feat(gui): make desktop setup flow real and testable

Add a GUI-first setup gate and runtime state API so desktop onboarding is safe, iterative, and works with isolated fresh-mode installs. Scaffold and wire the desktop shell/runtime pieces so this branch runs end-to-end without disturbing existing user installs.

.dockerignore

@@ -5,15 +5,7 @@
 
 # Dependencies
 node_modules
-**/node_modules
 .venv
-**/.venv
-
-# Built artifacts that are regenerated inside the image.  Excluded so local
-# rebuilds on the developer's machine don't invalidate the npm-install layer
-# that now depends on the full ui-tui/packages/hermes-ink/ tree being present.
-ui-tui/dist/
-ui-tui/packages/hermes-ink/dist/
 
 # CI/CD
 .github

.env.example

@@ -398,19 +398,3 @@ IMAGE_TOOLS_DEBUG=false
 # 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
-
-# =============================================================================
-# MICROSOFT TEAMS INTEGRATION
-# =============================================================================
-# Register a Bot in Azure: https://dev.botframework.com/ → "Register a bot"
-# Or use Azure Portal: Azure Active Directory → App registrations → New registration
-# Then add the bot to Teams via the Bot Framework or App Studio.
-#
-# TEAMS_CLIENT_ID=                     # Azure AD App (client) ID
-# TEAMS_CLIENT_SECRET=                 # Azure AD client secret value
-# TEAMS_TENANT_ID=                     # Azure AD tenant ID (or "common" for multi-tenant)
-# TEAMS_ALLOWED_USERS=                 # Comma-separated AAD object IDs or UPNs
-# TEAMS_ALLOW_ALL_USERS=false          # Set true to skip the allowlist
-# TEAMS_HOME_CHANNEL=                  # Default channel/chat ID for cron delivery
-# TEAMS_HOME_CHANNEL_NAME=             # Display name for the home channel
-# TEAMS_PORT=3978                      # Webhook listen port (Bot Framework default)

.github/actions/nix-setup/action.yml

@@ -1,18 +1,8 @@
 name: 'Setup Nix'
-description: 'Install Nix and configure Cachix binary cache'
-
-inputs:
-  cachix-auth-token:
-    description: 'Cachix auth token (enables push). Omit for read-only.'
-    required: false
-    default: ''
+description: 'Install Nix with DeterminateSystems and enable magic-nix-cache'
 
 runs:
   using: composite
   steps:
     - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25 # v22
-    - uses: cachix/cachix-action@1eb2ef646ac0255473d23a5907ad7b04ce94065c # v17
-      with:
-        name: hermes-agent
-        authToken: ${{ inputs.cachix-auth-token }}
-      continue-on-error: true
+    - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39 # v13

.github/workflows/deploy-site.yml

@@ -76,16 +76,6 @@ jobs:
         run: |
           mkdir -p _site/docs
           cp -r website/build/* _site/docs/
-          # llms.txt / llms-full.txt are also published at the site root
-          # (https://hermes-agent.nousresearch.com/llms.txt) because some
-          # agents and IDE plugins probe the classic root-level path rather
-          # than /docs/llms.txt. Same file, two URLs, one source of truth.
-          if [ -f website/build/llms.txt ]; then
-            cp website/build/llms.txt _site/llms.txt
-          fi
-          if [ -f website/build/llms-full.txt ]; then
-            cp website/build/llms-full.txt _site/llms-full.txt
-          fi
 
       - name: Upload artifact
         uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa  # v3

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

@@ -0,0 +1,68 @@
+name: Nix Lockfile Check
+
+on:
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pull-requests: write
+
+concurrency:
+  group: nix-lockfile-check-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    steps:
+      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+
+      - uses: ./.github/actions/nix-setup
+
+      - name: Resolve head SHA
+        id: sha
+        shell: bash
+        run: |
+          FULL="${{ github.event.pull_request.head.sha || github.sha }}"
+          echo "full=$FULL" >> "$GITHUB_OUTPUT"
+          echo "short=${FULL:0:7}" >> "$GITHUB_OUTPUT"
+
+      - name: Check lockfile hashes
+        id: check
+        continue-on-error: true
+        env:
+          LINK_SHA: ${{ steps.sha.outputs.full }}
+        run: nix run .#fix-lockfiles -- --check
+
+      - name: Post sticky PR comment (stale)
+        if: steps.check.outputs.stale == 'true' && github.event_name == 'pull_request'
+        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
+        with:
+          header: nix-lockfile-check
+          message: |
+            ### ⚠️ npm lockfile hash out of date
+
+            Checked against commit [`${{ steps.sha.outputs.short }}`](${{ github.server_url }}/${{ github.repository }}/commit/${{ steps.sha.outputs.full }}) (PR head at check time).
+
+            The `hash = "sha256-..."` line in these nix files no longer matches the committed `package-lock.json`:
+
+            ${{ steps.check.outputs.report }}
+
+            #### Apply the fix
+
+            - [ ] **Apply lockfile fix** — tick to push a commit with the correct hashes to this PR branch
+            - Or [run the Nix Lockfile Fix workflow](${{ github.server_url }}/${{ github.repository }}/actions/workflows/nix-lockfile-fix.yml) manually (pass PR `#${{ github.event.pull_request.number }}`)
+            - Or locally: `nix run .#fix-lockfiles -- --apply` and commit the diff
+
+      - name: Clear sticky PR comment (resolved)
+        if: steps.check.outputs.stale == 'false' && github.event_name == 'pull_request'
+        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
+        with:
+          header: nix-lockfile-check
+          delete: true
+
+      - name: Fail if stale
+        if: steps.check.outputs.stale == 'true'
+        run: exit 1

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

@@ -1,13 +1,6 @@
 name: Nix Lockfile Fix
 
 on:
-  push:
-    branches: [main]
-    paths:
-      - 'ui-tui/package-lock.json'
-      - 'ui-tui/package.json'
-      - 'web/package-lock.json'
-      - 'web/package.json'
   workflow_dispatch:
     inputs:
       pr_number:
@@ -26,105 +19,9 @@ concurrency:
   cancel-in-progress: false
 
 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
-  # update commit directly to main so Nix builds never stay broken.
-  #
-  # Safety invariants:
-  #   1. The fix commit only touches nix/*.nix files, which are NOT in
-  #      the paths filter above, so this cannot re-trigger itself.
-  #   2. An explicit file-whitelist check before commit aborts if
-  #      fix-lockfiles ever modifies unexpected files.
-  #   3. Job-level concurrency with cancel-in-progress: true ensures
-  #      back-to-back pushes collapse to the newest; ref: main checkout
-  #      always operates on the latest branch state.
-  #   4. Uses a GitHub App token (not GITHUB_TOKEN) so the fix commit
-  #      triggers downstream nix.yml verification.
-  auto-fix-main:
-    if: github.event_name == 'push'
-    runs-on: ubuntu-latest
-    timeout-minutes: 25
-    concurrency:
-      group: auto-fix-main
-      cancel-in-progress: true
-    steps:
-      - name: Generate GitHub App token
-        id: app-token
-        uses: actions/create-github-app-token@7bfa3a4717ef143a604ee0a99d859b8886a96d00  # v1.9.3
-        with:
-          app-id: ${{ secrets.APP_ID }}
-          private-key: ${{ secrets.APP_PRIVATE_KEY }}
-
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          ref: main
-          token: ${{ steps.app-token.outputs.token }}
-
-      - uses: ./.github/actions/nix-setup
-        with:
-          cachix-auth-token: ${{ secrets.CACHIX_AUTH_TOKEN }}
-
-      - name: Apply lockfile hashes
-        id: apply
-        run: nix run .#fix-lockfiles -- --apply
-
-      - name: Commit & push
-        if: steps.apply.outputs.changed == 'true'
-        shell: bash
-        run: |
-          set -euo pipefail
-
-          # Ensure only nix files were modified — prevents accidental
-          # self-triggering if fix-lockfiles ever touches package files.
-          unexpected="$(git diff --name-only | grep -Ev '^nix/(tui|web)\.nix$' || true)"
-          if [ -n "$unexpected" ]; then
-            echo "::error::Unexpected modified files: $unexpected"
-            exit 1
-          fi
-
-          # Record the base SHA before committing — used to detect package
-          # file changes if we need to rebase after a non-fast-forward push.
-          BASE_SHA="$(git rev-parse HEAD)"
-
-          git config user.name 'github-actions[bot]'
-          git config user.email '41898282+github-actions[bot]@users.noreply.github.com'
-          git add nix/tui.nix nix/web.nix
-          git commit -m "fix(nix): auto-refresh npm lockfile hashes" \
-            -m "Source: $GITHUB_SHA" \
-            -m "Run: $GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
-
-          # Retry push with rebase in case main advanced with an unrelated
-          # commit during the nix build. Without this, a non-fast-forward
-          # rejection silently loses the fix. If package files changed during
-          # the rebase, abort — a fresh auto-fix run will handle the new state.
-          for attempt in 1 2 3; do
-            if git push origin HEAD:main; then
-              exit 0
-            fi
-            echo "::warning::Push attempt $attempt failed (non-fast-forward?), rebasing…"
-            git fetch origin main
-
-            # If package files changed between our base and the new main,
-            # our computed hashes are stale. Abort and let the next triggered
-            # run recompute from the correct package-lock state.
-            pkg_changed="$(git diff --name-only "$BASE_SHA"..origin/main -- \
-              'ui-tui/package-lock.json' 'ui-tui/package.json' \
-              'web/package-lock.json' 'web/package.json' || true)"
-            if [ -n "$pkg_changed" ]; then
-              echo "::warning::Package files changed since hash computation — aborting; a fresh run will recompute"
-              exit 0
-            fi
-
-            git rebase origin/main
-          done
-          echo "::error::Failed to push after 3 rebase attempts"
-          exit 1
-
-  # ── PR fix (manual / checkbox) ─────────────────────────────────────
-  # Existing behavior: run on manual dispatch OR when a task-list
-  # checkbox in the sticky lockfile-check comment flips from [ ] to [x].
   fix:
+    # Run on manual dispatch OR when a task-list checkbox in the sticky
+    # lockfile-check comment flips from `[ ]` to `[x]`.
     if: |
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'issue_comment'
@@ -202,12 +99,10 @@ jobs:
           fetch-depth: 0
 
       - uses: ./.github/actions/nix-setup
-        with:
-          cachix-auth-token: ${{ secrets.CACHIX_AUTH_TOKEN }}
 
       - name: Apply lockfile hashes
         id: apply
-        run: nix run .#fix-lockfiles
+        run: nix run .#fix-lockfiles -- --apply
 
       - name: Commit & push
         if: steps.apply.outputs.changed == 'true'

.github/workflows/nix.yml

@@ -7,7 +7,6 @@ on:
 
 permissions:
   contents: read
-  pull-requests: write
 
 concurrency:
   group: nix-${{ github.ref }}
@@ -23,95 +22,12 @@ jobs:
     steps:
       - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
       - uses: ./.github/actions/nix-setup
-        with:
-          cachix-auth-token: ${{ secrets.CACHIX_AUTH_TOKEN }}
-
-      - name: Resolve head SHA
-        if: github.event_name == 'pull_request'
-        id: sha
-        shell: bash
-        run: |
-          FULL="${{ github.event.pull_request.head.sha || github.sha }}"
-          echo "full=$FULL" >> "$GITHUB_OUTPUT"
-          echo "short=${FULL:0:7}" >> "$GITHUB_OUTPUT"
-
       - name: Check flake
-        id: flake
         if: runner.os == 'Linux'
-        continue-on-error: true
         run: nix flake check --print-build-logs
-
       - name: Build package
-        id: build
         if: runner.os == 'Linux'
-        continue-on-error: true
         run: nix build --print-build-logs
-
-      # When the real Nix build fails, run a targeted diagnostic to see if
-      # the failure is specifically a stale npm lockfile hash in one of the
-      # known npm subpackages (tui / web).  This avoids surfacing a generic
-      # "build failed" message when the fix is a single known command.
-      - name: Diagnose npm lockfile hashes
-        id: hash_check
-        if: (steps.flake.outcome == 'failure' || steps.build.outcome == 'failure') && runner.os == 'Linux'
-        continue-on-error: true
-        env:
-          LINK_SHA: ${{ steps.sha.outputs.full }}
-        run: nix run .#fix-lockfiles -- --check
-
-      # If fix-lockfiles itself crashes (infrastructure blip, cache throttle,
-      # etc.) it won't set stale=true/false.  Treat that as a distinct failure
-      # mode rather than silently ignoring it.
-      - name: Fail if hash check crashed without reporting
-        if: steps.hash_check.outcome == 'failure' && steps.hash_check.outputs.stale != 'true' && steps.hash_check.outputs.stale != 'false'
-        run: |
-          echo "::error::fix-lockfiles exited without reporting stale status — likely an infrastructure or script failure"
-          exit 1
-
-      - name: Post sticky PR comment (stale hashes)
-        if: steps.hash_check.outputs.stale == 'true' && github.event_name == 'pull_request'
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          message: |
-            ### ⚠️ npm lockfile hash out of date
-
-            Checked against commit [`${{ steps.sha.outputs.short }}`](${{ github.server_url }}/${{ github.repository }}/commit/${{ steps.sha.outputs.full }}) (PR head at check time).
-
-            The `hash = "sha256-..."` line in these nix files no longer matches the committed `package-lock.json`:
-
-            ${{ steps.hash_check.outputs.report }}
-
-            #### Apply the fix
-
-            - [ ] **Apply lockfile fix** — tick to push a commit with the correct hashes to this PR branch
-            - Or [run the Nix Lockfile Fix workflow](${{ github.server_url }}/${{ github.repository }}/actions/workflows/nix-lockfile-fix.yml) manually (pass PR `#${{ github.event.pull_request.number }}`)
-            - Or locally: `nix run .#fix-lockfiles` and commit the diff
-
-      # Clear the sticky comment when either the build passed outright (no
-      # hash check needed) or the hash check explicitly returned stale=false
-      # (build failed for a non-hash reason).
-      - name: Clear sticky PR comment (resolved)
-        if: |
-          github.event_name == 'pull_request' &&
-          runner.os == 'Linux' &&
-          (steps.hash_check.outputs.stale == 'false' ||
-           (steps.flake.outcome == 'success' && steps.build.outcome == 'success'))
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          delete: true
-
-      - name: Final fail if build or flake failed
-        if: steps.flake.outcome == 'failure' || steps.build.outcome == 'failure'
-        run: |
-          if [ "${{ steps.hash_check.outputs.stale }}" == "true" ]; then
-            echo "::error::Nix build failed due to stale npm lockfile hash. Run: nix run .#fix-lockfiles"
-          else
-            echo "::error::Nix build/flake check failed. See logs above."
-          fi
-          exit 1
-
       - name: Evaluate flake (macOS)
         if: runner.os == 'macOS'
         run: nix flake show --json > /dev/null

.gitignore

@@ -69,4 +69,3 @@ mini-swe-agent/
 .nix-stamps/
 result
 website/static/api/skills-index.json
-models-dev-upstream/

AGENTS.md

@@ -38,7 +38,7 @@ hermes-agent/
 │   │                     #   homeassistant, signal, matrix, mattermost, email, sms,
 │   │                     #   dingtalk, wecom, weixin, feishu, qqbot, bluebubbles,
 │   │                     #   webhook, api_server, ...). See ADDING_A_PLATFORM.md.
-│   └── builtin_hooks/    # Extension point for always-registered gateway hooks (none shipped)
+│   └── builtin_hooks/    # Always-registered gateway hooks (boot-md, ...)
 ├── plugins/              # Plugin system (see "Plugins" section below)
 │   ├── memory/           # Memory-provider plugins (honcho, mem0, supermemory, ...)
 │   ├── context_engine/   # Context-engine plugins

CONTRIBUTING.md

@@ -494,7 +494,7 @@ branding:
   agent_name: "My Agent"
   welcome: "Welcome message"
   response_label: " ⚔ Agent "
-  prompt_symbol: "⚔"
+  prompt_symbol: "⚔ ❯ "
 
