fix(cli): /plugins shows installed-but-not-enabled plugins

The /plugins slash command read from the live PluginManager, which only
knows about *loaded* plugins. A freshly-installed plugin that hadn't been
enabled yet showed 'No plugins installed. Drop plugin directories into
~/.hermes/plugins/' — even though it was on disk and a valid plugin.

Switch to the same disk-discovery path as 'hermes plugins list'
(_discover_all_plugins + enabled/disabled sets + _plugin_status), so an
installed plugin now appears with its activation state ([not enabled],
enabled, or disabled) plus the exact enable command.

Default the quick /plugins view to user-installed plugins and summarize
bundled providers/platforms on one line (the full catalog stays behind
'hermes plugins list') so the output isn't drowned by 60+ bundled
provider plugins.

.dockerignore

@@ -63,45 +63,3 @@ data/
 # Compose/profile runtime state (bind-mounted; avoid ownership/secret issues)
 hermes-config/
 runtime/
-
-# ---------- Not needed inside the Docker image ----------
-
-# Desktop app source (Tauri/Electron); never installed in the container
-apps/
-
-# Test suite — not shipped in production images
-tests/
-
-# Documentation site (Docusaurus) and supplementary docs
-website/
-docs/
-
-# Assets only used by the GitHub README
-assets/
-infographic/
-
-# Plugin-level docs (hermes-achievements ships docs/ but the runtime doesn't read them)
-plugins/hermes-achievements/docs/
-
-# Nix / Homebrew / AUR packaging metadata — irrelevant to Docker
-nix/
-flake.nix
-flake.lock
-packaging/
-
-# Design and planning documents
-plans/
-.plans/
-
-# ACP registry manifest (icon + agent.json) — not consumed at runtime
-acp_registry/
-
-# Repo-level dotfiles that are git-only or dev-tooling config
-.env.example
-.envrc
-.gitattributes
-.hadolint.yaml
-.mailmap
-
-# Top-level LICENSE (not matched by *.md); not needed inside the container
-LICENSE

.github/workflows/deploy-site.yml

@@ -44,7 +44,7 @@ jobs:
 
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
-          node-version: 22
+          node-version: 20
           cache: npm
           cache-dependency-path: website/package-lock.json
 

.github/workflows/docs-site-checks.yml

@@ -18,7 +18,7 @@ jobs:
 
       - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
         with:
-          node-version: 22
+          node-version: 20
           cache: npm
           cache-dependency-path: website/package-lock.json
 

.github/workflows/tests.yml

@@ -55,31 +55,15 @@ jobs:
 
       - name: Install uv
         uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
-        with:
-          # Persist uv's download/wheel cache (~/.cache/uv) across runs.
-          # Keyed on the dependency manifests, so the cache is reused until
-          # pyproject.toml or uv.lock changes. `uv sync` still runs every
-          # time, but resolves from the warm cache instead of re-downloading
-          # and re-building wheels.
-          enable-cache: true
-          cache-dependency-glob: |
-            pyproject.toml
-            uv.lock
 
       - name: Set up Python 3.11
         run: uv python install 3.11
 
       - name: Install dependencies
-        # `uv sync --locked` installs the exact pinned set from uv.lock (and
-        # fails if the lock is out of sync with pyproject.toml), giving a
-        # reproducible env. It also creates .venv itself, so no separate
-        # `uv venv` step is needed.
-        run: uv sync --locked --python 3.11 --extra all --extra dev
-
-      - name: Minimize uv cache
-        # Optimized for CI: prunes pre-built wheels that are cheap to
-        # re-download, keeping the persisted cache small and fast to restore.
-        run: uv cache prune --ci
+        run: |
+          uv venv .venv --python 3.11
+          source .venv/bin/activate
+          uv pip install -e ".[all,dev]"
 
       - name: Run tests (slice ${{ matrix.slice }}/6)
         # Per-file isolation via scripts/run_tests_parallel.py: discovers
@@ -177,31 +161,15 @@ jobs:
 
       - name: Install uv
         uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
-        with:
-          # Persist uv's download/wheel cache (~/.cache/uv) across runs.
-          # Keyed on the dependency manifests, so the cache is reused until
-          # pyproject.toml or uv.lock changes. `uv sync` still runs every
-          # time, but resolves from the warm cache instead of re-downloading
-          # and re-building wheels.
-          enable-cache: true
-          cache-dependency-glob: |
-            pyproject.toml
-            uv.lock
 
       - name: Set up Python 3.11
         run: uv python install 3.11
 
       - name: Install dependencies
-        # `uv sync --locked` installs the exact pinned set from uv.lock (and
-        # fails if the lock is out of sync with pyproject.toml), giving a
-        # reproducible env. It also creates .venv itself, so no separate
-        # `uv venv` step is needed.
-        run: uv sync --locked --python 3.11 --extra all --extra dev
-
-      - name: Minimize uv cache
-        # Optimized for CI: prunes pre-built wheels that are cheap to
-        # re-download, keeping the persisted cache small and fast to restore.
-        run: uv cache prune --ci
+        run: |
+          uv venv .venv --python 3.11
+          source .venv/bin/activate
+          uv pip install -e ".[all,dev]"
 
       - name: Packaged-wheel i18n smoke test
         run: |

.github/workflows/typecheck.yml

@@ -1,25 +0,0 @@
-# .github/workflows/typecheck.yml
-name: Typecheck
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-    branches: [main]
-
-jobs:
-  typecheck:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        package:
-          [ui-tui, web, apps/bootstrap-installer, apps/desktop, apps/shared]
-      fail-fast: false # report all failures, not just the first one
-    steps:
-      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run --prefix ${{ matrix.package }} typecheck

.gitignore

@@ -89,9 +89,6 @@ website/static/api/skills-index.json
 # every build).
 website/static/api/skills.json
 website/static/api/skills-meta.json
-# automation-blueprints-index.json is a build artifact emitted by
-# website/scripts/extract-automation-blueprints.py during prebuild.
-website/static/api/automation-blueprints-index.json
 models-dev-upstream/
 
 # Local editor / agent tooling (machine-specific; keep in global config, not the repo)
@@ -117,12 +114,6 @@ docs/superpowers/*
 # treat it as a local edit and autostash it on every run (#38529).
 .hermes-bootstrap-complete
 
-# Interrupted-update breadcrumb + recovery lock written next to the shared venv
-# by `hermes update` / launch-time self-heal. Runtime state, never a code change
-# — ignore so `git status` stays clean and update's autostash skips them.
-.update-incomplete
-.update-incomplete.lock
-
 # 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/

AGENTS.md

@@ -4,201 +4,6 @@ Instructions for AI coding assistants and developers working on the hermes-agent
 
