fix(installer): try session PATH before registry refresh in Resolve-UvCmd

Address Copilot review on #37622:
- Check the current process PATH for a trusted uv before refreshing $env:Path
  from the registry, so a session-only trusted uv (prepended for this shell
  but not persisted) is honored instead of being clobbered by the refresh.
- Distinguish the failure modes in the thrown error: a uv that exists but was
  rejected as conda/Anaconda-managed now reports that explicitly, rather than
  implying no uv was found.

.env.example

@@ -417,9 +417,9 @@ IMAGE_TOOLS_DEBUG=false
 # Default STT provider is "local" (faster-whisper) — runs on your machine, no API key needed.
 # Install with: pip install faster-whisper
 # Model downloads automatically on first use (~150 MB for "base").
-# To use cloud providers instead, set GROQ_API_KEY or VOICE_TOOLS_OPENAI_KEY above.
-# Provider priority: local > groq > openai
-# Configure in config.yaml: stt.provider: local | groq | openai
+# To use cloud providers instead, set GROQ_API_KEY, VOICE_TOOLS_OPENAI_KEY, or ELEVENLABS_API_KEY above.
+# Provider priority: local > groq > openai > mistral > xai > elevenlabs
+# Configure in config.yaml: stt.provider: local | groq | openai | mistral | xai | elevenlabs
 
 # =============================================================================
 # STT ADVANCED OVERRIDES (optional)
@@ -427,10 +427,12 @@ IMAGE_TOOLS_DEBUG=false
 # Override default STT models per provider (normally set via stt.model in config.yaml)
 # STT_GROQ_MODEL=whisper-large-v3-turbo
 # STT_OPENAI_MODEL=whisper-1
+# STT_ELEVENLABS_MODEL=scribe_v2
 
 # Override STT provider endpoints (for proxies or self-hosted instances)
 # GROQ_BASE_URL=https://api.groq.com/openai/v1
 # STT_OPENAI_BASE_URL=https://api.openai.com/v1
+# ELEVENLABS_STT_BASE_URL=https://api.elevenlabs.io/v1
 
 # =============================================================================
 # MICROSOFT TEAMS INTEGRATION

.github/workflows/build-windows-installer.yml

@@ -0,0 +1,100 @@
+name: Build Windows Installer
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  # Gate: workflow_dispatch is already restricted to users with write access,
+  # but we want ADMIN-only. Explicitly check the triggering actor's repo
+  # permission via the API and fail fast for anyone below admin.
+  authorize:
+    name: Authorize (admins only)
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - name: Check actor is a repo admin
+        env:
+          GH_TOKEN: ${{ github.token }}
+          ACTOR: ${{ github.actor }}
+        run: |
+          set -euo pipefail
+          perm=$(gh api \
+            "repos/${{ github.repository }}/collaborators/${ACTOR}/permission" \
+            --jq '.permission')
+          echo "Actor '${ACTOR}' has permission: ${perm}"
+          if [ "${perm}" != "admin" ]; then
+            echo "::error::'${ACTOR}' is not a repo admin (permission=${perm}). Refusing to build/sign."
+            exit 1
+          fi
+          echo "Authorized: '${ACTOR}' is an admin."
+
+  build:
+    name: Hermes-Setup.exe
+    needs: authorize
+    runs-on: windows-latest
+    timeout-minutes: 30
+    permissions:
+      contents: read
+      # Required for OIDC auth to Azure (azure/login federated credentials).
+      id-token: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+
+      - name: Setup Node.js
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
+        with:
+          node-version: 22
+          cache: npm
+
+      - name: Install npm dependencies
+        run: npm ci
+
+      - name: Setup Rust
+        uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8  # stable
+
+      - name: Cache Rust targets
+        uses: Swatinem/rust-cache@e18b497796c12c097a38f9edb9d0641fb99eee32  # v2
+        with:
+          workspaces: apps/bootstrap-installer/src-tauri
+
+      - name: Build installer
+        run: npm run tauri:build
+        working-directory: apps/bootstrap-installer
+
+      - name: Azure login (OIDC)
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5  # v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+
+      - name: Sign Hermes-Setup.exe with Azure Artifact Signing
+        uses: azure/artifact-signing-action@c7ab2a863ab5f9a846ddb8265964877ef296ee82  # v2
+        with:
+          endpoint: ${{ vars.AZURE_SIGNING_ENDPOINT }}
+          signing-account-name: ${{ vars.AZURE_SIGNING_ACCOUNT_NAME }}
+          certificate-profile-name: ${{ vars.AZURE_SIGNING_CERTIFICATE_PROFILE }}
+          # Sign both the raw exe and the bundled NSIS installer.
+          files-folder: ${{ github.workspace }}\apps\bootstrap-installer\src-tauri\target\release
+          files-folder-filter: exe
+          files-folder-recurse: true
+          file-digest: SHA256
+          timestamp-rfc3161: http://timestamp.acs.microsoft.com
+          timestamp-digest: SHA256
+
+      - name: Upload NSIS installer
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
+        with:
+          name: Hermes-Setup-installer
+          path: apps/bootstrap-installer/src-tauri/target/release/bundle/nsis/*.exe
+
+      - name: Upload raw exe
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
+        with:
+          name: Hermes-Setup-exe
+          path: apps/bootstrap-installer/src-tauri/target/release/Hermes-Setup.exe

.github/workflows/docker-publish.yml

@@ -26,6 +26,10 @@ on:
 
 permissions:
   contents: read
+  # Needed so the arm64 job can push/pull its registry-backed build cache
+  # to ghcr.io (cache-to/cache-from type=registry).  See the build-arm64
+  # job for why registry cache replaced the gha cache on that arch.
+  packages: write
 
 # Concurrency: push/release runs are NEVER cancelled so every merge gets
 # its own image.  PR runs reuse a PR-scoped group with
@@ -196,11 +200,34 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
 
-      # Build once, load into the local daemon for smoke testing. PR arm64
-      # builds deliberately avoid the gha cache: cold-cache arm64 builds can
-      # outlive GitHub's short-lived Azure cache SAS token, then fail while
-      # reading or writing cache blobs before the smoke test can run.
-      - name: Build image (arm64, smoke test, uncached PR)
+      # Log in to ghcr.io so the registry-backed build cache below can be
+      # read (cache-from) on every event and written (cache-to) on
+      # push/release.  Uses the workflow's GITHUB_TOKEN, which is valid for
+      # the whole job — unlike the gha cache backend's short-lived Azure SAS
+      # token, which expired mid-build on slow cold-cache arm64 runs and
+      # crashed the build before the smoke test (the reason the gha cache
+      # was removed from arm64 PRs in the first place).
+      - name: Log in to ghcr.io (build cache)
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121  # v4.1.0
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Build once, load into the local daemon for smoke testing.
+      #
+      # PR builds use the registry-backed cache READ-ONLY (cache-from only):
+      # they pull warm layers pushed by the most recent main build but never
+      # write, so rapid PR pushes don't race on cache writes or pollute the
+      # cache ref.  This restores warm-cache speed to arm64 PR builds (which
+      # were running fully uncached and were ~45% slower than amd64, making
+      # them the job most often cancelled on supersede).
+      #
+      # Registry cache (type=registry on ghcr.io) is used instead of the gha
+      # cache that previously broke here: its credential is the job-lifetime
+      # GITHUB_TOKEN, not a short-lived SAS token, so the cold-build-outlives-
+      # token failure mode cannot recur.
+      - name: Build image (arm64, smoke test, cache read-only PR)
         if: github.event_name == 'pull_request'
         uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f  # v7.1.0
         with:
@@ -211,9 +238,11 @@ jobs:
           tags: ${{ env.IMAGE_NAME }}:test
           build-args: |
             HERMES_GIT_SHA=${{ github.sha }}
+          cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
 
-      # Main/release builds still use the per-arch gha cache so the digest
-      # push below can reuse layers from this smoke-test build.
+      # Main/release builds read AND write the registry cache so the digest
+      # push below reuses layers from this smoke-test build, and so the next
+      # PR/main build starts warm.
       - name: Build image (arm64, smoke test, cached publish)
         if: github.event_name != 'pull_request'
         uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f  # v7.1.0
@@ -225,8 +254,8 @@ jobs:
           tags: ${{ env.IMAGE_NAME }}:test
           build-args: |
             HERMES_GIT_SHA=${{ github.sha }}
-          cache-from: type=gha,scope=docker-arm64
-          cache-to: type=gha,mode=max,scope=docker-arm64
+          cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
+          cache-to: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64,mode=max
 
       - name: Smoke test image
         uses: ./.github/actions/hermes-smoke-test
@@ -253,8 +282,8 @@ jobs:
           build-args: |
             HERMES_GIT_SHA=${{ github.sha }}
           outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
-          cache-from: type=gha,scope=docker-arm64
-          cache-to: type=gha,mode=max,scope=docker-arm64
+          cache-from: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64
+          cache-to: type=registry,ref=ghcr.io/nousresearch/hermes-agent:buildcache-arm64,mode=max
 
       - name: Export digest
         if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'

.github/workflows/nix-lockfile-fix.yml

@@ -6,8 +6,8 @@ on:
     paths:
       - 'ui-tui/package-lock.json'
       - 'ui-tui/package.json'
-      - 'web/package-lock.json'
-      - 'web/package.json'
+      - 'apps/dashboard/package-lock.json'
+      - 'apps/dashboard/package.json'
   workflow_dispatch:
     inputs:
       pr_number:
@@ -28,7 +28,7 @@ concurrency:
 jobs:
   # ── Auto-fix on main ───────────────────────────────────────────────
   # Fires when a push to main touches package.json or package-lock.json
-  # in ui-tui/ or web/. Runs fix-lockfiles and pushes the hash
+  # in ui-tui/ or apps/dashboard/. Runs fix-lockfiles and pushes the hash
   # update commit directly to main so Nix builds never stay broken.
   #
   # Safety invariants:
@@ -110,7 +110,7 @@ jobs:
             # run recompute from the correct package-lock state.
             pkg_changed="$(git diff --name-only "$BASE_SHA"..origin/main -- \
               'ui-tui/package-lock.json' 'ui-tui/package.json' \
-              'web/package-lock.json' 'web/package.json' || true)"
+              'apps/dashboard/package-lock.json' 'apps/dashboard/package.json' || true)"
             if [ -n "$pkg_changed" ]; then
               echo "::warning::Package files changed since hash computation — aborting; a fresh run will recompute"
               exit 0

.gitignore

@@ -63,6 +63,10 @@ environments/benchmarks/evals/
 
 # Web UI build output
 hermes_cli/web_dist/
+apps/desktop/build/
+apps/desktop/dist/
+apps/desktop/release/
+apps/desktop/*.tsbuildinfo
 
 # Web UI assets — synced from @nous-research/ui at build time via
 # `npm run sync-assets` (see web/package.json).
@@ -85,6 +89,16 @@ website/static/api/skills-index.json
 website/static/api/skills.json
 website/static/api/skills-meta.json
 models-dev-upstream/
+
+# Local editor / agent tooling (machine-specific; keep in global config, not the repo)
+.codex/
+.cursor/
+.gemini/
+.zed/
+.mcp.json
+opencode.json
+config/mcporter.json
+
 hermes_cli/tui_dist/*
 hermes_cli/scripts/
 docs/superpowers/*

AGENTS.md

@@ -2,6 +2,8 @@
 
 Instructions for AI coding assistants and developers working on the hermes-agent codebase.
 
+**Never give up on the right solution.**
+
 ## Development Environment
 
 ```bash
@@ -47,8 +49,8 @@ hermes-agent/
 │   ├── hermes-achievements/  # Gamified achievement tracking
 │   ├── observability/    # Metrics / traces / logs plugin
 │   ├── image_gen/        # Image-generation providers
-│   └── <others>/         # disk-cleanup, example-dashboard, google_meet, platforms,
-│                         #   spotify, strike-freedom-cockpit, ...
+│   └── <others>/         # disk-cleanup, google_meet, platforms, spotify,
+│                         #   strike-freedom-cockpit, ...
 ├── optional-skills/      # Heavier/niche skills shipped but NOT active by default
 ├── skills/               # Built-in skills bundled with the repo
 ├── ui-tui/               # Ink (React) terminal UI — `hermes --tui`
@@ -66,6 +68,29 @@ hermes-agent/
 `gateway.log` when running the gateway. Profile-aware via `get_hermes_home()`.
 Browse with `hermes logs [--follow] [--level ...] [--session ...]`.
 
+## TypeScript Style
+
+Applies to TypeScript across Hermes: desktop, TUI, website, and future TS packages.
+
+- Prefer small nanostores over component state when state is shared, reused, or read by distant UI.
+- Let each feature own its atoms. Chat state belongs near chat, shell state near shell, shared state in `src/store`.
+- Components that render from an atom should use `useStore`. Non-rendering actions should read with `$atom.get()`.
+- Do not pass state through three components when the leaf can subscribe to the atom.
+- Keep persistence beside the atom that owns it.
+- Keep route roots thin. They compose routes and shell; they should not become controllers.
+- No monolithic hooks. A hook should own one narrow job.
+- Prefer colocated action modules over hidden god hooks.
+- If a callback is pure side effect, use the terse void form:
+  `onState={st => void setGatewayState(st)}`.
+- Async UI handlers should make intent explicit:
+  `onClick={() => void save()}`.
+- Prefer interfaces for public props and shared object shapes. Avoid `type X = { ... }` for object props.
+- Extend React primitives for props: `React.ComponentProps<'button'>`, `React.ComponentProps<typeof Dialog>`, `Omit<...>`, `Pick<...>`.
+- Table-driven beats condition ladders when mapping ids, routes, or views.
+- `src/app` owns routes, pages, and page-specific components.
+- `src/store` owns shared atoms.
+- `src/lib` owns shared pure helpers.
+
 ## File Dependency Chain
 
 ```

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 python3-dev libffi-dev procps git openssh-client docker-cli xz-utils && \
+    ca-certificates curl iputils-ping python3 python-is-python3 ripgrep ffmpeg gcc python3-dev python3-venv libffi-dev procps git openssh-client docker-cli xz-utils && \
     rm -rf /var/lib/apt/lists/*
 
 # ---------- s6-overlay install ----------
@@ -73,7 +73,17 @@ RUN set -eu; \
     tar -C / -Jxpf /tmp/s6-overlay-noarch.tar.xz; \
     tar -C / -Jxpf /tmp/s6-overlay-arch.tar.xz; \
     tar -C / -Jxpf /tmp/s6-overlay-symlinks-noarch.tar.xz; \
-    rm /tmp/s6-overlay-*.tar.xz /tmp/s6-overlay.sha256
+    rm /tmp/s6-overlay-*.tar.xz /tmp/s6-overlay.sha256; \
+    # #34192: backward-compat shim for orchestration templates that still\
+    # reference the legacy /usr/bin/tini entrypoint (e.g. Hostinger's\
+    # 'Hermes WebUI' catalog). The image has moved to s6-overlay /init\
+    # as PID 1 (see ENTRYPOINT below + the migration comment at the top\
+    # of this file), but external wrappers pinned to /usr/bin/tini will\
+    # crash with 'tini: No such file or directory' on startup. The shim\
+    # symlinks /usr/bin/tini -> /init so legacy wrappers exec the right\
+    # PID-1 reaper without behavior change for users on the current\
+    # ENTRYPOINT. Safe to drop once the affected catalogs are updated.\
+    ln -sf /init /usr/bin/tini
 
 # Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
 RUN useradd -u 10000 -m -d /opt/data hermes

README.md

@@ -36,9 +36,9 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), [Open
 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
 ```
 
-### Windows (native, PowerShell) — Early Beta
+### Windows (native, PowerShell)
 
-> **Heads up:** Native Windows support is **early beta**. It installs and runs, but hasn't been road-tested as broadly as our Linux/macOS/WSL2 paths. Please [file issues](https://github.com/NousResearch/hermes-agent/issues) when you hit rough edges. For the most battle-tested Windows setup today, run the Linux/macOS one-liner above inside **WSL2**.
+> **Heads up:** Native Windows runs Hermes without WSL — CLI, gateway, TUI, and tools all work natively. If you'd rather use WSL2, the Linux/macOS one-liner above works there too. Found a bug? Please [file issues](https://github.com/NousResearch/hermes-agent/issues).
 
 Run this in PowerShell:
 
@@ -46,13 +46,13 @@ Run this in PowerShell:
 iex (irm https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.ps1)
 ```
 
-The installer handles everything: uv, Python 3.11, Node.js, ripgrep, ffmpeg, **and a portable Git Bash** (MinGit, unpacked to `%LOCALAPPDATA%\hermes\git` — no admin required, completely isolated from any system Git install).  Hermes uses this bundled Git Bash to run shell commands.
+The installer handles everything: uv, Python 3.11, Node.js, ripgrep, ffmpeg, **and a portable Git Bash** (MinGit, unpacked to `%LOCALAPPDATA%\hermes\git` — no admin required, completely isolated from any system Git install). Hermes uses this bundled Git Bash to run shell commands.
 
-If you already have Git installed, the installer detects it and uses that instead.  Otherwise a ~45MB MinGit download is all you need — it won't touch or interfere with any system Git.
+If you already have Git installed, the installer detects it and uses that instead. Otherwise a ~45MB MinGit download is all you need — it won't touch or interfere with any system Git.
 
 > **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies.
 >
-> **Windows:** Native Windows is supported as an **early beta** — the PowerShell one-liner above installs everything, but expect rough edges and please file issues when you hit them. If you'd rather use WSL2 (our most battle-tested Windows path), the Linux command works there too. Native Windows install lives under `%LOCALAPPDATA%\hermes`; WSL2 installs under `~/.hermes` as on Linux.  The only Hermes feature that currently needs WSL2 specifically is the browser-based dashboard chat pane (it uses a POSIX PTY — classic CLI and gateway both run natively).
+> **Windows:** Native Windows is fully supported — the PowerShell one-liner above installs everything. If you'd rather use WSL2, the Linux command works there too. Native Windows install lives under `%LOCALAPPDATA%\hermes`; WSL2 installs under `~/.hermes` as on Linux.  The only Hermes feature that currently needs WSL2 specifically is the browser-based dashboard chat pane (it uses a POSIX PTY — classic CLI and gateway both run natively).
 
 After installation:
 
@@ -104,17 +104,17 @@ You can still bring your own keys per-tool whenever you want — the gateway is
 
 Hermes has two entry points: start the terminal UI with `hermes`, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.
 
-| Action | CLI | Messaging platforms |
-|---------|-----|---------------------|
-| Start chatting | `hermes` | Run `hermes gateway setup` + `hermes gateway start`, then send the bot a message |
-| Start fresh conversation | `/new` or `/reset` | `/new` or `/reset` |
-| Change model | `/model [provider:model]` | `/model [provider:model]` |
-| Set a personality | `/personality [name]` | `/personality [name]` |
-| Retry or undo the last turn | `/retry`, `/undo` | `/retry`, `/undo` |
-| Compress context / check usage | `/compress`, `/usage`, `/insights [--days N]` | `/compress`, `/usage`, `/insights [days]` |
-| Browse skills | `/skills` or `/<skill-name>` | `/<skill-name>` |
-| Interrupt current work | `Ctrl+C` or send a new message | `/stop` or send a new message |
-| Platform-specific status | `/platforms` | `/status`, `/sethome` |
+| Action                         | CLI                                           | Messaging platforms                                                              |
+| ------------------------------ | --------------------------------------------- | -------------------------------------------------------------------------------- |
+| Start chatting                 | `hermes`                                      | Run `hermes gateway setup` + `hermes gateway start`, then send the bot a message |
+| Start fresh conversation       | `/new` or `/reset`                            | `/new` or `/reset`                                                               |
+| Change model                   | `/model [provider:model]`                     | `/model [provider:model]`                                                        |
+| Set a personality              | `/personality [name]`                         | `/personality [name]`                                                            |
+| Retry or undo the last turn    | `/retry`, `/undo`                             | `/retry`, `/undo`                                                                |
+| Compress context / check usage | `/compress`, `/usage`, `/insights [--days N]` | `/compress`, `/usage`, `/insights [days]`                                        |
+| Browse skills                  | `/skills` or `/<skill-name>`                  | `/<skill-name>`                                                                  |
+| Interrupt current work         | `Ctrl+C` or send a new message                | `/stop` or send a new message                                                    |
+| Platform-specific status       | `/platforms`                                  | `/status`, `/sethome`                                                            |
 
 For the full command lists, see the [CLI guide](https://hermes-agent.nousresearch.com/docs/user-guide/cli) and the [Messaging Gateway guide](https://hermes-agent.nousresearch.com/docs/user-guide/messaging).
 
@@ -124,23 +124,23 @@ For the full command lists, see the [CLI guide](https://hermes-agent.nousresearc
 
 All documentation lives at **[hermes-agent.nousresearch.com/docs](https://hermes-agent.nousresearch.com/docs/)**:
 
-| Section | What's Covered |
-|---------|---------------|
-| [Quickstart](https://hermes-agent.nousresearch.com/docs/getting-started/quickstart) | Install → setup → first conversation in 2 minutes |
-| [CLI Usage](https://hermes-agent.nousresearch.com/docs/user-guide/cli) | Commands, keybindings, personalities, sessions |
-| [Configuration](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) | Config file, providers, models, all options |
-| [Messaging Gateway](https://hermes-agent.nousresearch.com/docs/user-guide/messaging) | Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant |
-| [Security](https://hermes-agent.nousresearch.com/docs/user-guide/security) | Command approval, DM pairing, container isolation |
-| [Tools & Toolsets](https://hermes-agent.nousresearch.com/docs/user-guide/features/tools) | 40+ tools, toolset system, terminal backends |
-| [Skills System](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) | Procedural memory, Skills Hub, creating skills |
-| [Memory](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) | Persistent memory, user profiles, best practices |
-| [MCP Integration](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) | Connect any MCP server for extended capabilities |
-| [Cron Scheduling](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) | Scheduled tasks with platform delivery |
-| [Context Files](https://hermes-agent.nousresearch.com/docs/user-guide/features/context-files) | Project context that shapes every conversation |
-| [Architecture](https://hermes-agent.nousresearch.com/docs/developer-guide/architecture) | Project structure, agent loop, key classes |
-| [Contributing](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) | Development setup, PR process, code style |
-| [CLI Reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) | All commands and flags |
-| [Environment Variables](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | Complete env var reference |
+| Section                                                                                             | What's Covered                                             |
+| --------------------------------------------------------------------------------------------------- | ---------------------------------------------------------- |
+| [Quickstart](https://hermes-agent.nousresearch.com/docs/getting-started/quickstart)                 | Install → setup → first conversation in 2 minutes          |
+| [CLI Usage](https://hermes-agent.nousresearch.com/docs/user-guide/cli)                              | Commands, keybindings, personalities, sessions             |
+| [Configuration](https://hermes-agent.nousresearch.com/docs/user-guide/configuration)                | Config file, providers, models, all options                |
+| [Messaging Gateway](https://hermes-agent.nousresearch.com/docs/user-guide/messaging)                | Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant |
+| [Security](https://hermes-agent.nousresearch.com/docs/user-guide/security)                          | Command approval, DM pairing, container isolation          |
+| [Tools & Toolsets](https://hermes-agent.nousresearch.com/docs/user-guide/features/tools)            | 40+ tools, toolset system, terminal backends               |
+| [Skills System](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills)              | Procedural memory, Skills Hub, creating skills             |
+| [Memory](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory)                     | Persistent memory, user profiles, best practices           |
+| [MCP Integration](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp)               | Connect any MCP server for extended capabilities           |
+| [Cron Scheduling](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron)              | Scheduled tasks with platform delivery                     |
+| [Context Files](https://hermes-agent.nousresearch.com/docs/user-guide/features/context-files)       | Project context that shapes every conversation             |
+| [Architecture](https://hermes-agent.nousresearch.com/docs/developer-guide/architecture)             | Project structure, agent loop, key classes                 |
+| [Contributing](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing)             | Development setup, PR process, code style                  |
+| [CLI Reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands)                  | All commands and flags                                     |
+| [Environment Variables](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | Complete env var reference                                 |
 