 tool_prefix: "╎"             # Tool output line prefix
 ```

Dockerfile

@@ -14,7 +14,7 @@ ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
 # that would otherwise accumulate when hermes runs as PID 1. See #15012.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-    build-essential curl nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini && \
+        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini && \
     rm -rf /var/lib/apt/lists/*
 
 # Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
@@ -28,40 +28,20 @@ WORKDIR /opt/hermes
 # ---------- Layer-cached dependency install ----------
 # Copy only package manifests first so npm install + Playwright are cached
 # unless the lockfiles themselves change.
-#
-# ui-tui/packages/hermes-ink/ is copied IN FULL (not just its manifests)
-# because it is referenced as a `file:` workspace dependency from
-# ui-tui/package.json.  Copying the tree up front lets npm resolve the
-# workspace to real content instead of stopping at a bare package.json.
 COPY package.json package-lock.json ./
 COPY web/package.json web/package-lock.json web/
-COPY ui-tui/package.json ui-tui/package-lock.json ui-tui/
-COPY ui-tui/packages/hermes-ink/ ui-tui/packages/hermes-ink/
-
-# `npm_config_install_links=false` forces npm to install `file:` deps as
-# symlinks (the npm 10+ default) even on Debian's older bundled npm 9.x,
-# which defaults to `install-links=true` and installs file deps as *copies*.
-# The host-side package-lock.json is generated with a newer npm that uses
-# symlinks, so an install-as-copy produces a hidden node_modules/.package-lock.json
-# that permanently disagrees with the root lock on the @hermes/ink entry.
-# That disagreement trips the TUI launcher's `_tui_need_npm_install()`
-# check on every startup and triggers a runtime `npm install` that then
-# fails with EACCES (node_modules/ is root-owned from build time).
-ENV npm_config_install_links=false
 
 RUN npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
     (cd web && npm install --prefer-offline --no-audit) && \
-    (cd ui-tui && npm install --prefer-offline --no-audit) && \
     npm cache clean --force
 
 # ---------- Source code ----------
 # .dockerignore excludes node_modules, so the installs above survive.
 COPY --chown=hermes:hermes . .
 
-# Build browser dashboard and terminal UI assets.
-RUN cd web && npm run build && \
-    cd ../ui-tui && npm run build
+# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
+RUN cd web && npm run build
 
 # ---------- Permissions ----------
 # Make install dir world-readable so any HERMES_UID can read it at runtime.

RELEASE_v0.12.0.md

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

acp_adapter/entry.py

@@ -112,17 +112,6 @@ def main() -> None:
     import acp
     from .server import HermesACPAgent
 
-    # MCP tool discovery from config.yaml — run before asyncio.run() so
-    # it's safe to use blocking waits.  (ACP also registers per-session
-    # MCP servers dynamically via asyncio.to_thread inside the event
-    # loop; that path is unaffected.)  Moved from model_tools.py module
-    # scope to avoid freezing the gateway's loop on lazy import (#16856).
-    try:
-        from tools.mcp_tool import discover_mcp_tools
-        discover_mcp_tools()
-    except Exception:
-        logger.debug("MCP tool discovery failed at ACP startup", exc_info=True)
-
     agent = HermesACPAgent()
     try:
         asyncio.run(acp.run_agent(agent, use_unstable_protocol=True))

acp_adapter/server.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import asyncio
-import contextvars
 import logging
 import os
 from collections import defaultdict, deque
@@ -13,7 +12,6 @@ from typing import Any, Deque, Optional
 import acp
 from acp.schema import (
     AgentCapabilities,
-    AgentMessageChunk,
     AuthenticateResponse,
     AvailableCommand,
     AvailableCommandsUpdate,
@@ -31,7 +29,6 @@ from acp.schema import (
     McpServerStdio,
     ModelInfo,
     NewSessionResponse,
-    PromptCapabilities,
     PromptResponse,
     ResumeSessionResponse,
     SetSessionConfigOptionResponse,
@@ -47,7 +44,6 @@ from acp.schema import (
     TextContentBlock,
     UnstructuredCommandInput,
     Usage,
-    UserMessageChunk,
 )
 
 # AuthMethodAgent was renamed from AuthMethod in agent-client-protocol 0.9.0
@@ -91,69 +87,17 @@ def _extract_text(
         | EmbeddedResourceContentBlock
     ],
 ) -> str:
-    """Extract plain text from ACP content blocks for display/commands."""
+    """Extract plain text from ACP content blocks."""
     parts: list[str] = []
     for block in prompt:
         if isinstance(block, TextContentBlock):
             parts.append(block.text)
         elif hasattr(block, "text"):
             parts.append(str(block.text))
+        # Non-text blocks are ignored for now.
     return "\n".join(parts)
 
 
-def _image_block_to_openai_part(block: ImageContentBlock) -> dict[str, Any] | None:
-    """Convert an ACP image content block to OpenAI-style multimodal content."""
-    data = str(getattr(block, "data", "") or "").strip()
-    uri = str(getattr(block, "uri", "") or "").strip()
-    mime_type = str(getattr(block, "mime_type", "") or "image/png").strip() or "image/png"
-
-    if data:
-        url = data if data.startswith("data:") else f"data:{mime_type};base64,{data}"
-    elif uri:
-        url = uri
-    else:
-        return None
-
-    return {"type": "image_url", "image_url": {"url": url}}
-
-
-def _content_blocks_to_openai_user_content(
-    prompt: list[
-        TextContentBlock
-        | ImageContentBlock
-        | AudioContentBlock
-        | ResourceContentBlock
-        | EmbeddedResourceContentBlock
-    ],
-) -> str | list[dict[str, Any]]:
-    """Convert ACP prompt blocks into a Hermes/OpenAI-compatible user content payload."""
-    parts: list[dict[str, Any]] = []
-    text_parts: list[str] = []
-
-    for block in prompt:
-        if isinstance(block, TextContentBlock):
-            if block.text:
-                parts.append({"type": "text", "text": block.text})
-                text_parts.append(block.text)
-            continue
-        if isinstance(block, ImageContentBlock):
-            image_part = _image_block_to_openai_part(block)
-            if image_part is not None:
-                parts.append(image_part)
-            continue
-
-    if not parts:
-        return _extract_text(prompt)
-
-    # Keep pure text prompts as strings so slash-command handling and text-only
-    # providers keep the exact legacy path. Switch to structured content only
-    # when an actual non-text block is present.
-    if all(part.get("type") == "text" for part in parts):
-        return "\n".join(text_parts)
-
-    return parts
-
-
 class HermesACPAgent(acp.Agent):
     """ACP Agent implementation wrapping Hermes AIAgent."""
 
@@ -164,8 +108,6 @@ class HermesACPAgent(acp.Agent):
         "context": "Show conversation context info",
         "reset": "Clear conversation history",
         "compact": "Compress conversation context",
-        "steer": "Inject guidance into the currently running agent turn",
-        "queue": "Queue a prompt to run after the current turn finishes",
         "version": "Show Hermes version",
     }
 
@@ -195,16 +137,6 @@ class HermesACPAgent(acp.Agent):
             "name": "compact",
             "description": "Compress conversation context",
         },
-        {
-            "name": "steer",
-            "description": "Inject guidance into the currently running agent turn",
-            "input_hint": "guidance for the active turn",
-        },
-        {
-            "name": "queue",
-            "description": "Queue a prompt to run after the current turn finishes",
-            "input_hint": "prompt to run next",
-        },
         {
             "name": "version",
             "description": "Show Hermes version",
@@ -419,7 +351,6 @@ class HermesACPAgent(acp.Agent):
             agent_info=Implementation(name="hermes-agent", version=HERMES_VERSION),
             agent_capabilities=AgentCapabilities(
                 load_session=True,
-                prompt_capabilities=PromptCapabilities(image=True),
                 session_capabilities=SessionCapabilities(
                     fork=SessionForkCapabilities(),
                     list=SessionListCapabilities(),
@@ -445,78 +376,6 @@ class HermesACPAgent(acp.Agent):
 
     # ---- Session management -------------------------------------------------
 
-    @staticmethod
-    def _history_message_text(message: dict[str, Any]) -> str:
-        """Extract displayable text from a persisted OpenAI-style message."""
-        content = message.get("content")
-        if isinstance(content, str):
-            return content.strip()
-        if isinstance(content, list):
-            parts: list[str] = []
-            for item in content:
-                if isinstance(item, dict):
-                    text = item.get("text")
-                    if isinstance(text, str):
-                        parts.append(text)
-                    elif item.get("type") == "text" and isinstance(item.get("content"), str):
-                        parts.append(item["content"])
-                elif isinstance(item, str):
-                    parts.append(item)
-            return "\n".join(part.strip() for part in parts if part and part.strip()).strip()
-        return ""
-
-    @staticmethod
-    def _history_message_update(
-        *,
-        role: str,
-        text: str,
-    ) -> UserMessageChunk | AgentMessageChunk | None:
-        """Build an ACP history replay update for a user/assistant message."""
-        block = TextContentBlock(type="text", text=text)
-        if role == "user":
-            return UserMessageChunk(
-                session_update="user_message_chunk",
-                content=block,
-            )
-        if role == "assistant":
-            return AgentMessageChunk(
-                session_update="agent_message_chunk",
-                content=block,
-            )
-        return None
-
-    async def _replay_session_history(self, state: SessionState) -> None:
-        """Send persisted user/assistant history to clients during session/load.
-
-        Zed's ACP history UI calls ``session/load`` after the user picks an item
-        from the Agents sidebar. The agent must then replay the full conversation
-        as ``user_message_chunk`` / ``agent_message_chunk`` notifications; merely
-        restoring server-side state makes Hermes remember context, but leaves the
-        editor looking like a clean thread.
-        """
-        if not self._conn or not state.history:
-            return
-
-        for message in state.history:
-            role = str(message.get("role") or "")
-            if role not in {"user", "assistant"}:
-                continue
-            text = self._history_message_text(message)
-            if not text:
-                continue
-            update = self._history_message_update(role=role, text=text)
-            if update is None:
-                continue
-            try:
-                await self._conn.session_update(session_id=state.session_id, update=update)
-            except Exception:
-                logger.warning(
-                    "Failed to replay ACP history for session %s",
-                    state.session_id,
-                    exc_info=True,
-                )
-                return
-
     async def new_session(
         self,
         cwd: str,
@@ -545,7 +404,6 @@ class HermesACPAgent(acp.Agent):
             return None
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Loaded session %s", session_id)
-        await self._replay_session_history(state)
         self._schedule_available_commands_update(session_id)
         return LoadSessionResponse(models=self._build_model_state(state))
 
@@ -562,16 +420,12 @@ class HermesACPAgent(acp.Agent):
             state = self.session_manager.create_session(cwd=cwd)
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Resumed session %s", state.session_id)
-        await self._replay_session_history(state)
         self._schedule_available_commands_update(state.session_id)
         return ResumeSessionResponse(models=self._build_model_state(state))
 
     async def cancel(self, session_id: str, **kwargs: Any) -> None:
         state = self.session_manager.get_session(session_id)
         if state and state.cancel_event:
-            with state.runtime_lock:
-                if state.is_running and state.current_prompt_text:
-                    state.interrupted_prompt_text = state.current_prompt_text
             state.cancel_event.set()
             try:
                 if getattr(state, "agent", None) and hasattr(state.agent, "interrupt"):
@@ -662,51 +516,11 @@ class HermesACPAgent(acp.Agent):
             return PromptResponse(stop_reason="refusal")
 
         user_text = _extract_text(prompt).strip()
-        user_content = _content_blocks_to_openai_user_content(prompt)
-        has_content = bool(user_text) or (
-            isinstance(user_content, list) and bool(user_content)
-        )
-        if not has_content:
+        if not user_text:
             return PromptResponse(stop_reason="end_turn")
 
-        # /steer on an idle session has no in-flight tool call to inject into.
-        # Rewrite it so the payload runs as a normal user prompt, matching the
-        # gateway's behavior (gateway/run.py ~L4898). Two sub-cases:
-        #   1. Zed-interrupt salvage — a prior prompt was cancelled by the
-        #      client right before /steer arrived; replay it with the steer
-        #      text attached as explicit correction/guidance so the user's
-        #      in-flight work isn't lost.
-        #   2. Plain idle — no prior work to salvage; just run the steer
-        #      payload as a regular prompt. Without this, _cmd_steer would
-        #      silently append to state.queued_prompts and respond with
-        #      "No active turn — queued for the next turn", which looks like
-        #      /queue even though the user never typed /queue.
-        if isinstance(user_content, str) and user_text.startswith("/steer"):
-            steer_text = user_text.split(maxsplit=1)[1].strip() if len(user_text.split(maxsplit=1)) > 1 else ""
-            interrupted_prompt = ""
-            rewrite_idle = False
-            with state.runtime_lock:
-                if not state.is_running and steer_text:
-                    if state.interrupted_prompt_text:
-                        interrupted_prompt = state.interrupted_prompt_text
-                        state.interrupted_prompt_text = ""
-                    else:
-                        rewrite_idle = True
-            if interrupted_prompt:
-                user_text = (
-                    f"{interrupted_prompt}\n\n"
-                    f"User correction/guidance after interrupt: {steer_text}"
-                )
-                user_content = user_text
-            elif rewrite_idle:
-                user_text = steer_text
-                user_content = steer_text
-
-        # Intercept slash commands — handle locally without calling the LLM.
-        # Slash commands are text-only; if the client included images/resources,
-        # send the whole multimodal prompt to the agent instead of treating it as
-        # an ACP command.
-        if isinstance(user_content, str) and user_text.startswith("/"):
+        # Intercept slash commands — handle locally without calling the LLM
+        if user_text.startswith("/"):
             response_text = self._handle_slash_command(user_text, state)
             if response_text is not None:
                 if self._conn:
@@ -714,24 +528,6 @@ class HermesACPAgent(acp.Agent):
                     await self._conn.session_update(session_id, update)
                 return PromptResponse(stop_reason="end_turn")
 
-        # If Zed sends another regular prompt while the same ACP session is
-        # still running, queue it instead of racing two AIAgent loops against
-        # the same state.history. /steer and /queue are handled above and can
-        # land immediately.
-        with state.runtime_lock:
-            if state.is_running:
-                queued_text = user_text or "[Image attachment]"
-                state.queued_prompts.append(queued_text)
-                depth = len(state.queued_prompts)
-                if self._conn:
-                    update = acp.update_agent_message_text(
-                        f"Queued for the next turn. ({depth} queued)"
-                    )
-                    await self._conn.session_update(session_id, update)
-                return PromptResponse(stop_reason="end_turn")
-            state.is_running = True
-            state.current_prompt_text = user_text or "[Image attachment]"
-
         logger.info("Prompt on session %s: %s", session_id, user_text[:100])
 
         conn = self._conn
@@ -778,22 +574,6 @@ class HermesACPAgent(acp.Agent):
 
         def _run_agent() -> dict:
             nonlocal previous_approval_cb, previous_interactive
-            # Bind HERMES_SESSION_KEY for this session so per-session caches
-            # (e.g. the interactive sudo password cache in tools.terminal_tool)
-            # scope to the ACP session rather than leaking across sessions
-            # that land on the same reused executor thread. This call runs
-            # inside a contextvars.copy_context() below, so the ContextVar
-            # write is isolated from other concurrent ACP sessions.
-            try:
-                from gateway.session_context import (
-                    clear_session_vars,
-                    set_session_vars,
-                )
-                session_tokens = set_session_vars(session_key=session_id)
-            except Exception:
-                session_tokens = None
-                clear_session_vars = None  # type: ignore[assignment]
-                logger.debug("Could not set ACP session context", exc_info=True)
             if approval_cb:
                 try:
                     from tools import terminal_tool as _terminal_tool
@@ -807,10 +587,9 @@ class HermesACPAgent(acp.Agent):
             os.environ["HERMES_INTERACTIVE"] = "1"
             try:
                 result = agent.run_conversation(
-                    user_message=user_content,
+                    user_message=user_text,
                     conversation_history=state.history,
                     task_id=session_id,
-                    persist_user_message=user_text or "[Image attachment]",
                 )
                 return result
             except Exception as e:
@@ -828,24 +607,11 @@ class HermesACPAgent(acp.Agent):
                         _terminal_tool.set_approval_callback(previous_approval_cb)
                     except Exception:
                         logger.debug("Could not restore approval callback", exc_info=True)
-                if session_tokens is not None and clear_session_vars is not None:
-                    try:
-                        clear_session_vars(session_tokens)
-                    except Exception:
-                        logger.debug("Could not clear ACP session context", exc_info=True)
 
         try:
-            # Wrap the executor call in a fresh copy of the current context so
-            # concurrent ACP sessions on the shared ThreadPoolExecutor don't
-            # stomp on each other's ContextVar writes (HERMES_SESSION_KEY in
-            # particular — used by the interactive sudo password cache scope).
-            ctx = contextvars.copy_context()
-            result = await loop.run_in_executor(_executor, ctx.run, _run_agent)
+            result = await loop.run_in_executor(_executor, _run_agent)
         except Exception:
             logger.exception("Executor error for session %s", session_id)
-            with state.runtime_lock:
-                state.is_running = False
-                state.current_prompt_text = ""
             return PromptResponse(stop_reason="end_turn")
 
         if result.get("messages"):
@@ -871,28 +637,6 @@ class HermesACPAgent(acp.Agent):
             update = acp.update_agent_message_text(final_response)
             await conn.session_update(session_id, update)
 
-        # Mark this turn idle before draining queued work so recursive prompt()
-        # calls can acquire the session. Queued turns are intentionally run as
-        # normal follow-up user prompts, preserving role alternation and history.
-        with state.runtime_lock:
-            state.is_running = False
-            state.current_prompt_text = ""
-
-        while True:
-            with state.runtime_lock:
-                if not state.queued_prompts:
-                    break
-                next_prompt = state.queued_prompts.pop(0)
-            if conn:
-                await conn.session_update(
-                    session_id,
-                    acp.update_user_message_text(next_prompt),
-                )
-            await self.prompt(
-                prompt=[TextContentBlock(type="text", text=next_prompt)],
-                session_id=session_id,
-            )
-
         usage = None
         if any(result.get(key) is not None for key in ("prompt_tokens", "completion_tokens", "total_tokens")):
             usage = Usage(
@@ -970,8 +714,6 @@ class HermesACPAgent(acp.Agent):
             "context": self._cmd_context,
             "reset": self._cmd_reset,
             "compact": self._cmd_compact,
-            "steer": self._cmd_steer,
-            "queue": self._cmd_queue,
             "version": self._cmd_version,
         }.get(cmd)
 
@@ -1068,16 +810,10 @@ class HermesACPAgent(acp.Agent):
             if not hasattr(agent, "_compress_context"):
                 return "Context compression not available for this agent."
 
-            from agent.model_metadata import estimate_request_tokens_rough
+            from agent.model_metadata import estimate_messages_tokens_rough
 
             original_count = len(state.history)
-            # Include system prompt + tool schemas so the figure reflects real
-            # request pressure, not a transcript-only underestimate (#6217).
-            _sys_prompt = getattr(agent, "_cached_system_prompt", "") or ""
-            _tools = getattr(agent, "tools", None) or None
-            approx_tokens = estimate_request_tokens_rough(
-                state.history, system_prompt=_sys_prompt, tools=_tools
-            )
+            approx_tokens = estimate_messages_tokens_rough(state.history)
             original_session_db = getattr(agent, "_session_db", None)
 
             try:
@@ -1097,13 +833,7 @@ class HermesACPAgent(acp.Agent):
             self.session_manager.save_session(state.session_id)
 
             new_count = len(state.history)
-            _sys_prompt_after = getattr(agent, "_cached_system_prompt", "") or _sys_prompt
-            _tools_after = getattr(agent, "tools", None) or _tools
-            new_tokens = estimate_request_tokens_rough(
-                state.history,
-                system_prompt=_sys_prompt_after,
-                tools=_tools_after,
-            )
+            new_tokens = estimate_messages_tokens_rough(state.history)
             return (
                 f"Context compressed: {original_count} -> {new_count} messages\n"
                 f"~{approx_tokens:,} -> ~{new_tokens:,} tokens"
@@ -1111,34 +841,6 @@ class HermesACPAgent(acp.Agent):
         except Exception as e:
             return f"Compression failed: {e}"
 
-    def _cmd_steer(self, args: str, state: SessionState) -> str:
-        steer_text = args.strip()
-        if not steer_text:
-            return "Usage: /steer <guidance>"
-
-        if state.is_running and hasattr(state.agent, "steer"):
-            try:
-                if state.agent.steer(steer_text):
-                    preview = steer_text[:80] + ("..." if len(steer_text) > 80 else "")
-                    return f"⏩ Steer queued for the active turn: {preview}"
-            except Exception as exc:
-                logger.warning("ACP steer failed for session %s: %s", state.session_id, exc)
-                return f"⚠️ Steer failed: {exc}"
-
-        with state.runtime_lock:
-            state.queued_prompts.append(steer_text)
-            depth = len(state.queued_prompts)
-        return f"No active turn — queued for the next turn. ({depth} queued)"
-
-    def _cmd_queue(self, args: str, state: SessionState) -> str:
-        queued_text = args.strip()
-        if not queued_text:
-            return "Usage: /queue <prompt>"
-        with state.runtime_lock:
-            state.queued_prompts.append(queued_text)
-            depth = len(state.queued_prompts)
-        return f"Queued for the next turn. ({depth} queued)"
-
     def _cmd_version(self, args: str, state: SessionState) -> str:
         return f"Hermes Agent v{HERMES_VERSION}"
 

acp_adapter/session.py

@@ -26,33 +26,6 @@ from typing import Any, Dict, List, Optional
 logger = logging.getLogger(__name__)
 
 
-def _win_path_to_wsl(path: str) -> str | None:
-    """Convert a Windows drive path to its WSL /mnt/<drive>/... equivalent."""
-    match = re.match(r"^([A-Za-z]):[\\/](.*)$", path)
-    if not match:
-        return None
-    drive = match.group(1).lower()
-    tail = match.group(2).replace("\\", "/")
-    return f"/mnt/{drive}/{tail}"
-
-
-def _translate_acp_cwd(cwd: str) -> str:
-    """Translate Windows ACP cwd values when Hermes itself is running in WSL.
-
-    Windows ACP clients can launch ``hermes acp`` inside WSL while still sending
-    editor workspaces as Windows drive paths such as ``E:\\Projects``. Store
-    and execute against the WSL mount path so agents, tools, and persisted ACP
-    sessions all agree on the usable workspace. Native Linux/macOS keeps the
-    original cwd unchanged.
-    """
-    from hermes_constants import is_wsl
-
-    if not is_wsl():
-        return cwd
-    translated = _win_path_to_wsl(str(cwd))
-    return translated if translated is not None else cwd
-
-
 def _normalize_cwd_for_compare(cwd: str | None) -> str:
     raw = str(cwd or ".").strip()
     if not raw:
@@ -61,9 +34,11 @@ def _normalize_cwd_for_compare(cwd: str | None) -> str:
 
     # Normalize Windows drive paths into the equivalent WSL mount form so
     # ACP history filters match the same workspace across Windows and WSL.
-    translated = _win_path_to_wsl(expanded)
-    if translated is not None:
-        expanded = translated
+    match = re.match(r"^([A-Za-z]):[\\/](.*)$", expanded)
+    if match:
+        drive = match.group(1).lower()
+        tail = match.group(2).replace("\\", "/")
+        expanded = f"/mnt/{drive}/{tail}"
     elif re.match(r"^/mnt/[A-Za-z]/", expanded):
         expanded = f"/mnt/{expanded[5].lower()}/{expanded[7:]}"
 
@@ -121,18 +96,12 @@ def _acp_stderr_print(*args, **kwargs) -> None:
 
 
 def _register_task_cwd(task_id: str, cwd: str) -> None:
-    """Bind a task/session id to the editor's working directory for tools.