 **Never give up on the right solution.**
 
-## What Hermes Is
-
-Hermes is a personal AI agent that runs the same agent core across a CLI, a
-messaging gateway (Telegram, Discord, Slack, and ~20 other platforms), a TUI,
-and an Electron desktop app. It learns across sessions (memory + skills),
-delegates to subagents, runs scheduled jobs, and drives a real terminal and
-browser. It is extended primarily through **plugins and skills**, not by
-growing the core.
-
-Two properties shape almost every design decision and are the lens for
-reviewing any change:
-
-- **Per-conversation prompt caching is sacred.** A long-lived conversation
-  reuses a cached prefix every turn. Anything that mutates past context,
-  swaps toolsets, or rebuilds the system prompt mid-conversation invalidates
-  that cache and multiplies the user's cost. We do not do it (the one
-  exception is context compression).
-- **The core is a narrow waist; capability lives at the edges.** Every model
-  tool we add is sent on every API call, so the bar for a new *core* tool is
-  high. Most new capability should arrive as a CLI command + skill, a
-  service-gated tool, or a plugin — not as core surface.
-
-## Contribution Rubric — What We Want / What We Don't
-
-This is the project's intent layer. Use it two ways:
-
-1. **For humans and for your own work** — what gets merged and what gets
-   rejected, so a contribution aims at the target.
-2. **For automated review (the triage sweeper)** — guidance on when a PR is
-   safe to close on the three allowed reasons (`implemented_on_main`,
-   `cannot_reproduce`, `incoherent`) and, just as important, **when NOT to
-   close** one. Taste-based "we don't want this / out of scope" closes are NOT
-   an automated decision — those stay with a human maintainer. The sweeper's
-   job here is to recognize design intent and *avoid wrongly closing a
-   legitimate contribution*, not to make the won't-implement call itself.
-
-Read the balance right: Hermes ships a **lot** — most merges are bug fixes to
-real reported behavior, and the product surface (platforms, channels,
-providers, models, desktop/TUI features) expands aggressively and on purpose.
-The restraint below is aimed squarely at the **core agent + the model tool
-schema**, the one place where every addition is paid for on every API call.
-"Smallest footprint" governs *how a capability is wired into the core*, NOT
-whether the product is allowed to grow. We are expansive at the edges and
-conservative at the waist.
-
-### What we want
-
-- **Fix real bugs, well.** The bulk of what lands is `fix(...)` against an
-  actual reported symptom. A good fix reproduces the symptom on current
-  `main`, points to the exact line where it manifests, and fixes the whole bug
-  class — sibling call paths included — not just the one site the reporter hit.
-- **Expand reach at the edges.** New platform adapters, channels, providers,
-  models, and desktop/TUI/dashboard features are welcome and land routinely,
-  including large ones (a new messaging channel, a session-cap feature, a
-  Windows PTY bridge). Breadth in the product is a goal, not a footprint
-  concern — as long as it integrates with the existing setup/config UX
-  (`hermes tools`, `hermes setup`, auto-install) rather than bolting on a raw
-  env var.
-- **Refactor god-files into clean modules.** Extracting a multi-thousand-line
-  cluster out of `cli.py` / `run_agent.py` / `gateway/run.py` into a focused
-  mixin or module is wanted work, even when the diff is huge and mechanical
-  (large `+N/-N` refactors merge regularly). The "every line traces to the
-  request" test applies to *feature* PRs; a declared refactor's request IS the
-  extraction.
-- **Keep the core narrow.** New *model tools* are the expensive exception —
-  every tool ships on every API call. Prefer, in order: extend existing code →
-  CLI command + skill → service-gated tool (`check_fn`) → plugin → MCP server
-  in the catalog → new core tool (last resort). See "The Footprint Ladder."
-- **Extend, don't duplicate.** Before adding a module/manager/hook, check
-  whether existing infrastructure already covers the use case. When several PRs
-  integrate the same *category*, design one shared interface instead of merging
-  them one at a time (see the ABC + orchestrator note under the Footprint
-  Ladder).
-- **Behavior contracts over snapshots.** Tests should assert how two pieces of
-  data must relate (invariants), not freeze a current value (model lists,
-  config version literals, enumeration counts). See "Don't write
-  change-detector tests."
-- **E2E validation, not just green unit mocks.** For anything touching
-  resolution chains, config propagation, security boundaries, remote
-  backends, or file/network I/O, exercise the real path with real imports
-  against a temp `HERMES_HOME`. Mocks hide integration bugs.
-- **Cache-, alternation-, and invariant-safe.** Preserve prompt caching, strict
-  message role alternation (never two same-role messages in a row; never a
-  synthetic user message injected mid-loop), and a system prompt that is
-  byte-stable for the life of a conversation.
-- **Contributor credit preserved.** Salvage external work by cherry-picking
-  (rebase-merge) so authorship survives in git history; don't reimplement from
-  scratch when you can build on top.
-
-### What we don't want (rejected even when well-built)
-
-- **Speculative infrastructure.** Hooks, callbacks, or extension points with no
-  concrete consumer. Adding a hook is easy; removing one after plugins depend
-  on it is hard. A hook is NOT speculative if a contributor has a real, stated
-  use case — even if the consumer ships separately.
-- **New `HERMES_*` env vars for non-secret config.** `.env` is for secrets
-  only (API keys, tokens, passwords). All behavioral settings — timeouts,
-  thresholds, feature flags, display prefs — go in `config.yaml`. Bridge to an
-  internal env var if the mechanism needs one, but user-facing docs point to
-  `config.yaml`. Reject PRs that tell users to "set X in your .env" unless X
-  is a credential.
-- **A new core tool when terminal + file already do the job, or when a skill
-  would.** If the only barrier is file visibility on a remote backend, fix the
-  mount, not the toolset.
-- **Lazy-reading escape hatches on instructional tools.** No `offset`/`limit`
-  pagination on tools that load content the agent must read fully (skills,
-  prompts, playbooks). Models will read page 1 and skip the rest.
-- **"Fixes" that destroy the feature they secure.** A mitigation that kills the
-  feature's purpose is the wrong mitigation. Read the original commit's intent
-  (`git log -p -S`) before restricting behavior; find a fix that preserves the
-  feature.
-- **Outbound telemetry / usage attribution without opt-in gating.** No new
-  analytics, third-party identifier tagging, or attribution tags until a
-  generic user-facing opt-in (config gate + setup prompt + `hermes tools`
-  toggle) exists. Park behind a label, do not merge.
-- **Change-detector tests, cache-breaking mid-conversation, dead code wired in
-  without E2E proof, and plugins that touch core files.** Plugins live in their
-  own directory and work within the ABCs/hooks we provide; if a plugin needs
-  more, widen the generic plugin surface, don't special-case it in core.
-
-### Before you call it a bug — verify the premise (and when NOT to close)
-
-The most common reason a well-written PR gets closed is not code quality — it
-is that the change is built on a **wrong premise**, or it treats an
-**intentional design as a gap**. These patterns cut both ways: they tell a
-human reviewer what to scrutinize, and they tell the automated sweeper when a
-PR is NOT safe to close as `implemented_on_main` / `cannot_reproduce` (when in
-doubt, leave it open for a human). They are distilled from real closes.
-
-- **"Intentional design, not a gap."** A limitation that looks like an
-  oversight is often deliberate. Before "fixing" a missing link or a
-  restriction, ask whether the isolation IS the design. Example: profiles are
-  independent islands on purpose — a PR adding live config inheritance from the
-  default profile was closed because coupling profiles together is exactly what
-  the design prevents (the copy-at-creation `--clone` path already covers the
-  legitimate "start from my default" case). Read the original commit's intent
-  (`git log -p -S "<symbol>"`) before assuming something is unfinished.
-- **"The premise doesn't hold against how X actually works."** A PR's
-  justification frequently rests on a wrong mental model of an existing
-  mechanism. Trace the real code/runtime before accepting the rationale. Two
-  real closes: a rate-limit "re-probe during cooldown" PR (the breaker only
-  trips on a *confirmed-empty* account bucket, so re-probing just hammers a
-  bucket we've already proven empty); a usage-accumulation fix whose new branch
-  **never executes at runtime** because an earlier guard already popped the
-  state it depended on. If you can't point to the exact line where the bug
-  manifests AND show the fix changes that line's behavior, you haven't verified
-  the premise.
-- **"This fix was wrong — the absence/omission was deliberate."** Adding the
-  obvious-looking missing piece can break things the omission was protecting.
-  Example: restoring "missing" `__init__.py` files made a test tree importable
-  as a dotted package that shadowed the real plugin, deleting its `register()`
-  at import time. The absence was load-bearing.
-- **"Overreached / resurrected an approach we'd moved past."** Scope creep that
-  supersedes an agreed-on base, or revives a direction the maintainers
-  deliberately closed, gets rejected even when the code works. Keep the change
-  to the narrow piece that was actually agreed; offer the rest as a focused
-  follow-up.
-
-The throughline: **verify the claim AND the intent against the codebase before
-writing or merging a fix.** A confirmed reproduction on current `main` plus a
-line-level account of where the fix acts beats a plausible-sounding rationale
-every time. When in doubt about intent, it is cheaper to ask than to ship a
-fix that fights the design.
-
-### The Footprint Ladder (new capability decision)
-
-Each rung adds more permanent surface than the one above. Choose the highest
-(least-footprint) rung that correctly solves the problem:
-
-1. **Extend existing code** — the capability is a variation of something that
-   already exists. Zero new surface.
-2. **CLI command + skill** — manages config/state/infra expressible as shell
-   commands. The agent runs `hermes <subcommand>` guided by a skill. Zero
-   model-tool footprint. Default choice for subscriptions, scheduled tasks,
-   service setup. Examples: `hermes webhook`, `hermes cron`, `hermes tools`.
-3. **Service-gated tool (`check_fn`)** — needs structured params/returns AND
-   only appears when a prerequisite is configured. Zero footprint otherwise.
-   Examples: Home Assistant tools (gated on token), memory-provider tools.
-4. **Plugin** — third-party/niche/user-specific capability that doesn't ship in
-   core. Lives in `~/.hermes/plugins/` or a pip package, discovered at runtime.
-5. **MCP server (in the catalog)** — if the capability genuinely needs to be a
-   tool (structured I/O the agent invokes) but isn't core-fundamental, prefer
-   building it as an MCP server and adding it to the MCP catalog over growing
-   the core toolset. The agent connects to it through the built-in MCP client;
-   zero permanent core-schema footprint, and it's reusable by any MCP host.
-6. **New core tool** — only when the capability is fundamental, broadly useful
-   to nearly every user, and unreachable via terminal + file (or an MCP server).
-   Examples of correct core tools: terminal, read_file, web_search,
-   browser_navigate.
-
-When 3+ open PRs try to integrate the same *category* of thing (memory
-backends, providers, notifiers), don't merge them one at a time — design an
-ABC + orchestrator, wrap the existing built-in as the first provider, and turn
-the competing PRs into plugins against that interface.
-
 ## Development Environment
 
 ```bash
@@ -459,7 +264,7 @@ npm install       # first time
 npm run dev       # watch mode (rebuilds hermes-ink + tsx --watch)
 npm start         # production
 npm run build     # full build (hermes-ink + tsc)
-npm run typecheck # typecheck only (tsc --noEmit)
+npm run type-check # typecheck only (tsc --noEmit)
 npm run lint      # eslint
 npm run fmt       # prettier
 npm test          # vitest
@@ -497,11 +302,9 @@ A **separate** chat surface from both the classic CLI and the dashboard's embedd
 
 ## Adding New Tools
 
-Before adding any tool, settle the footprint question first (see "The
-Footprint Ladder" in the Contribution Rubric): most capabilities should NOT
-be core tools. For custom or local-only tools, do **not** edit Hermes core.
-Use the plugin route instead: create `~/.hermes/plugins/<name>/plugin.yaml`
-and `~/.hermes/plugins/<name>/__init__.py`, then register tools with
+For most custom or local-only tools, do **not** edit Hermes core. Use the plugin
+route instead: create `~/.hermes/plugins/<name>/plugin.yaml` and
+`~/.hermes/plugins/<name>/__init__.py`, then register tools with
 `ctx.register_tool(...)`. Plugin toolsets are discovered automatically and can be
 enabled or disabled without touching `tools/` or `toolsets.py`.
 

Dockerfile

@@ -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 g++ make cmake python3-dev python3-venv libffi-dev libolm-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 ----------
@@ -146,9 +146,9 @@ RUN npm install --prefer-offline --no-audit && \
 #
 # `uv sync --frozen --no-install-project --extra all --extra messaging`
 # installs the deps reachable through the composite `[all]` extra
-# (handpicked set intended for the production image — excludes `[dev]`),
-# plus gateway messaging adapters that should work in the published image
-# without a first-boot lazy install.  We do NOT use `--all-extras`:
+# (handpicked set intended for the production image), plus gateway
+# messaging adapters that should work in the published image without a
+# first-boot lazy install.  We do NOT use `--all-extras`:
 # that would pull in `[rl]` (atroposlib + tinker + torch + wandb from
 # git), `[yc-bench]` (another git dep), and `[termux-all]` (Android
 # redundancy), none of which belong in the published container.
@@ -164,30 +164,19 @@ RUN npm install --prefer-offline --no-audit && \
 # image update and recall/retain then fails with
 # `ModuleNotFoundError: No module named 'hindsight_client'` (#38128).
 #
-# The Matrix gateway's deps ([matrix] extra) are baked in because
-# python-olm (transitive via mautrix[encryption]) builds from source on
-# Python/image combinations without usable wheels.  The Docker image is
-# Linux-only, so keeping the native libolm/build-toolchain packages here
-# avoids the cross-platform failures that kept [matrix] out of [all]
-# while still making Matrix work in the published container. Fixes #30399.
-#
 # 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 --extra hindsight --extra matrix
-
-# ---------- Frontend build (cached independently from Python source) ----------
-# Copy only the frontend source trees first so that Python-only changes don't
-# invalidate the (relatively slow) web + ui-tui build layer.
-COPY web/ web/
-COPY ui-tui/ ui-tui/
-RUN cd web && npm run build && \
-    cd ../ui-tui && npm run build
+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.
 COPY --chown=hermes:hermes . .
 
+# Build browser dashboard and terminal UI assets.
+RUN cd web && npm run build && \
+    cd ../ui-tui && npm run build
+
 # ---------- Permissions ----------
 # Make install dir world-readable so any HERMES_UID can read it at runtime.
 # The venv needs to be traversable too.

MANIFEST.in

@@ -1,6 +1,5 @@
 graft skills
 graft optional-skills
-graft optional-mcps
 graft locales
 # Bundled plugin manifests (plugin.yaml / plugin.yml). Without these the
 # PluginManager scan (hermes_cli/plugins.py) finds zero plugins on installs

README.md

@@ -3,9 +3,7 @@
 </p>
 
 # Hermes Agent ☤
-<p align="center">
-  <a href="https://hermes-agent.nousresearch.com/">Hermes Agent</a> | <a href="https://hermes-agent.nousresearch.com/">Hermes Desktop</a>
-</p>
+
 <p align="center">
   <a href="https://hermes-agent.nousresearch.com/docs/"><img src="https://img.shields.io/badge/Docs-hermes--agent.nousresearch.com-FFD700?style=for-the-badge" alt="Documentation"></a>
   <a href="https://discord.gg/NousResearch"><img src="https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a>

agent/agent_init.py

@@ -187,7 +187,6 @@ def init_agent(
     thinking_callback: callable = None,
     reasoning_callback: callable = None,
     clarify_callback: callable = None,
-    read_terminal_callback: callable = None,
     step_callback: callable = None,
     stream_delta_callback: callable = None,
     interim_assistant_callback: callable = None,
@@ -418,7 +417,6 @@ def init_agent(
     agent.thinking_callback = thinking_callback
     agent.reasoning_callback = reasoning_callback
     agent.clarify_callback = clarify_callback
-    agent.read_terminal_callback = read_terminal_callback
     agent.step_callback = step_callback
     agent.stream_delta_callback = stream_delta_callback
     agent.interim_assistant_callback = interim_assistant_callback

agent/agent_runtime_helpers.py

@@ -49,7 +49,7 @@ def _ra():
 
 
 AGENT_RUNTIME_POST_HOOK_TOOL_NAMES = frozenset(
-    {"todo", "session_search", "memory", "clarify", "read_terminal", "delegate_task"}
+    {"todo", "session_search", "memory", "clarify", "delegate_task"}
 )
 
 
@@ -679,28 +679,15 @@ def recover_with_credential_pool(
         # long-running TUI sessions stuck on stale tokens until the user
         # exited and reopened.
         is_entitlement = agent._is_entitlement_failure(error_context, status_code)
-        _auth_haystack = " ".join(
-            str(error_context.get(k) or "").lower()
-            for k in ("message", "reason", "code", "error")
-            if isinstance(error_context, dict)
-        )
-        if (
-            not is_entitlement
-            and status_code == 403
-            and "oauth authentication is currently not allowed for this organization" in _auth_haystack
-        ):
-            is_entitlement = True
-        if (
-            not is_entitlement
-            and status_code == 403
-            and (agent.provider or "") == "anthropic"
-            and getattr(agent, "api_mode", "") == "anthropic_messages"
-        ):
-            is_entitlement = True
         if not is_entitlement and status_code == 403 and (agent.provider or "") == "xai-oauth":
+            _disambiguator_haystack = " ".join(
+                str(error_context.get(k) or "").lower()
+                for k in ("message", "reason", "code", "error")
+                if isinstance(error_context, dict)
+            )
             _is_xai_auth_failure = (
-                "[wke=unauthenticated:" in _auth_haystack
-                or "oauth2 access token could not be validated" in _auth_haystack
+                "[wke=unauthenticated:" in _disambiguator_haystack
+                or "oauth2 access token could not be validated" in _disambiguator_haystack
             )
             if not _is_xai_auth_failure:
                 is_entitlement = True
@@ -1797,17 +1784,6 @@ def invoke_tool(agent, function_name: str, function_args: dict, effective_task_i
                 ),
                 next_args,
             )
-    elif function_name == "read_terminal":
-        def _execute(next_args: dict) -> Any:
-            from tools.read_terminal_tool import read_terminal_tool as _read_terminal_tool
-            return _finish_agent_tool(
-                _read_terminal_tool(
-                    start_line=next_args.get("start_line"),
-                    count=next_args.get("count"),
-                    callback=getattr(agent, "read_terminal_callback", None),
-                ),
-                next_args,
-            )
     elif function_name == "delegate_task":
         def _execute(next_args: dict) -> Any:
             return _finish_agent_tool(agent._dispatch_delegate_task(next_args), next_args)

agent/anthropic_adapter.py

@@ -73,50 +73,20 @@ ADAPTIVE_EFFORT_MAP = {
     "minimal": "low",
 }
 
-# ── Anthropic thinking-mode classification ────────────────────────────
-# Claude 4.6 replaced budget-based extended thinking with *adaptive* thinking,
-# and 4.7 additionally forbids the manual ``thinking`` block entirely and drops
-# temperature/top_p/top_k.  Newer Claude releases (4.8, and named models like
-# claude-fable-5) follow the same modern contract — but they share no common
-# version substring, so an allowlist of version numbers ("4.6", "4.7", …) goes
-# stale the moment a model ships without a recognized number and silently
-# routes it down the legacy manual-thinking path.
-#
-# Instead we DEFAULT unknown Claude models to the modern contract and keep an
-# explicit *legacy* list of the older Claude families that still require manual
-# thinking.  This mirrors _get_anthropic_max_output's "default to newest" design
-# (future models are unlikely to regress to the older contract), so each new
-# Claude release works without a code change.
-#
-# Non-Claude Anthropic-Messages models (minimax, qwen3, GLM, …) are NOT Claude,
-# so they fall through to the legacy path automatically — exactly what those
-# manual-thinking endpoints need.
-
-# Older Claude families that DON'T support adaptive thinking (manual thinking
-# with budget_tokens only). Substring-matched against the model name.
-_LEGACY_MANUAL_THINKING_CLAUDE_SUBSTRINGS = (
-    "claude-3",          # 3, 3.5, 3.7
-    "claude-opus-4-0", "claude-opus-4.0", "claude-opus-4-1", "claude-opus-4.1",
-    "claude-sonnet-4-0", "claude-sonnet-4.0",
-    "claude-opus-4-2025", "claude-sonnet-4-2025",  # date-stamped 4.0 IDs
-    "claude-opus-4-5", "claude-opus-4.5",
-    "claude-sonnet-4-5", "claude-sonnet-4.5",
-    "claude-haiku-4-5", "claude-haiku-4.5",
-)
-
-# Older Claude families that DON'T accept the "xhigh" effort level (4.6 only
-# supports low/medium/high/max). xhigh arrived with Opus 4.7. Adaptive models
-# not in this list (4.7, 4.8, fable, future) accept xhigh.
-_NO_XHIGH_CLAUDE_SUBSTRINGS = (
-    "claude-opus-4-6", "claude-opus-4.6",
-    "claude-sonnet-4-6", "claude-sonnet-4.6",
-)
-
-
-def _is_claude_model(model: str | None) -> bool:
-    return "claude" in (model or "").lower()
+# Models that accept the "xhigh" output_config.effort level.  Opus 4.7 added
+# xhigh as a distinct level between high and max; older adaptive-thinking
+# models (4.6) reject it with a 400.  Keep this substring list in sync with
+# the Anthropic migration guide as new model families ship.
+_XHIGH_EFFORT_SUBSTRINGS = ("4-7", "4.7", "4-8", "4.8")
 
+# Models where extended thinking is deprecated/removed (4.6+ behavior: adaptive
+# is the only supported mode; 4.7 additionally forbids manual thinking entirely
+# and drops temperature/top_p/top_k).
+_ADAPTIVE_THINKING_SUBSTRINGS = ("4-6", "4.6", "4-7", "4.7", "4-8", "4.8")
 
+# Models where temperature/top_p/top_k return 400 if set to non-default values.
+# This is the Opus 4.7 contract; future 4.x+ models are expected to follow it.
+_NO_SAMPLING_PARAMS_SUBSTRINGS = ("4-7", "4.7", "4-8", "4.8")
 _FAST_MODE_SUPPORTED_SUBSTRINGS = ("opus-4-6", "opus-4.6")
 
 # ── Max output token limits per Anthropic model ───────────────────────
@@ -124,8 +94,6 @@ _FAST_MODE_SUPPORTED_SUBSTRINGS = ("opus-4-6", "opus-4.6")
 # max_tokens as a mandatory field.  Previously we hardcoded 16384, which
 # starves thinking-enabled models (thinking tokens count toward the limit).
 _ANTHROPIC_OUTPUT_LIMITS = {
-    # Mythos-class named models (claude-fable-5, …) — 1M context, reasoning
-    "claude-fable":      128_000,
     # Claude 4.8
     "claude-opus-4-8":   128_000,
     # Claude 4.7
@@ -240,17 +208,8 @@ def _resolve_anthropic_messages_max_tokens(
 
 
 def _supports_adaptive_thinking(model: str) -> bool:
-    """Return True for Claude models that use adaptive thinking (4.6+).
-
-    Defaults *unknown* Claude models to adaptive (the modern contract) and
-    only returns False for the explicit legacy list of older Claude families
-    that require manual budget-based thinking. Non-Claude Anthropic-Messages
-    models (minimax, qwen3, …) return False so they keep the manual path.
-    """
-    if not _is_claude_model(model):
-        return False
-    m = model.lower()
-    return not any(v in m for v in _LEGACY_MANUAL_THINKING_CLAUDE_SUBSTRINGS)
+    """Return True for Claude 4.6+ models that support adaptive thinking."""
+    return any(v in model for v in _ADAPTIVE_THINKING_SUBSTRINGS)
 
 
 def _supports_xhigh_effort(model: str) -> bool:
@@ -260,33 +219,18 @@ def _supports_xhigh_effort(model: str) -> bool:
     Pre-4.7 adaptive models (Opus/Sonnet 4.6) only accept low/medium/high/max
     and reject xhigh with an HTTP 400. Callers should downgrade xhigh→max
     when this returns False.
-
-    Defaults unknown adaptive Claude models to accepting xhigh (4.7+ contract);
-    only the 4.6 family and legacy manual-thinking models are excluded.
     """
-    if not _supports_adaptive_thinking(model):
-        return False
-    m = model.lower()
-    return not any(v in m for v in _NO_XHIGH_CLAUDE_SUBSTRINGS)
+    return any(v in model for v in _XHIGH_EFFORT_SUBSTRINGS)
 
 
 def _forbids_sampling_params(model: str) -> bool:
     """Return True for models that 400 on any non-default temperature/top_p/top_k.
 
-    Opus 4.7 introduced this restriction; later Claude releases follow it.
-    Defaults unknown Claude models to forbidding sampling params (the modern
-    contract). The 4.6 family still accepts them, and the legacy manual-thinking
-    families (4.5 and older) accept them too, so both are excluded. Non-Claude
-    models are unaffected. Callers should omit these fields entirely rather than
-    passing zero/default values (the API rejects anything non-null).
+    Opus 4.7 explicitly rejects sampling parameters; later Claude releases are
+    expected to follow suit.  Callers should omit these fields entirely rather
+    than passing zero/default values (the API rejects anything non-null).
     """
-    if not _is_claude_model(model):
-        return False
-    m = model.lower()
-    # 4.6 family is adaptive but still accepts sampling params.
-    if any(v in m for v in _NO_XHIGH_CLAUDE_SUBSTRINGS):
-        return False
-    return not any(v in m for v in _LEGACY_MANUAL_THINKING_CLAUDE_SUBSTRINGS)
+    return any(v in model for v in _NO_SAMPLING_PARAMS_SUBSTRINGS)
 
 
 def _supports_fast_mode(model: str) -> bool:
@@ -877,7 +821,6 @@ def _read_claude_code_credentials_from_keychain() -> Optional[Dict[str, Any]]:
             capture_output=True,
             text=True,
             timeout=5,
-            stdin=subprocess.DEVNULL,
         )
     except (OSError, subprocess.TimeoutExpired):
         logger.debug("Keychain: security command not available or timed out")
@@ -1220,10 +1163,7 @@ def run_oauth_setup_token() -> Optional[str]:
             "Install it with: npm install -g @anthropic-ai/claude-code"
         )
 
-    # Run interactively — stdin/stdout/stderr inherited so the user can
-    # complete the OAuth login prompt. Must keep inherited stdin; the TUI-EOF
-    # concern does not apply to an interactive login the user explicitly
-    # invokes.  noqa: subprocess-stdin
+    # Run interactively — stdin/stdout/stderr inherited so user can interact
     try:
         subprocess.run([claude_path, "setup-token"])
     except (KeyboardInterrupt, EOFError):
@@ -1571,15 +1511,6 @@ def _convert_content_part_to_anthropic(part: Any) -> Optional[Dict[str, Any]]:
 
     if ptype == "input_text":
         block: Dict[str, Any] = {"type": "text", "text": part.get("text", "")}
-    elif ptype == "text":
-        # A stored Anthropic text block. Rebuild from whitelisted fields only —
-        # SDK response text blocks carry output-only siblings (parsed_output,
-        # citations=None) that the Messages INPUT schema rejects with HTTP 400
-        # "Extra inputs are not permitted". Do NOT dict(part) it verbatim.
-        block = {"type": "text", "text": part.get("text", "")}
-        cits = part.get("citations")
-        if isinstance(cits, list) and cits:
-            block["citations"] = cits
     elif ptype in {"image_url", "input_image"}:
         image_value = part.get("image_url", {})
         url = image_value.get("url", "") if isinstance(image_value, dict) else str(image_value or "")
@@ -1694,58 +1625,6 @@ def _content_parts_to_anthropic_blocks(parts: Any) -> List[Dict[str, Any]]:
     return out
 
 
-def _sanitize_replay_block(b: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    """Strip output-only fields from a stored Anthropic content block so it is
-    valid as REQUEST input on replay.
-
-    The SDK response objects carry output-only attributes that the Messages
-    *input* schema forbids ("Extra inputs are not permitted"): text blocks get
-    ``parsed_output``/``citations`` (when null), tool_use blocks get ``caller``,
-    etc. ``normalize_response`` captured blocks verbatim via ``_to_plain_data``,
-    so these leak back as input on the next turn → HTTP 400.
-
-    Whitelist per type (NOT a blacklist) so future SDK output-only fields can't
-    reintroduce the bug. Returns a clean block, or None to drop it.
-    """
-    if not isinstance(b, dict):
-        return None
-    btype = b.get("type")
-    if btype == "text":
-        out: Dict[str, Any] = {"type": "text", "text": b.get("text", "")}
-        # citations is input-valid ONLY when it's a non-empty list; the SDK
-        # emits citations=None on responses, which the input schema rejects.
-        cits = b.get("citations")
-        if isinstance(cits, list) and cits:
-            out["citations"] = cits
-        if isinstance(b.get("cache_control"), dict):
-            out["cache_control"] = b["cache_control"]
-        return out
-    if btype == "thinking":
-        out = {"type": "thinking", "thinking": b.get("thinking", "")}
-        if b.get("signature"):
-            out["signature"] = b["signature"]
-        return out
-    if btype == "redacted_thinking":
-        # Only valid with its data payload; drop if missing.
-        return {"type": "redacted_thinking", "data": b["data"]} if b.get("data") else None
-    if btype == "tool_use":
-        out = {
-            "type": "tool_use",
-            "id": _sanitize_tool_id(b.get("id", "")),
-            "name": b.get("name", ""),
-            "input": b.get("input", {}),
-        }
-        if isinstance(b.get("cache_control"), dict):
-            out["cache_control"] = b["cache_control"]
-        return out
-    if btype == "image":
-        src = b.get("source")
-        return {"type": "image", "source": src} if isinstance(src, dict) else None
-    # Unknown/unsupported block type on the input path — drop rather than risk
-    # another "Extra inputs are not permitted".
-    return None
-
-
 def _convert_assistant_message(m: Dict[str, Any]) -> Dict[str, Any]:
     """Convert an assistant message to Anthropic content blocks.
 
@@ -1753,55 +1632,6 @@ def _convert_assistant_message(m: Dict[str, Any]) -> Dict[str, Any]:
     reasoning_content injection for Kimi/DeepSeek endpoints.
     """
     content = m.get("content", "")
-    # Anthropic interleaved-thinking fast path: when this turn carries a
-    # verbatim, order-preserving block list (set by normalize_response only
-    # for turns that interleave SIGNED thinking with tool_use), replay it.
-    # Each block is run through _sanitize_replay_block to strip output-only
-    # SDK fields (parsed_output, caller, citations=None, …) that the Messages
-    # INPUT schema forbids — replaying them verbatim caused HTTP 400 "Extra
-    # inputs are not permitted" (text.parsed_output). Block ORDER is preserved
-    # (the reason this channel exists); only forbidden sibling fields are
-    # dropped, leaving thinking signatures and tool_use id/name/input intact.
-    ordered_blocks = m.get("anthropic_content_blocks")
-    if isinstance(ordered_blocks, list) and ordered_blocks:
-        # Re-source each tool_use input from the stored tool_calls map rather
-        # than the captured block. The ordered-blocks list captures tool_use
-        # input from the RAW API response (normalize_response), which is NOT
-        # credential-redacted; tool_calls[].function.arguments IS redacted at
-        # storage time (build_assistant_message, #19798). Replaying the raw
-        # block input would resurrect a secret the model inlined into a tool
-        # call (e.g. terminal(command="curl -H 'Authorization: Bearer sk-...'")
-        # onto the wire, even though the same value is redacted everywhere else
-        # in history. Keying by sanitized tool id preserves interleave order
-        # (the reason this channel exists) while swapping in the redacted
-        # input. Adapted from #36071 (replay-time tool-input re-sourcing).
-        redacted_input_by_id: Dict[str, Any] = {}
-        for tc in m.get("tool_calls", []) or []:
-            if not isinstance(tc, dict):
-                continue
-            fn = tc.get("function", {}) or {}
-            raw_args = fn.get("arguments", "{}")
-            try:
-                parsed_args = json.loads(raw_args) if isinstance(raw_args, str) else raw_args
-            except (json.JSONDecodeError, ValueError):
-                parsed_args = {}
-            redacted_input_by_id[_sanitize_tool_id(tc.get("id", ""))] = parsed_args
-        replayed: List[Dict[str, Any]] = []
-        for b in ordered_blocks:
-            clean = _sanitize_replay_block(b)
-            if clean is None:
-                continue
-            if clean.get("type") == "tool_use":
-                # Override raw (un-redacted) input with the redacted copy when
-                # we have one for this id; fall back to the sanitized block
-                # input only if the tool_call is missing (shape mismatch).
-                redacted = redacted_input_by_id.get(clean.get("id", ""))
-                if redacted is not None:
-                    clean["input"] = redacted
-            replayed.append(clean)
-        if replayed:
-            return {"role": "assistant", "content": replayed}
-
     blocks = _extract_preserved_thinking_blocks(m)
     if content:
         if isinstance(content, list):

agent/auxiliary_client.py

@@ -102,7 +102,7 @@ OpenAI = _OpenAIProxy()  # module-level name, resolves lazily on call/isinstance
 from agent.credential_pool import load_pool
 from hermes_cli.config import get_hermes_home
 from hermes_constants import OPENROUTER_BASE_URL
-from utils import base_url_host_matches, base_url_hostname, model_forces_max_completion_tokens, normalize_proxy_env_vars
+from utils import base_url_host_matches, base_url_hostname, normalize_proxy_env_vars
 
 logger = logging.getLogger(__name__)
 
@@ -4300,15 +4300,13 @@ def get_auxiliary_extra_body() -> dict:
     return _nous_extra_body() if auxiliary_is_nous else {}
 
 
-def auxiliary_max_tokens_param(value: int, *, model: Optional[str] = None) -> dict:
+def auxiliary_max_tokens_param(value: int) -> dict:
     """Return the correct max tokens kwarg for the auxiliary client's provider.
-
+    
     OpenRouter and local models use 'max_tokens'. Direct OpenAI with newer
-    models (gpt-4o, gpt-4.1, gpt-5+, o-series) requires 'max_completion_tokens'.
+    models (gpt-4o, o-series, gpt-5+) requires 'max_completion_tokens'.
     The Codex adapter translates max_tokens internally, so we use max_tokens
-    for it as well. Pass ``model`` so third-party OpenAI-compatible endpoints
-    fronting the newer families are also recognised — URL-only detection
-    misses the case where a custom base URL serves e.g. ``gpt-5.4``.
+    for it as well.
     """
     custom_base = _current_custom_base_url()
     or_key = os.getenv("OPENROUTER_API_KEY")
@@ -4318,9 +4316,6 @@ def auxiliary_max_tokens_param(value: int, *, model: Optional[str] = None) -> di
             and _read_nous_auth() is None
             and base_url_hostname(custom_base) in {"api.openai.com", "api.githubcopilot.com"}):
         return {"max_completion_tokens": value}
-    # ...and for any caller serving a newer OpenAI-family model by name.
-    if model_forces_max_completion_tokens(model):
-        return {"max_completion_tokens": value}
     return {"max_tokens": value}
 
 

agent/bedrock_adapter.py

@@ -208,41 +208,6 @@ def is_stale_connection_error(exc: BaseException) -> bool:
     return False
 
 
-def is_streaming_access_denied_error(exc: BaseException) -> bool:
-    """Return True when AWS denied the ``bedrock:InvokeModelWithResponseStream`` action.
-
-    IAM policies scoped to ``bedrock:InvokeModel`` only (a common least-privilege
-    setup) reject ``converse_stream()`` with an ``AccessDeniedException`` whose
-    message names the streaming action, e.g.::
-
-        User: arn:aws:iam::123456789012:user/x is not authorized to perform:
-        bedrock:InvokeModelWithResponseStream on resource: ...
-
-    This is permanent for the session — retrying the stream can never succeed —
-    so callers should flip to the non-streaming ``converse()`` path (which maps
-    to ``bedrock:InvokeModel``) instead of burning retries.
-
-    Detection is deliberately message-based: boto3 surfaces this as a
-    ``ClientError`` with ``Error.Code == "AccessDeniedException"``, and the
-    AnthropicBedrock SDK wraps the same AWS response in its own exception
-    types, but both preserve the action name in the message.
-    """
-    msg = str(exc).lower()
-    if "invokemodelwithresponsestream" not in msg:
-        return False
-    # ClientError with an explicit access-denied code is the canonical form.
-    try:
-        from botocore.exceptions import ClientError
-    except ImportError:  # pragma: no cover — botocore always present with boto3
-        ClientError = None  # type: ignore[assignment]
-    if ClientError is not None and isinstance(exc, ClientError):
-        code = (getattr(exc, "response", None) or {}).get("Error", {}).get("Code", "")
-        return code in ("AccessDeniedException", "UnauthorizedException")
-    # Wrapped forms (e.g. AnthropicBedrock SDK PermissionDeniedError) — match
-    # on the authorization-failure phrasing AWS uses.
-    return "not authorized" in msg or "accessdenied" in msg
-
-
 # ---------------------------------------------------------------------------
 # AWS credential detection
 # ---------------------------------------------------------------------------
@@ -1038,16 +1003,6 @@ def call_converse_stream(
     try:
         response = client.converse_stream(**kwargs)
     except Exception as exc:
-        if is_streaming_access_denied_error(exc):
-            # IAM allows bedrock:InvokeModel but not
-            # InvokeModelWithResponseStream — permanent for this session.
-            # Fall back to the non-streaming converse() path.
-            logger.info(
-                "bedrock: converse_stream denied by IAM on (region=%s, model=%s) — "
-                "falling back to non-streaming converse().",
-                region, model,
-            )
-            return normalize_converse_response(client.converse(**kwargs))
         if is_stale_connection_error(exc):
             logger.warning(
                 "bedrock: stale-connection error on converse_stream(region=%s, "

agent/chat_completion_helpers.py

@@ -952,18 +952,6 @@ def build_assistant_message(agent, assistant_message, finish_reason: str) -> dic
         if preserved:
             msg["reasoning_details"] = preserved
 
-    # Anthropic interleaved-thinking replay: when a turn interleaves signed
-    # thinking blocks with tool_use, the parallel reasoning_details +
-    # tool_calls fields lose the cross-type ordering, and reconstruction
-    # front-loads thinking — reordering signed blocks and triggering HTTP 400
-    # ("thinking ... blocks in the latest assistant message cannot be
-    # modified"). Carry the verbatim ordered block list so the adapter can
-    # replay the latest assistant message unchanged. See
-    # agent/transports/anthropic.py and agent/anthropic_adapter.py.
-    ordered_blocks = getattr(assistant_message, "anthropic_content_blocks", None)
-    if ordered_blocks:
-        msg["anthropic_content_blocks"] = ordered_blocks
-
     # Codex Responses API: preserve encrypted reasoning items for
     # multi-turn continuity. These get replayed as input on the next turn.
     codex_items = getattr(assistant_message, "codex_reasoning_items", None)
@@ -1615,8 +1603,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
                     _get_bedrock_runtime_client,
                     invalidate_runtime_client,
                     is_stale_connection_error,
-                    is_streaming_access_denied_error,
-                    normalize_converse_response,
                     stream_converse_with_callbacks,
                 )
                 region = api_kwargs.pop("__bedrock_region__", "us-east-1")
@@ -1625,29 +1611,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
                 try:
                     raw_response = client.converse_stream(**api_kwargs)
                 except Exception as _bedrock_exc:
-                    # IAM policies scoped to bedrock:InvokeModel only (no
-                    # InvokeModelWithResponseStream) reject converse_stream()
-                    # with AccessDeniedException. That denial is permanent for
-                    # the session — fall back to the non-streaming converse()
-                    # inline (it maps to bedrock:InvokeModel) and disable
-                    # streaming for subsequent calls so we don't re-fail every
-                    # turn.
-                    if is_streaming_access_denied_error(_bedrock_exc):
-                        agent._disable_streaming = True
-                        agent._safe_print(
-                            "\n⚠  AWS IAM denied bedrock:InvokeModelWithResponseStream — "
-                            "falling back to non-streaming InvokeModel.\n"
-                            "   Grant that action to restore streaming output.\n"
-                        )
-                        logger.info(
-                            "bedrock: converse_stream denied by IAM (%s) — "
-                            "using non-streaming converse() for this session.",
-                            type(_bedrock_exc).__name__,
-                        )
-                        result["response"] = normalize_converse_response(
-                            client.converse(**api_kwargs)
-                        )
-                        return
                     # Evict the cached client on stale-connection failures
                     # so the outer retry loop builds a fresh client/pool.
                     if is_stale_connection_error(_bedrock_exc):
@@ -1735,14 +1698,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
     # poll loop uses this to detect stale connections that keep receiving
     # SSE keep-alive pings but no actual data.
     last_chunk_time = {"t": time.time()}
-    # Stale-stream patience, shared between the httpx socket read timeout
-    # (built in ``_call_chat_completions`` below) and the stale-stream detector
-    # (computed further down, before the worker thread starts).  Initialized
-    # here so the read-timeout builder can floor itself at the stale value and
-    # never fire before the detector.  ``None`` until the detector value is
-    # resolved, so the builder degrades to its plain default if it ever runs
-    # first.
-    _stream_stale_timeout = None
 
     def _fire_first_delta():
         if not first_delta_fired["done"] and on_first_delta:
@@ -1779,26 +1734,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
                     "Local provider detected (%s) — stream read timeout raised to %.0fs",
                     agent.base_url, _stream_read_timeout,
                 )
-            elif (
-                _stream_read_timeout == 120.0
-                and _stream_stale_timeout is not None
-                and _stream_stale_timeout != float("inf")
-                and _stream_stale_timeout > _stream_read_timeout
-            ):
-                # Cloud reasoning models (e.g. Opus) routinely pause mid-stream
-                # for minutes during extended thinking.  The stale-stream
-                # detector is deliberately scaled up to tolerate this (180–300s,
-                # see the stale-timeout block below), but the raw httpx socket
-                # read timeout defaulted to a flat 120s and fired *first* —
-                # tearing down a healthy reasoning stream before the stale
-                # detector (which owns retry + diagnostics) could act.  Keep the
-                # socket read timeout in step with the detector so it no longer
-                # preempts it.
-                _stream_read_timeout = _stream_stale_timeout
-                logger.debug(
-                    "Cloud reasoning stream — read timeout raised to %.0fs to "
-                    "match stale-stream detector", _stream_read_timeout,
-                )
         # Cap connect/pool at 60s even when provider timeout is higher.
         # connect/pool cover TCP handshake, not model inference.
         _conn_cap = min(_base_timeout, 60.0) if _provider_timeout_cfg is not None else 30.0
@@ -2449,34 +2384,9 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
                             "stream" in _err_lower
                             and "not supported" in _err_lower
                         )
-                        # AWS Bedrock (AnthropicBedrock SDK path): IAM policies
-                        # with bedrock:InvokeModel but not
-                        # InvokeModelWithResponseStream reject messages.stream()
-                        # with a permission error naming the streaming action.
-                        # Permanent for the session — flip to non-streaming
-                        # (messages.create() maps to bedrock:InvokeModel).
-                        _is_bedrock_stream_denied = False
-                        if (
-                            not _is_stream_unsupported
-                            and "invokemodelwithresponsestream" in _err_lower
-                        ):
-                            # Cheap message pre-check before importing the
-                            # adapter — bedrock_adapter triggers a lazy boto3
-                            # install at import time, which must not run for
-                            # unrelated providers' stream errors.
-                            from agent.bedrock_adapter import (
-                                is_streaming_access_denied_error,
-                            )
-                            _is_bedrock_stream_denied = (
-                                is_streaming_access_denied_error(e)
-                            )
-                        if _is_stream_unsupported or _is_bedrock_stream_denied:
+                        if _is_stream_unsupported:
                             agent._disable_streaming = True
                             agent._safe_print(
-                                "\n⚠  AWS IAM denied bedrock:InvokeModelWithResponseStream. "
-                                "Switching to non-streaming.\n"
-                                "   Grant that action to restore streaming output.\n"
-                                if _is_bedrock_stream_denied else
                                 "\n⚠  Streaming is not supported for this "
                                 "model/provider. Switching to non-streaming.\n"
                                 "   To avoid this delay, set display.streaming: false "

agent/codex_runtime.py

@@ -25,154 +25,6 @@ from typing import Any, Dict, List
 logger = logging.getLogger(__name__)
 
 
-def _coerce_usage_int(value: Any) -> int:
-    if isinstance(value, bool):
-        return 0
-    if isinstance(value, int):
-        return max(value, 0)
-    if isinstance(value, float):
-        return max(int(value), 0)
-    if isinstance(value, str):
-        try:
-            return max(int(value), 0)
-        except ValueError:
-            return 0
-    return 0
-
-
-def _record_codex_app_server_usage(agent, turn) -> dict[str, Any]:
-    """Translate Codex app-server token usage into Hermes accounting.
-
-    Codex app-server reports usage via thread/tokenUsage/updated as:
-    inputTokens, cachedInputTokens, outputTokens, reasoningOutputTokens,
-    totalTokens.
-
-    Hermes' canonical prompt bucket includes uncached input + cached input.
-    The Codex app-server protocol does not currently expose cache-write tokens,
-    so that bucket remains zero on this runtime.
-
-    Even when Codex omits usage for a turn, Hermes should still count that turn
-    as one API call for session/status accounting.
-    """
-    agent.session_api_calls += 1
-
-    usage = getattr(turn, "token_usage_last", None)
-    if not isinstance(usage, dict) or not usage:
-        if agent._session_db and agent.session_id:
-            try:
-                if not agent._session_db_created:
-                    agent._ensure_db_session()
-                agent._session_db.update_token_counts(
-                    agent.session_id,
-                    model=agent.model,
-                    api_call_count=1,
-                )
-            except Exception as exc:
-                logger.debug(
-                    "Codex app-server api-call persistence failed (session=%s): %s",
-                    agent.session_id, exc,
-                )
-        return {}
-
-    from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
-
-    input_tokens = _coerce_usage_int(usage.get("inputTokens"))
-    cache_read_tokens = _coerce_usage_int(usage.get("cachedInputTokens"))
-    output_tokens = _coerce_usage_int(usage.get("outputTokens"))
-    reasoning_tokens = _coerce_usage_int(usage.get("reasoningOutputTokens"))
-    reported_total = _coerce_usage_int(usage.get("totalTokens"))
-
-    canonical_usage = CanonicalUsage(
-        input_tokens=input_tokens,
-        output_tokens=output_tokens,
-        cache_read_tokens=cache_read_tokens,
-        cache_write_tokens=0,
-        reasoning_tokens=reasoning_tokens,
-        raw_usage=usage,
-    )
-    prompt_tokens = canonical_usage.prompt_tokens
-    completion_tokens = canonical_usage.output_tokens
-    total_tokens = reported_total or canonical_usage.total_tokens
-    usage_dict = {
-        "prompt_tokens": prompt_tokens,
-        "completion_tokens": completion_tokens,
-        "total_tokens": total_tokens,
-        "input_tokens": canonical_usage.input_tokens,
-        "output_tokens": canonical_usage.output_tokens,
-        "cache_read_tokens": canonical_usage.cache_read_tokens,
-        "cache_write_tokens": canonical_usage.cache_write_tokens,
-        "reasoning_tokens": canonical_usage.reasoning_tokens,
-    }
-
-    compressor = getattr(agent, "context_compressor", None)
-    if compressor is not None:
-        try:
-            compressor.update_from_response(usage_dict)
-            context_window = getattr(turn, "model_context_window", None)
-            if isinstance(context_window, int) and context_window > 0:
-                compressor.context_length = context_window
-        except Exception:
-            logger.debug("codex app-server usage update failed", exc_info=True)
-
-    agent.session_prompt_tokens += prompt_tokens
-    agent.session_completion_tokens += completion_tokens
-    agent.session_total_tokens += total_tokens
-    agent.session_input_tokens += canonical_usage.input_tokens
-    agent.session_output_tokens += canonical_usage.output_tokens
-    agent.session_cache_read_tokens += canonical_usage.cache_read_tokens
-    agent.session_cache_write_tokens += canonical_usage.cache_write_tokens
-    agent.session_reasoning_tokens += canonical_usage.reasoning_tokens
-
-    cost_result = estimate_usage_cost(
-        agent.model,
-        canonical_usage,
-        provider=agent.provider,
-        base_url=agent.base_url,
-        api_key=getattr(agent, "api_key", ""),
-    )
-    if cost_result.amount_usd is not None:
-        agent.session_estimated_cost_usd += float(cost_result.amount_usd)
-    agent.session_cost_status = cost_result.status
-    agent.session_cost_source = cost_result.source
-
-    if agent._session_db and agent.session_id:
-        try:
-            if not agent._session_db_created:
-                agent._ensure_db_session()
-            agent._session_db.update_token_counts(
-                agent.session_id,
-                input_tokens=canonical_usage.input_tokens,
-                output_tokens=canonical_usage.output_tokens,
-                cache_read_tokens=canonical_usage.cache_read_tokens,
-                cache_write_tokens=canonical_usage.cache_write_tokens,
-                reasoning_tokens=canonical_usage.reasoning_tokens,
-                estimated_cost_usd=float(cost_result.amount_usd)
-                if cost_result.amount_usd is not None else None,
-                cost_status=cost_result.status,
-                cost_source=cost_result.source,
-                billing_provider=agent.provider,
-                billing_base_url=agent.base_url,
-                billing_mode="subscription_included"
-                if cost_result.status == "included" else None,
-                model=agent.model,
-                api_call_count=1,
-            )
-        except Exception as exc:
-            logger.debug(
-                "Codex app-server token persistence failed (session=%s, tokens=%d): %s",
-                agent.session_id, total_tokens, exc,
-            )
-
-    return {
-        **usage_dict,
-        "last_prompt_tokens": prompt_tokens,
-        "estimated_cost_usd": float(cost_result.amount_usd)
-        if cost_result.amount_usd is not None else None,
-        "cost_status": cost_result.status,
-        "cost_source": cost_result.source,
-    }
-
-
 def run_codex_app_server_turn(
     agent,
     *,
@@ -268,8 +120,6 @@ def run_codex_app_server_turn(
     agent._iters_since_skill = (
         getattr(agent, "_iters_since_skill", 0) + turn.tool_iterations
     )
-    usage_result = _record_codex_app_server_usage(agent, turn)
-    api_calls = 1
 
     # Now check the skill nudge AFTER iters were incremented — same
     # pattern the chat_completions path uses (line ~15432).
@@ -314,13 +164,12 @@ def run_codex_app_server_turn(
     return {
         "final_response": turn.final_text,
         "messages": messages,
-        "api_calls": api_calls,
+        "api_calls": 1,  # one app-server "turn" maps to one logical API call
         "completed": not turn.interrupted and turn.error is None,
         "partial": turn.interrupted or turn.error is not None,
         "error": turn.error,
         "codex_thread_id": turn.thread_id,
         "codex_turn_id": turn.turn_id,
-        **usage_result,
     }
 
 

agent/coding_context.py

@@ -1,731 +0,0 @@
-"""Coding-context awareness — base Hermes, every interactive surface.
-
-When the user runs Hermes inside a code workspace (CLI, TUI, desktop app, or an
-editor over ACP), Hermes shifts into a **coding posture**. This module is the
-single place that decides whether we're in that posture and what it implies,
-so the rest of the codebase never re-derives "are we coding?" on its own.
-
-Architecture — one seam, many consumers
-----------------------------------------
-The posture is modelled as a frozen :class:`RuntimeMode` selected from a small
-:class:`ContextProfile` registry (today: ``coding`` and ``general``). A profile
-is *data* — it declares the toolset to collapse to, the operating brief to
-inject, and hints for other domains (model routing, memory, subagents). Every
-domain reads the same resolved object instead of probing git/config itself:
-
-  * **System prompt** — ``RuntimeMode.system_blocks()`` → the operating brief +
-    a live git/workspace snapshot (``agent/system_prompt.py``).
-  * **Toolset** — ``RuntimeMode.toolset_selection()`` → the ``coding`` toolset
-    plus the user's enabled MCP servers (``cli.py`` / ``tui_gateway``). Only
-    under the opt-in ``focus`` mode: the default posture is prompt-only and
-    never touches the user's configured toolsets (toolsets like messaging /
-    smart-home / music are off-by-default anyway, and someone who explicitly
-    enabled image-gen or Spotify shouldn't lose it for being in a git repo).
-  * **Delegation** — subagents inherit the parent's toolset and run through the
-    same prompt builder, so the coding posture propagates to children for free.
-  * **Model / memory / compression** — declared on the profile
-    (``model_hint``, ``memory_policy``) as the extension seam; consumers read
-    ``mode.profile`` rather than re-deciding.
-
-Cache safety
-------------
-The mode is resolved **once** and is immutable. The workspace snapshot is built
-once at prompt-build time and baked into the *stable* system-prompt tier — never
-re-probed per turn (that would shatter the prompt cache). Branch and dirty state
-drift mid-session, so the brief tells the model to re-check with ``git`` before
-acting on the snapshot. A ``/coding`` flip therefore only takes effect next
-session (deferred), the same contract as ``/skills install`` vs ``--now``.
-
-Activation (config ``agent.coding_context``):
-
-  * ``auto`` (default) — posture (brief + snapshot) on an interactive coding
-    surface sitting in a code workspace (git repo or recognised project root).
-    Prompt-only; toolsets and the skill index untouched.
-  * ``focus`` — like ``auto``, but additionally collapses the toolset to the
-    ``coding`` set + enabled MCP servers and demotes non-coding skill
-    categories to names-only in the prompt's skill index (no skill is ever
-    hidden). Explicit opt-in for a lean schema.
-  * ``on`` — force the posture anywhere (incl. non-workspaces). Prompt-only.
-  * ``off`` — disable entirely.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import re
-import subprocess
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Any, Optional
-
-logger = logging.getLogger("hermes.coding_context")
-
-CODING_TOOLSET = "coding"
-
-# Surfaces where a coding posture makes sense under ``auto``. Messaging
-# platforms (telegram, discord, slack, …) are intentionally absent — a chat bot
-# in a group is not pair-programming.
-INTERACTIVE_CODING_PLATFORMS = {"cli", "tui", "acp", "desktop", ""}
-
-# Project-root signals that mark a directory as a code workspace even when it
-# isn't (yet) a git repo. Cheap filename checks — no parsing.
-_PROJECT_MARKERS = (
-    "pyproject.toml", "setup.py", "setup.cfg", "requirements.txt",
-    "package.json", "tsconfig.json", "deno.json",
-    "Cargo.toml", "go.mod", "pom.xml", "build.gradle", "build.gradle.kts",
-    "Gemfile", "composer.json", "mix.exs", "pubspec.yaml",
-    "CMakeLists.txt", "Makefile", "Dockerfile",
-    "AGENTS.md", "CLAUDE.md", ".cursorrules",
-)
-
-# Agent-instruction files surfaced separately from manifests in the snapshot.
-_CONTEXT_FILES = ("AGENTS.md", "CLAUDE.md", ".cursorrules")
-
-# Lockfile → package manager, checked in priority order.
-_PY_LOCKFILES = (("uv.lock", "uv"), ("poetry.lock", "poetry"), ("Pipfile.lock", "pipenv"))
-_JS_LOCKFILES = (
-    ("pnpm-lock.yaml", "pnpm"), ("bun.lockb", "bun"), ("bun.lock", "bun"),
-    ("yarn.lock", "yarn"), ("package-lock.json", "npm"),
-)
-
-# package.json scripts / Makefile targets worth surfacing as verify commands.
-_VERIFY_TARGETS = ("test", "tests", "lint", "typecheck", "check", "build", "fmt", "format")
-_MAX_VERIFY_COMMANDS = 8
-_MAX_FACT_FILE_BYTES = 256 * 1024
-
-_GIT_TIMEOUT = 2.5
-
-
-# Per-model edit-format steering. Matching the edit tool format to how a model
-# was trained reduces mistakes and wasted reasoning (OpenAI/Codex handle
-# patch-style diffs best; Anthropic models — and most open-weight coding
-# models, whose RL scaffolds use str_replace-style editors — do best with
-# string-replacement). Our `patch` tool exposes both: mode="patch" (V4A
-# multi-file) and mode="replace" (find-and-swap). We nudge each family toward
-# its native format. Unknown families get nothing (the brief's neutral wording
-# stands). Substrings match the model id; aligned with TOOL_USE_ENFORCEMENT_MODELS.
-#
-# GPT/Codex get V4A for ALL edits, single-file included: in codex-rs,
-# apply_patch (V4A — apply_patch.lark) is the ONLY file editor, no
-# str_replace-style tool exists, and the shipped model prompts say to use
-# apply_patch even "for single file edits" — so a replace-mode nudge would
-# steer those models toward a format their first-party harness never taught
-# them.
-_EDIT_FORMAT_GUIDANCE: dict[str, tuple[tuple[str, ...], str]] = {
-    "patch": (
-        ("gpt", "codex"),
-        "- Edit format: author new files with `write_file`; for edits to "
-        "existing code use `patch` with `mode='patch'` (V4A diff) — including "
-        "single-file edits. It's the edit format you handle most reliably.",
-    ),
-    "replace": (
-        ("claude", "sonnet", "opus", "haiku",
-         "gemini", "gemma", "deepseek", "qwen", "kimi", "glm", "grok",
-         "hermes", "llama", "mistral", "devstral", "minimax"),
-        "- Edit format: author new files with `write_file`; for edits to "
-        "existing code prefer `patch` in `mode='replace'` — match a unique "
-        "snippet and swap it. Reach for `mode='patch'` (V4A) only when an edit "
-        "genuinely spans several files at once.",
-    ),
-}
-
-
-def _model_family(model: Optional[str]) -> Optional[str]:
-    """Classify a model id into an edit-format family key, or ``None``.
-
-    Used to steer the coding posture toward the edit tool format a model was
-    trained on. Family-agnostic by design: an unrecognised model gets ``None``
-    and the operating brief's neutral edit wording applies.
-    """
-    if not model:
-        return None
-    lowered = model.lower()
-    for family, (needles, _line) in _EDIT_FORMAT_GUIDANCE.items():
-        if any(n in lowered for n in needles):
-            return family
-    return None
-
-
-def _edit_format_line(model: Optional[str]) -> str:
-    """The edit-format guidance line for this model's family (``""`` if none)."""
-    family = _model_family(model)
-    if family is None:
-        return ""
-    return _EDIT_FORMAT_GUIDANCE[family][1]
-
-
-# Operating brief for the coding posture. Tool names referenced here (read_file,
-# search_files, patch, write_file, terminal, todo) are in the coding toolset and
-# in _HERMES_CORE_TOOLS, so they're present on every surface this fires on.
-CODING_AGENT_GUIDANCE = (
-    "You are a coding agent pairing with the user inside their codebase. "
-    "Operate like a careful senior engineer.\n"
-    "\n"
-    "Gather context first:\n"
-    "- Read the relevant files with `read_file` and locate code with "
-    "`search_files` before changing anything. Trace a symbol to its definition "
-    "and usages rather than guessing its shape.\n"
-    "- Batch independent lookups: when several reads/searches don't depend on "
-    "each other, issue them together in one turn instead of one at a time.\n"
-    "- Never invent files, symbols, APIs, or imports. If you haven't seen it in "
-    "the repo, go look. Don't assume a library is available — check the project "
-    "manifest (pyproject.toml / package.json / Cargo.toml / go.mod) and how "
-    "neighbouring files import it.\n"
-    "\n"
-    "Make changes through the tools, not the chat:\n"
-    "- Edit with `patch`/`write_file`. Do NOT print code blocks to the user as "
-    "a substitute for editing — apply the change, then summarise it. Only show "
-    "code when the user explicitly asks to see it.\n"
-    "- Match the project's existing style and conventions; AGENTS.md / "
-    "CLAUDE.md / .cursorrules already in context win over your defaults. Touch "
-    "only what the task needs — no drive-by refactors, renames, or reformatting "
-    "— and add any imports/dependencies your code requires.\n"
-    "- If an edit fails to apply, re-read the file to get the current exact "
-    "contents before retrying — don't repeat a stale patch. If the same region "
-    "fails twice, rewrite the enclosing function or file with `write_file` "
-    "instead of attempting a third patch.\n"
-    "\n"
-    "Verify, and know when to stop:\n"
-    "- Use `terminal` for git, builds, tests, and inspection. Run the relevant "
-    "tests/linter/build and confirm they pass before claiming the work is done.\n"
-    "- Fix root causes, not symptoms: when you find a bug, check sibling call "
-    "paths for the same flaw and fix the class, not just the reported site.\n"
-    "- When fixing linter/type errors on a file, stop after about three "
-    "attempts on the same file and ask the user rather than looping.\n"
-    "- Track multi-step work with `todo`. Reference code as `path:line` instead "
-    "of pasting whole files.\n"
-    "\n"
-    "Respect the user's repo: don't commit, push, or rewrite history unless "
-    "asked, and never read, print, or commit secrets — leave `.env` and "
-    "credential files alone unless the user explicitly asks. The Workspace "
-    "block below is a snapshot from session start — re-run `git status`/"
-    "`git branch` before relying on it. Be concise: lead with the change or "
-    "answer, not a preamble."
-)
-
-
-# ── Context profiles (declarative posture definitions) ──────────────────────
-
-
-@dataclass(frozen=True)
-class ContextProfile:
-    """A named operating posture. Pure data — consumers read these fields.
-
-    ``toolset``      — collapse to this toolset (+ enabled MCP) when no explicit
-                       selection is pinned; ``None`` keeps the platform default.
-    ``guidance``     — operating brief injected into the stable system prompt;
-                       ``""`` injects nothing.
-    ``model_hint``   — routing preference key for smart model routing
-                       (extension seam; not yet consumed by the router).
-    ``memory_policy``— memory namespace/weighting hint (extension seam).
-    ``compact_skill_categories`` — skill categories DEMOTED to names-only in
