:00
Brooklyn Nicholson
6efc7eda57 refactor(hermes-ink): delete now-dead SGR mouse fragment recovery
With the tokenizer reassembling split CSI sequences across a flush (prior
commit), no SGR mouse fragment can reach a text token anymore — terminals
write a mouse report as one atomic sequence, and any read/flush split now
re-joins in the tokenizer buffer instead of leaking. That makes the whole
downstream recovery layer dead code:

- SGR_MOUSE_FRAGMENT_RE, MOUSE_BURST_NOISE_RE, MOUSE_BURST_RESIDUE_RE
- parseTextWithSgrMouseFragments / parseSgrMouseFragment /
  normalizeSgrMouseFragment
- the whole-text mouse-burst noise fast path in parseMultipleKeypresses

Remove all of it (~185 lines) and the tests that only exercised it. The
narrow legacy X10 wheel-tail resynth stays (distinct mechanism, kept with
its own test). This retires the #17701#18113#26781#28463#35512
regex hardening chain in favor of the one correct parser fix.
2026-06-03 19:29:42 -05:00
Brooklyn Nicholson
de124800a2 test(hermes-ink): drop input-event SGR guard test
The guard it covered was removed in the previous commit (fragments no
longer reach input-event — they reassemble at the tokenizer). Reassembly
is now covered by termio/tokenize.test.ts and the flush-boundary cases in
parse-keypress.test.ts.
2026-06-03 19:24:51 -05:00
Brooklyn Nicholson
f354323547 fix(hermes-ink): reassemble split mouse sequences at the tokenizer; drop the regex sink
Root-cause fix for the SGR mouse fragment leak (`46M35;40M...` typed into
the prompt). The leak was never really about the fragments — it was the
flush emitting them. When App's 50ms watchdog fires mid-CSI during a render
stall, the tokenizer was force-emitting the buffered partial as a token and
resetting to ground, so both the prefix and the ESC-less remainder surfaced
as unparseable input.

Make the flush state-aware (xterm.js discipline): a bare ESC still flushes
to the Escape key (the legitimate ESCDELAY case), but a buffer still inside
a multi-byte control sequence (csi/osc/dcs/apc/ss3/intermediate) is NOT
emitted — it's kept so the continuation reassembles on the next feed. A
one-tick truncation valve in createTokenizer.flush() drops a partial that
survives a second flush with no progress, so a genuinely truncated write
can't fuse into the next keypress.

With partials never entering the input stream, the downstream scrubber is
dead code: remove the SGR fragment guard from input-event.ts (both the
original `/^\[<\d+;\d+;\d+[Mm]/` and the consolidated form added earlier in
this PR). The parse-keypress burst-recovery regexes (MOUSE_BURST_*) are now
also redundant but left in place as a safety net for one release; they can
be removed in a follow-up once this soaks.

Tests: tokenize.test.ts proves a mid-CSI flush keeps/reassembles and that a
stale partial is dropped after a second flush and a bare ESC still emits;
parse-keypress.test.ts adds the end-to-end split-then-reassemble case
yielding a single clean mouse event with no leaked key.

Supersedes #29337.
2026-06-03 19:24:28 -05:00
Ben Barclay
5446153c98 fix(docker): chown build trees on UID remap independently of $HERMES_HOME (#35027 regression) (#38556)
The stage2 hook gates the recursive chown of the build trees under
$INSTALL_DIR (.venv, ui-tui, node_modules) so a HERMES_UID/PUID remap
leaves them writable by the new runtime UID — needed for lazy_deps
'uv pip install' of platform extras (#15012, #21100) and the TUI esbuild
rebuild into ui-tui/dist (#28851).

#35027 folded that chown under the $HERMES_HOME ownership check
('stat $HERMES_HOME != hermes_uid'). But 'usermod -u <new> hermes'
re-chowns the hermes home dir ($HERMES_HOME == /opt/data) to the new UID
as a side effect, so after any remap that stat is already satisfied and
needs_chown is false — silently skipping the build-tree chown on the
common PUID/NAS path. The venv stays owned by the build-time UID (10000),
so lazy installs and TUI rebuilds fail with EACCES.

Probe the build trees directly instead: chown only when /opt/hermes/.venv
is not already owned by the runtime hermes UID. Independent of
$HERMES_HOME ownership, idempotent across restarts.

Verified live: built the image, booted with HERMES_UID/HERMES_GID on a
fresh named volume, confirmed .venv/ui-tui/node_modules end up owned by
the remapped UID and 'uv pip install' into the venv succeeds; confirmed
the recursive chown fires once and is skipped on restart.
2026-06-04 10:17:55 +10:00
Brooklyn Nicholson
01c010e233 fix(hermes-ink): collapse SGR mouse fragment guards into one flush-aware rule
When App's 50ms flush watchdog fires mid-CSI during a render stall, an
SGR mouse report (ESC[<btn;col;row M/m) is split across stdin chunks: the
tokenizer force-emits the buffered prefix and resets to ground, so both
the prefix and the ESC-less remainder reach InputEvent as nameless tokens.

The previous guard only matched a full `[<\d+;\d+;\d+[Mm]` fragment, so
the flushed prefixes (`ESC[<0;35;`) and the 1-/2-field and leading-`;`
tails (`46M`, `35;46M`, `;46M`) still leaked into the composer as
`46M35;40M...` during long sessions.

Replace the three would-be narrow regexes with one consolidated rule that
covers every split position. A `(?=...\d)` lookahead keeps typed `<`, `[`,
`;`, and `M` safe (no coordinate digit), and the embedded M/m terminator
in the param class leaves stuck-together fragments / prose intact. The
existing `!keypress.name` gate continues to protect real keystrokes, which
arrive one char per chunk with a name set.

Supersedes #29337 (covers the prefix-leak and leading-`;`/1-/2-field tail
cases that PR's two added guards missed).
2026-06-03 19:05:26 -05:00
Teknium
f99665f99a feat(prompt): broaden Hermes self-knowledge pointer to docs + skill (#38538)
The HERMES_AGENT_HELP_GUIDANCE block (added #16535) only fired when the
user explicitly asked about configuring/setting up Hermes. Broaden it so
the agent treats the docs as a standing source of self-knowledge for any
Hermes-related help and for understanding its own features/tools, points
to the hermes-agent skill for additional guidance, and treats the docs as
the authoritative/latest source of truth when the two differ.

Static constant in the cache-safe stable tier — no prompt-cache impact.
2026-06-03 17:01:56 -07:00
Ben
a6e47314f9 fix(dashboard): sanction plugin WS/upload auth via SDK helpers (gated mode)
Dashboard plugins (kanban, hermes-achievements) read
window.__HERMES_SESSION_TOKEN__ directly and hand-assembled WebSocket
URLs with ?token=. That works in loopback/--insecure mode but is
rejected on OAuth-gated deployments, where the session token is absent
and _ws_auth_ok only accepts single-use ?ticket= auth. The result was
401s on plugin REST calls and 1008/403 on the kanban live-events WS
whenever the dashboard ran behind OAuth (e.g. hosted Fly agents).

Make the plugin SDK the single sanctioned auth surface:

- web/src/lib/api.ts: add authedFetch() (raw Response for FormData
  uploads / blob downloads, token-or-cookie auth, no throw / no 401
  redirect) and buildWsUrl() (assembles a ws(s):// URL with the correct
  auth param for the active mode — fresh single-use ticket in gated
  mode, token in loopback).
- web/src/plugins/registry.ts: expose authedFetch, buildWsUrl,
  buildWsAuthParam, and sdkVersion on window.__HERMES_PLUGIN_SDK__;
  add SDK_CONTRACT_VERSION.
- web/src/plugins/sdk.d.ts: hand-authored typed contract for the
  plugin SDK + registry globals (single source of truth for the
  Window declarations).
- plugins/kanban + hermes-achievements dist bundles: stop reading the
  session token directly; route uploads/downloads through
  SDK.authedFetch and the live-events WS through SDK.buildWsUrl.
- plugins/kanban plugin_api.py: _ws_upgrade_authorized() delegates the
  /events WS upgrade to the canonical web_server._ws_auth_ok gate, so
  it transparently accepts loopback token / gated ticket / internal
  credential and can never drift from core auth again.
- tests: guard test asserting no plugin dist reads
  __HERMES_SESSION_TOKEN__ directly; kanban gated-ticket WS test.

Verified live on a gated staging Fly agent: kanban /events upgrades
101 with a minted ticket (ticket_len=43, ws_auth_ok=True) where the
old code got 403.
2026-06-03 16:59:36 -07:00
brooklyn!
1c88360fed Merge pull request #38546 from NousResearch/bb/disable-provider-key-validation
fix(desktop): disable provider key validation in launch setup
2026-06-03 18:49:22 -05:00
Teknium
475ecea3d7 fix(install): cap requires-python at <3.14 and pin UV_PYTHON to the venv (#38535)
uv selects the project Python from requires-python and from the UV_PYTHON
env var, both of which override an already-created venv on the next
'uv sync'. With no upper bound on requires-python, an inherited
UV_PYTHON=3.14 (or a fresh distro whose newest interpreter uv auto-picks)
silently recreated the installer's 3.11 venv at 3.14, where Rust-backed
transitives (pydantic-core) have no cp314 wheel and fall back to a maturin
source build that fails. This bit a Windows/WSL user with UV_PYTHON set in
their shell and a fresh WSL-arch box where uv auto-picked 3.14.

Two layers:
- pyproject: requires-python '>=3.11' -> '>=3.11,<3.14' (+ uv lock regen).
  uv now refuses a 3.14 interpreter with a clear error instead of attempting
  the maturin build. Backstop independent of the installer.
- install.sh / install.ps1: pin UV_PYTHON to the venv interpreter after
  creating it (in both the venv step and the deps step, since bootstrap runs
  those stages as separate processes). An inherited UV_PYTHON can no longer
  hijack the sync/pip tiers, so the install just works regardless of shell env.

Verified E2E: hostile UV_PYTHON=3.14 + uv venv --python 3.11 + uv sync now
installs into 3.11 with pydantic-core's 3.11 wheel; without the re-pin the
capped requires-python produces a legible incompatibility error rather than a
cryptic build failure.
2026-06-03 16:45:47 -07:00
Nate George
e8c3ac2f5c fix: strip extra_content from tool_calls for strict APIs (Fireworks, Mistral)
Fireworks/Mistral reject HTTP 400 'Extra inputs are not permitted, field:
messages[N].tool_calls[M].extra_content' on any session whose history
contains prior Gemini tool calls. Gemini 3 thinking models attach
extra_content (thought_signature) to tool_calls; it survived to the wire
because the sanitize paths only stripped call_id/response_item_id.

Strip extra_content from the outgoing wire copy in both sanitize paths
(ChatCompletionsTransport.convert_messages + _sanitize_tool_calls_for_strict_api),
but gate it on the target model: keep extra_content for Gemini-family
targets (the thought_signature MUST be replayed or Gemini 400s), strip it
for everyone else — including non-Gemini models that inherit a stale Gemini
signature earlier in a mixed-provider session. Native Gemini is unaffected
(GeminiNativeClient bypasses these paths).

Original stored history is never mutated (only the per-call copy).

Fixes #17986.
2026-06-03 16:42:52 -07:00
Teknium
ec69c767ff docs(desktop): point Chat section to remote-backend + dashboard doc (#38545)
The Desktop Chat section described chat-only and gave no signpost that
remote-hosted Hermes connection is documented. Adds a pointer to the
in-page remote-backend section and to the deeper Web Dashboard doc.
2026-06-03 16:40:47 -07:00
Teknium
2f523a4691 fix(tui): cgroup-aware V8 heap cap so memory-limited containers stop dying silently (#38541)
The TUI hardcoded --max-old-space-size=8192. V8 is not cgroup-aware, so in a
Docker/k8s container capped below ~9-10GB the heap grows past the container
limit and the cgroup OOM-killer SIGKILLs the Node parent BEFORE V8's own heap
monitor fires. SIGKILL runs no JS handler, writes no [tui-parent] breadcrumb,
and closes the gateway child's stdin — the user sees only a bare gateway
'stdin EOF'. Complements #38224 (trail-text cap), which reduced pressure but
left the 8GB-vs-container mismatch in place.

- _read_cgroup_memory_limit(): read cgroup v2 (memory.max) then v1
  (memory.limit_in_bytes); handle 'max', the v1 unlimited sentinel, blank/zero,
  and >=1PB as unconstrained.
- _resolve_tui_heap_mb(): unconstrained -> 8192; constrained -> 75% of the
  cgroup limit (headroom for non-heap RSS + the Python child sharing the
  cgroup), floored at 1536MB, never above 8192.
- NODE_OPTIONS block uses the sized value; still respects a user-supplied
  --max-old-space-size.

Net: V8 now GCs/exits gracefully (onCritical breadcrumb fires) instead of being
reaped silently. Display/transport only — no agent context or behavior change.

Tests: tests/hermes_cli/test_tui_heap_sizing.py (20 tests).
2026-06-03 16:40:28 -07:00
Teknium
8a19884bf3 fix(update): stop stash/restore from clobbering desktop source on managed clones (#38542)
The stash/restore cycle in the update path was observed to clobber
freshly-pulled source files (apps/desktop/ deletion -> Vite
'[UNRESOLVED_ENTRY] Cannot resolve entry module index.html'). On a
managed clone the user never edits the source tree, so any 'dirty' state
is pure git artifact (CRLF renormalization, npm lockfile churn, files
left behind when a directory was deleted upstream such as
apps/bootstrap-installer/). Stashing that and re-applying it after a pull
is fragile and unnecessary.

- hermes update (hermes_cli/main.py): on a non-fork (managed) clone,
  discard working-tree dirt via reset --hard HEAD + clean -fd instead of
  stash/apply. Forks keep the stash machinery so intentional edits
  survive. Also pin core.autocrlf=false on Windows so the dirt is never
  created (mirrors install.ps1 #38239).
- install.sh: replace the update-path stash/restore dance with a hard
  reset to origin/<branch>; the installer is a managed-only entry point.
- install.sh + install.ps1 desktop stage: prefer 'npm ci' (wipes and
  reinstalls node_modules from the lockfile) over bare 'npm install',
  which can report 'up to date' against a stale marker while node_modules
  is empty -- leaving tsc unresolved so 'npm run pack' fails.

Tests: managed clone cleans instead of stashing; fork still stashes;
existing stash tests force the stash path explicitly.
2026-06-03 16:40:13 -07:00
Brooklyn Nicholson
7ea37cd082 fix(desktop): stop validating provider keys in launch setup
The launch provider setup screen rejected too many legitimate users:
a live credential probe ("key rejected"), a post-save runtime check
("still cannot reach X"), and an 8-char minimum all gated progression.
Corporate proxies, regional blocks, rate-limited/flaky probes, and
self-hosted endpoints all tripped these. Now we just require a
non-empty value and save it; a genuinely bad key surfaces later at
chat time instead of blocking onboarding.
2026-06-03 18:39:00 -05:00
brooklyn!
1927ff217e Merge pull request #38517 from NousResearch/bb/desktop-yolo-statusbar-toggle
feat(desktop): YOLO toggle in the status bar (per-session, TUI parity)
2026-06-03 23:33:09 +00:00
Teknium
63727f32bf docs(dashboard): document connecting Hermes Desktop to a remote backend (#38534)
Desktop's readiness probe only checks GET /api/status (public), but the
live chat rides /api/ws, which is gated by --tui (4403), a matching
session token (4401), and a non-loopback bind. The web-dashboard doc
covered --tui and the OAuth gate but never the Desktop remote-connection
flow, so the three independent failure modes weren't documented together.

Adds a 'Connecting Hermes Desktop to a remote backend' section: pin
HERMES_DASHBOARD_SESSION_TOKEN, run with --host 0.0.0.0 --insecure --tui,
the curl token-verification one-liner, and WS close-code triage.
2026-06-03 16:28:01 -07:00
Teknium
5c0a1fec0c fix(desktop): surface skill & quick-command slash commands in the palette (#38531)
The desktop chat app's slash curation (desktop-slash-commands.ts) only
suggested the ~19 curated built-ins. isDesktopSlashSuggestion required
membership in DESKTOP_COMMANDS, so every skill-derived command and user
quick_command was silently dropped from both completion paths
(commands.catalog empty-query + complete.slash typed-query) and from
filterDesktopCommandsCatalog — even though isDesktopSlashCommand let them
EXECUTE when typed in full. The tui_gateway backend already includes skills
in both RPCs; the gap was purely renderer-side.

Add isDesktopSlashExtensionCommand() (= not-a-known-Hermes-built-in, the
same predicate that already gates execution) and let extensions through the
suggestion path. The catalog filter routes through isDesktopSlashSuggestion,
so skill/quick-command categories and pairs are kept automatically.
2026-06-03 16:24:06 -07:00
Ben Barclay
96f0ddc6a9 fix(docker): bake hindsight-client into the image (#38128) (#38530)
The native Hindsight memory provider lazy-installs hindsight-client into
/opt/hermes/.venv at first use (tools/lazy_deps.py: memory.hindsight).
That venv lives inside the immutable image layer, not the mounted
/opt/data volume, so the dependency is wiped on every container recreate
/ image update. After an update, profile config still points at Hindsight
and the Hindsight server is healthy, but recall/retain fails with:

    ModuleNotFoundError: No module named 'hindsight_client'

The manual workaround (uv pip install hindsight-client inside the running
container) doesn't survive the next recreate, and pip-install-into-.venv
is not an officially supported durable Docker workflow.

Fix: add --extra hindsight to the image's uv sync line, same pattern as
the --extra anthropic/bedrock/azure-identity providers (#30504) and
--extra messaging (#24698) — bake the optional dependency into the build
layer so it survives container recreate. The pyproject [hindsight] pin
(hindsight-client==0.6.1) already matches tools/lazy_deps.py and uv.lock,
so this is a pure additive --extra with no lockfile churn.

Verified: 'uv sync --frozen --no-install-project --extra hindsight'
against the committed uv.lock installs hindsight-client 0.6.1 and the
module imports cleanly.

Adds a regression test (mirrors test_dockerfile_preinstalls_gateway_
messaging_dependencies) so a future Dockerfile cleanup can't silently
drop the extra.
2026-06-04 09:17:35 +10:00
helix4u
51a2c07016 fix(skills): document xurl X Article ingestion 2026-06-03 15:11:57 -07:00
Teknium
e223503b03 fix(packaging): modernize project.license to PEP 639 SPDX string (#38353)
* fix(packaging): modernize project.license to PEP 639 SPDX string

Drops the SetuptoolsDeprecationWarning ('project.license as a TOML table
is deprecated') emitted on every editable build under setuptools>=77 by
switching license = { text = "MIT" } to the SPDX string form plus an
explicit license-files entry. Bumps build-system requires to
setuptools>=77 so an older build backend can't reject the string form.

The warning was non-fatal (builds succeed with it) but surfaces
prominently in install.ps1 build-failure output, where it gets mistaken
for the cause of unrelated Windows build_editable crashes.

* fix(packaging): bound setuptools build requirement per supply-chain policy

Add the <83 upper bound to setuptools>=77.0 so the dep-bounds supply-chain
gate (>=floor,<next_major) passes.
2026-06-03 14:43:49 -07:00
kshitij
6fff744158 Merge pull request #38465 from kshitijk4poor/portal-quick-setup-model
feat(cli): make `hermes portal` run the full quick-setup Nous flow (model picker)
2026-06-03 14:09:47 -07:00
kshitijk4poor
26a57467a8 fix(cli): harden hermes portal SystemExit handling + finish model-pick doc sweep
Self-review of #38465 surfaced three real items:

1. SystemExit escape (defense): `_login_nous` raises SystemExit(130)/(1) on
   cancel/failure. The logged-out login path inside `_model_flow_nous` catches
   it, but the expired-session re-login path (main.py) only catches Exception,
   so a Ctrl-C during re-auth could propagate past `_run_portal_one_shot` and
   kill the CLI. Add SystemExit to the portal handler so all cancel/abort cases
   end with the graceful 'Setup cancelled / retry later' message.

2. Doc sweep: the model-pick step was only added to the bare-`hermes portal`
   prose. Propagate it to the surfaces describing `hermes setup --portal`
   behavior that still omitted model selection:
   - `--portal` argparse help (main.py)
   - nous-portal.md intro + the numbered 'what it does' step list (EN + zh-Hans)
   - run-hermes-with-nous-portal.md 'default model after setup --portal' line,
     which was now contradictory (there's a picker, not a forced default) (EN + zh)

3. Test coverage: add parametrized regression test asserting the portal handler
   swallows KeyboardInterrupt / EOFError / SystemExit (returns None, no escape).

Note on 'Skip (keep current)': delegating to _model_flow_nous means picking
Skip preserves the prior provider instead of force-switching to nous — this is
intentional and matches quick setup exactly; docs now say 'sets Nous as your
provider (when you pick a model)' rather than unconditionally.
2026-06-04 02:33:33 +05:30
kshitijk4poor
cd188b814e feat(cli): make hermes portal run the full quick-setup Nous flow (model picker)
`hermes portal` / `hermes setup --portal` previously logged in and set
provider=nous but left the model UNSELECTED (blank -> runtime default) and
never showed a picker — unlike the first-time quick setup, which runs the
model picker.

Route `_run_portal_one_shot` through `_model_flow_nous` — the exact same
routine quick setup (`_run_first_time_quick_setup`) and `hermes model` -> Nous
use. It handles both the logged-out path (device-code OAuth, which picks a
model internally) and the logged-in path (curated Nous model picker), then
offers the Tool Gateway opt-in and sets provider=nous. Net effect: `hermes
portal` now offers a model picker every time and is a true single-command
collapse of quick setup's Nous step.

Removes the hand-rolled auth_add_command + manual provider write + separate
Tool Gateway prompt (now a single source of truth). Re-syncs the in-memory
config from disk afterward so a caller's later save_config can't clobber the
model/provider written by the login flow.

Docs (CLI help, portal_cli docstrings, nous-portal EN + zh-Hans) updated to
mention model selection. New regression test asserts `_run_portal_one_shot`
delegates to `_model_flow_nous`.

Verified live: `hermes portal` now shows the 27-model curated picker, 'Skip
(keep current)' preserves prior provider/model.
2026-06-04 02:20:31 +05:30
kshitij
d4787d3e2e Merge pull request #38449 from kshitijk4poor/portal-login-alias
feat(cli): make `hermes portal` the human-readable Portal onboarding alias
2026-06-03 13:16:58 -07:00
stremtec
0caa23788f fix(desktop): prevent IME Enter from splitting messages and viewport resize from disarming scroll anchor (#38333)
* fix(desktop): prevent IME Enter from splitting messages and viewport resize from disarming scroll anchor

Two fixes for the Hermes Desktop composer:

1. IME composition Enter was treated as message submission. When a Korean/
   Japanese/Chinese IME is composing text and the user presses Enter to
   finalise the preedit, handleEditorKeyDown fired submitDraft() because it
   did not check event.nativeEvent.isComposing. The assistant-ui hidden
   textarea already guards this correctly; the custom contentEditable
   handler was missing it. Added an early return when isComposing is true.

2. Viewport resize (composer expand/collapse, window resize) was disarming
   the scroll sticky-bottom anchor. When the composer grows, the thread
   viewport shrinks, the browser adjusts scrollTop down to keep content
   visible, and the onScroll handler misread this as a user scroll-up.
   Added lastClientHeightRef tracking so the disarm condition now requires
   BOTH stable scrollHeight AND stable clientHeight before treating a
   scrollTop decrease as user intent.

Fixes: random mid-message sends during IME typing; scroll jumps when the
composer resizes or the window changes size.

* fix(desktop): prevent virtualizer measurement adjustments from fighting scroll anchoring

The virtualizer's measureElement callbacks trigger scroll adjustments when
item sizes differ from estimates. These fight our ResizeObserver +
pinToBottom loop, creating visible rubber-banding (view snaps to composer
then jumps back up), even during idle.

Three changes:
1. React.memo on VirtualizedThread to stop parent re-renders cascading
2. Shared stickyBottomRef so scrollToFn can check bottom state
3. scrollToFn override: skip adjustments when user is at bottom

* fix(desktop): use stable useCallback ref instead of inline arrow for onBranchInNewChat

The inline arrow `messageId => void branchInNewChat(messageId)` created a
new function reference on every render. This cascaded through:
  desktop-controller → ChatView → Thread → useMemo([...onBranchInNewChat])
→ new messageComponents object → VirtualizedThread receives new prop
→ React.memo overridden → virtualizer recalculates → measurement
adjustments trigger scroll jumps at the 15-second useStatusSnapshot
interval.

Pass the already-useCallback'd branchInNewChat directly.

* fix(desktop): use ctrlEnter submitMode on hidden textarea + gate ResizeObserver on isRunning

Two root-cause fixes:

1. IME message splitting: The hidden ComposerPrimitive.Input textarea had
   submitMode='enter' (default), so any Enter keydown it received — even
   during IME composition — triggered form.requestSubmit(). Changed to
   submitMode='ctrlEnter' so only the contentEditable div (which correctly
   checks isComposing) handles plain-Enter submission.

2. Scroll jumps during idle: The ResizeObserver auto-follow loop was
   active even when the thread wasn't running, causing spurious
   pinToBottom calls whenever any layout shift occurred (browser reflow,
   font load, GPU cache eviction). Gated the ResizeObserver on
   thread.isRunning so auto-scroll only follows during active streaming.
   User messages still pin via useLayoutEffect, and thread.runStart still
   calls jumpToBottom.

* fix(desktop): keep chat bottom anchor stable through idle layout shifts

* fix(desktop): prevent code block shrink scroll bounce

* fix(desktop): release bottom height lock on run completion

* fix(desktop): keep streaming code blocks rendered

* fix(desktop): keep bottom anchored through final render

* fix(desktop): render streaming reasoning code blocks

* feat(desktop): add subtle streaming block animations
2026-06-03 20:14:52 +00:00
kshitijk4poor
9ba7e5b1b4 fix(setup): point Portal login-failure retry hints at hermes portal
The two retry hints inside _run_portal_one_shot (shown when the OAuth login
fails) still suggested `hermes auth add nous --type oauth`. Since this path
backs both `hermes portal` and `hermes setup --portal`, point users at the
new human-readable `hermes portal` for consistency.
2026-06-04 01:40:11 +05:30
kshitijk4poor
da4f407e51 feat(cli): make hermes portal the human-readable Portal onboarding alias
`hermes portal` (no subcommand) now runs the one-shot Nous Portal onboarding
— OAuth login, switch provider to Nous, offer Tool Gateway — identical to
`hermes setup --portal` and the human-readable alias for
`hermes auth add nous --type oauth` (which still works).

The prior status default moves to `hermes portal info`; `status` is kept as a
hidden back-compat alias. `open`/`tools` subcommands are unchanged.

User-facing hints and docs (status.py, conversation_loop 401 guidance,
SystemPage, README, website docs + zh-Hans) now point at `hermes portal` /
`hermes portal info`. `--manual-paste` references keep the explicit auth
command since `hermes portal` does not expose that flag.
2026-06-04 01:19:28 +05:30
kshitijk4poor
39fee4f3bc test(installer): cover the post-update relaunch/install target derivation
The macOS self-update relaunches and installs over the app it derives via
resolve_hermes_desktop_app (.../Hermes.app/Contents/MacOS/Hermes ->
.../Hermes.app). That derivation is load-bearing for both the ditto
install target and the auto-relaunch (open <app>), but had no test.

Add unit coverage:
- resolve_hermes_desktop_app_finds_built_bundle: a fake built release tree
  resolves to the .app bundle on macOS (and the exe elsewhere).
- resolve_hermes_desktop_app_is_none_without_a_build: no build => None.

Verified the positive test FAILS if the .app parent-walk is wrong (e.g.
one too few .parent() hops), so it's a real guard against a regression
that would break the post-update relaunch target.

cargo test -> 17 passed.
2026-06-03 12:02:07 -07:00
kshitijk4poor
d3b1e43005 fix(installer): never brick the install when a self-update swap fails
The macOS self-update bundle swap (install_macos_app_update, added in
#38296) could leave the user with NO app installed. If moving the
existing /Applications/Hermes.app aside failed, the code deleted the
running app outright and set moved_old=false; if the subsequent move of
the freshly built bundle into place then also failed, the rollback was
gated on moved_old (now false) and skipped — leaving the target deleted
with no replacement.

Extract the swap into swap_in_new_bundle() with a strict invariant: on
ANY failure path the target is left pointing at a working bundle (either
the original, rolled back, or untouched) and is never deleted with no
replacement. Also clean up the staged .hermes-update-new copy on the
failure paths instead of orphaning it.

Add unit tests covering the happy path, the rollback-on-install-failure
path, and the catastrophic both-moves-fail path. The catastrophic-path
test was verified to FAIL against the old code ("original app must NOT
be deleted on failure") and pass against the fix.
2026-06-03 12:01:31 -07:00
Siddharth Balyan
c349eca823 fix(packaging): ship locales/ i18n catalogs in wheel, sdist, and Nix (#38383)
* fix(packaging): ship locales/ i18n catalogs in wheel, sdist, and Nix

locales/ is a bare data dir (no __init__.py), invisible to packages.find
and package-data. Sealed installs (pip wheel, Nix store venv) dropped it,
so gateway/CLI commands rendered raw i18n keys like
gateway.reset.header_default.

- pyproject: [tool.setuptools.data-files] locales = ["locales/*.yaml"] (wheel)
- MANIFEST.in: graft locales (sdist)
- agent/i18n._locales_dir: env override -> source -> sysconfig data scheme
- nix/hermes-agent.nix: copy locales into the store + set HERMES_BUNDLED_LOCALES
  as defense-in-depth. The wheel's data-files already materialize into the
  uv2nix venv, so resolution works with no env var; the override pins the
  store path against a future uv2nix change that could drop data-files.
- tests: metadata regression, wheel + sdist build-install smoke tests, and a
  bundled-locales flake check that verifies BOTH the wrapper override and the
  env-var-less data-files path. Smoke test wired into CI.

Closes #23943, #27632, #35374.
Supersedes #23966, #27716, #30261, #33841, #35429, #35494, #35735, #36697.

* test: cap locale e2e timeout, tighten catalog count guard

The two wheel/sdist e2e tests inherit the global --timeout=30 from
addopts; a cold-CI run (isolated build env + venv create + network pip
install) can plausibly exceed it. Add @pytest.mark.timeout(300) so they
don't ride the unit-test budget and flake intermittently.

Also assert the shipped catalog count equals len(SUPPORTED_LANGUAGES)
instead of a hardcoded >=16 floor, so the guard self-updates and trips
on a single dropped catalog (not just a fully-empty graft).
2026-06-03 12:00:27 -07:00
brooklyn!
b91c382035 Merge pull request #38393 from NousResearch/bb/desktop-session-fixes
fix(desktop): persist pins, reconnect after sleep, dedupe session search
2026-06-03 13:22:34 -05:00
Brooklyn Nicholson
1b89715e15 fix(desktop): guard reconnect sockets and keep branch search precise
Avoid stale WebSocket events from an old reconnect attempt flipping the gateway state after a newer socket opens. Also limit session-search dedupe to compression edges so branch-specific hits still open the branch instead of collapsing to the parent.
2026-06-03 13:13:21 -05:00
Brooklyn Nicholson
93228d5299 fix(desktop): persist pins, reconnect after sleep, dedupe session search
Four related desktop session-management bugs:

- Pins lost until refresh: pinned sessions are joined against the
  paginated in-memory session list, so a pinned chat that aged off the
  most-recent page got evicted on the next refresh (every message.complete
  triggers one) and the Pinned section went empty. mergeWorkingSessions ->
  mergeSessionPage now also preserves pinned rows (matched by live id or
  lineage root). Pin id checks in the chat header, command center, and
  delete/archive are normalized to the durable sessionPinId so pins survive
  auto-compression.

- Stuck on "Starting Hermes" after sleep: macOS sleep drops the renderer
  WebSocket; nothing reconnected on wake so the composer stayed disabled.
  The gateway boot hook now auto-reconnects with backoff on close/error and
  on wake signals (powerMonitor resume/unlock-screen IPC, window online,
  visibilitychange). connect() gains an open timeout so a hung reconnect
  can't deadlock in 'connecting'. Composer placeholder distinguishes
  "Reconnecting to Hermes" from a cold start.

- Loses chats from itself: the same hard-replace that dropped pins also
  dropped loaded sessions; mergeSessionPage keeps them.

- Multiple copies/branches in search: /api/sessions/search deduped only by
  raw session_id, so compression segments and branches surfaced as separate
  hits. It now dedupes by lineage root and returns the live compression tip,
  matching the session_search tool's behavior.
2026-06-03 12:39:31 -05:00
brooklyn!
b4b9a93848 Merge pull request #38384 from NousResearch/bb/fix-installer-emit-log-logstream
fix(installer): restore main build — pass LogStream to emit_log calls from #38296
2026-06-03 12:29:11 -05:00
Brooklyn Nicholson
1971b10526 fix(installer): pass LogStream to emit_log calls from #38296
PR #38296 added four emit_log() calls using the old 3-arg signature, but
main had already changed emit_log to take a `stream: LogStream` argument
(#38312, "stop mislabeling stdout-style progress as stderr"). The two PRs
touched different lines, so the merge auto-resolved with no conflict and
left main unable to compile the bootstrap installer (E0061: 4 args expected,
3 supplied).

Supply the missing stream: Stdout for the update/install progress lines and
Stderr for the "could not auto-launch desktop" failure, matching the
convention from #38312. cargo check passes.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-03 12:28:28 -05:00
brooklyn!
84710995ef Merge pull request #38312 from NousResearch/bb/installer-stderr-log-label
fix(installer): stop mislabeling stdout-style progress as stderr
2026-06-03 12:17:35 -05:00
brooklyn!
9632609447 Merge pull request #38296 from NousResearch/bb/fix-dmg-update-relaunch
fix(desktop): self-update rebuilds and relaunches cleanly on macOS
2026-06-03 12:06:30 -05:00
brooklyn!
2d9ea0997f Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-03 12:01:13 -05:00
brooklyn!
ee8aeea4ca Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-03 12:01:05 -05:00
Teknium
3c73d1852e docs: remote desktop connect needs --tui on the backend (#38350)
The Desktop App and Web Dashboard remote-connect instructions told users
to start the backend with `hermes dashboard --no-open --insecure --host
0.0.0.0`, omitting --tui. Without --tui the embedded-chat WebSockets
(/api/ws, /api/pty) are refused, so the desktop passes the /api/status
health check and reports the backend "ready" — but chat never works
because the socket is closed on connect.

- Add --tui to both backend command blocks (with an inline why-comment).
- Explain that the desktop chat runs over /api/ws + /api/pty and needs
  the embedded-chat surface enabled; a plain dashboard/gateway is not
  enough.
- Add a troubleshooting entry for the exact symptom (connects, says
  ready, chat dead) on both pages.
2026-06-03 09:30:20 -07:00
xxxigm
df848bd2da test(gateway): cover schtasks locale-safe decoding on Windows
Assert _exec_schtasks passes an explicit encoding and errors="replace" to
subprocess.run, and that _schtasks_encoding falls back to utf-8 when the
locale lookup is empty or raises (#38172).
2026-06-03 09:29:19 -07:00
xxxigm
973decc050 fix(gateway): decode schtasks output with locale encoding on Windows
_exec_schtasks ran schtasks.exe with text=True but no encoding/errors, so
localized Windows (e.g. Chinese) output in the console code page raised
UnicodeDecodeError tracebacks from subprocess' reader threads during
`hermes gateway status`. Decode with the locale's preferred encoding and
errors="replace" so non-UTF-8 status output is read cleanly.

Fixes #38172
2026-06-03 09:29:19 -07:00
Teknium
9666305630 fix(dashboard): clamp PTY resize dimensions for WSL2 winsize garbage (#38200)
* fix(dashboard): clamp PTY resize dimensions for WSL2 winsize garbage

WSL2 reports columns=131072, rows=1 from a broken winsize probe. The
dashboard /chat tab forwards xterm.js dimensions through PtyBridge.resize(),
which packs them as unsigned short via struct.pack. 131072 > 65535 raised
struct.error — uncaught (only OSError was handled) — breaking the resize
path and leaving the TUI laid out for a one-row, absurdly-wide screen, which
surfaces as blank/disappearing text.

Clamp cols/rows to a sane [1, 2000]x[1, 1000] range before packing.
Non-finite/non-integer probes fall back to the minimum so nothing can reach
struct.pack and raise.

* test(dashboard): de-flake pub/events broadcast test

test_pub_broadcasts_to_events_subscribers round-tripped a frame through
two nested Starlette TestClient WebSocket portals within a 10s wall-clock
budget. Under heavy parallel CI load a starved ASGI thread occasionally
blew that budget even though the server logic is correct, producing
intermittent 'broadcast not received within 10s' failures.

Drive _broadcast_event directly under asyncio with fake subscribers
instead. Same fan-out contract (verbatim delivery to every subscriber on
the channel, nothing to other channels), zero scheduling surface. Runs in
~0.3s, deterministic across 10 consecutive runs.
2026-06-03 09:00:16 -07:00
Brooklyn Nicholson
810e5864db fix(installer): stop mislabeling stdout-style progress as stderr
Both installers (Electron bootstrap-runner + Tauri) hardcoded a literal
`stderr: ` prefix onto every line that arrived on fd 2. Tools like
uv/pip/git/npm write normal progress to stderr by design, so routine
install output showed up tagged as "stderr" (and rendered red in the
Tauri progress UI), making a healthy install look like it was erroring.

Carry the stream as structured metadata (`stream: 'stdout' | 'stderr'`)
on the log event instead of mangling the line text. The UI now styles
stderr subtly (dimmed) rather than alarmingly, and the persistent
forensic logs keep their stdout/stderr distinction.
2026-06-03 10:38:34 -05:00
brooklyn!
ecac659d7d Merge pull request #38306 from NousResearch/bb/desktop-clipboard-image-double-paste
fix(desktop): dedupe clipboard image paste
2026-06-03 10:28:21 -05:00
Brooklyn Nicholson
c711146ad4 fix(desktop): dedupe clipboard image paste
Chromium exposes the same pasted image on both DataTransfer.items and
.files as distinct Blob objects, which attached twice. Prefer items and
skip the files mirror when items already yielded images.
2026-06-03 10:27:47 -05:00
Brooklyn Nicholson
a1cda2410b fix(desktop): self-update rebuilds and relaunches cleanly on macOS
The macOS DMG / in-app update could leave Hermes unable to relaunch: the
staged updater rebuilt the desktop without managed Node on PATH ("npm not
found"), never installed the rebuilt bundle over the running app, and could
race itself on `git stash`. Child install scripts also inherited a deleted
cwd from the .app bundle replaced during self-update.

- update.rs: prepend $HERMES_HOME/node/bin + venv bin to the rebuild PATH;
  read --branch / --target-app from args; add a macOS "install" stage that
  dittos the rebuilt bundle over the target app, clears quarantine, and
  relaunches via `open` (rolling back on a failed swap); guard start_update
  with an AtomicBool so concurrent startUpdate() calls can't race git stash.
- main.cjs: pass --branch <configured> and --target-app <running bundle> to
  the staged updater, and spawn it with HERMES_HOME + managed Node/venv on
  PATH and cwd=HERMES_HOME.
- bootstrap.rs: launch the desktop via `open <App>.app` on macOS instead of
  exec'ing Contents/MacOS/Hermes, avoiding cwd/quarantine issues post-rebuild.
- powershell.rs: pin child install scripts to a stable cwd so they don't emit
  getcwd errors when the launching .app is replaced mid-install.
- failure.tsx: in update mode show "Update didn't finish" / "Retry update"
  and retry via startUpdate() instead of re-running the installer bootstrap.
2026-06-03 10:19:44 -05:00
Austin Pickett
e02a6038a4 fix(tui): save TUI /save snapshots under Hermes home with system prompt (#38251)
* fix(tui): save TUI /save snapshots under Hermes home with system prompt

The TUI gateway's session.save RPC wrote hermes_conversation_<ts>.json to
the workspace/project CWD via os.path.abspath(...) and only exported model
and messages. This diverged from the classic CLI /save (which writes under
the Hermes profile home) and from the dashboard save (which includes the
system prompt).

Write the snapshot under get_hermes_home()/sessions/saved/ and include
system_prompt, session_id, and session_start so the TUI export matches the
CLI and dashboard behavior.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(tui): prefer agent.session_start for /save export; assert it in test

Address review feedback: derive session_start from the agent's session_start
datetime (matching the classic CLI export) and fall back to the gateway
session's created_at only when unavailable. Assert session_start in the
regression test.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-03 10:56:06 -04:00
brooklyn!
12ea7fc7e3 Merge pull request #38255 from NousResearch/bb/installer-desktop-build-logging
fix(install): require Node >=20.19/22.12 for the desktop build
2026-06-03 09:38:07 -05:00
Austin Pickett
7fb8a6b5c5 feat(dashboard): enrich profiles dashboard and de-dupe channel env vars (#37872)
* feat(desktop): enrich profiles dashboard and de-dupe channel env vars

Add active-profile switching, role descriptions (manual + auto-generate
via the auxiliary LLM), per-profile model selection, and gateway-running
/ distribution badges to the GUI Profiles page. New profile creation
gains clone-all, optional description and model assignment.

Hide messaging-platform credentials (channel_managed) from the Keys/Env
page since the Channels page is the canonical surface for them, and
relabel the trimmed "messaging" category as "Gateway".

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): address review feedback on profiles/env changes

- ProfilesPage: scope the action-menu outside-click handler to the menu's
  own container via a ref so opening one card's menu no longer leaves
  others open.
- EnvPage: route the "Gateway" label and hint through i18n
  (t.common.gateway / gatewayHint) instead of hard-coded English, with an
  English fallback for untranslated locales.
- web_server: only report description_auto=true when auto-generation
  actually succeeded.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): address second-round review on profiles

- ProfilesPage: treat describe-auto success by null-checking the
  description and trust the response's description_auto flag instead of
  assuming true; disable the model-editor Save button unless the selected
  choice resolves to a real /api/model/options entry (avoids silent
  no-op saves).
- tests: cover the new profile endpoints (active get/set + 404,
  description round-trip + 404, model round-trip + 400 validation, and
  describe-auto success/failure contracts).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): more profiles review fixes (toggles, races, tests)

- ProfilesPage: use the canonical `active` returned by setActiveProfile;
  make the SOUL/description/model action-menu items toggle their editor
  closed when already open; guard description save/auto-describe against
  stale responses via an activeDescRequest ref so a late reply can't
  clobber a different open editor.
- tests: assert /api/env channel_managed classification matches
  _channel_managed_env_keys().

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-03 10:37:36 -04:00
Brooklyn Nicholson
1dca7c6207 fix(install): require Node >=20.19/22.12 for the desktop build
The "Build desktop app" install step failed with an opaque "exit code 1"
on machines with an old Node, and nothing in the logs explained it.

Reproduced: on Node 20.5.1, `npm run pack`'s `vite build` crashes with

  You are using Node.js 20.5.1. Vite requires Node.js version 20.19+ or 22.12+.
  SyntaxError: The requested module 'node:util' does not provide an
  export named 'styleText'

Vite 8 (rolldown) imports node:util.styleText, which doesn't exist before
Node 20.12, so the build dies before producing the app. The installer's
check_node / Test-Node accepted ANY pre-existing Node with no version
floor, so a too-old system Node was used for the build instead of the
bundled Node 22.

Add a version floor (^20.19 || >=22.12) to check_node (install.sh) and
Test-Node (install.ps1): a too-old system Node is replaced with the
Hermes-managed Node 22 LTS, and the desktop stage re-resolves Node so the
build always runs on a satisfying version. Declare the same range in
apps/desktop/package.json engines.

Verified: build succeeds on Node 22, fails on 20.5.1 with the error above;
the floor logic matches Vite's range across boundary versions (20.18/20.19,
21.x, 22.11/22.12).
2026-06-03 09:19:04 -05:00
Teknium
214b7e070f fix(install.ps1): handle dirty worktree on Windows update (#38239)
Git for Windows defaults to core.autocrlf=true, which renormalizes the
repo's LF-only text files to CRLF in the working tree. On a managed,
never-user-edited clone this makes tracked files (.envrc, AGENTS.md,
agent/*.py, workflows) show as locally modified, so the update path's
bare git checkout aborts with 'Your local changes would be overwritten
by checkout' and the desktop bootstrap fails at stage=repository.

The bash installer already autostashes before checkout; the PowerShell
path had no dirty-tree handling at all and never pinned autocrlf.

Fix: (1) git reset --hard HEAD before fetch/checkout in the update path
to discard any pre-existing dirt, and (2) pin core.autocrlf=false on both
the update and fresh-clone paths so the dirt is never created again.
2026-06-03 06:45:48 -07:00
Teknium
6ee046a72f fix(doctor): detect + repair stale HERMES_MAX_ITERATIONS .env ghost shadowing config.yaml (#38222)
* fix(doctor): detect + repair stale HERMES_MAX_ITERATIONS .env ghost shadowing config.yaml

hermes doctor now flags when ~/.hermes/.env carries a HERMES_MAX_ITERATIONS
value that disagrees with agent.max_turns in config.yaml, and 'hermes doctor
--fix' removes the stale .env line so config.yaml is authoritative. 'hermes
config show' surfaces the same drift inline under Max turns.

The setup wizard stopped dual-writing this value, but users who edited only
config.yaml from a pre-fix install keep a .env ghost. The gateway bridge
normally overrides it at startup, but if the bridge bails on any earlier
config-parse error the ghost silently wins — config says 400 while the
gateway activity line reads N/90.

The detector reads the .env FILE directly (load_env), not get_env_value/
os.environ, since the startup bridge may already have overwritten os.environ
with the config value.

Closes #17534.

* fix(config): stop offering HERMES_MAX_ITERATIONS as an editable env var

Removes HERMES_MAX_ITERATIONS from OPTIONAL_ENV_VARS so the dashboard env
editor (PUT /api/env) and any env-var prompt no longer let a user write it
to .env — which would recreate the stale ghost that shadows config.yaml's
agent.max_turns (issue #17534). The iteration budget is configured only via
config.yaml; the env var stays a read-only backward-compat fallback in the
gateway/CLI, never a promoted write target.

Regression test asserts it is absent from OPTIONAL_ENV_VARS.
2026-06-03 06:38:40 -07:00
teknium1
de26b17854 test: stub has_hook in transform_tool_result hook tests
CI slice 3 caught that tests/test_transform_tool_result_hook.py monkeypatches
invoke_hook but not has_hook, so the new has_hook("transform_tool_result")
gate skipped the emit and the transform never ran. Stub has_hook=True in the
shared _run_handle_function_call helper whenever a custom invoke_hook is
supplied (the test intends hooks to fire). The no-hook-registered test keeps
the real has_hook=False path — that's the gate's intended behavior.
2026-06-03 06:36:46 -07:00
teknium1
827f251426 perf(observability): gate tool-hook emit on has_hook; slim per-tool footprint
The salvaged observer contract gated the API-request hot path on has_hook()
but left the per-tool emit ungated: every tool call ran result-field
derivation + payload dict build + invoke_hook dispatch even with zero
plugins registered.

- _emit_post_tool_call_hook now short-circuits on has_hook("post_tool_call")
  and derives status/error fields lazily (after the gate, only when a
  listener will consume them). status defaults to None -> derived; explicit
  blocked/cancelled callers still pass status through.
- transform_tool_result emit (pre-existing hook) likewise gated on
  has_hook(); skips _tool_result_observer_fields when no listener.
- Removed the now-redundant _tool_result_observer_fields pre-computation at
  the three ok-path call sites (model_tools, agent_runtime_helpers,
  tool_executor) — the helper derives them, so the no-listener path costs
  one dict lookup and the call sites shrink.
- Tests: stub has_hook=True where payload correctness is asserted; add a
  no-listener regression proving post_tool_call/transform_tool_result emit
  is skipped when nothing is registered.
2026-06-03 06:36:46 -07:00
kshitijk4poor
432325933a test: restore unrelated trailing newlines in cwd/tool-search tests
The salvaged PR incidentally stripped a trailing blank line from two
unrelated test files (test_file_tools_cwd_resolution.py,
test_tool_search.py). Restore them to keep the salvage diff scoped to
the observability feature.
2026-06-03 06:36:46 -07:00
Bryan Bednarski
0d9b7132ff feat(observability): observer-grade telemetry hooks + NeMo-Relay plugin
Adds backend-neutral observer hooks for plugins: session, turn, API
request, tool, approval, and subagent lifecycle events with stable
correlation IDs (session_id, task_id, turn_id, api_request_id,
tool_call_id, parent/child subagent ids). Extends VALID_HOOKS with
api_request_error and subagent_start.

Hot path is zero-cost when no plugin subscribes: has_hook()/presence
checks gate all payload construction, request payloads are returned
by reference when no middleware rewrites, and the sanitized response
payload no longer embeds raw response objects.

Bundles the optional NeMo-Relay observability plugin
(plugins/observability/nemo_relay) as an in-repo consumer of the new
hooks, peer to the existing langfuse plugin. Fails open when the
optional nemo-relay package is not installed.

Authored-by: Bryan Bednarski <bbednarski@nvidia.com>
Salvaged from #29722 onto current main.
2026-06-03 06:36:46 -07:00
brooklyn!
a78c73f3aa Merge pull request #38224 from NousResearch/hermes/hermes-79601e59
fix(tui): stop persisting full tool output in trail lines (silent OOM death)
2026-06-03 08:24:39 -05:00
Teknium
4c544b633d fix(kanban): don't permanently block tasks that hit a provider rate limit (#38223)
A kanban worker that exhausted its retries purely on a provider rate
limit / quota wall (e.g. opencode-go's 5-hour window) exited with code 1.
The dispatcher counted that as a crash, and with DEFAULT_FAILURE_LIMIT=2
two quota-wall hits permanently blocked the card. Fanning out many
workers against one shared quota made this routine.

Now a rate-limited worker exits with EX_TEMPFAIL (75); the dispatcher
classifies that as a 'rate_limited' exit, releases the task back to
'ready' WITHOUT incrementing consecutive_failures (the breaker can't trip
on a transient throttle), and the respawn guard defers the next attempt
on a cooldown (default 5min, HERMES_KANBAN_RATE_LIMIT_COOLDOWN_SECONDS)
until the quota window clears. Genuine crashes still count and trip the
breaker as before. The 120s Retry-After cap is unchanged — no worker
parks for hours holding a slot.

- conversation_loop.py: surface failure_reason in the exhaustion return
- cli.py: kanban worker picks exit 75 on rate_limit/billing failure
- kanban_db.py: rate_limited exit kind, no-count requeue, cooldown guard
2026-06-03 06:19:32 -07:00
brooklyn!
60b6352fe5 Merge pull request #38221 from NousResearch/hermes/hermes-45accc84
fix(desktop): stop chat scroll bounce — at-rest backward jump + wheel-up snap-back
2026-06-03 08:05:28 -05:00
teknium1
e76d8bf5aa fix(tui): stop persisting full tool output in trail lines (silent OOM death)
A heavy --tui session (browser snapshots, large tool outputs) silently
OOM-killed the Node parent within minutes — closing the gateway child's
stdin, which the user saw only as a bare "gateway exited" / stdin EOF.
CLI was immune. Root cause: each completed tool's verbose trail line
embedded up to 16KB of result_text, persisted in transcript Msg.tools[]
for the whole session and rendered EXPANDED by default, so an Ink
render-node tree was built for every one of up to 800 messages at once.
That tree blew past Node's heap at a few hundred MB — far below the 2.5GB
memory-monitor exit threshold, so the death was never even attributed.

- text.ts: persisted verbose tool-trail blocks now cap to a small preview
  (VERBOSE_TRAIL_MAX_CHARS=800/12 lines), not the 16KB live-render budget.
  Retained trail strings drop ~17x (12.2MB -> 0.7MB at 800 msgs); the live
  streaming tail still uses the larger LIVE_RENDER budget.
- tui_gateway/server.py: lower the gateway-side verbose text cap to match
  (1KB/16 lines) so we stop shipping output the TUI no longer renders.
- memoryMonitor.ts: derive critical/high thresholds from the real V8 heap
  ceiling (~88%/70%) instead of the hardcoded 2.5GB that killed the process
  at 31% of an 8GB ceiling; add a one-shot onWarn early-warning on fast
  sub-threshold heap growth so the next such death is diagnosable, not silent.
- entry.tsx: wire onWarn to a crash-log breadcrumb + stderr line.

Full tool output is unchanged in the agent context and SQLite session — this
is display/transport only, no behavior or context change.

Fixes #34095. Related #27282.

Tests: ui-tui text + new memoryMonitor suites (33 pass), python verbose-cap
guard (5 pass); full ui-tui suite shows no new failures vs pristine main.
E2E repro confirms the retention drop.
2026-06-03 06:00:22 -07:00
Teknium
c5d199eada feat(dashboard): check-before-update flow on the System page (#38205)
The dashboard's update button ran 'hermes update' immediately with no
preview. Now the System page shows whether an update is available and
asks the user to confirm before applying it.

- New GET /api/hermes/update/check: reports install method, current
  version, and commits-behind (via banner.check_for_updates, 6h-cached;
  ?force=1 busts the cache). Soft-fails to behind=null on network error;
  marks docker/nix/homebrew as can_apply=false with the out-of-band cmd.
- System page: update-status badge on the Hermes version row (latest /
  N behind), a Check-for-updates button, and an Update-now button that
  opens a ConfirmDialog showing the commit count before POST /api/hermes/
  update fires. Cached status loads with the rest of the page.
- Docs + 5 endpoint tests (git/up-to-date/docker/soft-failure + auth gate).
2026-06-03 05:57:15 -07:00
Fermin Quant
c930a49ce9 fix(desktop): honor upward wheel scroll in long threads 2026-06-03 05:54:49 -07:00
luyao618
3aa24e2619 fix(desktop): stop chat scroll backward-jump from content-growth interim scrolls (#37997)
The thread scroll-anchor hook in apps/desktop/src/components/assistant-ui/
thread-virtualizer.tsx was disarming sticky-bottom whenever scrollTop
decreased by >1px between scroll events. That check was too eager: when
content height grows mid-frame (virtualizer measurement of a newly visible
turn, streaming token, Streamdown/Shiki re-tokenization, composer chip
toggle), the browser emits an interim 'scroll' event whose scrollTop is
smaller than the previous frame's because scrollHeight just jumped. The
rAF-scheduled pinToBottom hasn't run yet, so programmaticScrollPendingRef
is 0 and the disarm fired. With sticky-bottom disarmed the scroller stuck
~50px above bottom — the visible at-rest backward jump that #37997
describes (and the same root cause as the wheel-up variant in #37527).

Fix:
- Track scrollHeight per frame (lastHeightRef). Disarm on scrollTop
  decrease ONLY when scrollHeight did not grow this frame. Real upward
  user intent (scrollbar drag, keyboard PgUp, programmatic scrollIntoView)
  still disarms because it moves scrollTop without growing the content.
  Wheel-up and touchmove continue to disarm via their own listeners.
- Stop observing the scroller element itself in the ResizeObserver; only
  observe its content child. Viewport-only resizes (window resize,
  devtools panel toggle) no longer trigger spurious pins, matching the
  intent of the auto-stick-to-bottom behavior.

Verified:
- apps/desktop `tsc -b` clean.
- apps/desktop `vitest run src/components/assistant-ui/streaming.test.tsx`
  passes (9/9), including the existing wheel-up disarm regression test
  that asserts scrollTop stays at 420 after a wheel-up + content growth.
2026-06-03 05:54:45 -07:00
teknium1
ba57ebec33 fix(nix): bump npmDepsHash for refreshed lockfile
Lockfile regeneration invalidated the flake's pinned npm-deps hash.
Hash taken from fetchNpmDeps' authoritative 'got:' line (the
prefetch-npm-deps Diagnose helper reports a different, wrong value
due to a fetcherVersion normalization discrepancy).
2026-06-03 05:50:36 -07:00
teknium1
b98b645f87 chore: regenerate lockfile + map vladkvlchk for salvaged #36978
- Add @testing-library/dom to apps/desktop devDeps in package-lock.json
  so npm ci validates against the manifest change (contributor left the
  lockfile out of the PR intentionally).
- Removes stale 'peer: true' flags now that dom is an explicit devDep.
- AUTHOR_MAP: prostoandrei9@gmail.com -> vladkvlchk (CI author gate).
2026-06-03 05:50:36 -07:00
Vladyslav Kovalchuk
f45d7dee7d fix(desktop): add @testing-library/dom as explicit dev dependency
@testing-library/react@16 declares @testing-library/dom as a peerDependency
and re-exports waitFor/fireEvent/screen/within from it. Without dom installed
as a direct dependency, tsc -b fails with TS2305 in every test file that
imports those names — which breaks the apps/desktop build during installer
bootstrap (Hermes Setup → "INSTALL DIDN'T FINISH").
2026-06-03 05:50:36 -07:00
Teknium
1b302a0474 feat(debug): include desktop.log in hermes debug share / /debug / hermes logs (#38203)
The Electron desktop app writes boot failures, backend spawn output, and
Python tracebacks to HERMES_HOME/logs/desktop.log, but debug-share only
captured agent/errors/gateway — so desktop boot issues never made it into
shared debug reports.

- logs.py: register desktop -> desktop.log (enables 'hermes logs desktop')
- debug.py: capture desktop snapshot, add to summary report, upload full
  desktop.log in 'share', update privacy notice
- gateway /debug inherits the desktop tail via collect_debug_report()
- main.py + docs: help text and log-name table (also adds missing gui row)
- tests: desktop seed in fixture, new report test, three_pastes -> four_pastes
2026-06-03 05:41:35 -07:00
Teknium
1d90b23982 fix(mcp): banner shows 'disabled' not 'failed' for enabled:false servers (#38204)
get_mcp_status() treated every non-connected server as a failure, so a
server configured with enabled: false rendered as red '— failed' in the
startup banner even though it was intentionally off. Add a 'disabled'
field derived from the enabled flag and render disabled servers dim as
'— disabled' instead.
2026-06-03 05:41:13 -07:00
Teknium
ef65298103 docs: make the Desktop App remote-backend section self-contained (#38194)
The section explained why the Session token is hidden but punted the actual
setup steps to the web-dashboard page via a link — a bounce for someone on
the Desktop App page trying to connect. Inline the concrete steps instead:
backend command block (mint token -> .env -> hermes dashboard --insecure),
the in-app Remote gateway steps, the env-var override, Tailscale guidance,
and a troubleshooting list. Keep a short pointer to the web-dashboard page
for the same setup from that angle.
2026-06-03 05:27:38 -07:00
kshitij
50ba36dcab chore: add bbednarski9 to AUTHOR_MAP for #29722 salvage (#38189)
Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
2026-06-03 05:25:35 -07:00
teknium1
5fca754ee3 fix(desktop): pass live backend PID to in-app update so its own dashboard is spared
The Python half (#37538) reads HERMES_DESKTOP_CHILD_PID to exclude the
desktop-managed backend from _kill_stale_dashboard_processes, but nothing
set it. applyUpdatesPosixInApp now passes the live backend PID in the
`hermes update` env, completing the #37532 fix end-to-end.
2026-06-03 04:59:49 -07:00
liuhao1024
192020992d fix(cli): exclude desktop-managed backend from stale-dashboard kill
Fixes #37532
2026-06-03 04:59:49 -07:00
Teknium
d833b1eff7 docs: add remote-backend section to the Desktop App page (#38180)
The Desktop App page covered install, settings, and chat but not how to
connect the app to a backend on another machine — the exact thing
@PedjaDrazic asked about. Add a 'Connecting to a remote backend' section
that explains the Session token is the dashboard token Hermes never
surfaces (pin it via HERMES_DASHBOARD_SESSION_TOKEN + run --insecure),
and link to the web-dashboard page for the full backend setup rather than
duplicating it. Add a reciprocal link from the web-dashboard remote section
back to the Desktop App page.
2026-06-03 04:59:04 -07:00
alt-glitch
a1264e9967 fix(matrix): make bang-command resolution robust + fix dead skill-command branch
Follow-up to the salvaged contributor commit:

- Underscore→hyphen tolerance now emits a resolvable token. Previously
  the detect set accepted the hyphenated variant but emit returned the
  raw token, so '!set_home' produced '/set_home' which the dispatcher
  could not resolve. Now emits '/set-home'. Aliases are left as-is — the
  gateway dispatcher canonicalizes them itself.
- Fix dead skill-command branch: skill command keys are stored
  slash-prefixed (e.g. '/arxiv') in get_skill_commands(), but the check
  compared the bare token, so '!arxiv' never normalized. Now compares
  the '/candidate' form, making skill aliases (e.g. !gif-search) work.
- Re-run bang normalization after Matrix reply-fallback stripping so a
  quoted reply whose content is a bang command reaches command parity
  with the slash form.
- Replace silent 'except Exception: pass' with logger.debug(exc_info=True).
- Add AUTHOR_MAP entry for @nepenth.

Tests: +5 (underscore-alias, skill-command branch, quoted-reply bang +
slash parity). 162 Matrix tests pass.
2026-06-03 17:19:27 +05:30
Chris
0022e94d74 feat(matrix): support bang command aliases 2026-06-03 17:19:27 +05:30
Teknium
6038bfb66e docs: explain remote-gateway session token for Hermes Desktop (#38144)
The desktop Remote gateway field asks for a session token that Hermes never
surfaces — by default web_server.py mints an ephemeral token per boot and
injects it into the served HTML, so there is nothing in config.yaml, /gateway,
or env to copy. Document that you pin it yourself via
HERMES_DASHBOARD_SESSION_TOKEN, run the backend with --insecure (keeps the
legacy token auth path instead of engaging the OAuth gate), then paste that
value into the desktop app.

- web-dashboard.md: new 'Connecting Hermes Desktop to a remote backend' section
  (backend + desktop steps, --insecure vs OAuth-gate nuance, HERMES_DESKTOP_*
  env override, Tailscale guidance, troubleshooting).
- environment-variables.md: new 'Web Dashboard & Hermes Desktop' env-var table
  (HERMES_DASHBOARD_SESSION_TOKEN, HERMES_DESKTOP_REMOTE_URL/TOKEN, the OAuth
  and public-url vars) — none were previously documented.
2026-06-03 04:16:00 -07:00
Teknium
047e7cf36f fix(docs): remove remaining stale submodule references missed by #38089 (#38105)
Follow-up to #38089. The merged PR removed --recurse-submodules from the
installer, CI, and getting-started docs, but missed the same stale clause in:
- CONTRIBUTING.md (Prerequisites table)
- website/docs/developer-guide/contributing.md (table + clone command)
- zh-Hans mirror of the developer-guide contributing doc

git-lfs is kept in the Git requirement rows since it's a separate, real
prerequisite. No .gitmodules has existed since the Atropos RL submodule was
removed in #26106.
2026-06-03 03:11:19 -07:00
ethernet
43fd63b4b5 fix(windows): rip out unused submodule support in installer & docker & docs
we have no submodules anymore, so #37702 was kinda right, but we can just delete it entirely.
2026-06-03 03:01:37 -07:00
Teknium
64202200a6 chore: remove committed RELEASE_v*.md changelogs from repo root (#37855)
These per-release changelog files are transient working files used only to
feed `gh release create --notes-file` at release time; the GitHub Release
itself permanently stores the published notes. They were never a build
artifact (no package-data glob, no MANIFEST.in include, no CI reference)
and don't belong in the tracked tree.

- Delete all 15 (v0.2.0 through v0.15.1)
- Add RELEASE_v*.md to .gitignore so an accidental `git add -A` can't
  recommit them

The hermes-release skill is updated separately to write the changelog to
/tmp/ for the whole release process and never stage it.
2026-06-03 01:55:59 -07:00
kshitij
f019a9c491 Merge pull request #37975 from kshitijk4poor/fix/desktop-session-view-bleed
fix(desktop): stop background session messages bleeding into the active transcript
2026-06-03 01:03:50 -07:00
kshitij
46ea0a184d Merge pull request #37999 from kshitijk4poor/desktop-slash-nav-dom-regression-test
fix(desktop): slash/@ menu keyboard nav — cycle all items + Esc dismiss
2026-06-03 00:51:54 -07:00
kshitijk4poor
49f1b9e4b4 fix(desktop): stop Esc reopening the slash/@ menu; harden keyup guard
Follow-up to #37937. That fix guarded the composer's keyup with
`shouldSkipTriggerRefreshOnKeyUp(key, trigger !== null)`. The `trigger !== null`
check is timing-fragile for Escape: Escape's *keydown* sets `trigger = null`
and closes the menu, but in a real browser the *keyup* fires after a re-render,
so the handler closure sees `trigger === null`, the guard returns false,
`refreshTrigger` runs, re-detects the still-present `/` in the input, and
instantly reopens the menu. (jsdom batches state synchronously so a unit test
could not observe this -- only the running app does.)

Replace the value-based guard with a `triggerKeyConsumedRef` set synchronously
in keydown whenever the open popover consumes a nav/control key
(Arrow/Enter/Tab/Escape). keyup consults and clears that ref, so it is immune
to the keydown->re-render->keyup timing. Applied to both the main composer
(chat/composer/index.tsx) and the message-edit composer
(assistant-ui/thread.tsx).

Removes the now-unused `shouldSkipTriggerRefreshOnKeyUp` helper and its unit
test. The real-DOM regression test now fires keydown+keyup pairs through the
ref-based handlers and asserts Esc closes and stays closed.

Verified by running a production renderer build (Vite v8) under Electron
against a local backend: ArrowDown/ArrowUp cycle the full list and Esc
dismisses the menu without reopening.
2026-06-03 13:15:08 +05:30
kshitijk4poor
c77c470d27 test(desktop): real-DOM regression for slash/@ menu keyboard nav
The existing slash-menu fix (PR #37937) shipped a unit test that drove the
keydown reducer directly. It did not exercise the actual DOM event path —
specifically the keyup-driven `refreshTrigger` that was the root cause — so
it would not have caught a regression in that path.

This adds a faithful @testing-library reproduction that mounts the real
`useLiveCompletionAdapter` plus the index.tsx trigger wiring and fires real
`keyDown` + `keyUp` event pairs on a contentEditable. It asserts:

- ArrowDown cycles through ALL items (0,1,2,3,4,0,1), not just the first two
- Escape closes the menu and keyup does not reopen it

Reverting the fix (always-refresh keyup + unconditional setTriggerActive(0))
makes this test fail with the highlight stuck at the top — confirming it
guards the real bug.
2026-06-03 12:46:14 +05:30
kshitijk4poor
e114b31eda test(dashboard): direct unit coverage for internal WS credential + docstring fix
Follow-up to Ben's PR #37892. Adds a TestInternalCredential block to
test_dashboard_auth_ws_tickets.py exercising the mint-once stability,
multi-use, unminted-rejection, empty-value, wrong-value, reset-and-remint,
and ticket-store-independence branches directly (previously only covered
indirectly via _ws_auth_ok, which left the unminted and empty-value
branches unexercised).

Also corrects the consume_internal_credential docstring: the returned
identity dict is discarded by the current _ws_auth_ok caller (which only
needs the boolean outcome), so the prior 'carry it into its session log'
wording over-promised.
2026-06-02 23:43:27 -07:00
Ben
fd1ec8033d fix(dashboard): authenticate server-spawned PTY child WS with a process-internal credential
The embedded-TUI PTY child attaches to two server-internal WebSockets:
/api/ws (its primary JSON-RPC gateway backend) and /api/pub (the event
sidecar). Both URLs are built server-side in web_server.py and handed to
the child via its environment.

In OAuth-gated mode (auth_required=true, every hosted Fly agent), _ws_auth_ok
unconditionally rejects the legacy ?token=<_SESSION_TOKEN> path — a leaked
session token must not grant WS access once the gate is engaged. But
_build_gateway_ws_url() still only emitted ?token=, with no gated-mode
branch (its sibling _build_sidecar_url had been given a ticket branch; the
gateway-url builder was missed). So the TUI child's /api/ws upgrade was
rejected 4401 -> 'gateway websocket connection failed' -> 'gateway startup
timeout', leaving the embedded chat unusable on every gated deployment.

A single-use 30s browser ticket is the wrong shape for this link: the child
reads its attach URL once at startup and reuses it on every reconnect, and
on a slow cold boot it may not dial within the TTL. (_build_sidecar_url's
own docstring already flagged this fragility.)

Fix: add a process-lifetime, multi-use internal credential to
dashboard_auth.ws_tickets (internal_ws_credential / consume_internal_credential),
minted once per process and NEVER injected into the SPA — it only leaves the
process via a spawned child's env, so browser-side XSS can't read it, and a
leak grants no more than a ticket already does. _ws_auth_ok accepts it via
?internal= in gated mode only. Both _build_gateway_ws_url and
_build_sidecar_url now use it, so the child can reconnect both sockets.

Loopback / --insecure behavior is unchanged (still ?token=).

Needs review: touches _ws_auth_ok + dashboard_auth (core auth surface).
2026-06-02 23:43:27 -07:00
kshitijk4poor
28f1590b7a fix(desktop): stop background session messages bleeding into the active transcript
A still-busy background session (one the user toggled away from) keeps
emitting updateSessionState() heartbeats — stream deltas, and especially
the 'session busy' prompt-rejection errors from auto-drained queued turns.
Each call invoked syncSessionStateToView() unconditionally, staging that
session's messages into the shared $messages view.

flushPendingViewState() guarded against the wrong session reaching the
view, but only one requestAnimationFrame is scheduled per frame and
pendingViewStateRef holds just the latest writer. So within a single
frame a background write could overwrite an already-pending foreground
write, and the stale background transcript (e.g. the red 'session busy'
rows) would render on top of whatever session the user switched to —
appearing to 'bleed' into every session.

Guard at the staging site: a session may only stage into the view when
it is the currently-active session. Background sessions still update
their own cache entry; they just never touch $messages. Pure render
fix, no behavior change to queuing, interrupt, or drain.
2026-06-03 12:09:18 +05:30
kshitij
ada04573a9 Merge pull request #37948 from kshitijk4poor/fix/desktop-stop-button-interrupt
fix(desktop): make Stop button actually interrupt when a turn is queued
2026-06-02 23:20:30 -07:00
kshitijk4poor
a23728dfcc fix(desktop): make Stop button actually interrupt when a turn is queued
When a follow-up message is queued during a busy turn, the composer
clears and the primary button switches back to the Stop affordance. But
clicking Stop ran interruptAndSendNextQueued(), which cancelled the turn
and *immediately* re-sent the head of the queue. The auto-drain effect
(busy true to false) compounded this: any explicit cancel flipped busy
false and re-fired the queue. The net effect was that Stop appeared to
never interrupt -- the agent kept running on the queued prompt.

Fix:
- Stop button (busy + empty composer) now always performs a pure
  interrupt via onCancel(); it no longer hijacks the queue.
- An explicit interrupt latches userInterruptedRef so the busy to false
  auto-drain skips exactly one drain. Queued turns are preserved and the
  user resumes them deliberately (Cmd/Ctrl+K, Enter, or the per-row
  send-now arrow), matching the documented Esc=cancel / Cmd+K=send-next
  affordances.
- Extracted the settle decision into shouldAutoDrainOnSettle() with unit
  tests covering natural completion vs. explicit interrupt.
2026-06-03 11:46:02 +05:30
kshitij
9b43ab8de5 Merge pull request #37937 from kshitijk4poor/fix/desktop-slash-menu-keyup-nav
fix(desktop): keep slash/@ completion menu navigable and Esc-dismissable
2026-06-02 22:54:05 -07:00
kshitijk4poor
188e52db91 fix(desktop): keep slash/@ completion menu navigable and Esc-dismissable
The desktop composer's `onKeyUp` handler unconditionally re-ran
`refreshTrigger` on every keyup, including the Arrow/Enter/Tab/Escape keys
the open-trigger `onKeyDown` branch had already fully handled. Because
`refreshTrigger` re-detects the trigger and resets the active index to 0,
this produced two bugs in the `/` (and `@`) completion popover:

- ArrowDown/ArrowUp moved the highlight on keydown, then keyup snapped it
  straight back to the top — so the user could never cycle past the first
  couple of items.
- Escape closed the menu on keydown, then keyup re-detected the still-present
  `/` and immediately reopened it — so Esc appeared to do nothing.

Fix: skip the keyup-driven refresh for the navigation/control keys while a
trigger menu is open (they never edit text, so refreshing is pointless), and
only reset the highlight in `refreshTrigger` when the detected trigger query
actually changed. Applied to both the main composer (chat/composer/index.tsx)
and the message-edit composer (assistant-ui/thread.tsx), which shared the
same bug. New `shouldSkipTriggerRefreshOnKeyUp` helper is unit-tested.
2026-06-03 11:19:07 +05:30
brooklyn!
5005b79bc3 Merge pull request #37932 from NousResearch/bb/desktop-remote-flicker
fix(desktop): disable GPU acceleration on remote displays to stop flicker
2026-06-03 00:43:37 -05:00
Brooklyn Nicholson
d0ea4caf7f fix(desktop): don't treat WSLg as a remote display
WSLg renders Linux GUIs locally through a vGPU surface rather than
shipping frames over the wire, so it doesn't show the remote-compositor
flicker — confirmed by a WSL user seeing zero flickering. Drop the WSL
branch from detectRemoteDisplay so WSLg keeps hardware acceleration;
detection now covers only genuinely-remote displays (SSH X11 forwarding,
VNC, RDP). The HERMES_DESKTOP_DISABLE_GPU override still works for anyone
who does hit it.
2026-06-03 00:42:05 -05:00
Brooklyn Nicholson
6a2909fe5a fix(desktop): disable GPU acceleration on remote displays to stop flicker
Users on remote/forwarded displays (SSH X11 forwarding, VNC, RDP, WSLg)
reported the window flickering during scroll/streaming; nobody on native
Windows/macOS ever saw it.

Root cause: the app shipped with Chromium's default GPU hardware
acceleration and no remote-display handling. Over a remote connection the
GPU compositor can't present accelerated layers cleanly across the wire,
so the surface flashes on repaint. Local sessions composite on the GPU
and never hit it.

Detect a remote display before app `ready` (detectRemoteDisplay in
bootstrap-platform.cjs) and fall back to software rendering via
app.disableHardwareAcceleration() + --disable-gpu-compositing. Software
compositing is rock-steady over the wire and the CPU cost is negligible
next to the connection's latency. HERMES_DESKTOP_DISABLE_GPU overrides
detection both ways for VNC/screen-sharing setups we can't sniff or
remote hosts that do have working acceleration.
2026-06-03 00:36:59 -05:00
Ben Barclay
9272e4019a fix(docker): point TUI launcher at prebuilt bundle via HERMES_TUI_DIR (#37923)
The embedded dashboard Chat tab dies on hosted images with a 502 /
"[session ended]": the PTY child's `hermes --tui` spawn runs a runtime
`npm install` that fails.

Root cause: the root package-lock.json describes the WHOLE npm monorepo
workspace set (root + web + ui-tui + apps/*), but the image only installs
root/web/ui-tui — apps/* (the desktop app) is never `npm install`ed here, and
its deps hoist into the shared root node_modules. So the actualized
node_modules permanently disagrees with the canonical lock,
`_tui_need_npm_install()` returns True on every launch, and the runtime
`npm install` it triggers (a) can never converge against the partial monorepo
and (b) races itself across concurrent /api/pty connections -> ENOTEMPTY ->
the launcher `sys.exit(1)`s, the slow install blows past Fly's WS-upgrade
window -> 502 -> the browser shows "[session ended]".

Fix: set `ENV HERMES_TUI_DIR=/opt/hermes/ui-tui` so `_make_tui_argv` takes the
prebuilt-bundle fast path (`node --expose-gc /opt/hermes/ui-tui/dist/entry.js`)
and never reaches the install check — exactly the nix/packaged-release path
the launcher was designed for. The bundle is already built at Layer 8
(`ui-tui && npm run build`); this just tells the launcher to use it.

Verified on a freshly-built image: HERMES_TUI_DIR is set, the prebuilt
dist/entry.js is present, `_make_tui_argv` resolves to the prebuilt node
invocation (no npm), and `docker run ... --tui` no longer prints
"npm install failed". New regression guard: tests/docker/test_tui_prebuilt_bundle.py.

A separate launcher hardening (make _tui_need_npm_install tolerant of
partial-monorepo installs) is tracked independently; this Docker-side fix
resolves the hosted-chat symptom on its own.

Area: docker (Dockerfile + tests/docker).
2026-06-03 15:30:45 +10:00
brooklyn!
feb50eee70 Merge pull request #37908 from NousResearch/bb/desktop-concurrent-session-loss
fix(desktop): keep in-flight new chats from vanishing on refresh
2026-06-03 00:29:13 -05:00
Brooklyn Nicholson
e0a999aa8a fix(desktop): label in-flight new chats with the first message
The send path created the optimistic sidebar row with a null preview, so
a new chat read "Untitled session" until its turn persisted and auto-title
ran. With concurrent new chats now preserved across refreshes, several
"Untitled session" rows could show at once.

Seed the optimistic preview with the user's first message (the branch path
already does this) so each in-flight row is labeled immediately. The
server's own preview/title supersedes it once the turn persists.
2026-06-03 00:25:19 -05:00
Brooklyn Nicholson
55a76ec669 fix(desktop): keep in-flight new chats from vanishing on refresh
Creating several sessions in a row (Ctrl-N, type, send, repeat) and
waiting for one to finish made the other still-running chats disappear
from the sidebar.

Root cause: a new session's first user message isn't flushed to the
SessionDB until its turn is persisted, so the row's message_count stays
0 mid-response. `refreshSessions()` lists with min_messages=1 and then
hard-replaces $sessions. Because every message.complete triggers a
refresh, the moment one session finished, the others (still at
message_count 0) were filtered out of the server page and dropped from
the list.

Fix: merge instead of replace. `mergeWorkingSessions()` preserves any
session that is still in $workingSessionIds but absent from the server
page, so concurrent new chats stay visible until their own turn persists.
Optimistic deletes/archives already remove the row from the previous
list, so a removed session can't be resurrected by the merge.
2026-06-03 00:21:05 -05:00
Ben Barclay
d9f7e7ac81 fix(docker): seed gateway_state.json from HERMES_GATEWAY_BOOTSTRAP_STATE on first boot (#37896)
On a fresh volume there is no gateway_state.json, so the boot reconciler
(cont-init.d/02-reconcile-profiles) registers the gateway-default s6 slot
but leaves it down — it only auto-starts when the last recorded state was
"running". A freshly-provisioned container therefore comes up with the
gateway down until something starts it (e.g. the dashboard's start button).

Add a generic, first-boot-only env-seed in stage2-hook.sh (which runs
before 02-reconcile-profiles): when HERMES_GATEWAY_BOOTSTRAP_STATE=running
and no gateway_state.json exists yet, seed {"gateway_state":"running"} so
the reconciler brings the supervised slot up on the very first boot.

This mirrors the existing HERMES_AUTH_JSON_BOOTSTRAP pattern: it seeds the
same state file the reconciler already consults, guarded by [ ! -f ] so
persisted runtime state always wins on later boots (a deliberately-stopped
gateway stays stopped across restarts). Only the literal "running" is
honoured (the sole value in the reconciler's _AUTOSTART_STATES).

Generic container contract — no host-specific code. Useful to any
orchestrator that provisions a blank volume and wants the gateway up from
first boot (the supervised gateway/dashboard already work on such hosts;
only the first-boot autostart was missing because the CLI lifecycle
commands can't drive the s6 layer when container self-detection misses).

Adds a shell-level contract test and documents the env var.
2026-06-03 15:11:15 +10:00
ethernet
e618cbee44 feat(desktop): custom zoom shortcuts at half default step
Replace Electron's built-in zoomIn/zoomOut/resetZoom menu roles with
custom implementations that use a 0.1 zoom-level step instead of
Chromium's default 0.2. This makes Ctrl/Cmd + +/-0 zoom feel more
granular and less jumpy.

Also adds installZoomShortcuts() which intercepts the keyboard shortcuts
via before-input-event. This is necessary on Linux/Windows where the
application menu is set to null, so Chromium's default handler would
otherwise apply the full 0.2 step.
2026-06-03 01:07:44 -04:00
brooklyn!
2f0ee66467 Merge pull request #37877 from NousResearch/bb/desktop-sticky-msg-clamp
feat(desktop): clamp sticky human messages to ~2 lines until hover/focus
2026-06-02 23:45:13 -05:00
Brooklyn Nicholson
cbc1d901ba chore: uptick 2026-06-02 23:44:51 -05:00
Brooklyn Nicholson
84eb5f1f89 fix(desktop): restore sticky human clamp transition at 0.75s 2026-06-02 23:44:06 -05:00
Brooklyn Nicholson
e5472da584 fix(desktop): drop sticky human clamp max-height transition 2026-06-02 23:43:52 -05:00
Brooklyn Nicholson
3ab783a7bb chore: uptick 2026-06-02 23:43:25 -05:00
Brooklyn Nicholson
06aa140fa1 fix(desktop): inset sticky human messages with --sticky-human-top
Pin user bubbles 0.75rem below the scroll top via a single token instead of
flush top-0, so the sticky header doesn't sit hard against the thread edge.
2026-06-02 23:42:38 -05:00
Ben Barclay
dd28f2ac9c fix(dashboard): trust non-web WS origins on OAuth-gated binds after ticket auth (#37870)
Generalises #37747. The WS Origin guard (_ws_host_origin_is_allowed) only
trusted the packaged Electron app's non-web origin (file:// / null / app://)
when the bind was NOT OAuth-gated. The packaged Hermes Desktop renderer loads
over file://, so when it drives a remote OAuth-gated gateway its /api/ws
upgrade was rejected with HTTP 403 even though _ws_auth_ok had already
validated the single-use ?ticket= one line earlier.

This guard runs only AFTER _ws_auth_ok has accepted the WS credential, which
is the real auth boundary in every mode:
  * loopback bind          -> legacy dashboard session token
  * non-loopback --insecure -> legacy session token (Tailscale / LAN, #37747)
  * OAuth-gated public bind -> single-use, 30s-TTL, identity-bound ?ticket=
A non-web origin can only come from a native client; a DNS-rebinding attack
always arrives from an http(s) origin and is still match-checked against the
bound host. So once the upstream credential check has passed, the Origin guard
adds nothing for a non-web origin. Collapsed the loopback/non-gated special
cases to 'return True' for non-web origins.

http(s) origins keep the strict same-host check, so browser DNS-rebinding
defence is unchanged.

Tests: gated file:///null/app:// now asserted ALLOWED; cross-site http(s)
still rejected on gated and loopback binds; #37747's loopback and
non-loopback-insecure cases retained. 37/37 test_dashboard_auth_ws_auth +
test_web_server_host_header pass.
2026-06-03 14:32:53 +10:00
Brooklyn Nicholson
9bdf01852a feat(desktop): clamp sticky human messages to ~2 lines until hover/focus
Long user prompts stick to the top of the thread while the response streams
beneath them, so a multi-line prompt could eat most of the viewport. Clamp the
read-only human bubble's text to ~2 lines with a soft bottom fade; the clamp
lifts on hover or keyboard focus, and clicking the bubble still opens the edit
composer (which shows the full text). Short messages are untouched — no clamp,
no fade.

Overflow is measured on an unclamped inner wrapper so the ResizeObserver only
fires on real content/width changes, not every frame while the outer
max-height animates open; the measured height feeds --human-msg-full so
expand/collapse animate to the true height instead of overshooting the cap.
2026-06-02 23:29:05 -05:00
brooklyn!
a92cbcac45 Merge pull request #37866 from NousResearch/bb/desktop-scroll-anchor
fix(desktop): stop chat scroll jumping by disabling native scroll anchoring
2026-06-02 23:19:32 -05:00
Brooklyn Nicholson
e67ab2e042 fix(desktop): stop chat scroll jumping by disabling native scroll anchoring
The thread renders virtualized turns in natural document flow with padding
spacers, and @tanstack/react-virtual already adjusts scrollTop itself when an
off-screen turn is measured and its real height differs from the 220px
estimate. With the browser default `overflow-anchor: auto`, native scroll
anchoring corrects that SAME size delta too, so the two double-correct and the
view lurches — most visibly with Windows mouse wheels, whose coarse notches
mount/measure several under-estimated turns per tick (Mac trackpads scroll
~1-3px/frame, keeping it sub-perceptual).

Set `overflow-anchor: none` on the thread viewport so only the virtualizer
compensates. Also adds `diag-scroll-reset.mjs`, a CDP wheel-up repro that A/B
tests the anchor behavior at runtime to confirm the fix.
2026-06-02 23:08:01 -05:00
brooklyn!
b6da66c5be Merge pull request #37786 from NousResearch/bb/tui-rightclick-and-boundaries
fix(tui): clear selection on right-click copy + clearer block boundaries
2026-06-02 22:43:48 -05:00
Brooklyn Nicholson
dfba3f3e51 fix(tui): clear selection on right-click copy + group transcript blocks
Two TUI polish fixes.

(1) Right-click copy now clears the highlight.
The right-click handler copied an active selection via onCopySelectionNoClear
(the copy-on-select variant that keeps the highlight during a drag) and never
cleared it, so after right-click-to-copy the selection stayed lit with no
confirmation and a follow-up right-click re-copied the stale range instead of
pasting. A successful right-click copy now clears the selection and notifies;
if the copy fails (no clipboard path) the highlight survives and we fall back
to the right-click paste handler, exactly as before.

(2) Group transcript blocks so boundaries read clearly.
Model replies, reasoning/tool trails, and system/error notes rendered with no
vertical separation, so distinct block types butted together and were hard to
scan. Group adjacent blocks by kind: one blank line opens only where the visual
group changes (model prose <-> reasoning/tool trails <-> notes), while a run of
same-kind blocks renders flush. The rule lives in domain/blockLayout.ts
(messageGroup + hasLeadGap) and is applied intrinsically in MessageLine via a
`prev` prop, which fixes the things ad-hoc per-block margins kept breaking:

  - Streaming stability: the gap is derived from the stable predecessor, never
    the live block's own changing text, so the actively-streaming reply computes
    the same gap while it streams as the settled segment does once it flushes.
    No reflow/jump.
  - Transparent empty trails: a trail hidden by /details, or one carrying only a
    token tally (the finalDetails segment message.complete appends), renders
    nothing and is transparent to grouping (prevRenderedMsg skips it), so there
    are no floating gaps, no doubled gap after a prompt, and no padded space
    above the final reply. In the default/collapsed modes content-bearing trails
    always render, so the grouping is a no-op there.

The virtual-height estimator counts the group-boundary line so scroll math
stays accurate before Yoga remeasures.

ui-tui/src/domain/blockLayout.ts (new), components/messageLine.tsx,
components/streamingAssistant.tsx, components/appLayout.tsx,
lib/virtualHeights.ts, app/useMainApp.ts.

Tests: blockLayout.test.ts (grouping + hidden/empty-trail visibility),
virtualHeights leadGap, app-mouse.test.ts copy behavior. Full ui-tui suite
green apart from 3 pre-existing local/env failures (cursorDrift, ink-resize,
virtualHeights user-prompt-width) unchanged from main.
2026-06-02 22:03:38 -05:00
Teknium
b28dd3417d fix(setup): default browser/TTS picker to free local backend, not paid Nous (#37800)
The Browser Automation and Text-to-Speech provider pickers listed the paid
"Nous Subscription" gateway row first, so on a fresh install the menu cursor
defaulted to index 0 (Nous). Pressing Enter selected it and ran the inline
Nous Portal device-code login — walking users into a paid offering they
never chose.

Reorder both provider lists so the free, no-key local backend is index 0
(Local Browser / Microsoft Edge TTS). Users who already configured Nous are
unaffected: _detect_active_provider_index still resolves their active row
first, so the cursor lands on Nous (now index 1) for them.

Reported by Javier via Kujila.
2026-06-02 19:49:10 -07:00
brooklyn!
918aef267b Merge pull request #37782 from NousResearch/bb/configurable-default-interface
feat(cli): configurable default interface (cli vs tui) + --cli flag
2026-06-02 21:16:19 -05:00
Teknium
205ed71ba0 fix(deps): refresh lockfile to clear 6 npm audit findings (#37752)
* fix(deps): refresh lockfile to clear 6 npm audit findings

Plain `npm audit fix` (no --force, no overrides) — every patched
version was already in-range, so a lockfile refresh clears all
findings without permanent override pins.

Cleared:
- tmp 0.2.5 -> 0.2.7 (path traversal, HIGH — GHSA-ph9p-34f9-6g65)
- brace-expansion 5.0.5 -> 5.0.6 (DoS — GHSA-jxxr-4gwj-5jf2)
- mermaid 11.14.0 -> 11.15.0 (4 advisories: GHSA-6m6c-36f7-fhxh,
  GHSA-xcj9-5m2h-648r, GHSA-87f9-hvmw-gh4p, GHSA-ghcm-xqfw-q4vr)

npm audit: 6 vulnerabilities -> 0. package.json untouched.

* fix(nix): bump npmDepsHash for refreshed lockfile

Uses the hash fetchNpmDeps (the actual build fetcher) produces, which
diverges from prefetch-npm-deps / nix run .#fix-lockfiles output for
this lockfile.
2026-06-02 18:51:23 -07:00
Brooklyn Nicholson
d6b0c23f87 feat(cli): configurable default interface (cli vs tui)
Add `display.interface` config key so users can make the modern TUI the
default for bare `hermes` / `hermes chat` without exporting HERMES_TUI=1 in
every shell. Default stays "cli" to preserve current behavior.

Add a `--cli` flag (mirrors `--tui`) so an explicit invocation can force the
classic prompt_toolkit REPL even when `display.interface: tui` is configured.

Precedence (highest first): `--cli` > `--tui`/`HERMES_TUI=1` > config
`display.interface` > classic REPL. Two resolvers enforce it:

  * `_resolve_use_tui(args)` — the args-aware resolver used by `cmd_chat`
    and the Termux fast-TUI path (uses full load_config()).
  * `_wants_tui_early(argv)` — a dependency-free early resolver used by
    mouse-residue suppression and the Termux fast paths, which run before
    argparse / hermes_cli.config are importable (minimal cached YAML read).

Both `--cli` and `--tui` are registered via `_inherited_flag`, so they are
carried across self-relaunch automatically.

- config: add display.interface ("cli" default), bump _config_version 25->26.
  The generic missing-field migration + load_config() deep-merge seed the key
  for existing configs; no bespoke migration block needed.
- docs: document --cli flag and display.interface in cli-commands.md and
  the TUI user guide.
- tests: new test_default_interface_resolution.py covering resolver
  precedence at every layer, early resolver edge cases (missing/garbage
  config), parser flags, and relaunch inheritance.
2026-06-02 20:49:44 -05:00
brooklyn!
7d0246ab57 Merge pull request #37745 from xxxigm/fix/macos-mic-entitlement-inherit
fix(desktop): inherit microphone entitlement for macOS helpers (#37718)
2026-06-02 20:43:05 -05:00
Vinoth
ae5b2de2fa fix: expand skill bundles in cron jobs 2026-06-02 18:39:28 -07:00
teknium1
1e047677a5 chore: add leonardsellem to AUTHOR_MAP for PR #37405 2026-06-02 18:29:08 -07:00
Leonard Sellem
6ed9a2de8f fix(dashboard): allow desktop websocket origins on remote binds 2026-06-02 18:29:08 -07:00
brooklyn!
54343bcade Merge pull request #37738 from NousResearch/bb/statusbar-model-menu
feat(desktop): inline model picker in the status bar
2026-06-02 20:00:39 -05:00
Brooklyn Nicholson
b6945ce772 fix(desktop): switch model on keyboard activation of picker rows
The model row is a Radix sub-trigger (no onSelect), so switching was
pointer-only. Wire Enter/Space alongside onClick so keyboard users can switch
models too.
2026-06-02 19:50:55 -05:00
brooklyn!
591c329f15 Merge pull request #37739 from NousResearch/bb/desktop-macos-install-forward
fix(desktop): adopt existing macOS install + auto-place app
2026-06-02 19:49:05 -05:00
Brooklyn Nicholson
afec339e96 docs(desktop): sync marker schema comment + default dock note arg
Address Copilot review: document the `adopted` flag and nullable `pinnedCommit`
in the marker schema comment, and default `done(note = {})` so the dock-pinned
marker write is unambiguous (object spread of undefined was already a no-op, but
explicit is clearer).
2026-06-02 19:42:59 -05:00
Brooklyn Nicholson
d704df2d6e fix(desktop): roll back optimistic model switch on failure
selectModel snapshots the prior model/provider and restores the store +
query cache when the backend switch fails, so the UI never shows a model the
backend didn't actually select.
2026-06-02 19:40:42 -05:00
xxxigm
39933f758b test(desktop): assert macOS device entitlements are inherited
Pin #37718: the inherit plist must grant audio-input, every device.*
entitlement on the main app must also be inherited by the Helper/Setup
processes, and both entitlement files must stay valid plists.
2026-06-03 07:32:00 +07:00
xxxigm
21e172b94a fix(desktop): inherit microphone entitlement for macOS helpers
Add com.apple.security.device.audio-input to entitlements.mac.inherit.plist.
Under hardenedRuntime the Electron Helper/Setup processes inherit this file,
and the missing entitlement made macOS TCC deny the microphone with no prompt,
breaking voice chat.

Fixes #37718
2026-06-03 07:32:00 +07:00
ethernet
46e513ef51 fix(desktop): configure Linux Electron sandbox helper
Electron's chrome-sandbox helper must be root:root 4755 on Linux or the
sandboxed renderer aborts before the desktop app starts. The existing
installer only searched for macOS .app bundles, so a successful Linux
build was reported as missing.

Changes:
- Add _desktop_linux_sandbox_fixup() to hermes_cli/main.py, called
  before launching a packaged desktop app on Linux.
- Use lstat() + S_ISREG check to reject symlinks — chown/chmod on a
  symlink target would set SUID on an arbitrary path.
- Update install.sh to recognize Linux unpacked artifacts and configure
  chrome-sandbox with proper error handling (the original PR silently
  ignored chown/chmod failures).
- Add regression tests: normal fixup flow, symlink rejection, and
  already-configured skip path.

Closes #37529 (rebased, merge conflicts resolved, copilot review
feedback addressed).
2026-06-02 20:30:13 -04:00
Brooklyn Nicholson
1daecfa4b0 fix(desktop): write Dock tile as a file-reference URL
The Dock stores persistent-apps as type-15 file:// URLs; the type-0/raw-path
tile we wrote was silently dropped on the next Dock restart (so the pin never
took, yet we'd stamped the marker and never retried). Use pathToFileURL + type
15 and flush prefs through cfprefsd before `killall Dock`. Verified end-to-end
on a packaged build: move -> adopt -> Dock tile lands as
file:///Applications/Hermes.app/.
2026-06-02 19:30:06 -05:00
ethernet
4a626ed187 fix(tests): add _patch_managed_uv autouse fixture to uv-dependent test files
Production code now uses ensure_uv()/update_managed_uv() from
managed_uv.py instead of shutil.which("uv") directly. Tests that
patched shutil.which to control uv availability no longer controlled
the actual code path, causing CI failures.

Add an autouse _patch_managed_uv fixture to test_update_autostash.py
and test_uv_tool_update.py (matching the existing fixture in
test_cmd_update.py). The fixture makes managed_uv functions delegate
to shutil.which so existing test patches flow through naturally.
2026-06-02 20:29:54 -04:00
ethernet
4df280d511 refactor(uv): single managed-uv path, delete fts5 installer escalation
Replace the multi-path UV resolution chain (PATH probing, conda guards,
5-location trust ordering, temp-dir fallback installs) with a single
managed uv binary at $HERMES_HOME/bin/uv. Every code path that needs
uv resolves it from that one location; if missing, ensure_uv()
bootstraps it via the official standalone installer.

Key changes:

- New hermes_cli/managed_uv.py: managed_uv_path(), resolve_uv(),
  ensure_uv() (returns (path, freshly_bootstrapped) tuple),
  update_managed_uv(), rebuild_venv(), installer internals.
- hermes_cli/main.py: replace all shutil.which('uv') with ensure_uv(),
  add venv rebuild on first-time managed uv bootstrap, update_managed_uv
  before dep install on all 3 update paths.
- scripts/install.sh: install_uv() always installs to
  $HERMES_HOME/bin/uv; delete ensure_fts5, _python_has_fts5,
  _reinstall_python_with_fts5, _warn_no_fts5 (61 lines).
  Managed uv always installs current Python with FTS5.
- scripts/install.ps1: Install-Uv always installs to
  $HermesHome\bin\uv.exe; Resolve-UvCmd checks managed location first.
- hermes_state.py: simplified FTS5 warning now suggests 'hermes update'
  as the fix instead of blaming install method.
- tests: 15 tests in test_managed_uv.py, autouse _patch_managed_uv
  fixture in test_cmd_update.py.

Closes #37605, Closes #37622
2026-06-02 20:29:54 -04:00
ethernet
a51a7b9b92 fix(node/nix): consolidate workspace lockfile + update all consumers
Consolidate per-package package-lock.json files into a single root-level
workspace lockfile.  Update all consumers:

- Nix: shared src/npmDeps/npmDepsHash in lib.nix; devshell hook stamps
  package.json paths then runs npm ci from root; individual .nix files
  use mkNpmPassthru attrs instead of per-package fetchNpmDeps.
- Python CLI: new _workspace_root() helper so _tui_need_npm_install,
  _make_tui_argv, _build_web_ui resolve lockfile/node_modules from the
  workspace root.
- Desktop: replace --force-build/mtime heuristic with content-hash build
  stamp (_compute_desktop_content_hash via pathspec).  Remove --force-build
  flag.
- Dockerfile: single root npm install; no per-directory lockfile copies.
- CI: nix-lockfile-fix and osv-scanner reference root package-lock.json;
  apps/dashboard → apps/desktop.
- Tests: new test_tui_npm_install.py; desktop stamp tests in
  test_gui_command.py; updated assertions in test_cmd_update.py,
  test_web_ui_build.py, test_dockerfile_pid1_reaping.py.
- Docs: remove --force-build from desktop flag table.

Deleted: apps/desktop/package-lock.json, ui-tui/package-lock.json,
ui-tui/packages/hermes-ink/package-lock.json, web/package-lock.json.
2026-06-02 20:28:18 -04:00
Brooklyn Nicholson
115671ae6b fix(desktop): address Copilot review on model picker
- selectModel reports success; edits bail (and roll back) instead of landing
  on the previously active model when a switch fails
- Fast toggle stays available to turn off a carried-over speed param even when
  the new model has no native fast mechanism
- active row's "Fast" label derives from the same fastControl as the submenu
  toggle, so it's consistent and handles standalone `-fast` model ids
2026-06-02 19:28:11 -05:00
Fearvox
01eaba7061 polish(gateway): address Copilot review comments on fd-leak fix
Seven Copilot inline review comments on #37679, four worth landing
in a polish pass before merge:

1. _dispose_unused_adapter signature: 'BasePlatformAdapter' ->
   'BasePlatformAdapter | None'. The function explicitly handles
   None and the reconnect watcher calls it with None in the
   except arm, so the annotation now matches the actual contract.

2. (duplicate of #1 on a different line) — same fix.

3. except Exception in _dispose_unused_adapter — the reviewer
   asked about asyncio.CancelledError swallowing. On Python 3.8+
   (Hermes requires 3.13, see pyproject.toml), CancelledError
   inherits from BaseException, NOT Exception, so the existing
   'except Exception' does NOT swallow task cancellation. Added
   an explicit comment explaining the contract so future readers
   don't repeat the analysis. We don't re-raise because the
   watcher loop intentionally treats dispose failures as
   best-effort: a failed dispose on an unowned adapter should not
   take down the watcher that's keeping the gateway alive.

4. _response_store = None after close in api_server.py — the
   reviewer flagged this for idempotency. Decided to keep the
   non-None state intentionally: setting it to None cascades
   to ~9 callers that access self._response_store without a
   None check, and 'close() is idempotent on a closed sqlite3
   Connection' means the current code is already safe. The
   type stays stable; LSP doesn't flag a cascade of
   reportOptionalMemberAccess errors. (This matches the
   pre-existing pattern in the codebase — e.g.
   _mark_disconnected doesn't reset state to None either.)

5. _build_adapter_with_store: reviewer worried about
   disconnect() failing on the self.name property if
   __init__ wasn't called. Already handled: we set
   'adapter.platform = Platform.API_SERVER' so the
   'self.platform.value.title()' property returns
   'Api_Server' without raising. The exception-swallowing
   branch in disconnect() does call self.name via the
   logger.debug format, so this is a real path that needs
   the platform attribute, and we have it.

6. test_disconnect_closes_response_store: bare 'pytest.raises(Exception)'
   -> 'pytest.raises(sqlite3.ProgrammingError)'. The bare
   Exception matcher would silently accept AttributeError,
   OperationalError, env-related issues, etc. The specific
   exception type ('Cannot operate on a closed database') is
   the actual signal we want — proves the SQLite conn is
   closed, not just that *something* raised.

7. test_nonretryable_failure_disposes_unowned_adapter:
   assertion tightened from '>= 1' to '== 1' on
   adapter._disconnect_calls. The docstring said 'exactly once',
   the assertion now matches. Catches the hypothetical
   'watcher disposes the same adapter twice' regression that
   '>=' would have missed.
2026-06-02 17:27:44 -07:00
Fearvox
7982560845 fix(release): add fearvox1015@gmail.com -> Fearvox to AUTHOR_MAP
The check-attribution CI job on #37679 failed because the commit
author email nolan@0xvox.com (a local git config mistake on this
machine) is not in scripts/release.py AUTHOR_MAP. The commit
itself is now re-authored to fearvox1015@gmail.com, and this
follow-up adds the entry to AUTHOR_MAP so any future commits
authored from this email also pass the check.
2026-06-02 17:27:44 -07:00
Fearvox
4b06c98fe4 fix(gateway): close ResponseStore + dispose unowned adapter on reconnect failure
Three separate code paths in the gateway's platform reconnect loop
leaked file descriptors every retry, exhausting the default 2560-fd
ulimit in ~12 hours of continuous failure and turning the gateway
into a zombie that raises OSError: [Errno 24] on every open() (#37011).

Root cause:
  * APIServerAdapter.__init__ opens a ResponseStore SQLite connection
    that holds 2 fds (db file + WAL sidecar).
  * APIServerAdapter.disconnect() previously only stopped the aiohttp
    web server — the ResponseStore connection was never closed.
  * The reconnect watcher in _platform_reconnect_watcher constructs a
    fresh adapter on every retry attempt. When the connect call fails
    (3 paths: non-retryable error, retryable error, exception during
    connect) the adapter is dropped without ever being installed on
    self.adapters, so nothing else calls its disconnect(). Result: the
    2 ResponseStore fds stay open until GC sweeps the unreachable
    object, which Python's cyclic GC does not do promptly for
    asyncio-bound native handles.

  2 fds × 1 retry × (3600s / 300s backoff cap) ≈ 12 fds/hour.
  2560 fds / 12 fds/hr ≈ 12h to ulimit exhaustion.

Fix:

  * APIServerAdapter.disconnect() now also calls
    self._response_store.close() (with a try/except so a SQLite
    close failure doesn't abort the aiohttp teardown).
  * New module-level helper _dispose_unused_adapter(adapter) in
    gateway/run.py that calls adapter.disconnect() and swallows
    any exception (so half-constructed adapters whose __init__
    crashed don't kill the watcher loop).
  * _platform_reconnect_watcher calls _dispose_unused_adapter() in
    all three failure paths: non-retryable, retryable, and the
    except Exception arm. adapter = None is initialized
    before the try so the except arm can see the partial
    construction.

Tests:

  * New file tests/gateway/test_platform_reconnect_fd_leak.py with
    7 regression tests covering all three failure paths, the
    _dispose_unused_adapter helper (None + raising-disconnect cases),
    and the APIServerAdapter ResponseStore close behavior (success +
    close-exception cases). The _CountingAdapter fixture tracks
    disconnect() invocations and an _open_fds counter that is
    decremented on dispose, so the assertion is the literal
    observable behavior of the leak.

Refs:
  - Closes #37011 (the original fd-leak report)
  - Supersedes #37018, #37110, #37238, #37260, #37394 (7 competing
    open PRs all addressing the same root cause from different angles;
    none of them rebased cleanly against current main, and none
    covered all three failure paths in one fix with regression tests
    for both the watcher and the platform-level close behavior)
2026-06-02 17:27:44 -07:00
Teknium
ab2472e692 fix(aux): self-heal Nous-routed calls when a pinned model leaves the catalog (#37732)
A long-lived process (gateway, watcher) caches the Nous Portal's
recommended-models payload and can pin a model for its whole lifetime.
When that model is later dropped from the Nous -> OpenRouter catalog,
every auxiliary call 404s with 'model does not exist in our
configuration or OpenRouter catalog' until the process restarts.

Now such a 404 force-refreshes the Portal recommendation and retries
once with the current pick (or the gemini-3-flash-preview default).
Scoped to Nous-routed calls only.

- _is_model_not_found_error(): 404/400 'not found / does not exist /
  not a valid model' predicate, excludes billing keywords so it never
  overlaps _is_payment_error.
- _refresh_nous_recommended_model(): force-refresh fetch, returns a
  model distinct from the one that failed, else the known-good default.
- Wired into both call_llm and async_call_llm error chains.
2026-06-02 17:14:36 -07:00
Brooklyn Nicholson
7466182179 fix(desktop): adopt existing macOS install + auto-place app
First-launch "already installed?" hinged solely on a marker that only the
desktop's own bootstrap writes, so a runtime from `install.sh --include-desktop`
(or a DMG launch over a prior CLI install) was runnable yet markerless and got
the WHOLE installer re-run on top of it. Detect a runnable ACTIVE_HERMES_ROOT
(valid source + venv), adopt it (stamp the marker, recording HEAD), and forward
straight to the app. Repair keeps forcing a real re-bootstrap.

Also: on first packaged macOS launch relocate the bundle into /Applications
(Electron relaunches from there) and pin the canonical copy to the Dock once,
so users stop re-opening the installer from Downloads/the DMG.
2026-06-02 19:11:05 -05:00
Brooklyn Nicholson
ea4fe15631 feat(desktop): inline model picker in the status bar
Replace the status-bar model chip's modal with a Cursor-style dropdown:
- providers grouped by name in a stable order (no recency reshuffle on select)
- per-model hover-Edit submenu for reasoning effort + fast, gated by per-model
  capabilities now surfaced in the model.options payload
- unified Fast toggle: flips the speed=fast param where supported, else swaps
  to the model's `-fast` variant (base and variant collapse into one row)
- localStorage-backed "Edit Models" dialog to choose which models appear

Adds reusable dropdown primitives (DropdownMenuSearch, shared row/label
tokens, portaled + collision-aware submenus) and reads session state from
nanostores rather than prop-drilling, so editing options doesn't rebuild and
close the menu.
2026-06-02 19:09:41 -05:00
Teknium
bb1c8b6f1a test(honcho): de-flake prewarm smoke test's thread wait (#37614)
TestDialecticLifecycleSmoke._await_thread did a single join(timeout=3.0) and
then proceeded regardless of whether the background dialectic thread had
finished. On a loaded CI runner (6 parallel test slices) the prewarm thread's
completion can slip past that 3s window, so the join times out silently and the
test reads _prefetch_result before the worker wrote it — the intermittent
'session-start prewarm must land in _prefetch_result' failure.

Join in a loop up to a 30s ceiling and assert the thread is actually dead, so a
genuine hang surfaces as a clear failure instead of a timing race. Reproduced
the old failure deterministically (5/5 fails with a 3.5s prewarm delay) and
confirmed the fix (0/8) before/after.
2026-06-02 17:00:04 -07:00
teknium1
082025abcd fix(gateway): route /background result media by type
Background-task (/background, /btw) result media now routes to the
type-specific sender — TTS clip → voice bubble, video → send_video,
image → send_image_file — instead of forcing everything through
send_document. Mirrors the streaming + kanban delivery paths and
reuses base.should_send_media_as_audio for the Telegram OGG nuance.

Co-authored-by: LJ Li <liliangjya@gmail.com>
Co-authored-by: Kolektori <256073454+Kolektori@users.noreply.github.com>
2026-06-02 16:55:25 -07:00
brooklyn!
30a7a94120 Merge pull request #37697 from NousResearch/bb/grok-provider-desktop
feat(desktop): make xAI Grok a first-class OAuth provider in the launcher
2026-06-02 18:43:31 -05:00
Brooklyn Nicholson
123b945731 Merge remote-tracking branch 'origin/main' into bb/grok-provider-desktop 2026-06-02 18:41:32 -05:00
ethernet
cbc82511ea fix(web-server): move event channel state from module globals to app.state (#37683)
Module-level asyncio.Lock() binds to whatever event loop was active at
import time.  When the same web_server module is reused across multiple
TestClient instances (or across uvicorn reloads), the old lock still
references a defunct loop, causing 'attached to a different loop' errors
and flaky subscriber-registration races in CI.

Replace the module-level _event_channels dict + _event_lock with:
  - _lifespan() async context manager that creates both on the running
    event loop during FastAPI startup (guaranteed correct loop binding)
  - _get_event_state() lazy accessor that initialises on app.state when
    TestClient is used without a `with` block (preserves backward compat)

All call sites (_broadcast_event, /api/pub, /api/events) now receive the
app reference and read state via _get_event_state(app) instead of the
module globals.  The test polling loop is updated to check
app.state.event_channels rather than the removed module attribute.
2026-06-02 18:40:12 -05:00
Brooklyn Nicholson
a13db76eaa fix(desktop): signal loopback worker to stop on cancel
Shutting down the callback server stopped the serve thread but left the
worker spinning in _xai_wait_for_callback (which polls callback_result)
until the timeout. Flag callback_result as cancelled on DELETE so the
wait returns promptly and the daemon thread exits — avoids thread
buildup on repeated cancel/retry.
2026-06-02 18:28:24 -05:00
Brooklyn Nicholson
33807e2b14 fix(desktop): use auth-store path as xAI OAuth source_label
source_label is meant to be a human-readable origin (file path / source),
not the internal auth_mode string ("oauth_pkce"). Surface the auth-store
path, then the source slug, then a generic label.
2026-06-02 18:21:17 -05:00
ethernet
a429a2a0bf ci(nix): fold package+devShell builds into flake check
Add build-package and build-devshell as cross-platform check
derivations so nix flake check verifies the default package and
devShell build on every platform (including darwin, which previously
only did eval-only checks).

This lets us drop the separate nix build step from the CI workflow
and removes the macOS-only eval fallback — a single nix flake check
now covers builds + runtime checks on all runners.
2026-06-02 19:14:18 -04:00
Brooklyn Nicholson
d963ad56c1 fix(desktop): address second Copilot pass on xAI loopback flow
- onboarding: openSignInUrl now falls back to window.open when the desktop
  bridge's openExternal throws/rejects (OS handler missing, user denied),
  not just when the bridge is absent
- web_server: cancelling a loopback session shuts down the 127.0.0.1
  callback server + joins its thread immediately, freeing the port instead
  of holding it until the wait times out (+ regression test)
- web_server: document the new "loopback" flow in the /api/providers/oauth
  enum, the poll-endpoint docstring, and the Phase 2 flow comment block
2026-06-02 18:14:00 -05:00
Brooklyn Nicholson
3be9fb7317 fix(desktop): address Copilot review on xAI loopback flow
- web_server: join the callback-server thread in the start error path so a
  failed discovery/URL build doesn't leave a daemon thread running
- web_server: loopback worker now bails if the session was cancelled while
  waiting for the callback or exchanging the code, instead of persisting
  tokens the user no longer wants (+ regression test)
- onboarding: fall back to window.open when the desktop bridge's
  openExternal is unavailable, so the flow never silently stalls
2026-06-02 17:55:22 -05:00
Brooklyn Nicholson
63e824831c fix(desktop): order xAI Grok after MiniMax in the OAuth catalog 2026-06-02 17:36:39 -05:00
Brooklyn Nicholson
dd5e97bd7f feat(desktop): make xAI Grok a first-class OAuth provider in the launcher
xAI Grok was only reachable via the "I have an API key" form. xAI's
OAuth (SuperGrok / Premium+) flow already exists in the backend
(`hermes auth add xai-oauth`) but was never surfaced in the desktop
onboarding launcher.

Add a loopback PKCE flow: the local backend binds the 127.0.0.1
callback listener, the client opens the browser, and the redirect lands
back automatically — no code to copy/paste. Reuses the existing xAI
OAuth helpers (discovery, callback server, token exchange, persist)
rather than duplicating them.

- web_server: catalog entry (flow: loopback) + status dispatch +
  _start_xai_loopback_flow + background worker + route branch
- desktop: 'loopback' flow type, awaiting_browser status, xAI Grok card
  (PROVIDER_DISPLAY / FLOW_SUBTITLES / FlowPanel waiting render)
- tests: catalog listing, start authorize-url, worker persist, state
  mismatch rejection
2026-06-02 17:34:00 -05:00
ethernet
c47b9d126f Merge pull request #37597 from NousResearch/ethie/desktop-linux-install
feat(desktop): content-hash build stamp, --build-only / --force-build flags
2026-06-02 16:51:44 -04:00
Austin Pickett
ac76bbe21f fix(desktop): triage batch of GUI quality-of-life fixes (#37536)
* fix(desktop): triage 24 GUI quality-of-life fixes across sidebar, composer, tool cards, messaging, and platform plumbing

A grab-bag of high-leverage UX fixes plus a few backend touches that the
GUI needs to behave correctly on Windows.

Sidebar / sessions
- Decrement $sessionsTotal on delete + archive so "Load N more" stops
  claiming removed rows are still on the server.
- Hide the "Group by workspace" toggle when no unpinned sessions exist.
- Accept Cmd/Ctrl+N as a "new session" accelerator (in addition to bare
  Shift+N), and render the kbd hint per-platform.
- Switch the statusbar to overflow-x-clip so untitled sessions don't
  paint a horizontal scrollbar at the bottom of the window.

Messaging + Cron
- Add [-webkit-app-region: no-drag] to the page-search input so clicks
  reach the field instead of routing to the OS window-drag handler.
- Replace single-letter PlatformAvatar with brand glyphs from
  @icons-pack/react-simple-icons (telegram, discord, matrix, signal,
  whatsapp, mattermost, wechat, qq, ...). Letter monogram fallback for
  Slack / Dingtalk / Feishu / WeCom (removed from Simple Icons at brand
  owner request).
- Drop the duplicate "Create first cron" button in the empty state.

Composer
- Dedupe pasted images by (name, size, lastModified, type) instead of
  Blob identity; Chromium hands us the same screenshot via both
  clipboard.items and clipboard.files with fresh File instances.
- Enable spellcheck on the contentEditable, configure Chromium's
  spellchecker with the system locale on whenReady, and add
  replaceMisspelling + "Add to dictionary" entries to the context menu.
- Render user messages through a minimal markdown pipeline (inline
  backtick code + fenced ``` blocks) while keeping @file:/@image:
  directive chips intact.
- max-h-[60vh] overflow-y-auto + collisionPadding on the prompt-snippet
  submenu.
- Bake cursor-pointer into the <Button> primitive (with
  disabled:cursor-default) and into titlebarButtonClass.

Dialogs + tabs + version
- Default DialogContent now has max-h-[85vh] overflow-y-auto so long
  bodies scroll instead of falling off-screen.
- Right-rail preview tabs close on middle-click (button === 1), with an
  onMouseDown swallow to suppress Chromium autoscroll.
- New refreshDesktopVersion() helper called from About mount, after
  every update check, and on throttled window focus so About reflects
  the just-installed binary.

Keys + Artifacts + Terminal
- Drop the global "Show advanced" toggle in KeysSettings. Provider
  groups now default-expand when they have any key set.
- Extend openExternalUrl to handle file:// via shell.openPath, with
  showItemInFolder fallback when the OS can't open the file.
- New lib/ansi.ts SGR parser + <AnsiText> component, applied to
  terminal/execute_code tool output.
- ToolView gained stdout / stderr / rendersAnsi; tool-fallback renders
  the two streams as separate labeled blocks with stderr in a neutral
  tone (not destructive — many CLIs log info on stderr).
- Drop 'stderr' from ERROR_MSG_KEYS in tool-result-summary.

Paths + platform
- resolveHermesCwd skips process.cwd() when packaged and prefers a
  user-configurable default project directory.
- New hermes:setting:defaultProjectDir:{get,set,pick} IPC handlers +
  preload bridge + global.d.ts typing + a "Default project directory"
  row in Sessions settings.
- FileOperations.delete_path(path, recursive=True) on the abstract
  base; ShellFileOperations.delete_file rewritten to run a cross-
  platform python3 -c snippet so deletes work on Windows shells (which
  have no rm/rm -rf). Fallback to `python` when `python3` isn't on PATH.
- README troubleshooting block split into macOS/Linux + Windows
  PowerShell recipes.
- Tightened renderer favicon links in index.html + added color-scheme
  and theme-color meta.

Backend lifecycle (renderer-side mitigation)
- New noteSessionActivity() heartbeat + session.ts watchdog: an
  8-minute silence on the stream auto-clears stuck $workingSessionIds
  entries so "Session Busy" never gets permanently wedged. Wired into
  useSessionStateCache so every state update refreshes the timer.

i18n spike
- docs/desktop-i18n-rfc.md scoping a future language-switcher PR
  (recommends react-intl, audits IME/RTL/CJK in the composer +
  chat bubbles, 4-PR rollout plan, ~3-4 eng-weeks for the first
  non-English locale).

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): replace native OS scrollbar in portaled dropdown menus

Radix's DropdownMenuPrimitive.Portal renders content under document.body,
outside the `.scrollbar-dt` scope on #root. Whenever a menu's max-height
clipped its content (even by a pixel — common for the composer "+" menu
that opens upward near the bottom of the window), the user saw the OS's
chunky native scrollbar painted across the whole menu.

Bake a thin, slot-styled scrollbar onto DropdownMenuContent and
DropdownMenuSubContent via [scrollbar-width:thin] + WebKit pseudo-element
arbitrary variants. The submenu also gets a max-h tied to
--radix-dropdown-menu-content-available-height so long snippet lists scroll
cleanly instead of running off the bottom of the viewport. Drop the now-
redundant max-h-[60vh] override on the prompt-snippet submenu.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): unbork dropdown menu — submenu opens, parent isn't a circle

Two regressions from the previous dropdown-scrollbar fix:

- The parent menu rendered as a rounded oval. Long Tailwind v4 arbitrary-
  variant strings like [&::-webkit-scrollbar-thumb]:rounded-full inside a
  cn() call were being mis-resolved so the `rounded-full` leaked onto the
  menu container itself. Replaced the whole tower of arbitrary variants
  with a real `.dt-portal-scrollbar` class in styles.css that mirrors what
  `.scrollbar-dt` already does for #root descendants. Plain CSS, no Tailwind
  parser ambiguity.
- The Prompt snippets submenu didn't open. Radix publishes
  --radix-dropdown-menu-content-available-height on Content but NOT on
  SubContent, so the `max-h` bound to that variable computed to 0 and the
  submenu collapsed to zero height. Switched SubContent to a fixed
  max-h-80 (≈20rem) which is plenty for a snippet list and never collapses.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): promote prompt snippets from Radix submenu to a real Dialog

The submenu refused to open when the parent dropdown was anchored at the
bottom of the window (composer "+" button) — Radix's collision detection +
SubContent positioning was fighting us. Rather than keep tuning side /
sideOffset / collisionPadding / max-h until something stuck, replace the
DropdownMenuSub with a clicked DropdownMenuItem that opens a proper
Dialog.

Side benefits over the submenu:
- Each snippet gets a description line, so a glance is enough to pick one.
- Focus management is handled by Dialog automatically.
- Easy to grow (search, custom user snippets, categories) without
  another round of Radix positioning bugs.

Also extract types/interfaces to the bottom of the file per workspace
convention.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): move cron 'New cron' button off the top bar into the body

Reverses the previous direction on cron empty-state dedup. The body
button is more discoverable for first-time users (it's anchored next to
the "No scheduled jobs yet" copy that explains the feature) and frees
the top bar from a global CTA that wasn't pulling its weight.

- Empty (zero jobs): EmptyState renders the "Create first cron" button
  again, like the original design.
- Empty (search filtered out all jobs): no button, just "Try a broader
  search query" copy.
- Has jobs: small inline header above the list shows `N/M active` plus
  a single "New cron" button (right-aligned). The rows themselves
  already cover edit/pause/trigger/delete, so this is the only "create"
  affordance.

Also drop the dead `<div className="hidden">…</div>` enabledCount line
the previous patch left behind; the count is now visible in the new
header instead of hidden.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop): address Copilot review on PR 37536

- sessions-settings: guard the WHOLE bridge call rather than chaining
  `?.settings.foo().then(...)` — the latter throws when
  `window.hermesDesktop` is undefined (non-Electron / Vitest contexts)
  because the chain short-circuits to `undefined.then(...)`.
- file_operations: drop `Path.unlink(missing_ok=True)` (Py>=3.8) so the
  generated delete snippet still works on remote backends running
  Python 3.7. The existing FileNotFoundError handler covers the same
  case and works back to 3.4.
- ansi.test.ts: add focused Vitest coverage for the SGR parser
  (basic/bright colors, bold toggles, default-fg reset, coalescing,
  256-color / truecolor arg consumption, non-SGR CSI drop, empty SGR
  full-reset) so future refactors can't silently regress terminal
  rendering.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(desktop/updates): swallow refreshDesktopVersion bridge errors

`refreshDesktopVersion()` is called best-effort with `void` from
`checkUpdates()`, `startUpdatePoller()`, and the window focus handler.
If the IPC bridge rejects (main process shutting down during reload,
bridge not yet ready on first paint), the rejection surfaces as an
unhandled promise rejection in the renderer. Wrap the call in try/catch
and return null on failure so callers can keep the existing
fire-and-forget pattern safely.

Co-authored-by: Cursor <cursoragent@cursor.com>

* chore(desktop): drop work duplicated by other in-flight PRs

- composer/text-utils.ts: revert paste-image dedupe — PR #37596
  ships the same fix with a cleaner content-key approach and a
  Vitest file (text-utils.test.ts). Letting that PR own the change.
- docs/desktop-i18n-rfc.md: delete the i18n scoping RFC — PR #37568
  has already shipped a working i18n surface (homegrown nanostores
  `t()` helper over en/zh dictionaries), so the RFC's framework
  recommendation (`react-intl`) is now obsolete and would just
  contradict the implementation that's actually landing.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-02 16:33:22 -04:00
brooklyn!
31c40c72c0 fix(desktop): stabilize project folder sessions (#37586)
* fix(desktop): stabilize project folder sessions

Keep desktop folder selection aligned with new sessions and scope TUI gateway cwd through session context so prompts and tools resolve against the selected workspace.

* fix(desktop): address review feedback on folder sessions

Snapshot sessions before iterating to avoid concurrent-mutation crashes,
optional-chain the revealLogs catch, and read console-message args from
the correct Electron event/messageDetails positions.

* fix(desktop): address second review pass on folder sessions

Sync the remembered workspace key with the cwd atom (clear on empty),
only load tree children for real directory nodes, and throttle renderer
auto-reloads so a deterministic startup crash can't loop forever.

* fix(desktop): inherit parent workspace for ephemeral agent tasks

Background and preview tasks use ephemeral ids absent from the session
map, so pass the parent session cwd into the session context explicitly
instead of clearing it back to the gateway launch dir. Also correct the
set_session_vars docstring about clear_session_vars semantics.

* fix(desktop): validate preview cwd before pinning session context

A non-empty but non-existent client cwd would pin an unusable override
and silently fall back to the launch dir. Validate once, reuse for both
the session context and the terminal override, and fall back to the
parent session workspace when invalid.

* fix(desktop): harden preview cwd normalization and adopt normalized cwd

Guard preview cwd normalization against malformed client paths so a bad
input can't fail the whole restart, and adopt the backend's normalized
config.get cwd in the no-active-session path so the persisted workspace
stays consistent with what the agent uses.
2026-06-02 20:23:09 +00:00
Teknium
79bfddd37c fix(models): restore gemini-3-flash-preview to Gemini OAuth picker (#37606)
#37046 swapped gemini-3-flash-preview -> gemini-3.5-flash in the
google-gemini-cli (OAuth/Code Assist) picker on the premise that the
preview slug was renamed. It wasn't. Per gemini-cli's models.ts, Code
Assist serves two distinct flash slugs with different access gates:
gemini-3-flash-preview (PREVIEW_GEMINI_FLASH_MODEL — what subscription/
free-tier OAuth users reach) and gemini-3.5-flash
(DEFAULT_GEMINI_3_5_FLASH_MODEL — GA-channel-gated). The model string is
passed verbatim into the {project, model, ...} envelope sent to
cloudcode-pa.googleapis.com, so non-GA users got a hard error on every
prompt because gemini-3.5-flash 404s for them.

Offer both slugs in the OAuth picker (matching gemini-cli's own /model
list) so non-GA users can select the preview flash that works. The
gemini (API-key), OpenRouter, and Nous lists are untouched —
google/gemini-3.5-flash is a real live model on those surfaces.
2026-06-02 12:49:19 -07:00
ethernet
c2050183a5 feat(desktop): content-hash build stamp with --build-only and --force-build flags
Add a SHA-256 content-hash based build stamp to `hermes desktop` so
unchanged source trees skip the npm install + build step. Uses pathspec
for .gitignore-aware file matching instead of a hardcoded skip-list.

New CLI flags:
- --build-only: run the build but don't launch the app
- --force-build: rebuild even when the stamp matches

`hermes update` now calls `hermes desktop --build-only` so the
desktop app is rebuilt (if needed) as part of the update flow.

16/16 tests passing.
2026-06-02 15:45:30 -04:00
brooklyn!
b34ee80741 feat(installer): rename macOS installer to "Hermes" and make it a launcher (#37516)
* feat(installer): rename macOS installer to "Hermes" and make it a launcher

The bootstrap installer was branded "Hermes Setup" and always re-ran the full
install flow on every open — so the /Applications app said "Setup" and couldn't
double as a way to relaunch Hermes (the real desktop app lives in ~/.hermes,
not /Applications, with no Dock/Launchpad entry).

Two changes, macOS-focused:

1. Rename the installer's user-visible name to "Hermes" (productName, window
   title, shortDescription, document title). Bundle id stays
   com.nousresearch.hermes.setup (distinct from the desktop app's
   com.nousresearch.hermes); the on-disk staged updater name (hermes-setup) is
   unchanged, so the desktop's update hand-off still resolves it.

2. Launcher fast path: on a bare ("Install") launch, if Hermes is already
   installed (bootstrap-complete marker + a built desktop app on disk), skip the
   installer UI entirely and relaunch the desktop app, then exit. First run still
   installs; Update mode and fresh/repair installs still show the UI. The window
   now starts hidden ("visible": false) and is revealed only when the UI is
   actually needed, so the launcher path never flashes a window.

Net UX: one "Hermes" in /Applications you can pin to the Dock — first click
installs, every later click opens the app instantly (same icon throughout, so
the Dock stays seamless). Nothing pins to the Dock permanently; the app shows a
normal Dock icon only while running.

Windows naming is intentionally left as-is in this change (scope: macOS).

* fix(installer): gate launcher fast path to macOS + log window-show failures

Address review feedback:
- Gate the already-installed launcher fast path to macOS (cfg!(target_os =
  "macos")). On Windows/Linux the installer keeps its prior behavior, so the
  change is a pure no-op there. This avoids relaunching the desktop app on
  Windows via a spawn that lacks the DETACHED_PROCESS + startup-grace handling
  launch_hermes_desktop uses (which could race the installer's exit).
- Add a brief startup grace before exiting on the mac fast path, mirroring
  launch_hermes_desktop.
- Log (instead of silently ignoring) failures to show the main window, and log
  when the "main" window can't be found, so a no-UI state is diagnosable.

* fix(installer): add --reinstall escape hatch + keep spawn detached on Windows

Address follow-up review:
- Add a `--reinstall`/`--repair` flag that forces the installer UI even when
  Hermes is already installed, so a broken install can be repaired by re-running
  setup instead of the launcher fast path silently relaunching the (possibly
  bad) app.
- Apply DETACHED_PROCESS on Windows in spawn_installed_desktop, mirroring
  launch_hermes_desktop, so the helper stays correct cross-platform even though
  its only caller is macOS-gated today.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* test(installer): unit-test --reinstall/--repair force-setup parsing

Extract the force-setup flag parsing into a unit-testable
`force_setup_from_args` helper (mirrors `AppMode::from_args`) and add tests:
- --reinstall and --repair are recognized
- bare/unrelated args (incl. --update) do not force setup
- the repair flags never affect Install<->Update mode selection

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-02 17:47:34 +00:00
brooklyn!
bb0619dbce fix(auth): align Codex OAuth persistence paths (#37517)
* fix(desktop): codex OAuth onboarding now resolves on fresh install

The desktop codex device-code worker persisted tokens with a hand-rolled
pool.add_entry(), writing only credential_pool.openai-codex. It never set
active_provider, so on a fresh install the onboarding setup.runtime_check
resolved provider "auto", couldn't detect the Codex OAuth session, and raised
"No inference provider configured" — while setup.status (which sniffs the pool)
reported configured. The disagreement surfaced as the onboarding banner
"Connected, but Hermes still cannot resolve a usable provider."

Use the canonical _save_codex_tokens() instead, matching the CLI's
`hermes auth add openai-codex` path and the Nous/MiniMax dashboard workers.
It writes the providers.openai-codex singleton (setting active_provider) and
syncs the pool.

* fix(auth): align Codex OAuth persistence paths

Ensure desktop and CLI Codex OAuth logins both write the canonical provider state so fresh installs resolve a usable runtime provider.

---------

Co-authored-by: teknium1 <127238744+teknium1@users.noreply.github.com>
2026-06-02 12:19:44 -05:00
ethernet
3e6b68252f Merge pull request #37518 from NousResearch/bb/desktop-installer-running-instances
Clarify desktop install retry guidance
2026-06-02 13:13:39 -04:00
ethernet
091ef7d304 Merge pull request #37484 from NousResearch/ethie/gui-docs
fix(docs): update desktop app docs
2026-06-02 13:11:36 -04:00
Brooklyn Nicholson
0c29cfd1a6 Clarify desktop install retry guidance 2026-06-02 12:08:39 -05:00
Austin Pickett
6d14a24b79 feat(dashboard): nous-blue theme, bulk sessions, schedule picker (#37383)
* feat(dashboard): nous-blue theme, bulk sessions, schedule picker

Batch of related dashboard improvements gathered on
austin/fix/dashboard-changes:

* Nous Blue theme — faithful port of the LENS_5I overlay system onto
  the existing DashboardTheme. Lifts the foreground inversion layer to
  z-index 200 to fix the long-standing hover / loading visual artifact,
  adds an explicit swatchColors slot so the theme picker shows the
  post-inversion preview, and migrates the legacy "lens-5i" theme key
  from localStorage / API to "nous-blue" on first read.
* Theme-aware series colors: new --series-input-token /
  --series-output-token CSS vars consumed by Analytics + Models
  charts; ToolCall + ModelInfoCard switched to semantic
  --color-success for diff lines and the Tools capability badge.
* Analytics + Models headers: consolidate period selector + refresh
  next to the page title and drop the redundant period badge.
* Bulk session management — "Delete empty (N)" button + per-row
  checkboxes with shift-click range select and a bulk-delete action
  bar. Backed by SessionDB.delete_sessions() /
  delete_empty_sessions() plus POST /api/sessions/bulk-delete and
  DELETE /api/sessions/empty (registered before the templated
  /api/sessions/{session_id} family so they don't get shadowed).
  Hard cap of 500 IDs per bulk request. Full pytest coverage.
* Cron page — human-readable schedule picker (every-interval / daily
  / weekly / monthly / once / custom) replaces the raw cron
  expression input; the job list now renders "Weekly on Mon, Wed,
  Fri at 14:30" instead of "30 14 * * 1,3,5". English-only ordinals
  for monthly schedules so non-English locales don't get incorrect
  suffixes.
* example-dashboard plugin moved from plugins/ to tests/fixtures/ so
  stock installs no longer ship the demo. Tests install it
  dynamically via a pytest fixture that also reorders the FastAPI
  routes.
* i18n: 40+ new keys for the bulk-select UI and schedule
  picker/describer translated across all 16 locales.

Co-authored-by: Cursor <cursoragent@cursor.com>

* refactor(dashboard): dedupe memory provider picker

The memory provider <Select> lived on both /system and /plugins,
writing the same config.yaml field through two different endpoints
with no cross-page refresh. Remove the picker from /system in favor
of a read-only status row + link to /plugins, where it pairs with
the context-engine picker under "Plugin providers".

/system retains the destructive admin controls (file sizes, Reset
MEMORY.md / USER.md / all). The api.setMemoryProvider client and
PUT /api/memory/provider backend endpoint are left in place for
CLI / script callers.

Co-authored-by: Cursor <cursoragent@cursor.com>

* docs(dashboard): address Copilot review on PR #37383

- Backdrop layer-stack comment claimed LENS_5I-style themes override
  --component-backdrop-bg-blend-mode to multiply, but our only
  LENS_5I-style theme (nous-blue) keeps the default difference.
  Reword to describe what the code actually does and present the
  var as a forward-looking extension hook.
- /api/sessions/bulk-delete docstring promised the response would
  echo back the list of deleted IDs, but the implementation only
  returns {ok, deleted}. Tighten the docstring to match the wire
  format; the client already knows what it asked to delete, so the
  IDs aren't needed.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(dashboard): address copilot review on cron describe + bulk-select checkbox

- schedule.ts: restrict `describeCronExpression` to strictly 5-field cron
  expressions. The backend `parse_schedule` also accepts the 6-field
  `min hour dom month dow year` form, and humanising those by
  destructuring only the first five fields would silently drop the year
  (e.g. ``0 9 * * * 2099`` rendered as "Daily at 09:00"). 6+ field
  expressions now fall through to the raw-string fallback so the user
  sees what's actually scheduled.

- SessionsPage.tsx (SessionRow): wire the bulk-select Checkbox's
  ``onClick`` directly instead of attaching it to a parent ``<span>``
  with a no-op ``onCheckedChange``. Radix forwards onClick to the
  underlying ``<button role=checkbox>``, so the same handler now drives
  both mouse clicks (preserving shift-key state for range select) and
  keyboard activation (Space on the focused checkbox, which the browser
  synthesises as a click on the <button>). Improves a11y / keyboard UX
  without changing the controlled-selection model.

- SessionsPage.tsx: also extend ``SessionRowProps`` with the new
  ``onRename`` / ``onExport`` props introduced on main so the row's
  destructured prop types resolve after the merge.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-02 12:37:40 -04:00
ethernet
7450bee8bc fix(docs): update desktop app docs 2026-06-02 11:52:33 -04:00
ethernet
a6b6afdff4 Merge pull request #36864 from maxmilian/fix/tui-reset-terminal-input-modes-on-exit
fix(cli): reset terminal input modes on TUI exit to stop focus/mouse leaks
2026-06-02 11:30:50 -04:00
brooklyn!
23c0578bd7 Merge pull request #37462 from NousResearch/bb/desktop-update-throttle
fix(desktop): throttle the update-available toast
2026-06-02 10:26:52 -05:00
Teknium
3eb6bd7f92 docs: add Desktop App guide (#37457)
The native Electron desktop app shipped (PR #20059 and follow-ups) but the
docs only told people how to download it, not what it is or how to use it.

Adds website/docs/user-guide/desktop.md covering install (installer +
prebuilt + Windows GUI), the chat-first UI and management panes, the
hermes desktop CLI flag reference, self-update, how-it-works, and
troubleshooting. Sourced from apps/desktop/README.md, routes.ts, and the
real argparse. Wired into sidebars.ts under Interfaces after the TUI.
2026-06-02 08:09:42 -07:00
brooklyn!
f58db77cd0 Merge pull request #37379 from NousResearch/bb/desktop-session-list
feat(desktop): session-list overhaul + cancellable install
2026-06-02 09:56:31 -05:00
brooklyn!
8977bf282e Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-02 09:51:51 -05:00
Brooklyn Nicholson
267e7fd395 Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/desktop-session-list 2026-06-02 09:27:34 -05:00
Brooklyn Nicholson
d183f75ee0 chore: uptick 2026-06-02 09:27:28 -05:00
Brooklyn Nicholson
4239230957 feat(desktop): cancellable first-launch install
The install overlay had no way to stop a running install — the runner already
supported an abortSignal, but nothing drove it. Wire it end to end:

- main.cjs holds an AbortController for the active runBootstrap and aborts it
  on a new hermes:bootstrap:cancel IPC and on app quit, so quitting/cancelling
  mid-install actually kills install.sh/ps1 instead of orphaning it.
- runBootstrap bails before spawning anything if the signal is already aborted.
- Install overlay gains a "Cancel install" button while a bootstrap is active;
  a cancel surfaces the recovery overlay (retry/repair).

Test: electron/bootstrap-runner.test.cjs asserts the already-aborted early
return (no spawn) via `node --test`.
2026-06-02 08:50:45 -05:00
Jeffrey Quesnelle
927fa7a980 Merge pull request #37330 from NousResearch/desktop/consolidate-models-into-settings
refactor(desktop): move model management from Command Center into Settings
2026-06-02 09:43:10 -04:00
Teknium
afea650e16 fix(model-picker): OpenAI shows curated models; OpenRouter no longer phantom-shows (#37404)
The model picker now matches `hermes model` for OpenAI, and OpenRouter
stops appearing as authenticated when only OPENAI_API_KEY is set.

- models.py: provider_model_ids() for the default api.openai.com endpoint
  intersects the live /v1/models dump (120+ entries incl. embeddings,
  whisper, tts, dall-e, moderation, legacy chat) with the curated agentic
  list, preserving curated order. Custom OpenAI-compatible endpoints keep
  the live list verbatim so discovery still works.
- providers.py: drop extra_env_vars=("OPENAI_API_KEY",) from the openrouter
  overlay. list_authenticated_providers reads extra_env_vars to decide
  whether a provider is authenticated, so any OpenAI user saw a phantom
  OpenRouter row. Runtime OpenRouter credential resolution still falls back
  to OPENAI_API_KEY (runtime_provider.py), independent of the overlay.
- Regression tests for both paths.
2026-06-02 06:31:37 -07:00
Teknium
195c4d2a98 feat(streaming): per-platform streaming defaults (Telegram on, Discord off) + dashboard toggles (#37303)
Streaming quality differs sharply by platform: Telegram has native animated
draft streaming (sendMessageDraft) which is smooth, while Discord/Slack only
have edit-based streaming (repeated editMessage) which visibly flickers. Ship
defaults that match reality instead of one global flag.

- hermes_cli/config.py: DEFAULT_CONFIG display.platforms now ships
  telegram.streaming=true and discord.streaming=false (was empty {}). These
  are gap-fillers — config deep-merge has user values win, so anyone who
  explicitly sets discord.streaming=true keeps it. The global
  streaming.enabled master switch still gates everything; these per-platform
  flags only take effect once streaming is on.
- Dashboard exposure comes for free: the web settings schema is generated
  from DEFAULT_CONFIG, so display.platforms.telegram.streaming and
  .discord.streaming now surface as editable boolean toggles in the UI with
  no frontend change. (Previously the per-platform tree was {} and invisible.)
- tests: pin the defaults, the resolver outcome (telegram on / discord off /
  unlisted platforms follow global), user-override-wins, and dashboard schema
  exposure.

No _config_version bump: deep-merge fills the gap for existing installs; no
value migration needed.
2026-06-02 05:52:54 -07:00
Brooklyn Nicholson
5b71f7dd72 feat(desktop): session search in the sidebar
Adds a search box above the session list. Loaded sessions match instantly
client-side; a debounced full-text search (existing /api/sessions/search FTS)
covers the rest so all sessions stay findable at 699+. Results replace the
pinned/agents sections while a query is active and resume on click.
2026-06-02 07:21:03 -05:00
Brooklyn Nicholson
135c65093a feat(desktop): stable in-workspace ordering + No-workspace default
- Sidebar: rows within a workspace group now sort by creation time instead of
  last activity, so they stop reshuffling every time a message lands (muscle
  memory). Groups still float up by recency.
- Sessions only persist a workspace cwd when one was explicitly chosen; an
  auto-detected launch directory is no longer stamped on the row, so untargeted
  sessions group under "No workspace" instead of "desktop". The agent still
  runs in the detected directory.
2026-06-02 07:18:47 -05:00
Brooklyn Nicholson
de8bdf529d fix(desktop): keep pinned + recent sessions visible across compression
Long-running sessions auto-compress: the gateway ends the original session
and surfaces the live continuation under a new id (list_sessions_rich projects
the root forward to its tip). Two symptoms fell out of the id rotation:

- A pinned session "vanished" — the pin is stored as the pre-compression root
  id, but the sidebar only matched on the live id, so it was filtered out.
  Pins now resolve on the durable lineage-root id (`_lineage_root_id`, already
  surfaced by the projection): the sidebar indexes sessions by both ids, pin/
  unpin and reorder operate on the durable id, and `sessionPinId()` is shared
  with the Cmd+P toggle. Existing pins keep working with no migration.

- A freshly-continued session was missing from the list until you ungrouped +
  "load 50 more" — the list paginated by original start time, so an old-but-
  active conversation sat past the first page. The desktop now requests
  `order=recent` (GET /api/sessions gains an `order` param backed by the
  existing recency CTE), surfacing live continuations on the first page.
2026-06-02 07:12:05 -05:00
Ben Barclay
c10ccaaf51 feat(dashboard-auth): rotate dashboard sessions via refresh token (#37247)
* feat(dashboard-auth): rotate dashboard sessions via refresh token

The dashboard auth-code grant now issues a 24h rotating refresh token
(server side: NousResearch/nous-account-service#293). This wires up the
Hermes client half so an expired access token is transparently refreshed
instead of bouncing the user to /login every 15 minutes.

plugins/dashboard_auth/nous:
- refresh_session() now POSTs grant_type=refresh_token to Portal's token
  endpoint and returns a Session carrying the ROTATED refresh token (was
  an unconditional RefreshExpiredError under the old "no RT in V1"
  contract). The RT is sent in BOTH the request body (Portal's schema
  requires it there) and the X-Refresh-Token header (log redaction) —
  verified against the #293 preview deploy: header-only is rejected as
  invalid_request, body is accepted.
- A 400 from Portal (expired / revoked / reuse-detected) maps to
  RefreshExpiredError so the middleware forces a clean re-login; network
  errors map to ProviderError; empty RT fast-fails without a network call.
- complete_login now captures the initial refresh token Portal returns
  (forward-tolerant: empty string if a deploy omits it).
- Extracted the shared token-response handling into
  _token_response_to_session, parameterised on the 400 exception type so
  the auth-code path raises InvalidCodeError and the refresh path raises
  RefreshExpiredError.
- revoke_session stays a best-effort no-op: Portal exposes no public
  token-endpoint revocation grant (revocation is the authenticated
  /sessions UI, keyed by sessionId+userId), so logout is cookie-clearing
  and the 24h session expires on its own. Documented for a future
  revoke grant.

hermes_cli/dashboard_auth/middleware:
- On an expired/invalid access token the gate now attempts refresh via
  the session's RT BEFORE forcing re-login. On success it serves the
  request and re-sets the rotated cookies on the response (mandatory:
  Portal rotates the RT every refresh and reuse-detects, so a stale RT
  cookie would revoke the whole session on the next refresh). On
  RefreshExpiredError (or no RT) it falls through to clear-and-relogin.
- ProviderError during refresh (Portal unreachable) forces a clean
  re-login rather than 500-ing the request.
- Uses the existing REFRESH_SUCCESS / REFRESH_FAILURE audit events.

Validation:
- 176 dashboard-auth unit/integration tests pass.
- Live E2E against the #293 preview deploy: refresh_session(bad rt) ->
  RefreshExpiredError through the real token endpoint; live JWKS fetch +
  RS256 verification rejects a forged token; empty-RT fast-fail. The
  successful happy-path rotation is covered by unit tests (a live run
  needs an interactive browser OAuth round trip + registered agent:*
  client).

Depends on: NousResearch/nous-account-service#293 (server-side RT issuance).

* fix(dashboard-auth): use Portal's x-nous-refresh-token header name

The refresh-token header must match Portal's REFRESH_TOKEN_HEADER exactly
("x-nous-refresh-token"); the initial cut used "X-Refresh-Token", which
Portal silently ignores (harmless since the RT is also in the body, which
is what the schema requires — but the header redaction was a no-op).
Confirmed against the NAS token route + re-validated live against the
#293 preview deploy.

* fix(dashboard-auth): refresh session when access-token cookie has been evicted

The gated middleware bounced users to /login the instant the access-token
cookie was absent, without ever consulting the refresh token:

    at, _rt = read_session_cookies(request)
    if not at:
        return _unauth_response(...)   # bailed here

This made transparent refresh effectively dead for the common case. The
access-token cookie is set with Max-Age = access_token_expires_in (~15 min),
so a real browser EVICTS hermes_session_at the moment the token lapses while
hermes_session_rt persists (30-day Max-Age). From that point the browser
sends only the refresh-token cookie — and the old guard rejected it before
_attempt_refresh could run. The _attempt_refresh path only fired for a
present-but-invalid access token, which never happens in a browser.

Fix: only hard-bounce when NEITHER cookie is present. A request carrying
just the refresh token now skips verification (no AT to verify) and flows
into the existing refresh path, which rotates both cookies and serves the
request transparently. A dead/expired RT still raises RefreshExpiredError
and falls through to clear-and-relogin.

This failure mode escaped the original tests + manual refresh button because
both kept the access-token cookie present; only a real browser evicting the
cookie at Max-Age exposes it. Added 3 regression tests covering: AT-evicted +
RT-present (transparent refresh), no-cookies (still bounces), and RT-only with
a dead RT (clean 401, no 500).
2026-06-02 21:16:41 +10:00
emozilla
5e55b35cc8 refactor(desktop): move model management from Command Center into Settings
Command Center's Models section and Settings > Model rendered the same
model state with identical persistence semantics — both write config and
apply to new sessions only (POST /api/model/set). The Command Center UI
was strictly better (provider catalog, curated model lists, friendly
auxiliary-task labels, Nous-gateway auto-routing on main-provider switch),
while Settings > Model was three barebones config fields.

Extract that UI into a shared settings/model-settings.tsx (restyled with
Settings primitives) and render it at the top of Settings > Model: main
model picker via setModelAssignment + the 9 auxiliary task slots with
per-task set-to-main / change / reset-all. model_context_length and
fallback_providers stay as config fields below it; the raw auxiliary.*
keys are dropped from Advanced (now covered by the panel).

Strip the Models section from Command Center entirely (section, state,
handlers, render, nav, search entry) leaving it focused on Sessions /
System / Usage, and move the live store-sync callback (onMainModelChanged)
from CommandCenterView to SettingsView. The composer's per-session model
picker (the only live hot-swap, via /model) is unchanged.
2026-06-02 05:53:15 -04:00
Jeffrey Quesnelle
c6501c0f49 Merge pull request #37310 from NousResearch/desktop/consolidate-skills-tools-pane
refactor(desktop): consolidate skills + tools management into one pane
2026-06-02 05:21:15 -04:00
emozilla
a2b8e430e8 refactor(desktop): consolidate skills + tools management into one pane
The left-nav Skills pane and Settings > Skills & Tools rendered the same
getSkills()/getToolsets() data with the same helpers and toggles — genuine
duplication that drifted (different default category labels, sort orders).