 ---
 
@@ -160,6 +160,7 @@ hermes claw migrate --overwrite  # Overwrite existing conflicts
 ```
 
 What gets imported:
+
 - **SOUL.md** — persona file
 - **Memories** — MEMORY.md and USER.md entries
 - **Skills** — user-created skills → `~/.hermes/skills/openclaw-imports/`

RELEASE_v0.14.0.md

@@ -3,75 +3,73 @@
 **Release Date:** May 16, 2026
 **Since v0.13.0:** 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community contributors (including co-authors)
 
-> The Foundation Release — Hermes installs and runs anywhere, ships with the things you actually want to use, and stops shipping the things you don't. xAI Grok lands as a SuperGrok OAuth provider with grok-4.3 bumped to a 1M context window. A new OpenAI-compatible local proxy turns any OAuth-authed Hermes provider — Claude Pro, ChatGPT Pro, SuperGrok — into an endpoint that Codex / Aider / Cline / Continue can hit. `x_search` lands as a first-class X (Twitter) search tool with OAuth-or-API-key auth. The Microsoft Teams stack is wired end-to-end (Graph auth + webhook listener + pipeline runtime + outbound delivery). A debloating wave makes installs dramatically lighter — heavyweight backends now lazy-install on first use, the `[all]` extras drop everything covered by lazy-deps, and a tiered install falls back when a wheel rejects on your platform. `pip install hermes-agent` works from PyPI. The cold-start wave shaves ~19 seconds off `hermes` launch. Browser CDP calls are 180x faster. Two new messaging platforms (LINE + SimpleX Chat) bring the total to 22. Cross-session 1-hour Claude prompt caching, `/handoff` that actually transfers sessions live, native button UI for `clarify` on Telegram and Discord, Discord channel history backfill, LSP semantic diagnostics on every write, a unified pluggable `video_generate`, a `computer_use` cua-driver backend that finally works with non-Anthropic providers, clickable URLs in any terminal, Zed ACP Registry integration via `uvx`, native Windows beta, 9 new optional skills, OpenRouter Pareto Code router, huggingface/skills as a trusted default tap. 12 P0 + 50 P1 closures.
+> The Foundation Release — Hermes Agent installs and runs anywhere now. Native Windows ships in early beta with a full PowerShell installer story, a `pip install hermes-agent` wheel lands on PyPI, lazy-deps reshape what `pip install hermes-agent` actually pulls down, the supply-chain checker scans every install/upgrade for unsafe versions, and a new OpenAI-compatible local proxy lets Codex / Aider / Cline talk to OAuth-only providers (Claude Pro, ChatGPT Pro, SuperGrok). The cold-start wave shaves ~19 seconds off `hermes` launch, browser-tool CDP calls run 180x faster, and `hermes tools` All-Platforms drops from 14s to under 1.5s. Two new messaging platforms (LINE and SimpleX Chat) and a Microsoft Graph foundation (Teams pipeline + webhook adapter) land alongside `/handoff` that finally transfers sessions live, `vision_analyze` passing pixels through to vision-capable models, `x_search` as a first-class tool, LSP semantic diagnostics on every `write_file` / `patch`, a unified pluggable `video_generate`, a `computer_use` cua-driver backend, cross-session 1-hour Claude prompt caching, a per-turn file-mutation verifier, plus 9 new optional skills. 50+ P1 closures, 12 P0 closures.
 
 ---
 
 ## ✨ Highlights
 
-- **xAI Grok via SuperGrok OAuth — and grok-4.3 jumps to a 1M context window** — If you pay for SuperGrok, you can now use Grok inside Hermes by signing in with your xAI account — no API key, no separate billing. The wire-through also bumps grok-4.3 to a 1M token context window, so you can drop whole codebases or research corpora into a single prompt. Includes proper handling for entitlement errors and an SSH-to-tunnel docs page for when you're SSH'd into a remote box and need to complete the OAuth flow. ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534), [#26664](https://github.com/NousResearch/hermes-agent/pull/26664), [#26644](https://github.com/NousResearch/hermes-agent/pull/26644), [#26592](https://github.com/NousResearch/hermes-agent/pull/26592))
+- **Native Windows support (early beta)** — full PowerShell installer, native subprocess/PTY paths, taskkill-based process management, MinGit auto-install, Microsoft Store python stub detection, foreground Ctrl+C preservation, taskkill+ps2 fallback, npm prefix handling, and ~40 follow-up Windows-only fixes across CLI / gateway / TUI / curator / tools. Hermes finally runs natively on `cmd.exe` and PowerShell, no WSL required. ([#21561](https://github.com/NousResearch/hermes-agent/pull/21561), [#22130](https://github.com/NousResearch/hermes-agent/pull/22130), [#22752](https://github.com/NousResearch/hermes-agent/pull/22752), [#26618](https://github.com/NousResearch/hermes-agent/pull/26618), and many more)
 
-- **OpenAI-compatible local proxy for OAuth providers** — Run `hermes proxy` and you get a `http://localhost:port` endpoint that speaks the OpenAI API but is backed by whichever OAuth provider you're signed into — Claude Pro, ChatGPT Pro, SuperGrok. Now any tool that expects an OpenAI-compatible endpoint (Codex CLI, Aider, Cline, Continue, your custom scripts) just works with your existing subscription, no API key required. One subscription, every tool. ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))
+- **`pip install hermes-agent && hermes`** — Hermes Agent is now a real PyPI package. One command, no clone, no git, no shell installer. Wheel includes the Ink TUI bundle and shell launcher. (salvage of [#26350](https://github.com/NousResearch/hermes-agent/pull/26350)) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
 
-- **`x_search` — first-class X (Twitter) search tool** — The agent can now search X directly without installing a skill or wiring up a custom integration. Search the timeline, find threads, surface specific posts — straight from the chat. Auth with either your X OAuth login or an API key, whichever you have. ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))
+- **Cold-start performance wave — ~19s off `hermes` launch** — skills cache, lazy Feishu import, no Nous HTTP at startup, plus PEP-562 lazy adapter imports (QQ, Yuanbao, Teams, Google Chat), deferred `fal_client` / `google-cloud` / `httpx` loads, models.dev disk-cache-first lookup, parallel doctor API checks, eager-skip plugin discovery on built-in subcommands, `hermes tools` All-Platforms drops from 14s to <1.5s, welcome banner skipped on `chat -q`. ([#22138](https://github.com/NousResearch/hermes-agent/pull/22138), [#22120](https://github.com/NousResearch/hermes-agent/pull/22120), [#22681](https://github.com/NousResearch/hermes-agent/pull/22681), [#22790](https://github.com/NousResearch/hermes-agent/pull/22790), [#22808](https://github.com/NousResearch/hermes-agent/pull/22808), [#22831](https://github.com/NousResearch/hermes-agent/pull/22831), [#22859](https://github.com/NousResearch/hermes-agent/pull/22859), [#22904](https://github.com/NousResearch/hermes-agent/pull/22904), [#22766](https://github.com/NousResearch/hermes-agent/pull/22766), [#25341](https://github.com/NousResearch/hermes-agent/pull/25341))
 
-- **Microsoft Teams — end-to-end** — Hermes can now read messages from Teams and post back. The full Microsoft Graph stack lands together: auth + client foundation, a webhook listener that receives Teams events, a pipeline plugin runtime, and outbound delivery. Wire up the bot once, then chat to your agent from any Teams channel, DM, or group. (salvages of #21408–#21411) ([#21922](https://github.com/NousResearch/hermes-agent/pull/21922), [#21969](https://github.com/NousResearch/hermes-agent/pull/21969), [#22007](https://github.com/NousResearch/hermes-agent/pull/22007), [#22024](https://github.com/NousResearch/hermes-agent/pull/22024))
+- **180x faster `browser_console` evaluations** — routed through the supervisor's persistent CDP WebSocket instead of spawning a fresh DevTools session per call. Real-world page interactions feel instant. ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
 
-- **Debloating wave — lighter installs, less you don't use** — A clean `pip install hermes-agent` used to pull down everything: every messaging adapter SDK, every image-gen SDK, every voice/TTS provider, whether you used them or not. Now those heavy backends (Slack / Matrix / Feishu / DingTalk adapters, hindsight client, codex app-server, Pixverse / Camofox / image-gen SDKs, voice/TTS providers) install automatically the first time you actually use them. The `[all]` extras drop everything covered by lazy-deps, the installer falls back through tiers when a wheel doesn't fit your platform, and a supply-chain advisory checker scans every install for unsafe versions. Faster installs, smaller disk footprint, fewer transitive vulnerabilities. ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220), [#24515](https://github.com/NousResearch/hermes-agent/pull/24515), [#25014](https://github.com/NousResearch/hermes-agent/pull/25014), [#25038](https://github.com/NousResearch/hermes-agent/pull/25038), [#25766](https://github.com/NousResearch/hermes-agent/pull/25766), [#21818](https://github.com/NousResearch/hermes-agent/pull/21818))
+- **Supply-chain advisory checker + lazy-deps framework + tiered install fallback** — every `pip install` / `hermes update` scans dependencies against an advisory list, lazy-deps replace heavy import-time loads with first-use installs, and the installer falls back through extras tiers when a wheel rejects on the target platform. ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
 
-- **`pip install hermes-agent && hermes`** — Hermes Agent is now a real PyPI package. No more cloning the repo or running shell installers — one pip command and you're running. The wheel ships with the Ink TUI bundle and the shell launcher, so the full experience comes out of the box. (salvage of [#26350](https://github.com/NousResearch/hermes-agent/pull/26350)) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593), [#26148](https://github.com/NousResearch/hermes-agent/pull/26148))
+- **OpenAI-compatible local proxy** — `hermes proxy` exposes any OAuth-authed provider (Claude Pro, ChatGPT Pro, SuperGrok) as an OpenAI-compatible endpoint that Codex / Aider / Cline / VS Code Continue can hit. Your subscription, your tools. ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))
 
-- **Cross-session 1h Claude prompt cache** — When you use Claude through Anthropic, OpenRouter, or Nous Portal, the prompt prefix (system prompt, skills, memory) now caches for an hour across sessions. Start a `/new` session and the first response comes back faster and cheaper because the cache is still warm from your last session. Background memory review hits the cache too, so it's not paying full price every turn. ([#23828](https://github.com/NousResearch/hermes-agent/pull/23828), [#25434](https://github.com/NousResearch/hermes-agent/pull/25434), [#24778](https://github.com/NousResearch/hermes-agent/pull/24778))
+- **Cross-session 1-hour Claude prompt cache** — Anthropic / OpenRouter / Nous Portal now share a 1h prefix cache across sessions for Claude models. Fast resume, fast `/new`, lower cost on repeat work. ([#23828](https://github.com/NousResearch/hermes-agent/pull/23828))
 
-- **180x faster `browser_console` evaluations** — When the agent uses the browser tool to inspect a page or run JavaScript, those calls now share one persistent connection to Chrome instead of spinning up a new DevTools session every time. The difference is huge: things that used to take a couple of seconds per call return in milliseconds. Real-world page interactions feel instant. ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
+- **Two new messaging platforms — LINE + SimpleX Chat** — LINE Messaging API lands as a first-class platform, SimpleX Chat salvages #2558 onto the modern adapter spec. Hermes is now on 22 platforms. ([#23197](https://github.com/NousResearch/hermes-agent/pull/23197), [#26232](https://github.com/NousResearch/hermes-agent/pull/26232))
 
-- **Cold-start performance wave — ~19 seconds off `hermes` launch** — Running `hermes` used to make you wait through a chunk of import overhead and network calls before you saw a prompt. Now the launch path is mostly deferred: heavy adapters only load when you use them, model catalogs come from disk cache first, doctor checks run in parallel, and `chat -q` skips the welcome banner entirely. The `hermes tools` All-Platforms screen alone dropped from 14 seconds to under 1.5 seconds. ([#22138](https://github.com/NousResearch/hermes-agent/pull/22138), [#22120](https://github.com/NousResearch/hermes-agent/pull/22120), [#22681](https://github.com/NousResearch/hermes-agent/pull/22681), [#22790](https://github.com/NousResearch/hermes-agent/pull/22790), [#22808](https://github.com/NousResearch/hermes-agent/pull/22808), [#22831](https://github.com/NousResearch/hermes-agent/pull/22831), [#22859](https://github.com/NousResearch/hermes-agent/pull/22859), [#22904](https://github.com/NousResearch/hermes-agent/pull/22904), [#22766](https://github.com/NousResearch/hermes-agent/pull/22766), [#25341](https://github.com/NousResearch/hermes-agent/pull/25341))
+- **Microsoft Graph foundation — Teams pipeline + webhook adapter** — `msgraph` auth/client foundation, webhook listener platform, Teams pipeline plugin runtime, and Teams outbound delivery via the existing adapter — Hermes can now read and post to Teams. (salvages of #21408–#21411) ([#21922](https://github.com/NousResearch/hermes-agent/pull/21922), [#21969](https://github.com/NousResearch/hermes-agent/pull/21969), [#22007](https://github.com/NousResearch/hermes-agent/pull/22007), [#22024](https://github.com/NousResearch/hermes-agent/pull/22024))
 
-- **Two new messaging platforms — LINE + SimpleX Chat** — LINE is huge in Japan, Korea, and Taiwan, and now Hermes runs natively on the LINE Messaging API. SimpleX Chat is the privacy-focused decentralized messenger with no user IDs — also wired up as a first-class platform. That brings Hermes to 22 messaging platforms total, so wherever you and your team chat, the agent can be there. ([#23197](https://github.com/NousResearch/hermes-agent/pull/23197), [#26232](https://github.com/NousResearch/hermes-agent/pull/26232))
+- **`/handoff` actually transfers the session live** — the agent's active session moves to a different model / persona / profile mid-conversation, with messages, tool history, and context preserved. ([#23395](https://github.com/NousResearch/hermes-agent/pull/23395))
 
-- **`/handoff` actually transfers the session live** — Switching models or personalities mid-conversation used to mean losing context or starting over. Now `/handoff` moves your active session — every message, every tool call, every piece of context — to the target model, persona, or profile, live, without dropping anything. Mid-debugging hand off from a fast model to a deep-reasoning one, or pass a session between profiles for different parts of a task. ([#23395](https://github.com/NousResearch/hermes-agent/pull/23395))
+- **`x_search` — first-class X (Twitter) search tool** — gated tool with OAuth-or-API-key auth, no skill needed to query the timeline. ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))
 
-- **Native button UI for `clarify` on Telegram and Discord** — When the agent uses the `clarify` tool to ask you a multiple-choice question, it now shows real platform-native buttons on Telegram and Discord instead of asking you to type back the option number. Tap the button, the agent gets your answer. Especially nice on mobile. ([#24199](https://github.com/NousResearch/hermes-agent/pull/24199), [#25485](https://github.com/NousResearch/hermes-agent/pull/25485))
+- **`vision_analyze` returns pixels to vision-capable models** — when the active model can see, `vision_analyze` now hands the image straight through instead of falling back to a text description. ([#22955](https://github.com/NousResearch/hermes-agent/pull/22955))
 
-- **Discord channel history backfill (default on)** — When Hermes joins a Discord channel or thread for the first time, it now reads the recent message history so it knows what's been said before it responds. No more "what are we talking about?" — the agent has the context that's already on screen for everyone else. ([#25984](https://github.com/NousResearch/hermes-agent/pull/25984))
+- **LSP semantic diagnostics on every write** — `write_file` and `patch` now run real language-server diagnostics on the post-edit file (delta-only) and surface real errors before they ship downstream. ([#24168](https://github.com/NousResearch/hermes-agent/pull/24168), [#25978](https://github.com/NousResearch/hermes-agent/pull/25978))
 
-- **`vision_analyze` returns pixels to vision-capable models** — When you point the agent at an image with `vision_analyze` and the active model can actually see (GPT-5, Claude, Gemini, Grok-vision), Hermes now passes the raw pixels straight to the model instead of converting them to a text description first. You get the model's actual visual reasoning instead of a degraded text-summary round-trip. ([#22955](https://github.com/NousResearch/hermes-agent/pull/22955))
+- **Per-turn file-mutation verifier footer** — after every turn that wrote files, the agent gets a verifier footer summarizing what actually changed on disk — catches silent overwrites and "wrote it but it didn't land" bugs. ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
 
-- **Per-turn file-mutation verifier footer** — After every turn that wrote or edited files, the agent now gets a short footer summarizing exactly what changed on disk — the file paths, the line counts, the actual delta. That means the agent catches its own mistakes when a write didn't land or got silently overwritten, instead of confidently telling you "I added the function" when the file wasn't actually saved. ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
+- **Unified `video_generate` with pluggable provider backends** — single tool, any backend. Drop in a new video provider as a plugin, no core changes. ([#25126](https://github.com/NousResearch/hermes-agent/pull/25126))
 
-- **LSP semantic diagnostics on every write** — When the agent uses `write_file` or `patch`, Hermes now runs a real language server against the edited file and surfaces any new errors back to the agent before the next turn. Type errors, undefined symbols, missing imports — caught immediately. Goes way beyond v0.13.0's basic Python/JSON/YAML/TOML linting because it's actual semantic analysis. ([#24168](https://github.com/NousResearch/hermes-agent/pull/24168), [#25978](https://github.com/NousResearch/hermes-agent/pull/25978))
+- **`computer_use` cua-driver backend** — proper focus-safe ops, non-Anthropic provider support, refresh on `hermes update`. Computer-use is no longer locked to a single SDK. (re-salvage of #16936) ([#21967](https://github.com/NousResearch/hermes-agent/pull/21967), [#24063](https://github.com/NousResearch/hermes-agent/pull/24063))
 
-- **Unified `video_generate` with pluggable provider backends** — One tool, any video model. Hermes ships with the obvious backends already, but you can drop in a new video provider as a plugin without touching core. So when a new video model lands next month, it can be a one-file plugin instead of a fork. ([#25126](https://github.com/NousResearch/hermes-agent/pull/25126))
+- **xAI Grok OAuth provider — SuperGrok via subscription** — sign in with your xAI account, talk to Grok models from Hermes. ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534))
 
-- **`computer_use` cua-driver backend — works with non-Anthropic models now** — Computer-use (the agent controlling your mouse and keyboard to drive GUI apps) used to be locked to Anthropic's SDK. The new cua-driver backend works with non-Anthropic providers too, has proper focus-safe operations, and refreshes itself on `hermes update`. Now any vision-capable model can drive your desktop. (re-salvage of #16936) ([#21967](https://github.com/NousResearch/hermes-agent/pull/21967), [#24063](https://github.com/NousResearch/hermes-agent/pull/24063))
+- **Clarify with buttons — native inline keyboards on Telegram + Discord** — the `clarify` tool renders multi-choice prompts as platform-native buttons instead of typed responses. ([#24199](https://github.com/NousResearch/hermes-agent/pull/24199), [#25485](https://github.com/NousResearch/hermes-agent/pull/25485))
 
-- **Clickable URLs in any terminal** — Links in agent output are now real OSC8 hyperlinks with hover-highlight in any terminal that supports them. Click to open in your browser — no more copy-paste-trim of long URLs from the transcript. Just works in iTerm2, Kitty, Ghostty, modern Windows Terminal, etc. (@OutThisLife) ([#25071](https://github.com/NousResearch/hermes-agent/pull/25071), [#24013](https://github.com/NousResearch/hermes-agent/pull/24013))
+- **Discord channel history backfill (default on)** — Hermes reads recent channel history when joining a thread so it actually knows what's been said. ([#25984](https://github.com/NousResearch/hermes-agent/pull/25984))
 
-- **Zed ACP Registry — `uvx` install in one click** — Hermes is now listed in Zed's Agent Client Protocol registry, so Zed users can install it with one click. The install path uses `uvx` so there's no npm dependency. `hermes acp --setup-browser` bootstraps the browser tools for registry-driven installs. (salvage of [#25908](https://github.com/NousResearch/hermes-agent/pull/25908)) ([#26079](https://github.com/NousResearch/hermes-agent/pull/26079), [#26120](https://github.com/NousResearch/hermes-agent/pull/26120), [#26234](https://github.com/NousResearch/hermes-agent/pull/26234))
+- **Watchers skill — RSS / HTTP JSON / GitHub polling via cron `no_agent` mode** — skill recipes that wire change-detection sources directly into cron's script-only watchdog mode. ([#21881](https://github.com/NousResearch/hermes-agent/pull/21881))
 
-- **OpenRouter Pareto Code router with `min_coding_score` knob** — OpenRouter's "Pareto" router automatically picks the cheapest model that meets a minimum quality bar. The new `min_coding_score` config lets you set that bar for coding tasks specifically — Hermes routes to the most affordable model that's at least that good at code. Stop paying for top-tier models when a mid-tier one would do. ([#22838](https://github.com/NousResearch/hermes-agent/pull/22838))
+- **Zed ACP Registry integration + uvx distribution** — Hermes is in the Zed registry, installable via `uvx` (no npm). Plus `hermes acp --setup-browser` bootstraps browser tools for registry installs. (salvage of [#25908](https://github.com/NousResearch/hermes-agent/pull/25908)) ([#26079](https://github.com/NousResearch/hermes-agent/pull/26079), [#26120](https://github.com/NousResearch/hermes-agent/pull/26120), [#26234](https://github.com/NousResearch/hermes-agent/pull/26234))
 
-- **NovitaAI as a new model provider** — NovitaAI joins the provider lineup, giving you another option for open-source model hosting (Llama, Qwen, DeepSeek, etc.) with their pricing and rate limits. (salvage #7219) (@kshitijk4poor) ([#25507](https://github.com/NousResearch/hermes-agent/pull/25507))
+- **OpenRouter Pareto Code router** — wire a new OpenRouter router with `min_coding_score` knob. Pick the cheapest model that meets your quality bar. ([#22838](https://github.com/NousResearch/hermes-agent/pull/22838))
 
-- **Codex app-server runtime for OpenAI/Codex models** — An optional runtime that drives OpenAI's Codex CLI under the hood when you're using OpenAI or Codex paths. You get session reuse, automatic retirement of wedged sessions, and proper OAuth refresh classification — the kind of plumbing that makes long agentic runs not fall over. ([#24182](https://github.com/NousResearch/hermes-agent/pull/24182), [#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
+- **Optional codex app-server runtime for OpenAI/Codex models** — drives the OpenAI Codex CLI under the hood for OpenAI/Codex paths, with session reuse, wedge retirement, and OAuth refresh classification. ([#24182](https://github.com/NousResearch/hermes-agent/pull/24182), [#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
 
-- **`huggingface/skills` as a trusted default tap** — The community skills index hosted at huggingface.co/skills is now wired into the Skills Hub by default. So when somebody publishes a useful skill there, you can install it from your own `hermes skills` browser without any extra config. (closes #2549) ([#26219](https://github.com/NousResearch/hermes-agent/pull/26219))
+- **`hermes-skills/huggingface` as a trusted default tap** — community skills index from huggingface.co/skills is available by default in the Skills Hub. ([#26219](https://github.com/NousResearch/hermes-agent/pull/26219))
 
-- **9 new optional skills** — Hyperliquid (perp + spot trading via the SDK and REST API), Yahoo Finance (live market data, fundamentals, historicals), api-testing (REST + GraphQL debug recipes), unified EVM multi-chain (one skill covers Ethereum + L2s + Base), darwinian-evolver (evolutionary prompt/skill tuning), osint-investigation (OSINT recipes for people / domains / orgs), pinggy-tunnel (expose local services to the public internet), watchers (polls RSS / HTTP JSON / GitHub via cron `no_agent` mode for change detection), and a full Notion overhaul for the May 2026 Developer Platform. ([#23582](https://github.com/NousResearch/hermes-agent/pull/23582), [#23583](https://github.com/NousResearch/hermes-agent/pull/23583), [#23590](https://github.com/NousResearch/hermes-agent/pull/23590), [#25299](https://github.com/NousResearch/hermes-agent/pull/25299), [#26760](https://github.com/NousResearch/hermes-agent/pull/26760), [#26729](https://github.com/NousResearch/hermes-agent/pull/26729), [#26765](https://github.com/NousResearch/hermes-agent/pull/26765), [#21881](https://github.com/NousResearch/hermes-agent/pull/21881), [#26612](https://github.com/NousResearch/hermes-agent/pull/26612))
+- **9 new optional skills** — Hyperliquid (perp/spot trading via SDK + REST) (@kshitijk4poor & Hermes), Yahoo Finance market data, api-testing (REST/GraphQL debug), unified EVM multi-chain skill (folds #25291 + #2010 + base/), darwinian-evolver, osint-investigation (closes #355), pinggy-tunnel, watchers (RSS/HTTP/GitHub via cron), Notion overhaul for the Developer Platform (May 2026). ([#23582](https://github.com/NousResearch/hermes-agent/pull/23582), [#23583](https://github.com/NousResearch/hermes-agent/pull/23583), [#23590](https://github.com/NousResearch/hermes-agent/pull/23590), [#25299](https://github.com/NousResearch/hermes-agent/pull/25299), [#26760](https://github.com/NousResearch/hermes-agent/pull/26760), [#26729](https://github.com/NousResearch/hermes-agent/pull/26729), [#26765](https://github.com/NousResearch/hermes-agent/pull/26765), [#21881](https://github.com/NousResearch/hermes-agent/pull/21881), [#26612](https://github.com/NousResearch/hermes-agent/pull/26612))
 
-- **API server exposes run approval events** — If you're driving Hermes programmatically through the HTTP API, long-running runs no longer silently hang when the agent hits an approval-required command. The approval request now surfaces on the API stream so your client can prompt the user and reply — no more silent stalls. (salvage of [#20311](https://github.com/NousResearch/hermes-agent/pull/20311)) ([#21899](https://github.com/NousResearch/hermes-agent/pull/21899))
+- **API server exposes run approval events** — long-running runs surface approval requests over the API stream, no more silent stalls. (salvage of [#20311](https://github.com/NousResearch/hermes-agent/pull/20311)) ([#21899](https://github.com/NousResearch/hermes-agent/pull/21899))
 
-- **Plugins can run any LLM call via `ctx.llm` + replace built-in tools via `tool_override`** — If you're writing a Hermes plugin, you now get first-class access to make LLM calls through the active provider and credentials — no manual client wiring. The new `tool_override` flag lets a plugin swap out a built-in tool with its own implementation cleanly. Plugin authors get the same model-routing and auth plumbing the core agent uses. (closes #11049) ([#23194](https://github.com/NousResearch/hermes-agent/pull/23194), [#26759](https://github.com/NousResearch/hermes-agent/pull/26759))
+- **`/subgoal` — user-added criteria appended to active `/goal`** — layer extra success criteria onto a running goal loop. The judge sees them in the prompt, no behavior change when subgoals are empty. ([#25449](https://github.com/NousResearch/hermes-agent/pull/25449))
 
-- **Brave Search (free tier) + DuckDuckGo (DDGS) as web-search providers** — Two new free web-search backends join Tavily, SearXNG, and Exa. Brave Search has a generous free tier; DDGS is the DuckDuckGo scraper that needs no key at all. Pick whichever fits your budget and rate-limit needs. ([#21337](https://github.com/NousResearch/hermes-agent/pull/21337))
+- **Plugins can run any LLM call via `ctx.llm`** — plugins get a first-class hook to make their own LLM requests through the active provider/credentials, no manual wiring. Plus `tool_override` flag for replacing built-in tools. ([#23194](https://github.com/NousResearch/hermes-agent/pull/23194), [#26759](https://github.com/NousResearch/hermes-agent/pull/26759))
 
-- **Sudo brute-force block + 3 dangerous-command bypasses closed + tool-error sanitization** — The approval gate now blocks `sudo -S` brute-force attempts and classifies stdin-fed or askpass-stripped sudo invocations as DANGEROUS. Three known bypasses of dangerous-command detection are closed (inspired by Claude Code's command-detection work). And tool error strings are now sanitized before being re-injected into the model context, so a malicious file or remote service can't pass instructions to your agent through error output. ([#23736](https://github.com/NousResearch/hermes-agent/pull/23736), [#26829](https://github.com/NousResearch/hermes-agent/pull/26829), [#26823](https://github.com/NousResearch/hermes-agent/pull/26823))
+- **Brave Search (free tier) + DuckDuckGo (DDGS) as web-search providers** — two new free search backends alongside Tavily / SearXNG / Exa. ([#21337](https://github.com/NousResearch/hermes-agent/pull/21337))
 
-- **`/subgoal` — user-added criteria appended to an active `/goal`** — When you've got a `/goal` running (the persistent Ralph-loop goal where the agent keeps going until criteria are met), you can now use `/subgoal <text>` to layer extra success criteria onto it mid-run. The judge factors your new criteria into the done-or-keep-going decision without restarting the loop. ([#25449](https://github.com/NousResearch/hermes-agent/pull/25449))
+- **Sudo brute-force block + sudo-stdin/askpass DANGEROUS classification** — closes the `sudo -S` brute-force avenue; approval gates classify stdin-fed and askpass-stripped sudo invocations as dangerous. (salvages of #22194 + #21128) ([#23736](https://github.com/NousResearch/hermes-agent/pull/23736))
 
-- **Provider rename — Alibaba Cloud → Qwen Cloud** — The Alibaba Cloud provider is renamed to Qwen Cloud in the picker and config to match what the rest of the world calls it. Existing config keys still work — no breaking changes — but the UI matches the actual brand now. ([#24835](https://github.com/NousResearch/hermes-agent/pull/24835))
-
-- **Native Windows support (early beta)** — Hermes now runs natively on `cmd.exe` and PowerShell without WSL. A full PowerShell installer handles MinGit auto-install, Microsoft Store python stub detection, and the foreground Ctrl+C dance. There's still rough edges (this is the "early beta" stamp) — ~40 follow-up Windows-only fixes already landed in the window — but the basic loop works end-to-end on a clean Windows box. ([#21561](https://github.com/NousResearch/hermes-agent/pull/21561))
+- **Provider rename — Alibaba Cloud → Qwen Cloud, picker reorder** — matches what the world calls it. Existing config keys still work. ([#24835](https://github.com/NousResearch/hermes-agent/pull/24835))
 
 
 ---

agent/anthropic_adapter.py

@@ -1783,11 +1783,25 @@ def _strip_orphaned_tool_blocks(result: List[Dict[str, Any]]) -> None:
                     tool_result_ids.add(block.get("tool_use_id"))
     for m in result:
         if m["role"] == "assistant" and isinstance(m["content"], list):
-            m["content"] = [
+            kept = [
                 b
                 for b in m["content"]
                 if b.get("type") != "tool_use" or b.get("id") in tool_result_ids
             ]
+            # If stripping an orphaned tool_use mutated a turn that also carries a
+            # signed thinking block, that block's Anthropic signature was computed
+            # against the ORIGINAL (un-stripped) turn content and is now invalid.
+            # Anthropic rejects the replayed turn with HTTP 400 "thinking blocks in
+            # the latest assistant message cannot be modified".  Flag the turn so
+            # _manage_thinking_signatures can demote the dead signature instead of
+            # replaying it verbatim.  See hermes-agent: extended-thinking + parallel
+            # tool batch interrupted mid-flight → non-retryable 400 crash-loop.
+            if len(kept) != len(m["content"]) and any(
+                isinstance(b, dict) and b.get("type") in {"thinking", "redacted_thinking"}
+                for b in m["content"]
+            ):
+                m["_thinking_signature_invalidated"] = True
+            m["content"] = kept
             if not m["content"]:
                 m["content"] = [{"type": "text", "text": "(tool call removed)"}]
 
@@ -1832,6 +1846,10 @@ def _merge_consecutive_roles(result: List[Dict[str, Any]]) -> List[Dict[str, Any
                     fixed[-1]["content"] = prev_content + curr_content
             else:
                 # Consecutive assistant messages — merge text content.
+                # Propagate the orphan-strip signature-invalidation flag onto the
+                # surviving (prev) dict so _manage_thinking_signatures still sees it.
+                if m.get("_thinking_signature_invalidated"):
+                    fixed[-1]["_thinking_signature_invalidated"] = True
                 # Drop thinking blocks from the *second* message: their
                 # signature was computed against a different turn boundary
                 # and becomes invalid once merged.
@@ -1920,11 +1938,26 @@ def _manage_thinking_signatures(
         else:
             # Latest assistant on direct Anthropic: keep signed, downgrade unsigned
             # to text so the reasoning isn't lost.
+            #
+            # Exception: if orphan-stripping (or another structural mutation) removed
+            # a tool_use block from THIS turn, every thinking signature on it was
+            # computed against the original turn content and is now dead.  Anthropic
+            # rejects the turn either way — replaying the signed block 400s with
+            # "thinking blocks in the latest assistant message cannot be modified",
+            # and a bare signed block with no following tool_use is also invalid.
+            # Demote ALL thinking blocks on this turn to text so the turn replays
+            # cleanly and the model can re-plan from the surviving tool results.
+            signature_dead = bool(m.get("_thinking_signature_invalidated"))
             new_content = []
             for b in m["content"]:
                 if not isinstance(b, dict) or b.get("type") not in _THINKING_TYPES:
                     new_content.append(b)
                     continue
+                if signature_dead:
+                    thinking_text = b.get("thinking", "")
+                    if thinking_text:
+                        new_content.append({"type": "text", "text": thinking_text})
+                    continue
                 if b.get("type") == "redacted_thinking":
                     # Redacted blocks use 'data' for the signature payload —
                     # drop the block when 'data' is missing (can't be validated).
@@ -1944,6 +1977,9 @@ def _manage_thinking_signatures(
             if isinstance(b, dict) and b.get("type") in _THINKING_TYPES:
                 b.pop("cache_control", None)
 
+        # Drop the internal bookkeeping flag — it must never reach the API payload.
+        m.pop("_thinking_signature_invalidated", None)
+
 
 def _evict_old_screenshots(result: List[Dict[str, Any]]) -> None:
     """Keep only the most recent ``_MAX_KEEP_IMAGES`` computer-use screenshots.

agent/auxiliary_client.py

@@ -1680,26 +1680,48 @@ def _read_main_provider() -> str:
 # per turn — no lock needed. Cleared by ``clear_runtime_main()``.
 _RUNTIME_MAIN_PROVIDER: str = ""
 _RUNTIME_MAIN_MODEL: str = ""
+_RUNTIME_MAIN_BASE_URL: str = ""
+_RUNTIME_MAIN_API_KEY: str = ""
+_RUNTIME_MAIN_API_MODE: str = ""
 
 
-def set_runtime_main(provider: str, model: str) -> None:
-    """Record the live runtime provider/model for the current AIAgent.
+def set_runtime_main(
+    provider: str,
+    model: str,
+    *,
+    base_url: str = "",
+    api_key: str = "",
+    api_mode: str = "",
+) -> None:
+    """Record the live runtime provider/model/credentials for the current AIAgent.
 
     Called by ``run_agent.AIAgent._sync_runtime_main_for_aux_routing`` (or
     equivalent setter) at the top of each turn so that
     ``_read_main_provider`` / ``_read_main_model`` reflect CLI/gateway
     overrides instead of the stale config.yaml default.
+
+    For ``custom:`` providers, ``base_url`` and ``api_key`` must also be
+    recorded so that ``_resolve_auto`` can construct a valid client in
+    Step 1 instead of falling through to the aggregator chain.
     """
     global _RUNTIME_MAIN_PROVIDER, _RUNTIME_MAIN_MODEL
+    global _RUNTIME_MAIN_BASE_URL, _RUNTIME_MAIN_API_KEY, _RUNTIME_MAIN_API_MODE
     _RUNTIME_MAIN_PROVIDER = (provider or "").strip().lower()
     _RUNTIME_MAIN_MODEL = (model or "").strip()
+    _RUNTIME_MAIN_BASE_URL = (base_url or "").strip()
+    _RUNTIME_MAIN_API_KEY = api_key.strip() if isinstance(api_key, str) else ""
+    _RUNTIME_MAIN_API_MODE = (api_mode or "").strip()
 
 
 def clear_runtime_main() -> None:
     """Clear the runtime override (e.g. on session end)."""
     global _RUNTIME_MAIN_PROVIDER, _RUNTIME_MAIN_MODEL
+    global _RUNTIME_MAIN_BASE_URL, _RUNTIME_MAIN_API_KEY, _RUNTIME_MAIN_API_MODE
     _RUNTIME_MAIN_PROVIDER = ""
     _RUNTIME_MAIN_MODEL = ""
+    _RUNTIME_MAIN_BASE_URL = ""
+    _RUNTIME_MAIN_API_KEY = ""
+    _RUNTIME_MAIN_API_MODE = ""
 
 
 def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str], Optional[str]]:
@@ -2980,6 +3002,18 @@ def _resolve_auto(main_runtime: Optional[Dict[str, Any]] = None) -> Tuple[Option
     runtime_api_key = runtime.get("api_key", "")
     runtime_api_mode = str(runtime.get("api_mode") or "")
 
+    # Fall back to process-local globals when main_runtime dict was not
+    # provided or was incomplete.  ``set_runtime_main()`` now records
+    # base_url/api_key/api_mode alongside provider/model, so custom:
+    # providers get the full credential surface in Step 1 of the
+    # auto-detect chain.
+    if not runtime_base_url and _RUNTIME_MAIN_BASE_URL:
+        runtime_base_url = _RUNTIME_MAIN_BASE_URL
+    if not runtime_api_key and _RUNTIME_MAIN_API_KEY:
+        runtime_api_key = _RUNTIME_MAIN_API_KEY
+    if not runtime_api_mode and _RUNTIME_MAIN_API_MODE:
+        runtime_api_mode = _RUNTIME_MAIN_API_MODE
+
     # ── Warn once if OPENAI_BASE_URL is set but config.yaml uses a named
     #    provider (not 'custom').  This catches the common "env poisoning"
     #    scenario where a user switches providers via `hermes model` but the
@@ -4725,24 +4759,23 @@ def _build_call_kwargs(
         kwargs["temperature"] = temperature
 
     if max_tokens is not None:
-        # Codex adapter handles max_tokens internally; OpenRouter/Nous use max_tokens.
-        # Direct OpenAI api.openai.com with newer models needs max_completion_tokens.
-        # ZAI vision models (glm-4v-flash, glm-4v-plus, etc.) reject max_tokens with
-        # error code 1210 ("API 调用参数有误") on multimodal requests — skip it.
-        _model_lower = (model or "").lower()
-        _skip_max_tokens = (
-            provider == "zai"
-            and ("4v" in _model_lower or "5v" in _model_lower or "-v" in _model_lower)
+        # We do NOT cap output by default. Most chat-completions providers treat
+        # an omitted max_tokens as "use the model's max output", which is what we
+        # want for auxiliary tasks (compression summaries, titles, vision, etc.) —
+        # an explicit cap only risks truncating a summary or 400-ing on providers
+        # that reject the parameter outright (e.g. GitHub Copilot / newer OpenAI
+        # GPT-5 models require max_completion_tokens, not max_tokens; ZAI vision
+        # models reject it entirely with error 1210). Omitting it sidesteps all of
+        # those wire-format quirks at once.
+        #
+        # The one exception is the Anthropic Messages wire (MiniMax and any
+        # ``/anthropic`` endpoint reached through the OpenAI SDK wrapper), where
+        # max_tokens is a MANDATORY field — omitting it is a hard 400. Keep it only
+        # there.
+        _effective_base = base_url or (
+            _current_custom_base_url() if provider == "custom" else ""
         )
-        if _skip_max_tokens:
-            pass  # ZAI vision models do not accept max_tokens
-        elif provider == "custom":
-            custom_base = base_url or _current_custom_base_url()
-            if base_url_hostname(custom_base) == "api.openai.com":
-                kwargs["max_completion_tokens"] = max_tokens
-            else:
-                kwargs["max_tokens"] = max_tokens
-        else:
+        if _is_anthropic_compat_endpoint(provider, _effective_base):
             kwargs["max_tokens"] = max_tokens
 
     if tools:

agent/chat_completion_helpers.py

@@ -1283,6 +1283,18 @@ def handle_max_iterations(agent, messages: list, api_call_count: int) -> str:
             agent._copy_reasoning_content_for_api(msg, api_msg)
             for internal_field in ("reasoning", "finish_reason", "_thinking_prefill"):
                 api_msg.pop(internal_field, None)
+            # Strict OpenAI-compatible gateways (Fireworks-backed OpenCode Go,
+            # Mistral, Moonshot/Kimi) reject any message key outside the Chat
+            # Completions schema. The main loop drops these via
+            # ChatCompletionsTransport.convert_messages(), but the summary path
+            # hand-builds messages and calls chat.completions.create() directly,