-
-    Zed can launch Hermes from a Windows workspace while the ACP process runs
-    inside WSL. In that case ACP sends cwd as e.g. ``E:\\Projects\\POTI``;
-    local tools need the WSL mount equivalent or subprocess creation fails
-    before the command can run.
-    """
+    """Bind a task/session id to the editor's working directory for tools."""
     if not task_id:
         return
     try:
         from tools.terminal_tool import register_task_env_overrides
-        register_task_env_overrides(task_id, {"cwd": _translate_acp_cwd(cwd)})
+        register_task_env_overrides(task_id, {"cwd": cwd})
     except Exception:
         logger.debug("Failed to register ACP task cwd override", exc_info=True)
 
@@ -176,11 +145,6 @@ class SessionState:
     model: str = ""
     history: List[Dict[str, Any]] = field(default_factory=list)
     cancel_event: Any = None  # threading.Event
-    is_running: bool = False
-    queued_prompts: List[str] = field(default_factory=list)
-    runtime_lock: Any = field(default_factory=Lock)
-    current_prompt_text: str = ""
-    interrupted_prompt_text: str = ""
 
 
 class SessionManager:
@@ -211,7 +175,6 @@ class SessionManager:
         """Create a new session with a unique ID and a fresh AIAgent."""
         import threading
 
-        cwd = _translate_acp_cwd(cwd)
         session_id = str(uuid.uuid4())
         agent = self._make_agent(session_id=session_id, cwd=cwd)
         state = SessionState(
@@ -254,7 +217,6 @@ class SessionManager:
         """Deep-copy a session's history into a new session."""
         import threading
 
-        cwd = _translate_acp_cwd(cwd)
         original = self.get_session(session_id)  # checks DB too
         if original is None:
             return None
@@ -356,7 +318,6 @@ class SessionManager:
 
     def update_cwd(self, session_id: str, cwd: str) -> Optional[SessionState]:
         """Update the working directory for a session and its tool overrides."""
-        cwd = _translate_acp_cwd(cwd)
         state = self.get_session(session_id)  # checks DB too
         if state is None:
             return None

agent/anthropic_adapter.py

@@ -20,27 +20,12 @@ from pathlib import Path
 
 from hermes_constants import get_hermes_home
 from typing import Any, Dict, List, Optional, Tuple
-from utils import base_url_host_matches, normalize_proxy_env_vars
+from utils import normalize_proxy_env_vars
 
-# NOTE: `import anthropic` is deliberately NOT at module top — the SDK pulls
-# ~220 ms of imports (anthropic.types, anthropic.lib.tools._beta_runner, etc.)
-# and the 3 usage sites (build_anthropic_client, build_anthropic_bedrock_client,
-# read_claude_code_credentials_from_keychain) are all on cold user-triggered
-# paths. Access via the `_get_anthropic_sdk()` accessor below, which caches
-# the module after the first call and returns None on ImportError.
-_anthropic_sdk: Any = ...  # sentinel — None means "tried and missing"
-
-
-def _get_anthropic_sdk():
-    """Return the ``anthropic`` SDK module, importing lazily. None if not installed."""
-    global _anthropic_sdk
-    if _anthropic_sdk is ...:
-        try:
-            import anthropic as _sdk
-            _anthropic_sdk = _sdk
-        except ImportError:
-            _anthropic_sdk = None
-    return _anthropic_sdk
+try:
+    import anthropic as _anthropic_sdk
+except ImportError:
+    _anthropic_sdk = None  # type: ignore[assignment]
 
 logger = logging.getLogger(__name__)
 
@@ -217,33 +202,19 @@ def _forbids_sampling_params(model: str) -> bool:
 
 
 # Beta headers for enhanced features (sent with ALL auth types).
-# As of Opus 4.7 (2026-04-16), the first two are GA on Claude 4.6+ — the
+# As of Opus 4.7 (2026-04-16), both of these are GA on Claude 4.6+ — the
 # beta headers are still accepted (harmless no-op) but not required. Kept
 # here so older Claude (4.5, 4.1) + third-party Anthropic-compat endpoints
 # that still gate on the headers continue to get the enhanced features.
-#
-# ``context-1m-2025-08-07`` unlocks the 1M context window on Claude Opus 4.6/4.7
-# and Sonnet 4.6 when served via AWS Bedrock or Azure AI Foundry. 1M is GA on
-# native Anthropic (api.anthropic.com) for Opus 4.6+, but Bedrock/Azure still
-# gate it behind this beta header as of 2026-04 — without it Bedrock caps Opus
-# at 200K even though model_metadata.py advertises 1M. The header is a harmless
-# no-op on endpoints where 1M is GA.
-#
-# Migration guide: remove these if you no longer support ≤4.5 models or once
-# Bedrock/Azure promote 1M to GA.
+# Migration guide: remove these if you no longer support ≤4.5 models.
 _COMMON_BETAS = [
     "interleaved-thinking-2025-05-14",
     "fine-grained-tool-streaming-2025-05-14",
-    "context-1m-2025-08-07",
 ]
 # MiniMax's Anthropic-compatible endpoints fail tool-use requests when
 # the fine-grained tool streaming beta is present.  Omit it so tool calls
 # fall back to the provider's default response path.
 _TOOL_STREAMING_BETA = "fine-grained-tool-streaming-2025-05-14"
-# 1M context beta — see comment on _COMMON_BETAS above. Stripped for
-# Bearer-auth (MiniMax) endpoints since they host their own models and
-# unknown Anthropic beta headers risk request rejection.
-_CONTEXT_1M_BETA = "context-1m-2025-08-07"
 
 # Fast mode beta — enables the ``speed: "fast"`` request parameter for
 # significantly higher output token throughput on Opus 4.6 (~2.5x).
@@ -365,88 +336,6 @@ def _is_kimi_coding_endpoint(base_url: str | None) -> bool:
     return normalized.rstrip("/").lower().startswith("https://api.kimi.com/coding")
 
 
-# Model-name prefixes that identify the Kimi / Moonshot family.  Covers
-# - official slugs: ``kimi-k2.5``, ``kimi_thinking``, ``moonshot-v1-8k``
-# - common release lines: ``k1.5-...``, ``k2-thinking``, ``k25-...``, ``k2.5-...``
-# Matched case-insensitively against the post-``normalize_model_name`` form,
-# so a caller's ``provider/vendor/model`` slug is handled the same as a
-# bare name.
-_KIMI_FAMILY_MODEL_PREFIXES = (
-    "kimi-", "kimi_",
-    "moonshot-", "moonshot_",
-    "k1.", "k1-",
-    "k2.", "k2-",
-    "k25", "k2.5",
-)
-
-
-def _model_name_is_kimi_family(model: str | None) -> bool:
-    if not isinstance(model, str):
-        return False
-    m = model.strip().lower()
-    if not m:
-        return False
-    # Strip vendor prefix (e.g. ``moonshotai/kimi-k2.5`` → ``kimi-k2.5``)
-    if "/" in m:
-        m = m.rsplit("/", 1)[-1]
-    return m.startswith(_KIMI_FAMILY_MODEL_PREFIXES)
-
-
-def _is_kimi_family_endpoint(base_url: str | None, model: str | None = None) -> bool:
-    """Return True for any Kimi / Moonshot Anthropic-Messages-speaking endpoint.
-
-    Broader than ``_is_kimi_coding_endpoint`` — matches:
-
-    - Kimi's official ``/coding`` URL (legacy check, preserved)
-    - Any ``api.kimi.com`` / ``moonshot.ai`` / ``moonshot.cn`` host
-    - Custom or proxied endpoints whose *model* name is in the Kimi / Moonshot
-      family (``kimi-*``, ``moonshot-*``, ``k1.*``, ``k2.*``, …).  Users with
-      ``api_mode: anthropic_messages`` on a private gateway fronting Kimi
-      fall into this branch — the upstream still enforces Kimi's thinking
-      semantics (reasoning_content required on every replayed tool-call
-      message) regardless of the gateway's hostname.
-
-    Used to decide whether to drop Anthropic's ``thinking`` kwarg and to
-    preserve unsigned reasoning_content-derived thinking blocks on replay.
-    See hermes-agent#13848, #17057.
-    """
-    if _is_kimi_coding_endpoint(base_url):
-        return True
-    for _domain in ("api.kimi.com", "moonshot.ai", "moonshot.cn"):
-        if base_url_host_matches(base_url or "", _domain):
-            return True
-    if _model_name_is_kimi_family(model):
-        return True
-    return False
-
-
-def _is_deepseek_anthropic_endpoint(base_url: str | None) -> bool:
-    """Return True for DeepSeek's Anthropic-compatible endpoint.
-
-    DeepSeek's ``/anthropic`` route speaks the Anthropic Messages protocol
-    but, when thinking mode is enabled, requires the ``thinking`` blocks
-    from prior assistant turns to round-trip on subsequent requests — the
-    generic third-party path strips them and triggers HTTP 400::
-
-        The content[].thinking in the thinking mode must be passed back
-        to the API.
-
-    Per DeepSeek's published compatibility matrix the blocks are unsigned
-    (no Anthropic-proprietary signature, no ``redacted_thinking`` support),
-    so this endpoint is handled with the same strip-signed / keep-unsigned
-    policy used for Kimi's ``/coding`` endpoint.  The match is pinned to
-    the ``/anthropic`` path so the OpenAI-compatible ``api.deepseek.com``
-    base URL (which never reaches this adapter) is not misclassified.
-    See hermes-agent#16748.
-    """
-    if not base_url_host_matches(base_url or "", "api.deepseek.com"):
-        return False
-    normalized = _normalize_base_url_text(base_url)
-    if not normalized:
-        return False
-    return "/anthropic" in normalized.rstrip("/").lower()
-
-
 def _requires_bearer_auth(base_url: str | None) -> bool:
     """Return True for Anthropic-compatible providers that require Bearer auth.
 
@@ -461,45 +350,20 @@ def _requires_bearer_auth(base_url: str | None) -> bool:
     return normalized.startswith(("https://api.minimax.io/anthropic", "https://api.minimaxi.com/anthropic"))
 
 
-def _common_betas_for_base_url(
-    base_url: str | None,
-    *,
-    drop_context_1m_beta: bool = False,
-) -> list[str]:
+def _common_betas_for_base_url(base_url: str | None) -> list[str]:
     """Return the beta headers that are safe for the configured endpoint.
 
     MiniMax's Anthropic-compatible endpoints (Bearer-auth) reject requests
     that include Anthropic's ``fine-grained-tool-streaming`` beta — every
     tool-use message triggers a connection error.  Strip that beta for
     Bearer-auth endpoints while keeping all other betas intact.
-
-    The ``context-1m-2025-08-07`` beta is also stripped for Bearer-auth
-    endpoints — MiniMax hosts its own models, not Claude, so the header is
-    irrelevant at best and risks request rejection at worst.
-
-    ``drop_context_1m_beta=True`` additionally strips the 1M-context beta on
-    otherwise-unrelated endpoints. The OAuth retry path flips this flag after
-    a subscription rejects the beta with
-    "The long context beta is not yet available for this subscription" so
-    subsequent requests in the same session don't repeat the probe. See the
-    reactive recovery loop in ``run_agent.py`` and issue-comment history on
-    PR #17680 for the full rationale.
     """
     if _requires_bearer_auth(base_url):
-        _stripped = {_TOOL_STREAMING_BETA, _CONTEXT_1M_BETA}
-        return [b for b in _COMMON_BETAS if b not in _stripped]
-    if drop_context_1m_beta:
-        return [b for b in _COMMON_BETAS if b != _CONTEXT_1M_BETA]
+        return [b for b in _COMMON_BETAS if b != _TOOL_STREAMING_BETA]
     return _COMMON_BETAS
 
 
-def build_anthropic_client(
-    api_key: str,
-    base_url: str = None,
-    timeout: float = None,
-    *,
-    drop_context_1m_beta: bool = False,
-):
+def build_anthropic_client(api_key: str, base_url: str = None, timeout: float = None):
     """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
 
     If *timeout* is provided it overrides the default 900s read timeout.  The
@@ -508,15 +372,8 @@ def build_anthropic_client(
     Anthropic-compatible providers respect the same knob as OpenAI-wire
     providers.
 
-    ``drop_context_1m_beta=True`` strips ``context-1m-2025-08-07`` from the
-    client-level ``anthropic-beta`` header. Used by the reactive OAuth retry
-    path in ``run_agent.py`` when a subscription rejects the beta; leave at
-    its default on fresh clients so 1M-capable subscriptions keep the
-    capability.
-
     Returns an anthropic.Anthropic instance.
     """
-    _anthropic_sdk = _get_anthropic_sdk()
     if _anthropic_sdk is None:
         raise ImportError(
             "The 'anthropic' package is required for the Anthropic provider. "
@@ -533,20 +390,8 @@ def build_anthropic_client(
         "timeout": Timeout(timeout=float(_read_timeout), connect=10.0),
     }
     if normalized_base_url:
-        # Azure Anthropic endpoints require an ``api-version`` query parameter.
-        # Pass it via default_query so the SDK appends it to every request URL
-        # without corrupting the base_url (appending it directly produces
-        # malformed paths like /anthropic?api-version=.../v1/messages).
-        _is_azure_endpoint = "azure.com" in normalized_base_url.lower()
-        if _is_azure_endpoint and "api-version" not in normalized_base_url:
-            kwargs["base_url"] = normalized_base_url.rstrip("/")
-            kwargs["default_query"] = {"api-version": "2025-04-15"}
-        else:
-            kwargs["base_url"] = normalized_base_url
-    common_betas = _common_betas_for_base_url(
-        normalized_base_url,
-        drop_context_1m_beta=drop_context_1m_beta,
-    )
+        kwargs["base_url"] = normalized_base_url
+    common_betas = _common_betas_for_base_url(normalized_base_url)
 
     if _is_kimi_coding_endpoint(base_url):
         # Kimi's /coding endpoint requires User-Agent: claude-code/0.1.0
@@ -602,16 +447,8 @@ def build_anthropic_bedrock_client(region: str):
     Claude feature parity: prompt caching, thinking budgets, adaptive
     thinking, fast mode — features not available via the Converse API.
 
-    Attaches the common Anthropic beta headers as client-level defaults so
-    that Bedrock-hosted Claude models get the same enhanced features as
-    native Anthropic. The ``context-1m-2025-08-07`` beta in particular
-    unlocks the 1M context window for Opus 4.6/4.7 on Bedrock — without
-    it, Bedrock caps these models at 200K even though the Anthropic API
-    serves them with 1M natively.
-
     Auth uses the boto3 default credential chain (IAM roles, SSO, env vars).
     """
-    _anthropic_sdk = _get_anthropic_sdk()
     if _anthropic_sdk is None:
         raise ImportError(
             "The 'anthropic' package is required for the Bedrock provider. "
@@ -627,7 +464,6 @@ def build_anthropic_bedrock_client(region: str):
     return _anthropic_sdk.AnthropicBedrock(
         aws_region=region,
         timeout=Timeout(timeout=900.0, connect=10.0),
-        default_headers={"anthropic-beta": ",".join(_COMMON_BETAS)},
     )
 
 
@@ -643,6 +479,9 @@ def _read_claude_code_credentials_from_keychain() -> Optional[Dict[str, Any]]:
 
     Returns dict with {accessToken, refreshToken?, expiresAt?} or None.
     """
+    import platform
+    import subprocess
+
     if platform.system() != "Darwin":
         return None
 
@@ -1187,12 +1026,9 @@ def normalize_model_name(model: str, preserve_dots: bool = False) -> str:
         # These must not be converted to hyphens.  See issue #12295.
         if _is_bedrock_model_id(model):
             return model
-        # Only convert dots to hyphens for Anthropic/Claude models.
-        # Non-Anthropic models (gpt-5.4, gemini-2.5, etc.) use dots
-        # as part of their canonical names.  See issue #17171.
-        _lower = model.lower()
-        if _lower.startswith("claude-") or _lower.startswith("anthropic/"):
-            model = model.replace(".", "-")
+        # OpenRouter uses dots for version separators (claude-opus-4.6),
+        # Anthropic uses hyphens (claude-opus-4-6). Convert dots to hyphens.
+        model = model.replace(".", "-")
     return model
 
 
@@ -1209,33 +1045,6 @@ def _sanitize_tool_id(tool_id: str) -> str:
     return sanitized or "tool_0"
 
 
-def _normalize_tool_input_schema(schema: Any) -> Dict[str, Any]:
-    """Normalize tool schemas before sending them to Anthropic.
-
-    Anthropic's tool schema validator rejects nullable unions such as
-    ``anyOf: [{"type": "string"}, {"type": "null"}]`` that Pydantic/MCP
-    commonly emits for optional fields. Tool optionality is represented by
-    the parent ``required`` array, so we delegate to the shared
-    ``strip_nullable_unions`` helper to collapse nullable unions to the
-    non-null branch while preserving metadata like description/default.
-
-    ``keep_nullable_hint=False`` because the Anthropic validator does not
-    recognize the OpenAPI-style ``nullable: true`` extension and strict
-    schema-to-grammar converters may reject unknown keywords.
-    """
-    if not schema:
-        return {"type": "object", "properties": {}}
-
-    from tools.schema_sanitizer import strip_nullable_unions
-
-    normalized = strip_nullable_unions(schema, keep_nullable_hint=False)
-    if not isinstance(normalized, dict):
-        return {"type": "object", "properties": {}}
-    if normalized.get("type") == "object" and not isinstance(normalized.get("properties"), dict):
-        normalized = {**normalized, "properties": {}}
-    return normalized
-
-
 def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
     """Convert OpenAI tool definitions to Anthropic format."""
     if not tools:
@@ -1246,9 +1055,7 @@ def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
         result.append({
             "name": fn.get("name", ""),
             "description": fn.get("description", ""),
-            "input_schema": _normalize_tool_input_schema(
-                fn.get("parameters", {"type": "object", "properties": {}})
-            ),
+            "input_schema": fn.get("parameters", {"type": "object", "properties": {}}),
         })
     return result
 
@@ -1379,7 +1186,6 @@ def _convert_content_to_anthropic(content: Any) -> Any:
 def convert_messages_to_anthropic(
     messages: List[Dict],
     base_url: str | None = None,
-    model: str | None = None,
 ) -> Tuple[Optional[Any], List[Dict]]:
     """Convert OpenAI-format messages to Anthropic format.
 
@@ -1391,12 +1197,6 @@ def convert_messages_to_anthropic(
     endpoint, all thinking block signatures are stripped.  Signatures are
     Anthropic-proprietary — third-party endpoints cannot validate them and will
     reject them with HTTP 400 "Invalid signature in thinking block".
-
-    When *model* is provided and matches the Kimi / Moonshot family (or
-    *base_url* is a Kimi / Moonshot host), unsigned thinking blocks
-    synthesised from ``reasoning_content`` are preserved on replayed
-    assistant tool-call messages — Kimi requires the field to exist, even
-    if empty.
     """
     system = None
     result = []
@@ -1625,16 +1425,7 @@ def convert_messages_to_anthropic(
     #    cache markers can interfere with signature validation.
     _THINKING_TYPES = frozenset(("thinking", "redacted_thinking"))
     _is_third_party = _is_third_party_anthropic_endpoint(base_url)
-    # Kimi /coding and DeepSeek /anthropic share a contract: both speak the
-    # Anthropic Messages protocol upstream but require that thinking blocks
-    # synthesised from reasoning_content round-trip on subsequent turns when
-    # thinking is enabled.  Signed Anthropic blocks still have to be stripped
-    # (neither endpoint can validate Anthropic's signatures); unsigned blocks
-    # are preserved.  See hermes-agent#13848 (Kimi) and #16748 (DeepSeek).
-    _preserve_unsigned_thinking = (
-        _is_kimi_family_endpoint(base_url, model)
-        or _is_deepseek_anthropic_endpoint(base_url)
-    )
+    _is_kimi = _is_kimi_coding_endpoint(base_url)
 
     last_assistant_idx = None
     for i in range(len(result) - 1, -1, -1):
@@ -1646,22 +1437,22 @@ def convert_messages_to_anthropic(
         if m.get("role") != "assistant" or not isinstance(m.get("content"), list):
             continue
 
-        if _preserve_unsigned_thinking:
-            # Kimi's /coding and DeepSeek's /anthropic endpoints both enable
-            # thinking server-side and require unsigned thinking blocks on
-            # replayed assistant tool-call messages.  Strip signed Anthropic
-            # blocks (neither upstream can validate Anthropic signatures) but
-            # preserve the unsigned ones we synthesised from reasoning_content.
+        if _is_kimi:
+            # Kimi's /coding endpoint enables thinking server-side and
+            # requires unsigned thinking blocks on replayed assistant
+            # tool-call messages.  Strip signed Anthropic blocks (Kimi
+            # can't validate signatures) but preserve the unsigned ones
+            # we synthesised from reasoning_content above.
             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 b.get("signature") or b.get("data"):
-                    # Anthropic-signed block — upstream can't validate, strip
+                    # Anthropic-signed block — Kimi can't validate, strip
                     continue
                 # Unsigned thinking (synthesised from reasoning_content) —
-                # keep it: the upstream needs it for message-history validation.
+                # keep it: Kimi needs it for message-history validation.
                 new_content.append(b)
             m["content"] = new_content or [{"type": "text", "text": "(empty)"}]
         elif _is_third_party or idx != last_assistant_idx:
@@ -1718,7 +1509,6 @@ def build_anthropic_kwargs(
     context_length: Optional[int] = None,
     base_url: str | None = None,
     fast_mode: bool = False,
-    drop_context_1m_beta: bool = False,
 ) -> Dict[str, Any]:
     """Build kwargs for anthropic.messages.create().
 
@@ -1758,9 +1548,7 @@ def build_anthropic_kwargs(
     Currently only supported on native Anthropic endpoints (not third-party
     compatible ones).
     """
-    system, anthropic_messages = convert_messages_to_anthropic(
-        messages, base_url=base_url, model=model
-    )
+    system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
     anthropic_tools = convert_tools_to_anthropic(tools) if tools else []
 
     model = normalize_model_name(model, preserve_dots=preserve_dots)
@@ -1866,7 +1654,7 @@ def build_anthropic_kwargs(
     # silently hides reasoning text that Hermes surfaces in its CLI. We
     # request "summarized" so the reasoning blocks stay populated — matching
     # 4.6 behavior and preserving the activity-feed UX during long tool runs.
-    _is_kimi_coding = _is_kimi_family_endpoint(base_url, model)
+    _is_kimi_coding = _is_kimi_coding_endpoint(base_url)
     if reasoning_config and isinstance(reasoning_config, dict) and not _is_kimi_coding:
         if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
             effort = str(reasoning_config.get("effort", "medium")).lower()
@@ -1907,10 +1695,7 @@ def build_anthropic_kwargs(
         kwargs.setdefault("extra_body", {})["speed"] = "fast"
         # Build extra_headers with ALL applicable betas (the per-request
         # extra_headers override the client-level anthropic-beta header).
-        betas = list(_common_betas_for_base_url(
-            base_url,
-            drop_context_1m_beta=drop_context_1m_beta,
-        ))
+        betas = list(_common_betas_for_base_url(base_url))
         if is_oauth:
             betas.extend(_OAUTH_ONLY_BETAS)
         betas.append(_FAST_MODE_BETA)

agent/bedrock_adapter.py

@@ -291,52 +291,14 @@ def has_aws_credentials(env: Optional[Dict[str, str]] = None) -> bool:
 def resolve_bedrock_region(env: Optional[Dict[str, str]] = None) -> str:
     """Resolve the AWS region for Bedrock API calls.
 
-    Priority:
-      1. AWS_REGION env var
-      2. AWS_DEFAULT_REGION env var
-      3. boto3/botocore configured region (from ~/.aws/config or SSO profile)
-      4. us-east-1 (hard fallback)
-
-    The boto3 fallback is critical for EU/AP users who configure their region
-    in ~/.aws/config via a named profile rather than env vars — without it,
-    live model discovery would always return us.* profile IDs regardless of
-    the user's actual region.
+    Priority: AWS_REGION → AWS_DEFAULT_REGION → us-east-1 (fallback).
     """
     env = env if env is not None else os.environ
-    explicit = (
+    return (
         env.get("AWS_REGION", "").strip()
         or env.get("AWS_DEFAULT_REGION", "").strip()
+        or "us-east-1"
     )
-    if explicit:
-        return explicit
-    try:
-        import botocore.session
-        region = botocore.session.get_session().get_config_variable("region")
-        if region:
-            return region
-    except Exception:
-        pass
-    return "us-east-1"
-
-
-def bedrock_model_ids_or_none() -> Optional[List[str]]:
-    """Live-discover Bedrock model IDs for the active region.
-
-    Returns a list of model ID strings if discovery succeeds and yields
-    at least one model, or ``None`` on failure / empty result.  Callers
-    should fall back to the static curated list when ``None`` is returned.
-
-    This helper consolidates the discover → extract-ids → fallback
-    pattern that was previously duplicated across ``provider_model_ids``,
-    ``list_authenticated_providers`` section 2, and section 3.
-    """
-    try:
-        discovered = discover_bedrock_models(resolve_bedrock_region())
-        if discovered:
-            return [m["id"] for m in discovered]
-    except Exception:
-        pass
-    return None
 
 
 # ---------------------------------------------------------------------------

agent/codex_responses_adapter.py

@@ -227,23 +227,6 @@ def _responses_tools(tools: Optional[List[Dict[str, Any]]] = None) -> Optional[L
 # Message format conversion
 # ---------------------------------------------------------------------------
 
-_RESPONSE_MESSAGE_STATUSES = {"completed", "incomplete", "in_progress"}
-
-
-def _normalize_responses_message_status(value: Any, *, default: str = "completed") -> str:
-    """Normalize a Responses assistant message status for replay.
-
-    The API accepts completed/incomplete/in_progress on replayed assistant
-    output messages.  Preserve those exactly (modulo case/hyphen spelling) so
-    incomplete Codex continuation turns don't get falsely marked completed.
-    """
-    if isinstance(value, str):
-        status = value.strip().lower().replace("-", "_").replace(" ", "_")
-        if status in _RESPONSE_MESSAGE_STATUSES:
-            return status
-    return default
-
-
 def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
     """Convert internal chat-style messages to Responses input items."""
     items: List[Dict[str, Any]] = []
@@ -289,57 +272,7 @@ def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Di
                                 seen_item_ids.add(item_id)
                             has_codex_reasoning = True
 
-                # Replay exact assistant message items (with id/phase) from
-                # previous turns so the API can maintain prefix-cache hits.
-                # OpenAI docs: "preserve and resend phase on all assistant
-                # messages — dropping it can degrade performance."
-                codex_message_items = msg.get("codex_message_items")
-                replayed_message_items = 0
-                if isinstance(codex_message_items, list):