Make the left pane the single home: it keeps its category-tabbed browsing
and now gains the functional bits it lacked — a real toolset enable/disable
switch (was a read-only pill) and the expandable ToolsetConfigPanel for
provider selection + per-key credential config. Remove the Tools section
from Settings (nav item, view branch, query slot, type union entries) and
delete tools-settings.tsx, migrating its toggle coverage into the skills
pane test. Relabel the entry point to 'Skills & Tools' in the sidebar and
command center.
2026-06-02 05:11:52 -04:00
Teknium
d78d77e460 feat(config): surface gateway streaming block in DEFAULT_CONFIG (#37285)
The gateway reads top-level streaming.* with StreamingConfig defaults when the
block is absent, so streaming was invisible — a user with no streaming block
sees responses arrive as single messages and has no way to discover the toggle
short of reading source. This materializes the block in config.yaml so it's
discoverable, with values byte-identical to the dataclass defaults (no behavior
change).

- DEFAULT_CONFIG gains a root-level streaming block (enabled, transport,
  edit_interval, buffer_threshold, cursor, fresh_final_after_seconds), each
  documented inline. Values match gateway/config.py StreamingConfig() exactly.
- _KNOWN_ROOT_KEYS gains 'streaming' so the validator accepts the root key.
- No _config_version bump: load_config deep-merges DEFAULT_CONFIG over user
  YAML, so existing installs pick up the default automatically; no value
  migration needed.

Does NOT touch the setup wizard — streaming stays opt-in, just discoverable.
2026-06-02 01:22:24 -07:00
Jeffrey Quesnelle
89db6c8534 Merge pull request #37283 from NousResearch/fix-toolset-provider-selection-display
fix(desktop): reflect active toolset provider in config panel
2026-06-02 04:05:52 -04:00
Teknium
787936d133 feat(gateway): structured stream-event protocol + Telegram draft formatting parity (#37250)
Introduce a typed agent→gateway delivery contract so the gateway (not the
agent) decides how each streaming event is rendered per platform. Moves toward
smart-agent/smart-gateway separation while reproducing today's behavior exactly
in the base class.

- gateway/stream_events.py: typed event vocabulary (MessageChunk/Stop,
  Commentary, ToolCallChunk/Finished, LongToolHint, GatewayNotice).
- gateway/stream_dispatch.py: GatewayEventDispatcher routes events through the
  adapter; adapters can eat events they can't render (e.g. tool chrome on
  plain-text platforms).
- gateway/platforms/base.py: render_message_event + format_tool_event default
  hooks reproduce the historical emoji/preview tool formatting and consumer
  delegation 1:1; adapters override for native rendering.
- gateway/platforms/telegram.py: send_draft now applies MarkdownV2 (format_message
  + parse_mode) with a plain-text fallback on BadRequest, fixing the jarring
  raw-text→formatted shift when the draft finalizes as a real sendMessage.
- gateway/config.py: default streaming transport edit → auto. Safe globally:
  adapters without draft support report supports_draft_streaming()==False and
  transparently use edit, so only Telegram DMs gain native drafts.

Presentation-only contract — nothing rendered here is persisted to conversation
history, preserving cache/message-flow invariants.
2026-06-02 00:33:50 -07:00
Teknium
2c0d648397 fix(cron): sanitize invisible unicode in vetted skill content instead of hard-blocking (#37245)
A stray zero-width space (U+200B), BOM, or bidi control in loaded skill
markdown permanently killed any cron that loaded it. The skills-attached
assembled-prompt scan hard-blocked on any invisible-unicode char, even
though skill bodies are already install-time vetted by skills_guard.py and
the chars commonly appear in copy-pasted unicode docs / code examples.

The skills path now strips invisibles (logging the codepoints) and runs the
cleaned prompt. The raw user-prompt path (_scan_cron_prompt) keeps the hard
block — that is the actual #3968 injection surface, where a small directive
prompt with a ZWSP is a smoking gun, not prose. Stripping does not let a real
injection slip through: the directive still matches after sanitization.

_scan_cron_skill_assembled now returns (cleaned_prompt, error).
2026-06-02 00:29:44 -07:00
emozilla
134643a2fa fix(desktop): reflect active toolset provider in config panel
The toolset config panel highlighted the first keyless provider (e.g.
Nous Portal) on load instead of the provider actually written to config.
The /api/tools/toolsets/{name}/config endpoint never reported which
provider was active, so the GUI's default-expand logic fell back to
"first configured" — and keyless providers are always "configured".

Backend now annotates each provider with is_active (via the same
_is_provider_active helper the CLI 'hermes tools' picker uses) plus a
top-level active_provider summary. The panel prefers that signal before
falling back to first-configured/first.

Adds a frontend regression test (active provider is expanded on load)
and backend coverage (config reports is_active/active_provider; selecting
a provider round-trips into the next config read).
2026-06-02 03:25:46 -04:00
Teknium
3c1d066a8a feat(dashboard): Channels page — set up every gateway messaging channel from the browser (#37211)
The /api/messaging/platforms endpoints (catalog, configure, test) shipped
with the desktop app but never got a dashboard UI; the recent admin-panel
PRs covered MCP/webhooks/hooks/system but skipped messaging channels. This
adds the missing page so all 20+ channels (Telegram, Discord, Slack, Matrix,
Mattermost, WhatsApp, Signal, BlueBubbles, Email, SMS, DingTalk, Feishu,
WeCom, WeChat, QQ Bot, Yuanbao, plugin platforms, etc.) can be configured,
enabled/disabled, tested, and connected entirely from the browser.

- web/src/pages/ChannelsPage.tsx: per-platform list with live status, enable
  Switch, Test, and a Configure modal that renders each platform's exact
  setup fields (secrets masked, required validated, redacted display).
- web/src/lib/api.ts: MessagingPlatform types + get/update/test client fns.
- web/src/App.tsx: /channels route + nav tab (Radio icon, after MCP).
- docs: Channels section + REST endpoints + screenshot.

Frontend-only — reuses the existing env-write + config-enable backend, which
auto-enables a platform once its required env vars are present and the
gateway restarts. No core changes, no new tool schema.
2026-06-01 23:41:35 -07:00
Spider-Vers
15cb4e2279 fix(docker): install python3-venv so ensurepip fallback works (closes #36813) (#36905)
Co-authored-by: alaamohanad169-ship-it <alaamohanad169-ship-it@users.noreply.github.com>
2026-06-02 16:39:32 +10:00
Teknium
0269eca7e1 test(minimax): assert M3 stale-cache guard contract, not a brittle 1M literal (#37220)
test_stale_m3_cache_dropped_and_reresolves_to_1m hardcoded
assert ctx == 1_000_000. The test re-resolves M3 through the live models.dev
registry (the seeded stale entry is dropped, so nothing short-circuits the
lookup), and models.dev now reports MiniMax-M3 at 512,000 — a change-detector
failure unrelated to any code change.

The guard's actual contract is: a stale <=204,800 catch-all value for an M3
slug must be DROPPED and re-resolved to M3's real (large) context. Both
sources satisfy that (hardcoded catalog 1,000,000; models.dev 512,000), so
assert the invariant (ctx > 204,800, stale value gone) instead of a literal
that external data can move. Renamed accordingly.

47/47 in test_minimax_provider.py pass.
2026-06-01 23:35:23 -07:00
Evi Nova
81dd43a8eb fix(docker): preserve Docker -w workdir in main-wrapper (#35472) (#36259)
Save the original working directory before init scripts cd to
/opt/data, then restore it before exec'ing the user command, so
the container starts in the Docker -w directory instead of /opt/data.

Adds regression test verifying cwd save/restore ordering in
main-wrapper.sh.
2026-06-02 16:13:44 +10:00
Teknium
272c2f30aa fix(kanban): kanban_create inherits the spawning worker's task workspace (#37182)
When a dispatcher-spawned worker (HERMES_KANBAN_TASK set) calls
kanban_create without an explicit workspace, the new child now inherits
the worker's own running-task workspace_kind/workspace_path instead of
defaulting to scratch. A worker editing a dir:/worktree project that
spawns a follow-up child keeps it in that project.

Orchestrators (kanban toolset, no HERMES_KANBAN_TASK) and CLI/dashboard
callers still default to scratch. An explicit workspace arg always wins.
2026-06-01 21:26:29 -07:00
Teknium
bd8e2ec1a6 feat(dashboard): complete admin panel — MCP catalog, enable/disable toggles, hook creation, system stats (#36736)
* feat(dashboard): MCP catalog + enable/disable, webhook toggle, hook create/delete, system stats

Backend for the comprehensive admin pass:
- MCP: GET /api/mcp/catalog (browse Nous-approved optional-mcps), POST
  /api/mcp/catalog/install, PUT /api/mcp/servers/{name}/enabled
- Webhooks: PUT /api/webhooks/{name}/enabled; gateway rejects disabled routes
  with 403 (hot-reloaded, no restart)
- Hooks: POST/DELETE /api/ops/hooks — create (with consent approval) + remove;
  list now reports accurate allowlist status + valid events
- System: GET /api/system/stats — OS/arch/python/cpu + psutil memory/disk/
  uptime/process, stdlib fallback

All gated by dashboard auth; secrets never returned.

* feat(dashboard): MCP catalog UI, enable/disable toggles, hook create, system stats

- McpPage: catalog section (browse Nous-approved MCPs, one-click install with
  env prompts) + per-server enable/disable toggle with gateway-restart note
- WebhooksPage: per-subscription enable/disable toggle (muted + badge when off)
- SystemPage: new Host stats section (OS/arch/python/cpu/mem/disk/uptime/load),
  shell-hook create modal + delete, 'Create backup' label
- api.ts: client methods + types for catalog, toggles, hook CRUD, system stats

* test(dashboard): cover catalog, toggles, hook CRUD, system stats, webhook toggle

Adds tests for the comprehensive pass: MCP enable/disable + catalog list +
catalog-install-unknown, hook create/delete with consent, system stats shape,
and webhook enable/disable. 26 tests total, all green.

* docs(dashboard): document the comprehensive admin pass + fresh screenshots

Updates the MCP/Webhooks/Pairing/System sections for catalog browse+install,
enable/disable toggles, hook creation, and host system stats; adds the new
endpoints to the API table; replaces the screenshots with live captures of
the rebuilt pages (real data, no dummies) including the hook-create modal.

* feat(dashboard): curator, portal status, and prompt-size/dump/migrate ops

Closes the last in-scope CLI gaps from the coverage audit:
- Curator: GET /api/curator (status), PUT /api/curator/paused, POST
  /api/curator/run (background)
- Portal: GET /api/portal (Nous auth + Tool Gateway routing, read-only)
- Diagnostics: POST /api/ops/prompt-size, /api/ops/dump, /api/ops/config-migrate
  (backgrounded, tailed via action status)

Host-bound commands (secrets/proxy/lsp/acp/computer-use/desktop/completion/
postinstall/uninstall/claw) remain CLI-only by design.

* feat(dashboard): curator + portal + diagnostics UI, tests

- SystemPage: Nous Portal status section (auth + Tool Gateway routing),
  Skill curator card (status + pause/resume + run now), and three new
  Operations buttons (prompt size, support dump, migrate config)
- api.ts: client methods + CuratorStatus/PortalStatus types
- tests: curator pause/resume, portal shape, system-stats shape, + auth-gate
  coverage for the new GET endpoints (31 tests total)

* docs(dashboard): document curator, portal, and diagnostics + refresh System screenshots

Updates the System section for the Nous Portal status, Skill curator
controls, and the new prompt-size/dump/migrate operations; adds them to the
API table; refreshes the System screenshots (now showing Portal + Curator)
and adds a dedicated curator/gateway/memory capture.

* feat(dashboard): session stats/export/prune + skills hub search endpoints

Completes the existing tabs' backend depth (audit vs CLI):
- Sessions: GET /api/sessions/stats (store stats), GET /api/sessions/{id}/export,
  POST /api/sessions/prune. /stats is registered before /{session_id} so the
  literal path isn't captured by the parameterized route.
- Skills: GET /api/skills/hub/search — parallel multi-source hub search (threaded),
  returns installable identifiers
- (rename via PATCH and cron-edit via PUT already existed; now surfaced in UI)

* feat(dashboard): complete existing tabs — sessions mgmt, skills hub browse, cron edit

Audited every existing tab against its CLI command and filled the gaps:
- Sessions: store stats bar, per-row rename + export (JSON download), and a
  prune-old-sessions control (mirrors hermes sessions rename/export/prune/stats)
- Skills: new 'Browse hub' view — search the skill hub across all sources,
  install by identifier with a live install log, and 'Update all' (mirrors
  hermes skills search/install/update)
- Cron: per-job Edit modal (pre-filled) calling updateCronJob (hermes cron edit)
- api.ts: renameSession/getSessionStats/exportSessionUrl/pruneSessions,
  updateCronJob, searchSkillsHub + types

Models tab was already comprehensive (provider+model picker, dynamic per-provider
lists, main + all 11 aux-task assignments, reset) — verified, no change needed.

* test(dashboard): cover session stats/rename/export/prune + skills hub search

Adds the route-shadowing guard for /api/sessions/stats (must not be captured
by /api/sessions/{session_id}), rename/export/prune, and the empty-query
short-circuit for hub search. 36 tests total, all green.

* docs(dashboard): document enhanced Sessions, Skills hub, and Cron edit

Sessions: stats bar, rename, export, prune (+ screenshot). Skills: new Browse
hub view for search/install/update (+ screenshot). Cron: edit action. API
table updated with the new endpoints.
2026-06-02 00:16:11 -04:00
Ben Barclay
40ae170647 ci(docker): use registry-backed build cache for arm64 (#37129)
The arm64 PR build ran fully uncached because the previous gha cache
backend's short-lived Azure SAS token expired mid-build on slow
cold-cache arm64 runs and crashed before the smoke test. Uncached arm64
PR builds were ~45% slower than amd64 (median 553s vs 382s), making the
arm64 job the one most often cancelled on supersede — surfacing as a red
X in PR checks and reading as 'the arm64 build keeps failing'.

Switch arm64 to a registry-backed cache on ghcr.io
(type=registry, ref ghcr.io/nousresearch/hermes-agent:buildcache-arm64).
Its credential is the job-lifetime GITHUB_TOKEN, not a time-boxed SAS
token, so the cold-build-outlives-token failure mode cannot recur.

- PR builds: cache-from only (read-only) — warm layers, no write races,
  no cache-ref pollution from rapid PR pushes.
- main/release builds: cache-from + cache-to (mode=max) to populate the
  cache for subsequent PR/main builds and let the digest push reuse the
  smoke-test build's layers.
- Add packages: write permission and a ghcr.io login for the cache.

amd64 keeps its gha cache: it builds fast enough to stay inside the SAS
token's lifetime, so it never hit this failure mode.
2026-06-02 14:03:40 +10:00
whyhkzk
1495f0cc38 fix(file-safety): extend sandbox-mirror guard to cover inner-container path (#32049) (#32407)
* fix(file-safety): extend sandbox-mirror guard to cover inner-container path (#32049)

Brian's shape-based guard (#32213) catches paths that still carry the
full sandboxes/<backend>/<task>/home/.hermes/… prefix on the host side.
The inner-container case is not covered: when file tools execute inside
Docker the bind-mount strips that prefix, so the guard receives plain
/root/.hermes/… and passes through. The root:root ownership on the
divergent SOUL.md in #32049 confirms this is the primary failure mode.

Add a ContextVar (_CONTAINER_HERMES_MIRROR) set by DockerEnvironment
when persistent=True. classify_container_mirror_target / get_container_
mirror_warning detect any write whose resolved path falls under that
prefix, using the same warning format and cross_profile=True bypass
contract as the existing guards. Chain the new guard in
_check_cross_profile_path after the two existing detectors.

* fix(file-safety): derive Docker mirror guard from task

---------

Co-authored-by: Ben <ben@nousresearch.com>
2026-06-02 14:03:37 +10:00
Stephen Chin
a5aecf26fa feat(kanban): gate notifier watcher on dispatch_in_gateway
Non-dispatch gateways no longer open per-board kanban DBs for notifier
polling. Mirrors the existing dispatcher gate (config
kanban.dispatch_in_gateway, default True; env override
HERMES_KANBAN_DISPATCH_IN_GATEWAY) so multi-gateway setups collapse to a
single process holding kanban.db file descriptors.

Salvaged from PR #31964 by @steveonjava; tests and docs trimmed during
salvage.
2026-06-01 20:30:24 -07:00
xxxigm
c35ede789f refactor(cli): normalize note and avoid blank lines in prepend helper
Adopt the cleaner handling from PR #37080: coerce/strip the note and
skip the extra newlines when the underlying message (or text part) is
empty, while keeping the safer fail-open behavior for unknown shapes.
2026-06-01 20:30:08 -07:00
xxxigm
a26a12ad07 test(cli): cover _prepend_note_to_message str/list handling
Regression coverage for the multimodal-message TypeError: note folding into
text parts, image-only insertion, empty-note passthrough, and unknown-shape
fail-open.
2026-06-01 20:30:08 -07:00
xxxigm
043350dfd3 fix(cli): prepend queued notes safely to multimodal messages
Sending an image to a vision model turns the user message into a list of
OpenAI-style content parts. When a /model or /reload-skills note was queued
for the same turn, the CLI did `note + "\n\n" + agent_message`, crashing the
agent thread with:

    TypeError: can only concatenate str (not "list") to str

Repro: `/model gpt-5.5 --provider openai-codex`, then paste+send an image.

Add _prepend_note_to_message(), which folds the note into the first text
part of a content-parts list (or inserts a leading text part for image-only
messages) and keeps the plain-string path unchanged. Used for both the
model-switch and skills-reload notes.
2026-06-01 20:30:08 -07:00
Teknium
21f55af769 fix(model-picker): stop routing OpenAI selection to OpenRouter (#37175)
The /model picker emitted a standalone slug=openai row (gated on
OPENAI_API_KEY). Selecting it ran resolve_provider_full("openai"),
which resolved the legacy providers.py alias openai->openrouter BEFORE
checking the user's own providers.openai config — silently switching
users onto OpenRouter (HTTP 401 when they have no OR key).

- model_switch.list_authenticated_providers: skip vendor names that are
  aliases to an aggregator (isolates openai->openrouter; copilot/kimi/etc.
  are real providers and unaffected). Kills the phantom picker row.
- providers.resolve_provider_full: user-config providers.<name> now wins
  over the built-in alias table, so providers.openai (api.openai.com)
  beats the alias.
- model_switch PATH A: user-config providers resolve credentials via
  their own endpoint instead of the name-based runtime resolver that
  doesn't know user-config slugs; plus a fail-loud guard for explicit
  unauthed-aggregator hops.

Verified E2E with the reporter's config (no OR key): selecting OpenAI +
gpt-4o-mini now resolves to api.openai.com instead of openrouter.ai.
2026-06-01 20:27:41 -07:00
Teknium
72e82f88c0 fix(kanban): decompose children inherit root workspace instead of forcing scratch (#37172)
decompose_triage_task hardcoded every fan-out child to workspace_kind
'scratch', ignoring the root task's workspace. A code-gen task created
with a dir:/worktree: workspace would fan out into throwaway scratch tmp
dirs (GC'd on archive), so generated code never landed in the project.

Children now inherit the root's workspace_kind + workspace_path. A child
dict may still override with its own workspace_kind/workspace_path; the
path only carries over when kinds match. Scratch roots are unchanged.
2026-06-01 20:26:57 -07:00
teknium1
fa3b06b035 refactor(telegram): generalize observed-media caching into a reusable primitive
Collapse the per-type observed-media dispatch into one platform-agnostic
cache_media_bytes() helper in gateway/platforms/base.py. Any adapter can now
hand it raw attachment bytes + a filename/MIME hint; it classifies against the
shared MIME registries, routes to the right cache_*_from_bytes helper,
sandbox-translates the path, and returns a CachedMedia with a ready
context_note(). Telegram's observed-group path shrinks to: size-gate, download,
call the helper, annotate. Also dedupes the addressed-media type ladder into
_media_message_type().

Net: contributor's Telegram-only +595 LOC becomes a +210/-32 production change,
with the reusable primitive available to Discord/Slack/Signal/etc.

Co-authored-by: Glucksberg <markuscontasul@gmail.com>
2026-06-01 20:18:41 -07:00
Glucksberg
f768e75ecf fix(telegram): cache observed group media 2026-06-01 20:18:41 -07:00
teknium1
34468ed0d4 fix: normalize terminalBackground default and drop unrelated lockfile churn
Follow-up to the salvaged terminalBackground commit:
- align the CSS-var fallback and type doc to the runtime default (#000000)
- revert web/package-lock.json to main (the original commit stripped peer
  flags as an npm-version artifact, unrelated to the feature)
2026-06-01 20:13:56 -07:00
davidgut1982
fc995634cc feat(dashboard): add terminalBackground field to DashboardTheme
Wires the xterm.js terminal pane background color into the theme
system. Previously hardcoded as #0d2626; now reads from
DashboardTheme.terminalBackground with #000000 as default.

Users can override via ~/.hermes/dashboard-themes/*.yaml:
  terminalBackground: "#1a0a2e"
2026-06-01 20:13:56 -07:00
Stephen Schoettler
f24b7ed9d9 fix: make Honcho startup fail open 2026-06-01 20:13:42 -07:00
Teknium
59510d7b44 feat(skills): fix browse cap, add source links + copy buttons + category cleanup (#37143)
Skills discovery surfaced ~136 of 88k skills in the CLI and gave community
skills no clickable source on the docs page. Three coupled fixes:

CLI browse:
- hermes skills browse capped at 50 because the per-source limit dict had no
  'hermes-index' key — when the centralized index is available the router
  skips external APIs and serves only the index, so the default-50 fallthrough
  silently truncated the whole hub. Add hermes-index: 5000. Browse now loads
  5367 (269 pages) instead of 136.
- Add an Identifier column + install/inspect hint to the browse table so users
  can act on what they see without a second 'search'.
- Route the TUI browse_skills() helper through parallel_search_sources so it
  inherits the same index-aware source-skip (was double-counting); expose
  identifier in its output.

Docs Skills Hub page:
- Synthesize a sourceUrl for every community skill (github tree URL, clawhub /
  skills.sh / lobehub / browse.sh detail pages), preferring the adapter's
  explicit extra.detail_url/source_url/repo_url. Expanded cards now show
  'View source' for community skills (was nothing) and keep 'View full
  documentation' for built-in/optional. 99% coverage.
- Add a Copy button on the install command.
- Add a loading state instead of flashing '0 skills / No skills found' while
  the 45MB catalog fetches.

Category cleanup:
- _guess_category fell back to tags[0] verbatim, producing ~430 junk one-off
  categories (version strings, brand names: '0.10.7 Dev', 'Doramagic Crystal').
  Now only curated buckets are accepted; unknowns fold into 'Other'. Widen the
  tag->category map so common community tags route to real buckets. 430 -> 173
  categories, top 20 all meaningful.

Tests: tests/website/test_extract_skills.py covers _source_url synthesis +
precedence and _guess_category curation (13 tests). All 27 skills-hub CLI
tests still pass. Docusaurus build verified; expanded cards confirmed in
browser for both community (View source) and built-in (View full docs).
2026-06-01 19:52:28 -07:00
Zyrixtrex
0cd5867bbb fix(whatsapp): honor dm_policy and group_policy open at the gateway 2026-06-01 19:51:21 -07:00
kyssta-exe
d4b533de4e fix: batch of small robustness/correctness fixes from @kyssta-exe
Salvages 8 distinct fixes from a batch of PRs by @kyssta-exe, reapplied
onto current main (original branches were stale) with a few refinements.

- cron(jobs.py): load_jobs() validates top-level JSON shape — a bare
  list auto-repairs into the {"jobs": [...]} dict; scalars/null raise a
  clear RuntimeError instead of an uncaught AttributeError that took
  down the whole cron subsystem (#37065, closes #36867).
- web(web_server.py): close the per-action log file handle after Popen
  so the parent stops leaking one fd per spawned action (#36843).
- web(web_server.py): DELETE /api/env returns 400 for invalid key names
  instead of a misleading 500, mirroring PUT /api/env (#36840).
- gateway(gateway.py): read /proc/<pid>/cmdline inside a with-block so
  the fd is released immediately instead of relying on GC (#36804).
- web-tools(web_tools.py): include "xai" in check_web_api_key() so a
  configured X.AI web backend reports as available (#36802).
- compression(conversation_compression.py): mark the feasibility check
  done only after it completes, and default the gate to "not checked"
  if the attribute is missing (#36803).
- completion(completion.py): replace `ls` with directory globbing in the
  generated bash/zsh/fish profile listers — handles names with spaces
  and skips non-directory entries (#36806).
- terminal-tool(terminal_tool.py): drop a duplicate `import threading`
  (#36808).
- claw(claw.py): the migrate recommendation now points at the real
  `hermes gateway stop` command instead of the non-existent
  `hermes stop` (#36795, #36796, closes #36771).
- tests: guard against a leaked HERMES_CRON_SESSION breaking gateway
  approval tests — add it to the hermetic conftest unset list (root
  cause, protects every test) and pop it in the affected test's
  setup_method (#36796).

Co-authored-by: kyssta-exe <kyssta-exe@users.noreply.github.com>
2026-06-01 19:51:03 -07:00
teknium1
64f7f36713 fix(mcp): make non-MCP HTTP endpoint fast-fail robust and non-retryable
Reworks the content-type preflight so a misconfigured HTTP MCP url (a web-app
root serving HTML) fails in <1s instead of hanging the full 60s connect_timeout
— and does so non-retryably, which neither original PR achieved.

- Allow-list detection (application/json, text/event-stream) instead of a
  text/html-only denylist — catches text/plain, application/xml, etc.
- New NonMcpEndpointError(ConnectionError); run() catches it in the same
  top-level fast-fail block as InvalidMcpUrlError, so it returns before the
  reconnect-backoff loop (truly non-retryable) and the probe runs once, not
  on every reconnect.
- Probe runs on its own httpx client OUTSIDE the SDK anyio task group, so the
  error propagates as itself rather than wrapped in an ExceptionGroup (the
  trap that made the in-SDK event-hook approach a no-op).
- Forwards ssl_verify + client_cert + headers; HEAD->GET fallback on 405/501;
  best-effort pass-through on missing content type, non-2xx, and network
  errors; skips SSE transport. CancelledError is never swallowed.
- Replaces the malformed test file (which never imported the real method and
  failed CI) with 21 tests driving the actual _preflight_content_type against
  a real local HTTP server, plus full run() integration verifying <1s
  non-retryable failure.

Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: uzunkuyruk <egitimviscara@gmail.com>
2026-06-01 19:49:50 -07:00
liuhao1024
c914e4a371 fix(mcp): fail fast on HTML content-type instead of waiting full connect_timeout
A misconfigured MCP server URL that returns text/html (e.g. pointing at
a web app root instead of an MCP endpoint) causes the MCP SDK to block
for the full connect_timeout (default 60 s) before surfacing
CancelledError.

Add a lightweight HEAD pre-flight check that detects text/html responses
in ≤5 s and raises ConnectionError with an actionable message. Non-HTML
responses, missing headers, and network errors pass through silently so
the normal MCP handshake proceeds unaffected.

Fixes #36052
2026-06-01 19:49:50 -07:00
brooklyn!
fabca0bdd8 feat(tui): single /model command + unified Sessions overlay (#37112)
* feat(tui): single /model command + unified Sessions overlay

Collapse the redundant `/provider` alias so `/model` is the only name
everywhere (it already drove the same 2-step ModelPicker in the TUI).

Merge the separate `/resume` (cold history browser) and `/sessions` (live
switcher) surfaces into one Sessions overlay reached by `/resume`,
`/sessions`, `/session`, and `/switch`. It pins a "+ new" row at the top
(always visible), lists live sessions with status, and lists resumable
history below — dispatching session.activate for live rows vs resume for
cold ones, with close/delete in place. Fixes `/session` opening an empty
live-only switcher and the hidden new-session affordance.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* fix(tui): address Copilot review on the Sessions overlay

- Track the armed history-delete by session id instead of row index so the
  1.5s live-status poll re-indexing rows can't redirect the second `d` to a
  different session.
- Re-add the busy-session guard to immediate `/resume <id>` and `/sessions new`
  actions (browsing the bare overlay stays allowed) so resuming/switching can't
  corrupt an in-flight turn's streaming/busy state.

* fix(tui): guard cold-resume (not live-switch/new) from the Sessions overlay

Copilot flagged that overlay actions bypassed the busy guard. Only cold
resume actually closes the current session, so only it is guarded — both
from the slash path and now from the overlay (appActions.resumeById).
Switching between live sessions and starting a `+ new` live session keep
the current session running in the background, so they stay unguarded:
that concurrency is the orchestrator's whole purpose. Also dropped the
over-broad guard on `/sessions new` for the same reason.

* fix(tui): address Copilot review (history dedup + desktop /provider)

- The 1.5s poll now re-derives the resumable list from the RAW session.list
  results (rawHistoryRef) against the current live set, so a session hidden
  while live reappears in history once it closes — instead of being lost
  until a full reload. Delete also prunes the raw ref.
- Drop the dead `/provider` entry from the desktop PICKER_OWNED_COMMANDS now
  that the alias is gone, so the desktop client no longer advertises it.

* fix(tui): surface session.list errors + keep selection stable across polls

- A garbled session.list response now surfaces an error and preserves the
  last good raw history, instead of silently blanking the resumable section.
- The 1.5s poll re-anchors the selection to the same row by session id
  (live or history) when the live list grows/shrinks, so the highlight no
  longer drifts to a different row mid-interaction.

* fix(tui): degrade session.list independently + cover overlay helpers

- Fetch active_list and session.list via Promise.allSettled so a failing
  session.list no longer rejects the whole load: live sessions still render
  and only the resumable history degrades (with an error).
- Add unit tests for the new helpers (sessionRowKindAt row ordering,
  resumableHistory dedupe, sessionsCountLabel, relativeSessionAge).

* test(tui-gateway): assert /provider alias is gone, /model remains

The CI test_complete_slash_includes_provider_alias asserted the removed
`/provider` alias still autocompleted. Flip it to lock in the removal:
`/pro` no longer offers `provider`, and `/mod` still completes `model`.

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-01 22:28:36 -04:00
Zyrixtrex
f7a3509b25 fix(gateway): honor WECOM_ALLOWED_USERS in env-only WeCom DM allowlist 2026-06-01 19:20:36 -07:00
brooklyn!
7d51cd7516 Merge pull request #37115 from NousResearch/bb/tui-statusbar-responsive
fix(tui): prioritize status/model over cwd in the status bar on narrow terminals
2026-06-01 21:10:18 -05:00
Brooklyn Nicholson
13a2350c8d fix(tui): pass indicatorStyle into FaceTicker so render matches reservation
FaceTicker now takes the indicator style as a prop (same value used by
busyIndicatorWidth) instead of reading the store independently, so the
rendered busy indicator and its reserved width can't desync on /indicator
changes.
2026-06-01 21:02:32 -05:00
Jeffrey Quesnelle
f600352e43 Merge pull request #37123 from NousResearch/installer-optional-commit-pin
feat(installer): make commit pinning opt-in, default to branch-follow
2026-06-01 22:01:57 -04:00
Julien Talbot
8104b20269 fix(xai): route video models by modality 2026-06-01 19:00:30 -07:00
Ben Barclay
eee32cdd52 fix(gateway): fall back to in-process heartbeat when s6 sleep is missing (#36208) (#37120)
Inside an s6 container, `gateway run` redirects to the supervised
gateway and then keeps the CMD process alive as a no-op heartbeat so
/init doesn't start stage-3 shutdown. That heartbeat is
`os.execvp("sleep", ["sleep", "infinity"])`, which does a PATH lookup
for the `sleep` binary. When PATH was empty/truncated/clobbered at that
point — e.g. after user customizations rewrote PATH, or on a minimal
image without `sleep` on PATH — the exec raised FileNotFoundError,
killing the CMD process and causing /init to tear down every service:
the container failed to start (issue #36208, a regression in the s6
image from 2026.5.28).

Wrap the exec in try/except OSError: on success it still replaces the
process with the cheap `sleep` heartbeat (no resident Python
interpreter, and the existing process-tree/recursion contract is
preserved); on failure it falls back to `_block_until_terminated()` —
a SIGTERM handler (clean 128+signum exit on `docker stop`) plus a
signal.pause() loop, which needs no external binary and so can't fail
on PATH state. A threading.Event().wait() fallback covers platforms
without signal.pause().

Keeping execvp as the primary path (rather than replacing it outright)
preserves the `sleep infinity` heartbeat that the docker integration
tests assert (test_gateway_run_supervised.py) and avoids leaving a
full Python interpreter resident for the container's lifetime.

Verified end-to-end on a built image: with execvp forced to fail,
_block_until_terminated() blocks cleanly instead of raising
FileNotFoundError; normal boot still runs the cheap `sleep infinity`
heartbeat; the 6 test_gateway_run_supervised.py integration tests pass.

Salvages the two community fixes for this issue — the fallback design
from #36221 (@Pluviobyte) and the signal.pause() heartbeat from #36267
(@karmeleon) — and adds regression tests for both the normal and
sleep-missing paths.

Co-authored-by: Pluviobyte <Pluviobyte@users.noreply.github.com>
Co-authored-by: karmeleon <karmeleon@users.noreply.github.com>

Closes #36208.
2026-06-02 11:59:27 +10:00
Brooklyn Nicholson
899e8b9067 fix(tui): keep fmtCwdBranch default, cap cwd at the status-bar call site
Reverts the shared fmtCwdBranch default (28 → 40) so it isn't an API/
behavior change for other callers, and instead passes max=28 explicitly
from the status-bar caller where the tighter cap is intended.
2026-06-01 20:55:14 -05:00
teknium1
abe0e19c0a refactor(bluebubbles): simplify mention-gating helpers
Collapse the three mention-parsing helpers into one _compile_mention_patterns
that handles list/string/None inputs, and inline the require_mention bool
coercion to match the signal/dingtalk convention. Same behavior, 16 fewer
lines, no per-instance state in the staticmethod.
2026-06-01 18:52:05 -07:00
Trevin Chow
d967e74427 chore: add contributor attribution mapping 2026-06-01 18:52:05 -07:00
Trevin Chow
05022066ea feat(bluebubbles): support group mention gating 2026-06-01 18:52:05 -07:00
Brooklyn Nicholson
e25b2a6e18 fix(tui): address Copilot review on status-bar tail disclosure
- Render SpawnHud last in the tail so its un-budgeted (dynamic) width can
  only truncate itself, never push budgeted segments past leftWidth.
- Precompute kaomoji/emoji frame widths once at module load instead of
  rescanning FACES/EMOJI_FRAMES on every status render.
- Correct the tail-priority comment to match the actual fits() order
  (bar, duration, compressions, voice, session count, bg, cost).
2026-06-01 20:49:51 -05:00
Brooklyn Nicholson
9cb7d40d8d fix(tui): derive busy/duration reservation width from fmtDuration
fmtDuration renders a space between units (e.g. `59m 59s`), so the flat
6-col reservation under-counted and could let the elapsed-time tail shove
the model off-screen / break the whole-segment budget. Reserve the bounded
clock width from fmtDuration itself (MAX_DURATION_WIDTH) in both the busy
indicator reservation and the tail duration budget.
2026-06-01 20:42:04 -05:00
brooklyn!
85b65e29f0 feat(desktop): session hygiene, archive, media streaming + connecting overlay (#37099)
* feat(desktop): session hygiene, archive, media streaming + connecting overlay

Address a batch of desktop feedback:

- Stop leaking empty "Untitled" sessions: the TUI gateway pre-created a DB
  row on every session.create (i.e. every launch/draft). Persist the row
  lazily on first prompt instead, and hide message-less rows in the sidebar.
- Archive/hide sessions: new `archived` column + set_session_archived, web
  API (`?archived=` + PATCH archived), Ctrl/⌘-click and a context-menu item
  in the sidebar, and an "Archived Chats" settings panel to restore/delete.
- Videos load via a streaming `hermes-media://` protocol instead of capped,
  in-memory data URLs (16 MB limit) — bypasses the cap and supports seeking.
- Background-process completions route to the session that launched them:
  the completion event now carries session_key and each poller only consumes
  its own.
- Sidebar: "Group by workspace" toggle is always visible; each workspace
  group gets a "+" to start a session in that directory; "New agent"/"Agents"
  relabeled to "New session"/"Sessions".
- New gateway connecting overlay (ascii decode → fade out) replacing the bare
  skeleton/"starting gateway" state.

* fix(desktop): bail connecting overlay on boot error

The shownRef latch kept the connecting overlay mounted behind
BootFailureOverlay after a hard boot failure. Return null on boot.error
so the failure recovery surface fully owns the screen.

* fix(desktop): address Copilot review

- /api/sessions: validate `archived` (400 on unknown) and return `archived`
  as a JSON boolean instead of SQLite's 0/1.
- PATCH /api/sessions/{id}: 400 (not a misleading 404) when the body has no
  updatable fields; stop conflating a no-op with "not found".
- hermes-media protocol: drop `bypassCSP` — streaming only needs
  secure/standard/stream/supportFetchAPI.
- Sidebar workspace header: split the toggle and the "+" into sibling buttons
  so we no longer nest interactive elements inside a <button>.

* fix(desktop): address Copilot re-review

- hermes-media protocol: restrict streaming to an audio/video extension
  allowlist (415 otherwise) so it can't be used to read arbitrary local files.
- Connecting overlay: use z-[1200] instead of the non-standard z-1200 utility.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-01 20:41:34 -05:00
Ben Barclay
ddc22866a3 chore(release): add whyhkzk to AUTHOR_MAP for PR #32407 (#37121) 2026-06-02 11:41:22 +10:00
emozilla
1d9aacbd00 feat(installer): make commit pinning opt-in, default to branch-follow
The bootstrap installer's build.rs unconditionally baked a commit pin via
`git rev-parse HEAD`, forcing every dev build to clone an exact SHA at
install time. That SHA had to be pushed to origin or the fresh-box clone
would fail.

Make the commit pin opt-in: by default build.rs bakes ONLY the detected
branch, so the installer follows that branch's HEAD at install time. Set
HERMES_BUILD_PIN_COMMIT (SHA, tag, or branch name) to bake an immutable
commit pin for reproducible/release builds; it is resolved to a SHA via
`git rev-parse --verify <ref>^{commit}` and fails loud on an unresolvable
ref. Runtime resolution already supported branch-only pins, so no changes
needed in bootstrap.rs / install_script.rs / install.ps1.
2026-06-01 21:35:46 -04:00
Brooklyn Nicholson
2f171743b7 fix(tui): pin status/model, whole-segment tail disclosure, smaller cwd
The previous reservation set the left box width but everything still
shared one flex row, so the lower-priority tail + cwd could still shrink
`ready`/model down to fragments ("re"). Pin the essentials (indicator +
model + context) in a non-shrinking group, and render the tail segments
(bar, duration, compressions, voice, session count, bg, cost) only when
the whole segment fits in the leftover space — in priority order — so
nothing truncates mid-segment and the low-value tail drops first.

Also shrink the cwd/branch label (max 40 → 28) so it stops dominating the
bar on roomy-but-not-huge terminals.
2026-06-01 20:32:27 -05:00
Brian D. Evans
162c7856ca fix(file-safety): add sandbox-mirror soft guard for writes to per-task .hermes mirrors (#32213)
#32049 reports that under terminal.backend: docker, write_file / patch
calls to authoritative profile state (SOUL.md, memories, etc.) land on
the sandbox-local mirror at
``<HERMES_HOME>/profiles/<name>/sandboxes/<backend>/<task>/home/.hermes/...``
— a path the host Hermes process never reads. The tool reports success,
the user sees no behavior change, and on disk two divergent copies of
SOUL.md (or any other profile file) accumulate.

The existing classify_cross_profile_target guard does not catch this:
its parts[2] check sees "sandboxes" and returns None, and the path is
in-profile from the inner-mirror perspective so even a fixed version
would not fire.

Add a parallel sandbox-mirror classifier in agent/file_safety:

  * classify_sandbox_mirror_target() detects the
    ``…/sandboxes/<backend>/<task>/home/.hermes/…`` shape via path parts.
    Detection is path-shape only — backend-agnostic, does not require
    the file to exist, and works regardless of which HERMES_HOME resolves.
  * get_sandbox_mirror_warning() returns a model-facing warning that
    names the mirror root and the inner authoritative path the agent
    likely meant.

Wire both detectors through tools/file_tools._check_cross_profile_path
so the existing write_file and v4a patch call sites pick up the new
guard with no API change. The bypass kwarg (``cross_profile=True``)
remains shared between the two guards — same "I know what I'm doing"
escape valve after explicit user direction.

This is the defense-in-depth piece of the proposal in #32049 ("any
…/sandboxes/<backend>/…/home/…hermes/… path as sandbox-mirror"). It
catches the host-side speculation case where the agent writes a literal
sandbox-mirror path. The inner-container case (where the bind mount
strips the ``sandboxes/`` prefix from the agent's path view) is out of
scope for this surgical change — that requires either a dispatch-layer
host-side check before the container handoff, or the host-side
``profile_state`` / ``soul`` tool the issue also proposes.

Soft guard, NOT a security boundary — matches the existing
classify_cross_profile_target contract.

Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>
Co-authored-by: Ben Barclay <ben@nousresearch.com>
2026-06-02 11:29:24 +10:00
Brooklyn Nicholson
1d7a1c00b4 fix(tui): make busy status-bar reservation /indicator-style aware
The left-content reservation used a flat constant for the busy face,
but its width varies by /indicator style: kaomoji is a wide glyph plus
a rotating verb, while unicode is a bare 1-col braille spinner with no
verb. Reserve the real width via busyIndicatorWidth(style, hasDuration)
so the model stays on-screen across styles without over-reserving the
unbounded elapsed-time tail.
2026-06-01 20:28:43 -05:00
Brooklyn Nicholson
e59b815c04 fix(tui): prioritize status/model over cwd in the status bar on narrow terminals
The status rule reserved only 8 cols for the left segments, so the
cwd + git-branch label on the right could grow until the loading
indicator, model, and context read-out were crushed to almost nothing
(sometimes collapsing to a single illegible line) on small screens.

Reverse the priority: `statusRuleWidths` now reserves the display width
of the must-keep left content (status indicator + model + context) so
the cwd/branch segment truncates first. Add `statusBarSegments(cols)`
progressive disclosure — as the terminal narrows the low-priority tail
sheds in order (cost → bg → voice → compressions → duration → context
bar), and below the bar breakpoint the context read-out collapses to a
bare token count. Status and model are always guaranteed room.

Default `minLeftContent = 0` keeps `statusRuleWidths` byte-identical for
existing callers.
2026-06-01 20:26:41 -05:00
Ben Barclay
4f7fe9bcff fix(dashboard): surface Docker update guidance instead of generic failure (#34347) (#37085)
The dashboard Update button's backend guard (#36263) already returns a
structured {ok:false, error:"docker_update_unsupported", message,
update_command} envelope (HTTP 200) when running in a Docker install,
instead of surfacing a raw SystemExit. But the frontend ignored that
envelope: runAction() only branched on a thrown error, so the 200 fell
through to the action-status poll, which reported a generic
"Action failed (exit 1)" toast and never showed the actual guidance.

Now runAction() inspects the update response and, on the
docker_update_unsupported case, surfaces the backend's guidance message
plus the recommended re-pull command directly (success-styled, since it's
actionable guidance — not a crash) without starting the poll.

Closes #34347.
2026-06-02 10:36:10 +10:00
firefly
3a8d643d37 chore(release): map caojiguang@gmail.com in AUTHOR_MAP
The fix commit preserves @caojiguang's authorship (from #31853); the
release-notes AUTHOR_MAP gate requires their email to map to a GitHub
username.
2026-06-01 17:31:40 -07:00
firefly
765790a216 test(weixin): regression suite for _api_post/_api_get timeout migration 2026-06-01 17:31:40 -07:00
Cao Jiguang
566669013f fix(weixin): replace aiohttp ClientTimeout with asyncio.wait_for in _api_post/_api_get
Cron delivery to WeChat fails with 'Timeout context manager should
be used inside a task' because _api_post and _api_get use aiohttp's
ClientTimeout directly.  When the cron scheduler calls send() via
asyncio.run_coroutine_threadsafe(), aiohttp cannot find a running
task and raises RuntimeError.

_upload_media, _download_bytes, and _download_remote_media already
use asyncio.wait_for() to avoid this.  Apply the same pattern to
_api_post and _api_get — the two remaining iLink API helpers that
still use the raw ClientTimeout approach.

This fixes cron delivery errors seen on the WeChat platform adapter
when meyo-external cron jobs attempt to deliver output to WeChat.
2026-06-01 17:31:40 -07:00
firefly
a1f76ba7e9 fix(gateway): recover extract-stripped tool responses on all platforms (#29346)
The extract pipeline (extract_media/extract_images/extract_local_files +
directive strips) can reduce a non-empty tool-using response to empty
text_content with no deliverable attachment. The 'if text_content' send
guard then silently skips delivery: a 'response ready' log with no
'Sending response', no error, and the answer never reaches the user.

- A2: snapshot the pre-extract response; when extraction yields empty text
  and no image/local/media attachment, deliver the recovered original from
  the post-extract_media body (so a spaced MEDIA path can't leak). Applies
  on ALL platforms (supersedes the Discord-only #33842 and the unsafe
  raw-fallback #29499).
- A3: loud delivery invariant - a non-empty response that produces nothing
  deliverable logs response_delivery_dropped at ERROR; every recovery logs
  response_delivery_recovered. No silent drop survives.
- Factor a _strip_media_directives helper for the [[...]] strips; MEDIA
  stripping stays owned by extract_media, whose grammar handles spaced and
  quoted paths.
- Salvaged + de-scoped the #33842 test harness to all platforms; added
  unrecoverable-drop and no-leak regression tests.
2026-06-01 17:31:32 -07:00
firefly
8bf498c21d fix(gateway): scope final-delivery flags to turn-final segment (#29346)
A streamed preamble ("Let me search...") finalized at a tool boundary
routed through _try_fresh_final, which unconditionally set
_final_response_sent=True even though it is a NON-final segment. The
gateway then reads that flag as "final delivered" and suppresses the
genuine final answer produced on the next API call, so the user silently
gets nothing. Only reproduces with fresh_final_after_seconds > 0.

- _try_fresh_final / _send_or_edit take is_turn_final; the segment-break
  call site passes is_turn_final=got_done so only the turn-final answer
  marks final-delivered.
- _reset_segment_state clears the final-delivery flags at every tool
  boundary as defense-in-depth against any future premature setter.
- Failing-first regression + happy-path no-duplicate test.
2026-06-01 17:31:32 -07:00
Teknium
92273e4f57 docs: add 25 new community user stories to the collage (#37048)
Sourced from X/Twitter, blogs (Medium/Substack/dev.to), and YouTube since the
last refresh. Deduped against the existing 237 entries by id, url, and author.
237 -> 262 stories.

Highlights: 24/7 Mac Mini agent at $21/mo (@witcheer), automated TikTok
slideshow factory (@cyrilXBT), per-client isolated profiles as an AI-ops
business (@IBuzovskyi), PM briefing 20->8min (@aakashgupta), Railway+Telegram
deploy gotchas (Tessa Kriesel), compounding-cost field report (chintanonweb),
18-agent Kanban fleet (Tonbi), and several daily-automation setups.
2026-06-01 17:01:18 -07:00
kshitijk4poor
0fdab53ef0 feat(cli): ranked fuzzy search in the curses model picker
Wires the salvaged search helpers into the shared curses menu driver and
turns on type-to-filter for the CLI model pickers (the 100+ model lists
that previously required scrolling).

- Search lives in the shared `_run_curses_menu` driver behind a
  `searchable` flag + `search_labels`, so both `curses_radiolist` and
  `curses_single_select` get it without per-menu duplication. `/` opens
  the filter, BACKSPACE edits, Ctrl+U clears, ESC clears the filter then
  cancels. Returned values are always original item indices.
- `_filter_indices` RANKS matches (best-first) via a Python port of the
  TS scorer in ui-tui/src/lib/fuzzy.ts and web/src/lib/fuzzy.ts. The port
  is byte-identical in score: same per-char bonuses, prefix (+8) and
  exact (+20) bonuses, camelCase/word-boundary detection (matching on the
  lowercased target, boundary on the original case), and the -len*0.01
  length tiebreak — so the CLI, TUI, and WebUI rank results identically.
  A cross-language parity test pins the exact scores.
- `_prompt_model_selection` (the canonical picker across the model flows)
  and the custom-provider model list pass `searchable=True`.
- Split `_decode_menu_key` out of `read_menu_key` so the search loop can
  peek the raw key (catch `/`) before nav decoding.
- ESC during active search now clears the query (restores the full list)
  so a no-match filter can't strand the user; printable-key capture is
  restricted to ASCII to avoid Latin-1 mojibake.
- Update two setup-menu tests whose mock signatures predate the new
  `searchable` kwarg; add ranked-scorer + parity + state-machine tests.
2026-06-01 16:58:58 -07:00
Harish Kukreja
53f598e7a2 feat(cli): add fuzzy search helpers for curses pickers
Pure, refactor-independent helpers for type-to-filter search in the
curses single-/radio-select menus: subsequence matching, filtered-index
mapping, cursor reconciliation, scroll clamping, and an active-search
key handler, plus unit tests.

Salvaged from #22758 (the curses event loop was since refactored into a
shared driver on main, so the integration is rebuilt in a follow-up
commit; these pure helpers and their tests carry over unchanged).
2026-06-01 16:58:58 -07:00
kshitijk4poor
7527e7aeac feat: fuzzy search for the model picker (WebUI + TUI)
Adds fuzzy subsequence matching with quality ranking to the model
pickers, replacing the WebUI's exact-substring filter and giving the
TUI a search where it previously had none.

- New fuzzy scorer (ui-tui/src/lib/fuzzy.ts + an identical copy at
  web/src/lib/fuzzy.ts, since the two are separate TS packages with no
  shared module). Matches a query as an ordered subsequence (so `g4o`
  matches `gpt-4o`), scores by quality (exact > prefix > word-boundary >
  contiguous > scattered) and returns matched character positions for
  highlighting. Multi-token AND semantics (`clad snnt` -> claude-sonnet).
  15 vitest tests cover the algorithm.

- WebUI ModelPickerDialog: ranked fuzzy filter on providers + models;
  matched characters in model rows are highlighted via <mark>.

- TUI modelPicker: type-to-filter on the provider and model stages with
  live ranking. Backspace edits the filter, Ctrl+U clears it, Esc clears
  a non-empty filter before navigating back. Persist-global / disconnect
  shortcuts moved from g/d to Ctrl+G / Ctrl+D so letters feed the filter.

Closes #30849
2026-06-01 16:58:58 -07:00
Teknium
c45593ceae docs: expand quickstart Skills section (#37047)
* fix(file_tools): block agent writes to ~/.hermes/config.yaml to prevent silent approval bypass

* fix(approval): pair terminal-side gate for ~/.hermes/config.yaml writes

Subway2023's #14639 blocks write_file/patch to ~/.hermes/config.yaml, but
the terminal side was only partially paired: echo>/tee/cp/mv to config.yaml
already tripped the project-config pattern, while `sed -i` and direct edits
slipped through with auto-approve. An unpaired write_file deny is theater per
SECURITY.md — the agent could flip approvals.mode=off via `sed -i` and the
mtime-keyed config cache reloads it mid-session.

config.yaml IS the security policy (approvals.mode/yolo/permanent allowlist
live there), so it warrants real pairing, not a half-door. Add a
_HERMES_CONFIG_PATH fragment mirroring _HERMES_ENV_PATH, fold it into
_SENSITIVE_WRITE_TARGET (covers tee/>/>>/cp/mv), and add sed -i coverage for
both config.yaml and .env. Pins 9 regression tests including no-regression
guards (reads pass, /tmp writes pass).

Co-authored-by: sbw2025 <subw3@mail2.sysu.edu.cn>

* chore(release): map Subway2023 for PR #14639 salvage

* docs: expand quickstart Skills section

The Skills section was two bare commands with no framing — it never said
what a skill is, how skills load, or what the install slug means. Expanded
to explain the concept, the bundled catalog, install/browse/use flow, and
slash-command activation. Removed the inaccurate /skills chat-command hint
(skills become individual /<name> commands; hermes skills is the CLI verb).

---------

Co-authored-by: sbw2025 <subw3@mail2.sysu.edu.cn>
2026-06-01 16:56:50 -07:00
firefly
128da68823 test(tools): characterize tool-surface TERMINAL_CWD contract (#29265)
Port PR #29365's tool-surface contract test: terminal/file/execute_code
already honor TERMINAL_CWD (out of scope for the resolver cluster). Pinning
the behavior makes the supersession of #29365 airtight and guards against a
future refactor silently regressing the workspace contract.
2026-06-01 16:55:04 -07:00
firefly
ac0cce5f3f test(agent): pin whitespace-strip and OSError-propagation in runtime_cwd
Cover the two new hardening behaviors that were unpinned: whitespace-only
TERMINAL_CWD falling through to getcwd/None, and OSError from the getcwd
fallback arm propagating to the build_environment_hints try/except guard.
2026-06-01 16:55:04 -07:00
firefly
75f478750c docs(test): correct None-semantics comment in test_runtime_cwd (discovery not skipped) 2026-06-01 16:55:04 -07:00
firefly
eadfeef60e docs(agent): correct resolve_context_cwd comment (None → caller getcwd fallback, not skip) 2026-06-01 16:55:04 -07:00
firefly
f90777a6b8 refactor(prompt): route context-file cwd through runtime_cwd resolver 2026-06-01 16:55:04 -07:00
firefly
c79b80a8a5 test(prompt): place cwd regression tests in TestEnvironmentHints (drop redundant docker case) 2026-06-01 16:55:04 -07:00
firefly
16047655b5 fix(prompt): show configured working directory in system prompt (closes #24882, #24969, #27383, #29265) 2026-06-01 16:55:04 -07:00
firefly
2564760d7a test(agent): pin context_cwd isdir-skip asymmetry and tilde expansion 2026-06-01 16:55:04 -07:00
firefly
4bc7296042 feat(agent): add runtime_cwd resolver (single source of truth for working dir) 2026-06-01 16:55:04 -07:00
teknium1
f1237aa95b chore(release): map maxcz79 author email for AUTHOR_MAP 2026-06-01 16:36:43 -07:00
maxcz79
32032e1e2d fix(simplex): avoid reconnecting healthy idle websocket
Do not treat lack of application-level SimpleX events as a stale WebSocket. The websockets client already uses protocol ping/pong for connection liveness, so quiet but healthy connections should not be closed by the health monitor.
2026-06-01 16:36:43 -07:00
Teknium
e946f49ab5 fix(models): add gemini-3.5-flash to Gemini OAuth + API-key pickers (#37046)
* fix(file_tools): block agent writes to ~/.hermes/config.yaml to prevent silent approval bypass

* fix(approval): pair terminal-side gate for ~/.hermes/config.yaml writes

Subway2023's #14639 blocks write_file/patch to ~/.hermes/config.yaml, but
the terminal side was only partially paired: echo>/tee/cp/mv to config.yaml
already tripped the project-config pattern, while `sed -i` and direct edits
slipped through with auto-approve. An unpaired write_file deny is theater per
SECURITY.md — the agent could flip approvals.mode=off via `sed -i` and the
mtime-keyed config cache reloads it mid-session.

config.yaml IS the security policy (approvals.mode/yolo/permanent allowlist
live there), so it warrants real pairing, not a half-door. Add a
_HERMES_CONFIG_PATH fragment mirroring _HERMES_ENV_PATH, fold it into
_SENSITIVE_WRITE_TARGET (covers tee/>/>>/cp/mv), and add sed -i coverage for
both config.yaml and .env. Pins 9 regression tests including no-regression
guards (reads pass, /tmp writes pass).

Co-authored-by: sbw2025 <subw3@mail2.sysu.edu.cn>

* chore(release): map Subway2023 for PR #14639 salvage

* fix(models): add gemini-3.5-flash to Gemini OAuth + API-key pickers

#34581 swapped gemini-3-flash-preview -> gemini-3.5-flash in the
OpenRouter and Nous lists but missed the curated Gemini catalogs, so
the Google OAuth (google-gemini-cli) picker still offered the retired
gemini-3-flash-preview slug and gemini-3.5-flash was unselectable.

Per Google's docs gemini-3-flash-preview was renamed to gemini-3.5-flash
and is served via Cloud Code Assist, so this completes the rename for:
- google-gemini-cli (OAuth/Code Assist) picker
- gemini (API-key) picker
- gemini provider default_aux_model

copilot keeps gemini-3-flash-preview (separate backend, own slug).

---------

Co-authored-by: sbw2025 <subw3@mail2.sysu.edu.cn>
2026-06-01 16:31:13 -07:00
Teknium
1ffa22ee6b fix(minimax): drop stale ≤204,800 cache entries for MiniMax-M3 (#36726)
M3 is 1M context, but pre-catalog builds resolved it via the generic
'minimax' catch-all (204,800) and persisted that to the context-length
cache. Step 1 of get_model_context_length returned the cached value
directly before reaching the 'minimax-m3' (1M) catalog entry, so users
who first probed M3 on an older build were stuck at 204K forever (e.g.
/new in the Telegram gateway showing 'Context: 204K tokens (detected)').

Mirror the existing Kimi/Codex stale-cache guards: when a cached entry
for a minimax-m3 slug is <= 204,800, drop it and re-resolve. M2.x slugs
(correctly 204,800) are untouched since they don't match the M3 name.
2026-06-01 14:59:07 -07:00
Ben
b9646276fd fix(utils): guard os.fchmod for Windows in atomic_json_write
os.fchmod is Unix-only; the Windows os module has no fchmod (only
chmod). Passing mode= (e.g. 0o600 when saving the Hindsight config
during `hermes memory setup`) crashed on Windows with:

    AttributeError: module 'os' has no attribute 'fchmod'

Guard the fchmod fast-path with hasattr(os, "fchmod"). Skipping it on
Windows is safe: mkstemp already creates the temp file as 0o600, and
the existing post-replace os.chmod(real_path, mode) — already wrapped
in try/except — applies the final mode durably (as far as Windows
honors it).

Adds regression tests: one simulating a Windows os module without
fchmod (must not raise), and one asserting the durable 0o600 mode on
POSIX.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 09:57:10 -07:00
kshitij
a5371b3e68 chore: add benfrank241 to AUTHOR_MAP (#36898)
Maps ben.bartholomew@vectorize.io -> benfrank241 so the contributor
attribution audit passes when their commit lands via #36824.
2026-06-01 16:47:07 +00:00
Max Hsu
038ed94a6c fix(cli): reset terminal input modes on TUI exit to stop focus/mouse leaks
When the TUI exits via Ctrl+C, SIGTERM/SIGHUP, or a crash, prompt_toolkit's
teardown can be bypassed, leaving DEC 1004 (focus reporting) and 1000/1002/1003
(mouse tracking) enabled. The terminal then emits raw ESC[I/ESC[O focus events
and fragmented SGR mouse reports as visible text in whatever runs next in the
same tab.

_run_cleanup() — the once-only cleanup that runs on every catchable exit path
(atexit-registered + called on the normal/EOF/interrupt exit) — now emits
_TERMINAL_INPUT_MODE_RESET_SEQ (the same disable sequence the in-session leak
recovery already uses) as its FIRST step, so the terminal is usable immediately
on Ctrl+C and a later teardown step raising can't skip it.

The reset is gated on a new _tui_input_modes_active flag (set right before
app.run(), cleared once the modes are disabled) so non-TUI one-shot CLI runs —
which share _run_cleanup via atexit — don't emit codes for modes they never
enabled. Writes to sys.stdout when it's the terminal, else falls back to
/dev/tty. SIGKILL is uncatchable and the kanban worker's os._exit(0) bypasses
atexit, but both are non-TTY/non-TUI so there is nothing to reset there.

Adds tests/cli/test_tui_terminal_reset_on_exit.py (9): emits on a TTY when the
TUI ran, no-ops when the TUI never ran, /dev/tty fallback when stdout is
redirected, no-op when neither is available, swallows stdout errors, flag set
and cleared, and wired into _run_cleanup as the first step even when a later
step raises.

Fixes #36823

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 23:27:44 +08:00
teknium1
ef3a650f05 chore(release): map Subway2023 for PR #14639 salvage 2026-06-01 03:29:48 -07:00
teknium1
4e9d886d9d fix(approval): pair terminal-side gate for ~/.hermes/config.yaml writes
Subway2023's #14639 blocks write_file/patch to ~/.hermes/config.yaml, but
the terminal side was only partially paired: echo>/tee/cp/mv to config.yaml
already tripped the project-config pattern, while `sed -i` and direct edits
slipped through with auto-approve. An unpaired write_file deny is theater per
SECURITY.md — the agent could flip approvals.mode=off via `sed -i` and the
mtime-keyed config cache reloads it mid-session.

config.yaml IS the security policy (approvals.mode/yolo/permanent allowlist
live there), so it warrants real pairing, not a half-door. Add a
_HERMES_CONFIG_PATH fragment mirroring _HERMES_ENV_PATH, fold it into
_SENSITIVE_WRITE_TARGET (covers tee/>/>>/cp/mv), and add sed -i coverage for
both config.yaml and .env. Pins 9 regression tests including no-regression
guards (reads pass, /tmp writes pass).

Co-authored-by: sbw2025 <subw3@mail2.sysu.edu.cn>
2026-06-01 03:29:48 -07:00
sbw2025
8f2931e3ee fix(file_tools): block agent writes to ~/.hermes/config.yaml to prevent silent approval bypass 2026-06-01 03:29:48 -07:00
Teknium
023149f665 fix(agent): stop reporting broken streams as output-length truncation (#36705)
A stream that drops mid-response after tokens are delivered (peer-closed
connection, stale-stream reconnect) is converted into a synthetic
finish_reason="length" stub. The conversation loop treated that network
stall as a max-output-tokens truncation: when the dropped content was a
tool call it retried exactly once, then hard-failed with "Response
truncated due to output length limit" — even on large-output models that
never hit any cap (e.g. Opus).

- Tool-call truncation now retries up to 3 times (was 1) with a
  progressive max_tokens boost, and is stub-aware: a PARTIAL_STREAM_STUB_ID
  stall prints "Stream interrupted mid tool-call — retrying (n/3)" instead
  of the false "model hit max output tokens", and the give-up message
  distinguishes a network drop from a real truncation.
- Length-continuation retries preserve the original request's output cap
  as a floor, so a high provider/model default isn't silently downshifted
  to 8K/12K on retry.
- Added _requested_output_cap_from_api_kwargs() helper.

Tests: stub-stall mid-tool-call recovery within 3 retries; continuation
preserves a large provider-default output cap.

Fixes #26425. Salvages the substance of #26427 (cap floor) and #9525
(retry bump), adapted to the post-refactor conversation_loop.py which
handles all three api_modes uniformly.

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Co-authored-by: ygd58 <ygd58@users.noreply.github.com>
2026-06-01 03:01:20 -07:00
Teknium
b571ec298d feat(dashboard): full administration panel — MCP, pairing, webhooks, credentials, memory, gateway, ops (#36704)
* feat(dashboard): backend API for MCP, pairing, webhooks, credential pool, memory, gateway lifecycle

Adds REST endpoints so a remote admin can manage these without CLI access:
- MCP servers: list/add/remove/test (config.yaml parity with hermes mcp)
- Pairing: list/approve/revoke/clear-pending messaging codes
- Webhooks: list/subscribe/remove (hot-reloaded JSON store)
- Credential pool: list/add/remove rotation keys (via CredentialPool API)
- Memory provider: status/select/disable/reset
- Gateway lifecycle: start/stop (restart+update already existed)

Secrets redacted on read; usable values only reach the agent at session start.
All endpoints sit behind the existing dashboard auth gate.

* feat(dashboard): backend API for ops + skills hub

- Ops actions (spawned, log-tailed via /api/actions): doctor, security audit,
  backup, import, checkpoints prune
- Ops reads (structured JSON): hooks list + allowlist status, checkpoints list
  with per-session size
- Skills hub actions (spawned): install / uninstall / update
- Registers new action log files for all spawn-based endpoints

All gated by the existing dashboard auth middleware.

* feat(dashboard): admin pages for MCP, pairing, webhooks, and system ops

Adds four new dashboard pages + nav entries so a remote admin can manage
Hermes without CLI access:
- MCP: list/add/remove/test MCP servers
- Webhooks: list/create/delete subscriptions (one-time secret reveal)
- Pairing: approve/revoke/clear messaging pairing codes
- System: gateway start/stop/restart, memory provider + reset, credential
  pool add/remove, ops (doctor/audit/backup/import/skills update) with a
  live action-log viewer, checkpoints prune, shell-hooks status

api.ts: client methods + types for all new endpoints.
App.tsx: routes + sidebar nav (plain labels, no i18n key required).

Verified: tsc -b clean, production build succeeds, new pages lint clean,
zero new eslint errors in App.tsx.

* test(dashboard): cover admin API endpoints

20 tests across MCP, credential pool, memory, pairing, webhooks, ops, plus
an auth-gate parametrize that asserts every admin endpoint requires the
session token. Asserts request contract + CLI-config parity, not catalog
values (per the no-change-detector-tests rule).

* docs(dashboard): document MCP, Webhooks, Pairing, and System admin pages

Adds Pages sections for the four new admin tabs and an Admin-endpoints table
to the REST API reference. Updates the page description to reflect the
dashboard's expanded role as a full administration panel.
2026-06-01 02:58:02 -07:00
Teknium
2ed96372ad feat(skills): blank-slate skills — install --no-skills + opt-out/opt-in (#36228)
* feat(install): --no-skills flag for blank-slate default profile

Add an install-time --no-skills flag so the default ~/.hermes profile can
be created with zero bundled skills, matching what
`hermes profile create --no-skills` already does for named profiles.

The flag writes $HERMES_HOME/.no-bundled-skills and skips the install-time
seed. sync_skills() now honors that marker with an early return
(skipped_opt_out=True), so neither the installer, a later `hermes update`,
nor a direct sync re-injects bundled skills into a profile that opted out.

Previously the marker was only checked by seed_profile_skills() (named
profiles); the default profile had no opt-out and `hermes update` would
re-seed it every time.

Tests: TestNoBundledSkillsOptOut covers marker-present (no-op) and
marker-absent (normal seed) paths.

* feat(skills): hermes skills opt-out / opt-in for existing profiles

Adds an interactive counterpart to the install-time --no-skills flag so
an already-installed profile (default or named) can toggle the
.no-bundled-skills marker without reinstalling.

- `hermes skills opt-out` writes the marker (stop future seeding). Safe
  by default: nothing on disk is touched.
- `hermes skills opt-out --remove` ALSO deletes already-present bundled
  skills, but ONLY ones that are manifest-tracked AND byte-identical to
  their origin hash. User-edited bundled skills, hub-installed skills, and
  hand-written skills are never removed. Previews + confirms before
  deleting (--yes to skip).
- `hermes skills opt-in [--sync]` removes the marker and optionally
  re-seeds immediately.

Core logic lives in tools/skills_sync.py (set_bundled_skills_opt_out,
is_bundled_skills_opt_out, remove_pristine_bundled_skills) reusing the
existing manifest origin-hash machinery for the safety check.

Tests: TestOptOutToggleAndRemove covers marker toggle idempotency and
proves user-modified + non-bundled skills survive --remove.

* docs: blank-slate skills — install --no-skills + opt-out/opt-in

- features/skills.md: new 'Starting with a blank slate' section covering
  the install flag, profile-create flag, and runtime opt-out/opt-in, with
  a safe-by-default note.
- reference/cli-commands.md: document the new skills opt-out / opt-in
  subcommands + examples.
- reference/profile-commands.md: fix the marker filename (was .no-skills,
  actually .no-bundled-skills) and cross-link the runtime commands.

Validated with a full docusaurus build (exit 0); the three edited pages
compile clean with no new warnings.
2026-06-01 02:57:57 -07:00
Teknium
70e1571d89 feat(curator): prune built-in skills after inactivity + track usage for all skills (#36701)
Two related changes to the skill curator:

1. Built-in pruning. New curator.prune_builtins config (default on) lets the
   curator archive bundled built-in skills after the inactivity period, not
   just agent-created ones. A .curator_suppressed list tells the update-time
   re-seeder (tools/skills_sync) to leave pruned built-ins archived, so the
   prune is durable across `hermes update`. Built-ins are seeded with a
   baseline record on first sight, so the inactivity clock starts at upgrade
   time -- no mass-prune on the first run. Hub-installed skills are never
   pruned regardless of the flag. Restoring a built-in clears its suppression.

2. Usage tracking for all skills. Telemetry (view/use/patch) was wrongly gated
   behind curation-eligibility, so built-ins were tracked only when prunable
   and hub skills never. Telemetry is observability and is now decoupled from
   curation: every skill accrues usage counts regardless of provenance, while
   lifecycle mutators (set_state/set_pinned/mark_agent_created) stay
   curation-gated. New usage_report() + provenance() expose all skills with an
   agent/bundled/hub tag.
2026-06-01 02:07:32 -07:00
Teknium
0622a70eb4 feat(gateway): bring /undo [N] to messaging platforms (parity with CLI/TUI) (#36699)
Gateway /undo was wired into every platform but still ran the old
single-turn hard-truncate. Now it matches the CLI/TUI: /undo [N] backs
up N user turns (default 1, clamps to oldest), soft-deletes the
truncated rows on disk (active=0, kept for audit, hidden from re-prompts
and search) via SessionDB.rewind_to_message, evicts the cached agent so
the next turn rebuilds from the active-only transcript (the gateway's
equivalent of the CLI's in-place history surgery + memory invalidation),
and echoes the backed-up message text so the user can copy/edit and
resend — platforms have no editable composer to prefill.

- gateway/session.py: SessionStore.rewind_session(session_id, n) wraps
  the soft-delete primitive; load_transcript already returns active-only
- gateway/run.py: _handle_undo_command parses [N], calls rewind_session,
  evicts the agent, echoes target text; confirm-prompt detail is count-aware
- locales: undo.removed gains {turns}; new undo.invalid_count, all 16 langs
- tests: tests/gateway/test_undo_rewind_session.py (6 cases)
2026-06-01 02:04:14 -07:00
Teknium
ba6ffd4ff1 fix(skills-guard): stop flagging benign skill content + honor skill ignore files (#36231)
The skill security scanner blocked legitimate community skills on three
intrinsic false-positive patterns:

- read_secrets_file matched `cat > file.env <<` heredocs (writing the
  user's own keys into their own local .env), not just `cat file.env`
  reads. Exclude output redirections.
- allowed-tools frontmatter is REQUIRED by the agent-skill spec; every
  compliant skill declares it. Drop from HIGH privilege_escalation to a
  LOW informational finding so it no longer drives the verdict.
- python_os_environ flagged `os.environ.get("CONFIG_VAR")` config reads
  as HIGH exfiltration. Exempt non-secret `.get()` reads; add a dedicated
  CRITICAL python_environ_get_secret pattern so secret-named reads
  (OPENAI_API_KEY etc.) are still caught.

Also: scan_skill() now honors a skill-provided .skillignore / .clawhubignore
(gitignore-style) so dev/docs artifacts shipped in a skill root are excluded
from both structural checks and pattern scanning. SKILL.md is never ignorable.

80 tests pass (64 existing + 16 new).
2026-06-01 01:58:48 -07:00
Teknium
9074a154c5 feat: explain Quick Setup vs Full setup inline in the first-time setup menu (#36227)
The setup-mode chooser showed two bare labels ('Quick Setup (Nous
Portal) — OAuth login, model & messaging' / 'Full setup — configure
everything') that didn't explain what Quick Setup actually is. Expand
both labels inline so each choice line carries a concise explanation:

  Quick Setup (Nous Portal) — free OAuth login, no API keys, model + tools
  Full setup — configure every provider, tool & option yourself (bring your own keys)

Single-file change to the choice labels; no new plumbing.
2026-06-01 01:58:30 -07:00
Teknium
92a567db2d fix(ci): regen model catalog + stop gui tests consuming macos-fixup subprocess calls (#36687)
Two pre-existing failures on main, unrelated to each other:

- test_model_catalog: website/static/api/model-catalog.json was stale vs
  _PROVIDER_MODELS — minimax/minimax-m2.7 was renamed to minimax/minimax-m3
  without regenerating the committed manifest. Ran scripts/build_model_catalog.py.

- test_gui_command: the macOS relaunchable-signing fixup
  (_desktop_macos_relaunchable_fixup) makes two subprocess.run calls (xattr +
  codesign) on darwin before launch. The two darwin GUI tests set
  sys.platform='darwin' and mock subprocess.run with a 2-element side_effect
  (pack + launch), so the fixup's calls drained the iterator -> StopIteration.
  Mock out the fixup in those two tests so the subprocess accounting stays
  focused on pack/launch.
2026-06-01 01:39:03 -07:00
Teknium
e1951ce704 fix(memory): only forward rewound kwarg when set
The on_session_switch fan-out passed rewound=rewound unconditionally,
injecting rewound=False into every provider's **kwargs on the common
/resume, /branch, /new, and compression paths. Providers that capture
extra kwargs into an 'extra' dict (and the exact-dict-equality tests
guarding them) broke. Forward rewound only when truthy; /undo sets it
explicitly, everyone else stays clean.
2026-06-01 01:22:38 -07:00
Teknium
3f7d1c801d feat(undo): /undo [N] backs up N user turns with prefill + soft-delete
Extends the existing /undo command from a single in-memory exchange
removal into a full rewind: back up N user turns (default 1), soft-delete
the truncated rows in SessionDB (active=0, kept for audit, hidden from
re-prompts and search), notify memory providers, and prefill the composer
with the backed-up message text for editing — CLI and TUI.

Reuses the SessionDB rewind primitives, the on_session_switch(rewound=True)
memory hook, and the TUI command.dispatch prefill payload from SaguaroDev's
#21910 work, wired to /undo [N] instead of a separate /rewind picker.

- cli.py: undo_last(n, prefill) — in-memory truncate + SQLite soft-delete
  + agent surgery (system-prompt invalidate, flush-index reset) + memory
  notify + editable buffer prefill; /undo dispatch parses optional count;
  checkpoint-rollback caller passes prefill=False
- tui_gateway/server.py: command.dispatch undo branch (was rewind) parses
  count, picks Nth-from-last user turn, clamps to oldest
- commands.py: /undo gains [N] args_hint
- tests: rename + expand TUI suite (multi-turn, clamp, invalid-count)
- release.py: AUTHOR_MAP entry for SaguaroDev

Co-authored-by: SaguaroDev <74339271+SaguaroDev@users.noreply.github.com>
2026-06-01 01:22:38 -07:00
SaguaroDev
243e836dce feat(tui): wire /rewind through command.dispatch + prefill payload (#21910)
Adds the TUI half of the /rewind feature so the Ink terminal UI gets
the same affordance as the prompt_toolkit CLI.

Python side (tui_gateway/server.py):
- /rewind added to _PENDING_INPUT_COMMANDS so slash.exec rejects it
  and the TUI falls through to command.dispatch (the only path with
  access to live session state + memory hooks).
- New command.dispatch branch for name == "rewind":
  v1 auto-picks the most recent user turn (Claude-Code-style single-
  step undo), calls SessionDB.rewind_to_message, refreshes the
  in-memory history, fires _memory_manager.on_session_switch with
  rewound=True, and returns the new "prefill" payload.
- A dedicated picker overlay (multi-step rewind) is tracked as a
  follow-up to #21910.

TS side (ui-tui/src/):
- New "prefill" variant on CommandDispatchResponse + asCommandDispatch
  validator. Mirrors "send" but does NOT auto-submit; the client drops
  the message into the composer for editing.
- createSlashHandler renders the optional notice via sys() and calls
  ctx.composer.setInput(d.message), letting the user edit-and-resubmit
  the rewound turn — the core UX promised by the issue.

Tests:
- 7 new tui_gateway tests covering prefill payload shape, in-memory
  history truncation, DB soft-delete, memory-provider notification
  (rewound=True), busy-session refusal, missing-session error, and
  registry placement in _PENDING_INPUT_COMMANDS.
- Extended asCommandDispatch vitest covering the new prefill variant
  (with + without notice, and rejection of malformed payloads).

Out of scope for v1 (tracked as #21910 follow-up):
- Dedicated picker overlay in Ink (the multi-step rewind UI). v1 auto-
  picks the most recent user turn, matching the most common case.
- Gateway platforms (Telegram, Discord, etc.) — issue scopes v1 to
  CLI + TUI only.
2026-06-01 01:22:38 -07:00
SaguaroDev
31cfa08c66 feat(memory): add rewound kwarg to on_session_switch hook 2026-06-01 01:22:38 -07:00
SaguaroDev
3e59be0c41 feat(state): add messages.active flag + rewind primitives (#21910)
Schema v12 adds:
- messages.active (default 1) — soft-delete flag for /rewind
- sessions.rewind_count (default 0) — audit counter
- idx_messages_session_active deferred index

New SessionDB methods:
- rewind_to_message(session_id, target_message_id) — soft-deletes rows
  >= target_id, refuses non-user targets, increments rewind_count
- restore_rewound(session_id, since_message_id) — undo for stretch goal
- list_recent_user_messages — picker source

Existing methods get include_inactive kwarg (default False):
- get_messages, get_messages_as_conversation, search_messages.
  Rewound rows excluded from session_search by default — opt-in for audit.

The deferred index pattern (DEFERRED_INDEX_SQL run after _reconcile_columns)
avoids 'no such column: active' on legacy pre-v12 databases, since
executescript(SCHEMA_SQL) runs before column reconciliation.
2026-06-01 01:22:38 -07:00
kshitijk4poor
6c73e8ffaa fix(gateway): keep code blocks verbatim in cleaned text when media present
Self-review of the code-block masking fix: the cleanup path ran
media_pattern.sub('') over the _mask_protected_spans() copy of the text and
assigned that back to 'cleaned', so whenever a real MEDIA: tag was delivered
(if media: branch), every fenced code block / inline code / blockquote in the
reply was blanked to whitespace in the user-visible text.

Now mask only a length-equal copy of 'cleaned' to locate the real tag spans,
then delete those spans from the unmasked 'cleaned' — masking is a locator,
not a text rewrite. Protected spans survive verbatim. Strengthens the existing
mixed-code test (it only asserted 'Done.' survived, not the code block) and
adds an inline-code-survives regression test. Both fail on the old sub-based
code and pass now.
2026-06-01 00:00:26 -07:00
kshitijk4poor
ec6261ae2f chore(release): add VinciZhu to AUTHOR_MAP for #16721 salvage 2026-06-01 00:00:26 -07:00
liuhao1024
3ccf4fdc6d fix(gateway): skip MEDIA: tags inside code blocks and blockquotes
extract_media() scanned the full response text without distinguishing
live delivery tags from example paths in fenced code blocks, inline code
spans, and blockquotes. This caused false positives where the agent's
explanation of MEDIA: syntax (or tool output containing example paths)
was stripped from user-visible text and the path was added to the media
delivery list.

Added _mask_protected_spans() helper that replaces protected regions
with equal-length whitespace before regex matching, preserving match
offsets. The helper skips backtick-quoted paths in MEDIA: tags to
maintain existing path extraction behavior.

Fixes #35695
2026-06-01 00:00:26 -07:00
VinciZhu
521d06975e fix(gateway): restrict auto-appended media to producer tools 2026-06-01 00:00:26 -07:00
kshitijk4poor
fb1b681b3b fix(gateway): keep JSON-embedded MEDIA: text verbatim in cleaned output
Self-review of #34375 fix: the cleanup path ran media_pattern.sub('') over
the JSON-masked copy of the text, which baked the masking spaces into the
user-visible 'cleaned' string — a serialized tool result like
{"old":"MEDIA:/x.png"} came back as {"old":"          "}.

Now mask only a length-equal copy of 'cleaned' to locate the real tag spans,
then delete those spans from the unmasked 'cleaned'. Real tags are stripped;
JSON-embedded MEDIA: text reads back verbatim. Masking 'cleaned' (not the
original 'content') keeps offsets valid after the [[audio_as_voice]] /
[[as_document]] directives are removed. Adds two cleaned-text regression tests.
2026-05-31 23:51:42 -07:00
liuhao1024
e8827ef704 fix(gateway): skip MEDIA: inside serialized JSON string values
Serialized tool results frequently embed a prior reply's text, e.g.
{"result": "MEDIA:/path/stale.png"}. The bare-path branch of
MEDIA_TAG_CLEANUP_RE matched these and re-delivered stale files (#34375).

Adds BasePlatformAdapter._mask_json_string_media, which blanks (offset-
preserving) only MEDIA:<bare-path> tokens that sit inside a JSON value-
context string (opened by : , { or [). Legitimate tags at line start,
after prose, indented, MEDIA:"quoted" form, and two-line TTS output are
all left untouched.

Reworked from the approach in #34388 (a line-start regex anchor), which
no longer applied to current main and regressed same-line/indented tags.

Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
2026-05-31 23:51:42 -07:00
Nicolay
b3aaf2676b fix(docker): discover Playwright headless_shell browser (#35717)
Co-authored-by: Nic <nicsequenzy@gmail.com>
2026-06-01 16:06:44 +10:00
Ben Barclay
e3998d4714 chore(attribution): map polnikale for PR #35717 (#36273)
Adds nicsequenzy@gmail.com -> polnikale to AUTHOR_MAP so the
check-attribution gate passes for the Playwright headless_shell browser
discovery fix (#35717).
2026-06-01 16:05:06 +10:00
Amin Vakil
f106e58afa fix(docker): create s6 envdir before browser path export (#34601) 2026-06-01 15:44:30 +10:00
Ben Barclay
c1a531d063 fix(dashboard): guard update endpoint in Docker with structured guidance (salvage #34831) (#36263)
* fix: guard dashboard update in Docker

* fix(dashboard): align action response type

---------

Co-authored-by: Donovan Yohan <donovan-yohan@users.noreply.github.com>
Co-authored-by: Donovan Yohan <34756395+donovan-yohan@users.noreply.github.com>
2026-06-01 15:39:35 +10:00
brooklyn!
359f2be12e feat(desktop): drop files anywhere in the chat area (#36262)
* feat(desktop): drop files anywhere in the chat area

File drops were only wired to the composer input. Add a reusable
useFileDropZone hook (enter/leave depth counting + capture-phase reset so
the affordance clears even when the composer claims the drop) and a
pointer-events-none ChatDropOverlay, wired onto the conversation viewport.
Drops funnel through the existing onAttachDroppedItems; composer drops keep
their own inline-ref behavior.

* fix(desktop): chat-area drops insert inline @file refs, not attachment cards

Match the composer-input drop behavior — funnel dropped paths through
droppedFileInlineRef + the composer insert bus so they render as inline
ref chips instead of attachment cards.

* fix(desktop): don't render bare file paths as tool images (404)

vision_analyze reports its input image as a local filesystem path, which
toolImageUrl handed straight to <img src>. In the renderer that resolves
against the dev-server origin and 404s. Restrict inline tool images to
fetchable sources (data: URLs and remote http(s)); bare paths now fall
back to the tool's codicon.
2026-06-01 00:30:39 -05:00
Ben Barclay
e1eba6f8cc fix(dashboard-auth): drop /api/* paths from OAuth next= round trip (#36244)
When an unauthenticated SPA fetch hit a gated /api/* endpoint (e.g.
GET /api/analytics/models?days=30 fired from ModelsPage on mount or
after a session expiry), the gated middleware stamped the request's
own path into next= on the 401 envelope's login_url. The SPA's global
401 handler in web/src/lib/api.ts full-page-navigated to that URL,
the PKCE cookie carried the encoded /api/* value through the OAuth
round trip to Portal, and /auth/callback's _validate_post_login_target
accepted it as same-origin and redirected the user to the raw JSON
endpoint instead of the dashboard.

Symptom Ben reported: after the OAuth screen he kept landing on
$DOMAIN/api/analytics/models?days=30 (raw JSON) rather than /models.
The bug was deterministic per page — whichever /api/* call ModelsPage,
AnalyticsPage, or SessionsPage fired first owned the redirect race.

Fix: both validators now reject /api/* targets in addition to the
existing /login, /auth/, /api/auth/ exclusions:

  - _safe_next_target in middleware.py drops the value before it ever
    enters login_url, so the SPA's 401 handler navigates to a bare
    /login (which the SPA itself can return-from via its own
    sessionStorage["hermes.lastLocation"] fallback that was already
    saving the actual browser location).
  - _validate_post_login_target in routes.py drops it as second-line
    defence at the callback boundary, so a legacy cookie, a regressed
    middleware, or an attacker-crafted /auth/login?next=/api/... value
    can't smuggle the redirect through. Either layer alone is enough;
    pairing them means a regression in one is caught by the other.

The match is anchored: ``decoded == "/api"`` or
``decoded.startswith("/api/")``. SPA route lookalikes like /apidocs
or /api-keys remain valid landing targets — tests pin that.

Test additions in test_dashboard_auth_401_reauth.py:

  - TestApi401Envelope: rewrote test_login_url_carries_next_for_deep_
    api_path (which asserted the pre-fix behaviour) as
    test_login_url_drops_next_for_deep_api_path, plus added the
    specific analytics-models repro case from Ben's report.
  - TestNextSameOriginValidation: rejects-api-paths + does-not-reject-
    api-prefix-lookalikes (covers /apidocs, /api-keys).
  - TestAuthCallbackNext: end-to-end test_callback_with_api_next_
    lands_at_root drives /auth/login?next=/api/... through to the
    callback and asserts the user lands at "/", not the API URL.
  - TestValidatePostLoginTarget: new class covering the callback-side
    validator directly, including the URL-encoded ``%2Fapi%2F...``
    form the PKCE cookie actually carries.

Mutation-tested: reverting both validators causes exactly the 5 new
or rewritten /api/*-related assertions to fail (each fix layer is
independently tested), while the 31 other assertions in the file
remain green. Full tests/hermes_cli/ suite (288 files, 5,938 tests)
passes with the fix applied.
2026-06-01 15:10:20 +10:00
brooklyn!
7fbe9b79ab fix(desktop): add missing PATCH /api/sessions/{id} so rename works (#36249)
The desktop rename dialog sent PATCH /api/sessions/{id}, but the backend
only defined GET and DELETE for that path — FastAPI returned 405 Method
Not Allowed, surfaced to the user as "Rename failed". Add the PATCH route
backed by SessionDB.set_session_title (handles sanitization, uniqueness,
and clearing the title when empty).

Also fix a misleading notification: any 405 was summarized as an unrelated
"does not support that audio endpoint" message. Make it a generic 405 hint.
2026-06-01 00:01:28 -05:00
Ben Barclay
bdceedf784 fix(docker): chown hermes-owned top-level state files on boot (#35098) (#36236)
The targeted data-volume chown in stage2-hook.sh only covers hermes-owned
*subdirectories*; loose state files living directly under $HERMES_HOME
(auth.json, state.db, gateway.lock, gateway_state.json, …) are missed.
When created or rewritten by `docker exec <container> hermes …` (root
unless `-u` is passed) they land root-owned, and the unprivileged hermes
runtime then hits PermissionError on next startup, producing a gateway
restart loop.

Fix: reset ownership of an explicit allowlist of hermes-owned top-level
files on every boot. The list mirrors the top-level file entries of
hermes_cli.profile_distribution.USER_OWNED_EXCLUDE plus the runtime lock
files.

This uses a targeted allowlist rather than the originally-proposed blanket
`find $HERMES_HOME -maxdepth 1 -user root` sweep, preserving the
targeted-ownership contract from #19788 / PR #19795: a bind-mounted
$HERMES_HOME may contain host-owned files Hermes does not manage, and
those must never be chowned. Verified end-to-end: allowlisted root-owned
files are reset to hermes on restart while a non-allowlisted host file
keeps its root ownership.

Co-authored-by: x1am1 <2663402852@qq.com>
2026-06-01 14:38:08 +10:00
brooklyn!
0bc616ecf9 fix(desktop): darken light-mode code comment color for legibility (#36234)
Shiki's github-light-default colors comments #6e7781 (~4.2:1 on the code
card background), which is borderline unreadable at the 11px code font
size — and worst for shell snippets, where a single `#` turns the rest
of the line into one long comment span. Remap light-mode comments to
GitHub's darker muted gray (#57606a, ~6.4:1) via per-theme
colorReplacements. Dark mode (~6.1:1) reads fine and is left untouched.
2026-05-31 23:21:58 -05:00
helix4u
b14e15c48e fix(gateway): clean service restart notifications 2026-05-31 21:05:53 -07:00
Nacho Avecilla
380ce4789b Remove prviliges drop when you never ran as root (#34837) 2026-06-01 13:54:18 +10:00
Bartok
064875a540 fix(docker): support s6 /init images in terminal sandbox (#34628) (#34635)
s6-overlay images (e.g. hermes-agent:latest) use /init as PID 1 and exec
/run/s6/basedir/bin/init during stage0 startup. The Docker terminal backend
unconditionally added Docker --init and mounted /run as noexec, which broke
those images in two ways: --init created a second competing PID-1 init, and
the noexec /run made s6 stage0 fail with "exec: /run/s6/basedir/bin/init:
Permission denied" (exit 126), so the container died and terminal commands
reported a generic "container is not running" error.

Detect images whose entrypoint is /init via 'docker image inspect' and, for
those images only, skip Docker --init and mount /run with exec. All other
images keep the hardened --init + noexec defaults. Detection is best-effort:
any inspect failure falls back to the safe defaults.
2026-06-01 13:46:04 +10:00
Bartok
a60bff282e fix(docker): add /usr/bin/tini compatibility shim for legacy wrappers (#34192) (#34382)
#34192 reports Hostinger's 'Hermes WebUI' catalog crashes on startup
with:

  /usr/bin/tini: No such file or directory

The image moved from tini to s6-overlay as PID 1 (/init) earlier in
2026. Orchestration templates that still pin /usr/bin/tini as the
entrypoint \u2014 like the Hostinger Hermes WebUI catalog \u2014 have no
binary to exec and the container crashes immediately.

Hermes has no control over the Hostinger catalog template, but we can
make the image backward-compatible by symlinking /usr/bin/tini -> /init
during the s6-overlay install step. External wrappers that exec
/usr/bin/tini will land on the same s6-overlay reaper they would have
landed on if they'd used the canonical /init entrypoint.

The image's own ENTRYPOINT continues to be /init verbatim \u2014 the shim
is purely for legacy external wrappers, not for the image's own
runtime path. Once affected catalogs are updated, the symlink can be
removed.

Other issues #34192 raises that are NOT addressed by this PR:

  * Problem #2 (UID 1024 vs 10000 mismatch): already fixed by #33148
    (S6_KEEP_ENV=1) and #32412 (with-contenv shebangs). The Hostinger
    template likely needs to update its env-var propagation.

  * Problem #3 (incompatible session formats): RFC for pluggable
    SessionDB is tracked in #23717.

  * Problem #4 (Telegram polling conflict): an operations problem on
    Hostinger's side, not in this codebase.

This PR is scoped to the one issue that can be fixed inside
Dockerfile: the missing /usr/bin/tini binary.

Tests (3 in test_dockerfile_tini_compat_shim.py):

  - test_tini_compat_symlink_present
    Guard: the symlink line must exist in Dockerfile.
  - test_tini_compat_comment_explains_why
    The #34192 anchor comment must be present so future readers know
    why the shim is there (avoid accidental removal).
  - test_entrypoint_still_init_not_tini
    Sanity check: ENTRYPOINT remains /init (s6-overlay). The shim is
    only for external wrappers.

Refs: #34192
Partial fix: addresses the immediate tini-binary crash. Catalog-side
fixes still needed by Hostinger for the UID and session-format
problems documented in the issue.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-01 13:32:55 +10:00
Bartok
740fb28d02 fix(config): chown ensure_hermes_home dirs to HERMES_UID/GID in Docker (#34107) (#34268)
Fixes #34107. When Hermes runs in Docker with HERMES_UID=1000 /
HERMES_GID=911, the entrypoint chowns the top-level HERMES_HOME once
at startup — but subdirectories created at runtime by
ensure_hermes_home() (especially for profile namespaces under
profiles/<name>/ spawned by kanban workers) were landing as root:root
and blocking subsequent uid-mapped worker invocations with:

  PermissionError: [Errno 13] Permission denied:
    '/opt/data/profiles/charles/logs/curator'

Fix: add _resolve_hermes_uid_gid + _chown_to_hermes_uid helpers that
read the env vars and apply chown after mkdir. Invoke from _secure_dir
which already runs after every directory creation in the home-init path,
so all newly-created subdirs (including the profile namespaces) get the
right ownership.

Safety properties:

- No-op when HERMES_UID/HERMES_GID unset (the dominant non-Docker path)
- No-op on Windows (os.chown doesn't exist; AttributeError swallowed)
- No-op when running as non-root (EPERM swallowed — the entrypoint's
  startup chown -R picks it up on next restart, and in most cases the
  dir was already correctly-owned by the calling user)
- Uses -1 sentinel for missing field so only the set value applies
- Empty-string env vars treated as unset

Adds 14 tests across:
- TestResolveHermesUidGid (7) — env-var parsing
- TestChownToHermesUid (5) — chown helper invariants
- TestSecureDirChown (2) — end-to-end through _secure_dir

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-01 13:27:30 +10:00
Teknium
e3b3d4d75e feat(models): add MiniMax-M3 to native minimax providers + 1M context (#36214)
Add MiniMax-M3 to the minimax, minimax-oauth, and minimax-cn curated
lists (these are hardcoded — the native Anthropic-format endpoint has no
/v1/models listing and the providers aren't in _MODELS_DEV_PREFERRED, so
new models don't auto-pull). Add a DEFAULT_CONTEXT_LENGTHS key
'minimax-m3' -> 1,000,000 so M3 resolves to its 1M context on every
surface (native ID + OpenRouter/Nous slug) via longest-key-first
substring match, while the M2.x series stays at 204,800.
2026-05-31 20:18:05 -07:00
630 changed files with 54588 additions and 51475 deletions

2
.envrc
View File

@@ -1,5 +1,5 @@
watch_file pyproject.toml uv.lock
watch_file ui-tui/package-lock.json ui-tui/package.json
watch_file package-lock.json package.json web/package.json ui-tui/package.json website/package.json apps/shared/package.json apps/desktop/package.json ui-tui/packages/hermes-ink/package.json
watch_file flake.nix flake.lock nix/devShell.nix nix/tui.nix nix/package.nix nix/python.nix
use flake

View File

@@ -26,6 +26,10 @@ on:
permissions:
contents: read
# Needed so the arm64 job can push/pull its registry-backed build cache
# to ghcr.io (cache-to/cache-from type=registry). See the build-arm64
# job for why registry cache replaced the gha cache on that arch.
packages: write
# Concurrency: push/release runs are NEVER cancelled so every merge gets
# its own image. PR runs reuse a PR-scoped group with
@@ -54,8 +58,6 @@ jobs:
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
submodules: recursive
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
@@ -190,17 +192,38 @@ jobs:
steps:
- name: Checkout code
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
submodules: recursive
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
# Build once, load into the local daemon for smoke testing. PR arm64
# builds deliberately avoid the gha cache: cold-cache arm64 builds can
# outlive GitHub's short-lived Azure cache SAS token, then fail while
# reading or writing cache blobs before the smoke test can run.
- name: Build image (arm64, smoke test, uncached PR)
# Log in to ghcr.io so the registry-backed build cache below can be
# read (cache-from) on every event and written (cache-to) on
# push/release. Uses the workflow's GITHUB_TOKEN, which is valid for
# the whole job — unlike the gha cache backend's short-lived Azure SAS
# token, which expired mid-build on slow cold-cache arm64 runs and
# crashed the build before the smoke test (the reason the gha cache
# was removed from arm64 PRs in the first place).
- name: Log in to ghcr.io (build cache)
uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# Build once, load into the local daemon for smoke testing.
#
# PR builds use the registry-backed cache READ-ONLY (cache-from only):
# they pull warm layers pushed by the most recent main build but never
# write, so rapid PR pushes don't race on cache writes or pollute the
# cache ref. This restores warm-cache speed to arm64 PR builds (which
# were running fully uncached and were ~45% slower than amd64, making
# them the job most often cancelled on supersede).
#
# Registry cache (type=registry on ghcr.io) is used instead of the gha
# cache that previously broke here: its credential is the job-lifetime
# GITHUB_TOKEN, not a short-lived SAS token, so the cold-build-outlives-
# token failure mode cannot recur.
- name: Build image (arm64, smoke test, cache read-only PR)
if: github.event_name == 'pull_request'
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
with:
@@ -211,9 +234,11 @@ jobs:
tags: ${{ env.IMAGE_NAME }}:test
build-args: |
HERMES_GIT_SHA=${{ github.sha }}
cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
# Main/release builds still use the per-arch gha cache so the digest
# push below can reuse layers from this smoke-test build.
# Main/release builds read AND write the registry cache so the digest
# push below reuses layers from this smoke-test build, and so the next
# PR/main build starts warm.
- name: Build image (arm64, smoke test, cached publish)
if: github.event_name != 'pull_request'
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
@@ -225,8 +250,8 @@ jobs:
tags: ${{ env.IMAGE_NAME }}:test
build-args: |
HERMES_GIT_SHA=${{ github.sha }}
cache-from: type=gha,scope=docker-arm64
cache-to: type=gha,mode=max,scope=docker-arm64
cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
cache-to: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64,mode=max
- name: Smoke test image
uses: ./.github/actions/hermes-smoke-test
@@ -253,8 +278,8 @@ jobs:
build-args: |
HERMES_GIT_SHA=${{ github.sha }}
outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha,scope=docker-arm64
cache-to: type=gha,mode=max,scope=docker-arm64
cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
cache-to: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64,mode=max
- name: Export digest
if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'

View File

@@ -4,10 +4,10 @@ on:
push:
branches: [main]
paths:
- 'ui-tui/package-lock.json'
- 'package-lock.json'
- 'package.json'
- 'ui-tui/package.json'
- 'apps/dashboard/package-lock.json'
- 'apps/dashboard/package.json'
- 'apps/desktop/package.json'
workflow_dispatch:
inputs:
pr_number:
@@ -27,9 +27,9 @@ concurrency:
jobs:
# ── Auto-fix on main ───────────────────────────────────────────────
# Fires when a push to main touches package.json or package-lock.json
# in ui-tui/ or apps/dashboard/. Runs fix-lockfiles and pushes the hash
# update commit directly to main so Nix builds never stay broken.
# Fires when a push to main touches package.json or package-lock.json.
# Runs fix-lockfiles and pushes the hash update commit directly to main
# so Nix builds never stay broken.
#
# Safety invariants:
# 1. The fix commit only touches nix/*.nix files, which are NOT in
@@ -109,8 +109,8 @@ jobs:
# our computed hashes are stale. Abort and let the next triggered
# run recompute from the correct package-lock state.
pkg_changed="$(git diff --name-only "$BASE_SHA"..origin/main -- \
'ui-tui/package-lock.json' 'ui-tui/package.json' \
'apps/dashboard/package-lock.json' 'apps/dashboard/package.json' || true)"
'package-lock.json' 'package.json' \
'ui-tui/package.json' 'apps/desktop/package.json' || true)"
if [ -n "$pkg_changed" ]; then
echo "::warning::Package files changed since hash computation — aborting; a fresh run will recompute"
exit 0

View File

@@ -37,23 +37,16 @@ jobs:
- name: Check flake
id: flake
if: runner.os == 'Linux'
continue-on-error: true
run: nix flake check --print-build-logs
- name: Build package
id: build
if: runner.os == 'Linux'
continue-on-error: true
run: nix build --print-build-logs
# When the real Nix build fails, run a targeted diagnostic to see if
# When the flake check fails, run a targeted diagnostic to see if
# the failure is specifically a stale npm lockfile hash in one of the
# known npm subpackages (tui / web). This avoids surfacing a generic
# "build failed" message when the fix is a single known command.
- name: Diagnose npm lockfile hashes
id: hash_check
if: (steps.flake.outcome == 'failure' || steps.build.outcome == 'failure') && runner.os == 'Linux'
if: steps.flake.outcome == 'failure' && runner.os == 'Linux'
continue-on-error: true
env:
LINK_SHA: ${{ steps.sha.outputs.full }}
@@ -88,30 +81,25 @@ jobs:
- Or [run the Nix Lockfile Fix workflow](${{ github.server_url }}/${{ github.repository }}/actions/workflows/nix-lockfile-fix.yml) manually (pass PR `#${{ github.event.pull_request.number }}`)
- Or locally: `nix run .#fix-lockfiles` and commit the diff
# Clear the sticky comment when either the build passed outright (no
# Clear the sticky comment when either the flake check passed outright (no
# hash check needed) or the hash check explicitly returned stale=false
# (build failed for a non-hash reason).
# (check failed for a non-hash reason).
- name: Clear sticky PR comment (resolved)
if: |
github.event_name == 'pull_request' &&
runner.os == 'Linux' &&
(steps.hash_check.outputs.stale == 'false' ||
(steps.flake.outcome == 'success' && steps.build.outcome == 'success'))
steps.flake.outcome == 'success')
uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2.9.1
with:
header: nix-lockfile-check
delete: true
- name: Final fail if build or flake failed
if: steps.flake.outcome == 'failure' || steps.build.outcome == 'failure'
- name: Final fail if flake check failed
if: steps.flake.outcome == 'failure'
run: |
if [ "${{ steps.hash_check.outputs.stale }}" == "true" ]; then
echo "::error::Nix build failed due to stale npm lockfile hash. Run: nix run .#fix-lockfiles"
else
echo "::error::Nix build/flake check failed. See logs above."
echo "::error::Nix flake check failed. See logs above."
fi
exit 1
- name: Evaluate flake (macOS)
if: runner.os == 'macOS'
run: nix flake show --json > /dev/null

View File

@@ -28,7 +28,6 @@ on:
- 'package.json'
- 'package-lock.json'
- 'ui-tui/package.json'
- 'ui-tui/package-lock.json'
- 'website/package.json'
- 'website/package-lock.json'
- '.github/workflows/osv-scanner.yml'
@@ -39,7 +38,6 @@ on:
- 'pyproject.toml'
- 'package.json'
- 'package-lock.json'
- 'ui-tui/package-lock.json'
- 'website/package-lock.json'
schedule:
# Weekly scan against main — catches CVEs published after merge for
@@ -62,6 +60,6 @@ jobs:
# the three sources of truth and skip vendored / test / worktree dirs.
scan-args: |-
--lockfile=uv.lock
--lockfile=ui-tui/package-lock.json
--lockfile=package-lock.json
--lockfile=website/package-lock.json
fail-on-vuln: false

View File

@@ -171,6 +171,11 @@ jobs:
source .venv/bin/activate
uv pip install -e ".[all,dev]"
- name: Packaged-wheel i18n smoke test
run: |
source .venv/bin/activate
python -m pytest -m integration tests/test_wheel_locales_e2e.py -v
- name: Run e2e tests
run: |
source .venv/bin/activate

6
.gitignore vendored
View File

@@ -110,3 +110,9 @@ docs/superpowers/*
# Tool Search live-test harness output — non-deterministic model transcripts,
# regenerated by scripts/tool_search_livetest.py. Never an artifact of the repo.
scripts/out/
# Per-release changelog drafts. These exist only transiently during a release
# cut (passed to `gh release create --notes-file`); the GitHub Release itself
# stores the published notes. They are not a build artifact and must never be
# committed to the repo root. See the hermes-release skill.
RELEASE_v*.md

View File

@@ -49,8 +49,8 @@ hermes-agent/
│ ├── hermes-achievements/ # Gamified achievement tracking
│ ├── observability/ # Metrics / traces / logs plugin
│ ├── image_gen/ # Image-generation providers
│ └── <others>/ # disk-cleanup, example-dashboard, google_meet, platforms,
│ # spotify, strike-freedom-cockpit, ...
│ └── <others>/ # disk-cleanup, google_meet, platforms, spotify,
│ # strike-freedom-cockpit, ...
├── optional-skills/ # Heavier/niche skills shipped but NOT active by default
├── skills/ # Built-in skills bundled with the repo
├── ui-tui/ # Ink (React) terminal UI — `hermes --tui`
@@ -283,6 +283,21 @@ The dashboard embeds the real `hermes --tui` — **not** a rewrite. See `hermes
**Structured React UI around the TUI is allowed when it is not a second chat surface.** Sidebar widgets, inspectors, summaries, status panels, and similar supporting views (e.g. `ChatSidebar`, `ModelPickerDialog`, `ToolCall`) are fine when they complement the embedded TUI rather than replacing the transcript / composer / terminal. Keep their state independent of the PTY child's session and surface their failures non-destructively so the terminal pane keeps working unimpaired.
### Electron Desktop Chat App (`apps/desktop/`)
A **separate** chat surface from both the classic CLI and the dashboard's embedded TUI. It is an Electron + React + nanostore renderer (`@assistant-ui/react`) that talks to a `tui_gateway` backend over JSON-RPC (`requestGateway(method, params)`). It does NOT embed `hermes --tui` — it has its own composer, transcript, and slash-command pipeline. Route desktop bugs to the `hermes-desktop-app-work` skill, not `hermes-dashboard-work`.
**Slash commands in the desktop app are curated client-side, then dispatched to the backend.** The pipeline:
- **Backend already provides everything.** `tui_gateway/server.py` `commands.catalog` (empty-query list) and `complete.slash` (typed-query completions) both include built-in commands, user `quick_commands`, AND skill-derived commands (`scan_skill_commands()` / `get_skill_commands()`). The desktop app does not need a new RPC to see skills.
- **The renderer curates via `apps/desktop/src/lib/desktop-slash-commands.ts`.** This is the load-bearing file. It holds `DESKTOP_COMMANDS` (the ~19 built-ins shown in the palette) plus block-lists for terminal-only / messaging-only / picker-owned / settings-owned / advanced commands that should NOT clutter the desktop popover.
- `isDesktopSlashCommand(name)` — gates **execution**. Returns true for built-ins AND for any non-built-in (skill / quick command), so typed extension commands run.
- `isDesktopSlashSuggestion(name)` — gates **discovery/completion**. Used by BOTH completion paths in `app/chat/composer/hooks/use-slash-completions.ts` (empty-query catalog filter + typed-query `complete.slash` filter) and by `filterDesktopCommandsCatalog`.
- `isDesktopSlashExtensionCommand(name)` — true when the command is NOT a known Hermes built-in (i.e. a skill or user quick command). Both suggestion and catalog-filter paths allow extensions through so skill commands surface in the palette. (Added when fixing "skill commands missing from the desktop slash palette" — the curated allow-list was silently dropping every skill/quick command from completions even though they executed fine when typed.)
- **Dispatch** lives in `app/session/hooks/use-prompt-actions.ts` (`runSlash`): built-ins that the desktop owns (`/skin`, `/help`, `/new`, …) are handled locally or via `commands.catalog`; everything else goes to `slash.exec`, falling back to `command.dispatch` (which the gateway resolves into skill / alias / exec directives). A skill command resolves to `{type: "skill", message}` and is submitted as a normal prompt.
**Rule:** the desktop slash palette's curation is about hiding noise (terminal-only / messaging-only built-ins), NOT about hiding user-activated extensions. Skill commands and `quick_commands` are extensions the backend surfaces — they belong in completions. If you tighten `desktop-slash-commands.ts`, keep `isDesktopSlashExtensionCommand` flowing into both the suggestion and catalog-filter paths. Tests: `apps/desktop/src/lib/desktop-slash-commands.test.ts` (run via the repo-root `vitest`, since `apps/desktop` resolves deps from the root workspace install).
---
## Adding New Tools

View File

@@ -73,7 +73,7 @@ This isn't a quality bar — it's a coupling-and-maintenance decision. Memory pr
| Requirement | Notes |
|-------------|-------|
| **Git** | With `--recurse-submodules` support, and the `git-lfs` extension installed |
| **Git** | With the `git-lfs` extension installed |
| **Python 3.11+** | uv will install it if missing |
| **uv** | Fast Python package manager ([install](https://docs.astral.sh/uv/)) |
| **Node.js 20+** | Optional — needed for browser tools and WhatsApp bridge (matches root `package.json` engines) |
@@ -81,7 +81,7 @@ This isn't a quality bar — it's a coupling-and-maintenance decision. Memory pr
### Clone and install
```bash
git clone --recurse-submodules https://github.com/NousResearch/hermes-agent.git
git clone https://github.com/NousResearch/hermes-agent.git
cd hermes-agent
# Create venv with Python 3.11

View File

@@ -25,7 +25,7 @@ ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
# hermes process, the dashboard, and per-profile gateways.
RUN apt-get update && \
apt-get install -y --no-install-recommends \
ca-certificates curl iputils-ping python3 python-is-python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli xz-utils && \
ca-certificates curl iputils-ping python3 python-is-python3 ripgrep ffmpeg gcc python3-dev python3-venv libffi-dev libolm-dev procps git openssh-client docker-cli xz-utils && \
rm -rf /var/lib/apt/lists/*
# ---------- s6-overlay install ----------
@@ -73,7 +73,17 @@ RUN set -eu; \
tar -C / -Jxpf /tmp/s6-overlay-noarch.tar.xz; \
tar -C / -Jxpf /tmp/s6-overlay-arch.tar.xz; \
tar -C / -Jxpf /tmp/s6-overlay-symlinks-noarch.tar.xz; \
rm /tmp/s6-overlay-*.tar.xz /tmp/s6-overlay.sha256
rm /tmp/s6-overlay-*.tar.xz /tmp/s6-overlay.sha256; \
# #34192: backward-compat shim for orchestration templates that still\
# reference the legacy /usr/bin/tini entrypoint (e.g. Hostinger's\
# 'Hermes WebUI' catalog). The image has moved to s6-overlay /init\
# as PID 1 (see ENTRYPOINT below + the migration comment at the top\
# of this file), but external wrappers pinned to /usr/bin/tini will\
# crash with 'tini: No such file or directory' on startup. The shim\
# symlinks /usr/bin/tini -> /init so legacy wrappers exec the right\
# PID-1 reaper without behavior change for users on the current\
# ENTRYPOINT. Safe to drop once the affected catalogs are updated.\
ln -sf /init /usr/bin/tini
# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
RUN useradd -u 10000 -m -d /opt/data hermes
@@ -103,8 +113,8 @@ WORKDIR /opt/hermes
# ui-tui/package.json. Copying the tree up front lets npm resolve the
# workspace to real content instead of stopping at a bare package.json.
COPY package.json package-lock.json ./
COPY web/package.json web/package-lock.json web/
COPY ui-tui/package.json ui-tui/package-lock.json ui-tui/
COPY web/package.json web/
COPY ui-tui/package.json ui-tui/
COPY ui-tui/packages/hermes-ink/ ui-tui/packages/hermes-ink/
# `npm_config_install_links=false` forces npm to install `file:` deps as
@@ -121,8 +131,6 @@ ENV npm_config_install_links=false
RUN npm install --prefer-offline --no-audit && \
npx playwright install --with-deps chromium --only-shell && \
(cd web && npm install --prefer-offline --no-audit) && \
(cd ui-tui && npm install --prefer-offline --no-audit) && \
npm cache clean --force
# ---------- Layer-cached Python dependency install ----------
@@ -149,10 +157,17 @@ RUN npm install --prefer-offline --no-audit && \
# so Docker users can use these providers without requiring runtime
# lazy-install access to PyPI (often blocked in containerized envs).
#
# The hindsight memory provider's client (hindsight-client) is baked in
# for the same reason: it lazy-installs into /opt/hermes/.venv at first
# use, which lives inside the (immutable) image layer rather than the
# mounted /opt/data volume, so it is lost on every container recreate /
# image update and recall/retain then fails with
# `ModuleNotFoundError: No module named 'hindsight_client'` (#38128).
#
# The editable link is created after the source copy below.
COPY pyproject.toml uv.lock ./
RUN touch ./README.md
RUN uv sync --frozen --no-install-project --extra all --extra messaging --extra anthropic --extra bedrock --extra azure-identity
RUN uv sync --frozen --no-install-project --extra all --extra messaging --extra anthropic --extra bedrock --extra azure-identity --extra hindsight
# ---------- Source code ----------
# .dockerignore excludes node_modules, so the installs above survive.
@@ -170,13 +185,16 @@ RUN cd web && npm run build && \
# hermes_cli/main.py succeeds (see #18800). /opt/hermes/web is build-time
# only (HERMES_WEB_DIST points at hermes_cli/web_dist) and is intentionally
# not chowned here.
# /opt/hermes/gateway is runtime-writable: Python may create __pycache__ and
# gateway state artifacts beneath the package after services drop privileges,
# especially when the hermes UID is remapped at boot (#27221).
# The .venv MUST remain hermes-writable so lazy_deps.py can install
# remaining optional platform packages and future pin bumps at first use.
# Without this, `uv pip install` fails with EACCES and adapters silently
# fail to load. See tools/lazy_deps.py.
USER root
RUN chmod -R a+rX /opt/hermes && \
chown -R hermes:hermes /opt/hermes/.venv /opt/hermes/ui-tui /opt/hermes/node_modules
chown -R hermes:hermes /opt/hermes/.venv /opt/hermes/ui-tui /opt/hermes/gateway /opt/hermes/node_modules
# Start as root so the s6-overlay stage2 hook can usermod/groupmod and chown
# the data volume. Each supervised service then drops to the hermes user via
# `s6-setuidgid hermes` in its run script. If HERMES_UID is unset, services
@@ -235,6 +253,23 @@ COPY --chmod=0755 docker/cont-init.d/02-reconcile-profiles /etc/cont-init.d/02-r
# ---------- Runtime ----------
ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
# Point the TUI launcher at the prebuilt bundle baked at build time (Layer 8:
# `ui-tui && npm run build`). This makes _make_tui_argv take the prebuilt-bundle
# fast path (`node --expose-gc /opt/hermes/ui-tui/dist/entry.js`) and skip the
# _tui_need_npm_install / runtime `npm install` branch entirely — exactly the
# nix/packaged-release path the launcher was designed for.
#
# Why this is required (not just an optimization): the root package-lock.json
# describes the WHOLE monorepo workspace set (root + web + ui-tui + apps/*),
# but the image only installs root/web/ui-tui (apps/* — the desktop app — is
# never `npm install`ed here). So the actualized node_modules permanently
# disagrees with the canonical lock, _tui_need_npm_install() returns True on
# every launch, and the runtime `npm install` it triggers (a) can never
# converge against the partial monorepo and (b) races itself across concurrent
# embedded-chat (/api/pty) connections → ENOTEMPTY → the chat tab dies with a
# 502 / "[session ended]". Pointing at the prebuilt bundle sidesteps the whole
# check. (A separate launcher hardening is tracked independently.)
ENV HERMES_TUI_DIR=/opt/hermes/ui-tui
ENV HERMES_HOME=/opt/data
# `docker exec` privilege-drop shim. When operators run

View File

@@ -1,5 +1,6 @@
graft skills
graft optional-skills
graft locales
# Bundled plugin manifests (plugin.yaml / plugin.yml). Without these the
# PluginManager scan (hermes_cli/plugins.py) finds zero plugins on installs
# built from the sdist (e.g. Homebrew, downstream packagers). package-data

View File

@@ -94,7 +94,7 @@ One command from a fresh install:
hermes setup --portal
```
That logs you in via OAuth, sets Nous as your provider, and turns on the Tool Gateway. Check what's wired up any time with `hermes portal status`. Full details on the [Tool Gateway docs page](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway).
That logs you in via OAuth, sets Nous as your provider, and turns on the Tool Gateway. Check what's wired up any time with `hermes portal info`. Full details on the [Tool Gateway docs page](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway).
You can still bring your own keys per-tool whenever you want — the gateway is per-backend, not all-or-nothing.