+            # bypassing the transport — so mirror that sanitization here:
+            # tool_name (SQLite FTS bookkeeping), the codex_* reasoning carriers,
+            # and every Hermes-internal underscore-prefixed scaffolding key.
+            for schema_foreign in ("tool_name", "codex_reasoning_items", "codex_message_items"):
+                api_msg.pop(schema_foreign, None)
+            for internal_key in [k for k in api_msg if isinstance(k, str) and k.startswith("_")]:
+                api_msg.pop(internal_key, None)
             if _needs_sanitize:
                 agent._sanitize_tool_calls_for_strict_api(api_msg)
             api_messages.append(api_msg)

agent/context_compressor.py

@@ -40,17 +40,47 @@ SUMMARY_PREFIX = (
     "window — treat it as background reference, NOT as active instructions. "
     "Do NOT answer questions or fulfill requests mentioned in this summary; "
     "they were already addressed. "
-    "Your current task is identified in the '## Active Task' section of the "
-    "summary — resume exactly from there. "
+    "Respond ONLY to the latest user message that appears AFTER this "
+    "summary — that message is the single source of truth for what to do "
+    "right now. "
+    "If the latest user message is consistent with the '## Active Task' "
+    "section, you may use the summary as background. If the latest user "
+    "message contradicts, supersedes, changes topic from, or in any way "
+    "diverges from '## Active Task' / '## In Progress' / '## Pending User "
+    "Asks' / '## Remaining Work', the latest message WINS — discard those "
+    "stale items entirely and do not 'wrap up the old task first'. "
+    "Reverse signals in the latest message (e.g. 'stop', 'undo', 'roll "
+    "back', 'just verify', 'don't do that anymore', 'never mind', a new "
+    "topic) must immediately end any in-flight work described in the "
+    "summary; do not re-surface it in later turns. "
     "IMPORTANT: Your persistent memory (MEMORY.md, USER.md) in the system "
     "prompt is ALWAYS authoritative and active — never ignore or deprioritize "
     "memory content due to this compaction note. "
-    "Respond ONLY to the latest user message "
-    "that appears AFTER this summary. The current session state (files, "
-    "config, etc.) may reflect work described here — avoid repeating it:"
+    "The current session state (files, config, etc.) may reflect work "
+    "described here — avoid repeating it:"
 )
 LEGACY_SUMMARY_PREFIX = "[CONTEXT SUMMARY]:"
 
+# Handoff prefixes that shipped in earlier releases. A summary persisted under
+# one of these can be inherited into a resumed lineage (#35344); when it is
+# re-normalized on re-compaction we must strip the OLD prefix too, otherwise the
+# stale directive it carried (e.g. "resume exactly from Active Task") survives
+# embedded in the body and keeps hijacking replies. Keep newest-first; entries
+# are matched literally. Add a frozen copy here whenever SUMMARY_PREFIX changes.
+_HISTORICAL_SUMMARY_PREFIXES = (
+    # Pre-#35344: contained the self-contradicting "resume exactly" directive.
+    "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted "
+    "into the summary below. This is a handoff from a previous context "
+    "window — treat it as background reference, NOT as active instructions. "
+    "Do NOT answer questions or fulfill requests mentioned in this summary; "
+    "they were already addressed. "
+    "Your current task is identified in the '## Active Task' section of the "
+    "summary — resume exactly from there. "
+    "Respond ONLY to the latest user message "
+    "that appears AFTER this summary. The current session state (files, "
+    "config, etc.) may reflect work described here — avoid repeating it:",
+)
+
 # Minimum tokens for the summary output
 _MIN_SUMMARY_TOKENS = 2000
 # Proportion of compressed content to allocate for summary
@@ -518,6 +548,10 @@ class ContextCompressor(ContextEngine):
         self._last_compression_savings_pct = 100.0
         self._ineffective_compression_count = 0
         self._summary_failure_cooldown_until = 0.0  # transient errors must not block a fresh session
+        self.last_real_prompt_tokens = 0
+        self.last_compression_rough_tokens = 0
+        self.last_rough_tokens_when_real_prompt_fit = 0
+        self.awaiting_real_usage_after_compression = False
 
     def update_model(
         self,
@@ -615,6 +649,10 @@ class ContextCompressor(ContextEngine):
 
         self.last_prompt_tokens = 0
         self.last_completion_tokens = 0
+        self.last_real_prompt_tokens = 0
+        self.last_compression_rough_tokens = 0
+        self.last_rough_tokens_when_real_prompt_fit = 0
+        self.awaiting_real_usage_after_compression = False
 
         self.summary_model = summary_model_override or ""
 
@@ -648,6 +686,44 @@ class ContextCompressor(ContextEngine):
         self.last_prompt_tokens = usage.get("prompt_tokens", 0)
         self.last_completion_tokens = usage.get("completion_tokens", 0)
         self.last_total_tokens = usage.get("total_tokens", self.last_prompt_tokens + self.last_completion_tokens)
+        if self.last_prompt_tokens > 0:
+            self.last_real_prompt_tokens = self.last_prompt_tokens
+            if self.last_prompt_tokens < self.threshold_tokens:
+                if self.awaiting_real_usage_after_compression and self.last_compression_rough_tokens > 0:
+                    self.last_rough_tokens_when_real_prompt_fit = self.last_compression_rough_tokens
+            else:
+                self.last_rough_tokens_when_real_prompt_fit = 0
+        self.awaiting_real_usage_after_compression = False
+
+    def should_defer_preflight_to_real_usage(self, rough_tokens: int) -> bool:
+        """Return True when a high rough preflight estimate is known-noisy.
+
+        ``estimate_request_tokens_rough(..., tools=...)`` intentionally
+        overestimates schema-heavy requests so Hermes compresses before a
+        provider rejects the payload. After a successful compressed API call,
+        though, provider ``prompt_tokens`` are a better signal than repeating
+        compaction from the same rough schema overhead. Defer only while the
+        rough estimate has grown modestly since a request the provider proved
+        fit under the threshold.
+        """
+        if rough_tokens < self.threshold_tokens:
+            return False
+        if self.last_real_prompt_tokens <= 0:
+            return False
+        if self.last_real_prompt_tokens >= self.threshold_tokens:
+            return False
+
+        baseline = self.last_rough_tokens_when_real_prompt_fit or self.last_compression_rough_tokens
+        if baseline <= 0:
+            return False
+
+        growth = max(0, rough_tokens - baseline)
+        tolerated_growth = max(4096, int(self.threshold_tokens * 0.05))
+        if growth > tolerated_growth:
+            return False
+
+        self.last_rough_tokens_when_real_prompt_fit = max(baseline, rough_tokens)
+        return True
 
     def should_compress(self, prompt_tokens: int = None) -> bool:
         """Check if context exceeds the compression threshold.
@@ -1190,11 +1266,27 @@ Summary generation was unavailable, so this is a best-effort deterministic fallb
 
         # Shared structured template (used by both paths).
         _template_sections = f"""## Active Task
-[THE SINGLE MOST IMPORTANT FIELD. Copy the user's most recent request or
-task assignment verbatim — the exact words they used. If multiple tasks
-were requested and only some are done, list only the ones NOT yet completed.
-Continuation should pick up exactly here. Example:
+[THE SINGLE MOST IMPORTANT FIELD. Capture the user's most recent unfulfilled
+input verbatim — the exact words they used. This includes:
+- Explicit task assignments ("refactor the auth module")
+- Questions awaiting an answer ("waarom staat X op Y?", "wat zijn de volgende stappen?")
+- Decisions awaiting input ("optie A of B?")
+- Ongoing discussions where the assistant owes the next substantive reply
+A conversation where the user just asked a question IS an active task — the
+task is "answer that question with full context". Do NOT write "None" merely
+because the user did not issue an imperative command; reserve "None" for the
+rare case where the last exchange was fully resolved and the user said
+something like "thanks, that's all".
+If multiple items are outstanding, list only the ones NOT yet completed.
+Continuation should pick up exactly here. Examples:
 "User asked: 'Now refactor the auth module to use JWT instead of sessions'"
+"User asked: 'Waarom stond provider ineens op openrouter?' — needs investigation + answer"
+"User chose option A; awaiting implementation of step 2"
+If the user's most recent message was a reverse signal (stop, undo, roll
+back, never mind, just verify, change of topic) that supersedes earlier
+work, write the reverse signal verbatim and DO NOT carry forward the
+cancelled task. Example: "User asked: 'Stop the i18n refactor and just
+verify the current diff' — earlier i18n in-flight work is cancelled."
 If no outstanding task exists, write "None."]
 
 ## Goal
@@ -1260,7 +1352,7 @@ PREVIOUS SUMMARY:
 NEW TURNS TO INCORPORATE:
 {content_to_summarize}
 
-Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new completed actions to the numbered list (continue numbering). Move items from "In Progress" to "Completed Actions" when done. Move answered questions to "Resolved Questions". Update "Active State" to reflect current state. Remove information only if it is clearly obsolete. CRITICAL: Update "## Active Task" to reflect the user's most recent unfulfilled request — this is the most important field for task continuity.
+Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new completed actions to the numbered list (continue numbering). Move items from "In Progress" to "Completed Actions" when done. Move answered questions to "Resolved Questions". Update "Active State" to reflect current state. Remove information only if it is clearly obsolete. CRITICAL: Update "## Active Task" to reflect the user's most recent unfulfilled input — this includes any question, decision request, or discussion turn that the assistant has not yet answered. Only write "None" if the last exchange was fully resolved.
 
 {_template_sections}"""
         else:
@@ -1424,9 +1516,16 @@ The user has requested that this compaction PRIORITISE preserving all informatio
 
     @staticmethod
     def _strip_summary_prefix(summary: str) -> str:
-        """Return summary body without the current or legacy handoff prefix."""
+        """Return summary body without the current, legacy, or any historical
+        handoff prefix.
+
+        Historical prefixes must be stripped too: a handoff persisted under an
+        older prefix can be inherited into a resumed lineage (#35344), and if we
+        only re-prepend the current prefix without removing the old one, the
+        stale directive it carried stays embedded in the body.
+        """
         text = (summary or "").strip()
-        for prefix in (SUMMARY_PREFIX, LEGACY_SUMMARY_PREFIX):
+        for prefix in (SUMMARY_PREFIX, LEGACY_SUMMARY_PREFIX, *_HISTORICAL_SUMMARY_PREFIXES):
             if text.startswith(prefix):
                 return text[len(prefix):].lstrip()
         return text
@@ -1440,7 +1539,9 @@ The user has requested that this compaction PRIORITISE preserving all informatio
     @staticmethod
     def _is_context_summary_content(content: Any) -> bool:
         text = _content_text_for_contains(content).lstrip()
-        return text.startswith(SUMMARY_PREFIX) or text.startswith(LEGACY_SUMMARY_PREFIX)
+        if text.startswith(SUMMARY_PREFIX) or text.startswith(LEGACY_SUMMARY_PREFIX):
+            return True
+        return any(text.startswith(p) for p in _HISTORICAL_SUMMARY_PREFIXES)
 
     @classmethod
     def _find_latest_context_summary(

agent/context_engine.py

@@ -115,6 +115,15 @@ class ContextEngine(ABC):
         """
         return False
 
+    def should_defer_preflight_to_real_usage(self, rough_tokens: int) -> bool:
+        """Return True when preflight should trust recent real usage instead.
+
+        Built-in compression uses this to avoid re-compacting from known-noisy
+        rough estimates after a compressed request has already fit. Third-party
+        engines can ignore it safely.
+        """
+        return False
+
     # -- Optional: manual /compress preflight ------------------------------
 
     def has_content_to_compress(self, messages: List[Dict[str, Any]]) -> bool:

agent/conversation_compression.py

@@ -308,11 +308,14 @@ def compress_context(
     # The check itself sets ``agent._compression_warning`` so the
     # status-callback replay machinery still emits the warning to the user
     # the first time it would matter.
-    if not getattr(agent, "_compression_feasibility_checked", True):
-        try:
-            check_compression_model_feasibility(agent)
-        finally:
-            agent._compression_feasibility_checked = True
+    if not getattr(agent, "_compression_feasibility_checked", False):
+        # Mark as checked only after the probe completes. If the check
+        # raises (e.g. a fatal aux-context ValueError that aborts the
+        # session), leaving the flag unset is harmless; a non-fatal
+        # transient failure is swallowed inside the function so the flag
+        # is set normally on the next successful pass.
+        check_compression_model_feasibility(agent)
+        agent._compression_feasibility_checked = True
 
     _pre_msg_count = len(messages)
     logger.info(
@@ -575,19 +578,18 @@ def compress_context(
             force=True,
         )
 
-    # Update token estimate after compaction so pressure calculations
-    # use the post-compression count, not the stale pre-compression one.
-    # Use estimate_request_tokens_rough() so tool schemas are included —
-    # with 50+ tools enabled, schemas alone can add 20-30K tokens, and
-    # omitting them delays the next compression cycle far past the
-    # configured threshold (issue #14695).
+    # Keep the post-compression rough estimate for diagnostics, but do not
+    # treat it as provider-reported prompt usage. Schema-heavy rough estimates
+    # can remain above threshold even after the next real API request fits.
     _compressed_est = estimate_request_tokens_rough(
         compressed,
         system_prompt=new_system_prompt or "",
         tools=agent.tools or None,
     )
-    agent.context_compressor.last_prompt_tokens = _compressed_est
+    agent.context_compressor.last_compression_rough_tokens = _compressed_est
+    agent.context_compressor.last_prompt_tokens = -1
     agent.context_compressor.last_completion_tokens = 0
+    agent.context_compressor.awaiting_real_usage_after_compression = True
 
     # Clear the file-read dedup cache.  After compression the original
     # read content is summarised away — if the model re-reads the same
@@ -599,7 +601,7 @@ def compress_context(
         pass
 
     logger.info(
-        "context compression done: session=%s messages=%d->%d tokens=~%s",
+        "context compression done: session=%s messages=%d->%d rough_tokens=~%s awaiting_real_usage=true",
         agent.session_id or "none", _pre_msg_count, len(compressed),
         f"{_compressed_est:,}",
     )
@@ -645,6 +647,12 @@ def try_shrink_image_parts_in_messages(api_messages: list) -> bool:
     # after a confirmed provider rejection, so the alternative is failure.
     target_bytes = 4 * 1024 * 1024
     changed_count = 0
+    # Track parts that are over the target but could NOT be shrunk under it.
+    # If any survive, retrying is pointless — the same oversized payload will
+    # be re-sent and rejected again, wasting the single retry budget.  We only
+    # report success (caller retries) when every over-threshold image was
+    # actually brought under the target.
+    unshrinkable_oversized = 0
 
     def _shrink_data_url(url: str) -> Optional[str]:
         """Return a smaller data URL, or None if shrink can't help."""
@@ -711,17 +719,34 @@ def try_shrink_image_parts_in_messages(api_messages: list) -> bool:
                 if resized:
                     image_value["url"] = resized
                     changed_count += 1
+                elif isinstance(url, str) and url.startswith("data:") \
+                        and len(url) > target_bytes:
+                    unshrinkable_oversized += 1
             elif isinstance(image_value, str):
                 resized = _shrink_data_url(image_value)
                 if resized:
                     part["image_url"] = resized
                     changed_count += 1
+                elif image_value.startswith("data:") \
+                        and len(image_value) > target_bytes:
+                    unshrinkable_oversized += 1
 
     if changed_count:
         logger.info(
             "image-shrink recovery: re-encoded %d image part(s) to fit under %.0f MB",
             changed_count, target_bytes / (1024 * 1024),
         )
+    if unshrinkable_oversized:
+        # At least one oversized image could not be shrunk under the target.
+        # Retrying would re-send it and fail identically, so signal "no
+        # progress" even if other parts shrank — the caller will surface the
+        # original error rather than burning its single retry on a no-op.
+        logger.warning(
+            "image-shrink recovery: %d oversized image part(s) could not be "
+            "shrunk under %.0f MB — not retrying (would re-send rejected payload)",
+            unshrinkable_oversized, target_bytes / (1024 * 1024),
+        )
+        return False
     return changed_count > 0
 
 

agent/conversation_loop.py

@@ -392,6 +392,9 @@ def run_conversation(
         set_runtime_main(
             getattr(agent, "provider", "") or "",
             getattr(agent, "model", "") or "",
+            base_url=getattr(agent, "base_url", "") or "",
+            api_key=getattr(agent, "api_key", "") or "",
+            api_mode=getattr(agent, "api_mode", "") or "",
         )
     except Exception:
         pass
@@ -600,18 +603,50 @@ def run_conversation(
             system_prompt=active_system_prompt or "",
             tools=agent.tools or None,
         )
+        _compressor = agent.context_compressor
+        _defer_preflight = getattr(
+            _compressor,
+            "should_defer_preflight_to_real_usage",
+            lambda _tokens: False,
+        )
+        _preflight_deferred = _defer_preflight(_preflight_tokens)
 
-        if agent.context_compressor.should_compress(_preflight_tokens):
+        if not _preflight_deferred:
+            # Keep the CLI/ACP context display in sync with what preflight
+            # actually measured.  The status bar reads
+            # ``compressor.last_prompt_tokens``, which otherwise only updates
+            # from a *successful* API response.  When the conversation has grown
+            # since the last successful call — or when compression then fails
+            # (e.g. the auxiliary summary model times out) and no fresh usage
+            # arrives — the bar stays stuck at the old, smaller value while
+            # preflight reports a much larger number, looking out of sync.
+            # Seed it with the fresh estimate (only ever revising upward; a real
+            # ``update_from_response`` will correct it after the next API call).
+            # Skipped when deferring — a deferred estimate is known to over-count
+            # vs the last real provider prompt, so trusting it for the display
+            # would re-introduce the very desync we're avoiding.
+            if _preflight_tokens > (_compressor.last_prompt_tokens or 0):
+                _compressor.last_prompt_tokens = _preflight_tokens
+
+        if _preflight_deferred:
+            logger.info(
+                "Skipping preflight compression: rough estimate ~%s >= %s, "
+                "but last real provider prompt was %s after compression",
+                f"{_preflight_tokens:,}",
+                f"{_compressor.threshold_tokens:,}",
+                f"{_compressor.last_real_prompt_tokens:,}",
+            )
+        elif _compressor.should_compress(_preflight_tokens):
             logger.info(
                 "Preflight compression: ~%s tokens >= %s threshold (model %s, ctx %s)",
                 f"{_preflight_tokens:,}",
-                f"{agent.context_compressor.threshold_tokens:,}",
+                f"{_compressor.threshold_tokens:,}",
                 agent.model,
-                f"{agent.context_compressor.context_length:,}",
+                f"{_compressor.context_length:,}",
             )
             agent._emit_status(
                 f"📦 Preflight compression: ~{_preflight_tokens:,} tokens "
-                f">= {agent.context_compressor.threshold_tokens:,} threshold. "
+                f">= {_compressor.threshold_tokens:,} threshold. "
                 "This may take a moment."
             )
             # May need multiple passes for very large sessions with small
@@ -646,8 +681,8 @@ def run_conversation(
                     system_prompt=active_system_prompt or "",
                     tools=agent.tools or None,
                 )
-                if _preflight_tokens < agent.context_compressor.threshold_tokens:
-                    break  # Under threshold
+                if not _compressor.should_compress(_preflight_tokens):
+                    break  # Under threshold or anti-thrash guard stopped it
 
     # Plugin hook: pre_llm_call
     # Fired once per turn before the tool-calling loop.  Plugins can
@@ -1457,7 +1492,8 @@ def run_conversation(
                     
                     if retry_count >= max_retries:
                         # Try fallback before giving up
-                        agent._buffer_status(f"⚠️ Max retries ({max_retries}) for invalid responses — trying fallback...")
+                        if agent._has_pending_fallback():
+                            agent._buffer_status(f"⚠️ Max retries ({max_retries}) for invalid responses — trying fallback...")
                         if agent._try_activate_fallback():
                             retry_count = 0
                             compression_attempts = 0
@@ -1703,20 +1739,52 @@ def run_conversation(
                     if agent.api_mode in {"chat_completions", "bedrock_converse", "anthropic_messages"}:
                         assistant_message = _trunc_msg
                         if assistant_message is not None and _trunc_has_tool_calls:
-                            if truncated_tool_call_retries < 1:
+                            _is_stub_stall = (
+                                getattr(response, "id", "") == PARTIAL_STREAM_STUB_ID
+                            )
+                            if truncated_tool_call_retries < 3:
                                 truncated_tool_call_retries += 1
-                                agent._buffer_vprint(
-                                    f"⚠️  Truncated tool call detected — retrying API call..."
-                                )
+                                if _is_stub_stall:
+                                    # The stream broke mid tool-call (network /
+                                    # peer-closed connection), not a real output
+                                    # cap — say so instead of "max output tokens".
+                                    agent._buffer_vprint(
+                                        f"⚠️  Stream interrupted mid tool-call — "
+                                        f"retrying ({truncated_tool_call_retries}/3)..."
+                                    )
+                                else:
+                                    agent._buffer_vprint(
+                                        f"⚠️  Truncated tool call detected — "
+                                        f"retrying API call "
+                                        f"({truncated_tool_call_retries}/3)..."
+                                    )
+                                # Boost max_tokens on each retry so the model has
+                                # more room to complete the tool-call JSON. A
+                                # network stall doesn't need a bigger budget, but
+                                # a genuine output-cap truncation does, and the
+                                # boost is harmless for the stall case.
+                                _tc_boost_base = agent.max_tokens if agent.max_tokens else 4096
+                                _tc_boost = _tc_boost_base * (truncated_tool_call_retries + 1)
+                                _tc_requested_cap = agent._requested_output_cap_from_api_kwargs(api_kwargs)
+                                if _tc_requested_cap is not None:
+                                    _tc_boost = max(_tc_boost, _tc_requested_cap)
+                                _tc_boost_cap = max(32768, _tc_requested_cap or 0)
+                                agent._ephemeral_max_output_tokens = min(_tc_boost, _tc_boost_cap)
                                 # Don't append the broken response to messages;
                                 # just re-run the same API call from the current
                                 # message state, giving the model another chance.
                                 continue
                             agent._flush_status_buffer()
-                            agent._vprint(
-                                f"{agent.log_prefix}⚠️  Truncated tool call response detected again — refusing to execute incomplete tool arguments.",
-                                force=True,
-                            )
+                            if _is_stub_stall:
+                                agent._vprint(
+                                    f"{agent.log_prefix}⚠️  Stream kept dropping mid tool-call after 3 retries — the action was not executed.",
+                                    force=True,
+                                )
+                            else:
+                                agent._vprint(
+                                    f"{agent.log_prefix}⚠️  Truncated tool call response detected again — refusing to execute incomplete tool arguments.",
+                                    force=True,
+                                )
                             agent._cleanup_task_resources(effective_task_id)
                             agent._persist_session(messages, conversation_history)
                             return {
@@ -1725,7 +1793,12 @@ def run_conversation(
                                 "api_calls": api_call_count,
                                 "completed": False,
                                 "partial": True,
-                                "error": "Response truncated due to output length limit",
+                                "error": (
+                                    "Stream repeatedly dropped mid tool-call (network); "
+                                    "the tool was not executed"
+                                    if _is_stub_stall
+                                    else "Response truncated due to output length limit"
+                                ),
                             }
 
                     # If we have prior messages, roll back to last complete state
@@ -3059,12 +3132,17 @@ def run_conversation(
                 ) and not is_context_length_error
 
                 if is_client_error:
-                    # Try fallback before aborting — a different provider
-                    # may not have the same issue (rate limit, auth, etc.)
-                    if classified.reason == FailoverReason.content_policy_blocked:
-                        agent._buffer_status("⚠️ Provider safety filter blocked this request — trying fallback...")
-                    else:
-                        agent._buffer_status(f"⚠️ Non-retryable error (HTTP {status_code}) — trying fallback...")
+                    # Try fallback before aborting — a different provider may
+                    # not have the same issue (rate limit, auth, etc.). Only
+                    # announce the attempt when a fallback chain actually
+                    # exists; otherwise "trying fallback..." is a lie and the
+                    # session looks like it's recovering when it's about to
+                    # abort silently (#35314, #17446).
+                    if agent._has_pending_fallback():
+                        if classified.reason == FailoverReason.content_policy_blocked:
+                            agent._buffer_status("⚠️ Provider safety filter blocked this request — trying fallback...")
+                        else:
+                            agent._buffer_status(f"⚠️ Non-retryable error (HTTP {status_code}) — trying fallback...")
                     if agent._try_activate_fallback():
                         retry_count = 0
                         compression_attempts = 0
@@ -3207,7 +3285,8 @@ def run_conversation(
                         retry_count = 0
                         continue
                     # Try fallback before giving up entirely
-                    agent._buffer_status(f"⚠️ Max retries ({max_retries}) exhausted — trying fallback...")
+                    if agent._has_pending_fallback():
+                        agent._buffer_status(f"⚠️ Max retries ({max_retries}) exhausted — trying fallback...")
                     if agent._try_activate_fallback():
                         retry_count = 0
                         compression_attempts = 0
@@ -3370,9 +3449,16 @@ def run_conversation(
             # Progressively boost the output token budget on each retry.
             # Retry 1 → 2× base, retry 2 → 3× base, capped at 32 768.
             # Applies to all providers via _ephemeral_max_output_tokens.
+            # If the original request already used a larger provider/model
+            # default budget, keep that floor so continuation retries do
+            # not accidentally downshift to a much smaller cap.
             _boost_base = agent.max_tokens if agent.max_tokens else 4096
             _boost = _boost_base * (length_continue_retries + 1)
-            agent._ephemeral_max_output_tokens = min(_boost, 32768)
+            _requested_cap = agent._requested_output_cap_from_api_kwargs(api_kwargs)
+            if _requested_cap is not None:
+                _boost = max(_boost, _requested_cap)
+            _boost_cap = max(32768, _requested_cap or 0)
+            agent._ephemeral_max_output_tokens = min(_boost, _boost_cap)
             continue
 
         # Guard: if all retries exhausted without a successful response
@@ -3862,6 +3948,11 @@ def run_conversation(
                     # inflate completion_tokens with reasoning,
                     # causing premature compression.  (#12026)
                     _real_tokens = _compressor.last_prompt_tokens
+                elif _compressor.last_prompt_tokens == -1:
+                    # Compression just ran and no API-reported prompt count
+                    # has arrived yet. Avoid treating a schema-heavy rough
+                    # post-compression estimate as real context pressure.
+                    _real_tokens = 0
                 else:
                     # Include tool schemas — with 50+ tools enabled
                     # these add 20-30K tokens the messages-only
@@ -4443,6 +4534,55 @@ def run_conversation(
         except Exception as _ver_err:
             logger.debug("file-mutation verifier footer failed: %s", _ver_err)
 
+    # Turn-completion explainer.
+    # When a turn ends abnormally after substantive work — empty content
+    # after retries, a partial/truncated stream, a still-pending tool
+    # result, or an iteration/budget limit — the user otherwise gets a
+    # blank or fragmentary response box with no consolidated reason why
+    # the agent stopped (#34452).  Surface a single user-visible
+    # explanation derived from ``_turn_exit_reason``, mirroring the
+    # file-mutation verifier footer pattern above.
+    #
+    # Gate carefully so healthy turns stay quiet:
+    #   - ``text_response(...)`` exits never produce an explanation
+    #     (handled inside the formatter), so a terse ``Done.`` is silent.
+    #   - We only ACT when there is no genuinely usable reply this turn:
+    #     an empty response, the "(empty)" terminal sentinel, or a
+    #     suspiciously short partial fragment with no terminating
+    #     punctuation (e.g. "The").  A real short answer keeps its text.
+    if not interrupted:
+        try:
+            if agent._turn_completion_explainer_enabled():
+                _stripped = (final_response or "").strip()
+                _is_empty_terminal = _stripped == "" or _stripped == "(empty)"
+                # A short fragment that is not a normal text_response exit
+                # and lacks sentence-ending punctuation is treated as a
+                # truncated partial (the "The" case from #34452).
+                _is_partial_fragment = (
+                    not _is_empty_terminal
+                    and not str(_turn_exit_reason).startswith("text_response")
+                    and len(_stripped) <= 24
+                    and _stripped[-1:] not in {".", "!", "?", "。", "！", "？", "`", ")"}
+                )
+                if _is_empty_terminal or _is_partial_fragment:
+                    _explanation = agent._format_turn_completion_explanation(
+                        _turn_exit_reason
+                    )
+                    if _explanation:
+                        if _is_empty_terminal:
+                            # Replace the bare "(empty)"/blank sentinel with
+                            # the actionable explanation.
+                            final_response = _explanation
+                        else:
+                            # Keep the partial fragment, append the reason so
+                            # the user sees both what arrived and why it
+                            # stopped.
+                            final_response = (
+                                _stripped + "\n\n" + _explanation
+                            )
+        except Exception as _exp_err:
+            logger.debug("turn-completion explainer failed: %s", _exp_err)
+
     _response_transformed = False
 
     # Plugin hook: transform_llm_output

agent/credential_pool.py

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

agent/curator.py

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

agent/curator_backup.py

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

agent/file_safety.py

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

agent/lsp/cli.py

@@ -247,18 +247,13 @@ def _cmd_restart() -> int:
 
 
 def _cmd_which(server_id: str) -> int:
-    from agent.lsp.install import INSTALL_RECIPES, hermes_lsp_bin_dir
-    import shutil as _shutil
+    from agent.lsp.install import INSTALL_RECIPES, _existing_binary
 
     recipe = INSTALL_RECIPES.get(server_id)
     bin_name = (recipe or {}).get("bin", server_id)
-    staged = hermes_lsp_bin_dir() / bin_name
-    if staged.exists():
-        sys.stdout.write(str(staged) + "\n")
-        return 0
-    on_path = _shutil.which(bin_name)
-    if on_path:
-        sys.stdout.write(on_path + "\n")
+    resolved = _existing_binary(bin_name)
+    if resolved:
+        sys.stdout.write(resolved + "\n")
         return 0
     sys.stderr.write(f"{server_id}: not installed\n")
     return 1
@@ -292,11 +287,9 @@ def _backend_warnings() -> list:
     suggestion across common platforms.
     """
     import shutil as _shutil
-    from agent.lsp.install import hermes_lsp_bin_dir
+    from agent.lsp.install import _existing_binary
     notes: list = []
-    bash_installed = _shutil.which("bash-language-server") is not None or (
-        (hermes_lsp_bin_dir() / "bash-language-server").exists()
-    )
+    bash_installed = _existing_binary("bash-language-server") is not None
     if bash_installed and _shutil.which("shellcheck") is None:
         notes.append(
             "bash-language-server is installed but shellcheck is missing — "

agent/lsp/client.py

@@ -44,6 +44,7 @@ from __future__ import annotations
 import asyncio
 import logging
 import os
+import sys
 from pathlib import Path
 from typing import Any, Awaitable, Callable, Dict, List, Optional, Set
 from urllib.parse import quote, unquote
@@ -244,15 +245,27 @@ class LSPClient:
             await self._cleanup_process()
             raise
 
+    @staticmethod
+    def _win_wrap_cmd(cmd: List[str]) -> List[str]:
+        """On Windows, wrap .cmd/.bat shims so CreateProcess can run them."""
+        exe = cmd[0]
+        if exe.lower().endswith((".cmd", ".bat")):
+            return ["cmd.exe", "/c", *cmd]
+        return cmd
+
     async def _spawn(self) -> None:
         env = dict(os.environ)
         if self._env:
             env.update(self._env)
 
+        cmd = self._command
+        if sys.platform == "win32":
+            cmd = self._win_wrap_cmd(cmd)
+
         try:
             self._proc = await asyncio.create_subprocess_exec(
-                self._command[0],
-                *self._command[1:],
+                cmd[0],
+                *cmd[1:],
                 stdin=asyncio.subprocess.PIPE,
                 stdout=asyncio.subprocess.PIPE,
                 stderr=asyncio.subprocess.PIPE,
@@ -261,7 +274,7 @@ class LSPClient:
             )
         except FileNotFoundError as e:
             raise LSPProtocolError(
-                f"LSP server binary not found: {self._command[0]} ({e})"
+                f"LSP server binary not found: {cmd[0]} ({e})"
             ) from e
 
         # Drain stderr at debug level — if we don't, the pipe buffer

agent/lsp/install.py

@@ -108,6 +108,11 @@ INSTALL_RECIPES: Dict[str, Dict[str, Any]] = {
 _install_locks: Dict[str, threading.Lock] = {}
 _install_results: Dict[str, Optional[str]] = {}
 _install_lock_meta = threading.Lock()
+_WINDOWS_WRAPPER_SUFFIXES = (".cmd", ".exe", ".bat")
+
+
+def _is_windows() -> bool:
+    return os.name == "nt"
 
 
 def hermes_lsp_bin_dir() -> Path:
@@ -120,14 +125,33 @@ def hermes_lsp_bin_dir() -> Path:
     return p
 
 
+def _native_binary_candidates(base: Path) -> list[Path]:
+    """Return platform-native executable candidates for a staged binary."""
+    candidates = [base]
+    if _is_windows():
+        existing = {str(base).lower()}
+        for suffix in _WINDOWS_WRAPPER_SUFFIXES:
+            candidate = Path(str(base) + suffix)
+            key = str(candidate).lower()
+            if key not in existing:
+                candidates.append(candidate)
+                existing.add(key)
+    return candidates
+
+
 def _existing_binary(name: str) -> Optional[str]:
     """Probe the staging dir + PATH for a binary named ``name``."""
-    staged = hermes_lsp_bin_dir() / name
-    if staged.exists() and os.access(staged, os.X_OK):
-        return str(staged)
+    for staged in _native_binary_candidates(hermes_lsp_bin_dir() / name):
+        if staged.exists() and os.access(staged, os.X_OK):
+            return str(staged)
     on_path = shutil.which(name)
     if on_path:
         return on_path
+    if _is_windows():
+        for suffix in _WINDOWS_WRAPPER_SUFFIXES:
+            on_path = shutil.which(f"{name}{suffix}")
+            if on_path:
+                return on_path
     return None
 
 
@@ -250,12 +274,7 @@ def _install_npm(
 
     # Find the bin
     nm_bin = staging / "node_modules" / ".bin" / bin_name
-    if os.name == "nt":
-        # On Windows npm sometimes drops `.cmd` shims
-        candidates = [nm_bin, nm_bin.with_suffix(".cmd")]
-    else:
-        candidates = [nm_bin]
-    for c in candidates:
+    for c in _native_binary_candidates(nm_bin):
         if c.exists():
             # Symlink into our `lsp/bin/` for stable PATH access.
             link = hermes_lsp_bin_dir() / c.name
@@ -301,7 +320,7 @@ def _install_go(pkg: str, bin_name: str) -> Optional[str]:
         logger.warning("[install] go install errored for %s: %s", pkg, e)
         return None
     bin_path = staging / bin_name
-    if os.name == "nt":
+    if _is_windows():
         bin_path = bin_path.with_suffix(".exe")
     if bin_path.exists():
         return str(bin_path)
@@ -337,19 +356,24 @@ def _install_pip(pkg: str, bin_name: str) -> Optional[str]:
     except (subprocess.TimeoutExpired, OSError) as e:
         logger.warning("[install] pip install errored for %s: %s", pkg, e)
         return None
-    # Look for the script
-    bin_path = pip_target / "bin" / bin_name
-    if bin_path.exists():
-        link = hermes_lsp_bin_dir() / bin_name
-        if not link.exists():
-            try:
-                link.symlink_to(bin_path)
-            except (OSError, NotImplementedError):
-                try:
-                    shutil.copy2(bin_path, link)
-                except OSError:
-                    return str(bin_path)
-        return str(link if link.exists() else bin_path)
+    # Look for the console script.  POSIX wheels generally write to bin/,
+    # while native Windows installs use Scripts/.
+    script_dirs = [pip_target / "bin"]
+    if _is_windows():
+        script_dirs.append(pip_target / "Scripts")
+    for script_dir in script_dirs:
+        for bin_path in _native_binary_candidates(script_dir / bin_name):
+            if bin_path.exists():
+                link = hermes_lsp_bin_dir() / bin_path.name
+                if not link.exists():
+                    try:
+                        link.symlink_to(bin_path)
+                    except (OSError, NotImplementedError):
+                        try:
+                            shutil.copy2(bin_path, link)
+                        except OSError:
+                            return str(bin_path)
+                return str(link if link.exists() else bin_path)
     return None
 
 

agent/memory_manager.py

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

agent/memory_provider.py

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

agent/model_metadata.py

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

agent/moonshot_schema.py

@@ -15,18 +15,6 @@ and MoonshotAI/kimi-cli#1595:
 2. When ``anyOf`` is used, ``type`` must be on the ``anyOf`` children, not
    the parent.  Presence of both causes "type should be defined in anyOf
    items instead of the parent schema".
-3. ``enum`` arrays on scalar-typed nodes may not contain ``null`` or empty
-   strings.  Strip those entries (drop the enum entirely if it becomes empty).
-4. ``$ref`` nodes may not carry sibling keywords.  Moonshot expands the
-   reference before validation and then rejects the node if sibling keys