-                    for raw_item in codex_message_items:
-                        if not isinstance(raw_item, dict):
-                            continue
-                        if raw_item.get("type") != "message" or raw_item.get("role") != "assistant":
-                            continue
-                        raw_content_parts = raw_item.get("content")
-                        if not isinstance(raw_content_parts, list):
-                            continue
-
-                        normalized_content_parts = []
-                        for part in raw_content_parts:
-                            if not isinstance(part, dict):
-                                continue
-                            part_type = str(part.get("type") or "").strip()
-                            if part_type not in {"output_text", "text"}:
-                                continue
-                            text = part.get("text", "")
-                            if text is None:
-                                text = ""
-                            if not isinstance(text, str):
-                                text = str(text)
-                            normalized_content_parts.append({"type": "output_text", "text": text})
-
-                        if not normalized_content_parts:
-                            continue
-
-                        replay_item = {
-                            "type": "message",
-                            "role": "assistant",
-                            "status": _normalize_responses_message_status(raw_item.get("status")),
-                            "content": normalized_content_parts,
-                        }
-                        item_id = raw_item.get("id")
-                        if isinstance(item_id, str) and item_id.strip():
-                            replay_item["id"] = item_id.strip()
-                        phase = raw_item.get("phase")
-                        if isinstance(phase, str) and phase.strip():
-                            replay_item["phase"] = phase.strip()
-                        items.append(replay_item)
-                        replayed_message_items += 1
-
-                if replayed_message_items > 0:
-                    pass
-                elif content_parts:
+                if content_parts:
                     items.append({"role": "assistant", "content": content_parts})
                 elif content_text.strip():
                     items.append({"role": "assistant", "content": content_text})
@@ -499,47 +432,6 @@ def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
                 normalized.append(reasoning_item)
             continue
 
-        if item_type == "message":
-            role = item.get("role")
-            if role != "assistant":
-                raise ValueError(f"Codex Responses input[{idx}] message items must have role='assistant'.")
-            content = item.get("content")
-            if not isinstance(content, list):
-                raise ValueError(f"Codex Responses input[{idx}] message item must have content list.")
-            normalized_content = []
-            for part_idx, part in enumerate(content):
-                if not isinstance(part, dict):
-                    raise ValueError(
-                        f"Codex Responses input[{idx}] message content[{part_idx}] must be an object."
-                    )
-                part_type = part.get("type")
-                if part_type not in {"output_text", "text"}:
-                    raise ValueError(
-                        f"Codex Responses input[{idx}] message content[{part_idx}] has unsupported type {part_type!r}."
-                    )
-                text = part.get("text", "")
-                if text is None:
-                    text = ""
-                if not isinstance(text, str):
-                    text = str(text)
-                normalized_content.append({"type": "output_text", "text": text})
-            if not normalized_content:
-                raise ValueError(f"Codex Responses input[{idx}] message item must contain at least one text part.")
-            normalized_item: Dict[str, Any] = {
-                "type": "message",
-                "role": "assistant",
-                "status": _normalize_responses_message_status(item.get("status")),
-                "content": normalized_content,
-            }
-            item_id = item.get("id")
-            if isinstance(item_id, str) and item_id.strip():
-                normalized_item["id"] = item_id.strip()
-            phase = item.get("phase")
-            if isinstance(phase, str) and phase.strip():
-                normalized_item["phase"] = phase.strip()
-            normalized.append(normalized_item)
-            continue
-
         role = item.get("role")
         if role in {"user", "assistant"}:
             content = item.get("content", "")
@@ -824,7 +716,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
     content_parts: List[str] = []
     reasoning_parts: List[str] = []
     reasoning_items_raw: List[Dict[str, Any]] = []
-    message_items_raw: List[Dict[str, Any]] = []
     tool_calls: List[Any] = []
     has_incomplete_items = response_status in {"queued", "in_progress", "incomplete"}
     saw_commentary_phase = False
@@ -843,7 +734,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
 
         if item_type == "message":
             item_phase = getattr(item, "phase", None)
-            normalized_phase = None
             if isinstance(item_phase, str):
                 normalized_phase = item_phase.strip().lower()
                 if normalized_phase in {"commentary", "analysis"}:
@@ -853,18 +743,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
             message_text = _extract_responses_message_text(item)
             if message_text:
                 content_parts.append(message_text)
-                raw_message_item: Dict[str, Any] = {
-                    "type": "message",
-                    "role": "assistant",
-                    "status": _normalize_responses_message_status(item_status),
-                    "content": [{"type": "output_text", "text": message_text}],
-                }
-                item_id = getattr(item, "id", None)
-                if isinstance(item_id, str) and item_id:
-                    raw_message_item["id"] = item_id
-                if normalized_phase:
-                    raw_message_item["phase"] = normalized_phase
-                message_items_raw.append(raw_message_item)
         elif item_type == "reasoning":
             reasoning_text = _extract_responses_reasoning_text(item)
             if reasoning_text:
@@ -977,7 +855,6 @@ def _normalize_codex_response(response: Any) -> tuple[Any, str]:
         reasoning_content=None,
         reasoning_details=None,
         codex_reasoning_items=reasoning_items_raw or None,
-        codex_message_items=message_items_raw or None,
     )
 
     if tool_calls:

agent/context_compressor.py

@@ -61,52 +61,9 @@ _PRUNED_TOOL_PLACEHOLDER = "[Old tool output cleared to save context space]"
 
 # Chars per token rough estimate
 _CHARS_PER_TOKEN = 4
-# Flat token cost per attached image part.  Real cost varies by provider and
-# dimensions (Anthropic ≈ width×height/750, GPT-4o up to ~1700 for
-# high-detail 2048×2048, Gemini 258/tile), but 1600 is a realistic ceiling
-# that keeps compression budgeting honest for multi-image conversations.
-# Matches Claude Code's IMAGE_TOKEN_ESTIMATE constant.
-_IMAGE_TOKEN_ESTIMATE = 1600
-# Same figure expressed in the char-budget currency the rest of the
-# compressor speaks in.  Used when accumulating message "content length"
-# for tail-cut decisions.
-_IMAGE_CHAR_EQUIVALENT = _IMAGE_TOKEN_ESTIMATE * _CHARS_PER_TOKEN
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
-def _content_length_for_budget(raw_content: Any) -> int:
-    """Return the effective char-length of a message's content for token budgeting.
-
-    Plain strings: ``len(content)``. Multimodal lists: sum of text-part
-    ``len(text)`` plus a flat ``_IMAGE_CHAR_EQUIVALENT`` per image part
-    (``image_url`` / ``input_image`` / Anthropic-style ``image``). This
-    keeps the compressor from treating a turn with 5 attached images as
-    near-zero tokens just because the text part is empty.
-    """
-    if isinstance(raw_content, str):
-        return len(raw_content)
-    if not isinstance(raw_content, list):
-        return len(str(raw_content or ""))
-
-    total = 0
-    for p in raw_content:
-        if isinstance(p, str):
-            total += len(p)
-            continue
-        if not isinstance(p, dict):
-            total += len(str(p))
-            continue
-        ptype = p.get("type")
-        if ptype in {"image_url", "input_image", "image"}:
-            total += _IMAGE_CHAR_EQUIVALENT
-        else:
-            # text / input_text / tool_result-with-text / anything else with
-            # a text field.  Ignore the raw base64 payload inside image_url
-            # dicts — dimensions don't matter, only whether it's an image.
-            total += len(p.get("text", "") or "")
-    return total
-
-
 def _content_text_for_contains(content: Any) -> str:
     """Return a best-effort text view of message content.
 
@@ -338,10 +295,6 @@ class ContextCompressor(ContextEngine):
         self._context_probe_persistable = False
         self._previous_summary = None
         self._last_summary_error = None
-        self._last_summary_dropped_count = 0
-        self._last_summary_fallback_used = False
-        self._last_aux_model_failure_error = None
-        self._last_aux_model_failure_model = None
         self._last_compression_savings_pct = 100.0
         self._ineffective_compression_count = 0
 
@@ -445,17 +398,6 @@ class ContextCompressor(ContextEngine):
         self._ineffective_compression_count: int = 0
         self._summary_failure_cooldown_until: float = 0.0
         self._last_summary_error: Optional[str] = None
-        # When summary generation fails and a static fallback is inserted,
-        # record how many turns were unrecoverably dropped so callers
-        # (gateway hygiene, /compress) can surface a visible warning.
-        self._last_summary_dropped_count: int = 0
-        self._last_summary_fallback_used: bool = False
-        # When a user-configured summary model fails and we recover by
-        # retrying on the main model, record the failure so gateway /
-        # CLI callers can still warn the user even though compression
-        # succeeded.  Silent recovery would hide the broken config.
-        self._last_aux_model_failure_error: Optional[str] = None
-        self._last_aux_model_failure_model: Optional[str] = None
 
     def update_from_response(self, usage: Dict[str, Any]):
         """Update tracked token usage from API response."""
@@ -538,11 +480,11 @@ class ContextCompressor(ContextEngine):
             # Token-budget approach: walk backward accumulating tokens
             accumulated = 0
             boundary = len(result)
-            min_protect = min(protect_tail_count, len(result))
+            min_protect = min(protect_tail_count, len(result) - 1)
             for i in range(len(result) - 1, -1, -1):
                 msg = result[i]
                 raw_content = msg.get("content") or ""
-                content_len = _content_length_for_budget(raw_content)
+                content_len = sum(len(p.get("text", "")) for p in raw_content) if isinstance(raw_content, list) else len(raw_content)
                 msg_tokens = content_len // _CHARS_PER_TOKEN + 10
                 for tc in msg.get("tool_calls") or []:
                     if isinstance(tc, dict):
@@ -915,50 +857,10 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                     "Falling back to main model '%s' for compression.",
                     self.summary_model, e, self.model,
                 )
-                # Record the aux-model failure so callers can warn the user
-                # even if the retry-on-main succeeds — a misconfigured aux
-                # model is something the user needs to fix.
-                _err_text = str(e).strip() or e.__class__.__name__
-                if len(_err_text) > 220:
-                    _err_text = _err_text[:217].rstrip() + "..."
-                self._last_aux_model_failure_error = _err_text
-                self._last_aux_model_failure_model = self.summary_model
                 self.summary_model = ""  # empty = use main model
                 self._summary_failure_cooldown_until = 0.0  # no cooldown
                 return self._generate_summary(turns_to_summarize, focus_topic=focus_topic)  # retry immediately
 
-            # Unknown-error best-effort retry on main model.  Losing N turns of
-            # context is almost always worse than one extra summary attempt, so
-            # if we haven't already fallen back and the summary model differs
-            # from the main model, try once more on main before entering
-            # cooldown.  Errors that DID match _is_model_not_found above are
-            # already handled by the fast-path retry; this branch catches
-            # everything else (400s, provider-specific "no route" strings,
-            # aggregator rejections, etc.) where auto-retry is still safer
-            # than dropping the turns.
-            if (
-                self.summary_model
-                and self.summary_model != self.model
-                and not getattr(self, "_summary_model_fallen_back", False)
-            ):
-                self._summary_model_fallen_back = True
-                logging.warning(
-                    "Summary model '%s' failed (%s). "
-                    "Retrying on main model '%s' before giving up.",
-                    self.summary_model, e, self.model,
-                )
-                # Record the aux-model failure (see 404 branch above) — user
-                # should know their configured model is broken even if main
-                # recovers the call.
-                _err_text = str(e).strip() or e.__class__.__name__
-                if len(_err_text) > 220:
-                    _err_text = _err_text[:217].rstrip() + "..."
-                self._last_aux_model_failure_error = _err_text
-                self._last_aux_model_failure_model = self.summary_model
-                self.summary_model = ""  # empty = use main model
-                self._summary_failure_cooldown_until = 0.0
-                return self._generate_summary(turns_to_summarize, focus_topic=focus_topic)
-
             # Transient errors (timeout, rate limit, network) — shorter cooldown
             _transient_cooldown = 60
             self._summary_failure_cooldown_until = time.monotonic() + _transient_cooldown
@@ -992,8 +894,8 @@ The user has requested that this compaction PRIORITISE preserving all informatio
     def _get_tool_call_id(tc) -> str:
         """Extract the call ID from a tool_call entry (dict or SimpleNamespace)."""
         if isinstance(tc, dict):
-            return tc.get("call_id", "") or tc.get("id", "") or ""
-        return getattr(tc, "call_id", "") or getattr(tc, "id", "") or ""
+            return tc.get("id", "")
+        return getattr(tc, "id", "") or ""
 
     def _sanitize_tool_pairs(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """Fix orphaned tool_call / tool_result pairs after compression.
@@ -1180,9 +1082,8 @@ The user has requested that this compaction PRIORITISE preserving all informatio
 
         for i in range(n - 1, head_end - 1, -1):
             msg = messages[i]
-            raw_content = msg.get("content") or ""
-            content_len = _content_length_for_budget(raw_content)
-            msg_tokens = content_len // _CHARS_PER_TOKEN + 10  # +10 for role/metadata
+            content = msg.get("content") or ""
+            msg_tokens = len(content) // _CHARS_PER_TOKEN + 10  # +10 for role/metadata
             # Include tool call arguments in estimate
             for tc in msg.get("tool_calls") or []:
                 if isinstance(tc, dict):
@@ -1251,13 +1152,6 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                 related to this topic and be more aggressive about compressing
                 everything else.  Inspired by Claude Code's ``/compact``.
         """
-        # Reset per-call summary failure state — callers inspect these fields
-        # after compress() returns to decide whether to surface a warning.
-        self._last_summary_dropped_count = 0
-        self._last_summary_fallback_used = False
-        self._last_summary_error = None
-        self._last_aux_model_failure_error = None
-        self._last_aux_model_failure_model = None
         n_messages = len(messages)
         # Only need head + 3 tail messages minimum (token budget decides the real tail size)
         _min_for_compress = self.protect_first_n + 3 + 1
@@ -1336,13 +1230,11 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             if not self.quiet_mode:
                 logger.warning("Summary generation failed — inserting static fallback context marker")
             n_dropped = compress_end - compress_start
-            self._last_summary_dropped_count = n_dropped
-            self._last_summary_fallback_used = True
             summary = (
                 f"{SUMMARY_PREFIX}\n"
-                f"Summary generation was unavailable. {n_dropped} message(s) were "
+                f"Summary generation was unavailable. {n_dropped} conversation turns were "
                 f"removed to free context space but could not be summarized. The removed "
-                f"messages contained earlier work in this session. Continue based on the "
+                f"turns contained earlier work in this session. Continue based on the "
                 f"recent messages below and the current state of any files or resources."
             )
 

agent/copilot_acp_client.py

@@ -608,7 +608,7 @@ class CopilotACPClient:
                     end = start + limit if isinstance(limit, int) and limit > 0 else None
                     content = "".join(lines[start:end])
                 if content:
-                    content = redact_sensitive_text(content, force=True)
+                    content = redact_sensitive_text(content)
                 response = {
                     "jsonrpc": "2.0",
                     "id": message_id,

agent/credential_pool.py

@@ -7,13 +7,13 @@ import random
 import threading
 import time
 import uuid
+import os
 import re
 from dataclasses import dataclass, fields, replace
 from datetime import datetime
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 from hermes_constants import OPENROUTER_BASE_URL
-from hermes_cli.config import get_env_value
 import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
     CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
@@ -455,70 +455,6 @@ class CredentialPool:
             logger.debug("Failed to sync from credentials file: %s", exc)
         return entry
 
-    def _sync_codex_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
-        """Sync a Codex device_code pool entry from auth.json if tokens differ.
-
-        When a Codex OAuth access token expires (or the ChatGPT account hits
-        its 5h/weekly quota), the pool entry gets marked ``STATUS_EXHAUSTED``
-        with a ``last_error_reset_at`` that can be many hours in the future.
-        Meanwhile the user may run ``hermes model`` / ``hermes auth`` which
-        performs a fresh device-code login and writes new tokens to
-        ``auth.json`` under ``_auth_store_lock``.  Without this sync the pool
-        entry stays frozen until ``last_error_reset_at`` elapses — even
-        though fresh credentials are sitting on disk — and every request
-        fails with "no available entries (all exhausted or empty)".
-
-        Mirrors the Nous/Anthropic resync paths above.  Only applies to
-        device_code-sourced entries; env/API-key-sourced entries have no
-        auth.json shadow to sync from.
-        """
-        if self.provider != "openai-codex" or entry.source != "device_code":
-            return entry
-        try:
-            with _auth_store_lock():
-                auth_store = _load_auth_store()
-                state = _load_provider_state(auth_store, "openai-codex")
-            if not isinstance(state, dict):
-                return entry
-            tokens = state.get("tokens")
-            if not isinstance(tokens, dict):
-                return entry
-            store_access = tokens.get("access_token", "")
-            store_refresh = tokens.get("refresh_token", "")
-            # Adopt auth.json tokens when either side differs.  Codex refresh
-            # tokens are single-use too, so a fresh refresh_token from
-            # another process means our entry's pair is consumed/stale.
-            entry_access = entry.access_token or ""
-            entry_refresh = entry.refresh_token or ""
-            if store_access and (
-                store_access != entry_access
-                or (store_refresh and store_refresh != entry_refresh)
-            ):
-                logger.debug(
-                    "Pool entry %s: syncing Codex tokens from auth.json "
-                    "(refreshed by another process)",
-                    entry.id,
-                )
-                field_updates: Dict[str, Any] = {
-                    "access_token": store_access,
-                    "refresh_token": store_refresh or entry.refresh_token,
-                    "last_status": None,
-                    "last_status_at": None,
-                    "last_error_code": None,
-                    "last_error_reason": None,
-                    "last_error_message": None,
-                    "last_error_reset_at": None,
-                }
-                if state.get("last_refresh"):
-                    field_updates["last_refresh"] = state["last_refresh"]
-                updated = replace(entry, **field_updates)
-                self._replace_entry(entry, updated)
-                self._persist()
-                return updated
-        except Exception as exc:
-            logger.debug("Failed to sync Codex entry from auth.json: %s", exc)
-        return entry
-
     def _sync_nous_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
         """Sync a Nous pool entry from auth.json if tokens differ.
 
@@ -851,18 +787,6 @@ class CredentialPool:
                 if synced is not entry:
                     entry = synced
                     cleared_any = True
-            # For openai-codex entries, same pattern: the user may have
-            # re-authed via `hermes model` / `hermes auth` after a 429/401,
-            # leaving fresh tokens on disk while the pool entry is still
-            # frozen behind last_error_reset_at (can be hours in the
-            # future for ChatGPT weekly windows).
-            if (self.provider == "openai-codex"
-                    and entry.source == "device_code"
-                    and entry.last_status == STATUS_EXHAUSTED):
-                synced = self._sync_codex_entry_from_auth_store(entry)
-                if synced is not entry:
-                    entry = synced
-                    cleared_any = True
             if entry.last_status == STATUS_EXHAUSTED:
                 exhausted_until = _exhausted_until(entry)
                 if exhausted_until is not None and now < exhausted_until:
@@ -1299,48 +1223,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
         except Exception as exc:
             logger.debug("Qwen OAuth token seed failed: %s", exc)
 
-    elif provider == "minimax-oauth":
-        # MiniMax OAuth tokens live in ~/.hermes/auth.json providers.minimax-oauth.
-        # Seed the pool so `/auth list` reflects the logged-in state and the
-        # standard `hermes auth remove minimax-oauth <N>` flow works.
-        # Use refresh_if_expiring=False equivalent: resolve_minimax_oauth_runtime_credentials
-        # always refreshes on expiry, so instead read raw state here to avoid
-        # surprise network calls during provider discovery.
-        try:
-            from hermes_cli.auth import get_provider_auth_state
-            state = get_provider_auth_state("minimax-oauth")
-            if state and state.get("access_token"):
-                source_name = "oauth"
-                if not _is_suppressed(provider, source_name):
-                    active_sources.add(source_name)
-                    expires_at_ms = None
-                    try:
-                        from datetime import datetime as _dt
-                        raw = state.get("expires_at", "")
-                        if raw:
-                            expires_at_ms = int(_dt.fromisoformat(raw).timestamp() * 1000)
-                    except Exception:
-                        expires_at_ms = None
-                    base_url = str(state.get("inference_base_url", "") or "").rstrip("/")
-                    changed |= _upsert_entry(
-                        entries,
-                        provider,
-                        source_name,
-                        {
-                            "source": source_name,
-                            "auth_type": AUTH_TYPE_OAUTH,
-                            "access_token": state["access_token"],
-                            "refresh_token": state.get("refresh_token"),
-                            "expires_at_ms": expires_at_ms,
-                            "base_url": base_url,
-                            "label": state.get("label", "") or label_from_token(
-                                state.get("access_token", ""), source_name
-                            ),
-                        },
-                    )
-        except Exception as exc:
-            logger.debug("MiniMax OAuth token seed failed: %s", exc)
-
     elif provider == "openai-codex":
         # Respect user suppression — `hermes auth remove openai-codex` marks
         # the device_code source as suppressed so it won't be re-seeded from
@@ -1391,8 +1273,7 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         def _is_source_suppressed(_p, _s):  # type: ignore[misc]
             return False
     if provider == "openrouter":
-        # Check both os.environ and ~/.hermes/.env file
-        token = (get_env_value("OPENROUTER_API_KEY") or "").strip()
+        token = os.getenv("OPENROUTER_API_KEY", "").strip()
         if token:
             source = "env:OPENROUTER_API_KEY"
             if _is_source_suppressed(provider, source):
@@ -1418,7 +1299,7 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
 
     env_url = ""
     if pconfig.base_url_env_var:
-        env_url = (get_env_value(pconfig.base_url_env_var) or "").strip().rstrip("/")
+        env_url = os.getenv(pconfig.base_url_env_var, "").strip().rstrip("/")
 
     env_vars = list(pconfig.api_key_env_vars)
     if provider == "anthropic":
@@ -1429,8 +1310,7 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         ]
 