View File

@@ -80,7 +80,7 @@ Hermes 始终允许你使用任意服务商,这点不会改变。但如果你
hermes setup --portal
```
它会通过 OAuth 登录、把 Nous 设为推理服务商,并启用 Tool Gateway。随时用 `hermes portal status` 查看路由状态。完整说明见 [Tool Gateway 文档](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway)。
它会通过 OAuth 登录、把 Nous 设为推理服务商,并启用 Tool Gateway。随时用 `hermes portal info` 查看路由状态。完整说明见 [Tool Gateway 文档](https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway)。
你随时可以按工具单独切回自己的 API Key — Gateway 是按工具粒度生效的,不是一刀切。

View File

@@ -1,27 +0,0 @@
# Hermes Agent v0.10.0 (v2026.4.16)
**Release Date:** April 16, 2026
> The Tool Gateway release — paid Nous Portal subscribers can now use web search, image generation, text-to-speech, and browser automation through their existing subscription with zero additional API keys.
---
## ✨ Highlights
- **Nous Tool Gateway** — Paid [Nous Portal](https://portal.nousresearch.com) subscribers now get automatic access to **web search** (Firecrawl), **image generation** (FAL / FLUX 2 Pro), **text-to-speech** (OpenAI TTS), and **browser automation** (Browser Use) through their existing subscription. No separate API keys needed — just run `hermes model`, select Nous Portal, and pick which tools to enable. Per-tool opt-in via `use_gateway` config, full integration with `hermes tools` and `hermes status`, and the runtime correctly prefers the gateway even when direct API keys exist. Replaces the old hidden `HERMES_ENABLE_NOUS_MANAGED_TOOLS` env var with clean subscription-based detection. ([#11206](https://github.com/NousResearch/hermes-agent/pull/11206), based on work by @jquesnelle; docs: [#11208](https://github.com/NousResearch/hermes-agent/pull/11208))
---
## 🐛 Bug Fixes & Improvements
This release includes 180+ commits with numerous bug fixes, platform improvements, and reliability enhancements across the agent core, gateway, CLI, and tool system. Full details will be published in the v0.11.0 changelog.
---
## 👥 Contributors
- **@jquesnelle** (emozilla) — Original Tool Gateway implementation ([#10799](https://github.com/NousResearch/hermes-agent/pull/10799)), salvaged and shipped in this release
---
**Full Changelog**: [v2026.4.13...v2026.4.16](https://github.com/NousResearch/hermes-agent/compare/v2026.4.13...v2026.4.16)

View File

@@ -1,453 +0,0 @@
# Hermes Agent v0.11.0 (v2026.4.23)
**Release Date:** April 23, 2026
**Since v0.9.0:** 1,556 commits · 761 merged PRs · 1,314 files changed · 224,174 insertions · 29 community contributors (290 including co-authors)
> The Interface release — a full React/Ink rewrite of the interactive CLI, a pluggable transport architecture underneath every provider, native AWS Bedrock support, five new inference paths, a 17th messaging platform (QQBot), a dramatically expanded plugin surface, and GPT-5.5 via Codex OAuth.
This release also folds in all the highlights deferred from v0.10.0 (which shipped only the Nous Tool Gateway) — so it covers roughly two weeks of work across the whole stack.
---
## ✨ Highlights
- **New Ink-based TUI** — `hermes --tui` is now a full React/Ink rewrite of the interactive CLI, with a Python JSON-RPC backend (`tui_gateway`). Sticky composer, live streaming with OSC-52 clipboard support, stable picker keys, status bar with per-turn stopwatch and git branch, `/clear` confirm, light-theme preset, and a subagent spawn observability overlay. ~310 commits to `ui-tui/` + `tui_gateway/`. (@OutThisLife + Teknium)
- **Transport ABC + Native AWS Bedrock** — Format conversion and HTTP transport were extracted from `run_agent.py` into a pluggable `agent/transports/` layer. `AnthropicTransport`, `ChatCompletionsTransport`, `ResponsesApiTransport`, and `BedrockTransport` each own their own format conversion and API shape. Native AWS Bedrock support via the Converse API ships on top of the new abstraction. ([#10549](https://github.com/NousResearch/hermes-agent/pull/10549), [#13347](https://github.com/NousResearch/hermes-agent/pull/13347), [#13366](https://github.com/NousResearch/hermes-agent/pull/13366), [#13430](https://github.com/NousResearch/hermes-agent/pull/13430), [#13805](https://github.com/NousResearch/hermes-agent/pull/13805), [#13814](https://github.com/NousResearch/hermes-agent/pull/13814) — @kshitijk4poor + Teknium)
- **Five new inference paths** — Native NVIDIA NIM ([#11774](https://github.com/NousResearch/hermes-agent/pull/11774)), Arcee AI ([#9276](https://github.com/NousResearch/hermes-agent/pull/9276)), Step Plan ([#13893](https://github.com/NousResearch/hermes-agent/pull/13893)), Google Gemini CLI OAuth ([#11270](https://github.com/NousResearch/hermes-agent/pull/11270)), and Vercel ai-gateway with pricing + dynamic discovery ([#13223](https://github.com/NousResearch/hermes-agent/pull/13223) — @jerilynzheng). Plus Gemini routed through the native AI Studio API for better performance ([#12674](https://github.com/NousResearch/hermes-agent/pull/12674)).
- **GPT-5.5 over Codex OAuth** — OpenAI's new GPT-5.5 reasoning model is now available through your ChatGPT Codex OAuth, with live model discovery wired into the model picker so new OpenAI releases show up without catalog updates. ([#14720](https://github.com/NousResearch/hermes-agent/pull/14720))
- **QQBot — 17th supported platform** — Native QQBot adapter via QQ Official API v2, with QR scan-to-configure setup wizard, streaming cursor, emoji reactions, and DM/group policy gating that matches WeCom/Weixin parity. ([#9364](https://github.com/NousResearch/hermes-agent/pull/9364), [#11831](https://github.com/NousResearch/hermes-agent/pull/11831))
- **Plugin surface expanded** — Plugins can now register slash commands (`register_command`), dispatch tools directly (`dispatch_tool`), block tool execution from hooks (`pre_tool_call` can veto), rewrite tool results (`transform_tool_result`), transform terminal output (`transform_terminal_output`), ship image_gen backends, and add custom dashboard tabs. The bundled disk-cleanup plugin is opt-in by default as a reference implementation. ([#9377](https://github.com/NousResearch/hermes-agent/pull/9377), [#10626](https://github.com/NousResearch/hermes-agent/pull/10626), [#10763](https://github.com/NousResearch/hermes-agent/pull/10763), [#10951](https://github.com/NousResearch/hermes-agent/pull/10951), [#12929](https://github.com/NousResearch/hermes-agent/pull/12929), [#12944](https://github.com/NousResearch/hermes-agent/pull/12944), [#12972](https://github.com/NousResearch/hermes-agent/pull/12972), [#13799](https://github.com/NousResearch/hermes-agent/pull/13799), [#14175](https://github.com/NousResearch/hermes-agent/pull/14175))
- **`/steer` — mid-run agent nudges** — `/steer <prompt>` injects a note that the running agent sees after its next tool call, without interrupting the turn or breaking prompt cache. For when you want to course-correct an agent in-flight. ([#12116](https://github.com/NousResearch/hermes-agent/pull/12116))
- **Shell hooks** — Wire any shell script as a Hermes lifecycle hook (pre_tool_call, post_tool_call, on_session_start, etc.) without writing a Python plugin. ([#13296](https://github.com/NousResearch/hermes-agent/pull/13296))
- **Webhook direct-delivery mode** — Webhook subscriptions can now forward payloads straight to a platform chat without going through the agent — zero-LLM push notifications for alerting, uptime checks, and event streams. ([#12473](https://github.com/NousResearch/hermes-agent/pull/12473))
- **Smarter delegation** — Subagents now have an explicit `orchestrator` role that can spawn their own workers, with configurable `max_spawn_depth` (default flat). Concurrent sibling subagents share filesystem state through a file-coordination layer so they don't clobber each other's edits. ([#13691](https://github.com/NousResearch/hermes-agent/pull/13691), [#13718](https://github.com/NousResearch/hermes-agent/pull/13718))
- **Auxiliary models — configurable UI + main-model-first** — `hermes model` has a dedicated "Configure auxiliary models" screen for per-task overrides (compression, vision, session_search, title_generation). `auto` routing now defaults to the main model for side tasks across all users (previously aggregator users were silently routed to a cheap provider-side default). ([#11891](https://github.com/NousResearch/hermes-agent/pull/11891), [#11900](https://github.com/NousResearch/hermes-agent/pull/11900))
- **Dashboard plugin system + live theme switching** — The web dashboard is now extensible. Third-party plugins can add custom tabs, widgets, and views without forking. Paired with a live-switching theme system — themes now control colors, fonts, layout, and density — so users can hot-swap the dashboard look without a reload. Same theming discipline the CLI has, now on the web. ([#10951](https://github.com/NousResearch/hermes-agent/pull/10951), [#10687](https://github.com/NousResearch/hermes-agent/pull/10687), [#14725](https://github.com/NousResearch/hermes-agent/pull/14725))
- **Dashboard polish** — i18n (English + Chinese), react-router sidebar layout, mobile-responsive, Vercel deployment, real per-session API call tracking, and one-click update + gateway restart buttons. ([#9228](https://github.com/NousResearch/hermes-agent/pull/9228), [#9370](https://github.com/NousResearch/hermes-agent/pull/9370), [#9453](https://github.com/NousResearch/hermes-agent/pull/9453), [#10686](https://github.com/NousResearch/hermes-agent/pull/10686), [#13526](https://github.com/NousResearch/hermes-agent/pull/13526), [#14004](https://github.com/NousResearch/hermes-agent/pull/14004) — @austinpickett + @DeployFaith + Teknium)
---
## 🏗️ Core Agent & Architecture
### Transport Layer (NEW)
- **Transport ABC** abstracts format conversion and HTTP transport from `run_agent.py` into `agent/transports/` ([#13347](https://github.com/NousResearch/hermes-agent/pull/13347))
- **AnthropicTransport** — Anthropic Messages API path ([#13366](https://github.com/NousResearch/hermes-agent/pull/13366), @kshitijk4poor)
- **ChatCompletionsTransport** — default path for OpenAI-compatible providers ([#13805](https://github.com/NousResearch/hermes-agent/pull/13805))
- **ResponsesApiTransport** — OpenAI Responses API + Codex build_kwargs wiring ([#13430](https://github.com/NousResearch/hermes-agent/pull/13430), @kshitijk4poor)
- **BedrockTransport** — AWS Bedrock Converse API transport ([#13814](https://github.com/NousResearch/hermes-agent/pull/13814))
### Provider & Model Support
- **Native AWS Bedrock provider** via Converse API ([#10549](https://github.com/NousResearch/hermes-agent/pull/10549))
- **NVIDIA NIM native provider** (salvage of #11703) ([#11774](https://github.com/NousResearch/hermes-agent/pull/11774))
- **Arcee AI direct provider** ([#9276](https://github.com/NousResearch/hermes-agent/pull/9276))
- **Step Plan provider** (salvage #6005) ([#13893](https://github.com/NousResearch/hermes-agent/pull/13893), @kshitijk4poor)
- **Google Gemini CLI OAuth** inference provider ([#11270](https://github.com/NousResearch/hermes-agent/pull/11270))
- **Vercel ai-gateway** with pricing, attribution, and dynamic discovery ([#13223](https://github.com/NousResearch/hermes-agent/pull/13223), @jerilynzheng)
- **GPT-5.5 over Codex OAuth** with live model discovery in the picker ([#14720](https://github.com/NousResearch/hermes-agent/pull/14720))
- **Gemini routed through native AI Studio API** ([#12674](https://github.com/NousResearch/hermes-agent/pull/12674))
- **xAI Grok upgraded to Responses API** ([#10783](https://github.com/NousResearch/hermes-agent/pull/10783))
- **Ollama improvements** — Cloud provider support, GLM continuation, `think=false` control, surrogate sanitization, `/v1` hint ([#10782](https://github.com/NousResearch/hermes-agent/pull/10782))
- **Kimi K2.6** across OpenRouter, Nous Portal, native Kimi, and HuggingFace ([#13148](https://github.com/NousResearch/hermes-agent/pull/13148), [#13152](https://github.com/NousResearch/hermes-agent/pull/13152), [#13169](https://github.com/NousResearch/hermes-agent/pull/13169))
- **Kimi K2.5** promoted to first position in all model suggestion lists ([#11745](https://github.com/NousResearch/hermes-agent/pull/11745), @kshitijk4poor)
- **Xiaomi MiMo v2.5-pro + v2.5** on OpenRouter, Nous Portal, and native ([#14184](https://github.com/NousResearch/hermes-agent/pull/14184), [#14635](https://github.com/NousResearch/hermes-agent/pull/14635), @kshitijk4poor)
- **GLM-5V-Turbo** for coding plan ([#9907](https://github.com/NousResearch/hermes-agent/pull/9907))
- **Claude Opus 4.7** in Nous Portal catalog ([#11398](https://github.com/NousResearch/hermes-agent/pull/11398))
- **OpenRouter elephant-alpha** in curated lists ([#9378](https://github.com/NousResearch/hermes-agent/pull/9378))
- **OpenCode-Go** — Kimi K2.6 and Qwen3.5/3.6 Plus in curated catalog ([#13429](https://github.com/NousResearch/hermes-agent/pull/13429))
- **minimax/minimax-m2.5:free** in OpenRouter catalog ([#13836](https://github.com/NousResearch/hermes-agent/pull/13836))
- **`/model` merges models.dev entries** for lesser-loved providers ([#14221](https://github.com/NousResearch/hermes-agent/pull/14221))
- **Per-provider + per-model `request_timeout_seconds`** config ([#12652](https://github.com/NousResearch/hermes-agent/pull/12652))
- **Configurable API retry count** via `agent.api_max_retries` ([#14730](https://github.com/NousResearch/hermes-agent/pull/14730))
- **ctx_size context length key** for Lemonade server (salvage #8536) ([#14215](https://github.com/NousResearch/hermes-agent/pull/14215))
- **Custom provider display name prompt** ([#9420](https://github.com/NousResearch/hermes-agent/pull/9420))
- **Recommendation badges** on tool provider selection ([#9929](https://github.com/NousResearch/hermes-agent/pull/9929))
- Fix: correct GPT-5 family context lengths in fallback defaults ([#9309](https://github.com/NousResearch/hermes-agent/pull/9309))
- Fix: clamp `minimal` reasoning effort to `low` on Responses API ([#9429](https://github.com/NousResearch/hermes-agent/pull/9429))
- Fix: strip reasoning item IDs from Responses API input when `store=False` ([#10217](https://github.com/NousResearch/hermes-agent/pull/10217))
- Fix: OpenViking correct account default + commit session on `/new` and compress ([#10463](https://github.com/NousResearch/hermes-agent/pull/10463))
- Fix: Kimi `/coding` thinking block survival + empty reasoning_content + block ordering (multiple PRs)
- Fix: don't send Anthropic thinking to api.kimi.com/coding ([#13826](https://github.com/NousResearch/hermes-agent/pull/13826))
- Fix: send `max_tokens`, `reasoning_effort`, and `thinking` for Kimi/Moonshot
- Fix: stream reasoning content through OpenAI-compatible providers that emit it
### Agent Loop & Conversation
- **`/steer <prompt>`** — mid-run agent nudges after next tool call ([#12116](https://github.com/NousResearch/hermes-agent/pull/12116))
- **Orchestrator role + configurable spawn depth** for `delegate_task` (default flat) ([#13691](https://github.com/NousResearch/hermes-agent/pull/13691))
- **Cross-agent file state coordination** for concurrent subagents ([#13718](https://github.com/NousResearch/hermes-agent/pull/13718))
- **Compressor smart collapse, dedup, anti-thrashing**, template upgrade, hardening ([#10088](https://github.com/NousResearch/hermes-agent/pull/10088))
- **Compression summaries respect the conversation's language** ([#12556](https://github.com/NousResearch/hermes-agent/pull/12556))
- **Compression model falls back to main model** on permanent 503/404 ([#10093](https://github.com/NousResearch/hermes-agent/pull/10093))
- **Auto-continue interrupted agent work** after gateway restart ([#9934](https://github.com/NousResearch/hermes-agent/pull/9934))
- **Activity heartbeats** prevent false gateway inactivity timeouts ([#10501](https://github.com/NousResearch/hermes-agent/pull/10501))
- **Auxiliary models UI** — dedicated screen for per-task overrides ([#11891](https://github.com/NousResearch/hermes-agent/pull/11891))
- **Auxiliary auto routing defaults to main model** for all users ([#11900](https://github.com/NousResearch/hermes-agent/pull/11900))
- **PLATFORM_HINTS for Matrix, Mattermost, Feishu** ([#14428](https://github.com/NousResearch/hermes-agent/pull/14428), @alt-glitch)
- Fix: reset retry counters after compression; stop poisoning conversation history ([#10055](https://github.com/NousResearch/hermes-agent/pull/10055))
- Fix: break compression-exhaustion infinite loop and auto-reset session ([#10063](https://github.com/NousResearch/hermes-agent/pull/10063))
- Fix: stale agent timeout, uv venv detection, empty response after tools ([#10065](https://github.com/NousResearch/hermes-agent/pull/10065))
- Fix: prevent premature loop exit when weak models return empty after substantive tool calls ([#10472](https://github.com/NousResearch/hermes-agent/pull/10472))
- Fix: preserve pre-start terminal interrupts ([#10504](https://github.com/NousResearch/hermes-agent/pull/10504))
- Fix: improve interrupt responsiveness during concurrent tool execution ([#10935](https://github.com/NousResearch/hermes-agent/pull/10935))
- Fix: word-wrap spinner, interruptable agent join, and delegate_task interrupt ([#10940](https://github.com/NousResearch/hermes-agent/pull/10940))
- Fix: `/stop` no longer resets the session ([#9224](https://github.com/NousResearch/hermes-agent/pull/9224))
- Fix: honor interrupts during MCP tool waits ([#9382](https://github.com/NousResearch/hermes-agent/pull/9382), @helix4u)
- Fix: break stuck session resume loops after repeated restarts ([#9941](https://github.com/NousResearch/hermes-agent/pull/9941))
- Fix: empty response nudge crash + placeholder leak to cron targets ([#11021](https://github.com/NousResearch/hermes-agent/pull/11021))
- Fix: streaming cursor sanitization to prevent message truncation (multiple PRs)
- Fix: resolve `context_length` for plugin context engines ([#9238](https://github.com/NousResearch/hermes-agent/pull/9238))
### Session & Memory
- **Auto-prune old sessions + VACUUM state.db** at startup ([#13861](https://github.com/NousResearch/hermes-agent/pull/13861))
- **Honcho overhaul** — context injection, 5-tool surface, cost safety, session isolation ([#10619](https://github.com/NousResearch/hermes-agent/pull/10619))
- **Hindsight richer session-scoped retain metadata** (salvage of #6290) ([#13987](https://github.com/NousResearch/hermes-agent/pull/13987))
- Fix: deduplicate memory provider tools to prevent 400 on strict providers ([#10511](https://github.com/NousResearch/hermes-agent/pull/10511))
- Fix: discover user-installed memory providers from `$HERMES_HOME/plugins/` ([#10529](https://github.com/NousResearch/hermes-agent/pull/10529))
- Fix: add `on_memory_write` bridge to sequential tool execution path ([#10507](https://github.com/NousResearch/hermes-agent/pull/10507))
- Fix: preserve `session_id` across `previous_response_id` chains in `/v1/responses` ([#10059](https://github.com/NousResearch/hermes-agent/pull/10059))
---
## 🖥️ New Ink-based TUI
A full React/Ink rewrite of the interactive CLI — invoked via `hermes --tui` or `HERMES_TUI=1`. Shipped across ~310 commits to `ui-tui/` and `tui_gateway/`.
### TUI Foundations
- New TUI based on Ink + Python JSON-RPC backend
- Prettier + ESLint + vitest tooling for `ui-tui/`
- Entry split between `src/entry.tsx` (TTY gate) and `src/app.tsx` (state machine)
- Persistent `_SlashWorker` subprocess for slash command dispatch
### UX & Features
- **Stable picker keys, /clear confirm, light-theme preset** ([#12312](https://github.com/NousResearch/hermes-agent/pull/12312), @OutThisLife)
- **Git branch in status bar** cwd label ([#12305](https://github.com/NousResearch/hermes-agent/pull/12305), @OutThisLife)
- **Per-turn elapsed stopwatch in FaceTicker + done-in sys line** ([#13105](https://github.com/NousResearch/hermes-agent/pull/13105), @OutThisLife)
- **Subagent spawn observability overlay** ([#14045](https://github.com/NousResearch/hermes-agent/pull/14045), @OutThisLife)
- **Per-prompt elapsed stopwatch in status bar** ([#12948](https://github.com/NousResearch/hermes-agent/pull/12948))
- Sticky composer that freezes during scroll
- OSC-52 clipboard support for copy across SSH sessions
- Virtualized history rendering for performance
- Slash command autocomplete via `complete.slash` RPC
- Path autocomplete via `complete.path` RPC
- Dozens of resize/ghosting/sticky-prompt fixes landed through the week
### Structural Refactors
- Decomposed `app.tsx` into `app/event-handler`, `app/slash-handler`, `app/stores`, `app/hooks` ([#14640](https://github.com/NousResearch/hermes-agent/pull/14640) and surrounding)
- Component split: `branding.tsx`, `markdown.tsx`, `prompts.tsx`, `sessionPicker.tsx`, `messageLine.tsx`, `thinking.tsx`, `maskedPrompt.tsx`
- Hook split: `useCompletion`, `useInputHistory`, `useQueue`, `useVirtualHistory`
---
## 📱 Messaging Platforms (Gateway)
### New Platforms
- **QQBot (17th platform)** — QQ Official API v2 adapter with QR setup, streaming, package split ([#9364](https://github.com/NousResearch/hermes-agent/pull/9364), [#11831](https://github.com/NousResearch/hermes-agent/pull/11831))
### Telegram
- **Dedicated `TELEGRAM_PROXY` env var + config.yaml proxy support** (closes #9414, #6530, #9074, #7786) ([#10681](https://github.com/NousResearch/hermes-agent/pull/10681))
- **`ignored_threads` config** for Telegram groups ([#9530](https://github.com/NousResearch/hermes-agent/pull/9530))
- **Config option to disable link previews** (closes #8728) ([#10610](https://github.com/NousResearch/hermes-agent/pull/10610))
- **Auto-wrap markdown tables** in code blocks ([#11794](https://github.com/NousResearch/hermes-agent/pull/11794))
- Fix: prevent duplicate replies when stream task is cancelled ([#9319](https://github.com/NousResearch/hermes-agent/pull/9319))
- Fix: prevent streaming cursor (▉) from appearing as standalone messages ([#9538](https://github.com/NousResearch/hermes-agent/pull/9538))
- Fix: retry transient tool sends + cold-boot budget ([#10947](https://github.com/NousResearch/hermes-agent/pull/10947))
- Fix: Markdown special char escaping in `send_exec_approval`
- Fix: parentheses in URLs during MarkdownV2 link conversion
- Fix: Unicode dash normalization in model switch (closes iOS smart-punctuation issue)
- Many platform hint / streaming / session-key fixes
### Discord
- **Forum channel support** (salvage of #10145 + media + polish) ([#11920](https://github.com/NousResearch/hermes-agent/pull/11920))
- **`DISCORD_ALLOWED_ROLES`** for role-based access control ([#11608](https://github.com/NousResearch/hermes-agent/pull/11608))
- **Config option to disable slash commands** (salvage #13130) ([#14315](https://github.com/NousResearch/hermes-agent/pull/14315))
- **Native `send_animation`** for inline GIF playback ([#10283](https://github.com/NousResearch/hermes-agent/pull/10283))
- **`send_message` Discord media attachments** ([#10246](https://github.com/NousResearch/hermes-agent/pull/10246))
- **`/skill` command group** with category subcommands ([#9909](https://github.com/NousResearch/hermes-agent/pull/9909))
- **Extract reply text from message references** ([#9781](https://github.com/NousResearch/hermes-agent/pull/9781))
### Feishu
- **Intelligent reply on document comments** with 3-tier access control ([#11898](https://github.com/NousResearch/hermes-agent/pull/11898))
- **Show processing state via reactions** on user messages ([#12927](https://github.com/NousResearch/hermes-agent/pull/12927))
- **Preserve @mention context for agent consumption** (salvage #13874) ([#14167](https://github.com/NousResearch/hermes-agent/pull/14167))
### DingTalk
- **`require_mention` + `allowed_users` gating** (parity with Slack/Telegram/Discord) ([#11564](https://github.com/NousResearch/hermes-agent/pull/11564))
- **QR-code device-flow authorization** for setup wizard ([#11574](https://github.com/NousResearch/hermes-agent/pull/11574))
- **AI Cards streaming, emoji reactions, and media handling** (salvage of #10985) ([#11910](https://github.com/NousResearch/hermes-agent/pull/11910))
### WhatsApp
- **`send_voice`** — native audio message delivery ([#13002](https://github.com/NousResearch/hermes-agent/pull/13002))
- **`dm_policy` and `group_policy`** parity with WeCom/Weixin/QQ adapters ([#13151](https://github.com/NousResearch/hermes-agent/pull/13151))
### WeCom / Weixin
- **WeCom QR-scan bot creation + interactive setup wizard** (salvage #13923) ([#13961](https://github.com/NousResearch/hermes-agent/pull/13961))
### Signal
- **Media delivery support** via `send_message` ([#13178](https://github.com/NousResearch/hermes-agent/pull/13178))
### Slack
- **Per-thread sessions for DMs by default** ([#10987](https://github.com/NousResearch/hermes-agent/pull/10987))
### BlueBubbles (iMessage)
- Group chat session separation, webhook registration & auth fixes ([#9806](https://github.com/NousResearch/hermes-agent/pull/9806))
### Gateway Core
- **Gateway proxy mode** — forward messages to a remote API server ([#9787](https://github.com/NousResearch/hermes-agent/pull/9787))
- **Per-channel ephemeral prompts** (Discord, Telegram, Slack, Mattermost) ([#10564](https://github.com/NousResearch/hermes-agent/pull/10564))
- **Surface plugin slash commands** natively on all platforms + decision-capable command hook ([#14175](https://github.com/NousResearch/hermes-agent/pull/14175))
- **Support document/archive extensions in MEDIA: tag extraction** (salvage #8255) ([#14307](https://github.com/NousResearch/hermes-agent/pull/14307))
- **Recognize `.pdf` in MEDIA: tag extraction** ([#13683](https://github.com/NousResearch/hermes-agent/pull/13683))
- **`--all` flag for `gateway start` and `restart`** ([#10043](https://github.com/NousResearch/hermes-agent/pull/10043))
- **Notify active sessions on gateway shutdown** + update health check ([#9850](https://github.com/NousResearch/hermes-agent/pull/9850))
- **Block agent from self-destructing the gateway** via terminal (closes #6666) ([#9895](https://github.com/NousResearch/hermes-agent/pull/9895))
- Fix: suppress duplicate replies on interrupt and streaming flood control ([#10235](https://github.com/NousResearch/hermes-agent/pull/10235))
- Fix: close temporary agents after one-off tasks ([#11028](https://github.com/NousResearch/hermes-agent/pull/11028), @kshitijk4poor)
- Fix: busy-session ack when user messages during active agent run ([#10068](https://github.com/NousResearch/hermes-agent/pull/10068))
- Fix: route watch-pattern notifications to the originating session ([#10460](https://github.com/NousResearch/hermes-agent/pull/10460))
- Fix: preserve notify context in executor threads ([#10921](https://github.com/NousResearch/hermes-agent/pull/10921), @kshitijk4poor)
- Fix: avoid duplicate replies after interrupted long tasks ([#11018](https://github.com/NousResearch/hermes-agent/pull/11018))
- Fix: unlink stale PID + lock files on cleanup
- Fix: force-unlink stale PID file after `--replace` takeover
---
## 🔧 Tool System
### Plugin Surface (major expansion)
- **`register_command()`** — plugins can now add slash commands ([#10626](https://github.com/NousResearch/hermes-agent/pull/10626))
- **`dispatch_tool()`** — plugins can invoke tools from their code ([#10763](https://github.com/NousResearch/hermes-agent/pull/10763))
- **`pre_tool_call` blocking** — plugins can veto tool execution ([#9377](https://github.com/NousResearch/hermes-agent/pull/9377))
- **`transform_tool_result`** — plugins rewrite tool results generically ([#12972](https://github.com/NousResearch/hermes-agent/pull/12972))
- **`transform_terminal_output`** — plugins rewrite terminal tool output ([#12929](https://github.com/NousResearch/hermes-agent/pull/12929))
- **Namespaced skill registration** for plugin skill bundles ([#9786](https://github.com/NousResearch/hermes-agent/pull/9786))
- **Opt-in-by-default + bundled disk-cleanup plugin** (salvage #12212) ([#12944](https://github.com/NousResearch/hermes-agent/pull/12944))
- **Pluggable `image_gen` backends + OpenAI provider** ([#13799](https://github.com/NousResearch/hermes-agent/pull/13799))
- **`openai-codex` image_gen plugin** (gpt-image-2 via Codex OAuth) ([#14317](https://github.com/NousResearch/hermes-agent/pull/14317))
- **Shell hooks** — wire shell scripts as hook callbacks ([#13296](https://github.com/NousResearch/hermes-agent/pull/13296))
### Browser
- **`browser_cdp` raw DevTools Protocol passthrough** ([#12369](https://github.com/NousResearch/hermes-agent/pull/12369))
- Camofox hardening + connection stability across the window
### Execute Code
- **Project/strict execution modes** (default: project) ([#11971](https://github.com/NousResearch/hermes-agent/pull/11971))
### Image Generation
- **Multi-model FAL support** with picker in `hermes tools` ([#11265](https://github.com/NousResearch/hermes-agent/pull/11265))
- **Recraft V3 → V4 Pro, Nano Banana → Pro upgrades** ([#11406](https://github.com/NousResearch/hermes-agent/pull/11406))
- **GPT Image 2** in FAL catalog ([#13677](https://github.com/NousResearch/hermes-agent/pull/13677))
- **xAI image generation provider** (grok-imagine-image) ([#14765](https://github.com/NousResearch/hermes-agent/pull/14765))
### TTS / STT / Voice
- **Google Gemini TTS provider** ([#11229](https://github.com/NousResearch/hermes-agent/pull/11229))
- **xAI Grok STT provider** ([#14473](https://github.com/NousResearch/hermes-agent/pull/14473))
- **xAI TTS** (shipped with Responses API upgrade) ([#10783](https://github.com/NousResearch/hermes-agent/pull/10783))
- **KittenTTS local provider** (salvage of #2109) ([#13395](https://github.com/NousResearch/hermes-agent/pull/13395))
- **CLI record beep toggle** ([#13247](https://github.com/NousResearch/hermes-agent/pull/13247), @helix4u)
### Webhook / Cron
- **Webhook direct-delivery mode** — zero-LLM push notifications ([#12473](https://github.com/NousResearch/hermes-agent/pull/12473))
- **Cron `wakeAgent` gate** — scripts can skip the agent entirely ([#12373](https://github.com/NousResearch/hermes-agent/pull/12373))
- **Cron per-job `enabled_toolsets`** — cap token overhead + cost per job ([#14767](https://github.com/NousResearch/hermes-agent/pull/14767))
### Delegate
- **Orchestrator role** + configurable spawn depth (default flat) ([#13691](https://github.com/NousResearch/hermes-agent/pull/13691))
- **Cross-agent file state coordination** ([#13718](https://github.com/NousResearch/hermes-agent/pull/13718))
### File / Patch
- **`patch` — "did you mean?" feedback** when patch fails to match ([#13435](https://github.com/NousResearch/hermes-agent/pull/13435))
### API Server
- **Stream `/v1/responses` SSE tool events** (salvage #9779) ([#10049](https://github.com/NousResearch/hermes-agent/pull/10049))
- **Inline image inputs** on `/v1/chat/completions` and `/v1/responses` ([#12969](https://github.com/NousResearch/hermes-agent/pull/12969))
### Docker / Podman
- **Entry-level Podman support** — `find_docker()` + rootless entrypoint ([#10066](https://github.com/NousResearch/hermes-agent/pull/10066))
- **Add docker-cli to Docker image** (salvage #10096) ([#14232](https://github.com/NousResearch/hermes-agent/pull/14232))
- **File-sync back to host on teardown** (salvage of #8189 + hardening) ([#11291](https://github.com/NousResearch/hermes-agent/pull/11291))
### MCP
- 12 MCP improvements across the window (status, timeout handling, tool-call forwarding, etc.)
---
## 🧩 Skills Ecosystem
### Skill System
- **Namespaced skill registration** for plugin bundles ([#9786](https://github.com/NousResearch/hermes-agent/pull/9786))
- **`hermes skills reset`** to un-stick bundled skills ([#11468](https://github.com/NousResearch/hermes-agent/pull/11468))
- **Skills guard opt-in** — `config.skills.guard_agent_created` (default off) ([#14557](https://github.com/NousResearch/hermes-agent/pull/14557))
- **Bundled skill scripts runnable out of the box** ([#13384](https://github.com/NousResearch/hermes-agent/pull/13384))
- **`xitter` replaced with `xurl`** — the official X API CLI ([#12303](https://github.com/NousResearch/hermes-agent/pull/12303))
- **MiniMax-AI/cli as default skill tap** (salvage #7501) ([#14493](https://github.com/NousResearch/hermes-agent/pull/14493))
- **Fuzzy `@` file completions + mtime sorting** ([#9467](https://github.com/NousResearch/hermes-agent/pull/9467))
### New Skills
- **concept-diagrams** (salvage of #11045, @v1k22) ([#11363](https://github.com/NousResearch/hermes-agent/pull/11363))
- **architecture-diagram** (Cocoon AI port) ([#9906](https://github.com/NousResearch/hermes-agent/pull/9906))
- **pixel-art** with hardware palettes and video animation ([#12663](https://github.com/NousResearch/hermes-agent/pull/12663), [#12725](https://github.com/NousResearch/hermes-agent/pull/12725))
- **baoyu-comic** ([#13257](https://github.com/NousResearch/hermes-agent/pull/13257), @JimLiu)
- **baoyu-infographic** — 21 layouts × 21 styles (salvage #9901) ([#12254](https://github.com/NousResearch/hermes-agent/pull/12254))
- **page-agent** — embed Alibaba's in-page GUI agent in your webapp ([#13976](https://github.com/NousResearch/hermes-agent/pull/13976))
- **fitness-nutrition** optional skill + optional env var support ([#9355](https://github.com/NousResearch/hermes-agent/pull/9355))
- **drug-discovery** — ChEMBL, PubChem, OpenFDA, ADMET ([#9443](https://github.com/NousResearch/hermes-agent/pull/9443))
- **touchdesigner-mcp** (salvage of #10081) ([#12298](https://github.com/NousResearch/hermes-agent/pull/12298))
- **adversarial-ux-test** optional skill (salvage of #2494, @omnissiah-comelse) ([#13425](https://github.com/NousResearch/hermes-agent/pull/13425))
- **maps** — added `guest_house`, `camp_site`, and dual-key bakery lookup ([#13398](https://github.com/NousResearch/hermes-agent/pull/13398))
- **llm-wiki** — port provenance markers, source hashing, and quality signals ([#13700](https://github.com/NousResearch/hermes-agent/pull/13700))
---
## 📊 Web Dashboard
- **i18n (English + Chinese) language switcher** ([#9453](https://github.com/NousResearch/hermes-agent/pull/9453))
- **Live-switching theme system** ([#10687](https://github.com/NousResearch/hermes-agent/pull/10687))
- **Dashboard plugin system** — extend the web UI with custom tabs ([#10951](https://github.com/NousResearch/hermes-agent/pull/10951))
- **react-router, sidebar layout, sticky header, dropdown component** ([#9370](https://github.com/NousResearch/hermes-agent/pull/9370), @austinpickett)
- **Responsive for mobile** ([#9228](https://github.com/NousResearch/hermes-agent/pull/9228), @DeployFaith)
- **Vercel deployment** ([#10686](https://github.com/NousResearch/hermes-agent/pull/10686), [#11061](https://github.com/NousResearch/hermes-agent/pull/11061), @austinpickett)
- **Context window config support** ([#9357](https://github.com/NousResearch/hermes-agent/pull/9357))
- **HTTP health probe for cross-container gateway detection** ([#9894](https://github.com/NousResearch/hermes-agent/pull/9894))
- **Update + restart gateway buttons** ([#13526](https://github.com/NousResearch/hermes-agent/pull/13526), @austinpickett)
- **Real API call count per session** (salvages #10140) ([#14004](https://github.com/NousResearch/hermes-agent/pull/14004))
---
## 🖱️ CLI & User Experience
- **Dynamic shell completion for bash, zsh, and fish** ([#9785](https://github.com/NousResearch/hermes-agent/pull/9785))
- **Light-mode skins + skin-aware completion menus** ([#9461](https://github.com/NousResearch/hermes-agent/pull/9461))
- **Numbered keyboard shortcuts** on approval and clarify prompts ([#13416](https://github.com/NousResearch/hermes-agent/pull/13416))
- **Markdown stripping, compact multiline previews, external editor** ([#12934](https://github.com/NousResearch/hermes-agent/pull/12934))
- **`--ignore-user-config` and `--ignore-rules` flags** (port codex#18646) ([#14277](https://github.com/NousResearch/hermes-agent/pull/14277))
- **Account limits section in `/usage`** ([#13428](https://github.com/NousResearch/hermes-agent/pull/13428))
- **Doctor: Command Installation check** for `hermes` bin symlink ([#10112](https://github.com/NousResearch/hermes-agent/pull/10112))
- **ESC cancels secret/sudo prompts**, clearer skip messaging ([#9902](https://github.com/NousResearch/hermes-agent/pull/9902))
- Fix: agent-facing text uses `display_hermes_home()` instead of hardcoded `~/.hermes` ([#10285](https://github.com/NousResearch/hermes-agent/pull/10285))
- Fix: enforce `config.yaml` as sole CWD source + deprecate `.env` CWD vars + add `hermes memory reset` ([#11029](https://github.com/NousResearch/hermes-agent/pull/11029))
---
## 🔒 Security & Reliability
- **Global toggle to allow private/internal URL resolution** ([#14166](https://github.com/NousResearch/hermes-agent/pull/14166))
- **Block agent from self-destructing the gateway** via terminal (closes #6666) ([#9895](https://github.com/NousResearch/hermes-agent/pull/9895))
- **Telegram callback authorization** on update prompts ([#10536](https://github.com/NousResearch/hermes-agent/pull/10536))
- **SECURITY.md** added ([#10532](https://github.com/NousResearch/hermes-agent/pull/10532), @I3eg1nner)
- **Warn about legacy hermes.service units** during `hermes update` ([#11918](https://github.com/NousResearch/hermes-agent/pull/11918))
- **Complete ASCII-locale UnicodeEncodeError recovery** for `api_messages`/`reasoning_content` (closes #6843) ([#10537](https://github.com/NousResearch/hermes-agent/pull/10537))
- **Prevent stale `os.environ` leak** after `clear_session_vars` ([#10527](https://github.com/NousResearch/hermes-agent/pull/10527))
- **Prevent agent hang when backgrounding processes** via terminal tool ([#10584](https://github.com/NousResearch/hermes-agent/pull/10584))
- Many smaller session-resume, interrupt, streaming, and memory-race fixes throughout the window
---
## 🐛 Notable Bug Fixes
The `fix:` category in this window covers 482 PRs. Highlights:
- Streaming cursor artifacts filtered from Matrix, Telegram, WhatsApp, Discord (multiple PRs)
- `<think>` and `<thought>` blocks filtered from gateway stream consumers ([#9408](https://github.com/NousResearch/hermes-agent/pull/9408))
- Gateway display.streaming root-config override regression ([#9799](https://github.com/NousResearch/hermes-agent/pull/9799))
- Context `session_search` coerces limit to int (prevents TypeError) ([#10522](https://github.com/NousResearch/hermes-agent/pull/10522))
- Memory tool stays available when `fcntl` is unavailable (Windows) ([#9783](https://github.com/NousResearch/hermes-agent/pull/9783))
- Trajectory compressor credentials load from `HERMES_HOME/.env` ([#9632](https://github.com/NousResearch/hermes-agent/pull/9632), @Dusk1e)
- `@_context_completions` no longer crashes on `@` mention ([#9683](https://github.com/NousResearch/hermes-agent/pull/9683), @kshitijk4poor)
- Group session `user_id` no longer treated as `thread_id` in shutdown notifications ([#10546](https://github.com/NousResearch/hermes-agent/pull/10546))
- Telegram `platform_hint` — markdown is supported (closes #8261) ([#10612](https://github.com/NousResearch/hermes-agent/pull/10612))
- Doctor checks for Kimi China credentials fixed
- Streaming: don't suppress final response when commentary message is sent ([#10540](https://github.com/NousResearch/hermes-agent/pull/10540))
- Rapid Telegram follow-ups no longer get cut off
---
## 🧪 Testing & CI
- **Contributor attribution CI check** on PRs ([#9376](https://github.com/NousResearch/hermes-agent/pull/9376))
- Hermetic test parity (`scripts/run_tests.sh`) held across this window
- Test count stabilized post-Transport refactor; CI matrix held green through the transport rollout
---
## 📚 Documentation
- Atropos + wandb links in user guide
- ACP / VS Code / Zed / JetBrains integration docs refresh
- Webhook subscription docs updated for direct-delivery mode
- Plugin author guide expanded for new hooks (`register_command`, `dispatch_tool`, `transform_tool_result`)
- Transport layer developer guide added
- Website removed Discussions link from README
---
## 👥 Contributors
### Core
- **@teknium1** (Teknium)
### Top Community Contributors (by merged PR count)
- **@kshitijk4poor** — 49 PRs · Transport refactor (AnthropicTransport, ResponsesApiTransport), Step Plan provider, Xiaomi MiMo v2.5 support, numerous gateway fixes, promoted Kimi K2.5, @ mention crash fix
- **@OutThisLife** (Brooklyn) — 31 PRs · TUI polish, git branch in status bar, per-turn stopwatch, stable picker keys, `/clear` confirm, light-theme preset, subagent spawn observability overlay
- **@helix4u** — 11 PRs · Voice CLI record beep, MCP tool interrupt handling, assorted stability fixes
- **@austinpickett** — 8 PRs · Dashboard react-router + sidebar + sticky header + dropdown, Vercel deployment, update + restart buttons
- **@alt-glitch** — 8 PRs · PLATFORM_HINTS for Matrix/Mattermost/Feishu, Matrix fixes
- **@ethernet8023** — 3 PRs
- **@benbarclay** — 3 PRs
- **@Aslaaen** — 2 PRs
### Also contributing
@jerilynzheng (ai-gateway pricing), @JimLiu (baoyu-comic skill), @Dusk1e (trajectory compressor credentials), @DeployFaith (mobile-responsive dashboard), @LeonSGP43, @v1k22 (concept-diagrams), @omnissiah-comelse (adversarial-ux-test), @coekfung (Telegram MarkdownV2 expandable blockquotes), @liftaris (TUI provider resolution), @arihantsethia (skill analytics dashboard), @topcheer + @xing8star (QQBot foundation), @kovyrin, @I3eg1nner (SECURITY.md), @PeterBerthelsen, @lengxii, @priveperfumes, @sjz-ks, @cuyua9, @Disaster-Terminator, @leozeli, @LehaoLin, @trevthefoolish, @loongfay, @MrNiceRicee, @WideLee, @bluefishs, @malaiwah, @bobashopcashier, @dsocolobsky, @iamagenius00, @IAvecilla, @aniruddhaadak80, @Es1la, @asheriif, @walli, @jquesnelle (original Tool Gateway work).
### All Contributors (alphabetical)
@0xyg3n, @10ishq, @A-afflatus, @Abnertheforeman, @admin28980, @adybag14-cyber, @akhater, @alexzhu0,
@AllardQuek, @alt-glitch, @aniruddhaadak80, @anna-oake, @anniesurla, @anthhub, @areu01or00, @arihantsethia,
@arthurbr11, @asheriif, @Aslaaen, @Asunfly, @austinpickett, @AviArora02-commits, @AxDSan, @azhengbot, @Bartok9,
@benbarclay, @bennytimz, @bernylinville, @bingo906, @binhnt92, @bkadish, @bluefishs, @bobashopcashier,
@brantzh6, @BrennerSpear, @brianclemens, @briandevans, @brooklynnicholson, @bugkill3r, @buray, @burtenshaw,
@cdanis, @cgarwood82, @ChimingLiu, @chongweiliu, @christopherwoodall, @coekfung, @cola-runner, @corazzione,
@counterposition, @cresslank, @cuyua9, @cypres0099, @danieldoderlein, @davetist, @davidvv, @DeployFaith,
@Dev-Mriganka, @devorun, @dieutx, @Disaster-Terminator, @dodo-reach, @draix, @DrStrangerUJN, @dsocolobsky,
@Dusk1e, @dyxushuai, @elkimek, @elmatadorgh, @emozilla, @entropidelic, @Erosika, @erosika, @Es1la, @etcircle,
@etherman-os, @ethernet8023, @fancydirty, @farion1231, @fatinghenji, @Fatty911, @fengtianyu88, @Feranmi10,
@flobo3, @francip, @fuleinist, @g-guthrie, @GenKoKo, @gianfrancopiana, @gnanam1990, @GuyCui, @haileymarshall,
@haimu0x, @handsdiff, @hansnow, @hedgeho9X, @helix4u, @hengm3467, @HenkDz, @heykb, @hharry11, @HiddenPuppy,
@honghua, @houko, @houziershi, @hsy5571616, @huangke19, @hxp-plus, @Hypn0sis, @I3eg1nner, @iacker,
@iamagenius00, @IAvecilla, @iborazzi, @Ifkellx, @ifrederico, @imink, @isaachuangGMICLOUD, @ismell0992-afk,
@j0sephz, @Jaaneek, @jackjin1997, @JackTheGit, @jaffarkeikei, @jerilynzheng, @JiaDe-Wu, @Jiawen-lee, @JimLiu,
@jinzheng8115, @jneeee, @jplew, @jquesnelle, @Julientalbot, @Junass1, @jvcl, @kagura-agent, @keifergu,
@kevinskysunny, @keyuyuan, @konsisumer, @kovyrin, @kshitijk4poor, @leeyang1990, @LehaoLin, @lengxii,
@LeonSGP43, @leozeli, @li0near, @liftaris, @Lind3ey, @Linux2010, @liujinkun2025, @LLQWQ, @Llugaes, @lmoncany,
@longsizhuo, @lrawnsley, @Lubrsy706, @lumenradley, @luyao618, @lvnilesh, @LVT382009, @m0n5t3r, @Magaav,
@MagicRay1217, @malaiwah, @manuelschipper, @Marvae, @MassiveMassimo, @mavrickdeveloper, @maxchernin, @memosr,
@meng93, @mengjian-github, @MestreY0d4-Uninter, @Mibayy, @MikeFac, @mikewaters, @milkoor, @minorgod,
@MrNiceRicee, @ms-alan, @mvanhorn, @n-WN, @N0nb0at, @Nan93, @NIDNASSER-Abdelmajid, @nish3451, @niyoh120,
@nocoo, @nosleepcassette, @NousResearch, @ogzerber, @omnissiah-comelse, @Only-Code-A, @opriz, @OwenYWT, @pedh,
@pefontana, @PeterBerthelsen, @phpoh, @pinion05, @plgonzalezrx8, @pradeep7127, @priveperfumes,
@projectadmin-dev, @PStarH, @rnijhara, @Roy-oss1, @roytian1217, @RucchiZ, @Ruzzgar, @RyanLee-Dev, @Salt-555,
@Sanjays2402, @sgaofen, @sharziki, @shenuu, @shin4, @SHL0MS, @shushuzn, @sicnuyudidi, @simon-gtcl,
@simon-marcus, @sirEven, @Sisyphus, @sjz-ks, @snreynolds, @Societus, @Somme4096, @sontianye, @sprmn24,
@StefanIsMe, @stephenschoettler, @Swift42, @taeng0204, @taeuk178, @tannerfokkens-maker, @TaroballzChen,
@ten-ltw, @teyrebaz33, @Tianworld, @topcheer, @Tranquil-Flow, @trevthefoolish, @TroyMitchell911, @UNLINEARITY,
@v1k22, @vivganes, @vominh1919, @vrinek, @VTRiot, @WadydX, @walli, @wenhao7, @WhiteWorld, @WideLee, @wujhsu,
@WuTianyi123, @Wysie, @xandersbell, @xiaoqiang243, @xiayh0107, @xinpengdr, @Xowiek, @ycbai, @yeyitech, @ygd58,
@youngDoo, @yudaiyan, @Yukipukii1, @yule975, @yyq4193, @yzx9, @ZaynJarvis, @zhang9w0v5, @zhanggttry,
@zhangxicen, @zhongyueming1121, @zhouxiaoya12, @zons-zhaozhy
Also: @maelrx, @Marco Rutsch, @MaxsolcuCrypto, @Mind-Dragon, @Paul Bergeron, @say8hi, @whitehatjr1001.
---
**Full Changelog**: [v2026.4.13...v2026.4.23](https://github.com/NousResearch/hermes-agent/compare/v2026.4.13...v2026.4.23)

View File

@@ -1,505 +0,0 @@
# Hermes Agent v0.12.0 (v2026.4.30)
**Release Date:** April 30, 2026
**Since v0.11.0:** 1,096 commits · 550 merged PRs · 1,270 files changed · 217,776 insertions · 213 community contributors (including co-authors)
> The Curator release — Hermes Agent now maintains itself. An autonomous background Curator grades, prunes, and consolidates your skill library on its own schedule. The self-improvement loop that reviews what to save got a substantial upgrade. Four new inference providers, a 18th messaging platform, a 19th via Teams plugin, native Spotify + Google Meet integrations, ComfyUI and TouchDesigner-MCP moved from optional to bundled-by-default, and a ~57% cut to visible TUI cold start.
---
## ✨ Highlights
- **Autonomous Curator** — `hermes curator` runs as a background agent on the gateway's cron ticker (7-day cycle default). It grades your skill library, consolidates related skills, prunes dead ones, and writes per-run reports to `logs/curator/run.json` + `REPORT.md`. Archived skills are classified consolidated-vs-pruned via model + heuristic. Defense-in-depth gates protect bundled/hub skills from mutation. Unified under `auxiliary.curator` — pick the curator's model in `hermes model`, manage it from the dashboard. `hermes curator status` ranks skills by usage (most-used / least-used). ([#17277](https://github.com/NousResearch/hermes-agent/pull/17277), [#17307](https://github.com/NousResearch/hermes-agent/pull/17307), [#17941](https://github.com/NousResearch/hermes-agent/pull/17941), [#17868](https://github.com/NousResearch/hermes-agent/pull/17868), [#18033](https://github.com/NousResearch/hermes-agent/pull/18033))
- **Self-improvement loop — substantially upgraded** — The background review fork (the core of Hermes' self-improvement: after each turn it decides what memories/skills to save or update) is now class-first (rubric-based rather than free-form), active-update biased (prefers the skill the agent just loaded), handles `references/`/`templates/` sub-files, and properly inherits the parent's live runtime (provider, model, credentials actually propagate). Restricted to memory + skills toolsets so it can't sprawl. Memory providers shut down cleanly. Prior-turn tool messages excluded from the summary so the fork sees a clean context. ([#16026](https://github.com/NousResearch/hermes-agent/pull/16026), [#17213](https://github.com/NousResearch/hermes-agent/pull/17213), [#16099](https://github.com/NousResearch/hermes-agent/pull/16099), [#16569](https://github.com/NousResearch/hermes-agent/pull/16569), [#16204](https://github.com/NousResearch/hermes-agent/pull/16204), [#15057](https://github.com/NousResearch/hermes-agent/pull/15057))
- **Skill integrations — major expansion** — **ComfyUI v5** with official CLI + REST + hardware-gated local install, moved from optional to **built-in by default** ([#17610](https://github.com/NousResearch/hermes-agent/pull/17610), [#17631](https://github.com/NousResearch/hermes-agent/pull/17631), [#17734](https://github.com/NousResearch/hermes-agent/pull/17734)). **TouchDesigner-MCP** bundled by default, expanded with GLSL, post-FX, audio, geometry, and 9 new reference docs ([#16753](https://github.com/NousResearch/hermes-agent/pull/16753), [#16624](https://github.com/NousResearch/hermes-agent/pull/16624), [#16768](https://github.com/NousResearch/hermes-agent/pull/16768) — @kshitijk4poor + @SHL0MS). **Humanizer** skill ports a text-cleaner that strips AI-isms ([#16787](https://github.com/NousResearch/hermes-agent/pull/16787)). **claude-design** HTML artifact skill + design-md (Google DESIGN.md spec) + airtable salvage + `skill_manage` edits in `external_dirs` + direct-URL skill install + `/reload-skills` slash command. ([#16358](https://github.com/NousResearch/hermes-agent/pull/16358), [#14876](https://github.com/NousResearch/hermes-agent/pull/14876), [#16291](https://github.com/NousResearch/hermes-agent/pull/16291), [#17512](https://github.com/NousResearch/hermes-agent/pull/17512), [#16323](https://github.com/NousResearch/hermes-agent/pull/16323), [#17744](https://github.com/NousResearch/hermes-agent/pull/17744))
- **LM Studio — first-class provider** — upgraded from a custom-endpoint alias to a full-blown native provider: dedicated auth, `hermes doctor` checks, reasoning transport, live `/models` listing. (Salvage of @kshitijk4poor's #17061.) ([#17102](https://github.com/NousResearch/hermes-agent/pull/17102))
- **Four more new inference providers** — **GMI Cloud** (first-class, salvage of #11955@isaachuangGMICLOUD), **Azure AI Foundry** with auto-detection, **MiniMax OAuth** with PKCE browser flow (salvage #15203), **Tencent Tokenhub** (salvage of #16860). ([#16663](https://github.com/NousResearch/hermes-agent/pull/16663), [#15845](https://github.com/NousResearch/hermes-agent/pull/15845), [#17524](https://github.com/NousResearch/hermes-agent/pull/17524), [#16960](https://github.com/NousResearch/hermes-agent/pull/16960))
- **Pluggable gateway platforms + Microsoft Teams** — the gateway is now a plugin host. Drop-in messaging adapters live outside the core, and Microsoft Teams is the first plugin-shipped platform. (Salvage of #17664.) ([#17751](https://github.com/NousResearch/hermes-agent/pull/17751), [#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
- **Tencent 元宝 (Yuanbao) — 18th messaging platform** — native gateway adapter with text + media delivery. ([#16298](https://github.com/NousResearch/hermes-agent/pull/16298), [#17424](https://github.com/NousResearch/hermes-agent/pull/17424))
- **Spotify — native tools + bundled skill + wizard** — 7 tools (play, search, queue, playlists, devices) behind PKCE OAuth, interactive setup wizard, bundled skill, surfacing in `hermes tools`, cron usage documented. ([#15121](https://github.com/NousResearch/hermes-agent/pull/15121), [#15130](https://github.com/NousResearch/hermes-agent/pull/15130), [#15154](https://github.com/NousResearch/hermes-agent/pull/15154), [#15180](https://github.com/NousResearch/hermes-agent/pull/15180))
- **Google Meet plugin** — join calls, transcribe, speak, follow up. Realtime OpenAI transport + Node bot server, full pipeline bundled as a plugin. ([#16364](https://github.com/NousResearch/hermes-agent/pull/16364))
- **`hermes -z` one-shot mode + `hermes update --check`** — non-interactive `hermes -z <prompt>` with `--model`/`--provider`/`HERMES_INFERENCE_MODEL`. `hermes update --check` preflight. Opt-in pre-update HERMES_HOME backup. ([#15702](https://github.com/NousResearch/hermes-agent/pull/15702), [#15704](https://github.com/NousResearch/hermes-agent/pull/15704), [#15841](https://github.com/NousResearch/hermes-agent/pull/15841), [#16539](https://github.com/NousResearch/hermes-agent/pull/16539), [#16566](https://github.com/NousResearch/hermes-agent/pull/16566))
- **Models dashboard tab + in-browser model config** — rich per-model analytics, switch main + auxiliary models from the dashboard. ([#17745](https://github.com/NousResearch/hermes-agent/pull/17745), [#17802](https://github.com/NousResearch/hermes-agent/pull/17802))
- **Remote model catalog manifest** — OpenRouter + Nous Portal model catalogs are now pulled from a remote manifest so new models show up without a release. ([#16033](https://github.com/NousResearch/hermes-agent/pull/16033))
- **Native multimodal image routing** — images now route based on the model's actual vision capability rather than provider defaults. ([#16506](https://github.com/NousResearch/hermes-agent/pull/16506))
- **Gateway media parity** — native multi-image sending across Telegram, Discord, Slack, Mattermost, Email, and Signal; centralized audio routing with FLAC support + Telegram document fallback. ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909), [#17833](https://github.com/NousResearch/hermes-agent/pull/17833))
- **TUI catches up to (and past) the classic CLI** — LaTeX rendering (@austinpickett), `/reload` .env hot-reload, pluggable busy-indicator styles (@OutThisLife, #13610), opt-in auto-resume of last session, expanded light-terminal auto-detection, session delete from `/resume` picker with `d`, modified mouse-wheel line scroll, and a `/mouse` toggle that kills ConPTY's phantom mouse injection (@kevin-ho). ([#17175](https://github.com/NousResearch/hermes-agent/pull/17175), [#17286](https://github.com/NousResearch/hermes-agent/pull/17286), [#17150](https://github.com/NousResearch/hermes-agent/pull/17150), [#17130](https://github.com/NousResearch/hermes-agent/pull/17130), [#17113](https://github.com/NousResearch/hermes-agent/pull/17113), [#17668](https://github.com/NousResearch/hermes-agent/pull/17668), [#17669](https://github.com/NousResearch/hermes-agent/pull/17669), [#15488](https://github.com/NousResearch/hermes-agent/pull/15488))
- **Observability + achievements plugins** — bundled Langfuse observability plugin (salvage #16845) + bundled hermes-achievements plugin that scans full session history. ([#16917](https://github.com/NousResearch/hermes-agent/pull/16917), [#17754](https://github.com/NousResearch/hermes-agent/pull/17754))
- **TTS provider registry + Piper local TTS** — pluggable `tts.providers.<name>` registry; Piper ships as a native local TTS provider. (Closes #8508.) ([#17843](https://github.com/NousResearch/hermes-agent/pull/17843), [#17885](https://github.com/NousResearch/hermes-agent/pull/17885))
- **Vercel Sandbox backend** — Vercel sandboxes as an execute_code/terminal backend (@kshitijk4poor). ([#17445](https://github.com/NousResearch/hermes-agent/pull/17445))
- **Secret redaction off by default** — default flipped to off. Prevents the long-standing patch-corruption incidents where fake secret-shaped substrings mangled tool outputs. Opt in via `redaction.enabled: true` when you need it. ([#16794](https://github.com/NousResearch/hermes-agent/pull/16794))
- **Cold-start performance** — visible TUI cold start cut **~57%** via lazy agent init (@OutThisLife), lazy imports of OpenAI / Anthropic / Firecrawl / account_usage, mtime-cached `load_config()`, memoized `get_tool_definitions()` with TTL-cached `check_fn` results, precompiled dangerous-command patterns. ([#17190](https://github.com/NousResearch/hermes-agent/pull/17190), [#17046](https://github.com/NousResearch/hermes-agent/pull/17046), [#17041](https://github.com/NousResearch/hermes-agent/pull/17041), [#17098](https://github.com/NousResearch/hermes-agent/pull/17098), [#17206](https://github.com/NousResearch/hermes-agent/pull/17206))
- **Configurable prompt cache TTL** — `prompt_caching.cache_ttl` (5m default, 1h opt-in — cost savings for bursty sessions that keep cache warm). Salvage of #12659. ([#15065](https://github.com/NousResearch/hermes-agent/pull/15065))
---
## 🧠 Autonomous Curator & Self-Improvement Loop
### Curator — autonomous skill maintenance
- **`hermes curator` as a background agent** — runs on the gateway's cron ticker, 7-day cycle by default, umbrella-first prompt, inherits parent config, unbounded iterations ([#17277](https://github.com/NousResearch/hermes-agent/pull/17277) — issue #7816)
- **Per-run reports** — `logs/curator/run.json` + `REPORT.md` per cycle ([#17307](https://github.com/NousResearch/hermes-agent/pull/17307))
- **Consolidated vs pruned classification** — archived skills split with model + heuristic ([#17941](https://github.com/NousResearch/hermes-agent/pull/17941))
- **`hermes curator status`** — ranks skills by usage, shows most-used and least-used ([#18033](https://github.com/NousResearch/hermes-agent/pull/18033))
- **Unified under `auxiliary.curator`** — pick the model in `hermes model`, configure from the dashboard ([#17868](https://github.com/NousResearch/hermes-agent/pull/17868))
- **Documentation** — dedicated curator feature page on the docs site ([#17563](https://github.com/NousResearch/hermes-agent/pull/17563))
- Fix: seed defaults on update, create `logs/curator/` directory, defer fire import ([#17927](https://github.com/NousResearch/hermes-agent/pull/17927))
- Fix: scan nested archive subdirs in `restore_skill` (@0xDevNinja) ([#17951](https://github.com/NousResearch/hermes-agent/pull/17951))
- Fix: use actual skill activity in curator status (@y0shua1ee) ([#17953](https://github.com/NousResearch/hermes-agent/pull/17953))
- Fix: `skill_manage` refuses writes on pinned skills; pinning now blocks curator writes ([#17562](https://github.com/NousResearch/hermes-agent/pull/17562), [#17578](https://github.com/NousResearch/hermes-agent/pull/17578))
- Fix: `bump_use()` wired into skill invocation + preload + skill_view (salvage #17782) ([#17932](https://github.com/NousResearch/hermes-agent/pull/17932))
### Self-improvement loop (background review fork)
- **Class-first skill-review prompt** — rubric-based grading rather than free-form "should this update" ([#16026](https://github.com/NousResearch/hermes-agent/pull/16026))
- **Active-update bias** — prefers updating skills the agent just loaded, handles `references/` + `templates/` sub-files ([#17213](https://github.com/NousResearch/hermes-agent/pull/17213))
- **Fork inherits parent's live runtime** — provider, model, credentials actually propagate now ([#16099](https://github.com/NousResearch/hermes-agent/pull/16099))
- **Scoped toolsets** — review fork restricted to memory + skills (no shell, no web) ([#16569](https://github.com/NousResearch/hermes-agent/pull/16569))
- **Clean shutdown** — background review memory providers exit properly (salvage #15289) ([#16204](https://github.com/NousResearch/hermes-agent/pull/16204))
- **Clean context** — prior-history tool messages excluded from review summary (salvage #14967) ([#15057](https://github.com/NousResearch/hermes-agent/pull/15057))
---
## 🧩 Skills Ecosystem
### Skill integrations — newly bundled or promoted
- **ComfyUI v5** — official CLI + REST + hardware-gated local install; **moved from optional to built-in** ([#17610](https://github.com/NousResearch/hermes-agent/pull/17610), [#17631](https://github.com/NousResearch/hermes-agent/pull/17631), [#17734](https://github.com/NousResearch/hermes-agent/pull/17734), [#17612](https://github.com/NousResearch/hermes-agent/pull/17612))
- **TouchDesigner-MCP** — **bundled by default** ([#16753](https://github.com/NousResearch/hermes-agent/pull/16753) — @kshitijk4poor), expanded with GLSL, post-FX, audio, geometry references ([#16624](https://github.com/NousResearch/hermes-agent/pull/16624)), 9 new reference docs ([#16768](https://github.com/NousResearch/hermes-agent/pull/16768) — @SHL0MS)
- **Humanizer** — strips AI-isms from text ([#16787](https://github.com/NousResearch/hermes-agent/pull/16787))
- **claude-design** — HTML artifact skill with disambiguation from other design skills ([#16358](https://github.com/NousResearch/hermes-agent/pull/16358))
- **design-md** — Google's DESIGN.md spec skill ([#14876](https://github.com/NousResearch/hermes-agent/pull/14876))
- **airtable** — salvaged skill + skill API keys wired into `.env` (#15838) ([#16291](https://github.com/NousResearch/hermes-agent/pull/16291))
- **pretext** — creative browser demos with @chenglou/pretext ([#17259](https://github.com/NousResearch/hermes-agent/pull/17259))
- **spike** + **sketch** — throwaway experiments + HTML mockups, adapted from gsd-build ([#17421](https://github.com/NousResearch/hermes-agent/pull/17421))
### Skills UX
- **Install skills from a direct HTTP(S) URL** — `hermes skills install <url>` ([#16323](https://github.com/NousResearch/hermes-agent/pull/16323))
- **`/reload-skills`** slash command (salvage #17670) ([#17744](https://github.com/NousResearch/hermes-agent/pull/17744))
- **`hermes skills list`** shows enabled/disabled status ([#16129](https://github.com/NousResearch/hermes-agent/pull/16129))
- **`skill_manage` refuses writes on pinned skills** ([#17562](https://github.com/NousResearch/hermes-agent/pull/17562))
- **`skill_manage` edits external_dirs skills in place** (salvage #9966) ([#17512](https://github.com/NousResearch/hermes-agent/pull/17512), [#17289](https://github.com/NousResearch/hermes-agent/pull/17289))
- Fix: inline-shell rendering in `skill_view` ([#15376](https://github.com/NousResearch/hermes-agent/pull/15376))
- Fix: exclude `.archive/` from skill index walk (salvage #17639) ([#17931](https://github.com/NousResearch/hermes-agent/pull/17931))
- Fix: dedicated docs page per bundled + optional skill ([#14929](https://github.com/NousResearch/hermes-agent/pull/14929))
- Fix: `google-workspace` shared HERMES_HOME helper + ship deps as optional extra ([#15405](https://github.com/NousResearch/hermes-agent/pull/15405))
- Fix: auto-wrap ASCII-art code blocks in generated skill pages ([#16497](https://github.com/NousResearch/hermes-agent/pull/16497))
- Point agent at `hermes-agent` skill + docs site for Hermes questions ([#16535](https://github.com/NousResearch/hermes-agent/pull/16535))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
#### New providers
- **GMI Cloud** — first-class API-key provider on par with Arcee/Kilocode/Xiaomi (salvage of #11955@isaachuangGMICLOUD) ([#16663](https://github.com/NousResearch/hermes-agent/pull/16663))
- **Azure AI Foundry** — auto-detection, full wiring ([#15845](https://github.com/NousResearch/hermes-agent/pull/15845))
- **LM Studio** — upgraded from custom-endpoint alias to first-class provider: dedicated auth, doctor checks, reasoning transport, live `/models` (salvage of #17061@kshitijk4poor) ([#17102](https://github.com/NousResearch/hermes-agent/pull/17102))
- **MiniMax OAuth** — PKCE browser flow with full OAuth integration (salvage #15203) ([#17524](https://github.com/NousResearch/hermes-agent/pull/17524))
- **Tencent Tokenhub** — new provider (salvage of #16860) ([#16960](https://github.com/NousResearch/hermes-agent/pull/16960))
#### Model catalog
- **Remote model catalog manifest** — OpenRouter + Nous Portal catalogs pulled from remote manifest so new models show up without a release ([#16033](https://github.com/NousResearch/hermes-agent/pull/16033))
- `openai/gpt-5.5` and `gpt-5.5-pro` added to OpenRouter + Nous Portal ([#15343](https://github.com/NousResearch/hermes-agent/pull/15343))
- `deepseek-v4-pro` and `deepseek-v4-flash` added ([#14934](https://github.com/NousResearch/hermes-agent/pull/14934))
- `qwen3.6-plus` added to Alibaba-supported models ([#16896](https://github.com/NousResearch/hermes-agent/pull/16896))
- Gemini free-tier keys blocked at setup with 429 guidance surfacing ([#15100](https://github.com/NousResearch/hermes-agent/pull/15100))
#### Model configuration
- **Configurable `prompt_caching.cache_ttl`** — 5m default, 1h opt-in (salvage #12659) ([#15065](https://github.com/NousResearch/hermes-agent/pull/15065))
- `/fast` whitelist broadened to all OpenAI + Anthropic models ([#16883](https://github.com/NousResearch/hermes-agent/pull/16883))
- `auxiliary.extra_body.reasoning` translates into Codex Responses API ([#17004](https://github.com/NousResearch/hermes-agent/pull/17004))
- `hermes fallback` command for managing fallback providers ([#16052](https://github.com/NousResearch/hermes-agent/pull/16052))
### Agent Loop & Conversation
- **Native multimodal image routing** — based on model vision capability, not provider defaults ([#16506](https://github.com/NousResearch/hermes-agent/pull/16506))
- **Delegate `child_timeout_seconds` default bumped to 600s** ([#14809](https://github.com/NousResearch/hermes-agent/pull/14809))
- **Diagnostic dump when subagent times out with 0 API calls** ([#15105](https://github.com/NousResearch/hermes-agent/pull/15105))
- **Gateway busts cached agent on compression/context_length config edits** ([#17008](https://github.com/NousResearch/hermes-agent/pull/17008))
- **Opt-in runtime-metadata footer on final replies** ([#17026](https://github.com/NousResearch/hermes-agent/pull/17026))
- `/reload-mcp` awareness — rebuild cached agents + prompt-cache cost confirmation ([#17729](https://github.com/NousResearch/hermes-agent/pull/17729))
- Fix: repair CamelCase + `_tool` suffix tool-call emissions ([#15124](https://github.com/NousResearch/hermes-agent/pull/15124))
- Fix: retry on `json.JSONDecodeError` instead of treating as local validation error ([#15107](https://github.com/NousResearch/hermes-agent/pull/15107))
- Fix: handle unescaped control chars in `tool_call.arguments` ([#15356](https://github.com/NousResearch/hermes-agent/pull/15356))
- Fix: ordering fix in `_copy_reasoning_content_for_api` — cross-provider reasoning isolation (@Zjianru) ([#15749](https://github.com/NousResearch/hermes-agent/pull/15749))
- Fix: inject empty `reasoning_content` for DeepSeek/Kimi `tool_calls` unconditionally (@Zjianru) ([#15762](https://github.com/NousResearch/hermes-agent/pull/15762))
- Fix: persist streamed `reasoning_content` on assistant turns (#16844) ([#16892](https://github.com/NousResearch/hermes-agent/pull/16892))
- Fix: cancel coroutine on timeout so worker thread exits; full traceback on tool failure ([#17428](https://github.com/NousResearch/hermes-agent/pull/17428))
- Fix: isolate `get_tool_definitions` quiet_mode cache + dedup LCM injection (#17335) ([#17889](https://github.com/NousResearch/hermes-agent/pull/17889))
- Fix: serialize concurrent `hermes_tools` RPC calls from `execute_code` (#17770) ([#17894](https://github.com/NousResearch/hermes-agent/pull/17894), [#17902](https://github.com/NousResearch/hermes-agent/pull/17902))
- Fix: rename `[SYSTEM:``[IMPORTANT:` in all user-injected markers (dodges Azure content filter) ([#16114](https://github.com/NousResearch/hermes-agent/pull/16114))
### Compression
- **Retry summary on main model for unknown errors before giving up** ([#16774](https://github.com/NousResearch/hermes-agent/pull/16774))
- **Notify users when configured aux model fails even if main-model fallback recovers** ([#16775](https://github.com/NousResearch/hermes-agent/pull/16775))
- `/compress` wrapped in `_busy_command` to block input during compression ([#15388](https://github.com/NousResearch/hermes-agent/pull/15388))
- Fix: reserve system + tools headroom when aux binds threshold ([#15631](https://github.com/NousResearch/hermes-agent/pull/15631))
- Fix: use text-char sum for multimodal token estimation in `_find_tail_cut_by_tokens` ([#16369](https://github.com/NousResearch/hermes-agent/pull/16369))
### Session, Memory & State
- **Trigram FTS5 index for CJK search, replace LIKE fallback** (@alt-glitch) ([#16651](https://github.com/NousResearch/hermes-agent/pull/16651))
- **Index `tool_name` + `tool_calls` in FTS5, with repair + migration** (salvages #16866) ([#16914](https://github.com/NousResearch/hermes-agent/pull/16914))
- **Checkpoints: auto-prune orphan and stale shadow repos at startup** ([#16303](https://github.com/NousResearch/hermes-agent/pull/16303))
- **Memory providers notified on mid-process session_id rotation** (#6672) ([#17409](https://github.com/NousResearch/hermes-agent/pull/17409))
- Fix: quote underscored terms in FTS5 query sanitization ([#16915](https://github.com/NousResearch/hermes-agent/pull/16915))
- Fix: resolve viking_read 500/412 on file URIs + pseudo-summary URIs (salvage #5886) ([#17869](https://github.com/NousResearch/hermes-agent/pull/17869))
- Fix: skip external-provider sync on interrupted turns ([#15395](https://github.com/NousResearch/hermes-agent/pull/15395))
- Fix: close embedded Hindsight async client cleanly (salvage #14605) ([#16209](https://github.com/NousResearch/hermes-agent/pull/16209))
- Fix: pass session transcript to `shutdown_memory_provider` on gateway + CLI (#15165) ([#16571](https://github.com/NousResearch/hermes-agent/pull/16571))
- Fix: write-origin metadata seam ([#15346](https://github.com/NousResearch/hermes-agent/pull/15346))
- Fix: preserve symlinks during atomic file writes ([#16980](https://github.com/NousResearch/hermes-agent/pull/16980))
- Refactor: remove `flush_memories` entirely ([#15696](https://github.com/NousResearch/hermes-agent/pull/15696))
### Auxiliary models
- Fix: surface auxiliary failures in UI (previously silent) ([#15324](https://github.com/NousResearch/hermes-agent/pull/15324))
- Fix: surface title-gen auxiliary failures instead of silently dropping ([#16371](https://github.com/NousResearch/hermes-agent/pull/16371))
- Fix: generalize unsupported-parameter detector and harden `max_tokens` retry ([#15633](https://github.com/NousResearch/hermes-agent/pull/15633))
---
## 📱 Messaging Platforms (Gateway)
### New Platforms
- **Microsoft Teams (19th platform)** — as a plugin, + xdist collision guard ([#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
- **Yuanbao (Tencent 元宝, 18th platform)** — native adapter with text + media delivery ([#16298](https://github.com/NousResearch/hermes-agent/pull/16298), [#17424](https://github.com/NousResearch/hermes-agent/pull/17424), [#16880](https://github.com/NousResearch/hermes-agent/pull/16880))
### Pluggable Gateway Platforms
- **Drop-in messaging adapters** — the gateway is now a plugin host for platforms (salvage of #17664) ([#17751](https://github.com/NousResearch/hermes-agent/pull/17751))
### Telegram
- **Chat allowlists for groups and forums** (@web3blind) ([#15027](https://github.com/NousResearch/hermes-agent/pull/15027))
- **Send fresh finals for stale preview streams** (port openclaw#72038) ([#16261](https://github.com/NousResearch/hermes-agent/pull/16261))
- **Render markdown tables as row-group bullets + prompt hint** ([#16997](https://github.com/NousResearch/hermes-agent/pull/16997))
- Document fallback in centralized audio routing ([#17833](https://github.com/NousResearch/hermes-agent/pull/17833))
- Native multi-image sending ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
### Discord
- **Opt-in toolsets + ID injection + tool split + Feishu wiring** (salvage #15457, #15458) ([#15610](https://github.com/NousResearch/hermes-agent/pull/15610), [#15613](https://github.com/NousResearch/hermes-agent/pull/15613))
- Fix: coerce `limit` parameter to int before `min()` call ([#16319](https://github.com/NousResearch/hermes-agent/pull/16319))
### Slack
- **Register every gateway command as a native slash (Discord/Telegram parity)** ([#16164](https://github.com/NousResearch/hermes-agent/pull/16164))
- **`strict_mention` config** — prevents thread auto-engagement ([#16193](https://github.com/NousResearch/hermes-agent/pull/16193))
- **`channel_skill_bindings`** — bind specific skills to specific Slack channels ([#16283](https://github.com/NousResearch/hermes-agent/pull/16283))
### Signal
- **Native formatting** — markdown → bodyRanges, reply quotes, reactions ([#17417](https://github.com/NousResearch/hermes-agent/pull/17417))
- Native multi-image sending ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
### Feishu / Mattermost / Email / Signal
- All participate in **native multi-image sending** ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
### Gateway Core
- **Centralized audio routing + FLAC support + Telegram doc fallback** ([#17833](https://github.com/NousResearch/hermes-agent/pull/17833))
- **Native multi-image sending** across Telegram, Discord, Slack, Mattermost, Email, Signal ([#17909](https://github.com/NousResearch/hermes-agent/pull/17909))
- **Make hygiene hard message limit configurable** ([#17000](https://github.com/NousResearch/hermes-agent/pull/17000))
- **Opt-in runtime-metadata footer on final replies** ([#17026](https://github.com/NousResearch/hermes-agent/pull/17026))
- **`pre_gateway_dispatch` hook** — plugins can intercept before dispatch ([#15050](https://github.com/NousResearch/hermes-agent/pull/15050))
- **`pre_approval_request` / `post_approval_response` hooks** ([#16776](https://github.com/NousResearch/hermes-agent/pull/16776))
- Fix: timeouts — guard `load_config()` call against runtime exceptions ([#16318](https://github.com/NousResearch/hermes-agent/pull/16318))
- Fix: support passing handler tools via registry ([#15613](https://github.com/NousResearch/hermes-agent/pull/15613))
---
## 🔧 Tool System
### Plugin-first architecture
- **Pluggable gateway platforms** — platforms can ship as plugins ([#17751](https://github.com/NousResearch/hermes-agent/pull/17751))
- **Microsoft Teams as first plugin-shipped platform** ([#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
- **`pre_gateway_dispatch` hook** ([#15050](https://github.com/NousResearch/hermes-agent/pull/15050))
- **`pre_approval_request` + `post_approval_response` hooks** ([#16776](https://github.com/NousResearch/hermes-agent/pull/16776))
- **`duration_ms` on `post_tool_call`** (inspired by Claude Code 2.1.119) ([#15429](https://github.com/NousResearch/hermes-agent/pull/15429))
- **Bundled plugins**: Spotify ([#15174](https://github.com/NousResearch/hermes-agent/pull/15174)), Google Meet ([#16364](https://github.com/NousResearch/hermes-agent/pull/16364)), Langfuse observability ([#16917](https://github.com/NousResearch/hermes-agent/pull/16917)), hermes-achievements ([#17754](https://github.com/NousResearch/hermes-agent/pull/17754))
- **Page-scoped plugin slots for built-in dashboard pages** ([#15658](https://github.com/NousResearch/hermes-agent/pull/15658))
- **Declarative plugin installation for NixOS module** (@alt-glitch) ([#15953](https://github.com/NousResearch/hermes-agent/pull/15953))
### Browser
- **CDP supervisor** — dialog detection + response + cross-origin iframe eval ([#14540](https://github.com/NousResearch/hermes-agent/pull/14540))
- **Auto-spawn local Chromium for LAN/localhost URLs** when cloud provider is configured ([#16136](https://github.com/NousResearch/hermes-agent/pull/16136))
### Execute code / Terminal
- **Vercel Sandbox backend** for `execute_code` / terminal (@kshitijk4poor) ([#17445](https://github.com/NousResearch/hermes-agent/pull/17445))
- **Collapse subagent `task_id`s to shared container** ([#16177](https://github.com/NousResearch/hermes-agent/pull/16177))
- **Docker: run container as host user** to avoid root-owned bind mounts (@benbarclay) ([#17305](https://github.com/NousResearch/hermes-agent/pull/17305))
- Fix: safely quote `~/` subpaths in wrapped `cd` commands ([#15394](https://github.com/NousResearch/hermes-agent/pull/15394))
- Fix: close file descriptor in `LocalEnvironment._update_cwd` ([#17300](https://github.com/NousResearch/hermes-agent/pull/17300))
- Fix: SSH — prevent tar from overwriting remote home dir permissions ([#17898](https://github.com/NousResearch/hermes-agent/pull/17898), [#17867](https://github.com/NousResearch/hermes-agent/pull/17867))
### Image generation
- See Provider section for updates; no new image providers this window.
### TTS / Voice
- **Pluggable TTS provider registry** under `tts.providers.<name>` ([#17843](https://github.com/NousResearch/hermes-agent/pull/17843))
- **Piper** as native local TTS provider (closes #8508) ([#17885](https://github.com/NousResearch/hermes-agent/pull/17885))
- **Voice mode CLI parity in the TUI** — VAD loop + TTS + crash forensics ([#14810](https://github.com/NousResearch/hermes-agent/pull/14810))
- Fix: vision — use HERMES_HOME-based cache dir instead of cwd ([#17719](https://github.com/NousResearch/hermes-agent/pull/17719))
### Cron
- **Honor `hermes tools` config for the cron platform** ([#14798](https://github.com/NousResearch/hermes-agent/pull/14798))
- **Per-job `workdir`** — project-aware cron runs ([#15110](https://github.com/NousResearch/hermes-agent/pull/15110))
- **`context_from` field** — chain cron job outputs ([#15606](https://github.com/NousResearch/hermes-agent/pull/15606))
- Fix: promote `croniter` to a core dependency ([#17577](https://github.com/NousResearch/hermes-agent/pull/17577))
### Web search
- **Expose `limit` for `web_search`** ([#16934](https://github.com/NousResearch/hermes-agent/pull/16934))
### Maps
- Fix: include seconds in timezone UTC offset output ([#16300](https://github.com/NousResearch/hermes-agent/pull/16300))
### Approvals
- **Hardline blocklist for unrecoverable commands** ([#15878](https://github.com/NousResearch/hermes-agent/pull/15878))
- Perf: precompile DANGEROUS_PATTERNS and HARDLINE_PATTERNS ([#17206](https://github.com/NousResearch/hermes-agent/pull/17206))
### ACP
- **Advertise and forward image prompts** ([#18030](https://github.com/NousResearch/hermes-agent/pull/18030))
### API Server
- **POST `/v1/runs/{run_id}/stop`** (salvage of #15656) ([#15842](https://github.com/NousResearch/hermes-agent/pull/15842))
- **Expose run status for external UIs** (#17085) ([#17458](https://github.com/NousResearch/hermes-agent/pull/17458))
### Nix
- **Declarative plugin installation for NixOS module** (@alt-glitch) ([#15953](https://github.com/NousResearch/hermes-agent/pull/15953))
- Fix: use `--rebuild` in fix-lockfiles to bypass cached FOD store paths ([#15444](https://github.com/NousResearch/hermes-agent/pull/15444))
- Fix: `extraPackages` now actually works via per-user profile ([#17047](https://github.com/NousResearch/hermes-agent/pull/17047))
- Fix: refresh web/ npm-deps hash to unblock main builds ([#17174](https://github.com/NousResearch/hermes-agent/pull/17174))
- Fix: replace magic-nix-cache with Cachix ([#17928](https://github.com/NousResearch/hermes-agent/pull/17928))
---
## 🖥️ TUI
### New features
- **LaTeX rendering** (@austinpickett) ([#17175](https://github.com/NousResearch/hermes-agent/pull/17175))
- **`/reload` .env hot-reload** — ported from the classic CLI ([#17286](https://github.com/NousResearch/hermes-agent/pull/17286))
- **Pluggable busy-indicator styles** (@OutThisLife, #13610) ([#17150](https://github.com/NousResearch/hermes-agent/pull/17150))
- **Opt-in auto-resume of the most recent session** (@OutThisLife) ([#17130](https://github.com/NousResearch/hermes-agent/pull/17130))
- **Expanded light-terminal auto-detection** — `HERMES_TUI_THEME` + background hex (@OutThisLife) ([#17113](https://github.com/NousResearch/hermes-agent/pull/17113))
- **Delete sessions from `/resume` picker with `d`** (@OutThisLife) ([#17668](https://github.com/NousResearch/hermes-agent/pull/17668))
- **Line-by-line scroll on modified mouse wheel** (@OutThisLife) ([#17669](https://github.com/NousResearch/hermes-agent/pull/17669))
- **Delete queued message while editing with ctrl-x / cancel with esc** (@OutThisLife) ([#16707](https://github.com/NousResearch/hermes-agent/pull/16707))
- **Per-section visibility for the details accordion** (@OutThisLife) ([#14968](https://github.com/NousResearch/hermes-agent/pull/14968))
- **Voice mode CLI parity** — VAD loop + TTS + crash forensics ([#14810](https://github.com/NousResearch/hermes-agent/pull/14810))
- **Contextual first-touch hints ported to TUI** — `/busy`, `/verbose` ([#16054](https://github.com/NousResearch/hermes-agent/pull/16054))
- **Mini help menu on `?` in the input field** (@ethernet8023) ([#18043](https://github.com/NousResearch/hermes-agent/pull/18043))
### Fixes
- Fix: proactive mouse disable on ConPTY + `/mouse` toggle command (@kevin-ho, WSL2 ghost-mouse fix) ([#15488](https://github.com/NousResearch/hermes-agent/pull/15488))
- Fix: restore skills search RPC ([#15870](https://github.com/NousResearch/hermes-agent/pull/15870))
- Perf: cache text measurements across yoga flex re-passes ([#14818](https://github.com/NousResearch/hermes-agent/pull/14818))
- Perf: stabilize long-session scrolling ([#15926](https://github.com/NousResearch/hermes-agent/pull/15926))
- Perf: lazily seed virtual history heights ([#16523](https://github.com/NousResearch/hermes-agent/pull/16523))
- Perf: cut visible cold start ~57% with lazy agent init ([#17190](https://github.com/NousResearch/hermes-agent/pull/17190))
---
## 🖱️ CLI & User Experience
### New commands
- **`hermes -z <prompt>`** — non-interactive one-shot mode ([#15702](https://github.com/NousResearch/hermes-agent/pull/15702))
- **`hermes -z` with `--model` / `--provider` / `HERMES_INFERENCE_MODEL`** ([#15704](https://github.com/NousResearch/hermes-agent/pull/15704))
- **`hermes update --check`** preflight flag ([#15841](https://github.com/NousResearch/hermes-agent/pull/15841))
- **`hermes fallback`** command for managing fallback providers ([#16052](https://github.com/NousResearch/hermes-agent/pull/16052))
- **`/busy`** slash command for busy input mode ([#15382](https://github.com/NousResearch/hermes-agent/pull/15382))
- **`/busy` input mode 'steer'** as a third option ([#16279](https://github.com/NousResearch/hermes-agent/pull/16279))
- **`/btw` as alias for `/background`** ([#16053](https://github.com/NousResearch/hermes-agent/pull/16053))
- **`/reload-skills`** slash command (salvage #17670) ([#17744](https://github.com/NousResearch/hermes-agent/pull/17744))
- **Surface `/queue`, `/bg`, `/steer` in agent-running placeholder** ([#16118](https://github.com/NousResearch/hermes-agent/pull/16118))
### Setup / onboarding
- **Auto-reconfigure on existing installs** ([#15879](https://github.com/NousResearch/hermes-agent/pull/15879))
- **Contextual first-touch hints for `/busy` and `/verbose`** ([#16046](https://github.com/NousResearch/hermes-agent/pull/16046))
- **Cost-saving tips from the April 30 tip-of-the-day** ([#17841](https://github.com/NousResearch/hermes-agent/pull/17841))
- **Hyperlink startup banner title to the latest GitHub Release** ([#14945](https://github.com/NousResearch/hermes-agent/pull/14945))
### Update / backup
- **Snapshot pairing data before `git pull`** ([#16383](https://github.com/NousResearch/hermes-agent/pull/16383))
- **Auto-backup HERMES_HOME before `hermes update`** (opt-in, off by default) ([#16539](https://github.com/NousResearch/hermes-agent/pull/16539), [#16566](https://github.com/NousResearch/hermes-agent/pull/16566))
- **Exclude `checkpoints/` from backups** ([#16572](https://github.com/NousResearch/hermes-agent/pull/16572))
- **Exclude SQLite WAL/SHM/journal sidecars from backups** ([#16576](https://github.com/NousResearch/hermes-agent/pull/16576))
- **Installer FHS layout for root installs on Linux** ([#15608](https://github.com/NousResearch/hermes-agent/pull/15608))
- Fix: kill stale dashboards instead of warning ([#17832](https://github.com/NousResearch/hermes-agent/pull/17832))
- Fix: show correct update status on nix-built hermes ([#17550](https://github.com/NousResearch/hermes-agent/pull/17550))
### Slash-command housekeeping
- Refactor: drop `/provider`, `/plan` handler, and clean up slash registry ([#15047](https://github.com/NousResearch/hermes-agent/pull/15047))
- Refactor: drop `persist_session` plumbing + fix broken `/btw` mid-turn bypass ([#16075](https://github.com/NousResearch/hermes-agent/pull/16075))
### OpenClaw migration (for folks coming from OpenClaw)
- **Hardened OpenClaw import** — plan-first apply, redaction, pre-migration backup ([#16911](https://github.com/NousResearch/hermes-agent/pull/16911))
- Fix: case-preserving brand rewrite + one-time `~/.openclaw` residue banner ([#16327](https://github.com/NousResearch/hermes-agent/pull/16327))
- Fix: resolve `openclaw` workspace files from `agents.defaults.workspace` ([#16879](https://github.com/NousResearch/hermes-agent/pull/16879))
- Fix: resolve model aliases against real OpenClaw catalog schema (salvage #16778) ([#16977](https://github.com/NousResearch/hermes-agent/pull/16977))
---
## 📊 Web Dashboard
- **Models tab** — rich per-model analytics ([#17745](https://github.com/NousResearch/hermes-agent/pull/17745))
- **Configure main + auxiliary models from the Models page** ([#17802](https://github.com/NousResearch/hermes-agent/pull/17802))
- **Dashboard Chat tab — xterm.js + JSON-RPC sidecar** (supersedes #12710 + #13379, @OutThisLife) ([#14890](https://github.com/NousResearch/hermes-agent/pull/14890))
- **Dashboard layout refresh** (@austinpickett) ([#14899](https://github.com/NousResearch/hermes-agent/pull/14899))
- **`--stop` and `--status` flags** on the dashboard CLI ([#17840](https://github.com/NousResearch/hermes-agent/pull/17840))
- **Page-scoped plugin slots for built-in pages** ([#15658](https://github.com/NousResearch/hermes-agent/pull/15658))
- Fix: replace all buttons for design system buttons ([#17007](https://github.com/NousResearch/hermes-agent/pull/17007))
---
## ⚡ Performance
- **TUI visible cold start cut ~57%** via lazy agent init ([#17190](https://github.com/NousResearch/hermes-agent/pull/17190))
- **Lazy-import OpenAI, Anthropic, Firecrawl, account_usage** ([#17046](https://github.com/NousResearch/hermes-agent/pull/17046))
- **mtime-cache `load_config()` and `read_raw_config()`** ([#17041](https://github.com/NousResearch/hermes-agent/pull/17041))
- **Memoize `get_tool_definitions()` + TTL-cache `check_fn` results** ([#17098](https://github.com/NousResearch/hermes-agent/pull/17098))
- **Precompile DANGEROUS_PATTERNS and HARDLINE_PATTERNS** ([#17206](https://github.com/NousResearch/hermes-agent/pull/17206))
- **Cache Ink text measurements across yoga flex re-passes** ([#14818](https://github.com/NousResearch/hermes-agent/pull/14818))
- **Stabilize long-session scrolling** ([#15926](https://github.com/NousResearch/hermes-agent/pull/15926))
- **Lazily seed virtual history heights** ([#16523](https://github.com/NousResearch/hermes-agent/pull/16523))
---
## 🔒 Security & Reliability
- **Secret redaction off by default** — stops corrupting patches / API payloads with fake-key substitutions. Opt in via `redaction.enabled: true` ([#16794](https://github.com/NousResearch/hermes-agent/pull/16794))
- **`[SYSTEM:``[IMPORTANT:`** in all user-injected markers (Azure content filter dodge) ([#16114](https://github.com/NousResearch/hermes-agent/pull/16114))
- **Hardline blocklist for unrecoverable commands** ([#15878](https://github.com/NousResearch/hermes-agent/pull/15878))
- **Canonical `mask_secret` helper; fix status.py DIM drift** ([#17207](https://github.com/NousResearch/hermes-agent/pull/17207))
- **Sweep expired paste.rs uploads on a real timer** ([#16431](https://github.com/NousResearch/hermes-agent/pull/16431))
- **Preserve symlinks during atomic file writes** ([#16980](https://github.com/NousResearch/hermes-agent/pull/16980))
- **Probe `/dev/tty` by opening it, not bare existence** ([#17024](https://github.com/NousResearch/hermes-agent/pull/17024))
---
## 🐛 Notable Bug Fixes
This window includes 360 `fix:` PRs. Selected highlights from across the stack:
- **Background review fork inherits parent's live runtime** — provider/model/creds now propagate correctly ([#16099](https://github.com/NousResearch/hermes-agent/pull/16099))
- **Hindsight configurable `HINDSIGHT_TIMEOUT` env var** ([#15077](https://github.com/NousResearch/hermes-agent/pull/15077))
- **Tools: normalize numeric entries + clear stale `no_mcp` in `_save_platform_tools`** ([#15607](https://github.com/NousResearch/hermes-agent/pull/15607))
- **MCP: rewrite `definitions` refs to `$defs` in input schemas** — closes provider-side 400s
- **Azure content filter compatibility** — renamed `[SYSTEM:` markers so Azure's content filter stops flagging them ([#16114](https://github.com/NousResearch/hermes-agent/pull/16114))
- **Vision cache uses HERMES_HOME instead of cwd** ([#17719](https://github.com/NousResearch/hermes-agent/pull/17719))
- **FTS5 search** — tool_name + tool_calls indexing with repair + migration ([#16914](https://github.com/NousResearch/hermes-agent/pull/16914))
- **Streaming reasoning persists on assistant turns** ([#16892](https://github.com/NousResearch/hermes-agent/pull/16892))
- **execute_code concurrent RPC serialization** (#17770) ([#17894](https://github.com/NousResearch/hermes-agent/pull/17894), [#17902](https://github.com/NousResearch/hermes-agent/pull/17902))
- **Background reviewer scoped to memory + skills toolsets** — no more accidental web/shell escapes ([#16569](https://github.com/NousResearch/hermes-agent/pull/16569))
- **Compression recovery** — retry on main before giving up; notify user when aux fails ([#16774](https://github.com/NousResearch/hermes-agent/pull/16774), [#16775](https://github.com/NousResearch/hermes-agent/pull/16775))
- **`croniter` promoted to a core dependency** ([#17577](https://github.com/NousResearch/hermes-agent/pull/17577))
- **Discord tool `limit` parameter coerced to int** before `min()` call ([#16319](https://github.com/NousResearch/hermes-agent/pull/16319))
- **Yuanbao messaging platform entrance fix** ([#16880](https://github.com/NousResearch/hermes-agent/pull/16880))
- **ACP advertise and forward image prompts** ([#18030](https://github.com/NousResearch/hermes-agent/pull/18030))
- **DeepSeek / Kimi reasoning content isolation** across cross-provider histories (@Zjianru) ([#15749](https://github.com/NousResearch/hermes-agent/pull/15749), [#15762](https://github.com/NousResearch/hermes-agent/pull/15762))
- **Preserve reasoning_content replay on DeepSeek v4 + Kimi/Moonshot thinking** ([#18045](https://github.com/NousResearch/hermes-agent/pull/18045))
The vast majority of the 360 fixes landed in the streaming/compression/tool-calling paths across all providers — DeepSeek, Kimi, Moonshot, GLM, Qwen, MiniMax, Gemini, Anthropic, OpenAI — alongside TUI polish (resize, scroll, sticky-prompt) and gateway platform-specific edge cases.
---
## 🧪 Testing & CI
- Hermetic test parity (`scripts/run_tests.sh`) held across this window
- **Microsoft Teams xdist collision guard** — prevents worker collisions when Teams platform tests run in parallel ([#17828](https://github.com/NousResearch/hermes-agent/pull/17828))
- Chore: remove unused imports and dead locals (ruff F401, F841) ([#17010](https://github.com/NousResearch/hermes-agent/pull/17010))
---
## 📚 Documentation
- **Curator feature page** added to docs site ([#17563](https://github.com/NousResearch/hermes-agent/pull/17563))
- **Document pin also blocking `skill_manage` writes** ([#17578](https://github.com/NousResearch/hermes-agent/pull/17578))
- **Direct-URL skill install documented** across features, reference, guide, and `hermes-agent` skill ([#16355](https://github.com/NousResearch/hermes-agent/pull/16355))
- **Hooks tutorial — build a BOOT.md startup checklist** (replaces the removed built-in hook) ([#17202](https://github.com/NousResearch/hermes-agent/pull/17202))
- **ComfyUI docs: ask local vs cloud FIRST before hardware check** ([#17612](https://github.com/NousResearch/hermes-agent/pull/17612))
- **Obliteratus skill: link YouTube video guide in SKILL.md** ([#15808](https://github.com/NousResearch/hermes-agent/pull/15808))
- Per-skill docs pages generated for bundled + optional skills; ASCII art code blocks auto-wrapped ([#14929](https://github.com/NousResearch/hermes-agent/pull/14929), [#16497](https://github.com/NousResearch/hermes-agent/pull/16497))
---
## ⚖️ Removed / Reverted
- **Kanban multi-profile collaboration board** — landed in #16081, reverted in ([#16098](https://github.com/NousResearch/hermes-agent/pull/16098)) while the design is reworked
- **computer-use cua-driver** — 3 preparatory PRs landed then were reverted in ([#16927](https://github.com/NousResearch/hermes-agent/pull/16927))
- **BOOT.md built-in hook** removed ([#17093](https://github.com/NousResearch/hermes-agent/pull/17093)); the hooks tutorial ([#17202](https://github.com/NousResearch/hermes-agent/pull/17202)) shows how to build the same workflow yourself with a shell hook
- **`/provider` + `/plan` slash commands dropped** ([#15047](https://github.com/NousResearch/hermes-agent/pull/15047))
- **`flush_memories` removed entirely** ([#15696](https://github.com/NousResearch/hermes-agent/pull/15696))
---
## 👥 Contributors
### Core
- **@teknium1** (Teknium)
### Top Community Contributors (by merged PR count since v0.11.0)
- **@OutThisLife** (Brooklyn) — 52 PRs · TUI — light-terminal detection + pluggable busy styles + auto-resume + session-delete from /resume + mouse-wheel scrolling + xterm.js dashboard Chat tab + cold-start cut + accordion polish
- **@kshitijk4poor** — 12 PRs · LM Studio first-class provider (salvage), Vercel Sandbox backend, GMI Cloud salvage, bundled-by-default touchdesigner-mcp, many tool-call / reasoning fixes
- **@helix4u** — 10 PRs · MCP schema robustness, assorted stability fixes
- **@alt-glitch** — 8 PRs · trigram FTS5 CJK search, declarative Nix plugin install, matrix/feishu hints and fixes
- **@ethernet8023** — 4 PRs
- **@austinpickett** — 4 PRs · LaTeX rendering in TUI, dashboard layout refresh
- **@benbarclay** — 3 PRs · Docker run-as-host-user so bind mounts don't get root-owned
- **@vominh1919** — 2 PRs
- **@stephenschoettler** — 2 PRs
- **@kevin-ho** — ConPTY mouse-injection fix (#15488)
- **@Zjianru** — cross-provider reasoning_content isolation + DeepSeek/Kimi empty-reasoning injection (#15749, #15762)
- **@web3blind** — Telegram chat allowlists for groups and forums (#15027)
- **@SHL0MS** — 9 new TouchDesigner-MCP reference docs (#16768)
- **@0xDevNinja** — curator `restore_skill` nested-archive fix (#17951)
- **@y0shua1ee** — curator `use` activity fix (#17953)
### Also contributing
Salvaged or co-authored work from **@isaachuangGMICLOUD** (GMI Cloud), earlier upstream PRs from the original author of each salvage chain, and a long tail of one-shot fixes, documentation nudges, and skill contributions from the community.
### All Contributors (alphabetical, excluding @teknium1)
@0xbyt4, @0xharryriddle, @0xDevNinja, @0z1-ghb, @5park1e, @A-FdL-Prog, @aj-nt, @akhater, @alblez, @alexg0bot,
@alexzhu0, @AllardQuek, @alt-glitch, @amanning3390, @amanuel2, @AndreKurait, @andrewhosf, @Andy283, @andyylin,
@angel12, @AntAISecurityLab, @ash, @austinpickett, @badgerbees, @BadTechBandit, @Bartok9, @beenherebefore,
@beesrsj2500, @BeliefanX, @benbarclay, @benjaminsehl, @BlackishGreen33, @bloodcarter, @BlueBirdBack,
@briandevans, @brooklynnicholson, @bsgdigital, @buray, @bwjoke, @camaragon, @cdanis, @cgarwood82,
@charles-brooks, @chen1749144759, @chengoak, @ching-kaching, @Contentment003111, @crayfish-ai, @CruxExperts,
@cyclingwithelephants, @dandaka, @danklynn, @ddupont808, @dhabibi, @difujia, @dimitrovi, @dlkakbs,
@dontcallmejames, @EKKOLearnAI, @emozilla, @ericnicolaides, @Erosika, @ethernet8023, @exiao, @Feranmi10,
@flobo3, @foxion37, @georgeglessner, @georgex8001, @ghostmfr, @H-Ali13381, @HangGlidersRule, @harryplusplus,
@haru398801, @heathley, @hejuntt1014, @hekaru-agent, @helix4u, @Heltman, @HenkDz, @heyitsaamir, @hharry11,
@hhhonzik, @hhuang91, @HiddenPuppy, @htsh, @iamagenius00, @in-liberty420, @innocarpe, @irispillars, @iRonin,
@isaachuangGMICLOUD, @Ito-69, @j3ffffff, @jackjin1997, @jakubkrcmar, @Jason2031, @JayGwod, @jerome-benoit,
@johnncenae, @Kailigithub, @keiravoss94, @kevin-ho, @knockyai, @konsisumer, @kshitijk4poor, @kunlabs, @l0hde,
@Leihb, @leoneparise, @LeonSGP43, @liizfq, @liuhao1024, @loongzhao, @lsdsjy, @luyao618, @ma-pony, @Magaav,
@MagicRay1217, @math0r-be, @MattMaximo, @maxims-oss, @MaxyMoos, @maymuneth, @mcndjxlefnd, @memosr,
@MestreY0d4-Uninter, @mewwts, @Mirac1eSky, @MorAlekss, @mrhwick, @mrunmayee17, @mssteuer, @Nanako0129,
@nazirulhafiy, @Nerijusas, @Nicecsh, @nicoloboschi, @nightq, @ningfangbin, @octo-patch, @Octopus,
@OutThisLife, @Paperclip, @pein892, @perlowja, @prasadus92, @qike-ms, @qiyin-code, @Readon, @ReginaldasR,
@revaraver, @rfilgueiras, @rmoen, @romanornr, @rugvedS07, @rylena, @samrusani, @Sanjays2402, @sasha-id,
@Satoshi-agi, @scheidti, @scotttrinh, @season179, @SeeYangZhi, @sgaofen, @shamork, @shannonsands, @SHL0MS,
@simbam99, @Societus, @socrates1024, @Sonoyunchu, @sprmn24, @stephenschoettler, @tangyuanjc, @TechPrototyper,
@tekgnosis-net, @ThomassJonax, @tmimmanuel, @tochukwuada, @Tosko4, @Tranquil-Flow, @twozle, @txbxxx,
@UgwujaGeorge, @Versun, @vlwkaos, @voidborne-d, @vominh1919, @Wang-tianhao, @Wangshengyang2004, @web3blind,
@westers, @Wysie, @xandersbell, @xiahu88988, @XieNBi, @xinbenlv, @xnbi, @y0shua1ee, @yatesjalex, @yes999zc,
@yeyitech, @Yoimex, @YueLich, @Yukipukii1, @zhiyanliu, @zicochaos, @Zjianru, @zkl2333, @zons-zhaozhy,
@ztexydt-cqh.
Also: @Siddharth Balyan, @YuShu.
---
**Full Changelog**: [v2026.4.23...v2026.4.30](https://github.com/NousResearch/hermes-agent/compare/v2026.4.23...v2026.4.30)

View File

@@ -1,641 +0,0 @@
# Hermes Agent v0.13.0 (v2026.5.7)
**Release Date:** May 7, 2026
**Since v0.12.0:** 864 commits · 588 merged PRs · 829 files changed · 128,366 insertions · 282 issues closed (13 P0, 36 P1) · 295 community contributors (including co-authors)
> The Tenacity Release — Hermes Agent now finishes what it starts. Kanban ships as a durable multi-agent board (heartbeat, reclaim, zombie detection, auto-block on incomplete exit, per-task retries, hallucination recovery). `/goal` keeps the agent locked on a target across turns (Ralph loop). Checkpoints v2 rewrites state persistence with real pruning. Gateway auto-resumes interrupted sessions after restart. Cron grows a `no_agent` watchdog mode. A security wave closes 8 P0s — redaction is now ON by default, Discord role-allowlists are guild-scoped, WhatsApp rejects strangers by default, and TOCTOU windows close across auth.json and MCP OAuth. Google Chat becomes the 20th platform. Providers become a pluggable surface. Seven i18n locales ship.
---
## ✨ Highlights
- **Multi-agent Kanban — delegate to an AI team that actually finishes** — Spin up a durable board, drop tasks on it, and let multiple Hermes workers pick them up, hand off, and close them out. Heartbeats, reclaim, zombie detection, retry budgets, and a hallucination gate keep the team honest. One install, many kanbans. ([#17805](https://github.com/NousResearch/hermes-agent/pull/17805), [#19653](https://github.com/NousResearch/hermes-agent/pull/19653), [#20232](https://github.com/NousResearch/hermes-agent/pull/20232), [#20332](https://github.com/NousResearch/hermes-agent/pull/20332), [#21330](https://github.com/NousResearch/hermes-agent/pull/21330), [#21183](https://github.com/NousResearch/hermes-agent/pull/21183), [#21214](https://github.com/NousResearch/hermes-agent/pull/21214))
- **`/goal` — the agent doesn't forget what you asked it to do** — Lock the agent onto a target and it stays on task across turns. The Ralph loop as a first-class primitive. ([#18262](https://github.com/NousResearch/hermes-agent/pull/18262), [#18275](https://github.com/NousResearch/hermes-agent/pull/18275), [#21287](https://github.com/NousResearch/hermes-agent/pull/21287))
- **Show it a video** — new `video_analyze` tool for native video understanding on Gemini and compatible multimodal models. (@alt-glitch) ([#19301](https://github.com/NousResearch/hermes-agent/pull/19301))
- **Clone a voice** — xAI Custom Voices lands as a TTS provider with voice cloning support. (@alt-glitch) ([#18776](https://github.com/NousResearch/hermes-agent/pull/18776))
- **Hermes speaks your language** — static gateway + CLI messages translate to 7 locales: Chinese, Japanese, German, Spanish, French, Ukrainian, and Turkish. Docs site gains a Chinese (zh-Hans) locale. ([#20231](https://github.com/NousResearch/hermes-agent/pull/20231), [#20329](https://github.com/NousResearch/hermes-agent/pull/20329), [#20467](https://github.com/NousResearch/hermes-agent/pull/20467), [#20474](https://github.com/NousResearch/hermes-agent/pull/20474), [#20430](https://github.com/NousResearch/hermes-agent/pull/20430), [#20431](https://github.com/NousResearch/hermes-agent/pull/20431))
- **Google Chat — the 20th messaging platform** — plus a generic platform-plugin hooks surface so third-party adapters drop in without touching core (IRC and Teams migrated). ([#21306](https://github.com/NousResearch/hermes-agent/pull/21306), [#21331](https://github.com/NousResearch/hermes-agent/pull/21331))
- **Sessions survive restarts** — gateway bounces mid-agent, `/update` restarts, source-file reloads — conversations auto-resume when the gateway comes back. ([#21192](https://github.com/NousResearch/hermes-agent/pull/21192))
- **Security wave — 8 P0 closures** — redaction ON by default, Discord role-allowlists guild-scoped (CVSS 8.1 cross-guild DM bypass closed), WhatsApp rejects strangers by default, TOCTOU windows closed across `auth.json` and MCP OAuth, browser enforces cloud-metadata SSRF floor, cron prompt-injection scans assembled skill content, `hermes debug share` redacts at upload. ([#21193](https://github.com/NousResearch/hermes-agent/pull/21193), [#21241](https://github.com/NousResearch/hermes-agent/pull/21241), [#21291](https://github.com/NousResearch/hermes-agent/pull/21291), [#21176](https://github.com/NousResearch/hermes-agent/pull/21176), [#21194](https://github.com/NousResearch/hermes-agent/pull/21194), [#21228](https://github.com/NousResearch/hermes-agent/pull/21228), [#21350](https://github.com/NousResearch/hermes-agent/pull/21350), [#19318](https://github.com/NousResearch/hermes-agent/pull/19318))
- **Checkpoints v2** — state persistence rewritten. Real pruning, disk guardrails, no more orphan shadow repos. ([#20709](https://github.com/NousResearch/hermes-agent/pull/20709))
- **The agent lints its own writes** — post-write delta lint on `write_file` + `patch`. Python, JSON, YAML, TOML. Syntax errors surface immediately instead of shipping downstream. ([#20191](https://github.com/NousResearch/hermes-agent/pull/20191))
- **`no_agent` cron mode — script-only watchdog** — cron jobs can now skip the agent entirely and just run a script. Empty stdout is silent, non-empty gets delivered verbatim. ([#19709](https://github.com/NousResearch/hermes-agent/pull/19709))
- **Platform allowlists everywhere** — `allowed_channels` / `allowed_chats` / `allowed_rooms` config across Slack, Telegram, Mattermost, Matrix, and DingTalk. ([#21251](https://github.com/NousResearch/hermes-agent/pull/21251))
- **Providers are now plugins** — `ProviderProfile` ABC + `plugins/model-providers/`. Drop in third-party providers without touching core. ([#20324](https://github.com/NousResearch/hermes-agent/pull/20324))
- **API server — long-term memory per session** — `X-Hermes-Session-Key` header gives memory providers a stable session identifier. ([#20199](https://github.com/NousResearch/hermes-agent/pull/20199))
- **MCP levels up** — SSE transport with OAuth forwarding, stale-pipe retries, image results surface as MEDIA tags instead of getting dropped, keepalive on long-lived lifecycle waits. ([#21227](https://github.com/NousResearch/hermes-agent/pull/21227), [#21323](https://github.com/NousResearch/hermes-agent/pull/21323), [#21289](https://github.com/NousResearch/hermes-agent/pull/21289), [#21328](https://github.com/NousResearch/hermes-agent/pull/21328), [#20209](https://github.com/NousResearch/hermes-agent/pull/20209))
- **Curator grows subcommands** — `hermes curator archive`, `prune`, `list-archived`. Manual `hermes curator run` is synchronous now — you see results without polling. ([#20200](https://github.com/NousResearch/hermes-agent/pull/20200), [#21236](https://github.com/NousResearch/hermes-agent/pull/21236), [#21216](https://github.com/NousResearch/hermes-agent/pull/21216))
- **ACP — `/steer` and `/queue`** — direct the in-flight agent or queue follow-ups from Zed, VS Code, or JetBrains. Plus atomic session persistence and reasoning-metadata preservation across restarts. (@HenkDz) ([#18114](https://github.com/NousResearch/hermes-agent/pull/18114), [#20279](https://github.com/NousResearch/hermes-agent/pull/20279), [#20296](https://github.com/NousResearch/hermes-agent/pull/20296), [#20433](https://github.com/NousResearch/hermes-agent/pull/20433))
- **TUI glow-up** — `/model` picker matches `hermes model` with inline auth (@austinpickett), collapsible startup banner sections (@kshitijk4poor), context-compression counter in the status bar. ([#18117](https://github.com/NousResearch/hermes-agent/pull/18117), [#20625](https://github.com/NousResearch/hermes-agent/pull/20625), [#21218](https://github.com/NousResearch/hermes-agent/pull/21218))
- **Dashboard grows up** — Plugins page (manage, enable/disable, auth status) (@austinpickett), Profiles management page (@vincez-hms-coder), sortable analytics tables, reverse-proxy support via `X-Forwarded-Prefix`, new `default-large` 18px theme. ([#18095](https://github.com/NousResearch/hermes-agent/pull/18095), [#16419](https://github.com/NousResearch/hermes-agent/pull/16419), [#18192](https://github.com/NousResearch/hermes-agent/pull/18192), [#21296](https://github.com/NousResearch/hermes-agent/pull/21296), [#20820](https://github.com/NousResearch/hermes-agent/pull/20820))
- **SearXNG + split web tools** — SearXNG ships as a native search-only backend; web tools now let you pick different backends per capability (search vs extract vs browse). (@kshitijk4poor) ([#20823](https://github.com/NousResearch/hermes-agent/pull/20823), [#20061](https://github.com/NousResearch/hermes-agent/pull/20061), [#20841](https://github.com/NousResearch/hermes-agent/pull/20841))
- **OpenRouter response caching** — explicit cache control for models that expose it. (@kshitijk4poor) ([#19132](https://github.com/NousResearch/hermes-agent/pull/19132))
- **`[[as_document]]` — skill media-routing directive** — skills can force the gateway to deliver output as a document on platforms that support it. ([#21210](https://github.com/NousResearch/hermes-agent/pull/21210))
- **`transform_llm_output` plugin hook** — new lifecycle hook that lets plugins reshape or filter LLM output before it hits the conversation. Useful for context-window reducers and content filters. ([#21235](https://github.com/NousResearch/hermes-agent/pull/21235))
- **Nous OAuth persists across profiles** — shared token store: sign in once, every profile inherits the session. ([#19712](https://github.com/NousResearch/hermes-agent/pull/19712))
- **QQBot — native approval keyboards** — feature parity with Telegram / Discord approval UX. Chunked upload, quoted attachments. ([#21342](https://github.com/NousResearch/hermes-agent/pull/21342), [#21353](https://github.com/NousResearch/hermes-agent/pull/21353))
- **6 new optional skills** — Shopify (Admin + Storefront GraphQL), here.now, shop-app personal shopping assistant, Anthropic financial-services bundle, kanban-video-orchestrator (@SHL0MS), searxng-search (@kshitijk4poor). ([#18116](https://github.com/NousResearch/hermes-agent/pull/18116), [#18170](https://github.com/NousResearch/hermes-agent/pull/18170), [#20702](https://github.com/NousResearch/hermes-agent/pull/20702), [#21180](https://github.com/NousResearch/hermes-agent/pull/21180), [#19281](https://github.com/NousResearch/hermes-agent/pull/19281), [#20841](https://github.com/NousResearch/hermes-agent/pull/20841))
- **New models** — `deepseek/deepseek-v4-pro`, `x-ai/grok-4.3`, `openrouter/owl-alpha` (free), `tencent/hy3-preview` (@Contentment003111), Arcee Trinity Large Thinking temperature + compression overrides. ([#20495](https://github.com/NousResearch/hermes-agent/pull/20495), [#20497](https://github.com/NousResearch/hermes-agent/pull/20497), [#18071](https://github.com/NousResearch/hermes-agent/pull/18071), [#21077](https://github.com/NousResearch/hermes-agent/pull/21077), [#20473](https://github.com/NousResearch/hermes-agent/pull/20473))
- **100 fresh CLI startup tips** — the random tip banner gets 100 new entries covering cron, kanban, curator, plugins, and lesser-known flags. ([#20168](https://github.com/NousResearch/hermes-agent/pull/20168))
---
## 🧩 Multi-Agent Kanban (Durable)
### New — durable multi-profile collaboration board
- **`feat(kanban): durable multi-profile collaboration board`** — post-revert reimplementation, multi-profile by design ([#17805](https://github.com/NousResearch/hermes-agent/pull/17805))
- **Multi-project boards** — one install, many kanbans ([#19653](https://github.com/NousResearch/hermes-agent/pull/19653), [#19679](https://github.com/NousResearch/hermes-agent/pull/19679))
- **Share board, workspaces, and worker logs across profiles** ([#19378](https://github.com/NousResearch/hermes-agent/pull/19378))
- **Hallucination gate + recovery UX for worker-created-card claims** (closes #20017) ([#20232](https://github.com/NousResearch/hermes-agent/pull/20232))
- **Generic diagnostics engine for task distress signals** ([#20332](https://github.com/NousResearch/hermes-agent/pull/20332))
- **Per-task `max_retries` override** (supersedes #20972) ([#21330](https://github.com/NousResearch/hermes-agent/pull/21330))
- **Multiline textarea for inline-create title** (salvage of #20970) ([#21243](https://github.com/NousResearch/hermes-agent/pull/21243))
### Kanban Dashboard
- **Workspace kind + path inputs in inline create form** ([#19679](https://github.com/NousResearch/hermes-agent/pull/19679))
- **Per-platform home-channel notification toggles** ([#19864](https://github.com/NousResearch/hermes-agent/pull/19864))
- **Sharper home-channel toggle contrast + drop → running action** ([#19916](https://github.com/NousResearch/hermes-agent/pull/19916))
- Fix: reject direct status transition to 'running' via dashboard API (salvage of #19554) ([#19705](https://github.com/NousResearch/hermes-agent/pull/19705))
- Fix: dashboard board pin authoritative over server current file (#20879) ([#21230](https://github.com/NousResearch/hermes-agent/pull/21230))
- Fix: treat dashboard event-stream cancellation as normal shutdown (#20790) ([#21222](https://github.com/NousResearch/hermes-agent/pull/21222))
- Fix: filter dashboard board by selected tenant (#19817) ([#21349](https://github.com/NousResearch/hermes-agent/pull/21349))
- Fix: code/pre styling theme-immune across all themes (#21086) ([#21247](https://github.com/NousResearch/hermes-agent/pull/21247))
- Fix: reset `<code>` background inside dashboard board ([#20687](https://github.com/NousResearch/hermes-agent/pull/20687))
- Fix: preserve dashboard completion summaries + add kanban edit (salvages #20016) ([#20195](https://github.com/NousResearch/hermes-agent/pull/20195))
- Fix: avoid fragile failure-column renames (salvage #20848) (@kshitijk4poor) ([#20855](https://github.com/NousResearch/hermes-agent/pull/20855))
### Worker lifecycle + reliability
- **Heartbeat + reclaim + zombie + retry-cap fixes** (#21147, #21141, #21169, #20881) ([#21183](https://github.com/NousResearch/hermes-agent/pull/21183))
- **Auto-block workers that exit without completing + shutdown race** (#20894) ([#21214](https://github.com/NousResearch/hermes-agent/pull/21214))
- **Detect darwin zombie workers** (salvages #20023) ([#20188](https://github.com/NousResearch/hermes-agent/pull/20188))
- **Unify failure counter across spawn/timeout/crash outcomes** ([#20410](https://github.com/NousResearch/hermes-agent/pull/20410))
- **Enforce worker task-ownership on destructive tool calls** ([#19713](https://github.com/NousResearch/hermes-agent/pull/19713))
- **Drop worker identity claim from KANBAN_GUIDANCE** ([#19427](https://github.com/NousResearch/hermes-agent/pull/19427))
- Fix: skip dispatch for tasks assigned to non-profile lanes (salvages #20105, #20134) ([#20165](https://github.com/NousResearch/hermes-agent/pull/20165))
- Fix: include default profile in on-disk assignee enumeration (salvages #20123) ([#20170](https://github.com/NousResearch/hermes-agent/pull/20170))
- Fix: ignore stale current board pointers (salvages #20063) ([#20183](https://github.com/NousResearch/hermes-agent/pull/20183))
- Fix: profile discovery ignores HERMES_HOME in custom-root deployments (@jackey8616) ([#19020](https://github.com/NousResearch/hermes-agent/pull/19020))
- Fix: allow orchestrator profiles to see kanban tools via toolsets config ([#19606](https://github.com/NousResearch/hermes-agent/pull/19606))
### Batch salvages
- Tier-1 batch — metadata test, max_spawn config, run-id lifecycle guard (salvages #19522 #19556 #19829) ([#20440](https://github.com/NousResearch/hermes-agent/pull/20440))
- Tier-2 batch — doctor, started_at, parent-guard, latest_summary, selects, linked-children ([#20448](https://github.com/NousResearch/hermes-agent/pull/20448))
### Documentation
- Backfill multi-board refs in reference docs ([#19704](https://github.com/NousResearch/hermes-agent/pull/19704))
- Document `/kanban` slash command ([#19584](https://github.com/NousResearch/hermes-agent/pull/19584))
- Document recommended handoff evidence metadata (salvage #19512) ([#20415](https://github.com/NousResearch/hermes-agent/pull/20415))
- Fix orchestrator + worker skill setup instructions (@helix4u) ([#20958](https://github.com/NousResearch/hermes-agent/pull/20958), [#20960](https://github.com/NousResearch/hermes-agent/pull/20960))
---
## 🎯 Persistent Goals, Checkpoints & Session Durability
### `/goal` — persistent cross-turn goals (Ralph loop)
- **`feat: /goal — persistent cross-turn goals`** ([#18262](https://github.com/NousResearch/hermes-agent/pull/18262))
- **Docs page — Persistent Goals (/goal)** ([#18275](https://github.com/NousResearch/hermes-agent/pull/18275))
- Fix: honor configured goal turn budget (salvage #19423) ([#21287](https://github.com/NousResearch/hermes-agent/pull/21287))
### Checkpoints v2
- **Single-store rewrite with real pruning + disk guardrails** ([#20709](https://github.com/NousResearch/hermes-agent/pull/20709))
### Session durability
- **Auto-resume interrupted sessions after gateway restart** (salvage #20888) ([#21192](https://github.com/NousResearch/hermes-agent/pull/21192))
- **Preserve pending update prompts across restarts** ([#20160](https://github.com/NousResearch/hermes-agent/pull/20160))
- **Preserve home-channel thread targets across restart notifications** (salvage #18440) ([#19271](https://github.com/NousResearch/hermes-agent/pull/19271))
- **Preserve thread routing from cached live session sources** ([#21206](https://github.com/NousResearch/hermes-agent/pull/21206))
- **Preserve assistant metadata when branching sessions** ([#18222](https://github.com/NousResearch/hermes-agent/pull/18222))
- **Preserve thread routing for /update progress and prompts** ([#18193](https://github.com/NousResearch/hermes-agent/pull/18193))
- **Preserve document type when merging queued events** ([#18215](https://github.com/NousResearch/hermes-agent/pull/18215))
---
## 🛡️ Security & Reliability
### Security hardening (8 P0 closures)
- **Enable secret redaction by default** (#17691, #20785) ([#21193](https://github.com/NousResearch/hermes-agent/pull/21193))
- **Discord — scope `DISCORD_ALLOWED_ROLES` to originating guild** (#12136, CVSS 8.1) ([#21241](https://github.com/NousResearch/hermes-agent/pull/21241))
- **WhatsApp — reject strangers by default, never respond in self-chat** (#8389) ([#21291](https://github.com/NousResearch/hermes-agent/pull/21291))
- **MCP OAuth — close TOCTOU window when saving credentials** ([#21176](https://github.com/NousResearch/hermes-agent/pull/21176))
- **`hermes_cli/auth.py` — close TOCTOU window in credential writers** ([#21194](https://github.com/NousResearch/hermes-agent/pull/21194))
- **Browser — enforce cloud-metadata SSRF floor in hybrid routing** (#16234) ([#21228](https://github.com/NousResearch/hermes-agent/pull/21228))
- **`hermes debug share` — redact log content at upload time** (@GodsBoy) ([#19318](https://github.com/NousResearch/hermes-agent/pull/19318))
- **Cron — scan assembled prompt including skill content for prompt injection** (#3968) ([#21350](https://github.com/NousResearch/hermes-agent/pull/21350))
- **Restore .env/auth.json/state.db with 0600 perms** ([#19699](https://github.com/NousResearch/hermes-agent/pull/19699))
- **SRI integrity for dashboard plugin scripts** (salvage #19389) ([#21277](https://github.com/NousResearch/hermes-agent/pull/21277))
- **Bind Meet node server to localhost, restrict token file to owner read** ([#19597](https://github.com/NousResearch/hermes-agent/pull/19597))
- **Extend sensitive-write target to cover shell RC and credential files** ([#19282](https://github.com/NousResearch/hermes-agent/pull/19282))
- **Harden YOLO mode env parsing against quoted-bool strings** ([#18214](https://github.com/NousResearch/hermes-agent/pull/18214))
- **OSV-Scanner CI + Dependabot for github-actions only** ([#20037](https://github.com/NousResearch/hermes-agent/pull/20037))
### Reliability — critical bug closures
- **CLI crash on startup — `Invalid key 'c-S-c'`** (P0, prompt_toolkit doesn't support Shift modifier) ([#19895](https://github.com/NousResearch/hermes-agent/pull/19895), [#19919](https://github.com/NousResearch/hermes-agent/pull/19919))
- **CLOSE_WAIT fd leak audit** — httpx keepalive + WhatsApp aiohttp leak + Feishu hygiene (#18451) ([#18766](https://github.com/NousResearch/hermes-agent/pull/18766))
- **Gateway creates AIAgent with empty OpenRouter API key when OPENROUTER_API_KEY is missing** (#20982) — fallback providers correctly honored
- **Background review + curator protected from overwriting bundled/hub skills** (#20273) ([#20194](https://github.com/NousResearch/hermes-agent/pull/20194))
- **TUI compression continuation — ghost sessions with incomplete metadata** (#20001)
- **`hermes mcp add` silently launches chat instead of registering MCP server** (#19785) ([#21204](https://github.com/NousResearch/hermes-agent/pull/21204))
- **Background review agent runtime propagation** — provider/model/credentials now actually inherit from parent
- **Inbound document host paths translated to container paths for Docker backend** (salvage #19048) ([#21184](https://github.com/NousResearch/hermes-agent/pull/21184))
- **Matrix gateway race between auto-redaction and message delivery with high-speed models** (#19075)
- **`/new` during active agent session never sends response on Telegram** (#18912)
---
## 📱 Messaging Platforms (Gateway)
### New platform
- **Google Chat — 20th platform** + generic `env_enablement_fn` / `cron_deliver_env_var` platform-plugin hooks (IRC + Teams migrated) ([#21306](https://github.com/NousResearch/hermes-agent/pull/21306), [#21331](https://github.com/NousResearch/hermes-agent/pull/21331))
### Cross-platform
- **`allowed_{channels,chats,rooms}` whitelist** — Slack (salvage #7401), Telegram, Mattermost, Matrix, DingTalk ([#21251](https://github.com/NousResearch/hermes-agent/pull/21251))
- **Per-platform `gateway_restart_notification` flag** ([#20892](https://github.com/NousResearch/hermes-agent/pull/20892))
- **`busy_ack_enabled` config — suppress ack messages** ([#18194](https://github.com/NousResearch/hermes-agent/pull/18194))
- **Auto-delete slash-command system notices after TTL** ([#18266](https://github.com/NousResearch/hermes-agent/pull/18266))
- **Opt-in cleanup of temporary progress bubbles** ([#21186](https://github.com/NousResearch/hermes-agent/pull/21186))
- **`[[as_document]]` directive — skill media routing** (salvage #19069) ([#21210](https://github.com/NousResearch/hermes-agent/pull/21210))
- **`hermes gateway list` — cross-profile status** (salvage #19129) ([#21225](https://github.com/NousResearch/hermes-agent/pull/21225))
- **Auto-resume interrupted sessions after restart** (salvage #20888) ([#21192](https://github.com/NousResearch/hermes-agent/pull/21192))
- **Atomic restart markers + Windows runtime-lock offset** (#17842) ([#18179](https://github.com/NousResearch/hermes-agent/pull/18179))
- Fix: `config.yaml` wins over `.env` for agent/display/timezone settings ([#18764](https://github.com/NousResearch/hermes-agent/pull/18764))
- Fix: auto-restart when source files change out from under us (#17648) ([#18409](https://github.com/NousResearch/hermes-agent/pull/18409))
- Fix: use git HEAD SHA for stale-code check, not file mtimes ([#19740](https://github.com/NousResearch/hermes-agent/pull/19740))
- Fix: shutdown + restart hygiene — drain timeout, false-fatal, success log ([#18761](https://github.com/NousResearch/hermes-agent/pull/18761))
- Fix: preserve max_turns after env reload (salvage #19183) ([#21240](https://github.com/NousResearch/hermes-agent/pull/21240))
- Fix: exclude ancestor PIDs from gateway process scan ([#19586](https://github.com/NousResearch/hermes-agent/pull/19586))
- Fix: move quick-command alias dispatch before built-ins ([#19588](https://github.com/NousResearch/hermes-agent/pull/19588))
- Fix: show other profiles in 'gateway status' to prevent confusion ([#19582](https://github.com/NousResearch/hermes-agent/pull/19582))
- Fix: include external_dirs skills in Telegram/Discord slash commands (salvage #8790) ([#18741](https://github.com/NousResearch/hermes-agent/pull/18741))
- Fix: match disabled/optional skills by frontmatter slug, not dir name ([#18753](https://github.com/NousResearch/hermes-agent/pull/18753))
- Fix: read /status token totals from SessionDB (#17158) ([#18206](https://github.com/NousResearch/hermes-agent/pull/18206))
- Fix: snapshot callback generation after agent binds it, not before ([#18219](https://github.com/NousResearch/hermes-agent/pull/18219))
- Fix: re-inject topic-bound skill after /new or /reset ([#18205](https://github.com/NousResearch/hermes-agent/pull/18205))
- Fix: isolate pending native image paths by session ([#18202](https://github.com/NousResearch/hermes-agent/pull/18202))
- Fix: clear queued reload skills notes on new/resume/branch ([#19431](https://github.com/NousResearch/hermes-agent/pull/19431))
- Fix: hide required-arg commands from Telegram menu ([#19400](https://github.com/NousResearch/hermes-agent/pull/19400))
- Fix: bridge top-level `require_mention` to Telegram config ([#19429](https://github.com/NousResearch/hermes-agent/pull/19429))
- Fix: suppress duplicate voice transcripts ([#19428](https://github.com/NousResearch/hermes-agent/pull/19428))
- Fix: show friendly error when service is not installed ([#19707](https://github.com/NousResearch/hermes-agent/pull/19707))
- Fix: read context_length from custom_providers in session info header ([#19708](https://github.com/NousResearch/hermes-agent/pull/19708))
- Fix: preserve WSL interop PATH in systemd units ([#19867](https://github.com/NousResearch/hermes-agent/pull/19867))
- Fix: handle planned service stops (salvage #19876) ([#19936](https://github.com/NousResearch/hermes-agent/pull/19936))
- Fix: keep DoH-confirmed Telegram IPs that match system DNS (salvage #17043) ([#20175](https://github.com/NousResearch/hermes-agent/pull/20175))
- Fix: load `reply_to_mode` from config.yaml for Discord + Telegram (salvage #17117) ([#20171](https://github.com/NousResearch/hermes-agent/pull/20171))
- Fix: tolerate malformed HERMES_HUMAN_DELAY_* env vars (salvage #16933) ([#20217](https://github.com/NousResearch/hermes-agent/pull/20217))
- Fix: deterministic thread eviction preserves newest entries (salvage #13639) ([#20285](https://github.com/NousResearch/hermes-agent/pull/20285))
- Fix: don't dead-end setup wizard when only system-scope unit is installed ([#20905](https://github.com/NousResearch/hermes-agent/pull/20905))
- Fix: wait for systemd restart readiness + harden Discord slash-command sync ([#20949](https://github.com/NousResearch/hermes-agent/pull/20949))
- Fix: avoid duplicated Responses history (salvage #18995) ([#21185](https://github.com/NousResearch/hermes-agent/pull/21185))
- Fix: surface bootstrap failures to stderr (salvage #21157) ([#21278](https://github.com/NousResearch/hermes-agent/pull/21278))
- Fix: log agent task failures instead of silently losing usage data (salvage #21159) ([#21274](https://github.com/NousResearch/hermes-agent/pull/21274))
- Fix: log runtime-status write failures with rate-limiting (salvage #21158) ([#21285](https://github.com/NousResearch/hermes-agent/pull/21285))
- Fix: reset-failed before every fallback restart so the gateway can't get stranded ([#21371](https://github.com/NousResearch/hermes-agent/pull/21371))
- Fix: Telegram — preserve `thread_id=1` for forum General typing indicator ([#21390](https://github.com/NousResearch/hermes-agent/pull/21390))
- Fix: batch critical fixes — session resume, /new race, HA WebSocket scheme (@kshitijk4poor) ([#19182](https://github.com/NousResearch/hermes-agent/pull/19182))
### Telegram
- **DM user-managed multi-session topics** (salvage of #19185) ([#19206](https://github.com/NousResearch/hermes-agent/pull/19206))
### Discord
- **Message deletion action** (salvage #19052) ([#21197](https://github.com/NousResearch/hermes-agent/pull/21197))
- Fix: allow `free_response_channels` to override `DISCORD_IGNORE_NO_MENTION` ([#19629](https://github.com/NousResearch/hermes-agent/pull/19629))
### Slack
- Fix: ephemeral slash-command ack, private notice delivery, format_message fixes (@kshitijk4poor) ([#18198](https://github.com/NousResearch/hermes-agent/pull/18198))
### WhatsApp
- Fix: load WhatsApp home channel from env overrides ([#18190](https://github.com/NousResearch/hermes-agent/pull/18190))
### Feishu
- **Operator-configurable bot admission and mention policy** ([#18208](https://github.com/NousResearch/hermes-agent/pull/18208))
- Fix: force text mode for markdown tables (salvage of #13723 by @WuTianyi123) ([#20275](https://github.com/NousResearch/hermes-agent/pull/20275))
### Matrix + Email
- Fix: `/sethome` on Matrix and Email now persists across restarts ([#18272](https://github.com/NousResearch/hermes-agent/pull/18272))
### Teams
- **Docs + feat: sidebar + threading with group-chat fallback** ([#20042](https://github.com/NousResearch/hermes-agent/pull/20042))
### Weixin
- Fix: deduplicate Weixin messages by content fingerprint ([#19742](https://github.com/NousResearch/hermes-agent/pull/19742))
### QQBot
- **Port SDK improvements in-tree — chunked upload, approval keyboards, quoted attachments** ([#21342](https://github.com/NousResearch/hermes-agent/pull/21342))
- **Wire native tool-approval UX via inline keyboards** ([#21353](https://github.com/NousResearch/hermes-agent/pull/21353))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
#### Pluggable providers
- **ProviderProfile ABC + `plugins/model-providers/`** — inference providers are now a pluggable surface (salvage of #14424) ([#20324](https://github.com/NousResearch/hermes-agent/pull/20324))
- **`list_picker_providers`** — credential-filtered picker (salvage #13561) ([#20298](https://github.com/NousResearch/hermes-agent/pull/20298))
- **Remove `/provider` alias for `/model`** ([#20358](https://github.com/NousResearch/hermes-agent/pull/20358))
- **Shared Hermes dotenv loader across CLI + plugins** (salvage #13660) ([#20281](https://github.com/NousResearch/hermes-agent/pull/20281))
- **Nous OAuth persisted across profiles via shared token store** ([#19712](https://github.com/NousResearch/hermes-agent/pull/19712))
#### New models
- `deepseek/deepseek-v4-pro` added to OpenRouter + Nous Portal ([#20495](https://github.com/NousResearch/hermes-agent/pull/20495))
- `x-ai/grok-4.3` added to OpenRouter + Nous Portal ([#20497](https://github.com/NousResearch/hermes-agent/pull/20497))
- `openrouter/owl-alpha` (free tier) added to curated OpenRouter list ([#18071](https://github.com/NousResearch/hermes-agent/pull/18071))
- `tencent/hy3-preview` paid route on OpenRouter (@Contentment003111) ([#21077](https://github.com/NousResearch/hermes-agent/pull/21077))
- Arcee Trinity Large Thinking — temperature + compression overrides ([#20473](https://github.com/NousResearch/hermes-agent/pull/20473))
- Rename `x-ai/grok-4.20-beta` to `x-ai/grok-4.20` ([#19640](https://github.com/NousResearch/hermes-agent/pull/19640))
- Demote Vercel AI Gateway to bottom of provider picker ([#18112](https://github.com/NousResearch/hermes-agent/pull/18112))
#### Provider configuration
- **OpenRouter — response caching support** (@kshitijk4poor) ([#19132](https://github.com/NousResearch/hermes-agent/pull/19132))
- **`image_gen.model` from config.yaml honored** (salvage #19376) ([#21273](https://github.com/NousResearch/hermes-agent/pull/21273))
- Fix: honor runtime default model during delegate provider resolution (@johnncenae) ([#17587](https://github.com/NousResearch/hermes-agent/pull/17587))
- Fix: avoid Bedrock credential probe in provider picker (@helix4u) ([#18998](https://github.com/NousResearch/hermes-agent/pull/18998))
- Fix: drop stale env-var override of persisted provider for cron ([#19627](https://github.com/NousResearch/hermes-agent/pull/19627))
- Fix: auxiliary curator api_key/base_url into runtime resolution ([#19421](https://github.com/NousResearch/hermes-agent/pull/19421))
### Agent Loop & Conversation
- **`video_analyze` — native video understanding tool** (@alt-glitch) ([#19301](https://github.com/NousResearch/hermes-agent/pull/19301))
- **Show context compression count in status bar** (CLI + TUI) ([#21218](https://github.com/NousResearch/hermes-agent/pull/21218))
- **Isolate `get_tool_definitions` quiet_mode cache + dedup LCM injection** (#17335) ([#17889](https://github.com/NousResearch/hermes-agent/pull/17889))
- Fix: warning-first tool-call loop guardrails ([#18227](https://github.com/NousResearch/hermes-agent/pull/18227))
- Fix: break permanent empty-response loop from orphan tool-tail ([#21385](https://github.com/NousResearch/hermes-agent/pull/21385))
- Fix: propagate ContextVars to concurrent tool worker threads (salvage #16660) ([#18123](https://github.com/NousResearch/hermes-agent/pull/18123))
- Fix: surface self-improvement review summaries across CLI, TUI, and gateway ([#18073](https://github.com/NousResearch/hermes-agent/pull/18073))
- Fix: serialize concurrent `hermes_tools` RPC calls from `execute_code` ([#17894](https://github.com/NousResearch/hermes-agent/pull/17894), [#17902](https://github.com/NousResearch/hermes-agent/pull/17902))
- Fix: include system prompt + tool schemas in token estimates for compression ([#18265](https://github.com/NousResearch/hermes-agent/pull/18265))
### Compression
- Fix: skip non-string tool content in dedup pass to prevent AttributeError ([#19398](https://github.com/NousResearch/hermes-agent/pull/19398))
- Fix: reset `_summary_failure_cooldown_until` on session reset ([#19622](https://github.com/NousResearch/hermes-agent/pull/19622))
- Fix: trigger fallback on timeout errors alongside model-unavailable errors ([#19665](https://github.com/NousResearch/hermes-agent/pull/19665))
- Fix: `_prune_old_tool_results` boundary direction ([#19725](https://github.com/NousResearch/hermes-agent/pull/19725))
- Fix: soften summary prompt for content filters (salvage #19456) ([#21302](https://github.com/NousResearch/hermes-agent/pull/21302))
### Delegate
- Fix: inherit parent fallback_chain in `_build_child_agent` ([#19601](https://github.com/NousResearch/hermes-agent/pull/19601))
- Fix: guard `_load_config()` against `delegation: null` in config.yaml ([#19662](https://github.com/NousResearch/hermes-agent/pull/19662))
- Fix: inherit parent api_key when `delegation.base_url` set without `delegation.api_key` ([#19741](https://github.com/NousResearch/hermes-agent/pull/19741))
- Fix: expand composite toolsets before intersection (salvage #19455) ([#21300](https://github.com/NousResearch/hermes-agent/pull/21300))
- Fix: correct ACP docs — Claude Code CLI has no --acp flag (salvage #19058) ([#21201](https://github.com/NousResearch/hermes-agent/pull/21201))
### Session & Memory
- **Hindsight — probe API for `update_mode='append'` to dedupe across processes** (@nicoloboschi) ([#20222](https://github.com/NousResearch/hermes-agent/pull/20222))
### Curator
- **`hermes curator archive` and `prune` subcommands** ([#20200](https://github.com/NousResearch/hermes-agent/pull/20200))
- **`hermes curator list-archived`** (#20651) ([#21236](https://github.com/NousResearch/hermes-agent/pull/21236))
- **Synchronous manual `hermes curator run`** (#20555) ([#21216](https://github.com/NousResearch/hermes-agent/pull/21216))
- Fix: preserve `last_report_path` in state ([#18169](https://github.com/NousResearch/hermes-agent/pull/18169))
- Fix: rewrite cron job skill refs after consolidation ([#18253](https://github.com/NousResearch/hermes-agent/pull/18253))
- Fix: defer first run + `--dry-run` preview (#18373) ([#18389](https://github.com/NousResearch/hermes-agent/pull/18389))
- Fix: authoritative `absorbed_into` on delete + restore cron skill links on rollback (#18671) ([#18731](https://github.com/NousResearch/hermes-agent/pull/18731))
- Fix: prevent false-positive consolidation from substring matching ([#19573](https://github.com/NousResearch/hermes-agent/pull/19573))
- Fix: only mark agent-created for background-review sediment ([#19621](https://github.com/NousResearch/hermes-agent/pull/19621))
- Fix: protect hub skills by frontmatter name ([#20194](https://github.com/NousResearch/hermes-agent/pull/20194))
---
## 🔧 Tool System
### File tools
- **Post-write delta lint on `write_file` + `patch`** — in-proc linters for Python, JSON, YAML, TOML ([#20191](https://github.com/NousResearch/hermes-agent/pull/20191))
### Cron
- **`no_agent` mode — script-only cron jobs (watchdog pattern)** ([#19709](https://github.com/NousResearch/hermes-agent/pull/19709))
- **`context_from` chaining docs** (salvage #15724) ([#20394](https://github.com/NousResearch/hermes-agent/pull/20394))
- Fix: treat non-dict origin as missing instead of crashing tick ([#19283](https://github.com/NousResearch/hermes-agent/pull/19283))
- Fix: bump skill usage when cron jobs load skills ([#19433](https://github.com/NousResearch/hermes-agent/pull/19433))
- Fix: recover null `next_run_at` jobs ([#19576](https://github.com/NousResearch/hermes-agent/pull/19576))
- Fix: skip AI call when prerun script produces no output ([#19628](https://github.com/NousResearch/hermes-agent/pull/19628))
- Fix: expand config.yaml refs during job execution ([#19872](https://github.com/NousResearch/hermes-agent/pull/19872))
- Fix: serialize `get_due_jobs` writes to prevent parallel state corruption ([#19874](https://github.com/NousResearch/hermes-agent/pull/19874))
- Fix: initialize MCP servers before constructing the cron AIAgent ([#21354](https://github.com/NousResearch/hermes-agent/pull/21354))
### MCP
- **SSE transport support** (salvage #19135) ([#21227](https://github.com/NousResearch/hermes-agent/pull/21227))
- **Forward OAuth auth + bump `sse_read_timeout` on SSE transport** ([#21323](https://github.com/NousResearch/hermes-agent/pull/21323))
- **Retry stale pipe transport failures as session-expired** ([#21289](https://github.com/NousResearch/hermes-agent/pull/21289))
- **Surface image tool results as MEDIA tags instead of dropping them** ([#21328](https://github.com/NousResearch/hermes-agent/pull/21328))
- **Periodic keepalive to `_wait_for_lifecycle_event`** (salvage #17016) ([#20209](https://github.com/NousResearch/hermes-agent/pull/20209))
- Fix: reconnect on terminated sessions ([#19380](https://github.com/NousResearch/hermes-agent/pull/19380))
- Fix: decouple AnyUrl import from mcp dependency ([#19695](https://github.com/NousResearch/hermes-agent/pull/19695))
- Fix: `mcp add --command` gets distinct argparse dest ([#21204](https://github.com/NousResearch/hermes-agent/pull/21204))
- Fix: clear stale thread interrupt before MCP discovery ([#21276](https://github.com/NousResearch/hermes-agent/pull/21276))
- Fix: report configured timeout in MCP call errors ([#21281](https://github.com/NousResearch/hermes-agent/pull/21281))
- Fix: include exception type in error messages when str(exc) is empty (salvage #19425) ([#21292](https://github.com/NousResearch/hermes-agent/pull/21292))
- Fix: re-raise CancelledError explicitly in `MCPServerTask.run` ([#21318](https://github.com/NousResearch/hermes-agent/pull/21318))
- Fix: coerce numeric tool args defensively in `mcp_serve` ([#21329](https://github.com/NousResearch/hermes-agent/pull/21329))
- Fix: gate utility stubs on server-advertised capabilities ([#21347](https://github.com/NousResearch/hermes-agent/pull/21347))
### Browser
- Fix: allow explicit CDP override without local agent-browser ([#19670](https://github.com/NousResearch/hermes-agent/pull/19670))
- Fix: inject `--no-sandbox` for root + AppArmor userns restrictions ([#19747](https://github.com/NousResearch/hermes-agent/pull/19747))
- Fix: tighten Lightpanda fallback edge cases (@kshitijk4poor) ([#20672](https://github.com/NousResearch/hermes-agent/pull/20672))
### Web tools
- **Per-capability backend selection — search/extract split** (@kshitijk4poor) ([#20061](https://github.com/NousResearch/hermes-agent/pull/20061))
- **SearXNG native search-only backend** (@kshitijk4poor) ([#20823](https://github.com/NousResearch/hermes-agent/pull/20823))
### Approval / Tool gating
- Fix: wake blocked gateway approvals on session cleanup ([#18171](https://github.com/NousResearch/hermes-agent/pull/18171))
- Fix: harden YOLO mode env parsing against quoted-bool strings ([#18214](https://github.com/NousResearch/hermes-agent/pull/18214))
- Fix: extend sensitive write target to cover shell RC and credential files ([#19282](https://github.com/NousResearch/hermes-agent/pull/19282))
---
## 🔌 Plugin System
- **`transform_llm_output` plugin hook** (salvage of #20813) ([#21235](https://github.com/NousResearch/hermes-agent/pull/21235))
- **Document `env_enablement_fn` + `cron_deliver_env_var` platform-plugin hooks** ([#21331](https://github.com/NousResearch/hermes-agent/pull/21331))
- **Pluggable surfaces coverage — model-provider guide, full plugin map, opt-in fix** ([#20749](https://github.com/NousResearch/hermes-agent/pull/20749))
- **Plugin-authoring gaps — image-gen provider guide + publishing a skill tap** ([#20800](https://github.com/NousResearch/hermes-agent/pull/20800))
---
## 🧩 Skills Ecosystem
### New optional skills
- **Shopify** — Admin + Storefront GraphQL optional skill ([#18116](https://github.com/NousResearch/hermes-agent/pull/18116))
- **here.now** — optional skill ([#18170](https://github.com/NousResearch/hermes-agent/pull/18170))
- **shop-app** — personal shopping assistant (optional) ([#20702](https://github.com/NousResearch/hermes-agent/pull/20702))
- **Anthropic financial-services bundle** — ported as optional finance skills ([#21180](https://github.com/NousResearch/hermes-agent/pull/21180))
- **kanban-video-orchestrator** — creative optional skill (@SHL0MS) ([#19281](https://github.com/NousResearch/hermes-agent/pull/19281))
- **searxng-search** — optional skill + Web Search + Extract docs page (@kshitijk4poor) ([#20841](https://github.com/NousResearch/hermes-agent/pull/20841), [#20844](https://github.com/NousResearch/hermes-agent/pull/20844))
### Skill UX
- **Linear skill — add Documents support + Python helper script** ([#20752](https://github.com/NousResearch/hermes-agent/pull/20752))
- **Modernize Obsidian skill to use file tools** (salvage #19332) ([#20413](https://github.com/NousResearch/hermes-agent/pull/20413))
- **Default custom tool creation to plugins** (@kshitijk4poor) ([#19755](https://github.com/NousResearch/hermes-agent/pull/19755))
- **skill_commands cache — rescan on platform scope changes** (salvage #14570 by @LeonSGP43) ([#18739](https://github.com/NousResearch/hermes-agent/pull/18739))
- **Skills — additional rescan paths in skill_commands cache** (salvage #19042) ([#21181](https://github.com/NousResearch/hermes-agent/pull/21181))
- Fix: regression tests for non-dict metadata in `extract_skill_conditions` ([#18213](https://github.com/NousResearch/hermes-agent/pull/18213))
- Docs: explain restoring bundled skills (salvage #19254) ([#20404](https://github.com/NousResearch/hermes-agent/pull/20404))
- Docs: document `hermes skills reset` subcommand (salvage #11544) ([#20395](https://github.com/NousResearch/hermes-agent/pull/20395))
- Docs: himalaya v1.2.0 `folder.aliases` syntax ([#19882](https://github.com/NousResearch/hermes-agent/pull/19882))
- Point agent at `hermes-agent` skill + docs site sync ([#20390](https://github.com/NousResearch/hermes-agent/pull/20390))
---
## 🖥️ CLI & User Experience
### CLI
- **`/new` accepts optional session name argument** (salvage of #19555) ([#19637](https://github.com/NousResearch/hermes-agent/pull/19637))
- **100 new CLI startup tips** ([#20168](https://github.com/NousResearch/hermes-agent/pull/20168))
- **`display.language` — static message translation** (zh/ja/de/es) ([#20231](https://github.com/NousResearch/hermes-agent/pull/20231))
- **French (fr) locale** (@Foolafroos) ([#20329](https://github.com/NousResearch/hermes-agent/pull/20329))
- **Ukrainian (uk) locale** ([#20467](https://github.com/NousResearch/hermes-agent/pull/20467))
- **Turkish (tr) locale** ([#20474](https://github.com/NousResearch/hermes-agent/pull/20474))
- Fix: recover classic CLI output after resize (@helix4u) ([#20444](https://github.com/NousResearch/hermes-agent/pull/20444))
- Fix: complete absolute paths as paths (@helix4u) ([#19930](https://github.com/NousResearch/hermes-agent/pull/19930))
- Fix: resolve lazy session creation regressions (#18370 fallout) (@alt-glitch) ([#20363](https://github.com/NousResearch/hermes-agent/pull/20363))
- Fix: local backend CLI always uses launch directory (@alt-glitch) ([#19334](https://github.com/NousResearch/hermes-agent/pull/19334))
- Refactor: drop dead c-S-c key binding (follow-up to #19895) ([#19919](https://github.com/NousResearch/hermes-agent/pull/19919))
### TUI (Ink)
- **`/model` picker overhaul to match `hermes model` with inline auth** (@austinpickett) ([#18117](https://github.com/NousResearch/hermes-agent/pull/18117))
- **Collapsible sections in startup banner** — skills, system prompt, MCP (@kshitijk4poor) ([#20625](https://github.com/NousResearch/hermes-agent/pull/20625))
- **Show context compression count in status bar** ([#21218](https://github.com/NousResearch/hermes-agent/pull/21218))
- Perf: reduce overlay render churn with focused selectors (@OutThisLife) ([#20393](https://github.com/NousResearch/hermes-agent/pull/20393))
- Fix: restore voice push-to-talk parity (salvage of #16189 by @Montbra) (@OutThisLife) ([#20897](https://github.com/NousResearch/hermes-agent/pull/20897))
- Fix: kanban button (@austinpickett) ([#18358](https://github.com/NousResearch/hermes-agent/pull/18358))
### Dashboard
- **Plugins page — manage, enable/disable, auth status** (@austinpickett) ([#18095](https://github.com/NousResearch/hermes-agent/pull/18095))
- **Profiles management page** (@vincez-hms-coder) ([#16419](https://github.com/NousResearch/hermes-agent/pull/16419))
- **Interactive column sorting in analytics tables** ([#18192](https://github.com/NousResearch/hermes-agent/pull/18192))
- **`default-large` built-in theme with 18px base size** ([#20820](https://github.com/NousResearch/hermes-agent/pull/20820))
- **Support serving under URL prefix via `X-Forwarded-Prefix`** (salvage #19450) ([#21296](https://github.com/NousResearch/hermes-agent/pull/21296))
- **Launch dashboard as side-process via `HERMES_DASHBOARD=1` in Docker** (@benbarclay) ([#19540](https://github.com/NousResearch/hermes-agent/pull/19540))
- Fix: dashboard theme layout shift (@AllardQuek) ([#17232](https://github.com/NousResearch/hermes-agent/pull/17232))
- Fix: gateway model picker current context (@helix4u) ([#20513](https://github.com/NousResearch/hermes-agent/pull/20513))
### Update + setup
- **`hermes update --yes/-y` to skip interactive prompts** ([#18261](https://github.com/NousResearch/hermes-agent/pull/18261))
- **Restart manual profile gateways after update** ([#18178](https://github.com/NousResearch/hermes-agent/pull/18178))
### Profiles
- **`--no-skills` flag for empty profile creation** ([#20986](https://github.com/NousResearch/hermes-agent/pull/20986))
---
## 🎵 Voice, Image & Media
- **xAI Custom Voices — voice cloning** (@alt-glitch) ([#18776](https://github.com/NousResearch/hermes-agent/pull/18776))
- **Achievements — share card render on unlocked badges** ([#19657](https://github.com/NousResearch/hermes-agent/pull/19657))
- **Refresh systemd unit on gateway boot (not just start/restart)** (@alt-glitch) ([#19684](https://github.com/NousResearch/hermes-agent/pull/19684))
---
## 🔗 API Server & Remote Access
- **`X-Hermes-Session-Key` header for long-term memory scoping** (closes #20060) ([#20199](https://github.com/NousResearch/hermes-agent/pull/20199))
---
## 🧰 ACP Adapter (VS Code / Zed / JetBrains)
- **`/steer` and `/queue` slash commands** (@HenkDz) ([#18114](https://github.com/NousResearch/hermes-agent/pull/18114))
- Fix: translate Windows cwd for WSL sessions (salvage #18128) ([#18233](https://github.com/NousResearch/hermes-agent/pull/18233))
- Fix: run `/steer` as a regular prompt on idle sessions ([#18258](https://github.com/NousResearch/hermes-agent/pull/18258))