-                       the system-prompt skill index under the opt-in ``focus``
-                       mode. Never hidden: every skill name stays visible
-                       (so memory-anchored recall keeps working) — only the
-                       descriptions are dropped to cut index noise. Deny-list
-                       semantics so unknown/custom categories keep full
-                       entries.
-    """
-
-    name: str
-    toolset: Optional[str] = None
-    guidance: str = ""
-    model_hint: Optional[str] = None
-    memory_policy: str = "default"
-    compact_skill_categories: tuple[str, ...] = ()
-
-
-# Skill categories that are clearly not part of a coding workflow. Demoted to
-# names-only in the prompt's skill index under the opt-in ``focus`` mode only
-# (deny-list — anything not listed here, incl. custom user categories, keeps
-# full entries). Coding-adjacent categories (devops, github, mcp,
-# data-science, diagramming, research, security, …) are intentionally absent.
-_NON_CODING_SKILL_CATEGORIES = (
-    "apple", "communication", "cooking", "creative", "email", "finance",
-    "gaming", "gifs", "health", "media", "music", "note-taking",
-    "productivity", "shopping", "smart-home", "social-media", "travel",
-    "yuanbao",
-)
-
-
-GENERAL_PROFILE = ContextProfile(name="general")
-CODING_PROFILE = ContextProfile(
-    name="coding",
-    toolset=CODING_TOOLSET,
-    guidance=CODING_AGENT_GUIDANCE,
-    model_hint="coding",
-    memory_policy="project",
-    compact_skill_categories=_NON_CODING_SKILL_CATEGORIES,
-)
-
-_PROFILES: dict[str, ContextProfile] = {
-    GENERAL_PROFILE.name: GENERAL_PROFILE,
-    CODING_PROFILE.name: CODING_PROFILE,
-}
-
-
-def get_profile(name: str) -> ContextProfile:
-    """Return a registered profile, falling back to ``general``."""
-    return _PROFILES.get(name, GENERAL_PROFILE)
-
-
-# ── Helpers ─────────────────────────────────────────────────────────────────
-
-
-def _coding_mode(config: Optional[dict[str, Any]]) -> str:
-    """Return the normalized ``agent.coding_context`` mode (auto/focus/on/off)."""
-    if config is None:
-        try:
-            from hermes_cli.config import load_config
-
-            config = load_config()
-        except Exception:
-            config = {}
-    raw = ((config or {}).get("agent", {}) or {}).get("coding_context", "auto")
-    mode = str(raw).strip().lower()
-    if mode in {"focus", "strict", "lean"}:
-        return "focus"
-    if mode in {"on", "true", "yes", "1", "always"}:
-        return "on"
-    if mode in {"off", "false", "no", "0", "never"}:
-        return "off"
-    return "auto"
-
-
-def _resolve_cwd(cwd: Optional[str | Path]) -> Path:
-    if cwd:
-        return Path(cwd).expanduser()
-    try:
-        from agent.runtime_cwd import resolve_agent_cwd
-
-        return resolve_agent_cwd()
-    except Exception:
-        return Path(os.getcwd())
-
-
-def _git_root(cwd: Path) -> Optional[Path]:
-    current = cwd.resolve()
-    for parent in [current, *current.parents]:
-        if (parent / ".git").exists():
-            return parent
-    return None
-
-
-def _home() -> Optional[Path]:
-    try:
-        return Path.home().resolve()
-    except (OSError, RuntimeError):
-        return None
-
-
-def _marker_root(cwd: Path) -> Optional[Path]:
-    """Nearest ancestor that looks like a project root, or ``None``.
-
-    Walks up at most a few levels so a manifest in the workspace root counts
-    even when the user is in a subdirectory. ``$HOME`` itself is skipped — a
-    Makefile or AGENTS.md sitting in the home directory is global user config,
-    not a project-root signal.
-    """
-    current = cwd.resolve()
-    home = _home()
-    for depth, parent in enumerate([current, *current.parents]):
-        if depth > 6:
-            break
-        if parent == home:
-            continue
-        for marker in _PROJECT_MARKERS:
-            if (parent / marker).exists():
-                return parent
-    return None
-
-
-def _detect_profile_name(mode: str, platform: str, cwd_str: str) -> str:
-    """Resolve which profile applies.
-
-    ``auto``/``focus``: coding when the surface is interactive AND the cwd is a
-    code workspace (a git repo or a recognised project root). ``on``: always
-    coding. ``off``: always general.
-
-    A git repo rooted at ``$HOME`` (the dotfiles pattern) is NOT a workspace
-    signal — without the guard, every session anywhere under a dotfiles-managed
-    home directory would silently flip to the coding posture.
-
-    Detection is intentionally not memoized: it's a handful of ``stat`` calls,
-    and callers resolve the mode once per session anyway. Caching here would
-    risk a stale posture if a long-lived process (gateway/TUI) serves sessions
-    from different working directories.
-    """
-    if mode == "off":
-        return GENERAL_PROFILE.name
-    if mode == "on":
-        return CODING_PROFILE.name
-    if platform and platform.strip().lower() not in INTERACTIVE_CODING_PLATFORMS:
-        return GENERAL_PROFILE.name
-    cwd = Path(cwd_str)
-    git_root = _git_root(cwd)
-    if git_root is not None and git_root == _home():
-        git_root = None  # dotfiles repo at $HOME — not a code workspace
-    if git_root is not None or _marker_root(cwd) is not None:
-        return CODING_PROFILE.name
-    return GENERAL_PROFILE.name
-
-
-# ── RuntimeMode (the seam) ──────────────────────────────────────────────────
-
-
-@dataclass(frozen=True)
-class RuntimeMode:
-    """The resolved operating posture for a session. Immutable by construction.
-
-    Built once via :func:`resolve_runtime_mode` and consumed by every domain
-    that cares about the coding/general distinction. Never mutate or re-resolve
-    mid-session — that would break the prompt cache.
-    """
-
-    profile: ContextProfile
-    surface: str
-    cwd: Path
-    # The normalized ``agent.coding_context`` mode this posture was resolved
-    # under (auto/focus/on/off). Toolset collapse is gated on ``focus``.
-    config_mode: str = "auto"
-    # The model id this session runs (e.g. "anthropic/claude-opus-4.8"). Used
-    # only to steer edit-format guidance toward the model's family — see
-    # ``_edit_format_line``. Fixed for the session, so cache-safe.
-    model: Optional[str] = None
-
-    @property
-    def kind(self) -> str:
-        return self.profile.name
-
-    @property
-    def is_coding(self) -> bool:
-        return self.profile.name == CODING_PROFILE.name
-
-    def toolset_selection(self, config: Optional[dict[str, Any]] = None) -> Optional[list[str]]:
-        """Toolset list for this posture, or ``None`` to keep the platform default.
-
-        Non-``None`` only under the opt-in ``focus`` mode. The default posture
-        is prompt-only: most strippable toolsets are off-by-default anyway, and
-        a user who explicitly enabled one (image-gen for frontend/game assets,
-        messaging for build notifications, …) keeps it while coding.
-
-        Callers apply this only when the user hasn't pinned an explicit
-        selection (``--toolsets``, ``HERMES_TUI_TOOLSETS``, …); they never
-        override a pin. Returns the profile's toolset plus enabled MCP servers.
-        """
-        if self.config_mode != "focus":
-            return None
-        if self.profile.toolset is None:
-            return None
-        return [self.profile.toolset, *_enabled_mcp_servers(config)]
-
-    def system_blocks(self) -> list[str]:
-        """Stable system-prompt blocks for this posture (brief + workspace).
-
-        The operating brief carries a model-family edit-format nudge appended
-        to it (one cached string, not a separate block) so the model is steered
-        toward the `patch` mode it handles best — see ``_edit_format_line``.
-        """
-        if not self.is_coding:
-            return []
-        blocks: list[str] = []
-        if self.profile.guidance:
-            brief = self.profile.guidance
-            edit_line = _edit_format_line(self.model)
-            if edit_line:
-                brief = f"{brief}\n{edit_line}"
-            blocks.append(brief)
-        workspace = build_coding_workspace_block(self.cwd)
-        if workspace:
-            blocks.append(workspace)
-        return blocks
-
-    def compact_skill_categories(self) -> frozenset[str]:
-        """Skill categories to demote to names-only in the prompt's skill index.
-
-        Gated on the opt-in ``focus`` mode, like the toolset collapse: the
-        default posture leaves the skill index untouched. Users who didn't ask
-        for a lean prompt keep full entries for every category — index changes
-        under ``auto`` proved too surprising in practice, even names-only ones
-        (a demoted description is information the model no longer weighs when
-        deciding what to load).
-
-        Demoted — never hidden — even under ``focus``. An earlier revision
-        fully pruned these categories from the index, which caused silent
-        capability loss in a real workflow: agent-created skills are the
-        model's accumulated project memory (server-ops runbooks, learned
-        pitfalls, …), and models do not reliably reach for ``skills_list`` to
-        rediscover what the index stopped showing them. Names-only keeps every
-        skill loadable on recall while still cutting the description noise.
-        """
-        if not self.is_coding or self.config_mode != "focus":
-            return frozenset()
-        return frozenset(self.profile.compact_skill_categories)
-
-
-def resolve_runtime_mode(
-    *,
-    platform: Optional[str] = None,
-    cwd: Optional[str | Path] = None,
-    config: Optional[dict[str, Any]] = None,
-    model: Optional[str] = None,
-) -> RuntimeMode:
-    """Resolve the operating posture once. Cheap — a handful of ``stat`` calls.
-
-    This is the single entry point every domain should call. The returned
-    object is immutable and safe to cache for the session. Detection itself is
-    intentionally *not* memoized (see ``_detect_profile_name``) so a long-lived
-    process can't pin a stale posture; callers resolve once per session and
-    hold the result. ``model`` is recorded only to steer edit-format guidance;
-    it never affects detection.
-    """
-    resolved_cwd = _resolve_cwd(cwd)
-    mode = _coding_mode(config)
-    name = _detect_profile_name(
-        mode, (platform or "").strip().lower(), str(resolved_cwd)
-    )
-    return RuntimeMode(
-        profile=get_profile(name),
-        surface=platform or "",
-        cwd=resolved_cwd,
-        config_mode=mode,
-        model=model,
-    )
-
-
-# ── Back-compat surface (thin wrappers over RuntimeMode) ────────────────────
-
-
-def is_coding_context(
-    *,
-    platform: Optional[str] = None,
-    cwd: Optional[str | Path] = None,
-    config: Optional[dict[str, Any]] = None,
-) -> bool:
-    """Whether Hermes should operate in its coding posture right now."""
-    return resolve_runtime_mode(platform=platform, cwd=cwd, config=config).is_coding
-
-
-def coding_selection(
-    *,
-    platform: Optional[str] = None,
-    cwd: Optional[str | Path] = None,
-    config: Optional[dict[str, Any]] = None,
-) -> Optional[list[str]]:
-    """Toolset selection for the coding posture.
-
-    ``None`` unless the user opted into ``focus`` mode AND the posture is
-    active — the default coding posture never overrides configured toolsets.
-    """
-    return resolve_runtime_mode(
-        platform=platform, cwd=cwd, config=config
-    ).toolset_selection(config)
-
-
-def coding_system_blocks(
-    *,
-    platform: Optional[str] = None,
-    cwd: Optional[str | Path] = None,
-    config: Optional[dict[str, Any]] = None,
-    model: Optional[str] = None,
-) -> list[str]:
-    """Stable system-prompt blocks for the current posture (empty when general).
-
-    ``model`` steers the brief's edit-format nudge toward the model's family.
-    """
-    return resolve_runtime_mode(
-        platform=platform, cwd=cwd, config=config, model=model
-    ).system_blocks()
-
-
-def coding_compact_skill_categories(
-    *,
-    platform: Optional[str] = None,
-    cwd: Optional[str | Path] = None,
-    config: Optional[dict[str, Any]] = None,
-) -> frozenset[str]:
-    """Skill categories the active posture demotes to names-only in the index.
-
-    Empty outside the coding posture and outside the opt-in ``focus`` mode —
-    the default posture never touches the skill index. Under ``focus``,
-    demoted — never hidden: every skill name stays in the index and remains
-    loadable via ``skill_view`` / ``skills_list``; only descriptions are
-    dropped.
-    """
-    return resolve_runtime_mode(
-        platform=platform, cwd=cwd, config=config
-    ).compact_skill_categories()
-
-
-def _enabled_mcp_servers(config: Optional[dict[str, Any]]) -> list[str]:
-    """Names of MCP servers the user has enabled — kept in the coding posture.
-
-    MCP servers (figma, browser, tophat, …) are explicitly configured and part
-    of the coding workflow, not noise to strip.
-    """
-    try:
-        from hermes_cli.config import read_raw_config
-        from hermes_cli.tools_config import _parse_enabled_flag
-
-        servers = read_raw_config().get("mcp_servers") or {}
-        return [
-            str(name)
-            for name, cfg in servers.items()
-            if isinstance(cfg, dict)
-            and _parse_enabled_flag(cfg.get("enabled", True), default=True)
-        ]
-    except Exception:
-        return []
-
-
-# ── git/workspace probe ─────────────────────────────────────────────────────
-
-
-def _git(cwd: Path, *args: str) -> str:
-    try:
-        out = subprocess.run(
-            ["git", "-C", str(cwd), *args],
-            capture_output=True,
-            text=True,
-            timeout=_GIT_TIMEOUT,
-        )
-    except (OSError, subprocess.SubprocessError):
-        return ""
-    return out.stdout.strip() if out.returncode == 0 else ""
-
-
-def _parse_status(porcelain: str) -> tuple[dict[str, str], dict[str, int]]:
-    """Parse ``git status --porcelain=2 --branch`` into branch + counts."""
-    branch: dict[str, str] = {}
-    counts = {"staged": 0, "modified": 0, "untracked": 0, "conflicts": 0}
-    for line in porcelain.splitlines():
-        if line.startswith("# branch.head"):
-            branch["head"] = line.split(maxsplit=2)[-1]
-        elif line.startswith("# branch.upstream"):
-            branch["upstream"] = line.split(maxsplit=2)[-1]
-        elif line.startswith("# branch.ab"):
-            parts = line.split()
-            branch["ahead"], branch["behind"] = parts[2].lstrip("+"), parts[3].lstrip("-")
-        elif line.startswith(("1 ", "2 ")):
-            xy = line.split(maxsplit=2)[1]
-            if xy[0] != ".":
-                counts["staged"] += 1
-            if xy[1] != ".":
-                counts["modified"] += 1
-        elif line.startswith("u "):
-            counts["conflicts"] += 1
-        elif line.startswith("? "):
-            counts["untracked"] += 1
-    return branch, counts
-
-
-def _read_small(path: Path) -> str:
-    """Read a small text file, or ``""`` — never raises, never reads huge files."""
-    try:
-        if not path.is_file() or path.stat().st_size > _MAX_FACT_FILE_BYTES:
-            return ""
-        return path.read_text(encoding="utf-8", errors="replace")
-    except OSError:
-        return ""
-
-
-def _project_facts(root: Path) -> list[str]:
-    """Detected project facts for the workspace snapshot.
-
-    The point is to hand the model its *verify loop* up front — which manifest,
-    which package manager, and the exact test/lint/build commands — instead of
-    making it rediscover them every session. Cheap: stat calls plus reads of a
-    couple of small files; built once at prompt-build time (cache-safe).
-    """
-    facts: list[str] = []
-
-    manifests = [m for m in _PROJECT_MARKERS if m not in _CONTEXT_FILES and (root / m).is_file()]
-    package_managers = [
-        pm for lock, pm in (*_PY_LOCKFILES, *_JS_LOCKFILES) if (root / lock).is_file()
-    ]
-    if manifests:
-        line = f"- Project: {', '.join(manifests[:6])}"
-        if package_managers:
-            line += f" ({'/'.join(dict.fromkeys(package_managers))})"
-        facts.append(line)
-
-    verify: list[str] = []
-    if (root / "scripts" / "run_tests.sh").is_file():
-        verify.append("scripts/run_tests.sh")
-    if (root / "package.json").is_file():
-        try:
-            scripts = json.loads(_read_small(root / "package.json") or "{}").get("scripts") or {}
-        except (json.JSONDecodeError, AttributeError):
-            scripts = {}
-        js_pm = next((pm for lock, pm in _JS_LOCKFILES if (root / lock).is_file()), "npm")
-        verify.extend(f"{js_pm} run {name}" for name in _VERIFY_TARGETS if name in scripts)
-    if (root / "pytest.ini").is_file() or "[tool.pytest" in _read_small(root / "pyproject.toml"):
-        verify.append("pytest")
-    makefile = _read_small(root / "Makefile")
-    if makefile:
-        verify.extend(
-            f"make {name}" for name in _VERIFY_TARGETS
-            if re.search(rf"^{re.escape(name)}\s*:", makefile, re.MULTILINE)
-        )
-    if verify:
-        deduped = list(dict.fromkeys(verify))[:_MAX_VERIFY_COMMANDS]
-        facts.append(f"- Verify: {'; '.join(deduped)}")
-
-    context_files = [c for c in _CONTEXT_FILES if (root / c).is_file()]
-    if context_files:
-        facts.append(f"- Context files: {', '.join(context_files)}")
-
-    return facts
-
-
-def build_coding_workspace_block(cwd: Optional[str | Path] = None) -> str:
-    """Workspace snapshot for the system prompt (empty outside a workspace).
-
-    Git state (branch/status/commits) when the cwd is in a repo, plus detected
-    project facts (manifest, package manager, verify commands, context files)
-    — so marker-only (non-git) projects still get a snapshot.
-    """
-    resolved = _resolve_cwd(cwd)
-    git_root = _git_root(resolved)
-    root = git_root or _marker_root(resolved)
-    if root is None:
-        return ""
-
-    lines = ["Workspace (snapshot at session start — re-check with `git` before acting on it):"]
-    lines.append(f"- Root: {root}")
-
-    if git_root is not None:
-        branch, counts = _parse_status(_git(root, "status", "--porcelain=2", "--branch"))
-        head = branch.get("head", "")
-        if head and head != "(detached)":
-            line = f"- Branch: {head}"
-            if branch.get("upstream"):
-                line += f" \u2192 {branch['upstream']}"
-                ahead, behind = branch.get("ahead", "0"), branch.get("behind", "0")
-                if ahead != "0" or behind != "0":
-                    line += f" (ahead {ahead}, behind {behind})"
-            lines.append(line)
-        elif head == "(detached)":
-            lines.append("- Branch: (detached HEAD)")
-
-        # Linked worktree: the per-worktree git dir differs from the shared common dir.
-        git_dir, common_dir = _git(root, "rev-parse", "--git-dir"), _git(root, "rev-parse", "--git-common-dir")
-        if git_dir and common_dir and Path(git_dir).resolve() != Path(common_dir).resolve():
-            main_tree = Path(common_dir).resolve().parent
-            lines.append(f"- Worktree: linked (primary tree at {main_tree})")
-
-        dirty = [f"{n} {label}" for label, n in (
-            ("staged", counts["staged"]), ("modified", counts["modified"]),
-            ("untracked", counts["untracked"]), ("conflicts", counts["conflicts"]),
-        ) if n]
-        lines.append(f"- Status: {', '.join(dirty) if dirty else 'clean'}")
-
-        recent = _git(root, "log", "-3", "--pretty=%h %s")
-        if recent:
-            lines.append("- Recent commits:")
-            lines.extend(f"    {c}" for c in recent.splitlines())
-
-    lines.extend(_project_facts(root))
-    return "\n".join(lines)

agent/context_references.py

@@ -246,14 +246,7 @@ def _expand_file_reference(
     if not path.is_file():
         return f"{ref.raw}: path is not a file", None
     if _is_binary_file(path):
-        # A binary file can't be inlined as text, but it IS on disk (the agent's
-        # tools run where this resolves — the local cwd, or the staged copy in a
-        # remote session workspace). Returning a bare "not supported" warning
-        # with no content was a dead end: the model saw a failure and gave up
-        # (told the user the file type wasn't supported). Instead, hand it an
-        # actionable block — the path, type, size, and a nudge to use its tools —
-        # so it can read/convert/view the file itself.
-        return None, _binary_reference_block(ref, path)
+        return f"{ref.raw}: binary files are not supported", None
 
     text = path.read_text(encoding="utf-8")
     if ref.line_start is not None:
@@ -297,7 +290,6 @@ def _expand_git_reference(
             capture_output=True,
             text=True,
             timeout=30,
-            stdin=subprocess.DEVNULL,
         )
     except subprocess.TimeoutExpired:
         return f"{ref.raw}: git command timed out (30s)", None
@@ -490,7 +482,6 @@ def _rg_files(path: Path, cwd: Path, limit: int) -> list[Path] | None:
             capture_output=True,
             text=True,
             timeout=10,
-            stdin=subprocess.DEVNULL,
         )
     except (FileNotFoundError, OSError, subprocess.TimeoutExpired):
         return None
@@ -500,30 +491,6 @@ def _rg_files(path: Path, cwd: Path, limit: int) -> list[Path] | None:
     return files[:limit]
 
 
-def _human_bytes(n: int) -> str:
-    size = float(n)
-    for unit in ("B", "KB", "MB", "GB"):
-        if size < 1024 or unit == "GB":
-            return f"{int(size)} {unit}" if unit == "B" else f"{size:.1f} {unit}"
-        size /= 1024
-    return f"{size:.1f} GB"
-
-
-def _binary_reference_block(ref: ContextReference, path: Path) -> str:
-    mime, _ = mimetypes.guess_type(path.name)
-    mime = mime or "application/octet-stream"
-    try:
-        size = _human_bytes(path.stat().st_size)
-    except OSError:
-        size = "unknown size"
-    return (
-        f"📎 {ref.raw} ({mime}, {size}) — binary file, not inlined as text. "
-        f"It is available on disk at `{path}`. Use your tools to work with it "
-        f"(read or convert it, extract its text, or view/render it as needed); "
-        f"do not tell the user the file type is unsupported."
-    )
-
-
 def _file_metadata(path: Path) -> str:
     if _is_binary_file(path):
         return f"{path.stat().st_size} bytes"

agent/conversation_loop.py

@@ -2221,54 +2221,30 @@ def run_conversation(
                     print(f"{agent.log_prefix}     • Legacy cleanup: hermes config set ANTHROPIC_TOKEN \"\"")
                     print(f"{agent.log_prefix}     • Clear stale keys: hermes config set ANTHROPIC_API_KEY \"\"")
 
-                # Thinking block signature recovery.
-                #
+                # ── Thinking block signature recovery ─────────────────
                 # Anthropic signs thinking blocks against the full turn
-                # content. Any upstream mutation (context compression,
+                # content.  Any upstream mutation (context compression,
                 # session truncation, message merging) invalidates the
-                # signature and the API replies HTTP 400 ("invalid
-                # signature" or "cannot be modified"). Recovery strips
-                # ``reasoning_details`` so the retry sends no thinking
-                # blocks at all. One-shot per outer loop.
-                #
-                # The strip targets ``api_messages``, which is the
-                # API-call-time list that ``_build_api_kwargs`` consumes
-                # on every retry. ``api_messages`` was populated once at
-                # the start of the turn from shallow copies of
-                # ``messages``, so mutating it does not touch the
-                # canonical store. The previous implementation popped
-                # ``reasoning_details`` from ``messages`` instead, which
-                # had two problems: ``api_messages`` carried its own
-                # reference to the field through the shallow copy, so the
-                # retry's wire payload still included thinking blocks and
-                # the recovery never reached the API; and the mutation
-                # persisted into ``state.db`` through any subsequent
-                # ``_persist_session`` call, permanently corrupting the
-                # conversation. Future turns would replay the stripped
-                # state, hit the same 400, and the agent would terminate
-                # with ``max_retries_exhausted``, often spawning
-                # cascading compaction-ended sessions chained off the
-                # corrupted parent.
+                # signature → HTTP 400.  Recovery: strip reasoning_details
+                # from all messages so the next retry sends no thinking
+                # blocks at all.  One-shot — don't retry infinitely.
                 if (
                     classified.reason == FailoverReason.thinking_signature
                     and not _retry.thinking_sig_retry_attempted
                 ):
                     _retry.thinking_sig_retry_attempted = True
-                    _api_stripped = 0
-                    for _m in api_messages:
-                        if isinstance(_m, dict) and "reasoning_details" in _m:
+                    for _m in messages:
+                        if isinstance(_m, dict):
                             _m.pop("reasoning_details", None)
-                            _api_stripped += 1
                     agent._vprint(
-                        f"{agent.log_prefix}⚠️  Thinking block signature invalid, "
-                        f"stripped reasoning_details from api_messages for retry...",
+                        f"{agent.log_prefix}⚠️  Thinking block signature invalid — "
+                        f"stripped all thinking blocks, retrying...",
                         force=True,
                     )
                     logger.warning(
                         "%sThinking block signature recovery: stripped "
-                        "reasoning_details from %d api_messages "
-                        "(canonical messages unchanged)",
-                        agent.log_prefix, _api_stripped,
+                        "reasoning_details from %d messages",
+                        agent.log_prefix, len(messages),
                     )
                     continue
 

agent/credits_tracker.py

@@ -194,71 +194,17 @@ class AgentNotice:
     id: Optional[str] = None
 
 
-# ── is_free_tier_model (local-data-only free-model check) ────────────────────
-
-
-def is_free_tier_model(model: str, base_url: str = "") -> bool:
-    """Return True when *model* is a Nous free-tier model, using ONLY local data.
-
-    Two signals, both zero-network:
-
-    1. The ``:free`` suffix — the canonical Nous free SKU marker (e.g.
-       ``nvidia/nemotron-3-ultra:free``). Free by construction on the API side
-       (spend is forced to 0 for ``:free`` ids).
-    2. A peek into the in-process pricing cache in ``hermes_cli.models``
-       (populated when the model picker fetched ``/v1/models`` pricing for
-       *base_url*). PEEK ONLY — a cache miss never triggers a fetch. This is
-       CLI/TUI-session best-effort: gateway sessions never run the picker's
-       pricing fetch, so suppression there rests entirely on the ``:free``
-       suffix (which all Nous free SKUs carry).
-
-    Fail-open to False (the depleted notice still shows) on any error: wrongly
-    showing the warning is recoverable noise; wrongly hiding it on a paid model
-    would mask a real billing block.
-    """
-    if not model:
-        return False
-    if model.endswith(":free"):
-        return True
-    if not base_url:
-        return False
-    try:
-        from hermes_cli.models import _is_model_free, _pricing_cache
-
-        # Mirror get_pricing_for_provider's key normalization: the agent's
-        # Nous base_url is /v1-suffixed (https://inference-api.nousresearch.com/v1)
-        # but the picker keys _pricing_cache on the pre-/v1 root.
-        key = base_url.rstrip("/")
-        if key.endswith("/v1"):
-            key = key[:-3].rstrip("/")
-        pricing = _pricing_cache.get(key)
-        if not pricing:
-            return False
-        return _is_model_free(model, pricing)
-    except Exception:
-        return False
-
-
 # ── evaluate_credits_notices (pure reconciliation function) ──────────────────
 
 
 def evaluate_credits_notices(
     state: CreditsState,
     latch: dict,
-    *,
-    model_is_free: bool = False,
 ) -> tuple[list[AgentNotice], list[str]]:
     """Reconcile credits notices against the latch. Mutates ``latch`` IN PLACE.
 
     latch = {"active": set[str], "seen_below_90": bool, "usage_band": Optional[int]}.
 
-    ``model_is_free``: True when the session's active model is a Nous free-tier
-    model (see :func:`is_free_tier_model`). Suppresses the ``credits.depleted``
-    notice — a depleted account on a free model can keep inferencing, so the
-    error banner is noise (and confuses free-tier users who never had credits).
-    Suppression does NOT emit the "restored" success notice; that fires only on
-    a genuine ``paid_access`` flip back to True.
-
     Returns ``(to_show: list[AgentNotice], to_clear: list[str])``.
     Caller emits to_clear FIRST, then to_show.
 
@@ -338,11 +284,7 @@ def evaluate_credits_notices(
         active.discard("credits.grant_spent")
 
     # ── depleted ─────────────────────────────────────────────────────────────
-    # Suppressed while the active model is free: inference still works there,
-    # so the error banner would just alarm users (free-tier users especially,
-    # who never had paid credits to "lose").
-    show_depleted = depleted_cond and not model_is_free
-    if show_depleted and "credits.depleted" not in active:
+    if depleted_cond and "credits.depleted" not in active:
         to_show.append(
             AgentNotice(
                 text="✕ Credit access paused · run /usage for balance",
@@ -353,23 +295,20 @@ def evaluate_credits_notices(
             )
         )
         active.add("credits.depleted")
-    elif "credits.depleted" in active and not show_depleted:
+    elif "credits.depleted" in active and not depleted_cond:
         to_clear.append("credits.depleted")
         active.discard("credits.depleted")
-        if not depleted_cond:
-            # Genuine recovery (paid_access flipped back True): also emit the
-            # success notice. A clear caused by switching to a free model while
-            # still depleted must NOT claim access was restored.
-            to_show.append(
-                AgentNotice(
-                    text="✓ Credit access restored",
-                    level="success",
-                    kind="ttl",
-                    ttl_ms=CREDITS_RESTORED_TTL_MS,
-                    key="credits.restored",
-                    id="credits.restored",
-                )
+        # Recovery: also emit the success notice
+        to_show.append(
+            AgentNotice(
+                text="✓ Credit access restored",
+                level="success",
+                kind="ttl",
+                ttl_ms=CREDITS_RESTORED_TTL_MS,
+                key="credits.restored",
+                id="credits.restored",
             )
+        )
 
     return (to_show, to_clear)
 

agent/curator.py

@@ -25,6 +25,7 @@ import json
 import logging
 import os
 import re
+import tempfile
 import threading
 from datetime import datetime, timedelta, timezone
 from pathlib import Path
@@ -32,7 +33,6 @@ from typing import Any, Callable, Dict, List, NamedTuple, Optional, Set
 
 from hermes_constants import get_hermes_home
 from tools import skill_usage
-from utils import atomic_json_write
 
 logger = logging.getLogger(__name__)
 
@@ -97,7 +97,20 @@ def load_state() -> Dict[str, Any]:
 def save_state(data: Dict[str, Any]) -> None:
     path = _state_file()
     try:
-        atomic_json_write(path, data, indent=2, sort_keys=True)
+        path.parent.mkdir(parents=True, exist_ok=True)
+        fd, tmp = tempfile.mkstemp(dir=str(path.parent), prefix=".curator_state_", suffix=".tmp")
+        try:
+            with os.fdopen(fd, "w", encoding="utf-8") as f:
+                json.dump(data, f, indent=2, sort_keys=True, ensure_ascii=False)
+                f.flush()
+                os.fsync(f.fileno())
+            os.replace(tmp, path)
+        except BaseException:
+            try:
+                os.unlink(tmp)
+            except OSError:
+                pass
+            raise
     except Exception as e:
         logger.debug("Failed to save curator state: %s", e, exc_info=True)
 

agent/display.py

@@ -858,20 +858,6 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
     return False, ""
 
 
-def _used_free_parallel(result: str | None) -> bool:
-    """True when a web result came from Parallel's free Search MCP.
-
-    Only the keyless Parallel path tags its result with ``provider="parallel"``;
-    the paid REST path and every other provider omit it. Used to label the tool
-    line "Parallel search" / "Parallel fetch" exactly when the free MCP served
-    the call.
-    """
-    if not isinstance(result, str) or '"provider"' not in result:
-        return False
-    data = safe_json_loads(result)
-    return isinstance(data, dict) and str(data.get("provider", "")).lower() == "parallel"
-
-
 def get_cute_tool_message(
     tool_name: str, args: dict, duration: float, result: str | None = None,
 ) -> str:
@@ -909,17 +895,15 @@ def get_cute_tool_message(
         return f"{line}{failure_suffix}"
 
     if tool_name == "web_search":
-        verb = "Parallel search" if _used_free_parallel(result) else "search"
-        return _wrap(f"┊ 🔍 {verb:<9} {_trunc(args.get('query', ''), 42)}  {dur}")
+        return _wrap(f"┊ 🔍 search    {_trunc(args.get('query', ''), 42)}  {dur}")
     if tool_name == "web_extract":
-        verb = "Parallel fetch" if _used_free_parallel(result) else "fetch"
         urls = args.get("urls", [])
         if urls:
             url = urls[0] if isinstance(urls, list) else str(urls)
             domain = url.replace("https://", "").replace("http://", "").split("/")[0]
             extra = f" +{len(urls)-1}" if len(urls) > 1 else ""
-            return _wrap(f"┊ 📄 {verb:<9} {_trunc(domain, 35)}{extra}  {dur}")
-        return _wrap(f"┊ 📄 {verb:<9} pages  {dur}")
+            return _wrap(f"┊ 📄 fetch     {_trunc(domain, 35)}{extra}  {dur}")
+        return _wrap(f"┊ 📄 fetch     pages  {dur}")
     if tool_name == "terminal":
         return _wrap(f"┊ 💻 $         {_trunc(args.get('command', ''), 42)}  {dur}")
     if tool_name == "process":

agent/error_classifier.py

@@ -549,32 +549,14 @@ def classify_api_error(
             should_fallback=True,
         )
 
-    # Anthropic thinking block recovery (400).  Two distinct failure modes,
-    # same recovery (strip all reasoning_details and retry without thinking
-    # blocks — see the thinking_signature handler in conversation_loop.py):
-    #   1. Signature mismatch: a thinking block is signed against the full
-    #      turn content; any upstream mutation (context compression, session
-    #      truncation, message merging) invalidates the signature.
-    #      Pattern: "signature" + "thinking".
-    #   2. Frozen-block mutation: Anthropic rejects any change to the
-    #      thinking/redacted_thinking blocks in the *latest* assistant
-    #      message — "`thinking` or `redacted_thinking` blocks in the latest
-    #      assistant message cannot be modified. These blocks must remain as
-    #      they were in the original response."  This carries no "signature"
-    #      token, so the original pattern missed it and the turn hard-aborted
-    #      as a non-retryable client error instead of self-healing.
-    #      Pattern: "thinking" + ("cannot be modified" | "must remain as they were").
+    # Anthropic thinking block signature invalid (400).
     # Don't gate on provider — OpenRouter proxies Anthropic errors, so the
     # provider may be "openrouter" even though the error is Anthropic-specific.
-    # The combined patterns are unique enough.
+    # The message pattern ("signature" + "thinking") is unique enough.
     if (
         status_code == 400
+        and "signature" in error_msg
         and "thinking" in error_msg
-        and (
-            "signature" in error_msg
-            or "cannot be modified" in error_msg
-            or "must remain as they were" in error_msg
-        )
     ):
         return _result(
             FailoverReason.thinking_signature,
@@ -984,34 +966,6 @@ def _classify_400(
             should_fallback=False,
         )
 
-    # Request-validation errors (unsupported / unknown parameter) MUST be
-    # checked BEFORE context_overflow.  A GPT-5 model rejecting max_tokens
-    # returns:
-    #   "Unsupported parameter: 'max_tokens' is not supported with this model.
-    #    Use 'max_completion_tokens' instead."
-    # That string contains the literal substring "max_tokens", which is one of
-    # the _CONTEXT_OVERFLOW_PATTERNS — so without this guard the 400 is
-    # misclassified as context_overflow, routed into the compression loop,
-    # re-sent with the same bad parameter, and ends in "Cannot compress
-    # further".  These errors are deterministic (every retry gets the identical
-    # rejection), so classify as a non-retryable format_error and fall back.
-    #
-    # NOTE: we deliberately do NOT key off the generic ``invalid_request_error``
-    # code here — OpenAI stamps that same code on genuine context-overflow 400s,
-    # so matching it would mis-route real overflows away from compression. The
-    # unambiguous signals are the explicit "unsupported/unknown parameter"
-    # message text and the specific parameter-level error codes.
-    if (
-        any(p in error_msg for p in _REQUEST_VALIDATION_PATTERNS
-            if p != "invalid_request_error")
-        or error_code_lower in {"unknown_parameter", "unsupported_parameter"}
-    ):
-        return result_fn(
-            FailoverReason.format_error,
-            retryable=False,
-            should_fallback=True,
-        )
-
     # Context overflow from 400
     if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
         return result_fn(

agent/lsp/install.py

@@ -262,7 +262,6 @@ def _install_npm(
             capture_output=True,
             text=True,
             timeout=300,
-            stdin=subprocess.DEVNULL,
         )
         if proc.returncode != 0:
             logger.warning(
@@ -311,7 +310,6 @@ def _install_go(pkg: str, bin_name: str) -> Optional[str]:
             text=True,
             timeout=600,
             env=env,
-            stdin=subprocess.DEVNULL,
         )
         if proc.returncode != 0:
             logger.warning(
@@ -349,7 +347,6 @@ def _install_pip(pkg: str, bin_name: str) -> Optional[str]:
             capture_output=True,
             text=True,
             timeout=300,
-            stdin=subprocess.DEVNULL,
         )
         if proc.returncode != 0:
             logger.warning(

agent/model_metadata.py

@@ -141,8 +141,6 @@ DEFAULT_CONTEXT_LENGTHS = {
     # fuzzy-match collisions (e.g. "anthropic/claude-sonnet-4" is a
     # substring of "anthropic/claude-sonnet-4.6").
     # OpenRouter-prefixed models resolve via OpenRouter live API or models.dev.
-    "claude-fable-5": 1000000,
-    "claude-fable": 1000000,
     "claude-opus-4-8": 1000000,
     "claude-opus-4.8": 1000000,
     "claude-opus-4-7": 1000000,
@@ -970,16 +968,6 @@ def parse_available_output_tokens_from_error(error_msg: str) -> Optional[int]:
         # OpenRouter/Nous phrasing of the same condition.
         "in the output" in error_lower
         and "maximum context length" in error_lower
-    ) or (
-        # LM Studio / llama.cpp / some OpenAI-compatible servers:
-        #   "This model's maximum context length is 65536 tokens. However, you
-        #    requested 65536 output tokens and your prompt contains 77409
-        #    characters ..."
-        # The "requested N output tokens" phrasing means the OUTPUT cap is the
-        # problem (the input itself fits) — reduce max_tokens, don't compress.
-        "maximum context length" in error_lower
-        and "requested" in error_lower
-        and "output tokens" in error_lower
     )
     if not is_output_cap_error:
         return None
@@ -1011,22 +999,6 @@ def parse_available_output_tokens_from_error(error_msg: str) -> Optional[int]:
         if _available >= 1:
             return _available
 
-    # LM Studio / llama.cpp style: context window is reported in tokens but the
-    # prompt size is reported in CHARACTERS, e.g.
-    #   "maximum context length is 65536 tokens ... your prompt contains 77409
-    #    characters ...".
-    # Estimate the input tokens conservatively (~3 chars/token, which
-    # over-reserves the input so the retried output cap stays safely inside the
-    # window) and leave the remainder of the window for output.
-    _m_ctx_tok = re.search(r'maximum context length is (\d+)\s*token', error_lower)
-    _m_chars = re.search(r'prompt contains (\d+)\s*character', error_lower)
-    if _m_ctx_tok and _m_chars:
-        _ctx = int(_m_ctx_tok.group(1))
-        _est_input = (int(_m_chars.group(1)) + 2) // 3
-        _available = _ctx - _est_input
-        if _available >= 1:
-            return _available
-
     return None
 
 
@@ -1812,43 +1784,10 @@ def get_model_context_length(
         if ctx is not None:
             save_context_length(model, base_url, ctx)
             return ctx
-    # 5f. OpenRouter live /models metadata — authoritative for OpenRouter-routed
-    # models. OpenRouter's catalog carries per-model context_length (e.g.
-    # anthropic/claude-fable-5 -> 1M) and refreshes as new slugs ship, so it
-    # must win over both models.dev (step 5g) and the hardcoded family catch-all
-    # (step 8). Before this branch, an OpenRouter selection set
-    # effective_provider="openrouter", which (a) made the models.dev lookup miss
-    # brand-new slugs and (b) skipped the step-6 OR fallback (gated on `not
-    # effective_provider`), so a fresh slug like claude-fable-5 fell through to
-    # the generic "claude": 200K entry and under-reported a 1M window. Mirrors
-    # the dedicated Nous/Copilot/GMI branches above.
-    if effective_provider == "openrouter":
-        metadata = fetch_model_metadata()
-        entry = metadata.get(model)
-        if entry:
-            or_ctx = entry.get("context_length")
-            # Guard against the known OpenRouter Kimi-family 32k underreport
-            # (same class the hardcoded overrides exist to mitigate).
-            if isinstance(or_ctx, int) and or_ctx > 0 and not (
-                or_ctx == 32768 and _model_name_suggests_kimi(model)
-            ):
-                return or_ctx
-
     if effective_provider:
         from agent.models_dev import lookup_models_dev_context
         ctx = lookup_models_dev_context(effective_provider, model)
         if ctx:
-            # MiniMax M3: models.dev reports 512K but actual context is 1M.
-            # Prefer hardcoded catalog over stale probe value.
-            if _model_name_suggests_minimax_m3(model):
-                catalog = DEFAULT_CONTEXT_LENGTHS.get("minimax-m3")
-                if catalog and ctx < catalog:
-                    logger.info(
-                        "Rejecting models.dev context=%s for %r "
-                        "(MiniMax-M3 underreport); using hardcoded default %s",
-                        ctx, model, f"{catalog:,}",
-                    )
-                    ctx = catalog
             return ctx
 
     # 6. OpenRouter live API metadata — provider-unaware fallback.

agent/prompt_builder.py

@@ -885,22 +885,6 @@ def build_environment_hints() -> str:
                 f"`uname -a && whoami && pwd`."
             )
 
-    # Hermes desktop GUI — any agent running under the desktop app should know
-    # it. HERMES_DESKTOP marks the backend powering the chat; HERMES_DESKTOP_TERMINAL
-    # marks a hermes launched in the embedded terminal pane. Both set by main.cjs.
-    _truthy = ("1", "true", "yes")
-    _in_desktop = (os.getenv("HERMES_DESKTOP") or "").strip().lower() in _truthy
-    _in_desktop_term = (os.getenv("HERMES_DESKTOP_TERMINAL") or "").strip().lower() in _truthy
-    if _in_desktop or _in_desktop_term:
-        _desktop_hint = "Runtime surface: you're running inside the Hermes desktop GUI app."
-        if _in_desktop_term:
-            _desktop_hint += (
-                " You're in its embedded terminal pane, beside the GUI chat — the user can "
-                "select your output (⌥-drag on macOS, Shift-drag elsewhere) and press "
-                "⌘/Ctrl+L to send it to the chat composer."
-            )
-        hints.append(_desktop_hint)
-
     if is_wsl():
         hints.append(WSL_ENVIRONMENT_HINT)
 
@@ -1101,12 +1085,11 @@ def _skill_should_show(
 def build_skills_system_prompt(
     available_tools: "set[str] | None" = None,
     available_toolsets: "set[str] | None" = None,
-    compact_categories: "frozenset[str] | None" = None,
 ) -> str:
     """Build a compact skill index for the system prompt.
 
     Two-layer cache:
-      1. In-process LRU dict keyed by (skills_dir, tools, toolsets, hidden)
+      1. In-process LRU dict keyed by (skills_dir, tools, toolsets)
       2. Disk snapshot (``.skills_prompt_snapshot.json``) validated by
          mtime/size manifest — survives process restarts
 
@@ -1116,12 +1099,6 @@ def build_skills_system_prompt(
     scanned alongside the local ``~/.hermes/skills/`` directory.  External dirs
     are read-only — they appear in the index but new skills are always created
     in the local dir.  Local skills take precedence when names collide.
-
-    ``compact_categories`` (e.g. from the coding posture — see
-    agent/coding_context.py) demotes whole categories to a names-only line in
-    the rendered index. Nothing is ever hidden: every skill name stays
-    visible and loadable via ``skill_view`` / ``skills_list``; only the
-    descriptions are dropped, and a footer note explains the demotion.
     """
     skills_dir = get_skills_dir()
     external_dirs = get_all_skills_dirs()[1:]  # skip local (index 0)
@@ -1146,7 +1123,6 @@ def build_skills_system_prompt(
         tuple(sorted(str(ts) for ts in (available_toolsets or set()))),
         _platform_hint,
         tuple(sorted(disabled)),
-        tuple(sorted(compact_categories or ())),
     )
     with _SKILLS_PROMPT_CACHE_LOCK:
         cached = _SKILLS_PROMPT_CACHE.get(cache_key)
@@ -1280,44 +1256,18 @@ def build_skills_system_prompt(
             except Exception as e:
                 logger.debug("Could not read external skill description %s: %s", desc_file, e)
 
-    # Posture-driven category demotion (e.g. non-coding skills while pairing
-    # on code). Demoted categories stay in the index as a single names-only
-    # line — descriptions are dropped to cut noise, but every skill name
-    # remains visible so memory-anchored recall ("load <name>") keeps working.
-    # NEVER remove entries entirely: agent-created skills are the model's
-    # project memory, and models don't reach for skills_list to rediscover
-    # what the index stops showing them. Match on the top-level category
-    # segment so nested categories ("social-media/twitter") are demoted with
-    # their parent.
-    demoted = frozenset(
-        cat for cat in skills_by_category
-        if cat.split("/", 1)[0] in (compact_categories or frozenset())
-    )
-
-    hidden_note = ""
-    if demoted:
-        hidden_note = (
-            "\n(Categories marked [names only] are outside the current coding "
-            "context, so their descriptions are omitted — the skills work "
-            "normally and load with skill_view(name) as usual.)"
-        )
-
     if not skills_by_category:
         result = ""
     else:
         index_lines = []
         for category in sorted(skills_by_category.keys()):
-            # Deduplicate and sort skills within each category
-            seen = set()
-            if category in demoted:
-                names = sorted({name for name, _ in skills_by_category[category]})
-                index_lines.append(f"  {category} [names only]: {', '.join(names)}")
-                continue
             cat_desc = category_descriptions.get(category, "")
             if cat_desc:
                 index_lines.append(f"  {category}: {cat_desc}")
             else:
                 index_lines.append(f"  {category}:")
+            # Deduplicate and sort skills within each category
+            seen = set()
             for name, desc in sorted(skills_by_category[category], key=lambda x: x[0]):
                 if name in seen:
                     continue
@@ -1354,7 +1304,6 @@ def build_skills_system_prompt(
             "</available_skills>\n"
             "\n"
             "Only proceed without loading a skill if genuinely none are relevant to the task."
-            + hidden_note
         )
 
     # ── Store in LRU cache ────────────────────────────────────────────

agent/secret_sources/bitwarden.py

@@ -274,7 +274,6 @@ def _platform_asset_name() -> str:
                 capture_output=True,
                 text=True,
                 timeout=2,
-                stdin=subprocess.DEVNULL,
             )
             if "musl" in (res.stdout + res.stderr).lower():
                 libc = "musl"
@@ -526,7 +525,6 @@ def _run_bws_list(
             capture_output=True,
             text=True,
             timeout=_BWS_RUN_TIMEOUT,
-            stdin=subprocess.DEVNULL,
         )
     except subprocess.TimeoutExpired as exc:
         raise RuntimeError(

agent/skill_preprocessing.py

@@ -74,7 +74,6 @@ def run_inline_shell(command: str, cwd: Path | None, timeout: int) -> str:
             text=True,
             timeout=max(1, int(timeout)),
             check=False,
-            stdin=subprocess.DEVNULL,
         )
     except subprocess.TimeoutExpired:
         return f"[inline-shell timeout after {timeout}s: {command}]"

agent/system_prompt.py

@@ -191,23 +191,9 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
             )
             if toolset
         }
-        # Focus mode (opt-in) demotes non-coding skill categories to
-        # names-only in the index (never hidden — skill_view/skills_list
-        # reach everything, and every name stays visible for recall). The
-        # default coding posture leaves the index untouched.
-        _compact_cats = frozenset()
-        try:
-            from agent.coding_context import coding_compact_skill_categories
-
-            _compact_cats = coding_compact_skill_categories(
-                platform=agent.platform, cwd=resolve_context_cwd()
-            )
-        except Exception:
-            _compact_cats = frozenset()
         skills_prompt = _r.build_skills_system_prompt(
             available_tools=agent.valid_tool_names,
             available_toolsets=avail_toolsets,
-            compact_categories=_compact_cats or None,
         )
     else:
         skills_prompt = ""
@@ -235,26 +221,6 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
     if _env_hints:
         stable_parts.append(_env_hints)
 
-    # Coding posture (base Hermes, any interactive coding surface in a code
-    # workspace — see agent/coding_context.py). The operating brief + the live
-    # git/workspace snapshot are built once here and cached for the session;
-    # the snapshot is never re-probed per turn (that would break the prompt
-    # cache), so the brief tells the model to re-check git before relying on it.
-    if agent.valid_tool_names:
-        try:
-            from agent.coding_context import coding_system_blocks
-
-            stable_parts.extend(
-                coding_system_blocks(
-                    platform=agent.platform,
-                    cwd=resolve_context_cwd(),
-                    model=agent.model,
-                )
-            )
-        except Exception:
-            # Coding-context probing must never block prompt build.
-            pass
-
     # Local Python toolchain probe — names python/pip/uv/PEP-668 state when
     # something is non-default so the model can pick the right install
     # strategy without discovering by failure.  Emits a single line; emits

agent/tool_executor.py

@@ -417,7 +417,7 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
 
     # ── Logging / callbacks ──────────────────────────────────────────
     tool_names_str = ", ".join(name for _, name, _, _, _, _ in parsed_calls)
-    if not agent.quiet_mode and getattr(agent, "tool_progress_mode", "all") != "off":
+    if not agent.quiet_mode:
         print(f"  ⚡ Concurrent: {num_tools} tool calls — {tool_names_str}")
         for i, (tc, name, args, middleware_trace, block_result, blocked_by_guardrail) in enumerate(parsed_calls, 1):
             args_str = json.dumps(args, ensure_ascii=False)
@@ -702,7 +702,7 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
         if agent._should_emit_quiet_tool_messages():
             cute_msg = _get_cute_tool_message_impl(name, args, tool_duration, result=function_result)
             agent._safe_print(f"  {cute_msg}")
-        elif not agent.quiet_mode and getattr(agent, "tool_progress_mode", "all") != "off":
+        elif getattr(agent, "tool_progress_mode", "all") != "off":
             _preview_str = _multimodal_text_summary(function_result)
             if agent.verbose_logging:
                 print(f"  ✅ Tool {i+1} completed in {tool_duration:.2f}s")
@@ -866,7 +866,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
         elif function_name == "skill_manage":
             agent._iters_since_skill = 0
 
-        if not agent.quiet_mode and getattr(agent, "tool_progress_mode", "all") != "off":
+        if not agent.quiet_mode:
             args_str = json.dumps(function_args, ensure_ascii=False)
             if agent.verbose_logging:
                 print(f"  📞 Tool {i}: {function_name}({list(function_args.keys())})")
@@ -1065,25 +1065,6 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
             tool_duration = time.time() - tool_start_time
             if agent._should_emit_quiet_tool_messages():
                 agent._vprint(f"  {_get_cute_tool_message_impl('clarify', function_args, tool_duration, result=function_result)}")
-        elif function_name == "read_terminal":
-            def _execute(next_args: dict) -> Any:
-                from tools.read_terminal_tool import read_terminal_tool as _read_terminal_tool
-                return _read_terminal_tool(
-                    start_line=next_args.get("start_line"),
-                    count=next_args.get("count"),
-                    callback=getattr(agent, "read_terminal_callback", None),
-                )
-            function_result, function_args = _run_agent_tool_execution_middleware(
-                agent,
-                function_name=function_name,
-                function_args=function_args,
-                effective_task_id=effective_task_id,
-                tool_call_id=getattr(tool_call, "id", "") or "",
-                execute=_execute,
-            )
-            tool_duration = time.time() - tool_start_time
-            if agent._should_emit_quiet_tool_messages():
-                agent._vprint(f"  {_get_cute_tool_message_impl('read_terminal', function_args, tool_duration, result=function_result)}")
         elif function_name == "delegate_task":
             tasks_arg = function_args.get("tasks")
             if tasks_arg and isinstance(tasks_arg, list):
@@ -1384,7 +1365,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
         # entire batch.  The model sees it on the next API iteration.
         agent._apply_pending_steer_to_tool_results(messages, 1)
 
-        if not agent.quiet_mode and getattr(agent, "tool_progress_mode", "all") != "off":
+        if not agent.quiet_mode:
             if agent.verbose_logging:
                 print(f"  ✅ Tool {i} completed in {tool_duration:.2f}s")
                 print(agent._wrap_verbose("Result: ", function_result))

agent/transports/anthropic.py

@@ -84,7 +84,7 @@ class AnthropicTransport(ProviderTransport):
         to OpenAI finish_reason, and collects reasoning_details in provider_data.
         """
         import json
-        from agent.anthropic_adapter import _to_plain_data, _sanitize_replay_block
+        from agent.anthropic_adapter import _to_plain_data
         from agent.transports.types import ToolCall
 
         strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
@@ -94,40 +94,14 @@ class AnthropicTransport(ProviderTransport):
         reasoning_parts = []
         reasoning_details = []
         tool_calls = []
-        # Verbatim, order-preserving copy of every content block in the turn.
-        # Anthropic signs each thinking block against the turn content that
-        # PRECEDES it at its position; when a turn interleaves thinking and
-        # tool_use (adaptive/interleaved thinking, Claude 4.6+), the parallel
-        # reasoning_details + tool_calls lists below lose that cross-type
-        # ordering. Replaying the latest assistant message in the wrong order
-        # invalidates the signatures -> HTTP 400 "thinking ... blocks in the
-        # latest assistant message cannot be modified". Preserve the exact
-        # block sequence here so the adapter can replay it unchanged. See
-        # tests/agent/test_anthropic_thinking_block_order.py.
-        ordered_blocks = []
 
         for block in response.content:
-            block_dict = _to_plain_data(block)
-            clean_block = None
-            if isinstance(block_dict, dict):
-                # Sanitize at capture so output-only SDK fields (parsed_output,
-                # caller, citations=None, …) never persist to state.db and leak
-                # back as request input on replay → HTTP 400 "Extra inputs are
-                # not permitted". Defence-in-depth with the replay-side sanitize.
-                clean_block = _sanitize_replay_block(block_dict)
-                if clean_block is not None:
-                    ordered_blocks.append(clean_block)
             if block.type == "text":
                 text_parts.append(block.text)
-            elif block.type in ("thinking", "redacted_thinking"):
-                if block.type == "thinking":
-                    reasoning_parts.append(block.thinking)
-                # Use the sanitized block (clean_block) for reasoning_details too,
-                # since _extract_preserved_thinking_blocks replays these on the
-                # non-ordered path. Falls back to raw only if sanitize dropped it.
-                if isinstance(clean_block, dict):
-                    reasoning_details.append(clean_block)
-                elif isinstance(block_dict, dict):
+            elif block.type == "thinking":
+                reasoning_parts.append(block.thinking)
+                block_dict = _to_plain_data(block)
+                if isinstance(block_dict, dict):
                     reasoning_details.append(block_dict)
             elif block.type == "tool_use":
                 name = block.name
@@ -156,23 +130,6 @@ class AnthropicTransport(ProviderTransport):
         provider_data = {}
         if reasoning_details:
             provider_data["reasoning_details"] = reasoning_details
-        # Only worth carrying the ordered-blocks channel when the turn
-        # actually interleaves signed thinking with tool_use — that's the
-        # only shape the parallel lists reconstruct incorrectly. A turn that
-        # is purely text, or thinking-then-tools with a single leading
-        # thinking block, replays correctly without it.
-        _has_signed_thinking = any(
-            isinstance(b, dict)
-            and b.get("type") in ("thinking", "redacted_thinking")
-            and (b.get("signature") or b.get("data"))
-            for b in ordered_blocks
-        )
-        _has_tool_use = any(
-            isinstance(b, dict) and b.get("type") == "tool_use"
-            for b in ordered_blocks
-        )
-        if _has_signed_thinking and _has_tool_use:
-            provider_data["anthropic_content_blocks"] = ordered_blocks
 
         return NormalizedResponse(
             content="\n".join(text_parts) if text_parts else None,

agent/transports/codex_app_server.py

@@ -378,7 +378,6 @@ def check_codex_binary(
             capture_output=True,
             text=True,
             timeout=10,
-            stdin=subprocess.DEVNULL,
         )
     except FileNotFoundError:
         return False, (

agent/transports/codex_app_server_session.py

@@ -72,9 +72,6 @@ class TurnResult:
     error: Optional[str] = None  # Set if turn ended in a non-recoverable error
     turn_id: Optional[str] = None
     thread_id: Optional[str] = None
-    token_usage_last: Optional[dict[str, Any]] = None
-    token_usage_total: Optional[dict[str, Any]] = None
-    model_context_window: Optional[int] = None
     # Hint to the caller that the underlying codex subprocess is likely
     # wedged (turn-level timeout fired, post-tool watchdog tripped, or
     # token-refresh failure killed the child). The caller should retire
@@ -504,7 +501,6 @@ class CodexAppServerSession:
                     pending = self._client.take_notification(timeout=0)
                     if pending is None:
                         break
-                    _apply_token_usage_notification(result, pending)
                     self._track_pending_file_change(pending)
                     proj = projector.project(pending)
                     if proj.messages:
@@ -540,8 +536,6 @@ class CodexAppServerSession:
                 except Exception:  # pragma: no cover - display callback
                     logger.debug("on_event callback raised", exc_info=True)
 
-            _apply_token_usage_notification(result, note)
-
             # Track in-progress fileChange items so the approval bridge
             # can surface a real change summary when codex requests
             # approval (the approval params themselves don't carry the
@@ -808,30 +802,6 @@ class CodexAppServerSession:
         return cached
 
 
-def _apply_token_usage_notification(result: TurnResult, note: dict) -> None:
-    """Capture Codex app-server token usage updates for caller accounting.
-
-    Codex does not put token usage on turn/completed. It emits a separate
-    thread/tokenUsage/updated notification containing cumulative totals and
-    the latest turn breakdown.
-    """
-    if not isinstance(note, dict) or note.get("method") != "thread/tokenUsage/updated":
-        return
-    params = note.get("params") or {}
-    token_usage = params.get("tokenUsage") or {}
-    if not isinstance(token_usage, dict):
-        return
-    last = token_usage.get("last")
-    total = token_usage.get("total")
-    if isinstance(last, dict):
-        result.token_usage_last = dict(last)
-    if isinstance(total, dict):
-        result.token_usage_total = dict(total)
-    window = token_usage.get("modelContextWindow")
-    if isinstance(window, int) and window > 0:
-        result.model_context_window = window
-
-
 def _approval_choice_to_codex_decision(choice: str) -> str:
     """Map Hermes approval choices onto codex's CommandExecutionApprovalDecision
     / FileChangeApprovalDecision wire values.

agent/transports/types.py

@@ -121,18 +121,6 @@ class NormalizedResponse:
         pd = self.provider_data or {}
         return pd.get("reasoning_details")
 
-    @property
-    def anthropic_content_blocks(self):
-        """Verbatim, order-preserving Anthropic content blocks for a turn.
-
-        Present only when an Anthropic turn interleaves signed thinking with
-        tool_use — the one shape the parallel reasoning_details + tool_calls
-        lists reconstruct in the wrong order, invalidating thinking-block
-        signatures on replay. See agent/transports/anthropic.py.
-        """
-        pd = self.provider_data or {}
-        return pd.get("anthropic_content_blocks")
-
     @property
     def codex_reasoning_items(self):
         pd = self.provider_data or {}

agent/usage_pricing.py

@@ -13,7 +13,6 @@ DEFAULT_PRICING = {"input": 0.0, "output": 0.0}
 
 _ZERO = Decimal("0")
 _ONE_MILLION = Decimal("1000000")
-_NOUS_DEFAULT_BASE_URL = "https://inference-api.nousresearch.com/v1"
 
 CostStatus = Literal["actual", "estimated", "included", "unknown"]
 CostSource = Literal[
@@ -571,8 +570,6 @@ def resolve_billing_route(
         return BillingRoute(provider="openai-codex", model=model, base_url=base_url or "", billing_mode="subscription_included")
     if provider_name == "openrouter" or base_url_host_matches(base_url or "", "openrouter.ai"):
         return BillingRoute(provider="openrouter", model=model, base_url=base_url or "", billing_mode="official_models_api")
-    if provider_name == "nous" or base_url_host_matches(base_url or "", "inference-api.nousresearch.com"):
-        return BillingRoute(provider="nous", model=model, base_url=base_url or _NOUS_DEFAULT_BASE_URL, billing_mode="official_models_api")
     if provider_name == "anthropic":
         return BillingRoute(provider="anthropic", model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
     if provider_name == "openai":

apps/bootstrap-installer/package.json

@@ -11,8 +11,7 @@
     "tauri": "tauri",
     "tauri:dev": "tauri dev",
     "tauri:build": "tauri build",
-    "tauri:build:debug": "tauri build --debug",
-    "typecheck": "tsc -p . --noEmit"
+    "tauri:build:debug": "tauri build --debug"
   },
   "dependencies": {
     "@nous-research/ui": "0.16.0",
@@ -41,7 +40,7 @@
     "@types/react": "^19.2.14",
     "@types/react-dom": "^19.2.3",
     "@vitejs/plugin-react": "^5.2.0",
-    "typescript": "^6.0.3",
+    "typescript": "~5.9.3",
     "vite": "^7.3.1"
   }
 }

apps/bootstrap-installer/tsconfig.json

@@ -16,8 +16,9 @@
     "noUnusedParameters": true,
     "esModuleInterop": true,
     "noFallthroughCasesInSwitch": true,
+    "baseUrl": ".",
     "paths": {
-      "@/*": ["./src/*"]
+      "@/*": ["src/*"]
     }
   },
   "include": ["src"],

apps/desktop/README.md

@@ -93,7 +93,7 @@ Run before opening a PR (lint may surface pre-existing warnings but must exit cl
 