     for env_var in env_vars:
-        # Check both os.environ and ~/.hermes/.env file
-        token = (get_env_value(env_var) or "").strip()
+        token = os.getenv(env_var, "").strip()
         if not token:
             continue
         source = f"env:{env_var}"

agent/credential_sources.py

@@ -47,6 +47,7 @@ from __future__ import annotations
 
 import os
 from dataclasses import dataclass, field
+from pathlib import Path
 from typing import Callable, List, Optional
 
 
@@ -252,19 +253,6 @@ def _remove_nous_device_code(provider: str, removed) -> RemovalResult:
     return result
 
 
-def _remove_minimax_oauth(provider: str, removed) -> RemovalResult:
-    """MiniMax OAuth lives in auth.json providers.minimax-oauth — clear it.
-
-    Same pattern as Nous: single-source OAuth state with refresh tokens.
-    Suppression of the `oauth` source ensures the pool reseed path
-    (_seed_from_singletons) doesn't instantly undo the removal.
-    """
-    result = RemovalResult()
-    if _clear_auth_store_provider(provider):
-        result.cleaned.append(f"Cleared {provider} OAuth tokens from auth store")
-    return result
-
-
 def _remove_codex_device_code(provider: str, removed) -> RemovalResult:
     """Codex tokens live in TWO places: our auth store AND ~/.codex/auth.json.
 
@@ -402,11 +390,6 @@ def _register_all_sources() -> None:
         remove_fn=_remove_qwen_cli,
         description="~/.qwen/oauth_creds.json",
     ))
-    register(RemovalStep(
-        provider="minimax-oauth", source_id="oauth",
-        remove_fn=_remove_minimax_oauth,
-        description="auth.json providers.minimax-oauth",
-    ))
     register(RemovalStep(
         provider="*", source_id="config:",
         match_fn=lambda src: src.startswith("config:") or src == "model_config",

agent/curator_backup.py

@@ -1,440 +0,0 @@
-"""Curator snapshot + rollback.
-
-A pre-run snapshot of ``~/.hermes/skills/`` (excluding ``.curator_backups/``
-itself) is taken before any mutating curator pass. Snapshots are tar.gz
-files under ``~/.hermes/skills/.curator_backups/<utc-iso>/`` with a
-companion ``manifest.json`` describing the snapshot (reason, time, size,
-counted skill files). Rollback picks a snapshot, moves the current
-``skills/`` tree aside into another snapshot so even the rollback itself
-is undoable, then extracts the chosen snapshot into place.
-
-The snapshot does NOT include:
-  - ``.curator_backups/`` (would recurse)
-  - ``.hub/`` (hub-installed skills — managed by the hub, not us)
-
-It DOES include:
-  - all SKILL.md files + their directories (``scripts/``, ``references/``,
-    ``templates/``, ``assets/``)
-  - ``.usage.json`` (usage telemetry — needed to rehydrate state cleanly)
-  - ``.archive/`` (so rollback restores previously-archived skills too)
-  - ``.curator_state`` (so rolling back also restores the last-run-at
-    pointer — otherwise the curator would immediately re-fire on the next
-    tick)
-  - ``.bundled_manifest`` (so protection markers stay consistent)
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import re
-import shutil
-import tarfile
-import tempfile
-import time
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-from hermes_constants import get_hermes_home
-
-logger = logging.getLogger(__name__)
-
-
-DEFAULT_KEEP = 5
-
-# Entries under skills/ that should NEVER be rolled up into a snapshot.
-# .hub/ is managed by the skills hub; rolling it back would break lockfile
-# invariants. .curator_backups is the backup dir itself — recursion bomb.
-_EXCLUDE_TOP_LEVEL = {".curator_backups", ".hub"}
-
-# Snapshot id regex: UTC ISO with colons replaced by dashes so the filename
-# is portable (Windows-safe). An optional ``-NN`` suffix handles two
-# snapshots landing in the same wallclock second.
-_ID_RE = re.compile(r"^\d{4}-\d{2}-\d{2}T\d{2}-\d{2}-\d{2}Z(-\d{2})?$")
-
-
-def _backups_dir() -> Path:
-    return get_hermes_home() / "skills" / ".curator_backups"
-
-
-def _skills_dir() -> Path:
-    return get_hermes_home() / "skills"
-
-
-def _utc_id(now: Optional[datetime] = None) -> str:
-    """UTC ISO-ish filesystem-safe timestamp: ``2026-05-01T13-05-42Z``."""
-    if now is None:
-        now = datetime.now(timezone.utc)
-    # isoformat → "2026-05-01T13:05:42.123456+00:00"; strip subseconds and tz.
-    s = now.replace(microsecond=0).isoformat()
-    if s.endswith("+00:00"):
-        s = s[:-6]
-    return s.replace(":", "-") + "Z"
-
-
-def _load_config() -> Dict[str, Any]:
-    try:
-        from hermes_cli.config import load_config
-        cfg = load_config()
-    except Exception as e:
-        logger.debug("Failed to load config for curator backup: %s", e)
-        return {}
-    if not isinstance(cfg, dict):
-        return {}
-    cur = cfg.get("curator") or {}
-    if not isinstance(cur, dict):
-        return {}
-    bk = cur.get("backup") or {}
-    return bk if isinstance(bk, dict) else {}
-
-
-def is_enabled() -> bool:
-    """Default ON — the whole point of the backup is safety by default."""
-    return bool(_load_config().get("enabled", True))
-
-
-def get_keep() -> int:
-    cfg = _load_config()
-    try:
-        n = int(cfg.get("keep", DEFAULT_KEEP))
-    except (TypeError, ValueError):
-        n = DEFAULT_KEEP
-    return max(1, n)
-
-
-# ---------------------------------------------------------------------------
-# Snapshot
-# ---------------------------------------------------------------------------
-
-def _count_skill_files(base: Path) -> int:
-    try:
-        return sum(1 for _ in base.rglob("SKILL.md"))
-    except OSError:
-        return 0
-
-
-def _write_manifest(dest: Path, reason: str, archive_path: Path,
-                    skills_counted: int) -> None:
-    manifest = {
-        "id": dest.name,
-        "reason": reason,
-        "created_at": datetime.now(timezone.utc).isoformat(),
-        "archive": archive_path.name,
-        "archive_bytes": archive_path.stat().st_size,
-        "skill_files": skills_counted,
-    }
-    (dest / "manifest.json").write_text(
-        json.dumps(manifest, indent=2, sort_keys=True), encoding="utf-8"
-    )
-
-
-def snapshot_skills(reason: str = "manual") -> Optional[Path]:
-    """Create a tar.gz snapshot of ``~/.hermes/skills/`` and prune old ones.
-
-    Returns the snapshot directory path, or ``None`` if the snapshot was
-    skipped (backup disabled, skills dir missing, or an IO error occurred —
-    in which case we log at debug and return None so the curator never
-    aborts a pass because of a backup failure).
-    """
-    if not is_enabled():
-        logger.debug("Curator backup disabled by config; skipping snapshot")
-        return None
-
-    skills = _skills_dir()
-    if not skills.exists():
-        logger.debug("No ~/.hermes/skills/ directory — nothing to back up")
-        return None
-
-    backups = _backups_dir()
-    try:
-        backups.mkdir(parents=True, exist_ok=True)
-    except OSError as e:
-        logger.debug("Failed to create backups dir %s: %s", backups, e)
-        return None
-
-    # Uniquify: if a snapshot with the same second already exists (can
-    # happen if two curator runs fire in the same second), append a short
-    # counter. Avoids clobbering and avoids timestamp collisions.
-    base_id = _utc_id()
-    snap_id = base_id
-    counter = 1
-    while (backups / snap_id).exists():
-        snap_id = f"{base_id}-{counter:02d}"
-        counter += 1
-
-    dest = backups / snap_id
-    try:
-        dest.mkdir(parents=True, exist_ok=False)
-    except OSError as e:
-        logger.debug("Failed to create snapshot dir %s: %s", dest, e)
-        return None
-
-    archive = dest / "skills.tar.gz"
-    try:
-        # Stream into the tarball — no tempdir copy needed.
-        with tarfile.open(archive, "w:gz", compresslevel=6) as tf:
-            for entry in sorted(skills.iterdir()):
-                if entry.name in _EXCLUDE_TOP_LEVEL:
-                    continue
-                # arcname: store paths relative to skills/ so extraction
-                # drops cleanly back into the skills dir.
-                tf.add(str(entry), arcname=entry.name, recursive=True)
-        _write_manifest(dest, reason, archive, _count_skill_files(skills))
-    except (OSError, tarfile.TarError) as e:
-        logger.debug("Curator snapshot failed: %s", e, exc_info=True)
-        # Clean up partial snapshot
-        try:
-            shutil.rmtree(dest, ignore_errors=True)
-        except OSError:
-            pass
-        return None
-
-    _prune_old(keep=get_keep())
-    logger.info("Curator snapshot created: %s (%s)", snap_id, reason)
-    return dest
-
-
-def _prune_old(keep: int) -> List[str]:
-    """Delete regular snapshots beyond the newest *keep*. Returns deleted
-    ids. Staging dirs (``.rollback-staging-*``) are implementation detail
-    and pruned independently on every call."""
-    backups = _backups_dir()
-    if not backups.exists():
-        return []
-    entries: List[Tuple[str, Path]] = []
-    stale_staging: List[Path] = []
-    for child in backups.iterdir():
-        if not child.is_dir():
-            continue
-        if child.name.startswith(".rollback-staging-"):
-            # Staging dirs are only supposed to exist briefly during a
-            # rollback. If we find one here (e.g. from a crashed rollback),
-            # clean it up opportunistically.
-            stale_staging.append(child)
-            continue
-        if _ID_RE.match(child.name):
-            entries.append((child.name, child))
-    # Newest first (lexicographic works because the id is UTC ISO).
-    entries.sort(key=lambda t: t[0], reverse=True)
-    deleted: List[str] = []
-    for _, path in entries[keep:]:
-        try:
-            shutil.rmtree(path)
-            deleted.append(path.name)
-        except OSError as e:
-            logger.debug("Failed to prune %s: %s", path, e)
-    for path in stale_staging:
-        try:
-            shutil.rmtree(path)
-        except OSError as e:
-            logger.debug("Failed to clean stale staging dir %s: %s", path, e)
-    return deleted
-
-
-# ---------------------------------------------------------------------------
-# List + rollback
-# ---------------------------------------------------------------------------
-
-def _read_manifest(snap_dir: Path) -> Dict[str, Any]:
-    mf = snap_dir / "manifest.json"
-    if not mf.exists():
-        return {}
-    try:
-        return json.loads(mf.read_text(encoding="utf-8"))
-    except (OSError, json.JSONDecodeError):
-        return {}
-
-
-def list_backups() -> List[Dict[str, Any]]:
-    """Return all restorable snapshots, newest first. Only entries with a
-    real ``skills.tar.gz`` tarball are listed — transient
-    ``.rollback-staging-*`` directories created mid-rollback are
-    implementation detail and not shown."""
-    backups = _backups_dir()
-    if not backups.exists():
-        return []
-    out: List[Dict[str, Any]] = []
-    for child in sorted(backups.iterdir(), reverse=True):
-        if not child.is_dir():
-            continue
-        if not _ID_RE.match(child.name):
-            continue
-        if not (child / "skills.tar.gz").exists():
-            continue
-        mf = _read_manifest(child)
-        mf.setdefault("id", child.name)
-        mf.setdefault("path", str(child))
-        if "archive_bytes" not in mf:
-            arc = child / "skills.tar.gz"
-            try:
-                mf["archive_bytes"] = arc.stat().st_size
-            except OSError:
-                mf["archive_bytes"] = 0
-        out.append(mf)
-    return out
-
-
-def _resolve_backup(backup_id: Optional[str]) -> Optional[Path]:
-    """Return the path of the requested backup, or the newest one if
-    *backup_id* is None. Returns None if no match."""
-    backups = _backups_dir()
-    if not backups.exists():
-        return None
-    if backup_id:
-        target = backups / backup_id
-        if (
-            target.is_dir()
-            and _ID_RE.match(backup_id)
-            and (target / "skills.tar.gz").exists()
-        ):
-            return target
-        return None
-    candidates = [
-        c for c in sorted(backups.iterdir(), reverse=True)
-        if c.is_dir() and _ID_RE.match(c.name) and (c / "skills.tar.gz").exists()
-    ]
-    return candidates[0] if candidates else None
-
-
-def rollback(backup_id: Optional[str] = None) -> Tuple[bool, str, Optional[Path]]:
-    """Restore ``~/.hermes/skills/`` from a snapshot.
-
-    Strategy:
-      1. Resolve the target snapshot (explicit id or newest regular).
-      2. Take a safety snapshot of the CURRENT skills tree under
-         ``.curator_backups/pre-rollback-<ts>/`` so the rollback itself is
-         undoable.
-      3. Move all current top-level entries (except ``.curator_backups``
-         and ``.hub``) into a tempdir.
-      4. Extract the chosen snapshot into ``~/.hermes/skills/``.
-      5. On failure during 4, move the tempdir contents back (best-effort)
-         and return failure.
-
-    Returns ``(ok, message, snapshot_path)``.
-    """
-    target = _resolve_backup(backup_id)
-    if target is None:
-        return (
-            False,
-            f"no matching backup found"
-            + (f" for id '{backup_id}'" if backup_id else "")
-            + " (use `hermes curator rollback --list` to see available snapshots)",
-            None,
-        )
-    archive = target / "skills.tar.gz"
-    if not archive.exists():
-        return (False, f"snapshot {target.name} has no skills.tar.gz — corrupted?", None)
-
-    skills = _skills_dir()
-    skills.mkdir(parents=True, exist_ok=True)
-    backups = _backups_dir()
-    backups.mkdir(parents=True, exist_ok=True)
-
-    # Step 2: safety snapshot of current state FIRST. If this fails we bail
-    # out before touching anything — otherwise a failed extract could leave
-    # the user with no skills.
-    try:
-        snapshot_skills(reason=f"pre-rollback to {target.name}")
-    except Exception as e:
-        return (False, f"pre-rollback safety snapshot failed: {e}", None)
-
-    # Additionally move current entries into an internal staging dir so
-    # the extract happens into an empty skills tree (predictable result).
-    # This dir is implementation detail — not listed as a restorable
-    # backup. The safety snapshot above is the user-facing undo handle.
-    staged = backups / f".rollback-staging-{_utc_id()}"
-    try:
-        staged.mkdir(parents=True, exist_ok=False)
-    except OSError as e:
-        return (False, f"failed to create staging dir: {e}", None)
-
-    moved: List[Tuple[Path, Path]] = []
-    try:
-        for entry in list(skills.iterdir()):
-            if entry.name in _EXCLUDE_TOP_LEVEL:
-                continue
-            dest = staged / entry.name
-            shutil.move(str(entry), str(dest))
-            moved.append((entry, dest))
-    except OSError as e:
-        # Best-effort rollback of the move
-        for orig, dest in moved:
-            try:
-                shutil.move(str(dest), str(orig))
-            except OSError:
-                pass
-        try:
-            shutil.rmtree(staged, ignore_errors=True)
-        except OSError:
-            pass
-        return (False, f"failed to stage current skills: {e}", None)
-
-    # Step 4: extract the snapshot into skills/
-    try:
-        with tarfile.open(archive, "r:gz") as tf:
-            # Python 3.12+ supports filter='data' for safer extraction.
-            # Fall back to the unfiltered call for older interpreters but
-            # still reject absolute paths and .. components defensively.
-            for member in tf.getmembers():
-                name = member.name
-                if name.startswith("/") or ".." in Path(name).parts:
-                    raise tarfile.TarError(
-                        f"refusing to extract unsafe path: {name!r}"
-                    )
-            try:
-                tf.extractall(str(skills), filter="data")  # type: ignore[call-arg]
-            except TypeError:
-                # Python < 3.12 — no filter kwarg
-                tf.extractall(str(skills))
-    except (OSError, tarfile.TarError) as e:
-        # Best-effort recover: move staged contents back
-        for orig, dest in moved:
-            try:
-                shutil.move(str(dest), str(orig))
-            except OSError:
-                pass
-        try:
-            shutil.rmtree(staged, ignore_errors=True)
-        except OSError:
-            pass
-        return (False, f"snapshot extract failed (state restored): {e}", None)
-
-    # Extract succeeded — the staging dir has served its purpose. The
-    # user's undo handle is the safety snapshot tarball we took earlier.
-    try:
-        shutil.rmtree(staged, ignore_errors=True)
-    except OSError:
-        pass
-
-    logger.info("Curator rollback: restored from %s", target.name)
-    return (True, f"restored from snapshot {target.name}", target)
-
-
-# ---------------------------------------------------------------------------
-# Human-readable summary for CLI
-# ---------------------------------------------------------------------------
-
-def format_size(n: int) -> str:
-    for unit in ("B", "KB", "MB", "GB"):
-        if n < 1024 or unit == "GB":
-            return f"{n:.1f} {unit}" if unit != "B" else f"{n} B"
-        n /= 1024
-    return f"{n:.1f} GB"
-
-
-def summarize_backups() -> str:
-    rows = list_backups()
-    if not rows:
-        return "No curator snapshots yet."
-    lines = [f"{'id':<24}  {'reason':<40}  {'skills':>6}  {'size':>8}"]
-    lines.append("─" * len(lines[0]))
-    for r in rows:
-        lines.append(
-            f"{r.get('id','?'):<24}  "
-            f"{(r.get('reason','?') or '?')[:40]:<40}  "
-            f"{r.get('skill_files', 0):>6}  "
-            f"{format_size(int(r.get('archive_bytes', 0))):>8}"
-        )
-    return "\n".join(lines)

agent/error_classifier.py

@@ -42,7 +42,6 @@ class FailoverReason(enum.Enum):
     # Context / payload
     context_overflow = "context_overflow"  # Context too large — compress, not failover
     payload_too_large = "payload_too_large"  # 413 — compress payload
-    image_too_large = "image_too_large"   # Native image part exceeds provider's per-image limit — shrink and retry
 
     # Model
     model_not_found = "model_not_found"  # 404 or invalid model — fallback to different model
@@ -54,7 +53,6 @@ class FailoverReason(enum.Enum):
     # Provider-specific
     thinking_signature = "thinking_signature"  # Anthropic thinking block sig invalid
     long_context_tier = "long_context_tier"    # Anthropic "extra usage" tier gate
-    oauth_long_context_beta_forbidden = "oauth_long_context_beta_forbidden"  # Anthropic OAuth subscription rejects 1M context beta — disable beta and retry
 
     # Catch-all
     unknown = "unknown"                  # Unclassifiable — retry with backoff
@@ -92,7 +90,6 @@ class ClassifiedError:
 _BILLING_PATTERNS = [
     "insufficient credits",
     "insufficient_quota",
-    "insufficient balance",
     "credit balance",
     "credits have been exhausted",
     "top up your credits",
@@ -150,20 +147,6 @@ _PAYLOAD_TOO_LARGE_PATTERNS = [
     "error code: 413",
 ]
 
-# Image-size patterns.  Matched against 400 bodies (not 413) because most
-# providers return a 400 with a specific image-too-big message before the
-# whole request hits the 413 size limit.  Anthropic's wording is the most
-# important here (hard 5 MB per image, returned as
-# "messages.N.content.K.image.source.base64: image exceeds 5 MB maximum").
-_IMAGE_TOO_LARGE_PATTERNS = [
-    "image exceeds",        # Anthropic: "image exceeds 5 MB maximum"
-    "image too large",      # generic
-    "image_too_large",      # error_code variant
-    "image size exceeds",   # variant
-    # "request_too_large" on a request known to contain an image → image is
-    # the likely culprit; we still try the shrink path before giving up.
-]
-
 # Context overflow patterns
 _CONTEXT_OVERFLOW_PATTERNS = [
     "context length",
@@ -451,25 +434,6 @@ def classify_api_error(
             should_compress=True,
         )
 
-    # Anthropic OAuth subscription rejects the 1M-context beta header.
-    # Observed error body: "The long context beta is not yet available for
-    # this subscription." Returned as HTTP 400 from native Anthropic when
-    # the subscription doesn't include 1M context, even though the request
-    # carries ``anthropic-beta: context-1m-2025-08-07``. The recovery path
-    # in run_agent.py rebuilds the Anthropic client with the beta stripped
-    # and retries once. Pattern is narrow enough that it won't collide with
-    # the 429 tier-gate pattern above (different status, different phrase).
-    if (
-        status_code == 400
-        and "long context beta" in error_msg
-        and "not yet available" in error_msg
-    ):
-        return _result(
-            FailoverReason.oauth_long_context_beta_forbidden,
-            retryable=True,
-            should_compress=False,
-        )
-
     # ── 2. HTTP status code classification ──────────────────────────
 
     if status_code is not None:
@@ -707,15 +671,6 @@ def _classify_400(
 ) -> ClassifiedError:
     """Classify 400 Bad Request — context overflow, format error, or generic."""
 
-    # Image-too-large from 400 (Anthropic's 5 MB per-image check fires this way).
-    # Must be checked BEFORE context_overflow because messages can trip both
-    # patterns ("exceeds" + "image") and image-shrink is a cheaper recovery.
-    if any(p in error_msg for p in _IMAGE_TOO_LARGE_PATTERNS):
-        return result_fn(
-            FailoverReason.image_too_large,
-            retryable=True,
-        )
-
     # Context overflow from 400
     if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
         return result_fn(
@@ -843,13 +798,6 @@ def _classify_by_message(
             should_compress=True,
         )
 
-    # Image-too-large patterns (from message text when no status_code)
-    if any(p in error_msg for p in _IMAGE_TOO_LARGE_PATTERNS):
-        return result_fn(
-            FailoverReason.image_too_large,
-            retryable=True,
-        )
-
     # Usage-limit patterns need the same disambiguation as 402: some providers
     # surface "usage limit" errors without an HTTP status code.  A transient
     # signal ("try again", "resets at", …) means it's a periodic quota, not

agent/gemini_cloudcode_adapter.py

@@ -30,6 +30,7 @@ from __future__ import annotations
 
 import json
 import logging
+import os
 import time
 import uuid
 from types import SimpleNamespace
@@ -41,6 +42,7 @@ from agent import google_oauth
 from agent.gemini_schema import sanitize_gemini_tool_parameters
 from agent.google_code_assist import (
     CODE_ASSIST_ENDPOINT,
+    FREE_TIER_ID,
     CodeAssistError,
     ProjectContext,
     resolve_project_context,

agent/gemini_schema.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Any, Dict
+from typing import Any, Dict, List
 
 # Gemini's ``FunctionDeclaration.parameters`` field accepts the ``Schema``
 # object, which is only a subset of OpenAPI 3.0 / JSON Schema.  Strip fields

agent/google_code_assist.py

@@ -29,6 +29,7 @@ from __future__ import annotations
 
 import json
 import logging
+import os
 import time
 import urllib.error
 import urllib.parse

agent/google_oauth.py

@@ -49,13 +49,14 @@ import json
 import logging
 import os
 import secrets
+import socket
 import stat
 import threading
 import time
 import urllib.error
 import urllib.parse
 import urllib.request
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Dict, Optional, Tuple
 
@@ -97,7 +98,6 @@ _DEFAULT_CLIENT_SECRET = f"GOCSPX-{_PUBLIC_CLIENT_SECRET_SUFFIX}"
 
 # Regex patterns for fallback scraping from an installed gemini-cli.
 import re as _re
-from utils import atomic_replace
 _CLIENT_ID_PATTERN = _re.compile(
     r"OAUTH_CLIENT_ID\s*=\s*['\"]([0-9]+-[a-z0-9]+\.apps\.googleusercontent\.com)['\"]"
 )
@@ -499,7 +499,7 @@ def save_credentials(creds: GoogleCredentials) -> Path:
                 fh.flush()
                 os.fsync(fh.fileno())
             os.chmod(tmp_path, stat.S_IRUSR | stat.S_IWUSR)
-            atomic_replace(tmp_path, path)
+            os.replace(tmp_path, path)
         finally:
             try:
                 if tmp_path.exists():

agent/image_routing.py

@@ -1,236 +0,0 @@
-"""Routing helpers for inbound user-attached images.
-
-Two modes:
-
-  native  — attach images as OpenAI-style ``image_url`` content parts on the
-            user turn. Provider adapters (Anthropic, Gemini, Bedrock, Codex,
-            OpenAI chat.completions) already translate these into their
-            vendor-specific multimodal formats.
-
-  text    — run ``vision_analyze`` on each image up-front and prepend the
-            description to the user's text. The model never sees the pixels;
-            it only sees a lossy text summary. This is the pre-existing
-            behaviour and still the right choice for non-vision models.
-
-The decision is made once per message turn by :func:`decide_image_input_mode`.
-It reads ``agent.image_input_mode`` from config.yaml (``auto`` | ``native``
-| ``text``, default ``auto``) and the active model's capability metadata.
-
-In ``auto`` mode:
-  - If the user has explicitly configured ``auxiliary.vision.provider``
-    (i.e. not ``auto`` and not empty), we assume they want the text pipeline
-    regardless of the main model — they've opted in to a specific vision
-    backend for a reason (cost, quality, local-only, etc.).
-  - Otherwise, if the active model reports ``supports_vision=True`` in its
-    models.dev metadata, we attach natively.
-  - Otherwise (non-vision model, no explicit override), we fall back to text.
-
-This keeps ``vision_analyze`` surfaced as a tool in every session — skills
-and agent flows that chain it (browser screenshots, deeper inspection of
-URL-referenced images, style-gating loops) keep working. The routing only
-affects *how user-attached images on the current turn* are presented to the
-main model.
-"""
-
-from __future__ import annotations
-
-import base64
-import logging
-import mimetypes
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-
-_VALID_MODES = frozenset({"auto", "native", "text"})
-
-
-def _coerce_mode(raw: Any) -> str:
-    """Normalize a config value into one of the valid modes."""
-    if not isinstance(raw, str):
-        return "auto"
-    val = raw.strip().lower()
-    if val in _VALID_MODES:
-        return val
-    return "auto"
-
-
-def _explicit_aux_vision_override(cfg: Optional[Dict[str, Any]]) -> bool:
-    """True when the user configured a specific auxiliary vision backend.
-
-    An explicit override means the user *wants* the text pipeline (they're
-    paying for a dedicated vision model), so we don't silently bypass it.
-    """
-    if not isinstance(cfg, dict):
-        return False
-    aux = cfg.get("auxiliary") or {}
-    if not isinstance(aux, dict):