- Fix: route Zed thoughts to reasoning + polish tool/context rendering ([#19139](https://github.com/NousResearch/hermes-agent/pull/19139))
- Fix: atomic session persistence via `replace_messages` (salvage #13675) ([#20279](https://github.com/NousResearch/hermes-agent/pull/20279))
- Fix: preserve assistant reasoning metadata in session persistence (salvage #13575) ([#20296](https://github.com/NousResearch/hermes-agent/pull/20296))
- Docs: update VS Code setup for ACP Client extension (salvage #12495) ([#20433](https://github.com/NousResearch/hermes-agent/pull/20433))
---
## 🐳 Docker
- **Launch dashboard as side-process via `HERMES_DASHBOARD=1`** (@benbarclay) ([#19540](https://github.com/NousResearch/hermes-agent/pull/19540))
- **Refuse root gateway runs in official image** (salvage #19215) ([#21250](https://github.com/NousResearch/hermes-agent/pull/21250))
- **Chown runtime `node_modules` trees to hermes user** (salvage #19303) ([#21267](https://github.com/NousResearch/hermes-agent/pull/21267))
- Fix: exclude compose/profile runtime state from build context ([#19626](https://github.com/NousResearch/hermes-agent/pull/19626))
- CI: don't cancel overlapping builds, guard `:latest` (@ethernet8023) ([#20890](https://github.com/NousResearch/hermes-agent/pull/20890))
- Test: align Dockerfile contract tests with simplified TUI flow (salvage #19024) ([#21174](https://github.com/NousResearch/hermes-agent/pull/21174))
- Docs: connect to local inference servers (vLLM, Ollama) (salvage #12335) ([#20407](https://github.com/NousResearch/hermes-agent/pull/20407))
- Docs: document `API_SERVER_*` env vars (salvage #11758) ([#20409](https://github.com/NousResearch/hermes-agent/pull/20409))
- Docs: clarify Docker terminal backend is a single persistent container ([#20003](https://github.com/NousResearch/hermes-agent/pull/20003))
---
## 🐛 Notable Bug Fixes
### Agent
- Fix: recover lazy session creation regressions (#18370 fallout) (@alt-glitch) ([#20363](https://github.com/NousResearch/hermes-agent/pull/20363))
- Fix: propagate ContextVars to concurrent tool worker threads (salvage #16660) ([#18123](https://github.com/NousResearch/hermes-agent/pull/18123))
- Fix: warning-first tool-call loop guardrails ([#18227](https://github.com/NousResearch/hermes-agent/pull/18227))
- Fix: surface self-improvement review summaries across CLI, TUI, and gateway ([#18073](https://github.com/NousResearch/hermes-agent/pull/18073))
### Gateway streaming
- Fix: harden StreamingConfig bool and numeric coercion (@simbam99) ([#16463](https://github.com/NousResearch/hermes-agent/pull/16463))
### Model
- Fix: avoid Bedrock credential probe in provider picker (@helix4u) ([#18998](https://github.com/NousResearch/hermes-agent/pull/18998))
### Doctor
- Fix: check global agent-browser when local install not found ([#19671](https://github.com/NousResearch/hermes-agent/pull/19671))
- Test: kimi-coding-cn provider validation regression ([#19734](https://github.com/NousResearch/hermes-agent/pull/19734))
### Update
- Fix: patch `isatty` on real streams to fix xdist-flaky `--yes` tests (salvage #19026) ([#21175](https://github.com/NousResearch/hermes-agent/pull/21175))
- Fix: teach restart-mocks about the post-update survivor sweep (salvage #19031) ([#21177](https://github.com/NousResearch/hermes-agent/pull/21177))
### Auth
- Fix: acp preserve assistant reasoning metadata ([#20296](https://github.com/NousResearch/hermes-agent/pull/20296))
### Redact
- Fix: add `code_file` param to skip false-positive ENV/JSON patterns ([#19715](https://github.com/NousResearch/hermes-agent/pull/19715))
### Email
- Fix: quoted-relative file-drop paths + Date header on tool email path ([#19646](https://github.com/NousResearch/hermes-agent/pull/19646))
---
## 🧪 Testing
- **ACP — accept prompt persistence kwargs in MCP E2E mocks** (@stephenschoettler) ([#18047](https://github.com/NousResearch/hermes-agent/pull/18047))
- **Toolsets — include kanban in expected post-#17805 toolset assertions** (@briandevans) ([#18122](https://github.com/NousResearch/hermes-agent/pull/18122))
- **Agent — cover max-iterations summary message sanitization** ([#19580](https://github.com/NousResearch/hermes-agent/pull/19580))
- **run_agent — `-inf` and `nan` regression coverage for `_coerce_number`** ([#19703](https://github.com/NousResearch/hermes-agent/pull/19703))
---
## 📚 Documentation
### Major docs additions
- **`llms.txt` + `llms-full.txt` — agent-friendly ingestion** ([#18276](https://github.com/NousResearch/hermes-agent/pull/18276))
- **User Stories and Use Cases collage page** ([#18282](https://github.com/NousResearch/hermes-agent/pull/18282))
- **Persistent Goals (/goal) feature page** ([#18275](https://github.com/NousResearch/hermes-agent/pull/18275))
- **Windows (WSL2) guide expansion** — filesystem, networking, services, pitfalls ([#20748](https://github.com/NousResearch/hermes-agent/pull/20748))
- **Chinese (zh-CN) README translation** (salvage #13508) ([#20431](https://github.com/NousResearch/hermes-agent/pull/20431))
- **zh-Hans Docusaurus locale** + Tool Gateway / image-gen / WSL quickstart translations (salvage #11728) ([#20430](https://github.com/NousResearch/hermes-agent/pull/20430))
- **Tool Gateway docs restructure** — lead with what it does, config moved to bottom ([#20827](https://github.com/NousResearch/hermes-agent/pull/20827))
- **Quickstart — Onchain AI Garage Hermes tutorials playlist** ([#20192](https://github.com/NousResearch/hermes-agent/pull/20192))
- **Open WebUI bootstrap script** (salvage #9566) ([#20427](https://github.com/NousResearch/hermes-agent/pull/20427))
- **Local Ollama setup guide** (salvage #5842) ([#20426](https://github.com/NousResearch/hermes-agent/pull/20426))
- **Google Gemini guide** (salvage #17450) ([#20401](https://github.com/NousResearch/hermes-agent/pull/20401))
- **Custom model aliases for /model command** ([#20475](https://github.com/NousResearch/hermes-agent/pull/20475))
- **Together/Groq/Perplexity cookbook via `custom_providers`** (salvage #15214) ([#20400](https://github.com/NousResearch/hermes-agent/pull/20400))
- **Doubao speech integration examples** (TTS + STT) (salvage #18065) ([#20418](https://github.com/NousResearch/hermes-agent/pull/20418))
- **WSL-to-Windows Chrome MCP bridge** (salvage #8313) ([#20428](https://github.com/NousResearch/hermes-agent/pull/20428))
- **Hermes skills docs sync** — slash commands + durable-systems section ([#20390](https://github.com/NousResearch/hermes-agent/pull/20390))
- **AGENTS.md — curator/cron/delegation/toolsets + fix plugin tree** ([#20226](https://github.com/NousResearch/hermes-agent/pull/20226))
- **Bedrock quickstart entry + fallback comment + deployment link** (salvage #11093) ([#20397](https://github.com/NousResearch/hermes-agent/pull/20397))
### Docs polish
- Collapse exploding skills tree to a single Skills node ([#18259](https://github.com/NousResearch/hermes-agent/pull/18259))
- Clarify `session_search` auxiliary model docs ([#19593](https://github.com/NousResearch/hermes-agent/pull/19593))
- Open WebUI Quick Setup gap fill ([#19654](https://github.com/NousResearch/hermes-agent/pull/19654))
- Default custom tool creation to plugins (@kshitijk4poor) ([#19755](https://github.com/NousResearch/hermes-agent/pull/19755))
- Clarify Telegram group chat troubleshooting (salvage #18672) ([#20416](https://github.com/NousResearch/hermes-agent/pull/20416))
- Codex OAuth auth prerequisite clarification (salvage #18688) ([#20417](https://github.com/NousResearch/hermes-agent/pull/20417))
- Discord Server Members Intent + SSRC-mapping drift + /voice join slash Choice (salvage #11350) ([#20411](https://github.com/NousResearch/hermes-agent/pull/20411))
- Document `ctx.dispatch_tool()` (salvage #10955) ([#20391](https://github.com/NousResearch/hermes-agent/pull/20391))
- Document `hermes webhook subscribe --deliver-only` (salvage #12612) ([#20392](https://github.com/NousResearch/hermes-agent/pull/20392))
- Document `hermes import` reference (salvage #14711) ([#20396](https://github.com/NousResearch/hermes-agent/pull/20396))
- Document per-provider TTS `max_text_length` caps (salvage #13825) ([#20389](https://github.com/NousResearch/hermes-agent/pull/20389))
- Clarify supported prompt customization surfaces (salvage #19987) ([#20383](https://github.com/NousResearch/hermes-agent/pull/20383))
- Correct `web_extract` summarizer timeout comment (salvage #20051) ([#20381](https://github.com/NousResearch/hermes-agent/pull/20381))
- Fix fallback provider config paths (salvage #20033) ([#20382](https://github.com/NousResearch/hermes-agent/pull/20382))
- Fix misleading RL install-extras claim (salvage #19080) ([#21213](https://github.com/NousResearch/hermes-agent/pull/21213))
- Clarify API server tool execution locality (salvage #19117) ([#21223](https://github.com/NousResearch/hermes-agent/pull/21223))
- Prefer `.venv` to match AGENTS.md and scripts/run_tests.sh (@xxxigm) ([#21334](https://github.com/NousResearch/hermes-agent/pull/21334))
- Align tool discovery + test runner with AGENTS.md (@xxxigm) ([#20791](https://github.com/NousResearch/hermes-agent/pull/20791))
- Align terminal-backend count and naming across docs and code (salvage #19044) ([#20402](https://github.com/NousResearch/hermes-agent/pull/20402))
- Refresh stale platform counts (salvage #19053) ([#20403](https://github.com/NousResearch/hermes-agent/pull/20403))
---
## 👥 Contributors
### Core
- **@teknium1** — salvage, triage, review, feature work, and release management
### Top Community Contributors
- **@kshitijk4poor** (21 PRs) — SearXNG native search backend, per-capability backend selection, collapsible TUI startup banner, Slack ephemeral ack + format fixes, Lightpanda fallback hardening, searxng-search optional skill + Web Search + Extract docs, default custom tool creation to plugins, kanban failure-column fix
- **@alt-glitch** (13 PRs) — video_analyze tool, xAI Custom Voices (voice cloning), local-backend CLI launch-directory fix, lazy-session creation regression recovery, systemd unit refresh on gateway boot
- **@OutThisLife** (9 PRs) — TUI perf — overlay render churn reduction, voice push-to-talk parity restoration (salvaging @Montbra)
- **@helix4u** (6 PRs) — Classic CLI output recovery after resize, absolute-path TUI completion, gateway model picker current-context fix, Bedrock credential probe avoidance, kanban docs fixes
- **@ethernet8023** (3 PRs) — Docker CI — don't cancel overlapping builds, :latest guard
- **@benbarclay** (3 PRs) — Docker — launch dashboard as side-process via HERMES_DASHBOARD=1
- **@austinpickett** (3 PRs) — Dashboard Plugins page, TUI /model picker overhaul with inline auth, kanban button fix
- **@sprmn24** (2 PRs) — Contributor (2 PRs)
- **@asheriif** (2 PRs) — Contributor (2 PRs)
- **@xxxigm** (2 PRs) — Contributing docs — .venv preference and test runner alignment with AGENTS.md
- **@stephenschoettler** (1 PR) — ACP — MCP E2E mock kwargs
- **@vincez-hms-coder** (1 PR) — Dashboard — Profiles management page
- **@cdanis** (1 PR) — Contributor
- **@briandevans** (1 PR) — Toolsets test — kanban assertions post-#17805
- **@heyitsaamir** (1 PR) — Contributor
### All Contributors
Thanks to everyone who contributed to v0.13.0 — commits, co-authored work, and salvaged PRs. 295 contributors in one week.
@0oAstro, @0xDevNinja, @0xharryriddle, @0xKingBack, @0xsir0000, @0xyg3n, @0z1-ghb, @abhinav11082001-stack,
@acc001k, @acesjohnny, @adamludwin, @adybag14-cyber, @agentlinker, @agilejava, @ai-ag2026, @AJV20,
@alanxchen85, @albert748, @AllardQuek, @alt-glitch, @altmazza0-star, @ambition0802, @amitgaur, @amroessam,
@andrewhosf, @Asce66, @asheriif, @ashermorse, @asimons81, @Aslaaen, @Asunfly, @atongrun, @austinpickett,
@banditburai, @barteqpl, @Bartok9, @Beandon13, @beardthelion, @beibi9966, @benbarclay, @binhnt92, @bjianhang,
@BlackJulySnow, @bobashopcashier, @bogerman1, @Bongulielmi, @Brecht-H, @briandevans, @brooklynnicholson,
@c3115644151, @camaragon, @CashWilliams, @CCClelo, @cdanis, @CES4751, @cg2aigc, @changchun989, @ChanlerDev,
@CharlieKerfoot, @chengoak, @chenyunbo411, @chinadbo, @CIRWEL, @cixuuz, @cmcgrabby-hue, @colorcross,
@Contentment003111, @CoreyNoDream, @counterposition, @curiouscleo, @DaniuXie, @deep-name, @dengtaoyuan450-a11y,
@discodirector, @donramon77, @dpaluy, @ee-blog, @ehz0ah, @el-analista, @elmatadorgh, @EmelyanenkoK,
@Emidomenge, @emozilla, @Es1la, @EthanGuo-coder, @etherman-os, @ethernet8023, @EvilDrag0n, @exxmen, @Fearvox,
@Feranmi10, @firefly, @flobo3, @fmercurio, @Foolafroos, @formulahendry, @franksong2702, @ggnnggez, @GinWU05,
@giwaov, @glesperance, @gnanirahulnutakki, @GodsBoy, @Gosuj, @Grey0202, @guillaumemeyer, @Gutslabs, @h0tp-ftw,
@haidao1919, @halmisen, @happy5318, @hedirman, @helix4u, @hendrixfreire, @HenkDz, @hex-clawd, @heyitsaamir,
@hharry11, @Hinotoi-agent, @holynn-q, @hrkzogw, @Hypn0sis, @Hypnus-Yuan, @ideathinklab01-source, @IMHaoyan,
@Interstellar-code, @ishardo, @jacdevos, @jackey8616, @JanCong, @jasonoutland, @jatingodnani, @JayGwod,
@jethac, @JezzaHehn, @JiaDe-Wu, @jjjojoj, @jkausel-ai, @John-tip, @johnncenae, @jrusso1020, @jslizar,
@JTroyerOvermatch, @julysir, @Junass1, @JustinUssuri, @Kailigithub, @keepcalmqqf, @kiala9, @konsisumer,
@kowenhaoai, @Krionex, @kshitijk4poor, @kyan12, @leavrcn, @leon7609, @LeonSGP43, @leprincep35700, @lhysdl,
@likejudy, @lisanhu, @liu-collab, @liuguangyong93, @liuhao1024, @LucianoSP, @luoyuctl, @luyao618, @M3RCUR2Y,
@maciekczech, @Magicray1217, @magicray1217, @MaHaoHao-ch, @malaiwah, @manateelazycat, @masonjames, @megastary,
@memosr, @MichaelWDanko, @mikeyobrien, @millerc79, @Mind-Dragon, @mioimotoai-lgtm, @misery-hl, @molvikar,
@momowind, @Montbra, @MottledShadow, @mrbob-git, @mrcharlesiv, @mrcoferland, @ms-alan, @mwnickerson,
@nazirulhafiy, @nftpoetrist, @nicoloboschi, @nightq, @nikolay-bratanov, @NikolayGusev-astra, @nocturnum91,
@noOne-list, @nouseman666, @novax635, @npmisantosh, @nudiltoys-cmyk, @olisikh, @oluwadareab12, @Oxidane-bot,
@pama0227, @pander, @pasevin, @paul-tian, @pdonizete, @perlowja, @pingchesu, @PratikRai0101, @priveperfumes,
@probepark, @QifengKuang, @quocanh261997, @qWaitCrypto, @qxxaa, @r266-tech, @rames-jusso, @revaraver,
@Ricardo-M-L, @rob-maron, @Roy-oss1, @rxdxxxx, @SandroHub013, @Sanjays2402, @Sertug17, @shashwatgokhe,
@shellybotmoyer, @SHL0MS, @SimbaKingjoe, @simbam99, @simplenamebox-ops, @socrates1024, @sonic-netizen,
@sprmn24, @steezkelly, @stephen0110, @stephenschoettler, @stevenchanin, @stevenchouai, @stormhierta,
@subtract0, @suncokret12, @swithek, @taeng0204, @TakeshiSawaguchi, @tangyuanjc, @TheEpTic, @thelumiereguy,
@Tkander1715, @tmdgusya, @Tranquil-Flow, @TruaShamu, @UgwujaGeorge, @valda, @vincez-hms-coder, @VinVC,
@vominh1919, @wabrent, @WadydX, @wanazhar, @WanderWang, @warabe1122, @web-dev0521, @WideLee, @willy-scr,
@wmagev, @WuTianyi123, @wxst, @wysie, @Wysie, @xsfX20, @xxxigm, @xyiy001, @YanzhongSu, @ygd58, @Yoimex,
@yuehei, @Yukipukii1, @yuqianma, @YX234, @zeejaytan, @zhanggttry, @zhao0112, @zng8418, @zons-zhaozhy, @Zyproth
---
**Full Changelog**: [v2026.4.30...v2026.5.7](https://github.com/NousResearch/hermes-agent/compare/v2026.4.30...v2026.5.7)

View File

@@ -1,477 +0,0 @@
# Hermes Agent v0.14.0 (v2026.5.16)
**Release Date:** May 16, 2026
**Since v0.13.0:** 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community contributors (including co-authors)
> The Foundation Release — Hermes Agent installs and runs anywhere now. Native Windows ships in early beta with a full PowerShell installer story, a `pip install hermes-agent` wheel lands on PyPI, lazy-deps reshape what `pip install hermes-agent` actually pulls down, the supply-chain checker scans every install/upgrade for unsafe versions, and a new OpenAI-compatible local proxy lets Codex / Aider / Cline talk to OAuth-only providers (Claude Pro, ChatGPT Pro, SuperGrok). The cold-start wave shaves ~19 seconds off `hermes` launch, browser-tool CDP calls run 180x faster, and `hermes tools` All-Platforms drops from 14s to under 1.5s. Two new messaging platforms (LINE and SimpleX Chat) and a Microsoft Graph foundation (Teams pipeline + webhook adapter) land alongside `/handoff` that finally transfers sessions live, `vision_analyze` passing pixels through to vision-capable models, `x_search` as a first-class tool, LSP semantic diagnostics on every `write_file` / `patch`, a unified pluggable `video_generate`, a `computer_use` cua-driver backend, cross-session 1-hour Claude prompt caching, a per-turn file-mutation verifier, plus 9 new optional skills. 50+ P1 closures, 12 P0 closures.
---
## ✨ Highlights
- **Native Windows support (early beta)** — full PowerShell installer, native subprocess/PTY paths, taskkill-based process management, MinGit auto-install, Microsoft Store python stub detection, foreground Ctrl+C preservation, taskkill+ps2 fallback, npm prefix handling, and ~40 follow-up Windows-only fixes across CLI / gateway / TUI / curator / tools. Hermes finally runs natively on `cmd.exe` and PowerShell, no WSL required. ([#21561](https://github.com/NousResearch/hermes-agent/pull/21561), [#22130](https://github.com/NousResearch/hermes-agent/pull/22130), [#22752](https://github.com/NousResearch/hermes-agent/pull/22752), [#26618](https://github.com/NousResearch/hermes-agent/pull/26618), and many more)
- **`pip install hermes-agent && hermes`** — Hermes Agent is now a real PyPI package. One command, no clone, no git, no shell installer. Wheel includes the Ink TUI bundle and shell launcher. (salvage of [#26350](https://github.com/NousResearch/hermes-agent/pull/26350)) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
- **Cold-start performance wave — ~19s off `hermes` launch** — skills cache, lazy Feishu import, no Nous HTTP at startup, plus PEP-562 lazy adapter imports (QQ, Yuanbao, Teams, Google Chat), deferred `fal_client` / `google-cloud` / `httpx` loads, models.dev disk-cache-first lookup, parallel doctor API checks, eager-skip plugin discovery on built-in subcommands, `hermes tools` All-Platforms drops from 14s to <1.5s, welcome banner skipped on `chat -q`. ([#22138](https://github.com/NousResearch/hermes-agent/pull/22138), [#22120](https://github.com/NousResearch/hermes-agent/pull/22120), [#22681](https://github.com/NousResearch/hermes-agent/pull/22681), [#22790](https://github.com/NousResearch/hermes-agent/pull/22790), [#22808](https://github.com/NousResearch/hermes-agent/pull/22808), [#22831](https://github.com/NousResearch/hermes-agent/pull/22831), [#22859](https://github.com/NousResearch/hermes-agent/pull/22859), [#22904](https://github.com/NousResearch/hermes-agent/pull/22904), [#22766](https://github.com/NousResearch/hermes-agent/pull/22766), [#25341](https://github.com/NousResearch/hermes-agent/pull/25341))
- **180x faster `browser_console` evaluations** — routed through the supervisor's persistent CDP WebSocket instead of spawning a fresh DevTools session per call. Real-world page interactions feel instant. ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
- **Supply-chain advisory checker + lazy-deps framework + tiered install fallback** — every `pip install` / `hermes update` scans dependencies against an advisory list, lazy-deps replace heavy import-time loads with first-use installs, and the installer falls back through extras tiers when a wheel rejects on the target platform. ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
- **OpenAI-compatible local proxy** — `hermes proxy` exposes any OAuth-authed provider (Claude Pro, ChatGPT Pro, SuperGrok) as an OpenAI-compatible endpoint that Codex / Aider / Cline / VS Code Continue can hit. Your subscription, your tools. ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))
- **Cross-session 1-hour Claude prompt cache** — Anthropic / OpenRouter / Nous Portal now share a 1h prefix cache across sessions for Claude models. Fast resume, fast `/new`, lower cost on repeat work. ([#23828](https://github.com/NousResearch/hermes-agent/pull/23828))
- **Two new messaging platforms — LINE + SimpleX Chat** — LINE Messaging API lands as a first-class platform, SimpleX Chat salvages #2558 onto the modern adapter spec. Hermes is now on 22 platforms. ([#23197](https://github.com/NousResearch/hermes-agent/pull/23197), [#26232](https://github.com/NousResearch/hermes-agent/pull/26232))
- **Microsoft Graph foundation — Teams pipeline + webhook adapter** — `msgraph` auth/client foundation, webhook listener platform, Teams pipeline plugin runtime, and Teams outbound delivery via the existing adapter — Hermes can now read and post to Teams. (salvages of #21408#21411) ([#21922](https://github.com/NousResearch/hermes-agent/pull/21922), [#21969](https://github.com/NousResearch/hermes-agent/pull/21969), [#22007](https://github.com/NousResearch/hermes-agent/pull/22007), [#22024](https://github.com/NousResearch/hermes-agent/pull/22024))
- **`/handoff` actually transfers the session live** — the agent's active session moves to a different model / persona / profile mid-conversation, with messages, tool history, and context preserved. ([#23395](https://github.com/NousResearch/hermes-agent/pull/23395))
- **`x_search` — first-class X (Twitter) search tool** — gated tool with OAuth-or-API-key auth, no skill needed to query the timeline. ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))
- **`vision_analyze` returns pixels to vision-capable models** — when the active model can see, `vision_analyze` now hands the image straight through instead of falling back to a text description. ([#22955](https://github.com/NousResearch/hermes-agent/pull/22955))
- **LSP semantic diagnostics on every write** — `write_file` and `patch` now run real language-server diagnostics on the post-edit file (delta-only) and surface real errors before they ship downstream. ([#24168](https://github.com/NousResearch/hermes-agent/pull/24168), [#25978](https://github.com/NousResearch/hermes-agent/pull/25978))
- **Per-turn file-mutation verifier footer** — after every turn that wrote files, the agent gets a verifier footer summarizing what actually changed on disk — catches silent overwrites and "wrote it but it didn't land" bugs. ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
- **Unified `video_generate` with pluggable provider backends** — single tool, any backend. Drop in a new video provider as a plugin, no core changes. ([#25126](https://github.com/NousResearch/hermes-agent/pull/25126))
- **`computer_use` cua-driver backend** — proper focus-safe ops, non-Anthropic provider support, refresh on `hermes update`. Computer-use is no longer locked to a single SDK. (re-salvage of #16936) ([#21967](https://github.com/NousResearch/hermes-agent/pull/21967), [#24063](https://github.com/NousResearch/hermes-agent/pull/24063))
- **xAI Grok OAuth provider — SuperGrok via subscription** — sign in with your xAI account, talk to Grok models from Hermes. ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534))
- **Clarify with buttons — native inline keyboards on Telegram + Discord** — the `clarify` tool renders multi-choice prompts as platform-native buttons instead of typed responses. ([#24199](https://github.com/NousResearch/hermes-agent/pull/24199), [#25485](https://github.com/NousResearch/hermes-agent/pull/25485))
- **Discord channel history backfill (default on)** — Hermes reads recent channel history when joining a thread so it actually knows what's been said. ([#25984](https://github.com/NousResearch/hermes-agent/pull/25984))
- **Watchers skill — RSS / HTTP JSON / GitHub polling via cron `no_agent` mode** — skill recipes that wire change-detection sources directly into cron's script-only watchdog mode. ([#21881](https://github.com/NousResearch/hermes-agent/pull/21881))
- **Zed ACP Registry integration + uvx distribution** — Hermes is in the Zed registry, installable via `uvx` (no npm). Plus `hermes acp --setup-browser` bootstraps browser tools for registry installs. (salvage of [#25908](https://github.com/NousResearch/hermes-agent/pull/25908)) ([#26079](https://github.com/NousResearch/hermes-agent/pull/26079), [#26120](https://github.com/NousResearch/hermes-agent/pull/26120), [#26234](https://github.com/NousResearch/hermes-agent/pull/26234))
- **OpenRouter Pareto Code router** — wire a new OpenRouter router with `min_coding_score` knob. Pick the cheapest model that meets your quality bar. ([#22838](https://github.com/NousResearch/hermes-agent/pull/22838))
- **Optional codex app-server runtime for OpenAI/Codex models** — drives the OpenAI Codex CLI under the hood for OpenAI/Codex paths, with session reuse, wedge retirement, and OAuth refresh classification. ([#24182](https://github.com/NousResearch/hermes-agent/pull/24182), [#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
- **`hermes-skills/huggingface` as a trusted default tap** — community skills index from huggingface.co/skills is available by default in the Skills Hub. ([#26219](https://github.com/NousResearch/hermes-agent/pull/26219))
- **9 new optional skills** — Hyperliquid (perp/spot trading via SDK + REST) (@kshitijk4poor & Hermes), Yahoo Finance market data, api-testing (REST/GraphQL debug), unified EVM multi-chain skill (folds #25291 + #2010 + base/), darwinian-evolver, osint-investigation (closes #355), pinggy-tunnel, watchers (RSS/HTTP/GitHub via cron), Notion overhaul for the Developer Platform (May 2026). ([#23582](https://github.com/NousResearch/hermes-agent/pull/23582), [#23583](https://github.com/NousResearch/hermes-agent/pull/23583), [#23590](https://github.com/NousResearch/hermes-agent/pull/23590), [#25299](https://github.com/NousResearch/hermes-agent/pull/25299), [#26760](https://github.com/NousResearch/hermes-agent/pull/26760), [#26729](https://github.com/NousResearch/hermes-agent/pull/26729), [#26765](https://github.com/NousResearch/hermes-agent/pull/26765), [#21881](https://github.com/NousResearch/hermes-agent/pull/21881), [#26612](https://github.com/NousResearch/hermes-agent/pull/26612))
- **API server exposes run approval events** — long-running runs surface approval requests over the API stream, no more silent stalls. (salvage of [#20311](https://github.com/NousResearch/hermes-agent/pull/20311)) ([#21899](https://github.com/NousResearch/hermes-agent/pull/21899))
- **`/subgoal` — user-added criteria appended to active `/goal`** — layer extra success criteria onto a running goal loop. The judge sees them in the prompt, no behavior change when subgoals are empty. ([#25449](https://github.com/NousResearch/hermes-agent/pull/25449))
- **Plugins can run any LLM call via `ctx.llm`** — plugins get a first-class hook to make their own LLM requests through the active provider/credentials, no manual wiring. Plus `tool_override` flag for replacing built-in tools. ([#23194](https://github.com/NousResearch/hermes-agent/pull/23194), [#26759](https://github.com/NousResearch/hermes-agent/pull/26759))
- **Brave Search (free tier) + DuckDuckGo (DDGS) as web-search providers** — two new free search backends alongside Tavily / SearXNG / Exa. ([#21337](https://github.com/NousResearch/hermes-agent/pull/21337))
- **Sudo brute-force block + sudo-stdin/askpass DANGEROUS classification** — closes the `sudo -S` brute-force avenue; approval gates classify stdin-fed and askpass-stripped sudo invocations as dangerous. (salvages of #22194 + #21128) ([#23736](https://github.com/NousResearch/hermes-agent/pull/23736))
- **Provider rename — Alibaba Cloud → Qwen Cloud, picker reorder** — matches what the world calls it. Existing config keys still work. ([#24835](https://github.com/NousResearch/hermes-agent/pull/24835))
---
## 🪟 Windows — Native Support (Early Beta)
### Bootstrap & installer
- **Native Windows support (early beta)** — first-class native Windows path across CLI / gateway / TUI / tools ([#21561](https://github.com/NousResearch/hermes-agent/pull/21561))
- **PyPI wheel packaging — `pip install hermes-agent && hermes`** (salvage of #26350) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
- **Recognise Shift+Enter as a newline key** + Windows docs (salvage #21545) ([#22130](https://github.com/NousResearch/hermes-agent/pull/22130))
- **Preserve Ctrl+C for Windows foreground runs** (@helix4u) ([#22752](https://github.com/NousResearch/hermes-agent/pull/22752))
- **Stop spamming cwd-missing + tirith-spawn warnings on every terminal call** ([#26618](https://github.com/NousResearch/hermes-agent/pull/26618))
- **Use `--extra all` not `--all-extras`; drop lazy-covered extras from `[all]`** ([#24515](https://github.com/NousResearch/hermes-agent/pull/24515))
### Windows-specific fixes (40+ across cli / tools / gateway / curator / TUI)
A long tail of native-Windows fixes shipped alongside the beta — taskkill-based subprocess management, MinGit auto-install, Microsoft Store python stub detection, npm prefix handling, native PTY paths, signal handling differences, foreground process management, ANSI sequence handling, path normalization, file-locking semantics, and many more. Full list in commit log under `fix(windows)` / `feat(windows)` / `windows`.
---
## 🚀 Performance Wave
### Cold start
- **Cut ~19s from `hermes` cold start** — skills cache + lazy Feishu + no Nous HTTP at startup ([#22138](https://github.com/NousResearch/hermes-agent/pull/22138))
- **Skip eager plugin discovery on known built-in subcommands** ([#22120](https://github.com/NousResearch/hermes-agent/pull/22120))
- **Cache Nous auth + .env loads** — `hermes tools` All Platforms from 14s to <1.5s ([#25341](https://github.com/NousResearch/hermes-agent/pull/25341))
- **Skip welcome banner on `chat -q` single-query mode** ([#22904](https://github.com/NousResearch/hermes-agent/pull/22904))
- **Defer heavy google-cloud imports in google_chat to first adapter use** ([#22681](https://github.com/NousResearch/hermes-agent/pull/22681))
- **Defer QQAdapter and YuanbaoAdapter imports via PEP 562** ([#22790](https://github.com/NousResearch/hermes-agent/pull/22790))
- **Defer httpx import in teams to first webhook call** ([#22831](https://github.com/NousResearch/hermes-agent/pull/22831))
- **Defer fal_client import to first generation request** ([#22859](https://github.com/NousResearch/hermes-agent/pull/22859))
- **models.dev cache-first lookup, skip network when disk cache is fresh** ([#22808](https://github.com/NousResearch/hermes-agent/pull/22808))
- **Parallelize API connectivity checks in `hermes doctor` and disable IMDS** ([#22766](https://github.com/NousResearch/hermes-agent/pull/22766))
### Runtime
- **180x faster `browser_console` evaluations** — route through supervisor's persistent CDP WebSocket ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
- **Tune Telegram cadence + adaptive fast-path for short replies** (salvage of #10388) ([#23587](https://github.com/NousResearch/hermes-agent/pull/23587))
- **Accumulate length-continuation prefix via list+join** ([#26237](https://github.com/NousResearch/hermes-agent/pull/26237))
### Prompt caching
- **Cross-session 1h prefix cache for Claude on Anthropic / OpenRouter / Nous Portal** ([#23828](https://github.com/NousResearch/hermes-agent/pull/23828))
- **Hit prefix cache in background review fork** (salvage #17276 + #25427) ([#25434](https://github.com/NousResearch/hermes-agent/pull/25434))
---
## 📦 Installation & Distribution
### PyPI + supply-chain
- **PyPI wheel packaging — `pip install hermes-agent && hermes`** (salvage of #26350) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
- **Supply-chain advisory checker + lazy-install framework + tiered install fallback** ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
- **Use `--extra all` not `--all-extras`; drop lazy-covered extras from `[all]`** ([#24515](https://github.com/NousResearch/hermes-agent/pull/24515))
- **Skip browser download when system chromium exists** (@helix4u) ([#25317](https://github.com/NousResearch/hermes-agent/pull/25317))
### Nix
- **`extraDependencyGroups` for sealed venv extras** (@alt-glitch) ([#21817](https://github.com/NousResearch/hermes-agent/pull/21817))
- **Refresh npm lockfile hashes** — keeps Nix flake builds reproducible
### Docker
- **Bootstrap auth.json from env on first boot** ([#21880](https://github.com/NousResearch/hermes-agent/pull/21880))
- **Drop manual @hermes/ink build, rely on esbuild bundle** — slimmer image
### ACP / Zed
- **Zed ACP Registry integration** (salvage of #25908) ([#26079](https://github.com/NousResearch/hermes-agent/pull/26079))
- **Switch to uvx distribution, drop npm launcher** ([#26120](https://github.com/NousResearch/hermes-agent/pull/26120))
- **`hermes acp --setup-browser` bootstraps browser tools for registry installs** ([#26234](https://github.com/NousResearch/hermes-agent/pull/26234))
---
## 🏗️ Core Agent & Architecture
### Sessions & handoff
- **`/handoff` actually transfers the session live** ([#23395](https://github.com/NousResearch/hermes-agent/pull/23395))
- **Expose `HERMES_SESSION_ID` env var to agent tools** (@alt-glitch) ([#23847](https://github.com/NousResearch/hermes-agent/pull/23847))
### Goals (Ralph loop)
- **`/subgoal` — user-added criteria appended to active `/goal`** ([#25449](https://github.com/NousResearch/hermes-agent/pull/25449))
- **`/goal` checklist + /subgoal user controls** ([#23456](https://github.com/NousResearch/hermes-agent/pull/23456)) — rolled back in window ([#23813](https://github.com/NousResearch/hermes-agent/pull/23813)); /subgoal returned in simpler form via #25449
### Compression
- **Make `protect_first_n` configurable** ([#25447](https://github.com/NousResearch/hermes-agent/pull/25447))
### Verification
- **Per-turn file-mutation verifier footer** ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
### Stream retry
- **Log inner cause, upstream headers, bytes/elapsed on every drop** ([#23005](https://github.com/NousResearch/hermes-agent/pull/23005))
---
## 🤖 Models & Providers
### New providers
- **xAI Grok OAuth (SuperGrok Subscription) provider** ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534))
- **NovitaAI provider** (salvage #7219) (@kshitijk4poor) ([#25507](https://github.com/NousResearch/hermes-agent/pull/25507))
- **NVIDIA NIM billing origin header** (salvage #25211) ([#26585](https://github.com/NousResearch/hermes-agent/pull/26585))
### Provider work
- **OpenRouter Pareto Code router with `min_coding_score` knob** ([#22838](https://github.com/NousResearch/hermes-agent/pull/22838))
- **Optional codex app-server runtime for OpenAI/Codex models** ([#24182](https://github.com/NousResearch/hermes-agent/pull/24182))
- **Codex-runtime: retire wedged sessions + post-tool watchdog + OAuth refresh classify** ([#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
- **Codex-runtime: skip unavailable plugins during migration** ([#25437](https://github.com/NousResearch/hermes-agent/pull/25437))
- **Codex-runtime: de-dup `[plugins.X]` tables and stop leaking HERMES_HOME into config.toml** (#26250) (@kshitijk4poor) ([#26260](https://github.com/NousResearch/hermes-agent/pull/26260))
- **Pass `reasoning.effort` to xAI Responses API** ([#22807](https://github.com/NousResearch/hermes-agent/pull/22807))
- **Custom provider: prompt and persist explicit `api_mode`** ([#25068](https://github.com/NousResearch/hermes-agent/pull/25068))
- **Rename Alibaba Cloud → Qwen Cloud, reorder picker** ([#24835](https://github.com/NousResearch/hermes-agent/pull/24835))
- **Restore gpt-5.3-codex-spark for ChatGPT Pro** (salvage #18286 + #19530, fixes #16172) (@kshitijk4poor) ([#22991](https://github.com/NousResearch/hermes-agent/pull/22991))
- **Inject tool-use enforcement for GLM models** ([#24715](https://github.com/NousResearch/hermes-agent/pull/24715))
- **Use Nous Portal as model metadata authority** (@rob-maron) ([#24502](https://github.com/NousResearch/hermes-agent/pull/24502))
- **Unified `client=hermes-client-v<version>` tag on every Portal request** ([#24779](https://github.com/NousResearch/hermes-agent/pull/24779))
- **Prevent stale Ollama credentials after provider switch** (@kshitijk4poor) ([#21703](https://github.com/NousResearch/hermes-agent/pull/21703))
- **Auxiliary client: rotate pooled auth after quota failures** (salvage #22779) ([#22792](https://github.com/NousResearch/hermes-agent/pull/22792))
- **Auxiliary client: skip providers without credentials immediately** (#25395) ([#25487](https://github.com/NousResearch/hermes-agent/pull/25487))
- **Auth: send Nous refresh token via header** (@shannonsands) ([#21578](https://github.com/NousResearch/hermes-agent/pull/21578))
- **MiniMax: harden OAuth dashboard and runtime** ([#24165](https://github.com/NousResearch/hermes-agent/pull/24165))
### OpenAI-compatible proxy
- **Local OpenAI-compatible proxy for OAuth providers** — Codex / Aider / Cline can hit Claude Pro, ChatGPT Pro, SuperGrok ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))
---
## 📱 Messaging Platforms (Gateway)
### New platforms
- **LINE Messaging API platform plugin** ([#23197](https://github.com/NousResearch/hermes-agent/pull/23197))
- **SimpleX Chat platform plugin** (salvages #2558) ([#26232](https://github.com/NousResearch/hermes-agent/pull/26232))
### Microsoft Graph foundation
- **msgraph: add auth and client foundation** (salvage of #21408) ([#21922](https://github.com/NousResearch/hermes-agent/pull/21922))
- **msgraph: add webhook listener platform** (salvage of #21409) ([#21969](https://github.com/NousResearch/hermes-agent/pull/21969))
- **teams-pipeline: add plugin runtime and operator cli** (salvage of #21410) ([#22007](https://github.com/NousResearch/hermes-agent/pull/22007))
- **teams: add pipeline outbound delivery via existing adapter** (salvage of #21411) ([#22024](https://github.com/NousResearch/hermes-agent/pull/22024))
### Cross-platform
- **Per-platform admin/user split for slash commands** (salvage of #4443) ([#23373](https://github.com/NousResearch/hermes-agent/pull/23373))
- **Forensics on signal handling — non-blocking diag, per-phase timing, stale-unit warning** ([#23285](https://github.com/NousResearch/hermes-agent/pull/23285))
- **Keep gateway running when platforms fail; add per-platform circuit breaker + `/platform`** ([#26600](https://github.com/NousResearch/hermes-agent/pull/26600))
- **Wire `clarify` tool with inline keyboard buttons on Telegram** ([#24199](https://github.com/NousResearch/hermes-agent/pull/24199))
- **Add `chat_id` to `hook_ctx` for message source tracking** ([#24710](https://github.com/NousResearch/hermes-agent/pull/24710))
### Telegram
- **Native draft streaming via `sendMessageDraft` (Bot API 9.5+)** (salvage of #3412) ([#23512](https://github.com/NousResearch/hermes-agent/pull/23512))
- **Stream Telegram edits safely** — salvage of #22264 (@kshitijk4poor) ([#22518](https://github.com/NousResearch/hermes-agent/pull/22518))
- **Telegram notification mode** (salvage #22772) ([#22793](https://github.com/NousResearch/hermes-agent/pull/22793))
- **Telegram guest mention mode** (@kshitijk4poor) ([#22759](https://github.com/NousResearch/hermes-agent/pull/22759))
- **Split-and-deliver oversized edits instead of silent truncation** (salvage of #19537) ([#23576](https://github.com/NousResearch/hermes-agent/pull/23576))
- **Preserve DM topic routing via reply fallback** (salvage #22053) (@kshitijk4poor) ([#22410](https://github.com/NousResearch/hermes-agent/pull/22410))
- **Pass `source.thread_id` explicitly on auto-reset notice** (carve-out of #7404) ([#23440](https://github.com/NousResearch/hermes-agent/pull/23440))
### Discord
- **Render clarify choices as buttons** ([#25485](https://github.com/NousResearch/hermes-agent/pull/25485))
- **Channel history backfill — default on, broadened scope** ([#25984](https://github.com/NousResearch/hermes-agent/pull/25984))
- **`thread_require_mention` for multi-bot threads** (salvage #25313) ([#25445](https://github.com/NousResearch/hermes-agent/pull/25445))
### Slack
- **Support `!cmd` as alternate prefix for slash commands in threads** ([#25355](https://github.com/NousResearch/hermes-agent/pull/25355))
### WhatsApp
- **Surface quoted reply metadata from Baileys** (#25398) ([#25489](https://github.com/NousResearch/hermes-agent/pull/25489))
### Feishu / Google Chat / others
- **Feishu: native update prompt cards** (@kshitijk4poor) ([#22448](https://github.com/NousResearch/hermes-agent/pull/22448))
- **Google Chat: repair setup prompt imports** (@helix4u) ([#22038](https://github.com/NousResearch/hermes-agent/pull/22038))
- **Google Chat: honor relay-declared sender_type** (salvage of #22107) (@kshitijk4poor) ([#22432](https://github.com/NousResearch/hermes-agent/pull/22432))
- **LINE: use `build_source` instead of nonexistent `create_source`** ([#24717](https://github.com/NousResearch/hermes-agent/pull/24717))
- **Add `weixin, and more` to gateway docs** (salvage of #21063 by @wuwuzhijing)
---
## 🖥️ CLI & TUI
### CLI
- **Show YOLO mode warning in banner and status bar** ([#26238](https://github.com/NousResearch/hermes-agent/pull/26238))
- **Confirm prompt for destructive slash commands** (#4069) ([#22687](https://github.com/NousResearch/hermes-agent/pull/22687))
- **`docker_extra_args` + `display.timestamps`** ([#23599](https://github.com/NousResearch/hermes-agent/pull/23599))
- **Delegate tool: show user's actual concurrency / spawn-depth limits in description** ([#22694](https://github.com/NousResearch/hermes-agent/pull/22694))
### TUI
- **`/sessions` slash command for browsing and resuming previous sessions** (@austinpickett) ([#20805](https://github.com/NousResearch/hermes-agent/pull/20805))
- **Segment turns with rule above non-first user msgs; trim ticker dead space** (@OutThisLife) ([#21846](https://github.com/NousResearch/hermes-agent/pull/21846))
- **Support attaching to an existing gateway** (@OutThisLife) ([#21978](https://github.com/NousResearch/hermes-agent/pull/21978))
- **Resolve markdown links to readable page titles** (@OutThisLife) ([#24013](https://github.com/NousResearch/hermes-agent/pull/24013))
- **Width-aware markdown table rendering with vertical fallback** (@alt-glitch) ([#26195](https://github.com/NousResearch/hermes-agent/pull/26195))
- **Keep Ink displayCursor in sync with fast-echo writes so cursor stops drifting** (@OutThisLife) ([#26717](https://github.com/NousResearch/hermes-agent/pull/26717))
- **Allow transcript scroll + Esc during approval/clarify/confirm prompts** (@OutThisLife) ([#26414](https://github.com/NousResearch/hermes-agent/pull/26414))
- **Preserve session when switching personality** (@austinpickett) ([#20942](https://github.com/NousResearch/hermes-agent/pull/20942))
- **Skip native safety net on OSC52-capable terminals** (@benbarclay) ([#20954](https://github.com/NousResearch/hermes-agent/pull/20954))
### Dashboard / GUI
- **Route embedded TUI through dashboard gateway** (@OutThisLife) ([#21979](https://github.com/NousResearch/hermes-agent/pull/21979))
- **Hide token/cost analytics behind config flag (default off)** ([#25438](https://github.com/NousResearch/hermes-agent/pull/25438))
- **Fix Langfuse observability — trace I/O, tool outputs, placeholder credentials** (closes #22342, #22763) (@kshitijk4poor) ([#26320](https://github.com/NousResearch/hermes-agent/pull/26320))
- **MiniMax 'Login' button launched Claude OAuth** (salvage #22849) ([#24058](https://github.com/NousResearch/hermes-agent/pull/24058))
- **Update cron modals** (@austinpickett) ([#25985](https://github.com/NousResearch/hermes-agent/pull/25985))
- **Analytics: prevent silent token loss and add Claude 4.54.7 pricing** (@austinpickett) ([#21455](https://github.com/NousResearch/hermes-agent/pull/21455))
---
## 🔧 Tools & Capabilities
### Vision & video
- **`vision_analyze` returns pixels to vision-capable models** ([#22955](https://github.com/NousResearch/hermes-agent/pull/22955))
- **Unified `video_generate` with pluggable provider backends** ([#25126](https://github.com/NousResearch/hermes-agent/pull/25126))
- **`image_gen`: actionable setup message when no FAL backend is reachable** ([#26222](https://github.com/NousResearch/hermes-agent/pull/26222))
### Computer use
- **`computer_use` cua-driver backend + focus-safe ops + non-Anthropic provider fix** (re-salvage #16936) ([#21967](https://github.com/NousResearch/hermes-agent/pull/21967))
- **Refresh cua-driver on `hermes update` + add `install --upgrade`** ([#24063](https://github.com/NousResearch/hermes-agent/pull/24063))
### LSP & write-time diagnostics
- **Semantic diagnostics from real language servers in `write_file`/`patch`** ([#24168](https://github.com/NousResearch/hermes-agent/pull/24168))
- **Shift baseline diagnostics into post-edit coordinates** ([#25978](https://github.com/NousResearch/hermes-agent/pull/25978))
### Search & web
- **Brave Search (free tier) and DDGS search providers** ([#21337](https://github.com/NousResearch/hermes-agent/pull/21337))
- **Bearer auth header for Tavily `/crawl` endpoint** ([#24658](https://github.com/NousResearch/hermes-agent/pull/24658))
### X (Twitter)
- **Gated `x_search` tool with OAuth-or-API-key auth** ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))
### Browser
- **Route `browser_console` eval through supervisor's persistent CDP WS (180x faster)** ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
- **Support externally managed Camofox sessions** ([#24499](https://github.com/NousResearch/hermes-agent/pull/24499))
### MCP
- **`supports_parallel_tool_calls` for MCP servers** (salvage of #9944) ([#26825](https://github.com/NousResearch/hermes-agent/pull/26825))
- **Codex preset for Codex CLI MCP server** (salvage #22663) ([#22679](https://github.com/NousResearch/hermes-agent/pull/22679))
- **Stop retrying initial MCP auth failures** (#25624) ([#25776](https://github.com/NousResearch/hermes-agent/pull/25776))
### Google Workspace
- **Drive write ops + Docs/Sheets create/append** ([#21895](https://github.com/NousResearch/hermes-agent/pull/21895))
### Per-turn verifier
- **Per-turn file-mutation verifier footer** ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
---
## 🧩 Kanban (Multi-Agent)
- **`specify` — auxiliary LLM fleshes out triage tasks** ([#21435](https://github.com/NousResearch/hermes-agent/pull/21435))
- **Orchestrator board tools — `kanban_list` + `kanban_unblock`** (carve-out of #20568) ([#23012](https://github.com/NousResearch/hermes-agent/pull/23012))
- **`stranded_in_ready` diagnostic for unclaimed tasks** ([#23578](https://github.com/NousResearch/hermes-agent/pull/23578))
- **Dashboard batch QOL upgrade** (salvage of #23240) ([#23550](https://github.com/NousResearch/hermes-agent/pull/23550))
- **Tooltips and docs link across dashboard** ([#21541](https://github.com/NousResearch/hermes-agent/pull/21541))
- **Dedupe notifier delivery via atomic claim + rewind on failure** (salvage #22558) ([#23401](https://github.com/NousResearch/hermes-agent/pull/23401))
- **Keep notifier subscriptions alive across retry cycles** (salvage #21398) ([#23423](https://github.com/NousResearch/hermes-agent/pull/23423))
- **Drop caller-controlled author override in `kanban_comment`** (salvage of #22109) (@kshitijk4poor) ([#22435](https://github.com/NousResearch/hermes-agent/pull/22435))
- **Sanitize comment author rendering in `build_worker_context`** ([#22769](https://github.com/NousResearch/hermes-agent/pull/22769))
---
## 🧠 Plugins & Extension
### Plugin surface
- **Run any LLM call from inside a plugin via `ctx.llm`** ([#23194](https://github.com/NousResearch/hermes-agent/pull/23194))
- **`tool_override` flag for replacing built-in tools** (closes #11049) ([#26759](https://github.com/NousResearch/hermes-agent/pull/26759))
- **`standalone_sender_fn` for out-of-process cron delivery** (@kshitijk4poor) ([#22461](https://github.com/NousResearch/hermes-agent/pull/22461))
- **`HERMES_PLUGINS_DEBUG=1` surfaces plugin discovery logs** ([#22684](https://github.com/NousResearch/hermes-agent/pull/22684))
- **Hindsight-client as optional dependency** (@alt-glitch) ([#21818](https://github.com/NousResearch/hermes-agent/pull/21818))
### Profile & distribution
- **Shareable profile distributions via git** ([#20831](https://github.com/NousResearch/hermes-agent/pull/20831))
---
## ⏰ Cron
- **Routing intent — `deliver=all` fans out to every connected channel** ([#21495](https://github.com/NousResearch/hermes-agent/pull/21495))
- **Support name-based lookup for job operations** ([#26231](https://github.com/NousResearch/hermes-agent/pull/26231))
- **Blank Cron dashboard tab + partial-record crashes** (salvage #21042 + #22330) (@kshitijk4poor) ([#22389](https://github.com/NousResearch/hermes-agent/pull/22389))
- **Do not seed `HERMES_SESSION_*` contextvars from cron origin** (salvage of #22356) (@kshitijk4poor) ([#22382](https://github.com/NousResearch/hermes-agent/pull/22382))
- **Scan assembled prompt including skill content for prompt injection** (#3968)
---
## 🧩 Skills Ecosystem
### Skills Hub
- **`hermes-skills/huggingface` as a trusted default tap** (closes #2549) ([#26219](https://github.com/NousResearch/hermes-agent/pull/26219))
- **Show per-skill pages in the left sidebar** ([#26646](https://github.com/NousResearch/hermes-agent/pull/26646))
- **Richer info panels on the Skills Hub** ([#22905](https://github.com/NousResearch/hermes-agent/pull/22905))
- **Refuse `skill_view` name collisions instead of guessing** (closes #6136 @polkn)
### Curator
- **Show rename map in user-visible summary** ([#22910](https://github.com/NousResearch/hermes-agent/pull/22910))
- **Hint at `hermes curator pin` in the rename block** ([#23212](https://github.com/NousResearch/hermes-agent/pull/23212))
### New optional skills
- **Hyperliquid** — perp/spot trading via SDK + REST (salvage of #1952) ([#23583](https://github.com/NousResearch/hermes-agent/pull/23583))
- **Yahoo Finance** market data ([#23590](https://github.com/NousResearch/hermes-agent/pull/23590))
- **api-testing** (REST/GraphQL debug, salvages #1800) ([#23582](https://github.com/NousResearch/hermes-agent/pull/23582))
- **Unified EVM multi-chain skill** (salvages #25291 + #2010 + folds in base/) ([#25299](https://github.com/NousResearch/hermes-agent/pull/25299))
- **darwinian-evolver** ([#26760](https://github.com/NousResearch/hermes-agent/pull/26760))
- **osint-investigation** (closes #355) ([#26729](https://github.com/NousResearch/hermes-agent/pull/26729))
- **pinggy-tunnel** ([#26765](https://github.com/NousResearch/hermes-agent/pull/26765))
- **watchers** — RSS / HTTP JSON / GitHub polling via cron no-agent ([#21881](https://github.com/NousResearch/hermes-agent/pull/21881))
- **Notion overhaul for the Developer Platform** (May 2026) ([#26612](https://github.com/NousResearch/hermes-agent/pull/26612))
---
## 🔒 Security & Reliability
### Security hardening
- **Sudo brute-force block + sudo-stdin/askpass DANGEROUS** (salvage of #22194 + #21128) (@kshitijk4poor) ([#23736](https://github.com/NousResearch/hermes-agent/pull/23736))
- **Drop caller-controlled author override in `kanban_comment`** (salvage of #22109) (@kshitijk4poor) ([#22435](https://github.com/NousResearch/hermes-agent/pull/22435))
- **Cover remaining SSRF fetch paths in skills-hub** (salvage #22804) ([#22843](https://github.com/NousResearch/hermes-agent/pull/22843))
- **Use credential_pool for custom endpoint model listing probes** (salvage #22810) ([#22842](https://github.com/NousResearch/hermes-agent/pull/22842))
- **Require dashboard auth for plugin API routes** (salvage #19541) ([#23220](https://github.com/NousResearch/hermes-agent/pull/23220))
- **Sanitize env and redact output in quick commands + remove write-only `_pending_messages`** ([#23584](https://github.com/NousResearch/hermes-agent/pull/23584))
- **Reduce unnecessary `shell=True` in subprocess calls** ([#25149](https://github.com/NousResearch/hermes-agent/pull/25149))
- **Sanitize Google Chat sender_type from relay** (salvage of #22107) (@kshitijk4poor) ([#22432](https://github.com/NousResearch/hermes-agent/pull/22432))
- **Supply-chain advisory checker** ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
- **Rewrite security policy around OS-level isolation as the boundary** (@jquesnelle) ([#20317](https://github.com/NousResearch/hermes-agent/pull/20317))
- **Remove public security advisory page** ([#24253](https://github.com/NousResearch/hermes-agent/pull/24253))
### Reliability — notable bug closures
- **SQLite: fall back to `journal_mode=DELETE` on NFS/SMB/FUSE** (fixes `/resume` on network mounts) (@kshitijk4poor) ([#22043](https://github.com/NousResearch/hermes-agent/pull/22043))
- **Codex-runtime: retire wedged sessions + post-tool watchdog + OAuth refresh classify** ([#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
- **Codex-runtime: de-dup `[plugins.X]` tables and stop leaking HERMES_HOME** (#26250) (@kshitijk4poor) ([#26260](https://github.com/NousResearch/hermes-agent/pull/26260))
- **Daytona: migrate legacy-sandbox lookup to cursor-based `list()`** ([#24587](https://github.com/NousResearch/hermes-agent/pull/24587))
- **MCP: stop retrying initial MCP auth failures** (#25624) ([#25776](https://github.com/NousResearch/hermes-agent/pull/25776))
- **Gateway: enable text-intercept for multi-choice clarify fallback** (#25587) ([#25778](https://github.com/NousResearch/hermes-agent/pull/25778))
- **Gateway: keep running when platforms fail; per-platform circuit breaker + `/platform`** ([#26600](https://github.com/NousResearch/hermes-agent/pull/26600))
- **Delegate: salvage #21933 JSON-string batch + diagnostic logging** (@kshitijk4poor) ([#22436](https://github.com/NousResearch/hermes-agent/pull/22436))
- **Profiles+banner: exclude infrastructure from `--clone-all` + fix stale update-check repo resolution** (@kshitijk4poor) ([#22475](https://github.com/NousResearch/hermes-agent/pull/22475))
- **ACP: inline file attachment resources** (salvage #21400 + image support) ([#21407](https://github.com/NousResearch/hermes-agent/pull/21407))
- **CI: unblock shared PR checks** (@stephenschoettler) ([#21012](https://github.com/NousResearch/hermes-agent/pull/21012), [#25957](https://github.com/NousResearch/hermes-agent/pull/25957))
### Notable reverts in window
- **`/goal` checklist + /subgoal feature stack** — rolled back ([#23813](https://github.com/NousResearch/hermes-agent/pull/23813)); `/subgoal` returned in simpler form via [#25449](https://github.com/NousResearch/hermes-agent/pull/25449)
- **Scrollback box width clamp** (#25975) rolled back to restore full-width borders ([#26163](https://github.com/NousResearch/hermes-agent/pull/26163))
- **`fix(cli): tolerate unreadable dirs when building systemd PATH`** rolled back
---
## 🌍 i18n
- **Localize all gateway commands + web dashboard, add 8 new locales (16 total)** ([#22914](https://github.com/NousResearch/hermes-agent/pull/22914))
---
## 📚 Documentation
- **Repair Voice & TTS provider table** (@nightcityblade, fixes #24101) ([#24138](https://github.com/NousResearch/hermes-agent/pull/24138))
- **Show per-skill pages in the left sidebar** ([#26646](https://github.com/NousResearch/hermes-agent/pull/26646))
- **Mention Weixin in gateway help and docstrings** (salvage of #21063 by @wuwuzhijing)
- **Richer info panels on the Skills Hub** ([#22905](https://github.com/NousResearch/hermes-agent/pull/22905))
- Many more doc updates across providers, platforms, skills, Windows install paths, and dashboard.
---
## 🧪 Testing & CI
- **Unblock shared PR checks** (@stephenschoettler) ([#21012](https://github.com/NousResearch/hermes-agent/pull/21012))
- **Stabilize shared test state after 21012** (@stephenschoettler) ([#25957](https://github.com/NousResearch/hermes-agent/pull/25957))
- A long tail of test additions for platforms, providers, plugins, and edge cases — 8 explicit `test:` PRs plus ~250 fix PRs that also added regression coverage.
---
## 👥 Contributors
### Core
- @teknium1 — release lead, architecture, ~406 PRs merged in window
### Top community contributors
- **@kshitijk4poor** — 38 PRs · Telegram cadence/streaming/topic routing, security hardening (sudo, SSRF, kanban_comment, dashboard auth), codex-runtime hygiene, NovitaAI provider, profile/banner fixes, Feishu update cards, gateway QOL across the board
- **@alt-glitch** — 13 PRs · Markdown-table TUI rendering, `HERMES_SESSION_ID` env var, hindsight-client optional dep, Nix `extraDependencyGroups`
- **@OutThisLife** (Brooklyn Nicholson) — 12 PRs · TUI turn segmentation, attach-to-gateway, markdown link titles, embedded TUI via dashboard gateway, Ink cursor sync, scroll/Esc during prompts
- **@austinpickett** — 8 PRs · `/sessions` slash command, personality switching preserves session, cron modals, dashboard analytics
- **@helix4u** — 5 PRs · Google Chat setup, browser install skip on system chromium, Windows Ctrl+C preservation
- **@rob-maron** — 4 PRs · Nous Portal as model metadata authority, provider polish
- **@stephenschoettler** — 3 PRs · CI stabilization
- **@ethernet8023** — 3 PRs · platform/gateway work
### All contributors (alphabetical)
@02356abc, @0xbyt4, @0xharryriddle, @1000Delta, @1RB, @29206394, @A-kamal, @aashizpoudel, @Abd0r,
@adybag14-cyber, @AgentArcLab, @ahmedbadr3, @AhmetArif0, @alblez, @Alex-yang00, @ALIYILD, @AllynSheep,
@alt-glitch, @am423, @amathxbt, @amethystani, @ArecaNon, @Arkmusn, @askclaw-vesper, @AsoTora, @austinpickett,
@aydnOktay, @ayushere, @baocin, @Bartok9, @benbarclay, @BennetYrWang, @Bihruze, @binhnt92, @briandevans,
@brooklynnicholson, @btorresgil, @buntingszn, @CalmProton, @chrisworksai, @CoinTheHat, @dandacompany, @Dangooy,
@DanielLSM, @David-0x221Eight, @ddupont808, @dhruv-saxena, @diablozzc, @dlkakbs, @dmahan93, @dmnkhorvath,
@domtriola, @donrhmexe, @Dusk1e, @eloklam, @emozilla, @ephron-ren, @erenkarakus, @EthanGuo-coder,
@ethernet8023, @evgyur, @explainanalyze, @fahdad, @fr33d3m0n, @Freeman-Consulting, @freqyfreqy, @Frowtek,
@fu576, @github-actions[bot], @gnanirahulnutakki, @GodsBoy, @guglielmofonda, @Gutslabs, @hanzckernel,
@heathley, @hekaru-agent, @helix4u, @HenkDz, @HiddenPuppy, @hllqkb, @hrygo, @HuangYuChuh, @Hugo-SEQUIER, @HxT9,
@iacker, @InB4DevOps, @isaachuangGMICLOUD, @iuyup, @Jaaneek, @jackey8616, @jackjin1997, @Jaggia, @jak983464779,
@jelrod27, @jethac, @JithendraNara, @johnisag, @Julientalbot, @Jwd-gity, @kallidean, @keyuyuan, @kfa-ai,
@kidonng, @KiraKatana, @kjames2001, @konsisumer, @Korkyzer, @kshitijk4poor, @KvnGz, @lars-hagen, @leehack,
@leepoweii, @LeonSGP43, @li0near, @libo1106, @liquidchen, @littlewwwhite, @liuhao1024, @liyoungc, @luandiasrj,
@luoyuctl, @luyao618, @magic524, @mbac, @McClean, @memosr, @Mibayy, @ming1523, @mizgyo, @mrshu, @ms-alan,
@MustafaKara7, @nederev, @nicoechaniz, @nidhi-singh02, @nightcityblade, @nik1t7n, @Ninso112, @NivOO5,
@novax635, @nv-kasikritc, @oferlaor, @oswaldb22, @outdoorsea, @oxngon, @PaTTeeL, @pearjelly, @pefontana,
@perng, @PhilipAD, @phuongvm, @polkn, @Prasanna28Devadiga, @princepal9120, @pty819, @purzbeats, @Quarkex,
@quocanh261997, @qWaitCrypto, @Qwinty, @rahimsais, @raymaylee, @ReqX, @rewbs, @RhombusMaximus, @rob-maron,
@Ruzzgar, @ryptotalent, @Sanjays2402, @shannonsands, @shaun0927, @SiliconID, @silv-mt-holdings, @simpolism,
@smwbev, @soichiyo, @sprmn24, @steezkelly, @stephenschoettler, @Sylw3ster, @szymonclawd, @teyrebaz33,
@Tianyu199509, @Tranquil-Flow, @TreyDong, @TurgutKural, @tw2818, @tymrtn, @uzunkuyruk, @v1b3coder,
@vanthinh6886, @VinceZcrikl, @vKongv, @vominh1919, @voteblake, @VTRiot, @wali-reheman, @wesleysimplicio,
@wilsen0, @WorldWriter, @worlldz, @wuli666, @wuwuzhijing, @Wysie, @XiaoXiao0221, @xieNniu, @xxxigm, @yehuosi,
@ygd58, @yifengingit, @yuga-hashimoto, @zccyman, @ZeterMordio, @Zhekinmaksim, @zhengyn0001
Also: @Nagatha (Claude Opus 4.7).
---
**Full Changelog**: [v2026.5.7...v2026.5.16](https://github.com/NousResearch/hermes-agent/compare/v2026.5.7...v2026.5.16)

View File

@@ -1,651 +0,0 @@
# Hermes Agent v0.15.0 (v2026.5.28)
**Release Date:** May 28, 2026
**Since v0.14.0:** 1,302 commits · 747 merged PRs · 1,746 files changed · 282,712 insertions · 36,699 deletions · 560+ issues closed (15 P0, 65 P1, 19 security-tagged) · 321 community contributors (including co-authors)
> **The Velocity Release.** Hermes gets dramatically faster — to start, to run, to ship work, and to grow. The 16,083-line `run_agent.py` collapses to 3,821 (-76%) across 14 cohesive `agent/*` modules. Kanban grew into a real multi-agent platform across 104 PRs — orchestrator auto-decomposition, swarm topology, scheduled tasks, worktree-per-task, per-task model overrides. The cold-start perf wave keeps going: another second shaved off launch, 47% fewer per-conversation function calls, `hermes --version` flipping the head-to-head benchmark against Codex CLI. `session_search` is 4,500× faster and free now. Promptware defense lands against Brainworm-class attacks. Bitwarden Secrets Manager replaces N per-provider API keys with one bootstrap token. Skill bundles let one slash command load a whole workflow. The Ink TUI gets a multi-session orchestrator. Two new image_gen providers (Krea 2 Medium + Large, FAL ported to plugin), the Nous-approved MCP catalog with an interactive picker, an OpenHands orchestration skill, ntfy as the 23rd messaging platform, and a deep xAI integration round (Web Search plugin, xai-oauth `hermes proxy` upstream, retired-May-15 model detection + `hermes migrate xai`, natural TTS speech-tag pauses, base_url leak guard, OpenAI-style execution guidance for Grok). 15 P0 + 65 P1 closures alongside.
---
## ✨ Highlights
- **The Big Refactor — `run_agent.py` is no longer 16,000 lines** — The file at the heart of Hermes — the agent conversation loop — has been reduced from 16,083 lines to 3,821 (-76%), with the extracted code redistributed across 14 cohesive modules under `agent/`. Behavior is unchanged: every extraction keeps a thin forwarder on `AIAgent`, every test patch path still works, every external caller is compatible. The reason you care: future Hermes development moves faster, plugin authors can finally grep the codebase, and the file that took 90 seconds to load in your editor opens in a blink. ([#27248](https://github.com/NousResearch/hermes-agent/pull/27248))
- **Kanban grew into a real multi-agent platform — 104 PRs end to end** — Triage auto-decomposes one task into a tree of sub-tasks. `hermes kanban swarm` creates a full Swarm v1 graph in one command — root, parallel workers, gated verifier, gated synthesizer, shared blackboard. Tasks support per-task model overrides (cheap models for boilerplate, expensive ones for hard sub-tasks), board-level default workdirs, per-task worktree paths and branches, scheduled start times, configurable claim TTL, retry fingerprinting, stale-task detection, respawn guards, and a drag-to-delete trash zone. Workers report through `/workers/active`, `/runs/{id}`, and `/inspect` endpoints. ([#27572](https://github.com/NousResearch/hermes-agent/pull/27572), [#28443](https://github.com/NousResearch/hermes-agent/pull/28443), [#28364](https://github.com/NousResearch/hermes-agent/pull/28364), [#28394](https://github.com/NousResearch/hermes-agent/pull/28394), [#28462](https://github.com/NousResearch/hermes-agent/pull/28462), [#28384](https://github.com/NousResearch/hermes-agent/pull/28384), [#28467](https://github.com/NousResearch/hermes-agent/pull/28467), [#28455](https://github.com/NousResearch/hermes-agent/pull/28455), [#28452](https://github.com/NousResearch/hermes-agent/pull/28452), [#28432](https://github.com/NousResearch/hermes-agent/pull/28432), [#28468](https://github.com/NousResearch/hermes-agent/pull/28468), [#28420](https://github.com/NousResearch/hermes-agent/pull/28420))
- **Cold-start perf wave keeps going — another second saved, 47% fewer per-turn function calls** — Three new optimization rounds: defer `openai._base_client` import (-240ms / -17MB on every CLI invocation), hot-path optimizations cut 47% of per-conversation function calls (399k → 213k for 31-turn chat), defer compression-feasibility check (-170 to -290ms on every agent construction), adaptive subprocess polling (-195ms per tool call, 1+ second per turn). Termux cold start drops from 2.9s to 0.8s. `hermes --version` cold drops 63% (701ms → 258ms), flipping the head-to-head benchmark against Codex CLI from 5/11 wins to 6/11. ([#28864](https://github.com/NousResearch/hermes-agent/pull/28864), [#28866](https://github.com/NousResearch/hermes-agent/pull/28866), [#28957](https://github.com/NousResearch/hermes-agent/pull/28957), [#29006](https://github.com/NousResearch/hermes-agent/pull/29006), [#29419](https://github.com/NousResearch/hermes-agent/pull/29419), [#30121](https://github.com/NousResearch/hermes-agent/pull/30121), [#30609](https://github.com/NousResearch/hermes-agent/pull/30609), [#31968](https://github.com/NousResearch/hermes-agent/pull/31968))
- **`session_search` rebuilt — no LLM, no cost, 4,500× faster** — The old `session_search` was an aux-LLM-powered tool that cost ~$0.30/call and took ~30 seconds to summarize three sessions, sometimes confabulating when the right session wasn't even in the FTS5 hit list. The new shape is one tool with three modes (discovery, scroll, browse) inferred from which args are set — no `mode` parameter, no aux-LLM, no config knob, no companion skill. Discovery is ~20ms instead of ~90s; scroll is ~1ms. Searching your past sessions for context is now free and instant. ([#27590](https://github.com/NousResearch/hermes-agent/pull/27590))
- **Promptware defense — Brainworm-class attacks blocked at three chokepoints** — Inspired by recent Brainworm / Promptware Kill Chain research (Origin HQ, arxiv 2601.09625), Hermes now defends the context window against prompt-injection attacks that try to hijack the agent via tool output, recalled memory, or stored skills. Single source of truth (`tools/threat_patterns.py`) with ~15 new Brainworm/C2 patterns; recalled memory is scanned at load time; tool results get delimiter markers so a malicious file or remote service can't impersonate Hermes' own system content. Paired with a new `security-guidance` plugin that pattern-matches dangerous code writes. ([#32269](https://github.com/NousResearch/hermes-agent/pull/32269), [#33131](https://github.com/NousResearch/hermes-agent/pull/33131), [#9151](https://github.com/NousResearch/hermes-agent/pull/9151))
- **Bitwarden Secrets Manager — one bootstrap token replaces every per-provider API key** — Stop keeping plaintext API keys in `~/.hermes/.env`. Install Bitwarden Secrets Manager (`bws` auto-installs lazily on first use), point Hermes at it with one bootstrap token (`BWS_ACCESS_TOKEN`), and every credential you need comes from Bitwarden at startup. Rotate a key in the Bitwarden web app and the rotation actually takes effect — Bitwarden defaults to source-of-truth so its values overwrite matching env vars on startup. Flip `secrets.bitwarden.override_existing: false` to invert. EU Cloud and self-hosted Bitwarden server URLs supported. Detected credentials are now labeled with their source so you can see at a glance which keys came from Bitwarden vs. the local env. ([#30035](https://github.com/NousResearch/hermes-agent/pull/30035), [#31378](https://github.com/NousResearch/hermes-agent/pull/31378), [#30364](https://github.com/NousResearch/hermes-agent/pull/30364))
- **ntfy as the 23rd messaging platform — push notifications without an account** — ntfy is the self-hostable push-notification service with no signup, no API key, just a topic URL. Hermes now adapts to it as a platform plugin (zero edits to core), so your agent can send you push notifications from any cron job, kanban task completion, or chat `send_message` — to your phone, your watch, your desktop, your homelab. (salvages [#30625](https://github.com/NousResearch/hermes-agent/pull/30625) → originally [#4043](https://github.com/NousResearch/hermes-agent/pull/4043)) ([#30867](https://github.com/NousResearch/hermes-agent/pull/30867))
- **Skill bundles — `/<name>` loads multiple skills at once** — A skill bundle is a named group of skills that loads them all together with one slash command. Set up your "writing day" bundle (humanizer + ideation + obsidian + youtube-content) and `/writing-day` activates all four for the session. Skills Hub now has health checks, a freshness badge, and a watchdog cron. Three new optional skills land: `code-wiki` (Karpathy's LLM-Wiki, persistent indexed dev wiki), `openhands` (delegate to OpenHands for parallel coding agents), and `web-pentest` (OWASP-style web pentest recipes). ([#28373](https://github.com/NousResearch/hermes-agent/pull/28373), [#32345](https://github.com/NousResearch/hermes-agent/pull/32345), [#32240](https://github.com/NousResearch/hermes-agent/pull/32240), [#32261](https://github.com/NousResearch/hermes-agent/pull/32261), [#32265](https://github.com/NousResearch/hermes-agent/pull/32265))
- **TUI session orchestrator — multiple live sessions in one TUI window** — The Ink TUI gained an active-session switcher overlay. List, switch between, refresh, and close multiple live process-local sessions without leaving the TUI; dispatch a new session with a session-scoped model picker. Plus a wave of TUI polish — mouse-tracking DEC mode presets, scrollback preservation across branches and termux, slash-dropdown fixes, x.com link rendering, and CJK / IME input rendering improvements. (salvages [#27642](https://github.com/NousResearch/hermes-agent/pull/27642)) ([#32980](https://github.com/NousResearch/hermes-agent/pull/32980), [#30084](https://github.com/NousResearch/hermes-agent/pull/30084))
- **Two new image_gen providers — Krea 2 Medium + Large, FAL ported to plugin** — Krea joins the image_gen lineup as a built-in plugin: `Krea 2 Medium` ($0.03) and `Krea 2 Large` ($0.06), auto-discovered, selectable via `hermes tools` → Image Generation → Krea. Available through both the native Krea plugin and the FAL.ai catalog. The FAL.ai backend got pulled out of the monolithic image-generation tool into `plugins/image_gen/fal/`, completing the four-way architectural parity already established by web, browser, and video_gen — new image providers are now one file, not a fork. ([#33236](https://github.com/NousResearch/hermes-agent/pull/33236), [#30380](https://github.com/NousResearch/hermes-agent/pull/30380), [#33506](https://github.com/NousResearch/hermes-agent/pull/33506))
- **Nous-approved MCP catalog with interactive picker** — A curated catalog of Nous-vetted MCP servers, mirroring the optional-skills shape. Run `hermes mcp` and you get an interactive picker; install with one keystroke, credentials prompted at install time and written to `~/.hermes/.env`. Ships with the n8n manifest first. Closes the discovery gap that left users hunting GitHub for trusted MCP servers. ([#30870](https://github.com/NousResearch/hermes-agent/pull/30870))
- **OpenHands orchestration skill** — A new optional skill under `optional-skills/autonomous-ai-agents/openhands/` lets the agent delegate coding tasks to the OpenHands CLI alongside `claude-code`, `codex`, and `opencode`. OpenHands is the model-agnostic member of that family — any LiteLLM-supported provider works (OpenAI, Anthropic, OpenRouter, your own), so you can route a sub-task to the cheapest model that can finish it. Drop-in worker for kanban swarms and `/delegate` flows. (closes [#477](https://github.com/NousResearch/hermes-agent/issues/477)) ([#32261](https://github.com/NousResearch/hermes-agent/pull/32261))
- **Deep xAI integration round — Web Search plugin, OAuth proxy upstream, May 15 retirement detection, natural TTS, security hardening** — Six interlocking xAI improvements:
- **xAI Web Search** lands as a `plugins/web/xai/` provider, slots alongside Brave / Tavily / Exa / SearXNG / DDGS / Firecrawl — reuses your existing Grok OAuth or `XAI_API_KEY` credentials, no new env vars. ([#29042](https://github.com/NousResearch/hermes-agent/pull/29042))
- **`hermes proxy` gains an xAI upstream** — your local OpenAI-compatible endpoint can now be backed by SuperGrok OAuth, no PKCE-refresh code to write in your client. ([#28356](https://github.com/NousResearch/hermes-agent/pull/28356))
- **May 15 model retirement detection** — `grok-4`, `grok-4-fast{,-reasoning,-non-reasoning}`, `grok-3`, `grok-code-fast-1`, `grok-imagine-image-pro` etc. are detected in doctor and chat startup, with `hermes migrate xai` to one-shot config migration to the supported model. No more silent 404s after the retirement date. ([#29277](https://github.com/NousResearch/hermes-agent/pull/29277))
- **Opt-in `auto_speech_tags`** for xAI TTS — inserts light `[pause]` tags between paragraphs and sentences for more natural-sounding voice replies. Default OFF. ([#29376](https://github.com/NousResearch/hermes-agent/pull/29376))
- **`xai-oauth` `base_url` pinned to `x.ai` origin** — closes a silent credential-leak vector where `XAI_BASE_URL` could repoint OAuth-authenticated inference to an attacker-controlled host. ([#28952](https://github.com/NousResearch/hermes-agent/pull/28952))
- **OpenAI-style execution guidance applied to Grok models** — Grok and xai-oauth now get the same family-specific execution discipline block GPT/Codex have, so the model stops claiming completion without tool calls and stops suggesting workarounds instead of using existing tools. ([#27797](https://github.com/NousResearch/hermes-agent/pull/27797))
- Plus `x_search` degraded-results surfacing, tier-gated 403 with API-key fallback, PKCE `code_challenge` round-trip fix, dead-token quarantine on terminal refresh failure, MiniMax-style short-token refresh on per-request, and `WKE=unauthenticated` honor at both classifier sites. ([#29484](https://github.com/NousResearch/hermes-agent/pull/29484), [#28351](https://github.com/NousResearch/hermes-agent/pull/28351), [#27560](https://github.com/NousResearch/hermes-agent/pull/27560), [#28116](https://github.com/NousResearch/hermes-agent/pull/28116), [#30619](https://github.com/NousResearch/hermes-agent/pull/30619), [#30872](https://github.com/NousResearch/hermes-agent/pull/30872))
---
## 🏗️ Core Agent & Architecture
### The Big Refactor — `run_agent.py` 16k → 3.8k
- `run_agent.py` from 16,083 → 3,821 lines (-76%), extracted into 14 cohesive `agent/*` modules. `run_conversation` alone was 3,877 lines before the refactor. Every extraction keeps a thin forwarder on `AIAgent`, every test-patch path is preserved, every external caller stays compatible. ([#27248](https://github.com/NousResearch/hermes-agent/pull/27248))
### Agent loop & conversation
- Auxiliary task layered fallback (primary → chain → main agent → graceful fail) on capacity errors (402/429/connection). (salvages [#26811](https://github.com/NousResearch/hermes-agent/pull/26811) + [#26998](https://github.com/NousResearch/hermes-agent/pull/26998)) ([#27625](https://github.com/NousResearch/hermes-agent/pull/27625))
- Buffer retry/fallback status; surface only on terminal failure (no more noisy "retrying..." spam in mid-run output). ([#33816](https://github.com/NousResearch/hermes-agent/pull/33816))
- Host contract for external context engines — condenses 5 prior PRs into one extension surface. ([#33750](https://github.com/NousResearch/hermes-agent/pull/33750))
- Fallback immediately on provider content-policy blocks. ([#33883](https://github.com/NousResearch/hermes-agent/pull/33883))
- Re-pad `reasoning_content` on cross-provider fallback to require-side providers. (salvage [#33784](https://github.com/NousResearch/hermes-agent/pull/33784)) ([#33795](https://github.com/NousResearch/hermes-agent/pull/33795))
- Per-turn tool-outcome verifier — patch tool gets indent preservation, CRLF preservation, per-file failure escalation. ([#32273](https://github.com/NousResearch/hermes-agent/pull/32273))
- Single-knob native vision for custom-provider models. ([#29679](https://github.com/NousResearch/hermes-agent/pull/29679))
- Background review fork isolated from external memory plugins. ([#27190](https://github.com/NousResearch/hermes-agent/pull/27190))
- Background review inherits parent toolset config for `tools[]` cache parity. ([#29704](https://github.com/NousResearch/hermes-agent/pull/29704))
- Recover from providers returning list-type tool content. ([#30259](https://github.com/NousResearch/hermes-agent/pull/30259))
- Treat partial-stream stub responses as length truncation rather than clean stop. ([#30998](https://github.com/NousResearch/hermes-agent/pull/30998))
- OpenAI execution guidance applied to xAI Grok / xai-oauth. ([#27797](https://github.com/NousResearch/hermes-agent/pull/27797))
- ContextVars propagate to concurrent tool worker threads.
- Preload `jiter` native parser. ([#33692](https://github.com/NousResearch/hermes-agent/pull/33692))
- Expose context engine tools with saved toolsets. (salvage of [#31194](https://github.com/NousResearch/hermes-agent/pull/31194)) ([#33719](https://github.com/NousResearch/hermes-agent/pull/33719))
### Sessions & memory
- `session_search` rebuilt — single-shape (discovery + scroll + browse), no aux-LLM, ~20ms vs. ~90s. ([#27590](https://github.com/NousResearch/hermes-agent/pull/27590))
- Salvage [#29182](https://github.com/NousResearch/hermes-agent/pull/29182) — opt-in JSON snapshot writer for sessions. ([#29278](https://github.com/NousResearch/hermes-agent/pull/29278))
- Persist `platform_message_id` for recall across gateway restarts. ([#29449](https://github.com/NousResearch/hermes-agent/pull/29449))
- Inline memory-context mentions stay visible in conversation. ([#28132](https://github.com/NousResearch/hermes-agent/pull/28132))
- Recalled memory labeled informational, not authoritative. ([#28583](https://github.com/NousResearch/hermes-agent/pull/28583))
- Memory + context-engine tool injection gated on `enabled_toolsets`. ([#30177](https://github.com/NousResearch/hermes-agent/pull/30177))
- Guard against external drift in `MEMORY.md` / `USER.md`. ([#30877](https://github.com/NousResearch/hermes-agent/pull/30877))
- Honcho runtime peer mapping — correctness follow-ups + setup wizard + docs. ([#30077](https://github.com/NousResearch/hermes-agent/pull/30077))
- Periodic memory logging for leak detection. (salvage of [#17667](https://github.com/NousResearch/hermes-agent/pull/17667)) ([#27102](https://github.com/NousResearch/hermes-agent/pull/27102))
### Codex / Responses-API maturation
- TTFB watchdog for stalled Codex Responses streams. ([#32042](https://github.com/NousResearch/hermes-agent/pull/32042))
- Actionable hint when stale-call detector fires on known silent-reject pattern. ([#32016](https://github.com/NousResearch/hermes-agent/pull/32016), [#33133](https://github.com/NousResearch/hermes-agent/pull/33133))
- Drop SDK `responses.stream()` helper; consume events directly. ([#33042](https://github.com/NousResearch/hermes-agent/pull/33042))
- Gracefully recover from `invalid_encrypted_content`. (salvage of [#10144](https://github.com/NousResearch/hermes-agent/pull/10144)) ([#33035](https://github.com/NousResearch/hermes-agent/pull/33035))
- Recover Codex Responses streams with null output. ([#32963](https://github.com/NousResearch/hermes-agent/pull/32963), [#33390](https://github.com/NousResearch/hermes-agent/pull/33390))
- Drop foreign-issuer reasoning and transient `rs_tmp` reasoning replay state. ([#33156](https://github.com/NousResearch/hermes-agent/pull/33156), [#33146](https://github.com/NousResearch/hermes-agent/pull/33146))
- Codex 429 quota classified as rate-limit, not missing credentials. ([#33168](https://github.com/NousResearch/hermes-agent/pull/33168))
- Codex chat path falls back to credential_pool when singleton is empty. ([#33189](https://github.com/NousResearch/hermes-agent/pull/33189))
- Codex re-auth syncs credential_pool. ([#33164](https://github.com/NousResearch/hermes-agent/pull/33164))
- Omit `tools` key when no tools registered. ([#33409](https://github.com/NousResearch/hermes-agent/pull/33409))
- Parse Codex image-generation SSE directly. ([#32933](https://github.com/NousResearch/hermes-agent/pull/32933))
---
## 🎛️ Kanban — Multi-Agent Maturation Wave
### Orchestration & dispatch
- Orchestrator-driven auto-decomposition on triage. ([#27572](https://github.com/NousResearch/hermes-agent/pull/27572))
- Kanban swarm topology helper — `hermes kanban swarm` creates a Swarm v1 graph (root + parallel workers + gated verifier + gated synthesizer + shared blackboard). (salvages [#26791](https://github.com/NousResearch/hermes-agent/pull/26791) by @Niraven) ([#28443](https://github.com/NousResearch/hermes-agent/pull/28443))
- Dispatcher wires review agents from the review column. ([#28449](https://github.com/NousResearch/hermes-agent/pull/28449))
- Stale-detection for running tasks in dispatcher. ([#28452](https://github.com/NousResearch/hermes-agent/pull/28452))
- Respawn guard blocks repeat worker storms. ([#28455](https://github.com/NousResearch/hermes-agent/pull/28455))
- Respawn guard defers `blocker_auth` instead of auto-blocking. ([#28683](https://github.com/NousResearch/hermes-agent/pull/28683))
- Cross-profile cron jobs surface in dashboard. ([#28457](https://github.com/NousResearch/hermes-agent/pull/28457))
- Worker visibility endpoints: `/workers/active`, `/runs/{id}`, `/inspect`. (salvages [#23761](https://github.com/NousResearch/hermes-agent/pull/23761) by @Interstellar-code) ([#28432](https://github.com/NousResearch/hermes-agent/pull/28432))
### Task configuration & scheduling
- Per-task model override. ([#28364](https://github.com/NousResearch/hermes-agent/pull/28364))
- Board-level default workdir. ([#28394](https://github.com/NousResearch/hermes-agent/pull/28394))
- Configurable worktree paths and branches. ([#28462](https://github.com/NousResearch/hermes-agent/pull/28462))
- Scheduled task start times. ([#28384](https://github.com/NousResearch/hermes-agent/pull/28384))
- Scheduled status for delayed follow-ups. ([#28467](https://github.com/NousResearch/hermes-agent/pull/28467))
- Trimmed task comments. ([#28399](https://github.com/NousResearch/hermes-agent/pull/28399))
- Initial-status for human-ops cards. ([#28414](https://github.com/NousResearch/hermes-agent/pull/28414))
- `max_in_progress` config to cap concurrent running tasks. ([#28420](https://github.com/NousResearch/hermes-agent/pull/28420))
- Filter tasks by workflow fields. ([#28454](https://github.com/NousResearch/hermes-agent/pull/28454))
- `--sort` for `hermes kanban list`. ([#28427](https://github.com/NousResearch/hermes-agent/pull/28427))
- Optional `board` parameter on all MCP tools. ([#28444](https://github.com/NousResearch/hermes-agent/pull/28444))
- Stamp originating ACP session_id on tasks. ([#28447](https://github.com/NousResearch/hermes-agent/pull/28447))
- `auto_promote_children` config toggle. ([#28344](https://github.com/NousResearch/hermes-agent/pull/28344))
- `archive --rm` to hard-delete archived tasks. ([#28355](https://github.com/NousResearch/hermes-agent/pull/28355))
- Promote dependents when parent is archived. ([#28372](https://github.com/NousResearch/hermes-agent/pull/28372))
- Promote blocked tasks when parent dependencies complete. ([#28377](https://github.com/NousResearch/hermes-agent/pull/28377))
- Demote ready children when parent is reopened. ([#28382](https://github.com/NousResearch/hermes-agent/pull/28382))
- `promote` verb for manual `todo→ready` recovery + bulk `--ids`. (salvage [#29464](https://github.com/NousResearch/hermes-agent/pull/29464)) ([#31334](https://github.com/NousResearch/hermes-agent/pull/31334))
### Dashboard
- Drag-to-delete trash zone + bulk delete. ([#28468](https://github.com/NousResearch/hermes-agent/pull/28468))
- Surface per-task `model_override` in show + tool output. ([#28442](https://github.com/NousResearch/hermes-agent/pull/28442))
- Cross-profile notification delivery via `kanban.notification_sources`. ([#28395](https://github.com/NousResearch/hermes-agent/pull/28395))
- Scratch-workspace deletion warning for users. ([#30949](https://github.com/NousResearch/hermes-agent/pull/30949))
- Mobile dashboard UX polish. ([#28127](https://github.com/NousResearch/hermes-agent/pull/28127))
### Reliability
- Worker log retention configurable. ([#27867](https://github.com/NousResearch/hermes-agent/pull/27867))
- Configurable claim TTL. ([#28392](https://github.com/NousResearch/hermes-agent/pull/28392))
- Fingerprint crash errors to prevent fleet-wide retry exhaustion. ([#28380](https://github.com/NousResearch/hermes-agent/pull/28380))
- Reset failure counters on `unblock_task`. ([#28379](https://github.com/NousResearch/hermes-agent/pull/28379))
- Detect cycles in `decompose_triage_task` sibling-link pre-validation. ([#28088](https://github.com/NousResearch/hermes-agent/pull/28088))
- Surface unusable triage auxiliary model (auto-decompose aware). ([#27871](https://github.com/NousResearch/hermes-agent/pull/27871))
- Align failure diagnostics with retry limit. ([#27868](https://github.com/NousResearch/hermes-agent/pull/27868))
- Align worker terminal timeout with task runtime. ([#27864](https://github.com/NousResearch/hermes-agent/pull/27864))
- Auto-install bundled skills (kanban-worker) on init. ([#28368](https://github.com/NousResearch/hermes-agent/pull/28368))
- Make legacy task migration idempotent. ([#28397](https://github.com/NousResearch/hermes-agent/pull/28397))
- Serialize DB initialization. ([#28383](https://github.com/NousResearch/hermes-agent/pull/28383))
- Persist worker session metadata on completion. ([#28387](https://github.com/NousResearch/hermes-agent/pull/28387))
- Pass `accept-hooks` to worker chat subprocess. ([#28393](https://github.com/NousResearch/hermes-agent/pull/28393))
- Preserve worker tools with restricted toolsets. ([#28396](https://github.com/NousResearch/hermes-agent/pull/28396))
- Avoid unsafe Windows worker Hermes shim resolution. ([#28398](https://github.com/NousResearch/hermes-agent/pull/28398))
- Sync slash subcommands with live parser. ([#28376](https://github.com/NousResearch/hermes-agent/pull/28376))
- Show scheduled kanban tasks in dashboard. ([#28400](https://github.com/NousResearch/hermes-agent/pull/28400))
- Assign single-task kanban decompositions. ([#28401](https://github.com/NousResearch/hermes-agent/pull/28401))
- Configurable `max_tokens` for kanban specify. ([#28374](https://github.com/NousResearch/hermes-agent/pull/28374))
- Per-job profile support for cron. ([#28124](https://github.com/NousResearch/hermes-agent/pull/28124))
- Codex app-server: include every Kanban-pinned path in `writable_roots`. ([#28435](https://github.com/NousResearch/hermes-agent/pull/28435))
- Cache kanban worker guidance at session init for prompt-cache reuse. ([#28425](https://github.com/NousResearch/hermes-agent/pull/28425))
---
## ⚡ Performance
- `openai._base_client` import deferred — 240ms / 17MB off every CLI cold start. ([#28864](https://github.com/NousResearch/hermes-agent/pull/28864))
- Agent-loop hot-path optimizations — 47% fewer per-conversation function calls (399k → 213k for 31-turn chat). ([#28866](https://github.com/NousResearch/hermes-agent/pull/28866))
- Compression-feasibility check deferred — 170-290ms off every agent construction. ([#28957](https://github.com/NousResearch/hermes-agent/pull/28957))
- Adaptive subprocess poll — ~195ms off every tool call, 1+ second per turn. ([#29006](https://github.com/NousResearch/hermes-agent/pull/29006))
- Termux TUI cold start speedup. ([#29419](https://github.com/NousResearch/hermes-agent/pull/29419))
- Termux non-TUI cold start speedup. (salvage [#29438](https://github.com/NousResearch/hermes-agent/pull/29438)) ([#30121](https://github.com/NousResearch/hermes-agent/pull/30121))
- Termux fast-path version + deferred bare-prompt agent startup. ([#30609](https://github.com/NousResearch/hermes-agent/pull/30609))
- Cut hermes `--version` wall time 63% — flips head-to-head vs Codex CLI. ([#31968](https://github.com/NousResearch/hermes-agent/pull/31968))
- Date-only timestamp + loud gateway-DB roundtrip logging — improves prompt-cache hit rate. ([#27675](https://github.com/NousResearch/hermes-agent/pull/27675))
- Cache kanban worker guidance at session init for prompt-cache reuse. ([#28425](https://github.com/NousResearch/hermes-agent/pull/28425))
---
## 🔧 Tool System
### Tool surface
- `patch`: indent preservation, CRLF preservation, per-file failure escalation. ([#32273](https://github.com/NousResearch/hermes-agent/pull/32273))
- `terminal`: warn at call time when `background=true` runs silently. ([#31289](https://github.com/NousResearch/hermes-agent/pull/31289))
- `terminal`: nudge homebrewed CI pollers at the tool surface. ([#33142](https://github.com/NousResearch/hermes-agent/pull/33142))
- `x_search`: surface degraded results + validate dates. ([#29484](https://github.com/NousResearch/hermes-agent/pull/29484))
- `x_search`: auto-enable toolset when xAI credentials are configured. ([#27376](https://github.com/NousResearch/hermes-agent/pull/27376))
- `computer_use`: route SOM/vision captures via auxiliary.vision. ([#30126](https://github.com/NousResearch/hermes-agent/pull/30126))
- `transcription`: reject symlinked audio inputs. ([#10082](https://github.com/NousResearch/hermes-agent/pull/10082))
- TTS: prevent double `[pause]` in xAI auto speech tags. ([#32237](https://github.com/NousResearch/hermes-agent/pull/32237))
- TTS: preserve native audio outside Telegram voice delivery. ([#28512](https://github.com/NousResearch/hermes-agent/pull/28512))
- TTS: opt-in xAI `auto_speech_tags` speech-tag pauses for natural voice replies. ([#29376](https://github.com/NousResearch/hermes-agent/pull/29376))
- Voice: chunk oversized CLI recordings. ([#30044](https://github.com/NousResearch/hermes-agent/pull/30044))
- Voice: honor `PULSE_SERVER` / `PIPEWIRE_REMOTE` inside Docker. ([#22534](https://github.com/NousResearch/hermes-agent/pull/22534))
### Browser
- All cloud browser providers (Browserbase, Anchor, Camofox, Hyperbrowser, etc.) migrated to image_gen-style plugins. (salvages [#25580](https://github.com/NousResearch/hermes-agent/pull/25580)) ([#27403](https://github.com/NousResearch/hermes-agent/pull/27403))
- Auto-launch Chromium-family browser for CDP. ([#29106](https://github.com/NousResearch/hermes-agent/pull/29106))
- Docker: discover agent-browser Chromium binary at boot. ([#33184](https://github.com/NousResearch/hermes-agent/pull/33184))
### Image generation
- **Krea** provider plugin (Krea 2 Medium + Large). ([#33236](https://github.com/NousResearch/hermes-agent/pull/33236))
- FAL backend ported to `plugins/image_gen/fal`. (salvage [#27966](https://github.com/NousResearch/hermes-agent/pull/27966)) ([#30380](https://github.com/NousResearch/hermes-agent/pull/30380))
- Cache xAI ephemeral URL responses to disk. ([#31759](https://github.com/NousResearch/hermes-agent/pull/31759))
### Web search
- **xAI Web Search** as a provider plugin. ([#29042](https://github.com/NousResearch/hermes-agent/pull/29042))
### MCP
- **Nous-approved MCP catalog** with interactive picker. ([#30870](https://github.com/NousResearch/hermes-agent/pull/30870))
- **TLS client certificate (mTLS) support** for HTTP and SSE MCP servers. ([#33721](https://github.com/NousResearch/hermes-agent/pull/33721))
- Stdin paste-back fallback for headless OAuth flow. ([#32053](https://github.com/NousResearch/hermes-agent/pull/32053))
- `skip` at paste prompt bypasses auth without disabling server. ([#32069](https://github.com/NousResearch/hermes-agent/pull/32069))
- Registry-aware `mcp_` prefix on both ends of round-trip. ([#31700](https://github.com/NousResearch/hermes-agent/pull/31700))
---
## 🧩 Skills Ecosystem
### Skills system
- **Skill bundles** — `/<name>` loads multiple skills. ([#28373](https://github.com/NousResearch/hermes-agent/pull/28373))
- Skills Hub: health checks, freshness badge, and a watchdog cron. ([#32345](https://github.com/NousResearch/hermes-agent/pull/32345))
- Opt-in AST deep diagnostics on skill writes. (salvage of [#30918](https://github.com/NousResearch/hermes-agent/pull/30918)) ([#31198](https://github.com/NousResearch/hermes-agent/pull/31198))
- Bundled/pinned skill protection in background-review prompts. ([#28338](https://github.com/NousResearch/hermes-agent/pull/28338))
- Show user-modified skill names in bundled skill sync summary. ([#28671](https://github.com/NousResearch/hermes-agent/pull/28671))
- Load symlinked skill slash commands. ([#27759](https://github.com/NousResearch/hermes-agent/pull/27759))
- Deduplicate Skills Hub search results by identifier, not name. ([#29490](https://github.com/NousResearch/hermes-agent/pull/29490))
### New skills
- `openhands` — delegate-to-OpenHands orchestration skill (closes [#477](https://github.com/NousResearch/hermes-agent/issues/477)) ([#32261](https://github.com/NousResearch/hermes-agent/pull/32261))
- `code-wiki` — persistent indexed dev wiki (closes [#486](https://github.com/NousResearch/hermes-agent/issues/486)) ([#32240](https://github.com/NousResearch/hermes-agent/pull/32240))
- `web-pentest` — OWASP recipes (closes [#400](https://github.com/NousResearch/hermes-agent/issues/400)) ([#32265](https://github.com/NousResearch/hermes-agent/pull/32265))
- `baoyu-article-illustrator` ([#28287](https://github.com/NousResearch/hermes-agent/pull/28287))
---
## ☁️ Providers
### xAI deep integration
- **xAI Web Search** as a `plugins/web/xai/` provider plugin. ([#29042](https://github.com/NousResearch/hermes-agent/pull/29042))
- **`hermes proxy` xAI upstream** — OpenAI-compatible local proxy backed by xai-oauth. ([#28356](https://github.com/NousResearch/hermes-agent/pull/28356))
- **May 15 model retirement detection + `hermes migrate xai`** for grok-4 / grok-3 / grok-code-fast-1 / grok-imagine-image-pro. ([#29277](https://github.com/NousResearch/hermes-agent/pull/29277))
- **Opt-in `auto_speech_tags`** for natural xAI TTS voice replies. ([#29376](https://github.com/NousResearch/hermes-agent/pull/29376))
- **xai-oauth base_url pinned to x.ai origin** — closes silent credential-leak vector. ([#28952](https://github.com/NousResearch/hermes-agent/pull/28952))
- **OpenAI-style execution guidance** applied to Grok / xai-oauth models. ([#27797](https://github.com/NousResearch/hermes-agent/pull/27797))
- xAI: detect retired May 15 models in doctor/chat startup. ([#29277](https://github.com/NousResearch/hermes-agent/pull/29277))
- xAI: resolve Grok Build context for OAuth. ([#30579](https://github.com/NousResearch/hermes-agent/pull/30579))
- xAI OAuth: tier-gated 403 with API-key fallback. ([#28351](https://github.com/NousResearch/hermes-agent/pull/28351))
- xAI OAuth: PKCE `code_challenge` echo. ([#27560](https://github.com/NousResearch/hermes-agent/pull/27560))
- xAI OAuth: quarantine dead tokens on terminal refresh failure. ([#28116](https://github.com/NousResearch/hermes-agent/pull/28116))
- xAI OAuth: honor `WKE=unauthenticated` disambiguator at both classifier sites. ([#30872](https://github.com/NousResearch/hermes-agent/pull/30872))
- xAI OAuth: accept bare-code manual paste (state=None). (closes [#26923](https://github.com/NousResearch/hermes-agent/issues/26923)) ([#33880](https://github.com/NousResearch/hermes-agent/pull/33880))
- xAI OAuth: fall back to manual paste on loopback timeout. ([#33231](https://github.com/NousResearch/hermes-agent/pull/33231))
- xAI proxy: handle 429 rate-limit responses in proxy retry path. ([#33743](https://github.com/NousResearch/hermes-agent/pull/33743))
### Other providers
- **OpenAI API as a first-class provider** (distinct from Codex runtime). ([#31898](https://github.com/NousResearch/hermes-agent/pull/31898))
- **Microsoft Entra ID** auth for Azure Foundry (with 1M Anthropic-Messages beta preserved on Bearer). (salvages [#27509](https://github.com/NousResearch/hermes-agent/pull/27509), [#27022](https://github.com/NousResearch/hermes-agent/pull/27022)) ([#28101](https://github.com/NousResearch/hermes-agent/pull/28101), [#28084](https://github.com/NousResearch/hermes-agent/pull/28084))
- **OpenRouter** sticky routing — `session_id` passed via `extra_body` so a long-running session keeps landing on the same upstream provider. (@Cybourgeoisie) ([#33939](https://github.com/NousResearch/hermes-agent/pull/33939))
- Nous: JWT token for inference; stop replaying invalid Nous refresh tokens. (@rewbs) ([#27663](https://github.com/NousResearch/hermes-agent/pull/27663))
- Nous Portal: one-shot setup, status CLI, and Nous-included markers. ([#30860](https://github.com/NousResearch/hermes-agent/pull/30860))
- Anthropic adapter: extract 7 helpers from `convert_messages_to_anthropic`. (salvage [#27784](https://github.com/NousResearch/hermes-agent/pull/27784)) ([#30386](https://github.com/NousResearch/hermes-agent/pull/30386))
- Catalog: add `qwen3.7-max` to Alibaba + Alibaba-Coding-Plan model lists. ([#33129](https://github.com/NousResearch/hermes-agent/pull/33129))
- opencode-go: route `qwen3.7-max` via `anthropic_messages`. (@beardthelion) ([#32780](https://github.com/NousResearch/hermes-agent/pull/32780))
- opencode-go: expose Kimi K2 + DeepSeek reasoning controls. ([#30845](https://github.com/NousResearch/hermes-agent/pull/30845))
- Remove Vercel AI Gateway and Vercel Sandbox.
- MiniMax OAuth: refresh short-lived access tokens per request. ([#30619](https://github.com/NousResearch/hermes-agent/pull/30619))
- Codex OAuth: quarantine terminal refresh errors. ([#28118](https://github.com/NousResearch/hermes-agent/pull/28118))
- Codex: drop dead model slugs that HTTP 400 on ChatGPT Pro. ([#33424](https://github.com/NousResearch/hermes-agent/pull/33424))
- Codex: sync `manual:device_code` pool entries on re-auth. ([#33744](https://github.com/NousResearch/hermes-agent/pull/33744))
- MiniMax OAuth: quarantine terminal refresh errors. ([#28119](https://github.com/NousResearch/hermes-agent/pull/28119))
---
## 🔑 Secrets
- **Bitwarden Secrets Manager** integration with lazy `bws` install. ([#30035](https://github.com/NousResearch/hermes-agent/pull/30035))
- Bitwarden: EU Cloud + self-hosted server URL support. ([#31378](https://github.com/NousResearch/hermes-agent/pull/31378))
- Label detected credentials with their source (Bitwarden). ([#30364](https://github.com/NousResearch/hermes-agent/pull/30364))
---
## 📱 Messaging Platforms (Gateway)
### Gateway core
- **Deliverable mode** — agents ship artifacts as native uploads from any platform (Slack/Discord/Telegram/Teams/Email). ([#27813](https://github.com/NousResearch/hermes-agent/pull/27813))
- `hermes send` — pipe any script's output to any messaging platform. (salvage of [#19631](https://github.com/NousResearch/hermes-agent/pull/19631)) ([#27188](https://github.com/NousResearch/hermes-agent/pull/27188))
- Debounce queued text follow-ups during active sessions. (salvage of [#31235](https://github.com/NousResearch/hermes-agent/pull/31235)) ([#31341](https://github.com/NousResearch/hermes-agent/pull/31341))
- Plugin-transformed final_response delivered through streaming gate. ([#31433](https://github.com/NousResearch/hermes-agent/pull/31433))
- Refresh cached agent tools on `/reload-mcp`. ([#32815](https://github.com/NousResearch/hermes-agent/pull/32815))
- Harden kanban + provider cleanup races on long-running workloads. ([#29479](https://github.com/NousResearch/hermes-agent/pull/29479))
### New / reorganized adapters
- **ntfy** — 23rd platform, push notifications, plugin shape, zero core edits. (salvages [#30625](https://github.com/NousResearch/hermes-agent/pull/30625) → [#4043](https://github.com/NousResearch/hermes-agent/pull/4043)) ([#30867](https://github.com/NousResearch/hermes-agent/pull/30867))
- **Discord** adapter migrated to bundled plugin. (salvage of [#24356](https://github.com/NousResearch/hermes-agent/pull/24356)) ([#30591](https://github.com/NousResearch/hermes-agent/pull/30591))
- **Mattermost** adapter migrated to bundled plugin. (salvage of [#30916](https://github.com/NousResearch/hermes-agent/pull/30916)) ([#31748](https://github.com/NousResearch/hermes-agent/pull/31748))
### Telegram
- Edit status messages in place instead of appending. (based on [#30141](https://github.com/NousResearch/hermes-agent/pull/30141) by @qike-ms) ([#30864](https://github.com/NousResearch/hermes-agent/pull/30864))
- Skip-STT audio path + 2GB cap via local Bot API server. ([#28541](https://github.com/NousResearch/hermes-agent/pull/28541))
- Route image documents (.png/.jpg/.webp/.gif) through vision pipeline. ([#28519](https://github.com/NousResearch/hermes-agent/pull/28519))
- Route audio file attachments away from STT pipeline. ([#28478](https://github.com/NousResearch/hermes-agent/pull/28478))
- `disable_topic_auto_rename` gateway flag. ([#28523](https://github.com/NousResearch/hermes-agent/pull/28523))
- `ignore_root_dm` config to drop messages without thread_id. ([#28536](https://github.com/NousResearch/hermes-agent/pull/28536))
- Chat-scoped auth without sender user_id. ([#28525](https://github.com/NousResearch/hermes-agent/pull/28525))
- Fail-closed auth fallback when `TELEGRAM_ALLOWED_USERS` is empty. ([#28494](https://github.com/NousResearch/hermes-agent/pull/28494))
- Roll over tool progress bubbles + scope audio_file_paths. ([#28482](https://github.com/NousResearch/hermes-agent/pull/28482))
- Avoid duplicate text after auto-TTS voice replies. ([#28509](https://github.com/NousResearch/hermes-agent/pull/28509))
- Mark final voice reply notify-worthy so Telegram delivers it audibly. ([#28504](https://github.com/NousResearch/hermes-agent/pull/28504))
### Discord
- Recover Windows voice opus decoding. ([#33182](https://github.com/NousResearch/hermes-agent/pull/33182))
- `allow_any_attachment` config to accept arbitrary file types. ([#27245](https://github.com/NousResearch/hermes-agent/pull/27245))
- Transcribe native voice notes. ([#28993](https://github.com/NousResearch/hermes-agent/pull/28993))
- Define UI view classes after lazy install. ([#28817](https://github.com/NousResearch/hermes-agent/pull/28817))
### Signal / Matrix / Feishu / Slack / WeCom
- Signal: `require_mention` filter for group chats. ([#28574](https://github.com/NousResearch/hermes-agent/pull/28574))
- Matrix: warn on clock-skew silent message drops. ([#27330](https://github.com/NousResearch/hermes-agent/pull/27330))
- Matrix E2EE installs full dep set; plugins respect `is_connected`. ([#31688](https://github.com/NousResearch/hermes-agent/pull/31688))
- Feishu: require webhook auth secret + honor config extras. ([#30746](https://github.com/NousResearch/hermes-agent/pull/30746))
- Feishu: enforce auth and chat binding for approval buttons. ([#30744](https://github.com/NousResearch/hermes-agent/pull/30744))
- Slack: socket recovery + Windows restart dedupe. ([#28873](https://github.com/NousResearch/hermes-agent/pull/28873))
- WeCom: safe-parse untrusted XML. ([#32442](https://github.com/NousResearch/hermes-agent/pull/32442))
### DingTalk / Webhooks / Microsoft Graph
- DingTalk: transcribe native voice notes. ([#28993](https://github.com/NousResearch/hermes-agent/pull/28993))
- Webhook: enforce `INSECURE_NO_AUTH` safety rail on dynamic route reloads. ([#30863](https://github.com/NousResearch/hermes-agent/pull/30863))
- Webhook: restrict default toolset capabilities. ([#30745](https://github.com/NousResearch/hermes-agent/pull/30745))
- Microsoft Graph: harden webhook auth requirements. ([#30169](https://github.com/NousResearch/hermes-agent/pull/30169))
---
## 🖥️ CLI & TUI
### CLI
- `/update` slash command in CLI and TUI. ([#23854](https://github.com/NousResearch/hermes-agent/pull/23854))
- Update auto-rollback when post-pull syntax check fails. ([#28669](https://github.com/NousResearch/hermes-agent/pull/28669))
- `--branch` flag for `hermes update`. (@jquesnelle) ([#29591](https://github.com/NousResearch/hermes-agent/pull/29591))
- `/exit --delete` flag to remove session on quit. (salvage of [#17665](https://github.com/NousResearch/hermes-agent/pull/17665)) ([#27101](https://github.com/NousResearch/hermes-agent/pull/27101))
- `▶ N` indicator in status bar for running `/background` tasks. ([#27175](https://github.com/NousResearch/hermes-agent/pull/27175))
- Live background terminal-process count in status bar. ([#32061](https://github.com/NousResearch/hermes-agent/pull/32061))
- Append session recap to `/status` output. (salvage of [#18587](https://github.com/NousResearch/hermes-agent/pull/18587)) ([#27176](https://github.com/NousResearch/hermes-agent/pull/27176))
- Configurable paste-collapse thresholds (TUI + CLI). (salvage [#29723](https://github.com/NousResearch/hermes-agent/pull/29723)) ([#32087](https://github.com/NousResearch/hermes-agent/pull/32087))
- `/resume` accepts position numbers. ([#31709](https://github.com/NousResearch/hermes-agent/pull/31709))
- Bring tool-call display back — verbose mode, specific failure reasons, todo progress. ([#31293](https://github.com/NousResearch/hermes-agent/pull/31293))
- Validate runtime token refresh in Qwen auth status. ([#31196](https://github.com/NousResearch/hermes-agent/pull/31196))
### TUI
- **TUI session orchestrator** — multiple live sessions in one TUI window. (salvages [#27642](https://github.com/NousResearch/hermes-agent/pull/27642)) ([#32980](https://github.com/NousResearch/hermes-agent/pull/32980))
- `mouse_tracking` DEC mode presets. (salvage of [#26681](https://github.com/NousResearch/hermes-agent/pull/26681) by @OutThisLife) ([#30084](https://github.com/NousResearch/hermes-agent/pull/30084))
- Termux scrollback preservation + touch-friendly defaults. ([#28910](https://github.com/NousResearch/hermes-agent/pull/28910))
- Full assistant text in scrollback (no history truncation). ([#28829](https://github.com/NousResearch/hermes-agent/pull/28829))
- Preserve scrollback when branching sessions. ([#30162](https://github.com/NousResearch/hermes-agent/pull/30162))
- Preserve Python dunder identifiers in markdown. ([#28582](https://github.com/NousResearch/hermes-agent/pull/28582))
- Active profile shown in TUI prompt. ([#28581](https://github.com/NousResearch/hermes-agent/pull/28581))
- Improve Charizard completion menu contrast. ([#28346](https://github.com/NousResearch/hermes-agent/pull/28346))
- Stop slash dropdown chopping last char of `/goal`. ([#31311](https://github.com/NousResearch/hermes-agent/pull/31311))
- Clipboard copy on linux/wayland. ([#29342](https://github.com/NousResearch/hermes-agent/pull/29342))
- Anchor `splitReasoning` unclosed-tag regex; stop eating last paragraph. ([#29426](https://github.com/NousResearch/hermes-agent/pull/29426))
- Surface verbose tool details. ([#30225](https://github.com/NousResearch/hermes-agent/pull/30225))
- Load Linux skills on Termux + salvage @adybag14-cyber's Termux gates. ([#30166](https://github.com/NousResearch/hermes-agent/pull/30166))
- Handle images with codex app-server. ([#31220](https://github.com/NousResearch/hermes-agent/pull/31220))
- Refresh virtual transcript on viewport resize. ([#31077](https://github.com/NousResearch/hermes-agent/pull/31077))
- Ignore late thinking deltas after completion. ([#31055](https://github.com/NousResearch/hermes-agent/pull/31055))
- Commit composer input bursts immediately. ([#31053](https://github.com/NousResearch/hermes-agent/pull/31053))
- Log parent gateway lifecycle exits. ([#31051](https://github.com/NousResearch/hermes-agent/pull/31051))
- Clear TTS env var on voice off + TTS indicator in status bar. ([#30987](https://github.com/NousResearch/hermes-agent/pull/30987))
- Pass `--expose-gc` as node argv instead of NODE_OPTIONS. ([#29998](https://github.com/NousResearch/hermes-agent/pull/29998))
- Align composer cursorLayout with wrap-ansi to kill multiline cursor drift. ([#27489](https://github.com/NousResearch/hermes-agent/pull/27489))
- Harden Terminal.app rendering and color paths. ([#27251](https://github.com/NousResearch/hermes-agent/pull/27251))
- Keep `/goal` verdict out of compact status row. ([#27971](https://github.com/NousResearch/hermes-agent/pull/27971))
- Clamp curses color 8 for 8-color terminals (Docker). ([#30260](https://github.com/NousResearch/hermes-agent/pull/30260))
---
## 🔒 Security & Reliability
### Promptware & memory hardening
- **Promptware defense** — shared threat patterns + memory load-time scan + tool-result delimiters. ([#32269](https://github.com/NousResearch/hermes-agent/pull/32269))
- Expand memory content scanning patterns to parity with skills guard. ([#9151](https://github.com/NousResearch/hermes-agent/pull/9151))
- Harden Skills Guard multi-word prompt patterns. (@YLChen-007) ([#26852](https://github.com/NousResearch/hermes-agent/pull/26852))
- Split cron scanner so skill prose stops false-positiving exfil patterns. ([#32339](https://github.com/NousResearch/hermes-agent/pull/32339))
### File safety
- Protect Hermes control-plane files from prompt injection (`auth.json`, `config.yaml`, `webhook_subscriptions.json`, `mcp-tokens/`). (salvages @PratikRai0101's [#14157](https://github.com/NousResearch/hermes-agent/pull/14157)) ([#30397](https://github.com/NousResearch/hermes-agent/pull/30397))
- Write-deny `<root>/.env` when running under a profile. ([#29687](https://github.com/NousResearch/hermes-agent/pull/29687))
- Defense-in-depth read-deny on credential stores. (salvages [#17659](https://github.com/NousResearch/hermes-agent/pull/17659) + [#8055](https://github.com/NousResearch/hermes-agent/pull/8055)) ([#30721](https://github.com/NousResearch/hermes-agent/pull/30721))
- TTS `output_path` traversal + update ZIP symlink reject. (salvage [#6693](https://github.com/NousResearch/hermes-agent/pull/6693) + [#15881](https://github.com/NousResearch/hermes-agent/pull/15881)) ([#32056](https://github.com/NousResearch/hermes-agent/pull/32056))
- Reject symlinked audio inputs. ([#10082](https://github.com/NousResearch/hermes-agent/pull/10082))
### Credential safety
- Avoid persisting borrowed credential secrets — runtime env-sourced keys no longer leak into `auth.json`. ([#31416](https://github.com/NousResearch/hermes-agent/pull/31416))
- Validate Nous Portal `inference_base_url` against host allowlist. (salvages [#27612](https://github.com/NousResearch/hermes-agent/pull/27612)) ([#30611](https://github.com/NousResearch/hermes-agent/pull/30611))
- Harden API server key placeholder handling. ([#30738](https://github.com/NousResearch/hermes-agent/pull/30738))
- Harden Google Chat OAuth credential persistence. (@Zyrixtrex) ([#24788](https://github.com/NousResearch/hermes-agent/pull/24788))
- xAI OAuth: pin inference `base_url` to x.ai origin. ([#28952](https://github.com/NousResearch/hermes-agent/pull/28952))
- Quarantine dead OAuth tokens on terminal refresh failure (xAI, Codex, MiniMax). ([#28116](https://github.com/NousResearch/hermes-agent/pull/28116), [#28118](https://github.com/NousResearch/hermes-agent/pull/28118), [#28119](https://github.com/NousResearch/hermes-agent/pull/28119))
### Supply-chain
- **On-demand supply-chain audit via OSV.dev** — `hermes audit`. ([#31460](https://github.com/NousResearch/hermes-agent/pull/31460))
- `hermes update` syntax-validates critical files post-pull, auto-rollback on failure. ([#28669](https://github.com/NousResearch/hermes-agent/pull/28669))
- Quarantine `hermes.exe` vs concurrent Windows instance. ([#26677](https://github.com/NousResearch/hermes-agent/pull/26677))
### Other hardening
- Restrict default webhook toolset capabilities. ([#30745](https://github.com/NousResearch/hermes-agent/pull/30745))
- Harden Microsoft Graph webhook auth requirements. ([#30169](https://github.com/NousResearch/hermes-agent/pull/30169))
- Require source CIDR allowlisting for public msgraph webhook binds. ([#33722](https://github.com/NousResearch/hermes-agent/pull/33722))
- Require `API_SERVER_KEY` before dispatching API server work. ([#33232](https://github.com/NousResearch/hermes-agent/pull/33232))
- env_passthrough: apply GHSA-rhgp-j443-p4rf filter to config.yaml path. (@roadhero) ([#27794](https://github.com/NousResearch/hermes-agent/pull/27794))
- Dashboard + WeCom: restrict markdown link schemes; safe-parse untrusted XML. ([#32442](https://github.com/NousResearch/hermes-agent/pull/32442))
- Salvage project-plugin RCE bypass fix from PR [#29311](https://github.com/NousResearch/hermes-agent/pull/29311) (GHSA-5qr3-c538-wm9j). ([#30837](https://github.com/NousResearch/hermes-agent/pull/30837))
- Cross-profile soft guard on file-write tools + system-prompt hint. ([#31290](https://github.com/NousResearch/hermes-agent/pull/31290))
- Reject unsafe tar members in Android psutil compatibility installer. ([#33742](https://github.com/NousResearch/hermes-agent/pull/33742))
- Reject non-regular tar members during tirith auto-install. ([#33786](https://github.com/NousResearch/hermes-agent/pull/33786))
---
## 🪟 Native Windows (Beta Continued)
- Complete Windows bootstrap — `dep_ensure` + `install.ps1` + detection. (@alt-glitch) ([#27845](https://github.com/NousResearch/hermes-agent/pull/27845))
- `install.ps1`: strip BOM, `-Commit`/`-Tag` pin params, harden git ops. (@jquesnelle) ([#28169](https://github.com/NousResearch/hermes-agent/pull/28169))
- Consolidate ACP browser bootstrap into `install.{sh,ps1}`. (@alt-glitch) ([#27851](https://github.com/NousResearch/hermes-agent/pull/27851))
- `hermes update` quarantines live `hermes.exe`. ([#26677](https://github.com/NousResearch/hermes-agent/pull/26677))
- Discord voice opus decoding on Windows. ([#33182](https://github.com/NousResearch/hermes-agent/pull/33182))
- Windows Docker Desktop compatible compose file. (@Sunil123135) ([#31031](https://github.com/NousResearch/hermes-agent/pull/31031))
---
## 🖥️ Web Dashboard
- Hardened Slack socket recovery + Windows restart dedupe. ([#28873](https://github.com/NousResearch/hermes-agent/pull/28873))
- Web dashboard: migrate checkboxes to `@nous-research/ui` + design-system polish. (@austinpickett) ([#28814](https://github.com/NousResearch/hermes-agent/pull/28814))
- Web dashboard: collapsible sidebar. (@austinpickett) ([#33421](https://github.com/NousResearch/hermes-agent/pull/33421))
- Dashboard typography & contrast pass. (salvage of [#28832](https://github.com/NousResearch/hermes-agent/pull/28832)) ([#30714](https://github.com/NousResearch/hermes-agent/pull/30714))
- Skills page: lazy-fetch catalog instead of bundling 34MB into JS. ([#33809](https://github.com/NousResearch/hermes-agent/pull/33809))
---
## 🐳 Docker
- **s6-overlay container supervision** — abstract `ServiceManager` protocol (systemd/launchd/Windows/s6 backends), per-profile gateway supervision in-container, container-restart reconciliation, hadolint/shellcheck CI. (salvage of [#30136](https://github.com/NousResearch/hermes-agent/pull/30136), @benbarclay) ([#31760](https://github.com/NousResearch/hermes-agent/pull/31760))
- Auto-redirect `gateway run` to supervised mode inside the s6 image. (@benbarclay) ([#33583](https://github.com/NousResearch/hermes-agent/pull/33583))
- Tee supervised gateway stdout to docker logs. (@benbarclay) ([#33621](https://github.com/NousResearch/hermes-agent/pull/33621))
- Drop `docker exec` to hermes uid before invoking the CLI. (@benbarclay) ([#33628](https://github.com/NousResearch/hermes-agent/pull/33628))
- Align HOME for dashboard and s6 gateway services. (@Dusk1e) ([#33481](https://github.com/NousResearch/hermes-agent/pull/33481))
- Bake build-time git SHA into image so `hermes dump` reports it. (@benbarclay) ([#33655](https://github.com/NousResearch/hermes-agent/pull/33655))
- `hermes update` prints `docker pull` guidance instead of bogus git error. (@benbarclay) ([#33659](https://github.com/NousResearch/hermes-agent/pull/33659))
- Upgrade Node to 22 LTS via multi-stage from `node:22-bookworm-slim`. (@benbarclay) ([#33060](https://github.com/NousResearch/hermes-agent/pull/33060))
- Drop `build-essential` from apt install. (@benbarclay) ([#33028](https://github.com/NousResearch/hermes-agent/pull/33028))
- Propagate env through s6 to cont-init and main CMD. ([#32412](https://github.com/NousResearch/hermes-agent/pull/32412))
- Targeted chown to preserve host file ownership in `HERMES_HOME`. ([#33033](https://github.com/NousResearch/hermes-agent/pull/33033))
- `mkdir HERMES_HOME` as root in stage2 before chown / privilege drop. ([#33078](https://github.com/NousResearch/hermes-agent/pull/33078))
- chown `ui-tui` and `node_modules` on UID remap so TUI esbuild works. ([#33045](https://github.com/NousResearch/hermes-agent/pull/33045))
- Include `anthropic`, `bedrock`, `azure-identity` extras in image. ([#30504](https://github.com/NousResearch/hermes-agent/pull/30504))
- Stop pushing per-commit SHA tags to Docker Hub. ([#29387](https://github.com/NousResearch/hermes-agent/pull/29387))
- Simplify Docker tagging — push both `:main` and `:latest` on main push. ([#33225](https://github.com/NousResearch/hermes-agent/pull/33225))
- Test slicing across GH actions jobs. (@ethernet8023) ([#30575](https://github.com/NousResearch/hermes-agent/pull/30575))
- Discover agent-browser Chromium binary at boot. ([#33184](https://github.com/NousResearch/hermes-agent/pull/33184))
---
## 🌐 API Server
- **Session control API** — `/api/sessions/*` (list/create/read/patch/delete/fork) + SSE-streaming chat. (salvages [#29302](https://github.com/NousResearch/hermes-agent/pull/29302) by @Codename-11 + multimodal followup by @Schwartz10) ([#33134](https://github.com/NousResearch/hermes-agent/pull/33134))
- `GET /v1/skills` and `/v1/toolsets`. ([#33016](https://github.com/NousResearch/hermes-agent/pull/33016))
- Coerce stringified booleans in stream/store/approval payloads. (salvage [#26639](https://github.com/NousResearch/hermes-agent/pull/26639)) ([#27293](https://github.com/NousResearch/hermes-agent/pull/27293))
- Honor `key_env` in auth-failure fallback resolution. ([#30840](https://github.com/NousResearch/hermes-agent/pull/30840))
---
## 🎟️ ACP (VS Code / Zed / JetBrains)
- Session edit auto-approval modes. (salvage of [#27034](https://github.com/NousResearch/hermes-agent/pull/27034)) ([#27862](https://github.com/NousResearch/hermes-agent/pull/27862))
- Enrich Zed permission cards — command in title + `reject_always`. ([#28148](https://github.com/NousResearch/hermes-agent/pull/28148))
- Replay session history before responding to `session/load`. ([#26957](https://github.com/NousResearch/hermes-agent/pull/26957), [#26943](https://github.com/NousResearch/hermes-agent/pull/26943))
- Plugin-transformed final_response delivered through streaming gate. ([#31433](https://github.com/NousResearch/hermes-agent/pull/31433))
---
## 🔌 Plugin Surface
- `register_tts_provider()` plugin hook. (salvage of [#30420](https://github.com/NousResearch/hermes-agent/pull/30420)) ([#31745](https://github.com/NousResearch/hermes-agent/pull/31745))
- `register_transcription_provider()` hook + `stt.providers` command-provider registry. (salvage of [#30493](https://github.com/NousResearch/hermes-agent/pull/30493)) ([#31907](https://github.com/NousResearch/hermes-agent/pull/31907))
- `register_auxiliary_task()` in PluginContext API. (salvage [#29817](https://github.com/NousResearch/hermes-agent/pull/29817)) ([#31177](https://github.com/NousResearch/hermes-agent/pull/31177))
- Bundled `security-guidance` plugin. ([#33131](https://github.com/NousResearch/hermes-agent/pull/33131))
- Discord and Mattermost migrated to bundled plugins. ([#30591](https://github.com/NousResearch/hermes-agent/pull/30591), [#31748](https://github.com/NousResearch/hermes-agent/pull/31748))
- ntfy as platform plugin. ([#30867](https://github.com/NousResearch/hermes-agent/pull/30867))
- Surface category-namespaced plugins in `hermes plugins list`. ([#27187](https://github.com/NousResearch/hermes-agent/pull/27187))
- Plugin discovery failures raised to WARNING level. ([#28318](https://github.com/NousResearch/hermes-agent/pull/28318))
- `hermes_plugins` included in gateway.log component filter. ([#28313](https://github.com/NousResearch/hermes-agent/pull/28313))
- Seed plugin extras before `is_connected` gate. ([#31703](https://github.com/NousResearch/hermes-agent/pull/31703))
- Dashboard: allowlist plugin assets + denylist subprocess-influencing env vars. ([#32277](https://github.com/NousResearch/hermes-agent/pull/32277))
---
## 📦 Distribution & Install
- Install-method stamping + Docker detection. (@alt-glitch) ([#27843](https://github.com/NousResearch/hermes-agent/pull/27843))
- Nix `#messaging` and `#full` package variants. (@alt-glitch) ([#33108](https://github.com/NousResearch/hermes-agent/pull/33108))
- Pre-load messaging gateway deps via `--extra messaging`. (salvage [#26394](https://github.com/NousResearch/hermes-agent/pull/26394)) ([#27558](https://github.com/NousResearch/hermes-agent/pull/27558))
- Avoid piping installer directly into `iex` (Windows). ([#28347](https://github.com/NousResearch/hermes-agent/pull/28347))
- Ship bundled skills in wheel. ([#28421](https://github.com/NousResearch/hermes-agent/pull/28421))
- Ship dashboard plugin assets in wheel. ([#28406](https://github.com/NousResearch/hermes-agent/pull/28406))
- Make Camofox lazy-installed instead of eager. ([#27055](https://github.com/NousResearch/hermes-agent/pull/27055))
- Wire STT lazy-install into transcription_tools.py. ([#30256](https://github.com/NousResearch/hermes-agent/pull/30256))
---
## 🐛 Notable Bug Fixes (highlights only)
- Match bare custom provider by active base URL in `hermes model`. ([#28908](https://github.com/NousResearch/hermes-agent/pull/28908))
- Route `auxiliary.vision.provider=openai` to api.openai.com, skip text-only main. ([#31452](https://github.com/NousResearch/hermes-agent/pull/31452))
- Lint: skip per-file shell linter when LSP will handle the file. ([#29054](https://github.com/NousResearch/hermes-agent/pull/29054))
- Treat empty credential pool entries as unauthenticated in `/model` picker. ([#28312](https://github.com/NousResearch/hermes-agent/pull/28312))
- Reverted within window: Firecrawl integration tag, send_message @username auto-mentions, Telegram quick-command-only menus, Telegram pin-on-turn.
---
## 🧪 Testing
- Disarm lazy-install probe so `_HAS_FASTER_WHISPER` patches work. ([#30334](https://github.com/NousResearch/hermes-agent/pull/30334))
- Cover default board dashboard pin. ([#28361](https://github.com/NousResearch/hermes-agent/pull/28361))
- Cover `_task_dict` `task_age` fallback. ([#28365](https://github.com/NousResearch/hermes-agent/pull/28365))
- Allowlist `tmp_path` for `kanban_notify` artifact delivery tests. ([#30851](https://github.com/NousResearch/hermes-agent/pull/30851), [#30852](https://github.com/NousResearch/hermes-agent/pull/30852))
- Cover null output stream terminal events in Codex. ([#33137](https://github.com/NousResearch/hermes-agent/pull/33137))
---
## 📚 Documentation
- **30-day docs overhaul** — full correctness audit, every PR in the window covered, Nous Portal weave, sidebar reorg. ([#33782](https://github.com/NousResearch/hermes-agent/pull/33782))
- Dedicated Nous Portal integration page and setup guide. ([#31296](https://github.com/NousResearch/hermes-agent/pull/31296))
- Providers: move Nous Portal first, Google Gemini OAuth last. ([#31287](https://github.com/NousResearch/hermes-agent/pull/31287))
- `session_search` rewrite for single-shape tool. ([#27840](https://github.com/NousResearch/hermes-agent/pull/27840))
- Kanban: document failure_limit, max_retries, inline create shortcuts, goals & kanban settings. ([#28357](https://github.com/NousResearch/hermes-agent/pull/28357), [#28358](https://github.com/NousResearch/hermes-agent/pull/28358), [#28359](https://github.com/NousResearch/hermes-agent/pull/28359), [#28360](https://github.com/NousResearch/hermes-agent/pull/28360), [#28362](https://github.com/NousResearch/hermes-agent/pull/28362))
- Kanban Codex lane skill. ([#28430](https://github.com/NousResearch/hermes-agent/pull/28430))
- xAI OAuth: note X Premium+ also unlocks Grok OAuth. ([#29055](https://github.com/NousResearch/hermes-agent/pull/29055))
- Docs site: Docker audio bridge notes, "Installing more tools in the container", xurl auth HOME in Docker.
- Email: clarify gateway vs Himalaya setup. (@helix4u) ([#33634](https://github.com/NousResearch/hermes-agent/pull/33634))
- Auth docs: replace stale `hermes login` references with `hermes auth add`. ([#32859](https://github.com/NousResearch/hermes-agent/pull/32859))
---
## 👥 Contributors
### Core
- @teknium1 (lead)
### Notable salvages & cherry-picks
- **@benbarclay** — s6-overlay container supervision (29 commits salvaged), Node 22 LTS upgrade, build-essential cleanup, `gateway run` auto-redirect in s6, tee supervised stdout to docker logs, `hermes update` Docker guidance, build-time SHA stamping
- **@OutThisLife** — `mouse_tracking` DEC mode presets
- **@jquesnelle** — Windows installer hardening, `--branch` flag for `hermes update`, install.ps1 BOM strip / commit-pin
- **@alt-glitch** — Windows `dep_ensure` bootstrap, Nix package variants (`.#messaging`, `.#full`), install-method stamping, ACP browser bootstrap consolidation
- **@austinpickett** — `/update` slash command, dashboard checkboxes → `@nous-research/ui`, mobile dashboard polish, collapsible sidebar
- **@ethernet8023** — CI test slicing across GH Actions jobs, TUI clipboard copy fix
- **@kshitijk4poor** — doctor section banner + fail-and-issue helpers extraction, post-tag salvage cluster (curator-fallout, kanban SQLite hardening, install world-readable uv dirs, xAI bare-code paste)
- **@rewbs** — Nous JWT inference switch + refresh-token replay fix
- **@Codename-11** + **@Schwartz10** — session control API (REST + SSE + multimodal followup)
- **@Niraven** — kanban swarm topology helper
- **@Interstellar-code** — kanban worker visibility endpoints
- **@adybag14-cyber** — termux cold-start optimizations (multiple PRs)
- **@qike-ms** — Telegram in-place status edits design
- **@sprmn24** — ntfy adapter
- **@Jaaneek** — xAI Web Search provider plugin
- **@yannsunn** — xAI upstream adapter for `hermes proxy`
- **@Cybourgeoisie** — OpenRouter sticky routing via session_id
- **@memosr** — Nous Portal base_url allowlist validation
- **@Sunil123135** — Windows Docker Desktop compose file
- **@Dusk1e** — Docker HOME alignment for dashboard + s6 gateway services
- **@beardthelion** — opencode-go anthropic_messages routing
- **@YLChen-007** — Skills Guard multi-word prompt patterns
- **@roadhero** — env_passthrough GHSA-rhgp-j443-p4rf filter
- **@Zyrixtrex** — Google Chat OAuth credential persistence hardening
- **@briandevans**, **@tomqiaozc** — defense-in-depth read-deny on credential stores
- **@PratikRai0101** — control-plane file write protection
- **@helix4u**, **@Bartok9**, **@zccyman** — auxiliary fallback ladder components
- **@ms-alan**, **@ticketclosed-wontfix**, **@donovan-yohan** — TUI session orchestrator + follow-ups
- **@daimon-nous[bot]** — cron per-job profile support
- **@bisko** — re-pad `reasoning_content` on cross-provider fallback
### All Contributors
@02356abc, @0xchainer, @0xDevNinja, @0xjackyang, @0xsir0000, @0z1-ghb, @8bit64k, @aaronlab, @AceWattGit,
@ACR27, @adam91holt, @AdamPlatin123, @Ade5954, @AdityaRajeshGadgil, @adybag14-cyber, @AhmetArif0, @ai-hana-ai,
@alaamohanad169-ship-it, @alber70g, @albert748, @alt-glitch, @aqilaziz, @argabor, @asdlem, @austinpickett,
@avifenesh, @awizemann, @B0Tch1, @Bartok9, @BaxBit, @Beandon13, @beardthelion, @benbarclay, @bensargotest-sys,
@binhnt92, @bird, @bisko, @BlackishGreen33, @booker1207, @bradhallett, @briandevans, @Brixyy, @brndnsvr,
@BROCCOLO1D, @btorresgil, @burjorjee, @carltonawong, @Carry00, @chaconne67, @chdlc, @chromalinx, @ChyuWei,
@CipherFrame, @cmullins70, @CNSeniorious000, @codeblackhole1024, @Codename-11, @colin-chang, @counterposition,
@cresslank, @CryptoByz, @cyb0rgk1tty, @Cybourgeoisie, @daizhonggeng, @darvsum, @davidcampbelldc, @deas,
@dgians, @dillweed, @DoGMaTiiC, @donovan-yohan, @draplater, @Drexuxux, @dskwe, @dsr-restyn, @Dusk1e,
@dusterbloom, @duyua9, @egilewski, @el-analista, @eliteworkstation94-ai, @eloklam, @EloquentBrush0x, @emonty,
@emozilla, @erhnysr, @erikengervall, @Erosika, @ether-btc, @ethernet8023, @EvilHumphrey, @fabiosiqueira,
@falasi, @falconexe, @fardoche6, @felix-windsor, @Fewmanism, @ffr31mr, @flamiinngo, @flanny7, @flooryyyy,
@fonhal, @francip, @fujinice, @gianfrancopiana, @glennc, @Glucksberg, @godlin-gh, @Grogger, @guillaumemeyer,
@Gutslabs, @H-Ali13381, @hanzckernel, @haran2001, @hawknewton, @hayka-pacha, @hehehe0803, @helix4u, @HenkDz,
@Hermes, @hermesagent26, @Hinotoi-agent, @hongchen1993, @honor2030, @houenyang-momo, @ht1072, @hueilau,
@iamfoz, @ilonagaja509-glitch, @InB4DevOps, @indigokarasu, @Interstellar-code, @iqdoctor, @iRonin, @Jaaneek,
@JabberELF, @jacevys, @jackey8616, @jackjin1997, @jdelmerico, @jfuenmayor, @Jiahui-Gu, @JimLiu, @joe102084,
@JohnC1009, @jonpol01, @Jpalmer95, @Julientalbot, @justemu, @justincc, @jvinals, @karthikeyann, @kasunvinod,
@kchuang1015, @kenyonxu, @khungate, @kiranvk-2011, @kjames2001, @konsisumer, @kpadilha, @kriscolab,
@krislidimo, @kronexoi, @kshitijk4poor, @kunci115, @Kylejeong2, @kylekahraman, @LaPhilosophie, @leeseoki0,
@lemassykoi, @Lempkey, @LeonJS, @LeonSGP43, @lidge-jun, @LifeJiggy, @liuhao1024, @LizerAIDev, @loicnico96,
@loongfay, @m0n3r0, @malaiwah, @matthewlai, @mavrickdeveloper, @maxmilian, @McClean-Edison, @memosr,
@Mind-Dragon, @momowind, @MoonJuhan, @MoonRay305, @moortekweb-art, @MorAlekss, @ms-alan, @Nami4D,
@nehaaprasaad, @nekwo, @nftpoetrist, @NickLarcombe, @nidhi-singh02, @Niraven, @nnnet, @noctilust, @novax635,
@nthrow, @nv-kasikritc, @nycomar, @OCWC22, @oemtalks, @OmX, @ooovenenoso, @orcool, @oseftg, @outsourc-e,
@OutThisLife, @Paperclip, @PaTTeeL, @pepelax, @phoenixshen, @Pluviobyte, @pnascimento9596, @pochi-gio, @pr7426,
@PratikRai0101, @Prithvi1994, @psionic73, @ptichalouf, @Que0x, @QuenVix, @quocanh261997, @qWaitCrypto, @Qwinty,
@r266-tech, @rak135, @rdasilva1016-ui, @rewbs, @roadhero, @rodrigoeqnit, @RonHillDev, @roycepersonalassistant,
@rudi193-cmd, @RyanRana, @sadiksaifi, @samahn0601, @samggggflynn, @SamuelZ12, @sanghyuk-seo-nexcube,
@Saurav0989, @savanne-kham, @Schrotti77, @Schwartz10, @SerenityTn, @sgtworkman, @sharziki, @shaun0927,
@shellybotmoyer, @shunsuke-hikiyama, @SimbaKingjoe, @SimoKiihamaki, @sir-ad, @Slimydog21, @slowtokki0409,
@Soju06, @someaka, @soynchux, @sprmn24, @Stark-X, @steezkelly, @stepanov1975, @stephenschoettler,
@stevehq26-bot, @steveonjava, @Strontvod, @subtract0, @Sunil123135, @superearn-fisher, @Sylw3ster, @tchanee,
@that-ambuj, @thedavidmurray, @TheOnlyMika, @therahul-yo, @thewillhuang, @ticketclosed-wontfix, @Timur00Kh,
@tomqiaozc, @Tosko4, @Tranquil-Flow, @tw2818, @uzunkuyruk, @vaddisrinivas, @vanthinh6886, @vgocoder,
@victorGPT, @vynxevainglory-ai, @waefrebeorn, @walli, @wangpuv, @wanwan2qq, @wesleysimplicio, @worlldz,
@wpengpeng168, @WuKongAI-CMU, @wuli666, @Wysie, @wysie, @xxxigm, @yannsunn, @YanzhongSu, @YarrowQiao, @ygd58,
@YLChen-007, @yoniebans, @yu-xin-c, @YuanHanzhong, @zapabob, @zccyman, @ziliangpeng, @zwolniony, @Zyrixtrex
---
**Full Changelog**: [v2026.5.16...v2026.5.28](https://github.com/NousResearch/hermes-agent/compare/v2026.5.16...v2026.5.28)

View File

@@ -1,110 +0,0 @@
# Hermes Agent v0.15.1 (v2026.5.29)
**Release Date:** May 29, 2026
**Since v0.15.0:** 28 commits · 21 merged PRs · hotfix release · 9 contributors
> **The Patch Release.** A same-day hotfix for v0.15.0. Headline fix: the dashboard infinite-reload loop that hit anyone running v0.15.0 in loopback mode (Docker, hosted Hermes, fresh installs). A handful of other v0.15.0 follow-ups go along for the ride — kanban worker SIGTERM, `/model` picker unification, `/yolo` session bypass, the full 19,932-entry skills.sh catalog, `.md` media delivery restoration, gateway probe-stepdown safety, web-URL redaction passthrough, kanban worker vision on referenced images, hindsight observation-default. Docker users get an explicit `--insecure` opt-in env var (no more bind-host inference), MCP server bare-command PATH resolution, and arm64 PR-build cache fixes.
---
## ✨ Highlights
- **Dashboard 401 reload loop fixed** — In loopback mode the dashboard's identity probe (`/api/auth/me`) returns 401 by design, but v0.15.0's stale-token reload guard treated every 401 as a rotated session token and full-page-reloaded to pick up a fresh one. Every successful sibling call cleared the one-shot reload guard, so the page reload-looped forever (Firefox: "Navigated to /sessions" storm; Chrome: React re-render storm). Fix adds an `allowUnauthorized` opt-out to `fetchJSON` that skips only the loopback stale-token reload — 401 still throws so `AuthWidget` swallows it, gated-mode `login_url` redirects are unaffected. Closes [#34206](https://github.com/NousResearch/hermes-agent/issues/34206), [#34202](https://github.com/NousResearch/hermes-agent/issues/34202). ([#30698](https://github.com/NousResearch/hermes-agent/pull/30698) — @austinpickett)
- **Docker dashboard `--insecure` is now an explicit env opt-in, never derived from bind host** — Previously the Docker entrypoint inferred `--insecure` when the dashboard bound to a non-loopback host. That conflated "I want LAN access" with "I want to disable the same-origin guard." The fix splits them: bind host is bind host, and disabling the dashboard's loopback auth requires an explicit `HERMES_DASHBOARD_INSECURE=1`. Existing setups that genuinely wanted insecure binding must now set the env var. ([#34188](https://github.com/NousResearch/hermes-agent/pull/34188), [#34204](https://github.com/NousResearch/hermes-agent/pull/34204) — @benbarclay)
- **MCP bare command resolution under Docker** — MCP servers configured with bare commands (`npx`, `npm`, `node`) now resolve against `/usr/local/bin` so they actually launch inside the Docker image where those binaries live. v0.15.0 left these failing silently in containers when the agent's effective PATH didn't include the Node toolchain location. ([#34186](https://github.com/NousResearch/hermes-agent/pull/34186) — @benbarclay)
- **Skills page sidebar / source pills restored** — A stale `useMemo` dependency in the new dashboard skills page collapsed the source pills and category sidebar to "All" only. Fixed; both surfaces now reflect the live catalog state. ([#34194](https://github.com/NousResearch/hermes-agent/pull/34194))
- **Kanban worker can be killed again** — `SIGTERM` on a kanban worker was being absorbed by an intermediate process and the worker stayed running. Closes [#28181](https://github.com/NousResearch/hermes-agent/issues/28181). ([#34045](https://github.com/NousResearch/hermes-agent/pull/34045))
- **Full skills.sh catalog (858 → 19,932 entries)** — The skills hub page was pulling a partial paginated catalog. The fetch now walks the sitemap, so all 19,932 skills.sh entries surface in the picker instead of just the first 858. ([#34025](https://github.com/NousResearch/hermes-agent/pull/34025))
---
## 🐛 Bug Fixes
### Dashboard / Web
- **`/api/auth/me` 401 no longer triggers reload loop** in loopback mode — ([#30698](https://github.com/NousResearch/hermes-agent/pull/30698) — @austinpickett)
- **Skills page source pills + category sidebar restored** — stale `useMemo` dep ([#34194](https://github.com/NousResearch/hermes-agent/pull/34194))
### Docker
- **`--insecure` is now explicit opt-in via env var**, not derived from bind host ([#34188](https://github.com/NousResearch/hermes-agent/pull/34188) — @benbarclay)
- **Dashboard test suite repaired** to match the insecure-opt-in fix ([#34204](https://github.com/NousResearch/hermes-agent/pull/34204) — @benbarclay)
- **arm64 PR builds skip the GHA cache** to avoid cache-thrash on cross-arch builders ([#33704](https://github.com/NousResearch/hermes-agent/pull/33704) — @BROCCOLO1D)
### MCP
- **Bare `npx`/`npm`/`node` resolve against `/usr/local/bin`** for Docker compatibility ([#34186](https://github.com/NousResearch/hermes-agent/pull/34186) — @benbarclay)
### Kanban
- **Worker SIGTERM actually terminates the process** ([#34045](https://github.com/NousResearch/hermes-agent/pull/34045))
- **Workers receive images referenced in task bodies** for vision-capable models ([#34210](https://github.com/NousResearch/hermes-agent/pull/34210))
### Gateway
- **`.md` files deliver again** — media-delivery validation defaults to denylist-only instead of an overly-narrow allowlist ([#34022](https://github.com/NousResearch/hermes-agent/pull/34022))
- **Probe stepdown safety** — on a context-overflow without an explicit provider context limit, the agent no longer steps down to a smaller model based on an unknown ceiling (salvage of [#33673](https://github.com/NousResearch/hermes-agent/pull/33673)) ([#33826](https://github.com/NousResearch/hermes-agent/pull/33826))
### CLI
- **`/yolo` mid-session enables the per-session bypass** instead of just toggling the env var (which the running agent had already snapshotted) ([#33931](https://github.com/NousResearch/hermes-agent/pull/33931) — @kshitijk4poor)
- **`/model` and `hermes model` show the same list**, plus disk cache for picker startup ([#33867](https://github.com/NousResearch/hermes-agent/pull/33867))
### Skills
- **Full skills.sh catalog via sitemap** — 858 → 19,932 entries ([#34025](https://github.com/NousResearch/hermes-agent/pull/34025))
### Redaction
- **Web URLs pass through unchanged** — the redactor was eating query parameters that looked credential-shaped ([#34029](https://github.com/NousResearch/hermes-agent/pull/34029))
---
## ✨ Small Features
- **Hindsight default narrowed to observation-only** for `recall_types` — tool path is also narrowed ([#34079](https://github.com/NousResearch/hermes-agent/pull/34079) — @nicoloboschi, follow-up [#34091](https://github.com/NousResearch/hermes-agent/pull/4df62d239e38bf8c212a595721c9c01e176f6c3a) — @kshitijk4poor)
- **Memory providers receive completed-turn message context** — salvage of [#28065](https://github.com/NousResearch/hermes-agent/pull/28065) ([#34097](https://github.com/NousResearch/hermes-agent/pull/34097) — @kshitijk4poor, credit to @devwdave)
---
## 📚 Documentation
- **`--no-supervise` / `HERMES_GATEWAY_NO_SUPERVISE` documented** in the reference docs (follow-up to [#33583](https://github.com/NousResearch/hermes-agent/pull/33583)) ([#33751](https://github.com/NousResearch/hermes-agent/pull/33751) — @r266-tech)
---
## 🛠️ Infrastructure
- **Vercel deploy workflow accepts `workflow_dispatch`** so docs deploys can be manually triggered ([#34081](https://github.com/NousResearch/hermes-agent/pull/34081))
- **`@nous-research/ui` bumped to 0.18.2** (Nix `npmDepsHash` also updated to match) ([#34193](https://github.com/NousResearch/hermes-agent/pull/34193) follow-ups — @austinpickett)
---
## 👥 Contributors
### Core
- @teknium1
### Community
- @austinpickett — dashboard 401 reload-loop fix (the headline), `@nous-research/ui` bump, Nix `npmDepsHash` updates
- @benbarclay — Docker `--insecure` opt-in, MCP bare-command resolution, dashboard test repair
- @kshitijk4poor`/yolo` session bypass, completed-turn memory context salvage, hindsight follow-up docs
- @nicoloboschi — hindsight `recall_types` observation default
- @BROCCOLO1D — arm64 PR build cache fix
- @r266-tech — `--no-supervise` reference docs
- @yangguangjin — probe stepdown safety (salvage of @yanghd's #33673)
- @devwdave — completed-turn memory context (credited via salvage)
- @andrewhosf — co-author
### Issue Reporters (the 401 loop)
- @routesmith ([#34206](https://github.com/NousResearch/hermes-agent/issues/34206))
- @beeaton ([#34202](https://github.com/NousResearch/hermes-agent/issues/34202))
---
**Full Changelog**: [v2026.5.28...v2026.5.29](https://github.com/NousResearch/hermes-agent/compare/v2026.5.28...v2026.5.29)

View File

@@ -1,383 +0,0 @@
# Hermes Agent v0.2.0 (v2026.3.12)
**Release Date:** March 12, 2026
> First tagged release since v0.1.0 (the initial pre-public foundation). In just over two weeks, Hermes Agent went from a small internal project to a full-featured AI agent platform — thanks to an explosion of community contributions. This release covers **216 merged pull requests** from **63 contributors**, resolving **119 issues**.
---
## ✨ Highlights
- **Multi-Platform Messaging Gateway** — Telegram, Discord, Slack, WhatsApp, Signal, Email (IMAP/SMTP), and Home Assistant platforms with unified session management, media attachments, and per-platform tool configuration.
- **MCP (Model Context Protocol) Client** — Native MCP support with stdio and HTTP transports, reconnection, resource/prompt discovery, and sampling (server-initiated LLM requests). ([#291](https://github.com/NousResearch/hermes-agent/pull/291) — @0xbyt4, [#301](https://github.com/NousResearch/hermes-agent/pull/301), [#753](https://github.com/NousResearch/hermes-agent/pull/753))
- **Skills Ecosystem** — 70+ bundled and optional skills across 15+ categories with a Skills Hub for community discovery, per-platform enable/disable, conditional activation based on tool availability, and prerequisite validation. ([#743](https://github.com/NousResearch/hermes-agent/pull/743) — @teyrebaz33, [#785](https://github.com/NousResearch/hermes-agent/pull/785) — @teyrebaz33)
- **Centralized Provider Router** — Unified `call_llm()`/`async_call_llm()` API replaces scattered provider logic across vision, summarization, compression, and trajectory saving. All auxiliary consumers route through a single code path with automatic credential resolution. ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003))
- **ACP Server** — VS Code, Zed, and JetBrains editor integration via the Agent Communication Protocol standard. ([#949](https://github.com/NousResearch/hermes-agent/pull/949))
- **CLI Skin/Theme Engine** — Data-driven visual customization: banners, spinners, colors, branding. 7 built-in skins + custom YAML skins.
- **Git Worktree Isolation** — `hermes -w` launches isolated agent sessions in git worktrees for safe parallel work on the same repo. ([#654](https://github.com/NousResearch/hermes-agent/pull/654))
- **Filesystem Checkpoints & Rollback** — Automatic snapshots before destructive operations with `/rollback` to restore. ([#824](https://github.com/NousResearch/hermes-agent/pull/824))
- **3,289 Tests** — From near-zero test coverage to a comprehensive test suite covering agent, gateway, tools, cron, and CLI.
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- Centralized provider router with `resolve_provider_client()` + `call_llm()` API ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003))
- Nous Portal as first-class provider in setup ([#644](https://github.com/NousResearch/hermes-agent/issues/644))
- OpenAI Codex (Responses API) with ChatGPT subscription support ([#43](https://github.com/NousResearch/hermes-agent/pull/43)) — @grp06
- Codex OAuth vision support + multimodal content adapter
- Validate `/model` against live API instead of hardcoded lists
- Self-hosted Firecrawl support ([#460](https://github.com/NousResearch/hermes-agent/pull/460)) — @caentzminger
- Kimi Code API support ([#635](https://github.com/NousResearch/hermes-agent/pull/635)) — @christomitov
- MiniMax model ID update ([#473](https://github.com/NousResearch/hermes-agent/pull/473)) — @tars90percent
- OpenRouter provider routing configuration (provider_preferences)
- Nous credential refresh on 401 errors ([#571](https://github.com/NousResearch/hermes-agent/pull/571), [#269](https://github.com/NousResearch/hermes-agent/pull/269)) — @rewbs
- z.ai/GLM, Kimi/Moonshot, MiniMax, Azure OpenAI as first-class providers
- Unified `/model` and `/provider` into single view
### Agent Loop & Conversation
- Simple fallback model for provider resilience ([#740](https://github.com/NousResearch/hermes-agent/pull/740))
- Shared iteration budget across parent + subagent delegation
- Iteration budget pressure via tool result injection
- Configurable subagent provider/model with full credential resolution
- Handle 413 payload-too-large via compression instead of aborting ([#153](https://github.com/NousResearch/hermes-agent/pull/153)) — @tekelala
- Retry with rebuilt payload after compression ([#616](https://github.com/NousResearch/hermes-agent/pull/616)) — @tripledoublev
- Auto-compress pathologically large gateway sessions ([#628](https://github.com/NousResearch/hermes-agent/issues/628))
- Tool call repair middleware — auto-lowercase and invalid tool handler
- Reasoning effort configuration and `/reasoning` command ([#921](https://github.com/NousResearch/hermes-agent/pull/921))
- Detect and block file re-read/search loops after context compression ([#705](https://github.com/NousResearch/hermes-agent/pull/705)) — @0xbyt4
### Session & Memory
- Session naming with unique titles, auto-lineage, rich listing, and resume by name ([#720](https://github.com/NousResearch/hermes-agent/pull/720))
- Interactive session browser with search filtering ([#733](https://github.com/NousResearch/hermes-agent/pull/733))
- Display previous messages when resuming a session ([#734](https://github.com/NousResearch/hermes-agent/pull/734))
- Honcho AI-native cross-session user modeling ([#38](https://github.com/NousResearch/hermes-agent/pull/38)) — @erosika
- Proactive async memory flush on session expiry
- Smart context length probing with persistent caching + banner display
- `/resume` command for switching to named sessions in gateway
- Session reset policy for messaging platforms
---
## 📱 Messaging Platforms (Gateway)
### Telegram
- Native file attachments: send_document + send_video
- Document file processing for PDF, text, and Office files — @tekelala
- Forum topic session isolation ([#766](https://github.com/NousResearch/hermes-agent/pull/766)) — @spanishflu-est1918
- Browser screenshot sharing via MEDIA: protocol ([#657](https://github.com/NousResearch/hermes-agent/pull/657))