 ```bash
 npm run fix
-npm run typecheck
+npm run type-check
 npm run lint
 npm run test:desktop:all
 ```

apps/desktop/electron/bootstrap-runner.cjs

@@ -40,15 +40,6 @@ const path = require('node:path')
 const https = require('node:https')
 const { spawn } = require('node:child_process')
 
-const IS_WINDOWS = process.platform === 'win32'
-
-function hiddenWindowsChildOptions(options = {}) {
-  if (!IS_WINDOWS || Object.prototype.hasOwnProperty.call(options, 'windowsHide')) {
-    return options
-  }
-  return { ...options, windowsHide: true }
-}
-
 const STAMP_COMMIT_RE = /^[0-9a-f]{7,40}$/i
 
 // Stages flagged needs_user_input=true in the manifest are skipped by the
@@ -293,7 +284,7 @@ function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, herme
     const ps = process.platform === 'win32' ? resolveWindowsPowerShell() : 'pwsh'
     const fullArgs = ['-NoProfile', '-ExecutionPolicy', 'Bypass', '-File', scriptPath, ...args]
 
-    const child = spawn(ps, fullArgs, hiddenWindowsChildOptions({
+    const child = spawn(ps, fullArgs, {
       stdio: ['ignore', 'pipe', 'pipe'],
       env: {
         ...process.env,
@@ -301,7 +292,7 @@ function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, herme
         // choice rather than re-computing the default.
         HERMES_HOME: hermesHome || process.env.HERMES_HOME || ''
       }
-    }))
+    })
 
     let stdout = ''
     let stderr = ''

apps/desktop/electron/fs-read-dir.cjs

@@ -1,109 +0,0 @@
-'use strict'
-
-const fs = require('node:fs')
-const path = require('node:path')
-const { resolveDirectoryForIpc } = require('./hardening.cjs')
-
-const FS_READDIR_STAT_CONCURRENCY = 16
-
-// Always-hidden noise (covers non-git projects too; gitignore catches many of
-// these, but the project tree should keep the same hygiene without one).
-const FS_READDIR_HIDDEN = new Set([
-  '.git',
-  '.hg',
-  '.svn',
-  '.cache',
-  '.next',
-  '.turbo',
-  '.venv',
-  '__pycache__',
-  'build',
-  'dist',
-  'node_modules',
-  'target',
-  'venv'
-])
-
-function direntIsDirectory(dirent) {
-  return typeof dirent.isDirectory === 'function' && dirent.isDirectory()
-}
-
-function direntIsFile(dirent) {
-  return typeof dirent.isFile === 'function' && dirent.isFile()
-}
-
-function direntIsSymbolicLink(dirent) {
-  return typeof dirent.isSymbolicLink === 'function' && dirent.isSymbolicLink()
-}
-
-function shouldStatDirent(dirent) {
-  if (direntIsDirectory(dirent)) return false
-
-  return direntIsSymbolicLink(dirent) || !direntIsFile(dirent)
-}
-
-async function entryForDirent(dirent, resolved, fsImpl) {
-  const fullPath = path.join(resolved, dirent.name)
-  let isDirectory = direntIsDirectory(dirent)
-
-  if (!isDirectory && shouldStatDirent(dirent)) {
-    try {
-      isDirectory = (await fsImpl.promises.stat(fullPath)).isDirectory()
-    } catch {
-      isDirectory = false
-    }
-  }
-
-  return { name: dirent.name, path: fullPath, isDirectory }
-}
-
-async function mapWithStatConcurrency(items, mapper) {
-  const results = new Array(items.length)
-  let nextIndex = 0
-
-  async function runWorker() {
-    while (nextIndex < items.length) {
-      const index = nextIndex
-      nextIndex += 1
-      results[index] = await mapper(items[index])
-    }
-  }
-
-  const workerCount = Math.min(FS_READDIR_STAT_CONCURRENCY, items.length)
-  const workers = Array.from({ length: workerCount }, () => runWorker())
-  await Promise.all(workers)
-
-  return results
-}
-
-async function readDirForIpc(dirPath, options = {}) {
-  const fsImpl = options.fs || fs
-  let resolved
-
-  try {
-    ;({ resolvedPath: resolved } = await resolveDirectoryForIpc(dirPath, {
-      fs: fsImpl,
-      purpose: 'Directory read'
-    }))
-  } catch (error) {
-    return { entries: [], error: error?.code || 'read-error' }
-  }
-
-  try {
-    const dirents = await fsImpl.promises.readdir(resolved, { withFileTypes: true })
-    const visibleDirents = dirents.filter(dirent => !FS_READDIR_HIDDEN.has(dirent.name))
-    const entries = await mapWithStatConcurrency(visibleDirents, dirent =>
-      entryForDirent(dirent, resolved, fsImpl)
-    )
-
-    entries.sort((a, b) => Number(b.isDirectory) - Number(a.isDirectory) || a.name.localeCompare(b.name))
-
-    return { entries }
-  } catch (error) {
-    return { entries: [], error: error?.code || 'read-error' }
-  }
-}
-
-module.exports = {
-  readDirForIpc
-}

apps/desktop/electron/fs-read-dir.test.cjs

@@ -1,364 +0,0 @@
-'use strict'
-
-const assert = require('node:assert/strict')
-const fs = require('node:fs')
-const os = require('node:os')
-const path = require('node:path')
-const test = require('node:test')
-const { pathToFileURL } = require('node:url')
-
-const { readDirForIpc } = require('./fs-read-dir.cjs')
-
-function mkTmpDir() {
-  return fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-fs-read-dir-'))
-}
-
-function fakeDirent(name, flags = {}) {
-  return {
-    name,
-    isDirectory: () => Boolean(flags.directory),
-    isFile: () => Boolean(flags.file),
-    isSymbolicLink: () => Boolean(flags.symlink)
-  }
-}
-
-test('readDirForIpc hides noisy directories and files from the project tree', async () => {
-  const root = mkTmpDir()
-
-  try {
-    fs.mkdirSync(path.join(root, 'node_modules'))
-    fs.mkdirSync(path.join(root, 'src'))
-    fs.writeFileSync(path.join(root, 'target'), 'hidden file')
-    fs.writeFileSync(path.join(root, 'README.md'), 'visible file')
-
-    const result = await readDirForIpc(root)
-
-    assert.equal(result.error, undefined)
-    assert.deepEqual(
-      result.entries.map(entry => entry.name),
-      ['src', 'README.md']
-    )
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc filters a hidden basename whether it is a file or directory', async () => {
-  const dirRoot = mkTmpDir()
-  const fileRoot = mkTmpDir()
-
-  try {
-    fs.mkdirSync(path.join(dirRoot, 'node_modules'))
-    fs.writeFileSync(path.join(dirRoot, 'visible.txt'), 'visible')
-    fs.writeFileSync(path.join(fileRoot, 'node_modules'), 'hidden file')
-    fs.writeFileSync(path.join(fileRoot, 'visible.txt'), 'visible')
-
-    assert.deepEqual(
-      (await readDirForIpc(dirRoot)).entries.map(entry => entry.name),
-      ['visible.txt']
-    )
-    assert.deepEqual(
-      (await readDirForIpc(fileRoot)).entries.map(entry => entry.name),
-      ['visible.txt']
-    )
-  } finally {
-    fs.rmSync(dirRoot, { recursive: true, force: true })
-    fs.rmSync(fileRoot, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc returns directories before files and sorts by name within groups', async () => {
-  const root = mkTmpDir()
-
-  try {
-    fs.writeFileSync(path.join(root, 'z.txt'), 'z')
-    fs.mkdirSync(path.join(root, 'src'))
-    fs.writeFileSync(path.join(root, 'a.txt'), 'a')
-    fs.mkdirSync(path.join(root, 'lib'))
-
-    const result = await readDirForIpc(root)
-
-    assert.equal(result.error, undefined)
-    assert.deepEqual(
-      result.entries.map(entry => entry.name),
-      ['lib', 'src', 'a.txt', 'z.txt']
-    )
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc accepts file URLs for directories', async () => {
-  const root = mkTmpDir()
-
-  try {
-    fs.mkdirSync(path.join(root, 'src'))
-    fs.writeFileSync(path.join(root, 'README.md'), 'visible file')
-
-    const result = await readDirForIpc(pathToFileURL(root).toString())
-
-    assert.equal(result.error, undefined)
-    assert.deepEqual(
-      result.entries.map(entry => entry.name),
-      ['src', 'README.md']
-    )
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc returns invalid-path for blank or non-string input', async () => {
-  let readdirCalls = 0
-  const fsImpl = {
-    promises: {
-      readdir: async () => {
-        readdirCalls += 1
-        return []
-      }
-    }
-  }
-
-  assert.deepEqual(await readDirForIpc('', { fs: fsImpl }), { entries: [], error: 'invalid-path' })
-  assert.deepEqual(await readDirForIpc('   ', { fs: fsImpl }), { entries: [], error: 'invalid-path' })
-  assert.deepEqual(await readDirForIpc(null, { fs: fsImpl }), { entries: [], error: 'invalid-path' })
-  assert.equal(readdirCalls, 0)
-})
-
-test('readDirForIpc rejects Windows device paths before readdir', async () => {
-  let readdirCalls = 0
-  const fsImpl = {
-    promises: {
-      readdir: async () => {
-        readdirCalls += 1
-        return []
-      }
-    }
-  }
-
-  assert.deepEqual(await readDirForIpc('\\\\?\\C:\\secret', { fs: fsImpl }), {
-    entries: [],
-    error: 'device-path'
-  })
-  assert.equal(readdirCalls, 0)
-})
-
-test('readDirForIpc returns filesystem error codes instead of throwing', async () => {
-  const root = mkTmpDir()
-
-  try {
-    const result = await readDirForIpc(path.join(root, 'missing'))
-
-    assert.deepEqual(result, { entries: [], error: 'ENOENT' })
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc marks a symlink to a directory as a directory', async t => {
-  const root = mkTmpDir()
-
-  try {
-    fs.mkdirSync(path.join(root, 'actual-dir'))
-
-    try {
-      fs.symlinkSync(path.join(root, 'actual-dir'), path.join(root, 'linked-dir'), 'dir')
-    } catch (error) {
-      if (error?.code === 'EPERM' || error?.code === 'EACCES') {
-        t.skip(`symlink creation is not permitted on this platform (${error.code})`)
-
-        return
-      }
-
-      throw error
-    }
-
-    const result = await readDirForIpc(root)
-    const linked = result.entries.find(entry => entry.name === 'linked-dir')
-
-    assert.equal(result.error, undefined)
-    assert.equal(linked?.isDirectory, true)
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc marks a Windows junction to a directory as a directory', async t => {
-  if (process.platform !== 'win32') {
-    t.skip('junctions are a Windows-specific symlink type')
-
-    return
-  }
-
-  const root = mkTmpDir()
-
-  try {
-    fs.mkdirSync(path.join(root, 'actual-dir'))
-
-    try {
-      fs.symlinkSync(path.join(root, 'actual-dir'), path.join(root, 'junction-dir'), 'junction')
-    } catch (error) {
-      if (error?.code === 'EPERM' || error?.code === 'EACCES') {
-        t.skip(`junction creation is not permitted on this platform (${error.code})`)
-
-        return
-      }
-
-      throw error
-    }
-
-    const result = await readDirForIpc(root)
-    const junction = result.entries.find(entry => entry.name === 'junction-dir')
-
-    assert.equal(result.error, undefined)
-    assert.equal(junction?.isDirectory, true)
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc allows expanding symlink or junction directories outside the project root', async t => {
-  const root = mkTmpDir()
-  const outside = mkTmpDir()
-
-  try {
-    fs.writeFileSync(path.join(outside, 'outside.txt'), 'ok')
-
-    const linkPath = path.join(root, 'outside-link')
-    try {
-      fs.symlinkSync(outside, linkPath, process.platform === 'win32' ? 'junction' : 'dir')
-    } catch (error) {
-      if (error?.code === 'EPERM' || error?.code === 'EACCES') {
-        t.skip(`directory symlink creation is not permitted on this platform (${error.code})`)
-
-        return
-      }
-
-      throw error
-    }
-
-    const result = await readDirForIpc(linkPath)
-
-    assert.equal(result.error, undefined)
-    assert.deepEqual(result.entries, [
-      { name: 'outside.txt', path: path.join(linkPath, 'outside.txt'), isDirectory: false }
-    ])
-  } finally {
-    fs.rmSync(root, { recursive: true, force: true })
-    fs.rmSync(outside, { recursive: true, force: true })
-  }
-})
-
-test('readDirForIpc stats symbolic links and unknown entries without dropping the whole listing', async () => {
-  const input = path.join('virtual-root')
-  const resolved = path.resolve(input)
-  const statCalls = []
-  const fsImpl = {
-    promises: {
-      readdir: async () => [
-        fakeDirent('unknown-entry'),
-        fakeDirent('linked-dir', { symlink: true }),
-        fakeDirent('broken-link', { symlink: true }),
-        fakeDirent('plain.txt', { file: true })
-      ],
-      stat: async fullPath => {
-        if (fullPath === resolved) {
-          return { isDirectory: () => true }
-        }
-
-        statCalls.push(fullPath)
-        if (fullPath.endsWith(`${path.sep}linked-dir`)) {
-          return { isDirectory: () => true }
-        }
-        throw Object.assign(new Error('gone'), { code: 'ENOENT' })
-      }
-    }
-  }
-
-  const result = await readDirForIpc(input, { fs: fsImpl })
-
-  assert.equal(result.error, undefined)
-  assert.deepEqual(
-    statCalls.sort(),
-    [path.join(resolved, 'broken-link'), path.join(resolved, 'linked-dir'), path.join(resolved, 'unknown-entry')].sort()
-  )
-  assert.deepEqual(result.entries, [
-    { name: 'linked-dir', path: path.join(resolved, 'linked-dir'), isDirectory: true },
-    { name: 'broken-link', path: path.join(resolved, 'broken-link'), isDirectory: false },
-    { name: 'plain.txt', path: path.join(resolved, 'plain.txt'), isDirectory: false },
-    { name: 'unknown-entry', path: path.join(resolved, 'unknown-entry'), isDirectory: false }
-  ])
-})
-
-test('readDirForIpc bounds concurrent stats while preserving complete sorted output', async () => {
-  const input = path.join('virtual-root')
-  const resolved = path.resolve(input)
-  const names = Array.from({ length: 105 }, (_, index) => `entry-${String(104 - index).padStart(3, '0')}`)
-  const failedName = 'entry-100'
-  const directoryNames = new Set(names.filter((_, index) => index % 10 === 4))
-  const successfulDirectoryNames = new Set([...directoryNames].filter(name => name !== failedName))
-  const statCalls = []
-  let active = 0
-  let peak = 0
-  let releaseStats
-  let markFirstStatStarted
-  const statsReleased = new Promise(resolve => {
-    releaseStats = resolve
-  })
-  const firstStatStarted = new Promise(resolve => {
-    markFirstStatStarted = resolve
-  })
-  const fsImpl = {
-    promises: {
-      readdir: async () => [
-        fakeDirent('node_modules', { symlink: true }),
-        ...names.map((name, index) => fakeDirent(name, { symlink: index % 2 === 0 }))
-      ],
-      stat: async fullPath => {
-        if (fullPath === resolved) {
-          return { isDirectory: () => true }
-        }
-
-        statCalls.push(fullPath)
-        active += 1
-        peak = Math.max(peak, active)
-        markFirstStatStarted()
-        await statsReleased
-        active -= 1
-
-        const name = path.basename(fullPath)
-        if (name === failedName) {
-          throw Object.assign(new Error('gone'), { code: 'ENOENT' })
-        }
-
-        return { isDirectory: () => successfulDirectoryNames.has(name) }
-      }
-    }
-  }
-
-  const resultPromise = readDirForIpc(input, { fs: fsImpl })
-  await firstStatStarted
-  await new Promise(resolve => setImmediate(resolve))
-  releaseStats()
-  const result = await resultPromise
-
-  const expectedNames = [
-    ...names.filter(name => successfulDirectoryNames.has(name)).sort(),
-    ...names.filter(name => !successfulDirectoryNames.has(name)).sort()
-  ]
-
-  assert.equal(result.error, undefined)
-  assert.equal(result.entries.length, names.length)
-  assert.equal(statCalls.length, names.length)
-  assert.equal(statCalls.some(fullPath => fullPath.endsWith(`${path.sep}node_modules`)), false)
-  assert.ok(peak > 1, `expected concurrent stats, observed peak ${peak}`)
-  assert.ok(peak <= 16, `expected at most 16 concurrent stats, observed peak ${peak}`)
-  assert.deepEqual(
-    result.entries.map(entry => entry.name),
-    expectedNames
-  )
-  assert.equal(result.entries.find(entry => entry.name === failedName)?.isDirectory, false)
-  assert.equal(
-    result.entries.filter(entry => entry.isDirectory).length,
-    successfulDirectoryNames.size
-  )
-})

apps/desktop/electron/git-root.cjs

@@ -1,54 +0,0 @@
-'use strict'
-
-const fs = require('node:fs')
-const path = require('node:path')
-const { resolveRequestedPathForIpc } = require('./hardening.cjs')
-
-function findGitRoot(start, fsImpl = fs) {
-  let dir = start
-
-  for (let i = 0; i < 50; i += 1) {
-    try {
-      if (fsImpl.existsSync(path.join(dir, '.git'))) {
-        return dir
-      }
-    } catch {
-      return null
-    }
-
-    const parent = path.dirname(dir)
-
-    if (parent === dir) {
-      return null
-    }
-
-    dir = parent
-  }
-
-  return null
-}
-
-async function gitRootForIpc(startPath, options = {}) {
-  const fsImpl = options.fs || fs
-  let resolved
-
-  try {
-    resolved = resolveRequestedPathForIpc(startPath, { purpose: 'Git root' })
-  } catch {
-    return null
-  }
-
-  try {
-    const stat = await fsImpl.promises.stat(resolved)
-    const start = stat.isDirectory() ? resolved : path.dirname(resolved)
-
-    return findGitRoot(start, fsImpl)
-  } catch {
-    return findGitRoot(resolved, fsImpl)
-  }
-}
-
-module.exports = {
-  findGitRoot,
-  gitRootForIpc
-}

apps/desktop/electron/git-root.test.cjs

@@ -1,40 +0,0 @@
-'use strict'
-
-const assert = require('node:assert/strict')
-const fs = require('node:fs')
-const os = require('node:os')
-const path = require('node:path')
-const test = require('node:test')
-const { pathToFileURL } = require('node:url')
-
-const { gitRootForIpc } = require('./git-root.cjs')
-
-function mkTmpDir() {
-  return fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-git-root-'))
-}
-
-test('gitRootForIpc returns null for invalid and device paths', async () => {
-  assert.equal(await gitRootForIpc(''), null)
-  assert.equal(await gitRootForIpc('   '), null)
-  assert.equal(await gitRootForIpc(null), null)
-  assert.equal(await gitRootForIpc('\\\\?\\C:\\secret'), null)
-  assert.equal(await gitRootForIpc('file:///%E0%A4%A'), null)
-})
-
-test('gitRootForIpc resolves directories files missing descendants and file URLs', async t => {
-  const root = mkTmpDir()
-  t.after(() => fs.rmSync(root, { recursive: true, force: true }))
-
-  const gitDir = path.join(root, '.git')
-  const srcDir = path.join(root, 'src')
-  const filePath = path.join(srcDir, 'index.ts')
-  fs.mkdirSync(gitDir)
-  fs.mkdirSync(srcDir)
-  fs.writeFileSync(filePath, 'export {}\n', 'utf8')
-
-  assert.equal(await gitRootForIpc(root), root)
-  assert.equal(await gitRootForIpc(srcDir), root)
-  assert.equal(await gitRootForIpc(filePath), root)
-  assert.equal(await gitRootForIpc(pathToFileURL(filePath).toString()), root)
-  assert.equal(await gitRootForIpc(path.join(srcDir, 'missing.ts')), root)
-})

apps/desktop/electron/hardening.cjs

@@ -106,155 +106,71 @@ function sensitiveFileBlockReason(filePath) {
   return null
 }
 
-function ipcPathError(code, message) {
-  const error = new Error(message)
-  error.code = code
-  return error
-}
-
-function rejectUnsafePathSyntax(filePath, purpose = 'File read') {
-  if (typeof filePath !== 'string') {
-    throw ipcPathError('invalid-path', `${purpose} failed: file path is required.`)
-  }
-
-  const raw = filePath.trim()
+function resolveRequestedFilePath(filePath, baseDir = process.cwd(), purpose = 'File read') {
+  const raw = String(filePath || '').trim()
 
   if (!raw) {
-    throw ipcPathError('invalid-path', `${purpose} failed: file path is required.`)
+    throw new Error(`${purpose} failed: file path is required.`)
   }
 
   if (raw.includes('\0')) {
-    throw ipcPathError('invalid-path', `${purpose} failed: file path is invalid.`)
+    throw new Error(`${purpose} failed: file path is invalid.`)
   }
 
-  const normalized = raw.replace(/\\/g, '/').toLowerCase()
-  if (
-    normalized.startsWith('//?/') ||
-    normalized.startsWith('//./') ||
-    normalized.startsWith('globalroot/device/') ||
-    normalized.includes('/globalroot/device/')
-  ) {
-    throw ipcPathError('device-path', `${purpose} blocked: Windows device paths are not allowed.`)
-  }
-
-  return raw
-}
-
-function resolveRequestedPathForIpc(filePath, options = {}) {
-  const purpose = String(options.purpose || 'File read')
-  const raw = rejectUnsafePathSyntax(filePath, purpose)
-
   if (/^file:/i.test(raw)) {
-    let resolvedPath
     try {
-      const parsed = new URL(raw)
-      if (parsed.protocol !== 'file:') {
-        throw new Error('not a file URL')
-      }
-      resolvedPath = fileURLToPath(parsed)
+      return fileURLToPath(raw)
     } catch {
-      throw ipcPathError('invalid-path', `${purpose} failed: file URL is invalid.`)
+      throw new Error(`${purpose} failed: file URL is invalid.`)
     }
-
-    rejectUnsafePathSyntax(resolvedPath, purpose)
-    return path.resolve(resolvedPath)
   }
 
-  const baseInput = typeof options.baseDir === 'string' && options.baseDir.trim() ? options.baseDir : process.cwd()
-  const safeBaseInput = rejectUnsafePathSyntax(baseInput, purpose)
-  const resolvedBase = path.resolve(safeBaseInput)
-  rejectUnsafePathSyntax(resolvedBase, purpose)
-  const resolvedPath = path.resolve(resolvedBase, raw)
-  rejectUnsafePathSyntax(resolvedPath, purpose)
-
-  return resolvedPath
-}
-
-async function statForIpc(fsImpl, resolvedPath, purpose, typeLabel) {
-  try {
-    return await fsImpl.promises.stat(resolvedPath)
-  } catch (error) {
-    const code = error && typeof error === 'object' ? error.code : ''
-    if (code === 'ENOENT' || code === 'ENOTDIR') {
-      throw ipcPathError(code || 'ENOENT', `${purpose} failed: ${typeLabel} does not exist.`)
-    }
-    throw ipcPathError(code || 'read-error', `${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
-  }
-}
-
-async function realpathForIpc(fsImpl, resolvedPath, purpose) {
-  if (typeof fsImpl.promises.realpath !== 'function') {
-    return resolvedPath
-  }
-
-  try {
-    const realPath = await fsImpl.promises.realpath(resolvedPath)
-    rejectUnsafePathSyntax(realPath, purpose)
-    return realPath
-  } catch (error) {
-    const code = error && typeof error === 'object' ? error.code : ''
-    throw ipcPathError(code || 'read-error', `${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
-  }
-}
-
-function rejectSensitiveFilePath(filePath, purpose) {
-  const blockReason = sensitiveFileBlockReason(filePath)
-  if (blockReason) {
-    throw ipcPathError('sensitive-file', `${purpose} blocked for sensitive file: ${blockReason}`)
-  }
-}
-
-async function resolveDirectoryForIpc(dirPath, options = {}) {
-  const purpose = String(options.purpose || 'Directory read')
-  const fsImpl = options.fs || fs
-  const resolvedPath = resolveRequestedPathForIpc(dirPath, { baseDir: options.baseDir, purpose })
-  const stat = await statForIpc(fsImpl, resolvedPath, purpose, 'directory')
-
-  if (!stat.isDirectory()) {
-    throw ipcPathError('ENOTDIR', `${purpose} failed: path is not a directory.`)
-  }
-
-  const realPath = await realpathForIpc(fsImpl, resolvedPath, purpose)
-
-  return { realPath, resolvedPath, stat }
+  const resolvedBase = path.resolve(String(baseDir || process.cwd()))
+  return path.resolve(resolvedBase, raw)
 }
 
 async function resolveReadableFileForIpc(filePath, options = {}) {
   const purpose = String(options.purpose || 'File read')
-  const fsImpl = options.fs || fs
-  const resolvedPath = resolveRequestedPathForIpc(filePath, { baseDir: options.baseDir, purpose })
+  const resolvedPath = resolveRequestedFilePath(filePath, options.baseDir, purpose)
 
   if (options.blockSensitive !== false) {
-    rejectSensitiveFilePath(resolvedPath, purpose)
+    const blockReason = sensitiveFileBlockReason(resolvedPath)
+    if (blockReason) {
+      throw new Error(`${purpose} blocked for sensitive file: ${blockReason}`)
+    }
   }
 
-  const stat = await statForIpc(fsImpl, resolvedPath, purpose, 'file')
+  let stat
+  try {
+    stat = await fs.promises.stat(resolvedPath)
+  } catch (error) {
+    const code = error && typeof error === 'object' ? error.code : ''
+    if (code === 'ENOENT' || code === 'ENOTDIR') {
+      throw new Error(`${purpose} failed: file does not exist.`)
+    }
+    throw new Error(`${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
+  }
 
   if (stat.isDirectory()) {
-    throw ipcPathError('EISDIR', `${purpose} failed: path points to a directory.`)
+    throw new Error(`${purpose} failed: path points to a directory.`)
   }
 
   if (!stat.isFile()) {
-    throw ipcPathError('EINVAL', `${purpose} failed: only regular files can be read.`)
-  }
-
-  const realPath = await realpathForIpc(fsImpl, resolvedPath, purpose)
-  if (options.blockSensitive !== false) {
-    rejectSensitiveFilePath(realPath, purpose)
+    throw new Error(`${purpose} failed: only regular files can be read.`)
   }
 
   const maxBytes = Number.isFinite(options.maxBytes) && Number(options.maxBytes) > 0 ? Number(options.maxBytes) : null
   if (maxBytes && stat.size > maxBytes) {
-    throw ipcPathError('EFBIG', `${purpose} failed: file is too large (${stat.size} bytes; limit ${maxBytes} bytes).`)
+    throw new Error(`${purpose} failed: file is too large (${stat.size} bytes; limit ${maxBytes} bytes).`)
   }
 
   try {
-    await fsImpl.promises.access(resolvedPath, fs.constants.R_OK)
+    await fs.promises.access(resolvedPath, fs.constants.R_OK)
   } catch {
-    throw ipcPathError('EACCES', `${purpose} failed: file is not readable.`)
+    throw new Error(`${purpose} failed: file is not readable.`)
   }
 
-  return { realPath, resolvedPath, stat }
+  return { resolvedPath, stat }
 }
 
 module.exports = {
@@ -262,10 +178,7 @@ module.exports = {
   DEFAULT_FETCH_TIMEOUT_MS,
   TEXT_PREVIEW_SOURCE_MAX_BYTES,
   encryptDesktopSecret,
-  rejectUnsafePathSyntax,
-  resolveDirectoryForIpc,
   resolveReadableFileForIpc,
-  resolveRequestedPathForIpc,
   resolveTimeoutMs,
   sensitiveFileBlockReason
 }

apps/desktop/electron/hardening.test.cjs

@@ -8,20 +8,11 @@ const { pathToFileURL } = require('node:url')
 const {
   DEFAULT_FETCH_TIMEOUT_MS,
   encryptDesktopSecret,
-  resolveDirectoryForIpc,
   resolveReadableFileForIpc,
-  resolveRequestedPathForIpc,
   resolveTimeoutMs,
   sensitiveFileBlockReason
 } = require('./hardening.cjs')
 
-async function rejectsWithCode(promise, code) {
-  await assert.rejects(promise, error => {
-    assert.equal(error?.code, code)
-    return true
-  })
-}
-
 test('resolveTimeoutMs falls back to defaults and accepts overrides', () => {
   assert.equal(resolveTimeoutMs(undefined), DEFAULT_FETCH_TIMEOUT_MS)
   assert.equal(resolveTimeoutMs(0), DEFAULT_FETCH_TIMEOUT_MS)
@@ -60,52 +51,6 @@ test('sensitiveFileBlockReason blocks obvious secret file patterns', () => {
   assert.match(String(sensitiveFileBlockReason('/tmp/server-cert.pem')), /\.pem/)
 })
 
-test('path helpers reject blank non-string NUL and Windows device syntax', async () => {
-  await rejectsWithCode(resolveReadableFileForIpc('', { purpose: 'File preview' }), 'invalid-path')
-  await rejectsWithCode(resolveReadableFileForIpc('   ', { purpose: 'File preview' }), 'invalid-path')
-  await rejectsWithCode(resolveReadableFileForIpc(null, { purpose: 'File preview' }), 'invalid-path')
-  await rejectsWithCode(resolveReadableFileForIpc(`safe${String.fromCharCode(0)}name.txt`), 'invalid-path')
-
-  const devicePaths = [
-    '\\\\?\\C:\\secret.txt',
-    '\\\\.\\C:\\secret.txt',
-    '\\\\?\\UNC\\server\\share\\secret.txt',
-    'GLOBALROOT/Device/HarddiskVolumeShadowCopy1/secret.txt'
-  ]
-
-  for (const devicePath of devicePaths) {
-    assert.throws(
-      () => resolveRequestedPathForIpc(devicePath, { purpose: 'File preview' }),
-      error => {
-        assert.equal(error?.code, 'device-path')
-        return true
-      }
-    )
-    await rejectsWithCode(resolveReadableFileForIpc(devicePath, { purpose: 'File preview' }), 'device-path')
-  }
-
-  assert.throws(
-    () => resolveRequestedPathForIpc('file:///%E0%A4%A', { purpose: 'File preview' }),
-    error => {
-      assert.equal(error?.code, 'invalid-path')
-      return true
-    }
-  )
-  await rejectsWithCode(resolveReadableFileForIpc('file:///%E0%A4%A', { purpose: 'File preview' }), 'invalid-path')
-})
-
-test('resolveRequestedPathForIpc resolves relative paths from the trimmed base directory', () => {
-  const baseDir = path.join(os.tmpdir(), 'hermes-desktop-base')
-
-  assert.equal(
-    resolveRequestedPathForIpc('notes.txt', {
-      baseDir: `  ${baseDir}  `,
-      purpose: 'File preview'
-    }),
-    path.resolve(baseDir, 'notes.txt')
-  )
-})
-
 test('resolveReadableFileForIpc validates existence type size and sensitivity', async t => {
   const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-desktop-hardening-'))
   t.after(() => fs.rmSync(tempDir, { recursive: true, force: true }))
@@ -126,13 +71,6 @@ test('resolveReadableFileForIpc validates existence type size and sensitivity',
   })
   assert.equal(fromFileUrl.resolvedPath, textPath)
 
-  const spacedPath = path.join(tempDir, 'notes with spaces.txt')
-  fs.writeFileSync(spacedPath, 'space ok', 'utf8')
-  const fromSpacedFileUrl = await resolveReadableFileForIpc(pathToFileURL(spacedPath).toString(), {
-    purpose: 'File preview'
-  })
-  assert.equal(fromSpacedFileUrl.resolvedPath, spacedPath)
-
   await assert.rejects(
     resolveReadableFileForIpc('missing.txt', {
       baseDir: tempDir,
@@ -176,91 +114,3 @@ test('resolveReadableFileForIpc validates existence type size and sensitivity',
   })
   assert.equal(envTemplate.resolvedPath, envTemplatePath)
 })
-
-test('resolveReadableFileForIpc blocks common sensitive files', async t => {
-  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-desktop-sensitive-'))
-  t.after(() => fs.rmSync(tempDir, { recursive: true, force: true }))
-
-  const sshDir = path.join(tempDir, '.ssh')
-  fs.mkdirSync(sshDir)
-
-  const blockedFiles = [
-    path.join(tempDir, '.env'),
-    path.join(tempDir, '.npmrc'),
-    path.join(sshDir, 'id_ed25519'),
-    path.join(tempDir, 'cert.pem'),
-    path.join(tempDir, 'cert.p12'),
-    path.join(tempDir, 'cert.pfx')
-  ]
-
-  for (const filePath of blockedFiles) {
-    fs.writeFileSync(filePath, 'secret', 'utf8')
-    await rejectsWithCode(resolveReadableFileForIpc(filePath, { purpose: 'File preview' }), 'sensitive-file')
-  }
-
-  const allowed = path.join(tempDir, '.env.example')
-  fs.writeFileSync(allowed, 'EXAMPLE_TOKEN=value', 'utf8')
-  assert.equal((await resolveReadableFileForIpc(allowed, { purpose: 'File preview' })).resolvedPath, allowed)
-})
-
-test('resolveReadableFileForIpc blocks symlinks whose realpath is sensitive', async t => {
-  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-desktop-realpath-'))
-  t.after(() => fs.rmSync(tempDir, { recursive: true, force: true }))
-
-  const envPath = path.join(tempDir, '.env')
-  const linkPath = path.join(tempDir, 'safe-name.txt')
-  fs.writeFileSync(envPath, 'SECRET_TOKEN=123', 'utf8')
-
-  try {
-    fs.symlinkSync(envPath, linkPath, 'file')
-  } catch (error) {
-    if (error?.code === 'EPERM' || error?.code === 'EACCES') {
-      t.skip(`symlink creation is not permitted on this platform (${error.code})`)
-      return
-    }
-    throw error
-  }
-
-  await rejectsWithCode(resolveReadableFileForIpc(linkPath, { purpose: 'File preview' }), 'sensitive-file')
-})
-
-test('resolveDirectoryForIpc accepts directories and rejects invalid directory targets', async t => {
-  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-desktop-dir-'))
-  t.after(() => fs.rmSync(tempDir, { recursive: true, force: true }))
-
-  const directory = path.join(tempDir, 'project')
-  const filePath = path.join(tempDir, 'file.txt')
-  fs.mkdirSync(directory)
-  fs.writeFileSync(filePath, 'not a directory', 'utf8')
-
-  const resolved = await resolveDirectoryForIpc(directory)
-  assert.equal(resolved.resolvedPath, directory)
-  assert.equal(resolved.stat.isDirectory(), true)
-
-  await rejectsWithCode(resolveDirectoryForIpc(filePath), 'ENOTDIR')
-  await rejectsWithCode(resolveDirectoryForIpc(path.join(tempDir, 'missing')), 'ENOENT')
-  await rejectsWithCode(resolveDirectoryForIpc('\\\\?\\C:\\secret'), 'device-path')
-})
-
-test('resolveDirectoryForIpc accepts directory symlinks or junctions', async t => {
-  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-desktop-dir-link-'))
-  t.after(() => fs.rmSync(tempDir, { recursive: true, force: true }))
-
-  const directory = path.join(tempDir, 'actual-project')
-  const linkPath = path.join(tempDir, 'linked-project')
-  fs.mkdirSync(directory)
-
-  try {
-    fs.symlinkSync(directory, linkPath, process.platform === 'win32' ? 'junction' : 'dir')
-  } catch (error) {
-    if (error?.code === 'EPERM' || error?.code === 'EACCES') {
-      t.skip(`directory symlink creation is not permitted on this platform (${error.code})`)
-      return
-    }
-    throw error
-  }
-
-  const resolved = await resolveDirectoryForIpc(linkPath)
-  assert.equal(resolved.resolvedPath, linkPath)
-  assert.equal(resolved.stat.isDirectory(), true)
-})

apps/desktop/electron/preload.cjs

@@ -5,7 +5,6 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
   revalidateConnection: () => ipcRenderer.invoke('hermes:connection:revalidate'),
   touchBackend: profile => ipcRenderer.invoke('hermes:backend:touch', profile),
   getGatewayWsUrl: profile => ipcRenderer.invoke('hermes:gateway:ws-url', profile),
-  openSessionWindow: sessionId => ipcRenderer.invoke('hermes:window:openSession', sessionId),
   getBootProgress: () => ipcRenderer.invoke('hermes:boot-progress:get'),
   getConnectionConfig: profile => ipcRenderer.invoke('hermes:connection-config:get', profile),
   saveConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:save', payload),
@@ -42,7 +41,6 @@ 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),
-  sanitizeWorkspaceCwd: cwd => ipcRenderer.invoke('hermes:workspace:sanitize', cwd),
   settings: {
     getDefaultProjectDir: () => ipcRenderer.invoke('hermes:setting:defaultProjectDir:get'),
     setDefaultProjectDir: dir => ipcRenderer.invoke('hermes:setting:defaultProjectDir:set', dir),
@@ -80,12 +78,6 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
     ipcRenderer.on('hermes:open-updates', listener)
     return () => ipcRenderer.removeListener('hermes:open-updates', listener)
   },
-  onDeepLink: callback => {
-    const listener = (_event, payload) => callback(payload)
-    ipcRenderer.on('hermes:deep-link', listener)
-    return () => ipcRenderer.removeListener('hermes:deep-link', listener)
-  },
-  signalDeepLinkReady: () => ipcRenderer.invoke('hermes:deep-link-ready'),
   onWindowStateChanged: callback => {
     const listener = (_event, payload) => callback(payload)
     ipcRenderer.on('hermes:window-state-changed', listener)
@@ -140,9 +132,5 @@ contextBridge.exposeInMainWorld('hermesDesktop', {
       ipcRenderer.on('hermes:updates:progress', listener)
       return () => ipcRenderer.removeListener('hermes:updates:progress', listener)
     }
-  },
-  themes: {
-    fetchMarketplace: id => ipcRenderer.invoke('hermes:vscode-theme:fetch', id),
-    searchMarketplace: query => ipcRenderer.invoke('hermes:vscode-theme:search', query)
   }
 })

apps/desktop/electron/session-windows.cjs

@@ -1,86 +0,0 @@
-// Secondary "session windows" — one extra OS window per chat so a user can
-// work with multiple chats side by side. The pure, Electron-free pieces live
-// here so they can be unit-tested with node --test (mirroring how the rest of
-// electron/*.cjs splits testable logic out of the main.cjs monolith).
-
-const { pathToFileURL } = require('node:url')
-
-// Build the renderer URL for a secondary window. The renderer uses a
-// HashRouter, so the session route lives after the '#'. The `?win=secondary`
-// flag MUST sit in the query string BEFORE the '#': anything after the '#' is
-// treated as the route by HashRouter and would break routeSessionId(). The
-// renderer reads the flag from window.location.search to suppress the install /
-// onboarding overlays and the global session sidebar.
-function buildSessionWindowUrl(sessionId, { devServer, rendererIndexPath } = {}) {
-  const route = `#/${encodeURIComponent(sessionId)}`
-
-  if (devServer) {
-    const base = devServer.endsWith('/') ? devServer.slice(0, -1) : devServer
-
-    return `${base}/?win=secondary${route}`
-  }
-
-  return `${pathToFileURL(rendererIndexPath).toString()}?win=secondary${route}`
-}
-
-// A small registry keyed by sessionId that guarantees one window per chat:
-// opening a session that already has a live window focuses it instead of
-// spawning a duplicate, and a window removes itself from the registry when it
-// closes. The actual BrowserWindow construction is injected (the `factory`) so
-// this module stays free of Electron and is unit-testable.
-function createSessionWindowRegistry() {
-  const windows = new Map()
-
-  function openOrFocus(sessionId, factory) {
-    const key = typeof sessionId === 'string' ? sessionId.trim() : ''
-
-    if (!key) {
-      return null
-    }
-
-    const existing = windows.get(key)
-
-    if (existing && !existing.isDestroyed()) {
-      // Focus-or-create: never duplicate a window for the same chat.
-      if (typeof existing.isMinimized === 'function' && existing.isMinimized()) {
-        existing.restore?.()
-      }
-
-      if (typeof existing.isVisible === 'function' && !existing.isVisible()) {
-        existing.show?.()
-      }
-
-      existing.focus?.()
-
-      return existing
-    }
-
-    const win = factory(key)
-
-    if (!win) {
-      return null
-    }
-
-    windows.set(key, win)
-
-    // Self-cleanup on close so the registry never holds a destroyed window.
-    win.on?.('closed', () => {
-      if (windows.get(key) === win) {
-        windows.delete(key)
-      }
-    })
-
-    return win
-  }
-
-  return {
-    openOrFocus,
-    get: key => windows.get(key),
-    has: key => windows.has(key),
-    get size() {
-      return windows.size
-    }
-  }
-}
-
-module.exports = { buildSessionWindowUrl, createSessionWindowRegistry }

apps/desktop/electron/session-windows.test.cjs

@@ -1,165 +0,0 @@
-const assert = require('node:assert/strict')
-const test = require('node:test')
-
-const { buildSessionWindowUrl, createSessionWindowRegistry } = require('./session-windows.cjs')
-
-// A minimal fake BrowserWindow: tracks listeners + destroyed state and lets a
-// test fire the 'closed' event, mirroring the slice of the Electron API the
-// registry actually touches.
-function makeFakeWindow() {
-  const listeners = {}
-  const calls = { focus: 0, show: 0, restore: 0 }
-  let destroyed = false
-  let minimized = false
-  let visible = true
-
-  return {
-    on(event, handler) {
-      listeners[event] = handler
-
-      return this
-    },
-    emit(event) {
-      listeners[event]?.()
-    },
-    isDestroyed: () => destroyed,
-    destroy() {
-      destroyed = true
-    },
-    isMinimized: () => minimized,
-    setMinimized(value) {
-      minimized = value
-    },
-    isVisible: () => visible,
-    setVisible(value) {
-      visible = value
-    },
-    restore() {
-      calls.restore += 1
-      minimized = false
-    },
-    show() {
-      calls.show += 1
-      visible = true
-    },
-    focus() {
-      calls.focus += 1
-    },
-    calls
-  }
-}
-
-test('buildSessionWindowUrl puts the secondary flag before the hash route (dev server)', () => {
-  const url = buildSessionWindowUrl('abc123', { devServer: 'http://localhost:5173' })
-
-  assert.equal(url, 'http://localhost:5173/?win=secondary#/abc123')
-})
-
-test('buildSessionWindowUrl avoids a double slash when the dev server has a trailing slash', () => {
-  const url = buildSessionWindowUrl('abc123', { devServer: 'http://localhost:5173/' })
-
-  assert.equal(url, 'http://localhost:5173/?win=secondary#/abc123')
-})
-
-test('buildSessionWindowUrl encodes the session id in the hash route', () => {
-  const url = buildSessionWindowUrl('a b/c', { devServer: 'http://localhost:5173' })
-
-  // The query flag must precede the '#' or HashRouter would swallow it as the
-  // route; the id is URL-encoded so slashes/spaces survive routeSessionId().
-  assert.equal(url, 'http://localhost:5173/?win=secondary#/a%20b%2Fc')
-  assert.ok(url.indexOf('?win=secondary') < url.indexOf('#'))
-})
-
-test('buildSessionWindowUrl builds a packaged file URL with the flag before the hash', () => {
-  const url = buildSessionWindowUrl('abc', { rendererIndexPath: '/opt/app/index.html' })
-
-  assert.match(url, /^file:\/\/.*index\.html\?win=secondary#\/abc$/)
-})
-
-test('registry opens one window per session and focuses on re-open', () => {
-  const registry = createSessionWindowRegistry()
-  let built = 0
-  const win = makeFakeWindow()
-  const factory = () => {
-    built += 1
-
-    return win
-  }
-
-  const first = registry.openOrFocus('s1', factory)
-  const second = registry.openOrFocus('s1', factory)
-
-  assert.equal(built, 1, 'factory runs once for the same session')
-  assert.equal(first, second)
-  assert.equal(registry.size, 1)
-  assert.equal(win.calls.focus, 1, 'second open focuses the existing window')
-})
-
-test('registry restores + shows a minimized/hidden window on re-open', () => {
-  const registry = createSessionWindowRegistry()
-  const win = makeFakeWindow()
-  registry.openOrFocus('s1', () => win)
-
-  win.setMinimized(true)
-  win.setVisible(false)
-  registry.openOrFocus('s1', () => win)
-
-  assert.equal(win.calls.restore, 1)
-  assert.equal(win.calls.show, 1)
-  assert.equal(win.calls.focus, 1)
-})
-
-test('registry drops the entry when the window closes', () => {
-  const registry = createSessionWindowRegistry()
-  const win = makeFakeWindow()
-  registry.openOrFocus('s1', () => win)
-  assert.equal(registry.size, 1)
-
-  win.emit('closed')
-
-  assert.equal(registry.size, 0)
-  assert.equal(registry.has('s1'), false)
-})
-
-test('registry rebuilds a fresh window after the previous one was destroyed', () => {
-  const registry = createSessionWindowRegistry()
-  const first = makeFakeWindow()
-  registry.openOrFocus('s1', () => first)
-  first.destroy()
-
-  let built = 0
-  const second = makeFakeWindow()
-  const result = registry.openOrFocus('s1', () => {
-    built += 1
-
-    return second
-  })
-
-  assert.equal(built, 1, 'a destroyed window is replaced, not focused')
-  assert.equal(result, second)
-})
-
-test('registry ignores empty / non-string session ids', () => {
-  const registry = createSessionWindowRegistry()
-  let built = 0
-  const factory = () => {
-    built += 1
-
-    return makeFakeWindow()
-  }
-
-  assert.equal(registry.openOrFocus('', factory), null)
-  assert.equal(registry.openOrFocus('   ', factory), null)
-  assert.equal(registry.openOrFocus(null, factory), null)
-  assert.equal(registry.openOrFocus(42, factory), null)
-  assert.equal(built, 0)
-  assert.equal(registry.size, 0)
-})
-
-test('registry trims the session id before keying', () => {
-  const registry = createSessionWindowRegistry()
-  const win = makeFakeWindow()
-  registry.openOrFocus('  s1  ', () => win)
-
-  assert.equal(registry.has('s1'), true)
-})

apps/desktop/electron/update-remote.cjs

@@ -1,56 +0,0 @@
-/**
- * Pure helpers for choosing a remote URL during passive update checks.
- *
- * A public install can end up with `origin=git@github.com:NousResearch/hermes-agent.git`.
- * If the user's GitHub SSH key is FIDO2/passkey-backed, a background `git fetch
- * origin` triggers an unexplained hardware-touch prompt. For passive checks
- * against the official repo we substitute the public HTTPS `ls-remote` path,
- * which needs no auth and cannot prompt. Active update/apply flows are left
- * unchanged.
- *
- * Extracted from main.cjs so the security-critical remote detection is unit
- * testable without booting Electron (main.cjs requires('electron') at load).
- */
-
-const OFFICIAL_REPO_HTTPS_URL = 'https://github.com/NousResearch/hermes-agent.git'
-const OFFICIAL_REPO_CANONICAL = 'github.com/nousresearch/hermes-agent'
-
-// Normalize common GitHub remote URL forms to `host/owner/repo` (lowercased,
-// no trailing slash, no .git suffix) so SSH and HTTPS forms of the same repo
-// compare equal.
-function canonicalGitHubRemote(url) {
-  if (!url) return ''
-  let value = String(url).trim()
-  if (value.startsWith('git@github.com:')) {
-    value = `github.com/${value.slice('git@github.com:'.length)}`
-  } else if (value.startsWith('ssh://git@github.com/')) {
-    value = `github.com/${value.slice('ssh://git@github.com/'.length)}`
-  } else {
-    try {
-      const parsed = new URL(value)
-      if (parsed.hostname && parsed.pathname) value = `${parsed.hostname}${parsed.pathname}`
-    } catch {
-      // Leave non-URL forms unchanged.
-    }
-  }
-  value = value.trim().replace(/\/+$/, '')
-  if (value.endsWith('.git')) value = value.slice(0, -4)
-  return value.toLowerCase()
-}
-
-function isSshRemote(url) {
-  const value = String(url || '').trim().toLowerCase()
-  return value.startsWith('git@') || value.startsWith('ssh://')
-}
-
-function isOfficialSshRemote(url) {
-  return isSshRemote(url) && canonicalGitHubRemote(url) === OFFICIAL_REPO_CANONICAL
-}
-
-module.exports = {
-  OFFICIAL_REPO_HTTPS_URL,
-  OFFICIAL_REPO_CANONICAL,
-  canonicalGitHubRemote,
-  isSshRemote,
-  isOfficialSshRemote
-}

apps/desktop/electron/update-remote.test.cjs

@@ -1,78 +0,0 @@
-/**
- * Tests for electron/update-remote.cjs — the remote-detection helpers that
- * keep passive update checks off the SSH origin for official installs.
- *
- * Run with: node --test electron/update-remote.test.cjs
- * (Wired into npm test:desktop:platforms in package.json.)
- *
- * Why this matters: a public install can carry
- * origin=git@github.com:NousResearch/hermes-agent.git. A background
- * `git fetch origin` then authenticates over SSH and, with a FIDO2/passkey
- * key, triggers an unexplained hardware-touch prompt. isOfficialSshRemote
- * must reliably recognize the official SSH remote (in every URL form,
- * case-insensitively) so the caller can swap in the anonymous HTTPS path —
- * while NOT misclassifying forks, other hosts, or the HTTPS remote (which
- * never prompts and should keep the normal fetch path).
- */
-
-const test = require('node:test')
-const assert = require('node:assert/strict')
-
-const {
-  OFFICIAL_REPO_HTTPS_URL,
-  OFFICIAL_REPO_CANONICAL,
-  canonicalGitHubRemote,
-  isSshRemote,
-  isOfficialSshRemote
-} = require('./update-remote.cjs')
-
-test('canonicalGitHubRemote normalizes SSH and HTTPS forms to the same value', () => {
-  assert.equal(canonicalGitHubRemote('git@github.com:NousResearch/hermes-agent.git'), OFFICIAL_REPO_CANONICAL)
-  assert.equal(canonicalGitHubRemote('git@github.com:NousResearch/hermes-agent'), OFFICIAL_REPO_CANONICAL)
-  assert.equal(canonicalGitHubRemote('ssh://git@github.com/NousResearch/hermes-agent.git'), OFFICIAL_REPO_CANONICAL)
-  assert.equal(canonicalGitHubRemote('https://github.com/NousResearch/hermes-agent.git'), OFFICIAL_REPO_CANONICAL)
-  // Case-insensitive: an uppercased owner still canonicalizes to the same repo.
-  assert.equal(canonicalGitHubRemote('git@github.com:nousresearch/hermes-agent.git'), OFFICIAL_REPO_CANONICAL)
-  // Trailing slashes are stripped.
-  assert.equal(canonicalGitHubRemote('https://github.com/NousResearch/hermes-agent/'), OFFICIAL_REPO_CANONICAL)
-})
-
-test('canonicalGitHubRemote is empty for falsy input', () => {
-  assert.equal(canonicalGitHubRemote(''), '')
-  assert.equal(canonicalGitHubRemote(null), '')
-  assert.equal(canonicalGitHubRemote(undefined), '')
-})
-
-test('isSshRemote detects scp-like and ssh:// forms only', () => {
-  assert.equal(isSshRemote('git@github.com:NousResearch/hermes-agent.git'), true)
-  assert.equal(isSshRemote('ssh://git@github.com/NousResearch/hermes-agent.git'), true)
-  assert.equal(isSshRemote('https://github.com/NousResearch/hermes-agent.git'), false)
-  assert.equal(isSshRemote(''), false)
-  assert.equal(isSshRemote(null), false)
-})
-
-test('isOfficialSshRemote is true only for the official repo over SSH', () => {
-  assert.equal(isOfficialSshRemote('git@github.com:NousResearch/hermes-agent.git'), true)
-  assert.equal(isOfficialSshRemote('git@github.com:NousResearch/hermes-agent'), true)
-  assert.equal(isOfficialSshRemote('ssh://git@github.com/NousResearch/hermes-agent.git'), true)
-  // Case-insensitive owner/repo match.
-  assert.equal(isOfficialSshRemote('git@github.com:nousresearch/hermes-agent.git'), true)
-})
-
-test('isOfficialSshRemote does NOT match forks, other hosts, or HTTPS', () => {
-  // A fork over SSH belongs to the user — fetching it is their own remote,
-  // not the official upstream, so the SSH-avoidance swap must not apply.
-  assert.equal(isOfficialSshRemote('git@github.com:someuser/hermes-agent.git'), false)
-  // Same repo name on a different host is not the official repo.
-  assert.equal(isOfficialSshRemote('git@gitlab.com:NousResearch/hermes-agent.git'), false)
-  // HTTPS to the official repo never prompts for SSH/FIDO2, so it keeps the
-  // normal fetch path — must not be flagged as an official SSH remote.
-  assert.equal(isOfficialSshRemote('https://github.com/NousResearch/hermes-agent.git'), false)
-  assert.equal(isOfficialSshRemote(''), false)
-  assert.equal(isOfficialSshRemote(null), false)
-})
-
-test('OFFICIAL_REPO_HTTPS_URL canonicalizes to OFFICIAL_REPO_CANONICAL', () => {
-  // Invariant: the URL we substitute in must be the same repo we detect.
-  assert.equal(canonicalGitHubRemote(OFFICIAL_REPO_HTTPS_URL), OFFICIAL_REPO_CANONICAL)
-})

apps/desktop/electron/vscode-marketplace.cjs

@@ -1,331 +0,0 @@
-'use strict'
-
-/**
- * VS Code Marketplace color-theme fetcher (main process).
- *
- * Resolves an extension's latest version via the (undocumented but stable)
- * gallery ExtensionQuery API, downloads the `.vsix` (a zip), and extracts the
- * color-theme JSON files it contributes. No theme code is ever executed — we
- * only read `package.json` + the referenced `*.json` theme files out of the
- * archive and hand their text back to the renderer to convert.
- *
- * Dependency-free on purpose: a `.vsix` is a plain zip, so we parse the central
- * directory and inflate just the entries we need with `zlib`. Avoids pulling a
- * zip library into the desktop bundle for a feature this small.
- */
-
-const https = require('node:https')
-const zlib = require('node:zlib')
-
-const GALLERY_QUERY_URL = 'https://marketplace.visualstudio.com/_apis/public/gallery/extensionquery'
-const VSIX_ASSET_TYPE = 'Microsoft.VisualStudio.Services.VSIXPackage'
-const MAX_VSIX_BYTES = 40 * 1024 * 1024 // 40 MB — themes are tiny; this is paranoia.
-const MAX_REDIRECTS = 5
-const REQUEST_TIMEOUT_MS = 20_000
-
-const ID_RE = /^[\w-]+\.[\w-]+$/
-
-/** Minimal HTTPS helper with redirect-following, timeout, and a size cap. */
-function request(url, { method = 'GET', headers = {}, body = null, maxBytes = MAX_VSIX_BYTES } = {}, redirectsLeft = MAX_REDIRECTS) {
-  return new Promise((resolve, reject) => {
-    const req = https.request(url, { method, headers }, res => {
-      const status = res.statusCode ?? 0
-
-      if (status >= 300 && status < 400 && res.headers.location) {