-        return False
-    vision = aux.get("vision") or {}
-    if not isinstance(vision, dict):
-        return False
-
-    provider = str(vision.get("provider") or "").strip().lower()
-    model = str(vision.get("model") or "").strip()
-    base_url = str(vision.get("base_url") or "").strip()
-
-    # "auto" / "" / blank = not explicit
-    if provider in ("", "auto") and not model and not base_url:
-        return False
-    return True
-
-
-def _lookup_supports_vision(provider: str, model: str) -> Optional[bool]:
-    """Return True/False if we can resolve caps, None if unknown."""
-    if not provider or not model:
-        return None
-    try:
-        from agent.models_dev import get_model_capabilities
-        caps = get_model_capabilities(provider, model)
-    except Exception as exc:  # pragma: no cover - defensive
-        logger.debug("image_routing: caps lookup failed for %s:%s — %s", provider, model, exc)
-        return None
-    if caps is None:
-        return None
-    return bool(caps.supports_vision)
-
-
-def decide_image_input_mode(
-    provider: str,
-    model: str,
-    cfg: Optional[Dict[str, Any]],
-) -> str:
-    """Return ``"native"`` or ``"text"`` for the given turn.
-
-    Args:
-      provider: active inference provider ID (e.g. ``"anthropic"``, ``"openrouter"``).
-      model:    active model slug as it would be sent to the provider.
-      cfg:      loaded config.yaml dict, or None. When None, behaves as auto.
-    """
-    mode_cfg = "auto"
-    if isinstance(cfg, dict):
-        agent_cfg = cfg.get("agent") or {}
-        if isinstance(agent_cfg, dict):
-            mode_cfg = _coerce_mode(agent_cfg.get("image_input_mode"))
-
-    if mode_cfg == "native":
-        return "native"
-    if mode_cfg == "text":
-        return "text"
-
-    # auto
-    if _explicit_aux_vision_override(cfg):
-        return "text"
-
-    supports = _lookup_supports_vision(provider, model)
-    if supports is True:
-        return "native"
-    return "text"
-
-
-# Image size handling is REACTIVE rather than proactive: we attempt native
-# attachment at full size regardless of provider, and rely on
-# ``run_agent._try_shrink_image_parts_in_messages`` to shrink + retry if
-# the provider rejects the request (e.g. Anthropic's hard 5 MB per-image
-# ceiling returned as HTTP 400 "image exceeds 5 MB maximum").
-#
-# Why reactive: our knowledge of provider ceilings is partial and evolving
-# (OpenAI accepts 49 MB+, Anthropic 5 MB, Gemini 100 MB, others unknown).
-# A proactive per-provider table would be stale the moment a provider raises
-# or lowers its limit, and silently degrading quality for users on providers
-# that would have accepted the full image is the worse failure mode.
-# The shrink-on-reject path loses 1 API call + maybe 1s of Pillow work when
-# it fires, which is cheaper than permanent quality loss.
-
-
-def _guess_mime(path: Path) -> str:
-    mime, _ = mimetypes.guess_type(str(path))
-    if mime and mime.startswith("image/"):
-        return mime
-    # mimetypes on some Linux distros mis-maps .jpg; default to jpeg when
-    # the suffix looks imagey.
-    suffix = path.suffix.lower()
-    return {
-        ".jpg": "image/jpeg",
-        ".jpeg": "image/jpeg",
-        ".png": "image/png",
-        ".gif": "image/gif",
-        ".webp": "image/webp",
-        ".bmp": "image/bmp",
-    }.get(suffix, "image/jpeg")
-
-
-def _file_to_data_url(path: Path) -> Optional[str]:
-    """Encode a local image as a base64 data URL at its native size.
-
-    Size limits are NOT enforced here — the agent retry loop
-    (``run_agent._try_shrink_image_parts_in_messages``) shrinks on the
-    provider's first rejection. Keeping this simple means providers that
-    accept large images (OpenAI 49 MB+, Gemini 100 MB) don't pay a silent
-    quality tax just because one other provider is stricter.
-
-    Returns None only if the file can't be read (missing, permission
-    denied, etc.); the caller reports those paths in ``skipped``.
-    """
-    try:
-        raw = path.read_bytes()
-    except Exception as exc:
-        logger.warning("image_routing: failed to read %s — %s", path, exc)
-        return None
-    mime = _guess_mime(path)
-    b64 = base64.b64encode(raw).decode("ascii")
-    return f"data:{mime};base64,{b64}"
-
-
-def build_native_content_parts(
-    user_text: str,
-    image_paths: List[str],
-) -> Tuple[List[Dict[str, Any]], List[str]]:
-    """Build an OpenAI-style ``content`` list for a user turn.
-
-    Shape:
-      [{"type": "text", "text": "..."},
-       {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}},
-       ...]
-
-    Images are attached at their native size. If a provider rejects the
-    request because an image is too large (e.g. Anthropic's 5 MB per-image
-    ceiling), the agent's retry loop transparently shrinks and retries
-    once — see ``run_agent._try_shrink_image_parts_in_messages``.
-
-    Returns (content_parts, skipped_paths). Skipped paths are files that
-    couldn't be read from disk.
-    """
-    parts: List[Dict[str, Any]] = []
-    skipped: List[str] = []
-
-    text = (user_text or "").strip()
-    if text:
-        parts.append({"type": "text", "text": text})
-
-    for raw_path in image_paths:
-        p = Path(raw_path)
-        if not p.exists() or not p.is_file():
-            skipped.append(str(raw_path))
-            continue
-        data_url = _file_to_data_url(p)
-        if not data_url:
-            skipped.append(str(raw_path))
-            continue
-        parts.append({
-            "type": "image_url",
-            "image_url": {"url": data_url},
-        })
-
-    # If the text was empty, add a neutral prompt so the turn isn't just images.
-    if not text and any(p.get("type") == "image_url" for p in parts):
-        parts.insert(0, {"type": "text", "text": "What do you see in this image?"})
-
-    return parts, skipped
-
-
-__all__ = [
-    "decide_image_input_mode",
-    "build_native_content_parts",
-]

agent/lmstudio_reasoning.py

@@ -1,48 +0,0 @@
-"""LM Studio reasoning-effort resolution shared by the chat-completions
-transport and run_agent's iteration-limit summary path.
-
-LM Studio publishes per-model ``capabilities.reasoning.allowed_options`` (e.g.
-``["off","on"]`` for toggle-style models, ``["off","minimal","low"]`` for
-graduated models). We map the user's ``reasoning_config`` onto LM Studio's
-OpenAI-compatible vocabulary, then clamp against the model's allowed set so
-the server doesn't 400 on an unsupported effort.
-"""
-
-from __future__ import annotations
-
-from typing import List, Optional
-
-# LM Studio accepts these top-level reasoning_effort values via its
-# OpenAI-compatible chat.completions endpoint.
-_LM_VALID_EFFORTS = {"none", "minimal", "low", "medium", "high", "xhigh"}
-
-# Toggle-style models publish allowed_options as ["off","on"] in /api/v1/models.
-# Map them onto the OpenAI-compatible request vocabulary.
-_LM_EFFORT_ALIASES = {"off": "none", "on": "medium"}
-
-
-def resolve_lmstudio_effort(
-    reasoning_config: Optional[dict],
-    allowed_options: Optional[List[str]],
-) -> Optional[str]:
-    """Return the ``reasoning_effort`` string to send to LM Studio, or ``None``.
-
-    ``None`` means "omit the field": the user picked a level the model can't
-    honor, so let LM Studio fall back to the model's declared default rather
-    than silently substituting a different effort. When ``allowed_options`` is
-    falsy (probe failed), skip clamping and send the resolved effort anyway.
-    """
-    effort = "medium"
-    if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is False:
-            effort = "none"
-        else:
-            raw = (reasoning_config.get("effort") or "").strip().lower()
-            raw = _LM_EFFORT_ALIASES.get(raw, raw)
-            if raw in _LM_VALID_EFFORTS:
-                effort = raw
-    if allowed_options:
-        allowed = {_LM_EFFORT_ALIASES.get(opt, opt) for opt in allowed_options}
-        if effort not in allowed:
-            return None
-    return effort

agent/manual_compression_feedback.py

@@ -20,25 +20,25 @@ def summarize_manual_compression(
         headline = f"No changes from compression: {before_count} messages"
         if after_tokens == before_tokens:
             token_line = (
-                f"Approx request size: ~{before_tokens:,} tokens (unchanged)"
+                f"Rough transcript estimate: ~{before_tokens:,} tokens (unchanged)"
             )
         else:
             token_line = (
-                f"Approx request size: ~{before_tokens:,} → "
+                f"Rough transcript estimate: ~{before_tokens:,} → "
                 f"~{after_tokens:,} tokens"
             )
     else:
         headline = f"Compressed: {before_count} → {after_count} messages"
         token_line = (
-            f"Approx request size: ~{before_tokens:,} → "
+            f"Rough transcript estimate: ~{before_tokens:,} → "
             f"~{after_tokens:,} tokens"
         )
 
     note = None
     if not noop and after_count < before_count and after_tokens > before_tokens:
         note = (
-            "Note: fewer messages can still raise this estimate when "
-            "compression rewrites the transcript into denser summaries."
+            "Note: fewer messages can still raise this rough transcript estimate "
+            "when compression rewrites the transcript into denser summaries."
         )
 
     return {

agent/memory_manager.py

@@ -28,6 +28,7 @@ Usage in run_agent.py:
 
 from __future__ import annotations
 
+import json
 import logging
 import re
 import inspect
@@ -62,124 +63,15 @@ def sanitize_context(text: str) -> str:
     return text
 
 
-class StreamingContextScrubber:
-    """Stateful scrubber for streaming text that may contain split memory-context spans.
-
-    The one-shot ``sanitize_context`` regex cannot survive chunk boundaries:
-    a ``<memory-context>`` opened in one delta and closed in a later delta
-    leaks its payload to the UI because the non-greedy block regex needs
-    both tags in one string.  This scrubber runs a small state machine
-    across deltas, holding back partial-tag tails and discarding
-    everything inside a span (including the system-note line).
-
-    Usage::
-
-        scrubber = StreamingContextScrubber()
-        for delta in stream:
-            visible = scrubber.feed(delta)
-            if visible:
-                emit(visible)
-        trailing = scrubber.flush()  # at end of stream
-        if trailing:
-            emit(trailing)
-
-    The scrubber is re-entrant per agent instance.  Callers building new
-    top-level responses (new turn) should create a fresh scrubber or call
-    ``reset()``.
-    """
-
-    _OPEN_TAG = "<memory-context>"
-    _CLOSE_TAG = "</memory-context>"
-
-    def __init__(self) -> None:
-        self._in_span: bool = False
-        self._buf: str = ""
-
-    def reset(self) -> None:
-        self._in_span = False
-        self._buf = ""
-
-    def feed(self, text: str) -> str:
-        """Return the visible portion of ``text`` after scrubbing.
-
-        Any trailing fragment that could be the start of an open/close tag
-        is held back in the internal buffer and surfaced on the next
-        ``feed()`` call or discarded/emitted by ``flush()``.
-        """
-        if not text:
-            return ""
-        buf = self._buf + text
-        self._buf = ""
-        out: list[str] = []
-
-        while buf:
-            if self._in_span:
-                idx = buf.lower().find(self._CLOSE_TAG)
-                if idx == -1:
-                    # Hold back a potential partial close tag; drop the rest
-                    held = self._max_partial_suffix(buf, self._CLOSE_TAG)
-                    self._buf = buf[-held:] if held else ""
-                    return "".join(out)
-                # Found close — skip span content + tag, continue
-                buf = buf[idx + len(self._CLOSE_TAG):]
-                self._in_span = False
-            else:
-                idx = buf.lower().find(self._OPEN_TAG)
-                if idx == -1:
-                    # No open tag — hold back a potential partial open tag
-                    held = self._max_partial_suffix(buf, self._OPEN_TAG)
-                    if held:
-                        out.append(buf[:-held])
-                        self._buf = buf[-held:]
-                    else:
-                        out.append(buf)
-                    return "".join(out)
-                # Emit text before the tag, enter span
-                if idx > 0:
-                    out.append(buf[:idx])
-                buf = buf[idx + len(self._OPEN_TAG):]
-                self._in_span = True
-
-        return "".join(out)
-
-    def flush(self) -> str:
-        """Emit any held-back buffer at end-of-stream.
-
-        If we're still inside an unterminated span the remaining content is
-        discarded (safer: leaking partial memory context is worse than a
-        truncated answer).  Otherwise the held-back partial-tag tail is
-        emitted verbatim (it turned out not to be a real tag).
-        """
-        if self._in_span:
-            self._buf = ""
-            self._in_span = False
-            return ""
-        tail = self._buf
-        self._buf = ""
-        return tail
-
-    @staticmethod
-    def _max_partial_suffix(buf: str, tag: str) -> int:
-        """Return the length of the longest buf-suffix that is a tag-prefix.
-
-        Case-insensitive.  Returns 0 if no suffix could start the tag.
-        """
-        tag_lower = tag.lower()
-        buf_lower = buf.lower()
-        max_check = min(len(buf_lower), len(tag_lower) - 1)
-        for i in range(max_check, 0, -1):
-            if tag_lower.startswith(buf_lower[-i:]):
-                return i
-        return 0
-
-
 def build_memory_context_block(raw_context: str) -> str:
-    """Wrap prefetched memory in a fenced block with system note."""
+    """Wrap prefetched memory in a fenced block with system note.
+
+    The fence prevents the model from treating recalled context as user
+    discourse.  Injected at API-call time only — never persisted.
+    """
     if not raw_context or not raw_context.strip():
         return ""
     clean = sanitize_context(raw_context)
-    if clean != raw_context:
-        logger.warning("memory provider returned pre-wrapped context; stripped")
     return (
         "<memory-context>\n"
         "[System note: The following is recalled memory context, "
@@ -402,41 +294,6 @@ class MemoryManager:
                     provider.name, e,
                 )
 
-    def on_session_switch(
-        self,
-        new_session_id: str,
-        *,
-        parent_session_id: str = "",
-        reset: bool = False,
-        **kwargs,
-    ) -> None:
-        """Notify all providers that the agent's session_id has rotated.
-
-        Fires on ``/resume``, ``/branch``, ``/reset``, ``/new``, and
-        context compression — any path that reassigns
-        ``AIAgent.session_id`` without tearing the provider down.
-
-        Providers keep running; they only need to refresh cached
-        per-session state so subsequent writes land in the correct
-        session's record. See ``MemoryProvider.on_session_switch`` for
-        the full contract.
-        """
-        if not new_session_id:
-            return
-        for provider in self._providers:
-            try:
-                provider.on_session_switch(
-                    new_session_id,
-                    parent_session_id=parent_session_id,
-                    reset=reset,
-                    **kwargs,
-                )
-            except Exception as e:
-                logger.debug(
-                    "Memory provider '%s' on_session_switch failed: %s",
-                    provider.name, e,
-                )
-
     def on_pre_compress(self, messages: List[Dict[str, Any]]) -> str:
         """Notify all providers before context compression.
 

agent/memory_provider.py

@@ -25,7 +25,6 @@ Lifecycle (called by MemoryManager, wired in run_agent.py):
 Optional hooks (override to opt in):
   on_turn_start(turn, message, **kwargs) — per-turn tick with runtime context
   on_session_end(messages)               — end-of-session extraction
-  on_session_switch(new_session_id, **kwargs) — mid-process session_id rotation
   on_pre_compress(messages) -> str       — extract before context compression
   on_memory_write(action, target, content, metadata=None) — mirror built-in memory writes
   on_delegation(task, result, **kwargs)  — parent-side observation of subagent work
@@ -161,45 +160,6 @@ class MemoryProvider(ABC):
         (CLI exit, /reset, gateway session expiry).
         """
 
-    def on_session_switch(
-        self,
-        new_session_id: str,
-        *,
-        parent_session_id: str = "",
-        reset: bool = False,
-        **kwargs,
-    ) -> None:
-        """Called when the agent switches session_id mid-process.
-
-        Fires on ``/resume``, ``/branch``, ``/reset``, ``/new`` (CLI), the
-        gateway equivalents, and context compression — any path that
-        reassigns ``AIAgent.session_id`` without tearing the provider down.
-
-        Providers that cache per-session state in ``initialize()``
-        (``_session_id``, ``_document_id``, accumulated turn buffers,
-        counters) should update or reset that state here so subsequent
-        writes land in the correct session's record.
-
-        Parameters
-        ----------
-        new_session_id:
-            The session_id the agent just switched to.
-        parent_session_id:
-            The previous session_id, if meaningful — set for ``/branch``
-            (fork lineage), context compression (continuation lineage),
-            and ``/resume`` (the session we're leaving). Empty string
-            when no lineage applies.
-        reset:
-            ``True`` when this is a genuinely new conversation, not a
-            resumption of an existing one. Fired by ``/reset`` / ``/new``.
-            Providers should flush accumulated per-session buffers
-            (``_session_turns``, ``_turn_counter``, etc.) when this is
-            set. ``False`` for ``/resume`` / ``/branch`` / compression
-            where the logical conversation continues under the new id.
-
-        Default is no-op for backward compatibility.
-        """
-
     def on_pre_compress(self, messages: List[Dict[str, Any]]) -> str:
         """Called before context compression discards old messages.
 

agent/model_metadata.py

@@ -46,13 +46,11 @@ def _resolve_requests_verify() -> bool | str:
 # are preserved so the full model name reaches cache lookups and server queries.
 _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
-    "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "stepfun", "minimax", "minimax-oauth", "minimax-cn", "anthropic", "deepseek",
+    "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "stepfun", "minimax", "minimax-cn", "anthropic", "deepseek",
     "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
     "qwen-oauth",
     "xiaomi",
     "arcee",
-    "gmi",
-    "tencent-tokenhub",
     "custom", "local",
     # Common aliases
     "google", "google-gemini", "google-ai-studio",
@@ -61,9 +59,7 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "ollama",
     "stepfun", "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
     "mimo", "xiaomi-mimo",
-    "tencent", "tokenhub", "tencent-cloud", "tencentmaas",
     "arcee-ai", "arceeai",
-    "gmi-cloud", "gmicloud",
     "xai", "x-ai", "x.ai", "grok",
     "nvidia", "nim", "nvidia-nim", "nemotron",
     "qwen-portal",
@@ -110,11 +106,9 @@ _endpoint_model_metadata_cache_time: Dict[str, float] = {}
 _ENDPOINT_MODEL_CACHE_TTL = 300
 
 # Descending tiers for context length probing when the model is unknown.
-# We start at 256K (covers GPT-5.x, many current large-context models) and
-# step down on context-length errors until one works.  Tier[0] is also the
-# default fallback when no detection method succeeds.
+# We start at 128K (a safe default for most modern models) and step down
+# on context-length errors until one works.
 CONTEXT_PROBE_TIERS = [
-    256_000,
     128_000,
     64_000,
     32_000,
@@ -149,11 +143,10 @@ DEFAULT_CONTEXT_LENGTHS = {
     "claude": 200000,
     # OpenAI — GPT-5 family (most have 400k; specific overrides first)
     # Source: https://developers.openai.com/api/docs/models
-    # GPT-5.5 (launched Apr 23 2026) is 1.05M on the direct OpenAI API and
-    # ChatGPT Codex OAuth caps it at 272K; both paths resolve via their own
-    # provider-aware branches (_resolve_codex_oauth_context_length + models.dev).
-    # This hardcoded value is only reached when every probe misses.
-    "gpt-5.5": 1050000,
+    # GPT-5.5 (launched Apr 23 2026). 400k is the fallback for providers we
+    # can't probe live. ChatGPT Codex OAuth actually caps lower (272k as of
+    # Apr 2026) and is resolved via _resolve_codex_oauth_context_length().
+    "gpt-5.5": 400000,
     "gpt-5.4-nano": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4-mini": 400000,           # 400k (not 1.05M like full 5.4)
     "gpt-5.4": 1050000,               # GPT-5.4, GPT-5.4 Pro (1.05M context)
@@ -169,17 +162,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "gemma-4-31b": 256000,
     "gemma-3": 131072,
     "gemma": 8192,  # fallback for older gemma models
-    # DeepSeek — V4 family ships with a 1M context window. The legacy
-    # aliases ``deepseek-chat`` / ``deepseek-reasoner`` are server-side
-    # mapped to the non-thinking / thinking modes of ``deepseek-v4-flash``
-    # and inherit the same 1M window. The ``deepseek`` substring entry
-    # below remains as a 128K fallback for older / unknown DeepSeek model
-    # ids (e.g. via custom endpoints).
-    # https://api-docs.deepseek.com/zh-cn/quick_start/pricing
-    "deepseek-v4-pro": 1_000_000,
-    "deepseek-v4-flash": 1_000_000,
-    "deepseek-chat": 1_000_000,
-    "deepseek-reasoner": 1_000_000,
+    # DeepSeek
     "deepseek": 128000,
     # Meta
     "llama": 131072,
@@ -210,8 +193,6 @@ DEFAULT_CONTEXT_LENGTHS = {
     "grok": 131072,             # catch-all (grok-beta, unknown grok-*)
     # Kimi
     "kimi": 262144,
-    # Tencent — Hy3 Preview (Hunyuan) with 256K context window
-    "hy3-preview": 256000,
     # Nemotron — NVIDIA's open-weights series (128K context across all sizes)
     "nemotron": 131072,
     # Arcee
@@ -313,8 +294,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "integrate.api.nvidia.com": "nvidia",
     "api.xiaomimimo.com": "xiaomi",
     "xiaomimimo.com": "xiaomi",
-    "api.gmi-serving.com": "gmi",
-    "tokenhub.tencentmaas.com": "tencent-tokenhub",
     "ollama.com": "ollama-cloud",
 }
 
@@ -625,6 +604,8 @@ def fetch_endpoint_model_metadata(
                         if isinstance(ctx, int) and ctx > 0:
                             context_length = ctx
                             break
+                    if context_length is None:
+                        context_length = _extract_context_length(model)
                     if context_length is not None:
                         entry["context_length"] = context_length
 
@@ -708,29 +689,6 @@ def fetch_endpoint_model_metadata(
     return {}
 
 
-def _resolve_endpoint_context_length(
-    model: str,
-    base_url: str,
-    api_key: str = "",
-) -> Optional[int]:
-    """Resolve context length from an endpoint's live ``/models`` metadata."""
-    endpoint_metadata = fetch_endpoint_model_metadata(base_url, api_key=api_key)
-    matched = endpoint_metadata.get(model)
-    if not matched:
-        if len(endpoint_metadata) == 1:
-            matched = next(iter(endpoint_metadata.values()))
-        else:
-            for key, entry in endpoint_metadata.items():
-                if model in key or key in model:
-                    matched = entry
-                    break
-    if matched:
-        context_length = matched.get("context_length")
-        if isinstance(context_length, int):
-            return context_length
-    return None
-
-
 def _get_context_cache_path() -> Path:
     """Return path to the persistent context length cache file."""
     from hermes_constants import get_hermes_home
@@ -1014,7 +972,10 @@ def _query_local_context_length(model: str, base_url: str, api_key: str = "") ->
                                 ctx = cfg.get("context_length")
                                 if ctx and isinstance(ctx, (int, float)):
                                     return int(ctx)
-                            break
+                            # Fall back to max_context_length (theoretical model max)
+                            ctx = m.get("max_context_length") or m.get("context_length")
+                            if ctx and isinstance(ctx, (int, float)):
+                                return int(ctx)
 
             # LM Studio / vLLM / llama.cpp: try /v1/models/{model}
             resp = client.get(f"{server_url}/v1/models/{model}")
@@ -1232,7 +1193,6 @@ def get_model_context_length(
     api_key: str = "",
     config_context_length: int | None = None,
     provider: str = "",
-    custom_providers: list | None = None,
 ) -> int:
     """Get the context length for a model.
 
@@ -1247,39 +1207,19 @@ def get_model_context_length(
     6. Nous suffix-match via OpenRouter cache
     7. models.dev registry lookup (provider-aware)
     8. Thin hardcoded defaults (broad family patterns)
-    9. Default fallback (256K)
+    9. Default fallback (128K)
     """
     # 0. Explicit config override — user knows best
     if config_context_length is not None and isinstance(config_context_length, int) and config_context_length > 0:
         return config_context_length
 
-    # 0b. custom_providers per-model override — check before any probe.
-    # This closes the gap where /model switch and display paths used to fall
-    # back to 128K despite the user having a per-model context_length set.
-    # See #15779.
-    if custom_providers and base_url and model:
-        try:
-            from hermes_cli.config import get_custom_provider_context_length
-            cp_ctx = get_custom_provider_context_length(
-                model=model,
-                base_url=base_url,
-                custom_providers=custom_providers,
-            )
-            if cp_ctx:
-                return cp_ctx
-        except Exception:
-            pass  # fall through to probing
-
     # Normalise provider-prefixed model names (e.g. "local:model-name" →
     # "model-name") so cache lookups and server queries use the bare ID that
     # local servers actually know about.  Ollama "model:tag" colons are preserved.
     model = _strip_provider_prefix(model)
 
     # 1. Check persistent cache (model+provider)
-    # LM Studio is excluded — its loaded context length is transient (the
-    # user can reload the model with a different context_length at any time