- Location support for find-nearby skill
- TTS voice message accumulation fix ([#176](https://github.com/NousResearch/hermes-agent/pull/176)) — @Bartok9
- Improved error handling and logging ([#763](https://github.com/NousResearch/hermes-agent/pull/763)) — @aydnOktay
- Italic regex newline fix + 43 format tests ([#204](https://github.com/NousResearch/hermes-agent/pull/204)) — @0xbyt4
### Discord
- Channel topic included in session context ([#248](https://github.com/NousResearch/hermes-agent/pull/248)) — @Bartok9
- DISCORD_ALLOW_BOTS config for bot message filtering ([#758](https://github.com/NousResearch/hermes-agent/pull/758))
- Document and video support ([#784](https://github.com/NousResearch/hermes-agent/pull/784))
- Improved error handling and logging ([#761](https://github.com/NousResearch/hermes-agent/pull/761)) — @aydnOktay
### Slack
- App_mention 404 fix + document/video support ([#784](https://github.com/NousResearch/hermes-agent/pull/784))
- Structured logging replacing print statements — @aydnOktay
### WhatsApp
- Native media sending — images, videos, documents ([#292](https://github.com/NousResearch/hermes-agent/pull/292)) — @satelerd
- Multi-user session isolation ([#75](https://github.com/NousResearch/hermes-agent/pull/75)) — @satelerd
- Cross-platform port cleanup replacing Linux-only fuser ([#433](https://github.com/NousResearch/hermes-agent/pull/433)) — @Farukest
- DM interrupt key mismatch fix ([#350](https://github.com/NousResearch/hermes-agent/pull/350)) — @Farukest
### Signal
- Full Signal messenger gateway via signal-cli-rest-api ([#405](https://github.com/NousResearch/hermes-agent/issues/405))
- Media URL support in message events ([#871](https://github.com/NousResearch/hermes-agent/pull/871))
### Email (IMAP/SMTP)
- New email gateway platform — @0xbyt4
### Home Assistant
- REST tools + WebSocket gateway integration ([#184](https://github.com/NousResearch/hermes-agent/pull/184)) — @0xbyt4
- Service discovery and enhanced setup
- Toolset mapping fix ([#538](https://github.com/NousResearch/hermes-agent/pull/538)) — @Himess
### Gateway Core
- Expose subagent tool calls and thinking to users ([#186](https://github.com/NousResearch/hermes-agent/pull/186)) — @cutepawss
- Configurable background process watcher notifications ([#840](https://github.com/NousResearch/hermes-agent/pull/840))
- `edit_message()` for Telegram/Discord/Slack with fallback
- `/compress`, `/usage`, `/update` slash commands
- Eliminated 3x SQLite message duplication in gateway sessions ([#873](https://github.com/NousResearch/hermes-agent/pull/873))
- Stabilize system prompt across gateway turns for cache hits ([#754](https://github.com/NousResearch/hermes-agent/pull/754))
- MCP server shutdown on gateway exit ([#796](https://github.com/NousResearch/hermes-agent/pull/796)) — @0xbyt4
- Pass session_db to AIAgent, fixing session_search error ([#108](https://github.com/NousResearch/hermes-agent/pull/108)) — @Bartok9
- Persist transcript changes in /retry, /undo; fix /reset attribute ([#217](https://github.com/NousResearch/hermes-agent/pull/217)) — @Farukest
- UTF-8 encoding fix preventing Windows crashes ([#369](https://github.com/NousResearch/hermes-agent/pull/369)) — @ch3ronsa
---
## 🖥️ CLI & User Experience
### Interactive CLI
- Data-driven skin/theme engine — 7 built-in skins (default, ares, mono, slate, poseidon, sisyphus, charizard) + custom YAML skins
- `/personality` command with custom personality + disable support ([#773](https://github.com/NousResearch/hermes-agent/pull/773)) — @teyrebaz33
- User-defined quick commands that bypass the agent loop ([#746](https://github.com/NousResearch/hermes-agent/pull/746)) — @teyrebaz33
- `/reasoning` command for effort level and display toggle ([#921](https://github.com/NousResearch/hermes-agent/pull/921))
- `/verbose` slash command to toggle debug at runtime ([#94](https://github.com/NousResearch/hermes-agent/pull/94)) — @cesareth
- `/insights` command — usage analytics, cost estimation & activity patterns ([#552](https://github.com/NousResearch/hermes-agent/pull/552))
- `/background` command for managing background processes
- `/help` formatting with command categories
- Bell-on-complete — terminal bell when agent finishes ([#738](https://github.com/NousResearch/hermes-agent/pull/738))
- Up/down arrow history navigation
- Clipboard image paste (Alt+V / Ctrl+V)
- Loading indicators for slow slash commands ([#882](https://github.com/NousResearch/hermes-agent/pull/882))
- Spinner flickering fix under patch_stdout ([#91](https://github.com/NousResearch/hermes-agent/pull/91)) — @0xbyt4
- `--quiet/-Q` flag for programmatic single-query mode
- `--fuck-it-ship-it` flag to bypass all approval prompts ([#724](https://github.com/NousResearch/hermes-agent/pull/724)) — @dmahan93
- Tools summary flag ([#767](https://github.com/NousResearch/hermes-agent/pull/767)) — @luisv-1
- Terminal blinking fix on SSH ([#284](https://github.com/NousResearch/hermes-agent/pull/284)) — @ygd58
- Multi-line paste detection fix ([#84](https://github.com/NousResearch/hermes-agent/pull/84)) — @0xbyt4
### Setup & Configuration
- Modular setup wizard with section subcommands and tool-first UX
- Container resource configuration prompts
- Backend validation for required binaries
- Config migration system (currently v7)
- API keys properly routed to .env instead of config.yaml ([#469](https://github.com/NousResearch/hermes-agent/pull/469)) — @ygd58
- Atomic write for .env to prevent API key loss on crash ([#954](https://github.com/NousResearch/hermes-agent/pull/954))
- `hermes tools` — per-platform tool enable/disable with curses UI
- `hermes doctor` for health checks across all configured providers
- `hermes update` with auto-restart for gateway service
- Show update-available notice in CLI banner
- Multiple named custom providers
- Shell config detection improvement for PATH setup ([#317](https://github.com/NousResearch/hermes-agent/pull/317)) — @mehmetkr-31
- Consistent HERMES_HOME and .env path resolution ([#51](https://github.com/NousResearch/hermes-agent/pull/51), [#48](https://github.com/NousResearch/hermes-agent/pull/48)) — @deankerr
- Docker backend fix on macOS + subagent auth for Nous Portal ([#46](https://github.com/NousResearch/hermes-agent/pull/46)) — @rsavitt
---
## 🔧 Tool System
### MCP (Model Context Protocol)
- Native MCP client with stdio + HTTP transports ([#291](https://github.com/NousResearch/hermes-agent/pull/291) — @0xbyt4, [#301](https://github.com/NousResearch/hermes-agent/pull/301))
- Sampling support — server-initiated LLM requests ([#753](https://github.com/NousResearch/hermes-agent/pull/753))
- Resource and prompt discovery
- Automatic reconnection and security hardening
- Banner integration, `/reload-mcp` command
- `hermes tools` UI integration
### Browser
- Local browser backend — zero-cost headless Chromium (no Browserbase needed)
- Console/errors tool, annotated screenshots, auto-recording, dogfood QA skill ([#745](https://github.com/NousResearch/hermes-agent/pull/745))
- Screenshot sharing via MEDIA: on all messaging platforms ([#657](https://github.com/NousResearch/hermes-agent/pull/657))
### Terminal & Execution
- `execute_code` sandbox with json_parse, shell_quote, retry helpers
- Docker: custom volume mounts ([#158](https://github.com/NousResearch/hermes-agent/pull/158)) — @Indelwin
- Daytona cloud sandbox backend ([#451](https://github.com/NousResearch/hermes-agent/pull/451)) — @rovle
- SSH backend fix ([#59](https://github.com/NousResearch/hermes-agent/pull/59)) — @deankerr
- Shell noise filtering and login shell execution for environment consistency
- Head+tail truncation for execute_code stdout overflow
- Configurable background process notification modes
### File Operations
- Filesystem checkpoints and `/rollback` command ([#824](https://github.com/NousResearch/hermes-agent/pull/824))
- Structured tool result hints (next-action guidance) for patch and search_files ([#722](https://github.com/NousResearch/hermes-agent/issues/722))
- Docker volumes passed to sandbox container config ([#687](https://github.com/NousResearch/hermes-agent/pull/687)) — @manuelschipper
---
## 🧩 Skills Ecosystem
### Skills System
- Per-platform skill enable/disable ([#743](https://github.com/NousResearch/hermes-agent/pull/743)) — @teyrebaz33
- Conditional skill activation based on tool availability ([#785](https://github.com/NousResearch/hermes-agent/pull/785)) — @teyrebaz33
- Skill prerequisites — hide skills with unmet dependencies ([#659](https://github.com/NousResearch/hermes-agent/pull/659)) — @kshitijk4poor
- Optional skills — shipped but not activated by default
- `hermes skills browse` — paginated hub browsing
- Skills sub-category organization
- Platform-conditional skill loading
- Atomic skill file writes ([#551](https://github.com/NousResearch/hermes-agent/pull/551)) — @aydnOktay
- Skills sync data loss prevention ([#563](https://github.com/NousResearch/hermes-agent/pull/563)) — @0xbyt4
- Dynamic skill slash commands for CLI and gateway
### New Skills (selected)
- **ASCII Art** — pyfiglet (571 fonts), cowsay, image-to-ascii ([#209](https://github.com/NousResearch/hermes-agent/pull/209)) — @0xbyt4
- **ASCII Video** — Full production pipeline ([#854](https://github.com/NousResearch/hermes-agent/pull/854)) — @SHL0MS
- **DuckDuckGo Search** — Firecrawl fallback ([#267](https://github.com/NousResearch/hermes-agent/pull/267)) — @gamedevCloudy; DDGS API expansion ([#598](https://github.com/NousResearch/hermes-agent/pull/598)) — @areu01or00
- **Solana Blockchain** — Wallet balances, USD pricing, token names ([#212](https://github.com/NousResearch/hermes-agent/pull/212)) — @gizdusum
- **AgentMail** — Agent-owned email inboxes ([#330](https://github.com/NousResearch/hermes-agent/pull/330)) — @teyrebaz33
- **Polymarket** — Prediction market data (read-only) ([#629](https://github.com/NousResearch/hermes-agent/pull/629))
- **OpenClaw Migration** — Official migration tool ([#570](https://github.com/NousResearch/hermes-agent/pull/570)) — @unmodeled-tyler
- **Domain Intelligence** — Passive recon: subdomains, SSL, WHOIS, DNS ([#136](https://github.com/NousResearch/hermes-agent/pull/136)) — @FurkanL0
- **Superpowers** — Software development skills ([#137](https://github.com/NousResearch/hermes-agent/pull/137)) — @kaos35
- **Hermes-Atropos** — RL environment development skill ([#815](https://github.com/NousResearch/hermes-agent/pull/815))
- Plus: arXiv search, OCR/documents, Excalidraw diagrams, YouTube transcripts, GIF search, Pokémon player, Minecraft modpack server, OpenHue (Philips Hue), Google Workspace, Notion, PowerPoint, Obsidian, find-nearby, and 40+ MLOps skills
---
## 🔒 Security & Reliability
### Security Hardening
- Path traversal fix in skill_view — prevented reading arbitrary files ([#220](https://github.com/NousResearch/hermes-agent/issues/220)) — @Farukest
- Shell injection prevention in sudo password piping ([#65](https://github.com/NousResearch/hermes-agent/pull/65)) — @leonsgithub
- Dangerous command detection: multiline bypass fix ([#233](https://github.com/NousResearch/hermes-agent/pull/233)) — @Farukest; tee/process substitution patterns ([#280](https://github.com/NousResearch/hermes-agent/pull/280)) — @dogiladeveloper
- Symlink boundary check fix in skills_guard ([#386](https://github.com/NousResearch/hermes-agent/pull/386)) — @Farukest
- Symlink bypass fix in write deny list on macOS ([#61](https://github.com/NousResearch/hermes-agent/pull/61)) — @0xbyt4
- Multi-word prompt injection bypass prevention ([#192](https://github.com/NousResearch/hermes-agent/pull/192)) — @0xbyt4
- Cron prompt injection scanner bypass fix ([#63](https://github.com/NousResearch/hermes-agent/pull/63)) — @0xbyt4
- Enforce 0600/0700 file permissions on sensitive files ([#757](https://github.com/NousResearch/hermes-agent/pull/757))
- .env file permissions restricted to owner-only ([#529](https://github.com/NousResearch/hermes-agent/pull/529)) — @Himess
- `--force` flag properly blocked from overriding dangerous verdicts ([#388](https://github.com/NousResearch/hermes-agent/pull/388)) — @Farukest
- FTS5 query sanitization + DB connection leak fix ([#565](https://github.com/NousResearch/hermes-agent/pull/565)) — @0xbyt4
- Expand secret redaction patterns + config toggle to disable
- In-memory permanent allowlist to prevent data leak ([#600](https://github.com/NousResearch/hermes-agent/pull/600)) — @alireza78a
### Atomic Writes (data loss prevention)
- sessions.json ([#611](https://github.com/NousResearch/hermes-agent/pull/611)) — @alireza78a
- Cron jobs ([#146](https://github.com/NousResearch/hermes-agent/pull/146)) — @alireza78a
- .env config ([#954](https://github.com/NousResearch/hermes-agent/pull/954))
- Process checkpoints ([#298](https://github.com/NousResearch/hermes-agent/pull/298)) — @aydnOktay
- Batch runner ([#297](https://github.com/NousResearch/hermes-agent/pull/297)) — @aydnOktay
- Skill files ([#551](https://github.com/NousResearch/hermes-agent/pull/551)) — @aydnOktay
### Reliability
- Guard all print() against OSError for systemd/headless environments ([#963](https://github.com/NousResearch/hermes-agent/pull/963))
- Reset all retry counters at start of run_conversation ([#607](https://github.com/NousResearch/hermes-agent/pull/607)) — @0xbyt4
- Return deny on approval callback timeout instead of None ([#603](https://github.com/NousResearch/hermes-agent/pull/603)) — @0xbyt4
- Fix None message content crashes across codebase ([#277](https://github.com/NousResearch/hermes-agent/pull/277))
- Fix context overrun crash with local LLM backends ([#403](https://github.com/NousResearch/hermes-agent/pull/403)) — @ch3ronsa
- Prevent `_flush_sentinel` from leaking to external APIs ([#227](https://github.com/NousResearch/hermes-agent/pull/227)) — @Farukest
- Prevent conversation_history mutation in callers ([#229](https://github.com/NousResearch/hermes-agent/pull/229)) — @Farukest
- Fix systemd restart loop ([#614](https://github.com/NousResearch/hermes-agent/pull/614)) — @voidborne-d
- Close file handles and sockets to prevent fd leaks ([#568](https://github.com/NousResearch/hermes-agent/pull/568) — @alireza78a, [#296](https://github.com/NousResearch/hermes-agent/pull/296) — @alireza78a, [#709](https://github.com/NousResearch/hermes-agent/pull/709) — @memosr)
- Prevent data loss in clipboard PNG conversion ([#602](https://github.com/NousResearch/hermes-agent/pull/602)) — @0xbyt4
- Eliminate shell noise from terminal output ([#293](https://github.com/NousResearch/hermes-agent/pull/293)) — @0xbyt4
- Timezone-aware now() for prompt, cron, and execute_code ([#309](https://github.com/NousResearch/hermes-agent/pull/309)) — @areu01or00
### Windows Compatibility
- Guard POSIX-only process functions ([#219](https://github.com/NousResearch/hermes-agent/pull/219)) — @Farukest
- Windows native support via Git Bash + ZIP-based update fallback
- pywinpty for PTY support ([#457](https://github.com/NousResearch/hermes-agent/pull/457)) — @shitcoinsherpa
- Explicit UTF-8 encoding on all config/data file I/O ([#458](https://github.com/NousResearch/hermes-agent/pull/458)) — @shitcoinsherpa
- Windows-compatible path handling ([#354](https://github.com/NousResearch/hermes-agent/pull/354), [#390](https://github.com/NousResearch/hermes-agent/pull/390)) — @Farukest
- Regex-based search output parsing for drive-letter paths ([#533](https://github.com/NousResearch/hermes-agent/pull/533)) — @Himess
- Auth store file lock for Windows ([#455](https://github.com/NousResearch/hermes-agent/pull/455)) — @shitcoinsherpa
---
## 🐛 Notable Bug Fixes
- Fix DeepSeek V3 tool call parser silently dropping multi-line JSON arguments ([#444](https://github.com/NousResearch/hermes-agent/pull/444)) — @PercyDikec
- Fix gateway transcript losing 1 message per turn due to offset mismatch ([#395](https://github.com/NousResearch/hermes-agent/pull/395)) — @PercyDikec
- Fix /retry command silently discarding the agent's final response ([#441](https://github.com/NousResearch/hermes-agent/pull/441)) — @PercyDikec
- Fix max-iterations retry returning empty string after think-block stripping ([#438](https://github.com/NousResearch/hermes-agent/pull/438)) — @PercyDikec
- Fix max-iterations retry using hardcoded max_tokens ([#436](https://github.com/NousResearch/hermes-agent/pull/436)) — @Farukest
- Fix Codex status dict key mismatch ([#448](https://github.com/NousResearch/hermes-agent/pull/448)) and visibility filter ([#446](https://github.com/NousResearch/hermes-agent/pull/446)) — @PercyDikec
- Strip \<think\> blocks from final user-facing responses ([#174](https://github.com/NousResearch/hermes-agent/pull/174)) — @Bartok9
- Fix \<think\> block regex stripping visible content when model discusses tags literally ([#786](https://github.com/NousResearch/hermes-agent/issues/786))
- Fix Mistral 422 errors from leftover finish_reason in assistant messages ([#253](https://github.com/NousResearch/hermes-agent/pull/253)) — @Sertug17
- Fix OPENROUTER_API_KEY resolution order across all code paths ([#295](https://github.com/NousResearch/hermes-agent/pull/295)) — @0xbyt4
- Fix OPENAI_BASE_URL API key priority ([#420](https://github.com/NousResearch/hermes-agent/pull/420)) — @manuelschipper
- Fix Anthropic "prompt is too long" 400 error not detected as context length error ([#813](https://github.com/NousResearch/hermes-agent/issues/813))
- Fix SQLite session transcript accumulating duplicate messages — 3-4x token inflation ([#860](https://github.com/NousResearch/hermes-agent/issues/860))
- Fix setup wizard skipping API key prompts on first install ([#748](https://github.com/NousResearch/hermes-agent/pull/748))
- Fix setup wizard showing OpenRouter model list for Nous Portal ([#575](https://github.com/NousResearch/hermes-agent/pull/575)) — @PercyDikec
- Fix provider selection not persisting when switching via hermes model ([#881](https://github.com/NousResearch/hermes-agent/pull/881))
- Fix Docker backend failing when docker not in PATH on macOS ([#889](https://github.com/NousResearch/hermes-agent/pull/889))
- Fix ClawHub Skills Hub adapter for API endpoint changes ([#286](https://github.com/NousResearch/hermes-agent/pull/286)) — @BP602
- Fix Honcho auto-enable when API key is present ([#243](https://github.com/NousResearch/hermes-agent/pull/243)) — @Bartok9
- Fix duplicate 'skills' subparser crash on Python 3.11+ ([#898](https://github.com/NousResearch/hermes-agent/issues/898))
- Fix memory tool entry parsing when content contains section sign ([#162](https://github.com/NousResearch/hermes-agent/pull/162)) — @aydnOktay
- Fix piped install silently aborting when interactive prompts fail ([#72](https://github.com/NousResearch/hermes-agent/pull/72)) — @cutepawss
- Fix false positives in recursive delete detection ([#68](https://github.com/NousResearch/hermes-agent/pull/68)) — @cutepawss
- Fix Ruff lint warnings across codebase ([#608](https://github.com/NousResearch/hermes-agent/pull/608)) — @JackTheGit
- Fix Anthropic native base URL fail-fast ([#173](https://github.com/NousResearch/hermes-agent/pull/173)) — @adavyas
- Fix install.sh creating ~/.hermes before moving Node.js directory ([#53](https://github.com/NousResearch/hermes-agent/pull/53)) — @JoshuaMart
- Fix SystemExit traceback during atexit cleanup on Ctrl+C ([#55](https://github.com/NousResearch/hermes-agent/pull/55)) — @bierlingm
- Restore missing MIT license file ([#620](https://github.com/NousResearch/hermes-agent/pull/620)) — @stablegenius49
---
## 🧪 Testing
- **3,289 tests** across agent, gateway, tools, cron, and CLI
- Parallelized test suite with pytest-xdist ([#802](https://github.com/NousResearch/hermes-agent/pull/802)) — @OutThisLife
- Unit tests batch 1: 8 core modules ([#60](https://github.com/NousResearch/hermes-agent/pull/60)) — @0xbyt4
- Unit tests batch 2: 8 more modules ([#62](https://github.com/NousResearch/hermes-agent/pull/62)) — @0xbyt4
- Unit tests batch 3: 8 untested modules ([#191](https://github.com/NousResearch/hermes-agent/pull/191)) — @0xbyt4
- Unit tests batch 4: 5 security/logic-critical modules ([#193](https://github.com/NousResearch/hermes-agent/pull/193)) — @0xbyt4
- AIAgent (run_agent.py) unit tests ([#67](https://github.com/NousResearch/hermes-agent/pull/67)) — @0xbyt4
- Trajectory compressor tests ([#203](https://github.com/NousResearch/hermes-agent/pull/203)) — @0xbyt4
- Clarify tool tests ([#121](https://github.com/NousResearch/hermes-agent/pull/121)) — @Bartok9
- Telegram format tests — 43 tests for italic/bold/code rendering ([#204](https://github.com/NousResearch/hermes-agent/pull/204)) — @0xbyt4
- Vision tools type hints + 42 tests ([#792](https://github.com/NousResearch/hermes-agent/pull/792))
- Compressor tool-call boundary regression tests ([#648](https://github.com/NousResearch/hermes-agent/pull/648)) — @intertwine
- Test structure reorganization ([#34](https://github.com/NousResearch/hermes-agent/pull/34)) — @0xbyt4
- Shell noise elimination + fix 36 test failures ([#293](https://github.com/NousResearch/hermes-agent/pull/293)) — @0xbyt4
---
## 🔬 RL & Evaluation Environments
- WebResearchEnv — Multi-step web research RL environment ([#434](https://github.com/NousResearch/hermes-agent/pull/434)) — @jackx707
- Modal sandbox concurrency limits to avoid deadlocks ([#621](https://github.com/NousResearch/hermes-agent/pull/621)) — @voteblake
- Hermes-atropos-environments bundled skill ([#815](https://github.com/NousResearch/hermes-agent/pull/815))
- Local vLLM instance support for evaluation — @dmahan93
- YC-Bench long-horizon agent benchmark environment
- OpenThoughts-TBLite evaluation environment and scripts
---
## 📚 Documentation
- Full documentation website (Docusaurus) with 37+ pages
- Comprehensive platform setup guides for Telegram, Discord, Slack, WhatsApp, Signal, Email
- AGENTS.md — development guide for AI coding assistants
- CONTRIBUTING.md ([#117](https://github.com/NousResearch/hermes-agent/pull/117)) — @Bartok9
- Slash commands reference ([#142](https://github.com/NousResearch/hermes-agent/pull/142)) — @Bartok9
- Comprehensive AGENTS.md accuracy audit ([#732](https://github.com/NousResearch/hermes-agent/pull/732))
- Skin/theme system documentation
- MCP documentation and examples
- Docs accuracy audit — 35+ corrections
- Documentation typo fixes ([#825](https://github.com/NousResearch/hermes-agent/pull/825), [#439](https://github.com/NousResearch/hermes-agent/pull/439)) — @JackTheGit
- CLI config precedence and terminology standardization ([#166](https://github.com/NousResearch/hermes-agent/pull/166), [#167](https://github.com/NousResearch/hermes-agent/pull/167), [#168](https://github.com/NousResearch/hermes-agent/pull/168)) — @Jr-kenny
- Telegram token regex documentation ([#713](https://github.com/NousResearch/hermes-agent/pull/713)) — @VolodymyrBg
---
## 👥 Contributors
Thank you to the 63 contributors who made this release possible! In just over two weeks, the Hermes Agent community came together to ship an extraordinary amount of work.
### Core
- **@teknium1** — 43 PRs: Project lead, core architecture, provider router, sessions, skills, CLI, documentation
### Top Community Contributors
- **@0xbyt4** — 40 PRs: MCP client, Home Assistant, security fixes (symlink, prompt injection, cron), extensive test coverage (6 batches), ascii-art skill, shell noise elimination, skills sync, Telegram formatting, and dozens more
- **@Farukest** — 16 PRs: Security hardening (path traversal, dangerous command detection, symlink boundary), Windows compatibility (POSIX guards, path handling), WhatsApp fixes, max-iterations retry, gateway fixes
- **@aydnOktay** — 11 PRs: Atomic writes (process checkpoints, batch runner, skill files), error handling improvements across Telegram, Discord, code execution, transcription, TTS, and skills
- **@Bartok9** — 9 PRs: CONTRIBUTING.md, slash commands reference, Discord channel topics, think-block stripping, TTS fix, Honcho fix, session count fix, clarify tests
- **@PercyDikec** — 7 PRs: DeepSeek V3 parser fix, /retry response discard, gateway transcript offset, Codex status/visibility, max-iterations retry, setup wizard fix
- **@teyrebaz33** — 5 PRs: Skills enable/disable system, quick commands, personality customization, conditional skill activation
- **@alireza78a** — 5 PRs: Atomic writes (cron, sessions), fd leak prevention, security allowlist, code execution socket cleanup
- **@shitcoinsherpa** — 3 PRs: Windows support (pywinpty, UTF-8 encoding, auth store lock)
- **@Himess** — 3 PRs: Cron/HomeAssistant/Daytona fix, Windows drive-letter parsing, .env permissions
- **@satelerd** — 2 PRs: WhatsApp native media, multi-user session isolation
- **@rovle** — 1 PR: Daytona cloud sandbox backend (4 commits)
- **@erosika** — 1 PR: Honcho AI-native memory integration
- **@dmahan93** — 1 PR: --fuck-it-ship-it flag + RL environment work
- **@SHL0MS** — 1 PR: ASCII video skill
### All Contributors
@0xbyt4, @BP602, @Bartok9, @Farukest, @FurkanL0, @Himess, @Indelwin, @JackTheGit, @JoshuaMart, @Jr-kenny, @OutThisLife, @PercyDikec, @SHL0MS, @Sertug17, @VencentSoliman, @VolodymyrBg, @adavyas, @alireza78a, @areu01or00, @aydnOktay, @batuhankocyigit, @bierlingm, @caentzminger, @cesareth, @ch3ronsa, @christomitov, @cutepawss, @deankerr, @dmahan93, @dogiladeveloper, @dragonkhoi, @erosika, @gamedevCloudy, @gizdusum, @grp06, @intertwine, @jackx707, @jdblackstar, @johnh4098, @kaos35, @kshitijk4poor, @leonsgithub, @luisv-1, @manuelschipper, @mehmetkr-31, @memosr, @PeterFile, @rewbs, @rovle, @rsavitt, @satelerd, @spanishflu-est1918, @stablegenius49, @tars90percent, @tekelala, @teknium1, @teyrebaz33, @tripledoublev, @unmodeled-tyler, @voidborne-d, @voteblake, @ygd58
---
**Full Changelog**: [v0.1.0...v2026.3.12](https://github.com/NousResearch/hermes-agent/compare/v0.1.0...v2026.3.12)

View File

@@ -1,377 +0,0 @@
# Hermes Agent v0.3.0 (v2026.3.17)
**Release Date:** March 17, 2026
> The streaming, plugins, and provider release — unified real-time token delivery, first-class plugin architecture, rebuilt provider system with Vercel AI Gateway, native Anthropic provider, smart approvals, live Chrome CDP browser connect, ACP IDE integration, Honcho memory, voice mode, persistent shell, and 50+ bug fixes across every platform.
---
## ✨ Highlights
- **Unified Streaming Infrastructure** — Real-time token-by-token delivery in CLI and all gateway platforms. Responses stream as they're generated instead of arriving as a block. ([#1538](https://github.com/NousResearch/hermes-agent/pull/1538))
- **First-Class Plugin Architecture** — Drop Python files into `~/.hermes/plugins/` to extend Hermes with custom tools, commands, and hooks. No forking required. ([#1544](https://github.com/NousResearch/hermes-agent/pull/1544), [#1555](https://github.com/NousResearch/hermes-agent/pull/1555))
- **Native Anthropic Provider** — Direct Anthropic API calls with Claude Code credential auto-discovery, OAuth PKCE flows, and native prompt caching. No OpenRouter middleman needed. ([#1097](https://github.com/NousResearch/hermes-agent/pull/1097))
- **Smart Approvals + /stop Command** — Codex-inspired approval system that learns which commands are safe and remembers your preferences. `/stop` kills the current agent run immediately. ([#1543](https://github.com/NousResearch/hermes-agent/pull/1543))
- **Honcho Memory Integration** — Async memory writes, configurable recall modes, session title integration, and multi-user isolation in gateway mode. By @erosika. ([#736](https://github.com/NousResearch/hermes-agent/pull/736))
- **Voice Mode** — Push-to-talk in CLI, voice notes in Telegram/Discord, Discord voice channel support, and local Whisper transcription via faster-whisper. ([#1299](https://github.com/NousResearch/hermes-agent/pull/1299), [#1185](https://github.com/NousResearch/hermes-agent/pull/1185), [#1429](https://github.com/NousResearch/hermes-agent/pull/1429))
- **Concurrent Tool Execution** — Multiple independent tool calls now run in parallel via ThreadPoolExecutor, significantly reducing latency for multi-tool turns. ([#1152](https://github.com/NousResearch/hermes-agent/pull/1152))
- **PII Redaction** — When `privacy.redact_pii` is enabled, personally identifiable information is automatically scrubbed before sending context to LLM providers. ([#1542](https://github.com/NousResearch/hermes-agent/pull/1542))
- **`/browser connect` via CDP** — Attach browser tools to a live Chrome instance through Chrome DevTools Protocol. Debug, inspect, and interact with pages you already have open. ([#1549](https://github.com/NousResearch/hermes-agent/pull/1549))
- **Vercel AI Gateway Provider** — Route Hermes through Vercel's AI Gateway for access to their model catalog and infrastructure. ([#1628](https://github.com/NousResearch/hermes-agent/pull/1628))
- **Centralized Provider Router** — Rebuilt provider system with `call_llm` API, unified `/model` command, auto-detect provider on model switch, and direct endpoint overrides for auxiliary/delegation clients. ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003), [#1506](https://github.com/NousResearch/hermes-agent/pull/1506), [#1375](https://github.com/NousResearch/hermes-agent/pull/1375))
- **ACP Server (IDE Integration)** — VS Code, Zed, and JetBrains can now connect to Hermes as an agent backend, with full slash command support. ([#1254](https://github.com/NousResearch/hermes-agent/pull/1254), [#1532](https://github.com/NousResearch/hermes-agent/pull/1532))
- **Persistent Shell Mode** — Local and SSH terminal backends can maintain shell state across tool calls — cd, env vars, and aliases persist. By @alt-glitch. ([#1067](https://github.com/NousResearch/hermes-agent/pull/1067), [#1483](https://github.com/NousResearch/hermes-agent/pull/1483))
- **Agentic On-Policy Distillation (OPD)** — New RL training environment for distilling agent policies, expanding the Atropos training ecosystem. ([#1149](https://github.com/NousResearch/hermes-agent/pull/1149))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- **Centralized provider router** with `call_llm` API and unified `/model` command — switch models and providers seamlessly ([#1003](https://github.com/NousResearch/hermes-agent/pull/1003))
- **Vercel AI Gateway** provider support ([#1628](https://github.com/NousResearch/hermes-agent/pull/1628))
- **Auto-detect provider** when switching models via `/model` ([#1506](https://github.com/NousResearch/hermes-agent/pull/1506))
- **Direct endpoint overrides** for auxiliary and delegation clients — point vision/subagent calls at specific endpoints ([#1375](https://github.com/NousResearch/hermes-agent/pull/1375))
- **Native Anthropic auxiliary vision** — use Claude's native vision API instead of routing through OpenAI-compatible endpoints ([#1377](https://github.com/NousResearch/hermes-agent/pull/1377))
- Anthropic OAuth flow improvements — auto-run `claude setup-token`, reauthentication, PKCE state persistence, identity fingerprinting ([#1132](https://github.com/NousResearch/hermes-agent/pull/1132), [#1360](https://github.com/NousResearch/hermes-agent/pull/1360), [#1396](https://github.com/NousResearch/hermes-agent/pull/1396), [#1597](https://github.com/NousResearch/hermes-agent/pull/1597))
- Fix adaptive thinking without `budget_tokens` for Claude 4.6 models — by @ASRagab ([#1128](https://github.com/NousResearch/hermes-agent/pull/1128))
- Fix Anthropic cache markers through adapter — by @brandtcormorant ([#1216](https://github.com/NousResearch/hermes-agent/pull/1216))
- Retry Anthropic 429/529 errors and surface details to users — by @0xbyt4 ([#1585](https://github.com/NousResearch/hermes-agent/pull/1585))
- Fix Anthropic adapter max_tokens, fallback crash, proxy base_url — by @0xbyt4 ([#1121](https://github.com/NousResearch/hermes-agent/pull/1121))
- Fix DeepSeek V3 parser dropping multiple parallel tool calls — by @mr-emmett-one ([#1365](https://github.com/NousResearch/hermes-agent/pull/1365), [#1300](https://github.com/NousResearch/hermes-agent/pull/1300))
- Accept unlisted models with warning instead of rejecting ([#1047](https://github.com/NousResearch/hermes-agent/pull/1047), [#1102](https://github.com/NousResearch/hermes-agent/pull/1102))
- Skip reasoning params for unsupported OpenRouter models ([#1485](https://github.com/NousResearch/hermes-agent/pull/1485))
- MiniMax Anthropic API compatibility fix ([#1623](https://github.com/NousResearch/hermes-agent/pull/1623))
- Custom endpoint `/models` verification and `/v1` base URL suggestion ([#1480](https://github.com/NousResearch/hermes-agent/pull/1480))
- Resolve delegation providers from `custom_providers` config ([#1328](https://github.com/NousResearch/hermes-agent/pull/1328))
- Kimi model additions and User-Agent fix ([#1039](https://github.com/NousResearch/hermes-agent/pull/1039))
- Strip `call_id`/`response_item_id` for Mistral compatibility ([#1058](https://github.com/NousResearch/hermes-agent/pull/1058))
### Agent Loop & Conversation
- **Anthropic Context Editing API** support ([#1147](https://github.com/NousResearch/hermes-agent/pull/1147))
- Improved context compaction handoff summaries — compressor now preserves more actionable state ([#1273](https://github.com/NousResearch/hermes-agent/pull/1273))
- Sync session_id after mid-run context compression ([#1160](https://github.com/NousResearch/hermes-agent/pull/1160))
- Session hygiene threshold tuned to 50% for more proactive compression ([#1096](https://github.com/NousResearch/hermes-agent/pull/1096), [#1161](https://github.com/NousResearch/hermes-agent/pull/1161))
- Include session ID in system prompt via `--pass-session-id` flag ([#1040](https://github.com/NousResearch/hermes-agent/pull/1040))
- Prevent closed OpenAI client reuse across retries ([#1391](https://github.com/NousResearch/hermes-agent/pull/1391))
- Sanitize chat payloads and provider precedence ([#1253](https://github.com/NousResearch/hermes-agent/pull/1253))
- Handle dict tool call arguments from Codex and local backends ([#1393](https://github.com/NousResearch/hermes-agent/pull/1393), [#1440](https://github.com/NousResearch/hermes-agent/pull/1440))
### Memory & Sessions
- **Improve memory prioritization** — user preferences and corrections weighted above procedural knowledge ([#1548](https://github.com/NousResearch/hermes-agent/pull/1548))
- Tighter memory and session recall guidance in system prompts ([#1329](https://github.com/NousResearch/hermes-agent/pull/1329))
- Persist CLI token counts to session DB for `/insights` ([#1498](https://github.com/NousResearch/hermes-agent/pull/1498))
- Keep Honcho recall out of the cached system prefix ([#1201](https://github.com/NousResearch/hermes-agent/pull/1201))
- Correct `seed_ai_identity` to use `session.add_messages()` ([#1475](https://github.com/NousResearch/hermes-agent/pull/1475))
- Isolate Honcho session routing for multi-user gateway ([#1500](https://github.com/NousResearch/hermes-agent/pull/1500))
---
## 📱 Messaging Platforms (Gateway)
### Gateway Core
- **System gateway service mode** — run as a system-level systemd service, not just user-level ([#1371](https://github.com/NousResearch/hermes-agent/pull/1371))
- **Gateway install scope prompts** — choose user vs system scope during setup ([#1374](https://github.com/NousResearch/hermes-agent/pull/1374))
- **Reasoning hot reload** — change reasoning settings without restarting the gateway ([#1275](https://github.com/NousResearch/hermes-agent/pull/1275))
- Default group sessions to per-user isolation — no more shared state across users in group chats ([#1495](https://github.com/NousResearch/hermes-agent/pull/1495), [#1417](https://github.com/NousResearch/hermes-agent/pull/1417))
- Harden gateway restart recovery ([#1310](https://github.com/NousResearch/hermes-agent/pull/1310))
- Cancel active runs during shutdown ([#1427](https://github.com/NousResearch/hermes-agent/pull/1427))
- SSL certificate auto-detection for NixOS and non-standard systems ([#1494](https://github.com/NousResearch/hermes-agent/pull/1494))
- Auto-detect D-Bus session bus for `systemctl --user` on headless servers ([#1601](https://github.com/NousResearch/hermes-agent/pull/1601))
- Auto-enable systemd linger during gateway install on headless servers ([#1334](https://github.com/NousResearch/hermes-agent/pull/1334))
- Fall back to module entrypoint when `hermes` is not on PATH ([#1355](https://github.com/NousResearch/hermes-agent/pull/1355))
- Fix dual gateways on macOS launchd after `hermes update` ([#1567](https://github.com/NousResearch/hermes-agent/pull/1567))
- Remove recursive ExecStop from systemd units ([#1530](https://github.com/NousResearch/hermes-agent/pull/1530))
- Prevent logging handler accumulation in gateway mode ([#1251](https://github.com/NousResearch/hermes-agent/pull/1251))
- Restart on retryable startup failures — by @jplew ([#1517](https://github.com/NousResearch/hermes-agent/pull/1517))
- Backfill model on gateway sessions after agent runs ([#1306](https://github.com/NousResearch/hermes-agent/pull/1306))
- PID-based gateway kill and deferred config write ([#1499](https://github.com/NousResearch/hermes-agent/pull/1499))
### Telegram
- Buffer media groups to prevent self-interruption from photo bursts ([#1341](https://github.com/NousResearch/hermes-agent/pull/1341), [#1422](https://github.com/NousResearch/hermes-agent/pull/1422))
- Retry on transient TLS failures during connect and send ([#1535](https://github.com/NousResearch/hermes-agent/pull/1535))
- Harden polling conflict handling ([#1339](https://github.com/NousResearch/hermes-agent/pull/1339))
- Escape chunk indicators and inline code in MarkdownV2 ([#1478](https://github.com/NousResearch/hermes-agent/pull/1478), [#1626](https://github.com/NousResearch/hermes-agent/pull/1626))
- Check updater/app state before disconnect ([#1389](https://github.com/NousResearch/hermes-agent/pull/1389))
### Discord
- `/thread` command with `auto_thread` config and media metadata fixes ([#1178](https://github.com/NousResearch/hermes-agent/pull/1178))
- Auto-thread on @mention, skip mention text in bot threads ([#1438](https://github.com/NousResearch/hermes-agent/pull/1438))
- Retry without reply reference for system messages ([#1385](https://github.com/NousResearch/hermes-agent/pull/1385))
- Preserve native document and video attachment support ([#1392](https://github.com/NousResearch/hermes-agent/pull/1392))
- Defer discord adapter annotations to avoid optional import crashes ([#1314](https://github.com/NousResearch/hermes-agent/pull/1314))
### Slack
- Thread handling overhaul — progress messages, responses, and session isolation all respect threads ([#1103](https://github.com/NousResearch/hermes-agent/pull/1103))
- Formatting, reactions, user resolution, and command improvements ([#1106](https://github.com/NousResearch/hermes-agent/pull/1106))
- Fix MAX_MESSAGE_LENGTH 3900 → 39000 ([#1117](https://github.com/NousResearch/hermes-agent/pull/1117))
- File upload fallback preserves thread context — by @0xbyt4 ([#1122](https://github.com/NousResearch/hermes-agent/pull/1122))
- Improve setup guidance ([#1387](https://github.com/NousResearch/hermes-agent/pull/1387))
### Email
- Fix IMAP UID tracking and SMTP TLS verification ([#1305](https://github.com/NousResearch/hermes-agent/pull/1305))
- Add `skip_attachments` option via config.yaml ([#1536](https://github.com/NousResearch/hermes-agent/pull/1536))
### Home Assistant
- Event filtering closed by default ([#1169](https://github.com/NousResearch/hermes-agent/pull/1169))
---
## 🖥️ CLI & User Experience
### Interactive CLI
- **Persistent CLI status bar** — always-visible model, provider, and token counts ([#1522](https://github.com/NousResearch/hermes-agent/pull/1522))
- **File path autocomplete** in the input prompt ([#1545](https://github.com/NousResearch/hermes-agent/pull/1545))
- **`/plan` command** — generate implementation plans from specs ([#1372](https://github.com/NousResearch/hermes-agent/pull/1372), [#1381](https://github.com/NousResearch/hermes-agent/pull/1381))
- **Major `/rollback` improvements** — richer checkpoint history, clearer UX ([#1505](https://github.com/NousResearch/hermes-agent/pull/1505))
- **Preload CLI skills on launch** — skills are ready before the first prompt ([#1359](https://github.com/NousResearch/hermes-agent/pull/1359))
- **Centralized slash command registry** — all commands defined once, consumed everywhere ([#1603](https://github.com/NousResearch/hermes-agent/pull/1603))
- `/bg` alias for `/background` ([#1590](https://github.com/NousResearch/hermes-agent/pull/1590))
- Prefix matching for slash commands — `/mod` resolves to `/model` ([#1320](https://github.com/NousResearch/hermes-agent/pull/1320))
- `/new`, `/reset`, `/clear` now start genuinely fresh sessions ([#1237](https://github.com/NousResearch/hermes-agent/pull/1237))
- Accept session ID prefixes for session actions ([#1425](https://github.com/NousResearch/hermes-agent/pull/1425))
- TUI prompt and accent output now respect active skin ([#1282](https://github.com/NousResearch/hermes-agent/pull/1282))
- Centralize tool emoji metadata in registry + skin integration ([#1484](https://github.com/NousResearch/hermes-agent/pull/1484))
- "View full command" option added to dangerous command approval — by @teknium1 based on design by community ([#887](https://github.com/NousResearch/hermes-agent/pull/887))
- Non-blocking startup update check and banner deduplication ([#1386](https://github.com/NousResearch/hermes-agent/pull/1386))
- `/reasoning` command output ordering and inline think extraction fixes ([#1031](https://github.com/NousResearch/hermes-agent/pull/1031))
- Verbose mode shows full untruncated output ([#1472](https://github.com/NousResearch/hermes-agent/pull/1472))
- Fix `/status` to report live state and tokens ([#1476](https://github.com/NousResearch/hermes-agent/pull/1476))
- Seed a default global SOUL.md ([#1311](https://github.com/NousResearch/hermes-agent/pull/1311))
### Setup & Configuration
- **OpenClaw migration** during first-time setup — by @kshitijk4poor ([#981](https://github.com/NousResearch/hermes-agent/pull/981))
- `hermes claw migrate` command + migration docs ([#1059](https://github.com/NousResearch/hermes-agent/pull/1059))
- Smart vision setup that respects the user's chosen provider ([#1323](https://github.com/NousResearch/hermes-agent/pull/1323))
- Handle headless setup flows end-to-end ([#1274](https://github.com/NousResearch/hermes-agent/pull/1274))
- Prefer curses over `simple_term_menu` in setup.py ([#1487](https://github.com/NousResearch/hermes-agent/pull/1487))
- Show effective model and provider in `/status` ([#1284](https://github.com/NousResearch/hermes-agent/pull/1284))
- Config set examples use placeholder syntax ([#1322](https://github.com/NousResearch/hermes-agent/pull/1322))
- Reload .env over stale shell overrides ([#1434](https://github.com/NousResearch/hermes-agent/pull/1434))
- Fix is_coding_plan NameError crash — by @0xbyt4 ([#1123](https://github.com/NousResearch/hermes-agent/pull/1123))
- Add missing packages to setuptools config — by @alt-glitch ([#912](https://github.com/NousResearch/hermes-agent/pull/912))
- Installer: clarify why sudo is needed at every prompt ([#1602](https://github.com/NousResearch/hermes-agent/pull/1602))
---
## 🔧 Tool System
### Terminal & Execution
- **Persistent shell mode** for local and SSH backends — maintain shell state across tool calls — by @alt-glitch ([#1067](https://github.com/NousResearch/hermes-agent/pull/1067), [#1483](https://github.com/NousResearch/hermes-agent/pull/1483))
- **Tirith pre-exec command scanning** — security layer that analyzes commands before execution ([#1256](https://github.com/NousResearch/hermes-agent/pull/1256))
- Strip Hermes provider env vars from all subprocess environments ([#1157](https://github.com/NousResearch/hermes-agent/pull/1157), [#1172](https://github.com/NousResearch/hermes-agent/pull/1172), [#1399](https://github.com/NousResearch/hermes-agent/pull/1399), [#1419](https://github.com/NousResearch/hermes-agent/pull/1419)) — initial fix by @eren-karakus0
- SSH preflight check ([#1486](https://github.com/NousResearch/hermes-agent/pull/1486))
- Docker backend: make cwd workspace mount explicit opt-in ([#1534](https://github.com/NousResearch/hermes-agent/pull/1534))
- Add project root to PYTHONPATH in execute_code sandbox ([#1383](https://github.com/NousResearch/hermes-agent/pull/1383))
- Eliminate execute_code progress spam on gateway platforms ([#1098](https://github.com/NousResearch/hermes-agent/pull/1098))
- Clearer docker backend preflight errors ([#1276](https://github.com/NousResearch/hermes-agent/pull/1276))
### Browser
- **`/browser connect`** — attach browser tools to a live Chrome instance via CDP ([#1549](https://github.com/NousResearch/hermes-agent/pull/1549))
- Improve browser cleanup, local browser PATH setup, and screenshot recovery ([#1333](https://github.com/NousResearch/hermes-agent/pull/1333))
### MCP
- **Selective tool loading** with utility policies — filter which MCP tools are available ([#1302](https://github.com/NousResearch/hermes-agent/pull/1302))
- Auto-reload MCP tools when `mcp_servers` config changes without restart ([#1474](https://github.com/NousResearch/hermes-agent/pull/1474))
- Resolve npx stdio connection failures ([#1291](https://github.com/NousResearch/hermes-agent/pull/1291))
- Preserve MCP toolsets when saving platform tool config ([#1421](https://github.com/NousResearch/hermes-agent/pull/1421))
### Vision
- Unify vision backend gating ([#1367](https://github.com/NousResearch/hermes-agent/pull/1367))
- Surface actual error reason instead of generic message ([#1338](https://github.com/NousResearch/hermes-agent/pull/1338))
- Make Claude image handling work end-to-end ([#1408](https://github.com/NousResearch/hermes-agent/pull/1408))
### Cron
- **Compress cron management into one tool** — single `cronjob` tool replaces multiple commands ([#1343](https://github.com/NousResearch/hermes-agent/pull/1343))
- Suppress duplicate cron sends to auto-delivery targets ([#1357](https://github.com/NousResearch/hermes-agent/pull/1357))
- Persist cron sessions to SQLite ([#1255](https://github.com/NousResearch/hermes-agent/pull/1255))
- Per-job runtime overrides (provider, model, base_url) ([#1398](https://github.com/NousResearch/hermes-agent/pull/1398))
- Atomic write in `save_job_output` to prevent data loss on crash ([#1173](https://github.com/NousResearch/hermes-agent/pull/1173))
- Preserve thread context for `deliver=origin` ([#1437](https://github.com/NousResearch/hermes-agent/pull/1437))
### Patch Tool
- Avoid corrupting pipe chars in V4A patch apply ([#1286](https://github.com/NousResearch/hermes-agent/pull/1286))
- Permissive `block_anchor` thresholds and unicode normalization ([#1539](https://github.com/NousResearch/hermes-agent/pull/1539))
### Delegation
- Add observability metadata to subagent results (model, tokens, duration, tool trace) ([#1175](https://github.com/NousResearch/hermes-agent/pull/1175))
---
## 🧩 Skills Ecosystem
### Skills System
- **Integrate skills.sh** as a hub source alongside ClawHub ([#1303](https://github.com/NousResearch/hermes-agent/pull/1303))
- Secure skill env setup on load ([#1153](https://github.com/NousResearch/hermes-agent/pull/1153))
- Honor policy table for dangerous verdicts ([#1330](https://github.com/NousResearch/hermes-agent/pull/1330))
- Harden ClawHub skill search exact matches ([#1400](https://github.com/NousResearch/hermes-agent/pull/1400))
- Fix ClawHub skill install — use `/download` ZIP endpoint ([#1060](https://github.com/NousResearch/hermes-agent/pull/1060))
- Avoid mislabeling local skills as builtin — by @arceus77-7 ([#862](https://github.com/NousResearch/hermes-agent/pull/862))
### New Skills
- **Linear** project management ([#1230](https://github.com/NousResearch/hermes-agent/pull/1230))
- **X/Twitter** via x-cli ([#1285](https://github.com/NousResearch/hermes-agent/pull/1285))
- **Telephony** — Twilio, SMS, and AI calls ([#1289](https://github.com/NousResearch/hermes-agent/pull/1289))
- **1Password** — by @arceus77-7 ([#883](https://github.com/NousResearch/hermes-agent/pull/883), [#1179](https://github.com/NousResearch/hermes-agent/pull/1179))
- **NeuroSkill BCI** integration ([#1135](https://github.com/NousResearch/hermes-agent/pull/1135))
- **Blender MCP** for 3D modeling ([#1531](https://github.com/NousResearch/hermes-agent/pull/1531))
- **OSS Security Forensics** ([#1482](https://github.com/NousResearch/hermes-agent/pull/1482))
- **Parallel CLI** research skill ([#1301](https://github.com/NousResearch/hermes-agent/pull/1301))
- **OpenCode** CLI skill ([#1174](https://github.com/NousResearch/hermes-agent/pull/1174))
- **ASCII Video** skill refactored — by @SHL0MS ([#1213](https://github.com/NousResearch/hermes-agent/pull/1213), [#1598](https://github.com/NousResearch/hermes-agent/pull/1598))
---
## 🎙️ Voice Mode
- Voice mode foundation — push-to-talk CLI, Telegram/Discord voice notes ([#1299](https://github.com/NousResearch/hermes-agent/pull/1299))
- Free local Whisper transcription via faster-whisper ([#1185](https://github.com/NousResearch/hermes-agent/pull/1185))
- Discord voice channel reliability fixes ([#1429](https://github.com/NousResearch/hermes-agent/pull/1429))
- Restore local STT fallback for gateway voice notes ([#1490](https://github.com/NousResearch/hermes-agent/pull/1490))
- Honor `stt.enabled: false` across gateway transcription ([#1394](https://github.com/NousResearch/hermes-agent/pull/1394))
- Fix bogus incapability message on Telegram voice notes (Issue [#1033](https://github.com/NousResearch/hermes-agent/issues/1033))
---
## 🔌 ACP (IDE Integration)
- Restore ACP server implementation ([#1254](https://github.com/NousResearch/hermes-agent/pull/1254))
- Support slash commands in ACP adapter ([#1532](https://github.com/NousResearch/hermes-agent/pull/1532))
---
## 🧪 RL Training
- **Agentic On-Policy Distillation (OPD)** environment — new RL training environment for agent policy distillation ([#1149](https://github.com/NousResearch/hermes-agent/pull/1149))
- Make tinker-atropos RL training fully optional ([#1062](https://github.com/NousResearch/hermes-agent/pull/1062))
---
## 🔒 Security & Reliability
### Security Hardening
- **Tirith pre-exec command scanning** — static analysis of terminal commands before execution ([#1256](https://github.com/NousResearch/hermes-agent/pull/1256))
- **PII redaction** when `privacy.redact_pii` is enabled ([#1542](https://github.com/NousResearch/hermes-agent/pull/1542))
- Strip Hermes provider/gateway/tool env vars from all subprocess environments ([#1157](https://github.com/NousResearch/hermes-agent/pull/1157), [#1172](https://github.com/NousResearch/hermes-agent/pull/1172), [#1399](https://github.com/NousResearch/hermes-agent/pull/1399), [#1419](https://github.com/NousResearch/hermes-agent/pull/1419))
- Docker cwd workspace mount now explicit opt-in — never auto-mount host directories ([#1534](https://github.com/NousResearch/hermes-agent/pull/1534))
- Escape parens and braces in fork bomb regex pattern ([#1397](https://github.com/NousResearch/hermes-agent/pull/1397))
- Harden `.worktreeinclude` path containment ([#1388](https://github.com/NousResearch/hermes-agent/pull/1388))
- Use description as `pattern_key` to prevent approval collisions ([#1395](https://github.com/NousResearch/hermes-agent/pull/1395))
### Reliability
- Guard init-time stdio writes ([#1271](https://github.com/NousResearch/hermes-agent/pull/1271))
- Session log writes reuse shared atomic JSON helper ([#1280](https://github.com/NousResearch/hermes-agent/pull/1280))
- Atomic temp cleanup protected on interrupts ([#1401](https://github.com/NousResearch/hermes-agent/pull/1401))
---
## 🐛 Notable Bug Fixes
- **`/status` always showing 0 tokens** — now reports live state (Issue [#1465](https://github.com/NousResearch/hermes-agent/issues/1465), [#1476](https://github.com/NousResearch/hermes-agent/pull/1476))
- **Custom model endpoints not working** — restored config-saved endpoint resolution (Issue [#1460](https://github.com/NousResearch/hermes-agent/issues/1460), [#1373](https://github.com/NousResearch/hermes-agent/pull/1373))
- **MCP tools not visible until restart** — auto-reload on config change (Issue [#1036](https://github.com/NousResearch/hermes-agent/issues/1036), [#1474](https://github.com/NousResearch/hermes-agent/pull/1474))
- **`hermes tools` removing MCP tools** — preserve MCP toolsets when saving (Issue [#1247](https://github.com/NousResearch/hermes-agent/issues/1247), [#1421](https://github.com/NousResearch/hermes-agent/pull/1421))
- **Terminal subprocesses inheriting `OPENAI_BASE_URL`** breaking external tools (Issue [#1002](https://github.com/NousResearch/hermes-agent/issues/1002), [#1399](https://github.com/NousResearch/hermes-agent/pull/1399))
- **Background process lost on gateway restart** — improved recovery (Issue [#1144](https://github.com/NousResearch/hermes-agent/issues/1144))
- **Cron jobs not persisting state** — now stored in SQLite (Issue [#1416](https://github.com/NousResearch/hermes-agent/issues/1416), [#1255](https://github.com/NousResearch/hermes-agent/pull/1255))
- **Cronjob `deliver: origin` not preserving thread context** (Issue [#1219](https://github.com/NousResearch/hermes-agent/issues/1219), [#1437](https://github.com/NousResearch/hermes-agent/pull/1437))
- **Gateway systemd service failing to auto-restart** when browser processes orphaned (Issue [#1617](https://github.com/NousResearch/hermes-agent/issues/1617))
- **`/background` completion report cut off in Telegram** (Issue [#1443](https://github.com/NousResearch/hermes-agent/issues/1443))
- **Model switching not taking effect** (Issue [#1244](https://github.com/NousResearch/hermes-agent/issues/1244), [#1183](https://github.com/NousResearch/hermes-agent/pull/1183))
- **`hermes doctor` reporting cronjob as unavailable** (Issue [#878](https://github.com/NousResearch/hermes-agent/issues/878), [#1180](https://github.com/NousResearch/hermes-agent/pull/1180))
- **WhatsApp bridge messages not received** from mobile (Issue [#1142](https://github.com/NousResearch/hermes-agent/issues/1142))
- **Setup wizard hanging on headless SSH** (Issue [#905](https://github.com/NousResearch/hermes-agent/issues/905), [#1274](https://github.com/NousResearch/hermes-agent/pull/1274))
- **Log handler accumulation** degrading gateway performance (Issue [#990](https://github.com/NousResearch/hermes-agent/issues/990), [#1251](https://github.com/NousResearch/hermes-agent/pull/1251))
- **Gateway NULL model in DB** (Issue [#987](https://github.com/NousResearch/hermes-agent/issues/987), [#1306](https://github.com/NousResearch/hermes-agent/pull/1306))
- **Strict endpoints rejecting replayed tool_calls** (Issue [#893](https://github.com/NousResearch/hermes-agent/issues/893))
- **Remaining hardcoded `~/.hermes` paths** — all now respect `HERMES_HOME` (Issue [#892](https://github.com/NousResearch/hermes-agent/issues/892), [#1233](https://github.com/NousResearch/hermes-agent/pull/1233))
- **Delegate tool not working with custom inference providers** (Issue [#1011](https://github.com/NousResearch/hermes-agent/issues/1011), [#1328](https://github.com/NousResearch/hermes-agent/pull/1328))
- **Skills Guard blocking official skills** (Issue [#1006](https://github.com/NousResearch/hermes-agent/issues/1006), [#1330](https://github.com/NousResearch/hermes-agent/pull/1330))
- **Setup writing provider before model selection** (Issue [#1182](https://github.com/NousResearch/hermes-agent/issues/1182))
- **`GatewayConfig.get()` AttributeError** crashing all message handling (Issue [#1158](https://github.com/NousResearch/hermes-agent/issues/1158), [#1287](https://github.com/NousResearch/hermes-agent/pull/1287))
- **`/update` hard-failing with "command not found"** (Issue [#1049](https://github.com/NousResearch/hermes-agent/issues/1049))
- **Image analysis failing silently** (Issue [#1034](https://github.com/NousResearch/hermes-agent/issues/1034), [#1338](https://github.com/NousResearch/hermes-agent/pull/1338))
- **API `BadRequestError` from `'dict'` object has no attribute `'strip'`** (Issue [#1071](https://github.com/NousResearch/hermes-agent/issues/1071))
- **Slash commands requiring exact full name** — now uses prefix matching (Issue [#928](https://github.com/NousResearch/hermes-agent/issues/928), [#1320](https://github.com/NousResearch/hermes-agent/pull/1320))
- **Gateway stops responding when terminal is closed on headless** (Issue [#1005](https://github.com/NousResearch/hermes-agent/issues/1005))
---
## 🧪 Testing
- Cover empty cached Anthropic tool-call turns ([#1222](https://github.com/NousResearch/hermes-agent/pull/1222))
- Fix stale CI assumptions in parser and quick-command coverage ([#1236](https://github.com/NousResearch/hermes-agent/pull/1236))
- Fix gateway async tests without implicit event loop ([#1278](https://github.com/NousResearch/hermes-agent/pull/1278))
- Make gateway async tests xdist-safe ([#1281](https://github.com/NousResearch/hermes-agent/pull/1281))
- Cross-timezone naive timestamp regression for cron ([#1319](https://github.com/NousResearch/hermes-agent/pull/1319))
- Isolate codex provider tests from local env ([#1335](https://github.com/NousResearch/hermes-agent/pull/1335))
- Lock retry replacement semantics ([#1379](https://github.com/NousResearch/hermes-agent/pull/1379))
- Improve error logging in session search tool — by @aydnOktay ([#1533](https://github.com/NousResearch/hermes-agent/pull/1533))
---
## 📚 Documentation
- Comprehensive SOUL.md guide ([#1315](https://github.com/NousResearch/hermes-agent/pull/1315))
- Voice mode documentation ([#1316](https://github.com/NousResearch/hermes-agent/pull/1316), [#1362](https://github.com/NousResearch/hermes-agent/pull/1362))
- Provider contribution guide ([#1361](https://github.com/NousResearch/hermes-agent/pull/1361))
- ACP and internal systems implementation guides ([#1259](https://github.com/NousResearch/hermes-agent/pull/1259))
- Expand Docusaurus coverage across CLI, tools, skills, and skins ([#1232](https://github.com/NousResearch/hermes-agent/pull/1232))
- Terminal backend and Windows troubleshooting ([#1297](https://github.com/NousResearch/hermes-agent/pull/1297))
- Skills hub reference section ([#1317](https://github.com/NousResearch/hermes-agent/pull/1317))
- Checkpoint, /rollback, and git worktrees guide ([#1493](https://github.com/NousResearch/hermes-agent/pull/1493), [#1524](https://github.com/NousResearch/hermes-agent/pull/1524))
- CLI status bar and /usage reference ([#1523](https://github.com/NousResearch/hermes-agent/pull/1523))
- Fallback providers + /background command docs ([#1430](https://github.com/NousResearch/hermes-agent/pull/1430))
- Gateway service scopes docs ([#1378](https://github.com/NousResearch/hermes-agent/pull/1378))
- Slack thread reply behavior docs ([#1407](https://github.com/NousResearch/hermes-agent/pull/1407))
- Redesigned landing page with Nous blue palette — by @austinpickett ([#974](https://github.com/NousResearch/hermes-agent/pull/974))
- Fix several documentation typos — by @JackTheGit ([#953](https://github.com/NousResearch/hermes-agent/pull/953))
- Stabilize website diagrams ([#1405](https://github.com/NousResearch/hermes-agent/pull/1405))
- CLI vs messaging quick reference in README ([#1491](https://github.com/NousResearch/hermes-agent/pull/1491))
- Add search to Docusaurus ([#1053](https://github.com/NousResearch/hermes-agent/pull/1053))
- Home Assistant integration docs ([#1170](https://github.com/NousResearch/hermes-agent/pull/1170))
---
## 👥 Contributors
### Core
- **@teknium1** — 220+ PRs spanning every area of the codebase
### Top Community Contributors
- **@0xbyt4** (4 PRs) — Anthropic adapter fixes (max_tokens, fallback crash, 429/529 retry), Slack file upload thread context, setup NameError fix
- **@erosika** (1 PR) — Honcho memory integration: async writes, memory modes, session title integration
- **@SHL0MS** (2 PRs) — ASCII video skill design patterns and refactoring
- **@alt-glitch** (2 PRs) — Persistent shell mode for local/SSH backends, setuptools packaging fix
- **@arceus77-7** (2 PRs) — 1Password skill, fix skills list mislabeling
- **@kshitijk4poor** (1 PR) — OpenClaw migration during setup wizard
- **@ASRagab** (1 PR) — Fix adaptive thinking for Claude 4.6 models
- **@eren-karakus0** (1 PR) — Strip Hermes provider env vars from subprocess environment
- **@mr-emmett-one** (1 PR) — Fix DeepSeek V3 parser multi-tool call support
- **@jplew** (1 PR) — Gateway restart on retryable startup failures
- **@brandtcormorant** (1 PR) — Fix Anthropic cache control for empty text blocks
- **@aydnOktay** (1 PR) — Improve error logging in session search tool
- **@austinpickett** (1 PR) — Landing page redesign with Nous blue palette
- **@JackTheGit** (1 PR) — Documentation typo fixes
### All Contributors
@0xbyt4, @alt-glitch, @arceus77-7, @ASRagab, @austinpickett, @aydnOktay, @brandtcormorant, @eren-karakus0, @erosika, @JackTheGit, @jplew, @kshitijk4poor, @mr-emmett-one, @SHL0MS, @teknium1
---
**Full Changelog**: [v2026.3.12...v2026.3.17](https://github.com/NousResearch/hermes-agent/compare/v2026.3.12...v2026.3.17)

View File

@@ -1,400 +0,0 @@
# Hermes Agent v0.4.0 (v2026.3.23)
**Release Date:** March 23, 2026
> The platform expansion release — OpenAI-compatible API server, 6 new messaging adapters, 4 new inference providers, MCP server management with OAuth 2.1, @ context references, gateway prompt caching, streaming enabled by default, and a sweeping reliability pass with 200+ bug fixes.
---
## ✨ Highlights
- **OpenAI-compatible API server** — Expose Hermes as an `/v1/chat/completions` endpoint with a new `/api/jobs` REST API for cron job management, hardened with input limits, field whitelists, SQLite-backed response persistence, and CORS origin protection ([#1756](https://github.com/NousResearch/hermes-agent/pull/1756), [#2450](https://github.com/NousResearch/hermes-agent/pull/2450), [#2456](https://github.com/NousResearch/hermes-agent/pull/2456), [#2451](https://github.com/NousResearch/hermes-agent/pull/2451), [#2472](https://github.com/NousResearch/hermes-agent/pull/2472))
- **6 new messaging platform adapters** — Signal, DingTalk, SMS (Twilio), Mattermost, Matrix, and Webhook adapters join Telegram, Discord, and WhatsApp. Gateway auto-reconnects failed platforms with exponential backoff ([#2206](https://github.com/NousResearch/hermes-agent/pull/2206), [#1685](https://github.com/NousResearch/hermes-agent/pull/1685), [#1688](https://github.com/NousResearch/hermes-agent/pull/1688), [#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2166](https://github.com/NousResearch/hermes-agent/pull/2166), [#2584](https://github.com/NousResearch/hermes-agent/pull/2584))
- **@ context references** — Claude Code-style `@file` and `@url` context injection with tab completions in the CLI ([#2343](https://github.com/NousResearch/hermes-agent/pull/2343), [#2482](https://github.com/NousResearch/hermes-agent/pull/2482))
- **4 new inference providers** — GitHub Copilot (OAuth + token validation), Alibaba Cloud / DashScope, Kilo Code, and OpenCode Zen/Go ([#1924](https://github.com/NousResearch/hermes-agent/pull/1924), [#1879](https://github.com/NousResearch/hermes-agent/pull/1879) by @mchzimm, [#1673](https://github.com/NousResearch/hermes-agent/pull/1673), [#1666](https://github.com/NousResearch/hermes-agent/pull/1666), [#1650](https://github.com/NousResearch/hermes-agent/pull/1650))
- **MCP server management CLI** — `hermes mcp` commands for installing, configuring, and authenticating MCP servers with full OAuth 2.1 PKCE flow ([#2465](https://github.com/NousResearch/hermes-agent/pull/2465))
- **Gateway prompt caching** — Cache AIAgent instances per session, preserving Anthropic prompt cache across turns for dramatic cost reduction on long conversations ([#2282](https://github.com/NousResearch/hermes-agent/pull/2282), [#2284](https://github.com/NousResearch/hermes-agent/pull/2284), [#2361](https://github.com/NousResearch/hermes-agent/pull/2361))
- **Context compression overhaul** — Structured summaries with iterative updates, token-budget tail protection, configurable summary endpoint, and fallback model support ([#2323](https://github.com/NousResearch/hermes-agent/pull/2323), [#1727](https://github.com/NousResearch/hermes-agent/pull/1727), [#2224](https://github.com/NousResearch/hermes-agent/pull/2224))
- **Streaming enabled by default** — CLI streaming on by default with proper spinner/tool progress display during streaming mode, plus extensive linebreak and concatenation fixes ([#2340](https://github.com/NousResearch/hermes-agent/pull/2340), [#2161](https://github.com/NousResearch/hermes-agent/pull/2161), [#2258](https://github.com/NousResearch/hermes-agent/pull/2258))
---
## 🖥️ CLI & User Experience
### New Commands & Interactions
- **@ context completions** — Tab-completable `@file`/`@url` references that inject file content or web pages into the conversation ([#2482](https://github.com/NousResearch/hermes-agent/pull/2482), [#2343](https://github.com/NousResearch/hermes-agent/pull/2343))
- **`/statusbar`** — Toggle a persistent config bar showing model + provider info in the prompt ([#2240](https://github.com/NousResearch/hermes-agent/pull/2240), [#1917](https://github.com/NousResearch/hermes-agent/pull/1917))
- **`/queue`** — Queue prompts for the agent without interrupting the current run ([#2191](https://github.com/NousResearch/hermes-agent/pull/2191), [#2469](https://github.com/NousResearch/hermes-agent/pull/2469))
- **`/permission`** — Switch approval mode dynamically during a session ([#2207](https://github.com/NousResearch/hermes-agent/pull/2207))
- **`/browser`** — Interactive browser sessions from the CLI ([#2273](https://github.com/NousResearch/hermes-agent/pull/2273), [#1814](https://github.com/NousResearch/hermes-agent/pull/1814))
- **`/cost`** — Live pricing and usage tracking in gateway mode ([#2180](https://github.com/NousResearch/hermes-agent/pull/2180))
- **`/approve` and `/deny`** — Replaced bare text approval in gateway with explicit commands ([#2002](https://github.com/NousResearch/hermes-agent/pull/2002))
### Streaming & Display
- Streaming enabled by default in CLI ([#2340](https://github.com/NousResearch/hermes-agent/pull/2340))
- Show spinners and tool progress during streaming mode ([#2161](https://github.com/NousResearch/hermes-agent/pull/2161))
- Show reasoning/thinking blocks when `show_reasoning` enabled ([#2118](https://github.com/NousResearch/hermes-agent/pull/2118))
- Context pressure warnings for CLI and gateway ([#2159](https://github.com/NousResearch/hermes-agent/pull/2159))
- Fix: streaming chunks concatenated without whitespace ([#2258](https://github.com/NousResearch/hermes-agent/pull/2258))
- Fix: iteration boundary linebreak prevents stream concatenation ([#2413](https://github.com/NousResearch/hermes-agent/pull/2413))
- Fix: defer streaming linebreak to prevent blank line stacking ([#2473](https://github.com/NousResearch/hermes-agent/pull/2473))
- Fix: suppress spinner animation in non-TTY environments ([#2216](https://github.com/NousResearch/hermes-agent/pull/2216))
- Fix: display provider and endpoint in API error messages ([#2266](https://github.com/NousResearch/hermes-agent/pull/2266))
- Fix: resolve garbled ANSI escape codes in status printouts ([#2448](https://github.com/NousResearch/hermes-agent/pull/2448))
- Fix: update gold ANSI color to true-color format ([#2246](https://github.com/NousResearch/hermes-agent/pull/2246))
- Fix: normalize toolset labels and use skin colors in banner ([#1912](https://github.com/NousResearch/hermes-agent/pull/1912))
### CLI Polish
- Fix: prevent 'Press ENTER to continue...' on exit ([#2555](https://github.com/NousResearch/hermes-agent/pull/2555))
- Fix: flush stdout during agent loop to prevent macOS display freeze ([#1654](https://github.com/NousResearch/hermes-agent/pull/1654))
- Fix: show human-readable error when `hermes setup` hits permissions error ([#2196](https://github.com/NousResearch/hermes-agent/pull/2196))
- Fix: `/stop` command crash + UnboundLocalError in streaming media delivery ([#2463](https://github.com/NousResearch/hermes-agent/pull/2463))
- Fix: allow custom/local endpoints without API key ([#2556](https://github.com/NousResearch/hermes-agent/pull/2556))
- Fix: Kitty keyboard protocol Shift+Enter for Ghostty/WezTerm (attempted + reverted due to prompt_toolkit crash) ([#2345](https://github.com/NousResearch/hermes-agent/pull/2345), [#2349](https://github.com/NousResearch/hermes-agent/pull/2349))
### Configuration
- **`${ENV_VAR}` substitution** in config.yaml ([#2684](https://github.com/NousResearch/hermes-agent/pull/2684))
- **Real-time config reload** — config.yaml changes apply without restart ([#2210](https://github.com/NousResearch/hermes-agent/pull/2210))
- **`custom_models.yaml`** for user-managed model additions ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214))
- **Priority-based context file selection** + CLAUDE.md support ([#2301](https://github.com/NousResearch/hermes-agent/pull/2301))
- **Merge nested YAML sections** instead of replacing on config update ([#2213](https://github.com/NousResearch/hermes-agent/pull/2213))
- Fix: config.yaml provider key overrides env var silently ([#2272](https://github.com/NousResearch/hermes-agent/pull/2272))
- Fix: log warning instead of silently swallowing config.yaml errors ([#2683](https://github.com/NousResearch/hermes-agent/pull/2683))
- Fix: disabled toolsets re-enable themselves after `hermes tools` ([#2268](https://github.com/NousResearch/hermes-agent/pull/2268))
- Fix: platform default toolsets silently override tool deselection ([#2624](https://github.com/NousResearch/hermes-agent/pull/2624))
- Fix: honor bare YAML `approvals.mode: off` ([#2620](https://github.com/NousResearch/hermes-agent/pull/2620))
- Fix: `hermes update` use `.[all]` extras with fallback ([#1728](https://github.com/NousResearch/hermes-agent/pull/1728))
- Fix: `hermes update` prompt before resetting working tree on stash conflicts ([#2390](https://github.com/NousResearch/hermes-agent/pull/2390))
- Fix: use git pull --rebase in update/install to avoid divergent branch error ([#2274](https://github.com/NousResearch/hermes-agent/pull/2274))
- Fix: add zprofile fallback and create zshrc on fresh macOS installs ([#2320](https://github.com/NousResearch/hermes-agent/pull/2320))
- Fix: remove `ANTHROPIC_BASE_URL` env var to avoid collisions ([#1675](https://github.com/NousResearch/hermes-agent/pull/1675))
- Fix: don't ask IMAP password if already in keyring or env ([#2212](https://github.com/NousResearch/hermes-agent/pull/2212))
- Fix: OpenCode Zen/Go show OpenRouter models instead of their own ([#2277](https://github.com/NousResearch/hermes-agent/pull/2277))
---
## 🏗️ Core Agent & Architecture
### New Providers
- **GitHub Copilot** — Full OAuth auth, API routing, token validation, and 400k context. ([#1924](https://github.com/NousResearch/hermes-agent/pull/1924), [#1896](https://github.com/NousResearch/hermes-agent/pull/1896), [#1879](https://github.com/NousResearch/hermes-agent/pull/1879) by @mchzimm, [#2507](https://github.com/NousResearch/hermes-agent/pull/2507))
- **Alibaba Cloud / DashScope** — Full integration with DashScope v1 runtime, model dot preservation, and 401 auth fixes ([#1673](https://github.com/NousResearch/hermes-agent/pull/1673), [#2332](https://github.com/NousResearch/hermes-agent/pull/2332), [#2459](https://github.com/NousResearch/hermes-agent/pull/2459))
- **Kilo Code** — First-class inference provider ([#1666](https://github.com/NousResearch/hermes-agent/pull/1666))
- **OpenCode Zen and OpenCode Go** — New provider backends ([#1650](https://github.com/NousResearch/hermes-agent/pull/1650), [#2393](https://github.com/NousResearch/hermes-agent/pull/2393) by @0xbyt4)
- **NeuTTS** — Local TTS provider backend with built-in setup flow, replacing the old optional skill ([#1657](https://github.com/NousResearch/hermes-agent/pull/1657), [#1664](https://github.com/NousResearch/hermes-agent/pull/1664))
### Provider Improvements
- **Eager fallback** to backup model on rate-limit errors ([#1730](https://github.com/NousResearch/hermes-agent/pull/1730))
- **Endpoint metadata** for custom model context and pricing; query local servers for actual context window size ([#1906](https://github.com/NousResearch/hermes-agent/pull/1906), [#2091](https://github.com/NousResearch/hermes-agent/pull/2091) by @dusterbloom)
- **Context length detection overhaul** — models.dev integration, provider-aware resolution, fuzzy matching for custom endpoints, `/v1/props` for llama.cpp ([#2158](https://github.com/NousResearch/hermes-agent/pull/2158), [#2051](https://github.com/NousResearch/hermes-agent/pull/2051), [#2403](https://github.com/NousResearch/hermes-agent/pull/2403))
- **Model catalog updates** — gpt-5.4-mini, gpt-5.4-nano, healer-alpha, haiku-4.5, minimax-m2.7, claude 4.6 at 1M context ([#1913](https://github.com/NousResearch/hermes-agent/pull/1913), [#1915](https://github.com/NousResearch/hermes-agent/pull/1915), [#1900](https://github.com/NousResearch/hermes-agent/pull/1900), [#2155](https://github.com/NousResearch/hermes-agent/pull/2155), [#2474](https://github.com/NousResearch/hermes-agent/pull/2474))
- **Custom endpoint improvements** — `model.base_url` in config.yaml, `api_mode` override for responses API, allow endpoints without API key, fail fast on missing keys ([#2330](https://github.com/NousResearch/hermes-agent/pull/2330), [#1651](https://github.com/NousResearch/hermes-agent/pull/1651), [#2556](https://github.com/NousResearch/hermes-agent/pull/2556), [#2445](https://github.com/NousResearch/hermes-agent/pull/2445), [#1994](https://github.com/NousResearch/hermes-agent/pull/1994), [#1998](https://github.com/NousResearch/hermes-agent/pull/1998))
- Inject model and provider into system prompt ([#1929](https://github.com/NousResearch/hermes-agent/pull/1929))
- Tie `api_mode` to provider config instead of env var ([#1656](https://github.com/NousResearch/hermes-agent/pull/1656))
- Fix: prevent Anthropic token leaking to third-party `anthropic_messages` providers ([#2389](https://github.com/NousResearch/hermes-agent/pull/2389))
- Fix: prevent Anthropic fallback from inheriting non-Anthropic `base_url` ([#2388](https://github.com/NousResearch/hermes-agent/pull/2388))
- Fix: `auxiliary_is_nous` flag never resets — leaked Nous tags to other providers ([#1713](https://github.com/NousResearch/hermes-agent/pull/1713))
- Fix: Anthropic `tool_choice 'none'` still allowed tool calls ([#1714](https://github.com/NousResearch/hermes-agent/pull/1714))
- Fix: Mistral parser nested JSON fallback extraction ([#2335](https://github.com/NousResearch/hermes-agent/pull/2335))
- Fix: MiniMax 401 auth resolved by defaulting to `anthropic_messages` ([#2103](https://github.com/NousResearch/hermes-agent/pull/2103))
- Fix: case-insensitive model family matching ([#2350](https://github.com/NousResearch/hermes-agent/pull/2350))
- Fix: ignore placeholder provider keys in activation checks ([#2358](https://github.com/NousResearch/hermes-agent/pull/2358))
- Fix: Preserve Ollama model:tag colons in context length detection ([#2149](https://github.com/NousResearch/hermes-agent/pull/2149))
- Fix: recognize Claude Code OAuth credentials in startup gate ([#1663](https://github.com/NousResearch/hermes-agent/pull/1663))
- Fix: detect Claude Code version dynamically for OAuth user-agent ([#1670](https://github.com/NousResearch/hermes-agent/pull/1670))
- Fix: OAuth flag stale after refresh/fallback ([#1890](https://github.com/NousResearch/hermes-agent/pull/1890))
- Fix: auxiliary client skips expired Codex JWT ([#2397](https://github.com/NousResearch/hermes-agent/pull/2397))
### Agent Loop
- **Gateway prompt caching** — Cache AIAgent per session, keep assistant turns, fix session restore ([#2282](https://github.com/NousResearch/hermes-agent/pull/2282), [#2284](https://github.com/NousResearch/hermes-agent/pull/2284), [#2361](https://github.com/NousResearch/hermes-agent/pull/2361))
- **Context compression overhaul** — Structured summaries, iterative updates, token-budget tail protection, configurable `summary_base_url` ([#2323](https://github.com/NousResearch/hermes-agent/pull/2323), [#1727](https://github.com/NousResearch/hermes-agent/pull/1727), [#2224](https://github.com/NousResearch/hermes-agent/pull/2224))
- **Pre-call sanitization and post-call tool guardrails** ([#1732](https://github.com/NousResearch/hermes-agent/pull/1732))
- **Auto-recover** from provider-rejected `tool_choice` by retrying without ([#2174](https://github.com/NousResearch/hermes-agent/pull/2174))
- **Background memory/skill review** replaces inline nudges ([#2235](https://github.com/NousResearch/hermes-agent/pull/2235))
- **SOUL.md as primary agent identity** instead of hardcoded default ([#1922](https://github.com/NousResearch/hermes-agent/pull/1922))
- Fix: prevent silent tool result loss during context compression ([#1993](https://github.com/NousResearch/hermes-agent/pull/1993))
- Fix: handle empty/null function arguments in tool call recovery ([#2163](https://github.com/NousResearch/hermes-agent/pull/2163))
- Fix: handle API refusal responses gracefully instead of crashing ([#2156](https://github.com/NousResearch/hermes-agent/pull/2156))
- Fix: prevent stuck agent loop on malformed tool calls ([#2114](https://github.com/NousResearch/hermes-agent/pull/2114))
- Fix: return JSON parse error to model instead of dispatching with empty args ([#2342](https://github.com/NousResearch/hermes-agent/pull/2342))
- Fix: consecutive assistant message merge drops content on mixed types ([#1703](https://github.com/NousResearch/hermes-agent/pull/1703))
- Fix: message role alternation violations in JSON recovery and error handler ([#1722](https://github.com/NousResearch/hermes-agent/pull/1722))
- Fix: `compression_attempts` resets each iteration — allowed unlimited compressions ([#1723](https://github.com/NousResearch/hermes-agent/pull/1723))
- Fix: `length_continue_retries` never resets — later truncations got fewer retries ([#1717](https://github.com/NousResearch/hermes-agent/pull/1717))
- Fix: compressor summary role violated consecutive-role constraint ([#1720](https://github.com/NousResearch/hermes-agent/pull/1720), [#1743](https://github.com/NousResearch/hermes-agent/pull/1743))
- Fix: remove hardcoded `gemini-3-flash-preview` as default summary model ([#2464](https://github.com/NousResearch/hermes-agent/pull/2464))
- Fix: correctly handle empty tool results ([#2201](https://github.com/NousResearch/hermes-agent/pull/2201))
- Fix: crash on None entry in `tool_calls` list ([#2209](https://github.com/NousResearch/hermes-agent/pull/2209) by @0xbyt4, [#2316](https://github.com/NousResearch/hermes-agent/pull/2316))
- Fix: per-thread persistent event loops in worker threads ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214) by @jquesnelle)
- Fix: prevent 'event loop already running' when async tools run in parallel ([#2207](https://github.com/NousResearch/hermes-agent/pull/2207))
- Fix: strip ANSI at the source — clean terminal output before it reaches the model ([#2115](https://github.com/NousResearch/hermes-agent/pull/2115))
- Fix: skip top-level `cache_control` on role:tool for OpenRouter ([#2391](https://github.com/NousResearch/hermes-agent/pull/2391))
- Fix: delegate tool — save parent tool names before child construction mutates global ([#2083](https://github.com/NousResearch/hermes-agent/pull/2083) by @ygd58, [#1894](https://github.com/NousResearch/hermes-agent/pull/1894))
- Fix: only strip last assistant message if empty string ([#2326](https://github.com/NousResearch/hermes-agent/pull/2326))
### Session & Memory
- **Session search** and management slash commands ([#2198](https://github.com/NousResearch/hermes-agent/pull/2198))
- **Auto session titles** and `.hermes.md` project config ([#1712](https://github.com/NousResearch/hermes-agent/pull/1712))
- Fix: concurrent memory writes silently drop entries — added file locking ([#1726](https://github.com/NousResearch/hermes-agent/pull/1726))
- Fix: search all sources by default in `session_search` ([#1892](https://github.com/NousResearch/hermes-agent/pull/1892))
- Fix: handle hyphenated FTS5 queries and preserve quoted literals ([#1776](https://github.com/NousResearch/hermes-agent/pull/1776))
- Fix: skip corrupt lines in `load_transcript` instead of crashing ([#1744](https://github.com/NousResearch/hermes-agent/pull/1744))
- Fix: normalize session keys to prevent case-sensitive duplicates ([#2157](https://github.com/NousResearch/hermes-agent/pull/2157))
- Fix: prevent `session_search` crash when no sessions exist ([#2194](https://github.com/NousResearch/hermes-agent/pull/2194))
- Fix: reset token counters on new session for accurate usage display ([#2101](https://github.com/NousResearch/hermes-agent/pull/2101) by @InB4DevOps)
- Fix: prevent stale memory overwrites by flush agent ([#2687](https://github.com/NousResearch/hermes-agent/pull/2687))
- Fix: remove synthetic error message injection, fix session resume after repeated failures ([#2303](https://github.com/NousResearch/hermes-agent/pull/2303))
- Fix: quiet mode with `--resume` now passes conversation_history ([#2357](https://github.com/NousResearch/hermes-agent/pull/2357))
- Fix: unify resume logic in batch mode ([#2331](https://github.com/NousResearch/hermes-agent/pull/2331))
### Honcho Memory
- Honcho config fixes and @ context reference integration ([#2343](https://github.com/NousResearch/hermes-agent/pull/2343))
- Self-hosted / Docker configuration documentation ([#2475](https://github.com/NousResearch/hermes-agent/pull/2475))
---
## 📱 Messaging Platforms (Gateway)
### New Platform Adapters
- **Signal Messenger** — Full adapter with attachment handling, group message filtering, and Note to Self echo-back protection ([#2206](https://github.com/NousResearch/hermes-agent/pull/2206), [#2400](https://github.com/NousResearch/hermes-agent/pull/2400), [#2297](https://github.com/NousResearch/hermes-agent/pull/2297), [#2156](https://github.com/NousResearch/hermes-agent/pull/2156))
- **DingTalk** — Adapter with gateway wiring and setup docs ([#1685](https://github.com/NousResearch/hermes-agent/pull/1685), [#1690](https://github.com/NousResearch/hermes-agent/pull/1690), [#1692](https://github.com/NousResearch/hermes-agent/pull/1692))
- **SMS (Twilio)** ([#1688](https://github.com/NousResearch/hermes-agent/pull/1688))
- **Mattermost** — With @-mention-only channel filter ([#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2443](https://github.com/NousResearch/hermes-agent/pull/2443))
- **Matrix** — With vision support and image caching ([#1683](https://github.com/NousResearch/hermes-agent/pull/1683), [#2520](https://github.com/NousResearch/hermes-agent/pull/2520))
- **Webhook** — Platform adapter for external event triggers ([#2166](https://github.com/NousResearch/hermes-agent/pull/2166))
- **OpenAI-compatible API server** — `/v1/chat/completions` endpoint with `/api/jobs` cron management ([#1756](https://github.com/NousResearch/hermes-agent/pull/1756), [#2450](https://github.com/NousResearch/hermes-agent/pull/2450), [#2456](https://github.com/NousResearch/hermes-agent/pull/2456))
### Telegram Improvements
- MarkdownV2 support — strikethrough, spoiler, blockquotes, escape parentheses/braces/backslashes/backticks ([#2199](https://github.com/NousResearch/hermes-agent/pull/2199), [#2200](https://github.com/NousResearch/hermes-agent/pull/2200) by @llbn, [#2386](https://github.com/NousResearch/hermes-agent/pull/2386))
- Auto-detect HTML tags and use `parse_mode=HTML` ([#1709](https://github.com/NousResearch/hermes-agent/pull/1709))
- Telegram group vision support + thread-based sessions ([#2153](https://github.com/NousResearch/hermes-agent/pull/2153))
- Auto-reconnect polling after network interruption ([#2517](https://github.com/NousResearch/hermes-agent/pull/2517))
- Aggregate split text messages before dispatching ([#1674](https://github.com/NousResearch/hermes-agent/pull/1674))
- Fix: streaming config bridge, not-modified, flood control ([#1782](https://github.com/NousResearch/hermes-agent/pull/1782), [#1783](https://github.com/NousResearch/hermes-agent/pull/1783))
- Fix: edited_message event crashes ([#2074](https://github.com/NousResearch/hermes-agent/pull/2074))
- Fix: retry 409 polling conflicts before giving up ([#2312](https://github.com/NousResearch/hermes-agent/pull/2312))
- Fix: topic delivery via `platform:chat_id:thread_id` format ([#2455](https://github.com/NousResearch/hermes-agent/pull/2455))
### Discord Improvements
- Document caching and text-file injection ([#2503](https://github.com/NousResearch/hermes-agent/pull/2503))
- Persistent typing indicator for DMs ([#2468](https://github.com/NousResearch/hermes-agent/pull/2468))
- Discord DM vision — inline images + attachment analysis ([#2186](https://github.com/NousResearch/hermes-agent/pull/2186))
- Persist thread participation across gateway restarts ([#1661](https://github.com/NousResearch/hermes-agent/pull/1661))
- Fix: gateway crash on non-ASCII guild names ([#2302](https://github.com/NousResearch/hermes-agent/pull/2302))
- Fix: thread permission errors ([#2073](https://github.com/NousResearch/hermes-agent/pull/2073))
- Fix: slash event routing in threads ([#2460](https://github.com/NousResearch/hermes-agent/pull/2460))
- Fix: remove bugged followup messages + `/ask` command ([#1836](https://github.com/NousResearch/hermes-agent/pull/1836))
- Fix: graceful WebSocket reconnection ([#2127](https://github.com/NousResearch/hermes-agent/pull/2127))
- Fix: voice channel TTS when streaming enabled ([#2322](https://github.com/NousResearch/hermes-agent/pull/2322))
### WhatsApp & Other Adapters
- WhatsApp: outbound `send_message` routing ([#1769](https://github.com/NousResearch/hermes-agent/pull/1769) by @sai-samarth), LID format self-chat ([#1667](https://github.com/NousResearch/hermes-agent/pull/1667)), `reply_prefix` config fix ([#1923](https://github.com/NousResearch/hermes-agent/pull/1923)), restart on bridge child exit ([#2334](https://github.com/NousResearch/hermes-agent/pull/2334)), image/bridge improvements ([#2181](https://github.com/NousResearch/hermes-agent/pull/2181))
- Matrix: correct `reply_to_message_id` parameter ([#1895](https://github.com/NousResearch/hermes-agent/pull/1895)), bare media types fix ([#1736](https://github.com/NousResearch/hermes-agent/pull/1736))
- Mattermost: MIME types for media attachments ([#2329](https://github.com/NousResearch/hermes-agent/pull/2329))
### Gateway Core
- **Auto-reconnect** failed platforms with exponential backoff ([#2584](https://github.com/NousResearch/hermes-agent/pull/2584))
- **Notify users when session auto-resets** ([#2519](https://github.com/NousResearch/hermes-agent/pull/2519))
- **Reply-to message context** for out-of-session replies ([#1662](https://github.com/NousResearch/hermes-agent/pull/1662))
- **Ignore unauthorized DMs** config option ([#1919](https://github.com/NousResearch/hermes-agent/pull/1919))
- Fix: `/reset` in thread-mode resets global session instead of thread ([#2254](https://github.com/NousResearch/hermes-agent/pull/2254))
- Fix: deliver MEDIA: files after streaming responses ([#2382](https://github.com/NousResearch/hermes-agent/pull/2382))
- Fix: cap interrupt recursion depth to prevent resource exhaustion ([#1659](https://github.com/NousResearch/hermes-agent/pull/1659))
- Fix: detect stopped processes and release stale locks on `--replace` ([#2406](https://github.com/NousResearch/hermes-agent/pull/2406), [#1908](https://github.com/NousResearch/hermes-agent/pull/1908))
- Fix: PID-based wait with force-kill for gateway restart ([#1902](https://github.com/NousResearch/hermes-agent/pull/1902))
- Fix: prevent `--replace` mode from killing the caller process ([#2185](https://github.com/NousResearch/hermes-agent/pull/2185))
- Fix: `/model` shows active fallback model instead of config default ([#1660](https://github.com/NousResearch/hermes-agent/pull/1660))
- Fix: `/title` command fails when session doesn't exist in SQLite yet ([#2379](https://github.com/NousResearch/hermes-agent/pull/2379) by @ten-jampa)
- Fix: process `/queue`'d messages after agent completion ([#2469](https://github.com/NousResearch/hermes-agent/pull/2469))
- Fix: strip orphaned `tool_results` + let `/reset` bypass running agent ([#2180](https://github.com/NousResearch/hermes-agent/pull/2180))
- Fix: prevent agents from starting gateway outside systemd management ([#2617](https://github.com/NousResearch/hermes-agent/pull/2617))
- Fix: prevent systemd restart storm on gateway connection failure ([#2327](https://github.com/NousResearch/hermes-agent/pull/2327))
- Fix: include resolved node path in systemd unit ([#1767](https://github.com/NousResearch/hermes-agent/pull/1767) by @sai-samarth)
- Fix: send error details to user in gateway outer exception handler ([#1966](https://github.com/NousResearch/hermes-agent/pull/1966))
- Fix: improve error handling for 429 usage limits and 500 context overflow ([#1839](https://github.com/NousResearch/hermes-agent/pull/1839))
- Fix: add all missing platform allowlist env vars to startup warning check ([#2628](https://github.com/NousResearch/hermes-agent/pull/2628))
- Fix: media delivery fails for file paths containing spaces ([#2621](https://github.com/NousResearch/hermes-agent/pull/2621))
- Fix: duplicate session-key collision in multi-platform gateway ([#2171](https://github.com/NousResearch/hermes-agent/pull/2171))
- Fix: Matrix and Mattermost never report as connected ([#1711](https://github.com/NousResearch/hermes-agent/pull/1711))
- Fix: PII redaction config never read — missing yaml import ([#1701](https://github.com/NousResearch/hermes-agent/pull/1701))
- Fix: NameError on skill slash commands ([#1697](https://github.com/NousResearch/hermes-agent/pull/1697))
- Fix: persist watcher metadata in checkpoint for crash recovery ([#1706](https://github.com/NousResearch/hermes-agent/pull/1706))
- Fix: pass `message_thread_id` in send_image_file, send_document, send_video ([#2339](https://github.com/NousResearch/hermes-agent/pull/2339))
- Fix: media-group aggregation on rapid successive photo messages ([#2160](https://github.com/NousResearch/hermes-agent/pull/2160))
---
## 🔧 Tool System
### MCP Enhancements
- **MCP server management CLI** + OAuth 2.1 PKCE auth ([#2465](https://github.com/NousResearch/hermes-agent/pull/2465))
- **Expose MCP servers as standalone toolsets** ([#1907](https://github.com/NousResearch/hermes-agent/pull/1907))
- **Interactive MCP tool configuration** in `hermes tools` ([#1694](https://github.com/NousResearch/hermes-agent/pull/1694))
- Fix: MCP-OAuth port mismatch, path traversal, and shared handler state ([#2552](https://github.com/NousResearch/hermes-agent/pull/2552))
- Fix: preserve MCP tool registrations across session resets ([#2124](https://github.com/NousResearch/hermes-agent/pull/2124))
- Fix: concurrent file access crash + duplicate MCP registration ([#2154](https://github.com/NousResearch/hermes-agent/pull/2154))
- Fix: normalise MCP schemas + expand session list columns ([#2102](https://github.com/NousResearch/hermes-agent/pull/2102))
- Fix: `tool_choice` `mcp_` prefix handling ([#1775](https://github.com/NousResearch/hermes-agent/pull/1775))
### Web Tool Backends
- **Tavily** as web search/extract/crawl backend ([#1731](https://github.com/NousResearch/hermes-agent/pull/1731))
- **Parallel** as alternative web search/extract backend ([#1696](https://github.com/NousResearch/hermes-agent/pull/1696))
- **Configurable web backend** — Firecrawl/BeautifulSoup/Playwright selection ([#2256](https://github.com/NousResearch/hermes-agent/pull/2256))
- Fix: whitespace-only env vars bypass web backend detection ([#2341](https://github.com/NousResearch/hermes-agent/pull/2341))
### New Tools
- **IMAP email** reading and sending ([#2173](https://github.com/NousResearch/hermes-agent/pull/2173))
- **STT (speech-to-text)** tool using Whisper API ([#2072](https://github.com/NousResearch/hermes-agent/pull/2072))
- **Route-aware pricing estimates** ([#1695](https://github.com/NousResearch/hermes-agent/pull/1695))
### Tool Improvements
- TTS: `base_url` support for OpenAI TTS provider ([#2064](https://github.com/NousResearch/hermes-agent/pull/2064) by @hanai)
- Vision: configurable timeout, tilde expansion in file paths, DM vision with multi-image and base64 fallback ([#2480](https://github.com/NousResearch/hermes-agent/pull/2480), [#2585](https://github.com/NousResearch/hermes-agent/pull/2585), [#2211](https://github.com/NousResearch/hermes-agent/pull/2211))
- Browser: race condition fix in session creation ([#1721](https://github.com/NousResearch/hermes-agent/pull/1721)), TypeError on unexpected LLM params ([#1735](https://github.com/NousResearch/hermes-agent/pull/1735))
- File tools: strip ANSI escape codes from write_file and patch content ([#2532](https://github.com/NousResearch/hermes-agent/pull/2532)), include pagination args in repeated search key ([#1824](https://github.com/NousResearch/hermes-agent/pull/1824) by @cutepawss), improve fuzzy matching accuracy + position calculation refactor ([#2096](https://github.com/NousResearch/hermes-agent/pull/2096), [#1681](https://github.com/NousResearch/hermes-agent/pull/1681))
- Code execution: resource leak and double socket close fix ([#2381](https://github.com/NousResearch/hermes-agent/pull/2381))
- Delegate: thread safety for concurrent subagent delegation ([#1672](https://github.com/NousResearch/hermes-agent/pull/1672)), preserve parent agent's tool list after delegation ([#1778](https://github.com/NousResearch/hermes-agent/pull/1778))
- Fix: make concurrent tool batching path-aware for file mutations ([#1914](https://github.com/NousResearch/hermes-agent/pull/1914))
- Fix: chunk long messages in `send_message_tool` before platform dispatch ([#1646](https://github.com/NousResearch/hermes-agent/pull/1646))
- Fix: add missing 'messaging' toolset ([#1718](https://github.com/NousResearch/hermes-agent/pull/1718))
- Fix: prevent unavailable tool names from leaking into model schemas ([#2072](https://github.com/NousResearch/hermes-agent/pull/2072))
- Fix: pass visited set by reference to prevent diamond dependency duplication ([#2311](https://github.com/NousResearch/hermes-agent/pull/2311))
- Fix: Daytona sandbox lookup migrated from `find_one` to `get/list` ([#2063](https://github.com/NousResearch/hermes-agent/pull/2063) by @rovle)
---
## 🧩 Skills Ecosystem
### Skills System Improvements
- **Agent-created skills** — Caution-level findings allowed, dangerous skills ask instead of block ([#1840](https://github.com/NousResearch/hermes-agent/pull/1840), [#2446](https://github.com/NousResearch/hermes-agent/pull/2446))
- **`--yes` flag** to bypass confirmation in `/skills install` and uninstall ([#1647](https://github.com/NousResearch/hermes-agent/pull/1647))
- **Disabled skills respected** across banner, system prompt, and slash commands ([#1897](https://github.com/NousResearch/hermes-agent/pull/1897))
- Fix: skills custom_tools import crash + sandbox file_tools integration ([#2239](https://github.com/NousResearch/hermes-agent/pull/2239))
- Fix: agent-created skills with pip requirements crash on install ([#2145](https://github.com/NousResearch/hermes-agent/pull/2145))
- Fix: race condition in `Skills.__init__` when `hub.yaml` missing ([#2242](https://github.com/NousResearch/hermes-agent/pull/2242))
- Fix: validate skill metadata before install and block duplicates ([#2241](https://github.com/NousResearch/hermes-agent/pull/2241))
- Fix: skills hub inspect/resolve — 4 bugs in inspect, redirects, discovery, tap list ([#2447](https://github.com/NousResearch/hermes-agent/pull/2447))
- Fix: agent-created skills keep working after session reset ([#2121](https://github.com/NousResearch/hermes-agent/pull/2121))
### New Skills
- **OCR-and-documents** — PDF/DOCX/XLS/PPTX/image OCR with optional GPU ([#2236](https://github.com/NousResearch/hermes-agent/pull/2236), [#2461](https://github.com/NousResearch/hermes-agent/pull/2461))
- **Huggingface-hub** bundled skill ([#1921](https://github.com/NousResearch/hermes-agent/pull/1921))
- **Sherlock OSINT** username search ([#1671](https://github.com/NousResearch/hermes-agent/pull/1671))
- **Meme-generation** — Image generator with Pillow ([#2344](https://github.com/NousResearch/hermes-agent/pull/2344))
- **Bioinformatics** gateway skill — index to 400+ bio skills ([#2387](https://github.com/NousResearch/hermes-agent/pull/2387))
- **Inference.sh** skill (terminal-based) ([#1686](https://github.com/NousResearch/hermes-agent/pull/1686))
- **Base blockchain** optional skill ([#1643](https://github.com/NousResearch/hermes-agent/pull/1643))
- **3D-model-viewer** optional skill ([#2226](https://github.com/NousResearch/hermes-agent/pull/2226))
- **FastMCP** optional skill ([#2113](https://github.com/NousResearch/hermes-agent/pull/2113))
- **Hermes-agent-setup** skill ([#1905](https://github.com/NousResearch/hermes-agent/pull/1905))
---
## 🔌 Plugin System Enhancements
- **TUI extension hooks** — Build custom CLIs on top of Hermes ([#2333](https://github.com/NousResearch/hermes-agent/pull/2333))
- **`hermes plugins install/remove/list`** commands ([#2337](https://github.com/NousResearch/hermes-agent/pull/2337))
- **Slash command registration** for plugins ([#2359](https://github.com/NousResearch/hermes-agent/pull/2359))
- **`session:end` lifecycle event** hook ([#1725](https://github.com/NousResearch/hermes-agent/pull/1725))
- Fix: require opt-in for project plugin discovery ([#2215](https://github.com/NousResearch/hermes-agent/pull/2215))
---
## 🔒 Security & Reliability
### Security
- **SSRF protection** for vision_tools and web_tools ([#2679](https://github.com/NousResearch/hermes-agent/pull/2679))
- **Shell injection prevention** in `_expand_path` via `~user` path suffix ([#2685](https://github.com/NousResearch/hermes-agent/pull/2685))
- **Block untrusted browser-origin** API server access ([#2451](https://github.com/NousResearch/hermes-agent/pull/2451))
- **Block sandbox backend creds** from subprocess env ([#1658](https://github.com/NousResearch/hermes-agent/pull/1658))
- **Block @ references** from reading secrets outside workspace ([#2601](https://github.com/NousResearch/hermes-agent/pull/2601) by @Gutslabs)
- **Malicious code pattern pre-exec scanner** for terminal_tool ([#2245](https://github.com/NousResearch/hermes-agent/pull/2245))
- **Harden terminal safety** and sandbox file writes ([#1653](https://github.com/NousResearch/hermes-agent/pull/1653))
- **PKCE verifier leak** fix + OAuth refresh Content-Type ([#1775](https://github.com/NousResearch/hermes-agent/pull/1775))
- **Eliminate SQL string formatting** in `execute()` calls ([#2061](https://github.com/NousResearch/hermes-agent/pull/2061) by @dusterbloom)
- **Harden jobs API** — input limits, field whitelist, startup check ([#2456](https://github.com/NousResearch/hermes-agent/pull/2456))
### Reliability
- Thread locks on 4 SessionDB methods ([#1704](https://github.com/NousResearch/hermes-agent/pull/1704))
- File locking for concurrent memory writes ([#1726](https://github.com/NousResearch/hermes-agent/pull/1726))
- Handle OpenRouter errors gracefully ([#2112](https://github.com/NousResearch/hermes-agent/pull/2112))
- Guard print() calls against OSError ([#1668](https://github.com/NousResearch/hermes-agent/pull/1668))
- Safely handle non-string inputs in redacting formatter ([#2392](https://github.com/NousResearch/hermes-agent/pull/2392), [#1700](https://github.com/NousResearch/hermes-agent/pull/1700))
- ACP: preserve session provider on model switch, persist sessions to disk ([#2380](https://github.com/NousResearch/hermes-agent/pull/2380), [#2071](https://github.com/NousResearch/hermes-agent/pull/2071))
- API server: persist ResponseStore to SQLite across restarts ([#2472](https://github.com/NousResearch/hermes-agent/pull/2472))
- Fix: `fetch_nous_models` always TypeError from positional args ([#1699](https://github.com/NousResearch/hermes-agent/pull/1699))
- Fix: resolve merge conflict markers in cli.py breaking startup ([#2347](https://github.com/NousResearch/hermes-agent/pull/2347))
- Fix: `minisweagent_path.py` missing from wheel ([#2098](https://github.com/NousResearch/hermes-agent/pull/2098) by @JiwaniZakir)
### Cron System
- **`[SILENT]` response** — cron agents can suppress delivery ([#1833](https://github.com/NousResearch/hermes-agent/pull/1833))
- **Scale missed-job grace window** with schedule frequency ([#2449](https://github.com/NousResearch/hermes-agent/pull/2449))
- **Recover recent one-shot jobs** ([#1918](https://github.com/NousResearch/hermes-agent/pull/1918))
- Fix: normalize `repeat<=0` to None — jobs deleted after first run when LLM passes -1 ([#2612](https://github.com/NousResearch/hermes-agent/pull/2612) by @Mibayy)
- Fix: Matrix added to scheduler delivery platform_map ([#2167](https://github.com/NousResearch/hermes-agent/pull/2167) by @buntingszn)
- Fix: naive ISO timestamps without timezone — jobs fire at wrong time ([#1729](https://github.com/NousResearch/hermes-agent/pull/1729))
- Fix: `get_due_jobs` reads `jobs.json` twice — race condition ([#1716](https://github.com/NousResearch/hermes-agent/pull/1716))
- Fix: silent jobs return empty response for delivery skip ([#2442](https://github.com/NousResearch/hermes-agent/pull/2442))
- Fix: stop injecting cron outputs into gateway session history ([#2313](https://github.com/NousResearch/hermes-agent/pull/2313))
- Fix: close abandoned coroutine when `asyncio.run()` raises RuntimeError ([#2317](https://github.com/NousResearch/hermes-agent/pull/2317))
---
## 🧪 Testing
- Resolve all consistently failing tests ([#2488](https://github.com/NousResearch/hermes-agent/pull/2488))
- Replace `FakePath` with `monkeypatch` for Python 3.12 compat ([#2444](https://github.com/NousResearch/hermes-agent/pull/2444))
- Align Hermes setup and full-suite expectations ([#1710](https://github.com/NousResearch/hermes-agent/pull/1710))
---
## 📚 Documentation
- Comprehensive docs update for recent features ([#1693](https://github.com/NousResearch/hermes-agent/pull/1693), [#2183](https://github.com/NousResearch/hermes-agent/pull/2183))
- Alibaba Cloud and DingTalk setup guides ([#1687](https://github.com/NousResearch/hermes-agent/pull/1687), [#1692](https://github.com/NousResearch/hermes-agent/pull/1692))
- Detailed skills documentation ([#2244](https://github.com/NousResearch/hermes-agent/pull/2244))
- Honcho self-hosted / Docker configuration ([#2475](https://github.com/NousResearch/hermes-agent/pull/2475))
- Context length detection FAQ and quickstart references ([#2179](https://github.com/NousResearch/hermes-agent/pull/2179))
- Fix docs inconsistencies across reference and user guides ([#1995](https://github.com/NousResearch/hermes-agent/pull/1995))
- Fix MCP install commands — use uv, not bare pip ([#1909](https://github.com/NousResearch/hermes-agent/pull/1909))
- Replace ASCII diagrams with Mermaid/lists ([#2402](https://github.com/NousResearch/hermes-agent/pull/2402))
- Gemini OAuth provider implementation plan ([#2467](https://github.com/NousResearch/hermes-agent/pull/2467))
- Discord Server Members Intent marked as required ([#2330](https://github.com/NousResearch/hermes-agent/pull/2330))
- Fix MDX build error in api-server.md ([#1787](https://github.com/NousResearch/hermes-agent/pull/1787))
- Align venv path to match installer ([#2114](https://github.com/NousResearch/hermes-agent/pull/2114))
- New skills added to hub index ([#2281](https://github.com/NousResearch/hermes-agent/pull/2281))
---
## 👥 Contributors
### Core
- **@teknium1** (Teknium) — 280 PRs
### Community Contributors
- **@mchzimm** (to_the_max) — GitHub Copilot provider integration ([#1879](https://github.com/NousResearch/hermes-agent/pull/1879))
- **@jquesnelle** (Jeffrey Quesnelle) — Per-thread persistent event loops fix ([#2214](https://github.com/NousResearch/hermes-agent/pull/2214))
- **@llbn** (lbn) — Telegram MarkdownV2 strikethrough, spoiler, blockquotes, and escape fixes ([#2199](https://github.com/NousResearch/hermes-agent/pull/2199), [#2200](https://github.com/NousResearch/hermes-agent/pull/2200))
- **@dusterbloom** — SQL injection prevention + local server context window querying ([#2061](https://github.com/NousResearch/hermes-agent/pull/2061), [#2091](https://github.com/NousResearch/hermes-agent/pull/2091))
- **@0xbyt4** — Anthropic tool_calls None guard + OpenCode-Go provider config fix ([#2209](https://github.com/NousResearch/hermes-agent/pull/2209), [#2393](https://github.com/NousResearch/hermes-agent/pull/2393))
- **@sai-samarth** (Saisamarth) — WhatsApp send_message routing + systemd node path ([#1769](https://github.com/NousResearch/hermes-agent/pull/1769), [#1767](https://github.com/NousResearch/hermes-agent/pull/1767))
- **@Gutslabs** (Guts) — Block @ references from reading secrets ([#2601](https://github.com/NousResearch/hermes-agent/pull/2601))
- **@Mibayy** (Mibay) — Cron job repeat normalization ([#2612](https://github.com/NousResearch/hermes-agent/pull/2612))
- **@ten-jampa** (Tenzin Jampa) — Gateway /title command fix ([#2379](https://github.com/NousResearch/hermes-agent/pull/2379))
- **@cutepawss** (lila) — File tools search pagination fix ([#1824](https://github.com/NousResearch/hermes-agent/pull/1824))
- **@hanai** (Hanai) — OpenAI TTS base_url support ([#2064](https://github.com/NousResearch/hermes-agent/pull/2064))
- **@rovle** (Lovre Pešut) — Daytona sandbox API migration ([#2063](https://github.com/NousResearch/hermes-agent/pull/2063))
- **@buntingszn** (bunting szn) — Matrix cron delivery support ([#2167](https://github.com/NousResearch/hermes-agent/pull/2167))
- **@InB4DevOps** — Token counter reset on new session ([#2101](https://github.com/NousResearch/hermes-agent/pull/2101))
- **@JiwaniZakir** (Zakir Jiwani) — Missing file in wheel fix ([#2098](https://github.com/NousResearch/hermes-agent/pull/2098))
- **@ygd58** (buray) — Delegate tool parent tool names fix ([#2083](https://github.com/NousResearch/hermes-agent/pull/2083))
---
**Full Changelog**: [v2026.3.17...v2026.3.23](https://github.com/NousResearch/hermes-agent/compare/v2026.3.17...v2026.3.23)

View File

@@ -1,348 +0,0 @@
# Hermes Agent v0.5.0 (v2026.3.28)
**Release Date:** March 28, 2026
> The hardening release — Hugging Face provider, /model command overhaul, Telegram Private Chat Topics, native Modal SDK, plugin lifecycle hooks, tool-use enforcement for GPT models, Nix flake, 50+ security and reliability fixes, and a comprehensive supply chain audit.
---
## ✨ Highlights
- **Nous Portal now supports 400+ models** — The Nous Research inference portal has expanded dramatically, giving Hermes Agent users access to over 400 models through a single provider endpoint
- **Hugging Face as a first-class inference provider** — Full integration with HF Inference API including curated agentic model picker that maps to OpenRouter analogues, live `/models` endpoint probe, and setup wizard flow ([#3419](https://github.com/NousResearch/hermes-agent/pull/3419), [#3440](https://github.com/NousResearch/hermes-agent/pull/3440))
- **Telegram Private Chat Topics** — Project-based conversations with functional skill binding per topic, enabling isolated workflows within a single Telegram chat ([#3163](https://github.com/NousResearch/hermes-agent/pull/3163))
- **Native Modal SDK backend** — Replaced swe-rex dependency with native Modal SDK (`Sandbox.create.aio` + `exec.aio`), eliminating tunnels and simplifying the Modal terminal backend ([#3538](https://github.com/NousResearch/hermes-agent/pull/3538))
- **Plugin lifecycle hooks activated** — `pre_llm_call`, `post_llm_call`, `on_session_start`, and `on_session_end` hooks now fire in the agent loop and CLI/gateway, completing the plugin hook system ([#3542](https://github.com/NousResearch/hermes-agent/pull/3542))
- **Improved OpenAI Model Reliability** — Added `GPT_TOOL_USE_GUIDANCE` to prevent GPT models from describing intended actions instead of making tool calls, plus automatic stripping of stale budget warnings from conversation history that caused models to avoid tools across turns ([#3528](https://github.com/NousResearch/hermes-agent/pull/3528))
- **Nix flake** — Full uv2nix build, NixOS module with persistent container mode, auto-generated config keys from Python source, and suffix PATHs for agent-friendliness ([#20](https://github.com/NousResearch/hermes-agent/pull/20), [#3274](https://github.com/NousResearch/hermes-agent/pull/3274), [#3061](https://github.com/NousResearch/hermes-agent/pull/3061)) by @alt-glitch
- **Supply chain hardening** — Removed compromised `litellm` dependency, pinned all dependency version ranges, regenerated `uv.lock` with hashes, added CI workflow scanning PRs for supply chain attack patterns, and bumped deps to fix CVEs ([#2796](https://github.com/NousResearch/hermes-agent/pull/2796), [#2810](https://github.com/NousResearch/hermes-agent/pull/2810), [#2812](https://github.com/NousResearch/hermes-agent/pull/2812), [#2816](https://github.com/NousResearch/hermes-agent/pull/2816), [#3073](https://github.com/NousResearch/hermes-agent/pull/3073))
- **Anthropic output limits fix** — Replaced hardcoded 16K `max_tokens` with per-model native output limits (128K for Opus 4.6, 64K for Sonnet 4.6), fixing "Response truncated" and thinking-budget exhaustion on direct Anthropic API ([#3426](https://github.com/NousResearch/hermes-agent/pull/3426), [#3444](https://github.com/NousResearch/hermes-agent/pull/3444))
---
## 🏗️ Core Agent & Architecture
### New Provider: Hugging Face
- First-class Hugging Face Inference API integration with auth, setup wizard, and model picker ([#3419](https://github.com/NousResearch/hermes-agent/pull/3419))
- Curated model list mapping OpenRouter agentic defaults to HF equivalents — providers with 8+ curated models skip live `/models` probe for speed ([#3440](https://github.com/NousResearch/hermes-agent/pull/3440))
- Added glm-5-turbo to Z.AI provider model list ([#3095](https://github.com/NousResearch/hermes-agent/pull/3095))
### Provider & Model Improvements
- `/model` command overhaul — extracted shared `switch_model()` pipeline for CLI and gateway, custom endpoint support, provider-aware routing ([#2795](https://github.com/NousResearch/hermes-agent/pull/2795), [#2799](https://github.com/NousResearch/hermes-agent/pull/2799))
- Removed `/model` slash command from CLI and gateway in favor of `hermes model` subcommand ([#3080](https://github.com/NousResearch/hermes-agent/pull/3080))
- Preserve `custom` provider instead of silently remapping to `openrouter` ([#2792](https://github.com/NousResearch/hermes-agent/pull/2792))
- Read root-level `provider` and `base_url` from config.yaml into model config ([#3112](https://github.com/NousResearch/hermes-agent/pull/3112))
- Align Nous Portal model slugs with OpenRouter naming ([#3253](https://github.com/NousResearch/hermes-agent/pull/3253))
- Fix Alibaba provider default endpoint and model list ([#3484](https://github.com/NousResearch/hermes-agent/pull/3484))
- Allow MiniMax users to override `/v1``/anthropic` auto-correction ([#3553](https://github.com/NousResearch/hermes-agent/pull/3553))
- Migrate OAuth token refresh to `platform.claude.com` with fallback ([#3246](https://github.com/NousResearch/hermes-agent/pull/3246))
### Agent Loop & Conversation
- **Improved OpenAI model reliability** — `GPT_TOOL_USE_GUIDANCE` prevents GPT models from describing actions instead of calling tools + automatic budget warning stripping from history ([#3528](https://github.com/NousResearch/hermes-agent/pull/3528))
- **Surface lifecycle events** — All retry, fallback, and compression events now surface to the user as formatted messages ([#3153](https://github.com/NousResearch/hermes-agent/pull/3153))
- **Anthropic output limits** — Per-model native output limits instead of hardcoded 16K `max_tokens` ([#3426](https://github.com/NousResearch/hermes-agent/pull/3426))
- **Thinking-budget exhaustion detection** — Skip useless continuation retries when model uses all output tokens on reasoning ([#3444](https://github.com/NousResearch/hermes-agent/pull/3444))
- Always prefer streaming for API calls to prevent hung subagents ([#3120](https://github.com/NousResearch/hermes-agent/pull/3120))
- Restore safe non-streaming fallback after stream failures ([#3020](https://github.com/NousResearch/hermes-agent/pull/3020))
- Give subagents independent iteration budgets ([#3004](https://github.com/NousResearch/hermes-agent/pull/3004))
- Update `api_key` in `_try_activate_fallback` for subagent auth ([#3103](https://github.com/NousResearch/hermes-agent/pull/3103))
- Graceful return on max retries instead of crashing thread ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Count compression restarts toward retry limit ([#3070](https://github.com/NousResearch/hermes-agent/pull/3070))
- Include tool tokens in preflight estimate, guard context probe persistence ([#3164](https://github.com/NousResearch/hermes-agent/pull/3164))
- Update context compressor limits after fallback activation ([#3305](https://github.com/NousResearch/hermes-agent/pull/3305))
- Validate empty user messages to prevent Anthropic API 400 errors ([#3322](https://github.com/NousResearch/hermes-agent/pull/3322))
- GLM reasoning-only and max-length handling ([#3010](https://github.com/NousResearch/hermes-agent/pull/3010))
- Increase API timeout default from 900s to 1800s for slow-thinking models ([#3431](https://github.com/NousResearch/hermes-agent/pull/3431))
- Send `max_tokens` for Claude/OpenRouter + retry SSE connection errors ([#3497](https://github.com/NousResearch/hermes-agent/pull/3497))
- Prevent AsyncOpenAI/httpx cross-loop deadlock in gateway mode ([#2701](https://github.com/NousResearch/hermes-agent/pull/2701)) by @ctlst
### Streaming & Reasoning
- **Persist reasoning across gateway session turns** with new schema v6 columns (`reasoning`, `reasoning_details`, `codex_reasoning_items`) ([#2974](https://github.com/NousResearch/hermes-agent/pull/2974))
- Detect and kill stale SSE connections ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Fix stale stream detector race causing spurious `RemoteProtocolError` ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Skip duplicate callback for `<think>`-extracted reasoning during streaming ([#3116](https://github.com/NousResearch/hermes-agent/pull/3116))
- Preserve reasoning fields in `rewrite_transcript` ([#3311](https://github.com/NousResearch/hermes-agent/pull/3311))
- Preserve Gemini thought signatures in streamed tool calls ([#2997](https://github.com/NousResearch/hermes-agent/pull/2997))
- Ensure first delta is fired during reasoning updates ([untagged commit](https://github.com/NousResearch/hermes-agent))
### Session & Memory
- **Session search recent sessions mode** — Omit query to browse recent sessions with titles, previews, and timestamps ([#2533](https://github.com/NousResearch/hermes-agent/pull/2533))
- **Session config surfacing** on `/new`, `/reset`, and auto-reset ([#3321](https://github.com/NousResearch/hermes-agent/pull/3321))
- **Third-party session isolation** — `--source` flag for isolating sessions by origin ([#3255](https://github.com/NousResearch/hermes-agent/pull/3255))
- Add `/resume` CLI handler, session log truncation guard, `reopen_session` API ([#3315](https://github.com/NousResearch/hermes-agent/pull/3315))
- Clear compressor summary and turn counter on `/clear` and `/new` ([#3102](https://github.com/NousResearch/hermes-agent/pull/3102))
- Surface silent SessionDB failures that cause session data loss ([#2999](https://github.com/NousResearch/hermes-agent/pull/2999))
- Session search fallback preview on summarization failure ([#3478](https://github.com/NousResearch/hermes-agent/pull/3478))
- Prevent stale memory overwrites by flush agent ([#2687](https://github.com/NousResearch/hermes-agent/pull/2687))
### Context Compression
- Replace dead `summary_target_tokens` with ratio-based scaling ([#2554](https://github.com/NousResearch/hermes-agent/pull/2554))
- Expose `compression.target_ratio`, `protect_last_n`, and `threshold` in `DEFAULT_CONFIG` ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Restore sane defaults and cap summary at 12K tokens ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Preserve transcript on `/compress` and hygiene compression ([#3556](https://github.com/NousResearch/hermes-agent/pull/3556))
- Update context pressure warnings and token estimates after compaction ([untagged commit](https://github.com/NousResearch/hermes-agent))
### Architecture & Dependencies
- **Remove mini-swe-agent dependency** — Inline Docker and Modal backends directly ([#2804](https://github.com/NousResearch/hermes-agent/pull/2804))
- **Replace swe-rex with native Modal SDK** for Modal backend ([#3538](https://github.com/NousResearch/hermes-agent/pull/3538))
- **Plugin lifecycle hooks** — `pre_llm_call`, `post_llm_call`, `on_session_start`, `on_session_end` now fire in the agent loop ([#3542](https://github.com/NousResearch/hermes-agent/pull/3542))
- Fix plugin toolsets invisible in `hermes tools` and standalone processes ([#3457](https://github.com/NousResearch/hermes-agent/pull/3457))
- Consolidate `get_hermes_home()` and `parse_reasoning_effort()` ([#3062](https://github.com/NousResearch/hermes-agent/pull/3062))
- Remove unused Hermes-native PKCE OAuth flow ([#3107](https://github.com/NousResearch/hermes-agent/pull/3107))
- Remove ~100 unused imports across 55 files ([#3016](https://github.com/NousResearch/hermes-agent/pull/3016))
- Fix 154 f-strings, simplify getattr/URL patterns, remove dead code ([#3119](https://github.com/NousResearch/hermes-agent/pull/3119))
---
## 📱 Messaging Platforms (Gateway)
### Telegram
- **Private Chat Topics** — Project-based conversations with functional skill binding per topic, enabling isolated workflows within a single Telegram chat ([#3163](https://github.com/NousResearch/hermes-agent/pull/3163))
- **Auto-discover fallback IPs via DNS-over-HTTPS** when `api.telegram.org` is unreachable ([#3376](https://github.com/NousResearch/hermes-agent/pull/3376))
- **Configurable reply threading mode** ([#2907](https://github.com/NousResearch/hermes-agent/pull/2907))
- Fall back to no `thread_id` on "Message thread not found" BadRequest ([#3390](https://github.com/NousResearch/hermes-agent/pull/3390))
- Self-reschedule reconnect when `start_polling` fails after 502 ([#3268](https://github.com/NousResearch/hermes-agent/pull/3268))
### Discord
- Stop phantom typing indicator after agent turn completes ([#3003](https://github.com/NousResearch/hermes-agent/pull/3003))
### Slack
- Send tool call progress messages to correct Slack thread ([#3063](https://github.com/NousResearch/hermes-agent/pull/3063))
- Scope progress thread fallback to Slack only ([#3488](https://github.com/NousResearch/hermes-agent/pull/3488))
### WhatsApp
- Download documents, audio, and video media from messages ([#2978](https://github.com/NousResearch/hermes-agent/pull/2978))
### Matrix
- Add missing Matrix entry in `PLATFORMS` dict ([#3473](https://github.com/NousResearch/hermes-agent/pull/3473))
- Harden e2ee access-token handling ([#3562](https://github.com/NousResearch/hermes-agent/pull/3562))
- Add backoff for `SyncError` in sync loop ([#3280](https://github.com/NousResearch/hermes-agent/pull/3280))
### Signal
- Track SSE keepalive comments as connection activity ([#3316](https://github.com/NousResearch/hermes-agent/pull/3316))
### Email
- Prevent unbounded growth of `_seen_uids` in EmailAdapter ([#3490](https://github.com/NousResearch/hermes-agent/pull/3490))
### Gateway Core
- **Config-gated `/verbose` command** for messaging platforms — toggle tool output verbosity from chat ([#3262](https://github.com/NousResearch/hermes-agent/pull/3262))
- **Background review notifications** delivered to user chat ([#3293](https://github.com/NousResearch/hermes-agent/pull/3293))
- **Retry transient send failures** and notify user on exhaustion ([#3288](https://github.com/NousResearch/hermes-agent/pull/3288))
- Recover from hung agents — `/stop` hard-kills session lock ([#3104](https://github.com/NousResearch/hermes-agent/pull/3104))
- Thread-safe `SessionStore` — protect `_entries` with `threading.Lock` ([#3052](https://github.com/NousResearch/hermes-agent/pull/3052))
- Fix gateway token double-counting with cached agents — use absolute set instead of increment ([#3306](https://github.com/NousResearch/hermes-agent/pull/3306), [#3317](https://github.com/NousResearch/hermes-agent/pull/3317))
- Fingerprint full auth token in agent cache signature ([#3247](https://github.com/NousResearch/hermes-agent/pull/3247))
- Silence background agent terminal output ([#3297](https://github.com/NousResearch/hermes-agent/pull/3297))
- Include per-platform `ALLOW_ALL` and `SIGNAL_GROUP` in startup allowlist check ([#3313](https://github.com/NousResearch/hermes-agent/pull/3313))
- Include user-local bin paths in systemd unit PATH ([#3527](https://github.com/NousResearch/hermes-agent/pull/3527))
- Track background task references in `GatewayRunner` ([#3254](https://github.com/NousResearch/hermes-agent/pull/3254))
- Add request timeouts to HA, Email, Mattermost, SMS adapters ([#3258](https://github.com/NousResearch/hermes-agent/pull/3258))
- Add media download retry to Mattermost, Slack, and base cache ([#3323](https://github.com/NousResearch/hermes-agent/pull/3323))
- Detect virtualenv path instead of hardcoding `venv/` ([#2797](https://github.com/NousResearch/hermes-agent/pull/2797))
- Use `TERMINAL_CWD` for context file discovery, not process cwd ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Stop loading hermes repo AGENTS.md into gateway sessions (~10k wasted tokens) ([#2891](https://github.com/NousResearch/hermes-agent/pull/2891))
---
## 🖥️ CLI & User Experience
### Interactive CLI
- **Configurable busy input mode** + fix `/queue` always working ([#3298](https://github.com/NousResearch/hermes-agent/pull/3298))
- **Preserve user input on multiline paste** ([#3065](https://github.com/NousResearch/hermes-agent/pull/3065))
- **Tool generation callback** — streaming "preparing terminal…" updates during tool argument generation ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Show tool progress for substantive tools, not just "preparing" ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Buffer reasoning preview chunks and fix duplicate display ([#3013](https://github.com/NousResearch/hermes-agent/pull/3013))
- Prevent reasoning box from rendering 3x during tool-calling loops ([#3405](https://github.com/NousResearch/hermes-agent/pull/3405))
- Eliminate "Event loop is closed" / "Press ENTER to continue" during idle — three-layer fix with `neuter_async_httpx_del()`, custom exception handler, and stale client cleanup ([#3398](https://github.com/NousResearch/hermes-agent/pull/3398))
- Fix status bar shows 26K instead of 260K for token counts with trailing zeros ([#3024](https://github.com/NousResearch/hermes-agent/pull/3024))
- Fix status bar duplicates and degrades during long sessions ([#3291](https://github.com/NousResearch/hermes-agent/pull/3291))
- Refresh TUI before background task output to prevent status bar overlap ([#3048](https://github.com/NousResearch/hermes-agent/pull/3048))
- Suppress KawaiiSpinner animation under `patch_stdout` ([#2994](https://github.com/NousResearch/hermes-agent/pull/2994))
- Skip KawaiiSpinner when TUI handles tool progress ([#2973](https://github.com/NousResearch/hermes-agent/pull/2973))
- Guard `isatty()` against closed streams via `_is_tty` property ([#3056](https://github.com/NousResearch/hermes-agent/pull/3056))
- Ensure single closure of streaming boxes during tool generation ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Cap context pressure percentage at 100% in display ([#3480](https://github.com/NousResearch/hermes-agent/pull/3480))
- Clean up HTML error messages in CLI display ([#3069](https://github.com/NousResearch/hermes-agent/pull/3069))
- Show HTTP status code and 400 body in API error output ([#3096](https://github.com/NousResearch/hermes-agent/pull/3096))
- Extract useful info from HTML error pages, dump debug on max retries ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Prevent TypeError on startup when `base_url` is None ([#3068](https://github.com/NousResearch/hermes-agent/pull/3068))
- Prevent update crash in non-TTY environments ([#3094](https://github.com/NousResearch/hermes-agent/pull/3094))
- Handle EOFError in sessions delete/prune confirmation prompts ([#3101](https://github.com/NousResearch/hermes-agent/pull/3101))
- Catch KeyboardInterrupt during `flush_memories` on exit and in exit cleanup handlers ([#3025](https://github.com/NousResearch/hermes-agent/pull/3025), [#3257](https://github.com/NousResearch/hermes-agent/pull/3257))
- Guard `.strip()` against None values from YAML config ([#3552](https://github.com/NousResearch/hermes-agent/pull/3552))
- Guard `config.get()` against YAML null values to prevent AttributeError ([#3377](https://github.com/NousResearch/hermes-agent/pull/3377))
- Store asyncio task references to prevent GC mid-execution ([#3267](https://github.com/NousResearch/hermes-agent/pull/3267))
### Setup & Configuration
- Use explicit key mapping for returning-user menu dispatch instead of positional index ([#3083](https://github.com/NousResearch/hermes-agent/pull/3083))
- Use `sys.executable` for pip in update commands to fix PEP 668 ([#3099](https://github.com/NousResearch/hermes-agent/pull/3099))
- Harden `hermes update` against diverged history, non-main branches, and gateway edge cases ([#3492](https://github.com/NousResearch/hermes-agent/pull/3492))
- OpenClaw migration overwrites defaults and setup wizard skips imported sections — fixed ([#3282](https://github.com/NousResearch/hermes-agent/pull/3282))
- Stop recursive AGENTS.md walk, load top-level only ([#3110](https://github.com/NousResearch/hermes-agent/pull/3110))
- Add macOS Homebrew paths to browser and terminal PATH resolution ([#2713](https://github.com/NousResearch/hermes-agent/pull/2713))
- YAML boolean handling for `tool_progress` config ([#3300](https://github.com/NousResearch/hermes-agent/pull/3300))
- Reset default SOUL.md to baseline identity text ([#3159](https://github.com/NousResearch/hermes-agent/pull/3159))
- Reject relative cwd paths for container terminal backends ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Add explicit `hermes-api-server` toolset for API server platform ([#3304](https://github.com/NousResearch/hermes-agent/pull/3304))
- Reorder setup wizard providers — OpenRouter first ([untagged commit](https://github.com/NousResearch/hermes-agent))
---
## 🔧 Tool System
### API Server
- **Idempotency-Key support**, body size limit, and OpenAI error envelope ([#2903](https://github.com/NousResearch/hermes-agent/pull/2903))
- Allow Idempotency-Key in CORS headers ([#3530](https://github.com/NousResearch/hermes-agent/pull/3530))
- Cancel orphaned agent + true interrupt on SSE disconnect ([#3427](https://github.com/NousResearch/hermes-agent/pull/3427))
- Fix streaming breaks when agent makes tool calls ([#2985](https://github.com/NousResearch/hermes-agent/pull/2985))
### Terminal & File Operations
- Handle addition-only hunks in V4A patch parser ([#3325](https://github.com/NousResearch/hermes-agent/pull/3325))
- Exponential backoff for persistent shell polling ([#2996](https://github.com/NousResearch/hermes-agent/pull/2996))
- Add timeout to subprocess calls in `context_references` ([#3469](https://github.com/NousResearch/hermes-agent/pull/3469))
### Browser & Vision
- Handle 402 insufficient credits error in vision tool ([#2802](https://github.com/NousResearch/hermes-agent/pull/2802))
- Fix `browser_vision` ignores `auxiliary.vision.timeout` config ([#2901](https://github.com/NousResearch/hermes-agent/pull/2901))
- Make browser command timeout configurable via config.yaml ([#2801](https://github.com/NousResearch/hermes-agent/pull/2801))
### MCP
- MCP toolset resolution for runtime and config ([#3252](https://github.com/NousResearch/hermes-agent/pull/3252))
- Add MCP tool name collision protection ([#3077](https://github.com/NousResearch/hermes-agent/pull/3077))
### Auxiliary LLM
- Guard aux LLM calls against None content + reasoning fallback + retry ([#3449](https://github.com/NousResearch/hermes-agent/pull/3449))
- Catch ImportError from `build_anthropic_client` in vision auto-detection ([#3312](https://github.com/NousResearch/hermes-agent/pull/3312))
### Other Tools
- Add request timeouts to `send_message_tool` HTTP calls ([#3162](https://github.com/NousResearch/hermes-agent/pull/3162)) by @memosr
- Auto-repair `jobs.json` with invalid control characters ([#3537](https://github.com/NousResearch/hermes-agent/pull/3537))
- Enable fine-grained tool streaming for Claude/OpenRouter ([#3497](https://github.com/NousResearch/hermes-agent/pull/3497))
---
## 🧩 Skills Ecosystem
### Skills System
- **Env var passthrough** for skills and user config — skills can declare environment variables to pass through ([#2807](https://github.com/NousResearch/hermes-agent/pull/2807))
- Cache skills prompt with shared `skill_utils` module for faster TTFT ([#3421](https://github.com/NousResearch/hermes-agent/pull/3421))
- Avoid redundant file re-read for skill conditions ([#2992](https://github.com/NousResearch/hermes-agent/pull/2992))
- Use Git Trees API to prevent silent subdirectory loss during install ([#2995](https://github.com/NousResearch/hermes-agent/pull/2995))
- Fix skills-sh install for deeply nested repo structures ([#2980](https://github.com/NousResearch/hermes-agent/pull/2980))
- Handle null metadata in skill frontmatter ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Preserve trust for skills-sh identifiers + reduce resolution churn ([#3251](https://github.com/NousResearch/hermes-agent/pull/3251))
- Agent-created skills were incorrectly treated as untrusted community content — fixed ([untagged commit](https://github.com/NousResearch/hermes-agent))
### New Skills
- **G0DM0D3 godmode jailbreaking skill** + docs ([#3157](https://github.com/NousResearch/hermes-agent/pull/3157))
- **Docker management skill** added to optional-skills ([#3060](https://github.com/NousResearch/hermes-agent/pull/3060))
- **OpenClaw migration v2** — 17 new modules, terminal recap for migrating from OpenClaw to Hermes ([#2906](https://github.com/NousResearch/hermes-agent/pull/2906))
---
## 🔒 Security & Reliability
### Security Hardening
- **SSRF protection** added to `browser_navigate` ([#3058](https://github.com/NousResearch/hermes-agent/pull/3058))
- **SSRF protection** added to `vision_tools` and `web_tools` (hardened) ([#2679](https://github.com/NousResearch/hermes-agent/pull/2679))
- **Restrict subagent toolsets** to parent's enabled set ([#3269](https://github.com/NousResearch/hermes-agent/pull/3269))
- **Prevent zip-slip path traversal** in self-update ([#3250](https://github.com/NousResearch/hermes-agent/pull/3250))
- **Prevent shell injection** in `_expand_path` via `~user` path suffix ([#2685](https://github.com/NousResearch/hermes-agent/pull/2685))
- **Normalize input** before dangerous command detection ([#3260](https://github.com/NousResearch/hermes-agent/pull/3260))
- Make tirith block verdicts approvable instead of hard-blocking ([#3428](https://github.com/NousResearch/hermes-agent/pull/3428))
- Remove compromised `litellm`/`typer`/`platformdirs` from deps ([#2796](https://github.com/NousResearch/hermes-agent/pull/2796))
- Pin all dependency version ranges ([#2810](https://github.com/NousResearch/hermes-agent/pull/2810))
- Regenerate `uv.lock` with hashes, use lockfile in setup ([#2812](https://github.com/NousResearch/hermes-agent/pull/2812))
- Bump dependencies to fix CVEs + regenerate `uv.lock` ([#3073](https://github.com/NousResearch/hermes-agent/pull/3073))
- Supply chain audit CI workflow for PR scanning ([#2816](https://github.com/NousResearch/hermes-agent/pull/2816))
### Reliability
- **SQLite WAL write-lock contention** causing 15-20s TUI freeze — fixed ([#3385](https://github.com/NousResearch/hermes-agent/pull/3385))
- **SQLite concurrency hardening** + session transcript integrity ([#3249](https://github.com/NousResearch/hermes-agent/pull/3249))
- Prevent recurring cron job re-fire on gateway crash/restart loop ([#3396](https://github.com/NousResearch/hermes-agent/pull/3396))
- Mark cron session as ended after job completes ([#2998](https://github.com/NousResearch/hermes-agent/pull/2998))
---
## ⚡ Performance
- **TTFT startup optimizations** — salvaged easy-win startup improvements ([#3395](https://github.com/NousResearch/hermes-agent/pull/3395))
- Cache skills prompt with shared `skill_utils` module ([#3421](https://github.com/NousResearch/hermes-agent/pull/3421))
- Avoid redundant file re-read for skill conditions in prompt builder ([#2992](https://github.com/NousResearch/hermes-agent/pull/2992))
---
## 🐛 Notable Bug Fixes
- Fix gateway token double-counting with cached agents ([#3306](https://github.com/NousResearch/hermes-agent/pull/3306), [#3317](https://github.com/NousResearch/hermes-agent/pull/3317))
- Fix "Event loop is closed" / "Press ENTER to continue" during idle sessions ([#3398](https://github.com/NousResearch/hermes-agent/pull/3398))
- Fix reasoning box rendering 3x during tool-calling loops ([#3405](https://github.com/NousResearch/hermes-agent/pull/3405))
- Fix status bar shows 26K instead of 260K for token counts ([#3024](https://github.com/NousResearch/hermes-agent/pull/3024))
- Fix `/queue` always working regardless of config ([#3298](https://github.com/NousResearch/hermes-agent/pull/3298))
- Fix phantom Discord typing indicator after agent turn ([#3003](https://github.com/NousResearch/hermes-agent/pull/3003))
- Fix Slack progress messages appearing in wrong thread ([#3063](https://github.com/NousResearch/hermes-agent/pull/3063))
- Fix WhatsApp media downloads (documents, audio, video) ([#2978](https://github.com/NousResearch/hermes-agent/pull/2978))
- Fix Telegram "Message thread not found" killing progress messages ([#3390](https://github.com/NousResearch/hermes-agent/pull/3390))
- Fix OpenClaw migration overwriting defaults ([#3282](https://github.com/NousResearch/hermes-agent/pull/3282))
- Fix returning-user setup menu dispatching wrong section ([#3083](https://github.com/NousResearch/hermes-agent/pull/3083))
- Fix `hermes update` PEP 668 "externally-managed-environment" error ([#3099](https://github.com/NousResearch/hermes-agent/pull/3099))
- Fix subagents hitting `max_iterations` prematurely via shared budget ([#3004](https://github.com/NousResearch/hermes-agent/pull/3004))
- Fix YAML boolean handling for `tool_progress` config ([#3300](https://github.com/NousResearch/hermes-agent/pull/3300))
- Fix `config.get()` crashes on YAML null values ([#3377](https://github.com/NousResearch/hermes-agent/pull/3377))
- Fix `.strip()` crash on None values from YAML config ([#3552](https://github.com/NousResearch/hermes-agent/pull/3552))
- Fix hung agents on gateway — `/stop` now hard-kills session lock ([#3104](https://github.com/NousResearch/hermes-agent/pull/3104))
- Fix `_custom` provider silently remapped to `openrouter` ([#2792](https://github.com/NousResearch/hermes-agent/pull/2792))
- Fix Matrix missing from `PLATFORMS` dict ([#3473](https://github.com/NousResearch/hermes-agent/pull/3473))
- Fix Email adapter unbounded `_seen_uids` growth ([#3490](https://github.com/NousResearch/hermes-agent/pull/3490))
---
## 🧪 Testing
- Pin `agent-client-protocol` < 0.9 to handle breaking upstream release ([#3320](https://github.com/NousResearch/hermes-agent/pull/3320))
- Catch anthropic ImportError in vision auto-detection tests ([#3312](https://github.com/NousResearch/hermes-agent/pull/3312))
- Update retry-exhaust test for new graceful return behavior ([#3320](https://github.com/NousResearch/hermes-agent/pull/3320))
- Add regression tests for null metadata frontmatter ([untagged commit](https://github.com/NousResearch/hermes-agent))
---
## 📚 Documentation
- Update all docs for `/model` command overhaul and custom provider support ([#2800](https://github.com/NousResearch/hermes-agent/pull/2800))
- Fix stale and incorrect documentation across 18 files ([#2805](https://github.com/NousResearch/hermes-agent/pull/2805))
- Document 9 previously undocumented features ([#2814](https://github.com/NousResearch/hermes-agent/pull/2814))
- Add missing skills, CLI commands, and messaging env vars to docs ([#2809](https://github.com/NousResearch/hermes-agent/pull/2809))
- Fix api-server response storage documentation — SQLite, not in-memory ([#2819](https://github.com/NousResearch/hermes-agent/pull/2819))
- Quote pip install extras to fix zsh glob errors ([#2815](https://github.com/NousResearch/hermes-agent/pull/2815))
- Unify hooks documentation — add plugin hooks to hooks page, add `session:end` event ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Clarify two-mode behavior in `session_search` schema description ([untagged commit](https://github.com/NousResearch/hermes-agent))
- Fix Discord Public Bot setting for Discord-provided invite link ([#3519](https://github.com/NousResearch/hermes-agent/pull/3519)) by @mehmoodosman
- Revise v0.4.0 changelog — fix feature attribution, reorder sections ([untagged commit](https://github.com/NousResearch/hermes-agent))
---
## 👥 Contributors
### Core
- **@teknium1** — 157 PRs covering the full scope of this release
### Community Contributors
- **@alt-glitch** (Siddharth Balyan) — 2 PRs: Nix flake with uv2nix build, NixOS module, and persistent container mode ([#20](https://github.com/NousResearch/hermes-agent/pull/20)); auto-generated config keys and suffix PATHs for Nix builds ([#3061](https://github.com/NousResearch/hermes-agent/pull/3061), [#3274](https://github.com/NousResearch/hermes-agent/pull/3274))
- **@ctlst** — 1 PR: Prevent AsyncOpenAI/httpx cross-loop deadlock in gateway mode ([#2701](https://github.com/NousResearch/hermes-agent/pull/2701))
- **@memosr** (memosr.eth) — 1 PR: Add request timeouts to `send_message_tool` HTTP calls ([#3162](https://github.com/NousResearch/hermes-agent/pull/3162))
- **@mehmoodosman** (Osman Mehmood) — 1 PR: Fix Discord docs for Public Bot setting ([#3519](https://github.com/NousResearch/hermes-agent/pull/3519))
### All Contributors
@alt-glitch, @ctlst, @mehmoodosman, @memosr, @teknium1
---
**Full Changelog**: [v2026.3.23...v2026.3.28](https://github.com/NousResearch/hermes-agent/compare/v2026.3.23...v2026.3.28)

View File

@@ -1,249 +0,0 @@
# Hermes Agent v0.6.0 (v2026.3.30)
**Release Date:** March 30, 2026
> The multi-instance release — Profiles for running isolated agent instances, MCP server mode, Docker container, fallback provider chains, two new messaging platforms (Feishu/Lark and WeCom), Telegram webhook mode, Slack multi-workspace OAuth, 95 PRs and 16 resolved issues in 2 days.
---
## ✨ Highlights
- **Profiles — Multi-Instance Hermes** — Run multiple isolated Hermes instances from the same installation. Each profile gets its own config, memory, sessions, skills, and gateway service. Create with `hermes profile create`, switch with `hermes -p <name>`, export/import for sharing. Full token-lock isolation prevents two profiles from using the same bot credential. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
- **MCP Server Mode** — Expose Hermes conversations and sessions to any MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.) via `hermes mcp serve`. Browse conversations, read messages, search across sessions, and manage attachments — all through the Model Context Protocol. Supports both stdio and Streamable HTTP transports. ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
- **Docker Container** — Official Dockerfile for running Hermes Agent in a container. Supports both CLI and gateway modes with volume-mounted config. ([#3668](https://github.com/NousResearch/hermes-agent/pull/3668), closes [#850](https://github.com/NousResearch/hermes-agent/issues/850))
- **Ordered Fallback Provider Chain** — Configure multiple inference providers with automatic failover. When your primary provider returns errors or is unreachable, Hermes automatically tries the next provider in the chain. Configure via `fallback_providers` in config.yaml. ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813), closes [#1734](https://github.com/NousResearch/hermes-agent/issues/1734))
- **Feishu/Lark Platform Support** — Full gateway adapter for Feishu (飞书) and Lark with event subscriptions, message cards, group chat, image/file attachments, and interactive card callbacks. ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817), closes [#1788](https://github.com/NousResearch/hermes-agent/issues/1788))
- **WeCom (Enterprise WeChat) Platform Support** — New gateway adapter for WeCom (企业微信) with text/image/voice messages, group chats, and callback verification. ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
- **Slack Multi-Workspace OAuth** — Connect a single Hermes gateway to multiple Slack workspaces via OAuth token file. Each workspace gets its own bot token, resolved dynamically per incoming event. ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
- **Telegram Webhook Mode & Group Controls** — Run the Telegram adapter in webhook mode as an alternative to polling — faster response times and better for production deployments behind a reverse proxy. New group mention gating controls when the bot responds: always, only when @mentioned, or via regex triggers. ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880), [#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
- **Exa Search Backend** — Add Exa as an alternative web search and content extraction backend alongside Firecrawl and DuckDuckGo. Set `EXA_API_KEY` and configure as preferred backend. ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
- **Skills & Credentials on Remote Backends** — Mount skill directories and credential files into Modal and Docker containers, so remote terminal sessions have access to the same skills and secrets as local execution. ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890), [#3671](https://github.com/NousResearch/hermes-agent/pull/3671), closes [#3665](https://github.com/NousResearch/hermes-agent/issues/3665), [#3433](https://github.com/NousResearch/hermes-agent/issues/3433))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- **Ordered fallback provider chain** — automatic failover across multiple configured providers ([#3813](https://github.com/NousResearch/hermes-agent/pull/3813))
- **Fix api_mode on provider switch** — switching providers via `hermes model` now correctly clears stale `api_mode` instead of hardcoding `chat_completions`, fixing 404s for providers with Anthropic-compatible endpoints ([#3726](https://github.com/NousResearch/hermes-agent/pull/3726), [#3857](https://github.com/NousResearch/hermes-agent/pull/3857), closes [#3685](https://github.com/NousResearch/hermes-agent/issues/3685))
- **Stop silent OpenRouter fallback** — when no provider is configured, Hermes now raises a clear error instead of silently routing to OpenRouter ([#3807](https://github.com/NousResearch/hermes-agent/pull/3807), [#3862](https://github.com/NousResearch/hermes-agent/pull/3862))
- **Gemini 3.1 preview models** — added to OpenRouter and Nous Portal catalogs ([#3803](https://github.com/NousResearch/hermes-agent/pull/3803), closes [#3753](https://github.com/NousResearch/hermes-agent/issues/3753))
- **Gemini direct API context length** — full context length resolution for direct Google AI endpoints ([#3876](https://github.com/NousResearch/hermes-agent/pull/3876))
- **gpt-5.4-mini** added to Codex fallback catalog ([#3855](https://github.com/NousResearch/hermes-agent/pull/3855))
- **Curated model lists preferred** over live API probe when the probe returns fewer models ([#3856](https://github.com/NousResearch/hermes-agent/pull/3856), [#3867](https://github.com/NousResearch/hermes-agent/pull/3867))
- **User-friendly 429 rate limit messages** with Retry-After countdown ([#3809](https://github.com/NousResearch/hermes-agent/pull/3809))
- **Auxiliary client placeholder key** for local servers without auth requirements ([#3842](https://github.com/NousResearch/hermes-agent/pull/3842))
- **INFO-level logging** for auxiliary provider resolution ([#3866](https://github.com/NousResearch/hermes-agent/pull/3866))
### Agent Loop & Conversation
- **Subagent status reporting** — reports `completed` status when summary exists instead of generic failure ([#3829](https://github.com/NousResearch/hermes-agent/pull/3829))
- **Session log file updated during compression** — prevents stale file references after context compression ([#3835](https://github.com/NousResearch/hermes-agent/pull/3835))
- **Omit empty tools param** — sends no `tools` parameter when empty instead of `None`, fixing compatibility with strict providers ([#3820](https://github.com/NousResearch/hermes-agent/pull/3820))
### Profiles & Multi-Instance
- **Profiles system** — `hermes profile create/list/switch/delete/export/import/rename`. Each profile gets isolated HERMES_HOME, gateway service, CLI wrapper. Token locks prevent credential collisions. Tab completion for profile names. ([#3681](https://github.com/NousResearch/hermes-agent/pull/3681))