-        if (redirectsLeft <= 0) {
-          res.resume()
-          reject(new Error('Too many redirects.'))
-
-          return
-        }
-
-        const next = new URL(res.headers.location, url).toString()
-        res.resume()
-        // Redirects to the CDN are plain GETs (drop the POST body).
-        resolve(request(next, { method: 'GET', headers: { 'User-Agent': headers['User-Agent'] }, maxBytes }, redirectsLeft - 1))
-
-        return
-      }
-
-      if (status < 200 || status >= 300) {
-        res.resume()
-        reject(new Error(`Request failed (${status}) for ${url}`))
-
-        return
-      }
-
-      const chunks = []
-      let total = 0
-
-      res.on('data', chunk => {
-        total += chunk.length
-
-        if (total > maxBytes) {
-          req.destroy()
-          reject(new Error('Response exceeded the size limit.'))
-
-          return
-        }
-
-        chunks.push(chunk)
-      })
-      res.on('end', () => resolve(Buffer.concat(chunks)))
-    })
-
-    req.on('error', reject)
-    req.setTimeout(REQUEST_TIMEOUT_MS, () => req.destroy(new Error('Request timed out.')))
-
-    if (body) {
-      req.write(body)
-    }
-
-    req.end()
-  })
-}
-
-/** Resolve `{ displayName, vsixUrl }` for the latest version of `id`. */
-async function resolveExtension(id) {
-  const json = await queryGallery({
-    // FilterType 7 = ExtensionName (the full publisher.extension id).
-    filters: [{ criteria: [{ filterType: 7, value: id }], pageNumber: 1, pageSize: 1 }],
-    // Flags: IncludeFiles | IncludeVersionProperties | IncludeAssetUri |
-    // IncludeCategoryAndTags | IncludeLatestVersionOnly = 914.
-    flags: 914
-  })
-  const extension = json?.results?.[0]?.extensions?.[0]
-
-  if (!extension) {
-    throw new Error(`Extension "${id}" was not found on the Marketplace.`)
-  }
-
-  const version = extension.versions?.[0]
-
-  if (!version) {
-    throw new Error(`Extension "${id}" has no published versions.`)
-  }
-
-  const asset = (version.files ?? []).find(file => file.assetType === VSIX_ASSET_TYPE)
-  const vsixUrl = asset?.source
-
-  if (!vsixUrl) {
-    throw new Error(`Could not find a downloadable package for "${id}".`)
-  }
-
-  return { displayName: extension.displayName || id, vsixUrl }
-}
-
-/** POST an ExtensionQuery payload and return the parsed gallery response. */
-async function queryGallery(payload, { maxBytes = 4 * 1024 * 1024 } = {}) {
-  const body = JSON.stringify(payload)
-  const raw = await request(GALLERY_QUERY_URL, {
-    method: 'POST',
-    headers: {
-      Accept: 'application/json;api-version=3.0-preview.1',
-      'Content-Type': 'application/json',
-      'Content-Length': Buffer.byteLength(body),
-      'User-Agent': 'Hermes-Desktop'
-    },
-    body,
-    maxBytes
-  })
-
-  return JSON.parse(raw.toString('utf8'))
-}
-
-/**
- * Search the Marketplace for color-theme extensions. With an empty query this
- * returns the most-installed themes; with a query it's a full-text search
- * scoped to the Themes category. Returns lightweight cards (no download).
- */
-/**
- * The "Themes" category also contains file-icon and product-icon themes (the
- * gallery has no color-only category). We can't see an extension's actual
- * contributions without downloading it, so filter the obvious icon packs out by
- * tag + name/description. Color themes that also ship icons are rare; worst case
- * a user installs them by exact id from settings.
- */
-function looksLikeIconTheme(extension) {
-  const tags = (extension.tags ?? []).map(tag => String(tag).toLowerCase())
-
-  if (tags.includes('icon-theme') || tags.includes('product-icon-theme')) {
-    return true
-  }
-
-  const text = `${extension.displayName ?? ''} ${extension.shortDescription ?? ''}`.toLowerCase()
-
-  return /\b(icon theme|file icons?|product icons?|icon pack|fileicons)\b/.test(text)
-}
-
-async function searchMarketplaceThemes(query, limit = 20) {
-  const text = String(query || '').trim()
-  const pageSize = Math.min(Math.max(Number(limit) || 20, 1), 50)
-
-  // FilterType: 8=Target, 5=Category, 10=SearchText, 12=ExcludeWithFlags.
-  const criteria = [
-    { filterType: 8, value: 'Microsoft.VisualStudio.Code' },
-    { filterType: 5, value: 'Themes' },
-    { filterType: 12, value: '4096' } // Exclude unpublished (Unpublished = 0x1000).
-  ]
-
-  if (text) {
-    criteria.push({ filterType: 10, value: text })
-  }
-
-  const json = await queryGallery({
-    // Over-fetch so the icon-theme filter below still leaves a full page.
-    filters: [{ criteria, pageNumber: 1, pageSize: Math.min(pageSize * 2, 50), sortBy: 4, sortOrder: 0 }],
-    // IncludeStatistics (0x100) | IncludeLatestVersionOnly (0x200) | IncludeCategoryAndTags (0x4).
-    flags: 772
-  })
-
-  const extensions = json?.results?.[0]?.extensions ?? []
-
-  return extensions
-    .filter(extension => !looksLikeIconTheme(extension))
-    .slice(0, pageSize)
-    .map(extension => {
-      const publisherName = extension.publisher?.publisherName ?? ''
-      const installStat = (extension.statistics ?? []).find(stat => stat.statisticName === 'install')
-
-      return {
-        extensionId: `${publisherName}.${extension.extensionName}`,
-        displayName: extension.displayName || extension.extensionName,
-        publisher: extension.publisher?.displayName || publisherName,
-        description: extension.shortDescription || '',
-        installs: Math.round(installStat?.value ?? 0)
-      }
-    })
-}
-
-// ─── Minimal zip reader ─────────────────────────────────────────────────────
-
-function findEndOfCentralDirectory(buf) {
-  // EOCD signature 0x06054b50, scanning back from the end (comment is rare).
-  for (let i = buf.length - 22; i >= 0; i--) {
-    if (buf.readUInt32LE(i) === 0x06054b50) {
-      return i
-    }
-  }
-
-  throw new Error('Not a valid zip archive (no end-of-central-directory).')
-}
-
-/** Parse the central directory into a name → record map. */
-function readCentralDirectory(buf) {
-  const eocd = findEndOfCentralDirectory(buf)
-  const count = buf.readUInt16LE(eocd + 10)
-  let offset = buf.readUInt32LE(eocd + 16)
-  const records = new Map()
-
-  for (let i = 0; i < count; i++) {
-    if (buf.readUInt32LE(offset) !== 0x02014b50) {
-      break
-    }
-
-    const method = buf.readUInt16LE(offset + 10)
-    const compressedSize = buf.readUInt32LE(offset + 20)
-    const nameLen = buf.readUInt16LE(offset + 28)
-    const extraLen = buf.readUInt16LE(offset + 30)
-    const commentLen = buf.readUInt16LE(offset + 32)
-    const localOffset = buf.readUInt32LE(offset + 42)
-    const name = buf.toString('utf8', offset + 46, offset + 46 + nameLen)
-
-    records.set(name, { method, compressedSize, localOffset })
-    offset += 46 + nameLen + extraLen + commentLen
-  }
-
-  return records
-}
-
-/** Inflate a single entry to a string. */
-function extractEntry(buf, record) {
-  // The local header's name/extra lengths can differ from the central record,
-  // so re-read them here to locate the compressed payload.
-  if (buf.readUInt32LE(record.localOffset) !== 0x04034b50) {
-    throw new Error('Corrupt zip: bad local file header.')
-  }
-
-  const nameLen = buf.readUInt16LE(record.localOffset + 26)
-  const extraLen = buf.readUInt16LE(record.localOffset + 28)
-  const dataStart = record.localOffset + 30 + nameLen + extraLen
-  const data = buf.subarray(dataStart, dataStart + record.compressedSize)
-
-  // 0 = stored, 8 = deflate. Theme files are one or the other.
-  return record.method === 0 ? data.toString('utf8') : zlib.inflateRawSync(data).toString('utf8')
-}
-
-/** Normalize a package.json theme path to its zip entry name. */
-function themeEntryName(themePath) {
-  const clean = String(themePath).replace(/^\.\//, '').replace(/^\//, '')
-
-  return `extension/${clean}`
-}
-
-/** Extract every contributed color theme from a `.vsix` buffer. */
-function extractThemes(vsixBuffer) {
-  const records = readCentralDirectory(vsixBuffer)
-  const pkgRecord = records.get('extension/package.json')
-
-  if (!pkgRecord) {
-    throw new Error('Package manifest missing from the extension.')
-  }
-
-  const pkg = JSON.parse(extractEntry(vsixBuffer, pkgRecord))
-  const contributed = pkg?.contributes?.themes
-
-  if (!Array.isArray(contributed) || contributed.length === 0) {
-    return []
-  }
-
-  const themes = []
-
-  for (const entry of contributed) {
-    if (!entry?.path) {
-      continue
-    }
-
-    const record = records.get(themeEntryName(entry.path))
-
-    if (!record) {
-      continue
-    }
-
-    try {
-      themes.push({
-        label: entry.label || entry.id || pkg.displayName || pkg.name || 'VS Code Theme',
-        uiTheme: entry.uiTheme,
-        contents: extractEntry(vsixBuffer, record)
-      })
-    } catch {
-      // Skip an entry we can't inflate rather than failing the whole install.
-    }
-  }
-
-  return themes
-}
-
-/**
- * Public entry: resolve, download, and extract color themes for `id`
- * (`publisher.extension`). Returns `{ extensionId, displayName, themes }`.
- */
-async function fetchMarketplaceThemes(id) {
-  const trimmed = String(id || '').trim()
-
-  if (!ID_RE.test(trimmed)) {
-    throw new Error('Expected a Marketplace id like "publisher.extension".')
-  }
-
-  const { displayName, vsixUrl } = await resolveExtension(trimmed)
-  const vsix = await request(vsixUrl, { headers: { 'User-Agent': 'Hermes-Desktop' } })
-  const themes = extractThemes(vsix)
-
-  return { extensionId: trimmed, displayName, themes }
-}
-
-module.exports = {
-  fetchMarketplaceThemes,
-  searchMarketplaceThemes,
-  extractThemes,
-  readCentralDirectory,
-  __testing: { themeEntryName, looksLikeIconTheme }
-}

apps/desktop/electron/vscode-marketplace.test.cjs

@@ -1,113 +0,0 @@
-'use strict'
-
-const assert = require('node:assert')
-const test = require('node:test')
-
-const { __testing, extractThemes, readCentralDirectory } = require('./vscode-marketplace.cjs')
-
-// Build a minimal zip with stored (uncompressed) entries so the test controls
-// the bytes exactly — exercises the central-directory reader + theme extraction
-// without a deflate dependency.
-function makeZip(entries) {
-  const locals = []
-  const centrals = []
-  let offset = 0
-
-  for (const { name, data } of entries) {
-    const nameBuf = Buffer.from(name, 'utf8')
-    const body = Buffer.from(data, 'utf8')
-
-    const local = Buffer.alloc(30 + nameBuf.length)
-    local.writeUInt32LE(0x04034b50, 0)
-    local.writeUInt16LE(0, 8) // method: stored
-    local.writeUInt32LE(body.length, 18) // compressed size
-    local.writeUInt32LE(body.length, 22) // uncompressed size
-    local.writeUInt16LE(nameBuf.length, 26)
-    nameBuf.copy(local, 30)
-
-    locals.push(local, body)
-
-    const central = Buffer.alloc(46 + nameBuf.length)
-    central.writeUInt32LE(0x02014b50, 0)
-    central.writeUInt16LE(0, 10) // method: stored
-    central.writeUInt32LE(body.length, 20)
-    central.writeUInt32LE(body.length, 24)
-    central.writeUInt16LE(nameBuf.length, 28)
-    central.writeUInt32LE(offset, 42) // local header offset
-    nameBuf.copy(central, 46)
-
-    centrals.push(central)
-    offset += local.length + body.length
-  }
-
-  const centralStart = offset
-  const centralBuf = Buffer.concat(centrals)
-
-  const eocd = Buffer.alloc(22)
-  eocd.writeUInt32LE(0x06054b50, 0)
-  eocd.writeUInt16LE(entries.length, 8)
-  eocd.writeUInt16LE(entries.length, 10)
-  eocd.writeUInt32LE(centralBuf.length, 12)
-  eocd.writeUInt32LE(centralStart, 16)
-
-  return Buffer.concat([...locals, centralBuf, eocd])
-}
-
-test('readCentralDirectory finds every entry', () => {
-  const zip = makeZip([
-    { name: 'extension/package.json', data: '{}' },
-    { name: 'extension/themes/x.json', data: '{}' }
-  ])
-
-  const records = readCentralDirectory(zip)
-  assert.ok(records.has('extension/package.json'))
-  assert.ok(records.has('extension/themes/x.json'))
-})
-
-test('extractThemes reads contributed color themes (resolving ./ paths)', () => {
-  const pkg = JSON.stringify({
-    name: 'theme-dracula',
-    displayName: 'Dracula',
-    contributes: {
-      themes: [{ label: 'Dracula', uiTheme: 'vs-dark', path: './themes/dracula.json' }]
-    }
-  })
-  const themeJson = JSON.stringify({ name: 'Dracula', type: 'dark', colors: { 'editor.background': '#282a36' } })
-
-  const zip = makeZip([
-    { name: 'extension/package.json', data: pkg },
-    { name: 'extension/themes/dracula.json', data: themeJson }
-  ])
-
-  const themes = extractThemes(zip)
-  assert.strictEqual(themes.length, 1)
-  assert.strictEqual(themes[0].label, 'Dracula')
-  assert.strictEqual(themes[0].uiTheme, 'vs-dark')
-  assert.match(themes[0].contents, /editor\.background/)
-})
-
-test('extractThemes returns empty when the extension contributes no themes', () => {
-  const zip = makeZip([{ name: 'extension/package.json', data: JSON.stringify({ name: 'x', contributes: {} }) }])
-  assert.deepStrictEqual(extractThemes(zip), [])
-})
-
-test('extractThemes throws when the manifest is missing', () => {
-  const zip = makeZip([{ name: 'extension/other.txt', data: 'hi' }])
-  assert.throws(() => extractThemes(zip), /manifest missing/i)
-})
-
-test('looksLikeIconTheme filters icon/product-icon packs out of theme search', () => {
-  const { looksLikeIconTheme } = __testing
-
-  // Tagged contribution points are the strongest signal.
-  assert.strictEqual(looksLikeIconTheme({ tags: ['theme', 'icon-theme'] }), true)
-  assert.strictEqual(looksLikeIconTheme({ tags: ['product-icon-theme'] }), true)
-
-  // Name/description fallback for packs that don't tag themselves.
-  assert.strictEqual(looksLikeIconTheme({ displayName: 'Material Icon Theme' }), true)
-  assert.strictEqual(looksLikeIconTheme({ shortDescription: 'A pack of file icons.' }), true)
-
-  // Real color themes survive.
-  assert.strictEqual(looksLikeIconTheme({ displayName: 'Dracula Official', tags: ['theme', 'color-theme'] }), false)
-  assert.strictEqual(looksLikeIconTheme({ displayName: 'One Dark Pro' }), false)
-})

apps/desktop/electron/windows-child-process.test.cjs

@@ -1,54 +0,0 @@
-'use strict'
-
-const test = require('node:test')
-const assert = require('node:assert/strict')
-const fs = require('node:fs')
-const path = require('node:path')
-
-const ELECTRON_DIR = __dirname
-
-function readElectronFile(name) {
-  return fs.readFileSync(path.join(ELECTRON_DIR, name), 'utf8')
-}
-
-function requireHiddenChildOptions(source, needle) {
-  const index = source.indexOf(needle)
-  assert.notEqual(index, -1, `missing call site: ${needle}`)
-  const snippet = source.slice(index, index + 700)
-  assert.match(
-    snippet,
-    /hiddenWindowsChildOptions\(/,
-    `expected ${needle} to wrap child-process options with hiddenWindowsChildOptions`
-  )
-}
-
-test('desktop background child processes opt into hidden Windows consoles', () => {
-  const source = readElectronFile('main.cjs')
-
-  assert.match(source, /function hiddenWindowsChildOptions\(options = \{\}\)/)
-
-  requireHiddenChildOptions(source, "execFileSync(\n          'reg'")
-  requireHiddenChildOptions(source, 'execFileSync(pyExe')
-  requireHiddenChildOptions(source, 'spawn(resolveGitBinary()')
-  requireHiddenChildOptions(source, "execFileSync('taskkill'")
-  requireHiddenChildOptions(source, 'spawn(command, args')
-  requireHiddenChildOptions(source, "spawn('curl'")
-  requireHiddenChildOptions(source, 'spawn(backend.command, backend.args')
-  requireHiddenChildOptions(source, 'hermesProcess = spawn(backend.command, backend.args')
-  requireHiddenChildOptions(source, "spawn(py, ['-m', 'hermes_cli.main', 'uninstall', '--gui-summary']")
-})
-
-test('intentional or interactive desktop child processes stay documented', () => {
-  const source = readElectronFile('main.cjs')
-
-  assert.match(source, /windowsHide: false/)
-  assert.match(source, /nodePty\.spawn\(command, args/)
-  assert.match(source, /spawn\('cmd\.exe', \['\/c', 'start'/)
-})
-
-test('bootstrap PowerShell runner hides Windows console children', () => {
-  const source = readElectronFile('bootstrap-runner.cjs')
-
-  assert.match(source, /function hiddenWindowsChildOptions\(options = \{\}\)/)
-  requireHiddenChildOptions(source, 'spawn(ps, fullArgs')
-})

apps/desktop/electron/workspace-cwd.cjs

@@ -1,38 +0,0 @@
-const path = require('node:path')
-
-/** True when `dir` lives inside a packaged app bundle / install tree. */
-function isPackagedInstallPath(dir, { installRoots, isPackaged }) {
-  if (!isPackaged || !dir) {
-    return false
-  }
-
-  let resolved
-
-  try {
-    resolved = path.resolve(String(dir))
-  } catch {
-    return false
-  }
-
-  const roots = new Set(
-    (installRoots ?? [])
-      .filter(Boolean)
-      .map(candidate => path.resolve(String(candidate)))
-  )
-
-  for (const root of roots) {
-    if (resolved === root) {
-      return true
-    }
-
-    const rel = path.relative(root, resolved)
-
-    if (rel && !rel.startsWith('..') && !path.isAbsolute(rel)) {
-      return true
-    }
-  }
-
-  return false
-}
-
-module.exports = { isPackagedInstallPath }

apps/desktop/electron/workspace-cwd.test.cjs

@@ -1,45 +0,0 @@
-/**
- * Tests for electron/workspace-cwd.cjs.
- *
- * Run with: node --test electron/workspace-cwd.test.cjs
- */
-
-const test = require('node:test')
-const assert = require('node:assert/strict')
-const path = require('node:path')
-
-const { isPackagedInstallPath } = require('./workspace-cwd.cjs')
-
-const installRoot = path.resolve('/opt/Hermes')
-
-test('isPackagedInstallPath returns false when not packaged', () => {
-  assert.equal(
-    isPackagedInstallPath(installRoot, { isPackaged: false, installRoots: [installRoot] }),
-    false
-  )
-})
-
-test('isPackagedInstallPath flags the install root itself', () => {
-  assert.equal(
-    isPackagedInstallPath(installRoot, { isPackaged: true, installRoots: [installRoot] }),
-    true
-  )
-})
-
-test('isPackagedInstallPath flags paths nested under the install root', () => {
-  const nested = path.join(installRoot, 'resources', 'app.asar')
-
-  assert.equal(
-    isPackagedInstallPath(nested, { isPackaged: true, installRoots: [installRoot] }),
-    true
-  )
-})
-
-test('isPackagedInstallPath ignores paths outside the install root', () => {
-  const homeProject = path.resolve('/home/user/projects/demo')
-
-  assert.equal(
-    isPackagedInstallPath(homeProject, { isPackaged: true, installRoots: [installRoot] }),
-    false
-  )
-})

apps/desktop/eslint.config.mjs

@@ -3,6 +3,7 @@ import typescriptEslint from '@typescript-eslint/eslint-plugin'
 import typescriptParser from '@typescript-eslint/parser'
 import perfectionist from 'eslint-plugin-perfectionist'
 import reactPlugin from 'eslint-plugin-react'
+import reactCompiler from 'eslint-plugin-react-compiler'
 import hooksPlugin from 'eslint-plugin-react-hooks'
 import unusedImports from 'eslint-plugin-unused-imports'
 import globals from 'globals'
@@ -46,6 +47,7 @@ export default [
       'custom-rules': customRules,
       perfectionist,
       react: reactPlugin,
+      'react-compiler': reactCompiler,
       'react-hooks': hooksPlugin,
       'unused-imports': unusedImports
     },
@@ -96,6 +98,7 @@ export default [
       'perfectionist/sort-jsx-props': ['error', { order: 'asc', type: 'natural' }],
       'perfectionist/sort-named-exports': ['error', { order: 'asc', type: 'natural' }],
       'perfectionist/sort-named-imports': ['error', { order: 'asc', type: 'natural' }],
+      'react-compiler/react-compiler': 'warn',
       'react-hooks/exhaustive-deps': 'warn',
       'react-hooks/rules-of-hooks': 'error',
       'unused-imports/no-unused-imports': 'error'

apps/desktop/package.json

@@ -35,8 +35,8 @@
     "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 electron/bootstrap-runner.test.cjs electron/connection-config.test.cjs electron/gateway-ws-probe.test.cjs electron/oauth-net-request.test.cjs electron/desktop-uninstall.test.cjs electron/session-windows.test.cjs electron/workspace-cwd.test.cjs electron/fs-read-dir.test.cjs electron/git-root.test.cjs electron/windows-child-process.test.cjs electron/update-remote.test.cjs",
-    "typecheck": "tsc -p . --noEmit",
+    "test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs electron/backend-probes.test.cjs electron/bootstrap-runner.test.cjs electron/connection-config.test.cjs electron/gateway-ws-probe.test.cjs electron/oauth-net-request.test.cjs electron/desktop-uninstall.test.cjs",
+    "type-check": "tsc -b",
     "lint": "eslint src/ electron/",
     "lint:fix": "eslint src/ electron/ --fix",
     "fmt": "prettier --write 'src/**/*.{ts,tsx}' 'electron/**/*.{js,cjs}' 'vite.config.ts'",
@@ -72,7 +72,6 @@
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "cmdk": "^1.1.1",
-    "dnd-core": "^14.0.1",
     "hast-util-from-html-isomorphic": "^2.0.0",
     "hast-util-to-text": "^4.0.2",
     "ignore": "^7.0.5",
@@ -84,7 +83,6 @@
     "radix-ui": "^1.4.3",
     "react": "^19.2.5",
     "react-arborist": "^3.5.0",
-    "react-dnd-html5-backend": "^14.0.3",
     "react-dom": "^19.2.5",
     "react-router-dom": "^7.17.0",
     "react-shiki": "^0.9.3",
@@ -105,19 +103,20 @@
     "@testing-library/dom": "^10.4.0",
     "@testing-library/react": "^16.3.2",
     "@types/hast": "^3.0.4",
-    "@types/node": "^24.12.0",
+    "@types/node": "^24.12.2",
     "@types/react": "^19.2.14",
     "@types/react-dom": "^19.2.3",
     "@typescript-eslint/eslint-plugin": "^8.59.1",
     "@typescript-eslint/parser": "^8.59.1",
     "@vitejs/plugin-react": "^6.0.1",
-    "concurrently": "^10.0.3",
+    "concurrently": "^9.2.1",
     "cross-env": "^10.1.0",
     "electron": "^40.9.3",
     "electron-builder": "^26.8.1",
     "eslint": "^9.39.4",
     "eslint-plugin-perfectionist": "^5.9.0",
     "eslint-plugin-react": "^7.37.5",
+    "eslint-plugin-react-compiler": "^19.1.0-rc.2",
     "eslint-plugin-react-hooks": "^7.1.1",
     "eslint-plugin-unused-imports": "^4.4.1",
     "globals": "^16.5.0",
@@ -134,14 +133,6 @@
     "appId": "com.nousresearch.hermes",
     "productName": "Hermes",
     "executableName": "Hermes",
-    "protocols": [
-      {
-        "name": "Hermes Protocol",
-        "schemes": [
-          "hermes"
-        ]
-      }
-    ],
     "artifactName": "Hermes-${version}-${os}-${arch}.${ext}",
     "icon": "assets/icon",
     "directories": {

apps/desktop/src/app/chat/composer/attachments.tsx

@@ -3,9 +3,8 @@ import { useStore } from '@nanostores/react'
 import { Codicon } from '@/components/ui/codicon'
 import { Tip } from '@/components/ui/tooltip'
 import { useI18n } from '@/i18n'
-import { AlertCircle, FileText, FolderOpen, ImageIcon, Link, Loader2, Terminal } from '@/lib/icons'
+import { FileText, FolderOpen, ImageIcon, Link, Terminal } from '@/lib/icons'
 import { normalizeOrLocalPreviewTarget } from '@/lib/local-preview'
-import { cn } from '@/lib/utils'
 import type { ComposerAttachment } from '@/store/composer'
 import { notifyError } from '@/store/notifications'
 import { setCurrentSessionPreviewTarget } from '@/store/preview'
@@ -32,9 +31,7 @@ function AttachmentPill({ attachment, onRemove }: { attachment: ComposerAttachme
   const c = t.composer
   const Icon = { folder: FolderOpen, url: Link, image: ImageIcon, file: FileText, terminal: Terminal }[attachment.kind]
   const cwd = useStore($currentCwd)
-  const isUploading = attachment.uploadState === 'uploading'
-  const hasUploadError = attachment.uploadState === 'error'
-  const canPreview = attachment.kind !== 'folder' && attachment.kind !== 'terminal' && !isUploading
+  const canPreview = attachment.kind !== 'folder' && attachment.kind !== 'terminal'
   const detail = attachment.detail && attachment.detail !== attachment.label ? attachment.detail : undefined
 
   async function openPreview() {
@@ -62,15 +59,7 @@ function AttachmentPill({ attachment, onRemove }: { attachment: ComposerAttachme
         throw new Error(c.couldNotPreview(attachment.label))
       }
 
-      // We already hold the image bytes (the card thumbnail) — render those
-      // directly so a screenshot/clipboard image previews even when its only
-      // on-disk copy is a transient path the renderer can't re-read.
-      const withBytes =
-        attachment.kind === 'image' && attachment.previewUrl
-          ? { ...preview, dataUrl: attachment.previewUrl, previewKind: 'image' as const }
-          : preview
-
-      setCurrentSessionPreviewTarget(withBytes, 'manual', target)
+      setCurrentSessionPreviewTarget(preview, 'manual', target)
     } catch (error) {
       notifyError(error, c.previewUnavailable)
     }
@@ -80,51 +69,30 @@ function AttachmentPill({ attachment, onRemove }: { attachment: ComposerAttachme
     <Tip label={attachment.path || attachment.detail || attachment.label}>
       <div className="group/attachment relative min-w-0 shrink-0">
         <button
-          aria-busy={isUploading || undefined}
           aria-label={canPreview ? c.previewLabel(attachment.label) : attachment.label}
-          className={cn(
-            'flex max-w-56 items-center gap-2 rounded-2xl border bg-background/50 px-2 py-1.5 text-left shadow-[inset_0_1px_0_rgba(255,255,255,0.18)] transition-colors disabled:cursor-default',
-            hasUploadError
-              ? 'border-destructive/45 hover:border-destructive/60'
-              : 'border-border/60 hover:border-primary/35 hover:bg-accent/45'
-          )}
+          className="flex max-w-56 items-center gap-2 border border-border/60 bg-background/50 px-2 py-1.5 text-left shadow-[inset_0_1px_0_rgba(255,255,255,0.25)] transition-colors hover:border-primary/35 hover:bg-accent/45 disabled:cursor-default"
           disabled={!canPreview}
           onClick={() => void openPreview()}
           type="button"
         >
-          <span className="relative grid size-8 shrink-0 place-items-center overflow-hidden rounded-lg border border-border/55 bg-muted/35 text-muted-foreground">
-            {attachment.previewUrl && attachment.kind === 'image' ? (
-              <img
-                alt={attachment.label}
-                className="size-full object-cover"
-                draggable={false}
-                src={attachment.previewUrl}
-              />
-            ) : (
+          {attachment.previewUrl && attachment.kind === 'image' ? (
+            <img
+              alt={attachment.label}
+              className="size-8 shrink-0 border border-border/70 object-cover"
+              draggable={false}
+              src={attachment.previewUrl}
+            />
+          ) : (
+            <span className="grid size-8 shrink-0 place-items-center border border-border/55 bg-muted/35 text-muted-foreground">
               <Icon className="size-3.5" />
-            )}
-            {isUploading && (
-              <span className="absolute inset-0 grid place-items-center bg-background/60 backdrop-blur-[1px]">
-                <Loader2 className="size-3.5 animate-spin text-foreground/75" />
-              </span>
-            )}
-            {hasUploadError && (
-              <span className="absolute inset-0 grid place-items-center bg-destructive/15">
-                <AlertCircle className="size-3.5 text-destructive" />
-              </span>
-            )}
-          </span>
+            </span>
+          )}
           <span className="min-w-0">
             <span className="block truncate text-[0.72rem] font-medium leading-4 text-foreground/90">
               {attachment.label}
             </span>
             {detail && (
-              <span
-                className={cn(
-                  'block truncate text-[0.62rem] leading-3.5',
-                  hasUploadError ? 'text-destructive/80' : 'text-muted-foreground/65'
-                )}
-              >
+              <span className="block truncate font-mono text-[0.6rem] leading-3 text-muted-foreground/65">
                 {detail}
               </span>
             )}

apps/desktop/src/app/chat/composer/completion-drawer.tsx

@@ -3,25 +3,32 @@ import { ComposerPrimitive } from '@assistant-ui/react'
 import type { ReactNode } from 'react'
 
 export const COMPLETION_DRAWER_CLASS = [
-  'absolute bottom-[calc(100%+0.375rem)] left-0 z-50',
-  'w-80 max-w-[calc(100vw-2rem)]',
-  'max-h-[min(22rem,calc(100vh-8rem))] overflow-y-auto overscroll-contain',
-  'rounded-xl border border-(--ui-stroke-secondary)',
-  'bg-[color-mix(in_srgb,var(--ui-bg-elevated)_97%,transparent)]',
-  'p-1 text-xs text-popover-foreground shadow-lg',
+  'absolute bottom-[calc(100%+0.25rem)] left-0 z-50',
+  'w-60 max-w-[calc(100vw-2rem)]',
+  'max-h-[min(23rem,calc(100vh-8rem))] overflow-y-auto overscroll-contain',
+  'rounded-lg border border-(--ui-stroke-secondary)',
+  'bg-[color-mix(in_srgb,var(--ui-bg-elevated)_96%,transparent)]',
+  'p-1 text-xs text-popover-foreground shadow-md',
   'backdrop-blur-md'
 ].join(' ')
 
 export const COMPLETION_DRAWER_BELOW_CLASS = [
-  'absolute left-0 top-[calc(100%+0.375rem)] z-50',
-  'w-80 max-w-[calc(100vw-2rem)]',
-  'max-h-[min(22rem,calc(100vh-8rem))] overflow-y-auto overscroll-contain',
-  'rounded-xl border border-(--ui-stroke-secondary)',
-  'bg-[color-mix(in_srgb,var(--ui-bg-elevated)_97%,transparent)]',
-  'p-1 text-xs text-popover-foreground shadow-lg',
+  'absolute left-0 top-[calc(100%+0.25rem)] z-50',
+  'w-60 max-w-[calc(100vw-2rem)]',
+  'max-h-[min(23rem,calc(100vh-8rem))] overflow-y-auto overscroll-contain',
+  'rounded-lg border border-(--ui-stroke-secondary)',
+  'bg-[color-mix(in_srgb,var(--ui-bg-elevated)_96%,transparent)]',
+  'p-1 text-xs text-popover-foreground shadow-md',
   'backdrop-blur-md'
 ].join(' ')
 
+export const COMPLETION_DRAWER_ROW_CLASS = [
+  'relative flex cursor-default select-none items-center gap-2 rounded-md px-2 py-1',
+  'w-full min-w-0 text-left text-xs outline-hidden transition-colors',
+  'hover:bg-(--ui-bg-tertiary)',
+  'data-[highlighted]:bg-(--ui-bg-tertiary) data-[highlighted]:text-foreground'
+].join(' ')
+
 export function ComposerCompletionDrawer({
   adapter,
   ariaLabel,

apps/desktop/src/app/chat/composer/controls.tsx

@@ -4,7 +4,6 @@ import { Tip } from '@/components/ui/tooltip'
 import { useI18n } from '@/i18n'
 import { triggerHaptic } from '@/lib/haptics'
 import { AudioLines, Layers3, Loader2, Square, SteeringWheel } from '@/lib/icons'
-import { formatCombo } from '@/lib/keybinds/combo'
 import { cn } from '@/lib/utils'
 
 import type { ConversationStatus } from './hooks/use-voice-conversation'
@@ -63,7 +62,6 @@ export function ComposerControls({
 }) {
   const { t } = useI18n()
   const c = t.composer
-  const steerLabel = `${c.steer} (${formatCombo('mod+enter')})`
 
   if (conversation.active) {
     return <ConversationPill {...conversation} disabled={disabled} />
@@ -75,9 +73,9 @@ export function ComposerControls({
     <div className="ml-auto flex shrink-0 items-center gap-(--composer-control-gap)">
       <DictationButton disabled={disabled} onToggle={onDictate} state={state.voice} status={voiceStatus} />
       {canSteer && (
-        <Tip label={steerLabel}>
+        <Tip label={c.steer}>
           <Button
-            aria-label={steerLabel}
+            aria-label={c.steer}
             className={GHOST_ICON_BTN}
             disabled={disabled}
             onClick={onSteer}

apps/desktop/src/app/chat/composer/enter-submit-dom-race.test.tsx

@@ -1,189 +0,0 @@
-import { act, cleanup, fireEvent, render } from '@testing-library/react'
-import { useRef, useState } from 'react'
-import { afterEach, describe, expect, it, vi } from 'vitest'
-
-// No global setupFiles registers auto-cleanup, so unmount between tests —
-// otherwise a second render() leaks the first editor and getByTestId('editor')
-// matches multiple nodes.
-afterEach(cleanup)
-
-// Faithful mirror of index.tsx's Enter wiring (handleEditorKeyDown's Enter
-// branch + submitDraft), driven through REAL DOM keydown events on a
-// contentEditable.
-//
-// Regression repro for #39630: pressing Enter right after typing (fast typing /
-// IME) did nothing. The composer state (`draft` from useAuiState) and its
-// derived `hasComposerPayload` lag the DOM by a render, so the keydown handler
-// read empty state and either dropped the message, drained a queued prompt
-// instead of sending, or (while busy) refused to queue. The fix reads the live
-// editor text — `hasLivePayload` in the handler and a DOM re-sync at the top of
-// submitDraft — so the just-typed text always wins.
-//
-// We model the race deterministically the way the IME repro does: mutate the
-// editor's textContent WITHOUT firing an input event, so the React `draft`
-// state stays stale while the DOM already holds the text.
-function Harness({
-  busy = false,
-  queued = [],
-  onSubmit,
-  onQueue,
-  onCancel,
-  onDrain
-}: {
-  busy?: boolean
-  queued?: readonly string[]
-  onSubmit: (text: string) => void
-  onQueue: (text: string) => void
-  onCancel: () => void
-  onDrain: () => void
-}) {
-  const editorRef = useRef<HTMLDivElement>(null)
-  const draftRef = useRef('')
-  // Mirrors `useAuiState(s => s.composer.text)` — updated only via setText, so
-  // it lags the DOM until React re-renders (the source of the bug).
-  const [draft, setDraft] = useState('')
-  const attachments: unknown[] = []
-
-  const composerPlainText = (el: HTMLElement) => el.textContent ?? ''
-
-  const setText = (next: string) => {
-    draftRef.current = next
-    setDraft(next)
-  }
-
-  const submitDraft = () => {
-    const editor = editorRef.current
-    if (editor) {
-      const domText = composerPlainText(editor)
-      if (domText !== draftRef.current) {
-        draftRef.current = domText
-        setDraft(domText)
-      }
-    }
-
-    const text = draftRef.current
-    const payloadPresent = text.trim().length > 0 || attachments.length > 0
-
-    if (busy) {
-      if (payloadPresent) {
-        onQueue(text)
-      } else {
-        onCancel()
-      }
-    } else if (!payloadPresent && queued.length > 0) {
-      onDrain()
-    } else if (payloadPresent) {
-      onSubmit(text)
-    }
-  }
-
-  const handleKeyDown = (event: React.KeyboardEvent<HTMLDivElement>) => {
-    if (event.key === 'Enter' && !event.shiftKey) {
-      event.preventDefault()
-
-      const editorText = editorRef.current ? composerPlainText(editorRef.current) : draftRef.current
-      const hasLivePayload = editorText.trim().length > 0 || attachments.length > 0
-
-      if (!busy && !hasLivePayload && queued.length > 0) {
-        onDrain()
-
-        return
-      }
-
-      if (busy && !hasLivePayload) {
-        return
-      }
-
-      submitDraft()
-    }
-  }
-
-  // `draft` is read so the lint/compiler treats the stale-state mirror as live;
-  // the assertions prove the handler never relies on it.
-  void draft
-
-  return (
-    <div
-      contentEditable
-      data-testid="editor"
-      onInput={event => setText(composerPlainText(event.currentTarget))}
-      onKeyDown={handleKeyDown}
-      ref={editorRef}
-      suppressContentEditableWarning
-    />
-  )
-}
-
-describe('composer Enter submit — live DOM vs stale composer state (#39630)', () => {
-  it('sends the just-typed text on Enter even when composer state has not synced', async () => {
-    const onSubmit = vi.fn()
-    const { getByTestId } = render(
-      <Harness onCancel={vi.fn()} onDrain={vi.fn()} onQueue={vi.fn()} onSubmit={onSubmit} />
-    )
-    const editor = getByTestId('editor')
-
-    // Fast typing: the DOM has the text but NO input event fired, so `draft`
-    // state is still empty (the exact stale-state race).
-    await act(async () => {
-      editor.textContent = 'hello world'
-      fireEvent.keyDown(editor, { key: 'Enter' })
-    })
-
-    expect(onSubmit).toHaveBeenCalledWith('hello world')
-  })
-
-  it('queues a fast-typed message while busy instead of draining the queue or cancelling', async () => {
-    const onQueue = vi.fn()
-    const onDrain = vi.fn()
-    const onCancel = vi.fn()
-    const { getByTestId } = render(
-      <Harness busy onCancel={onCancel} onDrain={onDrain} onQueue={onQueue} onSubmit={vi.fn()} queued={['queued-1']} />
-    )
-    const editor = getByTestId('editor')
-
-    await act(async () => {
-      editor.textContent = 'urgent follow-up'
-      fireEvent.keyDown(editor, { key: 'Enter' })
-    })
-
-    expect(onQueue).toHaveBeenCalledWith('urgent follow-up')
-    expect(onDrain).not.toHaveBeenCalled()
-    expect(onCancel).not.toHaveBeenCalled()
-  })
-
-  it('treats an empty Enter while busy as a no-op (never an accidental Stop)', async () => {
-    const onCancel = vi.fn()
-    const onSubmit = vi.fn()
-    const onQueue = vi.fn()
-    const { getByTestId } = render(
-      <Harness busy onCancel={onCancel} onDrain={vi.fn()} onQueue={onQueue} onSubmit={onSubmit} />
-    )
-    const editor = getByTestId('editor')
-
-    await act(async () => {
-      editor.textContent = ''
-      fireEvent.keyDown(editor, { key: 'Enter' })
-    })
-
-    expect(onCancel).not.toHaveBeenCalled()
-    expect(onSubmit).not.toHaveBeenCalled()
-    expect(onQueue).not.toHaveBeenCalled()
-  })
-
-  it('drains the next queued prompt on Enter when idle with a truly empty editor', async () => {
-    const onDrain = vi.fn()
-    const onSubmit = vi.fn()
-    const { getByTestId } = render(
-      <Harness onCancel={vi.fn()} onDrain={onDrain} onQueue={vi.fn()} onSubmit={onSubmit} queued={['queued-1']} />
-    )
-    const editor = getByTestId('editor')
-
-    await act(async () => {
-      editor.textContent = ''
-      fireEvent.keyDown(editor, { key: 'Enter' })
-    })
-
-    expect(onDrain).toHaveBeenCalledTimes(1)
-    expect(onSubmit).not.toHaveBeenCalled()
-  })
-})

apps/desktop/src/app/chat/composer/hooks/use-live-completion-adapter.ts

@@ -5,13 +5,6 @@ export interface CompletionEntry {
   text: string
   display?: unknown
   meta?: unknown
-  /** Optional section label (e.g. "Commands", "Skills"). The popover renders a
-   *  header whenever this changes between consecutive items, so the fetcher must
-   *  emit entries already grouped contiguously. */
-  group?: string
-  /** Optional completion-action id. When set, picking the item runs that action
-   *  (e.g. opening an overlay) instead of inserting a chip + waiting for submit. */
-  action?: string
 }
 
 export interface CompletionPayload {

apps/desktop/src/app/chat/composer/hooks/use-slash-completions.ts

@@ -2,17 +2,12 @@ import type { Unstable_TriggerAdapter, Unstable_TriggerItem } from '@assistant-u
 import { useCallback } from 'react'
 
 import type { HermesGateway } from '@/hermes'
-import { sessionTitle } from '@/lib/chat-runtime'
 import {
   type CommandsCatalogLike,
-  desktopSkinSlashCompletions,
   desktopSlashDescription,
-  type DesktopThemeCommandOption,
   filterDesktopCommandsCatalog,
-  isDesktopSlashExtensionCommand,
   isDesktopSlashSuggestion
 } from '@/lib/desktop-slash-commands'
-import { $sessions } from '@/store/session'
 
 import type { CompletionEntry, CompletionPayload } from './use-live-completion-adapter'
 import { useLiveCompletionAdapter } from './use-live-completion-adapter'
@@ -21,10 +16,7 @@ interface SlashItemMetadata extends Record<string, string> {
   command: string
   display: string
   meta: string
-  group: string
   rawText: string
-  /** Completion-action id; empty for ordinary insert-a-chip completions. */
-  action: string
 }
 
 function textValue(value: unknown, fallback = ''): string {
@@ -46,21 +38,12 @@ function commandText(value: string): string {
   return value.startsWith('/') ? value : `/${value}`
 }
 
-/** How many recent sessions to surface inline before the "Browse all…" entry. */
-const SESSION_INLINE_LIMIT = 7
-
 /** Live `/` completions backed by the gateway's `complete.slash` RPC. */
-export function useSlashCompletions(options: {
-  gateway: HermesGateway | null
-  /** Desktop theme list — `/skin` is owned client-side, so its arg completions
-   *  come from here, not the backend (whose skin list is CLI/TUI-only). */
-  skinThemes?: DesktopThemeCommandOption[]
-  activeSkin?: string
-}): {
+export function useSlashCompletions(options: { gateway: HermesGateway | null }): {
   adapter: Unstable_TriggerAdapter
   loading: boolean
 } {
-  const { gateway, skinThemes, activeSkin } = options
+  const { gateway } = options
   const enabled = Boolean(gateway)
 
   const fetcher = useCallback(
@@ -71,136 +54,34 @@ export function useSlashCompletions(options: {
 
       const text = `/${query}`
 
-      // The desktop owns /skin entirely (client-side theme context). Surface its
-      // theme list inside this single popover instead of a bespoke one, and skip
-      // the backend skin completions (which describe CLI/TUI skins that don't
-      // apply here). Matches once we're past `/skin ` into the arg stage.
-      const skinArg = /^\/skin\s+(.*)$/is.exec(text)
-
-      if (skinArg && skinThemes) {
-        const items = desktopSkinSlashCompletions(skinThemes, activeSkin ?? '', skinArg[1] ?? '').map(entry => ({
-          text: entry.text,
-          display: entry.display,
-          meta: entry.meta,
-          group: 'Themes'
-        }))
-
-        return { items, query }
-      }
-
-      // /resume (and its aliases) completes recent sessions inline — the same
-      // client-side list the picker overlay shows — instead of the backend
-      // (whose /resume opens an interactive TUI picker we can't render here).
-      const sessionArg = /^\/(?:resume|sessions|switch)\s+(.*)$/is.exec(text)
-
-      if (sessionArg) {
-        const needle = (sessionArg[1] ?? '').trim().toLowerCase()
-
-        const matches = (
-          needle
-            ? $sessions.get().filter(
-                session =>
-                  sessionTitle(session).toLowerCase().includes(needle) ||
-                  (session.preview ?? '').toLowerCase().includes(needle) ||
-                  session.id.toLowerCase().includes(needle)
-              )
-            : $sessions.get()
-        ).slice(0, SESSION_INLINE_LIMIT)
-
-        const items: CompletionEntry[] = matches.map(session => ({
-          text: `/resume ${session.id}`,
-          display: sessionTitle(session),
-          meta: (session.preview ?? '').trim(),
-          group: 'Sessions'
-        }))
-
-        // Trailing "more" affordance (Cursor-style): picking it opens the full
-        // session picker overlay directly. `text` stays a bare `/resume` so that
-        // submitting it (Enter) still opens the overlay if the action is skipped.
-        items.push({
-          text: '/resume',
-          display: 'Browse all sessions…',
-          meta: '',
-          group: 'Sessions',
-          action: 'session-picker'
-        })
-
-        return { items, query }
-      }
-
       try {
         if (!query) {
           const catalog = filterDesktopCommandsCatalog(await gateway.request<CommandsCatalogLike>('commands.catalog'))
 
-          // Prefer the categorized layout so the popover renders section headers
-          // (Session, Tools & Skills, ...). Fall back to the flat list when the
-          // backend didn't categorize.
-          const sections = catalog.categories?.length
-            ? catalog.categories
-            : [{ name: '', pairs: catalog.pairs ?? [] }]
-
-          const items = sections.flatMap(section =>
-            section.pairs.map(([command, meta]) => ({
-              text: command,
-              display: command,
-              group: section.name || undefined,
-              meta
-            }))
-          )
+          const items = (catalog.pairs ?? []).map(([command, meta]) => ({
+            text: command,
+            display: command,
+            meta
+          }))
 
           return { items, query }
         }
 
-        const result = await gateway.request<{ items?: CompletionEntry[]; replace_from?: number }>(
-          'complete.slash',
-          { text }
-        )
+        const result = await gateway.request<{ items?: CompletionEntry[] }>('complete.slash', { text })
 
-        // Arg-completion items (replace_from > 1) carry just the arg stub —
-        // e.g. complete.slash returns `{text: "alice"}` for `/personality alic`
-        // with replace_from = 14. Rewrite those entries so the popover inserts
-        // the full `/personality alice` token instead of stranding `/alice`.
-        const replaceFrom = typeof result.replace_from === 'number' ? result.replace_from : 1
-        const isArgCompletion = replaceFrom > 1
-        const prefix = isArgCompletion ? text.slice(0, replaceFrom) : ''
-
-        const decorated = (result.items ?? [])
-          .map(item => {
-            if (!isArgCompletion) {
-              return item
-            }
-
-            const argText = typeof item.text === 'string' ? item.text : ''
-
-            return { ...item, text: `${prefix}${argText}` }
-          })
-          .filter(item => isArgCompletion || isDesktopSlashSuggestion(item.text))
+        const items = (result.items ?? [])
+          .filter(item => isDesktopSlashSuggestion(item.text))
           .map(item => ({
             ...item,
-            // Arg suggestions (e.g. `/handoff <platform>`) live under one
-            // header; otherwise split skills out from built-in commands.
-            group: isArgCompletion ? 'Options' : isDesktopSlashExtensionCommand(item.text) ? 'Skills' : 'Commands',
-            // Arg items carry their own meta (the personality/toolset/platform
-            // blurb). Only command rows get the registry description — looking
-            // one up for `/personality none` would clobber it with the parent
-            // command's text.
-            meta: isArgCompletion ? textValue(item.meta) : desktopSlashDescription(item.text, textValue(item.meta))
+            meta: desktopSlashDescription(item.text, textValue(item.meta))
           }))
 
-        // Keep each group contiguous so headers render once: Commands before
-        // Skills (stable within a group, preserving backend relevance order).
-        const groupOrder = ['Commands', 'Skills', 'Options']
-
-        const items = isArgCompletion
-          ? decorated
-          : [...decorated].sort((a, b) => groupOrder.indexOf(a.group) - groupOrder.indexOf(b.group))
-
         return { items, query }
       } catch {
         return { items: [], query }
       }
     },
-    [gateway, skinThemes, activeSkin]
+    [gateway]
   )
 
   const toItem = useCallback((entry: CompletionEntry, index: number): Unstable_TriggerItem => {
@@ -212,8 +93,6 @@ export function useSlashCompletions(options: {
       command,
       display,
       meta,
-      group: textValue(entry.group),
-      action: textValue(entry.action),
       // Provide rawText so hermesDirectiveFormatter.serialize uses the
       // direct-insertion path instead of the legacy @type:id fallback.
       // Without this, the item.id (which includes a "|index" suffix for

apps/desktop/src/app/chat/composer/index.tsx

@@ -13,25 +13,17 @@ import {
   useState
 } from 'react'
 
-import { hermesDirectiveFormatter, type SlashChipKind } from '@/components/assistant-ui/directive-text'
+import { hermesDirectiveFormatter } from '@/components/assistant-ui/directive-text'
 import { Button } from '@/components/ui/button'
 import { useMediaQuery } from '@/hooks/use-media-query'
 import { useResizeObserver } from '@/hooks/use-resize-observer'
 import { useI18n } from '@/i18n'
 import { chatMessageText } from '@/lib/chat-messages'
 import { SLASH_COMMAND_RE } from '@/lib/chat-runtime'
-import { desktopSlashCommandTakesArgs } from '@/lib/desktop-slash-commands'
 import { DATA_IMAGE_URL_RE } from '@/lib/embedded-images'
 import { triggerHaptic } from '@/lib/haptics'
 import { cn } from '@/lib/utils'
-import {
-  $composerAttachments,
-  clearComposerAttachments,
-  clearSessionDraft,
-  type ComposerAttachment,
-  stashSessionDraft,
-  takeSessionDraft
-} from '@/store/composer'
+import { $composerAttachments, clearComposerAttachments, type ComposerAttachment } from '@/store/composer'
 import {
   browseBackward,
   browseForward,
@@ -48,11 +40,10 @@ import {
   shouldAutoDrainOnSettle,
   updateQueuedPrompt
 } from '@/store/composer-queue'
-import { $gatewayState, $messages, setSessionPickerOpen } from '@/store/session'
+import { $gatewayState, $messages } from '@/store/session'
 import { $threadScrolledUp } from '@/store/thread-scroll'
-import { useTheme } from '@/themes'
 
-import { extractDroppedFiles, HERMES_PATHS_MIME, partitionDroppedFiles } from '../hooks/use-composer-actions'
+import { extractDroppedFiles, HERMES_PATHS_MIME } from '../hooks/use-composer-actions'
 
 import { AttachmentList } from './attachments'
 import { ContextMenu } from './context-menu'
@@ -73,7 +64,7 @@ import { useVoiceConversation } from './hooks/use-voice-conversation'
 import { useVoiceRecorder } from './hooks/use-voice-recorder'
 import {
   dragHasAttachments,
-  droppedFileInlineRefs,
+  droppedFileInlineRef,
   type InlineRefInput,
   insertInlineRefsIntoEditor
 } from './inline-refs'
@@ -83,9 +74,9 @@ import {
   placeCaretEnd,
   refChipElement,
   renderComposerContents,
-  RICH_INPUT_SLOT,
-  slashChipElement
+  RICH_INPUT_SLOT
 } from './rich-editor'
+import { SkinSlashPopover } from './skin-slash-popover'
 import { detectTrigger, extractClipboardImageBlobs, textBeforeCaret, type TriggerState } from './text-utils'
 import { ComposerTriggerPopover } from './trigger-popover'
 import type { ChatBarProps } from './types'
@@ -104,30 +95,6 @@ const COMPOSER_FADE_BACKGROUND =
 
 const pickPlaceholder = (pool: readonly string[]) => pool[Math.floor(Math.random() * pool.length)]
 
-/** Completion items can carry an `action` (set in use-slash-completions) that
- *  runs a side effect on pick instead of inserting a chip — e.g. the session
- *  picker's "Browse all…" entry opens the overlay. Table-driven so new action
- *  items are a registry row, not a composer branch. */
-const COMPLETION_ACTIONS: Record<string, () => void> = {
-  'session-picker': () => setSessionPickerOpen(true)
-}
-
-/** Map a picked `/` completion to its pill accent. Driven by the completion
- *  group set in use-slash-completions (Skills / Themes / Commands|Options). */
-function slashChipKindForItem(item: Unstable_TriggerItem): SlashChipKind {
-  const group = (item.metadata as { group?: unknown } | undefined)?.group
-
-  if (group === 'Skills') {
-    return 'skill'
-  }
-
-  if (group === 'Themes') {
-    return 'theme'
-  }
-
-  return 'command'
-}
-
 interface QueueEditState {
   attachments: ComposerAttachment[]
   draft: string
@@ -137,10 +104,6 @@ interface QueueEditState {
 
 const cloneAttachments = (attachments: ComposerAttachment[]) => attachments.map(a => ({ ...a }))
 
-// Quiet period after the last keystroke before persisting the draft;
-// unmount/pagehide flushes bypass it.