-    # via /api/v1/models/load), so a stale cached value would mask reloads.
-    if base_url and provider != "lmstudio":
+    if base_url:
         cached = get_cached_context_length(model, base_url)
         if cached is not None:
             # Invalidate stale Codex OAuth cache entries: pre-PR #14935 builds
@@ -1324,16 +1264,28 @@ def get_model_context_length(
     # returns 128k) instead of the model's full context (400k).  models.dev
     # has the correct per-provider values and is checked at step 5+.
     if _is_custom_endpoint(base_url) and not _is_known_provider_base_url(base_url):
-        context_length = _resolve_endpoint_context_length(model, base_url, api_key=api_key)
-        if context_length is not None:
-            return context_length
+        endpoint_metadata = fetch_endpoint_model_metadata(base_url, api_key=api_key)
+        matched = endpoint_metadata.get(model)
+        if not matched:
+            # Single-model servers: if only one model is loaded, use it
+            if len(endpoint_metadata) == 1:
+                matched = next(iter(endpoint_metadata.values()))
+            else:
+                # Fuzzy match: substring in either direction
+                for key, entry in endpoint_metadata.items():
+                    if model in key or key in model:
+                        matched = entry
+                        break
+        if matched:
+            context_length = matched.get("context_length")
+            if isinstance(context_length, int):
+                return context_length
         if not _is_known_provider_base_url(base_url):
             # 3. Try querying local server directly
             if is_local_endpoint(base_url):
                 local_ctx = _query_local_context_length(model, base_url, api_key=api_key)
                 if local_ctx and local_ctx > 0:
-                    if provider != "lmstudio":
-                        save_context_length(model, base_url, local_ctx)
+                    save_context_length(model, base_url, local_ctx)
                     return local_ctx
             logger.info(
                 "Could not detect context length for model %r at %s — "
@@ -1391,12 +1343,6 @@ def get_model_context_length(
             if base_url:
                 save_context_length(model, base_url, codex_ctx)
             return codex_ctx
-    if effective_provider == "gmi" and base_url:
-        # GMI exposes authoritative context_length via /models, but it is not
-        # in models.dev yet. Preserve that higher-fidelity endpoint lookup.
-        ctx = _resolve_endpoint_context_length(model, base_url, api_key=api_key)
-        if ctx is not None:
-            return ctx
     if effective_provider:
         from agent.models_dev import lookup_models_dev_context
         ctx = lookup_models_dev_context(effective_provider, model)
@@ -1406,7 +1352,7 @@ def get_model_context_length(
     # 6. OpenRouter live API metadata (provider-unaware fallback)
     metadata = fetch_model_metadata()
     if model in metadata:
-        return metadata[model].get("context_length", DEFAULT_FALLBACK_CONTEXT)
+        return metadata[model].get("context_length", 128000)
 
     # 8. Hardcoded defaults (fuzzy match — longest key first for specificity)
     # Only check `default_model in model` (is the key a substring of the input).
@@ -1423,11 +1369,10 @@ def get_model_context_length(
     if base_url and is_local_endpoint(base_url):
         local_ctx = _query_local_context_length(model, base_url, api_key=api_key)
         if local_ctx and local_ctx > 0:
-            if provider != "lmstudio":
-                save_context_length(model, base_url, local_ctx)
+            save_context_length(model, base_url, local_ctx)
             return local_ctx
 
-    # 10. Default fallback — 256K
+    # 10. Default fallback — 128K
     return DEFAULT_FALLBACK_CONTEXT
 
 

agent/models_dev.py

@@ -149,7 +149,6 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "stepfun": "stepfun",
     "kimi-coding-cn": "kimi-for-coding",
     "minimax": "minimax",
-    "minimax-oauth": "minimax",
     "minimax-cn": "minimax-cn",
     "deepseek": "deepseek",
     "alibaba": "alibaba",

agent/moonshot_schema.py

@@ -81,56 +81,15 @@ def _repair_schema(node: Any, is_schema: bool = True) -> Any:
         return repaired
 
     # Rule 2: when anyOf is present, type belongs only on the children.
-    # Additionally, Moonshot rejects null-type branches inside anyOf
-    # (enum value (<nil>) does not match any type in [string]).
-    # Collapse the anyOf to the first non-null branch and infer its type.
     if "anyOf" in repaired and isinstance(repaired["anyOf"], list):
         repaired.pop("type", None)
-        non_null = [b for b in repaired["anyOf"]
-                    if isinstance(b, dict) and b.get("type") != "null"]
-        if non_null and len(non_null) < len(repaired["anyOf"]):
-            # Drop the anyOf wrapper — keep only the non-null branch.
-            # If there's a single non-null branch, promote it and fall
-            # through to Rules 1/3 so nullable/enum cleanup still applies
-            # to the merged node.
-            if len(non_null) == 1:
-                merge = {k: v for k, v in repaired.items() if k != "anyOf"}
-                merge.update(non_null[0])
-                repaired = merge
-            else:
-                repaired["anyOf"] = non_null
-                return repaired
-        else:
-            # Nothing to collapse — parent type stripped, children already
-            # repaired by the recursive walk above.
-            return repaired
-
-    # Moonshot also rejects non-standard keywords like ``nullable`` on
-    # parameter schemas — strip it.
-    repaired.pop("nullable", None)
+        return repaired
 
     # Rule 1: property schemas without type need one.  $ref nodes are exempt
     # — their type comes from the referenced definition.
-    # Fill missing type BEFORE Rule 3 so enum cleanup can check the type.
-    if "$ref" not in repaired:
-        repaired = _fill_missing_type(repaired)
-
-    # Rule 3: Moonshot rejects null/empty-string values inside enum arrays
-    # when the parent type is a scalar (string, integer, etc.).  The error:
-    #   "enum value (<nil>) does not match any type in [string]"
-    # Strip null and empty-string from enum values, and if the enum becomes
-    # empty, drop it entirely.
-    if "enum" in repaired and isinstance(repaired["enum"], list):
-        node_type = repaired.get("type")
-        if node_type in ("string", "integer", "number", "boolean"):
-            cleaned = [v for v in repaired["enum"]
-                       if v is not None and v != ""]
-            if cleaned:
-                repaired["enum"] = cleaned
-            else:
-                repaired.pop("enum")
-
-    return repaired
+    if "$ref" in repaired:
+        return repaired
+    return _fill_missing_type(repaired)
 
 
 def _fill_missing_type(node: Dict[str, Any]) -> Dict[str, Any]:

agent/nous_rate_guard.py

@@ -18,7 +18,6 @@ import os
 import tempfile
 import time
 from typing import Any, Mapping, Optional
-from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -119,7 +118,7 @@ def record_nous_rate_limit(
         try:
             with os.fdopen(fd, "w") as f:
                 json.dump(state, f)
-            atomic_replace(tmp_path, path)
+            os.replace(tmp_path, path)
         except Exception:
             # Clean up temp file on failure
             try:
@@ -181,145 +180,3 @@ def format_remaining(seconds: float) -> str:
     h, remainder = divmod(s, 3600)
     m = remainder // 60
     return f"{h}h {m}m" if m else f"{h}h"
-
-
-# Buckets with reset windows shorter than this are treated as transient
-# (upstream jitter, secondary throttling) rather than a genuine quota
-# exhaustion worth a cross-session breaker trip.
-_MIN_RESET_FOR_BREAKER_SECONDS = 60.0
-
-
-def is_genuine_nous_rate_limit(
-    *,
-    headers: Optional[Mapping[str, str]] = None,
-    last_known_state: Optional[Any] = None,
-) -> bool:
-    """Decide whether a 429 from Nous Portal is a real account rate limit.
-
-    Nous Portal multiplexes multiple upstream providers (DeepSeek, Kimi,
-    MiMo, Hermes, ...) behind one endpoint.  A 429 can mean either:
-
-      (a) The caller's own RPM / RPH / TPM / TPH bucket on Nous is
-          exhausted — a genuine rate limit that will last until the
-          bucket resets.
-      (b) The upstream provider is out of capacity for a specific model
-          — transient, clears in seconds, and has nothing to do with
-          the caller's quota on Nous.
-
-    Tripping the cross-session breaker on (b) blocks ALL Nous requests
-    (and all models, since Nous is one provider key) for minutes even
-    though the caller's account is healthy and a different model would
-    have worked.  That's the bug users hit when DeepSeek V4 Pro 429s
-    trigger a breaker that then blocks Kimi 2.6 and MiMo V2.5 Pro.
-
-    We tell the two apart by looking at:
-
-      1. The 429 response's own ``x-ratelimit-*`` headers.  Nous emits
-         the full suite on every response including 429s.  An exhausted
-         bucket (``remaining == 0`` with a reset window >= 60s) is
-         proof of (a).
-      2. The last-known-good rate-limit state captured by
-         ``_capture_rate_limits()`` on the previous successful
-         response.  If any bucket there was already near-exhausted with
-         a substantial reset window, the current 429 is almost
-         certainly (a) continuing from that condition.
-
-    If neither signal fires, we treat the 429 as (b): fail the single
-    request, let the retry loop or model-switch proceed, and do NOT
-    write the cross-session breaker file.
-
-    Returns True when the evidence points at (a).
-    """
-    # Signal 1: current 429 response headers.
-    state = _parse_buckets_from_headers(headers)
-    if _has_exhausted_bucket(state):
-        return True
-
-    # Signal 2: last-known-good state from a recent successful response.
-    # Accepts either a RateLimitState (dataclass from rate_limit_tracker)
-    # or a dict of bucket snapshots.
-    if last_known_state is not None and _has_exhausted_bucket_in_object(last_known_state):
-        return True
-
-    return False
-
-
-def _parse_buckets_from_headers(
-    headers: Optional[Mapping[str, str]],
-) -> dict[str, tuple[Optional[int], Optional[float]]]:
-    """Extract (remaining, reset_seconds) per bucket from x-ratelimit-* headers.
-
-    Returns empty dict when no rate-limit headers are present.
-    """
-    if not headers:
-        return {}
-
-    lowered = {k.lower(): v for k, v in headers.items()}
-    if not any(k.startswith("x-ratelimit-") for k in lowered):
-        return {}
-
-    def _maybe_int(raw: Optional[str]) -> Optional[int]:
-        if raw is None:
-            return None
-        try:
-            return int(float(raw))
-        except (TypeError, ValueError):
-            return None
-
-    def _maybe_float(raw: Optional[str]) -> Optional[float]:
-        if raw is None:
-            return None
-        try:
-            return float(raw)
-        except (TypeError, ValueError):
-            return None
-
-    result: dict[str, tuple[Optional[int], Optional[float]]] = {}
-    for tag in ("requests", "requests-1h", "tokens", "tokens-1h"):
-        remaining = _maybe_int(lowered.get(f"x-ratelimit-remaining-{tag}"))
-        reset = _maybe_float(lowered.get(f"x-ratelimit-reset-{tag}"))
-        if remaining is not None or reset is not None:
-            result[tag] = (remaining, reset)
-    return result
-
-
-def _has_exhausted_bucket(
-    buckets: Mapping[str, tuple[Optional[int], Optional[float]]],
-) -> bool:
-    """Return True when any bucket has remaining == 0 AND a meaningful reset window."""
-    for remaining, reset in buckets.values():
-        if remaining is None or remaining > 0:
-            continue
-        if reset is None:
-            continue
-        if reset >= _MIN_RESET_FOR_BREAKER_SECONDS:
-            return True
-    return False
-
-
-def _has_exhausted_bucket_in_object(state: Any) -> bool:
-    """Check a RateLimitState-like object for an exhausted bucket.
-
-    Accepts the dataclass from ``agent.rate_limit_tracker`` (buckets
-    exposed as attributes ``requests_min``, ``requests_hour``,
-    ``tokens_min``, ``tokens_hour``) and falls back gracefully for any
-    object missing those attributes.
-    """
-    for attr in ("requests_min", "requests_hour", "tokens_min", "tokens_hour"):
-        bucket = getattr(state, attr, None)
-        if bucket is None:
-            continue
-        limit = getattr(bucket, "limit", 0) or 0
-        remaining = getattr(bucket, "remaining", 0) or 0
-        # Prefer the adjusted "remaining_seconds_now" property when present;
-        # fall back to raw reset_seconds.
-        reset = getattr(bucket, "remaining_seconds_now", None)
-        if reset is None:
-            reset = getattr(bucket, "reset_seconds", 0.0) or 0.0
-        if limit <= 0:
-            continue
-        if remaining > 0:
-            continue
-        if reset >= _MIN_RESET_FOR_BREAKER_SECONDS:
-            return True
-    return False

agent/onboarding.py

@@ -1,193 +0,0 @@
-"""
-Contextual first-touch onboarding hints.
-
-Instead of blocking first-run questionnaires, show a one-time hint the *first*
-time a user hits a behavior fork — message-while-running, first long-running
-tool, etc.  Each hint is shown once per install (tracked in ``config.yaml`` under
-``onboarding.seen.<flag>``) and then never again.
-
-Keep this module tiny and dependency-free so both the CLI and gateway can import
-it without pulling in heavy modules.
-"""
-
-from __future__ import annotations
-
-import logging
-from pathlib import Path
-from typing import Any, Mapping, Optional
-
-logger = logging.getLogger(__name__)
-
-
-# -------------------------------------------------------------------------
-# Flag names (stable — used as config.yaml keys under onboarding.seen)
-# -------------------------------------------------------------------------
-
-BUSY_INPUT_FLAG = "busy_input_prompt"
-TOOL_PROGRESS_FLAG = "tool_progress_prompt"
-OPENCLAW_RESIDUE_FLAG = "openclaw_residue_cleanup"
-
-
-# -------------------------------------------------------------------------
-# Hint content
-# -------------------------------------------------------------------------
-
-def busy_input_hint_gateway(mode: str) -> str:
-    """Hint shown the first time a user messages while the agent is busy.
-
-    ``mode`` is the effective busy_input_mode that was just applied, so the
-    message matches reality ("I just interrupted…" vs "I just queued…").
-    """
-    if mode == "queue":
-        return (
-            "💡 First-time tip — I queued your message instead of interrupting. "
-            "Send `/busy interrupt` to make new messages stop the current task "
-            "immediately, or `/busy status` to check. This notice won't appear again."
-        )
-    if mode == "steer":
-        return (
-            "💡 First-time tip — I steered your message into the current run; "
-            "it will arrive after the next tool call instead of interrupting. "
-            "Send `/busy interrupt` or `/busy queue` to change this, or "
-            "`/busy status` to check. This notice won't appear again."
-        )
-    return (
-        "💡 First-time tip — I just interrupted my current task to answer you. "
-        "Send `/busy queue` to queue follow-ups for after the current task instead, "
-        "`/busy steer` to inject them mid-run without interrupting, or "
-        "`/busy status` to check. This notice won't appear again."
-    )
-
-
-def busy_input_hint_cli(mode: str) -> str:
-    """CLI version of the busy-input hint (plain text, no markdown)."""
-    if mode == "queue":
-        return (
-            "(tip) Your message was queued for the next turn. "
-            "Use /busy interrupt to make Enter stop the current run instead, "
-            "or /busy steer to inject mid-run. This tip only shows once."
-        )
-    if mode == "steer":
-        return (
-            "(tip) Your message was steered into the current run; it arrives "
-            "after the next tool call. Use /busy interrupt or /busy queue to "
-            "change this. This tip only shows once."
-        )
-    return (
-        "(tip) Your message interrupted the current run. "
-        "Use /busy queue to queue messages for the next turn instead, "
-        "or /busy steer to inject mid-run. This tip only shows once."
-    )
-
-
-def tool_progress_hint_gateway() -> str:
-    return (
-        "💡 First-time tip — that tool took a while and I'm streaming every step. "
-        "If the progress messages feel noisy, send `/verbose` to cycle modes "
-        "(all → new → off). This notice won't appear again."
-    )
-
-
-def tool_progress_hint_cli() -> str:
-    return (
-        "(tip) That tool ran for a while. Use /verbose to cycle tool-progress "
-        "display modes (all -> new -> off -> verbose). This tip only shows once."
-    )
-
-
-def openclaw_residue_hint_cli() -> str:
-    """Banner shown the first time Hermes starts and finds ``~/.openclaw/``.
-
-    Points users at ``hermes claw migrate`` (non-destructive port of config,
-    memory, and skills) first. ``hermes claw cleanup`` is mentioned as the
-    follow-up step for users who have already migrated and want to archive
-    the old directory — with a warning that archiving breaks OpenClaw.
-    """
-    return (
-        "A legacy OpenClaw directory was detected at ~/.openclaw/.\n"
-        "To port your config, memory, and skills over to Hermes, run "
-        "`hermes claw migrate`.\n"
-        "If you've already migrated and want to archive the old directory, "
-        "run `hermes claw cleanup` (renames it to ~/.openclaw.pre-migration — "
-        "OpenClaw will stop working after this).\n"
-        "This tip only shows once."
-    )
-
-
-def detect_openclaw_residue(home: Optional[Path] = None) -> bool:
-    """Return True if an OpenClaw workspace directory is present in ``$HOME``.
-
-    Pure filesystem check — no side effects. ``home`` override exists for tests.
-    """
-    base = home or Path.home()
-    try:
-        return (base / ".openclaw").is_dir()
-    except OSError:
-        return False
-
-
-# -------------------------------------------------------------------------
-# State read / write
-# -------------------------------------------------------------------------
-
-def _get_seen_dict(config: Mapping[str, Any]) -> Mapping[str, Any]:
-    onboarding = config.get("onboarding") if isinstance(config, Mapping) else None
-    if not isinstance(onboarding, Mapping):
-        return {}
-    seen = onboarding.get("seen")
-    return seen if isinstance(seen, Mapping) else {}
-
-
-def is_seen(config: Mapping[str, Any], flag: str) -> bool:
-    """Return True if the user has already been shown this first-touch hint."""
-    return bool(_get_seen_dict(config).get(flag))
-
-
-def mark_seen(config_path: Path, flag: str) -> bool:
-    """Persist ``onboarding.seen.<flag> = True`` to ``config_path``.
-
-    Uses the atomic YAML writer so a concurrent process can't observe a
-    partially-written file.  Returns True on success, False on any error
-    (including the config file being absent — onboarding is best-effort).
-    """
-    try:
-        import yaml
-        from utils import atomic_yaml_write
-    except Exception as e:  # pragma: no cover — dependency issue
-        logger.debug("onboarding: failed to import yaml/utils: %s", e)
-        return False
-
-    try:
-        cfg: dict = {}
-        if config_path.exists():
-            with open(config_path, encoding="utf-8") as f:
-                cfg = yaml.safe_load(f) or {}
-        if not isinstance(cfg.get("onboarding"), dict):
-            cfg["onboarding"] = {}
-        seen = cfg["onboarding"].get("seen")
-        if not isinstance(seen, dict):
-            seen = {}
-            cfg["onboarding"]["seen"] = seen
-        if seen.get(flag) is True:
-            return True  # already marked — nothing to do
-        seen[flag] = True
-        atomic_yaml_write(config_path, cfg)
-        return True
-    except Exception as e:
-        logger.debug("onboarding: failed to mark flag %s: %s", flag, e)
-        return False
-
-
-__all__ = [
-    "BUSY_INPUT_FLAG",
-    "TOOL_PROGRESS_FLAG",
-    "OPENCLAW_RESIDUE_FLAG",
-    "busy_input_hint_gateway",
-    "busy_input_hint_cli",
-    "tool_progress_hint_gateway",
-    "tool_progress_hint_cli",
-    "openclaw_residue_hint_cli",
-    "detect_openclaw_residue",
-    "is_seen",
-    "mark_seen",
-]

agent/prompt_builder.py

@@ -141,12 +141,6 @@ DEFAULT_AGENT_IDENTITY = (
     "Be targeted and efficient in your exploration and investigations."
 )
 
-HERMES_AGENT_HELP_GUIDANCE = (
-    "If the user asks about configuring, setting up, or using Hermes Agent "
-    "itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') "
-    "before answering. Docs: https://hermes-agent.nousresearch.com/docs"
-)
-
 MEMORY_GUIDANCE = (
     "You have persistent memory across sessions. Save durable facts using the memory "
     "tool: user preferences, environment details, tool quirks, and stable conventions. "
@@ -182,64 +176,6 @@ SKILLS_GUIDANCE = (
     "Skills that aren't maintained become liabilities."
 )
 
-KANBAN_GUIDANCE = (
-    "# You are a Kanban worker\n"
-    "You were spawned by the Hermes Kanban dispatcher to execute ONE task from "
-    "the shared board at `~/.hermes/kanban.db`. Your task id is in "
-    "`$HERMES_KANBAN_TASK`; your workspace is `$HERMES_KANBAN_WORKSPACE`. "
-    "The `kanban_*` tools in your schema are your primary coordination surface — "
-    "they write directly to the shared SQLite DB and work regardless of terminal "
-    "backend (local/docker/modal/ssh).\n"
-    "\n"
-    "## Lifecycle\n"
-    "\n"
-    "1. **Orient.** Call `kanban_show()` first (no args — it defaults to your "
-    "task). The response includes title, body, parent-task handoffs (summary + "
-    "metadata), any prior attempts on this task if you're a retry, the full "
-    "comment thread, and a pre-formatted `worker_context` you can treat as "
-    "ground truth.\n"
-    "2. **Work inside the workspace.** `cd $HERMES_KANBAN_WORKSPACE` before "
-    "any file operations. The workspace is yours for this run. Don't modify "
-    "files outside it unless the task explicitly asks.\n"
-    "3. **Heartbeat on long operations.** Call `kanban_heartbeat(note=...)` "
-    "every few minutes during long subprocesses (training, encoding, crawling). "
-    "Skip heartbeats for short tasks.\n"
-    "4. **Block on genuine ambiguity.** If you need a human decision you cannot "
-    "infer (missing credentials, UX choice, paywalled source, peer output you "
-    "need first), call `kanban_block(reason=\"...\")` and stop. Don't guess. "
-    "The user will unblock with context and the dispatcher will respawn you.\n"
-    "5. **Complete with structured handoff.** Call `kanban_complete(summary=..., "
-    "metadata=...)`. `summary` is 1–3 human-readable sentences naming concrete "
-    "artifacts. `metadata` is machine-readable facts "
-    "(`{changed_files: [...], tests_run: N, decisions: [...]}`). Downstream "
-    "workers read both via their own `kanban_show`. Never put secrets / "
-    "tokens / raw PII in either field — run rows are durable forever.\n"
-    "6. **If follow-up work appears, create it; don't do it.** Use "
-    "`kanban_create(title=..., assignee=<right-profile>, parents=[your-task-id])` "
-    "to spawn a child task for the appropriate specialist profile instead of "
-    "scope-creeping into the next thing.\n"
-    "\n"
-    "## Orchestrator mode\n"
-    "\n"
-    "If your task is itself a decomposition task (e.g. a planner profile given "
-    "a high-level goal), use `kanban_create` to fan out into child tasks — one "
-    "per specialist, each with an explicit `assignee` and `parents=[...]` to "
-    "express dependencies. Then `kanban_complete` your own task with a summary "
-    "of the decomposition. Do NOT execute the work yourself; your job is "
-    "routing, not implementation.\n"
-    "\n"
-    "## Do NOT\n"
-    "\n"
-    "- Do not shell out to `hermes kanban <verb>` for board operations. Use "
-    "the `kanban_*` tools — they work across all terminal backends.\n"
-    "- Do not complete a task you didn't actually finish. Block it.\n"
-    "- Do not assign follow-up work to yourself. Assign it to the right "
-    "specialist profile.\n"
-    "- Do not call `delegate_task` as a board substitute. `delegate_task` is "
-    "for short reasoning subtasks inside your own run; board tasks are for "
-    "cross-agent handoffs that outlive one API loop."
-)
-
 TOOL_USE_ENFORCEMENT_GUIDANCE = (
     "# Tool-use enforcement\n"
     "You MUST use your tools to take action — do not describe what you would do "
@@ -368,10 +304,6 @@ PLATFORM_HINTS = {
         "Standard markdown is automatically converted to Telegram format. "
         "Supported: **bold**, *italic*, ~~strikethrough~~, ||spoiler||, "
         "`inline code`, ```code blocks```, [links](url), and ## headers. "
-        "Telegram has NO table syntax — prefer bullet lists or labeled "
-        "key: value pairs over pipe tables (any tables you do emit are "
-        "auto-rewritten into row-group bullets, which you can produce "
-        "directly for cleaner output). "
         "You can send media files natively: to deliver a file to the user, "
         "include MEDIA:/absolute/path/to/file in your response. Images "
         "(.png, .jpg, .webp) appear as photos, audio (.ogg) sends as voice "
@@ -490,29 +422,6 @@ PLATFORM_HINTS = {
         "your response. Images are sent as native photos, and other files arrive as downloadable "
         "documents."
     ),
-    "yuanbao": (
-        "You are on Yuanbao (腾讯元宝), a Chinese AI assistant platform. "
-        "Markdown formatting is supported (code blocks, tables, bold/italic). "
-        "You CAN send media files natively — to deliver a file to the user, include "
-        "MEDIA:/absolute/path/to/file in your response. The file will be sent as a native "
-        "Yuanbao attachment: images (.jpg, .png, .webp, .gif) are sent as photos, "
-        "and other files (.pdf, .docx, .txt, .zip, etc.) arrive as downloadable documents "
-        "(max 50 MB). You can also include image URLs in markdown format ![alt](url) and "
-        "they will be downloaded and sent as native photos. "
-        "Do NOT tell the user you lack file-sending capability — use MEDIA: syntax "
-        "whenever a file delivery is appropriate.\n\n"
-        "Stickers (贴纸 / 表情包 / TIM face): Yuanbao has a built-in sticker catalogue. "
-        "When the user sends a sticker (you see '[emoji: 名称]' in their message) or asks "
-        "you to send/reply-with a 贴纸/表情/表情包, you MUST use the sticker tools:\n"