- **Profile-aware display paths** — all user-facing `~/.hermes` paths replaced with `display_hermes_home()` to show the correct profile directory ([#3623](https://github.com/NousResearch/hermes-agent/pull/3623))
- **Lazy display_hermes_home imports** — prevents `ImportError` during `hermes update` when modules cache stale bytecode ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
- **HERMES_HOME for protected paths** — `.env` write-deny path now respects HERMES_HOME instead of hardcoded `~/.hermes` ([#3840](https://github.com/NousResearch/hermes-agent/pull/3840))
---
## 📱 Messaging Platforms (Gateway)
### New Platforms
- **Feishu/Lark** — Full adapter with event subscriptions, message cards, group chat, image/file attachments, interactive card callbacks ([#3799](https://github.com/NousResearch/hermes-agent/pull/3799), [#3817](https://github.com/NousResearch/hermes-agent/pull/3817))
- **WeCom (Enterprise WeChat)** — Text/image/voice messages, group chats, callback verification ([#3847](https://github.com/NousResearch/hermes-agent/pull/3847))
### Telegram
- **Webhook mode** — run as webhook endpoint instead of polling for production deployments ([#3880](https://github.com/NousResearch/hermes-agent/pull/3880))
- **Group mention gating & regex triggers** — configurable bot response behavior in groups: always, @mention-only, or regex-matched ([#3870](https://github.com/NousResearch/hermes-agent/pull/3870))
- **Gracefully handle deleted reply targets** — no more crashes when the message being replied to was deleted ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858), closes [#3229](https://github.com/NousResearch/hermes-agent/issues/3229))
### Discord
- **Message processing reactions** — adds a reaction emoji while processing and removes it when done, giving visual feedback in channels ([#3871](https://github.com/NousResearch/hermes-agent/pull/3871))
- **DISCORD_IGNORE_NO_MENTION** — skip messages that @mention other users/bots but not Hermes ([#3640](https://github.com/NousResearch/hermes-agent/pull/3640))
- **Clean up deferred "thinking..."** — properly removes the "thinking..." indicator after slash commands complete ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674), closes [#3595](https://github.com/NousResearch/hermes-agent/issues/3595))
### Slack
- **Multi-workspace OAuth** — connect to multiple Slack workspaces from a single gateway via OAuth token file ([#3903](https://github.com/NousResearch/hermes-agent/pull/3903))
### WhatsApp
- **Persistent aiohttp session** — reuse HTTP sessions across requests instead of creating new ones per message ([#3818](https://github.com/NousResearch/hermes-agent/pull/3818))
- **LID↔phone alias resolution** — correctly match Linked ID and phone number formats in allowlists ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
- **Skip reply prefix in bot mode** — cleaner message formatting when running as a WhatsApp bot ([#3931](https://github.com/NousResearch/hermes-agent/pull/3931))
### Matrix
- **Native voice messages via MSC3245** — send voice messages as proper Matrix voice events instead of file attachments ([#3877](https://github.com/NousResearch/hermes-agent/pull/3877))
### Mattermost
- **Configurable mention behavior** — respond to messages without requiring @mention ([#3664](https://github.com/NousResearch/hermes-agent/pull/3664))
### Signal
- **URL-encode phone numbers** and correct attachment RPC parameter — fixes delivery failures with certain phone number formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)) — @kshitijk4poor
### Email
- **Close SMTP/IMAP connections on failure** — prevents connection leaks during error scenarios ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
### Gateway Core
- **Atomic config writes** — use atomic file writes for config.yaml to prevent data loss during crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
- **Home channel env overrides** — apply environment variable overrides for home channels consistently ([#3796](https://github.com/NousResearch/hermes-agent/pull/3796), [#3808](https://github.com/NousResearch/hermes-agent/pull/3808))
- **Replace print() with logger** — BasePlatformAdapter now uses proper logging instead of print statements ([#3669](https://github.com/NousResearch/hermes-agent/pull/3669))
- **Cron delivery labels** — resolve human-friendly delivery labels via channel directory ([#3860](https://github.com/NousResearch/hermes-agent/pull/3860), closes [#1945](https://github.com/NousResearch/hermes-agent/issues/1945))
- **Cron [SILENT] tightening** — prevent agents from prefixing reports with [SILENT] to suppress delivery ([#3901](https://github.com/NousResearch/hermes-agent/pull/3901))
- **Background task media delivery** and vision download timeout fixes ([#3919](https://github.com/NousResearch/hermes-agent/pull/3919))
- **Boot-md hook** — example built-in hook to run a BOOT.md file on gateway startup ([#3733](https://github.com/NousResearch/hermes-agent/pull/3733))
---
## 🖥️ CLI & User Experience
### Interactive CLI
- **Configurable tool preview length** — show full file paths by default instead of truncating at 40 chars ([#3841](https://github.com/NousResearch/hermes-agent/pull/3841))
- **Tool token context display** — `hermes tools` checklist now shows estimated token cost per toolset ([#3805](https://github.com/NousResearch/hermes-agent/pull/3805))
- **/bg spinner TUI fix** — route background task spinner through the TUI widget to prevent status bar collision ([#3643](https://github.com/NousResearch/hermes-agent/pull/3643))
- **Prevent status bar wrapping** into duplicate rows ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883)) — @kshitijk4poor
- **Handle closed stdout ValueError** in safe print paths — fixes crashes when stdout is closed during gateway thread shutdown ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843), closes [#3534](https://github.com/NousResearch/hermes-agent/issues/3534))
- **Remove input() from /tools disable** — eliminates freeze in terminal when disabling tools ([#3918](https://github.com/NousResearch/hermes-agent/pull/3918))
- **TTY guard for interactive CLI commands** — prevent CPU spin when launched without a terminal ([#3933](https://github.com/NousResearch/hermes-agent/pull/3933))
- **Argparse entrypoint** — use argparse in the top-level launcher for cleaner error handling ([#3874](https://github.com/NousResearch/hermes-agent/pull/3874))
- **Lazy-initialized tools show yellow** in banner instead of red, reducing false alarm about "missing" tools ([#3822](https://github.com/NousResearch/hermes-agent/pull/3822))
- **Honcho tools shown in banner** when configured ([#3810](https://github.com/NousResearch/hermes-agent/pull/3810))
### Setup & Configuration
- **Auto-install matrix-nio** during `hermes setup` when Matrix is selected ([#3802](https://github.com/NousResearch/hermes-agent/pull/3802), [#3873](https://github.com/NousResearch/hermes-agent/pull/3873))
- **Session export stdout support** — export sessions to stdout with `-` for piping ([#3641](https://github.com/NousResearch/hermes-agent/pull/3641), closes [#3609](https://github.com/NousResearch/hermes-agent/issues/3609))
- **Configurable approval timeouts** — set how long dangerous command approval prompts wait before auto-denying ([#3886](https://github.com/NousResearch/hermes-agent/pull/3886), closes [#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
- **Clear __pycache__ during update** — prevents stale bytecode ImportError after `hermes update` ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
---
## 🔧 Tool System
### MCP
- **MCP Server Mode** — `hermes mcp serve` exposes conversations, sessions, and attachments to MCP clients via stdio or Streamable HTTP ([#3795](https://github.com/NousResearch/hermes-agent/pull/3795))
- **Dynamic tool discovery** — respond to `notifications/tools/list_changed` events to pick up new tools from MCP servers without reconnecting ([#3812](https://github.com/NousResearch/hermes-agent/pull/3812))
- **Non-deprecated HTTP transport** — switched from `sse_client` to `streamable_http_client` ([#3646](https://github.com/NousResearch/hermes-agent/pull/3646))
### Web Tools
- **Exa search backend** — alternative to Firecrawl and DuckDuckGo for web search and extraction ([#3648](https://github.com/NousResearch/hermes-agent/pull/3648))
### Browser
- **Guard against None LLM responses** in browser snapshot and vision tools ([#3642](https://github.com/NousResearch/hermes-agent/pull/3642))
### Terminal & Remote Backends
- **Mount skill directories** into Modal and Docker containers ([#3890](https://github.com/NousResearch/hermes-agent/pull/3890))
- **Mount credential files** into remote backends with mtime+size caching ([#3671](https://github.com/NousResearch/hermes-agent/pull/3671))
- **Preserve partial output** when commands time out instead of losing everything ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
- **Stop marking persisted env vars as missing** on remote backends ([#3650](https://github.com/NousResearch/hermes-agent/pull/3650))
### Audio
- **.aac format support** in transcription tool ([#3865](https://github.com/NousResearch/hermes-agent/pull/3865), closes [#1963](https://github.com/NousResearch/hermes-agent/issues/1963))
- **Audio download retry** — retry logic for `cache_audio_from_url` matching the existing image download pattern ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401)) — @binhnt92
### Vision
- **Reject non-image files** and enforce website-only policy for vision analysis ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
### Tool Schema
- **Ensure name field** always present in tool definitions, fixing `KeyError: 'name'` crashes ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811), closes [#3729](https://github.com/NousResearch/hermes-agent/issues/3729))
### ACP (Editor Integration)
- **Complete session management surface** for VS Code/Zed/JetBrains clients — proper task lifecycle, cancel support, session persistence ([#3675](https://github.com/NousResearch/hermes-agent/pull/3675))
---
## 🧩 Skills & Plugins
### Skills System
- **External skill directories** — configure additional skill directories via `skills.external_dirs` in config.yaml ([#3678](https://github.com/NousResearch/hermes-agent/pull/3678))
- **Category path traversal blocked** — prevents `../` attacks in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
- **parallel-cli moved to optional-skills** — reduces default skill footprint ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)) — @kshitijk4poor
### New Skills
- **memento-flashcards** — spaced repetition flashcard system ([#3827](https://github.com/NousResearch/hermes-agent/pull/3827))
- **songwriting-and-ai-music** — songwriting craft and AI music generation prompts ([#3834](https://github.com/NousResearch/hermes-agent/pull/3834))
- **SiYuan Note** — integration with SiYuan note-taking app ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
- **Scrapling** — web scraping skill using Scrapling library ([#3742](https://github.com/NousResearch/hermes-agent/pull/3742))
- **one-three-one-rule** — communication framework skill ([#3797](https://github.com/NousResearch/hermes-agent/pull/3797))
### Plugin System
- **Plugin enable/disable commands** — `hermes plugins enable/disable <name>` for managing plugin state without removing them ([#3747](https://github.com/NousResearch/hermes-agent/pull/3747))
- **Plugin message injection** — plugins can now inject messages into the conversation stream on behalf of the user via `ctx.inject_message()` ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778)) — @winglian
- **Honcho self-hosted support** — allow local Honcho instances without requiring an API key ([#3644](https://github.com/NousResearch/hermes-agent/pull/3644))
---
## 🔒 Security & Reliability
### Security Hardening
- **Hardened dangerous command detection** — expanded pattern matching for risky shell commands and added file tool path guards for sensitive locations (`/etc/`, `/boot/`, docker.sock) ([#3872](https://github.com/NousResearch/hermes-agent/pull/3872))
- **Sensitive path write checks** in approval system — catch writes to system config files through file tools, not just terminal ([#3859](https://github.com/NousResearch/hermes-agent/pull/3859))
- **Secret redaction expansion** — now covers ElevenLabs, Tavily, and Exa API keys ([#3920](https://github.com/NousResearch/hermes-agent/pull/3920))
- **Vision file rejection** — reject non-image files passed to vision analysis to prevent information disclosure ([#3845](https://github.com/NousResearch/hermes-agent/pull/3845))
- **Category path traversal blocking** — prevent directory traversal in skill category names ([#3844](https://github.com/NousResearch/hermes-agent/pull/3844))
### Reliability
- **Atomic config.yaml writes** — prevent data loss during gateway crashes ([#3800](https://github.com/NousResearch/hermes-agent/pull/3800))
- **Clear __pycache__ on update** — prevent stale bytecode from causing ImportError after updates ([#3819](https://github.com/NousResearch/hermes-agent/pull/3819))
- **Lazy imports for update safety** — prevent ImportError chains during `hermes update` when modules reference new functions ([#3776](https://github.com/NousResearch/hermes-agent/pull/3776))
- **Restore terminalbench2 from patch corruption** — recovered file damaged by patch tool's secret redaction ([#3801](https://github.com/NousResearch/hermes-agent/pull/3801))
- **Terminal timeout preserves partial output** — no more lost command output on timeout ([#3868](https://github.com/NousResearch/hermes-agent/pull/3868))
---
## 🐛 Notable Bug Fixes
- **OpenClaw migration model config overwrite** — migration no longer overwrites model config dict with a string ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924)) — @0xbyt4
- **OpenClaw migration expanded** — covers full data footprint including sessions, cron, memory ([#3869](https://github.com/NousResearch/hermes-agent/pull/3869))
- **Telegram deleted reply targets** — gracefully handle replies to deleted messages instead of crashing ([#3858](https://github.com/NousResearch/hermes-agent/pull/3858))
- **Discord "thinking..." persistence** — properly cleans up deferred response indicators ([#3674](https://github.com/NousResearch/hermes-agent/pull/3674))
- **WhatsApp LID↔phone aliases** — fixes allowlist matching failures with Linked ID format ([#3830](https://github.com/NousResearch/hermes-agent/pull/3830))
- **Signal URL-encoded phone numbers** — fixes delivery failures with certain formats ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670))
- **Email connection leaks** — properly close SMTP/IMAP connections on error ([#3804](https://github.com/NousResearch/hermes-agent/pull/3804))
- **_safe_print ValueError** — no more gateway thread crashes on closed stdout ([#3843](https://github.com/NousResearch/hermes-agent/pull/3843))
- **Tool schema KeyError 'name'** — ensure name field always present in tool definitions ([#3811](https://github.com/NousResearch/hermes-agent/pull/3811))
- **api_mode stale on provider switch** — correctly clear when switching providers via `hermes model` ([#3857](https://github.com/NousResearch/hermes-agent/pull/3857))
---
## 🧪 Testing
- Resolved 10+ CI failures across hooks, tiktoken, plugins, and skill tests ([#3848](https://github.com/NousResearch/hermes-agent/pull/3848), [#3721](https://github.com/NousResearch/hermes-agent/pull/3721), [#3936](https://github.com/NousResearch/hermes-agent/pull/3936))
---
## 📚 Documentation
- **Comprehensive OpenClaw migration guide** — step-by-step guide for migrating from OpenClaw/Claw3D to Hermes Agent ([#3864](https://github.com/NousResearch/hermes-agent/pull/3864), [#3900](https://github.com/NousResearch/hermes-agent/pull/3900))
- **Credential file passthrough docs** — document how to forward credential files and env vars to remote backends ([#3677](https://github.com/NousResearch/hermes-agent/pull/3677))
- **DuckDuckGo requirements clarified** — note runtime dependency on duckduckgo-search package ([#3680](https://github.com/NousResearch/hermes-agent/pull/3680))
- **Skills catalog updated** — added red-teaming category and optional skills listing ([#3745](https://github.com/NousResearch/hermes-agent/pull/3745))
- **Feishu docs MDX fix** — escape angle-bracket URLs that break Docusaurus build ([#3902](https://github.com/NousResearch/hermes-agent/pull/3902))
---
## 👥 Contributors
### Core
- **@teknium1** — 90 PRs across all subsystems
### Community Contributors
- **@kshitijk4poor** — 3 PRs: Signal phone number fix ([#3670](https://github.com/NousResearch/hermes-agent/pull/3670)), parallel-cli to optional-skills ([#3673](https://github.com/NousResearch/hermes-agent/pull/3673)), status bar wrapping fix ([#3883](https://github.com/NousResearch/hermes-agent/pull/3883))
- **@winglian** — 1 PR: Plugin message injection interface ([#3778](https://github.com/NousResearch/hermes-agent/pull/3778))
- **@binhnt92** — 1 PR: Audio download retry logic ([#3401](https://github.com/NousResearch/hermes-agent/pull/3401))
- **@0xbyt4** — 1 PR: OpenClaw migration model config fix ([#3924](https://github.com/NousResearch/hermes-agent/pull/3924))
### Issues Resolved from Community
@Material-Scientist ([#850](https://github.com/NousResearch/hermes-agent/issues/850)), @hanxu98121 ([#1734](https://github.com/NousResearch/hermes-agent/issues/1734)), @penwyp ([#1788](https://github.com/NousResearch/hermes-agent/issues/1788)), @dan-and ([#1945](https://github.com/NousResearch/hermes-agent/issues/1945)), @AdrianScott ([#1963](https://github.com/NousResearch/hermes-agent/issues/1963)), @clawdbot47 ([#3229](https://github.com/NousResearch/hermes-agent/issues/3229)), @alanfwilliams ([#3404](https://github.com/NousResearch/hermes-agent/issues/3404)), @kentimsit ([#3433](https://github.com/NousResearch/hermes-agent/issues/3433)), @hayka-pacha ([#3534](https://github.com/NousResearch/hermes-agent/issues/3534)), @primmer ([#3595](https://github.com/NousResearch/hermes-agent/issues/3595)), @dagelf ([#3609](https://github.com/NousResearch/hermes-agent/issues/3609)), @HenkDz ([#3685](https://github.com/NousResearch/hermes-agent/issues/3685)), @tmdgusya ([#3729](https://github.com/NousResearch/hermes-agent/issues/3729)), @TypQxQ ([#3753](https://github.com/NousResearch/hermes-agent/issues/3753)), @acsezen ([#3765](https://github.com/NousResearch/hermes-agent/issues/3765))
---
**Full Changelog**: [v2026.3.28...v2026.3.30](https://github.com/NousResearch/hermes-agent/compare/v2026.3.28...v2026.3.30)

View File

@@ -1,290 +0,0 @@
# Hermes Agent v0.7.0 (v2026.4.3)
**Release Date:** April 3, 2026
> The resilience release — pluggable memory providers, credential pool rotation, Camofox anti-detection browser, inline diff previews, gateway hardening across race conditions and approval routing, and deep security fixes across 168 PRs and 46 resolved issues.
---
## ✨ Highlights
- **Pluggable Memory Provider Interface** — Memory is now an extensible plugin system. Third-party memory backends (Honcho, vector stores, custom DBs) implement a simple provider ABC and register via the plugin system. Built-in memory is the default provider. Honcho integration restored to full parity as the reference plugin with profile-scoped host/peer resolution. ([#4623](https://github.com/NousResearch/hermes-agent/pull/4623), [#4616](https://github.com/NousResearch/hermes-agent/pull/4616), [#4355](https://github.com/NousResearch/hermes-agent/pull/4355))
- **Same-Provider Credential Pools** — Configure multiple API keys for the same provider with automatic rotation. Thread-safe `least_used` strategy distributes load across keys, and 401 failures trigger automatic rotation to the next credential. Set up via the setup wizard or `credential_pool` config. ([#4188](https://github.com/NousResearch/hermes-agent/pull/4188), [#4300](https://github.com/NousResearch/hermes-agent/pull/4300), [#4361](https://github.com/NousResearch/hermes-agent/pull/4361))
- **Camofox Anti-Detection Browser Backend** — New local browser backend using Camoufox for stealth browsing. Persistent sessions with VNC URL discovery for visual debugging, configurable SSRF bypass for local backends, auto-install via `hermes tools`. ([#4008](https://github.com/NousResearch/hermes-agent/pull/4008), [#4419](https://github.com/NousResearch/hermes-agent/pull/4419), [#4292](https://github.com/NousResearch/hermes-agent/pull/4292))
- **Inline Diff Previews** — File write and patch operations now show inline diffs in the tool activity feed, giving you visual confirmation of what changed before the agent moves on. ([#4411](https://github.com/NousResearch/hermes-agent/pull/4411), [#4423](https://github.com/NousResearch/hermes-agent/pull/4423))
- **API Server Session Continuity & Tool Streaming** — The API server (Open WebUI integration) now streams tool progress events in real-time and supports `X-Hermes-Session-Id` headers for persistent sessions across requests. Sessions persist to the shared SessionDB. ([#4092](https://github.com/NousResearch/hermes-agent/pull/4092), [#4478](https://github.com/NousResearch/hermes-agent/pull/4478), [#4802](https://github.com/NousResearch/hermes-agent/pull/4802))
- **ACP: Client-Provided MCP Servers** — Editor integrations (VS Code, Zed, JetBrains) can now register their own MCP servers, which Hermes picks up as additional agent tools. Your editor's MCP ecosystem flows directly into the agent. ([#4705](https://github.com/NousResearch/hermes-agent/pull/4705))
- **Gateway Hardening** — Major stability pass across race conditions, photo media delivery, flood control, stuck sessions, approval routing, and compression death spirals. The gateway is substantially more reliable in production. ([#4727](https://github.com/NousResearch/hermes-agent/pull/4727), [#4750](https://github.com/NousResearch/hermes-agent/pull/4750), [#4798](https://github.com/NousResearch/hermes-agent/pull/4798), [#4557](https://github.com/NousResearch/hermes-agent/pull/4557))
- **Security: Secret Exfiltration Blocking** — Browser URLs and LLM responses are now scanned for secret patterns, blocking exfiltration attempts via URL encoding, base64, or prompt injection. Credential directory protections expanded to `.docker`, `.azure`, `.config/gh`. Execute_code sandbox output is redacted. ([#4483](https://github.com/NousResearch/hermes-agent/pull/4483), [#4360](https://github.com/NousResearch/hermes-agent/pull/4360), [#4305](https://github.com/NousResearch/hermes-agent/pull/4305), [#4327](https://github.com/NousResearch/hermes-agent/pull/4327))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- **Same-provider credential pools** — configure multiple API keys with automatic `least_used` rotation and 401 failover ([#4188](https://github.com/NousResearch/hermes-agent/pull/4188), [#4300](https://github.com/NousResearch/hermes-agent/pull/4300))
- **Credential pool preserved through smart routing** — pool state survives fallback provider switches and defers eager fallback on 429 ([#4361](https://github.com/NousResearch/hermes-agent/pull/4361))
- **Per-turn primary runtime restoration** — after fallback provider use, the agent automatically restores the primary provider on the next turn with transport recovery ([#4624](https://github.com/NousResearch/hermes-agent/pull/4624))
- **`developer` role for GPT-5 and Codex models** — uses OpenAI's recommended system message role for newer models ([#4498](https://github.com/NousResearch/hermes-agent/pull/4498))
- **Google model operational guidance** — Gemini and Gemma models get provider-specific prompting guidance ([#4641](https://github.com/NousResearch/hermes-agent/pull/4641))
- **Anthropic long-context tier 429 handling** — automatically reduces context to 200k when hitting tier limits ([#4747](https://github.com/NousResearch/hermes-agent/pull/4747))
- **URL-based auth for third-party Anthropic endpoints** + CI test fixes ([#4148](https://github.com/NousResearch/hermes-agent/pull/4148))
- **Bearer auth for MiniMax Anthropic endpoints** ([#4028](https://github.com/NousResearch/hermes-agent/pull/4028))
- **Fireworks context length detection** ([#4158](https://github.com/NousResearch/hermes-agent/pull/4158))
- **Standard DashScope international endpoint** for Alibaba provider ([#4133](https://github.com/NousResearch/hermes-agent/pull/4133), closes [#3912](https://github.com/NousResearch/hermes-agent/issues/3912))
- **Custom providers context_length** honored in hygiene compression ([#4085](https://github.com/NousResearch/hermes-agent/pull/4085))
- **Non-sk-ant keys** treated as regular API keys, not OAuth tokens ([#4093](https://github.com/NousResearch/hermes-agent/pull/4093))
- **Claude-sonnet-4.6** added to OpenRouter and Nous model lists ([#4157](https://github.com/NousResearch/hermes-agent/pull/4157))
- **Qwen 3.6 Plus Preview** added to model lists ([#4376](https://github.com/NousResearch/hermes-agent/pull/4376))
- **MiniMax M2.7** added to hermes model picker and OpenCode ([#4208](https://github.com/NousResearch/hermes-agent/pull/4208))
- **Auto-detect models from server probe** in custom endpoint setup ([#4218](https://github.com/NousResearch/hermes-agent/pull/4218))
- **Config.yaml single source of truth** for endpoint URLs — no more env var vs config.yaml conflicts ([#4165](https://github.com/NousResearch/hermes-agent/pull/4165))
- **Setup wizard no longer overwrites** custom endpoint config ([#4180](https://github.com/NousResearch/hermes-agent/pull/4180), closes [#4172](https://github.com/NousResearch/hermes-agent/issues/4172))
- **Unified setup wizard provider selection** with `hermes model` — single code path for both flows ([#4200](https://github.com/NousResearch/hermes-agent/pull/4200))
- **Root-level provider config** no longer overrides `model.provider` ([#4329](https://github.com/NousResearch/hermes-agent/pull/4329))
- **Rate-limit pairing rejection messages** to prevent spam ([#4081](https://github.com/NousResearch/hermes-agent/pull/4081))
### Agent Loop & Conversation
- **Preserve Anthropic thinking block signatures** across tool-use turns ([#4626](https://github.com/NousResearch/hermes-agent/pull/4626))
- **Classify think-only empty responses** before retrying — prevents infinite retry loops on models that produce thinking blocks without content ([#4645](https://github.com/NousResearch/hermes-agent/pull/4645))
- **Prevent compression death spiral** from API disconnects — stops the loop where compression triggers, fails, compresses again ([#4750](https://github.com/NousResearch/hermes-agent/pull/4750), closes [#2153](https://github.com/NousResearch/hermes-agent/issues/2153))
- **Persist compressed context** to gateway session after mid-run compression ([#4095](https://github.com/NousResearch/hermes-agent/pull/4095))
- **Context-exceeded error messages** now include actionable guidance ([#4155](https://github.com/NousResearch/hermes-agent/pull/4155), closes [#4061](https://github.com/NousResearch/hermes-agent/issues/4061))
- **Strip orphaned think/reasoning tags** from user-facing responses ([#4311](https://github.com/NousResearch/hermes-agent/pull/4311), closes [#4285](https://github.com/NousResearch/hermes-agent/issues/4285))
- **Harden Codex responses preflight** and stream error handling ([#4313](https://github.com/NousResearch/hermes-agent/pull/4313))
- **Deterministic call_id fallbacks** instead of random UUIDs for prompt cache consistency ([#3991](https://github.com/NousResearch/hermes-agent/pull/3991))
- **Context pressure warning spam** prevented after compression ([#4012](https://github.com/NousResearch/hermes-agent/pull/4012))
- **AsyncOpenAI created lazily** in trajectory compressor to avoid closed event loop errors ([#4013](https://github.com/NousResearch/hermes-agent/pull/4013))
### Memory & Sessions
- **Pluggable memory provider interface** — ABC-based plugin system for custom memory backends with profile isolation ([#4623](https://github.com/NousResearch/hermes-agent/pull/4623))
- **Honcho full integration parity** restored as reference memory provider plugin ([#4355](https://github.com/NousResearch/hermes-agent/pull/4355)) — @erosika
- **Honcho profile-scoped** host and peer resolution ([#4616](https://github.com/NousResearch/hermes-agent/pull/4616))
- **Memory flush state persisted** to prevent redundant re-flushes on gateway restart ([#4481](https://github.com/NousResearch/hermes-agent/pull/4481))
- **Memory provider tools** routed through sequential execution path ([#4803](https://github.com/NousResearch/hermes-agent/pull/4803))
- **Honcho config** written to instance-local path for profile isolation ([#4037](https://github.com/NousResearch/hermes-agent/pull/4037))
- **API server sessions** persist to shared SessionDB ([#4802](https://github.com/NousResearch/hermes-agent/pull/4802))
- **Token usage persisted** for non-CLI sessions ([#4627](https://github.com/NousResearch/hermes-agent/pull/4627))
- **Quote dotted terms in FTS5 queries** — fixes session search for terms containing dots ([#4549](https://github.com/NousResearch/hermes-agent/pull/4549))
---
## 📱 Messaging Platforms (Gateway)
### Gateway Core
- **Race condition fixes** — photo media loss, flood control, stuck sessions, and STT config issues resolved in one hardening pass ([#4727](https://github.com/NousResearch/hermes-agent/pull/4727))
- **Approval routing through running-agent guard** — `/approve` and `/deny` now route correctly when the agent is blocked waiting for approval instead of being swallowed as interrupts ([#4798](https://github.com/NousResearch/hermes-agent/pull/4798), [#4557](https://github.com/NousResearch/hermes-agent/pull/4557), closes [#4542](https://github.com/NousResearch/hermes-agent/issues/4542))
- **Resume agent after /approve** — tool result is no longer lost when executing blocked commands ([#4418](https://github.com/NousResearch/hermes-agent/pull/4418))
- **DM thread sessions seeded** with parent transcript to preserve context ([#4559](https://github.com/NousResearch/hermes-agent/pull/4559))
- **Skill-aware slash commands** — gateway dynamically registers installed skills as slash commands with paginated `/commands` list and Telegram 100-command cap ([#3934](https://github.com/NousResearch/hermes-agent/pull/3934), [#4005](https://github.com/NousResearch/hermes-agent/pull/4005), [#4006](https://github.com/NousResearch/hermes-agent/pull/4006), [#4010](https://github.com/NousResearch/hermes-agent/pull/4010), [#4023](https://github.com/NousResearch/hermes-agent/pull/4023))
- **Per-platform disabled skills** respected in Telegram menu and gateway dispatch ([#4799](https://github.com/NousResearch/hermes-agent/pull/4799))
- **Remove user-facing compression warnings** — cleaner message flow ([#4139](https://github.com/NousResearch/hermes-agent/pull/4139))
- **`-v/-q` flags wired to stderr logging** for gateway service ([#4474](https://github.com/NousResearch/hermes-agent/pull/4474))
- **HERMES_HOME remapped** to target user in system service unit ([#4456](https://github.com/NousResearch/hermes-agent/pull/4456))
- **Honor default for invalid bool-like config values** ([#4029](https://github.com/NousResearch/hermes-agent/pull/4029))
- **setsid instead of systemd-run** for `/update` command to avoid systemd permission issues ([#4104](https://github.com/NousResearch/hermes-agent/pull/4104), closes [#4017](https://github.com/NousResearch/hermes-agent/issues/4017))
- **'Initializing agent...'** shown on first message for better UX ([#4086](https://github.com/NousResearch/hermes-agent/pull/4086))
- **Allow running gateway service as root** for LXC/container environments ([#4732](https://github.com/NousResearch/hermes-agent/pull/4732))
### Telegram
- **32-char limit on command names** with collision avoidance ([#4211](https://github.com/NousResearch/hermes-agent/pull/4211))
- **Priority order enforced** in menu — core > plugins > skills ([#4023](https://github.com/NousResearch/hermes-agent/pull/4023))
- **Capped at 50 commands** — API rejects above ~60 ([#4006](https://github.com/NousResearch/hermes-agent/pull/4006))
- **Skip empty/whitespace text** to prevent 400 errors ([#4388](https://github.com/NousResearch/hermes-agent/pull/4388))
- **E2E gateway tests** added ([#4497](https://github.com/NousResearch/hermes-agent/pull/4497)) — @pefontana
### Discord
- **Button-based approval UI** — register `/approve` and `/deny` slash commands with interactive button prompts ([#4800](https://github.com/NousResearch/hermes-agent/pull/4800))
- **Configurable reactions** — `discord.reactions` config option to disable message processing reactions ([#4199](https://github.com/NousResearch/hermes-agent/pull/4199))
- **Skip reactions and auto-threading** for unauthorized users ([#4387](https://github.com/NousResearch/hermes-agent/pull/4387))
### Slack
- **Reply in thread** — `slack.reply_in_thread` config option for threaded responses ([#4643](https://github.com/NousResearch/hermes-agent/pull/4643), closes [#2662](https://github.com/NousResearch/hermes-agent/issues/2662))
### WhatsApp
- **Enforce require_mention in group chats** ([#4730](https://github.com/NousResearch/hermes-agent/pull/4730))
### Webhook
- **Platform support fixes** — skip home channel prompt, disable tool progress for webhook adapters ([#4660](https://github.com/NousResearch/hermes-agent/pull/4660))
### Matrix
- **E2EE decryption hardening** — request missing keys, auto-trust devices, retry buffered events ([#4083](https://github.com/NousResearch/hermes-agent/pull/4083))
---
## 🖥️ CLI & User Experience
### New Slash Commands
- **`/yolo`** — toggle dangerous command approvals on/off for the session ([#3990](https://github.com/NousResearch/hermes-agent/pull/3990))
- **`/btw`** — ephemeral side questions that don't affect the main conversation context ([#4161](https://github.com/NousResearch/hermes-agent/pull/4161))
- **`/profile`** — show active profile info without leaving the chat session ([#4027](https://github.com/NousResearch/hermes-agent/pull/4027))
### Interactive CLI
- **Inline diff previews** for write and patch operations in the tool activity feed ([#4411](https://github.com/NousResearch/hermes-agent/pull/4411), [#4423](https://github.com/NousResearch/hermes-agent/pull/4423))
- **TUI pinned to bottom** on startup — no more large blank spaces between response and input ([#4412](https://github.com/NousResearch/hermes-agent/pull/4412), [#4359](https://github.com/NousResearch/hermes-agent/pull/4359), closes [#4398](https://github.com/NousResearch/hermes-agent/issues/4398), [#4421](https://github.com/NousResearch/hermes-agent/issues/4421))
- **`/history` and `/resume`** now surface recent sessions directly instead of requiring search ([#4728](https://github.com/NousResearch/hermes-agent/pull/4728))
- **Cache tokens shown** in `/insights` overview so total adds up ([#4428](https://github.com/NousResearch/hermes-agent/pull/4428))
- **`--max-turns` CLI flag** for `hermes chat` to limit agent iterations ([#4314](https://github.com/NousResearch/hermes-agent/pull/4314))
- **Detect dragged file paths** instead of treating them as slash commands ([#4533](https://github.com/NousResearch/hermes-agent/pull/4533)) — @rolme
- **Allow empty strings and falsy values** in `config set` ([#4310](https://github.com/NousResearch/hermes-agent/pull/4310), closes [#4277](https://github.com/NousResearch/hermes-agent/issues/4277))
- **Voice mode in WSL** when PulseAudio bridge is configured ([#4317](https://github.com/NousResearch/hermes-agent/pull/4317))
- **Respect `NO_COLOR` env var** and `TERM=dumb` for accessibility ([#4079](https://github.com/NousResearch/hermes-agent/pull/4079), closes [#4066](https://github.com/NousResearch/hermes-agent/issues/4066)) — @SHL0MS
- **Correct shell reload instruction** for macOS/zsh users ([#4025](https://github.com/NousResearch/hermes-agent/pull/4025))
- **Zero exit code** on successful quiet mode queries ([#4613](https://github.com/NousResearch/hermes-agent/pull/4613), closes [#4601](https://github.com/NousResearch/hermes-agent/issues/4601)) — @devorun
- **on_session_end hook fires** on interrupted exits ([#4159](https://github.com/NousResearch/hermes-agent/pull/4159))
- **Profile list display** reads `model.default` key correctly ([#4160](https://github.com/NousResearch/hermes-agent/pull/4160))
- **Browser and TTS** shown in reconfigure menu ([#4041](https://github.com/NousResearch/hermes-agent/pull/4041))
- **Web backend priority** detection simplified ([#4036](https://github.com/NousResearch/hermes-agent/pull/4036))
### Setup & Configuration
- **Allowed_users preserved** during setup and quiet unconfigured provider warnings ([#4551](https://github.com/NousResearch/hermes-agent/pull/4551)) — @kshitijk4poor
- **Save API key to model config** for custom endpoints ([#4202](https://github.com/NousResearch/hermes-agent/pull/4202), closes [#4182](https://github.com/NousResearch/hermes-agent/issues/4182))
- **Claude Code credentials gated** behind explicit Hermes config in wizard trigger ([#4210](https://github.com/NousResearch/hermes-agent/pull/4210))
- **Atomic writes in save_config_value** to prevent config loss on interrupt ([#4298](https://github.com/NousResearch/hermes-agent/pull/4298), [#4320](https://github.com/NousResearch/hermes-agent/pull/4320))
- **Scopes field written** to Claude Code credentials on token refresh ([#4126](https://github.com/NousResearch/hermes-agent/pull/4126))
### Update System
- **Fork detection and upstream sync** in `hermes update` ([#4744](https://github.com/NousResearch/hermes-agent/pull/4744))
- **Preserve working optional extras** when one extra fails during update ([#4550](https://github.com/NousResearch/hermes-agent/pull/4550))
- **Handle conflicted git index** during hermes update ([#4735](https://github.com/NousResearch/hermes-agent/pull/4735))
- **Avoid launchd restart race** on macOS ([#4736](https://github.com/NousResearch/hermes-agent/pull/4736))
- **Missing subprocess.run() timeouts** added to doctor and status commands ([#4009](https://github.com/NousResearch/hermes-agent/pull/4009))
---
## 🔧 Tool System
### Browser
- **Camofox anti-detection browser backend** — local stealth browsing with auto-install via `hermes tools` ([#4008](https://github.com/NousResearch/hermes-agent/pull/4008))
- **Persistent Camofox sessions** with VNC URL discovery for visual debugging ([#4419](https://github.com/NousResearch/hermes-agent/pull/4419))
- **Skip SSRF check for local backends** (Camofox, headless Chromium) ([#4292](https://github.com/NousResearch/hermes-agent/pull/4292))
- **Configurable SSRF check** via `browser.allow_private_urls` ([#4198](https://github.com/NousResearch/hermes-agent/pull/4198)) — @nils010485
- **CAMOFOX_PORT=9377** added to Docker commands ([#4340](https://github.com/NousResearch/hermes-agent/pull/4340))
### File Operations
- **Inline diff previews** on write and patch actions ([#4411](https://github.com/NousResearch/hermes-agent/pull/4411), [#4423](https://github.com/NousResearch/hermes-agent/pull/4423))
- **Stale file detection** on write and patch — warns when file was modified externally since last read ([#4345](https://github.com/NousResearch/hermes-agent/pull/4345))
- **Staleness timestamp refreshed** after writes ([#4390](https://github.com/NousResearch/hermes-agent/pull/4390))
- **Size guard, dedup, and device blocking** on read_file ([#4315](https://github.com/NousResearch/hermes-agent/pull/4315))
### MCP
- **Stability fix pack** — reload timeout, shutdown cleanup, event loop handler, OAuth non-blocking ([#4757](https://github.com/NousResearch/hermes-agent/pull/4757), closes [#4462](https://github.com/NousResearch/hermes-agent/issues/4462), [#2537](https://github.com/NousResearch/hermes-agent/issues/2537))
### ACP (Editor Integration)
- **Client-provided MCP servers** registered as agent tools — editors pass their MCP servers to Hermes ([#4705](https://github.com/NousResearch/hermes-agent/pull/4705))
### Skills System
- **Size limits for agent writes** and **fuzzy matching for skill patch** — prevents oversized skill writes and improves edit reliability ([#4414](https://github.com/NousResearch/hermes-agent/pull/4414))
- **Validate hub bundle paths** before install — blocks path traversal in skill bundles ([#3986](https://github.com/NousResearch/hermes-agent/pull/3986))
- **Unified hermes-agent and hermes-agent-setup** into single skill ([#4332](https://github.com/NousResearch/hermes-agent/pull/4332))
- **Skill metadata type check** in extract_skill_conditions ([#4479](https://github.com/NousResearch/hermes-agent/pull/4479))
### New/Updated Skills
- **research-paper-writing** — full end-to-end research pipeline (replaced ml-paper-writing) ([#4654](https://github.com/NousResearch/hermes-agent/pull/4654)) — @SHL0MS
- **ascii-video** — text readability techniques and external layout oracle ([#4054](https://github.com/NousResearch/hermes-agent/pull/4054)) — @SHL0MS
- **youtube-transcript** updated for youtube-transcript-api v1.x ([#4455](https://github.com/NousResearch/hermes-agent/pull/4455)) — @el-analista
- **Skills browse and search page** added to documentation site ([#4500](https://github.com/NousResearch/hermes-agent/pull/4500)) — @IAvecilla
---
## 🔒 Security & Reliability
### Security Hardening
- **Block secret exfiltration** via browser URLs and LLM responses — scans for secret patterns in URL encoding, base64, and prompt injection vectors ([#4483](https://github.com/NousResearch/hermes-agent/pull/4483))
- **Redact secrets from execute_code sandbox output** ([#4360](https://github.com/NousResearch/hermes-agent/pull/4360))
- **Protect `.docker`, `.azure`, `.config/gh` credential directories** from read/write via file tools and terminal ([#4305](https://github.com/NousResearch/hermes-agent/pull/4305), [#4327](https://github.com/NousResearch/hermes-agent/pull/4327)) — @memosr
- **GitHub OAuth token patterns** added to redaction + snapshot redact flag ([#4295](https://github.com/NousResearch/hermes-agent/pull/4295))
- **Reject private and loopback IPs** in Telegram DoH fallback ([#4129](https://github.com/NousResearch/hermes-agent/pull/4129))
- **Reject path traversal** in credential file registration ([#4316](https://github.com/NousResearch/hermes-agent/pull/4316))
- **Validate tar archive member paths** on profile import — blocks zip-slip attacks ([#4318](https://github.com/NousResearch/hermes-agent/pull/4318))
- **Exclude auth.json and .env** from profile exports ([#4475](https://github.com/NousResearch/hermes-agent/pull/4475))
### Reliability
- **Prevent compression death spiral** from API disconnects ([#4750](https://github.com/NousResearch/hermes-agent/pull/4750), closes [#2153](https://github.com/NousResearch/hermes-agent/issues/2153))
- **Handle `is_closed` as method** in OpenAI SDK — prevents false positive client closure detection ([#4416](https://github.com/NousResearch/hermes-agent/pull/4416), closes [#4377](https://github.com/NousResearch/hermes-agent/issues/4377))
- **Exclude matrix from [all] extras** — python-olm is upstream-broken, prevents install failures ([#4615](https://github.com/NousResearch/hermes-agent/pull/4615), closes [#4178](https://github.com/NousResearch/hermes-agent/issues/4178))
- **OpenCode model routing** repaired ([#4508](https://github.com/NousResearch/hermes-agent/pull/4508))
- **Docker container image** optimized ([#4034](https://github.com/NousResearch/hermes-agent/pull/4034)) — @bcross
### Windows & Cross-Platform
- **Voice mode in WSL** with PulseAudio bridge ([#4317](https://github.com/NousResearch/hermes-agent/pull/4317))
- **Homebrew packaging** preparation ([#4099](https://github.com/NousResearch/hermes-agent/pull/4099))
- **CI fork conditionals** to prevent workflow failures on forks ([#4107](https://github.com/NousResearch/hermes-agent/pull/4107))
---
## 🐛 Notable Bug Fixes
- **Gateway approval blocked agent thread** — approval now blocks the agent thread like CLI does, preventing tool result loss ([#4557](https://github.com/NousResearch/hermes-agent/pull/4557), closes [#4542](https://github.com/NousResearch/hermes-agent/issues/4542))
- **Compression death spiral** from API disconnects — detected and halted instead of looping ([#4750](https://github.com/NousResearch/hermes-agent/pull/4750), closes [#2153](https://github.com/NousResearch/hermes-agent/issues/2153))
- **Anthropic thinking blocks lost** across tool-use turns ([#4626](https://github.com/NousResearch/hermes-agent/pull/4626))
- **Profile model config ignored** with `-p` flag — model.model now promoted to model.default correctly ([#4160](https://github.com/NousResearch/hermes-agent/pull/4160), closes [#4486](https://github.com/NousResearch/hermes-agent/issues/4486))
- **CLI blank space** between response and input area ([#4412](https://github.com/NousResearch/hermes-agent/pull/4412), [#4359](https://github.com/NousResearch/hermes-agent/pull/4359), closes [#4398](https://github.com/NousResearch/hermes-agent/issues/4398))
- **Dragged file paths** treated as slash commands instead of file references ([#4533](https://github.com/NousResearch/hermes-agent/pull/4533)) — @rolme
- **Orphaned `</think>` tags** leaking into user-facing responses ([#4311](https://github.com/NousResearch/hermes-agent/pull/4311), closes [#4285](https://github.com/NousResearch/hermes-agent/issues/4285))
- **OpenAI SDK `is_closed`** is a method not property — false positive client closure ([#4416](https://github.com/NousResearch/hermes-agent/pull/4416), closes [#4377](https://github.com/NousResearch/hermes-agent/issues/4377))
- **MCP OAuth server** could block Hermes startup instead of degrading gracefully ([#4757](https://github.com/NousResearch/hermes-agent/pull/4757), closes [#4462](https://github.com/NousResearch/hermes-agent/issues/4462))
- **MCP event loop closed** on shutdown with HTTP servers ([#4757](https://github.com/NousResearch/hermes-agent/pull/4757), closes [#2537](https://github.com/NousResearch/hermes-agent/issues/2537))
- **Alibaba provider** hardcoded to wrong endpoint ([#4133](https://github.com/NousResearch/hermes-agent/pull/4133), closes [#3912](https://github.com/NousResearch/hermes-agent/issues/3912))
- **Slack reply_in_thread** missing config option ([#4643](https://github.com/NousResearch/hermes-agent/pull/4643), closes [#2662](https://github.com/NousResearch/hermes-agent/issues/2662))
- **Quiet mode exit code** — successful `-q` queries no longer exit nonzero ([#4613](https://github.com/NousResearch/hermes-agent/pull/4613), closes [#4601](https://github.com/NousResearch/hermes-agent/issues/4601))
- **Mobile sidebar** shows only close button due to backdrop-filter issue in docs site ([#4207](https://github.com/NousResearch/hermes-agent/pull/4207)) — @xsmyile
- **Config restore reverted** by stale-branch squash merge — `_config_version` fixed ([#4440](https://github.com/NousResearch/hermes-agent/pull/4440))
---
## 🧪 Testing
- **Telegram gateway E2E tests** — full integration test suite for the Telegram adapter ([#4497](https://github.com/NousResearch/hermes-agent/pull/4497)) — @pefontana
- **11 real test failures fixed** plus sys.modules cascade poisoner resolved ([#4570](https://github.com/NousResearch/hermes-agent/pull/4570))
- **7 CI failures resolved** across hooks, plugins, and skill tests ([#3936](https://github.com/NousResearch/hermes-agent/pull/3936))
- **Codex 401 refresh tests** updated for CI compatibility ([#4166](https://github.com/NousResearch/hermes-agent/pull/4166))
- **Stale OPENAI_BASE_URL test** fixed ([#4217](https://github.com/NousResearch/hermes-agent/pull/4217))
---
## 📚 Documentation
- **Comprehensive documentation audit** — 9 HIGH and 20+ MEDIUM gaps fixed across 21 files ([#4087](https://github.com/NousResearch/hermes-agent/pull/4087))
- **Site navigation restructured** — features and platforms promoted to top-level ([#4116](https://github.com/NousResearch/hermes-agent/pull/4116))
- **Tool progress streaming** documented for API server and Open WebUI ([#4138](https://github.com/NousResearch/hermes-agent/pull/4138))
- **Telegram webhook mode** documentation ([#4089](https://github.com/NousResearch/hermes-agent/pull/4089))
- **Local LLM provider guides** — comprehensive setup guides with context length warnings ([#4294](https://github.com/NousResearch/hermes-agent/pull/4294))
- **WhatsApp allowlist behavior** clarified with `WHATSAPP_ALLOW_ALL_USERS` documentation ([#4293](https://github.com/NousResearch/hermes-agent/pull/4293))
- **Slack configuration options** — new config section in Slack docs ([#4644](https://github.com/NousResearch/hermes-agent/pull/4644))
- **Terminal backends section** expanded + docs build fixes ([#4016](https://github.com/NousResearch/hermes-agent/pull/4016))
- **Adding-providers guide** updated for unified setup flow ([#4201](https://github.com/NousResearch/hermes-agent/pull/4201))
- **ACP Zed config** fixed ([#4743](https://github.com/NousResearch/hermes-agent/pull/4743))
- **Community FAQ** entries for common workflows and troubleshooting ([#4797](https://github.com/NousResearch/hermes-agent/pull/4797))
- **Skills browse and search page** on docs site ([#4500](https://github.com/NousResearch/hermes-agent/pull/4500)) — @IAvecilla
---
## 👥 Contributors
### Core
- **@teknium1** — 135 commits across all subsystems
### Top Community Contributors
- **@kshitijk4poor** — 13 commits: preserve allowed_users during setup ([#4551](https://github.com/NousResearch/hermes-agent/pull/4551)), and various fixes
- **@erosika** — 12 commits: Honcho full integration parity restored as memory provider plugin ([#4355](https://github.com/NousResearch/hermes-agent/pull/4355))
- **@pefontana** — 9 commits: Telegram gateway E2E test suite ([#4497](https://github.com/NousResearch/hermes-agent/pull/4497))
- **@bcross** — 5 commits: Docker container image optimization ([#4034](https://github.com/NousResearch/hermes-agent/pull/4034))
- **@SHL0MS** — 4 commits: NO_COLOR/TERM=dumb support ([#4079](https://github.com/NousResearch/hermes-agent/pull/4079)), ascii-video skill updates ([#4054](https://github.com/NousResearch/hermes-agent/pull/4054)), research-paper-writing skill ([#4654](https://github.com/NousResearch/hermes-agent/pull/4654))
### All Contributors
@0xbyt4, @arasovic, @Bartok9, @bcross, @binhnt92, @camden-lowrance, @curtitoo, @Dakota, @Dave Tist, @Dean Kerr, @devorun, @dieutx, @Dilee, @el-analista, @erosika, @Gutslabs, @IAvecilla, @Jack, @Johannnnn506, @kshitijk4poor, @Laura Batalha, @Leegenux, @Lume, @MacroAnarchy, @maymuneth, @memosr, @NexVeridian, @Nick, @nils010485, @pefontana, @Penov, @rolme, @SHL0MS, @txchen, @xsmyile
### Issues Resolved from Community
@acsezen ([#2537](https://github.com/NousResearch/hermes-agent/issues/2537)), @arasovic ([#4285](https://github.com/NousResearch/hermes-agent/issues/4285)), @camden-lowrance ([#4462](https://github.com/NousResearch/hermes-agent/issues/4462)), @devorun ([#4601](https://github.com/NousResearch/hermes-agent/issues/4601)), @eloklam ([#4486](https://github.com/NousResearch/hermes-agent/issues/4486)), @HenkDz ([#3719](https://github.com/NousResearch/hermes-agent/issues/3719)), @hypotyposis ([#2153](https://github.com/NousResearch/hermes-agent/issues/2153)), @kazamak ([#4178](https://github.com/NousResearch/hermes-agent/issues/4178)), @lstep ([#4366](https://github.com/NousResearch/hermes-agent/issues/4366)), @Mark-Lok ([#4542](https://github.com/NousResearch/hermes-agent/issues/4542)), @NoJster ([#4421](https://github.com/NousResearch/hermes-agent/issues/4421)), @patp ([#2662](https://github.com/NousResearch/hermes-agent/issues/2662)), @pr0n ([#4601](https://github.com/NousResearch/hermes-agent/issues/4601)), @saulmc ([#4377](https://github.com/NousResearch/hermes-agent/issues/4377)), @SHL0MS ([#4060](https://github.com/NousResearch/hermes-agent/issues/4060), [#4061](https://github.com/NousResearch/hermes-agent/issues/4061), [#4066](https://github.com/NousResearch/hermes-agent/issues/4066), [#4172](https://github.com/NousResearch/hermes-agent/issues/4172), [#4277](https://github.com/NousResearch/hermes-agent/issues/4277)), @Z-Mackintosh ([#4398](https://github.com/NousResearch/hermes-agent/issues/4398))
---
**Full Changelog**: [v2026.3.30...v2026.4.3](https://github.com/NousResearch/hermes-agent/compare/v2026.3.30...v2026.4.3)

View File

@@ -1,346 +0,0 @@
# Hermes Agent v0.8.0 (v2026.4.8)
**Release Date:** April 8, 2026
> The intelligence release — background task auto-notifications, free MiMo v2 Pro on Nous Portal, live model switching across all platforms, self-optimized GPT/Codex guidance, native Google AI Studio, smart inactivity timeouts, approval buttons, MCP OAuth 2.1, and 209 merged PRs with 82 resolved issues.
---
## ✨ Highlights
- **Background Process Auto-Notifications (`notify_on_complete`)** — Background tasks can now automatically notify the agent when they finish. Start a long-running process (AI model training, test suites, deployments, builds) and the agent gets notified on completion — no polling needed. The agent can keep working on other things and pick up results when they land. ([#5779](https://github.com/NousResearch/hermes-agent/pull/5779))
- **Free Xiaomi MiMo v2 Pro on Nous Portal** — Nous Portal now supports the free-tier Xiaomi MiMo v2 Pro model for auxiliary tasks (compression, vision, summarization), with free-tier model gating and pricing display in model selection. ([#6018](https://github.com/NousResearch/hermes-agent/pull/6018), [#5880](https://github.com/NousResearch/hermes-agent/pull/5880))
- **Live Model Switching (`/model` Command)** — Switch models and providers mid-session from CLI, Telegram, Discord, Slack, or any gateway platform. Aggregator-aware resolution keeps you on OpenRouter/Nous when possible, with automatic cross-provider fallback when needed. Interactive model pickers on Telegram and Discord with inline buttons. ([#5181](https://github.com/NousResearch/hermes-agent/pull/5181), [#5742](https://github.com/NousResearch/hermes-agent/pull/5742))
- **Self-Optimized GPT/Codex Tool-Use Guidance** — The agent diagnosed and patched 5 failure modes in GPT and Codex tool calling through automated behavioral benchmarking, dramatically improving reliability on OpenAI models. Includes execution discipline guidance and thinking-only prefill continuation for structured reasoning. ([#6120](https://github.com/NousResearch/hermes-agent/pull/6120), [#5414](https://github.com/NousResearch/hermes-agent/pull/5414), [#5931](https://github.com/NousResearch/hermes-agent/pull/5931))
- **Google AI Studio (Gemini) Native Provider** — Direct access to Gemini models through Google's AI Studio API. Includes automatic models.dev registry integration for real-time context length detection across any provider. ([#5577](https://github.com/NousResearch/hermes-agent/pull/5577))
- **Inactivity-Based Agent Timeouts** — Gateway and cron timeouts now track actual tool activity instead of wall-clock time. Long-running tasks that are actively working will never be killed — only truly idle agents time out. ([#5389](https://github.com/NousResearch/hermes-agent/pull/5389), [#5440](https://github.com/NousResearch/hermes-agent/pull/5440))
- **Approval Buttons on Slack & Telegram** — Dangerous command approval via native platform buttons instead of typing `/approve`. Slack gets thread context preservation; Telegram gets emoji reactions for approval status. ([#5890](https://github.com/NousResearch/hermes-agent/pull/5890), [#5975](https://github.com/NousResearch/hermes-agent/pull/5975))
- **MCP OAuth 2.1 PKCE + OSV Malware Scanning** — Full standards-compliant OAuth for MCP server authentication, plus automatic malware scanning of MCP extension packages via the OSV vulnerability database. ([#5420](https://github.com/NousResearch/hermes-agent/pull/5420), [#5305](https://github.com/NousResearch/hermes-agent/pull/5305))
- **Centralized Logging & Config Validation** — Structured logging to `~/.hermes/logs/` (agent.log + errors.log) with the `hermes logs` command for tailing and filtering. Config structure validation catches malformed YAML at startup before it causes cryptic failures. ([#5430](https://github.com/NousResearch/hermes-agent/pull/5430), [#5426](https://github.com/NousResearch/hermes-agent/pull/5426))
- **Plugin System Expansion** — Plugins can now register CLI subcommands, receive request-scoped API hooks with correlation IDs, prompt for required env vars during install, and hook into session lifecycle events (finalize/reset). ([#5295](https://github.com/NousResearch/hermes-agent/pull/5295), [#5427](https://github.com/NousResearch/hermes-agent/pull/5427), [#5470](https://github.com/NousResearch/hermes-agent/pull/5470), [#6129](https://github.com/NousResearch/hermes-agent/pull/6129))
- **Matrix Tier 1 & Platform Hardening** — Matrix gets reactions, read receipts, rich formatting, and room management. Discord adds channel controls and ignored channels. Signal gets full MEDIA: tag delivery. Mattermost gets file attachments. Comprehensive reliability fixes across all platforms. ([#5275](https://github.com/NousResearch/hermes-agent/pull/5275), [#5975](https://github.com/NousResearch/hermes-agent/pull/5975), [#5602](https://github.com/NousResearch/hermes-agent/pull/5602))
- **Security Hardening Pass** — Consolidated SSRF protections, timing attack mitigations, tar traversal prevention, credential leakage guards, cron path traversal hardening, and cross-session isolation. Terminal workdir sanitization across all backends. ([#5944](https://github.com/NousResearch/hermes-agent/pull/5944), [#5613](https://github.com/NousResearch/hermes-agent/pull/5613), [#5629](https://github.com/NousResearch/hermes-agent/pull/5629))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- **Native Google AI Studio (Gemini) provider** with models.dev integration for automatic context length detection ([#5577](https://github.com/NousResearch/hermes-agent/pull/5577))
- **`/model` command — full provider+model system overhaul** — live switching across CLI and all gateway platforms with aggregator-aware resolution ([#5181](https://github.com/NousResearch/hermes-agent/pull/5181))
- **Interactive model picker for Telegram and Discord** — inline button-based model selection ([#5742](https://github.com/NousResearch/hermes-agent/pull/5742))
- **Nous Portal free-tier model gating** with pricing display in model selection ([#5880](https://github.com/NousResearch/hermes-agent/pull/5880))
- **Model pricing display** for OpenRouter and Nous Portal providers ([#5416](https://github.com/NousResearch/hermes-agent/pull/5416))
- **xAI (Grok) prompt caching** via `x-grok-conv-id` header ([#5604](https://github.com/NousResearch/hermes-agent/pull/5604))
- **Grok added to tool-use enforcement models** for direct xAI usage ([#5595](https://github.com/NousResearch/hermes-agent/pull/5595))
- **MiniMax TTS provider** (speech-2.8) ([#4963](https://github.com/NousResearch/hermes-agent/pull/4963))
- **Non-agentic model warning** — warns users when loading Hermes LLM models not designed for tool use ([#5378](https://github.com/NousResearch/hermes-agent/pull/5378))
- **Ollama Cloud auth, /model switch persistence**, and alias tab completion ([#5269](https://github.com/NousResearch/hermes-agent/pull/5269))
- **Preserve dots in OpenCode Go model names** (minimax-m2.7, glm-4.5, kimi-k2.5) ([#5597](https://github.com/NousResearch/hermes-agent/pull/5597))
- **MiniMax models 404 fix** — strip /v1 from Anthropic base URL for OpenCode Go ([#4918](https://github.com/NousResearch/hermes-agent/pull/4918))
- **Provider credential reset windows** honored in pooled failover ([#5188](https://github.com/NousResearch/hermes-agent/pull/5188))
- **OAuth token sync** between credential pool and credentials file ([#4981](https://github.com/NousResearch/hermes-agent/pull/4981))
- **Stale OAuth credentials** no longer block OpenRouter users on auto-detect ([#5746](https://github.com/NousResearch/hermes-agent/pull/5746))
- **Codex OAuth credential pool disconnect** + expired token import fix ([#5681](https://github.com/NousResearch/hermes-agent/pull/5681))
- **Codex pool entry sync** from `~/.codex/auth.json` on exhaustion — @GratefulDave ([#5610](https://github.com/NousResearch/hermes-agent/pull/5610))
- **Auxiliary client payment fallback** — retry with next provider on 402 ([#5599](https://github.com/NousResearch/hermes-agent/pull/5599))
- **Auxiliary client resolves named custom providers** and 'main' alias ([#5978](https://github.com/NousResearch/hermes-agent/pull/5978))
- **Use mimo-v2-pro** for non-vision auxiliary tasks on Nous free tier ([#6018](https://github.com/NousResearch/hermes-agent/pull/6018))
- **Vision auto-detection** tries main provider first ([#6041](https://github.com/NousResearch/hermes-agent/pull/6041))
- **Provider re-ordering and Quick Install** — @austinpickett ([#4664](https://github.com/NousResearch/hermes-agent/pull/4664))
- **Nous OAuth access_token** no longer used as inference API key — @SHL0MS ([#5564](https://github.com/NousResearch/hermes-agent/pull/5564))
- **HERMES_PORTAL_BASE_URL env var** respected during Nous login — @benbarclay ([#5745](https://github.com/NousResearch/hermes-agent/pull/5745))
- **Env var overrides** for Nous portal/inference URLs ([#5419](https://github.com/NousResearch/hermes-agent/pull/5419))
- **Z.AI endpoint auto-detect** via probe and cache ([#5763](https://github.com/NousResearch/hermes-agent/pull/5763))
- **MiniMax context lengths, model catalog, thinking guard, aux model, and config base_url** corrections ([#6082](https://github.com/NousResearch/hermes-agent/pull/6082))
- **Community provider/model resolution fixes** — salvaged 4 community PRs + MiniMax aux URL ([#5983](https://github.com/NousResearch/hermes-agent/pull/5983))
### Agent Loop & Conversation
- **Self-optimized GPT/Codex tool-use guidance** via automated behavioral benchmarking — agent self-diagnosed and patched 5 failure modes ([#6120](https://github.com/NousResearch/hermes-agent/pull/6120))
- **GPT/Codex execution discipline guidance** in system prompts ([#5414](https://github.com/NousResearch/hermes-agent/pull/5414))
- **Thinking-only prefill continuation** for structured reasoning responses ([#5931](https://github.com/NousResearch/hermes-agent/pull/5931))
- **Accept reasoning-only responses** without retries — set content to "(empty)" instead of infinite retry ([#5278](https://github.com/NousResearch/hermes-agent/pull/5278))
- **Jittered retry backoff** — exponential backoff with jitter for API retries ([#6048](https://github.com/NousResearch/hermes-agent/pull/6048))
- **Smart thinking block signature management** — preserve and manage Anthropic thinking signatures across turns ([#6112](https://github.com/NousResearch/hermes-agent/pull/6112))
- **Coerce tool call arguments** to match JSON Schema types — fixes models that send strings instead of numbers/booleans ([#5265](https://github.com/NousResearch/hermes-agent/pull/5265))
- **Save oversized tool results to file** instead of destructive truncation ([#5210](https://github.com/NousResearch/hermes-agent/pull/5210))
- **Sandbox-aware tool result persistence** ([#6085](https://github.com/NousResearch/hermes-agent/pull/6085))
- **Streaming fallback** improved after edit failures ([#6110](https://github.com/NousResearch/hermes-agent/pull/6110))
- **Codex empty-output gaps** covered in fallback + normalizer + auxiliary client ([#5724](https://github.com/NousResearch/hermes-agent/pull/5724), [#5730](https://github.com/NousResearch/hermes-agent/pull/5730), [#5734](https://github.com/NousResearch/hermes-agent/pull/5734))
- **Codex stream output backfill** from output_item.done events ([#5689](https://github.com/NousResearch/hermes-agent/pull/5689))
- **Stream consumer creates new message** after tool boundaries ([#5739](https://github.com/NousResearch/hermes-agent/pull/5739))
- **Codex validation aligned** with normalization for empty stream output ([#5940](https://github.com/NousResearch/hermes-agent/pull/5940))
- **Bridge tool-calls** in copilot-acp adapter ([#5460](https://github.com/NousResearch/hermes-agent/pull/5460))
- **Filter transcript-only roles** from chat-completions payload ([#4880](https://github.com/NousResearch/hermes-agent/pull/4880))
- **Context compaction failures fixed** on temperature-restricted models — @MadKangYu ([#5608](https://github.com/NousResearch/hermes-agent/pull/5608))
- **Sanitize tool_calls for all strict APIs** (Fireworks, Mistral, etc.) — @lumethegreat ([#5183](https://github.com/NousResearch/hermes-agent/pull/5183))
### Memory & Sessions
- **Supermemory memory provider** — new memory plugin with multi-container, search_mode, identity template, and env var override ([#5737](https://github.com/NousResearch/hermes-agent/pull/5737), [#5933](https://github.com/NousResearch/hermes-agent/pull/5933))
- **Shared thread sessions** by default — multi-user thread support across gateway platforms ([#5391](https://github.com/NousResearch/hermes-agent/pull/5391))
- **Subagent sessions linked to parent** and hidden from session list ([#5309](https://github.com/NousResearch/hermes-agent/pull/5309))
- **Profile-scoped memory isolation** and clone support ([#4845](https://github.com/NousResearch/hermes-agent/pull/4845))
- **Thread gateway user_id to memory plugins** for per-user scoping ([#5895](https://github.com/NousResearch/hermes-agent/pull/5895))
- **Honcho plugin drift overhaul** + plugin CLI registration system ([#5295](https://github.com/NousResearch/hermes-agent/pull/5295))
- **Honcho holographic prompt and trust score** rendering preserved ([#4872](https://github.com/NousResearch/hermes-agent/pull/4872))
- **Honcho doctor fix** — use recall_mode instead of memory_mode — @techguysimon ([#5645](https://github.com/NousResearch/hermes-agent/pull/5645))
- **RetainDB** — API routes, write queue, dialectic, agent model, file tools fixes ([#5461](https://github.com/NousResearch/hermes-agent/pull/5461))
- **Hindsight memory plugin overhaul** + memory setup wizard fixes ([#5094](https://github.com/NousResearch/hermes-agent/pull/5094))
- **mem0 API v2 compat**, prefetch context fencing, secret redaction ([#5423](https://github.com/NousResearch/hermes-agent/pull/5423))
- **mem0 env vars merged** with mem0.json instead of either/or ([#4939](https://github.com/NousResearch/hermes-agent/pull/4939))
- **Clean user message** used for all memory provider operations ([#4940](https://github.com/NousResearch/hermes-agent/pull/4940))
- **Silent memory flush failure** on /new and /resume fixed — @ryanautomated ([#5640](https://github.com/NousResearch/hermes-agent/pull/5640))
- **OpenViking atexit safety net** for session commit ([#5664](https://github.com/NousResearch/hermes-agent/pull/5664))
- **OpenViking tenant-scoping headers** for multi-tenant servers ([#4936](https://github.com/NousResearch/hermes-agent/pull/4936))
- **ByteRover brv query** runs synchronously before LLM call ([#4831](https://github.com/NousResearch/hermes-agent/pull/4831))
---
## 📱 Messaging Platforms (Gateway)
### Gateway Core
- **Inactivity-based agent timeout** — replaces wall-clock timeout with smart activity tracking; long-running active tasks never killed ([#5389](https://github.com/NousResearch/hermes-agent/pull/5389))
- **Approval buttons for Slack & Telegram** + Slack thread context preservation ([#5890](https://github.com/NousResearch/hermes-agent/pull/5890))
- **Live-stream /update output** + forward interactive prompts to user ([#5180](https://github.com/NousResearch/hermes-agent/pull/5180))
- **Infinite timeout support** + periodic notifications + actionable error messages ([#4959](https://github.com/NousResearch/hermes-agent/pull/4959))
- **Duplicate message prevention** — gateway dedup + partial stream guard ([#4878](https://github.com/NousResearch/hermes-agent/pull/4878))
- **Webhook delivery_info persistence** + full session id in /status ([#5942](https://github.com/NousResearch/hermes-agent/pull/5942))
- **Tool preview truncation** respects tool_preview_length in all/new progress modes ([#5937](https://github.com/NousResearch/hermes-agent/pull/5937))
- **Short preview truncation** restored for all/new tool progress modes ([#4935](https://github.com/NousResearch/hermes-agent/pull/4935))
- **Update-pending state** written atomically to prevent corruption ([#4923](https://github.com/NousResearch/hermes-agent/pull/4923))
- **Approval session key isolated** per turn ([#4884](https://github.com/NousResearch/hermes-agent/pull/4884))
- **Active-session guard bypass** for /approve, /deny, /stop, /new ([#4926](https://github.com/NousResearch/hermes-agent/pull/4926), [#5765](https://github.com/NousResearch/hermes-agent/pull/5765))
- **Typing indicator paused** during approval waits ([#5893](https://github.com/NousResearch/hermes-agent/pull/5893))
- **Caption check** uses exact line-by-line match instead of substring (all platforms) ([#5939](https://github.com/NousResearch/hermes-agent/pull/5939))
- **MEDIA: tags stripped** from streamed gateway messages ([#5152](https://github.com/NousResearch/hermes-agent/pull/5152))
- **MEDIA: tags extracted** from cron delivery before sending ([#5598](https://github.com/NousResearch/hermes-agent/pull/5598))
- **Profile-aware service units** + voice transcription cleanup ([#5972](https://github.com/NousResearch/hermes-agent/pull/5972))
- **Thread-safe PairingStore** with atomic writes — @CharlieKerfoot ([#5656](https://github.com/NousResearch/hermes-agent/pull/5656))
- **Sanitize media URLs** in base platform logs — @WAXLYY ([#5631](https://github.com/NousResearch/hermes-agent/pull/5631))
- **Reduce Telegram fallback IP activation log noise** — @MadKangYu ([#5615](https://github.com/NousResearch/hermes-agent/pull/5615))
- **Cron static method wrappers** to prevent self-binding ([#5299](https://github.com/NousResearch/hermes-agent/pull/5299))
- **Stale 'hermes login' replaced** with 'hermes auth' + credential removal re-seeding fix ([#5670](https://github.com/NousResearch/hermes-agent/pull/5670))
### Telegram
- **Group topics skill binding** for supergroup forum topics ([#4886](https://github.com/NousResearch/hermes-agent/pull/4886))
- **Emoji reactions** for approval status and notifications ([#5975](https://github.com/NousResearch/hermes-agent/pull/5975))
- **Duplicate message delivery prevented** on send timeout ([#5153](https://github.com/NousResearch/hermes-agent/pull/5153))
- **Command names sanitized** to strip invalid characters ([#5596](https://github.com/NousResearch/hermes-agent/pull/5596))
- **Per-platform disabled skills** respected in Telegram menu and gateway dispatch ([#4799](https://github.com/NousResearch/hermes-agent/pull/4799))
- **/approve and /deny** routed through running-agent guard ([#4798](https://github.com/NousResearch/hermes-agent/pull/4798))
### Discord
- **Channel controls** — ignored_channels and no_thread_channels config options ([#5975](https://github.com/NousResearch/hermes-agent/pull/5975))
- **Skills registered as native slash commands** via shared gateway logic ([#5603](https://github.com/NousResearch/hermes-agent/pull/5603))
- **/approve, /deny, /queue, /background, /btw** registered as native slash commands ([#4800](https://github.com/NousResearch/hermes-agent/pull/4800), [#5477](https://github.com/NousResearch/hermes-agent/pull/5477))
- **Unnecessary members intent** removed on startup + token lock leak fix ([#5302](https://github.com/NousResearch/hermes-agent/pull/5302))
### Slack
- **Thread engagement** — auto-respond in bot-started and mentioned threads ([#5897](https://github.com/NousResearch/hermes-agent/pull/5897))
- **mrkdwn in edit_message** + thread replies without @mentions ([#5733](https://github.com/NousResearch/hermes-agent/pull/5733))
### Matrix
- **Tier 1 feature parity** — reactions, read receipts, rich formatting, room management ([#5275](https://github.com/NousResearch/hermes-agent/pull/5275))
- **MATRIX_REQUIRE_MENTION and MATRIX_AUTO_THREAD** support ([#5106](https://github.com/NousResearch/hermes-agent/pull/5106))
- **Comprehensive reliability** — encrypted media, auth recovery, cron E2EE, Synapse compat ([#5271](https://github.com/NousResearch/hermes-agent/pull/5271))
- **CJK input, E2EE, and reconnect** fixes ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
### Signal
- **Full MEDIA: tag delivery** — send_image_file, send_voice, and send_video implemented ([#5602](https://github.com/NousResearch/hermes-agent/pull/5602))
### Mattermost
- **File attachments** — set message type to DOCUMENT when post has file attachments — @nericervin ([#5609](https://github.com/NousResearch/hermes-agent/pull/5609))
### Feishu
- **Interactive card approval buttons** ([#6043](https://github.com/NousResearch/hermes-agent/pull/6043))
- **Reconnect and ACL** fixes ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
### Webhooks
- **`{__raw__}` template token** and thread_id passthrough for forum topics ([#5662](https://github.com/NousResearch/hermes-agent/pull/5662))
---
## 🖥️ CLI & User Experience
### Interactive CLI
- **Defer response content** until reasoning block completes ([#5773](https://github.com/NousResearch/hermes-agent/pull/5773))
- **Ghost status-bar lines cleared** on terminal resize ([#4960](https://github.com/NousResearch/hermes-agent/pull/4960))
- **Normalise \r\n and \r line endings** in pasted text ([#4849](https://github.com/NousResearch/hermes-agent/pull/4849))
- **ChatConsole errors, curses scroll, skin-aware banner, git state** banner fixes ([#5974](https://github.com/NousResearch/hermes-agent/pull/5974))
- **Native Windows image paste** support ([#5917](https://github.com/NousResearch/hermes-agent/pull/5917))
- **--yolo and other flags** no longer silently dropped when placed before 'chat' subcommand ([#5145](https://github.com/NousResearch/hermes-agent/pull/5145))
### Setup & Configuration
- **Config structure validation** — detect malformed YAML at startup with actionable error messages ([#5426](https://github.com/NousResearch/hermes-agent/pull/5426))
- **Centralized logging** to `~/.hermes/logs/` — agent.log (INFO+), errors.log (WARNING+) with `hermes logs` command ([#5430](https://github.com/NousResearch/hermes-agent/pull/5430))
- **Docs links added** to setup wizard sections ([#5283](https://github.com/NousResearch/hermes-agent/pull/5283))
- **Doctor diagnostics** — sync provider checks, config migration, WAL and mem0 diagnostics ([#5077](https://github.com/NousResearch/hermes-agent/pull/5077))
- **Timeout debug logging** and user-facing diagnostics improved ([#5370](https://github.com/NousResearch/hermes-agent/pull/5370))
- **Reasoning effort unified** to config.yaml only ([#6118](https://github.com/NousResearch/hermes-agent/pull/6118))
- **Permanent command allowlist** loaded on startup ([#5076](https://github.com/NousResearch/hermes-agent/pull/5076))
- **`hermes auth remove`** now clears env-seeded credentials permanently ([#5285](https://github.com/NousResearch/hermes-agent/pull/5285))
- **Bundled skills synced to all profiles** during update ([#5795](https://github.com/NousResearch/hermes-agent/pull/5795))
- **`hermes update` no longer kills** freshly-restarted gateway service ([#5448](https://github.com/NousResearch/hermes-agent/pull/5448))
- **Subprocess.run() timeouts** added to all gateway CLI commands ([#5424](https://github.com/NousResearch/hermes-agent/pull/5424))
- **Actionable error message** when Codex refresh token is reused — @tymrtn ([#5612](https://github.com/NousResearch/hermes-agent/pull/5612))
- **Google-workspace skill scripts** can now run directly — @xinbenlv ([#5624](https://github.com/NousResearch/hermes-agent/pull/5624))
### Cron System
- **Inactivity-based cron timeout** — replaces wall-clock; active tasks run indefinitely ([#5440](https://github.com/NousResearch/hermes-agent/pull/5440))
- **Pre-run script injection** for data collection and change detection ([#5082](https://github.com/NousResearch/hermes-agent/pull/5082))
- **Delivery failure tracking** in job status ([#6042](https://github.com/NousResearch/hermes-agent/pull/6042))
- **Delivery guidance** in cron prompts — stops send_message thrashing ([#5444](https://github.com/NousResearch/hermes-agent/pull/5444))
- **MEDIA files delivered** as native platform attachments ([#5921](https://github.com/NousResearch/hermes-agent/pull/5921))
- **[SILENT] suppression** works anywhere in response — @auspic7 ([#5654](https://github.com/NousResearch/hermes-agent/pull/5654))
- **Cron path traversal** hardening ([#5147](https://github.com/NousResearch/hermes-agent/pull/5147))
---
## 🔧 Tool System
### Terminal & Execution
- **Execute_code on remote backends** — code execution now works on Docker, SSH, Modal, and other remote terminal backends ([#5088](https://github.com/NousResearch/hermes-agent/pull/5088))
- **Exit code context** for common CLI tools in terminal results — helps agent understand what went wrong ([#5144](https://github.com/NousResearch/hermes-agent/pull/5144))
- **Progressive subdirectory hint discovery** — agent learns project structure as it navigates ([#5291](https://github.com/NousResearch/hermes-agent/pull/5291))
- **notify_on_complete for background processes** — get notified when long-running tasks finish ([#5779](https://github.com/NousResearch/hermes-agent/pull/5779))
- **Docker env config** — explicit container environment variables via docker_env config ([#4738](https://github.com/NousResearch/hermes-agent/pull/4738))
- **Approval metadata included** in terminal tool results ([#5141](https://github.com/NousResearch/hermes-agent/pull/5141))
- **Workdir parameter sanitized** in terminal tool across all backends ([#5629](https://github.com/NousResearch/hermes-agent/pull/5629))
- **Detached process crash recovery** state corrected ([#6101](https://github.com/NousResearch/hermes-agent/pull/6101))
- **Agent-browser paths with spaces** preserved — @Vasanthdev2004 ([#6077](https://github.com/NousResearch/hermes-agent/pull/6077))
- **Portable base64 encoding** for image reading on macOS — @CharlieKerfoot ([#5657](https://github.com/NousResearch/hermes-agent/pull/5657))
### Browser
- **Switch managed browser provider** from Browserbase to Browser Use — @benbarclay ([#5750](https://github.com/NousResearch/hermes-agent/pull/5750))
- **Firecrawl cloud browser** provider — @alt-glitch ([#5628](https://github.com/NousResearch/hermes-agent/pull/5628))
- **JS evaluation** via browser_console expression parameter ([#5303](https://github.com/NousResearch/hermes-agent/pull/5303))
- **Windows browser** fixes ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
### MCP
- **MCP OAuth 2.1 PKCE** — full standards-compliant OAuth client support ([#5420](https://github.com/NousResearch/hermes-agent/pull/5420))
- **OSV malware check** for MCP extension packages ([#5305](https://github.com/NousResearch/hermes-agent/pull/5305))
- **Prefer structuredContent over text** + no_mcp sentinel ([#5979](https://github.com/NousResearch/hermes-agent/pull/5979))
- **Unknown toolsets warning suppressed** for MCP server names ([#5279](https://github.com/NousResearch/hermes-agent/pull/5279))
### Web & Files
- **.zip document support** + auto-mount cache dirs into remote backends ([#4846](https://github.com/NousResearch/hermes-agent/pull/4846))
- **Redact query secrets** in send_message errors — @WAXLYY ([#5650](https://github.com/NousResearch/hermes-agent/pull/5650))
### Delegation
- **Credential pool sharing** + workspace path hints for subagents ([#5748](https://github.com/NousResearch/hermes-agent/pull/5748))
### ACP (VS Code / Zed / JetBrains)
- **Aggregate ACP improvements** — auth compat, protocol fixes, command ads, delegation, SSE events ([#5292](https://github.com/NousResearch/hermes-agent/pull/5292))
---
## 🧩 Skills Ecosystem
### Skills System
- **Skill config interface** — skills can declare required config.yaml settings, prompted during setup, injected at load time ([#5635](https://github.com/NousResearch/hermes-agent/pull/5635))
- **Plugin CLI registration system** — plugins register their own CLI subcommands without touching main.py ([#5295](https://github.com/NousResearch/hermes-agent/pull/5295))
- **Request-scoped API hooks** with tool call correlation IDs for plugins ([#5427](https://github.com/NousResearch/hermes-agent/pull/5427))
- **Session lifecycle hooks** — on_session_finalize and on_session_reset for CLI + gateway ([#6129](https://github.com/NousResearch/hermes-agent/pull/6129))
- **Prompt for required env vars** during plugin install — @kshitijk4poor ([#5470](https://github.com/NousResearch/hermes-agent/pull/5470))
- **Plugin name validation** — reject names that resolve to plugins root ([#5368](https://github.com/NousResearch/hermes-agent/pull/5368))
- **pre_llm_call plugin context** moved to user message to preserve prompt cache ([#5146](https://github.com/NousResearch/hermes-agent/pull/5146))
### New & Updated Skills
- **popular-web-designs** — 54 production website design systems ([#5194](https://github.com/NousResearch/hermes-agent/pull/5194))
- **p5js creative coding** — @SHL0MS ([#5600](https://github.com/NousResearch/hermes-agent/pull/5600))
- **manim-video** — mathematical and technical animations — @SHL0MS ([#4930](https://github.com/NousResearch/hermes-agent/pull/4930))
- **llm-wiki** — Karpathy's LLM Wiki skill ([#5635](https://github.com/NousResearch/hermes-agent/pull/5635))
- **gitnexus-explorer** — codebase indexing and knowledge serving ([#5208](https://github.com/NousResearch/hermes-agent/pull/5208))
- **research-paper-writing** — AI-Scientist & GPT-Researcher patterns — @SHL0MS ([#5421](https://github.com/NousResearch/hermes-agent/pull/5421))
- **blogwatcher** updated to JulienTant's fork ([#5759](https://github.com/NousResearch/hermes-agent/pull/5759))
- **claude-code skill** comprehensive rewrite v2.0 + v2.2 ([#5155](https://github.com/NousResearch/hermes-agent/pull/5155), [#5158](https://github.com/NousResearch/hermes-agent/pull/5158))
- **Code verification skills** consolidated into one ([#4854](https://github.com/NousResearch/hermes-agent/pull/4854))
- **Manim CE reference docs** expanded — geometry, animations, LaTeX — @leotrs ([#5791](https://github.com/NousResearch/hermes-agent/pull/5791))
- **Manim-video references** — design thinking, updaters, paper explainer, decorations, production quality — @SHL0MS ([#5588](https://github.com/NousResearch/hermes-agent/pull/5588), [#5408](https://github.com/NousResearch/hermes-agent/pull/5408))
---
## 🔒 Security & Reliability
### Security Hardening
- **Consolidated security** — SSRF protections, timing attack mitigations, tar traversal prevention, credential leakage guards ([#5944](https://github.com/NousResearch/hermes-agent/pull/5944))
- **Cross-session isolation** + cron path traversal hardening ([#5613](https://github.com/NousResearch/hermes-agent/pull/5613))
- **Workdir parameter sanitized** in terminal tool across all backends ([#5629](https://github.com/NousResearch/hermes-agent/pull/5629))
- **Approval 'once' session escalation** prevented + cron delivery platform validation ([#5280](https://github.com/NousResearch/hermes-agent/pull/5280))
- **Profile-scoped Google Workspace OAuth tokens** protected ([#4910](https://github.com/NousResearch/hermes-agent/pull/4910))
### Reliability
- **Aggressive worktree and branch cleanup** to prevent accumulation ([#6134](https://github.com/NousResearch/hermes-agent/pull/6134))
- **O(n²) catastrophic backtracking** in redact regex fixed — 100x improvement on large outputs ([#4962](https://github.com/NousResearch/hermes-agent/pull/4962))
- **Runtime stability fixes** across core, web, delegate, and browser tools ([#4843](https://github.com/NousResearch/hermes-agent/pull/4843))
- **API server streaming fix** + conversation history support ([#5977](https://github.com/NousResearch/hermes-agent/pull/5977))
- **OpenViking API endpoint paths** and response parsing corrected ([#5078](https://github.com/NousResearch/hermes-agent/pull/5078))
---
## 🐛 Notable Bug Fixes
- **9 community bugfixes salvaged** — gateway, cron, deps, macOS launchd in one batch ([#5288](https://github.com/NousResearch/hermes-agent/pull/5288))
- **Batch core bug fixes** — model config, session reset, alias fallback, launchctl, delegation, atomic writes ([#5630](https://github.com/NousResearch/hermes-agent/pull/5630))
- **Batch gateway/platform fixes** — matrix E2EE, CJK input, Windows browser, Feishu reconnect + ACL ([#5665](https://github.com/NousResearch/hermes-agent/pull/5665))
- **Stale test skips removed**, regex backtracking, file search bug, and test flakiness ([#4969](https://github.com/NousResearch/hermes-agent/pull/4969))
- **Nix flake** — read version, regen uv.lock, add hermes_logging — @alt-glitch ([#5651](https://github.com/NousResearch/hermes-agent/pull/5651))
- **Lowercase variable redaction** regression tests ([#5185](https://github.com/NousResearch/hermes-agent/pull/5185))
---
## 🧪 Testing
- **57 failing CI tests repaired** across 14 files ([#5823](https://github.com/NousResearch/hermes-agent/pull/5823))
- **Test suite re-architecture** + CI failure fixes — @alt-glitch ([#5946](https://github.com/NousResearch/hermes-agent/pull/5946))
- **Codebase-wide lint cleanup** — unused imports, dead code, and inefficient patterns ([#5821](https://github.com/NousResearch/hermes-agent/pull/5821))
- **browser_close tool removed** — auto-cleanup handles it ([#5792](https://github.com/NousResearch/hermes-agent/pull/5792))
---
## 📚 Documentation
- **Comprehensive documentation audit** — fix stale info, expand thin pages, add depth ([#5393](https://github.com/NousResearch/hermes-agent/pull/5393))
- **40+ discrepancies fixed** between documentation and codebase ([#5818](https://github.com/NousResearch/hermes-agent/pull/5818))
- **13 features documented** from last week's PRs ([#5815](https://github.com/NousResearch/hermes-agent/pull/5815))
- **Guides section overhaul** — fix existing + add 3 new tutorials ([#5735](https://github.com/NousResearch/hermes-agent/pull/5735))
- **Salvaged 4 docs PRs** — docker setup, post-update validation, local LLM guide, signal-cli install ([#5727](https://github.com/NousResearch/hermes-agent/pull/5727))
- **Discord configuration reference** ([#5386](https://github.com/NousResearch/hermes-agent/pull/5386))
- **Community FAQ entries** for common workflows and troubleshooting ([#4797](https://github.com/NousResearch/hermes-agent/pull/4797))
- **WSL2 networking guide** for local model servers ([#5616](https://github.com/NousResearch/hermes-agent/pull/5616))
- **Honcho CLI reference** + plugin CLI registration docs ([#5308](https://github.com/NousResearch/hermes-agent/pull/5308))
- **Obsidian Headless setup** for servers in llm-wiki ([#5660](https://github.com/NousResearch/hermes-agent/pull/5660))
- **Hermes Mod visual skin editor** added to skins page ([#6095](https://github.com/NousResearch/hermes-agent/pull/6095))
---
## 👥 Contributors
### Core
- **@teknium1** — 179 PRs
### Top Community Contributors
- **@SHL0MS** (7 PRs) — p5js creative coding skill, manim-video skill + 5 reference expansions, research-paper-writing, Nous OAuth fix, manim font fix
- **@alt-glitch** (3 PRs) — Firecrawl cloud browser provider, test re-architecture + CI fixes, Nix flake fixes
- **@benbarclay** (2 PRs) — Browser Use managed provider switch, Nous portal base URL fix
- **@CharlieKerfoot** (2 PRs) — macOS portable base64 encoding, thread-safe PairingStore
- **@WAXLYY** (2 PRs) — send_message secret redaction, gateway media URL sanitization
- **@MadKangYu** (2 PRs) — Telegram log noise reduction, context compaction fix for temperature-restricted models
### All Contributors
@alt-glitch, @austinpickett, @auspic7, @benbarclay, @CharlieKerfoot, @GratefulDave, @kshitijk4poor, @leotrs, @lumethegreat, @MadKangYu, @nericervin, @ryanautomated, @SHL0MS, @techguysimon, @tymrtn, @Vasanthdev2004, @WAXLYY, @xinbenlv
---
**Full Changelog**: [v2026.4.3...v2026.4.8](https://github.com/NousResearch/hermes-agent/compare/v2026.4.3...v2026.4.8)

View File

@@ -1,329 +0,0 @@
# Hermes Agent v0.9.0 (v2026.4.13)
**Release Date:** April 13, 2026
**Since v0.8.0:** 487 commits · 269 merged PRs · 167 resolved issues · 493 files changed · 63,281 insertions · 24 contributors
> The everywhere release — Hermes goes mobile with Termux/Android, adds iMessage and WeChat, ships Fast Mode for OpenAI and Anthropic, introduces background process monitoring, launches a local web dashboard for managing your agent, and delivers the deepest security hardening pass yet across 16 supported platforms.
---
## ✨ Highlights
- **Local Web Dashboard** — A new browser-based dashboard for managing your Hermes Agent locally. Configure settings, monitor sessions, browse skills, and manage your gateway — all from a clean web interface without touching config files or the terminal. The easiest way to get started with Hermes.
- **Fast Mode (`/fast`)** — Priority processing for OpenAI and Anthropic models. Toggle `/fast` to route through priority queues for significantly lower latency on supported models (GPT-5.4, Codex, Claude). Expands across all OpenAI Priority Processing models and Anthropic's fast tier. ([#6875](https://github.com/NousResearch/hermes-agent/pull/6875), [#6960](https://github.com/NousResearch/hermes-agent/pull/6960), [#7037](https://github.com/NousResearch/hermes-agent/pull/7037))
- **iMessage via BlueBubbles** — Full iMessage integration through BlueBubbles, bringing Hermes to Apple's messaging ecosystem. Auto-webhook registration, setup wizard integration, and crash resilience. ([#6437](https://github.com/NousResearch/hermes-agent/pull/6437), [#6460](https://github.com/NousResearch/hermes-agent/pull/6460), [#6494](https://github.com/NousResearch/hermes-agent/pull/6494))
- **WeChat (Weixin) & WeCom Callback Mode** — Native WeChat support via iLink Bot API and a new WeCom callback-mode adapter for self-built enterprise apps. Streaming cursor, media uploads, markdown link handling, and atomic state persistence. Hermes now covers the Chinese messaging ecosystem end-to-end. ([#7166](https://github.com/NousResearch/hermes-agent/pull/7166), [#7943](https://github.com/NousResearch/hermes-agent/pull/7943))
- **Termux / Android Support** — Run Hermes natively on Android via Termux. Adapted install paths, TUI optimizations for mobile screens, voice backend support, and the `/image` command work on-device. ([#6834](https://github.com/NousResearch/hermes-agent/pull/6834))
- **Background Process Monitoring (`watch_patterns`)** — Set patterns to watch for in background process output and get notified in real-time when they match. Monitor for errors, wait for specific events ("listening on port"), or watch build logs — all without polling. ([#7635](https://github.com/NousResearch/hermes-agent/pull/7635))
- **Native xAI & Xiaomi MiMo Providers** — First-class provider support for xAI (Grok) and Xiaomi MiMo, with direct API access, model catalogs, and setup wizard integration. Plus Qwen OAuth with portal request support. ([#7372](https://github.com/NousResearch/hermes-agent/pull/7372), [#7855](https://github.com/NousResearch/hermes-agent/pull/7855))
- **Pluggable Context Engine** — Context management is now a pluggable slot via `hermes plugins`. Swap in custom context engines that control what the agent sees each turn — filtering, summarization, or domain-specific context injection. ([#7464](https://github.com/NousResearch/hermes-agent/pull/7464))
- **Unified Proxy Support** — SOCKS proxy, `DISCORD_PROXY`, and system proxy auto-detection across all gateway platforms. Hermes behind corporate firewalls just works. ([#6814](https://github.com/NousResearch/hermes-agent/pull/6814))
- **Comprehensive Security Hardening** — Path traversal protection in checkpoint manager, shell injection neutralization in sandbox writes, SSRF redirect guards in Slack image uploads, Twilio webhook signature validation (SMS RCE fix), API server auth enforcement, git argument injection prevention, and approval button authorization. ([#7933](https://github.com/NousResearch/hermes-agent/pull/7933), [#7944](https://github.com/NousResearch/hermes-agent/pull/7944), [#7940](https://github.com/NousResearch/hermes-agent/pull/7940), [#7151](https://github.com/NousResearch/hermes-agent/pull/7151), [#7156](https://github.com/NousResearch/hermes-agent/pull/7156))
- **`hermes backup` & `hermes import`** — Full backup and restore of your Hermes configuration, sessions, skills, and memory. Migrate between machines or create snapshots before major changes. ([#7997](https://github.com/NousResearch/hermes-agent/pull/7997))
- **16 Supported Platforms** — With BlueBubbles (iMessage) and WeChat joining Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, SMS, DingTalk, Feishu, WeCom, Mattermost, Home Assistant, and Webhooks, Hermes now runs on 16 messaging platforms out of the box.
- **`/debug` & `hermes debug share`** — New debugging toolkit: `/debug` slash command across all platforms for quick diagnostics, plus `hermes debug share` to upload a full debug report to a pastebin for easy sharing when troubleshooting. ([#8681](https://github.com/NousResearch/hermes-agent/pull/8681))
---
## 🏗️ Core Agent & Architecture
### Provider & Model Support
- **Native xAI (Grok) provider** with direct API access and model catalog ([#7372](https://github.com/NousResearch/hermes-agent/pull/7372))
- **Xiaomi MiMo as first-class provider** — setup wizard, model catalog, empty response recovery ([#7855](https://github.com/NousResearch/hermes-agent/pull/7855))
- **Qwen OAuth provider** with portal request support ([#6282](https://github.com/NousResearch/hermes-agent/pull/6282))
- **Fast Mode** — `/fast` toggle for OpenAI Priority Processing + Anthropic fast tier ([#6875](https://github.com/NousResearch/hermes-agent/pull/6875), [#6960](https://github.com/NousResearch/hermes-agent/pull/6960), [#7037](https://github.com/NousResearch/hermes-agent/pull/7037))
- **Structured API error classification** for smart failover decisions ([#6514](https://github.com/NousResearch/hermes-agent/pull/6514))
- **Rate limit header capture** shown in `/usage` ([#6541](https://github.com/NousResearch/hermes-agent/pull/6541))
- **API server model name** derived from profile name ([#6857](https://github.com/NousResearch/hermes-agent/pull/6857))
- **Custom providers** now included in `/model` listings and resolution ([#7088](https://github.com/NousResearch/hermes-agent/pull/7088))
- **Fallback provider activation** on repeated empty responses with user-visible status ([#7505](https://github.com/NousResearch/hermes-agent/pull/7505))
- **OpenRouter variant tags** (`:free`, `:extended`, `:fast`) preserved during model switch ([#6383](https://github.com/NousResearch/hermes-agent/pull/6383))
- **Credential exhaustion TTL** reduced from 24 hours to 1 hour ([#6504](https://github.com/NousResearch/hermes-agent/pull/6504))
- **OAuth credential lifecycle** hardening — stale pool keys, auth.json sync, Codex CLI race fixes ([#6874](https://github.com/NousResearch/hermes-agent/pull/6874))
- Empty response recovery for reasoning models (MiMo, Qwen, GLM) ([#8609](https://github.com/NousResearch/hermes-agent/pull/8609))
- MiniMax context lengths, thinking guard, endpoint corrections ([#6082](https://github.com/NousResearch/hermes-agent/pull/6082), [#7126](https://github.com/NousResearch/hermes-agent/pull/7126))
- Z.AI endpoint auto-detect via probe and cache ([#5763](https://github.com/NousResearch/hermes-agent/pull/5763))
### Agent Loop & Conversation
- **Pluggable context engine slot** via `hermes plugins` ([#7464](https://github.com/NousResearch/hermes-agent/pull/7464))
- **Background process monitoring** — `watch_patterns` for real-time output alerts ([#7635](https://github.com/NousResearch/hermes-agent/pull/7635))
- **Improved context compression** — higher limits, tool tracking, degradation warnings, token-budget tail protection ([#6395](https://github.com/NousResearch/hermes-agent/pull/6395), [#6453](https://github.com/NousResearch/hermes-agent/pull/6453))
- **`/compress <focus>`** — guided compression with a focus topic ([#8017](https://github.com/NousResearch/hermes-agent/pull/8017))
- **Tiered context pressure warnings** with gateway dedup ([#6411](https://github.com/NousResearch/hermes-agent/pull/6411))
- **Staged inactivity warning** before timeout escalation ([#6387](https://github.com/NousResearch/hermes-agent/pull/6387))
- **Prevent agent from stopping mid-task** — compression floor, budget overhaul, activity tracking ([#7983](https://github.com/NousResearch/hermes-agent/pull/7983))
- **Propagate child activity to parent** during `delegate_task` ([#7295](https://github.com/NousResearch/hermes-agent/pull/7295))
- **Truncated streaming tool call detection** before execution ([#6847](https://github.com/NousResearch/hermes-agent/pull/6847))
- Empty response retry (3 attempts with nudge) ([#6488](https://github.com/NousResearch/hermes-agent/pull/6488))
- Adaptive streaming backoff + cursor strip to prevent message truncation ([#7683](https://github.com/NousResearch/hermes-agent/pull/7683))
- Compression uses live session model instead of stale persisted config ([#8258](https://github.com/NousResearch/hermes-agent/pull/8258))
- Strip `<thought>` tags from Gemma 4 responses ([#8562](https://github.com/NousResearch/hermes-agent/pull/8562))
- Prevent `<think>` in prose from suppressing response output ([#6968](https://github.com/NousResearch/hermes-agent/pull/6968))
- Turn-exit diagnostic logging to agent loop ([#6549](https://github.com/NousResearch/hermes-agent/pull/6549))
- Scope tool interrupt signal per-thread to prevent cross-session leaks ([#7930](https://github.com/NousResearch/hermes-agent/pull/7930))
### Memory & Sessions
- **Hindsight memory plugin** — feature parity, setup wizard, config improvements — @nicoloboschi ([#6428](https://github.com/NousResearch/hermes-agent/pull/6428))
- **Honcho** — opt-in `initOnSessionStart` for tools mode — @Kathie-yu ([#6995](https://github.com/NousResearch/hermes-agent/pull/6995))
- Orphan children instead of cascade-deleting in prune/delete ([#6513](https://github.com/NousResearch/hermes-agent/pull/6513))
- Doctor command only checks the active memory provider ([#6285](https://github.com/NousResearch/hermes-agent/pull/6285))
---
## 📱 Messaging Platforms (Gateway)
### New Platforms
- **BlueBubbles (iMessage)** — full adapter with auto-webhook registration, setup wizard, and crash resilience ([#6437](https://github.com/NousResearch/hermes-agent/pull/6437), [#6460](https://github.com/NousResearch/hermes-agent/pull/6460), [#6494](https://github.com/NousResearch/hermes-agent/pull/6494), [#7107](https://github.com/NousResearch/hermes-agent/pull/7107))
- **Weixin (WeChat)** — native support via iLink Bot API with streaming, media uploads, markdown links ([#7166](https://github.com/NousResearch/hermes-agent/pull/7166), [#8665](https://github.com/NousResearch/hermes-agent/pull/8665))
- **WeCom Callback Mode** — self-built enterprise app adapter with atomic state persistence ([#7943](https://github.com/NousResearch/hermes-agent/pull/7943), [#7928](https://github.com/NousResearch/hermes-agent/pull/7928))
### Discord
- **Allowed channels whitelist** config — @jarvis-phw ([#7044](https://github.com/NousResearch/hermes-agent/pull/7044))
- **Forum channel topic inheritance** in thread sessions — @hermes-agent-dhabibi ([#6377](https://github.com/NousResearch/hermes-agent/pull/6377))
- **DISCORD_REPLY_TO_MODE** setting ([#6333](https://github.com/NousResearch/hermes-agent/pull/6333))
- Accept `.log` attachments, raise document size limit — @kira-ariaki ([#6467](https://github.com/NousResearch/hermes-agent/pull/6467))
- Decouple readiness from slash sync ([#8016](https://github.com/NousResearch/hermes-agent/pull/8016))
### Slack
- **Consolidated Slack improvements** — 7 community PRs salvaged into one ([#6809](https://github.com/NousResearch/hermes-agent/pull/6809))
- Handle assistant thread lifecycle events ([#6433](https://github.com/NousResearch/hermes-agent/pull/6433))
### Matrix
- **Migrated from matrix-nio to mautrix-python** ([#7518](https://github.com/NousResearch/hermes-agent/pull/7518))
- SQLite crypto store replacing pickle (fixes E2EE decryption) — @alt-glitch ([#7981](https://github.com/NousResearch/hermes-agent/pull/7981))
- Cross-signing recovery key verification for E2EE migration ([#8282](https://github.com/NousResearch/hermes-agent/pull/8282))
- DM mention threads + group chat events for Feishu ([#7423](https://github.com/NousResearch/hermes-agent/pull/7423))
### Gateway Core
- **Unified proxy support** — SOCKS, DISCORD_PROXY, multi-platform with macOS auto-detection ([#6814](https://github.com/NousResearch/hermes-agent/pull/6814))
- **Inbound text batching** for Discord, Matrix, WeCom + adaptive delay ([#6979](https://github.com/NousResearch/hermes-agent/pull/6979))
- **Surface natural mid-turn assistant messages** in chat platforms ([#7978](https://github.com/NousResearch/hermes-agent/pull/7978))
- **WSL-aware gateway** with smart systemd detection ([#7510](https://github.com/NousResearch/hermes-agent/pull/7510))
- **All missing platforms added to setup wizard** ([#7949](https://github.com/NousResearch/hermes-agent/pull/7949))
- **Per-platform `tool_progress` overrides** ([#6348](https://github.com/NousResearch/hermes-agent/pull/6348))
- **Configurable 'still working' notification interval** ([#8572](https://github.com/NousResearch/hermes-agent/pull/8572))
- `/model` switch persists across messages ([#7081](https://github.com/NousResearch/hermes-agent/pull/7081))
- `/usage` shows rate limits, cost, and token details between turns ([#7038](https://github.com/NousResearch/hermes-agent/pull/7038))
- Drain in-flight work before restart ([#7503](https://github.com/NousResearch/hermes-agent/pull/7503))
- Don't evict cached agent on failed runs — prevents MCP restart loop ([#7539](https://github.com/NousResearch/hermes-agent/pull/7539))
- Replace `os.environ` session state with `contextvars` ([#7454](https://github.com/NousResearch/hermes-agent/pull/7454))
- Derive channel directory platforms from enum instead of hardcoded list ([#7450](https://github.com/NousResearch/hermes-agent/pull/7450))
- Validate image downloads before caching (cross-platform) ([#7125](https://github.com/NousResearch/hermes-agent/pull/7125))
- Cross-platform webhook delivery for all platforms ([#7095](https://github.com/NousResearch/hermes-agent/pull/7095))
- Cron Discord thread_id delivery support ([#7106](https://github.com/NousResearch/hermes-agent/pull/7106))
- Feishu QR-based bot onboarding ([#8570](https://github.com/NousResearch/hermes-agent/pull/8570))
- Gateway status scoped to active profile ([#7951](https://github.com/NousResearch/hermes-agent/pull/7951))
- Prevent background process notifications from triggering false pairing requests ([#6434](https://github.com/NousResearch/hermes-agent/pull/6434))
---
## 🖥️ CLI & User Experience
### Interactive CLI
- **Termux / Android support** — adapted install paths, TUI, voice, `/image` ([#6834](https://github.com/NousResearch/hermes-agent/pull/6834))
- **Native `/model` picker modal** for provider → model selection ([#8003](https://github.com/NousResearch/hermes-agent/pull/8003))
- **Live per-tool elapsed timer** restored in TUI spinner ([#7359](https://github.com/NousResearch/hermes-agent/pull/7359))
- **Stacked tool progress scrollback** in TUI ([#8201](https://github.com/NousResearch/hermes-agent/pull/8201))
- **Random tips on new session start** (CLI + gateway, 279 tips) ([#8225](https://github.com/NousResearch/hermes-agent/pull/8225), [#8237](https://github.com/NousResearch/hermes-agent/pull/8237))
- **`hermes dump`** — copy-pasteable setup summary for debugging ([#6550](https://github.com/NousResearch/hermes-agent/pull/6550))
- **`hermes backup` / `hermes import`** — full config backup and restore ([#7997](https://github.com/NousResearch/hermes-agent/pull/7997))
- **WSL environment hint** in system prompt ([#8285](https://github.com/NousResearch/hermes-agent/pull/8285))
- **Profile creation UX** — seed SOUL.md + credential warning ([#8553](https://github.com/NousResearch/hermes-agent/pull/8553))
- Shell-aware sudo detection, empty password support ([#6517](https://github.com/NousResearch/hermes-agent/pull/6517))
- Flush stdin after curses/terminal menus to prevent escape sequence leakage ([#7167](https://github.com/NousResearch/hermes-agent/pull/7167))
- Handle broken stdin in prompt_toolkit startup ([#8560](https://github.com/NousResearch/hermes-agent/pull/8560))
### Setup & Configuration
- **Per-platform display verbosity** configuration ([#8006](https://github.com/NousResearch/hermes-agent/pull/8006))
- **Component-separated logging** with session context and filtering ([#7991](https://github.com/NousResearch/hermes-agent/pull/7991))
- **`network.force_ipv4`** config to fix IPv6 timeout issues ([#8196](https://github.com/NousResearch/hermes-agent/pull/8196))
- **Standardize message whitespace and JSON formatting** ([#7988](https://github.com/NousResearch/hermes-agent/pull/7988))
- **Rebrand OpenClaw → Hermes** during migration ([#8210](https://github.com/NousResearch/hermes-agent/pull/8210))
- Config.yaml takes priority over env vars for auxiliary settings ([#7889](https://github.com/NousResearch/hermes-agent/pull/7889))
- Harden setup provider flows + live OpenRouter catalog refresh ([#7078](https://github.com/NousResearch/hermes-agent/pull/7078))
- Normalize reasoning effort ordering across all surfaces ([#6804](https://github.com/NousResearch/hermes-agent/pull/6804))
- Remove dead `LLM_MODEL` env var + migration to clear stale entries ([#6543](https://github.com/NousResearch/hermes-agent/pull/6543))
- Remove `/prompt` slash command — prefix expansion footgun ([#6752](https://github.com/NousResearch/hermes-agent/pull/6752))
- `HERMES_HOME_MODE` env var to override permissions — @ygd58 ([#6993](https://github.com/NousResearch/hermes-agent/pull/6993))
- Fall back to default model when model config is empty ([#8303](https://github.com/NousResearch/hermes-agent/pull/8303))
- Warn when compression model context is too small ([#7894](https://github.com/NousResearch/hermes-agent/pull/7894))
---
## 🔧 Tool System
### Environments & Execution
- **Unified spawn-per-call execution layer** for environments ([#6343](https://github.com/NousResearch/hermes-agent/pull/6343))
- **Unified file sync** with mtime tracking, deletion, and transactional state ([#7087](https://github.com/NousResearch/hermes-agent/pull/7087))
- **Persistent sandbox envs** survive between turns ([#6412](https://github.com/NousResearch/hermes-agent/pull/6412))
- **Bulk file sync** via tar pipe for SSH/Modal backends — @alt-glitch ([#8014](https://github.com/NousResearch/hermes-agent/pull/8014))
- **Daytona** — bulk upload, config bridge, silent disk cap ([#7538](https://github.com/NousResearch/hermes-agent/pull/7538))
- Foreground timeout cap to prevent session deadlocks ([#7082](https://github.com/NousResearch/hermes-agent/pull/7082))
- Guard invalid command values ([#6417](https://github.com/NousResearch/hermes-agent/pull/6417))
### MCP
- **`hermes mcp add --env` and `--preset`** support ([#7970](https://github.com/NousResearch/hermes-agent/pull/7970))
- Combine `content` and `structuredContent` when both present ([#7118](https://github.com/NousResearch/hermes-agent/pull/7118))
- MCP tool name deconfliction fixes ([#7654](https://github.com/NousResearch/hermes-agent/pull/7654))
### Browser
- Browser hardening — dead code removal, caching, scroll perf, security, thread safety ([#7354](https://github.com/NousResearch/hermes-agent/pull/7354))
- `/browser connect` auto-launch uses dedicated Chrome profile dir ([#6821](https://github.com/NousResearch/hermes-agent/pull/6821))
- Reap orphaned browser sessions on startup ([#7931](https://github.com/NousResearch/hermes-agent/pull/7931))
### Voice & Vision
- **Voxtral TTS provider** (Mistral AI) ([#7653](https://github.com/NousResearch/hermes-agent/pull/7653))
- **TTS speed support** for Edge TTS, OpenAI TTS, MiniMax ([#8666](https://github.com/NousResearch/hermes-agent/pull/8666))
- **Vision auto-resize** for oversized images, raise limit to 20 MB, retry-on-failure ([#7883](https://github.com/NousResearch/hermes-agent/pull/7883), [#7902](https://github.com/NousResearch/hermes-agent/pull/7902))
- STT provider-model mismatch fix (whisper-1 vs faster-whisper) ([#7113](https://github.com/NousResearch/hermes-agent/pull/7113))
### Other Tools
- **`hermes dump`** command for setup summary ([#6550](https://github.com/NousResearch/hermes-agent/pull/6550))
- TODO store enforces ID uniqueness during replace operations ([#7986](https://github.com/NousResearch/hermes-agent/pull/7986))
- List all available toolsets in `delegate_task` schema description ([#8231](https://github.com/NousResearch/hermes-agent/pull/8231))
- API server: tool progress as custom SSE event to prevent model corruption ([#7500](https://github.com/NousResearch/hermes-agent/pull/7500))
- API server: share one Docker container across all conversations ([#7127](https://github.com/NousResearch/hermes-agent/pull/7127))
---
## 🧩 Skills Ecosystem
- **Centralized skills index + tree cache** — eliminates rate-limit failures on install ([#8575](https://github.com/NousResearch/hermes-agent/pull/8575))
- **More aggressive skill loading instructions** in system prompt (v3) ([#8209](https://github.com/NousResearch/hermes-agent/pull/8209), [#8286](https://github.com/NousResearch/hermes-agent/pull/8286))
- **Google Workspace skill** migrated to GWS CLI backend ([#6788](https://github.com/NousResearch/hermes-agent/pull/6788))
- **Creative divergence strategies** skill — @SHL0MS ([#6882](https://github.com/NousResearch/hermes-agent/pull/6882))
- **Creative ideation** — constraint-driven project generation — @SHL0MS ([#7555](https://github.com/NousResearch/hermes-agent/pull/7555))
- Parallelize skills browse/search to prevent hanging ([#7301](https://github.com/NousResearch/hermes-agent/pull/7301))
- Read name from SKILL.md frontmatter in skills_sync ([#7623](https://github.com/NousResearch/hermes-agent/pull/7623))
---
## 🔒 Security & Reliability
### Security Hardening
- **Twilio webhook signature validation** — SMS RCE fix ([#7933](https://github.com/NousResearch/hermes-agent/pull/7933))
- **Shell injection neutralization** in `_write_to_sandbox` via path quoting ([#7940](https://github.com/NousResearch/hermes-agent/pull/7940))
- **Git argument injection** and path traversal prevention in checkpoint manager ([#7944](https://github.com/NousResearch/hermes-agent/pull/7944))
- **SSRF redirect bypass** in Slack image uploads + base.py cache helpers ([#7151](https://github.com/NousResearch/hermes-agent/pull/7151))
- **Path traversal, credential gate, DANGEROUS_PATTERNS gaps** ([#7156](https://github.com/NousResearch/hermes-agent/pull/7156))
- **API bind guard** — enforce `API_SERVER_KEY` for non-loopback binding ([#7455](https://github.com/NousResearch/hermes-agent/pull/7455))
- **Approval button authorization** — require auth for session continuation — @Cafexss ([#6930](https://github.com/NousResearch/hermes-agent/pull/6930))
- Path boundary enforcement in skill manager operations ([#7156](https://github.com/NousResearch/hermes-agent/pull/7156))
- DingTalk/API webhook URL origin validation, header injection rejection ([#7455](https://github.com/NousResearch/hermes-agent/pull/7455))
### Reliability
- **Contextual error diagnostics** for invalid API responses ([#8565](https://github.com/NousResearch/hermes-agent/pull/8565))
- **Prevent 400 format errors** from triggering compression loop on Codex ([#6751](https://github.com/NousResearch/hermes-agent/pull/6751))
- **Don't halve context_length** on output-cap-too-large errors — @KUSH42 ([#6664](https://github.com/NousResearch/hermes-agent/pull/6664))
- **Recover primary client** on OpenAI transport errors ([#7108](https://github.com/NousResearch/hermes-agent/pull/7108))
- **Credential pool rotation** on billing-classified 400s ([#7112](https://github.com/NousResearch/hermes-agent/pull/7112))
- **Auto-increase stream read timeout** for local LLM providers ([#6967](https://github.com/NousResearch/hermes-agent/pull/6967))
- **Fall back to default certs** when CA bundle path doesn't exist ([#7352](https://github.com/NousResearch/hermes-agent/pull/7352))
- **Disambiguate usage-limit patterns** in error classifier — @sprmn24 ([#6836](https://github.com/NousResearch/hermes-agent/pull/6836))
- Harden cron script timeout and provider recovery ([#7079](https://github.com/NousResearch/hermes-agent/pull/7079))
- Gateway interrupt detection resilient to monitor task failures ([#8208](https://github.com/NousResearch/hermes-agent/pull/8208))
- Prevent unwanted session auto-reset after graceful gateway restarts ([#8299](https://github.com/NousResearch/hermes-agent/pull/8299))
- Prevent duplicate update prompt spam in gateway watcher ([#8343](https://github.com/NousResearch/hermes-agent/pull/8343))
- Deduplicate reasoning items in Responses API input ([#7946](https://github.com/NousResearch/hermes-agent/pull/7946))
### Infrastructure
- **Multi-arch Docker image** — amd64 + arm64 ([#6124](https://github.com/NousResearch/hermes-agent/pull/6124))
- **Docker runs as non-root user** with virtualenv — @benbarclay contributing ([#8226](https://github.com/NousResearch/hermes-agent/pull/8226))
- **Use `uv`** for Docker dependency resolution to fix resolution-too-deep ([#6965](https://github.com/NousResearch/hermes-agent/pull/6965))
- **Container-aware Nix CLI** — auto-route into managed container — @alt-glitch ([#7543](https://github.com/NousResearch/hermes-agent/pull/7543))
- **Nix shared-state permission model** for interactive CLI users — @alt-glitch ([#6796](https://github.com/NousResearch/hermes-agent/pull/6796))
- **Per-profile subprocess HOME isolation** ([#7357](https://github.com/NousResearch/hermes-agent/pull/7357))
- Profile paths fixed in Docker — profiles go to mounted volume ([#7170](https://github.com/NousResearch/hermes-agent/pull/7170))
- Docker container gateway pathway hardened ([#8614](https://github.com/NousResearch/hermes-agent/pull/8614))
- Enable unbuffered stdout for live Docker logs ([#6749](https://github.com/NousResearch/hermes-agent/pull/6749))
- Install procps in Docker image — @HiddenPuppy ([#7032](https://github.com/NousResearch/hermes-agent/pull/7032))
- Shallow git clone for faster installation — @sosyz ([#8396](https://github.com/NousResearch/hermes-agent/pull/8396))
- `hermes update` always reset on stash conflict ([#7010](https://github.com/NousResearch/hermes-agent/pull/7010))
- Write update exit code before gateway restart (cgroup kill race) ([#8288](https://github.com/NousResearch/hermes-agent/pull/8288))
- Nix: `setupSecrets` optional, tirith runtime dep — @devorun, @ethernet8023 ([#6261](https://github.com/NousResearch/hermes-agent/pull/6261), [#6721](https://github.com/NousResearch/hermes-agent/pull/6721))
- launchd stop uses `bootout` so `KeepAlive` doesn't respawn ([#7119](https://github.com/NousResearch/hermes-agent/pull/7119))
---
## 🐛 Notable Bug Fixes
- Fix: `/model` switch not persisting across gateway messages ([#7081](https://github.com/NousResearch/hermes-agent/pull/7081))
- Fix: session-scoped gateway model overrides ignored — @Hygaard ([#7662](https://github.com/NousResearch/hermes-agent/pull/7662))
- Fix: compaction model context length ignoring config — 3 related issues ([#8258](https://github.com/NousResearch/hermes-agent/pull/8258), [#8107](https://github.com/NousResearch/hermes-agent/pull/8107))
- Fix: OpenCode.ai context window resolved to 128K instead of 1M ([#6472](https://github.com/NousResearch/hermes-agent/pull/6472))
- Fix: Codex fallback auth-store lookup — @cherifya ([#6462](https://github.com/NousResearch/hermes-agent/pull/6462))
- Fix: duplicate completion notifications when process killed ([#7124](https://github.com/NousResearch/hermes-agent/pull/7124))
- Fix: agent daemon thread prevents orphan CLI processes on tab close ([#8557](https://github.com/NousResearch/hermes-agent/pull/8557))
- Fix: stale image attachment on text paste and voice input ([#7077](https://github.com/NousResearch/hermes-agent/pull/7077))
- Fix: DM thread session seeding causing cross-thread contamination ([#7084](https://github.com/NousResearch/hermes-agent/pull/7084))
- Fix: OpenClaw migration shows dry-run preview before executing ([#6769](https://github.com/NousResearch/hermes-agent/pull/6769))
- Fix: auth errors misclassified as retryable — @kuishou68 ([#7027](https://github.com/NousResearch/hermes-agent/pull/7027))
- Fix: Copilot-Integration-Id header missing ([#7083](https://github.com/NousResearch/hermes-agent/pull/7083))
- Fix: ACP session capabilities — @luyao618 ([#6985](https://github.com/NousResearch/hermes-agent/pull/6985))
- Fix: ACP PromptResponse usage from top-level fields ([#7086](https://github.com/NousResearch/hermes-agent/pull/7086))
- Fix: several failing/flaky tests on main — @dsocolobsky ([#6777](https://github.com/NousResearch/hermes-agent/pull/6777))
- Fix: backup marker filenames — @sprmn24 ([#8600](https://github.com/NousResearch/hermes-agent/pull/8600))
- Fix: `NoneType` in fast_mode check — @0xbyt4 ([#7350](https://github.com/NousResearch/hermes-agent/pull/7350))
- Fix: missing imports in uninstall.py — @JiayuuWang ([#7034](https://github.com/NousResearch/hermes-agent/pull/7034))
---
## 📚 Documentation
- Platform adapter developer guide + WeCom Callback docs ([#7969](https://github.com/NousResearch/hermes-agent/pull/7969))
- Cron troubleshooting guide ([#7122](https://github.com/NousResearch/hermes-agent/pull/7122))
- Streaming timeout auto-detection for local LLMs ([#6990](https://github.com/NousResearch/hermes-agent/pull/6990))
- Tool-use enforcement documentation expanded ([#7984](https://github.com/NousResearch/hermes-agent/pull/7984))
- BlueBubbles pairing instructions ([#6548](https://github.com/NousResearch/hermes-agent/pull/6548))
- Telegram proxy support section ([#6348](https://github.com/NousResearch/hermes-agent/pull/6348))
- `hermes dump` and `hermes logs` CLI reference ([#6552](https://github.com/NousResearch/hermes-agent/pull/6552))
- `tool_progress_overrides` configuration reference ([#6364](https://github.com/NousResearch/hermes-agent/pull/6364))
- Compression model context length warning docs ([#7879](https://github.com/NousResearch/hermes-agent/pull/7879))
---
## 👥 Contributors
**269 merged PRs** from **24 contributors** across **487 commits**.
### Community Contributors
- **@alt-glitch** (6 PRs) — Nix container-aware CLI, shared-state permissions, Matrix SQLite crypto store, bulk SSH/Modal file sync, Matrix mautrix compat
- **@SHL0MS** (2 PRs) — Creative divergence strategies skill, creative ideation skill
- **@sprmn24** (2 PRs) — Error classifier disambiguation, backup marker fix
- **@nicoloboschi** — Hindsight memory plugin feature parity
- **@Hygaard** — Session-scoped gateway model override fix
- **@jarvis-phw** — Discord allowed_channels whitelist
- **@Kathie-yu** — Honcho initOnSessionStart for tools mode
- **@hermes-agent-dhabibi** — Discord forum channel topic inheritance
- **@kira-ariaki** — Discord .log attachments and size limit
- **@cherifya** — Codex fallback auth-store lookup
- **@Cafexss** — Security: auth for session continuation
- **@KUSH42** — Compaction context_length fix
- **@kuishou68** — Auth error retryable classification fix
- **@luyao618** — ACP session capabilities
- **@ygd58** — HERMES_HOME_MODE env var override
- **@0xbyt4** — Fast mode NoneType fix
- **@JiayuuWang** — CLI uninstall import fix
- **@HiddenPuppy** — Docker procps installation
- **@dsocolobsky** — Test suite fixes
- **@bobashopcashier** (1 PR) — Graceful gateway drain before restart (salvaged into #7503 from #7290)
- **@benbarclay** — Docker image tag simplification
- **@sosyz** — Shallow git clone for faster install
- **@devorun** — Nix setupSecrets optional
- **@ethernet8023** — Nix tirith runtime dep
---
**Full Changelog**: [v2026.4.8...v2026.4.13](https://github.com/NousResearch/hermes-agent/compare/v2026.4.8...v2026.4.13)

View File

@@ -47,6 +47,20 @@ def _ra():
return run_agent
AGENT_RUNTIME_POST_HOOK_TOOL_NAMES = frozenset(
{"todo", "session_search", "memory", "clarify", "delegate_task"}
)
def agent_runtime_owns_post_tool_hook(agent: Any, function_name: str) -> bool:
"""Return True when an agent-level tool path emits its own post hook."""
if function_name in AGENT_RUNTIME_POST_HOOK_TOOL_NAMES:
return True
if getattr(agent, "_context_engine_tool_names", None) and function_name in agent._context_engine_tool_names:
return True
memory_manager = getattr(agent, "_memory_manager", None)
return bool(memory_manager and memory_manager.has_tool(function_name))
def convert_to_trajectory_format(agent, messages: List[Dict[str, Any]], user_query: str, completed: bool) -> List[Dict[str, Any]]:
"""
@@ -1618,36 +1632,84 @@ def invoke_tool(agent, function_name: str, function_args: dict, effective_task_i
try:
from hermes_cli.plugins import get_pre_tool_call_block_message
block_message = get_pre_tool_call_block_message(
function_name, function_args, task_id=effective_task_id or "",
function_name,
function_args,
task_id=effective_task_id or "",
session_id=getattr(agent, "session_id", "") or "",
tool_call_id=tool_call_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
)
except Exception:
pass
if block_message is not None:
return json.dumps({"error": block_message}, ensure_ascii=False)
result = json.dumps({"error": block_message}, ensure_ascii=False)
try:
from model_tools import _emit_post_tool_call_hook
_emit_post_tool_call_hook(
function_name=function_name,
function_args=function_args,
result=result,
task_id=effective_task_id or "",
session_id=getattr(agent, "session_id", "") or "",
tool_call_id=tool_call_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
status="blocked",
error_type="plugin_block",
error_message=block_message,
)
except Exception:
pass
return result
tool_start_time = time.monotonic()
def _finish_agent_tool(result: Any) -> Any:
try:
from model_tools import _emit_post_tool_call_hook
_emit_post_tool_call_hook(
function_name=function_name,
function_args=function_args,
result=result,
task_id=effective_task_id or "",
session_id=getattr(agent, "session_id", "") or "",
tool_call_id=tool_call_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
duration_ms=int((time.monotonic() - tool_start_time) * 1000),
)
except Exception:
pass
return result
if function_name == "todo":
from tools.todo_tool import todo_tool as _todo_tool
return _todo_tool(
todos=function_args.get("todos"),
merge=function_args.get("merge", False),
store=agent._todo_store,
return _finish_agent_tool(
_todo_tool(
todos=function_args.get("todos"),
merge=function_args.get("merge", False),
store=agent._todo_store,
)
)
elif function_name == "session_search":
session_db = agent._get_session_db_for_recall()
if not session_db:
from hermes_state import format_session_db_unavailable
return json.dumps({"success": False, "error": format_session_db_unavailable()})
return _finish_agent_tool(json.dumps({"success": False, "error": format_session_db_unavailable()}))
from tools.session_search_tool import session_search as _session_search
return _session_search(
query=function_args.get("query", ""),
role_filter=function_args.get("role_filter"),
limit=function_args.get("limit", 3),
session_id=function_args.get("session_id"),
around_message_id=function_args.get("around_message_id"),
window=function_args.get("window", 5),
sort=function_args.get("sort"),
db=session_db,
current_session_id=agent.session_id,
return _finish_agent_tool(
_session_search(
query=function_args.get("query", ""),
role_filter=function_args.get("role_filter"),
limit=function_args.get("limit", 3),
session_id=function_args.get("session_id"),
around_message_id=function_args.get("around_message_id"),
window=function_args.get("window", 5),
sort=function_args.get("sort"),
db=session_db,
current_session_id=agent.session_id,
)
)
elif function_name == "memory":
target = function_args.get("target", "memory")
@@ -1673,23 +1735,27 @@ def invoke_tool(agent, function_name: str, function_args: dict, effective_task_i
)
except Exception:
pass
return result
return _finish_agent_tool(result)
elif agent._memory_manager and agent._memory_manager.has_tool(function_name):
return agent._memory_manager.handle_tool_call(function_name, function_args)
return _finish_agent_tool(agent._memory_manager.handle_tool_call(function_name, function_args))
elif function_name == "clarify":
from tools.clarify_tool import clarify_tool as _clarify_tool
return _clarify_tool(
question=function_args.get("question", ""),
choices=function_args.get("choices"),
callback=agent.clarify_callback,
return _finish_agent_tool(
_clarify_tool(
question=function_args.get("question", ""),
choices=function_args.get("choices"),
callback=agent.clarify_callback,
)
)
elif function_name == "delegate_task":
return agent._dispatch_delegate_task(function_args)
return _finish_agent_tool(agent._dispatch_delegate_task(function_args))
else:
return _ra().handle_function_call(
function_name, function_args, effective_task_id,
tool_call_id=tool_call_id,
session_id=agent.session_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
enabled_tools=list(agent.valid_tool_names) if agent.valid_tool_names else None,
skip_pre_tool_call_hook=True,
enabled_toolsets=getattr(agent, "enabled_toolsets", None),

View File

@@ -1621,6 +1621,47 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
)
def _refresh_nous_recommended_model(
*, vision: bool, stale_model: Optional[str]
) -> Optional[str]:
"""Re-fetch the Nous Portal's recommended model after a stale-model 404.
Long-lived processes (gateway, watchers) cache the Portal's
``recommended-models`` payload for 10 minutes and, in practice, can pin a
model for the whole process lifetime. When that model is later dropped from
the Nous → OpenRouter catalog, every auxiliary call 404s with
"model does not exist". This forces a fresh Portal fetch and returns a
model name to retry with:
* the Portal's current recommendation for the task, if it differs from
the model that just failed; otherwise
* ``_NOUS_MODEL`` (google/gemini-3-flash-preview), the known-good default,
if it too differs from the failed model.
Returns ``None`` when no usable alternative is available (e.g. the Portal
still recommends the exact model that just 404'd and the default also
matches it) — callers should then let the original error propagate.
"""
stale = (stale_model or "").strip().lower()
fresh: Optional[str] = None
try:
from hermes_cli.models import get_nous_recommended_aux_model
fresh = get_nous_recommended_aux_model(vision=vision, force_refresh=True)
except Exception as exc:
logger.debug(
"Nous recommended-model refresh failed (%s); using default %s",
exc, _NOUS_MODEL,
)
if fresh and fresh.strip().lower() != stale:
return fresh
# Portal recommendation unchanged or unavailable — fall back to the
# hardcoded known-good default, but only if it's actually different.
if _NOUS_MODEL.strip().lower() != stale:
return _NOUS_MODEL
return None
def _read_main_model() -> str:
"""Read the user's configured main model from config.yaml.
@@ -2451,6 +2492,46 @@ def _is_unsupported_temperature_error(exc: Exception) -> bool:
return _is_unsupported_parameter_error(exc, "temperature")
def _is_model_not_found_error(exc: Exception) -> bool:
"""Detect "the requested model doesn't exist" errors (404 / invalid model).
This fires when a resolved model name is no longer served by the endpoint
— most commonly when a long-lived process pinned a Portal-recommended model
that has since been dropped from the Nous → OpenRouter catalog. The Nous
proxy returns 404 with a body like::
Model 'gpt-5.4-mini' not found. The requested model does not exist
in our configuration or OpenRouter catalog.
Distinct from :func:`_is_payment_error` (which also matches some 404s for
free-tier/credit language) — this one keys on "does not exist / not found /
not a valid model" phrasing, and explicitly excludes the billing keywords
that the payment path already owns so the two predicates don't overlap.
"""
status = getattr(exc, "status_code", None)
err_lower = str(exc).lower()
# Billing/quota 404s belong to _is_payment_error — don't claim them here.
if any(kw in err_lower for kw in (
"credits", "insufficient funds", "billing", "out of funds",
"balance_depleted", "no usable credits", "free tier", "free-tier",
"not available on the free tier",
)):
return False
if status not in {404, 400, None}:
return False
return any(kw in err_lower for kw in (
"model does not exist",
"does not exist in our configuration",
"openrouter catalog",
"is not a valid model",
"no such model",
"model not found",
"the model `", # OpenAI-style: "The model `X` does not exist"
"model_not_found",
"unknown model",
))
def _evict_cached_clients(provider: str) -> None:
"""Drop cached auxiliary clients for a provider so fresh creds are used."""
normalized = _normalize_aux_provider(provider)
@@ -5027,6 +5108,32 @@ def call_llm(
raise
first_err = retry_err
# ── Stale-model self-heal (Nous Portal recommendation drift) ───
# A long-lived process can pin a Portal-recommended model that has
# since been dropped from the Nous → OpenRouter catalog, so every
# auxiliary call 404s with "model does not exist". Force a fresh
# Portal fetch and retry once with the current recommendation (or the
# known-good default). Only applies to Nous-routed calls.
_heal_is_nous = (
resolved_provider == "nous"
or base_url_host_matches(_base_info, "inference-api.nousresearch.com")
)
if _is_model_not_found_error(first_err) and _heal_is_nous:
healed_model = _refresh_nous_recommended_model(
vision=(task == "vision"), stale_model=kwargs.get("model"))
if healed_model and healed_model != kwargs.get("model"):
logger.warning(
"Auxiliary %s: model %r no longer in Nous catalog; "
"retrying with refreshed recommendation %r",
task or "call", kwargs.get("model"), healed_model,
)
kwargs["model"] = healed_model
try:
return _validate_llm_response(
client.chat.completions.create(**kwargs), task)
except Exception as retry_err:
first_err = retry_err
# ── Nous auth refresh parity with main agent ──────────────────
client_is_nous = (
resolved_provider == "nous"
@@ -5464,6 +5571,31 @@ async def async_call_llm(
raise
first_err = retry_err
# ── Stale-model self-heal (Nous Portal recommendation drift) ───
# See the sync call_llm() path for the rationale: a long-lived process
# can pin a Portal-recommended model that has since been dropped from
# the Nous → OpenRouter catalog, 404'ing every auxiliary call. Force a
# fresh Portal fetch and retry once with the current recommendation.
_heal_is_nous = (
resolved_provider == "nous"
or base_url_host_matches(_client_base, "inference-api.nousresearch.com")
)
if _is_model_not_found_error(first_err) and _heal_is_nous:
healed_model = _refresh_nous_recommended_model(
vision=(task == "vision"), stale_model=kwargs.get("model"))
if healed_model and healed_model != kwargs.get("model"):
logger.warning(
"Auxiliary %s (async): model %r no longer in Nous catalog; "
"retrying with refreshed recommendation %r",
task or "call", kwargs.get("model"), healed_model,
)
kwargs["model"] = healed_model
try:
return _validate_llm_response(
await client.chat.completions.create(**kwargs), task)
except Exception as retry_err:
first_err = retry_err
# ── Nous auth refresh parity with main agent ──────────────────
client_is_nous = (
resolved_provider == "nous"

View File

@@ -1296,7 +1296,7 @@ def handle_max_iterations(agent, messages: list, api_call_count: int) -> str:
for internal_key in [k for k in api_msg if isinstance(k, str) and k.startswith("_")]:
api_msg.pop(internal_key, None)
if _needs_sanitize:
agent._sanitize_tool_calls_for_strict_api(api_msg)
agent._sanitize_tool_calls_for_strict_api(api_msg, model=agent.model)
api_messages.append(api_msg)
effective_system = agent._cached_system_prompt or ""

View File

@@ -308,11 +308,14 @@ def compress_context(
# The check itself sets ``agent._compression_warning`` so the
# status-callback replay machinery still emits the warning to the user
# the first time it would matter.
if not getattr(agent, "_compression_feasibility_checked", True):
try:
check_compression_model_feasibility(agent)
finally:
agent._compression_feasibility_checked = True
if not getattr(agent, "_compression_feasibility_checked", False):
# Mark as checked only after the probe completes. If the check
# raises (e.g. a fatal aux-context ValueError that aborts the
# session), leaving the flag unset is harmless; a non-fatal
# transient failure is swallowed inside the function so the flag
# is set normally on the next successful pass.
check_compression_model_feasibility(agent)
agent._compression_feasibility_checked = True
_pre_msg_count = len(messages)
logger.info(

View File

@@ -435,6 +435,9 @@ def run_conversation(
# state registry. Set BEFORE any tool dispatch so snapshots taken at
# child-launch time see the parent's real id, not None.
agent._current_task_id = effective_task_id
turn_id = f"{agent.session_id or 'session'}:{effective_task_id}:{uuid.uuid4().hex[:8]}"
agent._current_turn_id = turn_id
agent._current_api_request_id = ""
# Reset retry counters and iteration budget at the start of each turn
# so subagent usage from a previous turn doesn't eat into the next one.
@@ -702,6 +705,8 @@ def run_conversation(
_pre_results = _invoke_hook(
"pre_llm_call",
session_id=agent.session_id,
task_id=effective_task_id,
turn_id=turn_id,
user_message=original_user_message,
conversation_history=list(messages),
is_first_turn=(not bool(conversation_history)),
@@ -977,7 +982,7 @@ def run_conversation(
# Uses new dicts so the internal messages list retains the fields
# for Codex Responses compatibility.
if agent._should_sanitize_tool_calls():
agent._sanitize_tool_calls_for_strict_api(api_msg)
agent._sanitize_tool_calls_for_strict_api(api_msg, model=agent.model)
# Keep 'reasoning_details' - OpenRouter uses this for multi-turn reasoning context
# The signature field helps maintain reasoning continuity
api_messages.append(api_msg)
@@ -1153,6 +1158,8 @@ def run_conversation(
finish_reason = "stop"
response = None # Guard against UnboundLocalError if all retries fail
api_kwargs = None # Guard against UnboundLocalError in except handler
api_request_id = f"{turn_id}:api:{api_call_count}"
agent._current_api_request_id = api_request_id
while retry_count < max_retries:
# ── Nous Portal rate limit guard ──────────────────────
@@ -1220,37 +1227,58 @@ def run_conversation(
api_kwargs = agent._get_transport().preflight_kwargs(api_kwargs, allow_stream=False)
try:
from hermes_cli.plugins import invoke_hook as _invoke_hook
request_messages = api_kwargs.get("messages")
if not isinstance(request_messages, list):
request_messages = api_kwargs.get("input")
if not isinstance(request_messages, list):
request_messages = api_messages
# Shallow-copy the outer list so plugins that retain the
# reference for async snapshotting don't observe later
# mutations of api_messages. The inner dicts are not
# mutated by the agent loop, so a shallow copy is
# sufficient; a deepcopy would walk every tool result
# and base64 image on every API call.
_invoke_hook(
"pre_api_request",
task_id=effective_task_id,
session_id=agent.session_id or "",
user_message=original_user_message,
conversation_history=list(messages),
platform=agent.platform or "",
model=agent.model,
provider=agent.provider,
base_url=agent.base_url,
api_mode=agent.api_mode,
api_call_count=api_call_count,
request_messages=list(request_messages) if isinstance(request_messages, list) else [],
message_count=len(api_messages),
tool_count=len(agent.tools or []),
approx_input_tokens=approx_tokens,
request_char_count=total_chars,
max_tokens=agent.max_tokens,
from hermes_cli.plugins import (
has_hook,
invoke_hook as _invoke_hook,
)
if has_hook("pre_api_request"):
request_messages = api_kwargs.get("messages")
if not isinstance(request_messages, list):
request_messages = api_kwargs.get("input")
if not isinstance(request_messages, list):
request_messages = api_messages
# Shallow-copy the outer list so plugins that retain the
# reference for async snapshotting don't observe later
# mutations of api_messages. The inner dicts are not
# mutated by the agent loop, so a shallow copy is
# sufficient; a deepcopy would walk every tool result
# and base64 image on every API call.
#
# The ``request_messages`` and ``conversation_history``
# kwargs below are pre-existing raw passthroughs
# consumed by the bundled langfuse plugin
# (``plugins/observability/langfuse/__init__.py:_coerce_request_messages``).
# They predate ``request`` and are intentionally NOT
# sanitised — secrets are not expected here because
# ``api_kwargs`` is the same object passed to the
# provider client. New consumers should read the
# sanitised view from ``request["body"]["messages"]``.
_request_payload = agent._api_request_payload_for_hook(api_kwargs)
_invoke_hook(
"pre_api_request",
task_id=effective_task_id,
turn_id=turn_id,
api_request_id=api_request_id,
session_id=agent.session_id or "",
user_message=original_user_message,
conversation_history=list(messages),
platform=agent.platform or "",
model=agent.model,
provider=agent.provider,
base_url=agent.base_url,
api_mode=agent.api_mode,
api_call_count=api_call_count,
request_messages=list(request_messages)
if isinstance(request_messages, list)
else [],
message_count=len(api_messages),
tool_count=len(agent.tools or []),
approx_input_tokens=approx_tokens,
request_char_count=total_chars,
max_tokens=agent.max_tokens,
started_at=api_start_time,
request=_request_payload,
)
except Exception:
pass
@@ -1300,12 +1328,14 @@ def run_conversation(
if isinstance(getattr(agent, "client", None), Mock):
_use_streaming = False
if _use_streaming:
response = agent._interruptible_streaming_api_call(
api_kwargs, on_first_delta=_stop_spinner
)
else:
response = agent._interruptible_api_call(api_kwargs)
def _perform_api_call(next_api_kwargs):
if _use_streaming:
return agent._interruptible_streaming_api_call(
next_api_kwargs, on_first_delta=_stop_spinner
)
return agent._interruptible_api_call(next_api_kwargs)
response = _perform_api_call(api_kwargs)
api_duration = time.time() - api_start_time
@@ -1406,6 +1436,21 @@ def run_conversation(
error_details.append("response.choices is empty")
if response_invalid:
agent._invoke_api_request_error_hook(
task_id=effective_task_id,
turn_id=turn_id,
api_request_id=api_request_id,
api_call_count=api_call_count,
api_start_time=api_start_time,
api_kwargs=api_kwargs,
error_type="InvalidAPIResponse",
error_message=", ".join(error_details) or "Invalid API response",
status_code=getattr(getattr(response, "error", None), "code", None),
retry_count=retry_count,
max_retries=max_retries,
retryable=True,
reason="invalid_response",
)
# Stop spinner silently — retry status is now buffered
# and only surfaced if every retry+fallback exhausts.
if thinking_spinner:
@@ -1739,20 +1784,52 @@ def run_conversation(
if agent.api_mode in {"chat_completions", "bedrock_converse", "anthropic_messages"}:
assistant_message = _trunc_msg
if assistant_message is not None and _trunc_has_tool_calls:
if truncated_tool_call_retries < 1:
_is_stub_stall = (
getattr(response, "id", "") == PARTIAL_STREAM_STUB_ID
)
if truncated_tool_call_retries < 3:
truncated_tool_call_retries += 1
agent._buffer_vprint(
f"⚠️ Truncated tool call detected — retrying API call..."
)
if _is_stub_stall:
# The stream broke mid tool-call (network /
# peer-closed connection), not a real output
# cap — say so instead of "max output tokens".
agent._buffer_vprint(
f"⚠️ Stream interrupted mid tool-call — "
f"retrying ({truncated_tool_call_retries}/3)..."
)
else:
agent._buffer_vprint(
f"⚠️ Truncated tool call detected — "
f"retrying API call "
f"({truncated_tool_call_retries}/3)..."
)
# Boost max_tokens on each retry so the model has
# more room to complete the tool-call JSON. A
# network stall doesn't need a bigger budget, but
# a genuine output-cap truncation does, and the
# boost is harmless for the stall case.
_tc_boost_base = agent.max_tokens if agent.max_tokens else 4096
_tc_boost = _tc_boost_base * (truncated_tool_call_retries + 1)
_tc_requested_cap = agent._requested_output_cap_from_api_kwargs(api_kwargs)
if _tc_requested_cap is not None:
_tc_boost = max(_tc_boost, _tc_requested_cap)
_tc_boost_cap = max(32768, _tc_requested_cap or 0)
agent._ephemeral_max_output_tokens = min(_tc_boost, _tc_boost_cap)
# Don't append the broken response to messages;
# just re-run the same API call from the current
# message state, giving the model another chance.
continue
agent._flush_status_buffer()
agent._vprint(
f"{agent.log_prefix}⚠️ Truncated tool call response detected again — refusing to execute incomplete tool arguments.",
force=True,
)
if _is_stub_stall:
agent._vprint(
f"{agent.log_prefix}⚠️ Stream kept dropping mid tool-call after 3 retries — the action was not executed.",
force=True,
)
else:
agent._vprint(
f"{agent.log_prefix}⚠️ Truncated tool call response detected again — refusing to execute incomplete tool arguments.",
force=True,
)
agent._cleanup_task_resources(effective_task_id)
agent._persist_session(messages, conversation_history)
return {
@@ -1761,7 +1838,12 @@ def run_conversation(
"api_calls": api_call_count,
"completed": False,
"partial": True,
"error": "Response truncated due to output length limit",
"error": (
"Stream repeatedly dropped mid tool-call (network); "
"the tool was not executed"
if _is_stub_stall
else "Response truncated due to output length limit"
),
}
# If we have prior messages, roll back to last complete state
@@ -2241,6 +2323,21 @@ def run_conversation(
classified.retryable, classified.should_compress,
classified.should_rotate_credential, classified.should_fallback,
)
agent._invoke_api_request_error_hook(
task_id=effective_task_id,
turn_id=turn_id,
api_request_id=api_request_id,
api_call_count=api_call_count,
api_start_time=api_start_time,
api_kwargs=api_kwargs,
error_type=type(api_error).__name__,
error_message=str(api_error),
status_code=status_code,
retry_count=retry_count,
max_retries=max_retries,
retryable=classified.retryable,
reason=classified.reason.value,
)
if (
classified.reason == FailoverReason.billing
@@ -3158,7 +3255,7 @@ def run_conversation(
else: # nous
agent._vprint(f"{agent.log_prefix} 💡 Nous Portal OAuth token was rejected (HTTP 401). Your token may be", force=True)
agent._vprint(f"{agent.log_prefix} expired, revoked, or your account may be out of credits. To fix:", force=True)
agent._vprint(f"{agent.log_prefix} 1. Re-authenticate: hermes auth add nous --type oauth", force=True)
agent._vprint(f"{agent.log_prefix} 1. Re-authenticate: hermes portal", force=True)
agent._vprint(f"{agent.log_prefix} 2. Check your portal account: https://portal.nousresearch.com", force=True)
# ``:free`` is OpenRouter slug syntax; Nous Portal will reject
# the model name even after a successful re-auth.
@@ -3341,6 +3438,12 @@ def run_conversation(
"completed": False,
"failed": True,
"error": _final_summary,
# Surface the classified reason so callers (notably the
# kanban worker path in cli.py) can distinguish a
# transient throttle from a real failure and choose a
# different exit code. ``rate_limit`` / ``billing`` here
# mean "quota wall, not a task error".
"failure_reason": classified.reason.value,
}
# For rate limits, respect the Retry-After header if present
@@ -3412,9 +3515,16 @@ def run_conversation(
# Progressively boost the output token budget on each retry.
# Retry 1 → 2× base, retry 2 → 3× base, capped at 32 768.
# Applies to all providers via _ephemeral_max_output_tokens.
# If the original request already used a larger provider/model
# default budget, keep that floor so continuation retries do
# not accidentally downshift to a much smaller cap.
_boost_base = agent.max_tokens if agent.max_tokens else 4096
_boost = _boost_base * (length_continue_retries + 1)
agent._ephemeral_max_output_tokens = min(_boost, 32768)
_requested_cap = agent._requested_output_cap_from_api_kwargs(api_kwargs)
if _requested_cap is not None:
_boost = max(_boost, _requested_cap)
_boost_cap = max(32768, _requested_cap or 0)
agent._ephemeral_max_output_tokens = min(_boost, _boost_cap)
continue
# Guard: if all retries exhausted without a successful response
@@ -3457,29 +3567,44 @@ def run_conversation(
assistant_message.content = str(raw)
try:
from hermes_cli.plugins import invoke_hook as _invoke_hook
_assistant_tool_calls = getattr(assistant_message, "tool_calls", None) or []
_assistant_text = assistant_message.content or ""
_invoke_hook(
"post_api_request",
task_id=effective_task_id,
session_id=agent.session_id or "",
platform=agent.platform or "",
model=agent.model,
provider=agent.provider,
base_url=agent.base_url,
api_mode=agent.api_mode,
api_call_count=api_call_count,
api_duration=api_duration,
finish_reason=finish_reason,
message_count=len(api_messages),
response_model=getattr(response, "model", None),
response=response,
usage=agent._usage_summary_for_api_request_hook(response),
assistant_message=assistant_message,
assistant_content_chars=len(_assistant_text),
assistant_tool_call_count=len(_assistant_tool_calls),