-const DRAFT_PERSIST_DEBOUNCE_MS = 400
-
 export function ChatBar({
   busy,
   cwd,
@@ -182,9 +145,6 @@ export function ChatBar({
   const editorRef = useRef<HTMLDivElement | null>(null)
   const draftRef = useRef(draft)
   const previousBusyRef = useRef(busy)
-  const pendingDraftPersistRef = useRef<{ scope: string | null; text: string } | null>(null)
-  const activeQueueSessionKeyRef = useRef(activeQueueSessionKey)
-  activeQueueSessionKeyRef.current = activeQueueSessionKey
   const drainingQueueRef = useRef(false)
   const urlInputRef = useRef<HTMLInputElement | null>(null)
 
@@ -196,17 +156,14 @@ export function ChatBar({
   const [dragActive, setDragActive] = useState(false)
   const [queueEdit, setQueueEdit] = useState<QueueEditState | null>(null)
   const [focusRequestId, setFocusRequestId] = useState(0)
-  const queueEditRef = useRef(queueEdit)
-  queueEditRef.current = queueEdit
   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)')
 
-  const { availableThemes, themeName } = useTheme()
   const at = useAtCompletions({ gateway: gateway ?? null, sessionId: sessionId ?? null, cwd: cwd ?? null })
-  const slash = useSlashCompletions({ activeSkin: themeName, gateway: gateway ?? null, skinThemes: availableThemes })
+  const slash = useSlashCompletions({ gateway: gateway ?? null })
 
   const stacked = expanded || narrow || tight
   const trimmedDraft = draft.trim()
@@ -214,12 +171,10 @@ export function ChatBar({
   const canSubmit = busy || hasComposerPayload
   const editingQueuedPrompt = queueEdit ? (queuedPrompts.find(entry => entry.id === queueEdit.entryId) ?? null) : null
   const busyAction = busy && hasComposerPayload ? 'queue' : 'stop'
-
   // Steer only makes sense mid-turn, text-only (the gateway can't carry images
   // into a tool result) and never for a slash command (those execute inline).
   const canSteer =
     busy && !!onSteer && attachments.length === 0 && trimmedDraft.length > 0 && !SLASH_COMMAND_RE.test(trimmedDraft)
-
   const showHelpHint = draft === '?'
 
   const { t } = useI18n()
@@ -507,6 +462,12 @@ export function ChatBar({
     })
   }, [])
 
+  const selectSkinSlashCommand = (command: string) => {
+    draftRef.current = command
+    aui.composer().setText(command)
+    requestMainFocus()
+  }
+
   const handlePaste = (event: ClipboardEvent<HTMLDivElement>) => {
     const imageBlobs = extractClipboardImageBlobs(event.clipboardData)
 
@@ -659,50 +620,16 @@ export function ChatBar({
       return
     }
 
-    // Action items (e.g. "Browse all sessions…") run a side effect instead of
-    // inserting a chip: strip the typed trigger token, then fire the action.
-    const completionAction = (item.metadata as { action?: unknown } | undefined)?.action
-    const runAction = typeof completionAction === 'string' ? COMPLETION_ACTIONS[completionAction] : undefined
-
-    if (runAction) {
-      const current = composerPlainText(editor)
-      const prefix = current.slice(0, Math.max(0, current.length - trigger.tokenLength))
-
-      renderComposerContents(editor, prefix)
-      placeCaretEnd(editor)
-      draftRef.current = composerPlainText(editor)
-      aui.composer().setText(draftRef.current)
-      closeTrigger()
-      runAction()
-      requestMainFocus()
-
-      return
-    }
-
     const serialized = hermesDirectiveFormatter.serialize(item)
     const starter = serialized.endsWith(':')
-
-    // Picking a bare arg-taking command (e.g. `/personality`) shouldn't commit
-    // it — expand to its options step so the popover shows the inline list, just
-    // as typing `/personality ` by hand would. A serialized value with a space is
-    // already an arg pick (`/personality alice`), so it commits normally.
-    const command = (item.metadata as { command?: string } | undefined)?.command ?? ''
-
-    const expandsToArgs =
-      trigger.kind === '/' && !serialized.includes(' ') && desktopSlashCommandTakesArgs(command)
-
     const text = starter || serialized.endsWith(' ') ? serialized : `${serialized} `
     const directive = !starter && serialized.match(/^@([^:]+):(.+)$/)
-    // No pill while expanding — the bare command stays plain text until an arg
-    // is picked, at which point a single pill is emitted for the full command.
-    const slashKind = !expandsToArgs && trigger.kind === '/' ? slashChipKindForItem(item) : null
-    const keepTriggerOpen = starter || expandsToArgs
 
     const finish = () => {
       draftRef.current = composerPlainText(editor)
       aui.composer().setText(draftRef.current)
       requestMainFocus()
-      keepTriggerOpen ? window.setTimeout(refreshTrigger, 0) : closeTrigger()
+      starter ? window.setTimeout(refreshTrigger, 0) : closeTrigger()
     }
 
     const sel = window.getSelection()
@@ -712,20 +639,7 @@ export function ChatBar({
 
     if (!sel || !range || node?.nodeType !== Node.TEXT_NODE || offset < trigger.tokenLength) {
       const current = composerPlainText(editor)
-      const prefix = current.slice(0, Math.max(0, current.length - trigger.tokenLength))
-
-      if (slashKind) {
-        // Two-step arg picks (e.g. `/handoff` pill already inserted, now picking
-        // the platform) land here because the caret sits past a contenteditable
-        // chip. Rebuild the prefix and re-emit a single pill for the full command.
-        renderComposerContents(editor, prefix)
-        editor.append(slashChipElement(serialized, slashKind), document.createTextNode(' '))
-        placeCaretEnd(editor)
-
-        return finish()
-      }
-
-      renderComposerContents(editor, `${prefix}${text}`)
+      renderComposerContents(editor, `${current.slice(0, Math.max(0, current.length - trigger.tokenLength))}${text}`)
       placeCaretEnd(editor)
 
       return finish()
@@ -736,13 +650,8 @@ export function ChatBar({
     replaceRange.setEnd(node, offset)
     replaceRange.deleteContents()
 
-    const chip = slashKind
-      ? slashChipElement(serialized, slashKind)
-      : directive
-        ? refChipElement(directive[1], directive[2])
-        : null
-
-    if (chip) {
+    if (directive) {
+      const chip = refChipElement(directive[1], directive[2])
       const space = document.createTextNode(' ')
       const fragment = document.createDocumentFragment()
       fragment.append(chip, space)
@@ -905,16 +814,7 @@ export function ChatBar({
     if (event.key === 'Enter' && !event.shiftKey) {
       event.preventDefault()
 
-      // Decide from the DOM, not React state. `hasComposerPayload` is derived
-      // from the AUI composer state, which lags the latest keystroke by a
-      // render, so on fast typing / IME the just-typed text isn't in state yet.
-      // Without the live read, a real message typed while prompts are queued
-      // would drain the queue instead of sending. submitDraft() re-syncs and
-      // sends the live editor text.
-      const editorText = editorRef.current ? composerPlainText(editorRef.current) : draftRef.current
-      const hasLivePayload = editorText.trim().length > 0 || attachments.length > 0
-
-      if (!busy && !hasLivePayload && queuedPrompts.length > 0) {
+      if (!busy && !hasComposerPayload && queuedPrompts.length > 0) {
         void drainNextQueued()
 
         return
@@ -922,10 +822,7 @@ export function ChatBar({
 
       // Empty Enter while busy is a no-op — interrupting is explicit (Stop/Esc),
       // never a stray Enter after sending. With a payload, submitDraft queues it.
-      // Gate on the live DOM payload (not the render-lagged composer state) so a
-      // message typed fast / via IME while busy still reaches submitDraft() and
-      // gets queued instead of being mistaken for an empty Enter.
-      if (busy && !hasLivePayload) {
+      if (busy && !hasComposerPayload) {
         return
       }
 
@@ -1022,25 +919,24 @@ export function ChatBar({
       return
     }
 
-    // In-app drags (project tree / gutter) are workspace-relative paths the
-    // gateway resolves directly, so they stay inline @file:/@line: refs. OS
-    // drops are absolute local paths a remote gateway can't read (and images
-    // need byte upload for vision), so route them through the upload pipeline.
-    const { inAppRefs, osDrops } = partitionDroppedFiles(candidates)
-    const refs = droppedFileInlineRefs(inAppRefs, cwd)
+    if (Array.from(event.dataTransfer.types || []).includes(HERMES_PATHS_MIME)) {
+      const refs = candidates
+        .map(candidate => droppedFileInlineRef(candidate, cwd))
+        .filter((ref): ref is string => Boolean(ref))
 
-    if (refs.length && insertInlineRefs(refs)) {
-      triggerHaptic('selection')
+      if (insertInlineRefs(refs)) {
+        triggerHaptic('selection')
+      }
+
+      return
     }
 
-    if (osDrops.length) {
-      void Promise.resolve(onAttachDroppedItems(osDrops)).then(attached => {
-        if (attached) {
-          triggerHaptic('selection')
-          requestMainFocus()
-        }
-      })
-    }
+    void Promise.resolve(onAttachDroppedItems(candidates)).then(attached => {
+      if (attached) {
+        triggerHaptic('selection')
+        requestMainFocus()
+      }
+    })
   }
 
   const handleInputDragOver = (event: ReactDragEvent<HTMLDivElement>) => {
@@ -1060,7 +956,11 @@ export function ChatBar({
 
     const candidates = extractDroppedFiles(event.dataTransfer)
 
-    if (!candidates.length) {
+    const refs = candidates
+      .map(candidate => droppedFileInlineRef(candidate, cwd))
+      .filter((ref): ref is string => Boolean(ref))
+
+    if (!refs.length) {
       return
     }
 
@@ -1068,27 +968,9 @@ export function ChatBar({
     event.stopPropagation()
     resetDragState()
 
-    // Dropping straight onto the text box used to inline-ref *every* file —
-    // including OS/Finder drops, whose absolute local path a remote gateway
-    // can't read and whose image bytes never reached vision. Split by origin:
-    // in-app drags stay inline refs; OS drops go through the upload pipeline.
-    // (When no upload handler is wired, fall back to inline refs for all.)
-    const attach = onAttachDroppedItems
-    const { inAppRefs, osDrops } = partitionDroppedFiles(candidates)
-    const refs = droppedFileInlineRefs(attach ? inAppRefs : candidates, cwd)
-
-    if (refs.length && insertInlineRefs(refs)) {
+    if (insertInlineRefs(refs)) {
       triggerHaptic('selection')
     }
-
-    if (attach && osDrops.length) {
-      void Promise.resolve(attach(osDrops)).then(attached => {
-        if (attached) {
-          triggerHaptic('selection')
-          requestMainFocus()
-        }
-      })
-    }
   }
 
   const clearDraft = useCallback(() => {
@@ -1113,69 +995,6 @@ export function ChatBar({
     }
   }
 
-  const stashAt = (
-    scope: string | null,
-    text = draftRef.current,
-    attachments = $composerAttachments.get()
-  ) => stashSessionDraft(scope, text, attachments)
-
-  // Per-thread draft swap — the composer's only session coupling. Lifecycle
-  // never clears composer state; this effect alone stashes on leave, restores
-  // on enter. Keyed writes are idempotent, so no skip-sentinel.
-  useEffect(() => {
-    const { attachments, text } = takeSessionDraft(activeQueueSessionKey)
-    loadIntoComposer(text, attachments)
-
-    return () => {
-      const editing = queueEditRef.current
-
-      if (editing?.sessionKey === activeQueueSessionKey) {
-        stashAt(activeQueueSessionKey, editing.draft, editing.attachments)
-      } else if (!isBrowsingHistory(sessionId)) {
-        stashAt(activeQueueSessionKey)
-      }
-    }
-  }, [activeQueueSessionKey]) // eslint-disable-line react-hooks/exhaustive-deps
-
-  // Debounced stash into the active scope. Skipped while browsing history or
-  // editing a queued prompt — recalled text must not clobber the real draft.
-  useEffect(() => {
-    if (isBrowsingHistory(sessionId) || queueEdit) {
-      return
-    }
-
-    pendingDraftPersistRef.current = { scope: activeQueueSessionKey, text: draft }
-
-    const handle = window.setTimeout(() => {
-      pendingDraftPersistRef.current = null
-      stashAt(activeQueueSessionKey, draft)
-    }, DRAFT_PERSIST_DEBOUNCE_MS)
-
-    return () => window.clearTimeout(handle)
-  }, [activeQueueSessionKey, draft, queueEdit, sessionId])
-
-  // pagehide is load-bearing: React skips effect cleanups on reload, so Cmd+R
-  // inside the debounce window would drop trailing keystrokes without this.
-  useEffect(() => {
-    const flushPendingDraftPersist = () => {
-      const pending = pendingDraftPersistRef.current
-
-      if (!pending) {
-        return
-      }
-
-      pendingDraftPersistRef.current = null
-      stashAt(pending.scope, pending.text)
-    }
-
-    window.addEventListener('pagehide', flushPendingDraftPersist)
-
-    return () => {
-      window.removeEventListener('pagehide', flushPendingDraftPersist)
-      flushPendingDraftPersist()
-    }
-  }, [])
-
   const beginQueuedEdit = (entry: QueuedPromptEntry) => {
     if (!activeQueueSessionKey || queueEdit) {
       return
@@ -1378,61 +1197,21 @@ export function ChatBar({
     }
   }, [busy, drainNextQueued, queuedPrompts.length])
 
-  // Queue-edit cleanup: on session swap the scope effect already stashed the
-  // edit snapshot; only restore into the composer when still on the same scope.
+  // Clean up queue edit when its target disappears (session swap or external delete).
   useEffect(() => {
     if (!queueEdit) {
       return
     }
 
-    if (queueEdit.sessionKey === activeQueueSessionKey) {
-      if (editingQueuedPrompt) {
-        return
-      }
-
-      loadIntoComposer(queueEdit.draft, queueEdit.attachments)
+    if (queueEdit.sessionKey === activeQueueSessionKey && editingQueuedPrompt) {
+      return
     }
 
+    loadIntoComposer(queueEdit.draft, queueEdit.attachments)
     setQueueEdit(null)
   }, [activeQueueSessionKey, editingQueuedPrompt, queueEdit]) // eslint-disable-line react-hooks/exhaustive-deps
 
-  const dispatchSubmit = (text: string, attachments?: ComposerAttachment[]) => {
-    const submittedScope = activeQueueSessionKeyRef.current
-    const submittedAttachments = attachments ?? []
-
-    const restore = () => {
-      loadIntoComposer(text, submittedAttachments)
-      stashAt(activeQueueSessionKeyRef.current, text, submittedAttachments)
-    }
-
-    void Promise.resolve(attachments ? onSubmit(text, { attachments }) : onSubmit(text))
-      .then(accepted => void (accepted === false ? restore() : clearSessionDraft(submittedScope)))
-      .catch(restore)
-  }
-
   const submitDraft = () => {
-    // Source the text from the DOM editor, not React state. The AUI composer
-    // state (`draft`) and the derived `hasComposerPayload` lag the DOM by a
-    // render, so on fast typing or IME composition the final keystroke(s) may
-    // not have synced yet — reading state here drops the message (Enter looks
-    // like it does nothing; typing a trailing space only "fixes" it because the
-    // extra input event forces a state sync). draftRef is updated on every
-    // input event; refresh it from the editor once more to also cover an
-    // in-flight keystroke that hasn't fired its input event yet.
-    const editor = editorRef.current
-
-    if (editor) {
-      const domText = composerPlainText(editor)
-
-      if (domText !== draftRef.current) {
-        draftRef.current = domText
-        aui.composer().setText(domText)
-      }
-    }
-
-    const text = draftRef.current
-    const payloadPresent = text.trim().length > 0 || attachments.length > 0
-
     if (queueEdit) {
       exitQueuedEdit('save')
     } else if (busy) {
@@ -1443,11 +1222,12 @@ export function ChatBar({
       // busy guard for commands that genuinely need an idle session (skill
       // /send directives).  Queuing them would make every slash command wait
       // for the current turn to finish, which is how the TUI never behaves.
-      if (!attachments.length && SLASH_COMMAND_RE.test(text.trim())) {
+      if (!attachments.length && SLASH_COMMAND_RE.test(draft.trim())) {
+        const submitted = draft
         triggerHaptic('submit')
         clearDraft()
-        dispatchSubmit(text)
-      } else if (payloadPresent) {
+        void onSubmit(submitted)
+      } else if (hasComposerPayload) {
         queueCurrentDraft()
       } else {
         // Stop button (the only way to reach here while busy with an empty
@@ -1455,15 +1235,15 @@ export function ChatBar({
         triggerHaptic('cancel')
         void Promise.resolve(onCancel())
       }
-    } else if (!payloadPresent && queuedPrompts.length > 0) {
+    } else if (!hasComposerPayload && queuedPrompts.length > 0) {
       void drainNextQueued()
-    } else if (payloadPresent) {
-      const submittedAttachments = cloneAttachments(attachments)
+    } else if (draft.trim() || attachments.length > 0) {
+      const submitted = draft
       triggerHaptic('submit')
       resetBrowseState(sessionId)
       clearDraft()
       clearComposerAttachments()
-      dispatchSubmit(text, submittedAttachments)
+      void onSubmit(submitted, { attachments })
     }
 
     focusInput()
@@ -1630,7 +1410,7 @@ export function ChatBar({
         onPaste={handlePaste}
         ref={editorRef}
         role="textbox"
-        spellCheck={false}
+        spellCheck="true"
         suppressContentEditableWarning
       />
       {/* assistant-ui requires ComposerPrimitive.Input somewhere in the tree
@@ -1649,15 +1429,7 @@ export function ChatBar({
         `asChild` swaps TextareaAutosize for a Radix Slot wrapping our
         plain <textarea>, which carries the binding but skips autosize. */}
       <ComposerPrimitive.Input asChild submitMode="ctrlEnter" tabIndex={-1} unstable_focusOnScrollToBottom={false}>
-        <textarea
-          aria-hidden
-          autoCapitalize="off"
-          autoComplete="off"
-          autoCorrect="off"
-          className="sr-only"
-          spellCheck={false}
-          tabIndex={-1}
-        />
+        <textarea aria-hidden className="sr-only" tabIndex={-1} />
       </ComposerPrimitive.Input>
     </div>
   )
@@ -1696,6 +1468,7 @@ export function ChatBar({
               onPick={replaceTriggerWithChip}
             />
           )}
+          <SkinSlashPopover draft={draft} onSelect={selectSkinSlashCommand} />
           {activeQueueSessionKey && queuedPrompts.length > 0 && (
             // Out of flow so the queue never inflates the composer's measured
             // height (that drives thread bottom padding → chat resizes on

apps/desktop/src/app/chat/composer/inline-refs.ts

@@ -83,12 +83,6 @@ export function droppedFileInlineRef(candidate: DroppedFile, cwd: string | null
   return `@${kind}:${formatRefValue(rel)}`
 }
 
-/** Resolve a batch of drops to their inline `@file:`/`@line:`/`@folder:` refs,
- * dropping any that carry no path. */
-export function droppedFileInlineRefs(candidates: DroppedFile[], cwd: string | null | undefined): string[] {
-  return candidates.map(candidate => droppedFileInlineRef(candidate, cwd)).filter((ref): ref is string => Boolean(ref))
-}
-
 export function insertInlineRefsIntoEditor(editor: HTMLDivElement, refs: readonly InlineRefInput[]) {
   if (!refs.length) {
     return null

apps/desktop/src/app/chat/composer/rich-editor.ts

@@ -10,10 +10,7 @@ import {
   DIRECTIVE_CHIP_CLASS,
   directiveIconElement,
   directiveIconSvg,
-  formatRefValue,
-  slashChipClass,
-  type SlashChipKind,
-  slashIconElement
+  formatRefValue
 } from '@/components/assistant-ui/directive-text'
 
 export const RICH_INPUT_SLOT = 'composer-rich-input'
@@ -80,24 +77,6 @@ export function refChipElement(kind: string, rawValue: string, displayLabel?: st
   return chip
 }
 
-/** A non-editable pill for a picked slash command (`/skin nous`, `/tropes`).
- *  `data-ref-text` carries the literal command so `composerPlainText` round-trips
- *  it back to the exact text that gets submitted. */
-export function slashChipElement(command: string, kind: SlashChipKind, label?: string) {
-  const chip = document.createElement('span')
-  const text = document.createElement('span')
-
-  chip.contentEditable = 'false'
-  chip.dataset.refText = command
-  chip.dataset.slashKind = kind
-  chip.className = slashChipClass(kind)
-  text.className = 'truncate'
-  text.textContent = label || command
-  chip.append(slashIconElement(kind), text)
-
-  return chip
-}
-
 function appendTextWithBreaks(target: DocumentFragment | HTMLElement, text: string) {
   const lines = text.split('\n')
 

apps/desktop/src/app/chat/composer/skin-slash-popover.tsx

@@ -0,0 +1,61 @@
+import { useI18n } from '@/i18n'
+import { desktopSkinSlashCompletions } from '@/lib/desktop-slash-commands'
+import { triggerHaptic } from '@/lib/haptics'
+import { useTheme } from '@/themes/context'
+
+import { COMPLETION_DRAWER_CLASS, COMPLETION_DRAWER_ROW_CLASS, CompletionDrawerEmpty } from './completion-drawer'
+
+interface SkinSlashPopoverProps {
+  draft: string
+  onSelect: (command: string) => void
+}
+
+export function SkinSlashPopover({ draft, onSelect }: SkinSlashPopoverProps) {
+  const { t } = useI18n()
+  const c = t.composer
+  const { availableThemes, themeName } = useTheme()
+  const match = draft.match(/^\/skin\s+(\S*)$/i)
+
+  if (!match) {
+    return null
+  }
+
+  const items = desktopSkinSlashCompletions(availableThemes, themeName, match[1] ?? '')
+
+  return (
+    <div
+      aria-label={c.themeSuggestions}
+      className={COMPLETION_DRAWER_CLASS}
+      data-slot="composer-skin-completion-drawer"
+      data-state="open"
+      role="listbox"
+    >
+      <div className="grid gap-0.5 pt-0.5">
+        {items.length === 0 ? (
+          <CompletionDrawerEmpty title={c.noMatchingThemes}>
+            {c.themeTryPre}
+            <span className="font-mono text-foreground/80">/skin list</span>
+            {c.themeTryPost}
+          </CompletionDrawerEmpty>
+        ) : (
+          items.map(item => (
+            <button
+              className={COMPLETION_DRAWER_ROW_CLASS}
+              key={item.text}
+              onClick={() => {
+                triggerHaptic('selection')
+                onSelect(item.text)
+              }}
+              onMouseDown={event => event.preventDefault()}
+              role="option"
+              type="button"
+            >
+              <span className="shrink-0 font-mono font-medium leading-5 text-foreground">{item.display}</span>
+              <span className="min-w-0 truncate leading-5 text-muted-foreground/80">{item.meta}</span>
+            </button>
+          ))
+        )}
+      </div>
+    </div>
+  )
+}

apps/desktop/src/app/chat/composer/text-utils.test.ts

@@ -22,33 +22,6 @@ describe('detectTrigger', () => {
   it('returns null for plain text', () => {
     expect(detectTrigger('hello there')).toBeNull()
   })
-
-  it('keeps the slash trigger live while typing args', () => {
-    expect(detectTrigger('/personality ')).toEqual({
-      kind: '/',
-      query: 'personality ',
-      tokenLength: 13
-    })
-    expect(detectTrigger('/personality alic')).toEqual({
-      kind: '/',
-      query: 'personality alic',
-      tokenLength: 17
-    })
-    expect(detectTrigger('/tools enable foo')).toEqual({
-      kind: '/',
-      query: 'tools enable foo',
-      tokenLength: 17
-    })
-  })
-
-  it('does not treat file-style paths as slash triggers', () => {
-    expect(detectTrigger('src/foo/bar')).toBeNull()
-    expect(detectTrigger('/path/to/file')).toBeNull()
-  })
-
-  it('still anchors at-mention triggers strictly at the token edge', () => {
-    expect(detectTrigger('@file:path with space')).toBeNull()
-  })
 })
 
 describe('extractClipboardImageBlobs', () => {

apps/desktop/src/app/chat/composer/text-utils.ts

@@ -6,13 +6,7 @@ export interface TriggerState {
   tokenLength: number
 }
 
-// `@` triggers stop at the first whitespace — `@file:path` and `@diff` are
-// single tokens. `/` triggers keep going so the popover stays live while the
-// user types args (`/personality alic` → arg completer suggests `alice`).
-// Restricting the slash command name to `[a-zA-Z][\w-]*` avoids matching file
-// paths like `src/foo/bar`.
-const AT_TRIGGER_RE = /(?:^|[\s])(@)([^\s@/]*)$/
-const SLASH_TRIGGER_RE = /(?:^|[\s])(\/)((?:[a-zA-Z][\w-]*(?:\s+\S*)*)?)$/
+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 {
@@ -103,17 +97,11 @@ export function textBeforeCaret(editor: HTMLDivElement): string | null {
 }
 
 export function detectTrigger(textBefore: string): TriggerState | null {
-  const slash = SLASH_TRIGGER_RE.exec(textBefore)
+  const match = TRIGGER_RE.exec(textBefore)
 
-  if (slash) {
-    return { kind: '/', query: slash[2], tokenLength: 1 + slash[2].length }
+  if (!match) {
+    return null
   }
 
-  const at = AT_TRIGGER_RE.exec(textBefore)
-
-  if (at) {
-    return { kind: '@', query: at[2], tokenLength: 1 + at[2].length }
-  }
-
-  return null
+  return { kind: match[1] as '@' | '/', query: match[2], tokenLength: 1 + match[2].length }
 }

apps/desktop/src/app/chat/composer/trigger-popover.test.tsx

@@ -34,17 +34,9 @@ describe('ComposerTriggerPopover i18n', () => {
   })
 
   it('renders localized loading copy for slash commands', () => {
-    renderPopover('/', true)
+    const { container } = renderPopover('/', true)
 
-    // While loading the popover shows only the spinner + loading copy — the
-    // `/help` empty-state hint is reserved for the resolved (not-loading) state.
     expect(screen.getByText('查找中…')).toBeTruthy()
-  })
-
-  it('renders the slash empty-state hint when not loading', () => {
-    const { container } = renderPopover('/')
-
-    expect(screen.getByText('没有匹配项。')).toBeTruthy()
     expect(container.textContent).toContain('/help')
   })
 })

apps/desktop/src/app/chat/composer/trigger-popover.tsx

@@ -1,7 +1,5 @@
 import type { Unstable_TriggerItem } from '@assistant-ui/core'
-import { Fragment } from 'react'
 
-import { BrailleSpinner } from '@/components/ui/braille-spinner'
 import { Codicon } from '@/components/ui/codicon'
 import { useI18n } from '@/i18n'
 import { cn } from '@/lib/utils'
@@ -9,6 +7,7 @@ import { cn } from '@/lib/utils'
 import {
   COMPLETION_DRAWER_BELOW_CLASS,
   COMPLETION_DRAWER_CLASS,
+  COMPLETION_DRAWER_ROW_CLASS,
   CompletionDrawerEmpty
 } from './completion-drawer'
 
@@ -24,7 +23,11 @@ const AT_ICON_BY_TYPE: Record<string, string> = {
   url: 'globe'
 }
 
-function atIcon(item: Unstable_TriggerItem) {
+function completionIcon(kind: '@' | '/', item: Unstable_TriggerItem) {
+  if (kind === '/') {
+    return 'terminal'
+  }
+
   const meta = item.metadata as { rawText?: string } | undefined
   const raw = meta?.rawText || item.label
 
@@ -39,18 +42,6 @@ function atIcon(item: Unstable_TriggerItem) {
   return AT_ICON_BY_TYPE[item.type] || AT_ICON_BY_TYPE.simple
 }
 
-interface RowMeta {
-  display?: string
-  group?: string
-  meta?: string
-}
-
-const ROW_BASE_CLASS = [
-  'relative flex w-full cursor-default select-none rounded-md px-2 py-1 text-left',
-  'outline-hidden transition-colors hover:bg-(--ui-bg-tertiary)',
-  'data-[highlighted]:bg-(--ui-bg-tertiary) data-[highlighted]:text-foreground'
-].join(' ')
-
 interface ComposerTriggerPopoverProps {
   activeIndex: number
   items: readonly Unstable_TriggerItem[]
@@ -72,9 +63,6 @@ export function ComposerTriggerPopover({
 }: ComposerTriggerPopoverProps) {
   const { t } = useI18n()
   const copy = t.composer
-  const isSlash = kind === '/'
-
-  let lastGroup: string | undefined
 
   return (
     <div
@@ -85,94 +73,41 @@ export function ComposerTriggerPopover({
       role="listbox"
     >
       {items.length === 0 ? (
-        loading ? (
-          <div className="flex items-center gap-2 px-2 py-1.5 text-(--ui-text-tertiary)">
-            <BrailleSpinner ariaLabel={copy.lookupLoading} className="text-foreground/70" spinner="braille" />
-            <span>{copy.lookupLoading}</span>
-          </div>
-        ) : (
-          <CompletionDrawerEmpty title={copy.lookupNoMatches}>
-            {kind === '@' ? (
-              <>
-                {copy.lookupTry} <span className="font-mono text-foreground/80">@file:</span> {copy.lookupOr}{' '}
-                <span className="font-mono text-foreground/80">@folder:</span>.
-              </>
-            ) : (
-              <>
-                {copy.lookupTry} <span className="font-mono text-foreground/80">/help</span>.
-              </>
-            )}
-          </CompletionDrawerEmpty>
-        )
+        <CompletionDrawerEmpty title={loading ? copy.lookupLoading : copy.lookupNoMatches}>
+          {kind === '@' ? (
+            <>
+              {copy.lookupTry} <span className="font-mono text-foreground/80">@file:</span> {copy.lookupOr}{' '}
+              <span className="font-mono text-foreground/80">@folder:</span>.
+            </>
+          ) : (
+            <>
+              {copy.lookupTry} <span className="font-mono text-foreground/80">/help</span>.
+            </>
+          )}
+        </CompletionDrawerEmpty>
       ) : (
         items.map((item, index) => {
-          const meta = item.metadata as RowMeta | undefined
-          const display = meta?.display ?? (isSlash ? `/${item.label}` : item.label)
+          const meta = item.metadata as { display?: string; meta?: string } | undefined
+          const display = meta?.display ?? (kind === '/' ? `/${item.label}` : item.label)
           const description = meta?.meta || item.description
-          const group = meta?.group?.trim()
-          const showHeader = isSlash && Boolean(group) && group !== lastGroup
-          const isFirstHeader = lastGroup === undefined
-          lastGroup = group || lastGroup
-          const active = index === activeIndex
 
           return (
-            <Fragment key={item.id}>
-              {showHeader && (
-                <div
-                  className={cn(
-                    'select-none px-2 pb-0.5 text-[0.625rem] font-semibold uppercase tracking-wider text-(--ui-text-tertiary)',
-                    isFirstHeader ? 'pt-0.5' : 'pt-2'
-                  )}
-                >
-                  {group}
-                </div>
+            <button
+              className={cn(COMPLETION_DRAWER_ROW_CLASS, index === activeIndex && 'bg-(--ui-bg-tertiary)')}
+              data-highlighted={index === activeIndex ? '' : undefined}
+              key={item.id}
+              onClick={() => onPick(item)}
+              onMouseEnter={() => onHover(index)}
+              type="button"
+            >
+              <span className="grid size-3.5 shrink-0 place-items-center text-(--ui-text-tertiary)">
+                <Codicon name={completionIcon(kind, item)} size="0.875rem" />
+              </span>
+              <span className="min-w-0 shrink truncate font-mono font-medium leading-5 text-foreground">{display}</span>
+              {description && (
+                <span className="min-w-0 flex-1 truncate leading-5 text-(--ui-text-tertiary)">{description}</span>
               )}
-              <button
-                className={cn(ROW_BASE_CLASS, isSlash ? 'flex-col gap-0' : 'items-center gap-2')}
-                data-highlighted={active ? '' : undefined}
-                onClick={() => onPick(item)}
-                onMouseEnter={() => onHover(index)}
-                type="button"
-              >
-                {isSlash ? (
-                  <>
-                    {/* Active row (keyboard nav or hover) un-truncates inline so
-                        long command names / descriptions stay readable without a
-                        floating tooltip. */}
-                    <span
-                      className={cn(
-                        'text-[0.8125rem] font-medium leading-snug text-foreground',
-                        active ? 'whitespace-normal break-words' : 'truncate'
-                      )}
-                    >
-                      {display}
-                    </span>
-                    {description && (
-                      <span
-                        className={cn(
-                          'text-[0.6875rem] leading-snug text-(--ui-text-tertiary)',
-                          active ? 'whitespace-normal break-words' : 'truncate'
-                        )}
-                      >
-                        {description}
-                      </span>
-                    )}
-                  </>
-                ) : (
-                  <>
-                    <span className="grid size-4 shrink-0 place-items-center text-(--ui-text-tertiary)">
-                      <Codicon name={atIcon(item)} size="0.875rem" />
-                    </span>
-                    <span className="min-w-0 shrink truncate font-mono font-medium leading-5 text-foreground">
-                      {display}
-                    </span>
-                    {description && (
-                      <span className="min-w-0 flex-1 truncate leading-5 text-(--ui-text-tertiary)">{description}</span>
-                    )}
-                  </>
-                )}
-              </button>
-            </Fragment>
+            </button>
           )
         })
       )}

apps/desktop/src/app/chat/hooks/use-composer-actions.test.ts

@@ -1,57 +0,0 @@
-import { describe, expect, it } from 'vitest'
-
-import { type DroppedFile, partitionDroppedFiles } from './use-composer-actions'
-
-// A Finder/Explorer drop carries a native File handle; an in-app drag (project
-// tree, gutter line ref) is path-only. The split decides whether a drop becomes
-// an inline @file: ref (in-app, workspace-relative, gateway-resolvable) or goes
-// through the upload pipeline (OS drop — absolute local path a remote gateway
-// can't read, plus image bytes for vision).
-const osDrop = (path: string): DroppedFile => ({ file: new File(['x'], path.split('/').pop() || 'f'), path })
-const inAppRef = (path: string, extra: Partial<DroppedFile> = {}): DroppedFile => ({ path, ...extra })
-
-describe('partitionDroppedFiles', () => {
-  it('routes File-bearing OS drops to osDrops and path-only in-app drags to inAppRefs', () => {
-    const finderPdf = osDrop('/Users/mahmoud/Downloads/DEVIS_signed.pdf')
-    const projectFile = inAppRef('src/index.ts')
-
-    const { inAppRefs, osDrops } = partitionDroppedFiles([finderPdf, projectFile])
-
-    expect(osDrops).toEqual([finderPdf])
-    expect(inAppRefs).toEqual([projectFile])
-  })
-
-  it('treats an OS screenshot drop as an upload target (so it gets byte upload + vision)', () => {
-    const screenshot = osDrop('/var/folders/tmp/Screenshot 2026-06-09.png')
-
-    const { inAppRefs, osDrops } = partitionDroppedFiles([screenshot])
-
-    expect(osDrops).toEqual([screenshot])
-    expect(inAppRefs).toEqual([])
-  })
-
-  it('keeps gutter line-range drags inline (no File handle)', () => {
-    const lineRef = inAppRef('src/app.ts', { line: 10, lineEnd: 20 })
-
-    const { inAppRefs, osDrops } = partitionDroppedFiles([lineRef])
-
-    expect(osDrops).toEqual([])
-    expect(inAppRefs).toEqual([lineRef])
-  })
-
-  it('splits a mixed drop and preserves order within each group', () => {
-    const a = inAppRef('a.ts')
-    const b = osDrop('/abs/b.pdf')
-    const c = inAppRef('c.ts')
-    const d = osDrop('/abs/d.png')
-
-    const { inAppRefs, osDrops } = partitionDroppedFiles([a, b, c, d])
-
-    expect(inAppRefs).toEqual([a, c])
-    expect(osDrops).toEqual([b, d])
-  })
-
-  it('returns empty groups for an empty drop', () => {
-    expect(partitionDroppedFiles([])).toEqual({ inAppRefs: [], osDrops: [] })
-  })
-})

apps/desktop/src/app/chat/hooks/use-composer-actions.ts

@@ -33,7 +33,7 @@ function blobExtension(blob: Blob): string {
   return (mime && BLOB_MIME_EXTENSION[mime]) || '.png'
 }
 
-export function isImagePath(filePath: string): boolean {
+function isImagePath(filePath: string): boolean {
   return IMAGE_EXTENSION_PATTERN.test(filePath)
 }
 
@@ -181,35 +181,6 @@ export function extractDroppedFiles(transfer: DataTransfer): DroppedFile[] {
   return result
 }
 
-/**
- * Split dropped entries by origin. OS/Finder drops carry a native `File`
- * handle; in-app drags (project tree, gutter line refs) are path-only.
- *
- * The distinction is load-bearing: an in-app path is workspace-relative and
- * resolves on the gateway as-is, so it stays an inline `@file:`/`@line:` ref.
- * An OS drop is an absolute path on *this* machine — the gateway can't read it
- * in remote mode, and an image needs its bytes uploaded to get vision either
- * way. So OS drops must go through the attachment/upload pipeline rather than
- * leaking a local path into the prompt text.
- */
-export function partitionDroppedFiles(candidates: DroppedFile[]): {
-  osDrops: DroppedFile[]
-  inAppRefs: DroppedFile[]
-} {
-  const osDrops: DroppedFile[] = []
-  const inAppRefs: DroppedFile[] = []
-
-  for (const candidate of candidates) {
-    if (candidate.file) {
-      osDrops.push(candidate)
-    } else {
-      inAppRefs.push(candidate)
-    }
-  }
-
-  return { osDrops, inAppRefs }
-}
-
 interface ComposerActionsOptions {
   activeSessionId: string | null
   currentCwd: string

apps/desktop/src/app/chat/index.tsx

@@ -49,9 +49,9 @@ import { ChatDropOverlay } from './chat-drop-overlay'
 import { ChatSwapOverlay } from './chat-swap-overlay'
 import { ChatBar, ChatBarFallback } from './composer'
 import { requestComposerInsert, requestComposerInsertRefs } from './composer/focus'
-import { droppedFileInlineRefs, type SessionDragPayload, sessionInlineRef } from './composer/inline-refs'
+import { droppedFileInlineRef, type SessionDragPayload, sessionInlineRef } from './composer/inline-refs'
 import type { ChatBarState } from './composer/types'
-import { type DroppedFile, partitionDroppedFiles } from './hooks/use-composer-actions'
+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'
@@ -126,10 +126,7 @@ function ChatHeader({
     <header className={cn(titlebarHeaderBaseClass, isRoutedSessionView && titlebarHeaderShadowClass)}>
       <div
         className="min-w-0 flex-1"
-        style={{
-          maxWidth:
-            'calc(100vw - var(--titlebar-content-inset,0px) - var(--titlebar-tools-right) - var(--titlebar-tools-width) - 1.5rem)'
-        }}
+        style={{ maxWidth: 'calc(100vw - var(--titlebar-content-inset,0px) - var(--titlebar-tools-right) - var(--titlebar-tools-width) - 1.5rem)' }}
       >
         <SessionActionsMenu
           align="start"
@@ -302,25 +299,19 @@ export function ChatView({
   })
 
   // Drop files anywhere in the conversation area, not just on the composer
-  // input. In-app drags (project tree / gutter) carry workspace-relative paths
-  // the gateway resolves directly, so they stay inline `@file:` refs. OS/Finder
-  // drops carry absolute local paths that don't exist on a remote gateway (and
-  // images need byte upload for vision), so route them through the attachment
-  // pipeline — otherwise the local path leaks into the prompt verbatim.
+  // 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 { inAppRefs, osDrops } = partitionDroppedFiles(candidates)
-      const refs = droppedFileInlineRefs(inAppRefs, currentCwd)
+      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' })
       }
-
-      if (osDrops.length) {
-        void onAttachDroppedItems(osDrops)
-      }
     },
-    [currentCwd, onAttachDroppedItems]
+    [currentCwd]
   )
 
   // Dropping a sidebar session inserts an @session link the agent can resolve

apps/desktop/src/app/chat/right-rail/preview-file.tsx

@@ -13,7 +13,6 @@ import { Streamdown } from 'streamdown'
 import { HERMES_PATHS_MIME } from '@/app/chat/hooks/use-composer-actions'
 import { PageLoader } from '@/components/page-loader'
 import { translateNow, useI18n } from '@/i18n'
-import { readDesktopFileDataUrl, readDesktopFileText } from '@/lib/desktop-fs'
 import { cn } from '@/lib/utils'
 import type { PreviewTarget } from '@/store/preview'
 
@@ -181,13 +180,15 @@ function looksBinaryBytes(bytes: Uint8Array) {
 }
 
 async function readTextPreview(filePath: string) {
-  try {
-    return await readDesktopFileText(filePath)
-  } catch (error) {
-    const message = error instanceof Error ? error.message : String(error)
+  if (window.hermesDesktop.readFileText) {
+    try {
+      return await window.hermesDesktop.readFileText(filePath)
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error)
 
-    if (!message.includes("No handler registered for 'hermes:readFileText'")) {
-      throw error
+      if (!message.includes("No handler registered for 'hermes:readFileText'")) {
+        throw error
+      }
     }
   }
 
@@ -445,9 +446,7 @@ export function LocalFilePreview({ reloadKey, target }: { reloadKey: number; tar
 
       try {
         if (isImage) {
-          // Prefer bytes the caller already handed us (a pasted/dropped
-          // screenshot) over re-reading a path that may be transient/unreadable.
-          const dataUrl = target.dataUrl || (await readDesktopFileDataUrl(filePath))
+          const dataUrl = await window.hermesDesktop.readFileDataUrl(filePath)
 
           if (active) {
             setState({ dataUrl, loading: false })
@@ -485,7 +484,7 @@ export function LocalFilePreview({ reloadKey, target }: { reloadKey: number; tar
     return () => {
       active = false
     }
-  }, [blockedByTarget, filePath, forcePreview, isImage, isText, reloadKey, target.dataUrl, target.language])
+  }, [blockedByTarget, filePath, forcePreview, isImage, isText, reloadKey, target.language])
 
   if (state.loading) {
     return <PageLoader label={t.preview.loading} />

apps/desktop/src/app/chat/right-rail/preview-pane.test.tsx

@@ -1,50 +1,11 @@
 import { act, cleanup, render } from '@testing-library/react'
-import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
-
-import { $connection } from '@/store/session'
+import { afterEach, describe, expect, it, vi } from 'vitest'
 
 import { PreviewPane } from './preview-pane'
 
 describe('PreviewPane console state', () => {
-  beforeEach(() => {
-    vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) => window.setTimeout(() => callback(Date.now()), 0))
-    vi.stubGlobal('cancelAnimationFrame', (id: number) => window.clearTimeout(id))
-  })
-
   afterEach(() => {
     cleanup()
-    $connection.set(null)
-    vi.unstubAllGlobals()
-  })
-
-  it('does not watch backend-only remote filesystem previews locally', () => {
-    const watchPreviewFile = vi.fn(async () => ({ id: 'watch-1', path: '/remote/file.txt' }))
-    const onPreviewFileChanged = vi.fn(() => vi.fn())
-    $connection.set({ mode: 'remote' } as never)
-    vi.stubGlobal('window', {
-      ...window,
-      hermesDesktop: {
-        onPreviewFileChanged,
-        watchPreviewFile
-      }
-    })
-
-    render(
-      <PreviewPane
-        setTitlebarToolGroup={vi.fn()}
-        target={{
-          kind: 'file',
-          label: 'file.txt',
-          path: '/remote/file.txt',
-          previewKind: 'text',
-          source: '/remote/file.txt',
-          url: 'file:///remote/file.txt'
-        }}
-      />
-    )
-
-    expect(watchPreviewFile).not.toHaveBeenCalled()
-    expect(onPreviewFileChanged).not.toHaveBeenCalled()
   })
 
   it('does not rebuild the pane titlebar group for streamed console logs', () => {

apps/desktop/src/app/chat/right-rail/preview-pane.tsx

@@ -5,7 +5,6 @@ import { useCallback, useEffect, useRef, useState } from 'react'
 import type { SetTitlebarToolGroup, TitlebarTool } from '@/app/shell/titlebar-controls'
 import { Tip } from '@/components/ui/tooltip'
 import { type Translations, useI18n } from '@/i18n'
-import { isDesktopFsRemoteMode } from '@/lib/desktop-fs'
 import { Bug } from '@/lib/icons'
 import { cn } from '@/lib/utils'
 import { notify, notifyError } from '@/store/notifications'
@@ -407,7 +406,6 @@ export function PreviewPane({
   useEffect(() => {
     if (
       target.kind !== 'file' ||
-      isDesktopFsRemoteMode() ||
       !window.hermesDesktop?.watchPreviewFile ||
       !window.hermesDesktop?.onPreviewFileChanged
     ) {

apps/desktop/src/app/chat/sidebar/cron-jobs-section.tsx

@@ -14,8 +14,6 @@ import type { CronJob } from '@/types/hermes'
 import { jobState, jobTitle, STATE_DOT } from '../../cron/job-state'
 import { SidebarPanelLabel } from '../../shell/sidebar-label'
 
-import { SidebarLoadMoreRow } from './load-more-row'
-
 const INACTIVE_STATES = new Set(['completed', 'disabled', 'error', 'paused'])
 
 // Recent runs shown in the inline quick-peek — enough to glance at history
@@ -26,11 +24,6 @@ const PEEK_RUN_LIMIT = 5
 // open peek so a freshly-fired run shows up within a few seconds.
 const PEEK_POLL_INTERVAL_MS = 8000
 
-// Keep the section compact: show a few jobs up front, reveal more in larger
-// steps on demand (mirrors the messaging sections in the sidebar).
-const INITIAL_VISIBLE_JOBS = 3
-const LOAD_MORE_STEP = 10
-
 const relativeFmt = new Intl.RelativeTimeFormat(undefined, { numeric: 'auto', style: 'short' })
 
 // Localized "in 5 min" / "2 hr ago" without hand-rolled strings — picks the
@@ -40,25 +33,17 @@ function relativeTime(targetMs: number, nowMs: number): string {
   const abs = Math.abs(diff)
   const sign = diff < 0 ? -1 : 1
 
-  if (abs < 60_000) {
-    return relativeFmt.format(sign * Math.round(abs / 1000), 'second')
-  }
+  if (abs < 60_000) {return relativeFmt.format(sign * Math.round(abs / 1000), 'second')}
 
-  if (abs < 3_600_000) {
-    return relativeFmt.format(sign * Math.round(abs / 60_000), 'minute')
-  }
+  if (abs < 3_600_000) {return relativeFmt.format(sign * Math.round(abs / 60_000), 'minute')}
 
-  if (abs < 86_400_000) {
-    return relativeFmt.format(sign * Math.round(abs / 3_600_000), 'hour')
-  }
+  if (abs < 86_400_000) {return relativeFmt.format(sign * Math.round(abs / 3_600_000), 'hour')}
 
   return relativeFmt.format(sign * Math.round(abs / 86_400_000), 'day')
 }
 
 function nextRunMs(job: CronJob): null | number {
-  if (!job.next_run_at) {
-    return null
-  }
+  if (!job.next_run_at) {return null}
 
   const ms = Date.parse(job.next_run_at)
 
@@ -69,9 +54,7 @@ function nextRunMs(job: CronJob): null | number {
 // the timestamp is what tells them apart. Compact (no year, no seconds) for the
 // narrow sidebar.
 function formatRunTime(seconds?: null | number): string {
-  if (!seconds) {
-    return '—'
-  }
+  if (!seconds) {return '—'}
 
   const date = new Date(seconds * 1000)
 
@@ -107,15 +90,11 @@ export function SidebarCronJobsSection({
   const [nowMs, setNowMs] = useState(() => Date.now())
   // Single-open inline peek so the section stays scannable.
   const [peekJobId, setPeekJobId] = useState<null | string>(null)
-  // Rows revealed so far; starts compact, grows in steps via "load more".
-  const [visibleCount, setVisibleCount] = useState(INITIAL_VISIBLE_JOBS)
 
   // One clock for the whole section (rows are pure) so the countdowns tick
   // without re-rendering the rest of the sidebar. Only runs while expanded.
   useEffect(() => {
-    if (!open) {
-      return
-    }
+    if (!open) {return}
 
     const id = window.setInterval(() => setNowMs(Date.now()), 1000)
 
@@ -129,25 +108,17 @@ export function SidebarCronJobsSection({
       const an = nextRunMs(a)
       const bn = nextRunMs(b)
 
-      if (an !== null && bn !== null && an !== bn) {
-        return an - bn
-      }
+      if (an !== null && bn !== null && an !== bn) {return an - bn}
 
-      if (an === null && bn !== null) {
-        return 1
-      }
+      if (an === null && bn !== null) {return 1}
 
-      if (an !== null && bn === null) {
-        return -1
-      }
+      if (an !== null && bn === null) {return -1}
 
       return jobTitle(a).localeCompare(jobTitle(b))
     })
   }, [jobs])
 
-  const cap = Math.min(visibleCount, max)
-  const shown = sorted.slice(0, cap)
-  const hiddenCount = Math.min(sorted.length, max) - shown.length
+  const shown = sorted.slice(0, max)
   // When capped, signal "50+" rather than implying the list is complete.
   const countLabel = jobs.length > max ? `${max}+` : String(jobs.length)
 
@@ -168,7 +139,7 @@ export function SidebarCronJobsSection({
         </button>
       </div>
       {open && (
-        <SidebarGroupContent className="flex max-h-72 flex-col gap-px overflow-y-auto overscroll-contain pb-1.75 compact:max-h-none compact:overflow-visible">
+        <SidebarGroupContent className="flex max-h-72 shrink-0 flex-col gap-px overflow-y-auto overscroll-contain pb-1.75">
           {shown.map(job => (
             <CronJobSidebarRow
               expanded={peekJobId === job.id}
@@ -181,12 +152,6 @@ export function SidebarCronJobsSection({
               onTrigger={() => onTriggerJob(job.id)}
             />
           ))}
-          {hiddenCount > 0 && (
-            <SidebarLoadMoreRow
-              onClick={() => setVisibleCount(count => count + LOAD_MORE_STEP)}
-              step={Math.min(LOAD_MORE_STEP, hiddenCount)}
-            />
-          )}
         </SidebarGroupContent>
       )}
     </SidebarGroup>
@@ -216,7 +181,11 @@ function CronJobSidebarRow({
   const next = nextRunMs(job)
   const label = jobTitle(job)
 
-  const meta = INACTIVE_STATES.has(state) ? (c.states[state] ?? state) : next !== null ? relativeTime(next, nowMs) : '—'
+  const meta = INACTIVE_STATES.has(state)
+    ? (c.states[state] ?? state)
+    : next !== null
+      ? relativeTime(next, nowMs)
+      : '—'
 
   return (
     <div>
@@ -288,7 +257,13 @@ function CronJobSidebarRow({
   )
 }
 
-function CronJobSidebarRuns({ jobId, onOpenRun }: { jobId: string; onOpenRun: (sessionId: string) => void }) {
+function CronJobSidebarRuns({
+  jobId,
+  onOpenRun
+}: {
+  jobId: string
+  onOpenRun: (sessionId: string) => void
+}) {
   const { t } = useI18n()
   const c = t.cron
   const selectedSessionId = useStore($selectedStoredSessionId)
@@ -300,22 +275,16 @@ function CronJobSidebarRuns({ jobId, onOpenRun }: { jobId: string; onOpenRun: (s
     const load = () =>
       getCronJobRuns(jobId, PEEK_RUN_LIMIT)
         .then(result => {
-          if (!cancelled) {
-            setRuns(result)
-          }
+          if (!cancelled) {setRuns(result)}
         })
         .catch(() => {
-          if (!cancelled) {
-            setRuns(prev => prev ?? [])
-          }
+          if (!cancelled) {setRuns(prev => prev ?? [])}
         })
 
     void load()
 
     const intervalId = window.setInterval(() => {
-      if (document.visibilityState === 'visible') {
-        void load()
-      }
+      if (document.visibilityState === 'visible') {void load()}
     }, PEEK_POLL_INTERVAL_MS)
 
     return () => {

apps/desktop/src/app/chat/sidebar/index.tsx

@@ -48,7 +48,6 @@ import {
   $pinnedSessionIds,
   $sidebarAgentsGrouped,
   $sidebarCronOpen,
-  $sidebarMessagingOpenIds,
   $sidebarOpen,
   $sidebarOverlayMounted,
   $sidebarPinsOpen,
@@ -65,7 +64,6 @@ import {
   setSidebarSessionOrderIds,