-   like ``description`` remain on the same node as ``$ref``.  Strip every
-   sibling from ``$ref`` nodes so only ``{"$ref": "..."}`` survives.
-   (Ported from anomalyco/opencode#24730.)
-5. ``items`` may not be a tuple-style array (``items: [schemaA, schemaB]``
-   for positional element schemas).  Moonshot's schema engine requires a
-   single object schema applied to every array element.  Collapse tuple
-   ``items`` to the first element schema (or ``{}`` if the tuple is empty).
-   (Ported from anomalyco/opencode#24730.)
 
 The ``#/definitions/...`` → ``#/$defs/...`` rewrite for draft-07 refs is
 handled separately in ``tools/mcp_tool._normalize_mcp_input_schema`` so it
@@ -78,16 +66,6 @@ def _repair_schema(node: Any, is_schema: bool = True) -> Any:
             }
         elif key in _SCHEMA_LIST_KEYS and isinstance(value, list):
             repaired[key] = [_repair_schema(v, is_schema=True) for v in value]
-        elif key == "items" and isinstance(value, list):
-            # Rule 5: tuple-style ``items`` arrays (positional element
-            # schemas) are not accepted by Moonshot.  Collapse to the
-            # first element schema if present, else to ``{}``.  This
-            # matches opencode's behaviour for moonshotai / kimi models.
-            first = value[0] if value else {}
-            if isinstance(first, dict):
-                repaired[key] = _repair_schema(first, is_schema=True)
-            else:
-                repaired[key] = first
         elif key in _SCHEMA_NODE_KEYS:
             # items / not / additionalProperties: single nested schema.
             # additionalProperties can also be a bool — leave those alone.
@@ -152,15 +130,6 @@ def _repair_schema(node: Any, is_schema: bool = True) -> Any:
             else:
                 repaired.pop("enum")
 
-    # Rule 4: $ref nodes must not have sibling keywords.  Moonshot expands
-    # the reference before validation and then rejects the node if siblings
-    # like ``description`` / ``type`` / ``default`` appear alongside $ref.
-    # The referenced definition still carries its own description on the
-    # target node, which Moonshot accepts.
-    # (Ported from anomalyco/opencode#24730.)
-    if "$ref" in repaired:
-        return {"$ref": repaired["$ref"]}
-
     return repaired
 
 

agent/prompt_builder.py

@@ -14,6 +14,7 @@ from pathlib import Path
 from hermes_constants import get_hermes_home, get_skills_dir, is_wsl
 from typing import Optional
 
+from agent.runtime_cwd import resolve_agent_cwd
 from agent.skill_utils import (
     extract_skill_conditions,
     extract_skill_description,
@@ -802,7 +803,7 @@ def build_environment_hints() -> str:
 
         host_lines.append(f"User home directory: {os.path.expanduser('~')}")
         try:
-            host_lines.append(f"Current working directory: {os.getcwd()}")
+            host_lines.append(f"Current working directory: {resolve_agent_cwd()}")
         except OSError:
             pass
 

agent/redact.py

@@ -150,10 +150,6 @@ _JWT_RE = re.compile(
     r"(?:\.[A-Za-z0-9_=-]{4,}){0,2}"   # Optional payload and/or signature
 )
 
-# Discord user/role mentions: <@123456789012345678> or <@!123456789012345678>
-# Snowflake IDs are 17-20 digit integers that resolve to specific Discord accounts.
-_DISCORD_MENTION_RE = re.compile(r"<@!?(\d{17,20})>")
-
 # E.164 phone numbers: +<country><number>, 7-15 digits
 # Negative lookahead prevents matching hex strings or identifiers
 _SIGNAL_PHONE_RE = re.compile(r"(\+[1-9]\d{6,14})(?![A-Za-z0-9])")
@@ -419,10 +415,6 @@ def redact_sensitive_text(text: str, *, force: bool = False, code_file: bool = F
     if "&" in text and "=" in text:
         text = _redact_form_body(text)
 
-    # Discord user/role mentions (<@snowflake_id>)
-    if "<@" in text:
-        text = _DISCORD_MENTION_RE.sub(lambda m: f"<@{'!' if '!' in m.group(0) else ''}***>", text)
-
     # E.164 phone numbers (Signal, WhatsApp)
     if "+" in text:
         def _redact_phone(m):

agent/runtime_cwd.py

@@ -0,0 +1,33 @@
+"""Single source of truth for the agent working directory.
+
+`TERMINAL_CWD` is the runtime carrier for the configured working directory
+(design #19214/#19242: `terminal.cwd` is bridged once to `TERMINAL_CWD` at
+gateway/cron startup). The local-CLI backend deliberately leaves it unset and
+relies on the launch dir. Reading it in one place keeps the system prompt, the
+tool surfaces, and context-file discovery agreeing on where the agent lives.
+
+The #29531 per-session extension point is this function: a future PR adds a
+contextvar arm inside `resolve_agent_cwd` and `.set()`s it at the
+`set_session_vars` seam — by design, not a reopening hazard.
+"""
+
+import os
+from pathlib import Path
+
+
+def resolve_agent_cwd() -> Path:
+    raw = os.environ.get("TERMINAL_CWD", "").strip()
+    if raw:
+        p = Path(raw).expanduser()
+        if p.is_dir():
+            return p
+    return Path(os.getcwd())
+
+
+def resolve_context_cwd() -> Path | None:
+    # None means "no configured cwd": build_context_files_prompt then falls back
+    # to the launch dir (os.getcwd()) — correct for the local CLI. The gateway
+    # avoids slurping its install dir by setting TERMINAL_CWD (see system_prompt.py).
+    # No getcwd arm here: that fallback is owned by the caller, not this resolver.
+    raw = os.environ.get("TERMINAL_CWD", "").strip()
+    return Path(raw).expanduser() if raw else None

agent/system_prompt.py

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

agent/tool_executor.py

@@ -180,28 +180,9 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
         except Exception:
             pass
 
-        # Checkpoint for file-mutating tools
-        if function_name in {"write_file", "patch"} and agent._checkpoint_mgr.enabled:
-            try:
-                file_path = function_args.get("path", "")
-                if file_path:
-                    work_dir = agent._checkpoint_mgr.get_working_dir_for_path(file_path)
-                    agent._checkpoint_mgr.ensure_checkpoint(work_dir, f"before {function_name}")
-            except Exception:
-                pass
-
-        # Checkpoint before destructive terminal commands
-        if function_name == "terminal" and agent._checkpoint_mgr.enabled:
-            try:
-                cmd = function_args.get("command", "")
-                if _is_destructive_command(cmd):
-                    cwd = function_args.get("workdir") or os.getenv("TERMINAL_CWD", os.getcwd())
-                    agent._checkpoint_mgr.ensure_checkpoint(
-                        cwd, f"before terminal: {cmd[:60]}"
-                    )
-            except Exception:
-                pass
-
+        # ── Block evaluation (BEFORE checkpoint preflight) ───────────
+        # We must know whether the tool will execute before touching
+        # checkpoint state (dedup slot, real snapshots).
         block_result = None
         blocked_by_guardrail = False
         if _ts_scope_block is not None:
@@ -224,6 +205,30 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
                     block_result = agent._guardrail_block_result(guardrail_decision)
                     blocked_by_guardrail = True
 
+        # ── Checkpoint preflight (only for tools that will execute) ──
+        if block_result is None:
+            # Checkpoint for file-mutating tools
+            if function_name in {"write_file", "patch"} and agent._checkpoint_mgr.enabled:
+                try:
+                    file_path = function_args.get("path", "")
+                    if file_path:
+                        work_dir = agent._checkpoint_mgr.get_working_dir_for_path(file_path)
+                        agent._checkpoint_mgr.ensure_checkpoint(work_dir, f"before {function_name}")
+                except Exception:
+                    pass
+
+            # Checkpoint before destructive terminal commands
+            if function_name == "terminal" and agent._checkpoint_mgr.enabled:
+                try:
+                    cmd = function_args.get("command", "")
+                    if _is_destructive_command(cmd):
+                        cwd = function_args.get("workdir") or os.getenv("TERMINAL_CWD", os.getcwd())
+                        agent._checkpoint_mgr.ensure_checkpoint(
+                            cwd, f"before terminal: {cmd[:60]}"
+                        )
+                except Exception:
+                    pass
+
         parsed_calls.append((tool_call, function_name, function_args, block_result, blocked_by_guardrail))
 
     # ── Logging / callbacks ──────────────────────────────────────────
@@ -301,33 +306,38 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
         # submit site below (GHSA-qg5c-hvr5-hjgr, #13617).
         start = time.time()
         try:
-            result = agent._invoke_tool(
-                function_name,
-                function_args,
-                effective_task_id,
-                tool_call.id,
-                messages=messages,
-                pre_tool_block_checked=True,
-            )
-        except Exception as tool_error:
-            result = f"Error executing tool '{function_name}': {tool_error}"
-            logger.error("_invoke_tool raised for %s: %s", function_name, tool_error, exc_info=True)
-        duration = time.time() - start
-        is_error, _ = _detect_tool_failure(function_name, result)
-        if is_error:
-            logger.info("tool %s failed (%.2fs): %s", function_name, duration, result[:200])
-        else:
-            logger.info("tool %s completed (%.2fs, %d chars)", function_name, duration, len(result))
-        results[index] = (function_name, function_args, result, duration, is_error, False)
-        # Tear down worker-tid tracking.  Clear any interrupt bit we may
-        # have set so the next task scheduled onto this recycled tid
-        # starts with a clean slate.
-        with agent._tool_worker_threads_lock:
-            agent._tool_worker_threads.discard(_worker_tid)
-        try:
-            _ra()._set_interrupt(False, _worker_tid)
-        except Exception:
-            pass
+            try:
+                result = agent._invoke_tool(
+                    function_name,
+                    function_args,
+                    effective_task_id,
+                    tool_call.id,
+                    messages=messages,
+                    pre_tool_block_checked=True,
+                )
+            except Exception as tool_error:
+                result = f"Error executing tool '{function_name}': {tool_error}"
+                logger.error("_invoke_tool raised for %s: %s", function_name, tool_error, exc_info=True)
+            duration = time.time() - start
+            is_error, _ = _detect_tool_failure(function_name, result)
+            if is_error:
+                logger.info("tool %s failed (%.2fs): %s", function_name, duration, result[:200])
+            else:
+                logger.info("tool %s completed (%.2fs, %d chars)", function_name, duration, len(result))
+            results[index] = (function_name, function_args, result, duration, is_error, False)
+        finally:
+            # Tear down worker-tid tracking.  Clear any interrupt bit we may
+            # have set so the next task scheduled onto this recycled tid
+            # starts with a clean slate.  This MUST be in a finally block
+            # because BaseException subclasses (CancelledError, KeyboardInterrupt)
+            # bypass ``except Exception`` and would otherwise leak the tid
+            # into _interrupted_threads, poisoning the recycled thread.
+            with agent._tool_worker_threads_lock:
+                agent._tool_worker_threads.discard(_worker_tid)
+            try:
+                _ra()._set_interrupt(False, _worker_tid)
+            except Exception:
+                pass
 
     # Start spinner for CLI mode (skip when TUI handles tool progress)
     spinner = None
@@ -753,10 +763,14 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
         elif function_name == "delegate_task":
             tasks_arg = function_args.get("tasks")
             if tasks_arg and isinstance(tasks_arg, list):
-                spinner_label = f"🔀 delegating {len(tasks_arg)} tasks"
+                spinner_label = f"🔀 delegating {len(tasks_arg)} tasks · (/agents to monitor)"
             else:
                 goal_preview = (function_args.get("goal") or "")[:30]
-                spinner_label = f"🔀 {goal_preview}" if goal_preview else "🔀 delegating"
+                spinner_label = (
+                    f"🔀 {goal_preview} · (/agents to monitor)"
+                    if goal_preview
+                    else "🔀 delegating · (/agents to monitor)"
+                )
             spinner = None
             if agent._should_emit_quiet_tool_messages() and agent._should_start_quiet_spinner():
                 face = random.choice(KawaiiSpinner.get_waiting_faces())

apps/bootstrap-installer/.gitignore

@@ -0,0 +1,40 @@
+# Rust / Cargo
+/src-tauri/target/
+/src-tauri/Cargo.lock
+
+# Vite / build output
+/dist/
+/dist-ssr/
+*.local
+
+# TypeScript build info + tsc emit (we don't ship .js for the
+# vite.config.ts; Vite reads it directly via ts-node-style loader).
+*.tsbuildinfo
+vite.config.d.ts
+vite.config.js
+
+# Tauri generated artifacts (regenerated on each build)
+/src-tauri/gen/schemas/
+
+# Logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Editor
+.vscode/*
+!.vscode/extensions.json
+.idea/
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?
+
+# Node
+node_modules/
+
+# Internal placeholder (re-create if needed)
+.tauri-note

apps/bootstrap-installer/index.html

@@ -0,0 +1,12 @@
+<!doctype html>
+<html lang="en" class="h-full">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Hermes</title>
+  </head>
+  <body class="h-full antialiased">
+    <div id="root" class="h-full"></div>
+    <script type="module" src="/src/main.tsx"></script>
+  </body>
+</html>

apps/bootstrap-installer/package.json

@@ -0,0 +1,46 @@
+{
+  "name": "@hermes/bootstrap-installer",
+  "private": true,
+  "version": "0.0.1",
+  "description": "Hermes Setup — signed installer that drives scripts/install.ps1 with a polished native UI.",
+  "type": "module",
+  "scripts": {
+    "dev": "vite --host 127.0.0.1 --port 5175",
+    "build": "tsc -b && vite build",
+    "preview": "vite preview",
+    "tauri": "tauri",
+    "tauri:dev": "tauri dev",
+    "tauri:build": "tauri build",
+    "tauri:build:debug": "tauri build --debug"
+  },
+  "dependencies": {
+    "@nous-research/ui": "0.16.0",
+    "@tailwindcss/vite": "^4.2.1",
+    "@tailwindcss/typography": "^0.5.19",
+    "@tauri-apps/api": "^2.0.0",
+    "@tauri-apps/plugin-dialog": "^2.0.0",
+    "@tauri-apps/plugin-opener": "^2.0.0",
+    "@tauri-apps/plugin-process": "^2.0.0",
+    "@tauri-apps/plugin-shell": "^2.0.0",
+    "@vscode/codicons": "^0.0.45",
+    "class-variance-authority": "^0.7.1",
+    "clsx": "^2.1.1",
+    "katex": "^0.16.45",
+    "lucide-react": "^0.577.0",
+    "nanostores": "^1.3.0",
+    "radix-ui": "^1.4.3",
+    "react": "^19.2.4",
+    "react-dom": "^19.2.4",
+    "tailwind-merge": "^3.5.0",
+    "tailwindcss": "^4.2.1",
+    "tw-shimmer": "^0.4.11"
+  },
+  "devDependencies": {
+    "@tauri-apps/cli": "^2.0.0",
+    "@types/react": "^19.2.14",
+    "@types/react-dom": "^19.2.3",
+    "@vitejs/plugin-react": "^5.2.0",
+    "typescript": "~5.9.3",
+    "vite": "^7.3.1"
+  }
+}

apps/bootstrap-installer/src-tauri/Cargo.toml

@@ -0,0 +1,75 @@
+[package]
+name = "hermes-bootstrap"
+version = "0.0.1"
+description = "Hermes Setup — signed installer that drives scripts/install.ps1"
+authors = ["Nous Research <info@nousresearch.com>"]
+edition = "2021"
+rust-version = "1.77"
+
+# Rename the output binary so the distributed artifact is literally
+# `Hermes-Setup.exe` on disk — not `hermes-bootstrap.exe`. Grandma sees
+# what we hand her, period. Tauri honors [[bin]] over [package].name
+# for the produced executable name.
+[[bin]]
+name = "Hermes-Setup"
+path = "src/main.rs"
+
+# The library target name MUST match the `withGlobalTauri` binding name that
+# tauri.conf.json's `app.windows[].label` references. We don't ship a separate
+# lib for now; everything is in src/.
+[lib]
+name = "hermes_bootstrap_lib"
+crate-type = ["staticlib", "cdylib", "rlib"]
+
+[build-dependencies]
+tauri-build = { version = "2", features = [] }
+
+[dependencies]
+# Tauri runtime + plugins
+tauri = { version = "2", features = [] }
+tauri-plugin-dialog = "2"
+tauri-plugin-opener = "2"
+tauri-plugin-process = "2"
+tauri-plugin-shell = "2"
+
+# Async + IO
+tokio = { version = "1", features = ["full"] }
+futures = "0.3"
+
+# Serialization
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+
+# HTTP — rustls so we don't need OpenSSL on the build box
+reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "stream"] }
+
+# Logging — emitted to a file under HERMES_HOME/logs/ and (optionally) the
+# webview console via Tauri's event channel.
+tracing = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt"] }
+tracing-appender = "0.2"
+
+# Paths + utils
+dirs = "5"
+which = "6"
+anyhow = "1"
+thiserror = "1"
+once_cell = "1"
+uuid = { version = "1", features = ["v4"] }
+
+# Process control on Windows (CREATE_NO_WINDOW etc.)
+[target.'cfg(windows)'.dependencies]
+windows-sys = { version = "0.59", features = [
+    "Win32_Foundation",
+    "Win32_System_Threading",
+    "Win32_System_Console",
+    "Win32_UI_WindowsAndMessaging",
+] }
+
+[profile.release]
+# A 5-10MB signed installer is the goal. LTO + size-opt + single codegen unit.
+panic = "abort"
+codegen-units = 1
+lto = true
+opt-level = "s"
+strip = true

apps/bootstrap-installer/src-tauri/build.rs

@@ -0,0 +1,190 @@
+use std::process::Command;
+
+fn main() {
+    // -----------------------------------------------------------------
+    // Bake the install.ps1 pin into the binary at compile time.
+    //
+    // BUILD_PIN_COMMIT and BUILD_PIN_BRANCH are read by bootstrap.rs's
+    // `option_env!()` macro to default the install-script reference.
+    // Precedence (matches install.ps1's own arg precedence): commit > branch.
+    //
+    // The COMMIT pin is opt-in. By default a dev build pins ONLY the branch,
+    // so the produced installer follows that branch's HEAD at install time
+    // (tolerant of fast-forwards/new commits, and never references a SHA the
+    // local checkout hasn't pushed). Set HERMES_BUILD_PIN_COMMIT to bake an
+    // immutable commit pin for reproducible/release installers.
+    //
+    // Commit pin resolution:
+    //   - HERMES_BUILD_PIN_COMMIT, if set and non-empty. Accepts a SHA, tag,
+    //     or branch name; resolved to an immutable SHA via `git rev-parse`
+    //     when possible, else used verbatim if it already looks like a SHA.
+    //   - Otherwise: NO commit pin (branch-follow is the default).
+    //
+    // Branch pin resolution:
+    //   1. HERMES_BUILD_PIN_BRANCH, if set and non-empty.
+    //   2. `git rev-parse --abbrev-ref HEAD` of the checkout this build.rs
+    //      lives in — the current branch. (None on a detached HEAD.)
+    //   3. Last-resort fallback handled below: if neither commit nor branch
+    //      resolves, warn — the binary needs a runtime arg or dev-repo env.
+    //
+    // Build script reruns on git HEAD change so a new commit triggers
+    // a rebuild without `cargo clean`.
+    // -----------------------------------------------------------------
+
+    let commit = resolve_commit_pin();
+    let branch = resolve_branch_pin();
+
+    if let Some(c) = &commit {
+        println!("cargo:rustc-env=BUILD_PIN_COMMIT={c}");
+        println!(
+            "cargo:warning=hermes-bootstrap: pinning to commit {}",
+            short(c)
+        );
+    }
+    if let Some(b) = &branch {
+        println!("cargo:rustc-env=BUILD_PIN_BRANCH={b}");
+        match &commit {
+            Some(_) => println!("cargo:warning=hermes-bootstrap: pinning to branch {b}"),
+            None => println!(
+                "cargo:warning=hermes-bootstrap: following branch {b} HEAD (no commit pin; \
+                 set HERMES_BUILD_PIN_COMMIT for an immutable pin)"
+            ),
+        }
+    }
+    if commit.is_none() && branch.is_none() {
+        // Fail loudly rather than silently produce a binary that errors
+        // at runtime with "no install-script pin supplied". A build that
+        // can't resolve a pin almost certainly indicates a misconfigured
+        // build environment.
+        println!(
+            "cargo:warning=hermes-bootstrap: no pin resolved at build time; binary will fail at runtime without HERMES_SETUP_DEV_REPO_ROOT or runtime args"
+        );
+    }
+
+    // Rerun build.rs when HEAD moves. With branch-follow as the default the
+    // baked commit no longer changes per-commit, but a branch *switch* changes
+    // the detected branch name, so we still re-trigger. When an explicit
+    // HERMES_BUILD_PIN_COMMIT resolves a moving ref (tag/branch) to a SHA, a
+    // HEAD move can also change that resolution. .git/HEAD changes on every
+    // commit / branch switch / rebase.
+    let git_dir = locate_git_dir();
+    if let Some(gd) = &git_dir {
+        println!("cargo:rerun-if-changed={}/HEAD", gd.display());
+        // .git/HEAD often points at a ref (e.g. `ref: refs/heads/bb/gui`);
+        // also watch the ref itself so a new commit on the same branch
+        // re-triggers.
+        if let Ok(head) = std::fs::read_to_string(gd.join("HEAD")) {
+            if let Some(rest) = head.trim().strip_prefix("ref: ") {
+                println!("cargo:rerun-if-changed={}/{}", gd.display(), rest);
+            }
+        }
+    }
+    println!("cargo:rerun-if-env-changed=HERMES_BUILD_PIN_COMMIT");
+    println!("cargo:rerun-if-env-changed=HERMES_BUILD_PIN_BRANCH");
+
+    // -----------------------------------------------------------------
+    // Tauri windows manifest. See hermes-setup.manifest for rationale —
+    // declares level="asInvoker" so Windows's installer-detection
+    // heuristic doesn't refuse to launch us without UAC elevation.
+    // -----------------------------------------------------------------
+    #[cfg(target_os = "windows")]
+    let attrs = {
+        let manifest = include_str!("hermes-setup.manifest");
+        let win = tauri_build::WindowsAttributes::new().app_manifest(manifest);
+        tauri_build::Attributes::new().windows_attributes(win)
+    };
+
+    #[cfg(not(target_os = "windows"))]
+    let attrs = tauri_build::Attributes::new();
+
+    tauri_build::try_build(attrs).expect("failed to run tauri-build");
+}
+
+fn resolve_commit_pin() -> Option<String> {
+    // Commit pinning is OPT-IN. Only bake a commit when the caller explicitly
+    // asks for one via HERMES_BUILD_PIN_COMMIT. With no env var, we return
+    // None and the installer follows the branch HEAD at install time.
+    let requested = std::env::var("HERMES_BUILD_PIN_COMMIT").ok()?;
+    let requested = requested.trim();
+    if requested.is_empty() {
+        return None;
+    }
+    // Resolve the request (which may be a SHA, tag, or branch name) to an
+    // immutable commit SHA so the baked pin is reproducible. `^{commit}`
+    // dereferences tags to the commit they point at.
+    if let Ok(out) = Command::new("git")
+        .args(["rev-parse", "--verify", &format!("{requested}^{{commit}}")])
+        .output()
+    {
+        if out.status.success() {
+            if let Ok(s) = String::from_utf8(out.stdout) {
+                let s = s.trim().to_string();
+                if !s.is_empty() {
+                    return Some(s);
+                }
+            }
+        }
+    }
+    // Couldn't resolve via git (e.g. building outside a checkout). Accept the
+    // literal value only if it already looks like a SHA; otherwise fail loud
+    // rather than bake an unresolvable ref into the binary.
+    if is_sha(requested) {
+        return Some(requested.to_string());
+    }
+    panic!(
+        "HERMES_BUILD_PIN_COMMIT={requested:?} could not be resolved to a commit \
+         (git rev-parse failed and it is not a valid SHA)"
+    );
+}
+
+/// True if `s` looks like an abbreviated-or-full git SHA (7..=40 hex chars).
+fn is_sha(s: &str) -> bool {
+    let len = s.len();
+    (7..=40).contains(&len) && s.chars().all(|c| c.is_ascii_hexdigit())
+}
+
+fn resolve_branch_pin() -> Option<String> {
+    if let Ok(v) = std::env::var("HERMES_BUILD_PIN_BRANCH") {
+        if !v.trim().is_empty() {
+            return Some(v.trim().to_string());
+        }
+    }
+    let out = Command::new("git")
+        .args(["rev-parse", "--abbrev-ref", "HEAD"])
+        .output()
+        .ok()?;
+    if !out.status.success() {
+        return None;
+    }
+    let s = String::from_utf8(out.stdout).ok()?.trim().to_string();
+    // "HEAD" is what you get on a detached checkout — no meaningful branch
+    // to pin to. The commit pin still applies; just don't emit a branch.
+    if s.is_empty() || s == "HEAD" {
+        None
+    } else {
+        Some(s)
+    }
+}
+
+fn locate_git_dir() -> Option<std::path::PathBuf> {
+    let out = Command::new("git")
+        .args(["rev-parse", "--git-dir"])
+        .output()
+        .ok()?;
+    if !out.status.success() {
+        return None;
+    }
+    let s = String::from_utf8(out.stdout).ok()?.trim().to_string();
+    if s.is_empty() {
+        return None;
+    }
+    Some(std::path::PathBuf::from(s))
+}
+
+fn short(commit: &str) -> &str {
+    if commit.len() >= 12 {
+        &commit[..12]
+    } else {
+        commit
+    }
+}

apps/bootstrap-installer/src-tauri/capabilities/default.json

@@ -0,0 +1,16 @@
+{
+  "$schema": "https://schema.tauri.app/config/2/capability",
+  "identifier": "default",
+  "description": "Capabilities required by Hermes Setup. Narrowly scoped: we don't write user files outside HERMES_HOME, we don't read arbitrary paths, and the only external network call goes through reqwest (Rust side, not exposed to the webview).",
+  "windows": ["main"],
+  "permissions": [
+    "core:default",
+    "core:window:allow-close",
+    "core:window:allow-minimize",
+    "core:event:default",
+    "opener:default",
+    "dialog:default",
+    "process:default",
+    "shell:default"
+  ]
+}

apps/bootstrap-installer/src-tauri/hermes-setup.manifest

@@ -0,0 +1,75 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<!--
+    Hermes Setup application manifest.
+
+    The TL;DR: tell Windows we are NOT an installer in the classic "needs
+    UAC elevation" sense, despite the product name. We provision into
+    %LOCALAPPDATA%\hermes which is user-scoped and never touch HKLM or
+    Program Files. install.ps1 runs as a child process and elevates
+    itself only if a future stage explicitly needs HKLM access.
+
+    Without this manifest, the "Hermes Setup" productName embedded in
+    the binary's resource trips Windows's installer-detection heuristic
+    (https://learn.microsoft.com/en-us/windows/security/identity-protection/
+    user-account-control/how-user-account-control-works#installer-detection)
+    and CreateProcess fails with ERROR_ELEVATION_REQUIRED (740) when the
+    user double-clicks. asInvoker disables that.
+-->
+<assembly xmlns="urn:schemas-microsoft-com:asm.v1" manifestVersion="1.0">
+    <assemblyIdentity
+        version="0.0.1.0"
+        processorArchitecture="*"
+        name="NousResearch.Hermes.Setup"
+        type="win32"
+    />
+    <description>Hermes Setup</description>
+
+    <trustInfo xmlns="urn:schemas-microsoft-com:asm.v3">
+        <security>
+            <requestedPrivileges>
+                <requestedExecutionLevel level="asInvoker" uiAccess="false"/>
+            </requestedPrivileges>
+        </security>
+    </trustInfo>
+
+    <!-- Tell Windows we know about all supported OSes (10 + 11) so it
+         doesn't shim us into Vista-compat mode. -->
+    <compatibility xmlns="urn:schemas-microsoft-com:compatibility.v1">
+        <application>
+            <!-- Windows 10 / 11 -->
+            <supportedOS Id="{8e0f7a12-bfb3-4fe8-b9a5-48fd50a15a9a}"/>
+            <!-- Windows 8.1 -->
+            <supportedOS Id="{1f676c76-80e1-4239-95bb-83d0f6d0da78}"/>
+            <!-- Windows 8 -->
+            <supportedOS Id="{4a2f28e3-53b9-4441-ba9c-d69d4a4a6e38}"/>
+            <!-- Windows 7 -->
+            <supportedOS Id="{35138b9a-5d96-4fbd-8e2d-a2440225f93a}"/>
+            <!-- Windows Vista -->
+            <supportedOS Id="{e2011457-1546-43c5-a5fe-008deee3d3f0}"/>
+        </application>
+    </compatibility>
+
+    <!-- Per-monitor v2 DPI awareness so the installer doesn't go blurry
+         on high-DPI displays when dragged between monitors. -->
+    <application xmlns="urn:schemas-microsoft-com:asm.v3">
+        <windowsSettings>
+            <dpiAwareness xmlns="http://schemas.microsoft.com/SMI/2016/WindowsSettings">PerMonitorV2</dpiAwareness>
+            <activeCodePage xmlns="http://schemas.microsoft.com/SMI/2019/WindowsSettings">UTF-8</activeCodePage>
+        </windowsSettings>
+    </application>
+
+    <!-- Use the modern common controls (v6 themes). Without this, our
+         file picker / shell dialogs fall back to 1990s-era visuals. -->
+    <dependency>
+        <dependentAssembly>
+            <assemblyIdentity
+                type="win32"
+                name="Microsoft.Windows.Common-Controls"
+                version="6.0.0.0"
+                processorArchitecture="*"
+                publicKeyToken="6595b64144ccf1df"
+                language="*"
+            />
+        </dependentAssembly>
+    </dependency>
+</assembly>

apps/bootstrap-installer/src-tauri/src/bootstrap.rs

@@ -0,0 +1,741 @@
+//! Bootstrap orchestration.
+//!
+//! Direct port of `runBootstrap` from `apps/desktop/electron/bootstrap-runner.cjs`.
+//! Drives install.ps1 / install.sh stage-by-stage, emits progress events
+//! over the Tauri `bootstrap` channel, writes a forensic log to
+//! HERMES_HOME/logs/bootstrap-<timestamp>.log.
+//!
+//! Lifecycle:
+//!   1. `start_bootstrap` (Tauri command) → spawns the worker task.
+//!   2. Worker resolves install script (dev/cache/download).
+//!   3. Worker calls `install.ps1 -Manifest` → emits `manifest` event.
+//!   4. Worker iterates stages, calling `install.ps1 -Stage NAME -NonInteractive -Json`.
+//!   5. On success → `complete`. On any stage failure → `failed`. On cancel → `failed`.
+
+use std::path::PathBuf;
+use std::sync::Arc;
+use std::time::Instant;
+
+use anyhow::{anyhow, Result};
+use serde::{Deserialize, Serialize};
+use tauri::{AppHandle, Emitter, State};
+use tokio::sync::{mpsc, Mutex};
+
+use crate::events::{BootstrapEvent, Manifest, StageState};
+use crate::install_script::{self, Pin, ScriptKind, ScriptSource};
+use crate::powershell::{self, StreamSink};
+use crate::AppState;
+
+// ---------------------------------------------------------------------------
+// Public Tauri commands
+// ---------------------------------------------------------------------------
+
+/// Frontend → Rust: kick off the install.
+#[derive(Debug, Deserialize)]
+pub struct StartBootstrapArgs {
+    /// Optional override for the commit pin. Defaults to the build-time
+    /// pin baked in via `BUILD_PIN_COMMIT`.
+    pub commit: Option<String>,
+    /// Optional override for the branch pin. Defaults to `BUILD_PIN_BRANCH`.
+    pub branch: Option<String>,
+    /// Include Stage-Desktop (build apps/desktop) in the manifest. The
+    /// signed bootstrap installer passes true; the deprecated Electron-side
+    /// bootstrap-runner passes false to avoid building-while-running.
+    #[serde(default = "default_true")]
+    pub include_desktop: bool,
+    /// Optional override for HERMES_HOME. Tests use this; production
+    /// almost always falls back to the OS default.
+    pub hermes_home: Option<String>,
+}
+
+fn default_true() -> bool {
+    true
+}
+
+#[derive(Debug, Serialize)]
+pub struct BootstrapStatus {
+    pub running: bool,
+    pub completed: bool,
+    pub install_root: Option<String>,
+    pub last_error: Option<String>,
+}
+
+/// Handle stored in AppState while a bootstrap run is in flight. Carries
+/// the cancellation channel and the most recent terminal status so the
+/// frontend can re-query after a window refresh.
+pub struct BootstrapHandle {
+    pub cancel_tx: mpsc::Sender<()>,
+    pub started_at: Instant,
+    pub status: BootstrapStatus,
+}
+
+#[tauri::command]
+pub async fn start_bootstrap(
+    app: AppHandle,
+    state: State<'_, Arc<AppState>>,
+    args: StartBootstrapArgs,
+) -> Result<(), String> {
+    let mut guard = state.bootstrap.lock().await;
+    if let Some(h) = guard.as_ref() {
+        if h.status.running {
+            return Err("Bootstrap is already running".into());
+        }
+    }
+
+    let (cancel_tx, cancel_rx) = mpsc::channel::<()>(1);
+    let handle = BootstrapHandle {
+        cancel_tx,
+        started_at: Instant::now(),
+        status: BootstrapStatus {
+            running: true,
+            completed: false,
+            install_root: None,
+            last_error: None,
+        },
+    };
+    *guard = Some(handle);
+    drop(guard);
+
+    let app_for_task = app.clone();
+    let state_for_task = state.inner().clone();
+    let args_for_task = args;
+    let cancel_rx = Arc::new(Mutex::new(Some(cancel_rx)));
+
+    tokio::spawn(async move {
+        let result = run_bootstrap(app_for_task.clone(), args_for_task, cancel_rx).await;
+
+        // Reflect terminal state into AppState so get_bootstrap_status()
+        // can serve it after the task exits.
+        let mut guard = state_for_task.bootstrap.lock().await;
+        if let Some(h) = guard.as_mut() {
+            h.status.running = false;
+            match &result {
+                Ok(install_root) => {
+                    h.status.completed = true;
+                    h.status.install_root = Some(install_root.clone());
+                    h.status.last_error = None;
+                }
+                Err(err) => {
+                    h.status.completed = false;
+                    h.status.last_error = Some(err.to_string());
+                }
+            }
+        }
+    });
+
+    Ok(())
+}
+
+#[tauri::command]
+pub async fn cancel_bootstrap(state: State<'_, Arc<AppState>>) -> Result<(), String> {
+    let guard = state.bootstrap.lock().await;
+    if let Some(h) = guard.as_ref() {
+        let _ = h.cancel_tx.try_send(());
+    }
+    Ok(())
+}
+
+#[tauri::command]
+pub async fn get_bootstrap_status(
+    state: State<'_, Arc<AppState>>,
+) -> Result<BootstrapStatus, String> {
+    let guard = state.bootstrap.lock().await;
+    Ok(match guard.as_ref() {
+        Some(h) => BootstrapStatus {
+            running: h.status.running,
+            completed: h.status.completed,
+            install_root: h.status.install_root.clone(),
+            last_error: h.status.last_error.clone(),
+        },
+        None => BootstrapStatus {
+            running: false,
+            completed: false,
+            install_root: None,
+            last_error: None,
+        },
+    })
+}
+
+/// Spawn the locally-built Hermes desktop binary, then close the installer
+/// window. Caller resolves the binary path from `install_root`.
+///
+/// Returns Err with a human-readable message if the binary doesn't exist
+/// (e.g. when Stage-Desktop was skipped) so the frontend can present
+/// actionable failure UI rather than silently doing nothing.
+#[tauri::command]
+pub async fn launch_hermes_desktop(
+    app: AppHandle,
+    install_root: String,
+) -> Result<(), String> {
+    let install_root = PathBuf::from(install_root);
+    let exe_path = resolve_hermes_desktop_exe(&install_root).ok_or_else(|| {
+        format!(
+            "Couldn't find a built Hermes desktop at {}. The desktop build step \
+             may have been skipped or failed. Run `hermes desktop` from a \
+             terminal to build and launch it.",
+            install_root.join("apps").join("desktop").join("release").display()
+        )
+    })?;
+
+    tracing::info!(?exe_path, "launching Hermes desktop");
+
+    // Detach from us — the installer is about to exit.
+    let mut cmd = tokio::process::Command::new(&exe_path);
+    cmd.current_dir(exe_path.parent().unwrap_or(&install_root));
+    #[cfg(target_os = "windows")]
+    {
+        use std::os::windows::process::CommandExt;
+        // DETACHED_PROCESS = 0x00000008
+        cmd.creation_flags(0x0000_0008);
+    }
+
+    cmd.spawn().map_err(|e| {
+        format!(
+            "failed to launch {}: {e}",
+            exe_path.display()
+        )
+    })?;
+
+    // Give Windows ~150ms to actually start the new process before we exit.
+    tokio::time::sleep(std::time::Duration::from_millis(150)).await;
+
+    // Exit the installer cleanly. Tauri's process plugin gives us the
+    // right hook regardless of platform.
+    app.exit(0);
+    Ok(())
+}
+
+/// Walks the well-known electron-builder unpacked-app paths under
+/// `install_root`. Mirrors the resolver in `cmd_gui` (apps/desktop/release/
+/// <os>-unpacked/<exe>).
+pub(crate) fn resolve_hermes_desktop_exe(install_root: &std::path::Path) -> Option<PathBuf> {
+    let release_dir = install_root.join("apps").join("desktop").join("release");
+    let candidates: &[(&str, &str)] = if cfg!(target_os = "windows") {
+        &[
+            ("win-unpacked", "Hermes.exe"),
+            ("win-arm64-unpacked", "Hermes.exe"),
+        ]
+    } else if cfg!(target_os = "macos") {
+        &[
+            ("mac/Hermes.app/Contents/MacOS", "Hermes"),
+            ("mac-arm64/Hermes.app/Contents/MacOS", "Hermes"),
+        ]
+    } else {
+        &[("linux-unpacked", "hermes")]
+    };
+    for (subdir, exe) in candidates {
+        let p = release_dir.join(subdir).join(exe);
+        if p.exists() {
+            return Some(p);
+        }
+    }
+    None
+}
+
+/// True when a prior install completed (bootstrap-complete marker present) AND a
+/// launchable desktop app exists on disk. Used by the installer's launcher fast
+/// path so a bare re-open just opens Hermes instead of re-running setup.
+pub(crate) fn hermes_is_installed(install_root: &std::path::Path) -> bool {
+    install_root.join(".hermes-bootstrap-complete").exists()
+        && resolve_hermes_desktop_exe(install_root).is_some()
+}
+
+/// Spawn the already-built desktop app, detached. Returns Err if no built app
+/// exists or the spawn fails, so the caller can fall back to showing the
+/// installer UI.
+pub(crate) fn spawn_installed_desktop(install_root: &std::path::Path) -> std::io::Result<()> {
+    let exe = resolve_hermes_desktop_exe(install_root).ok_or_else(|| {
+        std::io::Error::new(std::io::ErrorKind::NotFound, "no built Hermes desktop app")
+    })?;
+    let mut cmd = std::process::Command::new(&exe);
+    cmd.current_dir(exe.parent().unwrap_or(install_root));
+    #[cfg(target_os = "windows")]
+    {
+        use std::os::windows::process::CommandExt;
+        // DETACHED_PROCESS = 0x00000008 — keep the desktop alive after the
+        // installer exits, mirroring launch_hermes_desktop. Kept correct here
+        // even though the only caller is macOS-gated today, so future reuse on
+        // Windows doesn't reintroduce the relaunch race.
+        cmd.creation_flags(0x0000_0008);
+    }
+    cmd.spawn().map(|_child| ())
+}
+
+// ---------------------------------------------------------------------------
+// Bootstrap implementation
+// ---------------------------------------------------------------------------
+
+async fn run_bootstrap(
+    app: AppHandle,
+    args: StartBootstrapArgs,
+    cancel_rx_holder: Arc<Mutex<Option<mpsc::Receiver<()>>>>,
+) -> Result<String> {
+    let kind = ScriptKind::for_current_os();
+
+    let pin = Pin {
+        commit: args.commit.or_else(|| option_env_string("BUILD_PIN_COMMIT")),
+        branch: args.branch.or_else(|| option_env_string("BUILD_PIN_BRANCH")),
+    };
+
+    tracing::info!(
+        ?pin,
+        kind = ?kind,
+        include_desktop = args.include_desktop,
+        "bootstrap starting"
+    );
+
+    let app_for_log = app.clone();
+    let emit_log = move |line: &str| {
+        emit_event(
+            &app_for_log,
+            BootstrapEvent::Log {
+                stage: None,
+                line: line.to_string(),
+            },
+        );
+        // Bump to info-level so the line shows in bootstrap-installer.log
+        // under the default INFO filter. Previously this was debug! which
+        // got dropped on the floor, leaving us blind whenever install.ps1
+        // failed — the log only had the "bootstrap starting" banner.
+        tracing::info!(target: "bootstrap.log", "{line}");
+    };
+
+    // 1. Resolve install.ps1
+    let script = install_script::resolve(kind, &pin, &emit_log)
+        .await
+        .map_err(|e| {
+            let msg = format!("resolve install script failed: {e:#}");
+            emit_event(
+                &app,
+                BootstrapEvent::Failed {
+                    stage: None,
+                    error: msg.clone(),
+                },
+            );
+            anyhow!(msg)
+        })?;
+
+    let source_note = match &script.source {
+        ScriptSource::DevCheckout => "dev checkout",
+        ScriptSource::Bundled => "bundled",
+        ScriptSource::Cached => "cached",
+        ScriptSource::Downloaded => "downloaded",
+    };
+    emit_log(&format!(
+        "[bootstrap] script {} via {}",
+        script.path.display(),
+        source_note
+    ));
+
+    // 2. Fetch manifest
+    //
+    // -IncludeDesktop MUST be passed to the manifest call too — install.ps1
+    // gates the desktop stage inclusion on this flag, so without it here
+    // the manifest comes back missing the desktop stage and we never run
+    // it. The per-stage call below also passes -IncludeDesktop to keep
+    // the contracts identical.
+    let manifest_args = build_pin_args(&script);
+    let mut manifest_args_full = vec!["-Manifest".to_string()];
+    manifest_args_full.extend(manifest_args.clone());
+    if args.include_desktop {
+        manifest_args_full.push("-IncludeDesktop".to_string());
+    }
+
+    let manifest_result = run_install_script(
+        &app,
+        &script.path,
+        &manifest_args_full,
+        args.hermes_home.as_deref(),
+        None,
+        Some("__manifest__".to_string()),
+    )
+    .await?;
+
+    if manifest_result.exit_code != Some(0) {
+        let err = format!(
+            "install.ps1 -Manifest failed: exit {:?}\n{}",
+            manifest_result.exit_code,