from hermes_cli.plugins import (
has_hook,
invoke_hook as _invoke_hook,
)
if has_hook("post_api_request"):
_assistant_tool_calls = (
getattr(assistant_message, "tool_calls", None) or []
)
_assistant_text = assistant_message.content or ""
_api_ended_at = api_start_time + api_duration
_invoke_hook(
"post_api_request",
task_id=effective_task_id,
turn_id=turn_id,
api_request_id=api_request_id,
session_id=agent.session_id or "",
platform=agent.platform or "",
model=agent.model,
provider=agent.provider,
base_url=agent.base_url,
api_mode=agent.api_mode,
api_call_count=api_call_count,
api_duration=api_duration,
started_at=api_start_time,
ended_at=_api_ended_at,
finish_reason=finish_reason,
message_count=len(api_messages),
response_model=getattr(response, "model", None),
response=agent._api_response_payload_for_hook(
response,
assistant_message,
finish_reason=finish_reason,
),
usage=agent._usage_summary_for_api_request_hook(response),
assistant_message=assistant_message,
assistant_content_chars=len(_assistant_text),
assistant_tool_call_count=len(_assistant_tool_calls),
)
except Exception:
pass
@@ -4573,6 +4698,8 @@ def run_conversation(
_invoke_hook(
"post_llm_call",
session_id=agent.session_id,
task_id=effective_task_id,
turn_id=turn_id,
user_message=original_user_message,
assistant_response=final_response,
conversation_history=list(messages),
@@ -4692,6 +4819,8 @@ def run_conversation(
_invoke_hook(
"on_session_end",
session_id=agent.session_id,
task_id=effective_task_id,
turn_id=turn_id,
completed=completed,
interrupted=interrupted,
model=agent.model,

View File

@@ -1891,6 +1891,7 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
# via `hermes auth openai-codex`.
if isinstance(tokens, dict) and tokens.get("access_token"):
active_sources.add("device_code")
custom_label = str(state.get("label") or "").strip()
changed |= _upsert_entry(
entries,
provider,
@@ -1902,7 +1903,7 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
"refresh_token": tokens.get("refresh_token"),
"base_url": "https://chatgpt.com/backend-api/codex",
"last_refresh": state.get("last_refresh"),
"label": label_from_token(tokens.get("access_token", ""), "device_code"),
"label": custom_label or label_from_token(tokens.get("access_token", ""), "device_code"),
},
)

View File

@@ -183,6 +183,18 @@ def get_archive_after_days() -> int:
return DEFAULT_ARCHIVE_AFTER_DAYS
def get_prune_builtins() -> bool:
"""Whether the curator may prune (archive) bundled built-in skills too.
ON by default. When on, built-ins become curation candidates and are
archived after the same inactivity period as agent-created skills, with a
suppression list keeping them archived across `hermes update` re-seeds.
Hub-installed skills are never pruned regardless of this flag.
"""
cfg = _load_config()
return bool(cfg.get("prune_builtins", True))
# ---------------------------------------------------------------------------
# Idle / interval check
# ---------------------------------------------------------------------------
@@ -254,9 +266,17 @@ def should_run_now(now: Optional[datetime] = None) -> bool:
# ---------------------------------------------------------------------------
def apply_automatic_transitions(now: Optional[datetime] = None) -> Dict[str, int]:
"""Walk every agent-created skill and move active/stale/archived based on
"""Walk every curator-managed skill and move active/stale/archived based on
the latest real activity timestamp. Pinned skills are never touched.
Returns a counter dict describing what changed."""
Built-ins (eligible only when ``curator.prune_builtins`` is on) are seeded
with a baseline record the first time they're seen so their inactivity
clock starts NOW rather than at epoch — a long-unused built-in is therefore
archived only after a fresh ``archive_after_days`` of non-use, not on the
first pass after the flag flips on.
Returns a counter dict describing what changed.
"""
from tools import skill_usage as _u
if now is None:
@@ -264,7 +284,7 @@ def apply_automatic_transitions(now: Optional[datetime] = None) -> Dict[str, int
stale_cutoff = now - timedelta(days=get_stale_after_days())
archive_cutoff = now - timedelta(days=get_archive_after_days())
counts = {"marked_stale": 0, "archived": 0, "reactivated": 0, "checked": 0}
counts = {"marked_stale": 0, "archived": 0, "reactivated": 0, "checked": 0, "seeded": 0}
for row in _u.agent_created_report():
counts["checked"] += 1
@@ -272,6 +292,13 @@ def apply_automatic_transitions(now: Optional[datetime] = None) -> Dict[str, int
if row.get("pinned"):
continue
# First sight of a curation-eligible skill with no persisted record
# (e.g. a newly-eligible built-in): anchor its clock to now and defer.
if not row.get("_persisted", True):
_u.seed_record_if_missing(name)
counts["seeded"] += 1
continue
last_activity = _parse_iso(row.get("last_activity_at"))
# If never active, treat created_at as the anchor so new skills don't
# immediately archive themselves.
@@ -1484,14 +1511,30 @@ def run_curator_review(
"error": None,
}
else:
# When pruning built-ins is enabled, the candidate list now
# includes bundled skills. Override the default "don't touch
# bundled" rule for them — but only archiving is permitted, and
# hub-installed skills remain strictly off-limits.
builtins_note = ""
if get_prune_builtins():
builtins_note = (
"\n\nPRUNE-BUILTINS MODE IS ON: bundled built-in skills "
"ARE included in the candidate list below and MAY be "
"archived for staleness/irrelevance, overriding hard "
"rule #1 for bundled skills ONLY. Hub-installed skills "
"remain strictly off-limits. Treat a stale built-in the "
"same as a stale agent-created skill: archive it (never "
"delete). It will be restored on `hermes update` only if "
"the user explicitly restores it."
)
if dry_run:
prompt = (
f"{CURATOR_DRY_RUN_BANNER}\n\n"
f"{CURATOR_REVIEW_PROMPT}\n\n"
f"{CURATOR_REVIEW_PROMPT}{builtins_note}\n\n"
f"{candidate_list}"
)
else:
prompt = f"{CURATOR_REVIEW_PROMPT}\n\n{candidate_list}"
prompt = f"{CURATOR_REVIEW_PROMPT}{builtins_note}\n\n{candidate_list}"
llm_meta = _run_llm_review(prompt)
final_summary = (
f"{prefix}{auto_summary}; llm: {llm_meta.get('summary', 'no change')}"

View File

@@ -21,6 +21,8 @@ It DOES include:
pointer — otherwise the curator would immediately re-fire on the next
tick)
- ``.bundled_manifest`` (so protection markers stay consistent)
- ``.curator_suppressed`` (so rollback restores the set of pruned built-ins
the re-seeder must leave archived)
Alongside the skills tarball, each snapshot also captures a copy of
``~/.hermes/cron/jobs.json`` as ``cron-jobs.json`` when it exists. Cron

View File

@@ -451,3 +451,190 @@ def get_cross_profile_warning(path: str) -> Optional[str]:
f"``cross_profile=True``. (Defense-in-depth — not a security "
f"boundary; the terminal tool can still bypass.)"
)
# ---------------------------------------------------------------------------
# Sandbox-mirror write guard (#32049)
#
# Non-local terminal backends (Docker, Daytona, etc.) bind a sandbox-local
# directory to the container's ``$HOME``. The on-disk layout looks like
#
# <HERMES_HOME>/profiles/<name>/sandboxes/<backend>/<task>/home/.hermes/...
#
# When the agent (running host-side) speculates that authoritative profile
# state lives at one of those sandbox-mirror paths, the write lands on the
# mirror — never read by the host process — while the host file is left
# untouched. The agent reports success, the user sees no change, and on
# disk two divergent copies accumulate. See #32049 for evidence.
#
# This guard is path-shape-only: it detects the
# ``…/sandboxes/<backend>/<task>/home/.hermes/…`` segment and warns
# regardless of which Hermes profile is active. It does NOT cover the
# inner-container case where the bind mount strips the ``sandboxes/`` prefix
# (the agent's view inside the container is plain ``/root/.hermes/...``);
# that case needs a separate dispatch-layer or host-side ``profile_state``
# tool.
# ---------------------------------------------------------------------------
def _find_sandbox_mirror_segments(parts: tuple) -> Optional[int]:
"""Return the index of the inner ``.hermes`` part in a sandbox-mirror path.
Matches ``…/sandboxes/<backend>/<task>/home/.hermes/…`` and returns the
index where the inner Hermes-state portion starts. Returns ``None`` for
paths that do not contain the sandbox-mirror shape.
"""
for i, part in enumerate(parts):
if part != "sandboxes":
continue
# Need at least: sandboxes / <backend> / <task> / home / .hermes / <thing>
if i + 5 >= len(parts):
continue
if parts[i + 3] == "home" and parts[i + 4] == ".hermes":
return i + 4
return None
def classify_sandbox_mirror_target(path: str) -> Optional[dict]:
"""Classify a write target as a sandbox-mirror of authoritative Hermes state.
Returns ``None`` when the path does not match the sandbox-mirror shape.
Otherwise returns a dict with:
* ``target_path``: the resolved path string
* ``mirror_root``: the ``…/sandboxes/<backend>/<task>/home/.hermes``
prefix (so callers can show users which sandbox owns the mirror)
* ``inner_path``: the portion under the mirror's ``.hermes`` (what the
agent likely meant to address on the host)
Detection is path-shape-only — does not require any Hermes resolver to
succeed, so it works correctly even when called from contexts where
HERMES_HOME resolution would be ambiguous.
"""
try:
target = Path(os.path.expanduser(str(path))).resolve()
except (OSError, RuntimeError):
return None
parts = target.parts
inner_idx = _find_sandbox_mirror_segments(parts)
if inner_idx is None:
return None
mirror_root = str(Path(*parts[: inner_idx + 1]))
inner_path = str(Path(*parts[inner_idx + 1 :])) if inner_idx + 1 < len(parts) else ""
return {
"target_path": str(target),
"mirror_root": mirror_root,
"inner_path": inner_path,
}
def get_sandbox_mirror_warning(path: str) -> Optional[str]:
"""Return a model-facing warning when ``path`` lands in a sandbox mirror.
Returns ``None`` when the path is not a sandbox-mirror target. Caller
is expected to surface the warning to the agent as a tool-result
error. The bypass kwarg (``cross_profile=True``) is shared with the
cross-profile guard: both are soft "I know what I'm doing" overrides
a user can authorise.
Defense-in-depth, NOT a security boundary: the terminal tool runs as
the same OS user and can write the mirror path directly. The guard
exists to surface the misclassification before the silent-success +
divergent-copy footgun in #32049 fires.
"""
info = classify_sandbox_mirror_target(path)
if info is None:
return None
return (
f"Sandbox-mirror write blocked by soft guard: {info['target_path']} "
f"sits under {info['mirror_root']!r}, which is a per-task mirror "
f"created by a non-local terminal backend (docker/daytona/etc.). "
f"Writes here land on a copy that the host Hermes process never "
f"reads — the authoritative file is likely {info['inner_path']!r} "
f"under the real HERMES_HOME. Use the host-side tool for "
f"authoritative state (e.g. ``memory`` for memories), or address "
f"the host path directly. To bypass this guard after explicit "
f"user direction, retry the call with ``cross_profile=True``. "
f"(Defense-in-depth — not a security boundary; the terminal tool "
f"can still bypass.)"
)
# ---------------------------------------------------------------------------
# Container-context mirror guard (inner-container case — #32049 follow-up)
#
# Brian's shape-based detector (#32213) catches paths that still carry the
# full ``…/sandboxes/<backend>/<task>/home/.hermes/…`` prefix on the host.
# But when file tools execute *inside* the container the bind-mount strips
# that prefix: the agent sees plain ``/root/.hermes/…``. The root:root
# ownership on the divergent SOUL.md in #32049 confirms this is the primary
# failure mode.
#
# Fix: file_tools passes the active Docker mirror prefix when the terminal
# backend is docker + persistent. This catches the very first file-tool call,
# before a DockerEnvironment object necessarily exists.
# ---------------------------------------------------------------------------
def classify_container_mirror_target(
path: str,
mirror_prefix: str | None = None,
) -> Optional[dict]:
"""Classify a write target as a container-side sandbox mirror.
``mirror_prefix`` must be supplied by the caller after it has established
that file tools are executing in a container whose home is a sandbox
mirror. Returns ``None`` when no such context is active or the path is not
under the mirror prefix. Otherwise returns:
* ``target_path``: resolved path string
* ``mirror_root``: the declared container mirror prefix
* ``inner_path``: portion under the mirror root (what the agent
likely meant to address in the host HERMES_HOME)
"""
if not mirror_prefix:
return None
try:
target = Path(os.path.expanduser(str(path))).resolve()
mirror = Path(os.path.expanduser(mirror_prefix)).resolve()
inner = target.relative_to(mirror)
except (OSError, RuntimeError, ValueError):
return None
return {
"target_path": str(target),
"mirror_root": str(mirror),
"inner_path": inner.as_posix(),
}
def get_container_mirror_warning(
path: str,
mirror_prefix: str | None = None,
) -> Optional[str]:
"""Return a model-facing warning when *path* lands in the container's
sandbox mirror of authoritative Hermes state.
The caller supplies ``mirror_prefix`` only when the current file-tool
backend is known to execute inside a Docker sandbox. Same contract as
``get_cross_profile_warning``: soft guard, returns ``None`` for
non-mirror paths, caller surfaces as a tool-result error. Bypass via
``cross_profile=True`` after explicit user direction.
"""
info = classify_container_mirror_target(path, mirror_prefix)
if info is None:
return None
return (
f"Sandbox-mirror write blocked by soft guard: {info['target_path']} "
f"sits under {info['mirror_root']!r}, which is the container's "
f"bind-mounted home — a per-task mirror that the host Hermes "
f"process never reads. The authoritative file is "
f"{info['inner_path']!r} under the real HERMES_HOME. Use the "
f"host-side tool for authoritative state (e.g. ``memory`` for "
f"memories), or address the host path directly. To bypass after "
f"explicit user direction, retry with ``cross_profile=True``. "
f"(Defense-in-depth — not a security boundary; the terminal tool "
f"can still bypass.)"
)

View File

@@ -32,6 +32,7 @@ from __future__ import annotations
import logging
import os
import sysconfig
import threading
from functools import lru_cache
from pathlib import Path
@@ -87,11 +88,54 @@ _catalog_lock = threading.Lock()
def _locales_dir() -> Path:
"""Return the directory containing locale YAML files.
Lives next to the repo root so both the bundled install and editable
checkouts find it without PYTHONPATH gymnastics.
Resolution order, first existing wins:
1. ``HERMES_BUNDLED_LOCALES`` env var -- set by the Nix wrapper (or any
sealed-packaging system) to point at the installed catalog directory.
2. ``<repo-root>/locales`` -- source checkouts and ``pip install -e .``,
where the working tree sits next to ``agent/``.
3. ``<sysconfig data|purelib|platlib>/locales`` -- pip wheel installs.
setuptools ``data-files`` extracts ``locales/*.yaml`` under the
interpreter's ``data`` scheme; the other schemes are checked as a
safety net for nonstandard layouts.
Falling through to the source-style path (even when missing) keeps
``_load_catalog`` error messages informative -- it logs the path it
looked at -- rather than raising.
"""
# agent/i18n.py -> agent/ -> repo root
return Path(__file__).resolve().parent.parent / "locales"
override = os.getenv("HERMES_BUNDLED_LOCALES", "").strip()
if override:
candidate = Path(override)
if candidate.is_dir():
return candidate
logger.warning(
"HERMES_BUNDLED_LOCALES points to a non-directory path (%s); "
"falling back to bundled/source locale resolution",
override,
)
# agent/i18n.py -> agent/ -> repo root (source checkout, editable install)
source_dir = Path(__file__).resolve().parent.parent / "locales"
if source_dir.is_dir():
return source_dir
# pip wheel install: data-files lands under the interpreter data scheme.
# ``data`` (== sys.prefix in a venv) is where setuptools data-files extract
# and is checked first. ``purelib``/``platlib`` (site-packages) are a safety
# net for nonstandard layouts. NOTE: this does NOT cover ``pip install
# --user`` (user scheme, ~/.local/locales) or ``pip install --target`` --
# both are out of scope; see the plan header.
for scheme in ("data", "purelib", "platlib"):
raw = sysconfig.get_path(scheme)
if not raw:
continue
candidate = Path(raw) / "locales"
if candidate.is_dir():
return candidate
# Last resort: return the source-style path so _load_catalog's catalog-missing
# log (logger.debug "i18n catalog missing for %s at %s") stays informative.
return source_dir
def _normalize_lang(value: Any) -> str:

View File

@@ -491,6 +491,7 @@ class MemoryManager:
*,
parent_session_id: str = "",
reset: bool = False,
rewound: bool = False,
**kwargs,
) -> None:
"""Notify all providers that the agent's session_id has rotated.
@@ -503,9 +504,21 @@ class MemoryManager:
per-session state so subsequent writes land in the correct
session's record. See ``MemoryProvider.on_session_switch`` for
the full contract.
``rewound=True`` signals that session_id is unchanged but the
transcript was truncated; providers caching per-turn document
state should invalidate.
"""
if not new_session_id:
return
# Only forward ``rewound`` when it's actually set. Passing it
# unconditionally would inject ``rewound=False`` into every
# provider's **kwargs for the common /resume, /branch, /new, and
# compression paths, polluting providers that capture extra kwargs
# (and breaking exact-dict assertions). The /undo path sets
# rewound=True explicitly; everyone else stays clean.
if rewound:
kwargs["rewound"] = True
for provider in self._providers:
try:
provider.on_session_switch(

View File

@@ -178,6 +178,7 @@ class MemoryProvider(ABC):
*,
parent_session_id: str = "",
reset: bool = False,
rewound: bool = False,
**kwargs,
) -> None:
"""Called when the agent switches session_id mid-process.
@@ -207,6 +208,10 @@ class MemoryProvider(ABC):
(``_session_turns``, ``_turn_counter``, etc.) when this is
set. ``False`` for ``/resume`` / ``/branch`` / compression
where the logical conversation continues under the new id.
rewound:
``True`` if session_id is unchanged but the transcript was
truncated; providers caching per-turn document state should
invalidate.
Default is no-op for backward compatibility.
"""

View File

@@ -200,8 +200,12 @@ DEFAULT_CONTEXT_LENGTHS = {
"qwen3-coder-plus": 1000000, # 1M context
"qwen3-coder": 262144, # 256K context
"qwen": 131072,
# MiniMax — official docs: 204,800 context for all models
# https://platform.minimax.io/docs/api-reference/text-anthropic-api
# MiniMax — M3 is 1M context (max output 512K); M2.x series is 204,800.
# Keys use substring matching (longest-first), so "minimax-m3" wins over
# the generic "minimax" catch-all for the M3 slug on every surface
# (native MiniMax-M3, OpenRouter/Nous minimax/minimax-m3).
# https://platform.minimax.io/docs/api-reference/text-chat-openai
"minimax-m3": 1000000,
"minimax": 204800,
# GLM
"glm": 202752,
@@ -1124,6 +1128,18 @@ def _model_name_suggests_kimi(model: str) -> bool:
return lower.startswith("kimi") or "moonshot" in lower
def _model_name_suggests_minimax_m3(model: str) -> bool:
"""Return True if the model name looks like MiniMax M3.
Catches ``MiniMax-M3``, ``minimax/minimax-m3``, and similar variants
across surfaces (native MiniMax-M3, OpenRouter/Nous minimax/minimax-m3).
Used as a guard against stale cache entries seeded by pre-catalog builds
that resolved M3 via the generic ``minimax`` catch-all (204,800) before
the ``minimax-m3`` (1M) entry existed in DEFAULT_CONTEXT_LENGTHS.
"""
return "minimax-m3" in model.lower()
def _query_local_context_length(model: str, base_url: str, api_key: str = "") -> Optional[int]:
"""Query a local server for the model's context length."""
import httpx
@@ -1535,6 +1551,19 @@ def get_model_context_length(
model, base_url, f"{cached:,}",
)
_invalidate_cached_context_length(model, base_url)
# Invalidate stale ≤204,800 cache entries for MiniMax-M3. Pre-catalog
# builds resolved M3 via the generic ``minimax`` catch-all (204,800)
# and persisted it before the ``minimax-m3`` (1M) entry existed; that
# stale value would otherwise stick forever here at step 1. M3 is 1M,
# so any sub-256K cached value for an M3 slug is a leftover — drop it
# and fall through to the hardcoded default.
elif cached <= 204_800 and _model_name_suggests_minimax_m3(model):
logger.info(
"Dropping stale MiniMax-M3 cache entry %s@%s -> %s (pre-catalog value); "
"re-resolving via hardcoded defaults",
model, base_url, f"{cached:,}",
)
_invalidate_cached_context_length(model, base_url)
# Nous Portal: the portal /v1/models endpoint is authoritative.
# Bypass the persistent cache so step 5b can always reconcile
# against it — this corrects pre-fix entries seeded from the

View File

@@ -14,6 +14,7 @@ from pathlib import Path
from hermes_constants import get_hermes_home, get_skills_dir, is_wsl
from typing import Optional
from agent.runtime_cwd import resolve_agent_cwd
from agent.skill_utils import (
extract_skill_conditions,
extract_skill_description,
@@ -128,9 +129,14 @@ DEFAULT_AGENT_IDENTITY = (
)
HERMES_AGENT_HELP_GUIDANCE = (
"If the user asks about configuring, setting up, or using Hermes Agent "
"itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') "
"before answering. Docs: https://hermes-agent.nousresearch.com/docs"
"You run on Hermes Agent (by Nous Research). When the user needs help with "
"Hermes itself — configuring, setting up, using, extending, or troubleshooting "
"it — or when you need to understand your own features, tools, or capabilities, "
"the documentation at https://hermes-agent.nousresearch.com/docs is your "
"authoritative reference and always holds the latest, most up-to-date "
"information. Load the `hermes-agent` skill with skill_view(name='hermes-agent') "
"for additional guidance and proven workflows, but treat the docs as the source "
"of truth when the two differ."
)
MEMORY_GUIDANCE = (
@@ -802,7 +808,7 @@ def build_environment_hints() -> str:
host_lines.append(f"User home directory: {os.path.expanduser('~')}")
try:
host_lines.append(f"Current working directory: {os.getcwd()}")
host_lines.append(f"Current working directory: {resolve_agent_cwd()}")
except OSError:
pass

62
agent/runtime_cwd.py Normal file
View File

@@ -0,0 +1,62 @@
"""Single source of truth for the agent working directory.
`TERMINAL_CWD` is the runtime carrier for the configured working directory
(design #19214/#19242: `terminal.cwd` is bridged once to `TERMINAL_CWD` at
gateway/cron startup). The local-CLI backend deliberately leaves it unset and
relies on the launch dir. Reading it in one place keeps the system prompt, the
tool surfaces, and context-file discovery agreeing on where the agent lives.
Multi-session gateways can pin a logical cwd via the `_SESSION_CWD`
contextvar; CLI/cron fall through to `TERMINAL_CWD`/launch cwd.
"""
import os
from contextvars import ContextVar, Token
from pathlib import Path
from typing import Any
_UNSET: Any = object()
_SESSION_CWD: ContextVar = ContextVar("HERMES_SESSION_CWD", default=_UNSET)
def set_session_cwd(cwd: str | None) -> Token:
"""Pin the logical cwd for the current context."""
return _SESSION_CWD.set((cwd or "").strip())
def clear_session_cwd() -> None:
_SESSION_CWD.set("")
def _session_cwd_override() -> str:
value = _SESSION_CWD.get()
if value is _UNSET:
return ""
return str(value).strip()
def resolve_agent_cwd() -> Path:
override = _session_cwd_override()
if override:
p = Path(override).expanduser()
if p.is_dir():
return p
raw = os.environ.get("TERMINAL_CWD", "").strip()
if raw:
p = Path(raw).expanduser()
if p.is_dir():
return p
return Path(os.getcwd())
def resolve_context_cwd() -> Path | None:
# None means "no configured cwd": build_context_files_prompt then falls back
# to the launch dir (os.getcwd()) — correct for the local CLI. The gateway
# avoids slurping its install dir by setting TERMINAL_CWD (see system_prompt.py)
# or, per session, the _SESSION_CWD contextvar above.
override = _session_cwd_override()
if override:
return Path(override).expanduser()
raw = os.environ.get("TERMINAL_CWD", "").strip()
return Path(raw).expanduser() if raw else None

View File

@@ -24,7 +24,6 @@ Pure helpers that read the agent's state. AIAgent keeps thin forwarders.
from __future__ import annotations
import json
import os
from typing import Any, Dict, List, Optional
from agent.prompt_builder import (
@@ -41,6 +40,7 @@ from agent.prompt_builder import (
TOOL_USE_ENFORCEMENT_GUIDANCE,
TOOL_USE_ENFORCEMENT_MODELS,
)
from agent.runtime_cwd import resolve_context_cwd
def _ra():
@@ -288,13 +288,12 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
context_parts.append(system_message)
if not agent.skip_context_files:
# Use TERMINAL_CWD for context file discovery when set (gateway
# mode). The gateway process runs from the hermes-agent install
# dir, so os.getcwd() would pick up the repo's AGENTS.md and
# other dev files — inflating token usage by ~10k for no benefit.
_context_cwd = os.getenv("TERMINAL_CWD") or None
# Prefer the configured TERMINAL_CWD (gateway mode). When unset (local
# CLI), None lets build_context_files_prompt fall back to the launch
# dir — the user's real cwd there, but the install dir for the gateway
# daemon, which is why the gateway sets TERMINAL_CWD.
context_files_prompt = _r.build_context_files_prompt(
cwd=_context_cwd, skip_soul=_soul_loaded)
cwd=resolve_context_cwd(), skip_soul=_soul_loaded)
if context_files_prompt:
context_parts.append(context_files_prompt)

View File

@@ -19,7 +19,7 @@ import os
import random
import threading
import time
from typing import Optional
from typing import Any, Optional
from agent.display import (
KawaiiSpinner,
@@ -58,6 +58,76 @@ def _ra():
return run_agent
def _emit_terminal_post_tool_call(
agent,
*,
function_name: str,
function_args: dict,
result: Any,
effective_task_id: str,
tool_call_id: str,
duration_ms: int = 0,
status: str | None = None,
error_type: str | None = None,
error_message: str | None = None,
) -> None:
try:
from model_tools import _emit_post_tool_call_hook
_emit_post_tool_call_hook(
function_name=function_name,
function_args=function_args,
result=result,
task_id=effective_task_id or "",
session_id=getattr(agent, "session_id", "") or "",
tool_call_id=tool_call_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
duration_ms=duration_ms,
status=status,
error_type=error_type,
error_message=error_message,
)
except Exception:
pass
def _cancelled_tool_result(reason: str = "user interrupt") -> str:
return json.dumps(
{
"error": f"Tool execution cancelled by {reason}",
"status": "cancelled",
},
ensure_ascii=False,
)
def _emit_cancelled_terminal_post_tool_call(
agent,
*,
function_name: str,
function_args: dict,
effective_task_id: str,
tool_call_id: str,
start_time: float,
reason: str = "user interrupt",
error_type: str = "keyboard_interrupt",
) -> str:
result = _cancelled_tool_result(reason)
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=result,
effective_task_id=effective_task_id,
tool_call_id=tool_call_id,
duration_ms=int((time.time() - start_time) * 1000),
status="cancelled",
error_type=error_type,
error_message=f"Tool execution cancelled by {reason}",
)
return result
def _tool_search_scoped_names(agent) -> frozenset:
"""Return the deferrable tool names the session may invoke via tool_call.
@@ -188,22 +258,61 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
if _ts_scope_block is not None:
# Out-of-scope tool_call: reject before hooks/guardrails/dispatch.
block_result = _ts_scope_block
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=block_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
status="blocked",
error_type="tool_scope_block",
error_message=_ts_scope_block,
)
else:
try:
from hermes_cli.plugins import get_pre_tool_call_block_message
block_message = get_pre_tool_call_block_message(
function_name, function_args, task_id=effective_task_id or "",
function_name,
function_args,
task_id=effective_task_id or "",
session_id=getattr(agent, "session_id", "") or "",
tool_call_id=getattr(tool_call, "id", "") or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
)
except Exception:
block_message = None
if block_message is not None:
block_result = json.dumps({"error": block_message}, ensure_ascii=False)
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=block_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
status="blocked",
error_type="plugin_block",
error_message=block_message,
)
else:
guardrail_decision = agent._tool_guardrails.before_call(function_name, function_args)
if not guardrail_decision.allows_execution:
block_result = agent._guardrail_block_result(guardrail_decision)
blocked_by_guardrail = True
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=block_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
status="blocked",
error_type="guardrail_block",
error_message=getattr(guardrail_decision, "message", None) or "Tool blocked by guardrail policy",
)
# ── Checkpoint preflight (only for tools that will execute) ──
if block_result is None:
@@ -315,6 +424,23 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
messages=messages,
pre_tool_block_checked=True,
)
except KeyboardInterrupt:
try:
agent.interrupt("keyboard interrupt")
except Exception:
pass
result = _emit_cancelled_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
start_time=start,
)
duration = time.time() - start
logger.info("tool %s cancelled (%.2fs)", function_name, duration)
results[index] = (function_name, function_args, result, duration, True, False)
return
except Exception as tool_error:
result = f"Error executing tool '{function_name}': {tool_error}"
logger.error("_invoke_tool raised for %s: %s", function_name, tool_error, exc_info=True)
@@ -426,8 +552,30 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
# Tool was cancelled (interrupt) or thread didn't return
if agent._interrupt_requested:
function_result = f"[Tool execution cancelled — {name} was skipped due to user interrupt]"
_emit_terminal_post_tool_call(
agent,
function_name=name,
function_args=args,
result=function_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tc, "id", "") or "",
status="cancelled",
error_type="keyboard_interrupt",
error_message="Tool execution cancelled by user interrupt",
)
else:
function_result = f"Error executing tool '{name}': thread did not return a result"
_emit_terminal_post_tool_call(
agent,
function_name=name,
function_args=args,
result=function_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tc, "id", "") or "",
status="error",
error_type="thread_missing_result",
error_message=function_result,
)
tool_duration = 0.0
else:
function_name, function_args, function_result, tool_duration, is_error, blocked = r
@@ -592,13 +740,21 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
# Check plugin hooks for a block directive before executing.
_block_msg: Optional[str] = None
_block_error_type = "plugin_block"
if _ts_scope_block is not None:
_block_msg = _ts_scope_block
_block_error_type = "tool_scope_block"
else:
try:
from hermes_cli.plugins import get_pre_tool_call_block_message
_block_msg = get_pre_tool_call_block_message(
function_name, function_args, task_id=effective_task_id or "",
function_name,
function_args,
task_id=effective_task_id or "",
session_id=getattr(agent, "session_id", "") or "",
tool_call_id=getattr(tool_call, "id", "") or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
)
except Exception:
pass
@@ -687,11 +843,33 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
# Tool blocked by plugin policy — return error without executing.
function_result = json.dumps({"error": _block_msg}, ensure_ascii=False)
tool_duration = 0.0
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=function_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
status="blocked",
error_type=_block_error_type,
error_message=_block_msg,
)
elif _guardrail_block_decision is not None:
# Tool blocked by tool-loop guardrail — synthesize exactly one
# tool result for the original tool_call_id without executing.
function_result = agent._guardrail_block_result(_guardrail_block_decision)
tool_duration = 0.0
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=function_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
status="blocked",
error_type="guardrail_block",
error_message=getattr(_guardrail_block_decision, "message", None) or "Tool blocked by guardrail policy",
)
elif function_name == "todo":
from tools.todo_tool import todo_tool as _todo_tool
function_result = _todo_tool(
@@ -850,12 +1028,29 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
function_name, function_args, effective_task_id,
tool_call_id=tool_call.id,
session_id=agent.session_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
enabled_tools=list(agent.valid_tool_names) if agent.valid_tool_names else None,
skip_pre_tool_call_hook=True,
enabled_toolsets=getattr(agent, "enabled_toolsets", None),
disabled_toolsets=getattr(agent, "disabled_toolsets", None),
)
_spinner_result = function_result
except KeyboardInterrupt:
function_result = _emit_cancelled_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
start_time=tool_start_time,
)
_spinner_result = function_result
try:
agent.interrupt("keyboard interrupt")
except Exception:
pass
raise
except Exception as tool_error:
function_result = f"Error executing tool '{function_name}': {tool_error}"
logger.error("handle_function_call raised for %s: %s", function_name, tool_error, exc_info=True)
@@ -872,11 +1067,27 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
function_name, function_args, effective_task_id,
tool_call_id=tool_call.id,
session_id=agent.session_id or "",
turn_id=getattr(agent, "_current_turn_id", "") or "",
api_request_id=getattr(agent, "_current_api_request_id", "") or "",
enabled_tools=list(agent.valid_tool_names) if agent.valid_tool_names else None,
skip_pre_tool_call_hook=True,
enabled_toolsets=getattr(agent, "enabled_toolsets", None),
disabled_toolsets=getattr(agent, "disabled_toolsets", None),
)
except KeyboardInterrupt:
_emit_cancelled_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
start_time=tool_start_time,
)
try:
agent.interrupt("keyboard interrupt")
except Exception:
pass
raise
except Exception as tool_error:
function_result = f"Error executing tool '{function_name}': {tool_error}"
logger.error("handle_function_call raised for %s: %s", function_name, tool_error, exc_info=True)
@@ -895,6 +1106,27 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
# Log tool errors to the persistent error log so [error] tags
# in the UI always have a corresponding detailed entry on disk.
_is_error_result, _ = _detect_tool_failure(function_name, function_result)
# The agent-runtime tools above (todo, session_search, memory,
# context-engine, memory-manager, clarify, delegate_task) are
# dispatched inline — they never reach handle_function_call, so the
# executor is the one that has to fire post_tool_call. For
# registry-dispatched tools the else-branch above invoked
# handle_function_call, which already fires the hook.
from agent.agent_runtime_helpers import agent_runtime_owns_post_tool_hook
_executor_must_emit_post_hook = (
not _execution_blocked
and agent_runtime_owns_post_tool_hook(agent, function_name)
)
if _executor_must_emit_post_hook:
_emit_terminal_post_tool_call(
agent,
function_name=function_name,
function_args=function_args,
result=function_result,
effective_task_id=effective_task_id,
tool_call_id=getattr(tool_call, "id", "") or "",
duration_ms=int(tool_duration * 1000),
)
if not _execution_blocked:
function_result = agent._append_guardrail_observation(
function_name,

View File

@@ -99,6 +99,22 @@ def _is_gemini_openai_compat_base_url(base_url: Any) -> bool:
return normalized.endswith("/openai")
def _model_consumes_thought_signature(model: Any) -> bool:
"""True when the outgoing model is a Gemini family model that requires
``extra_content`` (thought_signature) to be replayed on tool calls.
Gemini 3 thinking models attach ``extra_content`` to each tool call and
reject subsequent requests with HTTP 400 if it is missing. Every other
strict OpenAI-compatible provider (Fireworks, Mistral, ...) rejects the
request with 400 if ``extra_content`` *is* present. So the field must be
kept only when the target model is itself Gemini-family, and stripped
otherwise — including when a non-Gemini model inherits stale Gemini
``extra_content`` from earlier in a mixed-provider session.
"""
m = str(model or "").lower()
return "gemini" in m or "gemma" in m
class ChatCompletionsTransport(ProviderTransport):
"""Transport for api_mode='chat_completions'.
@@ -119,6 +135,14 @@ class ChatCompletionsTransport(ProviderTransport):
- Codex Responses API fields: ``codex_reasoning_items`` /
``codex_message_items`` on the message, ``call_id`` /
``response_item_id`` on ``tool_calls`` entries.
- ``extra_content`` on ``tool_calls`` (Gemini thought_signature) —
stripped unless the outgoing ``model`` is itself Gemini-family.
Gemini 3 thinking models attach it for replay, but strict providers
(Fireworks, Mistral) reject any payload containing it with
``Extra inputs are not permitted, field: 'messages[N].tool_calls[M].extra_content'``.
It must be kept for Gemini targets (replay required) and dropped for
everyone else, including non-Gemini models that inherited stale
Gemini ``extra_content`` earlier in a mixed-provider session.
- ``tool_name`` on tool-result messages — written by
``make_tool_result_message()`` for the SQLite FTS index, but not
part of the Chat Completions schema. Strict providers (Fireworks,
@@ -137,6 +161,9 @@ class ChatCompletionsTransport(ProviderTransport):
``Extra inputs are not permitted, field: 'messages[N]._empty_recovery_synthetic'``,
which then poisons every subsequent request in the session.
"""
strip_extra_content = not _model_consumes_thought_signature(
kwargs.get("model")
)
needs_sanitize = False
for msg in messages:
if not isinstance(msg, dict):
@@ -155,7 +182,9 @@ class ChatCompletionsTransport(ProviderTransport):
if isinstance(tool_calls, list):
for tc in tool_calls:
if isinstance(tc, dict) and (
"call_id" in tc or "response_item_id" in tc
"call_id" in tc
or "response_item_id" in tc
or (strip_extra_content and "extra_content" in tc)
):
needs_sanitize = True
break
@@ -183,6 +212,8 @@ class ChatCompletionsTransport(ProviderTransport):
if isinstance(tc, dict):
tc.pop("call_id", None)
tc.pop("response_item_id", None)
if strip_extra_content:
tc.pop("extra_content", None)
return sanitized
def convert_tools(self, tools: list[dict[str, Any]]) -> list[dict[str, Any]]:
@@ -240,8 +271,10 @@ class ChatCompletionsTransport(ProviderTransport):
anthropic_max_output: int | None
extra_body_additions: dict | None
"""
# Codex sanitization: drop reasoning_items / call_id / response_item_id
sanitized = self.convert_messages(messages)
# Codex sanitization: drop reasoning_items / call_id / response_item_id.
# Pass model so the Gemini thought_signature (extra_content) is kept for
# Gemini targets and stripped for strict non-Gemini providers.
sanitized = self.convert_messages(messages, model=model)
# ── Provider profile: single-path when present ──────────────────
_profile = params.get("provider_profile")

View File

@@ -3,7 +3,7 @@
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Hermes Setup</title>
<title>Hermes</title>
</head>
<body class="h-full antialiased">
<div id="root" class="h-full"></div>

View File

@@ -8,18 +8,24 @@ fn main() {
// `option_env!()` macro to default the install-script reference.
// Precedence (matches install.ps1's own arg precedence): commit > branch.
//
// Resolution order:
// 1. Env var override at build time (HERMES_BUILD_PIN_COMMIT, etc.).
// Useful for CI builds that want to pin to a tagged release SHA
// rather than whatever the checkout's HEAD happens to be.
// 2. `git rev-parse HEAD` + `git rev-parse --abbrev-ref HEAD` against
// the repo this build.rs lives in. Default for `cargo tauri build`
// from a dev machine — pins the produced .exe to your current
// checkout state.
// 3. Last-resort fallback: hardcoded `main` branch, no commit. The
// installer will fetch HEAD-of-main at runtime. Used when the
// build is happening outside a git checkout (e.g. cargo install
// from a packaged crate, unlikely for this binary but defensive).
// The COMMIT pin is opt-in. By default a dev build pins ONLY the branch,
// so the produced installer follows that branch's HEAD at install time
// (tolerant of fast-forwards/new commits, and never references a SHA the
// local checkout hasn't pushed). Set HERMES_BUILD_PIN_COMMIT to bake an
// immutable commit pin for reproducible/release installers.
//
// Commit pin resolution:
// - HERMES_BUILD_PIN_COMMIT, if set and non-empty. Accepts a SHA, tag,
// or branch name; resolved to an immutable SHA via `git rev-parse`
// when possible, else used verbatim if it already looks like a SHA.
// - Otherwise: NO commit pin (branch-follow is the default).
//
// Branch pin resolution:
// 1. HERMES_BUILD_PIN_BRANCH, if set and non-empty.
// 2. `git rev-parse --abbrev-ref HEAD` of the checkout this build.rs
// lives in — the current branch. (None on a detached HEAD.)
// 3. Last-resort fallback handled below: if neither commit nor branch
// resolves, warn — the binary needs a runtime arg or dev-repo env.
//
// Build script reruns on git HEAD change so a new commit triggers
// a rebuild without `cargo clean`.
@@ -30,11 +36,20 @@ fn main() {
if let Some(c) = &commit {
println!("cargo:rustc-env=BUILD_PIN_COMMIT={c}");
println!("cargo:warning=hermes-bootstrap: pinning to commit {}", short(c));
println!(
"cargo:warning=hermes-bootstrap: pinning to commit {}",
short(c)
);
}
if let Some(b) = &branch {
println!("cargo:rustc-env=BUILD_PIN_BRANCH={b}");
println!("cargo:warning=hermes-bootstrap: pinning to branch {b}");
match &commit {
Some(_) => println!("cargo:warning=hermes-bootstrap: pinning to branch {b}"),
None => println!(
"cargo:warning=hermes-bootstrap: following branch {b} HEAD (no commit pin; \
set HERMES_BUILD_PIN_COMMIT for an immutable pin)"
),
}
}
if commit.is_none() && branch.is_none() {
// Fail loudly rather than silently produce a binary that errors
@@ -46,8 +61,11 @@ fn main() {
);
}
// Rerun build.rs when HEAD moves so successive builds pick up new
// commits without needing `cargo clean`. .git/HEAD changes on every
// Rerun build.rs when HEAD moves. With branch-follow as the default the
// baked commit no longer changes per-commit, but a branch *switch* changes
// the detected branch name, so we still re-trigger. When an explicit
// HERMES_BUILD_PIN_COMMIT resolves a moving ref (tag/branch) to a SHA, a
// HEAD move can also change that resolution. .git/HEAD changes on every
// commit / branch switch / rebase.
let git_dir = locate_git_dir();
if let Some(gd) = &git_dir {
@@ -83,24 +101,46 @@ fn main() {
}
fn resolve_commit_pin() -> Option<String> {
if let Ok(v) = std::env::var("HERMES_BUILD_PIN_COMMIT") {
if !v.trim().is_empty() {
return Some(v.trim().to_string());
}
}
let out = Command::new("git")
.args(["rev-parse", "HEAD"])
.output()
.ok()?;
if !out.status.success() {
// Commit pinning is OPT-IN. Only bake a commit when the caller explicitly
// asks for one via HERMES_BUILD_PIN_COMMIT. With no env var, we return
// None and the installer follows the branch HEAD at install time.
let requested = std::env::var("HERMES_BUILD_PIN_COMMIT").ok()?;
let requested = requested.trim();
if requested.is_empty() {
return None;
}
let s = String::from_utf8(out.stdout).ok()?.trim().to_string();
if s.is_empty() {
None
} else {
Some(s)
// Resolve the request (which may be a SHA, tag, or branch name) to an
// immutable commit SHA so the baked pin is reproducible. `^{commit}`
// dereferences tags to the commit they point at.
if let Ok(out) = Command::new("git")
.args(["rev-parse", "--verify", &format!("{requested}^{{commit}}")])
.output()
{
if out.status.success() {
if let Ok(s) = String::from_utf8(out.stdout) {
let s = s.trim().to_string();
if !s.is_empty() {
return Some(s);
}
}
}
}
// Couldn't resolve via git (e.g. building outside a checkout). Accept the
// literal value only if it already looks like a SHA; otherwise fail loud
// rather than bake an unresolvable ref into the binary.
if is_sha(requested) {
return Some(requested.to_string());
}
panic!(
"HERMES_BUILD_PIN_COMMIT={requested:?} could not be resolved to a commit \
(git rev-parse failed and it is not a valid SHA)"
);
}
/// True if `s` looks like an abbreviated-or-full git SHA (7..=40 hex chars).
fn is_sha(s: &str) -> bool {
let len = s.len();
(7..=40).contains(&len) && s.chars().all(|c| c.is_ascii_hexdigit())
}
fn resolve_branch_pin() -> Option<String> {

View File

@@ -21,7 +21,7 @@ use serde::{Deserialize, Serialize};
use tauri::{AppHandle, Emitter, State};
use tokio::sync::{mpsc, Mutex};
use crate::events::{BootstrapEvent, Manifest, StageState};
use crate::events::{BootstrapEvent, LogStream, Manifest, StageState};
use crate::install_script::{self, Pin, ScriptKind, ScriptSource};
use crate::powershell::{self, StreamSink};
use crate::AppState;
@@ -179,9 +179,11 @@ pub async fn launch_hermes_desktop(
tracing::info!(?exe_path, "launching Hermes desktop");
// Detach from us — the installer is about to exit.
let mut cmd = tokio::process::Command::new(&exe_path);
cmd.current_dir(exe_path.parent().unwrap_or(&install_root));
// Detach from us — the installer is about to exit. On macOS launch the
// bundle through LaunchServices instead of exec'ing Contents/MacOS/Hermes
// directly; this matches user double-click/open behavior and avoids cwd /
// quarantine oddities after a self-update rebuild.
let mut cmd = desktop_launch_command(&exe_path, &install_root);
#[cfg(target_os = "windows")]
{
use std::os::windows::process::CommandExt;
@@ -208,7 +210,7 @@ pub async fn launch_hermes_desktop(
/// Walks the well-known electron-builder unpacked-app paths under
/// `install_root`. Mirrors the resolver in `cmd_gui` (apps/desktop/release/
/// <os>-unpacked/<exe>).
fn resolve_hermes_desktop_exe(install_root: &std::path::Path) -> Option<PathBuf> {
pub(crate) fn resolve_hermes_desktop_exe(install_root: &std::path::Path) -> Option<PathBuf> {
let release_dir = install_root.join("apps").join("desktop").join("release");
let candidates: &[(&str, &str)] = if cfg!(target_os = "windows") {
&[
@@ -232,6 +234,108 @@ fn resolve_hermes_desktop_exe(install_root: &std::path::Path) -> Option<PathBuf>
None
}
pub(crate) fn resolve_hermes_desktop_app(install_root: &std::path::Path) -> Option<PathBuf> {
let exe = resolve_hermes_desktop_exe(install_root)?;
#[cfg(target_os = "macos")]
{
// .../Hermes.app/Contents/MacOS/Hermes -> .../Hermes.app
let app = exe.parent()?.parent()?.parent()?.to_path_buf();
if app.extension().and_then(|e| e.to_str()) == Some("app") && app.is_dir() {
return Some(app);
}
}
#[cfg(not(target_os = "macos"))]
{
return Some(exe);
}
#[allow(unreachable_code)]
None
}
/// True when a prior install completed (bootstrap-complete marker present) AND a
/// launchable desktop app exists on disk. Used by the installer's launcher fast
/// path so a bare re-open just opens Hermes instead of re-running setup.
pub(crate) fn hermes_is_installed(install_root: &std::path::Path) -> bool {
install_root.join(".hermes-bootstrap-complete").exists()
&& resolve_hermes_desktop_exe(install_root).is_some()
}
/// Spawn the already-built desktop app, detached. Returns Err if no built app
/// exists or the spawn fails, so the caller can fall back to showing the
/// installer UI.
pub(crate) fn spawn_installed_desktop(install_root: &std::path::Path) -> std::io::Result<()> {
let exe = resolve_hermes_desktop_exe(install_root).ok_or_else(|| {
std::io::Error::new(std::io::ErrorKind::NotFound, "no built Hermes desktop app")
})?;
let mut cmd = desktop_launch_command_std(&exe, install_root);
#[cfg(target_os = "windows")]
{
use std::os::windows::process::CommandExt;
// DETACHED_PROCESS = 0x00000008 — keep the desktop alive after the
// installer exits, mirroring launch_hermes_desktop. Kept correct here
// even though the only caller is macOS-gated today, so future reuse on
// Windows doesn't reintroduce the relaunch race.
cmd.creation_flags(0x0000_0008);
}
cmd.spawn().map(|_child| ())
}
#[cfg(target_os = "macos")]
pub(crate) fn open_macos_app_detached(app_bundle: &std::path::Path) -> std::io::Result<()> {
let mut cmd = std::process::Command::new("/usr/bin/open");
cmd.arg(app_bundle);
cmd.current_dir(crate::paths::hermes_home());
cmd.spawn().map(|_child| ())
}
#[cfg(target_os = "macos")]
fn app_bundle_for_exe(exe: &std::path::Path) -> Option<PathBuf> {
let app = exe.parent()?.parent()?.parent()?.to_path_buf();
if app.extension().and_then(|e| e.to_str()) == Some("app") && app.is_dir() {
Some(app)
} else {
None
}
}
fn desktop_launch_command(
exe_path: &std::path::Path,
install_root: &std::path::Path,
) -> tokio::process::Command {
#[cfg(target_os = "macos")]
{
if let Some(app_bundle) = app_bundle_for_exe(exe_path) {
let mut cmd = tokio::process::Command::new("/usr/bin/open");
cmd.arg(app_bundle);
cmd.current_dir(crate::paths::hermes_home());
return cmd;
}
}
let mut cmd = tokio::process::Command::new(exe_path);
cmd.current_dir(exe_path.parent().unwrap_or(install_root));
cmd
}
fn desktop_launch_command_std(
exe_path: &std::path::Path,
install_root: &std::path::Path,
) -> std::process::Command {
#[cfg(target_os = "macos")]
{
if let Some(app_bundle) = app_bundle_for_exe(exe_path) {
let mut cmd = std::process::Command::new("/usr/bin/open");
cmd.arg(app_bundle);
cmd.current_dir(crate::paths::hermes_home());
return cmd;
}
}
let mut cmd = std::process::Command::new(exe_path);
cmd.current_dir(exe_path.parent().unwrap_or(install_root));
cmd
}
// ---------------------------------------------------------------------------
// Bootstrap implementation
// ---------------------------------------------------------------------------
@@ -262,6 +366,7 @@ async fn run_bootstrap(
BootstrapEvent::Log {
stage: None,
line: line.to_string(),
stream: LogStream::Stdout,
},
);
// Bump to info-level so the line shows in bootstrap-installer.log
@@ -596,6 +701,7 @@ async fn run_install_script(
BootstrapEvent::Log {
stage: stage_for_stdout.clone(),
line: line.to_string(),
stream: LogStream::Stdout,
},
);
// Tee to the rolling installer log so we have a persistent
@@ -614,7 +720,8 @@ async fn run_install_script(
&app_for_stderr,
BootstrapEvent::Log {
stage: stage_for_stderr.clone(),
line: format!("stderr: {line}"),
line: line.to_string(),
stream: LogStream::Stderr,
},
);
// stderr-level lines get warn! so they're visually distinct
@@ -710,3 +817,90 @@ fn truncate(s: &str, max: usize) -> String {
format!("{}...", &s[..max])
}
}
#[cfg(test)]
mod tests {
use super::*;
use std::path::PathBuf;
use std::path::Path;
fn unique_tmp_dir(tag: &str) -> PathBuf {
let base = std::env::temp_dir().join(format!(
"hermes-bootstrap-test-{tag}-{}-{}",
std::process::id(),
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.unwrap()
.as_nanos()
));
std::fs::create_dir_all(&base).unwrap();
base
}
// Build a fake built-desktop release tree at the platform's expected path
// and return (install_root, expected_app_bundle_or_exe).
fn make_release_tree(install_root: &Path) -> PathBuf {
let release = install_root.join("apps").join("desktop").join("release");
if cfg!(target_os = "macos") {
let macos_dir = release
.join("mac-arm64")
.join("Hermes.app")
.join("Contents")
.join("MacOS");
std::fs::create_dir_all(&macos_dir).unwrap();
std::fs::write(macos_dir.join("Hermes"), b"#!/bin/sh\n").unwrap();
macos_dir.parent().unwrap().parent().unwrap().to_path_buf() // .../Hermes.app
} else if cfg!(target_os = "windows") {
let dir = release.join("win-unpacked");
std::fs::create_dir_all(&dir).unwrap();
let exe = dir.join("Hermes.exe");
std::fs::write(&exe, b"stub").unwrap();
exe
} else {
let dir = release.join("linux-unpacked");
std::fs::create_dir_all(&dir).unwrap();
let exe = dir.join("hermes");
std::fs::write(&exe, b"stub").unwrap();
exe
}
}
// The relaunch / install target is derived from the rebuilt desktop app.
// On macOS this MUST resolve to the .app bundle (what `open` relaunches and
// what the updater ditto's over /Applications/Hermes.app). A regression in
// this derivation breaks the post-update auto-relaunch, so guard it.
#[test]
fn resolve_hermes_desktop_app_finds_built_bundle() {
let root = unique_tmp_dir("app-ok");
let expected = make_release_tree(&root);
let resolved = resolve_hermes_desktop_app(&root)
.expect("should resolve the freshly-built desktop app");
#[cfg(target_os = "macos")]
{
assert_eq!(resolved, expected, "must resolve to the .app bundle");
assert_eq!(
resolved.extension().and_then(|e| e.to_str()),
Some("app"),
"relaunch target must be a .app bundle on macOS"
);
}
#[cfg(not(target_os = "macos"))]
{
assert_eq!(resolved, expected);
}
let _ = std::fs::remove_dir_all(&root);
}
#[test]
fn resolve_hermes_desktop_app_is_none_without_a_build() {
let root = unique_tmp_dir("app-none");
// No release tree created.
assert!(
resolve_hermes_desktop_app(&root).is_none(),
"no resolved app when nothing has been built"
);
let _ = std::fs::remove_dir_all(&root);
}
}

View File

@@ -51,6 +51,16 @@ pub enum StageState {
Failed,
}
/// Which pipe a raw log line came from. Reported as structured metadata so
/// the UI can style stderr subtly rather than mislabeling it as an error:
/// uv/pip/git/npm write normal progress to stderr by design.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize)]
#[serde(rename_all = "lowercase")]
pub enum LogStream {
Stdout,
Stderr,
}
/// The single event channel `bootstrap` emits these. `type` discriminates.
#[derive(Debug, Clone, Serialize)]
#[serde(tag = "type", rename_all = "lowercase")]
@@ -72,11 +82,14 @@ pub enum BootstrapEvent {
#[serde(skip_serializing_if = "Option::is_none")]
error: Option<String>,
},
/// Raw stdout/stderr line from install.ps1 (or our wrapper).
/// Raw stdout/stderr line from install.ps1 (or our wrapper). `stream`
/// tells the UI which pipe it came from so stderr can be styled subtly
/// instead of being mislabeled as an error.
Log {
#[serde(skip_serializing_if = "Option::is_none")]
stage: Option<String>,
line: String,
stream: LogStream,
},
/// Sent once when all stages complete successfully.
Complete {

View File

@@ -50,6 +50,20 @@ impl AppMode {
}
}
/// Returns true when the args request a forced installer UI (repair/reinstall)
/// via `--reinstall` or `--repair`, which overrides the macOS launcher
/// fast-path so a broken install can be repaired. Arg-iterator generic so it's
/// unit-testable, mirroring `AppMode::from_args`. Independent of mode selection:
/// these flags never flip Install<->Update.
pub fn force_setup_from_args<I, S>(args: I) -> bool
where
I: IntoIterator<Item = S>,
S: AsRef<str>,
{
args.into_iter()
.any(|a| a.as_ref() == "--reinstall" || a.as_ref() == "--repair")
}
/// Process-wide install state, shared across Tauri commands.
///
/// The bootstrap is a one-shot, single-tenant process — we only need one
@@ -85,7 +99,11 @@ pub fn run() {
let _guard = paths::init_logging();
let mode = AppMode::from_args(std::env::args().skip(1));
tracing::info!(?mode, "Hermes Setup starting");
// Escape hatch: `--reinstall`/`--repair` forces the installer UI even when
// Hermes is already installed, so users can re-run setup to repair a broken
// install instead of the launcher fast path silently relaunching the app.
let force_setup = force_setup_from_args(std::env::args().skip(1));
tracing::info!(?mode, force_setup, "Hermes installer starting");
tauri::Builder::default()
.plugin(tauri_plugin_dialog::init())
@@ -93,6 +111,60 @@ pub fn run() {
.plugin(tauri_plugin_process::init())
.plugin(tauri_plugin_shell::init())
.manage(Arc::new(AppState::new(mode)))
.setup(move |app| {
use tauri::Manager;
// Launcher fast path (macOS only): a bare ("Install") launch when
// Hermes is already installed should NOT show the installer or
// rebuild — it should just open the app, so the /Applications
// "Hermes" doubles as a normal launcher (first run installs, every
// later run launches instantly). The window is kept hidden until
// here via `"visible": false` so this path never flashes a window.
//
// Gated to macOS deliberately: on Windows/Linux the installer keeps
// its existing behavior (Windows users relaunch via the Start
// Menu/Desktop "Hermes" shortcuts that install.ps1 creates, and a
// reliable detached relaunch there needs the DETACHED_PROCESS +
// startup-grace handling used by launch_hermes_desktop — out of
// scope here). So this is a pure no-op on non-macOS.
//
// `--reinstall`/`--repair` opts out so a broken install can be
// repaired by re-running setup instead of launching the bad app.
if cfg!(target_os = "macos") && mode == AppMode::Install && !force_setup {
let install_root = paths::hermes_home().join("hermes-agent");
if bootstrap::hermes_is_installed(&install_root) {
match bootstrap::spawn_installed_desktop(&install_root) {
Ok(()) => {
// Brief grace so the spawned app is registered
// before we exit (mirrors launch_hermes_desktop).
std::thread::sleep(std::time::Duration::from_millis(200));
tracing::info!(
"hermes already installed — relaunched desktop; exiting installer"
);
app.handle().exit(0);
return Ok(());
}
Err(err) => {
tracing::warn!(
?err,
"relaunch of installed desktop failed; showing installer UI"
);
}
}
}
}
// First run / repair install, or Update mode: reveal the UI.
match app.get_webview_window("main") {
Some(win) => {
if let Err(err) = win.show() {
tracing::error!(?err, "failed to show main installer window");
}
}
None => {
tracing::error!("main installer window not found; installer UI will not appear");
}
}
Ok(())
})
.invoke_handler(tauri::generate_handler![
// Mode (install vs update)
get_mode,
@@ -115,7 +187,7 @@ pub fn run() {
#[cfg(test)]
mod tests {
use super::AppMode;
use super::{force_setup_from_args, AppMode};
#[test]
fn bare_args_are_install() {
@@ -131,4 +203,30 @@ mod tests {
AppMode::Update
);
}
#[test]
fn reinstall_and_repair_flags_force_setup() {
assert!(force_setup_from_args(["--reinstall"]));
assert!(force_setup_from_args(["--repair"]));
assert!(force_setup_from_args(["--foo", "--repair", "--bar"]));
}
#[test]
fn bare_or_unrelated_args_do_not_force_setup() {
assert!(!force_setup_from_args(Vec::<String>::new()));
assert!(!force_setup_from_args(["--foo", "bar"]));
// --update must not be mistaken for a force-setup flag.
assert!(!force_setup_from_args(["--update"]));
}
#[test]
fn force_setup_flags_do_not_affect_mode_selection() {
// The repair flags must never flip Install<->Update.
assert_eq!(AppMode::from_args(["--reinstall"]), AppMode::Install);
assert_eq!(AppMode::from_args(["--repair"]), AppMode::Install);
assert_eq!(
AppMode::from_args(["--update", "--reinstall"]),
AppMode::Update
);
}
}

View File

@@ -45,6 +45,14 @@ pub async fn run_script(
) -> Result<ScriptResult> {
let mut cmd = build_command(script_path, args);
// The installer can be launched from a .app bundle that is later replaced
// during self-update. Pin child scripts to a stable directory so bash/zsh
// never starts from a deleted cwd and emits getcwd/job-working-directory
// errors at the end of an otherwise successful install.
if let Some(cwd) = stable_script_cwd(script_path, hermes_home_override) {
cmd.current_dir(cwd);
}
if let Some(home) = hermes_home_override {
cmd.env("HERMES_HOME", home);
}
@@ -146,6 +154,16 @@ pub async fn run_script(
})
}
fn stable_script_cwd<'a>(script_path: &'a Path, hermes_home_override: Option<&'a str>) -> Option<&'a Path> {
if let Some(home) = hermes_home_override {
let path = Path::new(home);
if path.is_dir() {
return Some(path);
}
}
script_path.parent().filter(|p| p.is_dir())
}
async fn recv_cancel(rx: &mut Option<CancelRx>) {
match rx {
Some(r) => {
@@ -264,4 +282,11 @@ info line
assert!(parse_stage_result("just banner\n").is_none());
assert!(parse_manifest("just banner\n").is_none());
}
#[test]
fn stable_script_cwd_prefers_existing_hermes_home() {
let script = Path::new("/tmp/install.sh");
let cwd = stable_script_cwd(script, Some("/"));
assert_eq!(cwd, Some(Path::new("/")));
}
}

View File

@@ -19,8 +19,11 @@
//! the no-window creation flag — both already cfg-gated. Keep new logic
//! OS-agnostic so the mac/linux port stays "fill in the paths".
use std::env;
use std::ffi::OsString;
use std::path::{Path, PathBuf};
use std::process::Stdio;
use std::sync::atomic::{AtomicBool, Ordering};
use std::time::{Duration, Instant};
use anyhow::{anyhow, Result};
@@ -28,7 +31,7 @@ use tauri::{AppHandle, Emitter};
use tokio::io::{AsyncBufReadExt, BufReader};
use tokio::process::Command;
use crate::events::{BootstrapEvent, StageInfo, StageState};
use crate::events::{BootstrapEvent, LogStream, StageInfo, StageState};
/// `hermes update` exit code meaning "another hermes process is holding the
/// venv shim open / dirty precondition" — see _cmd_update_impl in
@@ -40,10 +43,48 @@ const UPDATE_EXIT_CONCURRENT: i32 = 2;
const DESKTOP_EXIT_WAIT: Duration = Duration::from_secs(20);
const DESKTOP_EXIT_POLL: Duration = Duration::from_millis(500);
/// Guards against concurrent update runs. The frontend kicks `startUpdate()`
/// from a mount effect, which can fire more than once (React strict-mode
/// double-invokes effects in dev; a window reload or stray re-init can do it
/// in prod). Two `run_update` tasks racing on `git stash` corrupt the working
/// tree — one stashes the changes the other then can't find. Exactly one task
/// may hold this flag at a time.
static UPDATE_RUNNING: AtomicBool = AtomicBool::new(false);
/// Frontend → Rust: kick off the update flow. Mirrors `start_bootstrap`'s
/// fire-and-forget shape; progress arrives on the `bootstrap` event channel.
#[tauri::command]
pub async fn start_update(app: AppHandle) -> Result<(), String> {
// Re-entrancy guard (see UPDATE_RUNNING). compare_exchange lets exactly one
// caller flip false→true; any concurrent caller no-ops instead of spawning
// a second racing update.
if UPDATE_RUNNING
.compare_exchange(false, true, Ordering::SeqCst, Ordering::SeqCst)
.is_err()
{
// Already running: re-emit the manifest so a duplicate startUpdate()
// call (which resets the frontend store) can recover its stage list.
let target_app = if cfg!(target_os = "macos") {
target_app_from_args(std::env::args().skip(1))
} else {
None
};
let mut stages = vec![
stage_info("update", "Updating Hermes"),
stage_info("rebuild", "Rebuilding the desktop app"),
];
if cfg!(target_os = "macos") && target_app.is_some() {
stages.push(stage_info("install", "Installing the updated app"));
}
emit(
&app,
BootstrapEvent::Manifest {
stages,
protocol_version: None,
},
);
return Ok(());
}
tokio::spawn(async move {
if let Err(err) = run_update(app.clone()).await {
// run_update already emits a Failed event on the paths that matter;
@@ -56,6 +97,7 @@ pub async fn start_update(app: AppHandle) -> Result<(), String> {
},
);
}
UPDATE_RUNNING.store(false, Ordering::SeqCst);
});
Ok(())
}
@@ -63,6 +105,14 @@ pub async fn start_update(app: AppHandle) -> Result<(), String> {
async fn run_update(app: AppHandle) -> Result<()> {
let hermes_home = crate::paths::hermes_home();
let install_root = hermes_home.join("hermes-agent");
let update_branch = update_branch_from_args(std::env::args().skip(1))
.or_else(|| option_env_string("BUILD_PIN_BRANCH"))
.unwrap_or_else(|| "main".to_string());
let target_app = if cfg!(target_os = "macos") {
target_app_from_args(std::env::args().skip(1))
} else {
None
};
let hermes = resolve_hermes(&install_root).ok_or_else(|| {
let msg = format!(
@@ -81,13 +131,18 @@ async fn run_update(app: AppHandle) -> Result<()> {
})?;
// Synthetic manifest so the existing progress UI renders our two stages.
let mut stages = vec![
stage_info("update", "Updating Hermes"),
stage_info("rebuild", "Rebuilding the desktop app"),
];
if cfg!(target_os = "macos") && target_app.is_some() {
stages.push(stage_info("install", "Installing the updated app"));
}
emit(
&app,
BootstrapEvent::Manifest {
stages: vec![
stage_info("update", "Updating Hermes"),
stage_info("rebuild", "Rebuilding the desktop app"),
],
stages,
protocol_version: None,
},
);
@@ -107,12 +162,17 @@ async fn run_update(app: AppHandle) -> Result<()> {
// reports "already up to date" against the wrong branch. The desktop
// detected the update against this same branch, so we must update against
// it too.
let pin_branch = option_env_string("BUILD_PIN_BRANCH");
let mut update_args: Vec<&str> = vec!["update", "--yes", "--gateway"];
if let Some(b) = pin_branch.as_deref() {
update_args.push("--branch");
update_args.push(b);
}
emit_log(
&app,
Some("update"),
LogStream::Stdout,
&format!("[update] updating against branch {update_branch}"),
);
let child_env = update_child_env(&install_root);
let mut update_args: Vec<String> =
vec!["update".into(), "--yes".into(), "--gateway".into()];
update_args.push("--branch".into());
update_args.push(update_branch);
emit_stage(&app, "update", StageState::Running, None, None);
let started = Instant::now();
@@ -121,6 +181,7 @@ async fn run_update(app: AppHandle) -> Result<()> {
&hermes,
&update_args,
&install_root,
&child_env,
Some("update"),
)
.await?;
@@ -182,11 +243,13 @@ async fn run_update(app: AppHandle) -> Result<()> {
// repo-root deps with --workspaces=false). This is the rebuild it skips.
emit_stage(&app, "rebuild", StageState::Running, None, None);
let started = Instant::now();
let rebuild_args: Vec<String> = vec!["desktop".into(), "--build-only".into()];
let rebuild = run_streamed(
&app,
&hermes,
&["desktop", "--build-only"],
&rebuild_args,
&install_root,
&child_env,
Some("rebuild"),
)
.await?;
@@ -217,6 +280,43 @@ async fn run_update(app: AppHandle) -> Result<()> {
}
emit_stage(&app, "rebuild", StageState::Succeeded, Some(rebuild_ms), None);
let launch_target = if let Some(target_app) = target_app {
let started = Instant::now();
emit_stage(&app, "install", StageState::Running, None, None);
match install_macos_app_update(&app, &install_root, &target_app).await {
Ok(installed_app) => {
emit_stage(
&app,
"install",
StageState::Succeeded,
Some(started.elapsed().as_millis() as u64),
None,
);
Some(installed_app)
}
Err(err) => {
let msg = format!("{err:#}");
emit_stage(
&app,
"install",
StageState::Failed,
Some(started.elapsed().as_millis() as u64),
Some(msg.clone()),
);
emit(
&app,
BootstrapEvent::Failed {
stage: Some("install".into()),
error: msg.clone(),
},
);
return Err(anyhow!(msg));
}
}
} else {
None
};
// ---- done: signal complete, then launch the fresh desktop ------------
emit(
&app,
@@ -226,10 +326,17 @@ async fn run_update(app: AppHandle) -> Result<()> {
},
);
// Reuse the same detached-launch + app.exit(0) used post-install.
if let Err(err) =
crate::bootstrap::launch_hermes_desktop(app.clone(), install_root.to_string_lossy().into_owned())
.await
if let Some(target_app) = launch_target {
if let Err(err) = launch_macos_app_and_exit(&app, &target_app).await {
emit_log(
&app,
None,
LogStream::Stderr,
&format!("[update] could not auto-launch desktop: {err}. Launch Hermes manually."),
);
}
} else if let Err(err) =
crate::bootstrap::launch_hermes_desktop(app.clone(), install_root.to_string_lossy().into_owned()).await
{
// Launch failed: don't hard-fail the update (it succeeded); surface a
// log line so the success screen can still tell the user to launch
@@ -237,6 +344,7 @@ async fn run_update(app: AppHandle) -> Result<()> {
emit_log(
&app,
None,
LogStream::Stdout,
&format!("[update] could not auto-launch desktop: {err}. Launch Hermes manually."),
);
}
@@ -251,7 +359,7 @@ async fn wait_for_venv_free(install_root: &Path, app: &AppHandle) {
let shim = venv_hermes(install_root);
let deadline = Instant::now() + DESKTOP_EXIT_WAIT;
emit_log(app, Some("update"), "[update] waiting for Hermes to exit…");
emit_log(app, Some("update"), LogStream::Stdout, "[update] waiting for Hermes to exit…");
loop {
if !is_locked(&shim) {
@@ -261,6 +369,7 @@ async fn wait_for_venv_free(install_root: &Path, app: &AppHandle) {
emit_log(
app,
Some("update"),
LogStream::Stdout,
"[update] timed out waiting for Hermes to exit; proceeding anyway",
);
return;
@@ -289,8 +398,9 @@ fn is_locked(path: &Path) -> bool {
async fn run_streamed(
app: &AppHandle,
program: &Path,
args: &[&str],
args: &[String],
cwd: &Path,
envs: &[(String, OsString)],
stage: Option<&str>,
) -> Result<CmdResult> {
let mut cmd = Command::new(program);
@@ -299,6 +409,9 @@ async fn run_streamed(
.stdin(Stdio::null())
.stdout(Stdio::piped())
.stderr(Stdio::piped());
for (key, value) in envs {
cmd.env(key, value);
}
#[cfg(target_os = "windows")]
{
@@ -320,22 +433,22 @@ async fn run_streamed(
loop {
tokio::select! {
line = out.next_line() => match line {
Ok(Some(l)) => emit_log(app, stage_owned.as_deref(), &l),
Ok(Some(l)) => emit_log(app, stage_owned.as_deref(), LogStream::Stdout, &l),
Ok(None) => break,
Err(e) => { tracing::warn!("stdout read error: {e}"); break; }
},
line = err.next_line() => match line {
Ok(Some(l)) => emit_log(app, stage_owned.as_deref(), &format!("stderr: {l}")),
Ok(Some(l)) => emit_log(app, stage_owned.as_deref(), LogStream::Stderr, &l),
Ok(None) => {}
Err(e) => { tracing::warn!("stderr read error: {e}"); }
},
}
}
while let Ok(Some(l)) = out.next_line().await {
emit_log(app, stage_owned.as_deref(), &l);
emit_log(app, stage_owned.as_deref(), LogStream::Stdout, &l);
}
while let Ok(Some(l)) = err.next_line().await {
emit_log(app, stage_owned.as_deref(), &format!("stderr: {l}"));
emit_log(app, stage_owned.as_deref(), LogStream::Stderr, &l);
}
let status = child.wait().await.map_err(|e| anyhow!("waiting for child: {e}"))?;
@@ -378,6 +491,225 @@ fn resolve_hermes(install_root: &Path) -> Option<PathBuf> {
None
}
fn update_child_env(install_root: &Path) -> Vec<(String, OsString)> {
let hermes_home = crate::paths::hermes_home();
let mut envs = vec![(
"HERMES_HOME".to_string(),
hermes_home.as_os_str().to_os_string(),
)];
if let Some(path) = path_with_prepended_entries(&[
hermes_home.join("node").join("bin"),
venv_bin_dir(install_root),
]) {
envs.push(("PATH".to_string(), path));
}
envs
}
fn venv_bin_dir(install_root: &Path) -> PathBuf {
if cfg!(target_os = "windows") {
install_root.join("venv").join("Scripts")
} else {
install_root.join("venv").join("bin")
}
}
fn path_with_prepended_entries(entries: &[PathBuf]) -> Option<OsString> {
let mut parts: Vec<PathBuf> = entries.to_vec();
if let Some(existing) = env::var_os("PATH") {
parts.extend(env::split_paths(&existing));
}
env::join_paths(parts).ok()
}
fn update_branch_from_args<I, S>(args: I) -> Option<String>
where
I: IntoIterator<Item = S>,
S: AsRef<str>,
{
arg_value_from_args(args, "--branch")
.map(|s| s.trim().to_string())
.filter(|s| !s.is_empty())
}
fn target_app_from_args<I, S>(args: I) -> Option<PathBuf>
where
I: IntoIterator<Item = S>,
S: AsRef<str>,
{
arg_value_from_args(args, "--target-app")
.map(PathBuf::from)
.filter(|p| p.extension().and_then(|e| e.to_str()) == Some("app"))
}
fn arg_value_from_args<I, S>(args: I, name: &str) -> Option<String>
where
I: IntoIterator<Item = S>,
S: AsRef<str>,
{
let mut iter = args.into_iter().map(|s| s.as_ref().to_string()).peekable();
while let Some(arg) = iter.next() {
if arg == name {
return iter.next();
}
if let Some(value) = arg.strip_prefix(&format!("{name}=")) {
return Some(value.to_string());
}
}
None
}
#[cfg(target_os = "macos")]
async fn install_macos_app_update(
app: &AppHandle,
install_root: &Path,
target_app: &Path,
) -> Result<PathBuf> {
if target_app.extension().and_then(|e| e.to_str()) != Some("app") {
return Err(anyhow!(
"refusing to install update into non-app path: {}",
target_app.display()
));
}
let rebuilt_app = crate::bootstrap::resolve_hermes_desktop_app(install_root).ok_or_else(|| {
anyhow!(
"desktop rebuild succeeded but no Hermes.app was found under {}",
install_root.join("apps").join("desktop").join("release").display()
)
})?;
let same = match (rebuilt_app.canonicalize(), target_app.canonicalize()) {
(Ok(a), Ok(b)) => a == b,
_ => rebuilt_app == target_app,
};
if same {
emit_log(
app,
Some("install"),
LogStream::Stdout,
&format!(
"[update] rebuilt app is already the launch target: {}",
target_app.display()
),
);
return Ok(target_app.to_path_buf());
}
emit_log(
app,
Some("install"),
LogStream::Stdout,
&format!(
"[update] installing rebuilt app {} -> {}",
rebuilt_app.display(),
target_app.display()
),
);
if let Some(parent) = target_app.parent() {
tokio::fs::create_dir_all(parent).await?;
}
let tmp = PathBuf::from(format!("{}.hermes-update-new", target_app.display()));
let old = PathBuf::from(format!("{}.hermes-update-old", target_app.display()));
remove_dir_if_exists(&tmp).await;
remove_dir_if_exists(&old).await;
let ditto = Command::new("/usr/bin/ditto")
.arg(&rebuilt_app)
.arg(&tmp)
.current_dir(crate::paths::hermes_home())
.status()
.await
.map_err(|e| anyhow!("running ditto: {e}"))?;
if !ditto.success() {
return Err(anyhow!(
"ditto failed while copying updated app into {}",
tmp.display()
));
}
// Atomic-as-possible swap with rollback. Extracted so the invariant
// (target is never left deleted-with-no-replacement) can be unit-tested
// without ditto / a real .app bundle.
swap_in_new_bundle(&tmp, target_app, &old).await?;
let _ = Command::new("/usr/bin/xattr")
.arg("-dr")
.arg("com.apple.quarantine")
.arg(target_app)
.current_dir(crate::paths::hermes_home())
.status()
.await;
Ok(target_app.to_path_buf())
}
/// Move a freshly-staged bundle (`tmp`) into place at `target`, parking any
/// existing bundle at `old` so the move can succeed (macOS `rename` won't
/// overwrite a non-empty directory).
///
/// Invariant: on ANY failure path, `target` is left pointing at a working
/// bundle — either the original (rolled back from `old`) or untouched — and we
/// never delete the running app with no replacement in place. The staged `tmp`
/// copy is cleaned up on failure.
async fn swap_in_new_bundle(tmp: &Path, target: &Path, old: &Path) -> Result<()> {
let moved_old = if target.exists() {
if let Err(err) = tokio::fs::rename(target, old).await {
// Could not move the existing app aside. Leave it untouched and
// bail — a failed update must not brick the install.
remove_dir_if_exists(tmp).await;
return Err(anyhow!(
"could not move existing app aside at {} (leaving it in place): {err}",
target.display()
));
}
true
} else {
false
};
if let Err(err) = tokio::fs::rename(tmp, target).await {
// Restore the original app from the backup so the user keeps a working
// install, and clean up the staged copy.
if moved_old {
let _ = tokio::fs::rename(old, target).await;
}
remove_dir_if_exists(tmp).await;
return Err(anyhow!("installing updated app at {}: {err}", target.display()));
}
remove_dir_if_exists(old).await;
Ok(())
}
#[cfg(not(target_os = "macos"))]
async fn install_macos_app_update(
_app: &AppHandle,
_install_root: &Path,
target_app: &Path,
) -> Result<PathBuf> {
Ok(target_app.to_path_buf())
}
async fn remove_dir_if_exists(path: &Path) {
if path.exists() {
let _ = tokio::fs::remove_dir_all(path).await;
}
}
#[cfg(target_os = "macos")]
async fn launch_macos_app_and_exit(app: &AppHandle, target_app: &Path) -> Result<()> {
crate::bootstrap::open_macos_app_detached(target_app)
.map_err(|e| anyhow!("launching {}: {e}", target_app.display()))?;
tokio::time::sleep(std::time::Duration::from_millis(150)).await;
app.exit(0);
Ok(())
}
#[cfg(not(target_os = "macos"))]
async fn launch_macos_app_and_exit(_app: &AppHandle, _target_app: &Path) -> Result<()> {
Ok(())
}
// ---------------------------------------------------------------------------
// Event helpers — keep emit shape identical to bootstrap.rs so the UI is reused
// ---------------------------------------------------------------------------
@@ -429,7 +761,7 @@ fn emit_stage(
);
}
fn emit_log(app: &AppHandle, stage: Option<&str>, line: &str) {
fn emit_log(app: &AppHandle, stage: Option<&str>, stream: LogStream, line: &str) {
match stage {
Some(s) => tracing::info!(target: "bootstrap.log", stage = %s, "{line}"),
None => tracing::info!(target: "bootstrap.log", "{line}"),
@@ -439,6 +771,7 @@ fn emit_log(app: &AppHandle, stage: Option<&str>, line: &str) {
BootstrapEvent::Log {
stage: stage.map(|s| s.to_string()),
line: line.to_string(),
stream,
},
);
}
@@ -459,4 +792,118 @@ mod tests {
fn missing_file_is_not_locked() {
assert!(!is_locked(Path::new("/nonexistent/does/not/exist/xyz")));
}
#[test]
fn parses_update_branch_from_space_or_equals_args() {
assert_eq!(
update_branch_from_args(["--update", "--branch", "bb/test"]),
Some("bb/test".to_string())
);
assert_eq!(
update_branch_from_args(["--update", "--branch=main"]),
Some("main".to_string())
);
assert_eq!(update_branch_from_args(["--update"]), None);
}
#[test]
fn parses_only_app_targets() {
assert_eq!(
target_app_from_args(["--update", "--target-app", "/Applications/Hermes.app"]),
Some(PathBuf::from("/Applications/Hermes.app"))
);
assert_eq!(target_app_from_args(["--target-app", "/tmp/not-an-app"]), None);
}
// Helpers for the swap tests: make a throwaway dir tree we can rename.
fn unique_tmp_dir(tag: &str) -> PathBuf {
let base = std::env::temp_dir().join(format!(
"hermes-swap-test-{tag}-{}-{}",
std::process::id(),
std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.unwrap()
.as_nanos()
));
std::fs::create_dir_all(&base).unwrap();
base
}
fn write_marker(dir: &Path, contents: &str) {
std::fs::create_dir_all(dir).unwrap();
std::fs::write(dir.join("marker.txt"), contents).unwrap();
}
#[tokio::test]
async fn swap_installs_new_bundle_and_cleans_up() {
let base = unique_tmp_dir("ok");
let target = base.join("Hermes.app");
let tmp = base.join("Hermes.app.hermes-update-new");
let old = base.join("Hermes.app.hermes-update-old");
write_marker(&target, "OLD");
write_marker(&tmp, "NEW");
swap_in_new_bundle(&tmp, &target, &old).await.unwrap();
// New bundle is now at target; staging + backup dirs are gone.
assert_eq!(
std::fs::read_to_string(target.join("marker.txt")).unwrap(),
"NEW"
);
assert!(!tmp.exists(), "staged copy should be cleaned up");
assert!(!old.exists(), "backup should be cleaned up on success");
let _ = std::fs::remove_dir_all(&base);
}
#[tokio::test]
async fn swap_failure_never_leaves_target_missing() {
// Regression guard for the catastrophic path: the move-aside of the
// existing app fails AND the staged bundle can't be installed. The
// buggy version deleted `target` when move-aside failed and then
// skipped rollback, bricking the install. The fixed version must leave
// the original app intact on disk.
//
// Trigger both failures deterministically:
// - `old` is a NON-EMPTY dir -> rename(target, old) fails
// - `tmp` does not exist -> rename(tmp, target) fails
let base = unique_tmp_dir("fail");
let target = base.join("Hermes.app");
let tmp = base.join("Hermes.app.hermes-update-new"); // intentionally absent
let old = base.join("Hermes.app.hermes-update-old");
write_marker(&target, "OLD");
write_marker(&old, "OCCUPIED"); // non-empty => rename(target,old) fails
let result = swap_in_new_bundle(&tmp, &target, &old).await;
assert!(result.is_err(), "swap should fail when neither move can complete");
assert!(target.exists(), "original app must NOT be deleted on failure");
assert_eq!(
std::fs::read_to_string(target.join("marker.txt")).unwrap(),
"OLD",
"original app contents must be intact after a failed swap"
);
let _ = std::fs::remove_dir_all(&base);
}
#[tokio::test]
async fn swap_rolls_back_when_install_step_fails() {
// Move-aside succeeds but installing the staged bundle fails (tmp
// absent). The original must be rolled back from `old` to `target`.
let base = unique_tmp_dir("rollback");
let target = base.join("Hermes.app");
let tmp = base.join("Hermes.app.hermes-update-new"); // absent
let old = base.join("Hermes.app.hermes-update-old");
write_marker(&target, "OLD");
let result = swap_in_new_bundle(&tmp, &target, &old).await;
assert!(result.is_err());
assert!(target.exists(), "original must be restored after failed install");
assert_eq!(
std::fs::read_to_string(target.join("marker.txt")).unwrap(),
"OLD"
);
assert!(!old.exists(), "backup should be rolled back, not left behind");
let _ = std::fs::remove_dir_all(&base);
}
}

View File

@@ -1,6 +1,6 @@
{
"$schema": "https://schema.tauri.app/config/2",
"productName": "Hermes Setup",
"productName": "Hermes",
"version": "0.0.1",
"identifier": "com.nousresearch.hermes.setup",
"build": {
@@ -13,7 +13,7 @@
"windows": [
{
"label": "main",
"title": "Hermes Setup",
"title": "Hermes",
"width": 880,
"height": 620,
"minWidth": 720,
@@ -22,7 +22,8 @@
"fullscreen": false,
"decorations": true,
"transparent": false,
"center": true
"center": true,
"visible": false
}
],
"security": {
@@ -33,7 +34,7 @@
"bundle": {
"active": true,
"category": "DeveloperTool",
"shortDescription": "Hermes Setup",
"shortDescription": "Hermes",
"longDescription": "Installs Hermes Agent on your machine. Drives scripts/install.ps1 (Windows) and scripts/install.sh (macOS/Linux).",
"publisher": "Nous Research",
"copyright": "Copyright © 2026 Nous Research",

View File

@@ -3,8 +3,10 @@ import { useStore } from '@nanostores/react'
import { Button } from '../components/button'
import {
$logPath,
$mode,
openLogDir,
startInstall,
startUpdate,
type BootstrapStateModel
} from '../store'
import { RefreshCw, FileText } from 'lucide-react'
@@ -22,6 +24,8 @@ interface FailureProps {
*/
export default function Failure({ bootstrap }: FailureProps) {
const logPath = useStore($logPath)
const mode = useStore($mode)
const isUpdate = mode === 'update'
return (
<div className="hermes-fade-in flex h-full flex-col items-center justify-center gap-6 px-12 py-10">
@@ -37,24 +41,27 @@ export default function Failure({ bootstrap }: FailureProps) {
}
>
<span>
<span>Install didn&rsquo;t finish</span>
<span>{isUpdate ? 'Update didn\u2019t finish' : 'Install didn\u2019t finish'}</span>
</span>
<span aria-hidden="true">Install didn&rsquo;t finish</span>
<span aria-hidden="true">{isUpdate ? 'Update didn\u2019t finish' : 'Install didn\u2019t finish'}</span>
</p>
<p className="m-0 mx-auto max-w-xl text-center text-sm leading-normal tracking-tight text-muted-foreground">
{bootstrap.error ?? 'Something went wrong during installation.'}
{bootstrap.error ??
(isUpdate
? 'Something went wrong during the update.'
: 'Something went wrong during installation.')}
</p>
</div>
<div className="flex items-center gap-3">
<Button
onClick={() => void startInstall()}
onClick={() => void (isUpdate ? startUpdate() : startInstall())}
size="lg"
className="inline-flex items-center gap-2 px-6"
>
<RefreshCw size={16} />
Retry install
{isUpdate ? 'Retry update' : 'Retry install'}
</Button>
<Button
variant="outline"

View File

@@ -115,9 +115,7 @@ export default function ProgressScreen({ bootstrap }: ProgressProps) {
key={idx}
className={clsx(
'whitespace-pre-wrap',
entry.line.startsWith('stderr:')
? 'text-destructive'
: 'text-foreground/70'
entry.stream === 'stderr' ? 'text-foreground/45' : 'text-foreground/70'
)}
>
{entry.line}

View File

@@ -42,7 +42,7 @@ export interface BootstrapStateModel {
currentStage: string | null
installRoot: string | null
error: string | null
logs: Array<{ stage?: string; line: string }>
logs: Array<{ stage?: string; line: string; stream?: 'stdout' | 'stderr' }>
}
const INITIAL: BootstrapStateModel = {
@@ -106,6 +106,7 @@ interface BootstrapLogEvent {
type: 'log'
stage?: string
line: string
stream?: 'stdout' | 'stderr'
}
interface BootstrapCompleteEvent {
@@ -192,7 +193,7 @@ export async function initialize(): Promise<void> {
break
}
case 'log': {
const logs = [...cur.logs, { stage: payload.stage, line: payload.line }]
const logs = [...cur.logs, { stage: payload.stage, line: payload.line, stream: payload.stream }]
// Keep the rolling buffer bounded so the UI doesn't get OOM'd
// during a long install (playwright chromium download is ~10k lines).
const trimmed = logs.length > 2000 ? logs.slice(-2000) : logs

View File

@@ -111,15 +111,28 @@ npm run test:desktop:all
Boot logs land in `HERMES_HOME/logs/desktop.log` (includes backend output and recent Python tracebacks) — check it first if the app reports a boot failure.
**macOS / Linux:**
```bash
# Force a clean first-launch setup
rm "$HOME/.hermes/hermes-agent/.hermes-bootstrap-complete" # macOS/Linux
rm "$HOME/.hermes/hermes-agent/.hermes-bootstrap-complete"
# Rebuild a broken Python venv
rm -rf "$HOME/.hermes/hermes-agent/venv" # macOS/Linux
# Reset a stuck macOS microphone prompt
rm -rf "$HOME/.hermes/hermes-agent/venv"
# Reset a stuck macOS microphone prompt (macOS only)
tccutil reset Microphone com.nousresearch.hermes
```
**Windows (PowerShell):**
```powershell
# Force a clean first-launch setup
Remove-Item "$env:LOCALAPPDATA\hermes\hermes-agent\.hermes-bootstrap-complete"
# Rebuild a broken Python venv
Remove-Item -Recurse -Force "$env:LOCALAPPDATA\hermes\hermes-agent\venv"
```
> The default Hermes home on Windows is `%LOCALAPPDATA%\hermes`. Set the `HERMES_HOME` env var if you've relocated it.
---
## Community

View File

@@ -32,8 +32,58 @@ function bundledRuntimeImportCheck(platform = process.platform) {
return platform === 'win32' ? 'import fastapi, uvicorn, winpty' : 'import fastapi, uvicorn, ptyprocess'
}
const GPU_OVERRIDE_ON = new Set(['1', 'true', 'yes', 'on'])
const GPU_OVERRIDE_OFF = new Set(['0', 'false', 'no', 'off'])
/**
* Decide whether the app is being shown over a remote/forwarded display, where
* Chromium's GPU compositor produces an unstable, flickering surface (it can't
* present accelerated layers cleanly over the wire). Native local Windows/macOS
* sessions composite locally and never hit this, so we only fall back to
* software rendering when a remote display is detected.
*
* Returns a short reason string when GPU acceleration should be disabled, or
* null to keep it enabled. `HERMES_DESKTOP_DISABLE_GPU` overrides detection
* both ways (1/true/yes/on → always disable, 0/false/no/off → never disable).
*
* Pure + dependency-free so it can be unit-tested and called before app ready.
*/
function detectRemoteDisplay(options = {}) {
const env = options.env ?? process.env
const platform = options.platform ?? process.platform
const override = String(env.HERMES_DESKTOP_DISABLE_GPU || '').trim().toLowerCase()
if (GPU_OVERRIDE_ON.has(override)) return 'override (HERMES_DESKTOP_DISABLE_GPU)'
if (GPU_OVERRIDE_OFF.has(override)) return null
// Launched from an SSH session → the display is X11-forwarded or otherwise
// remote. Covers the common `ssh user@box` + GUI-forwarding case.
if (env.SSH_CONNECTION || env.SSH_CLIENT || env.SSH_TTY) return 'ssh-session'
if (platform === 'linux') {
// X11 forwarding sets DISPLAY to "<host>:N" (e.g. "localhost:10.0"); a
// local X server is ":0"/":1" with no host part before the colon.
// NB: WSLg deliberately isn't treated as remote — it reports
// GPU-accelerated vGPU surfaces locally and doesn't show the flicker.
const display = String(env.DISPLAY || '')
if (display.includes(':') && display.split(':')[0]) {
return `x11-forwarding (DISPLAY=${display})`
}
}
if (platform === 'win32') {
// RDP sessions report SESSIONNAME like "RDP-Tcp#7"; the local console is
// "Console".
const sessionName = String(env.SESSIONNAME || '')
if (/^rdp-/i.test(sessionName)) return `rdp (SESSIONNAME=${sessionName})`
}
return null
}
module.exports = {
bundledRuntimeImportCheck,
detectRemoteDisplay,
isWindowsBinaryPathInWsl,
isWslEnvironment
}

View File

@@ -3,7 +3,12 @@ const fs = require('node:fs')
const path = require('node:path')
const test = require('node:test')
const { bundledRuntimeImportCheck, isWindowsBinaryPathInWsl, isWslEnvironment } = require('./bootstrap-platform.cjs')
const {
bundledRuntimeImportCheck,
detectRemoteDisplay,
isWindowsBinaryPathInWsl,
isWslEnvironment
} = require('./bootstrap-platform.cjs')
test('isWslEnvironment detects WSL2 env vars on linux', () => {
assert.equal(isWslEnvironment({ WSL_DISTRO_NAME: 'Ubuntu' }, 'linux'), true)
@@ -28,6 +33,53 @@ test('bundledRuntimeImportCheck selects platform-specific import checks', () =>
assert.equal(bundledRuntimeImportCheck('linux'), 'import fastapi, uvicorn, ptyprocess')
})
test('detectRemoteDisplay keeps GPU on for local sessions', () => {
// Plain local X11, Wayland, native Windows, native macOS — no remote signal.
assert.equal(detectRemoteDisplay({ env: { DISPLAY: ':0' }, platform: 'linux' }), null)
assert.equal(detectRemoteDisplay({ env: { WAYLAND_DISPLAY: 'wayland-0' }, platform: 'linux' }), null)
assert.equal(detectRemoteDisplay({ env: { SESSIONNAME: 'Console' }, platform: 'win32' }), null)
assert.equal(detectRemoteDisplay({ env: {}, platform: 'darwin' }), null)
})
test('detectRemoteDisplay does not treat WSLg as remote', () => {
// WSLg renders locally via vGPU and doesn't show the flicker, so a WSL
// session with a local DISPLAY keeps hardware acceleration on.
assert.equal(detectRemoteDisplay({ env: { WSL_DISTRO_NAME: 'Ubuntu', DISPLAY: ':0' }, platform: 'linux' }), null)
assert.equal(detectRemoteDisplay({ env: { WSL_INTEROP: '/run/WSL/1_interop', DISPLAY: ':0' }, platform: 'linux' }), null)
})
test('detectRemoteDisplay flags SSH sessions on any platform', () => {
assert.equal(detectRemoteDisplay({ env: { SSH_CONNECTION: '1.2.3.4 5 6.7.8.9 22' }, platform: 'linux' }), 'ssh-session')
assert.equal(detectRemoteDisplay({ env: { SSH_CLIENT: '1.2.3.4 5 22' }, platform: 'darwin' }), 'ssh-session')
assert.equal(detectRemoteDisplay({ env: { SSH_TTY: '/dev/pts/0' }, platform: 'win32' }), 'ssh-session')
})
test('detectRemoteDisplay flags forwarded X11 displays but not local ones', () => {
assert.match(String(detectRemoteDisplay({ env: { DISPLAY: 'localhost:10.0' }, platform: 'linux' })), /x11-forwarding/)
assert.match(String(detectRemoteDisplay({ env: { DISPLAY: '192.168.1.5:0' }, platform: 'linux' })), /x11-forwarding/)
assert.equal(detectRemoteDisplay({ env: { DISPLAY: ':1' }, platform: 'linux' }), null)
})
test('detectRemoteDisplay flags RDP sessions', () => {
assert.match(String(detectRemoteDisplay({ env: { SESSIONNAME: 'RDP-Tcp#7' }, platform: 'win32' })), /^rdp/)
})
test('detectRemoteDisplay honors the HERMES_DESKTOP_DISABLE_GPU override both ways', () => {
// Force-on even on a local display.
assert.match(
String(detectRemoteDisplay({ env: { HERMES_DESKTOP_DISABLE_GPU: '1', DISPLAY: ':0' }, platform: 'linux' })),
/override/
)
// Force-off even over SSH (escape hatch when a remote display has working accel).
assert.equal(
detectRemoteDisplay({
env: { HERMES_DESKTOP_DISABLE_GPU: 'false', SSH_CONNECTION: '1.2.3.4 5 6.7.8.9 22' },
platform: 'linux'
}),
null
)
})
test('packaged electron entrypoints do not require unpackaged npm modules', () => {
const electronDir = __dirname
const entrypoints = ['main.cjs', 'preload.cjs', 'bootstrap-platform.cjs']

View File

@@ -22,7 +22,7 @@
* { type: 'manifest', stages: [{name, title, category, needs_user_input}, ...] }
* { type: 'stage', name, state: 'running'|'succeeded'|'skipped'|'failed',
* json?, durationMs?, error? }
* { type: 'log', stage?, line } // raw line from install.ps1
* { type: 'log', stage?, line, stream: 'stdout'|'stderr' } // raw line from install.ps1
* { type: 'complete', marker: <written marker payload> }
* { type: 'failed', stage?, error } // bootstrap aborted
*
@@ -229,7 +229,7 @@ function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, herme
while ((nl = stdoutBuf.indexOf('\n')) !== -1) {
const line = stdoutBuf.slice(0, nl).replace(/\r$/, '')
stdoutBuf = stdoutBuf.slice(nl + 1)
if (line) emit && emit({ type: 'log', stage: stageName, line })
if (line) emit && emit({ type: 'log', stage: stageName, line, stream: 'stdout' })
}
})
@@ -241,7 +241,7 @@ function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, herme
while ((nl = stderrBuf.indexOf('\n')) !== -1) {
const line = stderrBuf.slice(0, nl).replace(/\r$/, '')
stderrBuf = stderrBuf.slice(nl + 1)
if (line) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${line}` })
if (line) emit && emit({ type: 'log', stage: stageName, line, stream: 'stderr' })
}
})
@@ -253,8 +253,8 @@ function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, herme
child.on('close', (code, signal) => {
if (abortSignal) abortSignal.removeEventListener('abort', onAbort)
// Flush any trailing bytes
if (stdoutBuf) emit && emit({ type: 'log', stage: stageName, line: stdoutBuf })
if (stderrBuf) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${stderrBuf}` })
if (stdoutBuf) emit && emit({ type: 'log', stage: stageName, line: stdoutBuf, stream: 'stdout' })
if (stderrBuf) emit && emit({ type: 'log', stage: stageName, line: stderrBuf, stream: 'stderr' })
resolve({ stdout, stderr, code, signal, killed })
})
})
@@ -299,7 +299,7 @@ function spawnBash(scriptPath, args, { emit, stageName, abortSignal, hermesHome
while ((nl = stdoutBuf.indexOf('\n')) !== -1) {
const line = stdoutBuf.slice(0, nl).replace(/\r$/, '')
stdoutBuf = stdoutBuf.slice(nl + 1)
if (line) emit && emit({ type: 'log', stage: stageName, line })
if (line) emit && emit({ type: 'log', stage: stageName, line, stream: 'stdout' })
}
})
@@ -311,7 +311,7 @@ function spawnBash(scriptPath, args, { emit, stageName, abortSignal, hermesHome
while ((nl = stderrBuf.indexOf('\n')) !== -1) {
const line = stderrBuf.slice(0, nl).replace(/\r$/, '')
stderrBuf = stderrBuf.slice(nl + 1)
if (line) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${line}` })
if (line) emit && emit({ type: 'log', stage: stageName, line, stream: 'stderr' })
}
})
@@ -322,8 +322,8 @@ function spawnBash(scriptPath, args, { emit, stageName, abortSignal, hermesHome
child.on('close', (code, signal) => {
if (abortSignal) abortSignal.removeEventListener('abort', onAbort)
if (stdoutBuf) emit && emit({ type: 'log', stage: stageName, line: stdoutBuf })
if (stderrBuf) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${stderrBuf}` })
if (stdoutBuf) emit && emit({ type: 'log', stage: stageName, line: stdoutBuf, stream: 'stdout' })
if (stderrBuf) emit && emit({ type: 'log', stage: stageName, line: stderrBuf, stream: 'stderr' })
resolve({ stdout, stderr, code, signal, killed })
})
})
@@ -482,6 +482,18 @@ async function runBootstrap(opts) {
writeMarker // callback to write the bootstrap-complete marker; main.cjs provides
} = opts
// Bail before spawning anything if the user already cancelled — otherwise an
// already-aborted signal would still fetch the manifest (a spawn) before the
// in-loop abort check fires.
if (abortSignal && abortSignal.aborted) {
if (typeof onEvent === 'function') {
try {
onEvent({ type: 'failed', error: 'bootstrap cancelled by user' })
} catch {}
}
return { ok: false, cancelled: true }
}
const runLog = openRunLog(logRoot || path.join(hermesHome, 'logs'))
// Tee every event to the runLog AND the caller's onEvent. This gives us a

View File

@@ -0,0 +1,27 @@
const assert = require('node:assert/strict')
const test = require('node:test')
const { runBootstrap } = require('./bootstrap-runner.cjs')
test('runBootstrap bails immediately when the signal is already aborted', async () => {
const controller = new AbortController()
controller.abort()
const events = []
const result = await runBootstrap({
installStamp: null,
activeRoot: '/tmp/hermes-runner-test',
sourceRepoRoot: null,
hermesHome: '/tmp/hermes-runner-test',
logRoot: '/tmp/hermes-runner-test',
onEvent: ev => events.push(ev),
abortSignal: controller.signal
})
// Cancelled before any install script is spawned.
assert.deepEqual(result, { ok: false, cancelled: true })
assert.ok(
events.some(ev => ev.type === 'failed' && /cancelled/i.test(ev.error)),
'should emit a cancelled failure event'
)
})

View File

@@ -8,5 +8,7 @@
<true/>
<key>com.apple.security.cs.disable-library-validation</key>
<true/>
<key>com.apple.security.device.audio-input</key>
<true/>
</dict>
</plist>

View File

@@ -8,6 +8,9 @@ const {
ipcMain,
nativeImage,
nativeTheme,
net: electronNet,
powerMonitor,
protocol,
safeStorage,
session,
shell,
@@ -21,7 +24,7 @@ const net = require('node:net')
const path = require('node:path')
const { fileURLToPath, pathToFileURL } = require('node:url')
const { execFileSync, spawn } = require('node:child_process')
const { isWindowsBinaryPathInWsl, isWslEnvironment } = require('./bootstrap-platform.cjs')
const { detectRemoteDisplay, isWindowsBinaryPathInWsl, isWslEnvironment } = require('./bootstrap-platform.cjs')
const { runBootstrap } = require('./bootstrap-runner.cjs')
const { canImportHermesCli, verifyHermesCli } = require('./backend-probes.cjs')
const {
@@ -71,6 +74,26 @@ const IS_MAC = process.platform === 'darwin'
const IS_WINDOWS = process.platform === 'win32'
const IS_WSL = isWslEnvironment()
const APP_ROOT = app.getAppPath()
// Remote displays (SSH X11 forwarding, VNC, RDP) make Chromium's GPU
// compositor flicker — accelerated layers can't be presented cleanly over the
// wire, so the window flashes during scroll/streaming/animation. Local
// Windows/macOS (and WSLg, which renders locally via vGPU) composite on the
// GPU and never see it. Fall back to software rendering when a remote display
// is detected; it's rock-steady over the wire and the CPU cost is negligible
// next to the connection's latency. Must run before app `ready` — these
// switches only apply pre-launch. Override with HERMES_DESKTOP_DISABLE_GPU
// (1/true → always disable, 0/false → keep GPU on).
const REMOTE_DISPLAY_REASON = detectRemoteDisplay()
if (REMOTE_DISPLAY_REASON) {
app.disableHardwareAcceleration()
// Belt-and-suspenders for X11/VNC, where the Viz compositor can still glitch
// with only --disable-gpu: force compositing onto the CPU too.
app.commandLine.appendSwitch('disable-gpu-compositing')
console.log(
`[hermes] remote display detected (${REMOTE_DISPLAY_REASON}); disabling GPU hardware acceleration to prevent flicker`
)
}
const SOURCE_REPO_ROOT = path.resolve(APP_ROOT, '../..')
// Build-time install stamp -- the git ref this .exe was built against.
@@ -364,22 +387,98 @@ app.setAboutPanelOptions({
copyright: 'Copyright © 2026 Nous Research'
})
// Custom scheme for streaming local media (video/audio) into the renderer.
// Reading large media through `readFileDataUrl` failed: it base64-loads the
// whole file into memory and is hard-capped at DATA_URL_READ_MAX_BYTES (16 MB),
// so any non-trivial video silently refused to load. Streaming via a protocol
// handler removes the size cap and gives the <video> element seekable,
// range-aware playback. Must be registered before the app is ready.
const MEDIA_PROTOCOL = 'hermes-media'
// Only audio/video may be streamed. Without this the handler would read any
// non-blocklisted local file (no size cap) for any `fetch(hermes-media://…)`.
const STREAMABLE_MEDIA_EXTS = new Set([
'.avi',
'.flac',
'.m4a',
'.mkv',
'.mov',
'.mp3',
'.mp4',
'.ogg',
'.opus',
'.wav',
'.webm'
])
protocol.registerSchemesAsPrivileged([
{
scheme: MEDIA_PROTOCOL,
privileges: {
secure: true,
standard: true,
stream: true,
supportFetchAPI: true
}
}
])
function registerMediaProtocol() {
protocol.handle(MEDIA_PROTOCOL, async request => {
let resolvedPath
try {
const url = new URL(request.url)
const filePath = decodeURIComponent(url.pathname.replace(/^\/+/, ''))
;({ resolvedPath } = await resolveReadableFileForIpc(filePath, { purpose: 'Media stream' }))
} catch {
return new Response('Media not found', { status: 404 })
}
if (!STREAMABLE_MEDIA_EXTS.has(path.extname(resolvedPath).toLowerCase())) {
return new Response('Unsupported media type', { status: 415 })
}
// Delegate to Electron's net stack on a file:// URL — it resolves the
// content-type and honors Range requests so seeking works. Forward the
// renderer's headers (notably Range) and skip custom-protocol re-entry.
return electronNet.fetch(pathToFileURL(resolvedPath).toString(), {
bypassCustomProtocolHandlers: true,
headers: request.headers
})
})
}
let mainWindow = null
let hermesProcess = null
let connectionPromise = null
// Auto-reload budget for renderer crashes. A deterministic startup crash would
// otherwise loop forever (reload → crash → reload), pinning CPU and spamming
// logs. Allow a few reloads per rolling window, then stop and leave the dead
// window so the user can read the error / quit.
const RENDERER_RELOAD_WINDOW_MS = 60_000
const RENDERER_RELOAD_MAX = 3
let rendererReloadTimes = []
// Latched bootstrap failure: when the first-launch install fails, we hold
// onto the error so subsequent startHermes() calls (e.g. the renderer's
// ensureGatewayOpen retrying after the WS won't open) return the same error
// instead of re-running install.ps1 in a hot loop. Cleared explicitly by
// the renderer's "Reload and retry" path or by quitting the app.
let bootstrapFailure = null
// Active first-launch install, so the renderer's Cancel button (and app quit)
// can abort the in-flight install.sh/ps1 instead of leaving it running.
let bootstrapAbortController = null
// Set by the renderer's "Repair install" IPC. While true, resolution skips the
// existing-install adopt branch (3b) so repair re-drives the installer instead
// of re-adopting the install we're repairing. Cleared once a bootstrap runs.
let forceBootstrapRepair = false
let connectionConfigCache = null
let connectionConfigCacheMtime = null
const hermesLog = []
const previewWatchers = new Map()
let previewShortcutActive = false
let desktopLogBuffer = ''
let desktopLogFlushTimer = null
let desktopLogFlushPromise = Promise.resolve()
let nativeThemeListenerInstalled = false
let bootProgressState = {
error: null,
fakeMode: BOOT_FAKE_MODE,
@@ -463,6 +562,39 @@ function openExternalUrl(rawUrl) {
return false
}
// `file://` URLs come from the artifacts panel (the renderer can't open
// them itself because Chromium blocks file:// navigation from the app
// origin). Hand them to `shell.openPath`, which dispatches to the OS
// file association. If the OS can't open it (`error` is a non-empty
// string), fall back to revealing the file in the system file manager.
if (parsed.protocol === 'file:') {
let localPath
try {
localPath = fileURLToPath(parsed.toString())
} catch {
return false
}
void shell
.openPath(localPath)
.then(error => {
if (!error) {
return
}
rememberLog(`[file] openPath failed: ${error}; revealing in folder instead`)
try {
shell.showItemInFolder(localPath)
} catch (revealError) {
rememberLog(`[file] showItemInFolder failed: ${revealError.message}`)
}
})
.catch(error => rememberLog(`[file] openPath rejected: ${error.message}`))
return true
}
if (!['http:', 'https:', 'mailto:'].includes(parsed.protocol)) {
return false
}
@@ -593,7 +725,7 @@ function broadcastBootstrapEvent(ev) {
error: ev.error ?? null
}
} else if (ev.type === 'log') {
bootstrapState.log.push({ ts: Date.now(), stage: ev.stage || null, line: ev.line })
bootstrapState.log.push({ ts: Date.now(), stage: ev.stage || null, line: ev.line, stream: ev.stream || 'stdout' })
if (bootstrapState.log.length > BOOTSTRAP_LOG_RING_MAX) {
bootstrapState.log.splice(0, bootstrapState.log.length - BOOTSTRAP_LOG_RING_MAX)
}
@@ -971,9 +1103,17 @@ function readDesktopUpdateConfig() {
}
}
// Atomic file write: temp + rename (atomic on all platforms). Prevents
// partial writes on crash/power loss that corrupt JSON config files.
function writeFileAtomic(targetPath, data, encoding) {
const tmp = targetPath + '.tmp'
fs.writeFileSync(tmp, data, encoding)
fs.renameSync(tmp, targetPath)
}
function writeDesktopUpdateConfig(config) {
fs.mkdirSync(path.dirname(DESKTOP_UPDATE_CONFIG_PATH), { recursive: true })
fs.writeFileSync(DESKTOP_UPDATE_CONFIG_PATH, JSON.stringify(config, null, 2))
writeFileAtomic(DESKTOP_UPDATE_CONFIG_PATH, JSON.stringify(config, null, 2))
}
// Match the backend's source resolution but bias toward a real git checkout.
@@ -1190,16 +1330,34 @@ async function applyUpdates(opts = {}) {
emitUpdateProgress({ stage: 'restart', message: 'Handing off to the Hermes updater…', percent: 100 })
const updateRoot = resolveUpdateRoot()
const { branch: configuredBranch } = readDesktopUpdateConfig()
const branch = await resolveHealedBranch(updateRoot, configuredBranch || DEFAULT_UPDATE_BRANCH)
const updaterArgs = ['--update', '--branch', branch]
const targetApp = IS_MAC ? runningAppBundle() : null
if (targetApp) {
updaterArgs.push('--target-app', targetApp)
}
const venvBin = path.join(updateRoot, 'venv', IS_WINDOWS ? 'Scripts' : 'bin')
// Detached so the updater outlives this process — it needs us GONE before
// `hermes update` will run (the venv shim is locked while we live).
const child = spawn(updater, ['--update'], {
const child = spawn(updater, updaterArgs, {
cwd: HERMES_HOME,
env: {
...process.env,
HERMES_HOME,
PATH: [path.join(HERMES_HOME, 'node', 'bin'), venvBin, process.env.PATH]
.filter(Boolean)
.join(path.delimiter)
},
detached: true,
stdio: 'ignore',
windowsHide: false
})
child.unref()
rememberLog(`[updates] launched updater: ${updater} --update; exiting desktop to release venv shim`)
rememberLog(`[updates] launched updater: ${updater} ${updaterArgs.join(' ')}; exiting desktop to release venv shim`)
// Give the OS a beat to register the new process, then quit. The updater
// rebuilds and relaunches us when it's done.
@@ -1283,6 +1441,18 @@ async function applyUpdatesPosixInApp(opts = {}) {
PATH: [extraPath, process.env.PATH].filter(Boolean).join(path.delimiter)
}
// `hermes update` reaps stale `hermes dashboard` backends (a code update
// leaves the running process serving old Python against the freshly-updated
// JS bundle). But OUR backend is one of those processes, and killing it
// mid-update produces the boot→kill→crash loop in #37532 — the desktop
// already restarts its own backend via the rebuild+relaunch below, so the
// reap must spare it. Hand the live backend's PID to the update process;
// _kill_stale_dashboard_processes reads HERMES_DESKTOP_CHILD_PID and excludes
// it while still reaping any genuinely-orphaned dashboards. (#37532)
if (hermesProcess && Number.isInteger(hermesProcess.pid)) {
env.HERMES_DESKTOP_CHILD_PID = String(hermesProcess.pid)
}
// Branch-pin so a non-main checkout doesn't get switched to main (and self-heal
// to main when the pinned branch no longer exists on origin).
let branchArgs = []
@@ -1401,8 +1571,12 @@ function readJson(filePath) {
// Marker schema (version 1):
// {
// schemaVersion: 1,
// pinnedCommit: "<40-char SHA>", // what install.ps1 was driven against
// pinnedCommit: "<40-char SHA>" | null, // what install.ps1 was driven against;
// // may be null for adopted installs
// pinnedBranch: "<branch name>" | null,
// adopted: <bool>, // true when we adopted a pre-existing
// // install rather than bootstrapping it;
// // treated as authoritative even sans commit
// completedAt: "<ISO 8601>",
// desktopVersion: "<app.getVersion()>" // for forensics
// }
@@ -1410,11 +1584,25 @@ function readBootstrapMarker() {
return readJson(BOOTSTRAP_COMPLETE_MARKER)
}
// Marker-independent: is the canonical install at ACTIVE_HERMES_ROOT actually
// runnable right now? A complete CLI install (`install.sh --include-desktop`)
// or a DMG launch over a prior CLI install satisfies this WITHOUT the desktop
// ever having written the bootstrap marker -- so we must be able to recognise
// "already installed" off the filesystem alone, not just the marker.
function isActiveRuntimeUsable() {
return isHermesSourceRoot(ACTIVE_HERMES_ROOT) && fileExists(getVenvPython(VENV_ROOT))
}
function isBootstrapComplete() {
const marker = readBootstrapMarker()
if (!marker || typeof marker !== 'object') return false
if (marker.schemaVersion !== BOOTSTRAP_MARKER_SCHEMA_VERSION) return false
if (typeof marker.pinnedCommit !== 'string' || marker.pinnedCommit.length < 7) return false
if (typeof marker.pinnedCommit !== 'string' || marker.pinnedCommit.length < 7) {
// Adopted markers (an existing install we detected and took ownership of,
// possibly without a resolvable commit) are still authoritative -- they
// attest a runnable install we deliberately decided to forward to.
if (marker.adopted !== true) return false
}
// We DELIBERATELY do NOT verify that the checkout is currently at the
// pinned commit -- users update via the in-app update path or `hermes
// update`, which moves HEAD legitimately. The marker just attests "we
@@ -1422,7 +1610,22 @@ function isBootstrapComplete() {
// a runnable venv: an interrupted or split-home install can leave the marker
// + checkout without a venv, and trusting that spawns a dead backend
// ("gateway offline") instead of re-running bootstrap to repair it.
return isHermesSourceRoot(ACTIVE_HERMES_ROOT) && fileExists(getVenvPython(VENV_ROOT))
return isActiveRuntimeUsable()
}
// HEAD commit of ACTIVE_HERMES_ROOT so an adopted marker carries the same
// provenance a freshly-bootstrapped one would. null when git is unavailable or
// the root isn't a checkout -- the marker stays valid via its `adopted` flag.
function readActiveHeadCommit() {
try {
const sha = execFileSync(resolveGitBinary(), ['-C', ACTIVE_HERMES_ROOT, 'rev-parse', 'HEAD'], {
encoding: 'utf8',
stdio: ['ignore', 'pipe', 'ignore']
}).trim()
return /^[0-9a-f]{7,40}$/i.test(sha) ? sha : null
} catch {
return null
}
}
function writeBootstrapMarker(payload) {
@@ -1431,10 +1634,11 @@ function writeBootstrapMarker(payload) {
schemaVersion: BOOTSTRAP_MARKER_SCHEMA_VERSION,
pinnedCommit: payload.pinnedCommit || null,
pinnedBranch: payload.pinnedBranch || null,
adopted: Boolean(payload.adopted),
completedAt: new Date().toISOString(),
desktopVersion: app.getVersion()
}
fs.writeFileSync(BOOTSTRAP_COMPLETE_MARKER, JSON.stringify(merged, null, 2) + '\n', 'utf8')
writeFileAtomic(BOOTSTRAP_COMPLETE_MARKER, JSON.stringify(merged, null, 2) + '\n', 'utf8')
return merged
}
@@ -1454,10 +1658,18 @@ function resolveRendererIndex() {
}
function resolveHermesCwd() {
// In a packaged build, `process.cwd()` resolves to the install root (e.g.
// `…/win-unpacked` on Windows or `/Applications/Hermes.app/Contents/...`
// on macOS). Sessions spawned there leave files inside the app bundle
// and bewilder users when "where did my files go?" is the install dir.
// The user-configurable default project directory wins over everything,
// followed by env hints (only honored when packaged if they point at a
// real directory), then the home dir.
const candidates = [
readDefaultProjectDir(),
process.env.HERMES_DESKTOP_CWD,
process.env.INIT_CWD,
process.cwd(),
IS_PACKAGED ? null : process.cwd(),
!IS_PACKAGED ? SOURCE_REPO_ROOT : null,
app.getPath('home')
]
@@ -1471,6 +1683,48 @@ function resolveHermesCwd() {
return app.getPath('home')
}
// Persisted "Default project directory" — surfaced as a setting in the
// renderer (see app/settings/sessions-settings.tsx). Stored as JSON in
// userData so it survives self-updates without bleeding into the new
// install. `null` means "no preference, fall back to the usual chain".
const DEFAULT_PROJECT_DIR_CONFIG_FILENAME = 'project-dir.json'
function defaultProjectDirConfigPath() {
return path.join(app.getPath('userData'), DEFAULT_PROJECT_DIR_CONFIG_FILENAME)
}
function readDefaultProjectDir() {
try {
const raw = fs.readFileSync(defaultProjectDirConfigPath(), 'utf8')
const parsed = JSON.parse(raw)
if (parsed && typeof parsed.dir === 'string' && parsed.dir.trim()) {
const resolved = path.resolve(parsed.dir)
if (directoryExists(resolved)) {
return resolved
}
}
} catch {
// Missing / unreadable / malformed → fall through to the rest of the
// candidate chain.
}
return null
}
function writeDefaultProjectDir(dir) {
const target = defaultProjectDirConfigPath()
const payload = dir ? JSON.stringify({ dir: path.resolve(dir) }, null, 2) : JSON.stringify({}, null, 2)
try {
fs.mkdirSync(path.dirname(target), { recursive: true })
fs.writeFileSync(target, payload, 'utf8')
} catch (error) {
rememberLog(`[settings] write default project dir failed: ${error.message}`)
}
}
function createPythonBackend(root, label, dashboardArgs, options = {}) {
const python = findPythonForRoot(root)
if (!python) return null
@@ -1538,6 +1792,24 @@ function resolveHermesBackend(dashboardArgs) {
return createActiveBackend(dashboardArgs)
}
// 3b. Existing-but-unmarked install at ACTIVE_HERMES_ROOT. The marker is
// written only by OUR bootstrap, so a runtime from `install.sh
// --include-desktop` (or a DMG launch over a prior CLI install) is
// runnable yet markerless -- without this we'd fall to step 6 and re-run
// the WHOLE install on top of a working one. ACTIVE_HERMES_ROOT is our
// canonical location (unlike a random `hermes` on PATH), so adopt it:
// stamp the marker once and forward straight to the app. Repair skips
// this so a broken-but-present venv still gets rebuilt.
if (!forceBootstrapRepair && isActiveRuntimeUsable()) {
rememberLog(`[bootstrap] adopting existing install at ${ACTIVE_HERMES_ROOT}; skipping first-launch setup`)
try {
writeBootstrapMarker({ pinnedCommit: readActiveHeadCommit(), pinnedBranch: null, adopted: true })
} catch (err) {
rememberLog(`[bootstrap] could not stamp adopted marker: ${err.message}`)
}
return createActiveBackend(dashboardArgs)
}
// 4. Existing `hermes` on PATH -- installed via install.ps1 / install.sh from
// a previous tool-only setup, or pip-installed system-wide. Use it but
// do NOT write a bootstrap marker; the user did this themselves and we
@@ -1678,12 +1950,15 @@ async function ensureRuntime(backend) {
})
} catch {}
bootstrapAbortController = new AbortController()
const bootstrapResult = await runBootstrap({
installStamp: backend.installStamp,
activeRoot: backend.activeRoot,
sourceRepoRoot: SOURCE_REPO_ROOT,
hermesHome: HERMES_HOME,
logRoot: path.join(HERMES_HOME, 'logs'),
abortSignal: bootstrapAbortController.signal,
onEvent: ev => {
// Tee every bootstrap event to (a) the desktop log for forensics
// and (b) the renderer for live progress UI. Either may be absent;
@@ -1699,6 +1974,16 @@ async function ensureRuntime(backend) {
writeMarker: writeBootstrapMarker
})
bootstrapAbortController = null
if (bootstrapResult.cancelled) {
const cancelledError = new Error('Hermes install was cancelled.')
cancelledError.isBootstrapFailure = true
cancelledError.bootstrapCancelled = true
bootstrapFailure = cancelledError
throw cancelledError
}
if (!bootstrapResult.ok) {
const bootstrapError = new Error(
`Hermes bootstrap failed${bootstrapResult.failedStage ? ` at stage '${bootstrapResult.failedStage}'` : ''}: ` +
@@ -1715,6 +2000,9 @@ async function ensureRuntime(backend) {
}
rememberLog('[bootstrap] bootstrap complete; marker written. Re-resolving backend.')
// A repair (if any) has now re-run, so clear the gate -- the re-resolution
// below SHOULD land on the fresh marker fast-path rather than skip it.
forceBootstrapRepair = false
// Re-resolve now that the install exists. The new resolution lands in
// step 3 (bootstrap-complete marker) and we recurse to wire venvPython.
return ensureRuntime(resolveHermesBackend(backend.args))
@@ -1816,6 +2104,7 @@ function fetchJson(url, token, options = {}) {
},
res => {
const chunks = []
res.on('error', reject)
res.on('data', chunk => chunks.push(chunk))
res.on('end', () => {
const text = Buffer.concat(chunks).toString('utf8')
@@ -2155,6 +2444,7 @@ async function resourceBufferFromUrl(rawUrl) {
return
}
const chunks = []
res.on('error', reject)
res.on('data', chunk => chunks.push(chunk))
res.on('end', () => {
resolve({
@@ -2416,6 +2706,32 @@ function sendClosePreviewRequested() {
webContents.send('hermes:close-preview-requested')
}
// Tell the renderer the machine just woke. Sleep silently drops the
// renderer's WebSocket to the local backend; the renderer reconnects on this
// signal so the chat composer doesn't stay stuck on "Starting Hermes...".
function sendPowerResume() {
if (!mainWindow || mainWindow.isDestroyed()) return
const { webContents } = mainWindow
if (!webContents || webContents.isDestroyed()) return
webContents.send('hermes:power-resume')
}
let powerResumeRegistered = false
function registerPowerResumeListeners() {
if (powerResumeRegistered) return
powerResumeRegistered = true
try {
// 'resume' covers sleep/wake; 'unlock-screen' covers lock/unlock without a
// full suspend. Either can drop an idle socket.
powerMonitor.on('resume', sendPowerResume)
powerMonitor.on('unlock-screen', sendPowerResume)
} catch {
// powerMonitor is unavailable before app 'ready' on some platforms; the
// caller registers after 'ready', so this should not normally throw.
}
}
function getAppIconPath() {
return APP_ICON_PATHS.find(fileExists)
}
@@ -2504,9 +2820,31 @@ function buildApplicationMenu() {
{ role: 'forceReload' },
{ role: 'toggleDevTools' },
{ type: 'separator' },
{ role: 'resetZoom' },
{ role: 'zoomIn' },
{ role: 'zoomOut' },
{
label: 'Actual Size',
accelerator: 'CommandOrControl+0',
click: () => { if (mainWindow && !mainWindow.isDestroyed()) mainWindow.webContents.setZoomLevel(0) }
},
{
label: 'Zoom In',
accelerator: 'CommandOrControl+Plus',
click: () => {
if (mainWindow && !mainWindow.isDestroyed()) {
const next = Math.min(mainWindow.webContents.getZoomLevel() + 0.1, 9)
mainWindow.webContents.setZoomLevel(next)
}
}
},
{
label: 'Zoom Out',
accelerator: 'CommandOrControl+-',
click: () => {
if (mainWindow && !mainWindow.isDestroyed()) {
const next = Math.max(mainWindow.webContents.getZoomLevel() - 0.1, -9)
mainWindow.webContents.setZoomLevel(next)
}
}
},
{ type: 'separator' },
{ role: 'togglefullscreen' }
]
@@ -2565,6 +2903,32 @@ function installPreviewShortcut(window) {
})
}
function installZoomShortcuts(window) {
// Override Ctrl/Cmd + +/-/0 with half the default zoom step (0.1 vs 0.2).
// The menu items handle this on macOS (where the menu is always present),
// but on Linux/Windows the menu is null and Chromium's default handler
// would use the full 0.2 step, so we intercept here for consistency.
const ZOOM_STEP = 0.1
window.webContents.on('before-input-event', (event, input) => {
const mod = IS_MAC ? input.meta : input.control
if (!mod || input.alt || input.shift) return
const key = input.key
if (key === '0') {
event.preventDefault()
window.webContents.setZoomLevel(0)
} else if (key === '=' || key === '+') {
event.preventDefault()
const next = Math.min(window.webContents.getZoomLevel() + ZOOM_STEP, 9)
window.webContents.setZoomLevel(next)
} else if (key === '-') {
event.preventDefault()
const next = Math.max(window.webContents.getZoomLevel() - ZOOM_STEP, -9)
window.webContents.setZoomLevel(next)
}
})
}
function installContextMenu(window) {
window.webContents.on('context-menu', (_event, params) => {
const template = []
@@ -2617,6 +2981,28 @@ function installContextMenu(window) {
)
}
// Spell-check suggestions for the misspelled word under the caret.
// Chromium surfaces them on `params.dictionarySuggestions`; we offer the
// top 5 plus a "Add to dictionary" affordance.
const suggestions = Array.isArray(params.dictionarySuggestions) ? params.dictionarySuggestions : []
if (isEditable && params.misspelledWord && suggestions.length > 0) {
if (template.length) template.push({ type: 'separator' })
for (const suggestion of suggestions.slice(0, 5)) {
template.push({
label: suggestion,
click: () => window.webContents.replaceMisspelling(suggestion)
})
}
template.push({ type: 'separator' })
template.push({
label: 'Add to dictionary',
click: () => window.webContents.session.addWordToSpellCheckerDictionary(params.misspelledWord)
})
}
if (hasSelection || isEditable) {
if (template.length) template.push({ type: 'separator' })
if (isEditable) {
@@ -2761,7 +3147,17 @@ function decryptDesktopSecret(secret) {
}
function readDesktopConnectionConfig() {
if (connectionConfigCache) {
// Check if file changed on disk since last read (e.g. modified by another
// process or an external tool). Our own writes update the cache inline
// via writeDesktopConnectionConfig, but external changes would be missed.
let mtime = null
try {
mtime = fs.statSync(DESKTOP_CONNECTION_CONFIG_PATH).mtimeMs
} catch {
mtime = null
}
if (connectionConfigCache && connectionConfigCacheMtime === mtime) {
return connectionConfigCache
}
@@ -2782,14 +3178,16 @@ function readDesktopConnectionConfig() {
}
connectionConfigCache = config
connectionConfigCacheMtime = mtime
return config
}
function writeDesktopConnectionConfig(config) {
fs.mkdirSync(path.dirname(DESKTOP_CONNECTION_CONFIG_PATH), { recursive: true })
fs.writeFileSync(DESKTOP_CONNECTION_CONFIG_PATH, JSON.stringify(config, null, 2))
writeFileAtomic(DESKTOP_CONNECTION_CONFIG_PATH, JSON.stringify(config, null, 2))
connectionConfigCache = config
connectionConfigCacheMtime = fs.statSync(DESKTOP_CONNECTION_CONFIG_PATH).mtimeMs
}
function sanitizeDesktopConnectionConfig(config = readDesktopConnectionConfig()) {
@@ -3117,9 +3515,12 @@ function createWindow() {
}
if (!IS_MAC) {
nativeTheme.on('updated', () => {
mainWindow?.setTitleBarOverlay?.(getTitleBarOverlayOptions())
})
if (!nativeThemeListenerInstalled) {
nativeThemeListenerInstalled = true
nativeTheme.on('updated', () => {
mainWindow?.setTitleBarOverlay?.(getTitleBarOverlayOptions())
})
}
}
mainWindow.on('will-enter-full-screen', () => sendWindowStateChanged(true))
@@ -3129,6 +3530,7 @@ function createWindow() {
installPreviewShortcut(mainWindow)
installDevToolsShortcut(mainWindow)
installZoomShortcuts(mainWindow)
installContextMenu(mainWindow)
mainWindow.webContents.setWindowOpenHandler(details => {
openExternalUrl(details.url)
@@ -3144,6 +3546,51 @@ function createWindow() {
openExternalUrl(url)
})
mainWindow.webContents.on('render-process-gone', (_event, details) => {
rememberLog(`[renderer] render-process-gone reason=${details?.reason} exitCode=${details?.exitCode}`)
if (details?.reason === 'crashed' || details?.reason === 'oom') {
const now = Date.now()
rendererReloadTimes = rendererReloadTimes.filter(t => now - t < RENDERER_RELOAD_WINDOW_MS)
if (rendererReloadTimes.length >= RENDERER_RELOAD_MAX) {
rememberLog(
`[renderer] suppressing reload: ${rendererReloadTimes.length} crashes within ${RENDERER_RELOAD_WINDOW_MS}ms (likely a crash loop)`
)
return
}
rendererReloadTimes.push(now)
setImmediate(() => {
if (!mainWindow || mainWindow.isDestroyed()) return
try {
mainWindow.webContents.reload()
} catch (err) {
rememberLog(`[renderer] reload after crash failed: ${err?.message || err}`)
}
})
}
})
mainWindow.webContents.on('unresponsive', () => rememberLog('[renderer] webContents became unresponsive'))
// Electron always passes the event first. The canonical (Electron 36+) shape
// is (event, messageDetails); the deprecated positional shape is
// (event, level, message, line, sourceId). Handle both. `level` is numeric
// (0..3), where 3 === error.
mainWindow.webContents.on('console-message', (_event, detailsOrLevel, message, line, sourceId) => {
const details = detailsOrLevel && typeof detailsOrLevel === 'object' ? detailsOrLevel : null
const level = details ? details.level : detailsOrLevel
if (level !== 3) return
const text = details ? details.message : message
const src = details ? details.sourceUrl : sourceId
const lineNo = details ? details.lineNumber : line
rememberLog(`[renderer console] ${text} (${src}:${lineNo})`)
})
if (DEV_SERVER) {
mainWindow.loadURL(DEV_SERVER)
} else {
@@ -3164,6 +3611,7 @@ ipcMain.handle('hermes:bootstrap:reset', async () => {
// full backend flow (including a fresh runBootstrap pass).
rememberLog('[bootstrap] reset requested by renderer; clearing latched failure')
bootstrapFailure = null
forceBootstrapRepair = false
connectionPromise = null
bootstrapState = {
active: false,
@@ -3191,9 +3639,24 @@ ipcMain.handle('hermes:bootstrap:repair', async () => {
rememberLog(`[bootstrap] failed to remove marker during repair: ${error.message}`)
}
bootstrapFailure = null
// Force the next resolution past both the marker fast-path and the adopt
// branch so the installer actually re-runs (the whole point of repair).
forceBootstrapRepair = true
resetHermesConnection()
return { ok: true }
})
ipcMain.handle('hermes:bootstrap:cancel', async () => {
// Renderer's Cancel button during first-launch install. Abort the running
// install script (SIGTERM via the runner's abortSignal). runBootstrap
// resolves with { cancelled: true }, which surfaces the recovery overlay.
if (bootstrapAbortController) {
try {
bootstrapAbortController.abort()
} catch {}
return { ok: true, cancelled: true }
}
return { ok: false, cancelled: false }
})
ipcMain.handle('hermes:boot-progress:get', async () => bootProgressState)
ipcMain.handle('hermes:bootstrap:get', async () => getBootstrapState())
ipcMain.handle('hermes:connection-config:get', async () => sanitizeDesktopConnectionConfig())
@@ -3282,13 +3745,21 @@ ipcMain.handle('hermes:readFileText', async (_event, filePath) => {
})
ipcMain.handle('hermes:selectPaths', async (_event, options = {}) => {
const properties = ['openFile']
if (options?.directories) properties.push('openDirectory')
const properties = options?.directories ? ['openDirectory'] : ['openFile']
if (options?.multiple !== false) properties.push('multiSelections')
let resolvedDefaultPath
if (options?.defaultPath) {
try {
resolvedDefaultPath = path.resolve(String(options.defaultPath))
} catch {
resolvedDefaultPath = undefined
}
}
const result = await dialog.showOpenDialog(mainWindow, {
title: options?.title || 'Add context',
defaultPath: options?.defaultPath ? path.resolve(String(options.defaultPath)) : undefined,
defaultPath: resolvedDefaultPath,
properties,
filters: Array.isArray(options?.filters) ? options.filters : undefined
})
@@ -3347,6 +3818,45 @@ ipcMain.handle('hermes:openExternal', (_event, url) => {
}
})
// User-configurable default project directory. The renderer reads this on
// settings mount and seeds the value into the picker; writing back persists
// it via writeDefaultProjectDir so resolveHermesCwd picks it up on the next
// session spawn (no app restart needed).
ipcMain.handle('hermes:setting:defaultProjectDir:get', async () => ({
dir: readDefaultProjectDir(),
defaultLabel: path.join(app.getPath('home'), 'hermes-projects')
}))
ipcMain.handle('hermes:setting:defaultProjectDir:set', async (_event, dir) => {
const next = typeof dir === 'string' && dir.trim() ? dir.trim() : null
if (next) {
try {
fs.mkdirSync(next, { recursive: true })
} catch (error) {
throw new Error(`Could not create directory: ${error.message}`)
}
}
writeDefaultProjectDir(next)
return { dir: next }
})
ipcMain.handle('hermes:setting:defaultProjectDir:pick', async () => {
const result = await dialog.showOpenDialog({
title: 'Choose default project directory',
properties: ['openDirectory', 'createDirectory'],
defaultPath: readDefaultProjectDir() || app.getPath('home')
})
if (result.canceled || result.filePaths.length === 0) {
return { canceled: true, dir: null }
}
return { canceled: false, dir: result.filePaths[0] }
})
ipcMain.handle('hermes:fetchLinkTitle', (_event, url) => fetchLinkTitle(url))
ipcMain.handle('hermes:logs:reveal', async () => {
@@ -3647,14 +4157,109 @@ ipcMain.handle('hermes:version', async () => ({
hermesRoot: resolveUpdateRoot()
}))
// ---------------------------------------------------------------------------
// macOS first-launch placement: move into /Applications and pin to the Dock
// ---------------------------------------------------------------------------
//
// The DMG and CLI-built apps launch from wherever the user left them (a DMG
// mount, ~/Downloads, ~/.hermes/...) -- which means Gatekeeper translocation,
// no Dock tile, and "which icon do I click?" confusion. On first packaged
// launch we relocate into /Applications (Electron relaunches from there) and,
// once we're that canonical copy, pin to the Dock. Both macOS-only,
// packaged-only, best-effort, run at most once.
// Move the bundle into /Applications and relaunch. Returns true when a relaunch
// is underway (caller must stop init). No-op in dev, off macOS, or already in
// /Applications. `existsAndRunning` -> another copy owns the slot; don't fight
// it. `exists` -> stale copy; replace it so there's exactly one current app.
function maybeRelocateToApplications() {
if (!IS_MAC || !IS_PACKAGED || process.env.HERMES_DESKTOP_NO_AUTO_MOVE === '1') return false
try {
if (app.isInApplicationsFolder()) return false
const moved = app.moveToApplicationsFolder({ conflictHandler: type => type !== 'existsAndRunning' })
if (moved) rememberLog('[install] relocated into /Applications; relaunching')
return moved
} catch (err) {
rememberLog(`[install] move to /Applications skipped: ${err.message}`)
return false
}
}
const DOCK_PINNED_MARKER = 'dock-pinned.json'
// Pin the /Applications copy to the Dock once. macOS has no Electron API for
// this, so we append to com.apple.dock's persistent-apps and restart the Dock.
// Guarded by a userData marker + membership check so we never duplicate the tile.
function maybePinToDock() {
if (!IS_MAC || !IS_PACKAGED || process.env.HERMES_DESKTOP_NO_DOCK_PIN === '1') return
const marker = path.join(app.getPath('userData'), DOCK_PINNED_MARKER)
if (fileExists(marker)) return
let bundle
try {
if (!app.isInApplicationsFolder()) return // don't pin a soon-to-be-stale path
bundle = runningAppBundle()
} catch {
return
}
if (!bundle) return
// The Dock stores tiles as file-reference URLs (type 15), e.g.
// file:///Applications/Hermes.app/ -- NOT a raw POSIX path. A type-0/raw-path
// tile is silently dropped when the Dock rewrites persistent-apps on restart.
const url = pathToFileURL(bundle.endsWith('/') ? bundle : `${bundle}/`).href
const done = (note = {}) => {
try {
fs.writeFileSync(marker, JSON.stringify({ bundle, pinnedAt: new Date().toISOString(), ...note }) + '\n')
} catch {
// best-effort; we re-check next launch (membership guard dedupes)
}
}
try {
const apps = execFileSync('defaults', ['read', 'com.apple.dock', 'persistent-apps'], {
encoding: 'utf8',
stdio: ['ignore', 'pipe', 'ignore']
})
if (apps.includes(url)) return done({ alreadyPresent: true })
} catch {
// persistent-apps may not exist yet; -array-add creates it
}
const tile =
'<dict><key>tile-data</key><dict><key>file-data</key><dict>' +
`<key>_CFURLString</key><string>${url}</string><key>_CFURLStringType</key><integer>15</integer>` +
'</dict></dict></dict>'
try {
execFileSync('defaults', ['write', 'com.apple.dock', 'persistent-apps', '-array-add', tile], { stdio: 'ignore' })
// Flush the write through cfprefsd before restarting the Dock, otherwise the
// Dock reloads stale prefs and our tile is lost in the race.
execFileSync('defaults', ['read', 'com.apple.dock', 'persistent-apps'], { stdio: 'ignore' })
execFileSync('killall', ['Dock'], { stdio: 'ignore' })
done()
rememberLog(`[install] pinned to Dock: ${url}`)
} catch (err) {
rememberLog(`[install] Dock pin skipped: ${err.message}`)
}
}
app.whenReady().then(() => {
// macOS: relocate into /Applications before anything else so setup + state
// land in the final location; on success this relaunches, so bail here.
if (maybeRelocateToApplications()) return
maybePinToDock()
if (IS_MAC) {
Menu.setApplicationMenu(buildApplicationMenu())
} else {
Menu.setApplicationMenu(null)
}
installMediaPermissions()
registerMediaProtocol()
ensureWslWindowsFonts()
configureSpellChecker()
registerPowerResumeListeners()
createWindow()
app.on('activate', () => {
@@ -3662,7 +4267,37 @@ app.whenReady().then(() => {
})
})
// Seed Chromium's spellchecker with the system locale (falling back to en-US).
// On macOS Electron uses the native spellchecker which ignores this list, but
// on Windows/Linux Chromium downloads Hunspell dictionaries on demand and
// won't enable any without an explicit language.
function configureSpellChecker() {
try {
const defaultSession = session.defaultSession
if (!defaultSession || typeof defaultSession.setSpellCheckerLanguages !== 'function') {
return
}
const available = defaultSession.availableSpellCheckerLanguages || []
const locale = (app.getLocale && app.getLocale()) || 'en-US'
const candidates = [locale, locale.split('-')[0], 'en-US', 'en']
const chosen = candidates.find(lang => available.includes(lang)) || 'en-US'
defaultSession.setSpellCheckerLanguages([chosen])
} catch (error) {
rememberLog(`Spellchecker setup failed: ${error.message}`)
}
}
app.on('before-quit', () => {
// Quitting mid-install should stop the installer, not orphan it.
if (bootstrapAbortController) {
try {
bootstrapAbortController.abort()
} catch {}
}
if (desktopLogFlushTimer) {
clearTimeout(desktopLogFlushTimer)
desktopLogFlushTimer = null

View File

@@ -31,6 +31,11 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
setPreviewShortcutActive: active => ipcRenderer.send('hermes:previewShortcutActive', Boolean(active)),
openExternal: url => ipcRenderer.invoke('hermes:openExternal', url),
fetchLinkTitle: url => ipcRenderer.invoke('hermes:fetchLinkTitle', url),
settings: {
getDefaultProjectDir: () => ipcRenderer.invoke('hermes:setting:defaultProjectDir:get'),
setDefaultProjectDir: dir => ipcRenderer.invoke('hermes:setting:defaultProjectDir:set', dir),
pickDefaultProjectDir: () => ipcRenderer.invoke('hermes:setting:defaultProjectDir:pick')
},
revealLogs: () => ipcRenderer.invoke('hermes:logs:reveal'),
getRecentLogs: () => ipcRenderer.invoke('hermes:logs:recent'),
readDir: dirPath => ipcRenderer.invoke('hermes:fs:readDir', dirPath),
@@ -78,6 +83,11 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
ipcRenderer.on('hermes:backend-exit', listener)
return () => ipcRenderer.removeListener('hermes:backend-exit', listener)
},
onPowerResume: callback => {
const listener = () => callback()
ipcRenderer.on('hermes:power-resume', listener)
return () => ipcRenderer.removeListener('hermes:power-resume', listener)
},
onBootProgress: callback => {
const listener = (_event, payload) => callback(payload)
ipcRenderer.on('hermes:boot-progress', listener)
@@ -91,6 +101,7 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
getBootstrapState: () => ipcRenderer.invoke('hermes:bootstrap:get'),
resetBootstrap: () => ipcRenderer.invoke('hermes:bootstrap:reset'),
repairBootstrap: () => ipcRenderer.invoke('hermes:bootstrap:repair'),
cancelBootstrap: () => ipcRenderer.invoke('hermes:bootstrap:cancel'),
onBootstrapEvent: callback => {
const listener = (_event, payload) => callback(payload)
ipcRenderer.on('hermes:bootstrap:event', listener)

View File

@@ -3,8 +3,11 @@
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<link rel="icon" href="/apple-touch-icon.png" />
<link rel="apple-touch-icon" href="/apple-touch-icon.png" />
<meta name="color-scheme" content="light dark" />
<meta name="theme-color" content="#0a0a0a" />
<link rel="icon" type="image/png" sizes="180x180" href="/apple-touch-icon.png" />
<link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png" />
<link rel="shortcut icon" href="/apple-touch-icon.png" />
<title>Hermes</title>
</head>
<body>

File diff suppressed because it is too large Load Diff

View File

@@ -7,6 +7,9 @@
"author": "Nous Research",
"type": "module",
"main": "electron/main.cjs",
"engines": {
"node": "^20.19.0 || >=22.12.0"
},
"scripts": {
"dev": "concurrently -k \"npm:dev:renderer\" \"npm:dev:electron\"",
"dev:fake-boot": "cross-env HERMES_DESKTOP_BOOT_FAKE=1 HERMES_DESKTOP_BOOT_FAKE_STEP_MS=650 npm run dev",
@@ -32,7 +35,7 @@
"test:desktop:nsis": "node scripts/test-desktop.mjs nsis",
"test:desktop:existing": "node scripts/test-desktop.mjs existing",
"test:desktop:fresh": "node scripts/test-desktop.mjs fresh",
"test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-probes.test.cjs",
"test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-probes.test.cjs electron/bootstrap-runner.test.cjs",
"type-check": "tsc -b",
"lint": "eslint src/ electron/",
"lint:fix": "eslint src/ electron/ --fix",
@@ -50,6 +53,7 @@
"@dnd-kit/sortable": "^10.0.0",
"@dnd-kit/utilities": "^3.2.2",
"@hermes/shared": "file:../shared",
"@icons-pack/react-simple-icons": "^13.13.0",
"@nanostores/react": "^1.1.0",
"@nous-research/ui": "^0.13.0",
"@radix-ui/react-slot": "^1.2.4",
@@ -96,6 +100,7 @@
},
"devDependencies": {
"@eslint/js": "^9.39.4",
"@testing-library/dom": "^10.4.0",
"@testing-library/react": "^16.3.2",
"@types/hast": "^3.0.4",
"@types/node": "^24.12.2",

View File

@@ -0,0 +1,229 @@
// Reproduce + diagnose the "scroll wheel resets position while reading" bug.
//
// The complaint (Windows, mouse wheel): scrolling UP through a chat to re-read
// older content randomly yanks the view to a different position, so you have to
// fight the scrollbar. Mac users on trackpads don't see it.
//
// Hypothesis: the thread scroller has the browser default `overflow-anchor:
// auto`, and the thread renders items in natural document flow (padding
// spacers, NOT transforms). When an item above the viewport is measured by
// @tanstack/react-virtual (its real height differs a lot from the 220px
// estimate) — or when Shiki/images/fonts reflow it — TWO mechanisms both
// adjust scrollTop for the same delta: TanStack's measurement compensation AND
// the browser's native scroll anchoring. The double-correction lurches the
// view. A mouse wheel's coarse, discrete notches mount/measure several
// under-estimated turns per tick, so the over-correction is large and visible;
// a trackpad's ~1-3px/frame keeps it sub-perceptual.
//
// This script drives synthetic mouse-wheel-UP scrolling on a long thread and
// measures how much a tracked on-screen turn jumps, first with
// `overflow-anchor: auto` (reproduce) then `overflow-anchor: none` (the fix).
// If the fix run shows dramatically fewer/smaller jumps, the hypothesis holds.
//
// Prereq: a running desktop app with remote debugging on 9222, on a thread
// with enough history to scroll (the longer / more code+tool blocks, the
// better the repro). Then: node apps/desktop/scripts/diag-scroll-reset.mjs
const NOTCHES = 14 // wheel-up ticks per sweep
const NOTCH_PX = 120 // Windows wheel notch ≈ 120px
const NOTCH_GAP_MS = 130 // let each smooth-scroll animation settle
const REVERSE_JUMP_PX = 6 // tracked turn moving UP while scrolling up = wrong way
const LURCH_PX = 60 // single-frame on-screen jump that reads as a "reset"
const list = await (await fetch('http://127.0.0.1:9222/json/list')).json()
const tgt = list.find(t => t.type === 'page' && t.url.startsWith('http'))
if (!tgt) {
console.error('No page target on :9222. Is the desktop app running with --remote-debugging-port=9222?')
process.exit(1)
}
const ws = new WebSocket(tgt.webSocketDebuggerUrl)
let id = 0
const pending = new Map()
ws.addEventListener('message', ev => {
const m = JSON.parse(ev.data)
if (m.id != null && pending.has(m.id)) {
pending.get(m.id)(m)
pending.delete(m.id)
}
})
await new Promise(r => ws.addEventListener('open', r))
const send = (m, p = {}) =>
new Promise(r => {
const i = ++id
pending.set(i, r)
ws.send(JSON.stringify({ id: i, method: m, params: p }))
})
const evalP = async expr => {
const r = await send('Runtime.evaluate', { expression: expr, returnByValue: true })
if (r.result?.exceptionDetails) throw new Error(r.result.exceptionDetails.text)
return r.result.result.value
}
const sleep = ms => new Promise(r => setTimeout(r, ms))
// Install per-sweep instrumentation. `mode` is the overflow-anchor value to
// force inline so we A/B the exact same thread regardless of any CSS fix.
// Starts from ~45% down the thread so there's room to scroll up into
// not-yet-measured turns, tags the turn nearest viewport-center as the anchor,
// then records (per rAF) scrollTop + that turn's on-screen top, plus every
// scrollTop *setter* write (TanStack compensation) and ResizeObserver hit.
async function arm(mode) {
await evalP(`(() => {
const v = document.querySelector('[data-slot="aui_thread-viewport"]')
if (!v) throw new Error('thread viewport not found')
// Force the overflow-anchor behavior under test (inline beats CSS).
v.style.overflowAnchor = ${JSON.stringify(mode)}
// Park ~45% down so a wheel-up sweep climbs into estimated-but-unmeasured
// turns above the fold (where the measurement correction fires).
v.scrollTop = Math.round(v.scrollHeight * 0.45)
// Tag the turn closest to viewport center; we track its on-screen top.
const vr = v.getBoundingClientRect()
const center = vr.top + v.clientHeight / 2
let best = null, bestD = Infinity
for (const el of v.querySelectorAll('[data-index]')) {
const r = el.getBoundingClientRect()
const d = Math.abs((r.top + r.height / 2) - center)
if (d < bestD) { bestD = d; best = el }
}
document.querySelectorAll('[data-se-anchor]').forEach(e => e.removeAttribute('data-se-anchor'))
if (best) best.setAttribute('data-se-anchor', '1')
const anchorIndex = best ? best.getAttribute('data-index') : null
const samples = []
const writes = []
const ros = []
const t0 = performance.now()
// Intercept scrollTop writes → these are JS (TanStack) corrections.
// Native browser scroll anchoring does NOT go through this setter, so a
// scrollTop change with no write in the same frame is a native adjust.
const desc = Object.getOwnPropertyDescriptor(Element.prototype, 'scrollTop')
Object.defineProperty(v, 'scrollTop', {
configurable: true,
get() { return desc.get.call(this) },
set(val) {
writes.push({ t: performance.now() - t0, val, sh: this.scrollHeight })
desc.set.call(this, val)
}
})
window.__restoreScrollTop = () => Object.defineProperty(v, 'scrollTop', desc)
const ro = new ResizeObserver(entries => {
for (const e of entries) {
ros.push({ t: performance.now() - t0, slot: e.target.getAttribute?.('data-slot') || e.target.tagName, h: Math.round(e.contentRect.height) })
}
})
ro.observe(v)
if (v.firstElementChild) ro.observe(v.firstElementChild)
let running = true
const tick = () => {
if (!running) return
const a = v.querySelector('[data-se-anchor]')
const ar = a ? a.getBoundingClientRect() : null
samples.push({
t: performance.now() - t0,
st: Math.round(v.scrollTop * 100) / 100,
sh: v.scrollHeight,
ch: v.clientHeight,
atop: ar ? Math.round(ar.top * 100) / 100 : null,
aconn: !!a
})
requestAnimationFrame(tick)
}
requestAnimationFrame(tick)
window.__se = { samples, writes, ros, anchorIndex, dpr: window.devicePixelRatio, stop() { running = false; ro.disconnect(); window.__restoreScrollTop?.() } }
return true
})()`)
}
async function wheelUpSweep() {
const { x, y } = await evalP(`(() => {
const v = document.querySelector('[data-slot="aui_thread-viewport"]')
const r = v.getBoundingClientRect()
return { x: Math.round(r.left + r.width / 2), y: Math.round(r.top + r.height / 2) }
})()`)
for (let i = 0; i < NOTCHES; i++) {
await send('Input.dispatchMouseEvent', { type: 'mouseWheel', x, y, deltaX: 0, deltaY: -NOTCH_PX })
await sleep(NOTCH_GAP_MS)
}
await sleep(400)
}
async function collect() {
const data = JSON.parse(await evalP(`(() => { window.__se.stop(); return JSON.stringify(window.__se) })()`))
return data
}
function analyze(label, data) {
const { samples, writes, ros, anchorIndex, dpr } = data
let reverseJumps = 0
let reverseSum = 0
let lurches = 0
let maxJump = 0
let nativeMoves = 0
let prev = null
for (const s of samples) {
if (prev && prev.aconn && s.aconn && prev.atop != null && s.atop != null) {
const dTop = s.atop - prev.atop // wheel-up should move content DOWN → dTop >= 0
const dSt = s.st - prev.st
// Native (browser-anchoring) move: scrollTop changed with no setter write in this frame window.
const wroteThisFrame = writes.some(w => w.t > prev.t && w.t <= s.t)
if (Math.abs(dSt) > 0.5 && !wroteThisFrame) nativeMoves++
if (dTop < -REVERSE_JUMP_PX) {
reverseJumps++
reverseSum += -dTop
}
if (Math.abs(dTop) > LURCH_PX) lurches++
if (Math.abs(dTop) > maxJump) maxJump = Math.abs(dTop)
}
prev = s
}
console.log(`\n── ${label} ──`)
console.log(` devicePixelRatio: ${dpr}${Number.isInteger(dpr) ? '' : ' (fractional — Windows scaling, worsens rounding jitter)'}`)
console.log(` tracked turn index: ${anchorIndex}`)
console.log(` rAF frames: ${samples.length}`)
console.log(` scrollTop writes: ${writes.length} (TanStack measurement corrections)`)
console.log(` ResizeObserver hits: ${ros.length}`)
console.log(` native scroll moves: ${nativeMoves} (scrollTop moved with NO JS write = browser anchoring)`)
console.log(` reverse jumps: ${reverseJumps} (tracked turn yanked UP while scrolling up; total ${reverseSum.toFixed(0)}px)`)
console.log(` big lurches (>${LURCH_PX}px): ${lurches}`)
console.log(` max single-frame jump: ${maxJump.toFixed(0)}px`)
return { reverseJumps, reverseSum, lurches, maxJump, nativeMoves }
}
console.log(`Wheel-up repro: ${NOTCHES} notches × ${NOTCH_PX}px, anchored mid-thread.\n`)
await arm('auto')
await sleep(150)
await wheelUpSweep()
const a = analyze('overflow-anchor: auto (current / repro)', await collect())
await sleep(300)
await arm('none')
await sleep(150)
await wheelUpSweep()
const b = analyze('overflow-anchor: none (proposed fix)', await collect())
// Clean up our tag.
await evalP(`document.querySelectorAll('[data-se-anchor]').forEach(e => e.removeAttribute('data-se-anchor'))`)
console.log('\n══ verdict ══')
const drop = (x, y) => (x === 0 ? (y === 0 ? '0' : 'n/a') : `${Math.round((1 - y / x) * 100)}% fewer`)
console.log(` reverse jumps: auto=${a.reverseJumps} none=${b.reverseJumps} (${drop(a.reverseJumps, b.reverseJumps)})`)
console.log(` big lurches: auto=${a.lurches} none=${b.lurches} (${drop(a.lurches, b.lurches)})`)
console.log(` max jump: auto=${a.maxJump.toFixed(0)}px none=${b.maxJump.toFixed(0)}px`)
console.log(` native moves: auto=${a.nativeMoves} none=${b.nativeMoves} (browser anchoring should ~vanish at none)`)
if (a.reverseJumps + a.lurches > 0 && b.reverseJumps + b.lurches < a.reverseJumps + a.lurches) {
console.log('\n → Jumps drop sharply with overflow-anchor:none → root cause confirmed.')
} else if (a.reverseJumps + a.lurches === 0) {
console.log('\n → No jumps captured this run. Use a longer thread (many code/tool blocks),')
console.log(' raise NOTCHES, and ensure you start scrolled up from the bottom.')
}
ws.close()

View File