   setSidebarWorkspaceOrderIds,
   SIDEBAR_SESSIONS_PAGE_SIZE,
-  toggleSidebarMessagingOpen,
   unpinSession
 } from '@/store/layout'
 import {
@@ -78,9 +76,6 @@ import {
 } from '@/store/profile'
 import {
   $cronSessions,
-  $messagingPlatformTotals,
-  $messagingSessions,
-  $messagingTruncated,
   $selectedStoredSessionId,
   $sessionProfileTotals,
   $sessions,
@@ -95,19 +90,12 @@ import { SidebarPanelLabel } from '../../shell/sidebar-label'
 import type { SidebarNavItem } from '../../types'
 
 import { SidebarCronJobsSection } from './cron-jobs-section'
-import { SidebarLoadMoreRow } from './load-more-row'
 import { ProfileRail } from './profile-switcher'
 import { SidebarSessionRow } from './session-row'
 import { VirtualSessionList } from './virtual-session-list'
 
 const VIRTUALIZE_THRESHOLD = 25
 
-// Non-session groups (messaging platforms) stay compact: show a few rows up
-// front, reveal more in larger steps on demand. Keeps a busy platform from
-// dominating the sidebar before the user asks to see it.
-const NON_SESSION_INITIAL_ROWS = 3
-const NON_SESSION_LOAD_STEP = 10
-
 // 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.
@@ -136,16 +124,7 @@ const WORKSPACE_PAGE = 5
 // unified list scannable, then reveal/fetch more in N-sized steps on demand.
 const PROFILE_INITIAL_PAGE = 5
 const GROUP_DND_ID_PREFIX = 'group:'
-
-// Two modes via the `compact` height variant (styles.css):
-//   tall    → each section is shrink-0, capped, its own scroller; Sessions is flex-1.
-//   compact → COMPACT_FLAT drops the caps so the whole stack scrolls as one.
-// Sections stay shrink-0 so none can be squeezed below its content and bleed onto
-// the next — the flexbox `min-height: auto` overlap trap that caused the bug.
-const COMPACT_FLAT = 'compact:max-h-none compact:overflow-visible'
-
-// A non-session group's scroll body: own scroller when tall, flattened when compact.
-const GROUP_BODY = cn('overflow-y-auto overscroll-contain', COMPACT_FLAT)
+const LOCAL_SESSION_SOURCES = new Set(['cli', 'desktop', 'local', 'tui'])
 
 const groupDndId = (id: string) => `${GROUP_DND_ID_PREFIX}${id}`
 
@@ -162,25 +141,24 @@ function orderByIds<T>(items: T[], getId: (item: T) => string, orderIds: string[
 
   const byId = new Map(items.map(item => [getId(item), item]))
   const seen = new Set<string>()
-  const ordered: T[] = []
+  const out: T[] = []
 
   for (const id of orderIds) {
     const item = byId.get(id)
 
     if (item) {
-      ordered.push(item)
+      out.push(item)
       seen.add(id)
     }
   }
 
-  // Items missing from the persisted order are new since it was last
-  // reconciled. Callers pass recency-sorted lists (newest first), so surface
-  // these at the TOP instead of burying them beneath the saved order —
-  // otherwise a brand-new session sinks to the bottom of the sidebar and reads
-  // as "my latest session never showed up".
-  const fresh = items.filter(item => !seen.has(getId(item)))
+  for (const item of items) {
+    if (!seen.has(getId(item))) {
+      out.push(item)
+    }
+  }
 
-  return fresh.length ? [...fresh, ...ordered] : ordered
+  return out
 }
 
 function reconcileOrderIds(currentIds: string[], orderIds: string[]): string[] {
@@ -193,15 +171,17 @@ function reconcileOrderIds(currentIds: string[], orderIds: string[]): string[] {
   }
 
   const current = new Set(currentIds)
-  const retained = orderIds.filter(id => current.has(id))
-  const retainedSet = new Set(retained)
+  const next = orderIds.filter(id => current.has(id))
+  const known = new Set(next)
 
-  // New ids (absent from the saved order) are the newest sessions/groups; keep
-  // them ahead of the persisted order so fresh activity surfaces at the top of
-  // the sidebar rather than being appended to the bottom.
-  const fresh = currentIds.filter(id => !retainedSet.has(id))
+  for (const id of currentIds) {
+    if (!known.has(id)) {
+      next.push(id)
+      known.add(id)
+    }
+  }
 
-  return [...fresh, ...retained]
+  return next
 }
 
 function sameIds(left: string[], right: string[]) {
@@ -271,6 +251,43 @@ function workspaceGroupsFor(
   return [...groups.values()]
 }
 
+function sourceSessionGroupsFor(sessions: SessionInfo[]): {
+  localSessions: SessionInfo[]
+  sourceGroups: SidebarSessionGroup[]
+} {
+  const groups = new Map<string, SidebarSessionGroup>()
+  const localSessions: SessionInfo[] = []
+
+  for (const session of sessions) {
+    const sourceId = normalizeSessionSource(session.source)
+
+    if (!sourceId || LOCAL_SESSION_SOURCES.has(sourceId)) {
+      localSessions.push(session)
+
+      continue
+    }
+
+    const label = sessionSourceLabel(sourceId) ?? sourceId
+
+    const group = groups.get(sourceId) ?? {
+      id: `source:${sourceId}`,
+      label,
+      mode: 'source',
+      path: null,
+      sessions: [],
+      sourceId
+    }
+
+    group.sessions.push(session)
+    groups.set(sourceId, group)
+  }
+
+  return {
+    localSessions,
+    sourceGroups: [...groups.values()].sort((a, b) => sessionTime(b.sessions[0]) - sessionTime(a.sessions[0]))
+  }
+}
+
 function useSortableBindings(id: string) {
   const { attributes, isDragging, listeners, setNodeRef, transform, transition } = useSortable({ id })
 
@@ -292,7 +309,6 @@ interface ChatSidebarProps extends React.ComponentProps<typeof Sidebar> {
   onNavigate: (item: SidebarNavItem) => void
   onLoadMoreSessions: () => void
   onLoadMoreProfileSessions?: (profile: string) => Promise<void> | void
-  onLoadMoreMessaging?: (platform: string) => Promise<void> | void
   onResumeSession: (sessionId: string) => void
   onDeleteSession: (sessionId: string) => void
   onArchiveSession: (sessionId: string) => void
@@ -306,7 +322,6 @@ export function ChatSidebar({
   onNavigate,
   onLoadMoreSessions,
   onLoadMoreProfileSessions,
-  onLoadMoreMessaging,
   onResumeSession,
   onDeleteSession,
   onArchiveSession,
@@ -330,9 +345,6 @@ export function ChatSidebar({
   const sessions = useStore($sessions)
   const cronSessions = useStore($cronSessions)
   const cronJobs = useStore($cronJobs)
-  const messagingSessions = useStore($messagingSessions)
-  const messagingPlatformTotals = useStore($messagingPlatformTotals)
-  const messagingTruncated = useStore($messagingTruncated)
   const sessionsLoading = useStore($sessionsLoading)
   const sessionsTotal = useStore($sessionsTotal)
   const sessionProfileTotals = useStore($sessionProfileTotals)
@@ -352,10 +364,6 @@ export function ChatSidebar({
   const [serverMatches, setServerMatches] = useState<SessionSearchResult[]>([])
   const [newSessionKbdFlash, setNewSessionKbdFlash] = useState(false)
   const [profileLoadMorePending, setProfileLoadMorePending] = useState<Record<string, boolean>>({})
-  const [messagingLoadMorePending, setMessagingLoadMorePending] = useState<Record<string, boolean>>({})
-  const messagingOpenIds = useStore($sidebarMessagingOpenIds)
-  // Per-platform count of rows currently revealed (starts at NON_SESSION_INITIAL_ROWS).
-  const [messagingVisible, setMessagingVisible] = useState<Record<string, number>>({})
   const searchInputRef = useRef<HTMLInputElement>(null)
   const trimmedQuery = searchQuery.trim()
 
@@ -521,12 +529,24 @@ export function ChatSidebar({
     [unpinnedAgentSessions, agentOrderIds]
   )
 
-  // Recents are local-only: messaging-platform sessions are fetched as their
-  // own slice ($messagingSessions) and rendered in self-managed per-platform
-  // sections below, so there is no source-grouping magic to untangle here.
+  const { localSessions: localAgentSessions, sourceGroups } = useMemo(
+    () => sourceSessionGroupsFor(agentSessions),
+    [agentSessions]
+  )
+
+  const orderedSourceGroups = useMemo(
+    () => orderByIds(sourceGroups, g => g.id, workspaceOrderIds),
+    [sourceGroups, workspaceOrderIds]
+  )
+
   const agentGroups = useMemo(
-    () => orderByIds(workspaceGroupsFor(agentSessions, s.noWorkspace), g => g.id, workspaceOrderIds),
-    [agentSessions, s.noWorkspace, workspaceOrderIds]
+    () =>
+      orderByIds(
+        workspaceGroupsFor(localAgentSessions, s.noWorkspace, { preserveSessionOrder: sourceGroups.length > 0 }),
+        g => g.id,
+        workspaceOrderIds
+      ),
+    [localAgentSessions, s.noWorkspace, sourceGroups.length, workspaceOrderIds]
   )
 
   const loadMoreForProfileGroup = useCallback(
@@ -544,76 +564,6 @@ export function ChatSidebar({
     [onLoadMoreProfileSessions]
   )
 
-  const loadMoreForMessaging = useCallback(
-    (platform: string) => {
-      if (!onLoadMoreMessaging) {
-        return
-      }
-
-      setMessagingLoadMorePending(prev => ({ ...prev, [platform]: true }))
-
-      void Promise.resolve(onLoadMoreMessaging(platform))
-        .catch(() => undefined)
-        .finally(() => setMessagingLoadMorePending(({ [platform]: _done, ...rest }) => rest))
-    },
-    [onLoadMoreMessaging]
-  )
-
-  // Reveal another batch of a platform's rows; fetch from the backend too if we
-  // run past what's loaded and more remain on disk.
-  const revealMoreMessaging = (platform: string, loaded: number, hasMore: boolean) => {
-    const next = (messagingVisible[platform] ?? NON_SESSION_INITIAL_ROWS) + NON_SESSION_LOAD_STEP
-
-    setMessagingVisible(prev => ({ ...prev, [platform]: next }))
-
-    if (next > loaded && hasMore) {
-      loadMoreForMessaging(platform)
-    }
-  }
-
-  // Each messaging platform is its own self-managed section: split the
-  // separately-fetched messaging slice by source, newest platform first, rows
-  // within a platform by recency. Per-platform totals (when a "load more" has
-  // resolved them) drive the count + whether more remain on disk.
-  const messagingGroups = useMemo<MessagingSection[]>(() => {
-    if (!messagingSessions.length) {
-      return []
-    }
-
-    const bySource = new Map<string, SessionInfo[]>()
-
-    for (const session of messagingSessions) {
-      const sourceId = normalizeSessionSource(session.source)
-
-      if (!sourceId) {
-        continue
-      }
-
-      const list = bySource.get(sourceId) ?? []
-      list.push(session)
-      bySource.set(sourceId, list)
-    }
-
-    return [...bySource.entries()]
-      .map(([sourceId, list]) => {
-        const ordered = [...list].sort((a, b) => sessionTime(b) - sessionTime(a))
-        const known = messagingPlatformTotals[sourceId]
-        const total = Math.max(ordered.length, known ?? 0)
-
-        return {
-          // Known exact total → more exist iff total exceeds loaded; otherwise
-          // the seed fetch was capped, so assume more until a per-platform load
-          // resolves the count.
-          hasMore: known != null ? known > ordered.length : messagingTruncated,
-          label: sessionSourceLabel(sourceId) ?? sourceId,
-          sessions: ordered,
-          sourceId,
-          total
-        }
-      })
-      .sort((a, b) => sessionTime(b.sessions[0]) - sessionTime(a.sessions[0]))
-  }, [messagingSessions, messagingPlatformTotals, messagingTruncated])
-
   // ALL-profiles view: one collapsible group per profile, color on the header
   // (not on every row). Default profile floats to the top, the rest alpha.
   const profileGroups = useMemo<SidebarSessionGroup[] | undefined>(() => {
@@ -660,34 +610,37 @@ export function ChatSidebar({
     sessionProfileTotals
   ])
 
-  const displayAgentSessions = agentSessions
+  const displayAgentSessions = sourceGroups.length ? localAgentSessions : agentSessions
 
-  // Pagination is scope-aware. In "All profiles" mode it tracks the global
-  // unified set. When scoped to one profile it must compare that profile's own
-  // loaded rows against that profile's total — otherwise a huge default profile
-  // keeps "Load more" stuck on while you browse a small one (the aggregator's
-  // total sums every profile). Per-profile totals come from the aggregator
-  // (children excluded); fall back to the global total / loaded count.
-  const loadedSessionCount = showAllProfiles ? sessions.length : visibleSessions.length
-  const scopedProfileTotal = showAllProfiles ? undefined : sessionProfileTotals[profileScope]
+  const displayAgentGroups = useMemo(() => {
+    if (orderedSourceGroups.length) {
+      const localGroups = agentsGrouped
+        ? agentGroups
+        : localAgentSessions.length
+          ? [
+              {
+                id: 'local-sessions',
+                label: 'Local',
+                mode: 'workspace' as const,
+                path: null,
+                sessions: localAgentSessions
+              }
+            ]
+          : []
 
-  const knownSessionTotal = Math.max(
-    showAllProfiles ? sessionsTotal : (scopedProfileTotal ?? loadedSessionCount),
-    loadedSessionCount
-  )
+      return orderByIds([...orderedSourceGroups, ...localGroups], g => g.id, workspaceOrderIds)
+    }
 
-  const hasMoreSessions = knownSessionTotal > loadedSessionCount
-  const remainingSessionCount = Math.max(0, knownSessionTotal - loadedSessionCount)
-
-  const recentsMeta = countLabel(agentSessions.length, knownSessionTotal)
-
-  const displayAgentGroups = showAllProfiles ? profileGroups : agentsGrouped ? agentGroups : undefined
-
-  // The recents list owns its own (virtualized) scroll container only when it's a
-  // long flat list. In that case it must keep its scroller even in short mode, so
-  // we don't flatten it (flattening would defeat virtualization). Short flat lists
-  // and grouped views flatten into the single outer scroll instead.
-  const recentsVirtualizes = !displayAgentGroups?.length && displayAgentSessions.length >= VIRTUALIZE_THRESHOLD
+    return showAllProfiles ? profileGroups : agentsGrouped ? agentGroups : undefined
+  }, [
+    agentGroups,
+    agentsGrouped,
+    localAgentSessions,
+    orderedSourceGroups,
+    profileGroups,
+    showAllProfiles,
+    workspaceOrderIds
+  ])
 
   useEffect(() => {
     if (!displayAgentGroups?.length || showAllProfiles) {
@@ -708,6 +661,25 @@ export function ChatSidebar({
 
   const showSessionSections = showSessionSkeletons || sortedSessions.length > 0
 
+  // Pagination is scope-aware. In "All profiles" mode it tracks the global
+  // unified set. When scoped to one profile it must compare that profile's own
+  // loaded rows against that profile's total — otherwise a huge default profile
+  // keeps "Load more" stuck on while you browse a small one (the aggregator's
+  // total sums every profile). Per-profile totals come from the aggregator
+  // (children excluded); fall back to the global total / loaded count.
+  const loadedSessionCount = showAllProfiles ? sessions.length : visibleSessions.length
+  const scopedProfileTotal = showAllProfiles ? undefined : sessionProfileTotals[profileScope]
+
+  const knownSessionTotal = Math.max(
+    showAllProfiles ? sessionsTotal : (scopedProfileTotal ?? loadedSessionCount),
+    loadedSessionCount
+  )
+
+  const hasMoreSessions = knownSessionTotal > loadedSessionCount
+  const remainingSessionCount = Math.max(0, knownSessionTotal - loadedSessionCount)
+
+  const recentsMeta = countLabel(agentSessions.length, knownSessionTotal)
+
   const handlePinnedDragEnd = ({ active, over }: DragEndEvent) => {
     if (!over || active.id === over.id) {
       return
@@ -820,7 +792,9 @@ export function ChatSidebar({
                       <item.icon className="size-4 shrink-0 text-[color-mix(in_srgb,currentColor_72%,transparent)]" />
                       {contentVisible && (
                         <>
-                          <span className="min-w-0 flex-1 truncate">{s.nav[item.id] ?? item.label}</span>
+                          <span className="min-w-0 flex-1 truncate">
+                            {s.nav[item.id] ?? item.label}
+                          </span>
                           {isNewSession && (
                             <KbdGroup
                               className={cn('ml-auto', newSessionKbdFlash && 'opacity-100!')}
@@ -849,191 +823,135 @@ export function ChatSidebar({
           </div>
         )}
 
-        {contentVisible && showSessionSections && (
-          <div className="flex min-h-0 flex-1 flex-col overflow-y-auto overscroll-contain pb-1.75">
-            {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)">
-                    {s.noMatch(trimmedQuery)}
-                  </div>
-                }
-                label={s.results}
-                labelMeta={String(searchResults.length)}
-                onArchiveSession={onArchiveSession}
-                onDeleteSession={onDeleteSession}
-                onResumeSession={onResumeSession}
-                onToggle={() => undefined}
-                onTogglePin={pinSession}
-                open
-                pinned={false}
-                rootClassName="min-h-32 flex-1 overflow-hidden p-0"
-                sessions={searchResults}
-                workingSessionIdSet={workingSessionIdSet}
-              />
+        {contentVisible && 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)">
+                {s.noMatch(trimmedQuery)}
+              </div>
+            }
+            label={s.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}
+          />
+        )}
+
+        {contentVisible && 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={s.pinned}
+            onArchiveSession={onArchiveSession}
+            onDeleteSession={onDeleteSession}
+            onReorder={handlePinnedDragEnd}
+            onResumeSession={onResumeSession}
+            onToggle={() => setSidebarPinsOpen(!pinsOpen)}
+            onTogglePin={unpinSession}
+            open={pinsOpen}
+            pinned
+            rootClassName="shrink-0 p-0 pb-1"
+            sessions={pinnedSessions}
+            sortable={pinnedSessions.length > 1}
+            workingSessionIdSet={workingSessionIdSet}
+          />
+        )}
+
+        {contentVisible && showSessionSections && !trimmedQuery && (
+          <SidebarSessionsSection
+            activeSessionId={activeSidebarSessionId}
+            contentClassName={cn(
+              'flex min-h-0 flex-1 flex-col overflow-y-auto overscroll-contain pb-1.75',
+              // Separate profile sections clearly in the ALL view; rows inside
+              // each group keep their own tight gap-px rhythm.
+              showAllProfiles ? 'gap-3' : 'gap-px'
             )}
+            dndSensors={dndSensors}
+            emptyState={showSessionSkeletons ? <SidebarSessionSkeletons /> : <SidebarAllPinnedState />}
+            footer={
+              // Hide "load more" only when workspace-grouped (those groups page
+              // themselves). ALL-profiles now pages per-profile from each profile
+              // header; the global footer only applies to non-ALL views.
+              !showAllProfiles && !agentsGrouped && !showSessionSkeletons && hasMoreSessions ? (
+                <SidebarLoadMoreRow
+                  loading={sessionsLoading}
+                  onClick={onLoadMoreSessions}
+                  step={Math.min(SIDEBAR_SESSIONS_PAGE_SIZE, remainingSessionCount)}
+                />
+              ) : null
+            }
+            forceEmptyState={showSessionSkeletons}
+            groups={displayAgentGroups}
+            headerAction={
+              // Always reserve the icon-xs (size-6) slot so the header keeps the
+              // same height whether or not the toggle renders — otherwise the
+              // "Sessions" label jumps when switching to the ALL-profiles view.
+              // Grouping operates on unpinned recents; if everything is pinned
+              // the toggle does nothing, and it's irrelevant in the ALL-profiles
+              // view (always grouped by profile), so hide the button (not the slot).
+              <div className="grid size-6 shrink-0 place-items-center">
+                {!showAllProfiles && localAgentSessions.length > 0 ? (
+                  <Tip label={agentsGrouped ? s.groupTitleGrouped : s.groupTitleUngrouped}>
+                    <Button
+                      aria-label={agentsGrouped ? s.groupAriaGrouped : s.groupAriaUngrouped}
+                      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"
+                      variant="ghost"
+                    >
+                      <Codicon name={agentsGrouped ? 'list-unordered' : 'root-folder'} size="0.75rem" />
+                    </Button>
+                  </Tip>
+                ) : null}
+              </div>
+            }
+            label={s.sessions}
+            labelMeta={recentsMeta}
+            onArchiveSession={onArchiveSession}
+            onDeleteSession={onDeleteSession}
+            onNewSessionInWorkspace={showAllProfiles ? undefined : onNewSessionInWorkspace}
+            onReorder={showAllProfiles ? undefined : handleAgentDragEnd}
+            onResumeSession={onResumeSession}
+            onToggle={() => setSidebarRecentsOpen(!agentsOpen)}
+            onTogglePin={pinSession}
+            open={agentsOpen}
+            pinned={false}
+            rootClassName="min-h-0 flex-1 p-0"
+            sessions={displayAgentSessions}
+            sortable={!showAllProfiles && agentSessions.length > 1}
+            workingSessionIdSet={workingSessionIdSet}
+          />
+        )}
 
-            {!trimmedQuery && (
-              <SidebarSessionsSection
-                activeSessionId={activeSidebarSessionId}
-                contentClassName={cn('flex max-h-44 flex-col gap-px rounded-lg pb-2 pt-1', GROUP_BODY)}
-                dndSensors={dndSensors}
-                emptyState={<SidebarPinnedEmptyState />}
-                label={s.pinned}
-                onArchiveSession={onArchiveSession}
-                onDeleteSession={onDeleteSession}
-                onReorder={handlePinnedDragEnd}
-                onResumeSession={onResumeSession}
-                onToggle={() => setSidebarPinsOpen(!pinsOpen)}
-                onTogglePin={unpinSession}
-                open={pinsOpen}
-                pinned
-                rootClassName="shrink-0 p-0 pb-1"
-                sessions={pinnedSessions}
-                sortable={pinnedSessions.length > 1}
-                workingSessionIdSet={workingSessionIdSet}
-              />
-            )}
-
-            {!trimmedQuery && (
-              <SidebarSessionsSection
-                activeSessionId={activeSidebarSessionId}
-                contentClassName={cn(
-                  'flex min-h-0 flex-1 flex-col overflow-y-auto overscroll-contain pb-1.75',
-                  // Separate profile sections clearly in the ALL view; rows inside
-                  // each group keep their own tight gap-px rhythm.
-                  showAllProfiles ? 'gap-3' : 'gap-px',
-                  // Flatten into the single scroll when compact — unless this is the
-                  // virtualized long list, which must keep its own scroller.
-                  !recentsVirtualizes && COMPACT_FLAT
-                )}
-                dndSensors={dndSensors}
-                emptyState={showSessionSkeletons ? <SidebarSessionSkeletons /> : <SidebarAllPinnedState />}
-                footer={
-                  // Hide "load more" only when workspace-grouped (those groups page
-                  // themselves). ALL-profiles now pages per-profile from each profile
-                  // header; the global footer only applies to non-ALL views.
-                  !showAllProfiles && !agentsGrouped && !showSessionSkeletons && hasMoreSessions ? (
-                    <SidebarLoadMoreRow
-                      loading={sessionsLoading}
-                      onClick={onLoadMoreSessions}
-                      step={Math.min(SIDEBAR_SESSIONS_PAGE_SIZE, remainingSessionCount)}
-                    />
-                  ) : null
-                }
-                forceEmptyState={showSessionSkeletons}
-                groups={displayAgentGroups}
-                headerAction={
-                  // Always reserve the icon-xs (size-6) slot so the header keeps the
-                  // same height whether or not the toggle renders — otherwise the
-                  // "Sessions" label jumps when switching to the ALL-profiles view.
-                  // Grouping operates on unpinned recents; if everything is pinned
-                  // the toggle does nothing, and it's irrelevant in the ALL-profiles
-                  // view (always grouped by profile), so hide the button (not the slot).
-                  <div className="grid size-6 shrink-0 place-items-center">
-                    {!showAllProfiles && agentSessions.length > 0 ? (
-                      <Tip label={agentsGrouped ? s.groupTitleGrouped : s.groupTitleUngrouped}>
-                        <Button
-                          aria-label={agentsGrouped ? s.groupAriaGrouped : s.groupAriaUngrouped}
-                          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"
-                          variant="ghost"
-                        >
-                          <Codicon name={agentsGrouped ? 'list-unordered' : 'root-folder'} size="0.75rem" />
-                        </Button>
-                      </Tip>
-                    ) : null}
-                  </div>
-                }
-                label={s.sessions}
-                labelMeta={recentsMeta}
-                onArchiveSession={onArchiveSession}
-                onDeleteSession={onDeleteSession}
-                onNewSessionInWorkspace={showAllProfiles ? undefined : onNewSessionInWorkspace}
-                onReorder={showAllProfiles ? undefined : handleAgentDragEnd}
-                onResumeSession={onResumeSession}
-                onToggle={() => setSidebarRecentsOpen(!agentsOpen)}
-                onTogglePin={pinSession}
-                open={agentsOpen}
-                pinned={false}
-                rootClassName={cn(
-                  'min-h-32 flex-1 overflow-hidden p-0',
-                  !recentsVirtualizes && 'compact:min-h-0 compact:flex-none compact:overflow-visible'
-                )}
-                sessions={displayAgentSessions}
-                sortable={!showAllProfiles && agentSessions.length > 1}
-                workingSessionIdSet={workingSessionIdSet}
-              />
-            )}
-
-            {!trimmedQuery &&
-              messagingGroups.map(group => {
-                const visible = messagingVisible[group.sourceId] ?? NON_SESSION_INITIAL_ROWS
-                const shownSessions = group.sessions.slice(0, visible)
-                // More to show if rows are hidden behind the cap, or the backend
-                // still has older threads on disk.
-                const canRevealMore = visible < group.sessions.length || group.hasMore
-
-                return (
-                  <SidebarSessionsSection
-                    activeSessionId={activeSidebarSessionId}
-                    contentClassName={cn('flex max-h-56 flex-col gap-px pb-1.75', GROUP_BODY)}
-                    emptyState={null}
-                    footer={
-                      canRevealMore ? (
-                        <SidebarLoadMoreRow
-                          loading={Boolean(messagingLoadMorePending[group.sourceId])}
-                          onClick={() => revealMoreMessaging(group.sourceId, group.sessions.length, group.hasMore)}
-                          step={Math.min(NON_SESSION_LOAD_STEP, Math.max(0, group.total - shownSessions.length))}
-                        />
-                      ) : null
-                    }
-                    key={group.sourceId}
-                    label={group.label}
-                    labelIcon={
-                      <PlatformAvatar
-                        className="size-4 rounded-[4px] text-[0.5625rem] [&_svg]:size-3"
-                        platformId={group.sourceId}
-                        platformName={group.label}
-                      />
-                    }
-                    labelMeta={countLabel(group.sessions.length, group.total)}
-                    onArchiveSession={onArchiveSession}
-                    onDeleteSession={onDeleteSession}
-                    onResumeSession={onResumeSession}
-                    onToggle={() => toggleSidebarMessagingOpen(group.sourceId)}
-                    onTogglePin={pinSession}
-                    open={messagingOpenIds.includes(group.sourceId)}
-                    pinned={false}
-                    rootClassName="shrink-0 p-0"
-                    sessions={shownSessions}
-                    workingSessionIdSet={workingSessionIdSet}
-                  />
-                )
-              })}
-
-            {!trimmedQuery && cronJobs.length > 0 && (
-              <SidebarCronJobsSection
-                jobs={cronJobs}
-                label={s.cronJobs}
-                onManageJob={onManageCronJob}
-                onOpenRun={onResumeSession}
-                onToggle={() => setSidebarCronOpen(!cronOpen)}
-                onTriggerJob={onTriggerCronJob}
-                open={cronOpen}
-              />
-            )}
-          </div>
+        {contentVisible && !trimmedQuery && cronJobs.length > 0 && (
+          <SidebarCronJobsSection
+            jobs={cronJobs}
+            label={s.cronJobs}
+            onManageJob={onManageCronJob}
+            onOpenRun={onResumeSession}
+            onToggle={() => setSidebarCronOpen(!cronOpen)}
+            onTriggerJob={onTriggerCronJob}
+            open={cronOpen}
+          />
         )}
 
         {contentVisible && !showSessionSections && <div className="min-h-0 flex-1" />}
@@ -1054,10 +972,9 @@ interface SidebarSectionHeaderProps {
   onToggle: () => void
   action?: React.ReactNode
   meta?: React.ReactNode
-  icon?: React.ReactNode
 }
 
-function SidebarSectionHeader({ label, open, onToggle, action, meta, icon }: SidebarSectionHeaderProps) {
+function SidebarSectionHeader({ label, open, onToggle, action, meta }: SidebarSectionHeaderProps) {
   return (
     <div className="group/section flex shrink-0 items-center justify-between pb-1 pt-1.5">
       <button
@@ -1065,7 +982,6 @@ function SidebarSectionHeader({ label, open, onToggle, action, meta, icon }: Sid
         onClick={onToggle}
         type="button"
       >
-        {icon}
         <SidebarPanelLabel>{label}</SidebarPanelLabel>
         {meta && <SidebarCount>{meta}</SidebarCount>}
         <DisclosureCaret
@@ -1128,14 +1044,6 @@ interface SidebarSessionGroup {
   totalCount?: number
 }
 
-interface MessagingSection {
-  sourceId: string
-  label: string
-  sessions: SessionInfo[]
-  total: number
-  hasMore: boolean
-}
-
 interface SidebarSessionsSectionProps {
   label: string
   open: boolean
@@ -1157,7 +1065,6 @@ interface SidebarSessionsSectionProps {
   footer?: React.ReactNode
   groups?: SidebarSessionGroup[]
   labelMeta?: React.ReactNode
-  labelIcon?: React.ReactNode
   sortable?: boolean
   onReorder?: (event: DragEndEvent) => void
   dndSensors?: ReturnType<typeof useSensors>
@@ -1184,7 +1091,6 @@ function SidebarSessionsSection({
   footer,
   groups,
   labelMeta,
-  labelIcon,
   sortable = false,
   onReorder,
   dndSensors
@@ -1275,7 +1181,6 @@ function SidebarSessionsSection({
     inner = (
       <VirtualSessionList
         activeSessionId={activeSessionId}
-        className={contentClassName}
         onArchiveSession={onArchiveSession}
         onDeleteSession={onDeleteSession}
         onResumeSession={onResumeSession}
@@ -1304,14 +1209,7 @@ function SidebarSessionsSection({
 
   return (
     <SidebarGroup className={rootClassName}>
-      <SidebarSectionHeader
-        action={headerAction}
-        icon={labelIcon}
-        label={label}
-        meta={labelMeta}
-        onToggle={onToggle}
-        open={open}
-      />
+      <SidebarSectionHeader action={headerAction} label={label} meta={labelMeta} onToggle={onToggle} open={open} />
       {open && (
         <SidebarGroupContent className={resolvedContentClassName}>
           {body}
@@ -1500,3 +1398,30 @@ interface SortableSessionRowProps {
 function SortableSidebarSessionRow(props: SortableSessionRowProps) {
   return <SidebarSessionRow {...props} {...useSortableBindings(props.session.id)} />
 }
+
+interface SidebarLoadMoreRowProps {
+  loading: boolean
+  onClick: () => void
+  step: number
+}
+
+function SidebarLoadMoreRow({ loading, onClick, step }: SidebarLoadMoreRowProps) {
+  const { t } = useI18n()
+  const label = loading ? t.sidebar.loading : step > 0 ? t.sidebar.loadCount(step) : t.sidebar.loadMore
+
+  return (
+    <button
+      className="flex min-h-5 items-center gap-1.5 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"
+    >
+      {/* Seat the icon in the same w-3.5 column session rows use for their dot
+          so the chevron + label line up with the rows above. */}
+      <span className="grid w-3.5 shrink-0 place-items-center">
+        <Codicon className="opacity-70" name={loading ? 'loading' : 'chevron-down'} size="0.75rem" spinning={loading} />
+      </span>
+      <span>{label}</span>
+    </button>
+  )
+}

apps/desktop/src/app/chat/sidebar/load-more-row.tsx

@@ -1,30 +0,0 @@
-import { Codicon } from '@/components/ui/codicon'
-import { useI18n } from '@/i18n'
-
-interface SidebarLoadMoreRowProps {
-  step: number
-  onClick: () => void
-  loading?: boolean
-}
-
-// "Load N more" affordance shared by the recents, messaging, and cron sections.
-// The chevron sits in the same w-3.5 column the rows use for their dot, so it
-// lines up with the list above.
-export function SidebarLoadMoreRow({ step, onClick, loading = false }: SidebarLoadMoreRowProps) {
-  const { t } = useI18n()
-  const label = loading ? t.sidebar.loading : step > 0 ? t.sidebar.loadCount(step) : t.sidebar.loadMore
-
-  return (
-    <button
-      className="flex min-h-5 items-center gap-1.5 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"
-    >
-      <span className="grid w-3.5 shrink-0 place-items-center">
-        <Codicon className="opacity-70" name={loading ? 'loading' : 'chevron-down'} size="0.75rem" spinning={loading} />
-      </span>
-      <span>{label}</span>
-    </button>
-  )
-}

apps/desktop/src/app/chat/sidebar/profile-switcher.tsx

@@ -83,9 +83,8 @@ const stepThroughCells: Modifier = ({ containerNodeRect, draggingNodeRect, trans
 // Arc-Spaces-style profile rail at the sidebar foot: a default↔all toggle pinned
 // left, the colored named profiles scrolling between, and Manage pinned right.
 // The active profile pops in its own color — the "where am I" cue. Single-
-// profile users see the "+" (create their first profile) and the Manage
-// overflow (edit the default profile's SOUL.md); the colored named squares
-// and the default↔all toggle only appear once a second profile exists.
+// profile users see only the "+" (create their first profile); everything else
+// appears once a second profile exists.
 export function ProfileRail() {
   const { t } = useI18n()
   const p = t.profiles
@@ -269,11 +268,9 @@ export function ProfileRail() {
         </Tip>
       </div>
 
-      {/* Always reachable, even with only the default profile: the manage
-          overlay is the only place to edit a profile's SOUL.md, and a
-          single-profile user must be able to edit the default's persona
-          without first creating a throwaway second profile. */}
-      <ProfilePill active={false} glyph="ellipsis" label={p.manageProfiles} onSelect={() => navigate(PROFILES_ROUTE)} />
+      {multiProfile && (
+        <ProfilePill active={false} glyph="ellipsis" label={p.manageProfiles} onSelect={() => navigate(PROFILES_ROUTE)} />
+      )}
 
       {/* Land in the new profile on a fresh chat (selectProfile triggers the
           new-session reset), not stuck on the session you were just in. */}

apps/desktop/src/app/chat/sidebar/session-actions-menu.tsx

@@ -21,7 +21,6 @@ import { triggerHaptic } from '@/lib/haptics'
 import { exportSession } from '@/lib/session-export'
 import { notify, notifyError } from '@/store/notifications'
 import { setSessions } from '@/store/session'
-import { canOpenSessionWindow, openSessionInNewWindow } from '@/store/windows'
 
 interface SessionActions {
   sessionId: string
@@ -69,19 +68,6 @@ function useSessionActions({ sessionId, title, pinned = false, profile, onPin, o
         void writeClipboardText(sessionId).catch(err => notifyError(err, r.copyIdFailed))
       }
     },
-    ...(canOpenSessionWindow()
-      ? [
-          {
-            disabled: !sessionId,
-            icon: 'link-external',
-            label: r.newWindow,
-            onSelect: () => {
-              triggerHaptic('selection')
-              void openSessionInNewWindow(sessionId)
-            }
-          }
-        ]
-      : []),
     {
       disabled: !sessionId,
       icon: 'cloud-download',

apps/desktop/src/app/chat/sidebar/session-row.tsx

@@ -2,18 +2,14 @@ import { useStore } from '@nanostores/react'
 import type * as React from 'react'
 
 import { writeSessionDrag } from '@/app/chat/composer/inline-refs'
-import { PlatformAvatar } from '@/app/messaging/platform-icon'
 import { Button } from '@/components/ui/button'
 import { Codicon } from '@/components/ui/codicon'
-import { Tip } from '@/components/ui/tooltip'
 import type { SessionInfo } from '@/hermes'
 import { type Translations, useI18n } from '@/i18n'
 import { sessionTitle } from '@/lib/chat-runtime'
 import { triggerHaptic } from '@/lib/haptics'
-import { handoffOriginSource, sessionSourceLabel } from '@/lib/session-source'
 import { cn } from '@/lib/utils'
 import { $attentionSessionIds } from '@/store/session'
-import { canOpenSessionWindow, openSessionInNewWindow } from '@/store/windows'
 
 import { SessionActionsMenu, SessionContextMenu } from './session-actions-menu'
 
@@ -71,11 +67,6 @@ export function SidebarSessionRow({
   const title = sessionTitle(session)
   const age = formatAge(session.last_active || session.started_at, r)
   const handleLabel = `Reorder ${title}`
-  // A handed-off session's live source is local, but it originated on a
-  // messaging platform — surface that origin as a small badge so e.g. a
-  // Telegram thread continued here still reads as Telegram.
-  const handoffSource = handoffOriginSource(session.handoff_state, session.handoff_platform)
-  const handoffLabel = handoffSource ? sessionSourceLabel(handoffSource) ?? handoffSource : null
   // 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.
@@ -133,15 +124,11 @@ export function SidebarSessionRow({
               return
             }
 
-            // ⌘-click (mac) / ⌃-click (win/linux) pops the chat into its own
-            // window — the universal "open in a new window" gesture. Archive
-            // lives in the row's ⋯ and right-click menus. Falls through to a
-            // normal resume when standalone windows aren't available (web embed).
-            if ((event.metaKey || event.ctrlKey) && canOpenSessionWindow()) {
+            if (event.metaKey || event.ctrlKey) {
               event.preventDefault()
               event.stopPropagation()
               triggerHaptic('selection')
-              void openSessionInNewWindow(session.id)
+              onArchive()
 
               return
             }
@@ -192,15 +179,6 @@ export function SidebarSessionRow({
               <SidebarRowDot isWorking={isWorking} needsInput={needsInput} />
             </span>
           )}
-          {handoffSource && handoffLabel ? (
-            <Tip label={r.handoffOrigin(handoffLabel)}>
-              <PlatformAvatar
-                className="size-4 rounded-[4px] text-[0.5rem] [&_svg]:size-2.5"
-                platformId={handoffSource}
-                platformName={handoffLabel}
-              />
-            </Tip>
-          ) : null}
           <span className="min-w-0 flex-1 truncate text-[0.8125rem] font-normal text-(--ui-text-secondary) group-hover:text-foreground group-data-[working=true]:text-foreground/90">
             {title}
           </span>

apps/desktop/src/app/command-palette/index.tsx

@@ -4,10 +4,7 @@ import { Dialog as DialogPrimitive } from 'radix-ui'
 import { useCallback, useEffect, useMemo, useState } from 'react'
 import { useNavigate } from 'react-router-dom'
 
-import { HUD_HEADING, HUD_ITEM, HUD_POSITION, HUD_SURFACE, HUD_TEXT } from '@/app/floating-hud'
-import { setTerminalTakeover } from '@/app/right-sidebar/store'
 import { Command, CommandEmpty, CommandGroup, CommandInput, CommandItem, CommandList } from '@/components/ui/command'
-import { KbdGroup } from '@/components/ui/kbd'
 import { getHermesConfigRecord, listSessions } from '@/hermes'
 import { useI18n } from '@/i18n'
 import { sessionTitle } from '@/lib/chat-runtime'
@@ -15,11 +12,11 @@ import {
   Activity,
   Archive,
   BarChart3,
+  Check,
   ChevronLeft,
   ChevronRight,
   Clock,
   Cpu,
-  Download,
   Globe,
   type IconComponent,
   Info,
@@ -33,18 +30,13 @@ import {
   Settings,
   Settings2,
   Sun,
-  Terminal,
   Users,
   Wrench,
   Zap
 } from '@/lib/icons'
-import { comboTokens } from '@/lib/keybinds/combo'
 import { cn } from '@/lib/utils'
 import { $commandPaletteOpen, closeCommandPalette, setCommandPaletteOpen } from '@/store/command-palette'
-import { $bindings } from '@/store/keybinds'
-import { luminance } from '@/themes/color'
 import { type ThemeMode, useTheme } from '@/themes/context'
-import { isUserTheme, resolveTheme } from '@/themes/user-themes'
 
 import {
   AGENTS_ROUTE,
@@ -62,11 +54,8 @@ import { FIELD_LABELS, SECTIONS } from '../settings/constants'
 import { fieldCopyForSchemaKey } from '../settings/field-copy'
 import { prettyName } from '../settings/helpers'
 
-import { MarketplaceThemePage } from './marketplace-theme-page'
-
 interface PaletteItem {
-  /** Keybind action id — its live combo renders as a hotkey hint. */
-  action?: string
+  active?: boolean
   icon: IconComponent
   id: string
   /** Keep the palette open after running (live-preview pickers like theme/mode). */
@@ -80,16 +69,10 @@ interface PaletteItem {
 }
 
 interface PaletteGroup {
-  /** Optional: a headingless group renders as a bare action row (e.g. the
-   *  "Install theme…" entry pinned atop the theme picker). */
-  heading?: string
+  heading: string
   items: PaletteItem[]
 }
 
-// Nested page → its parent, so Back / Esc step up one level instead of closing
-// the palette. Pages absent here go straight back to the root list.
-const PAGE_PARENTS: Record<string, string> = { 'install-theme': 'theme' }
-
 /** A nested page reachable from a root item via `to`. */
 interface PalettePage {
   groups: PaletteGroup[]
@@ -103,22 +86,6 @@ interface SessionEntry {
   title: string
 }
 
-// cmdk defaults to fuzzy subsequence scoring, so "color" matches anything with
-// c…o…l…o…r scattered across it. Use case-insensitive multi-term substring
-// matching instead: every typed word must literally appear in the item's
-// value/keywords, which keeps results tight and predictable.
-const paletteFilter = (value: string, search: string, keywords?: string[]): number => {
-  const needle = search.trim().toLowerCase()
-
-  if (!needle) {
-    return 1
-  }
-
-  const haystack = `${value} ${keywords?.join(' ') ?? ''}`.toLowerCase()
-
-  return needle.split(/\s+/).every(term => haystack.includes(term)) ? 1 : 0
-}
-
 type SessionRow = Awaited<ReturnType<typeof listSessions>>['sessions'][number]
 
 const toSessionEntry = (session: SessionRow): SessionEntry => ({
@@ -179,32 +146,11 @@ const THEME_MODES: ReadonlyArray<{ icon: IconComponent; mode: ThemeMode }> = [
   { icon: Monitor, mode: 'system' }
 ]
 
-// Which Light/Dark groups a theme belongs in. Built-ins render in both modes
-// (the engine synthesises the missing side). Imported VS Code themes only carry
-// the variant(s) the extension shipped — a single dark theme like Dracula lives
-// under Dark only, while a GitHub/Solarized family (light + dark) lives in both.
-function themeSupportsMode(name: string, target: 'light' | 'dark'): boolean {
-  if (!isUserTheme(name)) {
-    return true
-  }
-
-  const resolved = resolveTheme(name)
-
-  if (!resolved) {
-    return true
-  }
-
-  const background = target === 'dark' ? (resolved.darkColors ?? resolved.colors).background : resolved.colors.background
-
-  return target === 'dark' ? luminance(background) <= 0.5 : luminance(background) > 0.5
-}
-
 export function CommandPalette() {
   const { t } = useI18n()
   const open = useStore($commandPaletteOpen)
-  const bindings = useStore($bindings)
   const navigate = useNavigate()
-  const { availableThemes, resolvedMode, setMode, setTheme, themeName } = useTheme()
+  const { availableThemes, mode, resolvedMode, setMode, setTheme, themeName } = useTheme()
   const [search, setSearch] = useState('')
   const [page, setPage] = useState<string | null>(null)
 
@@ -248,19 +194,10 @@ export function CommandPalette() {
   }, [open])
 
   const go = useCallback((path: string) => () => navigate(path), [navigate])
-
-  // Step up one nested page (or back to the root list), clearing the filter so
-  // the parent page doesn't reopen mid-search.
-  const goBack = useCallback(() => {
-    setSearch('')
-    setPage(prev => (prev ? (PAGE_PARENTS[prev] ?? null) : null))
-  }, [])
-
   const settingsSectionLabel = useCallback(
     (section: (typeof SECTIONS)[number]) => t.settings.sections[section.id] ?? section.label,
     [t.settings.sections]
   )
-
   const configFieldLabel = useCallback(
     (key: string) =>
       fieldCopyForSchemaKey(t.settings.fieldLabels, key) ??
@@ -277,61 +214,20 @@ export function CommandPalette() {
       {
         heading: cc.goTo,
         items: [
+          { icon: Plus, id: 'nav-new', keywords: ['chat', 'create'], label: cc.nav.newChat.title, run: go(NEW_CHAT_ROUTE) },
+          { icon: Settings, id: 'nav-settings', label: cc.nav.settings.title, run: go(SETTINGS_ROUTE) },
           {
-            action: 'session.new',
-            icon: Plus,
-            id: 'nav-new',
-            keywords: ['chat', 'create'],
-            label: cc.nav.newChat.title,
-            run: go(NEW_CHAT_ROUTE)
-          },
-          {
-            action: 'view.showTerminal',
-            icon: Terminal,
-            id: 'nav-terminal',
-            keywords: ['terminal', 'shell', 'console'],
-            label: t.keybinds.actions['view.showTerminal'],
-            run: () => setTerminalTakeover(true)
-          },
-          {
-            action: 'nav.settings',
-            icon: Settings,
-            id: 'nav-settings',
-            label: cc.nav.settings.title,
-            run: go(SETTINGS_ROUTE)
-          },
-          {
-            action: 'nav.skills',
             icon: Wrench,
             id: 'nav-skills',
             keywords: ['tools', 'toolsets'],
             label: cc.nav.skills.title,
             run: go(SKILLS_ROUTE)
           },
-          {
-            action: 'nav.messaging',
-            icon: MessageCircle,
-            id: 'nav-messaging',
-            label: cc.nav.messaging.title,
-            run: go(MESSAGING_ROUTE)
-          },
-          {
-            action: 'nav.artifacts',
-            icon: Package,
-            id: 'nav-artifacts',
-            label: cc.nav.artifacts.title,
-            run: go(ARTIFACTS_ROUTE)
-          },
-          {
-            action: 'nav.cron',
-            icon: Clock,
-            id: 'nav-cron',
-            keywords: ['schedule', 'jobs'],
-            label: t.shell.statusbar.cron,
-            run: go(CRON_ROUTE)
-          },
-          { action: 'nav.profiles', icon: Users, id: 'nav-profiles', label: t.profiles.title, run: go(PROFILES_ROUTE) },
-          { action: 'nav.agents', icon: Cpu, id: 'nav-agents', label: t.agents.title, run: go(AGENTS_ROUTE) }
+          { icon: MessageCircle, id: 'nav-messaging', label: cc.nav.messaging.title, run: go(MESSAGING_ROUTE) },
+          { icon: Package, id: 'nav-artifacts', label: cc.nav.artifacts.title, run: go(ARTIFACTS_ROUTE) },
+          { icon: Clock, id: 'nav-cron', keywords: ['schedule', 'jobs'], label: t.shell.statusbar.cron, run: go(CRON_ROUTE) },
+          { icon: Users, id: 'nav-profiles', label: t.profiles.title, run: go(PROFILES_ROUTE) },
+          { icon: Cpu, id: 'nav-agents', label: t.agents.title, run: go(AGENTS_ROUTE) }
         ]
       },
       {
@@ -477,40 +373,24 @@ export function CommandPalette() {
       theme: {
         title: t.settings.appearance.themeTitle,
         placeholder: t.settings.appearance.themeDesc,
-        groups: [
-          // Pinned at the top: drills into the Marketplace browser.
-          {
-            items: [
-              {
-                icon: Download,
-                id: 'theme-install',
-                keywords: ['install', 'marketplace', 'vscode', 'vs code', 'download', 'new', 'color'],
-                label: t.commandCenter.installTheme.title,
-                to: 'install-theme'
-              }
-            ]
-          },
-          // Built-ins and imported families list under the mode(s) they support;
-          // picking sets skin + mode at once. A multi-variant import (GitHub,
-          // Solarized) appears in both groups and switches variants with the mode.
-          ...(['light', 'dark'] as const).map(groupMode => ({
-            heading: groupMode === 'light' ? t.settings.modeOptions.light.label : t.settings.modeOptions.dark.label,
-            items: availableThemes
-              .filter(theme => themeSupportsMode(theme.name, groupMode))
-              .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)
-                }
-              }))
+        // 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' ? t.settings.modeOptions.light.label : t.settings.modeOptions.dark.label,
+          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: t.settings.appearance.colorMode,
@@ -519,6 +399,7 @@ export function CommandPalette() {
           {
             heading: t.settings.appearance.colorMode,
             items: THEME_MODES.map(entry => ({
+              active: mode === entry.mode,
               icon: entry.icon,
               id: `mode-${entry.mode}`,
               keepOpen: true,
@@ -528,16 +409,9 @@ export function CommandPalette() {
             }))
           }
         ]
-      },
-      // Server-driven page: items come from the Marketplace, rendered by
-      // <MarketplaceThemePage> (loader + live search + per-row install).
-      'install-theme': {
-        title: t.commandCenter.installTheme.title,
-        placeholder: t.commandCenter.installTheme.placeholder,
-        groups: []
       }
     }),
-    [availableThemes, resolvedMode, setMode, setTheme, t, themeName]
+    [availableThemes, mode, resolvedMode, setMode, setTheme, t, themeName]
   )
 
   const activePage = page ? subPages[page] : null
@@ -562,22 +436,17 @@ export function CommandPalette() {
   return (
     <DialogPrimitive.Root onOpenChange={setCommandPaletteOpen} open={open}>