+            manifest_result.stderr.trim()
+        );
+        emit_event(
+            &app,
+            BootstrapEvent::Failed {
+                stage: None,
+                error: err.clone(),
+            },
+        );
+        return Err(anyhow!(err));
+    }
+
+    let manifest: Manifest = powershell::parse_manifest(&manifest_result.stdout).ok_or_else(|| {
+        let err = format!(
+            "install.ps1 -Manifest produced no parseable JSON payload\n{}",
+            truncate(&manifest_result.stdout, 4000)
+        );
+        emit_event(
+            &app,
+            BootstrapEvent::Failed {
+                stage: None,
+                error: err.clone(),
+            },
+        );
+        anyhow!(err)
+    })?;
+
+    emit_event(
+        &app,
+        BootstrapEvent::Manifest {
+            stages: manifest.stages.clone(),
+            protocol_version: manifest.protocol_version,
+        },
+    );
+
+    // 3. Iterate stages.
+    for stage in &manifest.stages {
+        // Skip Stage-Desktop unless explicitly requested. install.ps1 may
+        // or may not include it in the manifest depending on the flag we
+        // pass, but if it slipped in, gate client-side too.
+        if !args.include_desktop && stage.name.eq_ignore_ascii_case("desktop") {
+            emit_event(
+                &app,
+                BootstrapEvent::Stage {
+                    name: stage.name.clone(),
+                    state: StageState::Skipped,
+                    duration_ms: Some(0),
+                    result: None,
+                    error: Some("skipped by include_desktop=false".into()),
+                },
+            );
+            continue;
+        }
+
+        if cancellation_signalled(&cancel_rx_holder).await {
+            let err = "bootstrap cancelled by user".to_string();
+            emit_event(
+                &app,
+                BootstrapEvent::Failed {
+                    stage: Some(stage.name.clone()),
+                    error: err.clone(),
+                },
+            );
+            return Err(anyhow!(err));
+        }
+
+        let started = Instant::now();
+        emit_event(
+            &app,
+            BootstrapEvent::Stage {
+                name: stage.name.clone(),
+                state: StageState::Running,
+                duration_ms: None,
+                result: None,
+                error: None,
+            },
+        );
+
+        let mut stage_args = vec![
+            "-Stage".to_string(),
+            stage.name.clone(),
+            "-NonInteractive".to_string(),
+            "-Json".to_string(),
+        ];
+        stage_args.extend(manifest_args.clone());
+        if args.include_desktop {
+            stage_args.push("-IncludeDesktop".to_string());
+        }
+
+        // Each stage gets its own cancel receiver because tokio::select!
+        // in run_script consumes it. Take/return through the Arc<Mutex>.
+        let local_cancel_rx = cancel_rx_holder.lock().await.take();
+
+        let stage_result = run_install_script(
+            &app,
+            &script.path,
+            &stage_args,
+            args.hermes_home.as_deref(),
+            local_cancel_rx,
+            Some(stage.name.clone()),
+        )
+        .await?;
+
+        let duration_ms = started.elapsed().as_millis() as u64;
+
+        if stage_result.killed {
+            emit_event(
+                &app,
+                BootstrapEvent::Stage {
+                    name: stage.name.clone(),
+                    state: StageState::Failed,
+                    duration_ms: Some(duration_ms),
+                    result: None,
+                    error: Some("cancelled by user".into()),
+                },
+            );
+            emit_event(
+                &app,
+                BootstrapEvent::Failed {
+                    stage: Some(stage.name.clone()),
+                    error: "cancelled by user".into(),
+                },
+            );
+            return Err(anyhow!("cancelled by user"));
+        }
+
+        let result_frame = powershell::parse_stage_result(&stage_result.stdout);
+
+        match result_frame {
+            None => {
+                let err = format!(
+                    "install.ps1 -Stage {} produced no JSON result frame (exit={:?})",
+                    stage.name, stage_result.exit_code
+                );
+                emit_event(
+                    &app,
+                    BootstrapEvent::Stage {
+                        name: stage.name.clone(),
+                        state: StageState::Failed,
+                        duration_ms: Some(duration_ms),
+                        result: None,
+                        error: Some(err.clone()),
+                    },
+                );
+                emit_event(
+                    &app,
+                    BootstrapEvent::Failed {
+                        stage: Some(stage.name.clone()),
+                        error: err.clone(),
+                    },
+                );
+                return Err(anyhow!(err));
+            }
+            Some(frame) if frame.ok && frame.skipped => {
+                emit_event(
+                    &app,
+                    BootstrapEvent::Stage {
+                        name: stage.name.clone(),
+                        state: StageState::Skipped,
+                        duration_ms: Some(duration_ms),
+                        result: Some(frame),
+                        error: None,
+                    },
+                );
+            }
+            Some(frame) if frame.ok => {
+                emit_event(
+                    &app,
+                    BootstrapEvent::Stage {
+                        name: stage.name.clone(),
+                        state: StageState::Succeeded,
+                        duration_ms: Some(duration_ms),
+                        result: Some(frame),
+                        error: None,
+                    },
+                );
+            }
+            Some(frame) => {
+                let err = frame
+                    .reason
+                    .clone()
+                    .unwrap_or_else(|| format!("exit code {:?}", stage_result.exit_code));
+                emit_event(
+                    &app,
+                    BootstrapEvent::Stage {
+                        name: stage.name.clone(),
+                        state: StageState::Failed,
+                        duration_ms: Some(duration_ms),
+                        result: Some(frame),
+                        error: Some(err.clone()),
+                    },
+                );
+                emit_event(
+                    &app,
+                    BootstrapEvent::Failed {
+                        stage: Some(stage.name.clone()),
+                        error: err.clone(),
+                    },
+                );
+                return Err(anyhow!(err));
+            }
+        }
+    }
+
+    // 4. Resolve install_root. install.ps1 doesn't (yet) report this back
+    // explicitly; we infer it from $HermesHome which Stage-Repository clones
+    // the repo INTO at $HermesHome\hermes-agent. Mirrors hermes_constants.
+    let hermes_home = args
+        .hermes_home
+        .clone()
+        .unwrap_or_else(|| crate::paths::hermes_home().to_string_lossy().into_owned());
+    let install_root = PathBuf::from(&hermes_home).join("hermes-agent");
+
+    // Copy ourselves to HERMES_HOME/hermes-setup.exe so the desktop app can
+    // re-invoke us with `--update` and shortcuts have a stable target. This is
+    // a one-shot install concern; an `--update` re-invocation no-ops because
+    // we're already running from that path. Best-effort — a failure here must
+    // not fail an otherwise-successful install.
+    if let Err(err) = crate::paths::copy_self_to_hermes_home() {
+        tracing::warn!(?err, "failed to copy installer into HERMES_HOME (non-fatal)");
+        emit_log(&format!(
+            "[bootstrap] warning: could not stage updater binary: {err}"
+        ));
+    }
+
+    emit_event(
+        &app,
+        BootstrapEvent::Complete {
+            install_root: install_root.to_string_lossy().into_owned(),
+            marker: Some(serde_json::json!({
+                "pinnedCommit": pin.commit,
+                "pinnedBranch": pin.branch,
+            })),
+        },
+    );
+
+    Ok(install_root.to_string_lossy().into_owned())
+}
+
+async fn cancellation_signalled(holder: &Arc<Mutex<Option<mpsc::Receiver<()>>>>) -> bool {
+    let mut guard = holder.lock().await;
+    if let Some(rx) = guard.as_mut() {
+        rx.try_recv().is_ok()
+    } else {
+        false
+    }
+}
+
+async fn run_install_script(
+    app: &AppHandle,
+    script_path: &std::path::Path,
+    args: &[String],
+    hermes_home_override: Option<&str>,
+    cancel_rx: Option<mpsc::Receiver<()>>,
+    stage_name: Option<String>,
+) -> Result<powershell::ScriptResult> {
+    let app_for_stdout = app.clone();
+    let stage_for_stdout = stage_name.clone();
+    let app_for_stderr = app.clone();
+    let stage_for_stderr = stage_name.clone();
+    let stage_for_stdout_log = stage_name.clone();
+    let stage_for_stderr_log = stage_name.clone();
+
+    let sink = StreamSink {
+        on_stdout_line: Box::new(move |line: &str| {
+            emit_event(
+                &app_for_stdout,
+                BootstrapEvent::Log {
+                    stage: stage_for_stdout.clone(),
+                    line: line.to_string(),
+                },
+            );
+            // Tee to the rolling installer log so we have a persistent
+            // record of every install.ps1 line. Without this, the only
+            // log evidence of a failure was the Tauri event stream —
+            // which gets discarded the moment the failure route mounts.
+            match &stage_for_stdout_log {
+                Some(name) => {
+                    tracing::info!(target: "bootstrap.log", stage = %name, "{line}")
+                }
+                None => tracing::info!(target: "bootstrap.log", "{line}"),
+            }
+        }),
+        on_stderr_line: Box::new(move |line: &str| {
+            emit_event(
+                &app_for_stderr,
+                BootstrapEvent::Log {
+                    stage: stage_for_stderr.clone(),
+                    line: format!("stderr: {line}"),
+                },
+            );
+            // stderr-level lines get warn! so they're visually distinct
+            // when scrolling through the log later.
+            match &stage_for_stderr_log {
+                Some(name) => {
+                    tracing::warn!(target: "bootstrap.log", stage = %name, "stderr: {line}")
+                }
+                None => tracing::warn!(target: "bootstrap.log", "stderr: {line}"),
+            }
+        }),
+    };
+
+    powershell::run_script(script_path, args, sink, hermes_home_override, cancel_rx)
+        .await
+        .map_err(|e| {
+            tracing::error!(?e, "install script invocation failed");
+            anyhow!("install script invocation failed: {e:#}")
+        })
+}
+
+fn build_pin_args(script: &install_script::ResolvedScript) -> Vec<String> {
+    let mut out = Vec::new();
+    if let Some(c) = &script.commit {
+        out.push("-Commit".to_string());
+        out.push(c.clone());
+    }
+    if let Some(b) = &script.branch {
+        out.push("-Branch".to_string());
+        out.push(b.clone());
+    }
+    out
+}
+
+fn emit_event(app: &AppHandle, event: BootstrapEvent) {
+    // Tee important state transitions to the rolling installer log so
+    // bootstrap-installer.log isn't just "starting" + final summary.
+    // Log lines (the noisy stuff) handle their own tracing in
+    // run_install_script's sink; here we cover the lifecycle frames.
+    match &event {
+        BootstrapEvent::Manifest { stages, .. } => {
+            tracing::info!(
+                stage_count = stages.len(),
+                names = ?stages.iter().map(|s| s.name.as_str()).collect::<Vec<_>>(),
+                "manifest received"
+            );
+        }
+        BootstrapEvent::Stage {
+            name,
+            state,
+            duration_ms,
+            error,
+            ..
+        } => {
+            tracing::info!(
+                stage = %name,
+                ?state,
+                duration_ms = ?duration_ms,
+                error = ?error,
+                "stage transition"
+            );
+        }
+        BootstrapEvent::Complete { install_root, .. } => {
+            tracing::info!(install_root = %install_root, "bootstrap complete");
+        }
+        BootstrapEvent::Failed { stage, error } => {
+            tracing::error!(stage = ?stage, error = %error, "bootstrap FAILED");
+        }
+        BootstrapEvent::Log { .. } => {
+            // Log lines are teed via the sink callbacks in
+            // run_install_script — don't double-emit here.
+        }
+    }
+    if let Err(e) = app.emit(BootstrapEvent::CHANNEL, &event) {
+        tracing::warn!(?e, "failed to emit bootstrap event");
+    }
+}
+
+fn option_env_string(key: &str) -> Option<String> {
+    // option_env! only accepts literals, so we hardcode the known keys.
+    let val = match key {
+        "BUILD_PIN_COMMIT" => option_env!("BUILD_PIN_COMMIT"),
+        "BUILD_PIN_BRANCH" => option_env!("BUILD_PIN_BRANCH"),
+        _ => None,
+    };
+    val.map(|s| s.to_string())
+}
+
+fn truncate(s: &str, max: usize) -> String {
+    if s.len() <= max {
+        s.to_string()
+    } else {
+        format!("{}...", &s[..max])
+    }
+}

apps/bootstrap-installer/src-tauri/src/events.rs

@@ -0,0 +1,99 @@
+//! Event types streamed from Rust → React.
+//!
+//! These mirror `apps/desktop/electron/bootstrap-runner.cjs`'s event shape
+//! 1:1 so the React installer code can be roughly identical to the Electron
+//! install-overlay we'll replace.
+//!
+//! The Tauri event channel name is `"bootstrap"` for all of these — the
+//! `type` discriminator on each payload is how the frontend routes.
+
+use serde::{Deserialize, Serialize};
+
+/// Stage definition as reported by `install.ps1 -Manifest`.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct StageInfo {
+    pub name: String,
+    pub title: String,
+    pub category: String,
+    /// `needs_user_input=true` stages run with -NonInteractive and emit
+    /// skipped=true; the post-install wizard takes over for those.
+    #[serde(rename = "needs_user_input", alias = "needsUserInput")]
+    pub needs_user_input: bool,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct Manifest {
+    pub stages: Vec<StageInfo>,
+    #[serde(rename = "protocol_version", alias = "protocolVersion", default)]
+    pub protocol_version: Option<u32>,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct StageResultPayload {
+    pub stage: String,
+    pub ok: bool,
+    #[serde(default)]
+    pub skipped: bool,
+    #[serde(default)]
+    pub reason: Option<String>,
+    /// install.ps1 may attach stage-specific structured data here.
+    #[serde(default)]
+    pub data: Option<serde_json::Value>,
+}
+
+/// Run-state for a single stage as we transition through it.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "lowercase")]
+pub enum StageState {
+    Running,
+    Succeeded,
+    Skipped,
+    Failed,
+}
+
+/// The single event channel `bootstrap` emits these. `type` discriminates.
+#[derive(Debug, Clone, Serialize)]
+#[serde(tag = "type", rename_all = "lowercase")]
+pub enum BootstrapEvent {
+    /// Sent once at the start with the full stage list.
+    Manifest {
+        stages: Vec<StageInfo>,
+        #[serde(rename = "protocolVersion")]
+        protocol_version: Option<u32>,
+    },
+    /// Stage state transition. `result` populated only on terminal states.
+    Stage {
+        name: String,
+        state: StageState,
+        #[serde(rename = "durationMs", skip_serializing_if = "Option::is_none")]
+        duration_ms: Option<u64>,
+        #[serde(skip_serializing_if = "Option::is_none")]
+        result: Option<StageResultPayload>,
+        #[serde(skip_serializing_if = "Option::is_none")]
+        error: Option<String>,
+    },
+    /// Raw stdout/stderr line from install.ps1 (or our wrapper).
+    Log {
+        #[serde(skip_serializing_if = "Option::is_none")]
+        stage: Option<String>,
+        line: String,
+    },
+    /// Sent once when all stages complete successfully.
+    Complete {
+        #[serde(rename = "installRoot")]
+        install_root: String,
+        marker: Option<serde_json::Value>,
+    },
+    /// Sent once if the run aborts.
+    Failed {
+        #[serde(skip_serializing_if = "Option::is_none")]
+        stage: Option<String>,
+        error: String,
+    },
+}
+
+impl BootstrapEvent {
+    /// Tauri event name. Single channel for all bootstrap events; the
+    /// `type` tag tells the renderer how to interpret the payload.
+    pub const CHANNEL: &'static str = "bootstrap";
+}

apps/bootstrap-installer/src-tauri/src/install_script.rs

@@ -0,0 +1,273 @@
+//! Resolves and downloads `scripts/install.ps1` (and `install.sh`).
+//!
+//! Resolution order:
+//!   1. Dev shortcut: a sibling repo checkout via $HERMES_SETUP_DEV_REPO_ROOT
+//!      env var. Lets devs iterate without re-publishing the script.
+//!   2. Bundled fallback: if the installer was bundled with a script (e.g.
+//!      tauri's `resource` mechanism), serve from there. Not used today.
+//!   3. Network: download from GitHub raw at a pinned commit or branch.
+//!      Commit pins are immutable; branch pins are HEAD-tracking.
+//!
+//! Mirrors `apps/desktop/electron/bootstrap-runner.cjs`'s `resolveInstallScript`,
+//! but the dev-checkout resolution is driven by an env var rather than the
+//! Electron app's APP_ROOT/../.. trick, because Hermes-Setup.exe is meant
+//! to live OUTSIDE any repo checkout.
+
+use anyhow::{anyhow, Context, Result};
+use std::path::{Path, PathBuf};
+use tokio::io::AsyncWriteExt;
+
+use crate::paths;
+
+/// Identity of the install.ps1 we'll execute. Used by both the manifest
+/// fetch and the per-stage runs.
+#[derive(Debug, Clone)]
+pub struct ResolvedScript {
+    pub path: PathBuf,
+    pub source: ScriptSource,
+    /// Commit pin (40-char SHA) if known. install.ps1's `-Commit` arg is
+    /// what makes the repo stage clone the exact tested SHA.
+    pub commit: Option<String>,
+    pub branch: Option<String>,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum ScriptSource {
+    DevCheckout,
+    Bundled,
+    Cached,
+    Downloaded,
+}
+
+/// What flavor of script (Windows .ps1 vs Unix .sh).
+#[derive(Debug, Clone, Copy)]
+pub enum ScriptKind {
+    Ps1,
+    Sh,
+}
+
+impl ScriptKind {
+    pub fn for_current_os() -> Self {
+        if cfg!(target_os = "windows") {
+            Self::Ps1
+        } else {
+            Self::Sh
+        }
+    }
+
+    fn filename(&self) -> &'static str {
+        match self {
+            Self::Ps1 => "install.ps1",
+            Self::Sh => "install.sh",
+        }
+    }
+}
+
+/// Validates a string looks like a git SHA (7+ hex chars). Mirrors
+/// `STAMP_COMMIT_RE` from bootstrap-runner.cjs.
+fn is_valid_commit(s: &str) -> bool {
+    let len = s.len();
+    (7..=40).contains(&len) && s.chars().all(|c| c.is_ascii_hexdigit())
+}
+
+/// Resolves the install script to use for this run.
+///
+/// `pin` is the commit-or-branch from either Hermes-Setup's build-time
+/// constant (compiled into the installer) or a runtime override.
+pub async fn resolve(
+    kind: ScriptKind,
+    pin: &Pin,
+    emit_log: &impl Fn(&str),
+) -> Result<ResolvedScript> {
+    // 1. Dev shortcut.
+    if let Ok(repo_root) = std::env::var("HERMES_SETUP_DEV_REPO_ROOT") {
+        let candidate = PathBuf::from(repo_root).join("scripts").join(kind.filename());
+        if candidate.exists() {
+            emit_log(&format!(
+                "[bootstrap] dev mode — using local {} at {}",
+                kind.filename(),
+                candidate.display()
+            ));
+            return Ok(ResolvedScript {
+                path: candidate,
+                source: ScriptSource::DevCheckout,
+                commit: pin.commit.clone(),
+                branch: pin.branch.clone(),
+            });
+        }
+    }
+
+    // 2. (Not implemented) bundled fallback.
+
+    // 3. Network. Pin must be a real commit or a branch ref.
+    let commit_or_ref = match (&pin.commit, &pin.branch) {
+        (Some(c), _) if is_valid_commit(c) => c.clone(),
+        (_, Some(b)) if !b.trim().is_empty() => b.clone(),
+        (Some(other), _) => {
+            return Err(anyhow!(
+                "install script pin commit `{other}` is not a valid git SHA"
+            ));
+        }
+        _ => {
+            return Err(anyhow!(
+                "no install-script pin supplied — installer cannot resolve a script source"
+            ));
+        }
+    };
+
+    let cached = cached_path(kind, &commit_or_ref);
+    if cached.exists() {
+        emit_log(&format!(
+            "[bootstrap] using cached {} for {}",
+            kind.filename(),
+            truncate_ref(&commit_or_ref)
+        ));
+        return Ok(ResolvedScript {
+            path: cached,
+            source: ScriptSource::Cached,
+            commit: pin.commit.clone(),
+            branch: pin.branch.clone(),
+        });
+    }
+
+    emit_log(&format!(
+        "[bootstrap] downloading {} for {} from GitHub",
+        kind.filename(),
+        truncate_ref(&commit_or_ref)
+    ));
+
+    download(kind, &commit_or_ref, &cached).await?;
+
+    emit_log(&format!("[bootstrap] cached to {}", cached.display()));
+
+    Ok(ResolvedScript {
+        path: cached,
+        source: ScriptSource::Downloaded,
+        commit: pin.commit.clone(),
+        branch: pin.branch.clone(),
+    })
+}
+
+#[derive(Debug, Clone, Default)]
+pub struct Pin {
+    pub commit: Option<String>,
+    pub branch: Option<String>,
+}
+
+fn cached_path(kind: ScriptKind, commit_or_ref: &str) -> PathBuf {
+    let safe = sanitize_ref(commit_or_ref);
+    let filename = match kind {
+        ScriptKind::Ps1 => format!("install-{safe}.ps1"),
+        ScriptKind::Sh => format!("install-{safe}.sh"),
+    };
+    paths::bootstrap_cache_dir().join(filename)
+}
+
+/// Replace anything that's not [A-Za-z0-9._-] with `_`. Branch refs can
+/// contain `/`, dots, etc.; we want a flat filename.
+fn sanitize_ref(s: &str) -> String {
+    s.chars()
+        .map(|c| {
+            if c.is_ascii_alphanumeric() || c == '.' || c == '-' || c == '_' {
+                c
+            } else {
+                '_'
+            }
+        })
+        .collect()
+}
+
+fn truncate_ref(s: &str) -> &str {
+    if is_valid_commit(s) && s.len() >= 12 {
+        &s[..12]
+    } else {
+        s
+    }
+}
+
+/// Downloads to `dest_path` via reqwest with rustls. Atomically renames
+/// `dest_path.tmp` → `dest_path` so partial writes don't poison the cache.
+async fn download(kind: ScriptKind, commit_or_ref: &str, dest_path: &Path) -> Result<()> {
+    let url = format!(
+        "https://raw.githubusercontent.com/NousResearch/hermes-agent/{}/scripts/{}",
+        commit_or_ref,
+        kind.filename()
+    );
+
+    if let Some(parent) = dest_path.parent() {
+        std::fs::create_dir_all(parent).with_context(|| {
+            format!("creating bootstrap-cache parent dir {}", parent.display())
+        })?;
+    }
+
+    let tmp_path = dest_path.with_extension({
+        let ext = dest_path
+            .extension()
+            .and_then(|s| s.to_str())
+            .unwrap_or("tmp");
+        format!("{ext}.tmp")
+    });
+
+    let response = reqwest::Client::new()
+        .get(&url)
+        .header("User-Agent", "hermes-setup/0.0.1")
+        .send()
+        .await
+        .with_context(|| format!("GET {url}"))?;
+
+    if !response.status().is_success() {
+        return Err(anyhow!(
+            "Failed to download {}: HTTP {} from {}",
+            kind.filename(),
+            response.status(),
+            url
+        ));
+    }
+
+    let bytes = response
+        .bytes()
+        .await
+        .with_context(|| format!("reading body of {url}"))?;
+
+    let mut file = tokio::fs::File::create(&tmp_path)
+        .await
+        .with_context(|| format!("creating temp file {}", tmp_path.display()))?;
+    file.write_all(&bytes)
+        .await
+        .with_context(|| format!("writing temp file {}", tmp_path.display()))?;
+    file.flush().await.context("flushing temp file")?;
+    drop(file);
+
+    tokio::fs::rename(&tmp_path, dest_path)
+        .await
+        .with_context(|| {
+            format!(
+                "renaming {} → {}",
+                tmp_path.display(),
+                dest_path.display()
+            )
+        })?;
+
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn is_valid_commit_accepts_short_and_full_shas() {
+        assert!(is_valid_commit("02d26981d3d4ad50e142399b8476f59ad5953ff0"));
+        assert!(is_valid_commit("02d2698"));
+        assert!(!is_valid_commit("02d269"));
+        assert!(!is_valid_commit("not-a-sha"));
+        assert!(!is_valid_commit(""));
+    }
+
+    #[test]
+    fn sanitize_ref_replaces_slashes() {
+        assert_eq!(sanitize_ref("bb/gui"), "bb_gui");
+        assert_eq!(sanitize_ref("main"), "main");
+        assert_eq!(sanitize_ref("release/1.2.3"), "release_1.2.3");
+    }
+}

apps/bootstrap-installer/src-tauri/src/lib.rs

@@ -0,0 +1,232 @@
+//! Hermes Setup — Tauri entrypoint.
+//!
+//! Spawns a single window pointed at the React frontend (apps/bootstrap-installer/src/).
+//! All install-time work lives in `bootstrap.rs` and is invoked through the Tauri
+//! commands registered at the bottom of `run()`.
+//!
+//! The Windows-subsystem strip lives on the binary crate (src/main.rs), not
+//! here — a crate-level attribute on a lib doesn't propagate to the linker
+//! flags of the executable that consumes it.
+
+mod bootstrap;
+mod events;
+mod install_script;
+mod powershell;
+mod paths;
+mod update;
+
+use std::sync::Arc;
+use tokio::sync::Mutex;
+
+/// How the installer was invoked. Resolved once from the process args in
+/// `run()` and exposed to the frontend via `get_mode` so it can route to the
+/// install flow (first-run onboarding) or the update flow (driven by the
+/// desktop app handing off via `Hermes-Setup.exe --update`).
+///
+/// Bare launch (double-click, first-run) => Install.
+/// `--update` (spawned by the desktop's "Update" button) => Update.
+#[derive(Debug, Clone, Copy, PartialEq, Eq, serde::Serialize)]
+#[serde(rename_all = "lowercase")]
+pub enum AppMode {
+    Install,
+    Update,
+}
+
+impl AppMode {
+    /// Resolve the mode from an argument iterator. Anything containing the
+    /// `--update` flag selects Update; otherwise Install. Kept arg-iterator
+    /// generic (not reading `std::env` directly) so it's unit-testable.
+    pub fn from_args<I, S>(args: I) -> Self
+    where
+        I: IntoIterator<Item = S>,
+        S: AsRef<str>,
+    {
+        for a in args {
+            if a.as_ref() == "--update" {
+                return AppMode::Update;
+            }
+        }
+        AppMode::Install
+    }
+}
+
+/// Returns true when the args request a forced installer UI (repair/reinstall)
+/// via `--reinstall` or `--repair`, which overrides the macOS launcher
+/// fast-path so a broken install can be repaired. Arg-iterator generic so it's
+/// unit-testable, mirroring `AppMode::from_args`. Independent of mode selection:
+/// these flags never flip Install<->Update.
+pub fn force_setup_from_args<I, S>(args: I) -> bool
+where
+    I: IntoIterator<Item = S>,
+    S: AsRef<str>,
+{
+    args.into_iter()
+        .any(|a| a.as_ref() == "--reinstall" || a.as_ref() == "--repair")
+}
+
+/// Process-wide install state, shared across Tauri commands.
+///
+/// The bootstrap is a one-shot, single-tenant process — we only need one
+/// of these per window. `Arc<Mutex<...>>` lets command handlers grab it
+/// without lifetime gymnastics.
+pub struct AppState {
+    pub bootstrap: Mutex<Option<bootstrap::BootstrapHandle>>,
+    /// How this process was launched (install vs update). Immutable for the
+    /// lifetime of the process; read by the `get_mode` command.
+    pub mode: AppMode,
+}
+
+impl AppState {
+    fn new(mode: AppMode) -> Self {
+        Self {
+            bootstrap: Mutex::new(None),
+            mode,
+        }
+    }
+}
+
+/// Frontend → Rust: which flow should the UI render?
+#[tauri::command]
+fn get_mode(state: tauri::State<'_, Arc<AppState>>) -> AppMode {
+    state.mode
+}
+
+#[cfg_attr(mobile, tauri::mobile_entry_point)]
+pub fn run() {
+    // Tracing → bootstrap-installer.log under HERMES_HOME/logs/ so install
+    // failures leave a trail for support. Console output also goes here in
+    // debug builds.
+    let _guard = paths::init_logging();
+
+    let mode = AppMode::from_args(std::env::args().skip(1));
+    // Escape hatch: `--reinstall`/`--repair` forces the installer UI even when
+    // Hermes is already installed, so users can re-run setup to repair a broken
+    // install instead of the launcher fast path silently relaunching the app.
+    let force_setup = force_setup_from_args(std::env::args().skip(1));
+    tracing::info!(?mode, force_setup, "Hermes installer starting");
+
+    tauri::Builder::default()
+        .plugin(tauri_plugin_dialog::init())
+        .plugin(tauri_plugin_opener::init())
+        .plugin(tauri_plugin_process::init())
+        .plugin(tauri_plugin_shell::init())
+        .manage(Arc::new(AppState::new(mode)))
+        .setup(move |app| {
+            use tauri::Manager;
+            // Launcher fast path (macOS only): a bare ("Install") launch when
+            // Hermes is already installed should NOT show the installer or
+            // rebuild — it should just open the app, so the /Applications
+            // "Hermes" doubles as a normal launcher (first run installs, every
+            // later run launches instantly). The window is kept hidden until
+            // here via `"visible": false` so this path never flashes a window.
+            //
+            // Gated to macOS deliberately: on Windows/Linux the installer keeps
+            // its existing behavior (Windows users relaunch via the Start
+            // Menu/Desktop "Hermes" shortcuts that install.ps1 creates, and a
+            // reliable detached relaunch there needs the DETACHED_PROCESS +
+            // startup-grace handling used by launch_hermes_desktop — out of
+            // scope here). So this is a pure no-op on non-macOS.
+            //
+            // `--reinstall`/`--repair` opts out so a broken install can be
+            // repaired by re-running setup instead of launching the bad app.
+            if cfg!(target_os = "macos") && mode == AppMode::Install && !force_setup {
+                let install_root = paths::hermes_home().join("hermes-agent");
+                if bootstrap::hermes_is_installed(&install_root) {
+                    match bootstrap::spawn_installed_desktop(&install_root) {
+                        Ok(()) => {
+                            // Brief grace so the spawned app is registered
+                            // before we exit (mirrors launch_hermes_desktop).
+                            std::thread::sleep(std::time::Duration::from_millis(200));
+                            tracing::info!(
+                                "hermes already installed — relaunched desktop; exiting installer"
+                            );
+                            app.handle().exit(0);
+                            return Ok(());
+                        }
+                        Err(err) => {
+                            tracing::warn!(
+                                ?err,
+                                "relaunch of installed desktop failed; showing installer UI"
+                            );
+                        }
+                    }
+                }
+            }
+            // First run / repair install, or Update mode: reveal the UI.
+            match app.get_webview_window("main") {
+                Some(win) => {
+                    if let Err(err) = win.show() {
+                        tracing::error!(?err, "failed to show main installer window");
+                    }
+                }
+                None => {
+                    tracing::error!("main installer window not found; installer UI will not appear");
+                }
+            }
+            Ok(())
+        })
+        .invoke_handler(tauri::generate_handler![
+            // Mode (install vs update)
+            get_mode,
+            // Bootstrap lifecycle
+            bootstrap::start_bootstrap,
+            bootstrap::cancel_bootstrap,
+            bootstrap::get_bootstrap_status,
+            // Update lifecycle
+            update::start_update,
+            // Hand-off
+            bootstrap::launch_hermes_desktop,
+            // Diagnostics
+            paths::get_log_path,
+            paths::get_hermes_home,
+            paths::open_log_dir,
+        ])
+        .run(tauri::generate_context!())
+        .expect("error while running Hermes Setup");
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{force_setup_from_args, AppMode};
+
+    #[test]
+    fn bare_args_are_install() {
+        assert_eq!(AppMode::from_args(Vec::<String>::new()), AppMode::Install);
+        assert_eq!(AppMode::from_args(["--foo", "bar"]), AppMode::Install);
+    }
+
+    #[test]
+    fn update_flag_selects_update() {
+        assert_eq!(AppMode::from_args(["--update"]), AppMode::Update);
+        assert_eq!(
+            AppMode::from_args(["--something", "--update", "--else"]),
+            AppMode::Update
+        );
+    }
+
+    #[test]
+    fn reinstall_and_repair_flags_force_setup() {
+        assert!(force_setup_from_args(["--reinstall"]));
+        assert!(force_setup_from_args(["--repair"]));
+        assert!(force_setup_from_args(["--foo", "--repair", "--bar"]));
+    }
+
+    #[test]
+    fn bare_or_unrelated_args_do_not_force_setup() {
+        assert!(!force_setup_from_args(Vec::<String>::new()));
+        assert!(!force_setup_from_args(["--foo", "bar"]));
+        // --update must not be mistaken for a force-setup flag.
+        assert!(!force_setup_from_args(["--update"]));
+    }
+
+    #[test]
+    fn force_setup_flags_do_not_affect_mode_selection() {
+        // The repair flags must never flip Install<->Update.
+        assert_eq!(AppMode::from_args(["--reinstall"]), AppMode::Install);
+        assert_eq!(AppMode::from_args(["--repair"]), AppMode::Install);
+        assert_eq!(
+            AppMode::from_args(["--update", "--reinstall"]),
+            AppMode::Update
+        );
+    }
+}

apps/bootstrap-installer/src-tauri/src/main.rs

@@ -0,0 +1,19 @@
+// Hermes Setup — process entrypoint. All logic lives in lib.rs so it can
+// be unit-tested as a library; this file just calls into it.
+//
+// The windows_subsystem attribute MUST live here on the binary crate
+// (not lib.rs) — placing it on the lib was the bug that left a stray
+// cmd window behind Hermes-Setup.exe on release builds.
+//
+// `windows_subsystem = "windows"` strips the console allocation that
+// the default `windows_subsystem = "console"` would do, so double-clicking
+// the .exe gives you ONLY the Tauri window.
+//
+// debug_assertions guard: dev builds keep the console so tracing output
+// is visible during `cargo tauri dev`.
+
+#![cfg_attr(not(debug_assertions), windows_subsystem = "windows")]
+
+fn main() {
+    hermes_bootstrap_lib::run()
+}

apps/bootstrap-installer/src-tauri/src/paths.rs

@@ -0,0 +1,168 @@
+//! Filesystem paths + logging setup.
+//!
+//! Mirrors `hermes_constants.get_hermes_home()` from the Python CLI:
+//!   Windows: %LOCALAPPDATA%\hermes
+//!   macOS:   ~/.hermes
+//!   Linux:   ~/.hermes  (override via $HERMES_HOME)
+//!
+//! NOTE (macOS): Python's get_hermes_home(), scripts/install.sh, and the
+//! Electron desktop's resolveHermesHome() ALL use ~/.hermes on macOS — there
+//! is no ~/Library/Application Support branch anywhere else. An earlier
+//! version of this file used Application Support, which drifted from every
+//! other component: the installer wrote the install to one dir and the
+//! desktop looked for it in another, so first launch never found the backend.
+//!
+//! IMPORTANT: this must match exactly. Drift here means install.ps1
+//! writes to one place and the installer reads from another, breaking
+//! the bootstrap-complete check.
+
+use std::path::{Path, PathBuf};
+use tracing_appender::non_blocking::WorkerGuard;
+
+/// Returns the canonical Hermes home directory, respecting $HERMES_HOME if set.
+pub fn hermes_home() -> PathBuf {
+    if let Ok(override_path) = std::env::var("HERMES_HOME") {
+        if !override_path.trim().is_empty() {
+            return PathBuf::from(override_path);
+        }
+    }
+
+    #[cfg(target_os = "windows")]
+    {
+        // %LOCALAPPDATA%\hermes — matches scripts/install.ps1's $HermesHome.
+        if let Some(local_app_data) = dirs::data_local_dir() {
+            return local_app_data.join("hermes");
+        }
+    }
+
+    // macOS + Linux + fallback: ~/.hermes (matches Python get_hermes_home(),
+    // install.sh, and the Electron desktop's resolveHermesHome()).
+    if let Some(home) = dirs::home_dir() {
+        return home.join(".hermes");
+    }
+
+    // Last resort — current dir, almost certainly wrong but at least
+    // doesn't panic.
+    PathBuf::from(".hermes")
+}
+
+pub fn log_dir() -> PathBuf {
+    hermes_home().join("logs")
+}
+
+pub fn log_path() -> PathBuf {
+    log_dir().join("bootstrap-installer.log")
+}
+
+pub fn bootstrap_cache_dir() -> PathBuf {
+    hermes_home().join("bootstrap-cache")
+}
+
+/// Stable location the installer copies itself to after a successful install.
+/// The desktop app re-invokes this with `--update`, and the start-menu /
+/// desktop shortcuts can point users back to it. Lives directly under
+/// HERMES_HOME so it survives repo checkout deletion (unlike anything under
+/// hermes-agent/).
+///
+/// On Windows this is `%LOCALAPPDATA%\hermes\hermes-setup.exe`; on other
+/// platforms the extension differs but the directory is the same.
+pub fn installer_dest() -> PathBuf {
+    let name = if cfg!(target_os = "windows") {
+        "hermes-setup.exe"
+    } else {
+        "hermes-setup"
+    };
+    hermes_home().join(name)
+}
+
+/// Copy the currently-running installer binary to `installer_dest()` so it's
+/// available for future `--update` runs and shortcut launches.
+///
+/// No-ops (returns Ok) when the running exe is ALREADY the destination — which
+/// is exactly the case during an `--update` run (the desktop launched us FROM
+/// that path), where copying onto ourselves would be a Windows sharing
+/// violation. Best-effort: a failure here must not fail the install, so the
+/// caller logs and continues.
+pub fn copy_self_to_hermes_home() -> std::io::Result<()> {
+    let src = std::env::current_exe()?;
+    let dest = installer_dest();
+
+    // Skip if we're already running from the destination (update re-invocation
+    // or a prior copy). canonicalize both so symlinks / 8.3 short paths / case
+    // differences don't trick us into a self-copy.
+    let same = match (src.canonicalize(), dest.canonicalize()) {
+        (Ok(a), Ok(b)) => a == b,
+        _ => src == dest,
+    };
+    if same {
+        tracing::info!(?dest, "installer already at destination; skipping self-copy");
+        return Ok(());
+    }
+
+    if let Some(parent) = dest.parent() {
+        std::fs::create_dir_all(parent)?;
+    }
+    std::fs::copy(&src, &dest)?;
+    tracing::info!(?src, ?dest, "copied installer to HERMES_HOME");
+    Ok(())
+}
+
+/// Where install.ps1 writes the bootstrap-complete marker (existence-only file
+/// the Electron app also checks). Per main.cjs:
+///   const BOOTSTRAP_COMPLETE_MARKER = path.join(ACTIVE_HERMES_ROOT, '.hermes-bootstrap-complete')
+/// We don't always know ACTIVE_HERMES_ROOT until install.ps1 reports it, so
+/// this is a probe helper, not a definitive path.
+pub fn likely_bootstrap_marker(install_root: &Path) -> PathBuf {
+    install_root.join(".hermes-bootstrap-complete")
+}
+
+/// Initializes tracing to bootstrap-installer.log under HERMES_HOME/logs/.
+/// Returns a guard that flushes the appender on drop — keep it alive for
+/// the lifetime of the process.
+pub fn init_logging() -> Option<WorkerGuard> {
+    let dir = log_dir();
+    if let Err(err) = std::fs::create_dir_all(&dir) {
+        // No log dir → log to stderr only. Don't panic; the installer
+        // should still be usable on an exotic filesystem.
+        eprintln!("[hermes-setup] could not create log dir {dir:?}: {err}");
+        return None;
+    }
+
+    let file_appender = tracing_appender::rolling::never(&dir, "bootstrap-installer.log");
+    let (non_blocking, guard) = tracing_appender::non_blocking(file_appender);
+
+    let env_filter = tracing_subscriber::EnvFilter::try_from_env("HERMES_BOOTSTRAP_LOG")
+        .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info"));
+
+    tracing_subscriber::fmt()
+        .with_env_filter(env_filter)
+        .with_writer(non_blocking)
+        .with_ansi(false)
+        .with_target(true)
+        .init();
+
+    Some(guard)
+}
+
+// ---------------------------------------------------------------------------
+// Tauri commands
+// ---------------------------------------------------------------------------
+
+#[tauri::command]
+pub fn get_log_path() -> String {
+    log_path().to_string_lossy().into_owned()
+}
+
+#[tauri::command]
+pub fn get_hermes_home() -> String {
+    hermes_home().to_string_lossy().into_owned()
+}
+
+#[tauri::command]
+pub fn open_log_dir(app: tauri::AppHandle) -> Result<(), String> {
+    use tauri_plugin_opener::OpenerExt;
+    let path = log_dir();
+    app.opener()
+        .open_path(path.to_string_lossy(), None::<&str>)
+        .map_err(|e| e.to_string())
+}

apps/bootstrap-installer/src-tauri/src/powershell.rs

@@ -0,0 +1,267 @@
+//! Drives PowerShell (Windows) or bash (Unix) for install.ps1 / install.sh.
+//!
+//! Port of `spawnPowerShell` from bootstrap-runner.cjs, with the same
+//! line-buffered stdout/stderr streaming + cancellation semantics.
+//!
+//! On Windows we pass `-NoProfile -ExecutionPolicy Bypass -File <script>`.
+//! On Unix we shell out to `bash <script>` since install.sh expects bash.
+
+use anyhow::{Context, Result};
+use std::path::Path;
+use std::process::Stdio;
+use tokio::io::{AsyncBufReadExt, BufReader};
+use tokio::process::{Child, Command};
+use tokio::sync::mpsc;
+