@@ -5,7 +5,6 @@ import { useNavigate } from 'react-router-dom'
import { ZoomableImage } from '@/components/chat/zoomable-image'
import { PageLoader } from '@/components/page-loader'
import { Button } from '@/components/ui/button'
import { Codicon } from '@/components/ui/codicon'
import { CopyButton } from '@/components/ui/copy-button'
import {
Pagination,
@@ -25,7 +24,9 @@ import { cn } from '@/lib/utils'
import { notifyError } from '@/store/notifications'
import type { SessionInfo, SessionMessage } from '@/types/hermes'
import { useRefreshHotkey } from '../hooks/use-refresh-hotkey'
import { useRouteEnumParam } from '../hooks/use-route-enum-param'
import { PAGE_INSET_NEG_X, PAGE_INSET_X } from '../layout-constants'
import { PageSearchShell } from '../page-search-shell'
import { sessionRoute } from '../routes'
import type { SetStatusbarItemGroup } from '../shell/statusbar-controls'
@@ -372,14 +373,11 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
const [kindFilter, setKindFilter] = useRouteEnumParam('tab', ARTIFACT_FILTERS, 'all')
const [refreshing, setRefreshing] = useState(false)
const [failedImageIds, setFailedImageIds] = useState<Set<string>>(() => new Set())
const [imagePage, setImagePage] = useState(1)
const [filePage, setFilePage] = useState(1)
const refreshArtifacts = useCallback(async () => {
setRefreshing(true)
try {
const sessions = (await listSessions(30, 1)).sessions
const results = await Promise.allSettled(sessions.map(session => getSessionMessages(session.id)))
@@ -398,11 +396,11 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
} catch (err) {
notifyError(err, 'Artifacts failed to load')
setArtifacts([])
} finally {
setRefreshing(false)
}
}, [])
useRefreshHotkey(refreshArtifacts)
useEffect(() => {
void refreshArtifacts()
}, [refreshArtifacts])
@@ -502,7 +500,11 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
return (
<PageSearchShell
{...props}
filters={
onSearchChange={setQuery}
searchHidden={counts.all === 0}
searchPlaceholder="Search artifacts..."
searchValue={query}
tabs={
<>
<TextTab active={kindFilter === 'all'} onClick={() => setKindFilter('all')}>
All <TextTabMeta>({counts.all})</TextTabMeta>
@@ -518,23 +520,6 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
</TextTab>
</>
}
onSearchChange={setQuery}
searchPlaceholder="Search artifacts..."
searchTrailingAction={
<Button
aria-label={refreshing ? 'Refreshing artifacts' : 'Refresh artifacts'}
className="text-(--ui-text-tertiary) hover:bg-transparent hover:text-foreground"
disabled={refreshing}
onClick={() => void refreshArtifacts()}
size="icon-xs"
title={refreshing ? 'Refreshing artifacts' : 'Refresh artifacts'}
type="button"
variant="ghost"
>
<Codicon name="refresh" size="0.875rem" spinning={refreshing} />
</Button>
}
searchValue={query}
>
{!artifacts ? (
<PageLoader label="Indexing recent session artifacts" />
@@ -549,10 +534,16 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
</div>
) : (
<div className="h-full overflow-y-auto">
<div className="flex flex-col gap-3 px-2 pb-2">
<div className={cn('flex flex-col gap-3 pb-2', PAGE_INSET_X)}>
{visibleImageArtifacts.length > 0 && (
<section className="flex flex-col">
<div className="sticky top-0 z-10 -mx-2 flex h-7 items-center gap-3 overflow-x-auto bg-background px-3">
<div
className={cn(
'sticky top-0 z-10 flex h-7 items-center gap-3 overflow-x-auto bg-background',
PAGE_INSET_NEG_X,
PAGE_INSET_X
)}
>
<ArtifactsPagination
className="ml-auto justify-end px-0"
itemLabel="images"
@@ -578,7 +569,13 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
{visibleFileArtifacts.length > 0 && (
<section className="flex flex-col">
<div className="sticky top-0 z-10 -mx-2 flex h-7 items-center gap-3 overflow-x-auto bg-background px-3">
<div
className={cn(
'sticky top-0 z-10 flex h-7 items-center gap-3 overflow-x-auto bg-background',
PAGE_INSET_NEG_X,
PAGE_INSET_X
)}
>
<ArtifactsPagination
className="ml-auto justify-end px-0"
itemLabel={itemsLabel(kindFilter)}
@@ -588,7 +585,7 @@ export function ArtifactsView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
total={visibleFileArtifacts.length}
/>
</div>
<div className="overflow-x-auto rounded-lg border border-(--ui-stroke-tertiary) bg-(--ui-chat-bubble-background) shadow-sm">
<div className="overflow-x-auto rounded-lg border border-(--ui-stroke-tertiary) bg-(--ui-chat-bubble-background)">
<ArtifactTable artifacts={pagedFileArtifacts} ctx={cellCtx} filter={kindFilter} />
</div>
</section>
@@ -660,11 +657,7 @@ interface ArtifactImageCardProps {
function ArtifactImageCard({ artifact, failedImage, onImageError, onOpenChat }: ArtifactImageCardProps) {
return (
<article
className={cn(
'group/artifact overflow-hidden rounded-lg border border-(--ui-stroke-tertiary) bg-(--ui-chat-bubble-background) shadow-sm'
)}
>
<article className="group/artifact overflow-hidden rounded-lg border border-(--ui-stroke-tertiary) bg-(--ui-chat-bubble-background)">
<div
className={cn(
'relative flex h-40 w-full items-center justify-center overflow-hidden border-b border-(--ui-stroke-tertiary) bg-(--ui-bg-quinary) p-1.5',
@@ -674,7 +667,7 @@ function ArtifactImageCard({ artifact, failedImage, onImageError, onOpenChat }:
{!failedImage && (
<ZoomableImage
alt={artifact.label}
className="max-h-40 max-w-full cursor-zoom-in rounded-md object-contain shadow-sm"
className="max-h-40 max-w-full cursor-zoom-in rounded-md object-contain"
containerClassName="max-h-full"
decoding="async"
loading="lazy"
@@ -702,7 +695,7 @@ function ArtifactImageCard({ artifact, failedImage, onImageError, onOpenChat }:
</div>
<div className="flex flex-wrap gap-1.5">
<Button onClick={() => onOpenChat(artifact.sessionId)} size="xs" type="button" variant="outline">
<Button onClick={() => onOpenChat(artifact.sessionId)} size="xs" type="button" variant="textStrong">
<FolderOpen className="size-3" />
Chat
</Button>
@@ -741,10 +734,7 @@ function ArtifactCellAction({
return (
<button
className={cn(
'flex h-full w-full min-w-0 items-center gap-2 px-2.5 py-1.5 text-left text-[length:var(--conversation-caption-font-size)] leading-(--conversation-caption-line-height) font-normal text-(--ui-text-secondary) no-underline underline-offset-4 decoration-current/20 transition-colors hover:text-foreground hover:underline',
'cursor-pointer'
)}
className="flex h-full w-full min-w-0 items-center gap-2 px-2.5 py-1.5 text-left text-[length:var(--conversation-caption-font-size)] leading-(--conversation-caption-line-height) font-normal text-(--ui-text-secondary) no-underline underline-offset-4 decoration-current/20 transition-colors hover:text-foreground hover:underline"
onClick={onClick}
title={title}
type="button"
@@ -863,7 +853,7 @@ function ArtifactTable({
))}
</tr>
</thead>
<tbody className="divide-y divide-(--ui-stroke-quaternary)">
<tbody>
{artifacts.map(artifact => (
<tr className="group/artifact" key={artifact.id}>
{ARTIFACT_COLUMNS.map(col => {

View File

@@ -0,0 +1,27 @@
import { Codicon } from '@/components/ui/codicon'
import { cn } from '@/lib/utils'
/**
* Full-bleed affordance shown while files are dragged over the chat area. Always
* `pointer-events-none` so the drop lands on the real element underneath and the
* drop-zone handler claims it — the overlay is purely visual. Mirrors the
* composer surface so the two read as one family.
*/
export function ChatDropOverlay({ active }: { active: boolean }) {
return (
<div
aria-hidden
className={cn(
'pointer-events-none absolute inset-0 z-40 flex items-center justify-center p-4 transition-opacity duration-150 ease-out',
active ? 'opacity-100' : 'opacity-0'
)}
data-slot="chat-drop-overlay"
>
<div className="absolute inset-2 rounded-2xl border-2 border-dashed border-[color-mix(in_srgb,var(--dt-composer-ring)_55%,transparent)] bg-[color-mix(in_srgb,var(--dt-card)_55%,transparent)] backdrop-blur-[2px] [-webkit-backdrop-filter:blur(2px)]" />
<div className="relative flex items-center gap-2 rounded-full border border-[color-mix(in_srgb,var(--dt-composer-ring)_45%,transparent)] bg-[color-mix(in_srgb,var(--dt-card)_92%,transparent)] px-4 py-2 text-[0.8125rem] font-medium text-foreground shadow-composer">
<Codicon className="text-(--ui-accent)" name="cloud-upload" size="1rem" />
Drop files to attach
</div>
</div>
)
}

View File

@@ -1,14 +1,20 @@
import { useState } from 'react'
import { Button } from '@/components/ui/button'
import { Codicon } from '@/components/ui/codicon'
import {
Dialog,
DialogContent,
DialogDescription,
DialogHeader,
DialogTitle
} from '@/components/ui/dialog'
import {
DropdownMenu,
DropdownMenuContent,
DropdownMenuItem,
DropdownMenuLabel,
DropdownMenuSeparator,
DropdownMenuSub,
DropdownMenuSubContent,
DropdownMenuSubTrigger,
DropdownMenuTrigger
} from '@/components/ui/dropdown-menu'
import { Clipboard, FileText, FolderOpen, type IconComponent, ImageIcon, Link, MessageSquareText } from '@/lib/icons'
@@ -17,6 +23,24 @@ import { cn } from '@/lib/utils'
import { GHOST_ICON_BTN } from './controls'
import type { ChatBarState } from './types'
const PROMPT_SNIPPETS: readonly PromptSnippet[] = [
{
description: 'Audit the current change for regressions, dropped edge cases, and missing tests.',
label: 'Code review',
text: 'Please review this for bugs, regressions, and missing tests.'
},
{
description: 'Outline an approach before touching code so the diff stays focused.',
label: 'Implementation plan',
text: 'Please make a concise implementation plan before changing code.'
},
{
description: 'Walk through how the selected code works and link to the key files.',
label: 'Explain this',
text: 'Please explain how this works and point me to the key files.'
}
]
export function ContextMenu({
state,
onInsertText,
@@ -25,81 +49,114 @@ export function ContextMenu({
onPickFiles,
onPickFolders,
onPickImages
}: {
state: ChatBarState
onInsertText: (text: string) => void
onOpenUrlDialog: () => void
onPasteClipboardImage?: () => void
onPickFiles?: () => void
onPickFolders?: () => void
onPickImages?: () => void
}) {
}: ContextMenuProps) {
// Prompt snippets used to be a Radix submenu. That submenu didn't open
// reliably when the parent menu was positioned at the bottom of the
// window (composer "+" anchor), so we promoted it to a real Dialog —
// easier to grow with search / descriptions, and no positioning math.
const [snippetsOpen, setSnippetsOpen] = useState(false)
return (
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button
aria-label={state.tools.label}
className={cn(
GHOST_ICON_BTN,
'data-[state=open]:bg-(--chrome-action-hover) data-[state=open]:text-foreground'
)}
disabled={!state.tools.enabled}
size="icon"
title={state.tools.label}
type="button"
variant="ghost"
>
<Codicon name="add" size="1rem" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="start" className="w-60" side="top" sideOffset={10}>
<DropdownMenuLabel className="text-[0.7rem] font-medium uppercase tracking-wide text-muted-foreground/85">
Attach
</DropdownMenuLabel>
<ContextMenuItem disabled={!onPickFiles} icon={FileText} onSelect={onPickFiles}>
Files
</ContextMenuItem>
<ContextMenuItem disabled={!onPickFolders} icon={FolderOpen} onSelect={onPickFolders}>
Folder
</ContextMenuItem>
<ContextMenuItem disabled={!onPickImages} icon={ImageIcon} onSelect={onPickImages}>
Images
</ContextMenuItem>
<ContextMenuItem disabled={!onPasteClipboardImage} icon={Clipboard} onSelect={onPasteClipboardImage}>
Paste image
</ContextMenuItem>
<ContextMenuItem icon={Link} onSelect={onOpenUrlDialog}>
URL
</ContextMenuItem>
<>
<DropdownMenu>
<DropdownMenuTrigger asChild>
<Button
aria-label={state.tools.label}
className={cn(
GHOST_ICON_BTN,
'data-[state=open]:bg-(--chrome-action-hover) data-[state=open]:text-foreground'
)}
disabled={!state.tools.enabled}
size="icon"
title={state.tools.label}
type="button"
variant="ghost"
>
<Codicon name="add" size="1rem" />
</Button>
</DropdownMenuTrigger>
<DropdownMenuContent align="start" className="w-60" side="top" sideOffset={10}>
<DropdownMenuLabel className="text-[0.7rem] font-medium uppercase tracking-wide text-muted-foreground/85">
Attach
</DropdownMenuLabel>
<ContextMenuItem disabled={!onPickFiles} icon={FileText} onSelect={onPickFiles}>
Files
</ContextMenuItem>
<ContextMenuItem disabled={!onPickFolders} icon={FolderOpen} onSelect={onPickFolders}>
Folder
</ContextMenuItem>
<ContextMenuItem disabled={!onPickImages} icon={ImageIcon} onSelect={onPickImages}>
Images
</ContextMenuItem>
<ContextMenuItem disabled={!onPasteClipboardImage} icon={Clipboard} onSelect={onPasteClipboardImage}>
Paste image
</ContextMenuItem>
<ContextMenuItem icon={Link} onSelect={onOpenUrlDialog}>
URL
</ContextMenuItem>
<DropdownMenuSeparator />
<DropdownMenuSeparator />
<DropdownMenuSub>
<DropdownMenuSubTrigger>
<MessageSquareText />
<span>Prompt snippets</span>
</DropdownMenuSubTrigger>
<DropdownMenuSubContent className="w-72">
{[
{ label: 'Code review', text: 'Please review this for bugs, regressions, and missing tests.' },
{ label: 'Implementation plan', text: 'Please make a concise implementation plan before changing code.' },
{ label: 'Explain this', text: 'Please explain how this works and point me to the key files.' }
].map(snippet => (
<ContextMenuItem icon={MessageSquareText} key={snippet.label} onSelect={() => onInsertText(snippet.text)}>
{snippet.label}
</ContextMenuItem>
))}
</DropdownMenuSubContent>
</DropdownMenuSub>
<ContextMenuItem icon={MessageSquareText} onSelect={() => setSnippetsOpen(true)}>
Prompt snippets
</ContextMenuItem>
<DropdownMenuSeparator />
<DropdownMenuSeparator />
<div className="px-2 py-1 text-[0.7rem] text-muted-foreground/80">
Tip: type <kbd className="rounded bg-muted/70 px-1 py-px font-mono text-[0.65rem]">@</kbd> to reference files
inline.
</div>
</DropdownMenuContent>
</DropdownMenu>
<div className="px-2 py-1 text-[0.7rem] text-muted-foreground/80">
Tip: type <kbd className="rounded bg-muted/70 px-1 py-px font-mono text-[0.65rem]">@</kbd> to reference files
inline.
</div>
</DropdownMenuContent>
</DropdownMenu>
<PromptSnippetsDialog
onInsertText={onInsertText}
onOpenChange={setSnippetsOpen}
open={snippetsOpen}
snippets={PROMPT_SNIPPETS}
/>
</>
)
}
function PromptSnippetsDialog({
onInsertText,
onOpenChange,
open,
snippets
}: PromptSnippetsDialogProps) {
return (
<Dialog onOpenChange={onOpenChange} open={open}>
<DialogContent className="max-w-md gap-3">
<DialogHeader>
<DialogTitle>Prompt snippets</DialogTitle>
<DialogDescription>Pick a starter prompt to drop into the composer.</DialogDescription>
</DialogHeader>
<ul className="grid gap-1">
{snippets.map(snippet => (
<li key={snippet.label}>
<button
className="group/snippet flex w-full items-start gap-2.5 rounded-md border border-transparent px-2.5 py-2 text-left transition-colors hover:border-(--ui-stroke-tertiary) hover:bg-(--ui-control-hover-background) focus-visible:border-(--ui-stroke-tertiary) focus-visible:bg-(--ui-control-hover-background) focus-visible:outline-none"
onClick={() => {
onInsertText(snippet.text)
onOpenChange(false)
}}
type="button"
>
<MessageSquareText className="mt-0.5 size-3.5 shrink-0 text-(--ui-text-tertiary) group-hover/snippet:text-foreground" />
<span className="grid min-w-0 gap-0.5">
<span className="text-sm font-medium text-foreground">{snippet.label}</span>
<span className="text-[length:var(--conversation-caption-font-size)] text-(--ui-text-tertiary)">
{snippet.description}
</span>
</span>
</button>
</li>
))}
</ul>
</DialogContent>
</Dialog>
)
}
@@ -108,12 +165,7 @@ export function ContextMenuItem({
disabled,
icon: Icon,
onSelect
}: {
children: string
disabled?: boolean
icon: IconComponent
onSelect?: () => void
}) {
}: ContextMenuItemProps) {
return (
<DropdownMenuItem disabled={disabled} onSelect={onSelect}>
<Icon />
@@ -121,3 +173,33 @@ export function ContextMenuItem({
</DropdownMenuItem>
)
}
interface ContextMenuItemProps {
children: string
disabled?: boolean
icon: IconComponent
onSelect?: () => void
}
interface ContextMenuProps {
onInsertText: (text: string) => void
onOpenUrlDialog: () => void
onPasteClipboardImage?: () => void
onPickFiles?: () => void
onPickFolders?: () => void
onPickImages?: () => void
state: ChatBarState
}
interface PromptSnippet {
description: string
label: string
text: string
}
interface PromptSnippetsDialogProps {
onInsertText: (text: string) => void
onOpenChange: (open: boolean) => void
open: boolean
snippets: readonly PromptSnippet[]
}

View File

@@ -31,9 +31,10 @@ import {
enqueueQueuedPrompt,
type QueuedPromptEntry,
removeQueuedPrompt,
shouldAutoDrainOnSettle,
updateQueuedPrompt
} from '@/store/composer-queue'
import { $messages } from '@/store/session'
import { $gatewayState, $messages } from '@/store/session'
import { $threadScrolledUp } from '@/store/thread-scroll'
import { extractDroppedFiles, HERMES_PATHS_MIME } from '../hooks/use-composer-actions'
@@ -72,9 +73,39 @@ import { VoiceActivity, VoicePlaybackActivity } from './voice-activity'
const COMPOSER_STACK_BREAKPOINT_PX = 320
// A single editor line is ~28px (--composer-input-min-height 1.625rem + 0.5rem
// vertical padding). Anything taller means the text wrapped to a second line,
// which is when the composer should expand to the stacked layout.
const COMPOSER_SINGLE_LINE_MAX_PX = 36
const COMPOSER_FADE_BACKGROUND =
'linear-gradient(to bottom, transparent, color-mix(in srgb, var(--dt-background) 10%, transparent))'
// Resting composer placeholders. New sessions get open-ended starters; an
// existing chat gets phrasings that read as a continuation of the thread.
// One is picked at random per session (stable until the session changes).
const NEW_SESSION_PLACEHOLDERS = [
'What are we building?',
'Give Hermes a task',
"What's on your mind?",
'Describe what you need',
'What should we tackle?',
'Ask anything',
'Start with a goal'
]
const FOLLOW_UP_PLACEHOLDERS = [
'Send a follow-up',
'Add more context',
'Refine the request',
"What's next?",
'Keep it going',
'Push it further',
'Adjust or continue'
]
const pickPlaceholder = (pool: readonly string[]) => pool[Math.floor(Math.random() * pool.length)]
interface QueueEditState {
attachments: ComposerAttachment[]
draft: string
@@ -124,6 +155,12 @@ export function ChatBar({
const draftRef = useRef(draft)
const previousBusyRef = useRef(busy)
const drainingQueueRef = useRef(false)
// Set when the user explicitly interrupts the running turn via the Stop
// button (busy + empty composer). It suppresses the next busy→false
// auto-drain so an explicit Stop actually halts instead of immediately
// firing the head of the queue. The queue is preserved; the user resumes
// it deliberately via Cmd/Ctrl+K, Enter, or the per-row "send now" arrow.
const userInterruptedRef = useRef(false)
const urlInputRef = useRef<HTMLInputElement | null>(null)
const [urlOpen, setUrlOpen] = useState(false)
@@ -135,6 +172,7 @@ export function ChatBar({
const [queueEdit, setQueueEdit] = useState<QueueEditState | null>(null)
const [focusRequestId, setFocusRequestId] = useState(0)
const dragDepthRef = useRef(0)
const composingRef = useRef(false) // true during IME composition (CJK input)
const lastSpokenIdRef = useRef<string | null>(null)
const narrow = useMediaQuery('(max-width: 30rem)')
@@ -149,7 +187,44 @@ export function ChatBar({
const busyAction = busy && hasComposerPayload ? 'queue' : 'stop'
const showHelpHint = draft === '?'
const placeholder = disabled ? 'Starting Hermes...' : 'Send follow-up'
const gatewayState = useStore($gatewayState)
// Resting placeholder: a starter for brand-new sessions, a continuation for
// existing ones. Picked once and only re-rolled when we genuinely move to a
// *different* conversation. Critically, the first id assignment of a freshly
// started session (null → id, on the first send) is treated as the same
// conversation so the placeholder doesn't visibly flip mid-stream.
const [restingPlaceholder, setRestingPlaceholder] = useState(() =>
pickPlaceholder(sessionId ? FOLLOW_UP_PLACEHOLDERS : NEW_SESSION_PLACEHOLDERS)
)
const prevSessionIdRef = useRef(sessionId)
useEffect(() => {
const prev = prevSessionIdRef.current
prevSessionIdRef.current = sessionId
if (prev === sessionId) {
return
}
// null → id: the new session we're already in just got persisted. Keep the
// starter we showed instead of swapping to a follow-up under the user.
if (prev == null && sessionId) {
return
}
setRestingPlaceholder(pickPlaceholder(sessionId ? FOLLOW_UP_PLACEHOLDERS : NEW_SESSION_PLACEHOLDERS))
}, [sessionId])
// When the bar is disabled it's because the gateway isn't open. Distinguish a
// cold start ("Starting Hermes...") from a dropped connection we're trying to
// restore (e.g. after the Mac slept) so the stuck state reads as recoverable.
const placeholder = disabled
? gatewayState === 'closed' || gatewayState === 'error'
? 'Reconnecting to Hermes…'
: 'Starting Hermes...'
: restingPlaceholder
const focusInput = useCallback(() => {
focusComposerInput(editorRef.current)
@@ -240,14 +315,13 @@ export function ChatBar({
}
}, [urlOpen])
// Track expansion via cheap heuristics (newline or length threshold) instead
// of reading editor.scrollHeight on every keystroke. scrollHeight forces a
// synchronous layout flush — measured at 2.27 layouts per character typed
// (see scripts/leak-typing.mjs). With ~30 chars before a typical wrap on
// composer-default-width, this heuristic flips at roughly the right time
// and the user only notices if they type far past the wrap boundary
// without a newline; in that case the ResizeObserver below catches it via
// a height delta and we still expand.
// Expansion (input on its own full-width row, controls below) is driven by
// the editor's *actual* rendered height via the ResizeObserver in
// syncComposerMetrics — it only fires when the text genuinely wraps to a
// second line, so the layout flips exactly at the wrap point rather than at
// a guessed character count. We only handle the two cases the observer
// can't: an explicit newline (expand before layout settles) and an emptied
// draft (collapse back). We never read scrollHeight per keystroke.
useEffect(() => {
if (!draft) {
setExpanded(false)
@@ -259,7 +333,7 @@ export function ChatBar({
return
}
if (draft.includes('\n') || draft.length > 60) {
if (draft.includes('\n')) {
setExpanded(true)
}
}, [draft, expanded])
@@ -295,6 +369,18 @@ export function ChatBar({
}
}
// Expand once the input has actually wrapped past a single line. The
// observer only fires on real size changes, so this reads scrollHeight at
// most once per wrap (not per keystroke). One line ≈ 28px (1.625rem
// min-height + padding); a second line clears ~36px. We only ever expand
// here — collapse is handled by the emptied-draft effect to avoid
// oscillating across the wrap boundary as the input switches widths.
const editor = editorRef.current
if (editor && editor.scrollHeight > COMPOSER_SINGLE_LINE_MAX_PX) {
setExpanded(true)
}
if (height > 0) {
const bucket = Math.round(height / 8) * 8
@@ -314,7 +400,7 @@ export function ChatBar({
}
}, [])
useResizeObserver(syncComposerMetrics, composerRef, composerSurfaceRef)
useResizeObserver(syncComposerMetrics, composerRef, composerSurfaceRef, editorRef)
useEffect(() => {
return () => {
@@ -392,13 +478,19 @@ export function ChatBar({
return
}
const pastedText = event.clipboardData.getData('text')
// Trim surrounding whitespace so a copy that dragged along leading/trailing
// blank lines (common when selecting from terminals, code blocks, web pages)
// doesn't dump multiline padding into the composer. Internal newlines are
// preserved — only the edges are cleaned up.
const pastedText = event.clipboardData.getData('text').trim()
if (!pastedText) {
event.preventDefault()
return
}
if (DATA_IMAGE_URL_RE.test(pastedText.trim())) {
if (DATA_IMAGE_URL_RE.test(pastedText)) {
event.preventDefault()
return
@@ -414,6 +506,14 @@ export function ChatBar({
const [trigger, setTrigger] = useState<TriggerState | null>(null)
const [triggerActive, setTriggerActive] = useState(0)
const [triggerItems, setTriggerItems] = useState<readonly Unstable_TriggerItem[]>([])
// Set synchronously in keydown when the open trigger popover consumes a
// navigation/control key (Arrow/Enter/Tab/Escape). The subsequent keyup must
// NOT run refreshTrigger for that keypress: it never edits text, and for
// Escape the keydown has already set trigger=null, so a keyup refresh would
// re-detect the still-present `/` and instantly reopen the menu. A ref is
// used instead of reading `trigger` in keyup because by keyup time React has
// re-rendered and the handler closure sees the post-keydown state.
const triggerKeyConsumedRef = useRef(false)
const refreshTrigger = useCallback(() => {
const editor = editorRef.current
@@ -442,10 +542,24 @@ export function ChatBar({
const detected = detectTrigger(before ?? composerPlainText(editor))
setTrigger(detected)
setTriggerActive(0)
// Only reset the highlight when the trigger actually changed (opened, or
// the query/kind differs). Re-detecting the *same* trigger — e.g. on a
// caret move (mouseup) or a stray refresh — must preserve the user's
// current selection instead of snapping back to the first item.
if (detected?.kind !== trigger?.kind || detected?.query !== trigger?.query) {
setTriggerActive(0)
}
}, [trigger])
const handleEditorInput = (event: FormEvent<HTMLDivElement>) => {
// During IME composition the DOM contains uncommitted preedit text
// mixed with real content. Skip state writes — compositionend will
// deliver the finalized text via a clean input event.
if (composingRef.current) {
return
}
const editor = event.currentTarget
if (editor.childNodes.length === 1 && editor.firstChild?.nodeName === 'BR') {
@@ -545,7 +659,18 @@ export function ChatBar({
}
const handleEditorKeyDown = (event: KeyboardEvent<HTMLDivElement>) => {
if ((event.metaKey || event.ctrlKey) && !event.altKey && !event.shiftKey && event.key.toLowerCase() === 'k') {
// IME composition: Enter confirms composed text, not a message submission.
// We check both composingRef (set by compositionstart/compositionend, robust
// across browsers) and nativeEvent.isComposing (Chromium fallback). Without
// this guard, pressing Enter to finalise a Korean/Japanese/Chinese IME
// preedit fires submitDraft() and splits the message mid-word.
if (composingRef.current || event.nativeEvent.isComposing) {
return
}
// Cmd/Ctrl+Shift+K drains the next queued message. Plain Cmd/Ctrl+K is
// reserved for the global command palette.
if ((event.metaKey || event.ctrlKey) && !event.altKey && event.shiftKey && event.key.toLowerCase() === 'k') {
event.preventDefault()
if (!busy) {
@@ -558,6 +683,7 @@ export function ChatBar({
if (trigger && triggerItems.length > 0) {
if (event.key === 'ArrowDown') {
event.preventDefault()
triggerKeyConsumedRef.current = true
setTriggerActive(idx => (idx + 1) % triggerItems.length)
return
@@ -565,6 +691,7 @@ export function ChatBar({
if (event.key === 'ArrowUp') {
event.preventDefault()
triggerKeyConsumedRef.current = true
setTriggerActive(idx => (idx - 1 + triggerItems.length) % triggerItems.length)
return
@@ -572,6 +699,7 @@ export function ChatBar({
if (event.key === 'Enter' || event.key === 'Tab') {
event.preventDefault()
triggerKeyConsumedRef.current = true
const item = triggerItems[triggerActive]
if (item) {
@@ -583,6 +711,7 @@ export function ChatBar({
if (event.key === 'Escape') {
event.preventDefault()
triggerKeyConsumedRef.current = true
closeTrigger()
return
@@ -603,6 +732,18 @@ export function ChatBar({
}
const handleEditorKeyUp = () => {
// If this keyup belongs to a key the open trigger popover already consumed
// in keydown (Arrow/Enter/Tab/Escape), skip the refresh. Those keys never
// edit text, and for Escape the keydown already closed the menu — a refresh
// here would re-detect the still-present `/` and instantly reopen it. We
// read a ref set during keydown rather than `trigger`, because by keyup
// time React has re-rendered and `trigger` may already be null.
if (triggerKeyConsumedRef.current) {
triggerKeyConsumedRef.current = false
return
}
window.setTimeout(refreshTrigger, 0)
}
@@ -844,26 +985,42 @@ export function ChatBar({
[queueEdit, runDrain]
)
const interruptAndSendNextQueued = useCallback(async () => {
if (queuedPrompts.length === 0) {
return false
}
await Promise.resolve(onCancel())
return drainNextQueued()
}, [drainNextQueued, onCancel, queuedPrompts.length])
// Auto-drain on busy → false (turn settled).
// Auto-drain on busy → false (turn settled). An explicit user interrupt
// (Stop button) sets userInterruptedRef so we skip exactly one auto-drain:
// the user asked to halt, so we must not immediately re-send the queue.
// The queued turns stay intact and the user resumes them on demand.
useEffect(() => {
const wasBusy = previousBusyRef.current
previousBusyRef.current = busy
if (busy || !wasBusy || queuedPrompts.length === 0) {
// Clear the interrupt latch when a new turn starts (false → true). This
// guards the sub-frame race where a Stop click lands after busy already
// flipped false (button not yet unmounted): the stale latch can no longer
// survive into the next turn and wrongly suppress its natural auto-drain.
if (busy && !wasBusy) {
userInterruptedRef.current = false
return
}
void drainNextQueued()
const interrupted = userInterruptedRef.current
// Consume the interrupt latch on any settle so a later natural completion
// is not wrongly suppressed.
if (!busy && wasBusy && interrupted) {
userInterruptedRef.current = false
}
if (
shouldAutoDrainOnSettle({
isBusy: busy,
queueLength: queuedPrompts.length,
userInterrupted: interrupted,
wasBusy
})
) {
void drainNextQueued()
}
}, [busy, drainNextQueued, queuedPrompts.length])
// Clean up queue edit when its target disappears (session swap or external delete).
@@ -886,9 +1043,13 @@ export function ChatBar({
} else if (busy) {
if (hasComposerPayload) {
queueCurrentDraft()
} else if (queuedPrompts.length > 0) {
void interruptAndSendNextQueued()
} else {
// Stop button: an explicit interrupt must actually halt the running
// turn. Mark the interrupt so the busy→false auto-drain effect skips
// re-sending the queue — otherwise a queued follow-up would fire the
// instant we cancel and Stop would appear to "never work". Queued
// turns are preserved; the user sends them on demand.
userInterruptedRef.current = true
triggerHaptic('cancel')
void Promise.resolve(onCancel())
}
@@ -898,7 +1059,8 @@ export function ChatBar({
const submitted = draft
triggerHaptic('submit')
clearDraft()
void onSubmit(submitted)
clearComposerAttachments()
void onSubmit(submitted, { attachments })
}
focusInput()
@@ -1024,8 +1186,10 @@ export function ChatBar({
<div className={cn('relative', stacked ? 'w-full' : 'min-w-(--composer-input-inline-min-width) flex-1')}>
<div
aria-label="Message"
autoCapitalize="off"
autoCorrect="off"
className={cn(
'min-h-(--composer-input-min-height) max-h-(--composer-input-max-height) overflow-y-auto bg-transparent pb-1 pr-1 pt-1 leading-normal text-foreground outline-none disabled:cursor-not-allowed',
'min-h-(--composer-input-min-height) max-h-(--composer-input-max-height) overflow-y-auto whitespace-pre-wrap break-words [overflow-wrap:anywhere] bg-transparent pb-1 pr-1 pt-1 leading-normal text-foreground outline-none disabled:cursor-not-allowed',
'empty:before:content-[attr(data-placeholder)] empty:before:text-muted-foreground/60',
'**:data-ref-text:cursor-default',
stacked && 'pl-3',
@@ -1035,6 +1199,12 @@ export function ChatBar({
data-placeholder={placeholder}
data-slot={RICH_INPUT_SLOT}
onBlur={() => window.setTimeout(closeTrigger, 80)}
onCompositionEnd={() => {
composingRef.current = false
}}
onCompositionStart={() => {
composingRef.current = true
}}
onDragOver={handleInputDragOver}
onDrop={handleInputDrop}
onFocus={() => markActiveComposer('main')}
@@ -1045,6 +1215,7 @@ export function ChatBar({
onPaste={handlePaste}
ref={editorRef}
role="textbox"
spellCheck="true"
suppressContentEditableWarning
/>
{/* assistant-ui requires ComposerPrimitive.Input somewhere in the tree
@@ -1062,7 +1233,7 @@ export function ChatBar({
`asChild` swaps TextareaAutosize for a Radix Slot wrapping our
plain <textarea>, which carries the binding but skips autosize. */}
<ComposerPrimitive.Input asChild tabIndex={-1} unstable_focusOnScrollToBottom={false}>
<ComposerPrimitive.Input asChild submitMode="ctrlEnter" tabIndex={-1} unstable_focusOnScrollToBottom={false}>
<textarea aria-hidden className="sr-only" tabIndex={-1} />
</ComposerPrimitive.Input>
</div>
@@ -1082,6 +1253,9 @@ export function ChatBar({
onDrop={handleDrop}
onSubmit={e => {
e.preventDefault()
if (composingRef.current) {
return
}
submitDraft()
}}
ref={composerRef}
@@ -1184,7 +1358,7 @@ export function ChatBar({
'grid w-full',
stacked
? 'grid-cols-[auto_1fr] gap-(--composer-row-gap) [grid-template-areas:"input_input"_"menu_controls"]'
: 'grid-cols-[auto_1fr_auto] items-end gap-(--composer-control-gap) [grid-template-areas:"menu_input_controls"]'
: 'grid-cols-[auto_1fr_auto] items-center gap-(--composer-control-gap) [grid-template-areas:"menu_input_controls"]'
)}
>
<div className="flex items-center [grid-area:menu]">{contextMenu}</div>

View File

@@ -0,0 +1,183 @@
import type { Unstable_TriggerAdapter, Unstable_TriggerItem } from '@assistant-ui/core'
import { act, fireEvent, render } from '@testing-library/react'
import { useCallback, useEffect, useRef, useState } from 'react'
import { describe, expect, it, vi } from 'vitest'
import { useLiveCompletionAdapter } from './hooks/use-live-completion-adapter'
import { detectTrigger, type TriggerState } from './text-utils'
// Faithful mirror of index.tsx's trigger wiring, driven through REAL DOM
// keydown+keyup events on a contentEditable. Exercises the parts a direct
// reducer-call repro misses: the keyup -> refreshTrigger path, the
// keydown-set "consumed" ref that guards it, and per-press keydown+keyup
// ordering (critical for Escape, whose keydown nulls `trigger` before keyup).
function Harness({
onState
}: {
onState: (s: { active: number; items: readonly Unstable_TriggerItem[]; open: boolean }) => void
}) {
const editorRef = useRef<HTMLDivElement>(null)
const triggerKeyConsumedRef = useRef(false)
const [trigger, setTrigger] = useState<TriggerState | null>(null)
const [triggerActive, setTriggerActive] = useState(0)
const [triggerItems, setTriggerItems] = useState<readonly Unstable_TriggerItem[]>([])
const { adapter } = useLiveCompletionAdapter({
enabled: true,
debounceMs: 0,
fetcher: async (query: string) => ({
query,
items: Array.from({ length: 5 }, (_, i) => ({ text: `/cmd${i}`, display: `/cmd${i}`, meta: '' }))
}),
toItem: (entry, index) => ({ id: `${entry.text}|${index}`, type: 'slash', label: entry.text.slice(1) })
})
const triggerAdapter: Unstable_TriggerAdapter | null = trigger?.kind === '/' ? adapter : null
const refreshTrigger = useCallback(() => {
const editor = editorRef.current
if (!editor) {return}
const raw = editor.textContent ?? ''
if (!raw.includes('@') && !raw.includes('/')) {
if (trigger) {
setTrigger(null)
setTriggerActive(0)
}
return
}
const detected = detectTrigger(raw)
setTrigger(detected)
if (detected?.kind !== trigger?.kind || detected?.query !== trigger?.query) {
setTriggerActive(0)
}
}, [trigger])
useEffect(() => {
if (!trigger || !triggerAdapter?.search) {
setTriggerItems([])
return
}
setTriggerItems(triggerAdapter.search(trigger.query))
}, [trigger, triggerAdapter])
useEffect(() => {
setTriggerActive(idx => Math.min(idx, Math.max(0, triggerItems.length - 1)))
}, [triggerItems.length])
onState({ active: triggerActive, items: triggerItems, open: trigger !== null })
const closeTrigger = () => {
setTrigger(null)
setTriggerItems([])
setTriggerActive(0)
}
// Exact copies of index.tsx handlers, including the keydown-set "consumed"
// ref that the keyup consults.
const handleKeyDown = (event: React.KeyboardEvent<HTMLDivElement>) => {
if (trigger && triggerItems.length > 0) {
if (event.key === 'ArrowDown') {
event.preventDefault()
triggerKeyConsumedRef.current = true
setTriggerActive(idx => (idx + 1) % triggerItems.length)
return
}
if (event.key === 'ArrowUp') {
event.preventDefault()
triggerKeyConsumedRef.current = true
setTriggerActive(idx => (idx - 1 + triggerItems.length) % triggerItems.length)
return
}
if (event.key === 'Escape') {
event.preventDefault()
triggerKeyConsumedRef.current = true
closeTrigger()
return
}
}
}
const handleKeyUp = () => {
if (triggerKeyConsumedRef.current) {
triggerKeyConsumedRef.current = false
return
}
// index.tsx defers via setTimeout(refreshTrigger, 0); call synchronously
// here so the test deterministically observes the keyup-driven refresh.
refreshTrigger()
}
return (
<div
contentEditable
data-testid="editor"
onInput={() => refreshTrigger()}
onKeyDown={handleKeyDown}
onKeyUp={handleKeyUp}
ref={editorRef}
suppressContentEditableWarning
/>
)
}
async function flush() {
await act(async () => {
await new Promise(r => setTimeout(r, 20))
})
}
describe('slash menu navigation — real DOM keydown+keyup', () => {
it('cycles through ALL items and Esc closes (and stays closed)', async () => {
vi.useRealTimers()
let latest = { active: 0, items: [] as readonly Unstable_TriggerItem[], open: false }
const { getByTestId } = render(<Harness onState={s => (latest = s)} />)
const editor = getByTestId('editor')
// Simulate typing '/'.
await act(async () => {
editor.textContent = '/'
fireEvent.input(editor)
})
await flush()
expect(latest.open).toBe(true)
expect(latest.items.length).toBe(5)
// ArrowDown 6x with REAL keydown+keyup pairs. Bug = stuck [0,1,0,1,...].
const seen: number[] = [latest.active]
for (let i = 0; i < 6; i++) {
await act(async () => {
fireEvent.keyDown(editor, { key: 'ArrowDown' })
fireEvent.keyUp(editor, { key: 'ArrowDown' })
await Promise.resolve()
})
seen.push(latest.active)
}
expect(seen).toEqual([0, 1, 2, 3, 4, 0, 1])
// Escape: keydown closes; keyup must NOT reopen (the '/' is still in text).
await act(async () => {
fireEvent.keyDown(editor, { key: 'Escape' })
fireEvent.keyUp(editor, { key: 'Escape' })
await Promise.resolve()
})
await flush()
expect(latest.open).toBe(false)
})
})

View File

@@ -0,0 +1,77 @@
import { describe, expect, it } from 'vitest'
import { blobDedupeKey, detectTrigger, extractClipboardImageBlobs } from './text-utils'
describe('detectTrigger', () => {
it('detects a bare slash trigger with an empty query', () => {
expect(detectTrigger('/')).toEqual({ kind: '/', query: '', tokenLength: 1 })
})
it('detects a slash command query', () => {
expect(detectTrigger('/skill')).toEqual({ kind: '/', query: 'skill', tokenLength: 6 })
})
it('detects a bare at-mention trigger with an empty query', () => {
expect(detectTrigger('@')).toEqual({ kind: '@', query: '', tokenLength: 1 })
})
it('detects an at-mention query', () => {
expect(detectTrigger('@file')).toEqual({ kind: '@', query: 'file', tokenLength: 5 })
})
it('returns null for plain text', () => {
expect(detectTrigger('hello there')).toBeNull()
})
})
describe('extractClipboardImageBlobs', () => {
it('dedupes the same image exposed on both items and files', () => {
const image = new File([new Uint8Array([1, 2, 3])], 'paste.png', {
type: 'image/png',
lastModified: 1_700_000_000_000
})
const clipboard = {
files: {
length: 1,
item: (index: number) => (index === 0 ? image : null)
},
getData: () => '',
items: [
{
kind: 'file',
type: 'image/png',
getAsFile: () => image
}
]
} as unknown as DataTransfer
expect(extractClipboardImageBlobs(clipboard)).toEqual([image])
})
it('falls back to files when items has no image', () => {
const image = new File([new Uint8Array([4, 5])], 'shot.jpg', {
type: 'image/jpeg',
lastModified: 1_700_000_000_001
})
const clipboard = {
files: {
length: 1,
item: (index: number) => (index === 0 ? image : null)
},
getData: () => '',
items: []
} as unknown as DataTransfer
expect(extractClipboardImageBlobs(clipboard)).toEqual([image])
})
})
describe('blobDedupeKey', () => {
it('uses file metadata for File blobs', () => {
const file = new File([], 'a.png', { type: 'image/png', lastModified: 42 })
expect(blobDedupeKey(file)).toBe('file:a.png:0:image/png:42')
})
})

View File

@@ -8,16 +8,31 @@ export interface TriggerState {
const TRIGGER_RE = /(?:^|[\s])([@/])([^\s@/]*)$/
/** Stable key for paste dedupe — `items` and `files` often mirror the same image as different objects. */
export function blobDedupeKey(blob: Blob): string {
if (blob instanceof File) {
return `file:${blob.name}:${blob.size}:${blob.type}:${blob.lastModified}`
}
return `blob:${blob.size}:${blob.type}`
}
export function extractClipboardImageBlobs(clipboard: DataTransfer): Blob[] {
const blobs: Blob[] = []
const seen = new Set<Blob>()
const seen = new Set<string>()
const push = (blob: Blob | null) => {
if (!blob || blob.size === 0 || seen.has(blob)) {
if (!blob || blob.size === 0) {
return
}
seen.add(blob)
const key = blobDedupeKey(blob)
if (seen.has(key)) {
return
}
seen.add(key)
blobs.push(blob)
}
@@ -29,7 +44,8 @@ export function extractClipboardImageBlobs(clipboard: DataTransfer): Blob[] {
}
}
if (clipboard.files?.length) {
// Chromium/Electron expose the same pasted image on both `items` and `files`.
if (blobs.length === 0 && clipboard.files?.length) {
for (let i = 0; i < clipboard.files.length; i += 1) {
const file = clipboard.files.item(i)

View File

@@ -0,0 +1,82 @@
import { type DragEvent as ReactDragEvent, useCallback, useRef, useState } from 'react'
import { dragHasAttachments } from '@/app/chat/composer/inline-refs'
import { type DroppedFile, extractDroppedFiles, HERMES_PATHS_MIME } from './use-composer-actions'
const hasFiles = (event: ReactDragEvent) => dragHasAttachments(event.dataTransfer, HERMES_PATHS_MIME)
interface FileDropZoneOptions {
/** When false the zone ignores drags entirely. */
enabled?: boolean
onDropFiles: (files: DroppedFile[]) => void
}
/**
* "Drop files anywhere in this region" affordance. An enter/leave depth counter
* keeps nested children from flickering the active state; `onDropCapture` clears
* it even when a nested target (the composer) handles the drop and stops
* propagation before our bubble-phase `onDrop` would fire.
*
* Spread `dropHandlers` onto the container; render an overlay off `dragActive`.
*/
export function useFileDropZone({ enabled = true, onDropFiles }: FileDropZoneOptions) {
const [dragActive, setDragActive] = useState(false)
const depth = useRef(0)
const reset = useCallback(() => {
depth.current = 0
setDragActive(false)
}, [])
const onDragEnter = useCallback(
(event: ReactDragEvent) => {
if (!enabled || !hasFiles(event)) {
return
}
event.preventDefault()
depth.current += 1
setDragActive(true)
},
[enabled]
)
const onDragOver = useCallback(
(event: ReactDragEvent) => {
if (!enabled || !hasFiles(event)) {
return
}
event.preventDefault()
event.dataTransfer.dropEffect = 'copy'
},
[enabled]
)
const onDragLeave = useCallback(() => {
if (enabled && --depth.current <= 0) {
reset()
}
}, [enabled, reset])
const onDrop = useCallback(
(event: ReactDragEvent) => {
if (!enabled || !hasFiles(event)) {
return
}
event.preventDefault()
reset()
const files = extractDroppedFiles(event.dataTransfer)
if (files.length) {
onDropFiles(files)
}
},
[enabled, onDropFiles, reset]
)
return { dragActive, dropHandlers: { onDragEnter, onDragLeave, onDragOver, onDrop, onDropCapture: reset } }
}

View File

@@ -7,12 +7,13 @@ import {
import { useStore } from '@nanostores/react'
import { useQuery } from '@tanstack/react-query'
import type * as React from 'react'
import { Suspense, useMemo, useRef } from 'react'
import { Suspense, useCallback, useMemo, useRef } from 'react'
import { useLocation } from 'react-router-dom'
import { Thread } from '@/components/assistant-ui/thread'
import { Backdrop } from '@/components/Backdrop'
import { NotificationStack } from '@/components/notifications'
import { PromptOverlays } from '@/components/prompt-overlays'
import { Button } from '@/components/ui/button'
import { Codicon } from '@/components/ui/codicon'
import { getGlobalModelOptions, type HermesGateway } from '@/hermes'
@@ -36,16 +37,21 @@ import {
$introSeed,
$messages,
$selectedStoredSessionId,
$sessions
$sessions,
sessionPinId
} from '@/store/session'
import type { ModelOptionsResponse } from '@/types/hermes'
import { routeSessionId } from '../routes'
import { titlebarHeaderBaseClass, titlebarHeaderShadowClass } from '../shell/titlebar'
import { ChatDropOverlay } from './chat-drop-overlay'
import { ChatBar, ChatBarFallback } from './composer'
import { requestComposerInsert } from './composer/focus'
import { droppedFileInlineRef } from './composer/inline-refs'
import type { ChatBarState } from './composer/types'
import type { DroppedFile } from './hooks/use-composer-actions'
import { useFileDropZone } from './hooks/use-file-drop-zone'
import { SessionActionsMenu } from './sidebar/session-actions-menu'
import { lastVisibleMessageIsUser, threadLoadingState } from './thread-loading'
@@ -92,9 +98,27 @@ function ChatHeader({
}: ChatHeaderProps) {
const sessions = useStore($sessions)
const pinnedSessionIds = useStore($pinnedSessionIds)
const activeStoredSession = sessions.find(session => session.id === selectedSessionId) || null
const title = activeStoredSession ? sessionTitle(activeStoredSession) : 'New agent'
const selectedIsPinned = selectedSessionId ? pinnedSessionIds.includes(selectedSessionId) : false
const activeStoredSession =
sessions.find(session => session.id === selectedSessionId || session._lineage_root_id === selectedSessionId) || null
const title = activeStoredSession ? sessionTitle(activeStoredSession) : 'New session'
// Pins live on the durable lineage-root id, but selectedSessionId is the live
// (tip) id — resolve through the loaded row so the menu reflects the pin
// state after auto-compression rotates the id.
const selectedIsPinned = activeStoredSession
? pinnedSessionIds.includes(sessionPinId(activeStoredSession))
: selectedSessionId
? pinnedSessionIds.includes(selectedSessionId)
: false
// A brand-new session has no session to pin/delete/rename, so the header is
// just a dead "New session" label + chevron. Drop it (and its border)
// entirely until there's a real session to act on.
if (!selectedSessionId && !activeSessionId && !isRoutedSessionView) {
return null
}
return (
<header className={cn(titlebarHeaderBaseClass, isRoutedSessionView && titlebarHeaderShadowClass)}>
@@ -109,7 +133,7 @@ function ChatHeader({
title={title}
>
<Button
className="pointer-events-auto h-6 min-w-0 gap-1 rounded-md border border-transparent bg-transparent px-2 py-0 text-(--ui-text-secondary) hover:border-(--ui-stroke-tertiary) hover:bg-(--ui-control-hover-background) hover:text-foreground data-[state=open]:border-(--ui-stroke-tertiary) data-[state=open]:bg-(--ui-control-active-background) [-webkit-app-region:no-drag]"
className="pointer-events-auto h-6 min-w-0 gap-1 border border-transparent bg-transparent px-2 py-0 text-(--ui-text-secondary) hover:border-(--ui-stroke-tertiary) hover:bg-(--ui-control-hover-background) hover:text-foreground data-[state=open]:border-(--ui-stroke-tertiary) data-[state=open]:bg-(--ui-control-active-background) [-webkit-app-region:no-drag]"
type="button"
variant="ghost"
>
@@ -267,6 +291,24 @@ export function ChatView({
onReload
})
// Drop files anywhere in the conversation area, not just on the composer
// input — appending the same inline `@file:` ref chips the composer drop
// produces (vs. attachment cards) so both surfaces behave identically.
const onDropFiles = useCallback(
(candidates: DroppedFile[]) => {
const refs = candidates
.map(candidate => droppedFileInlineRef(candidate, currentCwd))
.filter((ref): ref is string => Boolean(ref))
if (refs.length) {
requestComposerInsert(refs.join(' '), { mode: 'inline', target: 'main' })
}
},
[currentCwd]
)
const { dragActive, dropHandlers } = useFileDropZone({ enabled: showChatBar, onDropFiles })
return (
<div
className={cn(
@@ -284,8 +326,12 @@ export function ChatView({
/>
<NotificationStack />
<PromptOverlays />
<div className="relative min-h-0 max-w-full flex-1 overflow-hidden bg-(--ui-chat-surface-background) contain-[layout_paint]">
<div
className="relative min-h-0 max-w-full flex-1 overflow-hidden bg-(--ui-chat-surface-background) contain-[layout_paint]"
{...dropHandlers}
>
<AssistantRuntimeProvider runtime={runtime}>
<Thread
clampToComposer={showChatBar}
@@ -326,6 +372,7 @@ export function ChatView({
</Suspense>
)}
</AssistantRuntimeProvider>
<ChatDropOverlay active={dragActive} />
</div>
</div>
)

View File

@@ -82,7 +82,7 @@ function ConsoleRow({ copyText, log, onSend, onToggleSelect, selected }: Console
>
<button
className={cn(
'mt-0.5 cursor-pointer text-left uppercase opacity-70 transition-colors hover:opacity-100',
'mt-0.5 text-left uppercase opacity-70 transition-colors hover:opacity-100',
consoleLevelClass[log.level] ?? consoleLevelClass[0]
)}
onClick={onToggleSelect}

View File

@@ -11,6 +11,7 @@ import ShikiHighlighter from 'react-shiki'
import { Streamdown } from 'streamdown'
import { HERMES_PATHS_MIME } from '@/app/chat/hooks/use-composer-actions'
import { PageLoader } from '@/components/page-loader'
import { cn } from '@/lib/utils'
import type { PreviewTarget } from '@/store/preview'
@@ -481,7 +482,7 @@ export function LocalFilePreview({ reloadKey, target }: { reloadKey: number; tar
}, [blockedByTarget, filePath, forcePreview, isImage, isText, reloadKey, target.language])
if (state.loading) {
return <div className="grid h-full place-items-center text-xs text-muted-foreground">Loading preview</div>
return <PageLoader label="Loading preview" />
}
if (state.error) {

View File

@@ -83,7 +83,7 @@ function PreviewLoadError({
body={
<>
<a
className="pointer-events-auto block cursor-pointer font-mono text-muted-foreground/90 underline decoration-current/20 underline-offset-4 transition-colors hover:text-foreground"
className="pointer-events-auto block font-mono text-muted-foreground/90 underline decoration-current/20 underline-offset-4 transition-colors hover:text-foreground"
href={error.url}
onClick={event => {
event.preventDefault()
@@ -608,7 +608,7 @@ export function PreviewPane({
<div className="pointer-events-none flex min-h-(--titlebar-height) items-center gap-1.5 border-b border-border/60 bg-background px-2 py-1">
<div className="min-w-0 flex-1">
<a
className="pointer-events-auto inline max-w-full cursor-pointer truncate text-left text-xs font-medium text-foreground underline-offset-4 decoration-current/20 transition-colors hover:text-primary hover:underline"
className="pointer-events-auto inline max-w-full truncate text-left text-xs font-medium text-foreground underline-offset-4 decoration-current/20 transition-colors hover:text-primary hover:underline"
href={currentUrl}
rel="noreferrer"
target="_blank"

View File

@@ -97,6 +97,17 @@ export function ChatPreviewRail({ onRestartServer, setTitlebarToolGroup }: ChatP
: 'border-r border-(--ui-stroke-quaternary) text-(--ui-text-tertiary) [--tab-bg:var(--ui-sidebar-surface-background)] hover:bg-(--chrome-action-hover) hover:text-foreground'
)}
key={tab.id}
// Middle-click closes the tab, matching browser/IDE muscle
// memory. `onMouseDown` swallows the middle-button press so
// Chromium doesn't switch into autoscroll mode.
onAuxClick={event => {
if (event.button !== 1) return
event.preventDefault()
closeRightRailTab(tab.id)
}}
onMouseDown={event => {
if (event.button === 1) event.preventDefault()
}}
>
{active && (
<span aria-hidden="true" className="absolute inset-x-0 top-0 h-px bg-(--ui-stroke-primary)" />

View File

@@ -17,12 +17,13 @@ import {
import { CSS } from '@dnd-kit/utilities'
import { useStore } from '@nanostores/react'
import type * as React from 'react'
import { useMemo, useState } from 'react'
import { useEffect, useMemo, useState } from 'react'
import { Button } from '@/components/ui/button'
import { Codicon } from '@/components/ui/codicon'
import { DisclosureCaret } from '@/components/ui/disclosure-caret'
import { KbdGroup } from '@/components/ui/kbd'
import { SearchField } from '@/components/ui/search-field'
import {
Sidebar,
SidebarContent,
@@ -33,9 +34,10 @@ import {
SidebarMenuItem
} from '@/components/ui/sidebar'
import { Skeleton } from '@/components/ui/skeleton'
import type { SessionInfo } from '@/hermes'
import { searchSessions, type SessionInfo, type SessionSearchResult } from '@/hermes'
import { cn } from '@/lib/utils'
import {
$panesFlipped,
$pinnedSessionIds,
$sidebarAgentsGrouped,
$sidebarOpen,
@@ -54,7 +56,8 @@ import {
$sessions,
$sessionsLoading,
$sessionsTotal,
$workingSessionIds
$workingSessionIds,
sessionPinId
} from '@/store/session'
import { type AppView, ARTIFACTS_ROUTE, MESSAGING_ROUTE, SKILLS_ROUTE } from '../../routes'
@@ -66,9 +69,25 @@ import { VirtualSessionList } from './virtual-session-list'
const VIRTUALIZE_THRESHOLD = 25
// Render the modifier key the user actually presses on this platform. The
// global accelerator is bound to both Cmd+N (macOS) and Ctrl+N (everywhere
// else) in desktop-controller.tsx, but the hint should match muscle memory.
const NEW_SESSION_KBD: readonly string[] =
typeof navigator !== 'undefined' && navigator.platform.toLowerCase().includes('mac') ? ['⌘', 'N'] : ['Ctrl', 'N']
const SIDEBAR_NAV: SidebarNavItem[] = [
{ id: 'new-session', label: 'New agent', icon: props => <Codicon name="robot" {...props} />, action: 'new-session' },
{ id: 'skills', label: 'Skills', icon: props => <Codicon name="symbol-misc" {...props} />, route: SKILLS_ROUTE },
{
id: 'new-session',
label: 'New session',
icon: props => <Codicon name="robot" {...props} />,
action: 'new-session'
},
{
id: 'skills',
label: 'Skills & Tools',
icon: props => <Codicon name="symbol-misc" {...props} />,
route: SKILLS_ROUTE
},
{ id: 'messaging', label: 'Messaging', icon: props => <Codicon name="comment" {...props} />, route: MESSAGING_ROUTE },
{ id: 'artifacts', label: 'Artifacts', icon: props => <Codicon name="files" {...props} />, route: ARTIFACTS_ROUTE }
]
@@ -115,6 +134,32 @@ const baseName = (path: string) =>
.filter(Boolean)
.pop()
// FTS results cover sessions that aren't in the loaded page; synthesize a
// minimal SessionInfo so they render in the same row component (resume works
// by id; the snippet stands in for the preview).
function searchResultToSession(result: SessionSearchResult): SessionInfo {
const ts = result.session_started ?? Date.now() / 1000
return {
archived: false,
cwd: null,
ended_at: null,
id: result.session_id,
_lineage_root_id: result.lineage_root ?? null,
input_tokens: 0,
is_active: false,
last_active: ts,
message_count: 0,
model: result.model ?? null,
output_tokens: 0,
preview: result.snippet?.trim() || null,
source: result.source ?? null,
started_at: ts,
title: null,
tool_call_count: 0
}
}
function workspaceGroupsFor(sessions: SessionInfo[]): SidebarSessionGroup[] {
const groups = new Map<string, SidebarSessionGroup>()
@@ -128,6 +173,14 @@ function workspaceGroupsFor(sessions: SessionInfo[]): SidebarSessionGroup[] {
groups.set(id, group)
}
// Groups keep recency order (Map insertion = first-seen in the recency-sorted
// input, so an active project floats up), but rows *within* a group sort by
// creation time so they don't reshuffle every time a message lands — keeps
// muscle memory intact.
for (const group of groups.values()) {
group.sessions.sort((a, b) => b.started_at - a.started_at)
}
return [...groups.values()]
}
@@ -149,6 +202,8 @@ interface ChatSidebarProps extends React.ComponentProps<typeof Sidebar> {
onLoadMoreSessions: () => void
onResumeSession: (sessionId: string) => void
onDeleteSession: (sessionId: string) => void
onArchiveSession: (sessionId: string) => void
onNewSessionInWorkspace: (path: null | string) => void
}
export function ChatSidebar({
@@ -156,9 +211,12 @@ export function ChatSidebar({
onNavigate,
onLoadMoreSessions,
onResumeSession,
onDeleteSession
onDeleteSession,
onArchiveSession,
onNewSessionInWorkspace
}: ChatSidebarProps) {
const sidebarOpen = useStore($sidebarOpen)
const panesFlipped = useStore($panesFlipped)
const agentsGrouped = useStore($sidebarAgentsGrouped)
const pinnedSessionIds = useStore($pinnedSessionIds)
const pinsOpen = useStore($sidebarPinsOpen)
@@ -170,6 +228,29 @@ export function ChatSidebar({
const workingSessionIds = useStore($workingSessionIds)
const [agentOrderIds, setAgentOrderIds] = useState<string[]>([])
const [workspaceOrderIds, setWorkspaceOrderIds] = useState<string[]>([])
const [searchQuery, setSearchQuery] = useState('')
const [serverMatches, setServerMatches] = useState<SessionSearchResult[]>([])
const [newSessionKbdFlash, setNewSessionKbdFlash] = useState(false)
const trimmedQuery = searchQuery.trim()
// Flash the ⌘N hint full-opacity (no transition) for the press, so hitting
// the shortcut visibly pings its affordance in the sidebar.
useEffect(() => {
let timeout: ReturnType<typeof setTimeout> | undefined
const onShortcut = () => {
setNewSessionKbdFlash(true)
clearTimeout(timeout)
timeout = setTimeout(() => setNewSessionKbdFlash(false), 140)
}
window.addEventListener('hermes:new-session-shortcut', onShortcut)
return () => {
window.removeEventListener('hermes:new-session-shortcut', onShortcut)
clearTimeout(timeout)
}
}, [])
const activeSidebarSessionId = currentView === 'chat' ? selectedSessionId : null
@@ -180,24 +261,99 @@ export function ChatSidebar({
const sortedSessions = useMemo(() => [...sessions].sort((a, b) => sessionTime(b) - sessionTime(a)), [sessions])
const sessionsById = useMemo(() => new Map(sessions.map(s => [s.id, s])), [sessions])
const workingSessionIdSet = useMemo(() => new Set(workingSessionIds), [workingSessionIds])
const visiblePinnedIds = useMemo(
() => pinnedSessionIds.filter(id => sessionsById.has(id)),
[pinnedSessionIds, sessionsById]
)
// Index sessions by both their live id and their lineage-root id so a pin
// stored as the pre-compression root resolves to the live continuation tip.
const sessionByAnyId = useMemo(() => {
const map = new Map<string, SessionInfo>()
const visiblePinnedIdSet = useMemo(() => new Set(visiblePinnedIds), [visiblePinnedIds])
for (const s of sessions) {
map.set(s.id, s)
const pinnedSessions = useMemo(
() => visiblePinnedIds.map(id => sessionsById.get(id)!).filter(Boolean),
[visiblePinnedIds, sessionsById]
)
if (s._lineage_root_id && !map.has(s._lineage_root_id)) {
map.set(s._lineage_root_id, s)
}
}
return map
}, [sessions])
const pinnedSessions = useMemo(() => {
const seen = new Set<string>()
const out: SessionInfo[] = []
for (const pinId of pinnedSessionIds) {
const session = sessionByAnyId.get(pinId)
if (session && !seen.has(session.id)) {
seen.add(session.id)
out.push(session)
}
}
return out
}, [pinnedSessionIds, sessionByAnyId])
const pinnedRealIdSet = useMemo(() => new Set(pinnedSessions.map(s => s.id)), [pinnedSessions])
// Full-text search across *all* sessions (not just the loaded page) so 699
// sessions stay findable. Debounced; loaded sessions are matched instantly
// client-side and merged ahead of the server hits.
useEffect(() => {
if (!trimmedQuery) {
setServerMatches([])
return
}
let cancelled = false
const id = window.setTimeout(() => {
void searchSessions(trimmedQuery)
.then(res => {
if (!cancelled) {
setServerMatches(res.results)
}
})
.catch(() => undefined)
}, 200)
return () => {
cancelled = true
window.clearTimeout(id)
}
}, [trimmedQuery])
const searchResults = useMemo(() => {
if (!trimmedQuery) {
return []
}
const needle = trimmedQuery.toLowerCase()
const out = new Map<string, SessionInfo>()
for (const s of sortedSessions) {
if (`${s.title ?? ''} ${s.preview ?? ''} ${s.cwd ?? ''}`.toLowerCase().includes(needle)) {
out.set(s.id, s)
}
}
for (const match of serverMatches) {
if (out.has(match.session_id)) {
continue
}
const loaded = sessionByAnyId.get(match.session_id)
out.set(match.session_id, loaded ?? searchResultToSession(match))
}
return [...out.values()]
}, [trimmedQuery, sortedSessions, serverMatches, sessionByAnyId])
const unpinnedAgentSessions = useMemo(
() => sortedSessions.filter(s => !visiblePinnedIdSet.has(s.id)),
[sortedSessions, visiblePinnedIdSet]
() => sortedSessions.filter(s => !pinnedRealIdSet.has(s.id)),
[sortedSessions, pinnedRealIdSet]
)
const agentSessions = useMemo(
@@ -227,7 +383,10 @@ export function ChatSidebar({
return
}
reorderPinnedSession(String(active.id), newIndex)
// Sortable ids are live session ids; the pinned store is keyed by durable
// (lineage-root) ids, so translate before reordering.
const dragged = sessionByAnyId.get(String(active.id))
reorderPinnedSession(dragged ? sessionPinId(dragged) : String(active.id), newIndex)
}
const handleAgentDragEnd = ({ active, over }: DragEndEvent) => {
@@ -270,7 +429,8 @@ export function ChatSidebar({
return (
<Sidebar
className={cn(
'relative h-full min-w-0 overflow-hidden border-r border-t-0 border-b-0 border-l-0 text-foreground transition-none',
'relative h-full min-w-0 overflow-hidden border-t-0 border-b-0 text-foreground transition-none',
panesFlipped ? 'border-l border-r-0' : 'border-r border-l-0',
sidebarOpen
? 'border-(--sidebar-edge-border) bg-(--ui-sidebar-surface-background) opacity-100'
: 'pointer-events-none border-transparent bg-transparent opacity-0'
@@ -294,7 +454,7 @@ export function ChatSidebar({
<SidebarMenuButton
aria-disabled={!isInteractive}
className={cn(
'flex h-7 w-full cursor-pointer justify-start gap-2 rounded-md border border-transparent px-2 text-left text-[0.8125rem] font-medium text-(--ui-text-secondary) transition-colors duration-100 ease-out hover:bg-(--ui-control-hover-background) hover:text-foreground hover:transition-none',
'flex h-7 w-full justify-start gap-2 rounded-md border border-transparent px-2 text-left text-[0.8125rem] font-medium text-(--ui-text-secondary) transition-colors duration-100 ease-out hover:bg-(--ui-control-hover-background) hover:text-foreground hover:transition-none',
active &&
'border-(--ui-stroke-tertiary) bg-(--ui-control-active-background) text-foreground shadow-none hover:border-(--ui-stroke-tertiary)!',
!isInteractive &&
@@ -309,7 +469,10 @@ export function ChatSidebar({
<>
<span className="min-w-0 flex-1 truncate max-[46.25rem]:hidden">{item.label}</span>
{item.id === 'new-session' && (
<KbdGroup className="ml-auto max-[46.25rem]:hidden" keys={['⇧', 'N']} />
<KbdGroup
className={cn('ml-auto max-[46.25rem]:hidden', newSessionKbdFlash && 'opacity-100!')}
keys={[...NEW_SESSION_KBD]}
/>
)}
</>
)}
@@ -322,12 +485,48 @@ export function ChatSidebar({
</SidebarGroup>
{sidebarOpen && showSessionSections && (
<div className="shrink-0 px-2 pb-1 pt-1">
<SearchField
aria-label="Search sessions"
onChange={setSearchQuery}
placeholder="Search sessions…"
value={searchQuery}
/>
</div>
)}
{sidebarOpen && showSessionSections && trimmedQuery && (
<SidebarSessionsSection
activeSessionId={activeSidebarSessionId}
contentClassName="flex min-h-0 flex-1 flex-col gap-px overflow-y-auto overscroll-contain pb-1.75"
emptyState={
<div className="grid min-h-24 place-items-center rounded-lg px-2 text-center text-xs text-(--ui-text-tertiary)">
No sessions match {trimmedQuery}.
</div>
}
label="Results"
labelMeta={String(searchResults.length)}
onArchiveSession={onArchiveSession}
onDeleteSession={onDeleteSession}
onResumeSession={onResumeSession}
onToggle={() => undefined}
onTogglePin={pinSession}
open
pinned={false}
rootClassName="min-h-0 flex-1 p-0"
sessions={searchResults}
workingSessionIdSet={workingSessionIdSet}
/>
)}
{sidebarOpen && showSessionSections && !trimmedQuery && (
<SidebarSessionsSection
activeSessionId={activeSidebarSessionId}
contentClassName="flex min-h-10 shrink-0 flex-col gap-px rounded-lg pb-2 pt-1"
dndSensors={dndSensors}
emptyState={<SidebarPinnedEmptyState />}
label="Pinned"
onArchiveSession={onArchiveSession}
onDeleteSession={onDeleteSession}
onReorder={handlePinnedDragEnd}
onResumeSession={onResumeSession}
@@ -342,7 +541,7 @@ export function ChatSidebar({
/>
)}
{sidebarOpen && showSessionSections && (
{sidebarOpen && showSessionSections && !trimmedQuery && (
<SidebarSessionsSection
activeSessionId={activeSidebarSessionId}
contentClassName="flex min-h-0 flex-1 flex-col gap-px overflow-y-auto overscroll-contain pb-1.75"
@@ -360,27 +559,34 @@ export function ChatSidebar({
forceEmptyState={showSessionSkeletons}
groups={agentsGrouped ? agentGroups : undefined}
headerAction={
<Button
aria-label={agentsGrouped ? 'Show agents as a single list' : 'Group agents by workspace'}
className={cn(
'cursor-pointer text-(--ui-text-tertiary) opacity-0 hover:bg-(--ui-control-hover-background) hover:text-foreground hover:opacity-100 focus-visible:opacity-100 group-hover/section:opacity-100',
agentsGrouped && 'bg-(--ui-control-active-background) text-foreground opacity-100'
)}
onClick={event => {
event.stopPropagation()
setSidebarRecentsOpen(true)
setSidebarAgentsGrouped(!agentsGrouped)
}}
size="icon-xs"
title={agentsGrouped ? 'Ungroup agents' : 'Group by workspace'}
variant="ghost"
>
<Codicon name={agentsGrouped ? 'list-unordered' : 'root-folder'} size="0.75rem" />
</Button>
// Grouping operates on unpinned recents; if everything is
// pinned the toggle does nothing visible, so hide it to avoid
// a phantom click target.
agentSessions.length > 0 ? (
<Button
aria-label={agentsGrouped ? 'Show sessions as a single list' : 'Group sessions by workspace'}
className={cn(
'text-(--ui-text-tertiary) opacity-70 hover:bg-(--ui-control-hover-background) hover:text-foreground hover:opacity-100 focus-visible:opacity-100',
agentsGrouped && 'bg-(--ui-control-active-background) text-foreground opacity-100'
)}
onClick={event => {
event.stopPropagation()
setSidebarRecentsOpen(true)
setSidebarAgentsGrouped(!agentsGrouped)
}}
size="icon-xs"
title={agentsGrouped ? 'Ungroup sessions' : 'Group by workspace'}
variant="ghost"
>
<Codicon name={agentsGrouped ? 'list-unordered' : 'root-folder'} size="0.75rem" />
</Button>
) : null
}
label="Agents"
label="Sessions"
labelMeta={countLabel(agentSessions.length, knownSessionTotal)}
onArchiveSession={onArchiveSession}
onDeleteSession={onDeleteSession}
onNewSessionInWorkspace={onNewSessionInWorkspace}
onReorder={handleAgentDragEnd}
onResumeSession={onResumeSession}
onToggle={() => setSidebarRecentsOpen(!agentsOpen)}
@@ -410,7 +616,7 @@ function SidebarSectionHeader({ label, open, onToggle, action, meta }: SidebarSe
return (
<div className="group/section flex shrink-0 items-center justify-between pb-1 pt-1.5">
<button
className="group/section-label flex w-fit cursor-pointer items-center gap-1 bg-transparent text-left leading-none"
className="group/section-label flex w-fit items-center gap-1 bg-transparent text-left leading-none"
onClick={onToggle}
type="button"
>
@@ -451,7 +657,7 @@ function SidebarPinnedEmptyState() {
<span className="grid w-3.5 shrink-0 place-items-center text-(--ui-text-quaternary)">
<Codicon name="pin" size="0.75rem" />
</span>
<span>Shift click to pin a chat</span>
<span>Shift-click a chat to pin</span>
</div>
)
}
@@ -472,7 +678,9 @@ interface SidebarSessionsSectionProps {
workingSessionIdSet: Set<string>
onResumeSession: (sessionId: string) => void
onDeleteSession: (sessionId: string) => void
onArchiveSession: (sessionId: string) => void
onTogglePin: (sessionId: string) => void
onNewSessionInWorkspace?: (path: null | string) => void
pinned: boolean
rootClassName?: string
contentClassName?: string
@@ -496,7 +704,9 @@ function SidebarSessionsSection({
workingSessionIdSet,
onResumeSession,
onDeleteSession,
onArchiveSession,
onTogglePin,
onNewSessionInWorkspace,
pinned,
rootClassName,
contentClassName,
@@ -518,8 +728,9 @@ function SidebarSessionsSection({
isPinned: pinned,
isSelected: session.id === activeSessionId,
isWorking: workingSessionIdSet.has(session.id),
onArchive: () => onArchiveSession(session.id),
onDelete: () => onDeleteSession(session.id),
onPin: () => onTogglePin(session.id),
onPin: () => onTogglePin(sessionPinId(session)),
onResume: () => onResumeSession(session.id),
session
}
@@ -551,9 +762,19 @@ function SidebarSessionsSection({
} else if (groups?.length) {
const groupNodes = groups.map(group =>
dndActive ? (
<SortableSidebarWorkspaceGroup group={group} key={group.id} renderRows={renderSessionList} />
<SortableSidebarWorkspaceGroup
group={group}
key={group.id}
onNewSession={onNewSessionInWorkspace}
renderRows={renderSessionList}
/>
) : (
<SidebarWorkspaceGroup group={group} key={group.id} renderRows={renderSessionList} />
<SidebarWorkspaceGroup
group={group}
key={group.id}
onNewSession={onNewSessionInWorkspace}
renderRows={renderSessionList}
/>
)
)
@@ -568,6 +789,7 @@ function SidebarSessionsSection({
inner = (
<VirtualSessionList
activeSessionId={activeSessionId}
onArchiveSession={onArchiveSession}
onDeleteSession={onDeleteSession}
onResumeSession={onResumeSession}
onTogglePin={onTogglePin}
@@ -610,6 +832,7 @@ function SidebarSessionsSection({
interface SidebarWorkspaceGroupProps extends React.ComponentProps<'div'> {
group: SidebarSessionGroup
renderRows: (sessions: SessionInfo[]) => React.ReactNode
onNewSession?: (path: null | string) => void
reorderable?: boolean
dragging?: boolean
dragHandleProps?: React.HTMLAttributes<HTMLElement>
@@ -618,6 +841,7 @@ interface SidebarWorkspaceGroupProps extends React.ComponentProps<'div'> {
function SidebarWorkspaceGroup({
group,
renderRows,
onNewSession,
reorderable = false,
dragging = false,
dragHandleProps,
@@ -634,18 +858,31 @@ function SidebarWorkspaceGroup({
return (
<div className={cn('grid gap-px', dragging && 'z-10 opacity-60', className)} ref={ref} style={style} {...rest}>
<button
className="group/workspace flex min-h-6 cursor-pointer items-center gap-1 px-2 pt-1 text-left text-[0.6875rem] font-medium text-(--ui-text-tertiary) hover:text-(--ui-text-secondary)"
onClick={() => setOpen(value => !value)}
title={group.path ?? undefined}
type="button"
>
<span className="truncate">{group.label}</span>
<SidebarCount>{group.sessions.length}</SidebarCount>
<DisclosureCaret
className="text-(--ui-text-tertiary) opacity-0 transition group-hover/workspace:opacity-100"
open={open}
/>
<div className="group/workspace flex min-h-6 items-center gap-1 px-2 pt-1 text-[0.6875rem] font-medium text-(--ui-text-tertiary)">
<button
className="flex min-w-0 items-center gap-1 bg-transparent text-left hover:text-(--ui-text-secondary)"
onClick={() => setOpen(value => !value)}
title={group.path ?? undefined}
type="button"
>
<span className="truncate">{group.label}</span>
<SidebarCount>{group.sessions.length}</SidebarCount>
<DisclosureCaret
className="text-(--ui-text-tertiary) opacity-0 transition group-hover/workspace:opacity-100"
open={open}
/>
</button>
{onNewSession && (
<button
aria-label={`New session in ${group.label}`}
className="grid size-4 shrink-0 place-items-center rounded-sm bg-transparent text-(--ui-text-quaternary) opacity-0 transition-opacity hover:bg-(--ui-control-hover-background) hover:text-foreground group-hover/workspace:opacity-100"
onClick={() => onNewSession(group.path)}
title={`New session in ${group.label}`}
type="button"
>
<Codicon name="add" size="0.75rem" />
</button>
)}
{reorderable && (
<span
{...dragHandleProps}
@@ -663,14 +900,14 @@ function SidebarWorkspaceGroup({
/>
</span>
)}
</button>
</div>
{open && (
<>
{renderRows(visibleSessions)}
{hiddenCount > 0 && (
<button
aria-label={`Show ${nextCount} more in ${group.label}`}
className="ml-auto grid size-5 cursor-pointer place-items-center rounded-sm bg-transparent text-(--ui-text-tertiary) transition-colors hover:bg-(--ui-control-hover-background) hover:text-foreground"
className="ml-auto grid size-5 place-items-center rounded-sm bg-transparent text-(--ui-text-tertiary) transition-colors hover:bg-(--ui-control-hover-background) hover:text-foreground"
onClick={() => setVisibleCount(count => count + WORKSPACE_PAGE)}
title={`Show ${nextCount} more in ${group.label}`}
type="button"
@@ -687,6 +924,7 @@ function SidebarWorkspaceGroup({
interface SortableWorkspaceProps {
group: SidebarSessionGroup
renderRows: (sessions: SessionInfo[]) => React.ReactNode
onNewSession?: (path: null | string) => void
}
function SortableSidebarWorkspaceGroup(props: SortableWorkspaceProps) {
@@ -702,6 +940,7 @@ interface SortableSessionRowProps {
isPinned: boolean
isSelected: boolean
isWorking: boolean
onArchive: () => void
onDelete: () => void
onPin: () => void
onResume: () => void
@@ -722,7 +961,7 @@ function SidebarLoadMoreRow({ loading, onClick, step }: SidebarLoadMoreRowProps)
return (
<button
className="flex min-h-5 cursor-pointer items-center gap-1 self-start bg-transparent pl-2 text-left text-[0.6875rem] text-(--ui-text-tertiary) transition-colors duration-100 ease-out hover:text-foreground hover:transition-none disabled:cursor-default disabled:opacity-60 disabled:hover:text-(--ui-text-tertiary)"
className="flex min-h-5 items-center gap-1 self-start bg-transparent pl-2 text-left text-[0.6875rem] text-(--ui-text-tertiary) transition-colors duration-100 ease-out hover:text-foreground hover:transition-none disabled:cursor-default disabled:opacity-60 disabled:hover:text-(--ui-text-tertiary)"
disabled={loading}
onClick={onClick}
type="button"

View File

@@ -26,6 +26,7 @@ interface SessionActions {
title: string
pinned?: boolean
onPin?: () => void
onArchive?: () => void
onDelete?: () => void
}
@@ -40,7 +41,7 @@ interface ItemSpec {
variant?: 'destructive'
}
function useSessionActions({ sessionId, title, pinned = false, onPin, onDelete }: SessionActions) {
function useSessionActions({ sessionId, title, pinned = false, onPin, onArchive, onDelete }: SessionActions) {
const [renameOpen, setRenameOpen] = useState(false)
const items: ItemSpec[] = [
@@ -81,6 +82,15 @@ function useSessionActions({ sessionId, title, pinned = false, onPin, onDelete }
setRenameOpen(true)
}
},
{
disabled: !onArchive,
icon: 'archive',
label: 'Archive',
onSelect: () => {
triggerHaptic('selection')
onArchive?.()
}
},
{
className: 'text-destructive focus:text-destructive',
disabled: !onDelete,

View File

@@ -1,3 +1,4 @@
import { useStore } from '@nanostores/react'
import type * as React from 'react'
import { Button } from '@/components/ui/button'
@@ -6,6 +7,7 @@ import type { SessionInfo } from '@/hermes'
import { sessionTitle } from '@/lib/chat-runtime'
import { triggerHaptic } from '@/lib/haptics'
import { cn } from '@/lib/utils'
import { $attentionSessionIds } from '@/store/session'
import { SessionActionsMenu, SessionContextMenu } from './session-actions-menu'
@@ -14,6 +16,7 @@ interface SidebarSessionRowProps extends React.ComponentProps<'div'> {
isPinned: boolean
isSelected: boolean
isWorking: boolean
onArchive: () => void
onDelete: () => void
onPin: () => void
onResume: () => void
@@ -45,6 +48,7 @@ export function SidebarSessionRow({
isPinned,
isSelected,
isWorking,
onArchive,
onDelete,
onPin,
onResume,
@@ -59,9 +63,20 @@ export function SidebarSessionRow({
const title = sessionTitle(session)
const age = formatAge(session.last_active || session.started_at)
const handleLabel = `Reorder ${title}`
// Subscribe per-row (the leaf) instead of drilling a set through the list —
// the atom is tiny and rarely non-empty. True when a clarify prompt in this
// session is waiting on the user.
const needsInput = useStore($attentionSessionIds).includes(session.id)
return (
<SessionContextMenu onDelete={onDelete} onPin={onPin} pinned={isPinned} sessionId={session.id} title={title}>
<SessionContextMenu
onArchive={onArchive}
onDelete={onDelete}
onPin={onPin}
pinned={isPinned}
sessionId={session.id}
title={title}
>
<div
className={cn(
'group relative grid min-h-[1.625rem] cursor-pointer grid-cols-[minmax(0,1fr)_1.375rem] items-center rounded-md transition-colors duration-100 ease-out hover:bg-(--ui-row-hover-background) hover:transition-none',
@@ -75,9 +90,9 @@ export function SidebarSessionRow({
style={style}
{...rest}
>
{isWorking && <span aria-hidden="true" className="arc-border" />}
{isWorking && !needsInput && <span aria-hidden="true" className="arc-border" />}
<button
className="z-0 flex min-w-0 cursor-pointer items-center gap-1.5 bg-transparent py-0.5 pl-2 pr-1 text-left group-hover:pr-12"
className="z-0 flex min-w-0 items-center gap-1.5 bg-transparent py-0.5 pl-2 pr-1 text-left group-hover:pr-12"
onClick={event => {
if (event.shiftKey) {
event.preventDefault()
@@ -88,6 +103,15 @@ export function SidebarSessionRow({
return
}
if (event.metaKey || event.ctrlKey) {
event.preventDefault()
event.stopPropagation()
triggerHaptic('selection')
onArchive()
return
}
onResume()
}}
type="button"
@@ -96,16 +120,25 @@ export function SidebarSessionRow({
<span
{...dragHandleProps}
aria-label={handleLabel}
className="relative -my-0.5 grid w-4 shrink-0 cursor-grab touch-none place-items-center self-stretch overflow-hidden active:cursor-grabbing"
className={cn(
// Scope the dot↔grabber swap to a local group so the grabber
// only reveals when hovering/focusing the handle itself, not
// anywhere on the row.
'group/handle relative -my-0.5 grid w-4 shrink-0 cursor-grab touch-none place-items-center self-stretch overflow-hidden active:cursor-grabbing',
// The quest-glow box-shadow extends past the dot; let it bleed
// out instead of being clipped by this handle's overflow-hidden.
needsInput && 'overflow-visible'
)}
onClick={event => event.stopPropagation()}
>
<SidebarRowDot
className="transition-opacity group-hover:opacity-0 group-focus-within:opacity-0"
className="transition-opacity group-hover/handle:opacity-0 group-focus-within/handle:opacity-0"
isWorking={isWorking}
needsInput={needsInput}
/>
<Codicon
className={cn(
'absolute text-(--ui-text-quaternary) opacity-0 transition-opacity group-hover:opacity-80 group-focus-within:opacity-80 hover:text-(--ui-text-secondary)',
'absolute text-(--ui-text-quaternary) opacity-0 transition-opacity group-hover/handle:opacity-80 group-focus-within/handle:opacity-80 hover:text-(--ui-text-secondary)',
dragging && 'text-(--ui-text-secondary) opacity-100'
)}
name="grabber"
@@ -113,8 +146,8 @@ export function SidebarSessionRow({
/>
</span>
) : (
<span className="grid w-3.5 shrink-0 place-items-center overflow-hidden">
<SidebarRowDot isWorking={isWorking} />
<span className={cn('grid w-3.5 shrink-0 place-items-center', needsInput ? 'overflow-visible' : 'overflow-hidden')}>
<SidebarRowDot isWorking={isWorking} needsInput={needsInput} />
</span>
)}
<span className="truncate text-[0.8125rem] font-normal text-(--ui-text-secondary) group-hover:text-foreground group-data-[working=true]:text-foreground/90">
@@ -127,10 +160,17 @@ export function SidebarSessionRow({
{age}
</span>
)}
<SessionActionsMenu onDelete={onDelete} onPin={onPin} pinned={isPinned} sessionId={session.id} title={title}>
<SessionActionsMenu
onArchive={onArchive}
onDelete={onDelete}
onPin={onPin}
pinned={isPinned}
sessionId={session.id}
title={title}
>
<Button
aria-label={`Actions for ${title}`}
className="size-5 rounded-md bg-transparent text-transparent transition-colors duration-100 hover:bg-(--ui-control-active-background) hover:text-foreground focus-visible:bg-(--ui-control-active-background) focus-visible:text-foreground focus-visible:ring-0 data-[state=open]:bg-(--ui-control-active-background) data-[state=open]:text-foreground group-hover:text-(--ui-text-tertiary) [&_svg]:size-3.5!"
className="size-5 rounded-[4px] bg-transparent text-transparent transition-colors duration-100 hover:bg-(--ui-control-active-background) hover:text-foreground focus-visible:bg-(--ui-control-active-background) focus-visible:text-foreground focus-visible:ring-0 data-[state=open]:bg-(--ui-control-active-background) data-[state=open]:text-foreground group-hover:text-(--ui-text-tertiary) [&_svg]:size-3.5!"
size="icon"
title="Session actions"
variant="ghost"
@@ -144,7 +184,30 @@ export function SidebarSessionRow({
)
}
function SidebarRowDot({ isWorking, className }: { isWorking: boolean; className?: string }) {
function SidebarRowDot({
isWorking,
needsInput = false,
className
}: {
isWorking: boolean
needsInput?: boolean
className?: string
}) {
// "Needs input" wins over "working": a clarify-blocked session is technically
// still running, but the actionable state is that it's waiting on the user.
// Amber + steady (no ping) reads as "your turn", distinct from the accent
// pulse of an active turn.
if (needsInput) {
return (
<span
aria-label="Needs your input"
className={cn('quest-glow relative size-1.5 rounded-full bg-amber-500', className)}
role="status"
title="Waiting for your answer"
/>
)
}
return (
<span
aria-label={isWorking ? 'Session running' : undefined}

View File

@@ -5,6 +5,7 @@ import { type FC, useCallback, useMemo, useRef } from 'react'
import type { SessionInfo } from '@/hermes'
import { cn } from '@/lib/utils'
import { sessionPinId } from '@/store/session'
import { SidebarSessionRow } from './session-row'
@@ -12,6 +13,7 @@ interface SessionRowCommonProps {
isPinned: boolean
isSelected: boolean
isWorking: boolean
onArchive: () => void
onDelete: () => void
onPin: () => void
onResume: () => void
@@ -20,6 +22,7 @@ interface SessionRowCommonProps {
interface VirtualSessionListProps {
activeSessionId: null | string
className?: string
onArchiveSession: (sessionId: string) => void
onDeleteSession: (sessionId: string) => void
onResumeSession: (sessionId: string) => void
onTogglePin: (sessionId: string) => void
@@ -35,6 +38,7 @@ const OVERSCAN_ROWS = 12
export const VirtualSessionList: FC<VirtualSessionListProps> = ({
activeSessionId,
className,
onArchiveSession,
onDeleteSession,
onResumeSession,
onTogglePin,
@@ -72,8 +76,9 @@ export const VirtualSessionList: FC<VirtualSessionListProps> = ({
isPinned: pinned,
isSelected: session.id === activeSessionId,
isWorking: workingSessionIdSet.has(session.id),
onArchive: () => onArchiveSession(session.id),
onDelete: () => onDeleteSession(session.id),
onPin: () => onTogglePin(session.id),
onPin: () => onTogglePin(sessionPinId(session)),
onResume: () => onResumeSession(session.id)
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,460 @@
import { useStore } from '@nanostores/react'
import { useQuery } from '@tanstack/react-query'
import { Dialog as DialogPrimitive } from 'radix-ui'
import { useCallback, useEffect, useMemo, useState } from 'react'
import { useNavigate } from 'react-router-dom'
import {
Command,
CommandEmpty,
CommandGroup,
CommandInput,
CommandItem,
CommandList
} from '@/components/ui/command'
import { getHermesConfigRecord, listSessions } from '@/hermes'
import { sessionTitle } from '@/lib/chat-runtime'
import {
Activity,
Archive,
BarChart3,
Check,
ChevronLeft,
ChevronRight,
Clock,
Cpu,
Globe,
type IconComponent,
Info,
KeyRound,
MessageCircle,
Monitor,
Moon,
Package,
Palette,
Plus,
Settings,
Sun,
Users,
Wrench
} from '@/lib/icons'
import { cn } from '@/lib/utils'
import { $commandPaletteOpen, closeCommandPalette, setCommandPaletteOpen } from '@/store/command-palette'
import { type ThemeMode, useTheme } from '@/themes/context'
import {
AGENTS_ROUTE,
ARTIFACTS_ROUTE,
COMMAND_CENTER_ROUTE,
CRON_ROUTE,
MESSAGING_ROUTE,
NEW_CHAT_ROUTE,
PROFILES_ROUTE,
sessionRoute,
SETTINGS_ROUTE,
SKILLS_ROUTE
} from '../routes'
import { FIELD_LABELS, SECTIONS } from '../settings/constants'
import { prettyName } from '../settings/helpers'
interface PaletteItem {
active?: boolean
icon: IconComponent
id: string
/** Keep the palette open after running (live-preview pickers like theme/mode). */
keepOpen?: boolean
keywords?: string[]
label: string
/** Action to run when selected. Mutually exclusive with `to`. */
run?: () => void
/** Open a nested palette page (VS Code-style "choose X → options"). */
to?: string
}
interface PaletteGroup {
heading: string
items: PaletteItem[]
}
/** A nested page reachable from a root item via `to`. */
interface PalettePage {
groups: PaletteGroup[]
placeholder: string
title: string
}
interface SessionEntry {
id: string
preview?: string
title: string
}
type SessionRow = Awaited<ReturnType<typeof listSessions>>['sessions'][number]
const toSessionEntry = (session: SessionRow): SessionEntry => ({
id: session.id,
preview: session.preview ?? undefined,
title: sessionTitle(session)
})
const NON_CONFIG_SETTINGS: ReadonlyArray<{ icon: IconComponent; keywords?: string[]; label: string; tab: string }> = [
{ icon: Globe, keywords: ['connection', 'messaging'], label: 'Gateway', tab: 'gateway' },
{ icon: KeyRound, keywords: ['api', 'secrets', 'tokens', 'credentials'], label: 'API Keys', tab: 'keys' },
{ icon: Wrench, keywords: ['servers', 'tools'], label: 'MCP', tab: 'mcp' },
{ icon: Archive, keywords: ['history', 'archived'], label: 'Archived Chats', tab: 'sessions' },
{ icon: Info, keywords: ['version', 'about'], label: 'About', tab: 'about' }
]
const THEME_MODES: ReadonlyArray<{ icon: IconComponent; label: string; mode: ThemeMode }> = [
{ icon: Sun, label: 'Light', mode: 'light' },
{ icon: Moon, label: 'Dark', mode: 'dark' },
{ icon: Monitor, label: 'System', mode: 'system' }
]
function fieldLabel(key: string): string {
return FIELD_LABELS[key] ?? prettyName(key.split('.').pop() ?? key)
}
export function CommandPalette() {
const open = useStore($commandPaletteOpen)
const navigate = useNavigate()
const { availableThemes, mode, resolvedMode, setMode, setTheme, themeName } = useTheme()
const [search, setSearch] = useState('')
const [page, setPage] = useState<string | null>(null)
// Server-backed sources for the type-to-search groups, fetched lazily while
// the palette is open. react-query handles caching/dedup/staleness.
const configQuery = useQuery({ queryKey: ['command-palette', 'config'], queryFn: getHermesConfigRecord, enabled: open })
const sessionsQuery = useQuery({
queryKey: ['command-palette', 'sessions'],
queryFn: () => listSessions(200, 1, 'exclude'),
enabled: open
})
const archivedQuery = useQuery({
queryKey: ['command-palette', 'archived'],
queryFn: () => listSessions(200, 0, 'only'),
enabled: open
})
const mcpServers = useMemo(() => {
const raw = configQuery.data?.mcp_servers
return raw && typeof raw === 'object' && !Array.isArray(raw) ? Object.keys(raw as Record<string, unknown>).sort() : []
}, [configQuery.data])
const sessions = useMemo(() => (sessionsQuery.data?.sessions ?? []).map(toSessionEntry), [sessionsQuery.data])
const archivedSessions = useMemo(() => (archivedQuery.data?.sessions ?? []).map(toSessionEntry), [archivedQuery.data])
// Reset the query/sub-page on close so it reopens clean.
useEffect(() => {
if (!open) {
setSearch('')
setPage(null)
}
}, [open])
const go = useCallback((path: string) => () => navigate(path), [navigate])
const baseGroups = useMemo<PaletteGroup[]>(() => {
const settingsTab = (tab: string) => `${SETTINGS_ROUTE}?tab=${tab}`
return [
{
heading: 'Go to',
items: [
{ icon: Plus, id: 'nav-new', keywords: ['chat', 'create'], label: 'New session', run: go(NEW_CHAT_ROUTE) },
{ icon: Settings, id: 'nav-settings', label: 'Settings', run: go(SETTINGS_ROUTE) },
{
icon: Wrench,
id: 'nav-skills',
keywords: ['tools', 'toolsets', 'providers'],
label: 'Skills & Tools',
run: go(SKILLS_ROUTE)
},
{ icon: MessageCircle, id: 'nav-messaging', label: 'Messaging', run: go(MESSAGING_ROUTE) },
{ icon: Package, id: 'nav-artifacts', label: 'Artifacts', run: go(ARTIFACTS_ROUTE) },
{ icon: Clock, id: 'nav-cron', keywords: ['schedule', 'jobs'], label: 'Cron', run: go(CRON_ROUTE) },
{ icon: Users, id: 'nav-profiles', label: 'Profiles', run: go(PROFILES_ROUTE) },
{ icon: Cpu, id: 'nav-agents', label: 'Agents', run: go(AGENTS_ROUTE) }
]
},
{
heading: 'Command Center',
items: [
{
icon: Archive,
id: 'cc-sessions',
keywords: ['command center', 'sessions', 'pin'],
label: 'Sessions',
run: go(`${COMMAND_CENTER_ROUTE}?section=sessions`)
},
{
icon: Activity,
id: 'cc-system',
keywords: ['command center', 'system', 'status', 'logs'],
label: 'System',
run: go(`${COMMAND_CENTER_ROUTE}?section=system`)
},
{
icon: BarChart3,
id: 'cc-usage',
keywords: ['command center', 'usage', 'tokens', 'cost'],
label: 'Usage',
run: go(`${COMMAND_CENTER_ROUTE}?section=usage`)
}
]
},
{
heading: 'Settings',
items: [
...SECTIONS.map(section => ({
icon: section.icon,
id: `set-config-${section.id}`,
keywords: ['settings', section.label],
label: section.label,
run: go(settingsTab(`config:${section.id}`))
})),
...NON_CONFIG_SETTINGS.map(entry => ({
icon: entry.icon,
id: `set-${entry.tab}`,
keywords: ['settings', ...(entry.keywords ?? [])],
label: entry.label,
run: go(settingsTab(entry.tab))
}))
]
},
{
heading: 'Appearance',
items: [
{
icon: Palette,
id: 'appearance-theme',
keywords: ['theme', 'appearance', 'color', 'palette', 'skin', 'dark', 'light', 'look'],
label: 'Change theme…',
to: 'theme'
},
{
icon: Sun,
id: 'appearance-mode',
keywords: ['appearance', 'color mode', 'brightness', 'dark', 'light', 'system'],
label: 'Change color mode…',
to: 'color-mode'
}
]
}
]
}, [go])
// The long, granular lists (settings fields, API keys, MCP servers, archived
// chats) only surface once the user types — otherwise they'd bury the
// navigation entries on an empty palette.
const searchGroups = useMemo<PaletteGroup[]>(() => {
if (!search.trim()) {
return []
}
const result: PaletteGroup[] = []
if (sessions.length > 0) {
result.push({
heading: 'Sessions',
items: sessions.map(session => ({
icon: MessageCircle,
id: `session-${session.id}`,
keywords: ['chat', 'session', ...(session.preview ? [session.preview] : [])],
label: session.title,
run: go(sessionRoute(session.id))
}))
})
}
const fieldItems = SECTIONS.flatMap(section =>
section.keys.map(key => ({
icon: section.icon,
id: `field-${key}`,
keywords: ['settings', key, section.label],
label: `${section.label}: ${fieldLabel(key)}`,
run: go(`${SETTINGS_ROUTE}?tab=config:${section.id}&field=${encodeURIComponent(key)}`)
}))
)
result.push({ heading: 'Settings fields', items: fieldItems })
if (mcpServers.length > 0) {
result.push({
heading: 'MCP servers',
items: mcpServers.map(name => ({
icon: Wrench,
id: `mcp-${name}`,
keywords: ['mcp', 'server', 'tool'],
label: name,
run: go(`${SETTINGS_ROUTE}?tab=mcp&server=${encodeURIComponent(name)}`)
}))
})
}
if (archivedSessions.length > 0) {
result.push({
heading: 'Archived chats',
items: archivedSessions.map(session => ({
icon: Archive,
id: `archived-${session.id}`,
keywords: ['archived', 'chat', 'session', ...(session.preview ? [session.preview] : [])],
label: session.title,
run: go(`${SETTINGS_ROUTE}?tab=sessions&session=${encodeURIComponent(session.id)}`)
}))
})
}
return result
}, [archivedSessions, go, mcpServers, search, sessions])
const groups = useMemo(() => [...baseGroups, ...searchGroups], [baseGroups, searchGroups])
// Nested palette pages (VS Code-style submenus). Reusable: add an entry here
// and point a root item at it via `to`.
const subPages = useMemo<Record<string, PalettePage>>(
() => ({
theme: {
title: 'Theme',
placeholder: 'Choose a theme…',
// Skins aren't inherently light/dark — the same skin renders in either
// mode. Group by appearance so picking an entry sets skin + mode at
// once, and keep the palette open so each pick previews live.
groups: (['light', 'dark'] as const).map(groupMode => ({
heading: groupMode === 'light' ? 'Light' : 'Dark',
items: availableThemes.map(theme => ({
active: themeName === theme.name && resolvedMode === groupMode,
icon: groupMode === 'light' ? Sun : Moon,
id: `theme-${theme.name}-${groupMode}`,
keepOpen: true,
keywords: ['theme', 'appearance', 'palette', groupMode, theme.label, theme.description ?? ''],
label: theme.label,
run: () => {
setTheme(theme.name)
setMode(groupMode)
}
}))
}))
},
'color-mode': {
title: 'Color mode',
placeholder: 'Choose color mode…',
groups: [
{
heading: 'Color mode',
items: THEME_MODES.map(entry => ({
active: mode === entry.mode,
icon: entry.icon,
id: `mode-${entry.mode}`,
keepOpen: true,
keywords: ['appearance', 'brightness', entry.label],
label: entry.label,
run: () => setMode(entry.mode)
}))
}
]
}
}),
[availableThemes, mode, resolvedMode, setMode, setTheme, themeName]
)
const activePage = page ? subPages[page] : null
const visibleGroups = activePage ? activePage.groups : groups
const placeholder = activePage ? activePage.placeholder : 'Search commands and settings...'
const handleSelect = (item: PaletteItem) => {
if (item.to) {
setPage(item.to)
setSearch('')
return
}
item.run?.()
if (!item.keepOpen) {
closeCommandPalette()
}
}
return (
<DialogPrimitive.Root onOpenChange={setCommandPaletteOpen} open={open}>
<DialogPrimitive.Portal>
<DialogPrimitive.Overlay className="fixed inset-0 z-[200] bg-black/15 backdrop-blur-[1px] data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=open]:animate-in data-[state=open]:fade-in-0" />
<DialogPrimitive.Content
aria-describedby={undefined}
className="fixed left-1/2 top-[14vh] z-[210] w-[min(40rem,calc(100vw-2rem))] -translate-x-1/2 overflow-hidden rounded-xl border border-(--ui-stroke-secondary) bg-(--ui-chat-bubble-background) shadow-lg duration-150 data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=closed]:zoom-out-95 data-[state=open]:animate-in data-[state=open]:fade-in-0 data-[state=open]:slide-in-from-top-2 data-[state=open]:zoom-in-95"
>
<DialogPrimitive.Title className="sr-only">Command palette</DialogPrimitive.Title>
<Command className="bg-transparent" loop>
{activePage && (
<button
className="flex w-full items-center gap-1.5 border-b border-border px-3 py-1.5 text-left text-xs text-muted-foreground transition-colors hover:text-foreground"
onClick={() => setPage(null)}
type="button"
>
<ChevronLeft className="size-3.5" />
<span>Back</span>
<span className="text-muted-foreground/50">/</span>
<span className="font-medium text-foreground">{activePage.title}</span>
</button>
)}
<CommandInput
onKeyDown={event => {
if (!activePage) {
return
}
// In a submenu: Esc and empty-input Backspace step back out
// instead of closing the whole palette.
if (event.key === 'Escape' || (event.key === 'Backspace' && search === '')) {
event.preventDefault()
event.stopPropagation()
setPage(null)
}
}}
onValueChange={setSearch}
placeholder={placeholder}
value={search}
/>
<CommandList className="max-h-[min(24rem,60vh)]">
<CommandEmpty>No results found.</CommandEmpty>
{visibleGroups.map(group => (
<CommandGroup
className="**:[[cmdk-group-heading]]:uppercase **:[[cmdk-group-heading]]:tracking-wider **:[[cmdk-group-heading]]:text-[0.6875rem] **:[[cmdk-group-heading]]:text-muted-foreground/70"
heading={group.heading}
key={group.heading}
>
{group.items.map(item => {
const Icon = item.icon
return (
<CommandItem
className="gap-2.5"
key={item.id}
keywords={item.keywords}
onSelect={() => handleSelect(item)}
value={`${item.label} ${item.keywords?.join(' ') ?? ''} ${item.id}`}
>
<Icon className="size-4 shrink-0 text-muted-foreground" />
<span className="truncate">{item.label}</span>
{item.to ? (
<ChevronRight className="ml-auto size-4 shrink-0 text-muted-foreground/70" />
) : (
<Check className={cn('ml-auto size-4 text-foreground', !item.active && 'invisible')} />
)}
</CommandItem>
)
})}
</CommandGroup>
))}
</CommandList>
</Command>
</DialogPrimitive.Content>
</DialogPrimitive.Portal>
</DialogPrimitive.Root>
)
}

View File

@@ -1,7 +1,7 @@
import type * as React from 'react'
import { useCallback, useEffect, useMemo, useState } from 'react'
import { PageLoader } from '@/components/page-loader'
import { Badge, type BadgeProps } from '@/components/ui/badge'
import { Button } from '@/components/ui/button'
import { Codicon } from '@/components/ui/codicon'
import {
@@ -13,6 +13,7 @@ import {
DialogTitle
} from '@/components/ui/dialog'
import { Input } from '@/components/ui/input'
import { SearchField } from '@/components/ui/search-field'
import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '@/components/ui/select'
import { Textarea } from '@/components/ui/textarea'
import {
@@ -25,12 +26,12 @@ import {
triggerCronJob,
updateCronJob
} from '@/hermes'
import { AlertTriangle, Clock, Pause, Pencil, Play, Trash2, Zap } from '@/lib/icons'
import { AlertTriangle, Clock } from '@/lib/icons'
import { cn } from '@/lib/utils'
import { notify, notifyError } from '@/store/notifications'
import { PageSearchShell } from '../page-search-shell'
import type { SetStatusbarItemGroup } from '../shell/statusbar-controls'
import { useRefreshHotkey } from '../hooks/use-refresh-hotkey'
import { OverlayView } from '../overlays/overlay-view'
const DEFAULT_DELIVER = 'local'
@@ -86,23 +87,16 @@ const SCHEDULE_OPTIONS: ReadonlyArray<ScheduleOption> = [
}
]
const STATE_TONE: Record<string, 'good' | 'muted' | 'warn' | 'bad'> = {
enabled: 'good',
scheduled: 'good',
running: 'good',
const STATE_VARIANT: Record<string, BadgeProps['variant']> = {
enabled: 'default',
scheduled: 'default',
running: 'default',
paused: 'warn',
disabled: 'muted',
error: 'bad',
error: 'destructive',
completed: 'muted'
}
const PILL_TONE: Record<'good' | 'muted' | 'warn' | 'bad', string> = {
good: 'bg-primary/10 text-primary',
muted: 'bg-muted text-muted-foreground',
warn: 'bg-amber-500/10 text-amber-600 dark:text-amber-300',
bad: 'bg-destructive/10 text-destructive'
}
const asText = (value: unknown): string => (typeof value === 'string' ? value : '')
const truncate = (value: string, max = 80): string => (value.length > max ? `${value.slice(0, max)}` : value)
@@ -305,14 +299,13 @@ function matchesQuery(job: CronJob, q: string): boolean {
)
}
interface CronViewProps extends React.ComponentProps<'section'> {
setStatusbarItemGroup?: SetStatusbarItemGroup
interface CronViewProps {
onClose: () => void
}
export function CronView({ setStatusbarItemGroup: _setStatusbarItemGroup, ...props }: CronViewProps) {
export function CronView({ onClose }: CronViewProps) {
const [jobs, setJobs] = useState<CronJob[] | null>(null)
const [query, setQuery] = useState('')
const [refreshing, setRefreshing] = useState(false)
const [busyJobId, setBusyJobId] = useState<null | string>(null)
const [editor, setEditor] = useState<EditorState>({ mode: 'closed' })
@@ -320,18 +313,16 @@ export function CronView({ setStatusbarItemGroup: _setStatusbarItemGroup, ...pro
const [deleting, setDeleting] = useState(false)
const refresh = useCallback(async () => {
setRefreshing(true)
try {
const result = await getCronJobs()
setJobs(result)
} catch (err) {
notifyError(err, 'Failed to load cron jobs')
} finally {
setRefreshing(false)
}
}, [])
useRefreshHotkey(refresh)
useEffect(() => {
void refresh()
}, [refresh])
@@ -426,37 +417,25 @@ export function CronView({ setStatusbarItemGroup: _setStatusbarItemGroup, ...pro
}
return (
<PageSearchShell
{...props}
filters={
<div className="flex flex-wrap items-center justify-center gap-2">
<Button onClick={() => setEditor({ mode: 'create' })} size="sm">
<Codicon name="add" />
New cron
</Button>
</div>
}
onSearchChange={setQuery}
searchPlaceholder="Search cron jobs..."
searchTrailingAction={
<Button
aria-label={refreshing ? 'Refreshing cron jobs' : 'Refresh cron jobs'}
className="text-(--ui-text-tertiary) hover:bg-(--chrome-action-hover) hover:text-foreground"
disabled={refreshing}
onClick={() => void refresh()}
size="icon-xs"
title={refreshing ? 'Refreshing cron jobs' : 'Refresh cron jobs'}
type="button"
variant="ghost"
>
<Codicon name="refresh" size="0.875rem" spinning={refreshing} />
</Button>
}
searchValue={query}
>
{!jobs ? (
<PageLoader label="Loading cron jobs..." />
) : visibleJobs.length === 0 ? (
<OverlayView closeLabel="Close cron" onClose={onClose}>
<div className="flex min-h-0 flex-1 flex-col pt-[calc(var(--titlebar-height)+0.5rem)]">
{totalCount > 0 && (
<div className="mx-auto flex w-full max-w-4xl items-center gap-2 px-4 pb-2">
<SearchField
containerClassName="max-w-[60vw]"
onChange={setQuery}
placeholder="Search cron jobs…"
value={query}
/>
</div>
)}
{!jobs ? (
<PageLoader label="Loading cron jobs..." />
) : visibleJobs.length === 0 ? (
// Empty state owns the primary "create" CTA — we used to also have
// one in the filters bar but it was redundant. Only show the button
// when there are zero jobs total; the search-empty case ("No
// matches") just asks the user to broaden their query.
<EmptyState
actionLabel={totalCount === 0 ? 'Create first cron' : undefined}
description={
@@ -467,25 +446,37 @@ export function CronView({ setStatusbarItemGroup: _setStatusbarItemGroup, ...pro
onAction={totalCount === 0 ? () => setEditor({ mode: 'create' }) : undefined}
title={totalCount === 0 ? 'No scheduled jobs yet' : 'No matches'}
/>
) : (
<div className="h-full overflow-y-auto px-4 py-3">
<div className="divide-y divide-border/40 rounded-lg border border-border/40 bg-background/70">
{visibleJobs.map(job => (
<CronJobRow
busy={busyJobId === job.id}
job={job}
key={job.id}
onDelete={() => setPendingDelete(job)}
onEdit={() => setEditor({ mode: 'edit', job })}
onPauseResume={() => void handlePauseResume(job)}
onTrigger={() => void handleTrigger(job)}
/>
))}
) : (
<div className="mx-auto w-full max-w-4xl min-h-0 flex-1 overflow-y-auto px-4 py-3">
{/* Inline header replaces the old top-bar "New cron" button. We
still need a single, always-visible affordance to add a job
when the list is non-empty (rows themselves only expose
edit/pause/trigger/delete). */}
<div className="mb-2 flex items-center justify-between">
<span className="text-[0.7rem] uppercase tracking-wide text-muted-foreground">
{enabledCount}/{totalCount} active
</span>
<Button onClick={() => setEditor({ mode: 'create' })} size="sm">
<Codicon name="add" />
New cron
</Button>
</div>
<div>
{visibleJobs.map(job => (
<CronJobRow
busy={busyJobId === job.id}
job={job}
key={job.id}
onDelete={() => setPendingDelete(job)}
onEdit={() => setEditor({ mode: 'edit', job })}
onPauseResume={() => void handlePauseResume(job)}
onTrigger={() => void handleTrigger(job)}
/>
))}
</div>
</div>
</div>
)}
<div className="hidden">{totalCount === 0 ? 'No scheduled jobs' : `${enabledCount}/${totalCount} active`}</div>
)}
</div>
<CronEditorDialog editor={editor} onClose={() => setEditor({ mode: 'closed' })} onSave={handleEditorSave} />
<Dialog onOpenChange={open => !open && !deleting && setPendingDelete(null)} open={pendingDelete !== null}>
@@ -512,7 +503,7 @@ export function CronView({ setStatusbarItemGroup: _setStatusbarItemGroup, ...pro
</DialogFooter>
</DialogContent>
</Dialog>
</PageSearchShell>
</OverlayView>
)
}
@@ -540,14 +531,20 @@ function CronJobRow({
return (
<div className="grid gap-3 px-3 py-2.5 sm:grid-cols-[minmax(0,1fr)_auto] sm:items-start">
<button
className="min-w-0 cursor-pointer rounded-md text-left transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring/40"
className="min-w-0 rounded-md text-left transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring/40"
onClick={onEdit}
type="button"
>
<div className="flex flex-wrap items-center gap-2">
<span className="truncate text-sm font-medium">{jobTitle(job)}</span>
<StatePill tone={STATE_TONE[state] ?? 'muted'}>{state}</StatePill>
{deliver && deliver !== DEFAULT_DELIVER && <StatePill tone="muted">{deliver}</StatePill>}
<Badge className="capitalize" variant={STATE_VARIANT[state] ?? 'muted'}>
{state}
</Badge>
{deliver && deliver !== DEFAULT_DELIVER && (
<Badge className="capitalize" variant="muted">
{deliver}
</Badge>
)}
</div>
{hasName && prompt && <p className="mt-1 truncate text-xs text-muted-foreground">{truncate(prompt, 120)}</p>}
<div className="mt-1 flex flex-wrap items-center gap-x-4 gap-y-1 text-[0.68rem] text-muted-foreground">
@@ -573,13 +570,13 @@ function CronJobRow({
onClick={onPauseResume}
title={isPaused ? 'Resume' : 'Pause'}
>
{isPaused ? <Play className="size-3.5" /> : <Pause className="size-3.5" />}
<Codicon name={isPaused ? 'play' : 'debug-pause'} size="0.875rem" />
</IconAction>
<IconAction aria-label="Trigger now" disabled={busy} onClick={onTrigger} title="Trigger now">
<Zap className="size-3.5" />
<Codicon name="zap" size="0.875rem" />
</IconAction>
<IconAction aria-label="Edit cron" onClick={onEdit} title="Edit">
<Pencil className="size-3.5" />
<Codicon name="edit" size="0.875rem" />
</IconAction>
<IconAction
aria-label="Delete cron"
@@ -587,7 +584,7 @@ function CronJobRow({
onClick={onDelete}
title="Delete"
>
<Trash2 className="size-3.5" />
<Codicon name="trash" size="0.875rem" />
</IconAction>
</div>
</div>
@@ -597,8 +594,8 @@ function CronJobRow({
function IconAction({ children, className, ...props }: Omit<React.ComponentProps<typeof Button>, 'size' | 'variant'>) {
return (
<Button
className={cn('size-7 text-muted-foreground hover:text-foreground', className)}
size="icon"
className={cn('text-muted-foreground hover:text-foreground', className)}
size="icon-sm"
variant="ghost"
{...props}
>
@@ -607,16 +604,6 @@ function IconAction({ children, className, ...props }: Omit<React.ComponentProps
)
}
function StatePill({ children, tone }: { children: string; tone: keyof typeof PILL_TONE }) {
return (
<span
className={cn('inline-flex items-center rounded-full px-1.5 py-0.5 text-[0.64rem] capitalize', PILL_TONE[tone])}
>
{children}
</span>
)
}
function EmptyState({
actionLabel,
description,
@@ -761,7 +748,7 @@ function CronEditorDialog({
<div className="grid items-start gap-4 sm:grid-cols-2">
<Field htmlFor="cron-frequency" label="Frequency">
<Select onValueChange={handleSchedulePresetChange} value={schedulePreset}>
<SelectTrigger className="h-9 rounded-md" id="cron-frequency">
<SelectTrigger id="cron-frequency">
<SelectValue />
</SelectTrigger>
<SelectContent>
@@ -776,7 +763,7 @@ function CronEditorDialog({
<Field htmlFor="cron-deliver" label="Deliver to">
<Select onValueChange={setDeliver} value={deliver}>
<SelectTrigger className="h-9 rounded-md" id="cron-deliver">
<SelectTrigger id="cron-deliver">
<SelectValue />
</SelectTrigger>
<SelectContent>

View File

@@ -1,18 +1,21 @@
import { useStore } from '@nanostores/react'
import { useQueryClient } from '@tanstack/react-query'
import { lazy, Suspense, useCallback, useEffect, useRef } from 'react'
import { lazy, Suspense, useCallback, useEffect, useMemo, useRef } from 'react'
import { Navigate, Route, Routes, useLocation, useNavigate, useParams } from 'react-router-dom'
import { BootFailureOverlay } from '@/components/boot-failure-overlay'
import { DesktopInstallOverlay } from '@/components/desktop-install-overlay'
import { DesktopOnboardingOverlay } from '@/components/desktop-onboarding-overlay'
import { GatewayConnectingOverlay } from '@/components/gateway-connecting-overlay'
import { Pane, PaneMain } from '@/components/pane-shell'
import { useSkinCommand } from '@/themes/use-skin-command'
import { formatRefValue } from '../components/assistant-ui/directive-text'
import { getSessionMessages, listSessions } from '../hermes'
import { preserveLocalAssistantErrors, toChatMessages } from '../lib/chat-messages'
import { toggleCommandPalette } from '../store/command-palette'
import {
$panesFlipped,
$pinnedSessionIds,
$sessionsLimit,
bumpSessionsLimit,
@@ -31,8 +34,14 @@ import {
$freshDraftReady,
$gatewayState,
$selectedStoredSessionId,
$sessions,
$workingSessionIds,
mergeSessionPage,
sessionPinId,
setAwaitingResponse,
setBusy,
setCurrentBranch,
setCurrentCwd,
setCurrentModel,
setCurrentProvider,
setMessages,
@@ -51,13 +60,15 @@ import {
PREVIEW_RAIL_PANE_WIDTH
} from './chat/right-rail'
import { ChatSidebar } from './chat/sidebar'
import { CommandPalette } from './command-palette'
import { useGatewayBoot } from './gateway/hooks/use-gateway-boot'
import { useGatewayRequest } from './gateway/hooks/use-gateway-request'
import { ModelPickerOverlay } from './model-picker-overlay'
import { ModelVisibilityOverlay } from './model-visibility-overlay'
import { RightSidebarPane } from './right-sidebar'
import { $terminalTakeover } from './right-sidebar/store'
import { PersistentTerminal, TerminalSlot } from './right-sidebar/terminal/persistent'
import { NEW_CHAT_ROUTE, routeSessionId, sessionRoute } from './routes'
import { NEW_CHAT_ROUTE, routeSessionId, sessionRoute, SETTINGS_ROUTE } from './routes'
import { useContextSuggestions } from './session/hooks/use-context-suggestions'
import { useCwdActions } from './session/hooks/use-cwd-actions'
import { useHermesConfig } from './session/hooks/use-hermes-config'
@@ -72,6 +83,7 @@ import { AppShell } from './shell/app-shell'
import { useOverlayRouting } from './shell/hooks/use-overlay-routing'
import { useStatusSnapshot } from './shell/hooks/use-status-snapshot'
import { useStatusbarItems } from './shell/hooks/use-statusbar-items'
import { ModelMenuPanel } from './shell/model-menu-panel'
import type { StatusbarItem } from './shell/statusbar-controls'
import type { TitlebarTool } from './shell/titlebar-controls'
import { useGroupRegistry } from './shell/use-group-registry'
@@ -103,6 +115,7 @@ export function DesktopController() {
const previewTarget = useStore($previewTarget)
const selectedStoredSessionId = useStore($selectedStoredSessionId)
const terminalTakeover = useStore($terminalTakeover)
const panesFlipped = useStore($panesFlipped)
const routedSessionId = routeSessionId(location.pathname)
const routeToken = `${location.pathname}:${location.search}:${location.hash}`
@@ -116,12 +129,15 @@ export function DesktopController() {
closeOverlayToPreviousRoute,
commandCenterInitialSection,
commandCenterOpen,
cronOpen,
currentView,
openAgents,
openCommandCenterSection,
profilesOpen,
settingsOpen,
toggleCommandCenter
} = useOverlayRouting()
const terminalTakeoverActive = chatOpen && terminalTakeover
const titlebarToolGroups = useGroupRegistry<TitlebarTool>()
@@ -185,6 +201,31 @@ export function DesktopController() {
}
}, [])
// Global chrome shortcuts (plain Cmd/Ctrl, no alt/shift): Cmd+K → command
// palette (the composer's "drain next queued" moved to Cmd+Shift+K), Cmd+. →
// command center (sessions / system / usage).
useEffect(() => {
const onKeyDown = (event: KeyboardEvent) => {
if (!(event.metaKey || event.ctrlKey) || event.altKey || event.shiftKey) {
return
}
const key = event.key.toLowerCase()
if (key === 'k') {
event.preventDefault()
toggleCommandPalette()
} else if (key === '.') {
event.preventDefault()
toggleCommandCenter()
}
}
window.addEventListener('keydown', onKeyDown)
return () => window.removeEventListener('keydown', onKeyDown)
}, [toggleCommandCenter])
const refreshSessions = useCallback(async () => {
const requestId = refreshSessionsRequestRef.current + 1
refreshSessionsRequestRef.current = requestId
@@ -192,10 +233,19 @@ export function DesktopController() {
try {
const limit = $sessionsLimit.get()
const result = await listSessions(limit)
// Require at least one message so abandoned/empty "Untitled" drafts (one
// was created per TUI/desktop launch before the lazy-create fix) don't
// clutter the sidebar.
const result = await listSessions(limit, 1)
if (refreshSessionsRequestRef.current === requestId) {
setSessions(result.sessions)
// Don't hard-replace. Two kinds of rows must survive a refresh the
// server didn't return: (1) sessions whose first turn is still in
// flight (message_count 0, so min_messages=1 omits them) and (2)
// pinned sessions that have aged off the most-recent page — otherwise
// the pin "disappears until you refresh". mergeSessionPage keeps both.
const keepIds = new Set<string>([...$workingSessionIds.get(), ...$pinnedSessionIds.get()])
setSessions(prev => mergeSessionPage(prev, result.sessions, keepIds))
setSessionsTotal(typeof result.total === 'number' ? result.total : result.sessions.length)
}
} finally {
@@ -217,10 +267,14 @@ export function DesktopController() {
return
}
if ($pinnedSessionIds.get().includes(sessionId)) {
unpinSession(sessionId)
// Pin on the durable lineage-root id so the pin survives auto-compression.
const session = $sessions.get().find(s => s.id === sessionId || s._lineage_root_id === sessionId)
const pinId = session ? sessionPinId(session) : sessionId
if ($pinnedSessionIds.get().includes(pinId)) {
unpinSession(pinId)
} else {
pinSession(sessionId)
pinSession(pinId)
}
}, [])
@@ -261,6 +315,22 @@ export function DesktopController() {
requestGateway
})
const openProviderSettings = useCallback(() => {
navigate(`${SETTINGS_ROUTE}?tab=keys`)
}, [navigate])
const modelMenuContent = useMemo(
() =>
gatewayState === 'open' ? (
<ModelMenuPanel
gateway={gatewayRef.current || undefined}
onSelectModel={selectModel}
requestGateway={requestGateway}
/>
) : null,
[gatewayRef, gatewayState, requestGateway, selectModel]
)
useContextSuggestions({
activeSessionId,
activeSessionIdRef,
@@ -324,6 +394,7 @@ export function DesktopController() {
})
const {
archiveSession,
branchCurrentSession,
createBackendSessionForSend,
openSettings,
@@ -358,14 +429,24 @@ export function DesktopController() {
target instanceof HTMLTextAreaElement ||
target instanceof HTMLSelectElement
if (editing || event.defaultPrevented || event.repeat || event.altKey || event.ctrlKey || event.metaKey) {
if (event.defaultPrevented || event.repeat || event.altKey || event.code !== 'KeyN') {
return
}
if (event.shiftKey && event.code === 'KeyN') {
event.preventDefault()
startFreshSessionDraft()
// Two accelerators for "new session":
// - Cmd/Ctrl+N (browser-like, works while typing in any input)
// - Shift+N (single-key, only when no input is focused)
const accelerator = event.metaKey || event.ctrlKey
const singleKey = !accelerator && !editing && event.shiftKey
if (!accelerator && !singleKey) {
return
}
event.preventDefault()
startFreshSessionDraft()
// Briefly light up the sidebar's ⌘N hint so the shortcut is discoverable.
window.dispatchEvent(new CustomEvent('hermes:new-session-shortcut'))
}
window.addEventListener('keydown', onKeyDown)
@@ -392,6 +473,29 @@ export function DesktopController() {
[branchCurrentSession, refreshSessions]
)
const startSessionInWorkspace = useCallback(
(path: null | string) => {
startFreshSessionDraft()
const target = path?.trim()
if (!target) {
return
}
// The next message creates the backend session in $currentCwd, so seed
// it (and the branch) from the workspace the user clicked the + on.
setCurrentCwd(target)
void requestGateway<{ branch?: string; cwd?: string }>('config.get', { key: 'project', cwd: target })
.then(info => {
setCurrentCwd(info.cwd || target)
setCurrentBranch(info.branch || '')
})
.catch(() => undefined)
},
[requestGateway, startFreshSessionDraft]
)
const handleSkinCommand = useSkinCommand()
const { cancelRun, editMessage, handleThreadMessagesChange, reloadFromMessage, submitText, transcribeVoiceAudio } =
@@ -452,8 +556,11 @@ export function DesktopController() {
gatewayLogLines,
gatewayState,
inferenceStatus,
modelMenuContent,
openAgents,
freshDraftReady,
openCommandCenterSection,
requestGateway,
statusSnapshot,
toggleCommandCenter
})
@@ -461,9 +568,11 @@ export function DesktopController() {
const sidebar = (
<ChatSidebar
currentView={currentView}
onArchiveSession={sessionId => void archiveSession(sessionId)}
onDeleteSession={sessionId => void removeSession(sessionId)}
onLoadMoreSessions={loadMoreSessions}
onNavigate={selectSidebarItem}
onNewSessionInWorkspace={startSessionInWorkspace}
onResumeSession={sessionId => navigate(sessionRoute(sessionId))}
/>
)
@@ -484,8 +593,11 @@ export function DesktopController() {
requestGateway={requestGateway}
/>
<ModelPickerOverlay gateway={gatewayRef.current || undefined} onSelect={selectModel} />
<ModelVisibilityOverlay gateway={gatewayRef.current || undefined} onOpenProviders={openProviderSettings} />
<UpdatesOverlay />
<GatewayConnectingOverlay />
<BootFailureOverlay />
<CommandPalette />
{settingsOpen && (
<Suspense fallback={null}>
@@ -497,6 +609,13 @@ export function DesktopController() {
void refreshCurrentModel()
void queryClient.invalidateQueries({ queryKey: ['model-options'] })
}}
onMainModelChanged={(provider, model) => {
setCurrentProvider(provider)
setCurrentModel(model)
updateModelOptionsCache(provider, model, true)
void refreshCurrentModel()
void queryClient.invalidateQueries({ queryKey: ['model-options'] })
}}
/>
</Suspense>
)}
@@ -507,14 +626,6 @@ export function DesktopController() {
initialSection={commandCenterInitialSection}
onClose={closeOverlayToPreviousRoute}
onDeleteSession={removeSession}
onMainModelChanged={(provider, model) => {
setCurrentProvider(provider)
setCurrentModel(model)
updateModelOptionsCache(provider, model, true)
void refreshCurrentModel()
void queryClient.invalidateQueries({ queryKey: ['model-options'] })
}}
onNavigateRoute={path => navigate(path)}
onOpenSession={sessionId => navigate(sessionRoute(sessionId))}
/>
</Suspense>
@@ -525,6 +636,18 @@ export function DesktopController() {
<AgentsView onClose={closeOverlayToPreviousRoute} />
</Suspense>
)}
{cronOpen && (
<Suspense fallback={null}>
<CronView onClose={closeOverlayToPreviousRoute} />
</Suspense>
)}
{profilesOpen && (
<Suspense fallback={null}>
<ProfilesView onClose={closeOverlayToPreviousRoute} />
</Suspense>
)}
</>
)
@@ -536,7 +659,7 @@ export function DesktopController() {
onAddUrl={url => composer.addContextRefAttachment(`@url:${formatRefValue(url)}`, url)}
onAttachDroppedItems={composer.attachDroppedItems}
onAttachImageBlob={composer.attachImageBlob}
onBranchInNewChat={messageId => void branchInNewChat(messageId)}
onBranchInNewChat={branchInNewChat}
onCancel={cancelRun}
onDeleteSelectedSession={() => {
if (selectedStoredSessionId) {
@@ -563,24 +686,64 @@ export function DesktopController() {
</div>
)
// Flipped layout mirrors the default: sessions sidebar → right, file
// browser + preview rail → left. Same panes, swapped sides.
const sidebarSide = panesFlipped ? 'right' : 'left'
const railSide = panesFlipped ? 'left' : 'right'
const previewPane = (
<Pane
disabled={!chatOpen || (!previewTarget && !filePreviewTarget)}
id="preview"
key="preview"
maxWidth={PREVIEW_RAIL_MAX_WIDTH}
minWidth={PREVIEW_RAIL_MIN_WIDTH}
resizable
side={railSide}
width={PREVIEW_RAIL_PANE_WIDTH}
>
{chatOpen ? (
<ChatPreviewRail onRestartServer={restartPreviewServer} setTitlebarToolGroup={setTitlebarToolGroup} />
) : null}
</Pane>
)
const fileBrowserPane = (
<Pane
defaultOpen={false}
disabled={!chatOpen}
id="file-browser"
key="file-browser"
maxWidth={FILE_BROWSER_MAX_WIDTH}
minWidth={FILE_BROWSER_MIN_WIDTH}
resizable
side={railSide}
width={FILE_BROWSER_DEFAULT_WIDTH}
>
<RightSidebarPane
onActivateFile={composer.attachContextFilePath}
onActivateFolder={composer.attachContextFolderPath}
onChangeCwd={changeSessionCwd}
/>
</Pane>
)
return (
<AppShell
commandCenterOpen={commandCenterOpen}
leftStatusbarItems={leftStatusbarItems}
leftTitlebarTools={titlebarToolGroups.flat.left}
onOpenSearch={() => openCommandCenterSection('sessions')}
onOpenSettings={openSettings}
overlays={overlays}
statusbarItems={statusbarItems}
titlebarTools={titlebarToolGroups.flat.right}
>
<Pane
disabled={terminalTakeoverActive}
id="chat-sidebar"
maxWidth={SIDEBAR_MAX_WIDTH}
minWidth={SIDEBAR_DEFAULT_WIDTH}
disabled={terminalTakeoverActive}
resizable
side="left"
side={sidebarSide}
width={`${SIDEBAR_DEFAULT_WIDTH}px`}
>
{sidebar}
@@ -613,25 +776,8 @@ export function DesktopController() {
}
path="artifacts"
/>
<Route
element={
<Suspense fallback={null}>
<CronView setStatusbarItemGroup={setStatusbarItemGroup} />
</Suspense>
}
path="cron"
/>
<Route
element={
<Suspense fallback={null}>
<ProfilesView
setStatusbarItemGroup={setStatusbarItemGroup}
setTitlebarToolGroup={setTitlebarToolGroup}
/>
</Suspense>
}
path="profiles"
/>
<Route element={null} path="cron" />
<Route element={null} path="profiles" />
<Route element={null} path="settings" />
<Route element={null} path="command-center" />
<Route element={null} path="agents" />
@@ -640,35 +786,13 @@ export function DesktopController() {
<Route element={<Navigate replace to={NEW_CHAT_ROUTE} />} path="*" />
</Routes>
</PaneMain>
<Pane
disabled={!chatOpen || (!previewTarget && !filePreviewTarget)}
id="preview"
maxWidth={PREVIEW_RAIL_MAX_WIDTH}
minWidth={PREVIEW_RAIL_MIN_WIDTH}
resizable
side="right"
width={PREVIEW_RAIL_PANE_WIDTH}
>
{chatOpen ? (
<ChatPreviewRail onRestartServer={restartPreviewServer} setTitlebarToolGroup={setTitlebarToolGroup} />
) : null}
</Pane>
<Pane
defaultOpen={false}
disabled={!chatOpen}
id="file-browser"
maxWidth={FILE_BROWSER_MAX_WIDTH}
minWidth={FILE_BROWSER_MIN_WIDTH}
resizable
side="right"
width={FILE_BROWSER_DEFAULT_WIDTH}
>
<RightSidebarPane
onActivateFile={composer.attachContextFilePath}
onActivateFolder={composer.attachContextFolderPath}
onChangeCwd={changeSessionCwd}
/>
</Pane>
{/*
Order within a side maps to column order. Default (rail on the right):
main | preview | file-browser. Flipped (rail on the left): mirror it to
file-browser | preview | main so preview stays adjacent to the chat.
*/}
{panesFlipped ? fileBrowserPane : previewPane}
{panesFlipped ? previewPane : fileBrowserPane}
</AppShell>
)
}

View File

@@ -63,6 +63,94 @@ export function useGatewayBoot({
return () => void (cancelled = true)
}
// --- Reconnect-after-sleep machinery -------------------------------------
// macOS sleep silently drops the renderer's WebSocket. The backend Python
// process keeps running, but nothing re-opened the socket on wake, so the
// composer stayed disabled forever on "Starting Hermes...". Once the
// initial boot succeeds we treat any non-open state as recoverable and
// reconnect with backoff, and we nudge a reconnect on the OS/browser
// signals that fire around wake (power resume, network online, the window
// becoming visible).
let bootCompleted = false
let reconnecting = false
let reconnectTimer: ReturnType<typeof setTimeout> | null = null
let reconnectAttempt = 0
// Wrap the live getter in a call so TS control-flow analysis doesn't narrow
// `connectionState` to a constant across the early-return guards (the state
// genuinely changes between reads).
const gatewayOpen = () => gateway.connectionState === 'open'
const clearReconnectTimer = () => {
if (reconnectTimer !== null) {
clearTimeout(reconnectTimer)
reconnectTimer = null
}
}
const attemptReconnect = async () => {
if (cancelled || reconnecting || gatewayOpen()) {
return
}
reconnecting = true
try {
const conn = await desktop.getConnection()
if (cancelled) {
return
}
publish(conn)
await gateway.connect(conn.wsUrl)
if (cancelled) {
return
}
reconnectAttempt = 0
// Resync state that may have moved on the backend while we were asleep.
await callbacksRef.current.refreshHermesConfig().catch(() => undefined)
await callbacksRef.current.refreshSessions().catch(() => undefined)
} catch {
// Fall through to scheduleReconnect's backoff below.
} finally {
reconnecting = false
if (!cancelled && !gatewayOpen()) {
scheduleReconnect()
}
}
}
function scheduleReconnect() {
if (cancelled || reconnecting || reconnectTimer !== null || gatewayOpen()) {
return
}
// 1s, 2s, 4s … capped at 15s.
const delay = Math.min(15_000, 1_000 * 2 ** Math.min(reconnectAttempt, 4))
reconnectAttempt += 1
reconnectTimer = setTimeout(() => {
reconnectTimer = null
void attemptReconnect()
}, delay)
}
const reconnectNow = () => {
if (cancelled || !bootCompleted) {
return
}
clearReconnectTimer()
reconnectAttempt = 0
if (!gatewayOpen()) {
void attemptReconnect()
}
}
const offBootProgress = desktop.onBootProgress(payload => applyDesktopBootProgress(payload))
void desktop
.getBootProgress()
@@ -79,9 +167,34 @@ export function useGatewayBoot({
callbacksRef.current.onGatewayReady(gateway)
setGateway(gateway)
const offState = gateway.onState(st => void setGatewayState(st))
const offState = gateway.onState(st => {
setGatewayState(st)
if (st === 'open') {
reconnectAttempt = 0
clearReconnectTimer()
} else if (bootCompleted && (st === 'closed' || st === 'error')) {
// The socket dropped after a healthy boot (typically sleep/wake). Try
// to bring it back instead of leaving the composer stuck disabled.
scheduleReconnect()
}
})
const offEvent = gateway.onEvent(event => callbacksRef.current.handleGatewayEvent(event))
// Wake signals: power resume (macOS/Windows), network coming back, and the
// window regaining focus/visibility. Each nudges an immediate reconnect.
const offPowerResume = desktop.onPowerResume?.(() => reconnectNow())
const onOnline = () => reconnectNow()
const onVisible = () => {
if (document.visibilityState === 'visible') {
reconnectNow()
}
}
window.addEventListener('online', onOnline)
document.addEventListener('visibilitychange', onVisible)
const offWindowState = desktop.onWindowStateChanged?.(payload => {
const current = $connection.get()
@@ -141,6 +254,7 @@ export function useGatewayBoot({
})
await callbacksRef.current.refreshSessions()
completeDesktopBoot()
bootCompleted = true
} catch (err) {
if (!cancelled) {
const message = err instanceof Error ? err.message : String(err)
@@ -155,6 +269,10 @@ export function useGatewayBoot({
return () => {
cancelled = true
clearReconnectTimer()
window.removeEventListener('online', onOnline)
document.removeEventListener('visibilitychange', onVisible)
offPowerResume?.()
offState()
offEvent()
offExit()

View File

@@ -0,0 +1,45 @@
import { useEffect, useRef } from 'react'
/**
* Binds the bare `r` key to a refresh action while the calling view is mounted.
* Ignored when a modifier is held, the event repeats, or focus is in an
* editable field (so typing "r" in a search/input never triggers it).
*/
export function useRefreshHotkey(onRefresh: () => void, enabled = true) {
const ref = useRef(onRefresh)
ref.current = onRefresh
useEffect(() => {
if (!enabled) {
return
}
const onKeyDown = (event: KeyboardEvent) => {
if (event.key !== 'r' && event.key !== 'R') {
return
}
if (event.metaKey || event.ctrlKey || event.altKey || event.shiftKey || event.repeat) {
return
}
const target = event.target as HTMLElement | null
if (
target?.isContentEditable ||
target instanceof HTMLInputElement ||
target instanceof HTMLTextAreaElement ||
target instanceof HTMLSelectElement
) {
return
}
event.preventDefault()
ref.current()
}
window.addEventListener('keydown', onKeyDown)
return () => window.removeEventListener('keydown', onKeyDown)
}, [enabled])
}

View File

@@ -0,0 +1,13 @@
// Responsive horizontal gutter for primary content bodies (settings right side,
// skills, artifacts, command center / sessions). Ratio-based so it scales with
// the window, but clamped so it never collapses on narrow widths or runs away
// on ultrawide displays. Headers/tabs intentionally keep their own tighter
// padding.
//
// NOTE: these must stay literal strings — Tailwind's scanner only picks up
// complete class names, so do not build them via template interpolation.
export const PAGE_INSET_X = 'px-[clamp(1.25rem,4vw,4rem)]'
// Matching negative inline-margin to bleed an element (e.g. a sticky header bar)
// out to the gutter edges before re-applying PAGE_INSET_X.
export const PAGE_INSET_NEG_X = '-mx-[clamp(1.25rem,4vw,4rem)]'

View File

@@ -3,6 +3,7 @@ import { useCallback, useEffect, useMemo, useState } from 'react'
import { PageLoader } from '@/components/page-loader'
import { StatusDot, type StatusTone } from '@/components/status-dot'
import { Badge, type BadgeProps } from '@/components/ui/badge'
import { Button } from '@/components/ui/button'
import { DisclosureCaret } from '@/components/ui/disclosure-caret'
import { Input } from '@/components/ui/input'
@@ -17,10 +18,13 @@ import { AlertTriangle, ExternalLink, Save, Trash2 } from '@/lib/icons'
import { cn } from '@/lib/utils'
import { notify, notifyError } from '@/store/notifications'
import { useRefreshHotkey } from '../hooks/use-refresh-hotkey'
import { useRouteEnumParam } from '../hooks/use-route-enum-param'
import { PageSearchShell } from '../page-search-shell'
import type { SetStatusbarItemGroup } from '../shell/statusbar-controls'
import { PlatformAvatar } from './platform-icon'
interface MessagingViewProps extends React.ComponentProps<'section'> {
setStatusbarItemGroup?: SetStatusbarItemGroup
}
@@ -39,34 +43,11 @@ const STATE_LABELS: Record<string, string> = {
startup_failed: 'Startup failed'
}
const PLATFORM_TINTS: Record<string, string> = {
telegram: 'bg-sky-500/15 text-sky-600 dark:text-sky-300',
discord: 'bg-indigo-500/15 text-indigo-600 dark:text-indigo-300',
slack: 'bg-violet-500/15 text-violet-600 dark:text-violet-300',
mattermost: 'bg-blue-500/15 text-blue-600 dark:text-blue-300',
matrix: 'bg-emerald-500/15 text-emerald-600 dark:text-emerald-300',
signal: 'bg-cyan-500/15 text-cyan-600 dark:text-cyan-300',
whatsapp: 'bg-green-500/15 text-green-600 dark:text-green-300',
bluebubbles: 'bg-blue-500/15 text-blue-600 dark:text-blue-300',
homeassistant: 'bg-teal-500/15 text-teal-600 dark:text-teal-300',
email: 'bg-amber-500/15 text-amber-600 dark:text-amber-300',
sms: 'bg-rose-500/15 text-rose-600 dark:text-rose-300',
dingtalk: 'bg-blue-500/15 text-blue-600 dark:text-blue-300',
feishu: 'bg-cyan-500/15 text-cyan-600 dark:text-cyan-300',
wecom: 'bg-emerald-500/15 text-emerald-600 dark:text-emerald-300',
wecom_callback: 'bg-emerald-500/15 text-emerald-600 dark:text-emerald-300',
weixin: 'bg-green-500/15 text-green-600 dark:text-green-300',
qqbot: 'bg-amber-500/15 text-amber-600 dark:text-amber-300',
yuanbao: 'bg-orange-500/15 text-orange-600 dark:text-orange-300',
api_server: 'bg-slate-500/15 text-slate-600 dark:text-slate-300',
webhook: 'bg-zinc-500/15 text-zinc-600 dark:text-zinc-300'
}
const PILL_TONE: Record<StatusTone, string> = {
good: 'bg-primary/10 text-primary',
muted: 'bg-muted text-muted-foreground',
warn: 'bg-amber-500/10 text-amber-600 dark:text-amber-300',
bad: 'bg-destructive/10 text-destructive'
const TONE_VARIANT: Record<StatusTone, BadgeProps['variant']> = {
good: 'default',
muted: 'muted',
warn: 'warn',
bad: 'destructive'
}
const HINT_BY_STATE: Record<string, string> = {
@@ -234,6 +215,8 @@ export function MessagingView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
}
}, [])
useRefreshHotkey(() => void refreshPlatforms())
useEffect(() => {
void refreshPlatforms()
}, [refreshPlatforms])
@@ -364,15 +347,15 @@ export function MessagingView({ setStatusbarItemGroup: _setStatusbarItemGroup, .
<PageSearchShell
{...props}
onSearchChange={setQuery}
searchHidden={(platforms?.length ?? 0) === 0}
searchPlaceholder="Search messaging..."
searchTrailingAction={null}
searchValue={query}
>
{!platforms ? (
<PageLoader label="Loading messaging platforms..." />
) : (
<div className="grid h-full min-h-0 grid-cols-1 lg:grid-cols-[14rem_minmax(0,1fr)]">
<aside className="min-h-0 overflow-y-auto border-b border-(--ui-stroke-tertiary) p-2 lg:border-b-0 lg:border-r">
<aside className="min-h-0 overflow-y-auto p-2">
<ul className="space-y-1">
{visiblePlatforms.map(platform => (
<li key={platform.id}>
@@ -427,8 +410,8 @@ function PlatformRow({
className={cn(
'flex w-full items-center gap-2 rounded-md px-2 py-1.5 text-left transition-colors',
active
? 'bg-(--ui-bg-tertiary) text-foreground'
: 'text-(--ui-text-secondary) hover:bg-(--chrome-action-hover) hover:text-foreground'
? 'bg-(--ui-row-active-background) text-foreground'
: 'text-(--ui-text-secondary) hover:bg-(--ui-row-hover-background) hover:text-foreground'
)}
onClick={onSelect}
type="button"
@@ -442,19 +425,6 @@ function PlatformRow({
)
}
function PlatformAvatar({ platformId, platformName }: { platformId: string; platformName: string }) {
return (
<span
className={cn(
'inline-flex size-6 shrink-0 items-center justify-center rounded-md text-[length:var(--conversation-caption-font-size)] font-medium',
PLATFORM_TINTS[platformId] || 'bg-(--ui-bg-tertiary) text-(--ui-text-tertiary)'
)}
>
{platformName.charAt(0).toUpperCase()}
</span>
)
}
function PlatformDetail({
edits,
onClear,
@@ -516,7 +486,7 @@ function PlatformDetail({
{introCopy(platform)}
</p>
<div className="mt-3">
<Button asChild size="sm" variant="outline">
<Button asChild size="sm" variant="textStrong">
<a href={platform.docs_url} rel="noreferrer" target="_blank">
Open setup guide
<ExternalLink className="size-3.5" />
@@ -594,19 +564,15 @@ function PlatformDetail({
</div>
</div>
<footer className="border-t border-(--ui-stroke-tertiary) bg-(--ui-chat-surface-background) px-5 py-2.5">
<footer className="bg-(--ui-chat-surface-background) px-5 py-2.5">
<div className="mx-auto flex max-w-2xl flex-wrap items-center gap-2">
<label className="flex shrink-0 items-center gap-2 rounded-md border border-(--ui-stroke-tertiary) bg-(--ui-bg-quinary) px-2.5 py-1.5 text-[length:var(--conversation-text-font-size)]">
<Switch
aria-label={platform.enabled ? `Disable ${platform.name}` : `Enable ${platform.name}`}
checked={platform.enabled}
disabled={saving === `enabled:${platform.id}`}
onCheckedChange={onToggle}
/>
<span className="text-xs font-medium text-muted-foreground">
{platform.enabled ? 'Enabled' : 'Disabled'}
</span>
</label>
<Switch
aria-label={platform.enabled ? `Disable ${platform.name}` : `Enable ${platform.name}`}
checked={platform.enabled}
disabled={saving === `enabled:${platform.id}`}
onCheckedChange={onToggle}
size="xs"
/>
<div className="ml-auto flex items-center gap-2">
{hasEdits && <span className="text-xs text-muted-foreground">Unsaved changes</span>}
@@ -685,7 +651,7 @@ function MessagingField({
</div>
<div className="flex items-center gap-2">
<Input
className="h-9 rounded-lg font-mono text-sm"
className="font-mono"
id={`messaging-field-${field.key}`}
onChange={event => onEdit(field.key, event.target.value)}
placeholder={field.is_set ? field.redacted_value || 'Replace current value' : copy.placeholder}
@@ -732,27 +698,13 @@ function PlatformHint({ platform }: { platform: MessagingPlatformInfo }) {
function StatePill({ children, tone }: { children: string; tone: StatusTone }) {
return (
<span
className={cn(
'inline-flex shrink-0 items-center gap-1.5 rounded-full px-2 py-0.5 text-[0.66rem] font-medium',
PILL_TONE[tone]
)}
>
<Badge variant={TONE_VARIANT[tone]}>
<StatusDot tone={tone} />
{children}
</span>
</Badge>
)
}
function SetupPill({ active, children }: { active: boolean; children: string }) {
return (
<span
className={cn(
'inline-flex items-center rounded-full px-2 py-0.5 text-[0.66rem] font-medium',
PILL_TONE[active ? 'good' : 'muted']
)}
>
{children}
</span>
)
return <Badge variant={active ? 'default' : 'muted'}>{children}</Badge>
}

View File

@@ -0,0 +1,97 @@
import type { ComponentType, SVGProps } from 'react'
import {
SiApple,
SiBilibili,
SiDiscord,
SiGmail,
SiHomeassistant,
SiMatrix,
SiMattermost,
SiQq,
SiSignal,
SiTelegram,
SiWechat,
SiWhatsapp
} from '@icons-pack/react-simple-icons'
import { Globe, Link as LinkIcon, MessageSquareText } from '@/lib/icons'
import { cn } from '@/lib/utils'
// We render simpleicons.org brand glyphs for platforms whose owners publish a
// usable mark (telegram, discord, matrix, ...). A few brands — Slack, Dingtalk,
// Feishu, WeCom — have been removed from Simple Icons at the brand owner's
// request, so we fall back to a colored letter monogram for those.
//
// `iconColor` is the brand's hex from simpleicons.org so we can paint each
// glyph in its native color on top of a soft tint. The fallback monogram uses
// the same hex to keep visual consistency.
type IconKind = 'brand' | 'generic'
interface PlatformIconSpec {
Icon: ComponentType<SVGProps<SVGSVGElement>>
color: string
kind: IconKind
}
const PLATFORM_ICONS: Record<string, PlatformIconSpec> = {
telegram: { Icon: SiTelegram, color: '#26A5E4', kind: 'brand' },
discord: { Icon: SiDiscord, color: '#5865F2', kind: 'brand' },
// Slack removed from Simple Icons by Salesforce request — letter monogram.
mattermost: { Icon: SiMattermost, color: '#0058CC', kind: 'brand' },
matrix: { Icon: SiMatrix, color: '#000000', kind: 'brand' },
signal: { Icon: SiSignal, color: '#3A76F0', kind: 'brand' },
whatsapp: { Icon: SiWhatsapp, color: '#25D366', kind: 'brand' },
bluebubbles: { Icon: SiApple, color: '#0BD318', kind: 'brand' },
homeassistant: { Icon: SiHomeassistant, color: '#18BCF2', kind: 'brand' },
email: { Icon: SiGmail, color: '#EA4335', kind: 'brand' },
sms: { Icon: MessageSquareText, color: '#F43F5E', kind: 'generic' },
webhook: { Icon: LinkIcon, color: '#71717A', kind: 'generic' },
api_server: { Icon: Globe, color: '#64748B', kind: 'generic' },
weixin: { Icon: SiWechat, color: '#07C160', kind: 'brand' },
qqbot: { Icon: SiQq, color: '#EB1923', kind: 'brand' },
yuanbao: { Icon: SiBilibili, color: '#FB7299', kind: 'brand' }
}
interface PlatformAvatarProps {
platformId: string
platformName: string
className?: string
}
export function PlatformAvatar({ className, platformId, platformName }: PlatformAvatarProps) {
const spec = PLATFORM_ICONS[platformId]
const baseClass = cn(
'inline-grid size-6 shrink-0 place-items-center rounded-md text-[length:var(--conversation-caption-font-size)] font-medium',
className
)
if (!spec) {
return (
<span
aria-hidden="true"
className={cn(baseClass, 'bg-(--ui-bg-tertiary) text-(--ui-text-tertiary)')}
>
{platformName.charAt(0).toUpperCase()}
</span>
)
}
const { Icon, color } = spec
return (
<span
aria-hidden="true"
className={baseClass}
style={{
// 16% tint of the brand color so the glyph reads against any surface
// without the avatar dominating the row.
backgroundColor: `color-mix(in srgb, ${color} 16%, transparent)`,
color
}}
>
<Icon className="size-3.5" />
</span>
)
}

View File

@@ -0,0 +1,31 @@
import { useStore } from '@nanostores/react'
import { ModelVisibilityDialog } from '@/components/model-visibility-dialog'
import type { HermesGateway } from '@/hermes'
import { $modelVisibilityOpen, setModelVisibilityOpen } from '@/store/model-visibility'
import { $activeSessionId, $gatewayState } from '@/store/session'
interface ModelVisibilityOverlayProps {
gateway?: HermesGateway
onOpenProviders: () => void
}
export function ModelVisibilityOverlay({ gateway, onOpenProviders }: ModelVisibilityOverlayProps) {
const activeSessionId = useStore($activeSessionId)
const gatewayOpen = useStore($gatewayState) === 'open'
const open = useStore($modelVisibilityOpen)
if (!gatewayOpen) {
return null
}
return (
<ModelVisibilityDialog
gw={gateway}
onOpenChange={setModelVisibilityOpen}
onOpenProviders={onOpenProviders}
open={open}
sessionId={activeSessionId}
/>
)
}

View File

@@ -1,77 +0,0 @@
import type { ReactNode, RefObject } from 'react'
import { Button } from '@/components/ui/button'
import { Codicon } from '@/components/ui/codicon'
import { Input } from '@/components/ui/input'
import { Loader2, Search } from '@/lib/icons'
import { cn } from '@/lib/utils'
interface OverlaySearchInputProps {
placeholder: string
value: string
onChange: (value: string) => void
containerClassName?: string
inputClassName?: string
loading?: boolean
onClear?: () => void
inputRef?: RefObject<HTMLInputElement | null>
trailingAction?: ReactNode
}
export function OverlaySearchInput({
placeholder,
value,
onChange,
containerClassName,
inputClassName,
loading = false,
onClear,
inputRef,
trailingAction
}: OverlaySearchInputProps) {
const clear = onClear ?? (() => onChange(''))
const hasTrailing = Boolean(trailingAction)
return (
<div className={cn('relative', containerClassName)}>
<Search className="pointer-events-none absolute left-3 top-1/2 z-1 size-3.5 -translate-y-1/2 text-muted-foreground/80" />
<Input
className={cn(
'relative z-0 h-8 rounded-lg py-2 pl-8 text-[length:var(--conversation-text-font-size)]',
hasTrailing || loading || value ? 'pr-16' : 'pr-8',
inputClassName
)}
onChange={event => onChange(event.target.value)}
placeholder={placeholder}
ref={inputRef}
value={value}
/>
<div className="absolute right-1.5 top-1/2 z-1 flex -translate-y-1/2 items-center gap-0.5">
{trailingAction}
{loading ? (
<Loader2 className="pointer-events-none size-3.5 animate-spin text-muted-foreground/70" />
) : value ? (
<Button
aria-label="Clear search"
className="text-muted-foreground/85 hover:bg-accent/60 hover:text-foreground"
onClick={clear}
size="icon-xs"
variant="ghost"
>
<Codicon name="close" size="0.875rem" />
</Button>
) : null}
</div>
</div>
)
}
export function PageSearchInput(props: OverlaySearchInputProps) {
return (
<OverlaySearchInput
{...props}
containerClassName={cn('mx-auto w-[min(36rem,calc(100%-2rem))] min-w-0', props.containerClassName)}
inputClassName={cn('h-8 rounded-lg py-2 pl-8', props.inputClassName)}
/>
)
}

View File

@@ -3,6 +3,8 @@ import type { ReactNode } from 'react'
import type { IconComponent } from '@/lib/icons'
import { cn } from '@/lib/utils'
import { PAGE_INSET_X } from '../layout-constants'
interface OverlaySplitLayoutProps {
children: ReactNode
className?: string
@@ -43,7 +45,9 @@ export function OverlaySidebar({ children, className }: OverlaySidebarProps) {
return (
<aside
className={cn(
'flex min-h-0 flex-col gap-0.5 overflow-y-auto bg-(--ui-sidebar-surface-background) px-2.5 py-3',
// pt clears the floating titlebar/header; the bg itself fills from the
// card's top edge so there's no surface-colored gap above the sidebar.
'flex min-h-0 flex-col gap-0.5 overflow-y-auto bg-(--ui-sidebar-surface-background) px-2.5 pb-3 pt-[calc(var(--titlebar-height)+1rem)]',
className
)}
>
@@ -54,7 +58,15 @@ export function OverlaySidebar({ children, className }: OverlaySidebarProps) {
export function OverlayMain({ children, className }: OverlayMainProps) {
return (
<main className={cn('flex min-h-0 flex-1 flex-col overflow-hidden bg-transparent p-3', className)}>{children}</main>
<main
className={cn(
'flex min-h-0 flex-1 flex-col overflow-hidden bg-transparent pb-3 pt-[calc(var(--titlebar-height)+1rem)]',
PAGE_INSET_X,
className
)}
>
{children}
</main>
)
}

View File

@@ -64,23 +64,26 @@ export function OverlayView({
>
<div className="pointer-events-none absolute inset-x-0 top-0 z-10 h-[calc(var(--titlebar-height)+0.1875rem)] [-webkit-app-region:drag]">
{headerContent && (
<div className="pointer-events-auto absolute left-1/2 top-[calc(1rem+var(--titlebar-height)/2)] -translate-x-1/2 -translate-y-1/2 [-webkit-app-region:no-drag]">
<div className="pointer-events-auto absolute left-1/2 top-[calc(0.5rem+var(--titlebar-height)/2)] -translate-x-1/2 -translate-y-1/2 [-webkit-app-region:no-drag]">
{headerContent}
</div>
)}
<Button
aria-label={closeLabel}
className="pointer-events-auto absolute right-3 top-[calc(0.1875rem+var(--titlebar-height)/2)] h-7 w-7 -translate-y-1/2 rounded-md text-(--ui-text-tertiary) hover:bg-(--chrome-action-hover) hover:text-foreground [-webkit-app-region:no-drag]"
className="pointer-events-auto absolute right-3 top-[calc(0.1875rem+var(--titlebar-height)/2)] -translate-y-1/2 text-(--ui-text-tertiary) hover:bg-(--chrome-action-hover) hover:text-foreground [-webkit-app-region:no-drag]"
onClick={closeOverlay}
size="icon"
size="icon-titlebar"
variant="ghost"
>
<Codicon name="close" size="1rem" />
</Button>
</div>
<div className={cn('min-h-0 flex flex-1 flex-col pt-(--titlebar-height)', contentClassName)}>{children}</div>
{/* No top padding here: the split-layout columns own their own
titlebar clearance so their backgrounds run flush to the card top
(otherwise the card surface shows as a gap above the sidebar). */}
<div className={cn('min-h-0 flex flex-1 flex-col', contentClassName)}>{children}</div>
</div>
</div>
)

View File

@@ -1,26 +1,30 @@
import type { ReactNode } from 'react'
import { SearchField } from '@/components/ui/search-field'
import { cn } from '@/lib/utils'
import { PageSearchInput } from './overlays/overlay-search-input'
interface PageSearchShellProps extends React.ComponentProps<'section'> {
children: ReactNode
/** Primary tabs shown on the top row, beside the search. */
tabs?: ReactNode
/** Secondary filters shown full-width on their own row below (expands). */
filters?: ReactNode
onSearchChange: (value: string) => void
searchPlaceholder: string
searchTrailingAction?: ReactNode
searchValue: string
/** Hide the search field when there's nothing to search (empty dataset). */
searchHidden?: boolean
}
export function PageSearchShell({
children,
className,
tabs,
filters,
onSearchChange,
searchPlaceholder,
searchTrailingAction,
searchValue,
searchHidden = false,
...props
}: PageSearchShellProps) {
return (
@@ -28,24 +32,43 @@ export function PageSearchShell({
{...props}
className={cn('flex h-full min-w-0 flex-col overflow-hidden bg-(--ui-chat-surface-background)', className)}
>
<div className="relative z-10 grid gap-2 border-b border-(--ui-stroke-tertiary) px-3 py-2.5">
{/* Reserve the top-right titlebar tools + native window-controls
footprint so the full-width search input never slides under them
(this header sits in the titlebar row at the window top). */}
<div
style={{
paddingRight:
'max(0px, calc(var(--titlebar-tools-right, 0px) + var(--titlebar-tools-width, 0px) - 0.75rem))'
}}
>
<PageSearchInput
onChange={onSearchChange}
placeholder={searchPlaceholder}
trailingAction={searchTrailingAction}
value={searchValue}
/>
</div>
{filters ? <div className="flex flex-wrap items-center justify-center gap-1.5">{filters}</div> : null}
{/*
Header lives in the page body, below the window chrome (the shell floats
traffic lights over the top titlebar-height strip, which the `pt` clears
and leaves draggable). Top row: primary tabs + search. Second row:
secondary filters, full-width so they expand. Interactive bits opt out
of the drag region.
*/}
{/*
IMPORTANT: do NOT put `-webkit-app-region: drag` on this header. It spans
full width over the band where the floating titlebar icon clusters live,
and an overlapping OS drag region eats their clicks at the compositor
level (pointer-events / no-drag carve-outs across separate stacking
contexts don't reliably fix it on macOS). The shell already supplies a
draggable titlebar strip that is `calc()`'d around the icon clusters
(see app-shell.tsx), so window dragging still works here.
*/}
<div className="shrink-0">
{(tabs || !searchHidden) && (
<div className="flex items-center gap-3 px-3 pb-2 pt-[calc(var(--titlebar-height)+0.5rem)]">
{tabs ? (
<div className="flex min-w-0 flex-1 flex-wrap items-center gap-x-2 gap-y-1">{tabs}</div>
) : null}
{!searchHidden && (
<div className={cn('flex shrink-0 items-center', !tabs && 'flex-1')}>
<SearchField
containerClassName="max-w-[45vw]"
onChange={onSearchChange}
placeholder={searchPlaceholder}
value={searchValue}
/>
</div>
)}
</div>
)}
{filters ? (
<div className="flex flex-wrap items-center gap-x-2 gap-y-1 px-3 pb-2">{filters}</div>
) : null}
</div>
<div className="min-h-0 flex-1 overflow-hidden bg-(--ui-chat-surface-background)">{children}</div>
</section>

Some files were not shown because too many files have changed in this diff Show More