       <DialogPrimitive.Portal>
-        {/* Transparent overlay: keeps click-away + focus trap, but no dim/blur. */}
-        <DialogPrimitive.Overlay className="fixed inset-0 z-[200]" />
+        <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={cn(
-            HUD_POSITION,
-            HUD_SURFACE,
-            'z-[210] w-[min(34rem,calc(100vw-2rem))] overflow-hidden 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'
-          )}
+          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">{t.commandCenter.paletteTitle}</DialogPrimitive.Title>
-          <Command className="bg-transparent" filter={paletteFilter} loop>
+          <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={goBack}
+                onClick={() => setPage(null)}
                 type="button"
               >
                 <ChevronLeft className="size-3.5" />
@@ -587,7 +456,6 @@ export function CommandPalette() {
               </button>
             )}
             <CommandInput
-              className={HUD_TEXT}
               onKeyDown={event => {
                 if (!activePage) {
                   return
@@ -598,45 +466,38 @@ export function CommandPalette() {
                 if (event.key === 'Escape' || (event.key === 'Backspace' && search === '')) {
                   event.preventDefault()
                   event.stopPropagation()
-                  goBack()
+                  setPage(null)
                 }
               }}
               onValueChange={setSearch}
               placeholder={placeholder}
               value={search}
             />
-            <CommandList className="dt-portal-scrollbar max-h-[min(20rem,56vh)]">
-              {page === 'install-theme' ? (
-                <MarketplaceThemePage onPickTheme={setTheme} search={search} />
-              ) : (
-                <CommandEmpty>{t.commandCenter.noResults}</CommandEmpty>
-              )}
-              {visibleGroups.map((group, index) => (
+            <CommandList className="max-h-[min(24rem,60vh)]">
+              <CommandEmpty>{t.commandCenter.noResults}</CommandEmpty>
+              {visibleGroups.map(group => (
                 <CommandGroup
-                  className={HUD_HEADING}
+                  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 ?? `palette-group-${index}`}
+                  key={group.heading}
                 >
                   {group.items.map(item => {
                     const Icon = item.icon
-                    const combo = item.action ? bindings[item.action]?.[0] : undefined
-                    const keys = combo ? comboTokens(combo) : null
 
                     return (
                       <CommandItem
-                        className={cn(HUD_ITEM, HUD_TEXT)}
+                        className="gap-2.5"
                         key={item.id}
                         keywords={item.keywords}
                         onSelect={() => handleSelect(item)}
                         value={`${item.label} ${item.keywords?.join(' ') ?? ''} ${item.id}`}
                       >
-                        <Icon className="size-3.5 shrink-0 text-muted-foreground" />
+                        <Icon className="size-4 shrink-0 text-muted-foreground" />
                         <span className="truncate">{item.label}</span>
-                        {keys && <KbdGroup className="ml-auto" keys={keys} />}
-                        {item.to && (
-                          <ChevronRight
-                            className={cn('size-3.5 shrink-0 text-muted-foreground/70', !keys && 'ml-auto')}
-                          />
+                        {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>
                     )

apps/desktop/src/app/command-palette/marketplace-theme-page.tsx

@@ -1,157 +0,0 @@
-/**
- * Cmd-K "Install theme…" page.
- *
- * Browses the VS Code Marketplace for color themes: an empty query shows the
- * most-installed themes, typing runs a live (debounced) search against the
- * Marketplace. Selecting a row downloads + converts + installs it via the same
- * pipeline as the settings importer, then activates it — and stays open so the
- * user can grab several.
- */
-
-import { useQuery } from '@tanstack/react-query'
-import { useEffect, useState } from 'react'
-
-import { HUD_ITEM, HUD_TEXT } from '@/app/floating-hud'
-import type { DesktopMarketplaceSearchItem } from '@/global'
-import { useI18n } from '@/i18n'
-import { triggerHaptic } from '@/lib/haptics'
-import { Check, Download, Loader2, Palette } from '@/lib/icons'
-import { cn } from '@/lib/utils'
-import { installVscodeThemeFromMarketplace } from '@/themes/install'
-
-const compactNumber = new Intl.NumberFormat(undefined, { notation: 'compact', maximumFractionDigits: 1 })
-
-function useDebounced<T>(value: T, delayMs: number): T {
-  const [debounced, setDebounced] = useState(value)
-
-  useEffect(() => {
-    const handle = setTimeout(() => setDebounced(value), delayMs)
-
-    return () => clearTimeout(handle)
-  }, [value, delayMs])
-
-  return debounced
-}
-
-interface MarketplaceThemePageProps {
-  search: string
-  /** Activate a freshly installed theme by slug. */
-  onPickTheme: (name: string) => void
-}
-
-export function MarketplaceThemePage({ search, onPickTheme }: MarketplaceThemePageProps) {
-  const { t } = useI18n()
-  const copy = t.commandCenter.installTheme
-  const debouncedSearch = useDebounced(search.trim(), 300)
-  const [installingId, setInstallingId] = useState<string | null>(null)
-  const [installed, setInstalled] = useState<Record<string, true>>({})
-  const [installError, setInstallError] = useState<string | null>(null)
-
-  const query = useQuery({
-    queryKey: ['marketplace-themes', debouncedSearch],
-    queryFn: () => window.hermesDesktop?.themes?.searchMarketplace(debouncedSearch) ?? Promise.resolve([]),
-    staleTime: 5 * 60 * 1000
-  })
-
-  const install = async (item: DesktopMarketplaceSearchItem) => {
-    if (installingId) {
-      return
-    }
-
-    setInstallingId(item.extensionId)
-    setInstallError(null)
-
-    try {
-      const theme = await installVscodeThemeFromMarketplace(item.extensionId)
-
-      triggerHaptic('crisp')
-      setInstalled(prev => ({ ...prev, [item.extensionId]: true }))
-      onPickTheme(theme.name)
-    } catch (error) {
-      setInstallError(error instanceof Error ? error.message : copy.error)
-    } finally {
-      setInstallingId(null)
-    }
-  }
-
-  if (query.isLoading) {
-    return <Status icon={<Loader2 className="size-3.5 animate-spin" />} text={copy.loading} />
-  }
-
-  if (query.isError) {
-    return <Status text={copy.error} tone="error" />
-  }
-
-  const results = query.data ?? []
-
-  if (results.length === 0) {
-    return <Status text={copy.empty} />
-  }
-
-  return (
-    <div role="listbox">
-      {installError && <p className="px-2 pb-1 pt-1.5 text-[0.6875rem] text-(--ui-red)">{installError}</p>}
-      {results.map(item => {
-        const busy = installingId === item.extensionId
-        const done = installed[item.extensionId]
-
-        return (
-          <button
-            className={cn(
-              'flex w-full items-start rounded-md text-left transition-colors hover:bg-(--chrome-action-hover) disabled:opacity-60 aria-disabled:opacity-60',
-              HUD_ITEM,
-              HUD_TEXT
-            )}
-            disabled={Boolean(installingId) && !busy}
-            key={item.extensionId}
-            onClick={() => void install(item)}
-            onMouseDown={event => event.preventDefault()}
-            role="option"
-            type="button"
-          >
-            <Palette className="mt-0.5 size-3.5 shrink-0 text-muted-foreground" />
-            <span className="flex min-w-0 flex-col">
-              <span className="truncate font-medium">{item.displayName}</span>
-              <span className="truncate text-[0.6875rem] text-muted-foreground/80">
-                {item.publisher}
-                {item.installs > 0 ? ` · ${copy.installs(compactNumber.format(item.installs))}` : ''}
-              </span>
-            </span>
-            <span className="ml-auto mt-0.5 flex shrink-0 items-center gap-1 text-[0.6875rem] text-muted-foreground">
-              {busy ? (
-                <>
-                  <Loader2 className="size-3 animate-spin" />
-                  {copy.installing}
-                </>
-              ) : done ? (
-                <>
-                  <Check className="size-3 text-(--ui-green)" />
-                  {copy.installed}
-                </>
-              ) : (
-                <>
-                  <Download className="size-3" />
-                  {copy.install}
-                </>
-              )}
-            </span>
-          </button>
-        )
-      })}
-    </div>
-  )
-}
-
-function Status({ icon, text, tone }: { icon?: React.ReactNode; text: string; tone?: 'error' }) {
-  return (
-    <div
-      className={cn(
-        'flex items-center justify-center gap-2 px-2 py-6 text-xs',
-        tone === 'error' ? 'text-(--ui-red)' : 'text-muted-foreground'
-      )}
-    >
-      {icon}
-      {text}
-    </div>
-  )
-}

apps/desktop/src/app/desktop-controller.tsx

@@ -11,16 +11,9 @@ import { Pane, PaneMain } from '@/components/pane-shell'
 import { useMediaQuery } from '@/hooks/use-media-query'
 import { useSkinCommand } from '@/themes/use-skin-command'
 
-import { requestComposerFocus, requestComposerInsert } from './chat/composer/focus'
 import { formatRefValue } from '../components/assistant-ui/directive-text'
 import { getCronJobs, getSessionMessages, listAllProfileSessions, type SessionInfo, triggerCronJob } from '../hermes'
 import { preserveLocalAssistantErrors, toChatMessages } from '../lib/chat-messages'
-import {
-  isMessagingSource,
-  LOCAL_SESSION_SOURCE_IDS,
-  MESSAGING_SESSION_SOURCE_IDS,
-  normalizeSessionSource
-} from '../lib/session-source'
 import { setCronFocusJobId, setCronJobs } from '../store/cron'
 import {
   $panesFlipped,
@@ -51,14 +44,12 @@ import {
   $currentCwd,
   $freshDraftReady,
   $gatewayState,
-  $messagingSessions,
   $selectedStoredSessionId,
   $sessions,
   $workingSessionIds,
   CRON_SECTION_LIMIT,
   getRecentlySettledSessionIds,
   mergeSessionPage,
-  MESSAGING_SECTION_LIMIT,
   sessionPinId,
   setAwaitingResponse,
   setBusy,
@@ -68,16 +59,12 @@ import {
   setCurrentModel,
   setCurrentProvider,
   setMessages,
-  setMessagingPlatformTotals,
-  setMessagingSessions,
-  setMessagingTruncated,
   setSessionProfileTotals,
   setSessions,
   setSessionsLoading,
   setSessionsTotal
 } from '../store/session'
 import { openUpdatesWindow, startUpdatePoller, stopUpdatePoller } from '../store/updates'
-import { isSecondaryWindow } from '../store/windows'
 
 import { ChatView } from './chat'
 import { useComposerActions } from './chat/hooks/use-composer-actions'
@@ -99,8 +86,6 @@ import { RightSidebarPane } from './right-sidebar'
 import { $terminalTakeover } from './right-sidebar/store'
 import { PersistentTerminal, TerminalSlot } from './right-sidebar/terminal/persistent'
 import { CRON_ROUTE, NEW_CHAT_ROUTE, routeSessionId, sessionRoute, SETTINGS_ROUTE } from './routes'
-import { SessionPickerOverlay } from './session-picker-overlay'
-import { SessionSwitcher } from './session-switcher'
 import { useContextSuggestions } from './session/hooks/use-context-suggestions'
 import { useCwdActions } from './session/hooks/use-cwd-actions'
 import { useHermesConfig } from './session/hooks/use-hermes-config'
@@ -136,22 +121,11 @@ const SkillsView = lazy(async () => ({ default: (await import('./skills')).Skill
 // this cadence while the app is open + visible so new runs surface promptly
 // instead of waiting for the next user-triggered refreshSessions().
 const CRON_POLL_INTERVAL_MS = 30_000
-// The recents list is local-only: cron rows have their own section, and each
-// messaging platform (telegram, discord, …) is fetched separately into its own
-// self-managed sidebar section (refreshMessagingSessions). Excluding both here
-// keeps "Load more" paging through interactive local chats instead of
-// interleaving gateway threads that bury them.
-const SIDEBAR_EXCLUDED_SOURCES = ['cron', ...MESSAGING_SESSION_SOURCE_IDS]
-// The messaging slice is the inverse: drop cron + every local source so only
-// external-platform conversations remain, then split per platform in the UI.
-const MESSAGING_EXCLUDED_SOURCES = ['cron', ...LOCAL_SESSION_SOURCE_IDS]
 
 // Cheap signature compare so the poll only swaps the atom (and re-renders the
 // sidebar) when the visible cron rows actually changed.
 function sameCronSignature(a: SessionInfo[], b: SessionInfo[]): boolean {
-  if (a.length !== b.length) {
-    return false
-  }
+  if (a.length !== b.length) {return false}
 
   return a.every((session, i) => session.id === b[i]?.id && session.title === b[i]?.title)
 }
@@ -227,7 +201,7 @@ export function DesktopController() {
     toggleCommandCenter
   } = useOverlayRouting()
 
-  const terminalSidebarOpen = chatOpen && terminalTakeover
+  const terminalTakeoverActive = chatOpen && terminalTakeover
 
   const titlebarToolGroups = useGroupRegistry<TitlebarTool>()
   const statusbarItemGroups = useGroupRegistry<StatusbarItem>()
@@ -267,31 +241,6 @@ export function DesktopController() {
     }
   }, [])
 
-  // hermes:// deep links (e.g. a docs "Send to App" button for an automation blueprint).
-  // Build the equivalent /blueprint slash command from the payload and drop
-  // it into the composer — the user reviews/edits, then sends; the agent (or
-  // the shared command handler) creates the job. Signal readiness so a link
-  // that arrived during boot is flushed exactly once.
-  useEffect(() => {
-    const unsubscribe = window.hermesDesktop?.onDeepLink?.((payload) => {
-      if (!payload || payload.kind !== 'blueprint' || !payload.name) {
-        return
-      }
-      const slots = Object.entries(payload.params || {})
-        .map(([k, v]) => {
-          const sval = /\s/.test(v) ? `"${v.replace(/"/g, '\\"')}"` : v
-          return `${k}=${sval}`
-        })
-        .join(' ')
-      const command = `/blueprint ${payload.name}${slots ? ' ' + slots : ''}`
-      requestComposerInsert(command, { mode: 'block', target: 'main' })
-      requestComposerFocus('main')
-    })
-    // Tell the main process the renderer is ready to receive deep links.
-    void window.hermesDesktop?.signalDeepLinkReady?.()
-    return () => unsubscribe?.()
-  }, [])
-
   useEffect(() => {
     const onKeyDown = (event: KeyboardEvent) => {
       if (!$filePreviewTarget.get() && !$previewTarget.get()) {
@@ -331,51 +280,6 @@ export function DesktopController() {
     }
   }, [])
 
-  // Messaging-platform sessions as their own slice, fetched separately from
-  // local recents so each platform renders a self-managed section and never
-  // competes with local chats for the recents page budget. One combined fetch
-  // seeds every platform; the sidebar splits the rows per source.
-  const refreshMessagingSessions = useCallback(async () => {
-    try {
-      const result = await listAllProfileSessions(MESSAGING_SECTION_LIMIT, 1, 'exclude', 'recent', 'all', {
-        excludeSources: MESSAGING_EXCLUDED_SOURCES
-      })
-
-      // Drop any non-messaging source the broad exclude didn't catch (custom
-      // sources) — those stay in local recents, not a platform section.
-      const rows = result.sessions.filter(s => isMessagingSource(s.source))
-
-      setMessagingSessions(prev => (sameCronSignature(prev, rows) ? prev : rows))
-      // Hit the cap → at least one platform may have more on disk than loaded,
-      // so platform sections offer their own per-platform "load more".
-      setMessagingTruncated(result.sessions.length >= MESSAGING_SECTION_LIMIT)
-    } catch {
-      // Non-fatal: the messaging sections just stay empty/stale.
-    }
-  }, [])
-
-  // Page a single platform's section independently (mirrors the per-profile
-  // pager): fetch that source's next window and merge it back in place, leaving
-  // every other platform's rows untouched. Resolves the platform's exact total.
-  const loadMoreMessagingForPlatform = useCallback(async (platform: string) => {
-    const inPlatform = (s: SessionInfo) => normalizeSessionSource(s.source) === platform
-    const loaded = $messagingSessions.get().filter(inPlatform).length
-
-    const result = await listAllProfileSessions(loaded + SIDEBAR_SESSIONS_PAGE_SIZE, 1, 'exclude', 'recent', 'all', {
-      source: platform
-    })
-
-    const incoming = result.sessions.filter(s => normalizeSessionSource(s.source) === platform)
-
-    setMessagingSessions(prev => [
-      ...prev.filter(s => !inPlatform(s)),
-      ...mergeSessionPage(prev.filter(inPlatform), incoming, sessionsToKeep())
-    ])
-
-    const total = result.total ?? incoming.length
-    setMessagingPlatformTotals(prev => ({ ...prev, [platform]: Math.max(total, incoming.length) }))
-  }, [])
-
   // Cron *jobs* drive the sidebar "Cron jobs" section. Jobs are created
   // synchronously (agent tool call or the cron UI), so refreshing here right
   // after an agent turn surfaces a new job immediately; the interval poll keeps
@@ -412,7 +316,7 @@ export function DesktopController() {
       const sessionProfile = profileScope === ALL_PROFILES ? 'all' : profileScope
 
       const result = await listAllProfileSessions(limit, 1, 'exclude', 'recent', sessionProfile, {
-        excludeSources: SIDEBAR_EXCLUDED_SOURCES
+        excludeSources: ['cron']
       })
 
       if (refreshSessionsRequestRef.current === requestId) {
@@ -428,8 +332,7 @@ export function DesktopController() {
 
     void refreshCronSessions()
     void refreshCronJobs()
-    void refreshMessagingSessions()
-  }, [profileScope, refreshCronSessions, refreshCronJobs, refreshMessagingSessions])
+  }, [profileScope, refreshCronSessions, refreshCronJobs])
 
   const loadMoreSessions = useCallback(() => {
     bumpSessionsLimit()
@@ -444,15 +347,12 @@ export function DesktopController() {
     const loaded = $sessions.get().filter(inKey).length
 
     const result = await listAllProfileSessions(loaded + SIDEBAR_SESSIONS_PAGE_SIZE, 1, 'exclude', 'recent', key, {
-      excludeSources: SIDEBAR_EXCLUDED_SOURCES
+      excludeSources: ['cron']
     })
 
     const keep = sessionsToKeep(key)
 
-    setSessions(prev => [
-      ...prev.filter(s => !inKey(s)),
-      ...mergeSessionPage(prev.filter(inKey), result.sessions, keep)
-    ])
+    setSessions(prev => [...prev.filter(s => !inKey(s)), ...mergeSessionPage(prev.filter(inKey), result.sessions, keep)])
 
     const total = result.profile_totals?.[key] ?? result.total ?? result.sessions.length
     setSessionProfileTotals(prev => ({ ...prev, [key]: Math.max(total, result.sessions.length) }))
@@ -713,20 +613,19 @@ export function DesktopController() {
     submitText,
     transcribeVoiceAudio
   } = usePromptActions({
-    activeSessionId,
-    activeSessionIdRef,
-    branchCurrentSession: branchInNewChat,
-    busyRef,
-    createBackendSessionForSend,
-    handleSkinCommand,
-    refreshSessions,
-    requestGateway,
-    resumeStoredSession: resumeSession,
-    selectedStoredSessionIdRef,
-    startFreshSessionDraft,
-    sttEnabled,
-    updateSessionState
-  })
+      activeSessionId,
+      activeSessionIdRef,
+      branchCurrentSession: branchInNewChat,
+      busyRef,
+      createBackendSessionForSend,
+      handleSkinCommand,
+      refreshSessions,
+      requestGateway,
+      selectedStoredSessionIdRef,
+      startFreshSessionDraft,
+      sttEnabled,
+      updateSessionState
+    })
 
   useGatewayBoot({
     handleGatewayEvent: handleDesktopGatewayEvent,
@@ -752,14 +651,10 @@ export function DesktopController() {
   // in the background (advancing next-run/state and creating runs), so poll the
   // job list on an interval (and on tab re-focus) while connected.
   useEffect(() => {
-    if (gatewayState !== 'open') {
-      return
-    }
+    if (gatewayState !== 'open') {return}
 
     const tick = () => {
-      if (document.visibilityState === 'visible') {
-        void refreshCronJobs()
-      }
+      if (document.visibilityState === 'visible') {void refreshCronJobs()}
     }
 
     const intervalId = window.setInterval(tick, CRON_POLL_INTERVAL_MS)
@@ -771,13 +666,6 @@ export function DesktopController() {
     }
   }, [gatewayState, refreshCronJobs])
 
-  useEffect(() => {
-    if (gatewayState === 'open' && !activeSessionId && freshDraftReady) {
-      void refreshCurrentModel()
-      void refreshHermesConfig()
-    }
-  }, [activeSessionId, freshDraftReady, gatewayState, refreshCurrentModel, refreshHermesConfig])
-
   useRouteResume({
     activeSessionId,
     activeSessionIdRef,
@@ -796,7 +684,6 @@ export function DesktopController() {
 
   const { leftStatusbarItems, statusbarItems } = useStatusbarItems({
     agentsOpen,
-    chatOpen,
     commandCenterOpen,
     extraLeftItems: statusbarItemGroups.flat.left,
     extraRightItems: statusbarItemGroups.flat.right,
@@ -817,7 +704,6 @@ export function DesktopController() {
       currentView={currentView}
       onArchiveSession={sessionId => void archiveSession(sessionId)}
       onDeleteSession={sessionId => void removeSession(sessionId)}
-      onLoadMoreMessaging={loadMoreMessagingForPlatform}
       onLoadMoreProfileSessions={loadMoreSessionsForProfile}
       onLoadMoreSessions={loadMoreSessions}
       onManageCronJob={jobId => {
@@ -835,35 +721,27 @@ export function DesktopController() {
     />
   )
 
-  // One PTY-backed terminal mounted forever; <TerminalSlot /> placeholders decide
-  // where it shows. Lives in main's stacking context (not the root overlay layer)
-  // so pane resize handles still paint above it. Toggling never rebuilds the shell.
-  const mainOverlays = (
-    <PersistentTerminal cwd={currentCwd} onAddSelectionToChat={composer.addTerminalSelectionAttachment} />
-  )
-
   const overlays = (
     <>
-      {!isSecondaryWindow() && <DesktopInstallOverlay />}
-      {!isSecondaryWindow() && (
-        <DesktopOnboardingOverlay
-          enabled={gatewayState === 'open'}
-          onCompleted={() => {
-            void refreshHermesConfig()
-            void refreshCurrentModel()
-            void queryClient.invalidateQueries({ queryKey: ['model-options'] })
-          }}
-          requestGateway={requestGateway}
-        />
-      )}
+      <DesktopInstallOverlay />
+      {/* One PTY-backed terminal mounted forever; <TerminalSlot /> placeholders
+          decide where it shows. Toggling fullscreen never rebuilds the shell. */}
+      <PersistentTerminal cwd={currentCwd} onAddSelectionToChat={composer.addTerminalSelectionAttachment} />
+      <DesktopOnboardingOverlay
+        enabled={gatewayState === 'open'}
+        onCompleted={() => {
+          void refreshHermesConfig()
+          void refreshCurrentModel()
+          void queryClient.invalidateQueries({ queryKey: ['model-options'] })
+        }}
+        requestGateway={requestGateway}
+      />
       <ModelPickerOverlay gateway={gatewayRef.current || undefined} onSelect={selectModel} />
-      <SessionPickerOverlay onResume={resumeSession} />
       <ModelVisibilityOverlay gateway={gatewayRef.current || undefined} onOpenProviders={openProviderSettings} />
       <UpdatesOverlay />
       <GatewayConnectingOverlay />
       <BootFailureOverlay />
       <CommandPalette />
-      <SessionSwitcher />
 
       {settingsOpen && (
         <Suspense fallback={null}>
@@ -951,6 +829,12 @@ export function DesktopController() {
     />
   )
 
+  const takeoverTerminalView = (
+    <div className="relative flex h-full min-h-0 min-w-0 flex-col overflow-hidden bg-(--ui-chat-surface-background) pt-(--titlebar-height)">
+      <TerminalSlot />
+    </div>
+  )
+
   // Flipped layout mirrors the default: sessions sidebar → right, file
   // browser + preview rail → left. Same panes, swapped sides.
   const sidebarSide = panesFlipped ? 'right' : 'left'
@@ -995,56 +879,33 @@ export function DesktopController() {
     </Pane>
   )
 
-  const terminalPane = (
-    <Pane
-      defaultOpen
-      disabled={!terminalSidebarOpen}
-      divider
-      id="terminal-sidebar"
-      key="terminal-sidebar"
-      maxWidth="80vw"
-      minWidth="22vw"
-      resizable
-      side={railSide}
-      width="42vw"
-    >
-      <div className="relative flex h-full min-h-0 min-w-0 flex-col overflow-hidden bg-(--ui-editor-surface-background) pt-(--titlebar-height)">
-        <TerminalSlot />
-      </div>
-    </Pane>
-  )
-
   return (
     <AppShell
       leftStatusbarItems={leftStatusbarItems}
       leftTitlebarTools={titlebarToolGroups.flat.left}
-      mainOverlays={mainOverlays}
       onOpenSettings={openSettings}
       overlays={overlays}
-      previewPaneOpen={chatOpen && Boolean(previewTarget || filePreviewTarget)}
       statusbarItems={statusbarItems}
-      terminalPaneOpen={terminalSidebarOpen}
       titlebarTools={titlebarToolGroups.flat.right}
     >
-      {!isSecondaryWindow() && (
-        <Pane
-          forceCollapsed={narrowViewport}
-          hoverReveal
-          id="chat-sidebar"
-          maxWidth={SIDEBAR_MAX_WIDTH}
-          minWidth={SIDEBAR_DEFAULT_WIDTH}
-          onOverlayActiveChange={setSidebarOverlayMounted}
-          resizable
-          side={sidebarSide}
-          width={`${SIDEBAR_DEFAULT_WIDTH}px`}
-        >
-          {sidebar}
-        </Pane>
-      )}
+      <Pane
+        disabled={terminalTakeoverActive}
+        forceCollapsed={narrowViewport}
+        hoverReveal
+        id="chat-sidebar"
+        maxWidth={SIDEBAR_MAX_WIDTH}
+        minWidth={SIDEBAR_DEFAULT_WIDTH}
+        onOverlayActiveChange={setSidebarOverlayMounted}
+        resizable
+        side={sidebarSide}
+        width={`${SIDEBAR_DEFAULT_WIDTH}px`}
+      >
+        {sidebar}
+      </Pane>
       <PaneMain>
         <Routes>
-          <Route element={chatView} index />
-          <Route element={chatView} path=":sessionId" />
+          <Route element={terminalTakeoverActive ? takeoverTerminalView : chatView} index />
+          <Route element={terminalTakeoverActive ? takeoverTerminalView : chatView} path=":sessionId" />
           <Route
             element={
               <Suspense fallback={null}>
@@ -1081,13 +942,11 @@ export function DesktopController() {
       </PaneMain>
       {/*
         Order within a side maps to column order. Default (rail on the right):
-        main | terminal | preview | file-browser. Flipped (rail on the left):
-        mirror to file-browser | preview | terminal | main so terminal stays
-        adjacent to the chat.
+        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 : terminalPane}
-      {previewPane}
-      {panesFlipped ? terminalPane : fileBrowserPane}
+      {panesFlipped ? fileBrowserPane : previewPane}
+      {panesFlipped ? previewPane : fileBrowserPane}
     </AppShell>
   )
 }

apps/desktop/src/app/floating-hud.ts

@@ -1,22 +0,0 @@
-// Shared chrome for the top-center floating HUDs (command palette + session
-// switcher). They pin just under the title bar, centered, and lean on a crisp
-// border + shadow to separate from the app — no dimming/blurring backdrop.
-// Each caller layers on its own z-index, width, and overflow.
-export const HUD_POSITION = 'fixed left-1/2 top-3 -translate-x-1/2'
-
-// Matches the app's borderless-overlay surface (dialog, keybind panel, …):
-// hairline `--stroke-nous` paired with the soft `--shadow-nous` float.
-export const HUD_SURFACE = 'rounded-xl border border-(--stroke-nous) bg-(--ui-chat-bubble-background) shadow-nous'
-
-// One row/text size for both HUDs (compact — two notches under `text-sm`).
-export const HUD_TEXT = 'text-xs'
-
-// Shared item layout + padding for both HUDs. Tight vertical rhythm so rows
-// don't feel chunky; overrides the shadcn `CommandItem` default (`px-2 py-1.5`).
-export const HUD_ITEM = 'gap-2 px-2 py-1'
-
-// Section headings styled like the sidebar panel labels: brand-tinted, uppercase,
-// tightly tracked — plain text, no sticky chrome bar. Targets the cmdk group
-// heading via the universal-descendant variant.
-export const HUD_HEADING =
-  '**:[[cmdk-group-heading]]:static **:[[cmdk-group-heading]]:bg-transparent **:[[cmdk-group-heading]]:px-2.5 **:[[cmdk-group-heading]]:pb-1 **:[[cmdk-group-heading]]:pt-2.5 **:[[cmdk-group-heading]]:text-[0.64rem] **:[[cmdk-group-heading]]:font-semibold **:[[cmdk-group-heading]]:uppercase **:[[cmdk-group-heading]]:tracking-[0.16em] **:[[cmdk-group-heading]]:text-(--theme-primary)'

apps/desktop/src/app/gateway/hooks/use-gateway-boot.ts

@@ -3,7 +3,6 @@ import { useEffect, useRef } from 'react'
 import type { HermesConnection } from '@/global'
 import { HermesGateway } from '@/hermes'
 import { translateNow } from '@/i18n'
-import { desktopDefaultCwd } from '@/lib/desktop-fs'
 import { isGatewayReauthRequired, resolveGatewayWsUrl } from '@/lib/gateway-ws-url'
 import {
   $desktopBoot,
@@ -26,16 +25,11 @@ import {
 import { notify, notifyError } from '@/store/notifications'
 import { $activeGatewayProfile, normalizeProfileKey, touchActiveGatewayBackend } from '@/store/profile'
 import {
-  $activeSessionId,
   $attentionSessionIds,
   $connection,
-  $currentCwd,
   $sessions,
   $workingSessionIds,
-  ensureDefaultWorkspaceCwd,
   setConnection,
-  setCurrentBranch,
-  setCurrentCwd,
   setSessionsLoading
 } from '@/store/session'
 import type { RpcEvent } from '@/types/hermes'
@@ -357,12 +351,6 @@ export function useGatewayBoot({
           message: translateNow('boot.steps.loadingSettings'),
           progress: 97
         })
-        await ensureDefaultWorkspaceCwd()
-        const remoteDefault = await desktopDefaultCwd().catch(() => null)
-        if (remoteDefault?.cwd && !$activeSessionId.get() && !$currentCwd.get()) {
-          setCurrentCwd(remoteDefault.cwd)
-          setCurrentBranch(remoteDefault.branch || '')
-        }
         await callbacksRef.current.refreshHermesConfig()
 
         if (cancelled) {

apps/desktop/src/app/hooks/use-keybinds.ts

@@ -1,10 +1,10 @@
 import { useEffect, useRef } from 'react'
 import { useNavigate } from 'react-router-dom'
 
-import { $terminalTakeover, setTerminalTakeover } from '@/app/right-sidebar/store'
+import { setRightSidebarTab } from '@/app/right-sidebar/store'
 import { PANE_TOGGLE_REVEAL_EVENT } from '@/components/pane-shell'
 import { matchesQuery } from '@/hooks/use-media-query'
-import { PROFILE_SLOT_COUNT, SESSION_SLOT_COUNT } from '@/lib/keybinds/actions'
+import { PROFILE_SLOT_COUNT } from '@/lib/keybinds/actions'
 import { comboAllowedInInput, comboFromEvent, isEditableTarget } from '@/lib/keybinds/combo'
 import { toggleCommandPalette } from '@/store/command-palette'
 import { $capture, $comboIndex, endCapture, setBinding, toggleKeybindPanel } from '@/store/keybinds'
@@ -18,25 +18,13 @@ import {
   toggleSidebarOpen
 } from '@/store/layout'
 import {
-  $newChatProfile,
   cycleProfile,
   requestProfileCreate,
   switchProfileToSlot,
   switchToDefaultProfile,
   toggleShowAllProfiles
 } from '@/store/profile'
-import { setModelPickerOpen } from '@/store/session'
-import {
-  $switcherOpen,
-  closeSwitcher,
-  commitOnCtrlUp,
-  onSwitcherTabDown,
-  onSwitcherTabUp,
-  openOrAdvanceSwitcher,
-  slotSessionId,
-  switcherActive,
-  switcherJustClosed
-} from '@/store/session-switcher'
+import { $activeSessionId, $sessions, setModelPickerOpen } from '@/store/session'
 import { useTheme } from '@/themes/context'
 
 import { requestComposerFocus } from '../chat/composer/focus'
@@ -72,7 +60,6 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
 
   // Keep the latest closures without re-subscribing the listener.
   const handlersRef = useRef<HandlerMap>({})
-  const commitSwitcherRef = useRef<() => void>(() => {})
 
   const profileSwitchHandlers: HandlerMap = {}
 
@@ -80,32 +67,26 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
     profileSwitchHandlers[`profile.switch.${slot}`] = () => switchProfileToSlot(slot)
   }
 
-  const goToSession = (sessionId: null | string) => {
-    if (sessionId) {
-      navigate(sessionRoute(sessionId))
+  // Move to the adjacent session in recency order, wrapping at the ends.
+  const cycleSession = (direction: 1 | -1) => {
+    const sessions = $sessions.get()
+
+    if (sessions.length < 2) {
+      return
+    }
+
+    const current = sessions.findIndex(session => session.id === $activeSessionId.get())
+    const start = current === -1 ? (direction === 1 ? -1 : 0) : current
+    const next = sessions[(start + direction + sessions.length) % sessions.length]
+
+    if (next) {
+      navigate(sessionRoute(next.id))
     }
   }
 
-  // ^N jumps straight to the Nth recent session and dismisses the switcher.
-  const sessionSlotHandlers: HandlerMap = {}
-
-  for (let slot = 1; slot <= SESSION_SLOT_COUNT; slot += 1) {
-    sessionSlotHandlers[`session.slot.${slot}`] = () => {
-      closeSwitcher()
-      goToSession(slotSessionId(slot))
-    }
-  }
-
-  commitSwitcherRef.current = () => goToSession(commitOnCtrlUp())
-
-  const stepSession = (direction: 1 | -1) => {
-    onSwitcherTabDown()
-    goToSession(openOrAdvanceSwitcher(direction))
-  }
-
-  const showFiles = () => {
+  const showRightSidebarTab = (tab: 'files' | 'terminal') => {
     setFileBrowserOpen(true)
-    setTerminalTakeover(false)
+    setRightSidebarTab(tab)
   }
 
   handlersRef.current = {
@@ -125,16 +106,11 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
     'nav.agents': () => navigate(AGENTS_ROUTE),
 
     'session.new': () => {
-      // Match the sidebar New Session button. A plain keyboard new chat should
-      // target the current live profile, not a stale per-profile quick-create
-      // selection from a prior action.
-      $newChatProfile.set(null)
       deps.startFreshSession()
       window.dispatchEvent(new CustomEvent('hermes:new-session-shortcut'))
     },
-    'session.next': () => stepSession(1),
-    'session.prev': () => stepSession(-1),
-    ...sessionSlotHandlers,
+    'session.next': () => cycleSession(1),
+    'session.prev': () => cycleSession(-1),
     'session.focusSearch': requestSessionSearchFocus,
     'session.togglePin': deps.toggleSelectedPin,
 
@@ -152,8 +128,8 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
         toggleFileBrowserOpen()
       }
     },
-    'view.showFiles': showFiles,
-    'view.showTerminal': () => setTerminalTakeover(!$terminalTakeover.get()),
+    'view.showFiles': () => showRightSidebarTab('files'),
+    'view.showTerminal': () => showRightSidebarTab('terminal'),
     'view.flipPanes': togglePanesFlipped,
 
     'appearance.toggleMode': () => setMode(resolvedMode === 'dark' ? 'light' : 'dark'),
@@ -194,16 +170,6 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
         return
       }
 
-      // While the session switcher is up, Esc abandons it (stay put) before any
-      // combo dispatch — ⌃Tab keeps stepping through the existing handler.
-      if (switcherActive() && event.key === 'Escape') {
-        event.preventDefault()
-        event.stopPropagation()
-        closeSwitcher()
-
-        return
-      }
-
       const combo = comboFromEvent(event)
 
       if (!combo) {
@@ -230,39 +196,8 @@ export function useKeybinds(deps: KeybindRuntimeDeps): void {
       handler()
     }
 
-    // Mac-app-switcher commit: lifting Ctrl with the overlay open lands on the
-    // highlighted session. A window blur (Cmd+Tab away mid-switch) cancels so
-    // the overlay never gets stranded waiting for a keyup that never comes.
-    const onKeyUp = (event: KeyboardEvent) => {
-      if (event.key === 'Tab') {
-        onSwitcherTabUp()
-      }
-
-      if (event.key === 'Control') {
-        commitSwitcherRef.current()
-      }
-    }
-
-    const onBlur = () => switcherActive() && closeSwitcher()
-
-    // Swallow trailing contextmenu after Ctrl+click commit (Electron main menu).
-    const onContextMenu = (event: MouseEvent) => {
-      if ($switcherOpen.get() || switcherJustClosed()) {
-        event.preventDefault()
-        event.stopPropagation()
-      }
-    }
-
     window.addEventListener('keydown', onKeyDown, { capture: true })
-    window.addEventListener('keyup', onKeyUp, { capture: true })
-    window.addEventListener('blur', onBlur)
-    window.addEventListener('contextmenu', onContextMenu, { capture: true })
 
-    return () => {
-      window.removeEventListener('keydown', onKeyDown, { capture: true })
-      window.removeEventListener('keyup', onKeyUp, { capture: true })
-      window.removeEventListener('blur', onBlur)
-      window.removeEventListener('contextmenu', onContextMenu, { capture: true })
-    }
+    return () => window.removeEventListener('keydown', onKeyDown, { capture: true })
   }, [])
 }

apps/desktop/src/app/right-sidebar/files/dnd-manager.ts

@@ -1,27 +0,0 @@
-import { createDragDropManager, type DragDropManager } from 'dnd-core'
-import { HTML5Backend } from 'react-dnd-html5-backend'
-
-let manager: DragDropManager | null = null
-
-/**
- * A single, app-lifetime react-dnd manager for the file tree.
- *
- * react-arborist mounts its own react-dnd `DndProvider` with `HTML5Backend`
- * inside every `<Tree>`. react-dnd v14 stores that provider's manager on a
- * global, ref-counted singleton context and nulls it when the count hits 0.
- * On a keyed remount (cwd / collapse changes force a fresh `<Tree>`), the
- * singleton can be torn down and recreated while the previous `HTML5Backend`
- * still owns the `window.__isReactDndHtml5Backend` setup flag — so the new
- * backend's `setup()` throws "Cannot have two HTML5 backends at the same
- * time." and trips the file-tree error boundary (it never recovers, because
- * "Try again" just remounts into the same race).
- *
- * Passing arborist a stable `dndManager` makes it skip the global-singleton
- * path entirely and reuse one backend for the lifetime of the app, so the
- * window flag is never double-claimed.
- */
-export function getFileTreeDndManager(): DragDropManager {
-  manager ??= createDragDropManager(HTML5Backend)
-
-  return manager
-}

apps/desktop/src/app/right-sidebar/files/ipc.test.ts

@@ -1,100 +0,0 @@
-/// <reference types="node" />
-
-import { Buffer } from 'node:buffer'
-
-import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
-
-import type { HermesReadDirEntry, HermesReadDirResult } from '@/global'
-
-import { clearProjectDirCache, readProjectDir } from './ipc'
-
-const readDir = vi.fn<(path: string) => Promise<HermesReadDirResult>>()
-const readFileDataUrl = vi.fn<(path: string) => Promise<string>>()
-const gitRoot = vi.fn<(path: string) => Promise<string | null>>()
-
-function ok(entries: HermesReadDirEntry[]): HermesReadDirResult {
-  return { entries }
-}
-
-function dataUrl(text: string) {
-  return `data:text/plain;base64,${Buffer.from(text, 'utf8').toString('base64')}`
-}
-
-function installBridge() {
-  ;(
-    window as unknown as {
-      hermesDesktop: {
-        gitRoot: typeof gitRoot
-        readDir: typeof readDir
-        readFileDataUrl: typeof readFileDataUrl
-      }
-    }
-  ).hermesDesktop = { gitRoot, readDir, readFileDataUrl }
-}
-
-describe('readProjectDir', () => {
-  beforeEach(() => {
-    clearProjectDirCache()
-    readDir.mockReset()
-    readFileDataUrl.mockReset()
-    gitRoot.mockReset()
-    installBridge()
-  })
-
-  afterEach(() => {
-    clearProjectDirCache()
-    delete (window as unknown as { hermesDesktop?: unknown }).hermesDesktop
-  })
-
-  it('returns no-bridge when the desktop bridge is unavailable', async () => {
-    delete (window as unknown as { hermesDesktop?: unknown }).hermesDesktop
-
-    await expect(readProjectDir('/repo')).resolves.toEqual({ entries: [], error: 'no-bridge' })
-  })
-
-  it('filters gitignored entries when readDir returns Windows-style paths', async () => {
-    gitRoot.mockResolvedValue('C:\\repo')
-    readDir.mockImplementation(async path => {
-      if (path === 'C:\\repo\\src') {
-        return ok([
-          { name: 'debug.log', path: 'C:\\repo\\src\\debug.log', isDirectory: false },
-          { name: '临时.txt', path: 'C:\\repo\\src\\临时.txt', isDirectory: false },
-          { name: 'keep.ts', path: 'C:\\repo\\src\\keep.ts', isDirectory: false }
-        ])
-      }
-
-      if (path === 'C:/repo') {
-        return ok([{ name: '.gitignore', path: 'C:/repo/.gitignore', isDirectory: false }])
-      }
-
-      if (path === 'C:/repo/src') {
-        return ok([])
-      }
-
-      return ok([])
-    })
-    readFileDataUrl.mockResolvedValue(dataUrl('# Unicode 路径规则\nsrc/*.log\nsrc/临时.txt\n'))
-
-    const result = await readProjectDir('C:\\repo\\src', 'C:\\repo')
-
-    expect(result.entries.map(entry => entry.name)).toEqual(['keep.ts'])
-    expect(gitRoot).toHaveBeenCalledWith('C:/repo')
-    expect(readFileDataUrl).toHaveBeenCalledWith('C:/repo/.gitignore')
-  })
-
-  it('does not fetch .gitignore contents when listings do not contain .gitignore', async () => {
-    gitRoot.mockResolvedValue('/repo')
-    readDir.mockImplementation(async path => {
-      if (path === '/repo/src') {
-        return ok([{ name: 'debug.log', path: '/repo/src/debug.log', isDirectory: false }])
-      }
-
-      return ok([])
-    })
-
-    const result = await readProjectDir('/repo/src', '/repo')
-
-    expect(result.entries.map(entry => entry.name)).toEqual(['debug.log'])
-    expect(readFileDataUrl).not.toHaveBeenCalled()
-  })
-})

apps/desktop/src/app/right-sidebar/files/ipc.ts

@@ -1,6 +1,5 @@
 import ignore from 'ignore'
 
-import { desktopFsCacheKey, desktopGitRoot, readDesktopDir, readDesktopFileDataUrl } from '@/lib/desktop-fs'
 import type { HermesReadDirEntry, HermesReadDirResult } from '@/global'
 
 export type ProjectTreeEntry = HermesReadDirEntry
@@ -28,7 +27,7 @@ function decodeDataUrl(dataUrl: string) {
 }
 
 function clean(path: string) {
-  return path.replace(/\\/g, '/').replace(/\/+$/, '') || '/'
+  return path.replace(/\/+$/, '') || '/'
 }
 
 /** Strict POSIX-style relative path; null if `child` is not inside `root`. */
@@ -64,11 +63,15 @@ function ancestorDirs(root: string, dir: string) {
 }
 
 async function gitRootFor(start: string) {
-  const key = `${desktopFsCacheKey()}:${clean(start)}`
+  if (!window.hermesDesktop?.gitRoot) {
+    return null
+  }
+
+  const key = clean(start)
   let cached = gitRootCache.get(key)
 
   if (!cached) {
-    cached = desktopGitRoot(start)
+    cached = window.hermesDesktop.gitRoot(key)
     gitRootCache.set(key, cached)
   }
 
@@ -77,14 +80,18 @@ async function gitRootFor(start: string) {
 
 /** Read .gitignore at `dir` if it actually exists — never probe missing files. */
 async function readGitignore(dir: string): Promise<GitignoreRule | null> {
+  if (!window.hermesDesktop?.readDir || !window.hermesDesktop.readFileDataUrl) {
+    return null
+  }
+
   try {
-    const listing = await readDesktopDir(dir)
+    const listing = await window.hermesDesktop.readDir(dir)
 
     if (!listing.entries.some(e => e.name === '.gitignore' && !e.isDirectory)) {
       return null
     }
 
-    const text = decodeDataUrl(await readDesktopFileDataUrl(`${dir}/.gitignore`))
+    const text = decodeDataUrl(await window.hermesDesktop.readFileDataUrl(`${dir}/.gitignore`))
 
     return { base: dir, ig: ignore().add(text) }
   } catch {
@@ -93,11 +100,11 @@ async function readGitignore(dir: string): Promise<GitignoreRule | null> {
 }
 
 async function gitignoreFor(dir: string) {
-  const key = `${desktopFsCacheKey()}:${clean(dir)}`
+  const key = clean(dir)
   let cached = gitignoreCache.get(key)
 
   if (!cached) {
-    cached = readGitignore(clean(dir))
+    cached = readGitignore(key)
     gitignoreCache.set(key, cached)
   }
 
@@ -135,10 +142,9 @@ export async function readProjectDir(dirPath: string, rootPath = dirPath): Promi
     return { entries: [], error: 'no-bridge' }
   }
 
-  const result = await readDesktopDir(dirPath)
-  const entries = result?.entries ?? []
+  const result = await window.hermesDesktop.readDir(dirPath)
 
-  return { ...result, entries: await filterIgnored(entries, rootPath, dirPath) }
+  return { ...result, entries: await filterIgnored(result.entries, rootPath, dirPath) }
 }
 
 export function clearProjectDirCache(rootPath?: string) {
@@ -149,7 +155,7 @@ export function clearProjectDirCache(rootPath?: string) {
     return
   }
 
-  const key = `${desktopFsCacheKey()}:${clean(rootPath)}`
+  const key = clean(rootPath)
   gitRootCache.delete(key)
   gitignoreCache.delete(key)
 }

apps/desktop/src/app/right-sidebar/files/remote-picker.tsx

@@ -1,177 +0,0 @@
-import { useEffect, useMemo, useState } from 'react'
-
-import { Button } from '@/components/ui/button'
-import { Codicon } from '@/components/ui/codicon'
-import { Dialog, DialogContent, DialogDescription, DialogTitle } from '@/components/ui/dialog'
-import { useI18n } from '@/i18n'
-import { readDesktopDir, setDesktopFsRemotePicker } from '@/lib/desktop-fs'
-import { cn } from '@/lib/utils'
-
-function clean(path: string) {
-  return path.replace(/\/+$/, '') || '/'
-}
-
-function parentDir(path: string) {
-  const value = clean(path)
-  if (value === '/') {
-    return '/'
-  }
-  const parent = value.slice(0, value.lastIndexOf('/'))
-  return parent || '/'
-}
-
-function pathName(path: string) {
-  return path.split('/').filter(Boolean).pop() || path
-}
-
-interface PendingSelection {
-  defaultPath: string
-  resolve: (paths: string[]) => void
-  title: string
-}
-
-export function RemoteFolderPicker() {
-  const { t } = useI18n()
-  const r = t.rightSidebar
-  const [pending, setPending] = useState<PendingSelection | null>(null)
-  const [currentPath, setCurrentPath] = useState('/')
-  const [entries, setEntries] = useState<Array<{ name: string; path: string }>>([])
-  const [error, setError] = useState<string | null>(null)
-  const [loading, setLoading] = useState(false)
-
-  useEffect(() => {
-    setDesktopFsRemotePicker({
-      selectPaths: options =>
-        new Promise(resolve => {
-          const defaultPath = clean(options?.defaultPath || '/')
-          setCurrentPath(defaultPath)
-          setPending({ defaultPath, resolve, title: options?.title || r.remotePickerTitle })
-        })
-    })
-    return () => setDesktopFsRemotePicker(null)
-  }, [r.remotePickerTitle])
-
-  useEffect(() => {
-    if (!pending) {
-      return
-    }
-
-    let active = true
-    setLoading(true)
-    setError(null)
-
-    void readDesktopDir(currentPath)
-      .then(result => {
-        if (!active) {
-          return
-        }
-        if (result.error) {
-          setError(result.error)
-          setEntries([])
-          return
-        }
-        setEntries(result.entries.filter(entry => entry.isDirectory).map(entry => ({ name: entry.name, path: entry.path })))
-      })
-      .catch(err => {
-        if (active) {
-          setError(err instanceof Error ? err.message : String(err))
-          setEntries([])
-        }
-      })
-      .finally(() => {
-        if (active) {
-          setLoading(false)
-        }
-      })
-
-    return () => {
-      active = false
-    }
-  }, [currentPath, pending])
-
-  const crumbs = useMemo(() => {
-    const parts = clean(currentPath).split('/').filter(Boolean)
-    const out = [{ label: '/', path: '/' }]
-    let acc = ''
-    for (const part of parts) {
-      acc += `/${part}`
-      out.push({ label: part, path: acc })
-    }
-    return out
-  }, [currentPath])
-
-  const close = (paths: string[] = []) => {
-    pending?.resolve(paths)
-    setPending(null)
-    setEntries([])
-    setError(null)
-  }
-
-  return (
-    <Dialog onOpenChange={open => !open && close()} open={Boolean(pending)}>
-      <DialogContent className="max-w-lg gap-0 overflow-hidden p-0">
-        <div className="border-b border-border/70 px-4 py-3">
-          <DialogTitle className="text-sm">{pending?.title || r.remotePickerTitle}</DialogTitle>
-          <DialogDescription className="mt-1 text-xs">{r.remotePickerDescription}</DialogDescription>
-        </div>
-
-        <div className="flex min-h-[22rem] flex-col">
-          <div className="flex flex-wrap items-center gap-1 border-b border-border/50 px-3 py-2 text-xs text-muted-foreground">
-            {crumbs.map((crumb, index) => (
-              <button
-                className={cn('rounded px-1.5 py-0.5 hover:bg-muted hover:text-foreground', index === crumbs.length - 1 && 'text-foreground')}
-                key={crumb.path}
-                onClick={() => setCurrentPath(crumb.path)}
-                type="button"
-              >
-                {crumb.label}
-              </button>
-            ))}
-          </div>
-
-          <div className="min-h-0 flex-1 overflow-y-auto p-2">
-            <FolderRow disabled={currentPath === '/'} name=".." onClick={() => setCurrentPath(parentDir(currentPath))} />
-            {loading ? (
-              <div className="flex items-center gap-2 px-2 py-3 text-xs text-muted-foreground">
-                <Codicon name="loading" size="0.8rem" spinning />
-                {r.loadingFiles}
-              </div>
-            ) : error ? (
-              <div className="px-2 py-3 text-xs text-destructive">{r.unreadableBody(error)}</div>
-            ) : entries.length === 0 ? (
-              <div className="px-2 py-3 text-xs text-muted-foreground">{r.emptyBody}</div>
-            ) : (
-              entries.map(entry => <FolderRow key={entry.path} name={pathName(entry.path)} onClick={() => setCurrentPath(entry.path)} />)
-            )}
-          </div>
-        </div>
-
-        <div className="flex items-center justify-between gap-2 border-t border-border/70 px-4 py-3">
-          <div className="min-w-0 truncate text-xs text-muted-foreground">{currentPath}</div>
-          <div className="flex shrink-0 items-center gap-2">
-            <Button onClick={() => close()} size="sm" variant="ghost">
-              {t.common.cancel}
-            </Button>
-            <Button onClick={() => close([currentPath])} size="sm">
-              {r.remotePickerSelect}
-            </Button>
-          </div>
-        </div>
-      </DialogContent>
-    </Dialog>
-  )
-}
-
-function FolderRow({ disabled = false, name, onClick }: { disabled?: boolean; name: string; onClick: () => void }) {
-  return (
-    <button
-      className="flex w-full items-center gap-2 rounded-md px-2 py-1.5 text-left text-xs text-(--ui-text-secondary) hover:bg-(--ui-row-hover-background) hover:text-foreground disabled:pointer-events-none disabled:opacity-40"
-      disabled={disabled}
-      onClick={onClick}
-      type="button"
-    >
-      <Codicon name="folder" size="0.875rem" />
-      <span className="min-w-0 truncate">{name}</span>
-    </button>
-  )
-}