+/// Hooks the caller installs to receive output.
+pub struct StreamSink {
+    pub on_stdout_line: Box<dyn Fn(&str) + Send + Sync>,
+    pub on_stderr_line: Box<dyn Fn(&str) + Send + Sync>,
+}
+
+/// Outcome of a script invocation. Mirrors bootstrap-runner.cjs's
+/// `{stdout, stderr, code, signal, killed}` shape.
+#[derive(Debug)]
+pub struct ScriptResult {
+    pub stdout: String,
+    pub stderr: String,
+    pub exit_code: Option<i32>,
+    pub killed: bool,
+}
+
+/// Cancellation signal — `cancel_tx.send(()).await` aborts the running script.
+pub type CancelRx = mpsc::Receiver<()>;
+
+/// Spawns install.ps1 / install.sh with the given args and streams output.
+///
+/// `hermes_home_override` propagates to the child as $HERMES_HOME so the
+/// install script writes to the same directory the installer is reading from.
+pub async fn run_script(
+    script_path: &Path,
+    args: &[String],
+    sink: StreamSink,
+    hermes_home_override: Option<&str>,
+    mut cancel_rx: Option<CancelRx>,
+) -> Result<ScriptResult> {
+    let mut cmd = build_command(script_path, args);
+
+    if let Some(home) = hermes_home_override {
+        cmd.env("HERMES_HOME", home);
+    }
+
+    cmd.stdin(Stdio::null())
+        .stdout(Stdio::piped())
+        .stderr(Stdio::piped());
+
+    // On Windows, avoid spawning a flashing cmd window when we're hosted
+    // inside a GUI process. Tauri's main window is already created, so
+    // the side-effect console for the child is unwanted.
+    #[cfg(target_os = "windows")]
+    {
+        // CREATE_NO_WINDOW = 0x08000000
+        cmd.creation_flags(0x0800_0000);
+    }
+
+    let mut child: Child = cmd
+        .spawn()
+        .with_context(|| format!("spawning {}", script_path.display()))?;
+
+    let stdout = child.stdout.take().expect("stdout was piped");
+    let stderr = child.stderr.take().expect("stderr was piped");
+
+    let mut stdout_reader = BufReader::new(stdout).lines();
+    let mut stderr_reader = BufReader::new(stderr).lines();
+
+    let mut combined_stdout = String::new();
+    let mut combined_stderr = String::new();
+    let mut killed = false;
+
+    // Loop: poll stdout, stderr, cancel, and child exit concurrently.
+    loop {
+        tokio::select! {
+            line = stdout_reader.next_line() => {
+                match line {
+                    Ok(Some(l)) => {
+                        (sink.on_stdout_line)(&l);
+                        combined_stdout.push_str(&l);
+                        combined_stdout.push('\n');
+                    }
+                    Ok(None) => {
+                        // EOF on stdout — wait for stderr + exit.
+                        break;
+                    }
+                    Err(e) => {
+                        tracing::warn!("stdout read error: {e}");
+                        break;
+                    }
+                }
+            }
+            line = stderr_reader.next_line() => {
+                match line {
+                    Ok(Some(l)) => {
+                        (sink.on_stderr_line)(&l);
+                        combined_stderr.push_str(&l);
+                        combined_stderr.push('\n');
+                    }
+                    Ok(None) => {
+                        // stderr EOF — keep draining stdout.
+                    }
+                    Err(e) => {
+                        tracing::warn!("stderr read error: {e}");
+                    }
+                }
+            }
+            _ = recv_cancel(&mut cancel_rx) => {
+                tracing::warn!("cancellation received — killing child");
+                killed = true;
+                // best-effort kill; don't propagate errors
+                let _ = child.start_kill();
+                break;
+            }
+        }
+    }
+
+    // Drain remaining lines after the loop exited.
+    while let Ok(Some(l)) = stdout_reader.next_line().await {
+        (sink.on_stdout_line)(&l);
+        combined_stdout.push_str(&l);
+        combined_stdout.push('\n');
+    }
+    while let Ok(Some(l)) = stderr_reader.next_line().await {
+        (sink.on_stderr_line)(&l);
+        combined_stderr.push_str(&l);
+        combined_stderr.push('\n');
+    }
+
+    let status = child
+        .wait()
+        .await
+        .context("waiting for install script to exit")?;
+
+    Ok(ScriptResult {
+        stdout: combined_stdout,
+        stderr: combined_stderr,
+        exit_code: status.code(),
+        killed,
+    })
+}
+
+async fn recv_cancel(rx: &mut Option<CancelRx>) {
+    match rx {
+        Some(r) => {
+            let _ = r.recv().await;
+        }
+        None => std::future::pending::<()>().await,
+    }
+}
+
+#[cfg(target_os = "windows")]
+fn build_command(script_path: &Path, args: &[String]) -> Command {
+    // We want PowerShell 5.1 / 7. install.ps1 uses 5.1-safe syntax everywhere.
+    // Prefer `powershell.exe` (5.1 baseline, present on every Windows since 7)
+    // over `pwsh.exe` (7+, may not be present).
+    let mut cmd = Command::new("powershell.exe");
+    cmd.arg("-NoProfile");
+    cmd.arg("-ExecutionPolicy").arg("Bypass");
+    cmd.arg("-File").arg(script_path);
+    for a in args {
+        cmd.arg(a);
+    }
+    cmd
+}
+
+#[cfg(not(target_os = "windows"))]
+fn build_command(script_path: &Path, args: &[String]) -> Command {
+    // install.sh expects bash. /bin/bash is fine on macOS (Apple still
+    // ships an old 3.2 bash; install.sh is written to that baseline).
+    let mut cmd = Command::new("bash");
+    cmd.arg(script_path);
+    for a in args {
+        cmd.arg(a);
+    }
+    cmd
+}
+
+/// Parses the LAST line of stdout that looks like a JSON object matching
+/// the install.ps1 stage-result contract: `{ok: bool, stage: string, ...}`.
+///
+/// Mirrors `parseStageResult` from bootstrap-runner.cjs. install.ps1 may
+/// print info/banner lines before the result frame; we scan from the end.
+pub fn parse_stage_result(stdout: &str) -> Option<crate::events::StageResultPayload> {
+    for line in stdout.lines().rev() {
+        let trimmed = line.trim();
+        if trimmed.is_empty() {
+            continue;
+        }
+        if let Ok(value) = serde_json::from_str::<serde_json::Value>(trimmed) {
+            if value.get("ok").and_then(|v| v.as_bool()).is_some()
+                && value.get("stage").and_then(|v| v.as_str()).is_some()
+            {
+                if let Ok(parsed) =
+                    serde_json::from_value::<crate::events::StageResultPayload>(value)
+                {
+                    return Some(parsed);
+                }
+            }
+        }
+    }
+    None
+}
+
+/// Same logic but for the `-Manifest` payload (the LAST line with a `stages`
+/// array). Returns the parsed manifest.
+pub fn parse_manifest(stdout: &str) -> Option<crate::events::Manifest> {
+    for line in stdout.lines().rev() {
+        let trimmed = line.trim();
+        if trimmed.is_empty() {
+            continue;
+        }
+        if let Ok(value) = serde_json::from_str::<serde_json::Value>(trimmed) {
+            if value.get("stages").and_then(|v| v.as_array()).is_some() {
+                if let Ok(parsed) = serde_json::from_value::<crate::events::Manifest>(value) {
+                    return Some(parsed);
+                }
+            }
+        }
+    }
+    None
+}
+
+#[cfg(target_os = "windows")]
+use std::os::windows::process::CommandExt;
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn parse_stage_result_picks_last_json_line() {
+        let stdout = r#"
+[bootstrap] some info
+{"ok": false, "stage": "venv", "reason": "bad python"}
+{"ok": true, "stage": "venv"}
+final non-json banner
+"#;
+        let result = parse_stage_result(stdout).unwrap();
+        assert_eq!(result.stage, "venv");
+        assert!(result.ok);
+    }
+
+    #[test]
+    fn parse_manifest_finds_stages_array() {
+        let stdout = r#"
+info line
+{"stages": [{"name": "uv", "title": "uv", "category": "prereqs", "needs_user_input": false}], "protocol_version": 1}
+"#;
+        let m = parse_manifest(stdout).unwrap();
+        assert_eq!(m.stages.len(), 1);
+        assert_eq!(m.stages[0].name, "uv");
+        assert_eq!(m.protocol_version, Some(1));
+    }
+
+    #[test]
+    fn parse_returns_none_when_no_match() {
+        assert!(parse_stage_result("just banner\n").is_none());
+        assert!(parse_manifest("just banner\n").is_none());
+    }
+}

apps/bootstrap-installer/src-tauri/src/update.rs

@@ -0,0 +1,462 @@
+//! Update orchestration.
+//!
+//! Driven when the installer is launched as `Hermes-Setup.exe --update` (see
+//! `AppMode` in lib.rs). The desktop app hands off to us — it exits, then we:
+//!
+//!   1. wait for the old Hermes desktop process to fully exit (so the venv
+//!      shim is free; otherwise `hermes update` aborts with exit code 2),
+//!   2. run `hermes update --yes --gateway` (Python/repo update; this does NOT
+//!      rebuild apps/desktop by design — see cmd_update in hermes_cli/main.py),
+//!   3. run `hermes desktop --build-only` (the rebuild step update skips),
+//!   4. launch the freshly-built desktop (reuses bootstrap::launch logic).
+//!
+//! We reuse the `BootstrapEvent` channel + the existing progress UI by
+//! emitting a synthetic two-stage manifest ("update", "rebuild"). To the
+//! frontend an update looks like a short bootstrap.
+//!
+//! Cross-platform note: `hermes update` already handles macOS/Linux (git/pip).
+//! The only OS-specific bits here are the venv shim path (resolve_hermes) and
+//! the no-window creation flag — both already cfg-gated. Keep new logic
+//! OS-agnostic so the mac/linux port stays "fill in the paths".
+
+use std::path::{Path, PathBuf};
+use std::process::Stdio;
+use std::time::{Duration, Instant};
+
+use anyhow::{anyhow, Result};
+use tauri::{AppHandle, Emitter};
+use tokio::io::{AsyncBufReadExt, BufReader};
+use tokio::process::Command;
+
+use crate::events::{BootstrapEvent, StageInfo, StageState};
+
+/// `hermes update` exit code meaning "another hermes process is holding the
+/// venv shim open / dirty precondition" — see _cmd_update_impl in
+/// hermes_cli/main.py (sys.exit(2)). We surface a targeted message for this.
+const UPDATE_EXIT_CONCURRENT: i32 = 2;
+
+/// How long to wait for the old desktop process to release the venv shim
+/// before giving up and letting `hermes update`'s own guard decide.
+const DESKTOP_EXIT_WAIT: Duration = Duration::from_secs(20);
+const DESKTOP_EXIT_POLL: Duration = Duration::from_millis(500);
+
+/// Frontend → Rust: kick off the update flow. Mirrors `start_bootstrap`'s
+/// fire-and-forget shape; progress arrives on the `bootstrap` event channel.
+#[tauri::command]
+pub async fn start_update(app: AppHandle) -> Result<(), String> {
+    tokio::spawn(async move {
+        if let Err(err) = run_update(app.clone()).await {
+            // run_update already emits a Failed event on the paths that matter;
+            // this catches anything that escaped. Emit defensively.
+            emit(
+                &app,
+                BootstrapEvent::Failed {
+                    stage: None,
+                    error: format!("{err:#}"),
+                },
+            );
+        }
+    });
+    Ok(())
+}
+
+async fn run_update(app: AppHandle) -> Result<()> {
+    let hermes_home = crate::paths::hermes_home();
+    let install_root = hermes_home.join("hermes-agent");
+
+    let hermes = resolve_hermes(&install_root).ok_or_else(|| {
+        let msg = format!(
+            "Could not find the hermes CLI under {}. Is Hermes installed? \
+             Re-run the installer to repair the install.",
+            install_root.display()
+        );
+        emit(
+            &app,
+            BootstrapEvent::Failed {
+                stage: None,
+                error: msg.clone(),
+            },
+        );
+        anyhow!(msg)
+    })?;
+
+    // Synthetic manifest so the existing progress UI renders our two stages.
+    emit(
+        &app,
+        BootstrapEvent::Manifest {
+            stages: vec![
+                stage_info("update", "Updating Hermes"),
+                stage_info("rebuild", "Rebuilding the desktop app"),
+            ],
+            protocol_version: None,
+        },
+    );
+
+    // ---- pre-step: wait for the old desktop to die -----------------------
+    // The desktop exec'd us then called app.exit(), but process teardown is
+    // async on Windows. If it still holds the venv shim, `hermes update`
+    // aborts with exit 2. Give it a bounded window to clear.
+    wait_for_venv_free(&install_root, &app).await;
+
+    // ---- stage 1: hermes update -----------------------------------------
+    // Pass --branch so `hermes update` targets the branch this installer was
+    // built/pinned against (BUILD_PIN_BRANCH), NOT its built-in default of
+    // `main`. The install was a detached-HEAD checkout of a specific commit;
+    // without --branch, `hermes update` switches the checkout to `main` (a
+    // divergent branch that may not even have the desktop CLI command), then
+    // reports "already up to date" against the wrong branch. The desktop
+    // detected the update against this same branch, so we must update against
+    // it too.
+    let pin_branch = option_env_string("BUILD_PIN_BRANCH");
+    let mut update_args: Vec<&str> = vec!["update", "--yes", "--gateway"];
+    if let Some(b) = pin_branch.as_deref() {
+        update_args.push("--branch");
+        update_args.push(b);
+    }
+
+    emit_stage(&app, "update", StageState::Running, None, None);
+    let started = Instant::now();
+    let update = run_streamed(
+        &app,
+        &hermes,
+        &update_args,
+        &install_root,
+        Some("update"),
+    )
+    .await?;
+    let update_ms = started.elapsed().as_millis() as u64;
+
+    match update.exit_code {
+        Some(0) => {
+            emit_stage(&app, "update", StageState::Succeeded, Some(update_ms), None);
+        }
+        Some(code) if code == UPDATE_EXIT_CONCURRENT => {
+            let msg = "Hermes is still running. Close all Hermes windows and try \
+                       the update again."
+                .to_string();
+            emit_stage(
+                &app,
+                "update",
+                StageState::Failed,
+                Some(update_ms),
+                Some(msg.clone()),
+            );
+            emit(
+                &app,
+                BootstrapEvent::Failed {
+                    stage: Some("update".into()),
+                    error: msg.clone(),
+                },
+            );
+            return Err(anyhow!(msg));
+        }
+        other => {
+            let msg = format!(
+                "hermes update failed (exit {:?}). See {} for details.",
+                other,
+                crate::paths::hermes_home()
+                    .join("logs")
+                    .join("update.log")
+                    .display()
+            );
+            emit_stage(
+                &app,
+                "update",
+                StageState::Failed,
+                Some(update_ms),
+                Some(msg.clone()),
+            );
+            emit(
+                &app,
+                BootstrapEvent::Failed {
+                    stage: Some("update".into()),
+                    error: msg.clone(),
+                },
+            );
+            return Err(anyhow!(msg));
+        }
+    }
+
+    // ---- stage 2: hermes desktop --build-only ----------------------------
+    // `hermes update` deliberately does NOT build apps/desktop (it installs
+    // repo-root deps with --workspaces=false). This is the rebuild it skips.
+    emit_stage(&app, "rebuild", StageState::Running, None, None);
+    let started = Instant::now();
+    let rebuild = run_streamed(
+        &app,
+        &hermes,
+        &["desktop", "--build-only"],
+        &install_root,
+        Some("rebuild"),
+    )
+    .await?;
+    let rebuild_ms = started.elapsed().as_millis() as u64;
+
+    if rebuild.exit_code != Some(0) {
+        let msg = format!(
+            "Rebuilding the desktop app failed (exit {:?}). The update was \
+             applied but the app could not be rebuilt; run `hermes desktop` \
+             from a terminal to see the error.",
+            rebuild.exit_code
+        );
+        emit_stage(
+            &app,
+            "rebuild",
+            StageState::Failed,
+            Some(rebuild_ms),
+            Some(msg.clone()),
+        );
+        emit(
+            &app,
+            BootstrapEvent::Failed {
+                stage: Some("rebuild".into()),
+                error: msg.clone(),
+            },
+        );
+        return Err(anyhow!(msg));
+    }
+    emit_stage(&app, "rebuild", StageState::Succeeded, Some(rebuild_ms), None);
+
+    // ---- done: signal complete, then launch the fresh desktop ------------
+    emit(
+        &app,
+        BootstrapEvent::Complete {
+            install_root: install_root.to_string_lossy().into_owned(),
+            marker: None,
+        },
+    );
+
+    // Reuse the same detached-launch + app.exit(0) used post-install.
+    if let Err(err) =
+        crate::bootstrap::launch_hermes_desktop(app.clone(), install_root.to_string_lossy().into_owned())
+            .await
+    {
+        // Launch failed: don't hard-fail the update (it succeeded); surface a
+        // log line so the success screen can still tell the user to launch
+        // manually.
+        emit_log(
+            &app,
+            None,
+            &format!("[update] could not auto-launch desktop: {err}. Launch Hermes manually."),
+        );
+    }
+
+    Ok(())
+}
+
+/// Poll until the venv shim is no longer locked (Windows) or a bounded timeout
+/// elapses. On non-Windows this is a short fixed grace since file locking
+/// isn't the failure mode there.
+async fn wait_for_venv_free(install_root: &Path, app: &AppHandle) {
+    let shim = venv_hermes(install_root);
+    let deadline = Instant::now() + DESKTOP_EXIT_WAIT;
+
+    emit_log(app, Some("update"), "[update] waiting for Hermes to exit…");
+
+    loop {
+        if !is_locked(&shim) {
+            return;
+        }
+        if Instant::now() >= deadline {
+            emit_log(
+                app,
+                Some("update"),
+                "[update] timed out waiting for Hermes to exit; proceeding anyway",
+            );
+            return;
+        }
+        tokio::time::sleep(DESKTOP_EXIT_POLL).await;
+    }
+}
+
+/// Best-effort lock probe: try to open the file for read+write. On Windows an
+/// exclusively-held running .exe refuses the open with a sharing violation.
+/// On Unix this almost always succeeds (no mandatory locking), which is fine —
+/// the venv-shim contention is a Windows-only problem.
+fn is_locked(path: &Path) -> bool {
+    if !path.exists() {
+        return false;
+    }
+    match std::fs::OpenOptions::new().read(true).write(true).open(path) {
+        Ok(_) => false,
+        Err(_) => true,
+    }
+}
+
+/// Spawn `hermes <args>` from `cwd`, stream stdout/stderr as Log events on the
+/// bootstrap channel, and return the exit code. Mirrors powershell::run_script
+/// but for an arbitrary command (no install.ps1 -File wrapping).
+async fn run_streamed(
+    app: &AppHandle,
+    program: &Path,
+    args: &[&str],
+    cwd: &Path,
+    stage: Option<&str>,
+) -> Result<CmdResult> {
+    let mut cmd = Command::new(program);
+    cmd.args(args)
+        .current_dir(cwd)
+        .stdin(Stdio::null())
+        .stdout(Stdio::piped())
+        .stderr(Stdio::piped());
+
+    #[cfg(target_os = "windows")]
+    {
+        use std::os::windows::process::CommandExt;
+        // CREATE_NO_WINDOW = 0x08000000 — no flashing console behind the GUI.
+        cmd.creation_flags(0x0800_0000);
+    }
+
+    let mut child = cmd
+        .spawn()
+        .map_err(|e| anyhow!("spawning {} {:?}: {e}", program.display(), args))?;
+
+    let stdout = child.stdout.take().expect("stdout piped");
+    let stderr = child.stderr.take().expect("stderr piped");
+    let mut out = BufReader::new(stdout).lines();
+    let mut err = BufReader::new(stderr).lines();
+
+    let stage_owned = stage.map(|s| s.to_string());
+    loop {
+        tokio::select! {
+            line = out.next_line() => match line {
+                Ok(Some(l)) => emit_log(app, stage_owned.as_deref(), &l),
+                Ok(None) => break,
+                Err(e) => { tracing::warn!("stdout read error: {e}"); break; }
+            },
+            line = err.next_line() => match line {
+                Ok(Some(l)) => emit_log(app, stage_owned.as_deref(), &format!("stderr: {l}")),
+                Ok(None) => {}
+                Err(e) => { tracing::warn!("stderr read error: {e}"); }
+            },
+        }
+    }
+    while let Ok(Some(l)) = out.next_line().await {
+        emit_log(app, stage_owned.as_deref(), &l);
+    }
+    while let Ok(Some(l)) = err.next_line().await {
+        emit_log(app, stage_owned.as_deref(), &format!("stderr: {l}"));
+    }
+
+    let status = child.wait().await.map_err(|e| anyhow!("waiting for child: {e}"))?;
+    Ok(CmdResult {
+        exit_code: status.code(),
+    })
+}
+
+struct CmdResult {
+    exit_code: Option<i32>,
+}
+
+/// Path to the venv hermes shim under an install root, regardless of existence.
+fn venv_hermes(install_root: &Path) -> PathBuf {
+    if cfg!(target_os = "windows") {
+        install_root.join("venv").join("Scripts").join("hermes.exe")
+    } else {
+        install_root.join("venv").join("bin").join("hermes")
+    }
+}
+
+/// Resolve the hermes CLI to drive. Prefer the venv shim in the install we
+/// just updated; fall back to `hermes` on PATH.
+fn resolve_hermes(install_root: &Path) -> Option<PathBuf> {
+    let shim = venv_hermes(install_root);
+    if shim.exists() {
+        return Some(shim);
+    }
+    // PATH fallback. which-style probe via env, kept dependency-free.
+    let exe = if cfg!(target_os = "windows") { "hermes.exe" } else { "hermes" };
+    if let Ok(path) = std::env::var("PATH") {
+        let sep = if cfg!(target_os = "windows") { ';' } else { ':' };
+        for dir in path.split(sep) {
+            let cand = Path::new(dir).join(exe);
+            if cand.exists() {
+                return Some(cand);
+            }
+        }
+    }
+    None
+}
+
+// ---------------------------------------------------------------------------
+// Event helpers — keep emit shape identical to bootstrap.rs so the UI is reused
+// ---------------------------------------------------------------------------
+
+fn stage_info(name: &str, title: &str) -> StageInfo {
+    StageInfo {
+        name: name.to_string(),
+        title: title.to_string(),
+        category: "update".to_string(),
+        needs_user_input: false,
+    }
+}
+
+// option_env! only accepts string literals, so the build-time pins are read
+// by their literal names here. Mirrors bootstrap.rs's helper of the same name
+// (kept local rather than shared because option_env! can't be parameterized).
+fn option_env_string(key: &str) -> Option<String> {
+    let val = match key {
+        "BUILD_PIN_COMMIT" => option_env!("BUILD_PIN_COMMIT"),
+        "BUILD_PIN_BRANCH" => option_env!("BUILD_PIN_BRANCH"),
+        _ => None,
+    };
+    val.map(|s| s.to_string())
+}
+
+fn emit(app: &AppHandle, event: BootstrapEvent) {
+    if let Err(e) = app.emit(BootstrapEvent::CHANNEL, &event) {
+        tracing::warn!(?e, "failed to emit update event");
+    }
+}
+
+fn emit_stage(
+    app: &AppHandle,
+    name: &str,
+    state: StageState,
+    duration_ms: Option<u64>,
+    error: Option<String>,
+) {
+    tracing::info!(stage = %name, ?state, ?duration_ms, ?error, "update stage");
+    emit(
+        app,
+        BootstrapEvent::Stage {
+            name: name.to_string(),
+            state,
+            duration_ms,
+            result: None,
+            error,
+        },
+    );
+}
+
+fn emit_log(app: &AppHandle, stage: Option<&str>, line: &str) {
+    match stage {
+        Some(s) => tracing::info!(target: "bootstrap.log", stage = %s, "{line}"),
+        None => tracing::info!(target: "bootstrap.log", "{line}"),
+    }
+    emit(
+        app,
+        BootstrapEvent::Log {
+            stage: stage.map(|s| s.to_string()),
+            line: line.to_string(),
+        },
+    );
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn venv_hermes_is_under_install_root() {
+        let root = Path::new("/x/hermes-agent");
+        let shim = venv_hermes(root);
+        assert!(shim.starts_with(root));
+        assert!(shim.to_string_lossy().contains("venv"));
+    }
+
+    #[test]
+    fn missing_file_is_not_locked() {
+        assert!(!is_locked(Path::new("/nonexistent/does/not/exist/xyz")));
+    }
+}

apps/bootstrap-installer/src-tauri/tauri.conf.json

@@ -0,0 +1,68 @@
+{
+  "$schema": "https://schema.tauri.app/config/2",
+  "productName": "Hermes",
+  "version": "0.0.1",
+  "identifier": "com.nousresearch.hermes.setup",
+  "build": {
+    "beforeDevCommand": "npm run dev",
+    "devUrl": "http://127.0.0.1:5175",
+    "beforeBuildCommand": "npm run build",
+    "frontendDist": "../dist"
+  },
+  "app": {
+    "windows": [
+      {
+        "label": "main",
+        "title": "Hermes",
+        "width": 880,
+        "height": 620,
+        "minWidth": 720,
+        "minHeight": 520,
+        "resizable": true,
+        "fullscreen": false,
+        "decorations": true,
+        "transparent": false,
+        "center": true,
+        "visible": false
+      }
+    ],
+    "security": {
+      "csp": "default-src 'self'; img-src 'self' data:; style-src 'self' 'unsafe-inline'; script-src 'self'; font-src 'self' data:; connect-src 'self' ipc: http://ipc.localhost"
+    },
+    "withGlobalTauri": false
+  },
+  "bundle": {
+    "active": true,
+    "category": "DeveloperTool",
+    "shortDescription": "Hermes",
+    "longDescription": "Installs Hermes Agent on your machine. Drives scripts/install.ps1 (Windows) and scripts/install.sh (macOS/Linux).",
+    "publisher": "Nous Research",
+    "copyright": "Copyright © 2026 Nous Research",
+    "targets": [
+      "app",
+      "dmg",
+      "appimage"
+    ],
+    "icon": [
+      "icons/32x32.png",
+      "icons/128x128.png",
+      "icons/128x128@2x.png",
+      "icons/icon.icns",
+      "icons/icon.ico"
+    ],
+    "windows": {
+      "webviewInstallMode": {
+        "type": "embedBootstrapper"
+      }
+    },
+    "macOS": {
+      "minimumSystemVersion": "11.0",
+      "hardenedRuntime": true
+    }
+  },
+  "plugins": {
+    "shell": {
+      "open": true
+    }
+  }
+}

apps/bootstrap-installer/src/app.tsx

@@ -0,0 +1,35 @@
+import { useStore } from '@nanostores/react'
+import { useEffect } from 'react'
+import { $route, $bootstrap, initialize } from './store'
+import Welcome from './routes/welcome'
+import Progress from './routes/progress'
+import Success from './routes/success'
+import Failure from './routes/failure'
+
+/*
+ * App shell — Hermes Setup.
+ *
+ * No header chrome (the OS title bar already says "Hermes Setup"; an
+ * in-window repeat of the H mark + words was redundant slop).
+ *
+ * Route state lives in a single $route atom — 4 screens, no react-router.
+ */
+export default function App() {
+  const route = useStore($route)
+  const bootstrap = useStore($bootstrap)
+
+  useEffect(() => {
+    void initialize()
+  }, [])
+
+  return (
+    <div className="relative flex h-full flex-col overflow-hidden bg-background text-foreground">
+      <main className="relative z-10 flex flex-1 flex-col overflow-hidden">
+        {route === 'welcome' && <Welcome />}
+        {route === 'progress' && <Progress bootstrap={bootstrap} />}
+        {route === 'success' && <Success />}
+        {route === 'failure' && <Failure bootstrap={bootstrap} />}
+      </main>
+    </div>
+  )
+}

apps/bootstrap-installer/src/components/button.tsx

@@ -0,0 +1,80 @@
+import { cva, type VariantProps } from 'class-variance-authority'
+import { Slot } from 'radix-ui'
+import * as React from 'react'
+
+import { cn } from '../lib/utils'
+
+/*
+ * Button — copied verbatim from apps/desktop/src/components/ui/button.tsx.
+ *
+ * We import the desktop's local shadcn-style Button rather than
+ * @nous-research/ui's <Button>, because the DS Button uses bg-midground /
+ * text-background-base utilities that resolve to the DS's hardcoded
+ * gold/brown brand defaults (#ffac02 / #170d02) unless overridden in
+ * runtime. The desktop never sets those vars; it routes through its
+ * own --dt-* token chain via shadcn classes like bg-primary. We do
+ * the same so visuals match exactly.
+ */
+
+const buttonVariants = cva(
+  "inline-flex shrink-0 items-center justify-center gap-2 rounded-md text-sm font-medium whitespace-nowrap transition-all outline-none focus-visible:border-ring focus-visible:ring-[0.1875rem] focus-visible:ring-ring/50 disabled:pointer-events-none disabled:opacity-50 aria-invalid:border-destructive aria-invalid:ring-destructive/20 dark:aria-invalid:ring-destructive/40 [&_svg]:pointer-events-none [&_svg]:shrink-0 [&_svg:not([class*='size-'])]:size-4",
+  {
+    variants: {
+      variant: {
+        default: 'bg-primary text-primary-foreground hover:bg-primary/90',
+        destructive:
+          'bg-destructive text-white hover:bg-destructive/90 focus-visible:ring-destructive/20 dark:bg-destructive/60 dark:focus-visible:ring-destructive/40',
+        outline:
+          'border bg-background shadow-xs hover:bg-accent hover:text-accent-foreground dark:border-input dark:bg-input/30 dark:hover:bg-input/50',
+        secondary:
+          'bg-secondary text-secondary-foreground hover:bg-secondary/80',
+        ghost:
+          'hover:bg-accent hover:text-accent-foreground dark:hover:bg-accent/50',
+        link: 'text-primary underline-offset-4 decoration-current/20 hover:underline'
+      },
+      size: {
+        default: 'h-9 px-4 py-2 has-[>svg]:px-3',
+        xs: "h-6 gap-1 rounded-md px-2 text-xs has-[>svg]:px-1.5 [&_svg:not([class*='size-'])]:size-3",
+        sm: 'h-8 gap-1.5 rounded-md px-3 has-[>svg]:px-2.5',
+        lg: 'h-10 rounded-md px-6 has-[>svg]:px-4',
+        icon: 'size-9',
+        'icon-xs':
+          "size-6 rounded-md [&_svg:not([class*='size-'])]:size-3",
+        'icon-sm': 'size-8',
+        'icon-lg': 'size-10'
+      }
+    },
+    defaultVariants: {
+      variant: 'default',
+      size: 'default'
+    }
+  }
+)
+
+interface ButtonProps
+  extends React.ComponentProps<'button'>,
+    VariantProps<typeof buttonVariants> {
+  asChild?: boolean
+}
+
+export function Button({
+  className,
+  variant = 'default',
+  size = 'default',
+  asChild = false,
+  ...props
+}: ButtonProps) {
+  const Comp = asChild ? Slot.Root : 'button'
+
+  return (
+    <Comp
+      className={cn(buttonVariants({ variant, size }), className)}
+      data-size={size}
+      data-slot="button"
+      data-variant={variant}
+      {...props}
+    />
+  )
+}
+
+export { buttonVariants }

apps/bootstrap-installer/src/lib/utils.ts

@@ -0,0 +1,12 @@
+import { type ClassValue, clsx } from 'clsx'
+import { twMerge } from 'tailwind-merge'
+
+/*
+ * cn — Tailwind-aware class merger. Same util the desktop and dashboard
+ * use. clsx handles conditional classes; twMerge resolves utility
+ * conflicts so `cn('px-2', condition && 'px-4')` ends up with px-4 only,
+ * not both.
+ */
+export function cn(...inputs: ClassValue[]) {
+  return twMerge(clsx(inputs))
+}

apps/bootstrap-installer/src/main.tsx

@@ -0,0 +1,14 @@
+import { StrictMode } from 'react'
+import { createRoot } from 'react-dom/client'
+import App from './app.tsx'
+import './styles.css'
+
+// Default to LIGHT mode — matches the Hermes desktop's default. The
+// desktop's runtime theme system can switch to .dark later, but our
+// installer ships in light mode only since we don't carry the theme
+// provider machinery.
+createRoot(document.getElementById('root')!).render(
+  <StrictMode>
+    <App />
+  </StrictMode>
+)

apps/bootstrap-installer/src/routes/failure.tsx

@@ -0,0 +1,77 @@
+import { type CSSProperties } from 'react'
+import { useStore } from '@nanostores/react'
+import { Button } from '../components/button'
+import {
+  $logPath,
+  openLogDir,
+  startInstall,
+  type BootstrapStateModel
+} from '../store'
+import { RefreshCw, FileText } from 'lucide-react'
+
+interface FailureProps {
+  bootstrap: BootstrapStateModel
+}
+
+/*
+ * Failure screen. Same hero treatment as Welcome/Success — the wordmark
+ * carries the brand, so we keep it across every terminal state.
+ *
+ * The actual error message lives below in muted text. Two clear
+ * affordances: Retry (primary) and Open log folder (secondary).
+ */
+export default function Failure({ bootstrap }: FailureProps) {
+  const logPath = useStore($logPath)
+
+  return (
+    <div className="hermes-fade-in flex h-full flex-col items-center justify-center gap-6 px-12 py-10">
+      <div className="w-full max-w-2xl min-w-0 text-center">
+        <p
+          className="fit-text mx-auto mb-4 w-full font-['Collapse'] font-bold uppercase leading-[0.9] tracking-[0.08em] text-destructive mix-blend-plus-lighter dark:text-destructive/90"
+          style={
+            {
+              '--fit-text-line-height': '0.9',
+              '--fit-text-max': '5rem',
+              '--fit-text-min': '2.25rem'
+            } as CSSProperties
+          }
+        >
+          <span>
+            <span>Install didn&rsquo;t finish</span>
+          </span>
+          <span aria-hidden="true">Install didn&rsquo;t finish</span>
+        </p>
+
+        <p className="m-0 mx-auto max-w-xl text-center text-sm leading-normal tracking-tight text-muted-foreground">
+          {bootstrap.error ?? 'Something went wrong during installation.'}
+        </p>
+      </div>
+
+      <div className="flex items-center gap-3">
+        <Button
+          onClick={() => void startInstall()}
+          size="lg"
+          className="inline-flex items-center gap-2 px-6"
+        >
+          <RefreshCw size={16} />
+          Retry install
+        </Button>
+        <Button
+          variant="outline"
+          size="lg"
+          onClick={() => void openLogDir()}
+          className="inline-flex items-center gap-2"
+        >
+          <FileText size={16} />
+          Open log folder
+        </Button>
+      </div>
+
+      {logPath && (
+        <p className="max-w-lg text-center text-xs text-muted-foreground/70">
+          Log: <code className="font-mono">{logPath}</code>
+        </p>
+      )}
+    </div>
+  )
+}

apps/bootstrap-installer/src/routes/progress.tsx

@@ -0,0 +1,190 @@
+import { useEffect, useRef, useState } from 'react'
+import { useStore } from '@nanostores/react'
+import { Button } from '../components/button'
+import {
+  cancelInstall,
+  $progress,
+  type BootstrapStateModel,
+  type StageState
+} from '../store'
+import { Check, X, ChevronRight, FileText, Loader2 } from 'lucide-react'
+import clsx from 'clsx'
+
+interface ProgressProps {
+  bootstrap: BootstrapStateModel
+}
+
+/*
+ * Progress screen — drives a stage list + collapsible log panel. Uses
+ * the DS <Progress> for the top bar so its motion + ring match the rest
+ * of the product.
+ */
+export default function ProgressScreen({ bootstrap }: ProgressProps) {
+  const progress = useStore($progress)
+  const [showLogs, setShowLogs] = useState(false)
+  const logEndRef = useRef<HTMLDivElement>(null)
+
+  useEffect(() => {
+    if (showLogs && logEndRef.current) {
+      logEndRef.current.scrollIntoView({ behavior: 'smooth' })
+    }
+  }, [bootstrap.logs.length, showLogs])
+
+  const currentStage =
+    bootstrap.currentStage != null
+      ? bootstrap.stages[bootstrap.currentStage]
+      : null
+
+  return (
+    <div className="hermes-fade-in flex h-full flex-col">
+      <div className="border-b border-border px-6 py-4">
+        <div className="mb-3 flex items-center justify-between text-xs">
+          <div className="flex items-center gap-2 text-foreground">
+            {bootstrap.status === 'running' && (
+              <Loader2 size={12} className="animate-spin text-primary" />
+            )}
+            <span>
+              {bootstrap.status === 'running'
+                ? currentStage
+                  ? currentStage.info.title
+                  : 'Preparing\u2026'
+                : bootstrap.status === 'completed'
+                  ? 'Done'
+                  : 'Installing'}
+            </span>
+          </div>
+          <div className="text-muted-foreground">
+            {progress.done} of {progress.total} steps
+          </div>
+        </div>
+        {/* Top progress bar — plain HTML, derived from --primary so it
+            tracks the theme accent. */}
+        <div className="h-1 w-full overflow-hidden rounded-full bg-muted">
+          <div
+            className="h-full bg-primary transition-all duration-300 ease-out"
+            style={{ width: `${Math.max(2, progress.fraction * 100)}%` }}
+          />
+        </div>
+      </div>
+
+      <div className="flex flex-1 overflow-hidden">
+        <div className="flex-1 overflow-y-auto px-6 py-4">
+          <ol className="space-y-1">
+            {bootstrap.stageOrder.map((name) => {
+              const rec = bootstrap.stages[name]
+              if (!rec) return null
+              return (
+                <li
+                  key={name}
+                  className={clsx(
+                    'flex items-center gap-3 rounded-md px-3 py-2 text-sm transition-colors',
+                    rec.state === 'running' && 'bg-card text-foreground',
+                    rec.state === 'succeeded' && 'text-foreground/80',
+                    rec.state === 'skipped' && 'text-muted-foreground',
+                    rec.state === 'failed' &&
+                      'bg-destructive/10 text-destructive',
+                    !rec.state && 'text-muted-foreground/60'
+                  )}
+                >
+                  <StateIcon state={rec.state ?? null} />
+                  <span className="flex-1 truncate">{rec.info.title}</span>
+                  {rec.durationMs != null && (
+                    <span className="text-xs text-muted-foreground">
+                      {formatDuration(rec.durationMs)}
+                    </span>
+                  )}
+                </li>
+              )
+            })}
+          </ol>
+        </div>
+
+        {showLogs && (
+          <div className="flex w-1/2 flex-col border-l border-border bg-card/40">
+            <div className="flex shrink-0 items-center justify-between border-b border-border px-3 py-2">
+              <div className="text-xs font-medium text-foreground/80">
+                Live output
+              </div>
+              <div className="text-xs text-muted-foreground">
+                {bootstrap.logs.length} lines
+              </div>
+            </div>
+            <div className="flex-1 overflow-y-auto px-3 py-2 font-mono text-[11px] leading-relaxed">
+              {bootstrap.logs.map((entry, idx) => (
+                <div
+                  key={idx}
+                  className={clsx(
+                    'whitespace-pre-wrap',
+                    entry.line.startsWith('stderr:')
+                      ? 'text-destructive'
+                      : 'text-foreground/70'
+                  )}
+                >
+                  {entry.line}
+                </div>
+              ))}
+              <div ref={logEndRef} />
+            </div>
+          </div>
+        )}
+      </div>
+
+      <div className="flex shrink-0 items-center justify-between border-t border-border px-6 py-3">
+        <button
+          type="button"
+          onClick={() => setShowLogs((v) => !v)}
+          className="inline-flex items-center gap-1.5 text-xs text-muted-foreground transition-colors hover:text-foreground"
+        >
+          <FileText size={14} />
+          {showLogs ? 'Hide details' : 'Show details'}
+          <ChevronRight
+            size={12}
+            className={clsx(
+              'transition-transform',
+              showLogs && 'rotate-90'
+            )}
+          />
+        </button>
+
+        {bootstrap.status === 'running' && (
+          <Button
+            variant="outline"
+            size="sm"
+            onClick={() => void cancelInstall()}
+          >
+            Cancel
+          </Button>
+        )}
+      </div>
+    </div>
+  )
+}
+
+function StateIcon({ state }: { state: StageState | null }) {
+  if (state === 'running') {
+    return <Loader2 size={14} className="animate-spin text-primary" />
+  }
+  if (state === 'succeeded') {
+    return <Check size={14} className="text-emerald-400" />
+  }
+  if (state === 'skipped') {
+    return <ChevronRight size={14} className="text-muted-foreground/70" />
+  }
+  if (state === 'failed') {
+    return <X size={14} className="text-destructive" />
+  }
+  return (
+    <div
+      className="h-[6px] w-[6px] rounded-full bg-muted-foreground/40"
+      aria-hidden
+    />
+  )
+}
+
+function formatDuration(ms: number): string {
+  if (ms < 1000) return `${ms}ms`
+  if (ms < 60000) return `${(ms / 1000).toFixed(1)}s`
+  const m = Math.floor(ms / 60000)
+  const s = Math.round((ms % 60000) / 1000)
+  return `${m}m ${s}s`
+}

apps/bootstrap-installer/src/routes/success.tsx

@@ -0,0 +1,87 @@
+import { useState } from 'react'
+import { type CSSProperties } from 'react'
+import { Button } from '../components/button'
+import { launchHermesDesktop } from '../store'
+import { Rocket, AlertCircle } from 'lucide-react'
+
+/*
+ * Success screen. HERMES AGENT wordmark stays as the visual anchor
+ * (same Collapse Bold treatment as Welcome + the desktop chat intro),
+ * with a status line below.
+ *
+ * Launching the desktop can fail (e.g. Stage-Desktop was skipped and
+ * Hermes.exe doesn't exist). We catch the Tauri error and surface it
+ * inline rather than silently doing nothing — the previous version
+ * had `onClick={() => void launchHermesDesktop()}` which swallowed
+ * the rejection and left the user staring at an unresponsive button.
+ */
+export default function Success() {
+  const [error, setError] = useState<string | null>(null)
+  const [launching, setLaunching] = useState(false)
+
+  async function handleLaunch() {
+    setError(null)
+    setLaunching(true)
+    try {
+      await launchHermesDesktop()
+      // On success the installer exits — control never returns here.
+    } catch (e) {
+      const msg = e instanceof Error ? e.message : String(e)
+      setError(msg)
+      setLaunching(false)
+    }
+  }
+
+  return (
+    <div className="hermes-fade-in flex h-full flex-col items-center justify-center gap-8 px-12 py-10">
+      <div className="w-full max-w-2xl min-w-0 text-center">
+        <p
+          className="fit-text mx-auto mb-4 w-full font-['Collapse'] font-bold uppercase leading-[0.9] tracking-[0.08em] text-midground mix-blend-plus-lighter dark:text-foreground/90"
+          style={
+            {
+              '--fit-text-line-height': '0.9',
+              '--fit-text-max': '5rem',
+              '--fit-text-min': '2.25rem'
+            } as CSSProperties
+          }
+        >
+          <span>
+            <span>Hermes is ready</span>
+          </span>
+          <span aria-hidden="true">Hermes is ready</span>
+        </p>
+
+        <p className="m-0 text-center text-base leading-normal tracking-tight text-muted-foreground">
+          You can launch from here, or any time from your terminal with{' '}
+          <code className="rounded bg-muted/60 px-1 py-0.5 font-mono text-sm">
+            hermes desktop
+          </code>
+          .
+        </p>
+      </div>
+
+      <Button
+        onClick={() => void handleLaunch()}
+        size="lg"
+        disabled={launching}
+        className="inline-flex items-center gap-2 px-6"
+      >
+        <Rocket size={18} />
+        {launching ? 'Launching…' : 'Launch Hermes'}
+      </Button>
+
+      {error && (
+        <div
+          role="alert"
+          className="flex max-w-2xl items-start gap-2 rounded-md border border-destructive/30 bg-destructive/10 px-4 py-3 text-sm text-destructive"
+        >
+          <AlertCircle size={16} className="mt-0.5 shrink-0" />
+          <div className="min-w-0">
+            <div className="font-medium">Couldn&rsquo;t launch the desktop app</div>
+            <div className="mt-1 text-destructive/80">{error}</div>
+          </div>
+        </div>
+      )}
+    </div>
+  )
+}

apps/bootstrap-installer/src/routes/welcome.tsx

@@ -0,0 +1,58 @@
+import { type CSSProperties } from 'react'
+import { Button } from '../components/button'
+import { startInstall } from '../store'
+import { ArrowRight } from 'lucide-react'
+
+/*
+ * Welcome screen.
+ *
+ * Mirrors the desktop's chat intro (apps/desktop/src/components/chat/intro.tsx):
+ *   - HERMES AGENT wordmark rendered in Collapse Bold, uppercase, tracked
+ *   - mix-blend-plus-lighter so the type "glows" on the canvas
+ *   - fit-text utility so the wordmark sizes itself to the column
+ *
+ * No install-path footer. The default install location is correct for
+ * 99% of users; the rest will use the CLI installer with a -HermesHome
+ * flag. Showing %LOCALAPPDATA% to grandma is developer-brain.
+ */
+export default function Welcome() {
+  return (
+    <div className="hermes-fade-in flex h-full flex-col items-center justify-center gap-10 px-12 py-10">
+      {/* Hero — same recipe the desktop's chat/intro.tsx uses */}
+      <div className="w-full max-w-2xl min-w-0 text-center">
+        <p
+          className="fit-text mx-auto mb-4 w-full font-['Collapse'] font-bold uppercase leading-[0.9] tracking-[0.08em] text-midground mix-blend-plus-lighter dark:text-foreground/90"
+          style={
+            {
+              '--fit-text-line-height': '0.9',
+              '--fit-text-max': '6rem',
+              '--fit-text-min': '2.5rem'
+            } as CSSProperties
+          }
+        >
+          <span>
+            <span>HERMES AGENT</span>
+          </span>
+          <span aria-hidden="true">HERMES AGENT</span>
+        </p>
+
+        <p className="m-0 text-center text-base leading-normal tracking-tight text-muted-foreground">
+          The agent that grows with you. We&rsquo;ll set things up in the
+          background &mdash; takes a few minutes.
+        </p>
+      </div>
+
+      <Button
+        onClick={() => void startInstall()}
+        size="lg"
+        className="group inline-flex items-center gap-2 px-6"
+      >
+        Install Hermes
+        <ArrowRight
+          size={18}
+          className="transition-transform group-hover:translate-x-0.5"
+        />
+      </Button>
+    </div>
+  )
+}

apps/bootstrap-installer/src/store.ts

@@ -0,0 +1,277 @@
+import { atom, computed } from 'nanostores'
+import { listen, type UnlistenFn } from '@tauri-apps/api/event'
+import { invoke } from '@tauri-apps/api/core'
+
+/*
+ * Bootstrap state store — single source of truth for installer screens.
+ *
+ * Lives in nanostores per the project's TypeScript guidelines (apps/desktop
+ * AGENTS.md): "Prefer small nanostores over component state when state is
+ * shared, reused, or read by distant UI."
+ *
+ * One channel from Rust ('bootstrap' event), discriminated by payload.type.
+ * We translate those events into typed atom updates here so the rest of
+ * the app only deals with React-friendly state.
+ */
+
+// ---------------------------------------------------------------------------
+// Types — mirror src-tauri/src/events.rs
+// ---------------------------------------------------------------------------
+
+export interface StageInfo {
+  name: string
+  title: string
+  category: string
+  needs_user_input: boolean
+}
+
+export type StageState = 'running' | 'succeeded' | 'skipped' | 'failed'
+
+export interface StageRecord {
+  info: StageInfo
+  state: StageState | null
+  durationMs?: number
+  error?: string
+}
+
+export interface BootstrapStateModel {
+  status: 'idle' | 'running' | 'completed' | 'failed'
+  protocolVersion: number | null
+  stages: Record<string, StageRecord>
+  stageOrder: string[]
+  currentStage: string | null
+  installRoot: string | null
+  error: string | null
+  logs: Array<{ stage?: string; line: string }>
+}
+
+const INITIAL: BootstrapStateModel = {
+  status: 'idle',
+  protocolVersion: null,
+  stages: {},
+  stageOrder: [],
+  currentStage: null,
+  installRoot: null,
+  error: null,
+  logs: []
+}
+
+// ---------------------------------------------------------------------------
+// Atoms
+// ---------------------------------------------------------------------------
+
+export type Route = 'welcome' | 'progress' | 'success' | 'failure'
+
+/// How the installer was launched, mirrored from src-tauri AppMode.
+/// 'install' = first-run onboarding (bare launch). 'update' = driven by the
+/// desktop app handing off via `Hermes-Setup.exe --update`.
+export type AppMode = 'install' | 'update'
+
+export const $route = atom<Route>('welcome')
+export const $mode = atom<AppMode>('install')
+export const $bootstrap = atom<BootstrapStateModel>(INITIAL)
+export const $logPath = atom<string | null>(null)
+export const $hermesHome = atom<string | null>(null)
+
+export const $progress = computed($bootstrap, (b) => {
+  const total = b.stageOrder.length
+  if (total === 0) return { done: 0, total: 0, fraction: 0 }
+  let done = 0
+  for (const name of b.stageOrder) {
+    const s = b.stages[name]?.state
+    if (s === 'succeeded' || s === 'skipped' || s === 'failed') done += 1
+  }
+  return { done, total, fraction: done / total }
+})
+
+// ---------------------------------------------------------------------------
+// Tauri event subscription
+// ---------------------------------------------------------------------------
+
+interface BootstrapManifestEvent {
+  type: 'manifest'
+  stages: StageInfo[]
+  protocolVersion: number | null
+}
+
+interface BootstrapStageEvent {
+  type: 'stage'
+  name: string
+  state: StageState
+  durationMs?: number
+  error?: string
+}
+
+interface BootstrapLogEvent {
+  type: 'log'
+  stage?: string
+  line: string
+}
+
+interface BootstrapCompleteEvent {
+  type: 'complete'
+  installRoot: string
+  marker: unknown
+}
+
+interface BootstrapFailedEvent {
+  type: 'failed'
+  stage?: string
+  error: string
+}
+
+type BootstrapEvent =
+  | BootstrapManifestEvent
+  | BootstrapStageEvent
+  | BootstrapLogEvent
+  | BootstrapCompleteEvent
+  | BootstrapFailedEvent
+
+let unlisten: UnlistenFn | null = null
+
+export async function initialize(): Promise<void> {
+  if (unlisten) return
+
+  // Pull static info on mount for the diagnostics footer.
+  try {
+    const [logPath, hermesHome, mode] = await Promise.all([
+      invoke<string>('get_log_path'),
+      invoke<string>('get_hermes_home'),
+      invoke<AppMode>('get_mode')
+    ])
+    $logPath.set(logPath)
+    $hermesHome.set(hermesHome)
+    $mode.set(mode)
+  } catch (err) {
+    console.warn('failed to fetch installer paths', err)
+  }
+
+  unlisten = await listen<BootstrapEvent>('bootstrap', (event) => {
+    const payload = event.payload
+    const cur = $bootstrap.get()
+    switch (payload.type) {
+      case 'manifest': {
+        const stages: Record<string, StageRecord> = {}
+        const order: string[] = []
+        for (const s of payload.stages) {
+          stages[s.name] = { info: s, state: null }
+          order.push(s.name)
+        }
+        $bootstrap.set({
+          ...cur,
+          status: 'running',
+          protocolVersion: payload.protocolVersion,
+          stages,
+          stageOrder: order,
+          currentStage: null,
+          installRoot: null,
+          error: null,
+          logs: []
+        })
+        $route.set('progress')
+        break
+      }
+      case 'stage': {
+        const existing = cur.stages[payload.name]
+        if (!existing) {
+          console.warn('stage event for unknown stage', payload.name)
+          break
+        }
+        const next: StageRecord = {
+          ...existing,
+          state: payload.state,
+          durationMs: payload.durationMs,
+          error: payload.error
+        }
+        $bootstrap.set({
+          ...cur,
+          stages: { ...cur.stages, [payload.name]: next },
+          currentStage:
+            payload.state === 'running' ? payload.name : cur.currentStage
+        })
+        break
+      }
+      case 'log': {
+        const logs = [...cur.logs, { stage: payload.stage, line: payload.line }]
+        // Keep the rolling buffer bounded so the UI doesn't get OOM'd
+        // during a long install (playwright chromium download is ~10k lines).
+        const trimmed = logs.length > 2000 ? logs.slice(-2000) : logs
+        $bootstrap.set({ ...cur, logs: trimmed })
+        break
+      }
+      case 'complete':
+        $bootstrap.set({
+          ...cur,
+          status: 'completed',
+          installRoot: payload.installRoot,
+          currentStage: null
+        })
+        // Install: show the "launch Hermes" success screen. Update: this is a
+        // hand-off — the installer relaunches the desktop and exits within a
+        // few hundred ms, so routing to success just flashes that screen
+        // before the window closes. Stay on progress until we exit.
+        if ($mode.get() !== 'update') {
+          $route.set('success')
+        }
+        break
+      case 'failed':
+        $bootstrap.set({
+          ...cur,
+          status: 'failed',
+          error: payload.error,
+          currentStage: null
+        })
+        $route.set('failure')
+        break
+    }
+  })
+
+  // Update mode is a hand-off, not a user-initiated flow: the desktop already
+  // exited and re-launched us as `--update`. Kick the update immediately so
+  // the user lands on progress, not a redundant "click to update" screen.
+  if ($mode.get() === 'update') {
+    void startUpdate()
+  }
+}
+
+// ---------------------------------------------------------------------------
+// Actions
+// ---------------------------------------------------------------------------
+
+export async function startInstall(opts?: { branch?: string }): Promise<void> {
+  // Reset before kicking off so a retry from the failure screen clears
+  // the previous run's state.
+  $bootstrap.set(INITIAL)
+  $route.set('progress')
+  await invoke('start_bootstrap', {
+    args: {
+      commit: null,
+      branch: opts?.branch ?? null,
+      include_desktop: true,
+      hermes_home: null
+    }
+  })
+}
+
+export async function startUpdate(): Promise<void> {
+  // Update is driven by the desktop handing off (Hermes-Setup.exe --update);
+  // there's no welcome click. Reset + jump straight to progress, then let the
+  // Rust side stream the synthetic update manifest.
+  $bootstrap.set(INITIAL)
+  $route.set('progress')
+  await invoke('start_update')
+}
+
+export async function cancelInstall(): Promise<void> {
+  await invoke('cancel_bootstrap')
+}
+
+export async function launchHermesDesktop(): Promise<void> {
+  const installRoot = $bootstrap.get().installRoot
+  if (!installRoot) throw new Error('no install root')
+  await invoke('launch_hermes_desktop', { installRoot })
+}
+
+export async function openLogDir(): Promise<void> {
+  await invoke('open_log_dir')
+}

apps/bootstrap-installer/src/styles.css

@@ -0,0 +1,51 @@
+/*
+ * Hermes Setup — defer entirely to the desktop's styles.css.
+ *
+ * Rather than re-implement the Hermes design system (and inevitably drift
+ * from it), we import apps/desktop/src/styles.css wholesale. The desktop
+ * is the canonical source of truth for fonts, color tokens, button chrome,
+ * scrollbars, layout utilities, and animations. Any change to the
+ * Hermes look propagates here automatically with no copy-paste maintenance.
+ *
+ * Path resolution caveats:
+ *   - Tailwind v4's `@import` resolves relative to this file. The desktop's
+ *     `@source '../../../node_modules/...'` declarations therefore re-resolve
+ *     against apps/bootstrap-installer/src/. Since both apps live two levels
+ *     deep under the same repo root, `../../../node_modules` lands in the
+ *     same place. (Verify if either app ever moves.)
+ *   - The desktop's `@font-face url('../../../node_modules/...')` references
+ *     are baked into the *imported* stylesheet; CSS resolves url()s relative
+ *     to the file that contains them, so they continue to point at the
+ *     correct node_modules path even from here.
+ *
+ * Forced light mode: the desktop ships with a runtime theme switcher
+ * (ThemeProvider + applyTheme) that can flip to dark via document.documentElement.
+ * The installer has no UI for theme switching, so we stay on the desktop's
+ * default light surface (Nous-blue accent on near-white chrome).
+ */
+@import '../../desktop/src/styles.css';
+
+/* Installer-only additions: a fade-in animation and a warm radial glow
+   for the welcome screen. Everything else inherits from the desktop. */
+@keyframes hermes-fade-in {
+  from {
+    opacity: 0;
+    transform: translateY(4px);
+  }
+  to {
+    opacity: 1;
+    transform: translateY(0);
+  }
+}
+
+.hermes-fade-in {
+  animation: hermes-fade-in 0.45s ease-out both;
+}
+
+.hermes-glow {
+  background: radial-gradient(
+    ellipse at center,
+    color-mix(in srgb, var(--ui-warm) 18%, transparent) 0%,
+    transparent 60%
+  );
+}

apps/bootstrap-installer/src/vite-env.d.ts

@@ -0,0 +1 @@
+/// <reference types="vite/client" />

apps/bootstrap-installer/tsconfig.json

@@ -0,0 +1,26 @@
+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "useDefineForClassFields": true,
+    "lib": ["ES2022", "DOM", "DOM.Iterable"],
+    "module": "ESNext",
+    "skipLibCheck": true,
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "resolveJsonModule": true,
+    "isolatedModules": true,
+    "noEmit": true,
+    "jsx": "react-jsx",
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "esModuleInterop": true,
+    "noFallthroughCasesInSwitch": true,
+    "baseUrl": ".",
+    "paths": {
+      "@/*": ["src/*"]
+    }
+  },
+  "include": ["src"],
+  "references": [{ "path": "./tsconfig.node.json" }]
+}

apps/bootstrap-installer/tsconfig.node.json

@@ -0,0 +1,11 @@
+{
+  "compilerOptions": {
+    "composite": true,
+    "skipLibCheck": true,
+    "module": "ESNext",
+    "moduleResolution": "bundler",
+    "allowSyntheticDefaultImports": true,
+    "strict": true
+  },
+  "include": ["vite.config.ts"]
+}

apps/bootstrap-installer/vite.config.ts

@@ -0,0 +1,46 @@
+import { defineConfig } from 'vite'
+import react from '@vitejs/plugin-react'
+import tailwindcss from '@tailwindcss/vite'
+import path from 'node:path'
+
+// Hermes Setup — Tauri-targeted Vite config.
+//
+// Port 5175 keeps us out of the way of:
+//   web       (vite default 5173)
+//   apps/desktop dev     (5174 per its package.json)
+//
+// `clearScreen: false` is the Tauri convention — they spawn vite as a child
+// process and want our errors to stay visible.
+
+const host = process.env.TAURI_DEV_HOST
+
+export default defineConfig({
+  plugins: [react(), tailwindcss()],
+  resolve: {
+    alias: {
+      '@': path.resolve(__dirname, './src')
+    }
+  },
+  clearScreen: false,
+  server: {
+    port: 5175,
+    strictPort: true,
+    host: host || '127.0.0.1',
+    hmr: host
+      ? {
+          protocol: 'ws',
+          host,
+          port: 5176
+        }
+      : undefined,
+    watch: {
+      // Don't watch the Rust side — tauri-cli handles it.
+      ignored: ['**/src-tauri/**']
+    }
+  },
+  build: {
+    target: 'esnext',
+    outDir: 'dist',
+    emptyOutDir: true
+  }
+})

apps/desktop/.prettierrc

@@ -0,0 +1,11 @@
+{
+  "arrowParens": "avoid",
+  "bracketSpacing": true,
+  "endOfLine": "auto",
+  "printWidth": 120,
+  "semi": false,
+  "singleQuote": true,
+  "tabWidth": 2,
+  "trailingComma": "none",
+  "useTabs": false
+}

apps/desktop/README.md

@@ -0,0 +1,137 @@
+# Hermes Desktop ☤
+
+<p align="center">
+  <a href="https://github.com/NousResearch/hermes-agent/releases"><img src="https://img.shields.io/badge/Download-macOS%20%C2%B7%20Windows%20%C2%B7%20Linux-FFD700?style=for-the-badge" alt="Download"></a>
+  <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>
+  <a href="https://github.com/NousResearch/hermes-agent/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-green?style=for-the-badge" alt="License: MIT"></a>
+</p>
+
+**The native desktop app for [Hermes Agent](../../README.md) — the self-improving AI agent from [Nous Research](https://nousresearch.com).** Same agent, same skills, same memory as the CLI and gateway, in a polished native window — chat with streaming tool output, side-by-side previews, a file browser, voice, and settings, no terminal required. Available for **macOS, Windows, and Linux**.
+
+<table>
+<tr><td><b>Chat with the full agent</b></td><td>Streaming responses, live tool activity, structured tool summaries, and the same conversation history as every other Hermes surface.</td></tr>
+<tr><td><b>Side-by-side previews</b></td><td>Render web pages, files, and tool outputs in a right-hand pane while you keep chatting.</td></tr>
+<tr><td><b>File browser</b></td><td>Explore and preview the working directory without leaving the app.</td></tr>
+<tr><td><b>Voice</b></td><td>Talk to Hermes and hear it back.</td></tr>
+<tr><td><b>Settings & onboarding</b></td><td>Manage providers, models, tools, and credentials from a real UI. First-run setup gets you to your first message in seconds.</td></tr>
+<tr><td><b>Stays current</b></td><td>Built-in updates pull the latest agent and rebuild the app in place.</td></tr>
+</table>
+
+---
+
+## Install
+
+### Install with Hermes (recommended)
+
+Add `--include-desktop` to the [one-line installer](../../README.md#quick-install) and it sets up the agent and builds the desktop app in one go:
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash -s -- --include-desktop
+```
+
+Already have the Hermes CLI? Just run:
+
+```bash
+hermes desktop
+```
+
+It builds and launches the GUI against your existing install — same config, keys, sessions, and skills. On first launch Hermes walks you through picking a provider and model; nothing else to configure.
+
+### Prebuilt installers
+
+When a release ships desktop installers they're attached to its [releases page](https://github.com/NousResearch/hermes-agent/releases) — `.dmg` (macOS), `.exe` / `.msi` (Windows), `.AppImage` / `.deb` / `.rpm` (Linux). These are published manually, so the install-with-Hermes path above is the most reliable way to get the latest.
+
+---
+
+## Updating
+
+The app checks for updates in the background and offers a one-click update when one is ready. You can also update any time from the CLI:
+
+```bash
+hermes update
+```
+
+---
+
+## Requirements
+
+The installer handles everything for you (Python 3.11+, a portable Git, ripgrep). The only thing worth knowing:
+
+- **Windows** — the installer bundles its own Git and Python; no admin rights or system changes required.
+- **macOS / Linux** — uses your system Python 3.11+ (installed automatically if missing).
+
+---
+
+## Development
+
+Want to hack on the app itself? Install workspace deps from the repo root once, then run the dev server from this directory:
+
+```bash
+npm install          # from repo root — links apps/desktop, web, apps/shared
+cd apps/desktop
+npm run dev          # Vite renderer + Electron, which boots the Python backend
+```
+
+Point the app at a specific source checkout, or sandbox it away from your real config:
+
+```bash
+HERMES_DESKTOP_HERMES_ROOT=/path/to/clone npm run dev
+HERMES_HOME=/tmp/throwaway npm run dev
+npm run dev:fake-boot   # exercise the startup overlay with deterministic delays
+```
+
+### Building installers
+
+```bash
+npm run dist:mac     # DMG + zip
+npm run dist:win     # NSIS + MSI
+npm run dist:linux   # AppImage + deb + rpm
+npm run pack         # unpacked app under release/ (no installer)
+```
+
+Installers are built and uploaded to GitHub Releases manually. macOS/Windows signing & notarization happen automatically when the relevant credentials are present in the environment (`CSC_LINK` / `CSC_KEY_PASSWORD` / `APPLE_*` for macOS, `WIN_CSC_*` for Windows).
+
+### How it works
+
+The packaged app ships only the Electron shell. On first launch it installs the Hermes Agent runtime into `HERMES_HOME` (`~/.hermes`, or `%LOCALAPPDATA%\hermes` on Windows) — the **same layout a CLI install uses**, so the two are interchangeable. The renderer (React, in `src/`) talks to a `hermes dashboard --tui` backend over the standard gateway APIs and reuses the embedded TUI rather than reimplementing chat. The install, backend-resolution, and self-update logic all live in `electron/main.cjs`.
+
+### Verification
+
+Run before opening a PR (lint may surface pre-existing warnings but must exit cleanly):
+
+```bash
+npm run fix
+npm run type-check
+npm run lint
+npm run test:desktop:all
+```
+
+### Troubleshooting
+
+Boot logs land in `HERMES_HOME/logs/desktop.log` (includes backend output and recent Python tracebacks) — check it first if the app reports a boot failure.
+
+```bash
+# Force a clean first-launch setup
+rm "$HOME/.hermes/hermes-agent/.hermes-bootstrap-complete"   # macOS/Linux
+# Rebuild a broken Python venv
+rm -rf "$HOME/.hermes/hermes-agent/venv"                     # macOS/Linux
+# Reset a stuck macOS microphone prompt
+tccutil reset Microphone com.nousresearch.hermes
+```
+
+---
+
+## Community
+
+- 💬 [Discord](https://discord.gg/NousResearch)
+- 📖 [Documentation](https://hermes-agent.nousresearch.com/docs/)
+- 🐛 [Issues](https://github.com/NousResearch/hermes-agent/issues)
+
+---
+
+## License
+
+MIT — see [LICENSE](../../LICENSE).
+
+Built by [Nous Research](https://nousresearch.com).

apps/desktop/components.json

@@ -0,0 +1,21 @@
+{
+  "$schema": "https://ui.shadcn.com/schema.json",
+  "style": "new-york",
+  "rsc": false,
+  "tsx": true,
+  "tailwind": {
+    "config": "",
+    "css": "src/styles.css",
+    "baseColor": "neutral",
+    "cssVariables": true,
+    "prefix": ""
+  },
+  "aliases": {
+    "components": "@/components",
+    "utils": "@/lib/utils",
+    "ui": "@/components/ui",
+    "lib": "@/lib",
+    "hooks": "@/hooks"
+  },
+  "iconLibrary": "lucide"
+}

apps/desktop/electron/backend-probes.cjs

@@ -0,0 +1,106 @@
+/**
+ * backend-probes.cjs
+ *
+ * Cheap "does this candidate backend actually work" checks used by
+ * resolveHermesBackend (main.cjs). The resolver walks a ladder of
+ * candidates -- bootstrap marker, `hermes` on PATH, system Python with
+ * hermes_cli installed -- and historically returned the first candidate
+ * whose binary existed on disk. That assumption breaks when a user has
+ * a pre-installed Python 3.11-3.13 (so findSystemPython() returns a
+ * path) but no hermes_cli in its site-packages: the resolver hands back
+ * a backend the spawn step can't actually run, and the user gets a
+ * dead-on-arrival "ModuleNotFoundError: No module named 'hermes_cli'"
+ * instead of the first-launch installer.
+ *
+ * These probes give the resolver a way to verify a candidate before
+ * trusting it. Failure (non-zero exit, exception, timeout) means "skip
+ * this rung, try the next one"; success means "spawn this for real."
+ * Falling off the bottom of the ladder lands on the bootstrap-needed
+ * sentinel, which is exactly what we want when nothing pre-existing
+ * actually works.
+ *
+ * Both probes are deliberately fast and forgiving:
+ *   - 5s timeout (a hung interpreter beats forever, but we still give
+ *     slow disks / cold caches room to breathe)
+ *   - stdio ignored (we only care about exit code; stdout/stderr are
+ *     not surfaced to the user, just to recentHermesLog for forensics
+ *     via the caller's catch block if it chooses)
+ *   - any throw -> false (never propagate -- resolver wants a boolean)
+ *
+ * Kept in a standalone cjs module so it can be unit-tested with
+ * `node --test` without dragging in the electron runtime (same pattern
+ * as bootstrap-platform.cjs and hardening.cjs).
+ */
+
+const { execFileSync } = require('node:child_process')
+
+const PROBE_TIMEOUT_MS = 5000
+
+/**
+ * Return true iff `python -c "import hermes_cli"` exits 0.
+ *
+ * Used to gate the "fallback to system Python with hermes_cli installed"
+ * rung of resolveHermesBackend. Without this, a system Python 3.11-3.13
+ * registered in PEP 514 makes findSystemPython() succeed regardless of
+ * whether hermes_cli has actually been pip-installed into its
+ * site-packages -- and the resolver returns a backend that immediately
+ * dies on spawn.
+ *
+ * @param {string} pythonPath - Absolute path to a python.exe / python.
+ * @returns {boolean}
+ */
+function canImportHermesCli(pythonPath) {
+  if (!pythonPath) return false
+  try {
+    execFileSync(pythonPath, ['-c', 'import hermes_cli'], {
+      stdio: 'ignore',
+      timeout: PROBE_TIMEOUT_MS,
+      windowsHide: true
+    })
+    return true
+  } catch {
+    return false
+  }
+}
+
+/**
+ * Return true iff `<hermesCommand> --version` exits 0.
+ *
+ * Used to gate the "existing `hermes` on PATH" rung. Without this, a
+ * stale hermes.cmd shim left behind by an uninstalled pip install (or
+ * a half-built venv whose `hermes` entry-point points at a deleted
+ * Python) survives findOnPath() and gets selected as the backend.
+ *
+ * We intentionally avoid invoking the command with the dashboard args
+ * here -- `--version` is the cheapest "is this binary alive" smoke
+ * test that every hermes_cli entry-point has supported since 0.1.
+ *
+ * @param {string} hermesCommand - Resolved absolute path to a hermes
+ *   executable (or an interpreter+script wrapper).
+ * @param {object} [opts]
+ * @param {boolean} [opts.shell] - Whether to run through a shell. For
+ *   .cmd/.bat shims on Windows execFileSync needs shell:true to find
+ *   the cmd interpreter; mirrors the same flag isCommandScript() drives
+ *   in resolveHermesBackend.
+ * @returns {boolean}
+ */
+function verifyHermesCli(hermesCommand, opts = {}) {
+  if (!hermesCommand) return false
+  try {
+    execFileSync(hermesCommand, ['--version'], {
+      stdio: 'ignore',
+      timeout: PROBE_TIMEOUT_MS,
+      shell: Boolean(opts.shell),
+      windowsHide: true
+    })
+    return true
+  } catch {
+    return false
+  }
+}
+
+module.exports = {
+  canImportHermesCli,
+  verifyHermesCli,
+  PROBE_TIMEOUT_MS
+}

apps/desktop/electron/backend-probes.test.cjs

@@ -0,0 +1,80 @@
+/**
+ * Tests for electron/backend-probes.cjs.
+ *
+ * Run with: node --test electron/backend-probes.test.cjs
+ * (Wired into npm test:desktop:platforms in package.json.)
+ */
+
+const test = require('node:test')
+const assert = require('node:assert/strict')
+const fs = require('node:fs')
+const os = require('node:os')
+const path = require('node:path')
+
+const { canImportHermesCli, verifyHermesCli } = require('./backend-probes.cjs')
+
+// Resolve the host's own Node binary -- guaranteed to be on disk and
+// runnable. We use it as both a stand-in for "a python that doesn't
+// have hermes_cli" (since `node -c "import hermes_cli"` will exit
+// non-zero) and as a way to script verifyHermesCli's success path
+// (a tiny script we write to disk that exits 0 on --version).
+const NODE_BIN = process.execPath
+
+test('canImportHermesCli returns false when path is falsy', () => {
+  assert.equal(canImportHermesCli(''), false)
+  assert.equal(canImportHermesCli(null), false)
+  assert.equal(canImportHermesCli(undefined), false)
+})
+
+test('canImportHermesCli returns false when interpreter cannot run -c', () => {
+  // node IS an interpreter, but `node -c "import hermes_cli"` is a
+  // SyntaxError -- different exit reason from a real Python's
+  // ModuleNotFoundError, but the predicate is "exit 0 or not" and
+  // both land on "not", which is exactly what we want for the
+  // resolver fall-through.
+  assert.equal(canImportHermesCli(NODE_BIN), false)
+})
+
+test('canImportHermesCli returns false when binary does not exist', () => {
+  const ghost = path.join(os.tmpdir(), 'hermes-probes-ghost-' + Date.now() + '.exe')
+  assert.equal(canImportHermesCli(ghost), false)
+})
+
+test('verifyHermesCli returns false when command is falsy', () => {
+  assert.equal(verifyHermesCli(''), false)
+  assert.equal(verifyHermesCli(null), false)
+  assert.equal(verifyHermesCli(undefined), false)
+})
+
+test('verifyHermesCli returns false when binary does not exist', () => {
+  const ghost = path.join(os.tmpdir(), 'hermes-probes-ghost-' + Date.now() + '.exe')
+  assert.equal(verifyHermesCli(ghost), false)
+})
+
+test('verifyHermesCli returns true when --version exits 0', () => {
+  // Write a tiny script that exits 0 regardless of args, then invoke
+  // it through node. This stands in for a working hermes binary --
+  // verifyHermesCli only cares about the exit code.
+  const scriptPath = path.join(os.tmpdir(), `hermes-probes-ok-${Date.now()}-${process.pid}.cjs`)
+  fs.writeFileSync(scriptPath, 'process.exit(0)\n')
+  try {
+    // Use node as the launcher and our script as the "command". Pass
+    // shell:false (default) -- node is a real binary, no shim.
+    // execFileSync passes ['--version'] as args, which node ignores
+    // gracefully (well, it prints its version and exits 0, which is
+    // perfect -- exit code 0 is the only signal we read).
+    assert.equal(verifyHermesCli(NODE_BIN), true)
+  } finally {
+    try {
+      fs.unlinkSync(scriptPath)
+    } catch {}
+  }
+})
+
+test('verifyHermesCli swallows timeouts (does not throw)', () => {
+  // We can't easily provoke a real 5s hang in CI without slowing the
+  // suite, but we CAN confirm that an invocation that DOES throw
+  // (because the binary is missing) returns false rather than
+  // propagating. Same code path the timeout case takes.
+  assert.equal(verifyHermesCli('/definitely/not/a/real/binary/anywhere'), false)
+})

apps/desktop/electron/bootstrap-platform.cjs

@@ -0,0 +1,39 @@
+const fs = require('node:fs')
+
+function isWslEnvironment(env = process.env, platform = process.platform, kernelRelease = null) {
+  if (platform !== 'linux') return false
+  if (env.WSL_DISTRO_NAME || env.WSL_INTEROP) return true
+
+  try {
+    const release = kernelRelease ?? fs.readFileSync('/proc/sys/kernel/osrelease', 'utf8')
+    return /microsoft|wsl/i.test(release)
+  } catch {
+    return false
+  }
+}
+
+function isWindowsBinaryPathInWsl(filePath, options = {}) {
+  const isWsl = options.isWsl ?? isWslEnvironment(options.env, options.platform)
+  if (!isWsl) return false
+
+  const normalized = String(filePath || '')
+    .replace(/\\/g, '/')
+    .toLowerCase()
+
+  return (
+    normalized.endsWith('.exe') ||
+    normalized.endsWith('.cmd') ||
+    normalized.endsWith('.bat') ||
+    normalized.endsWith('.ps1')
+  )
+}
+
+function bundledRuntimeImportCheck(platform = process.platform) {
+  return platform === 'win32' ? 'import fastapi, uvicorn, winpty' : 'import fastapi, uvicorn, ptyprocess'
+}
+
+module.exports = {
+  bundledRuntimeImportCheck,
+  isWindowsBinaryPathInWsl,
+  isWslEnvironment
+}

apps/desktop/electron/bootstrap-platform.test.cjs

@@ -0,0 +1,53 @@
+const assert = require('node:assert/strict')
+const fs = require('node:fs')
+const path = require('node:path')
+const test = require('node:test')
+
+const { bundledRuntimeImportCheck, isWindowsBinaryPathInWsl, isWslEnvironment } = require('./bootstrap-platform.cjs')
+
+test('isWslEnvironment detects WSL2 env vars on linux', () => {
+  assert.equal(isWslEnvironment({ WSL_DISTRO_NAME: 'Ubuntu' }, 'linux'), true)
+  assert.equal(isWslEnvironment({ WSL_INTEROP: '/run/WSL/123_interop' }, 'linux'), true)
+  assert.equal(isWslEnvironment({}, 'linux', '6.6.87.2-microsoft-standard-WSL2'), true)
+  assert.equal(isWslEnvironment({}, 'linux', '6.6.87-generic'), false)
+  assert.equal(isWslEnvironment({ WSL_DISTRO_NAME: 'Ubuntu' }, 'darwin'), false)
+})
+
+test('isWindowsBinaryPathInWsl blocks Windows binary types on WSL', () => {
+  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.exe', { isWsl: true }), true)
+  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.cmd', { isWsl: true }), true)
+  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.bat', { isWsl: true }), true)
+  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/install.ps1', { isWsl: true }), true)
+  assert.equal(isWindowsBinaryPathInWsl('/usr/local/bin/hermes', { isWsl: true }), false)
+  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.exe', { isWsl: false }), false)
+})
+
+test('bundledRuntimeImportCheck selects platform-specific import checks', () => {
+  assert.equal(bundledRuntimeImportCheck('win32'), 'import fastapi, uvicorn, winpty')
+  assert.equal(bundledRuntimeImportCheck('darwin'), 'import fastapi, uvicorn, ptyprocess')
+  assert.equal(bundledRuntimeImportCheck('linux'), 'import fastapi, uvicorn, ptyprocess')
+})
+
+test('packaged electron entrypoints do not require unpackaged npm modules', () => {
+  const electronDir = __dirname
+  const entrypoints = ['main.cjs', 'preload.cjs', 'bootstrap-platform.cjs']
+  // - electron: provided by the electron runtime, always resolvable in packaged builds.
+  // - node-pty: hoisted by workspace dedup AND shipped via extraResources to
+  //   resources/native-deps/node-pty (see scripts/stage-native-deps.cjs). main.cjs
+  //   has a try/catch fallback at line ~38 that resolves the staged copy when the
+  //   bare require fails in the packaged asar, so the bare require itself is by
+  //   design rather than an oversight.
+  const allowedBareRequires = new Set(['electron', 'node-pty'])
+  const requirePattern = /require\(['"]([^'"]+)['"]\)/g
+
+  for (const entrypoint of entrypoints) {
+    const source = fs.readFileSync(path.join(electronDir, entrypoint), 'utf8')
+    const bareRequires = Array.from(source.matchAll(requirePattern))
+      .map(match => match[1])
+      .filter(specifier => !specifier.startsWith('node:'))
+      .filter(specifier => !specifier.startsWith('.'))
+      .filter(specifier => !allowedBareRequires.has(specifier))
+
+    assert.deepEqual(bareRequires, [], `${entrypoint} has unpackaged runtime requires`)
+  }
+})

apps/desktop/electron/bootstrap-runner.cjs

@@ -0,0 +1,591 @@
+'use strict'
+
+/**
+ * bootstrap-runner.cjs
+ *
+ * Drives apps/desktop's first-launch install of Hermes Agent by spawning
+ * scripts/install.ps1 stage-by-stage and streaming progress events back to
+ * the renderer.
+ *
+ * Wired from electron/main.cjs:
+ *   const { runBootstrap } = require('./bootstrap-runner.cjs')
+ *   const result = await runBootstrap({
+ *     installStamp,        // INSTALL_STAMP from main.cjs (may be null in dev)
+ *     activeRoot,          // ACTIVE_HERMES_ROOT
+ *     sourceRepoRoot,      // SOURCE_REPO_ROOT (for dev install.ps1 lookup)
+ *     hermesHome,          // HERMES_HOME
+ *     logRoot,             // HERMES_HOME/logs
+ *     emit: ev => {...}    // event sink (sender.send or similar)
+ *   })
+ *
+ * Emits events with shape:
+ *   { type: 'manifest',  stages: [{name, title, category, needs_user_input}, ...] }
+ *   { type: 'stage',     name, state: 'running'|'succeeded'|'skipped'|'failed',
+ *                        json?, durationMs?, error? }
+ *   { type: 'log',       stage?, line }      // raw line from install.ps1
+ *   { type: 'complete',  marker: <written marker payload> }
+ *   { type: 'failed',    stage?, error }     // bootstrap aborted
+ *
+ * Resolves with the same shape as the final 'complete' or 'failed' event so
+ * callers can await either way.
+ *
+ * NOT implemented yet (deferred to Phase 1E / 1F):
+ *   - User-facing retry / cancel from the renderer (event channels exist;
+ *     no UI consumes them yet)
+ */
+
+const fs = require('node:fs')
+const fsp = require('node:fs/promises')
+const path = require('node:path')
+const https = require('node:https')
+const { spawn } = require('node:child_process')
+
+const STAMP_COMMIT_RE = /^[0-9a-f]{7,40}$/i
+
+// Stages flagged needs_user_input=true in the manifest are skipped by the
+// runner (passed -NonInteractive to install.ps1, which the install script
+// itself handles by emitting skipped=true frames). The renderer / 1E onboarding
+// overlay takes over for those concerns (API keys, model, persona, gateway).
+// We let install.ps1's own -NonInteractive logic drive this rather than
+// filtering client-side -- single source of truth.
+
+// ---------------------------------------------------------------------------
+// install.ps1 source resolution
+// ---------------------------------------------------------------------------
+
+function installScriptName() {
+  return process.platform === 'win32' ? 'install.ps1' : 'install.sh'
+}
+
+function installScriptKind() {
+  return process.platform === 'win32' ? 'powershell' : 'posix'
+}
+
+function resolveLocalInstallScript(sourceRepoRoot) {
+  if (!sourceRepoRoot) return null
+  const candidate = path.join(sourceRepoRoot, 'scripts', installScriptName())
+  try {
+    fs.accessSync(candidate, fs.constants.R_OK)
+    return candidate
+  } catch {
+    return null
+  }
+}
+
+function bootstrapCacheDir(hermesHome) {
+  return path.join(hermesHome, 'bootstrap-cache')
+}
+
+function cachedScriptPath(hermesHome, commit) {
+  return path.join(bootstrapCacheDir(hermesHome), `install-${commit}.${process.platform === 'win32' ? 'ps1' : 'sh'}`)
+}
+
+function downloadInstallScript(commit, destPath) {
+  // Fetch from GitHub raw at the pinned commit. The raw URL with a SHA
+  // is immutable (unlike a branch ref), so we don't need integrity
+  // verification beyond "did the file we wrote pass a syntax probe."
+  const scriptName = installScriptName()
+  const url = `https://raw.githubusercontent.com/NousResearch/hermes-agent/${commit}/scripts/${scriptName}`
+  return new Promise((resolve, reject) => {
+    fs.mkdirSync(path.dirname(destPath), { recursive: true })
+    const tmpPath = destPath + '.tmp'
+    const out = fs.createWriteStream(tmpPath)
+    https
+      .get(url, res => {
+        if (res.statusCode === 301 || res.statusCode === 302) {
+          // GitHub raw shouldn't redirect for a SHA URL, but follow once
+          // defensively.
+          out.close()
+          fs.unlinkSync(tmpPath)
+          https
+            .get(res.headers.location, res2 => {
+              if (res2.statusCode !== 200) {
+                reject(
+                  new Error(`Failed to download ${scriptName}: HTTP ${res2.statusCode} from redirect ${res.headers.location}`)
+                )
+                return
+              }
+              const out2 = fs.createWriteStream(tmpPath)
+              res2.pipe(out2)
+              out2.on('finish', () => {
+                out2.close()
+                fs.renameSync(tmpPath, destPath)
+                resolve(destPath)
+              })
+              out2.on('error', reject)
+            })
+            .on('error', reject)
+          return
+        }
+        if (res.statusCode !== 200) {
+          out.close()
+          try {
+            fs.unlinkSync(tmpPath)
+          } catch {}
+          reject(new Error(`Failed to download ${scriptName}: HTTP ${res.statusCode} from ${url}`))
+          return
+        }
+        res.pipe(out)
+        out.on('finish', () => {
+          out.close()
+          fs.renameSync(tmpPath, destPath)
+          resolve(destPath)
+        })
+        out.on('error', err => {
+          try {
+            fs.unlinkSync(tmpPath)
+          } catch {}
+          reject(err)
+        })
+      })
+      .on('error', err => {
+        try {
+          fs.unlinkSync(tmpPath)
+        } catch {}
+        reject(err)
+      })
+  })
+}
+
+async function resolveInstallScript({ installStamp, sourceRepoRoot, hermesHome, emit }) {
+  // 1. Dev shortcut: prefer a local checkout's installer so we can iterate
+  //    without pushing. SOURCE_REPO_ROOT comes from main.cjs (path.resolve
+  //    of APP_ROOT/../..).
+  const localScript = resolveLocalInstallScript(sourceRepoRoot)
+  if (localScript) {
+    emit({ type: 'log', line: `[bootstrap] using local ${installScriptName()} at ${localScript}` })
+    return { path: localScript, source: 'local', kind: installScriptKind() }
+  }
+
+  // 2. Packaged path: download from GitHub at the pinned commit (1B's stamp).
+  if (!installStamp || !installStamp.commit || !STAMP_COMMIT_RE.test(installStamp.commit)) {
+    throw new Error(
+      `Cannot resolve ${installScriptName()}: no SOURCE_REPO_ROOT and no install stamp. ` +
+        'This packaged build was produced without a valid build-time stamp.'
+    )
+  }
+
+  const cached = cachedScriptPath(hermesHome, installStamp.commit)
+  try {
+    await fsp.access(cached, fs.constants.R_OK)
+    emit({ type: 'log', line: `[bootstrap] using cached ${installScriptName()} for ${installStamp.commit.slice(0, 12)}` })
+    return { path: cached, source: 'cache', commit: installStamp.commit, kind: installScriptKind() }
+  } catch {
+    // not cached; download
+  }
+
+  emit({ type: 'log', line: `[bootstrap] fetching ${installScriptName()} for ${installStamp.commit.slice(0, 12)} from GitHub` })
+  await downloadInstallScript(installStamp.commit, cached)
+  emit({ type: 'log', line: `[bootstrap] saved to ${cached}` })
+  return { path: cached, source: 'download', commit: installStamp.commit, kind: installScriptKind() }
+}
+
+// ---------------------------------------------------------------------------
+// powershell wrapper
+// ---------------------------------------------------------------------------
+
+function spawnPowerShell(scriptPath, args, { emit, stageName, abortSignal, hermesHome } = {}) {
+  return new Promise((resolve, reject) => {
+    const ps = process.platform === 'win32' ? 'powershell.exe' : 'pwsh'
+    const fullArgs = ['-NoProfile', '-ExecutionPolicy', 'Bypass', '-File', scriptPath, ...args]
+
+    const child = spawn(ps, fullArgs, {
+      stdio: ['ignore', 'pipe', 'pipe'],
+      env: {
+        ...process.env,
+        // Pass HERMES_HOME through so install.ps1 respects the caller's
+        // choice rather than re-computing the default.
+        HERMES_HOME: hermesHome || process.env.HERMES_HOME || ''
+      }
+    })
+
+    let stdout = ''
+    let stderr = ''
+    let killed = false
+
+    const onAbort = () => {
+      killed = true
+      try {
+        child.kill('SIGTERM')
+      } catch {}
+    }
+    if (abortSignal) {
+      if (abortSignal.aborted) {
+        onAbort()
+      } else {
+        abortSignal.addEventListener('abort', onAbort, { once: true })
+      }
+    }
+
+    child.stdout.setEncoding('utf8')
+    child.stderr.setEncoding('utf8')
+
+    // Stream stdout line-by-line so the renderer sees progress in real time.
+    let stdoutBuf = ''
+    child.stdout.on('data', chunk => {
+      stdout += chunk
+      stdoutBuf += chunk
+      let nl
+      while ((nl = stdoutBuf.indexOf('\n')) !== -1) {
+        const line = stdoutBuf.slice(0, nl).replace(/\r$/, '')
+        stdoutBuf = stdoutBuf.slice(nl + 1)
+        if (line) emit && emit({ type: 'log', stage: stageName, line })
+      }
+    })
+
+    let stderrBuf = ''
+    child.stderr.on('data', chunk => {
+      stderr += chunk
+      stderrBuf += chunk
+      let nl
+      while ((nl = stderrBuf.indexOf('\n')) !== -1) {
+        const line = stderrBuf.slice(0, nl).replace(/\r$/, '')
+        stderrBuf = stderrBuf.slice(nl + 1)
+        if (line) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${line}` })
+      }
+    })
+
+    child.on('error', err => {
+      if (abortSignal) abortSignal.removeEventListener('abort', onAbort)
+      reject(err)
+    })
+
+    child.on('close', (code, signal) => {
+      if (abortSignal) abortSignal.removeEventListener('abort', onAbort)
+      // Flush any trailing bytes
+      if (stdoutBuf) emit && emit({ type: 'log', stage: stageName, line: stdoutBuf })
+      if (stderrBuf) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${stderrBuf}` })
+      resolve({ stdout, stderr, code, signal, killed })
+    })
+  })
+}
+
+function spawnBash(scriptPath, args, { emit, stageName, abortSignal, hermesHome } = {}) {
+  return new Promise((resolve, reject) => {
+    const child = spawn('bash', [scriptPath, ...args], {
+      stdio: ['ignore', 'pipe', 'pipe'],
+      env: {
+        ...process.env,
+        HERMES_HOME: hermesHome || process.env.HERMES_HOME || ''
+      }
+    })
+
+    let stdout = ''
+    let stderr = ''
+    let killed = false
+
+    const onAbort = () => {
+      killed = true
+      try {
+        child.kill('SIGTERM')
+      } catch {}
+    }
+    if (abortSignal) {
+      if (abortSignal.aborted) {
+        onAbort()
+      } else {
+        abortSignal.addEventListener('abort', onAbort, { once: true })
+      }
+    }
+
+    child.stdout.setEncoding('utf8')
+    child.stderr.setEncoding('utf8')
+
+    let stdoutBuf = ''
+    child.stdout.on('data', chunk => {
+      stdout += chunk
+      stdoutBuf += chunk
+      let nl
+      while ((nl = stdoutBuf.indexOf('\n')) !== -1) {
+        const line = stdoutBuf.slice(0, nl).replace(/\r$/, '')
+        stdoutBuf = stdoutBuf.slice(nl + 1)
+        if (line) emit && emit({ type: 'log', stage: stageName, line })
+      }
+    })
+
+    let stderrBuf = ''
+    child.stderr.on('data', chunk => {
+      stderr += chunk
+      stderrBuf += chunk
+      let nl
+      while ((nl = stderrBuf.indexOf('\n')) !== -1) {
+        const line = stderrBuf.slice(0, nl).replace(/\r$/, '')
+        stderrBuf = stderrBuf.slice(nl + 1)
+        if (line) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${line}` })
+      }
+    })
+
+    child.on('error', err => {
+      if (abortSignal) abortSignal.removeEventListener('abort', onAbort)
+      reject(err)
+    })
+
+    child.on('close', (code, signal) => {
+      if (abortSignal) abortSignal.removeEventListener('abort', onAbort)
+      if (stdoutBuf) emit && emit({ type: 'log', stage: stageName, line: stdoutBuf })
+      if (stderrBuf) emit && emit({ type: 'log', stage: stageName, line: `stderr: ${stderrBuf}` })
+      resolve({ stdout, stderr, code, signal, killed })
+    })
+  })
+}
+
+// ---------------------------------------------------------------------------
+// Manifest + stage dispatch
+// ---------------------------------------------------------------------------
+
+// Build the install.ps1 pin args (-Commit / -Branch) from the install-stamp
+// so the repository stage clones the exact SHA the .exe was tested with
+// instead of falling back to install.ps1's default ($Branch = "main").
+function buildPinArgs(installStamp) {
+  const args = []
+  if (installStamp && installStamp.commit) {
+    args.push('-Commit', installStamp.commit)
+  }
+  if (installStamp && installStamp.branch) {
+    args.push('-Branch', installStamp.branch)
+  }
+  return args
+}
+
+function buildPosixPinArgs({ installStamp, activeRoot, hermesHome }) {
+  const args = ['--dir', activeRoot, '--hermes-home', hermesHome]
+  if (installStamp && installStamp.branch) {
+    args.push('--branch', installStamp.branch)
+  }
+  if (installStamp && installStamp.commit) {
+    args.push('--commit', installStamp.commit)
+  }
+  return args
+}
+
+async function fetchManifest({ scriptPath, installerKind, emit, hermesHome, activeRoot, installStamp }) {
+  const isPosix = installerKind === 'posix'
+  const args = isPosix
+    ? ['--manifest', ...buildPosixPinArgs({ installStamp, activeRoot, hermesHome })]
+    : ['-Manifest', ...buildPinArgs(installStamp)]
+  const result = await (isPosix ? spawnBash : spawnPowerShell)(scriptPath, args, {
+    emit,
+    stageName: '__manifest__',
+    hermesHome
+  })
+  if (result.code !== 0) {
+    throw new Error(`${isPosix ? 'install.sh --manifest' : 'install.ps1 -Manifest'} failed: exit ${result.code}\n${result.stderr || result.stdout}`)
+  }
+  // The manifest is the LAST JSON line on stdout (install.ps1 may print
+  // banner / info lines first depending on Console.OutputEncoding effects).
+  // Find the last line that parses as JSON with a `stages` field.
+  const lines = result.stdout.split(/\r?\n/).filter(Boolean)
+  for (let i = lines.length - 1; i >= 0; i--) {
+    try {
+      const parsed = JSON.parse(lines[i])
+      if (parsed && Array.isArray(parsed.stages)) {
+        return parsed
+      }
+    } catch {}
+  }
+  throw new Error(`${isPosix ? 'install.sh --manifest' : 'install.ps1 -Manifest'} produced no parseable JSON payload\n${result.stdout}`)
+}
+
+// Parse the JSON result frame from a stage run. The protocol guarantees
+// exactly one JSON line per stage in -Json or -Stage mode (post #27224 fix
+// for the double-emit bug we addressed in the install.ps1 PR).
+function parseStageResult(stdout) {
+  const lines = stdout.split(/\r?\n/).filter(Boolean)
+  for (let i = lines.length - 1; i >= 0; i--) {
+    try {
+      const parsed = JSON.parse(lines[i])
+      if (parsed && typeof parsed.ok === 'boolean' && typeof parsed.stage === 'string') {
+        return parsed
+      }
+    } catch {}
+  }
+  return null
+}
+
+async function runStage({ scriptPath, installerKind, stage, emit, hermesHome, activeRoot, abortSignal, installStamp }) {
+  const startedAt = Date.now()
+  emit({ type: 'stage', name: stage.name, state: 'running' })
+
+  const isPosix = installerKind === 'posix'
+  const args = isPosix
+    ? ['--stage', stage.name, '--non-interactive', '--json', ...buildPosixPinArgs({ installStamp, activeRoot, hermesHome })]
+    : ['-Stage', stage.name, '-NonInteractive', '-Json', ...buildPinArgs(installStamp)]
+  const result = await (isPosix ? spawnBash : spawnPowerShell)(
+    scriptPath,
+    args,
+    { emit, stageName: stage.name, abortSignal, hermesHome }
+  )
+
+  const durationMs = Date.now() - startedAt
+
+  if (result.killed) {
+    const ev = { type: 'stage', name: stage.name, state: 'failed', durationMs, error: 'cancelled by user' }
+    emit(ev)
+    return ev
+  }
+
+  const json = parseStageResult(result.stdout)
+
+  if (!json) {
+    const ev = {
+      type: 'stage',
+      name: stage.name,
+      state: 'failed',
+      durationMs,
+      error: `${isPosix ? 'install.sh --stage' : 'install.ps1 -Stage'} ${stage.name} produced no JSON result frame (exit=${result.code})`,
+      json: null
+    }
+    emit(ev)
+    return ev
+  }
+
+  if (json.ok && json.skipped) {
+    const ev = { type: 'stage', name: stage.name, state: 'skipped', durationMs, json }
+    emit(ev)
+    return ev
+  }
+  if (json.ok) {
+    const ev = { type: 'stage', name: stage.name, state: 'succeeded', durationMs, json }
+    emit(ev)
+    return ev
+  }
+  const ev = { type: 'stage', name: stage.name, state: 'failed', durationMs, json, error: json.reason || `exit code ${result.code}` }
+  emit(ev)
+  return ev
+}
+
+// ---------------------------------------------------------------------------
+// Per-run log file
+// ---------------------------------------------------------------------------
+
+function openRunLog(logRoot) {
+  fs.mkdirSync(logRoot, { recursive: true })
+  const ts = new Date().toISOString().replace(/[:.]/g, '-')
+  const logPath = path.join(logRoot, `bootstrap-${ts}.log`)
+  const stream = fs.createWriteStream(logPath, { flags: 'a' })
+  return { path: logPath, stream }
+}
+
+// ---------------------------------------------------------------------------
+// Public entrypoint
+// ---------------------------------------------------------------------------
+
+async function runBootstrap(opts) {
+  const {
+    installStamp,
+    activeRoot,
+    sourceRepoRoot,
+    hermesHome,
+    logRoot,
+    onEvent,
+    abortSignal,
+    writeMarker // callback to write the bootstrap-complete marker; main.cjs provides
+  } = opts
+
+  // Bail before spawning anything if the user already cancelled — otherwise an
+  // already-aborted signal would still fetch the manifest (a spawn) before the
+  // in-loop abort check fires.
+  if (abortSignal && abortSignal.aborted) {
+    if (typeof onEvent === 'function') {
+      try {
+        onEvent({ type: 'failed', error: 'bootstrap cancelled by user' })
+      } catch {}
+    }
+    return { ok: false, cancelled: true }
+  }
+
+  const runLog = openRunLog(logRoot || path.join(hermesHome, 'logs'))
+
+  // Tee every event to the runLog AND the caller's onEvent. This gives us a
+  // forensic trail per bootstrap run AND lets the renderer subscribe live.
+  const emit = ev => {
+    try {
+      runLog.stream.write(JSON.stringify(ev) + '\n')
+    } catch {}
+    try {
+      if (typeof onEvent === 'function') onEvent(ev)
+    } catch (err) {
+      // Don't let a subscriber bug crash the bootstrap
+      runLog.stream.write(`emit error: ${err && err.message}\n`)
+    }
+  }
+
+  emit({
+    type: 'log',
+    line:
+      `[bootstrap] starting at ${new Date().toISOString()}; ` +
+      `activeRoot=${activeRoot}; ` +
+      `stamp=${installStamp ? installStamp.commit.slice(0, 12) : '<none>'}; ` +
+      `runLog=${runLog.path}`
+  })
+
+  try {
+    // 1. Resolve the platform installer.
+    const scriptInfo = await resolveInstallScript({ installStamp, sourceRepoRoot, hermesHome, emit })
+    const installerKind = scriptInfo.kind || 'powershell'
+
+    // 2. Fetch manifest
+    const manifest = await fetchManifest({
+      scriptPath: scriptInfo.path,
+      installerKind,
+      emit,
+      hermesHome,
+      activeRoot,
+      installStamp
+    })
+    emit({
+      type: 'manifest',
+      stages: manifest.stages,
+      protocolVersion: manifest.protocol_version || manifest.protocolVersion || null
+    })
+
+    // 3. Iterate stages in order. Stages flagged needs_user_input are still
+    //    invoked -- install.ps1's own -NonInteractive handler in those stages
+    //    emits skipped=true. We trust the protocol rather than filtering
+    //    client-side.
+    for (const stage of manifest.stages) {
+      if (abortSignal && abortSignal.aborted) {
+        emit({ type: 'failed', error: 'bootstrap cancelled by user' })
+        return { ok: false, cancelled: true }
+      }
+      const ev = await runStage({
+        scriptPath: scriptInfo.path,
+        installerKind,
+        stage,
+        emit,
+        hermesHome,
+        activeRoot,
+        abortSignal,
+        installStamp
+      })
+      if (ev.state === 'failed') {
+        emit({ type: 'failed', stage: stage.name, error: ev.error || 'stage failed' })
+        return { ok: false, failedStage: stage.name, error: ev.error }
+      }
+    }
+
+    // 4. Write the bootstrap-complete marker.
+    const markerPayload = {
+      pinnedCommit: installStamp ? installStamp.commit : null,
+      pinnedBranch: installStamp ? installStamp.branch : null
+    }
+    const marker = typeof writeMarker === 'function' ? writeMarker(markerPayload) : markerPayload
+    emit({ type: 'complete', marker })
+    return { ok: true, marker }
+  } catch (err) {
+    emit({ type: 'failed', error: err.message || String(err) })
+    return { ok: false, error: err.message || String(err) }
+  } finally {
+    try {
+      runLog.stream.end()
+    } catch {}
+  }
+}
+
+module.exports = {
+  runBootstrap,
+  // Exposed for testability
+  parseStageResult,
+  resolveLocalInstallScript,
+  cachedScriptPath
+}

apps/desktop/electron/bootstrap-runner.test.cjs

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

apps/desktop/electron/entitlements.mac.inherit.plist

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+  <key>com.apple.security.cs.allow-jit</key>
+  <true/>
+  <key>com.apple.security.cs.allow-unsigned-executable-memory</key>
+  <true/>
+  <key>com.apple.security.cs.disable-library-validation</key>
+  <true/>
+</dict>
+</plist>

apps/desktop/electron/entitlements.mac.plist

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+  <key>com.apple.security.cs.allow-jit</key>
+  <true/>
+  <key>com.apple.security.cs.allow-unsigned-executable-memory</key>
+  <true/>
+  <key>com.apple.security.cs.disable-library-validation</key>
+  <true/>
+  <key>com.apple.security.device.audio-input</key>
+  <true/>
+</dict>
+</plist>

apps/desktop/electron/hardening.cjs

@@ -0,0 +1,184 @@
+const fs = require('node:fs')
+const path = require('node:path')
+const { fileURLToPath } = require('node:url')
+
+const DEFAULT_FETCH_TIMEOUT_MS = 15_000
+const DATA_URL_READ_MAX_BYTES = 16 * 1024 * 1024
+const TEXT_PREVIEW_SOURCE_MAX_BYTES = 64 * 1024 * 1024
+
+const SAFE_ENV_SUFFIXES = new Set(['dist', 'example', 'sample', 'template'])
+const SENSITIVE_EXTENSIONS = new Set(['.kdbx', '.p12', '.pem', '.pfx'])
+
+function resolveTimeoutMs(timeoutMs, fallbackMs = DEFAULT_FETCH_TIMEOUT_MS) {
+  const fallback =
+    Number.isFinite(fallbackMs) && Number(fallbackMs) > 0 ? Math.round(Number(fallbackMs)) : DEFAULT_FETCH_TIMEOUT_MS
+  const parsed = Number(timeoutMs)
+
+  if (Number.isFinite(parsed) && parsed > 0) {
+    return Math.round(parsed)
+  }
+
+  return fallback
+}
+
+function encryptDesktopSecret(value, safeStorageApi) {
+  const raw = String(value || '')
+
+  if (!raw) {
+    return null
+  }
+
+  let encryptionAvailable = false
+
+  try {
+    encryptionAvailable = Boolean(safeStorageApi?.isEncryptionAvailable?.())
+  } catch {
+    encryptionAvailable = false
+  }
+
+  if (!encryptionAvailable) {
+    throw new Error(
+      'Secure token storage is unavailable, so Hermes Desktop cannot save remote gateway tokens. ' +
+        'Set HERMES_DESKTOP_REMOTE_URL and HERMES_DESKTOP_REMOTE_TOKEN in your environment, or enable OS keychain access and try again.'
+    )
+  }
+
+  try {
+    return {
+      encoding: 'safeStorage',
+      value: safeStorageApi.encryptString(raw).toString('base64')
+    }
+  } catch (error) {
+    const detail = error instanceof Error && error.message ? ` (${error.message})` : ''
+    throw new Error(
+      `Failed to encrypt the remote gateway token for secure storage${detail}. ` +
+        'Set HERMES_DESKTOP_REMOTE_URL and HERMES_DESKTOP_REMOTE_TOKEN in your environment as a fallback.'
+    )
+  }
+}
+
+function sensitiveFileBlockReason(filePath) {
+  const normalized = String(filePath || '')
+    .replace(/\\/g, '/')
+    .toLowerCase()
+  const basename = path.basename(normalized)
+  const ext = path.extname(basename)
+
+  if (!basename) {
+    return null
+  }
+
+  if (normalized.includes('/.ssh/')) {
+    return 'SSH key/config files are blocked.'
+  }
+
+  if (normalized.includes('/.gnupg/')) {
+    return 'GPG key material is blocked.'
+  }
+
+  if (normalized.endsWith('/.aws/credentials')) {
+    return 'AWS credential files are blocked.'
+  }
+
+  if (basename === '.env') {
+    return '.env files are blocked because they commonly contain secrets.'
+  }
+
+  if (basename.startsWith('.env.')) {
+    const suffix = basename.slice('.env.'.length)
+    if (!SAFE_ENV_SUFFIXES.has(suffix)) {
+      return `${basename} is blocked because it appears to contain environment secrets.`
+    }
+  }
+
+  if (/^id_(rsa|dsa|ecdsa|ed25519)(?:\..+)?$/.test(basename) && !basename.endsWith('.pub')) {
+    return 'SSH private key files are blocked.'
+  }
+
+  if (SENSITIVE_EXTENSIONS.has(ext)) {
+    return `${ext} key/certificate files are blocked.`
+  }
+
+  if (basename === '.npmrc' || basename === '.netrc' || basename === '.pypirc') {
+    return `${basename} is blocked because it may include auth credentials.`
+  }
+
+  return null
+}
+
+function resolveRequestedFilePath(filePath, baseDir = process.cwd(), purpose = 'File read') {
+  const raw = String(filePath || '').trim()
+
+  if (!raw) {
+    throw new Error(`${purpose} failed: file path is required.`)
+  }
+
+  if (raw.includes('\0')) {
+    throw new Error(`${purpose} failed: file path is invalid.`)
+  }
+
+  if (/^file:/i.test(raw)) {
+    try {
+      return fileURLToPath(raw)
+    } catch {
+      throw new Error(`${purpose} failed: file URL is invalid.`)
+    }
+  }
+
+  const resolvedBase = path.resolve(String(baseDir || process.cwd()))
+  return path.resolve(resolvedBase, raw)
+}
+
+async function resolveReadableFileForIpc(filePath, options = {}) {
+  const purpose = String(options.purpose || 'File read')
+  const resolvedPath = resolveRequestedFilePath(filePath, options.baseDir, purpose)
+
+  if (options.blockSensitive !== false) {
+    const blockReason = sensitiveFileBlockReason(resolvedPath)
+    if (blockReason) {
+      throw new Error(`${purpose} blocked for sensitive file: ${blockReason}`)
+    }
+  }
+
+  let stat
+  try {
+    stat = await fs.promises.stat(resolvedPath)
+  } catch (error) {
+    const code = error && typeof error === 'object' ? error.code : ''
+    if (code === 'ENOENT' || code === 'ENOTDIR') {
+      throw new Error(`${purpose} failed: file does not exist.`)
+    }
+    throw new Error(`${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
+  }
+
+  if (stat.isDirectory()) {
+    throw new Error(`${purpose} failed: path points to a directory.`)
+  }
+
+  if (!stat.isFile()) {
+    throw new Error(`${purpose} failed: only regular files can be read.`)
+  }
+
+  const maxBytes = Number.isFinite(options.maxBytes) && Number(options.maxBytes) > 0 ? Number(options.maxBytes) : null
+  if (maxBytes && stat.size > maxBytes) {
+    throw new Error(`${purpose} failed: file is too large (${stat.size} bytes; limit ${maxBytes} bytes).`)
+  }
+
+  try {
+    await fs.promises.access(resolvedPath, fs.constants.R_OK)
+  } catch {
+    throw new Error(`${purpose} failed: file is not readable.`)
+  }
+
+  return { resolvedPath, stat }
+}
+
+module.exports = {
+  DATA_URL_READ_MAX_BYTES,
+  DEFAULT_FETCH_TIMEOUT_MS,
+  TEXT_PREVIEW_SOURCE_MAX_BYTES,
+  encryptDesktopSecret,
+  resolveReadableFileForIpc,
+  resolveTimeoutMs,
+  sensitiveFileBlockReason
+}

apps/desktop/electron/hardening.test.cjs

@@ -0,0 +1,116 @@
+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 {
+  DEFAULT_FETCH_TIMEOUT_MS,
+  encryptDesktopSecret,
+  resolveReadableFileForIpc,
+  resolveTimeoutMs,
+  sensitiveFileBlockReason
+} = require('./hardening.cjs')
+
+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)
+  assert.equal(resolveTimeoutMs(-25), DEFAULT_FETCH_TIMEOUT_MS)
+  assert.equal(resolveTimeoutMs('2750'), 2750)
+})
+
+test('encryptDesktopSecret requires available secure storage', () => {
+  assert.equal(
+    encryptDesktopSecret('', { isEncryptionAvailable: () => true, encryptString: () => Buffer.alloc(0) }),
+    null
+  )
+
+  assert.throws(
+    () => encryptDesktopSecret('token', { isEncryptionAvailable: () => false, encryptString: () => Buffer.alloc(0) }),
+    /Secure token storage is unavailable/
+  )
+})
+
+test('encryptDesktopSecret stores safeStorage base64 payload', () => {
+  const secret = encryptDesktopSecret('token-123', {
+    isEncryptionAvailable: () => true,
+    encryptString: value => Buffer.from(`enc:${value}`, 'utf8')
+  })
+
+  assert.deepEqual(secret, {
+    encoding: 'safeStorage',
+    value: Buffer.from('enc:token-123', 'utf8').toString('base64')
+  })
+})
+
+test('sensitiveFileBlockReason blocks obvious secret file patterns', () => {
+  assert.match(String(sensitiveFileBlockReason('/tmp/.env')), /\.env/)
+  assert.equal(sensitiveFileBlockReason('/tmp/.env.example'), null)
+  assert.match(String(sensitiveFileBlockReason('/Users/me/.ssh/id_ed25519')), /SSH/)
+  assert.match(String(sensitiveFileBlockReason('/tmp/server-cert.pem')), /\.pem/)
+})
+
+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 }))
+
+  const textPath = path.join(tempDir, 'notes.txt')
+  fs.writeFileSync(textPath, 'hello world', 'utf8')
+
+  const fromRelative = await resolveReadableFileForIpc('notes.txt', {
+    baseDir: tempDir,
+    maxBytes: 256,
+    purpose: 'File preview'
+  })
+  assert.equal(fromRelative.resolvedPath, textPath)
+  assert.equal(fromRelative.stat.size, 11)
+
+  const fromFileUrl = await resolveReadableFileForIpc(pathToFileURL(textPath).toString(), {
+    purpose: 'File preview'
+  })
+  assert.equal(fromFileUrl.resolvedPath, textPath)
+
+  await assert.rejects(
+    resolveReadableFileForIpc('missing.txt', {
+      baseDir: tempDir,
+      purpose: 'Text preview'
+    }),
+    /file does not exist/
+  )
+
+  const nestedDir = path.join(tempDir, 'directory')
+  fs.mkdirSync(nestedDir)
+  await assert.rejects(
+    resolveReadableFileForIpc(nestedDir, {
+      purpose: 'Text preview'
+    }),
+    /path points to a directory/
+  )
+
+  const largePath = path.join(tempDir, 'large.txt')
+  fs.writeFileSync(largePath, 'x'.repeat(40), 'utf8')
+  await assert.rejects(
+    resolveReadableFileForIpc(largePath, {
+      maxBytes: 8,
+      purpose: 'File preview'
+    }),
+    /file is too large/
+  )
+
+  const envPath = path.join(tempDir, '.env')
+  fs.writeFileSync(envPath, 'SECRET_TOKEN=123', 'utf8')
+  await assert.rejects(
+    resolveReadableFileForIpc(envPath, {
+      purpose: 'File preview'
+    }),
+    /blocked for sensitive file/
+  )
+
+  const envTemplatePath = path.join(tempDir, '.env.example')
+  fs.writeFileSync(envTemplatePath, 'EXAMPLE_TOKEN=value', 'utf8')
+  const envTemplate = await resolveReadableFileForIpc(envTemplatePath, {
+    purpose: 'File preview'
+  })
+  assert.equal(envTemplate.resolvedPath, envTemplatePath)
+})

apps/desktop/electron/preload.cjs

@@ -0,0 +1,112 @@
+const { contextBridge, ipcRenderer, webUtils } = require('electron')
+
+contextBridge.exposeInMainWorld('hermesDesktop', {
+  getConnection: () => ipcRenderer.invoke('hermes:connection'),
+  getBootProgress: () => ipcRenderer.invoke('hermes:boot-progress:get'),
+  getConnectionConfig: () => ipcRenderer.invoke('hermes:connection-config:get'),
+  saveConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:save', payload),
+  applyConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:apply', payload),
+  testConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:test', payload),
+  api: request => ipcRenderer.invoke('hermes:api', request),
+  notify: payload => ipcRenderer.invoke('hermes:notify', payload),
+  requestMicrophoneAccess: () => ipcRenderer.invoke('hermes:requestMicrophoneAccess'),
+  readFileDataUrl: filePath => ipcRenderer.invoke('hermes:readFileDataUrl', filePath),
+  readFileText: filePath => ipcRenderer.invoke('hermes:readFileText', filePath),
+  selectPaths: options => ipcRenderer.invoke('hermes:selectPaths', options),
+  writeClipboard: text => ipcRenderer.invoke('hermes:writeClipboard', text),
+  saveImageFromUrl: url => ipcRenderer.invoke('hermes:saveImageFromUrl', url),
+  saveImageBuffer: (data, ext) => ipcRenderer.invoke('hermes:saveImageBuffer', { data, ext }),
+  saveClipboardImage: () => ipcRenderer.invoke('hermes:saveClipboardImage'),
+  getPathForFile: file => {
+    try {
+      return webUtils.getPathForFile(file) || ''
+    } catch {
+      return ''
+    }
+  },
+  normalizePreviewTarget: (target, baseDir) => ipcRenderer.invoke('hermes:normalizePreviewTarget', target, baseDir),
+  watchPreviewFile: url => ipcRenderer.invoke('hermes:watchPreviewFile', url),
+  stopPreviewFileWatch: id => ipcRenderer.invoke('hermes:stopPreviewFileWatch', id),
+  setTitleBarTheme: payload => ipcRenderer.send('hermes:titlebar-theme', payload),
+  setPreviewShortcutActive: active => ipcRenderer.send('hermes:previewShortcutActive', Boolean(active)),
+  openExternal: url => ipcRenderer.invoke('hermes:openExternal', url),
+  fetchLinkTitle: url => ipcRenderer.invoke('hermes:fetchLinkTitle', url),
+  revealLogs: () => ipcRenderer.invoke('hermes:logs:reveal'),
+  getRecentLogs: () => ipcRenderer.invoke('hermes:logs:recent'),
+  readDir: dirPath => ipcRenderer.invoke('hermes:fs:readDir', dirPath),
+  gitRoot: startPath => ipcRenderer.invoke('hermes:fs:gitRoot', startPath),
+  terminal: {
+    dispose: id => ipcRenderer.invoke('hermes:terminal:dispose', id),
+    resize: (id, size) => ipcRenderer.invoke('hermes:terminal:resize', id, size),
+    start: options => ipcRenderer.invoke('hermes:terminal:start', options),
+    write: (id, data) => ipcRenderer.invoke('hermes:terminal:write', id, data),
+    onData: (id, callback) => {
+      const channel = `hermes:terminal:${id}:data`
+      const listener = (_event, payload) => callback(payload)
+      ipcRenderer.on(channel, listener)
+      return () => ipcRenderer.removeListener(channel, listener)
+    },
+    onExit: (id, callback) => {
+      const channel = `hermes:terminal:${id}:exit`
+      const listener = (_event, payload) => callback(payload)
+      ipcRenderer.on(channel, listener)
+      return () => ipcRenderer.removeListener(channel, listener)
+    }
+  },
+  onClosePreviewRequested: callback => {
+    const listener = () => callback()
+    ipcRenderer.on('hermes:close-preview-requested', listener)
+    return () => ipcRenderer.removeListener('hermes:close-preview-requested', listener)
+  },
+  onOpenUpdatesRequested: callback => {
+    const listener = () => callback()
+    ipcRenderer.on('hermes:open-updates', listener)
+    return () => ipcRenderer.removeListener('hermes:open-updates', listener)
+  },
+  onWindowStateChanged: callback => {
+    const listener = (_event, payload) => callback(payload)
+    ipcRenderer.on('hermes:window-state-changed', listener)
+    return () => ipcRenderer.removeListener('hermes:window-state-changed', listener)
+  },
+  onPreviewFileChanged: callback => {
+    const listener = (_event, payload) => callback(payload)
+    ipcRenderer.on('hermes:preview-file-changed', listener)
+    return () => ipcRenderer.removeListener('hermes:preview-file-changed', listener)
+  },
+  onBackendExit: callback => {
+    const listener = (_event, payload) => callback(payload)
+    ipcRenderer.on('hermes:backend-exit', listener)
+    return () => ipcRenderer.removeListener('hermes:backend-exit', listener)
+  },
+  onBootProgress: callback => {
+    const listener = (_event, payload) => callback(payload)
+    ipcRenderer.on('hermes:boot-progress', listener)
+    return () => ipcRenderer.removeListener('hermes:boot-progress', listener)
+  },
+  // First-launch bootstrap progress -- emitted by the install.ps1 stage
+  // runner in main.cjs (apps/desktop/electron/bootstrap-runner.cjs).
+  // Renderer's install overlay subscribes to live events and queries the
+  // current snapshot via getBootstrapState() to recover after a devtools
+  // reload mid-bootstrap.
+  getBootstrapState: () => ipcRenderer.invoke('hermes:bootstrap:get'),
+  resetBootstrap: () => ipcRenderer.invoke('hermes:bootstrap:reset'),
+  repairBootstrap: () => ipcRenderer.invoke('hermes:bootstrap:repair'),
+  cancelBootstrap: () => ipcRenderer.invoke('hermes:bootstrap:cancel'),
+  onBootstrapEvent: callback => {
+    const listener = (_event, payload) => callback(payload)
+    ipcRenderer.on('hermes:bootstrap:event', listener)
+    return () => ipcRenderer.removeListener('hermes:bootstrap:event', listener)
+  },
+  getVersion: () => ipcRenderer.invoke('hermes:version'),
+  updates: {
+    check: () => ipcRenderer.invoke('hermes:updates:check'),
+    apply: opts => ipcRenderer.invoke('hermes:updates:apply', opts),
+    getBranch: () => ipcRenderer.invoke('hermes:updates:branch:get'),
+    setBranch: name => ipcRenderer.invoke('hermes:updates:branch:set', name),
+    onProgress: callback => {
+      const listener = (_event, payload) => callback(payload)
+      ipcRenderer.on('hermes:updates:progress', listener)
+      return () => ipcRenderer.removeListener('hermes:updates:progress', listener)
+    }
+  }
+})

apps/desktop/eslint.config.mjs

@@ -0,0 +1,122 @@
+import js from '@eslint/js'
+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'
+
+const noopRule = {
+  meta: { schema: [], type: 'problem' },
+  create: () => ({})
+}
+
+const customRules = {
+  rules: {
+    'no-process-cwd': noopRule,
+    'no-process-env-top-level': noopRule,
+    'no-sync-fs': noopRule,
+    'no-top-level-dynamic-import': noopRule,
+    'no-top-level-side-effects': noopRule
+  }
+}
+
+export default [
+  {
+    ignores: ['**/node_modules/**', '**/dist/**', 'src/**/*.js']
+  },
+  js.configs.recommended,
+  {
+    files: ['**/*.{ts,tsx}'],
+    languageOptions: {
+      globals: {
+        ...globals.browser,
+        ...globals.node
+      },
+      parser: typescriptParser,
+      parserOptions: {
+        ecmaFeatures: { jsx: true },
+        ecmaVersion: 'latest',
+        sourceType: 'module'
+      }
+    },
+    plugins: {
+      '@typescript-eslint': typescriptEslint,
+      'custom-rules': customRules,
+      perfectionist,
+      react: reactPlugin,
+      'react-compiler': reactCompiler,
+      'react-hooks': hooksPlugin,
+      'unused-imports': unusedImports
+    },
+    rules: {
+      '@typescript-eslint/consistent-type-imports': ['error', { prefer: 'type-imports' }],
+      '@typescript-eslint/no-unused-vars': 'off',
+      curly: ['error', 'all'],
+      'no-fallthrough': ['error', { allowEmptyCase: true }],
+      'no-undef': 'off',
+      'no-unused-vars': 'off',
+      'padding-line-between-statements': [
+        1,
+        {
+          blankLine: 'always',
+          next: [
+            'block-like',
+            'block',
+            'return',
+            'if',
+            'class',
+            'continue',
+            'debugger',
+            'break',
+            'multiline-const',
+            'multiline-let'
+          ],
+          prev: '*'
+        },
+        {
+          blankLine: 'always',
+          next: '*',
+          prev: ['case', 'default', 'multiline-const', 'multiline-let', 'multiline-block-like']
+        },
+        { blankLine: 'never', next: ['block', 'block-like'], prev: ['case', 'default'] },
+        { blankLine: 'always', next: ['block', 'block-like'], prev: ['block', 'block-like'] },
+        { blankLine: 'always', next: ['empty'], prev: 'export' },
+        { blankLine: 'never', next: 'iife', prev: ['block', 'block-like', 'empty'] }
+      ],
+      'perfectionist/sort-exports': ['error', { order: 'asc', type: 'natural' }],
+      'perfectionist/sort-imports': [
+        'error',
+        {
+          groups: ['side-effect', 'builtin', 'external', 'internal', 'parent', 'sibling', 'index'],
+          order: 'asc',
+          type: 'natural'
+        }
+      ],
+      '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'
+    },
+    settings: {
+      react: { version: 'detect' }
+    }
+  },
+  {
+    files: ['**/*.js', '**/*.cjs'],
+    ignores: ['**/node_modules/**', '**/dist/**'],
+    languageOptions: {
+      ecmaVersion: 'latest',
+      globals: { ...globals.node },
+      sourceType: 'commonjs'
+    }
+  },
+  {
+    ignores: ['*.config.*']
+  }
+]

apps/desktop/index.html

@@ -0,0 +1,14 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="icon" href="/apple-touch-icon.png" />
+    <link rel="apple-touch-icon" href="/apple-touch-icon.png" />
+    <title>Hermes</title>
+  </head>
+  <body>
+    <div id="root" class="scrollbar-dt"></div>
+    <script type="module" src="/src/main.tsx"></script>
+  </body>
+</html>

apps/desktop/package.json

@@ -0,0 +1,232 @@
+{
+  "name": "hermes",
+  "productName": "Hermes",
+  "private": true,
+  "version": "0.15.1",
+  "description": "Native desktop shell for Hermes Agent.",
+  "author": "Nous Research",
+  "type": "module",
+  "main": "electron/main.cjs",
+  "scripts": {
+    "dev": "concurrently -k \"npm:dev:renderer\" \"npm:dev:electron\"",
+    "dev:fake-boot": "cross-env HERMES_DESKTOP_BOOT_FAKE=1 HERMES_DESKTOP_BOOT_FAKE_STEP_MS=650 npm run dev",
+    "dev:renderer": "node scripts/assert-root-install.cjs && vite --host 127.0.0.1 --port 5174",
+    "dev:electron": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron .",
+    "profile:main": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron --inspect=9229 .",
+    "profile:main:cpu": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 NODE_OPTIONS=--cpu-prof HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron .",
+    "start": "npm run build && electron .",
+    "build": "node scripts/assert-root-install.cjs && node scripts/write-build-stamp.cjs && node scripts/stage-native-deps.cjs && tsc -b && vite build",
+    "builder": "cross-env NODE_OPTIONS=--max-old-space-size=16384 electron-builder",
+    "pack": "npm run build && npm run builder -- --dir",
+    "dist": "npm run build && npm run builder",
+    "dist:mac": "npm run build && npm run builder -- --mac",
+    "dist:mac:dmg": "npm run build && npm run builder -- --mac dmg",
+    "dist:mac:zip": "npm run build && npm run builder -- --mac zip",
+    "dist:win": "npm run build && npm run builder -- --win",
+    "dist:win:msi": "npm run build && npm run builder -- --win msi",
+    "dist:win:nsis": "npm run build && npm run builder -- --win nsis",
+    "dist:linux": "npm run build && npm run builder -- --linux AppImage deb rpm",
+    "test:desktop": "node scripts/test-desktop.mjs",
+    "test:desktop:all": "node scripts/test-desktop.mjs all",
+    "test:desktop:dmg": "node scripts/test-desktop.mjs dmg",
+    "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",
+    "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'",
+    "fix": "npm run lint:fix && npm run fmt",
+    "test:ui": "vitest run --environment jsdom",
+    "preview": "node scripts/assert-root-install.cjs && vite preview --host 127.0.0.1 --port 4174"
+  },
+  "dependencies": {
+    "@assistant-ui/react": "^0.12.28",
+    "@assistant-ui/react-streamdown": "^0.1.11",
+    "@audiowave/react": "^0.6.2",
+    "@chenglou/pretext": "^0.0.6",
+    "@dnd-kit/core": "^6.3.1",
+    "@dnd-kit/sortable": "^10.0.0",
+    "@dnd-kit/utilities": "^3.2.2",
+    "@hermes/shared": "file:../shared",
+    "@nanostores/react": "^1.1.0",
+    "@nous-research/ui": "^0.13.0",
+    "@radix-ui/react-slot": "^1.2.4",
+    "@streamdown/code": "^1.1.1",
+    "@tabler/icons-react": "^3.41.1",
+    "@tailwindcss/typography": "^0.5.19",
+    "@tailwindcss/vite": "^4.2.4",
+    "@tanstack/react-query": "^5.100.6",
+    "@tanstack/react-virtual": "^3.13.24",
+    "@vscode/codicons": "^0.0.45",
+    "@xterm/addon-fit": "^0.11.0",
+    "@xterm/addon-unicode11": "^0.9.0",
+    "@xterm/addon-web-links": "^0.12.0",
+    "@xterm/addon-webgl": "^0.19.0",
+    "@xterm/xterm": "^6.0.0",
+    "class-variance-authority": "^0.7.1",
+    "clsx": "^2.1.1",
+    "cmdk": "^1.1.1",
+    "hast-util-from-html-isomorphic": "^2.0.0",
+    "hast-util-to-text": "^4.0.2",
+    "ignore": "^7.0.5",
+    "katex": "^0.16.45",
+    "leva": "^0.10.1",
+    "motion": "^12.38.0",
+    "nanostores": "^1.3.0",
+    "node-pty": "1.1.0",
+    "radix-ui": "^1.4.3",
+    "react": "^19.2.5",
+    "react-arborist": "^3.5.0",
+    "react-dom": "^19.2.5",
+    "react-router-dom": "^7.14.2",
+    "react-shiki": "^0.9.3",
+    "remark-math": "^6.0.0",
+    "shiki": "^4.0.2",
+    "streamdown": "^2.5.0",
+    "tailwind-merge": "^3.5.0",
+    "tailwindcss": "^4.2.4",
+    "tw-shimmer": "^0.4.11",
+    "unicode-animations": "^1.0.3",
+    "unified": "^11.0.5",
+    "unist-util-visit-parents": "^6.0.2",
+    "vfile": "^6.0.3",
+    "web-haptics": "^0.0.6"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.39.4",
+    "@testing-library/react": "^16.3.2",
+    "@types/hast": "^3.0.4",
+    "@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": "^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",
+    "jsdom": "^29.1.1",
+    "prettier": "^3.8.3",
+    "rcedit": "^5.0.2",
+    "typescript": "^6.0.3",
+    "vite": "^8.0.10",
+    "vitest": "^4.1.5",
+    "wait-on": "^9.0.5"
+  },
+  "build": {
+    "electronVersion": "40.9.3",
+    "appId": "com.nousresearch.hermes",
+    "productName": "Hermes",
+    "executableName": "Hermes",
+    "artifactName": "Hermes-${version}-${os}-${arch}.${ext}",
+    "icon": "assets/icon",
+    "directories": {
+      "output": "release"
+    },
+    "files": [
+      "dist/**",
+      "assets/**",
+      "electron/**",
+      "public/**",
+      "package.json"
+    ],
+    "beforeBuild": "scripts/before-build.cjs",
+    "afterPack": "scripts/after-pack.cjs",
+    "extraResources": [
+      {
+        "from": "build/install-stamp.json",
+        "to": "install-stamp.json"
+      },
+      {
+        "from": "build/native-deps",
+        "to": "native-deps"
+      },
+      {
+        "from": "assets/icon.ico",
+        "to": "icon.ico"
+      }
+    ],
+    "asar": true,
+    "afterSign": "scripts/notarize.cjs",
+    "asarUnpack": [
+      "**/*.node",
+      "**/prebuilds/**"
+    ],
+    "mac": {
+      "category": "public.app-category.developer-tools",
+      "entitlements": "electron/entitlements.mac.plist",
+      "entitlementsInherit": "electron/entitlements.mac.inherit.plist",
+      "extendInfo": {
+        "CFBundleDisplayName": "Hermes",
+        "CFBundleExecutable": "Hermes",
+        "CFBundleName": "Hermes",
+        "NSAudioCaptureUsageDescription": "Hermes uses audio capture for voice conversations.",
+        "NSMicrophoneUsageDescription": "Hermes uses the microphone for voice input and voice conversations."
+      },
+      "gatekeeperAssess": false,
+      "hardenedRuntime": true,
+      "target": [
+        "dmg",
+        "zip"
+      ]
+    },
+    "dmg": {
+      "title": "Install Hermes",
+      "backgroundColor": "#f5f5f7",
+      "iconSize": 96,
+      "window": {
+        "width": 560,
+        "height": 360
+      },
+      "contents": [
+        {
+          "x": 160,
+          "y": 170,
+          "type": "file"
+        },
+        {
+          "x": 400,
+          "y": 170,
+          "type": "link",
+          "path": "/Applications"
+        }
+      ]
+    },
+    "win": {
+      "legalTrademarks": "Hermes",
+      "target": [
+        "nsis",
+        "msi"
+      ],
+      "signAndEditExecutable": false
+    },
+    "linux": {
+      "category": "Development",
+      "maintainer": "Nous Research <support@nousresearch.com>",
+      "synopsis": "Native desktop shell for Hermes Agent.",
+      "target": [
+        "AppImage",
+        "deb",
+        "rpm"
+      ]
+    },
+    "nsis": {
+      "oneClick": false,
+      "allowToChangeInstallationDirectory": true,
+      "perMachine": false,
+      "shortcutName": "Hermes",
+      "uninstallDisplayName": "Hermes",
+      "warningsAsErrors": false
+    }
+  }
+}

apps/desktop/preview-demo.html

@@ -0,0 +1,65 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8" />
+<meta name="viewport" content="width=device-width,initial-scale=1" />
+<title>Preview Demo</title>
+<style>
+  :root { color-scheme: dark; }
+  html, body { height: 100%; margin: 0; }
+  body {
+    font-family: ui-sans-serif, system-ui, -apple-system, "SF Pro Text", sans-serif;
+    background: radial-gradient(1200px 600px at 20% 10%, #4a1a33 0%, #2a1020 40%, #120810 100%);
+    color: #ffe4f1;
+    display: grid;
+    place-items: center;
+    padding: 2rem;
+  }
+  .card {
+    max-width: 520px;
+    padding: 2rem 2.25rem;
+    border: 1px solid rgba(255,182,214,0.18);
+    border-radius: 14px;
+    background: rgba(28,14,22,0.6);
+    backdrop-filter: blur(6px);
+    box-shadow: 0 10px 40px rgba(0,0,0,0.4);
+  }
+  h1 {
+    margin: 0 0 0.5rem;
+    font-size: 1.5rem;
+    letter-spacing: 0.01em;
+  }
+  p { margin: 0.35rem 0; opacity: 0.85; line-height: 1.5; }
+  .dot {
+    display: inline-block; width: 10px; height: 10px; border-radius: 50%;
+    background: #ff6fb5; margin-right: 0.5rem;
+    box-shadow: 0 0 12px #ff6fb5;
+    animation: pulse 1.6s ease-in-out infinite;
+  }
+  @keyframes pulse {
+    0%,100% { transform: scale(1); opacity: 1; }
+    50%     { transform: scale(1.4); opacity: 0.6; }
+  }
+  code {
+    background: rgba(255,182,214,0.10);
+    padding: 0.1rem 0.35rem;
+    border-radius: 4px;
+    font-size: 0.9em;
+  }
+  .time { font-variant-numeric: tabular-nums; opacity: 0.7; font-size: 0.85rem; margin-top: 1rem; }
+</style>
+</head>
+<body>
+  <div class="card">
+    <h1><span class="dot"></span>preview-demo.html</h1>
+    <p>Tiny standalone HTML artifact — no server, no build step.</p>
+    <p>Open directly in a browser via <code>file://</code>.</p>
+    <p class="time" id="t"></p>
+  </div>
+  <script>
+    const el = document.getElementById('t');
+    const tick = () => { el.textContent = new Date().toLocaleString(); };
+    tick(); setInterval(tick, 1000);
+  </script>
+</body>
+</html>