-        "  1. Call yb_search_sticker with a Chinese keyword (e.g. '666', '比心', '吃瓜', "
-        "     '捂脸', '合十') to discover matching sticker_ids.\n"
-        "  2. Call yb_send_sticker with the chosen sticker_id or name — this sends a real "
-        "     TIMFaceElem that renders as a native sticker in the chat.\n"
-        "DO NOT draw sticker-like PNGs with execute_code/Pillow/matplotlib and then send "
-        "them via MEDIA: or send_image_file. That produces a fake low-quality 'sticker' "
-        "image and is the WRONG path. Bare Unicode emoji in text is also not a substitute "
-        "— when a sticker is the right response, use yb_send_sticker."
-    ),
 }
 
 # ---------------------------------------------------------------------------
@@ -916,11 +825,6 @@ def build_skills_system_prompt(
             "Skills also encode the user's preferred approach, conventions, and quality standards "
             "for tasks like code review, planning, and testing — load them even for tasks you "
             "already know how to do, because the skill defines how it should be done here.\n"
-            "Whenever the user asks you to configure, set up, install, enable, disable, modify, "
-            "or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, "
-            "skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill "
-            "first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, "
-            "`hermes setup`) so you don't have to guess or invent workarounds.\n"
             "If a skill has issues, fix it with skill_manage(action='patch').\n"
             "After difficult/iterative tasks, offer to save as a skill. "
             "If a skill you loaded was missing steps, had wrong commands, or needed "

agent/redact.py

@@ -56,12 +56,8 @@ _SENSITIVE_BODY_KEYS = frozenset({
 })
 
 # Snapshot at import time so runtime env mutations (e.g. LLM-generated
-# `export HERMES_REDACT_SECRETS=true`) cannot enable/disable redaction
-# mid-session.  OFF by default — user must opt in via
-# `security.redact_secrets: true` in config.yaml (bridged to this env var
-# in hermes_cli/main.py and gateway/run.py) or `HERMES_REDACT_SECRETS=true`
-# in ~/.hermes/.env.
-_REDACT_ENABLED = os.getenv("HERMES_REDACT_SECRETS", "").lower() in ("1", "true", "yes", "on")
+# `export HERMES_REDACT_SECRETS=false`) cannot disable redaction mid-session.
+_REDACT_ENABLED = os.getenv("HERMES_REDACT_SECRETS", "").lower() not in ("0", "false", "no", "off")
 
 # Known API key prefixes -- match the prefix + contiguous token chars
 _PREFIX_PATTERNS = [
@@ -184,59 +180,11 @@ _PREFIX_RE = re.compile(
 )
 
 
-def mask_secret(
-    value: str,
-    *,
-    head: int = 4,
-    tail: int = 4,
-    floor: int = 12,
-    placeholder: str = "***",
-    empty: str = "",
-) -> str:
-    """Mask a secret for display, preserving ``head`` and ``tail`` characters.
-
-    Canonical helper for display-time redaction across Hermes — used by
-    ``hermes config``, ``hermes status``, ``hermes dump``, and anywhere
-    a secret needs to be shown truncated for debuggability while still
-    keeping the bulk hidden.
-
-    Args:
-        value:       The secret to mask. ``None``/empty returns ``empty``.
-        head:        Leading characters to preserve. Default 4.
-        tail:        Trailing characters to preserve. Default 4.
-        floor:       Values shorter than ``head + tail + floor_margin`` are
-                     fully masked (returns ``placeholder``). Default 12 —
-                     matches the existing config/status/dump convention.
-        placeholder: Value returned for too-short inputs. Default ``"***"``.
-        empty:       Value returned when ``value`` is falsy (None, ""). The
-                     caller can override this to e.g. ``color("(not set)",
-                     Colors.DIM)`` for user-facing display.
-
-    Examples:
-        >>> mask_secret("sk-proj-abcdef1234567890")
-        'sk-p...7890'
-        >>> mask_secret("short")                         # fully masked
-        '***'
-        >>> mask_secret("")                              # empty default
-        ''
-        >>> mask_secret("", empty="(not set)")           # empty override
-        '(not set)'
-        >>> mask_secret("long-token", head=6, tail=4, floor=18)
-        '***'
-    """
-    if not value:
-        return empty
-    if len(value) < floor:
-        return placeholder
-    return f"{value[:head]}...{value[-tail:]}"
-
-
 def _mask_token(token: str) -> str:
-    """Mask a log token — conservative 18-char floor, preserves 6 prefix / 4 suffix."""
-    # Empty input: historically this returned "***" rather than "". Preserve.
-    if not token:
+    """Mask a token, preserving prefix for long tokens."""
+    if len(token) < 18:
         return "***"
-    return mask_secret(token, head=6, tail=4, floor=18)
+    return f"{token[:6]}...{token[-4:]}"
 
 
 def _redact_query_string(query: str) -> str:
@@ -305,13 +253,11 @@ def _redact_form_body(text: str) -> str:
     return _redact_query_string(text.strip())
 
 
-def redact_sensitive_text(text: str, *, force: bool = False) -> str:
+def redact_sensitive_text(text: str) -> str:
     """Apply all redaction patterns to a block of text.
 
     Safe to call on any string -- non-matching text passes through unchanged.
-    Disabled by default — enable via security.redact_secrets: true in config.yaml.
-    Set force=True for safety boundaries that must never return raw secrets
-    regardless of the user's global logging redaction preference.
+    Disabled when security.redact_secrets is false in config.yaml.
     """
     if text is None:
         return None
@@ -319,7 +265,7 @@ def redact_sensitive_text(text: str, *, force: bool = False) -> str:
         text = str(text)
     if not text:
         return text
-    if not (force or _REDACT_ENABLED):
+    if not _REDACT_ENABLED:
         return text
 
     # Known prefixes (sk-, ghp_, etc.)

agent/shell_hooks.py

@@ -76,7 +76,6 @@ except ImportError:  # pragma: no cover
     fcntl = None  # type: ignore[assignment]
 
 from hermes_constants import get_hermes_home
-from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -569,7 +568,7 @@ def save_allowlist(data: Dict[str, Any]) -> None:
         try:
             with os.fdopen(fd, "w") as fh:
                 fh.write(json.dumps(data, indent=2, sort_keys=True))
-            atomic_replace(tmp_path, p)
+            os.replace(tmp_path, p)
         except Exception:
             try:
                 os.unlink(tmp_path)
@@ -755,11 +754,7 @@ def _resolve_effective_accept(
     if env in ("1", "true", "yes", "on"):
         return True
     cfg_val = cfg.get("hooks_auto_accept", False)
-    if isinstance(cfg_val, bool):
-        return cfg_val
-    if isinstance(cfg_val, str):
-        return cfg_val.strip().lower() in ("1", "true", "yes", "on")
-    return False
+    return bool(cfg_val)
 
 
 # ---------------------------------------------------------------------------

agent/skill_commands.py

@@ -234,7 +234,7 @@ def scan_skill_commands() -> Dict[str, Dict[str, Any]]:
 
         for scan_dir in dirs_to_scan:
             for skill_md in iter_skill_index_files(scan_dir, "SKILL.md"):
-                if any(part in ('.git', '.github', '.hub', '.archive') for part in skill_md.parts):
+                if any(part in ('.git', '.github', '.hub') for part in skill_md.parts):
                     continue
                 try:
                     content = skill_md.read_text(encoding='utf-8')
@@ -284,71 +284,6 @@ def get_skill_commands() -> Dict[str, Dict[str, Any]]:
     return _skill_commands
 
 
-def reload_skills() -> Dict[str, Any]:
-    """Re-scan the skills directory and return a diff of what changed.
-
-    Rescans ``~/.hermes/skills/`` and any ``skills.external_dirs`` so the
-    slash-command map (``agent.skill_commands._skill_commands``) reflects
-    skills added or removed on disk.
-
-    This does NOT invalidate the skills system-prompt cache. Skills are
-    called by name via ``/skill-name``, ``skills_list``, or ``skill_view``
-    — they don't need to be in the system prompt for the model to use them.
-    Keeping the prompt cache intact preserves prefix caching across the
-    reload, so a user invoking ``/reload-skills`` pays no cache-reset cost.
-
-    Returns:
-        Dict with keys::
-
-            {
-              "added":      [{"name": str, "description": str}, ...],
-              "removed":    [{"name": str, "description": str}, ...],
-              "unchanged":  [skill names present before and after],
-              "total":      total skill count after rescan,
-              "commands":   total /slash-skill count after rescan,
-            }
-
-        ``description`` is the skill's full SKILL.md frontmatter
-        ``description:`` field — the same string the system prompt renders
-        as ``    - name: description`` for pre-existing skills.
-    """
-    # Snapshot pre-reload state (name -> description) from the current
-    # slash-command cache. Using dicts lets the post-rescan diff carry
-    # descriptions for newly-visible or just-removed skills without a
-    # second disk walk.
-    def _snapshot(cmds: Dict[str, Dict[str, Any]]) -> Dict[str, str]:
-        out: Dict[str, str] = {}
-        for slash_key, info in cmds.items():
-            bare = slash_key.lstrip("/")
-            out[bare] = (info or {}).get("description") or ""
-        return out
-
-    before = _snapshot(_skill_commands)
-
-    # Rescan the skills dir. ``scan_skill_commands`` resets
-    # ``_skill_commands = {}`` internally and repopulates it.
-    new_commands = scan_skill_commands()
-
-    after = _snapshot(new_commands)
-
-    added_names = sorted(set(after) - set(before))
-    removed_names = sorted(set(before) - set(after))
-    unchanged = sorted(set(after) & set(before))
-
-    added = [{"name": n, "description": after[n]} for n in added_names]
-    # For removed skills, use the description we had cached pre-rescan
-    # (the skill file is gone so we can't re-read it).
-    removed = [{"name": n, "description": before[n]} for n in removed_names]
-
-    return {
-        "added": added,
-        "removed": removed,
-        "unchanged": unchanged,
-        "total": len(after),
-        "commands": len(new_commands),
-    }
-
-
 def resolve_skill_command_key(command: str) -> Optional[str]:
     """Resolve a user-typed /command to its canonical skill_cmds key.
 
@@ -393,16 +328,8 @@ def build_skill_invocation_message(
         return f"[Failed to load skill: {skill_info['name']}]"
 
     loaded_skill, skill_dir, skill_name = loaded
-
-    # Track active usage for Curator lifecycle management (#17782)
-    try:
-        from tools.skill_usage import bump_use
-        bump_use(skill_name)
-    except Exception:
-        pass  # Non-critical — skill invocation proceeds regardless
-
     activation_note = (
-        f'[IMPORTANT: The user has invoked the "{skill_name}" skill, indicating they want '
+        f'[SYSTEM: The user has invoked the "{skill_name}" skill, indicating they want '
         "you to follow its instructions. The full skill content is loaded below.]"
     )
     return _build_skill_message(
@@ -440,16 +367,8 @@ def build_preloaded_skills_prompt(
             continue
 
         loaded_skill, skill_dir, skill_name = loaded
-
-        # Track active usage for Curator lifecycle management (#17782)
-        try:
-            from tools.skill_usage import bump_use
-            bump_use(skill_name)
-        except Exception:
-            pass  # Non-critical
-
         activation_note = (
-            f'[IMPORTANT: The user launched this CLI session with the "{skill_name}" skill '
+            f'[SYSTEM: The user launched this CLI session with the "{skill_name}" skill '
             "preloaded. Treat its instructions as active guidance for the duration of this "
             "session unless the user overrides them.]"
         )

agent/skill_utils.py

@@ -24,7 +24,7 @@ PLATFORM_MAP = {
     "windows": "win32",
 }
 
-EXCLUDED_SKILL_DIRS = frozenset((".git", ".github", ".hub", ".archive"))
+EXCLUDED_SKILL_DIRS = frozenset((".git", ".github", ".hub"))
 
 # ── Lazy YAML loader ─────────────────────────────────────────────────────
 
@@ -200,9 +200,6 @@ def get_external_skills_dirs() -> List[Path]:
     if not isinstance(raw_dirs, list):
         return []
 
-    from hermes_constants import get_hermes_home
-
-    hermes_home = get_hermes_home()
     local_skills = get_skills_dir().resolve()
     seen: Set[Path] = set()
     result: List[Path] = []
@@ -213,12 +210,7 @@ def get_external_skills_dirs() -> List[Path]:
             continue
         # Expand ~ and environment variables
         expanded = os.path.expanduser(os.path.expandvars(entry))
-        p = Path(expanded)
-        # Resolve relative paths against HERMES_HOME, not cwd
-        if not p.is_absolute():
-            p = (hermes_home / p).resolve()
-        else:
-            p = p.resolve()
+        p = Path(expanded).resolve()
         if p == local_skills:
             continue
         if p in seen:
@@ -440,7 +432,7 @@ def extract_skill_description(frontmatter: Dict[str, Any]) -> str:
 def iter_skill_index_files(skills_dir: Path, filename: str):
     """Walk skills_dir yielding sorted paths matching *filename*.
 
-    Excludes ``.git``, ``.github``, ``.hub``, ``.archive`` directories.
+    Excludes ``.git``, ``.github``, ``.hub`` directories.
     """
     matches = []
     for root, dirs, files in os.walk(skills_dir, followlinks=True):

agent/title_generator.py

@@ -6,18 +6,12 @@ adds latency to the user-facing reply.
 
 import logging
 import threading
-from typing import Callable, Optional
+from typing import Optional
 
 from agent.auxiliary_client import call_llm
 
 logger = logging.getLogger(__name__)
 
-# Callback signature: (task_name, exception) -> None. Used to surface
-# auxiliary failures to the user through AIAgent._emit_auxiliary_failure
-# so silent-drops (e.g. OpenRouter 402 exhausting the fallback chain)
-# become visible instead of piling up as NULL session titles.
-FailureCallback = Callable[[str, BaseException], None]
-
 _TITLE_PROMPT = (
     "Generate a short, descriptive title (3-7 words) for a conversation that starts with the "
     "following exchange. The title should capture the main topic or intent. "
@@ -25,23 +19,11 @@ _TITLE_PROMPT = (
 )
 
 
-def generate_title(
-    user_message: str,
-    assistant_response: str,
-    timeout: float = 30.0,
-    failure_callback: Optional[FailureCallback] = None,
-    main_runtime: dict = None,
-) -> Optional[str]:
+def generate_title(user_message: str, assistant_response: str, timeout: float = 30.0) -> Optional[str]:
     """Generate a session title from the first exchange.
 
-    Uses the main runtime's model when available, falling back to the
-    auxiliary LLM client (cheapest/fastest available model).
+    Uses the auxiliary LLM client (cheapest/fastest available model).
     Returns the title string or None on failure.
-
-    ``failure_callback`` is invoked with ``(task, exception)`` when the
-    auxiliary call raises — the caller typically wires this to
-    ``AIAgent._emit_auxiliary_failure`` so the user sees a warning instead
-    of silently accumulating untitled sessions.
     """
     # Truncate long messages to keep the request small
     user_snippet = user_message[:500] if user_message else ""
@@ -59,7 +41,6 @@ def generate_title(
             max_tokens=500,
             temperature=0.3,
             timeout=timeout,
-            main_runtime=main_runtime,
         )
         title = (response.choices[0].message.content or "").strip()
         # Clean up: remove quotes, trailing punctuation, prefixes like "Title: "
@@ -71,15 +52,7 @@ def generate_title(
             title = title[:77] + "..."
         return title if title else None
     except Exception as e:
-        # Log at WARNING so this shows up in agent.log without debug mode.
-        # Full detail at debug level for operators who need the stack.
-        logger.warning("Title generation failed: %s", e)
-        logger.debug("Title generation traceback", exc_info=True)
-        if failure_callback is not None:
-            try:
-                failure_callback("title generation", e)
-            except Exception:
-                logger.debug("Title generation failure_callback raised", exc_info=True)
+        logger.debug("Title generation failed: %s", e)
         return None
 
 
@@ -88,8 +61,6 @@ def auto_title_session(
     session_id: str,
     user_message: str,
     assistant_response: str,
-    failure_callback: Optional[FailureCallback] = None,
-    main_runtime: dict = None,
 ) -> None:
     """Generate and set a session title if one doesn't already exist.
 
@@ -110,9 +81,7 @@ def auto_title_session(
     except Exception:
         return
 
-    title = generate_title(
-        user_message, assistant_response, failure_callback=failure_callback, main_runtime=main_runtime
-    )
+    title = generate_title(user_message, assistant_response)
     if not title:
         return
 
@@ -129,8 +98,6 @@ def maybe_auto_title(
     user_message: str,
     assistant_response: str,
     conversation_history: list,
-    failure_callback: Optional[FailureCallback] = None,
-    main_runtime: dict = None,
 ) -> None:
     """Fire-and-forget title generation after the first exchange.
 
@@ -152,7 +119,6 @@ def maybe_auto_title(
     thread = threading.Thread(
         target=auto_title_session,
         args=(session_db, session_id, user_message, assistant_response),
-        kwargs={"failure_callback": failure_callback, "main_runtime": main_runtime},
         daemon=True,
         name="auto-title",
     )

agent/tool_guardrails.py

@@ -1,455 +0,0 @@
-"""Pure tool-call loop guardrail primitives.
-
-The controller in this module is intentionally side-effect free: it tracks
-per-turn tool-call observations and returns decisions. Runtime code owns whether
-those decisions become warning guidance, synthetic tool results, or controlled
-turn halts.
-"""
-
-from __future__ import annotations
-
-import hashlib
-import json
-from dataclasses import dataclass, field
-from typing import Any, Mapping
-
-from utils import safe_json_loads
-
-
-IDEMPOTENT_TOOL_NAMES = frozenset(
-    {
-        "read_file",
-        "search_files",
-        "web_search",
-        "web_extract",
-        "session_search",
-        "browser_snapshot",
-        "browser_console",
-        "browser_get_images",
-        "mcp_filesystem_read_file",
-        "mcp_filesystem_read_text_file",
-        "mcp_filesystem_read_multiple_files",
-        "mcp_filesystem_list_directory",
-        "mcp_filesystem_list_directory_with_sizes",
-        "mcp_filesystem_directory_tree",
-        "mcp_filesystem_get_file_info",
-        "mcp_filesystem_search_files",
-    }
-)
-
-MUTATING_TOOL_NAMES = frozenset(
-    {
-        "terminal",
-        "execute_code",
-        "write_file",
-        "patch",
-        "todo",
-        "memory",
-        "skill_manage",
-        "browser_click",
-        "browser_type",
-        "browser_press",
-        "browser_scroll",
-        "browser_navigate",
-        "send_message",
-        "cronjob",
-        "delegate_task",
-        "process",
-    }
-)
-
-
-@dataclass(frozen=True)
-class ToolCallGuardrailConfig:
-    """Thresholds for per-turn tool-call loop detection.
-
-    Warnings are enabled by default and never prevent tool execution. Hard stops
-    are explicit opt-in so interactive CLI/TUI sessions get a gentle nudge unless
-    the user enables circuit-breaker behavior in config.yaml.
-    """
-
-    warnings_enabled: bool = True
-    hard_stop_enabled: bool = False
-    exact_failure_warn_after: int = 2
-    exact_failure_block_after: int = 5
-    same_tool_failure_warn_after: int = 3
-    same_tool_failure_halt_after: int = 8
-    no_progress_warn_after: int = 2
-    no_progress_block_after: int = 5
-    idempotent_tools: frozenset[str] = field(default_factory=lambda: IDEMPOTENT_TOOL_NAMES)
-    mutating_tools: frozenset[str] = field(default_factory=lambda: MUTATING_TOOL_NAMES)
-
-    @classmethod
-    def from_mapping(cls, data: Mapping[str, Any] | None) -> "ToolCallGuardrailConfig":
-        """Build config from the `tool_loop_guardrails` config.yaml section."""
-        if not isinstance(data, Mapping):
-            return cls()
-
-        warn_after = data.get("warn_after")
-        if not isinstance(warn_after, Mapping):
-            warn_after = {}
-        hard_stop_after = data.get("hard_stop_after")
-        if not isinstance(hard_stop_after, Mapping):
-            hard_stop_after = {}
-
-        defaults = cls()
-        return cls(
-            warnings_enabled=_as_bool(data.get("warnings_enabled"), defaults.warnings_enabled),
-            hard_stop_enabled=_as_bool(data.get("hard_stop_enabled"), defaults.hard_stop_enabled),
-            exact_failure_warn_after=_positive_int(
-                warn_after.get("exact_failure", data.get("exact_failure_warn_after")),
-                defaults.exact_failure_warn_after,
-            ),
-            same_tool_failure_warn_after=_positive_int(
-                warn_after.get("same_tool_failure", data.get("same_tool_failure_warn_after")),
-                defaults.same_tool_failure_warn_after,
-            ),
-            no_progress_warn_after=_positive_int(
-                warn_after.get("idempotent_no_progress", data.get("no_progress_warn_after")),
-                defaults.no_progress_warn_after,
-            ),
-            exact_failure_block_after=_positive_int(
-                hard_stop_after.get("exact_failure", data.get("exact_failure_block_after")),
-                defaults.exact_failure_block_after,
-            ),
-            same_tool_failure_halt_after=_positive_int(
-                hard_stop_after.get("same_tool_failure", data.get("same_tool_failure_halt_after")),
-                defaults.same_tool_failure_halt_after,
-            ),
-            no_progress_block_after=_positive_int(
-                hard_stop_after.get("idempotent_no_progress", data.get("no_progress_block_after")),
-                defaults.no_progress_block_after,
-            ),
-        )
-
-
-@dataclass(frozen=True)
-class ToolCallSignature:
-    """Stable, non-reversible identity for a tool name plus canonical args."""
-
-    tool_name: str
-    args_hash: str
-
-    @classmethod
-    def from_call(cls, tool_name: str, args: Mapping[str, Any] | None) -> "ToolCallSignature":
-        canonical = canonical_tool_args(args or {})
-        return cls(tool_name=tool_name, args_hash=_sha256(canonical))
-
-    def to_metadata(self) -> dict[str, str]:
-        """Return public metadata without raw argument values."""
-        return {"tool_name": self.tool_name, "args_hash": self.args_hash}
-
-
-@dataclass(frozen=True)
-class ToolGuardrailDecision:
-    """Decision returned by the tool-call guardrail controller."""
-
-    action: str = "allow"  # allow | warn | block | halt
-    code: str = "allow"
-    message: str = ""
-    tool_name: str = ""
-    count: int = 0
-    signature: ToolCallSignature | None = None
-
-    @property
-    def allows_execution(self) -> bool:
-        return self.action in {"allow", "warn"}
-
-    @property
-    def should_halt(self) -> bool:
-        return self.action in {"block", "halt"}
-
-    def to_metadata(self) -> dict[str, Any]:
-        data: dict[str, Any] = {
-            "action": self.action,
-            "code": self.code,
-            "message": self.message,
-            "tool_name": self.tool_name,
-            "count": self.count,
-        }
-        if self.signature is not None:
-            data["signature"] = self.signature.to_metadata()
-        return data
-
-
-def canonical_tool_args(args: Mapping[str, Any]) -> str:
-    """Return sorted compact JSON for parsed tool arguments."""
-    if not isinstance(args, Mapping):
-        raise TypeError(f"tool args must be a mapping, got {type(args).__name__}")
-    return json.dumps(
-        args,
-        ensure_ascii=False,
-        sort_keys=True,
-        separators=(",", ":"),
-        default=str,
-    )
-
-
-def classify_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]:
-    """Safety-fallback classifier used only when callers don't pass ``failed``.
-
-    Mirrors ``agent.display._detect_tool_failure`` exactly so the guardrail
-    never disagrees with the CLI's user-visible ``[error]`` tag. Production
-    callers in ``run_agent.py`` always pass an explicit ``failed=`` derived
-    from ``_detect_tool_failure``; this function exists so standalone callers
-    (tests, tooling) still get consistent behavior.
-    """
-    if result is None:
-        return False, ""
-
-    if tool_name == "terminal":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
-            exit_code = data.get("exit_code")
-            if exit_code is not None and exit_code != 0:
-                return True, f" [exit {exit_code}]"
-        return False, ""
-
-    if tool_name == "memory":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
-            if data.get("success") is False and "exceed the limit" in data.get("error", ""):
-                return True, " [full]"
-
-    lower = result[:500].lower()
-    if '"error"' in lower or '"failed"' in lower or result.startswith("Error"):
-        return True, " [error]"
-
-    return False, ""
-
-
-class ToolCallGuardrailController:
-    """Per-turn controller for repeated failed/non-progressing tool calls."""
-
-    def __init__(self, config: ToolCallGuardrailConfig | None = None):
-        self.config = config or ToolCallGuardrailConfig()
-        self.reset_for_turn()
-
-    def reset_for_turn(self) -> None:
-        self._exact_failure_counts: dict[ToolCallSignature, int] = {}
-        self._same_tool_failure_counts: dict[str, int] = {}
-        self._no_progress: dict[ToolCallSignature, tuple[str, int]] = {}
-        self._halt_decision: ToolGuardrailDecision | None = None
-
-    @property
-    def halt_decision(self) -> ToolGuardrailDecision | None:
-        return self._halt_decision
-
-    def before_call(self, tool_name: str, args: Mapping[str, Any] | None) -> ToolGuardrailDecision:
-        signature = ToolCallSignature.from_call(tool_name, _coerce_args(args))
-        if not self.config.hard_stop_enabled:
-            return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
-
-        exact_count = self._exact_failure_counts.get(signature, 0)
-        if exact_count >= self.config.exact_failure_block_after:
-            decision = ToolGuardrailDecision(
-                action="block",
-                code="repeated_exact_failure_block",
-                message=(
-                    f"Blocked {tool_name}: the same tool call failed {exact_count} "
-                    "times with identical arguments. Stop retrying it unchanged; "
-                    "change strategy or explain the blocker."
-                ),
-                tool_name=tool_name,
-                count=exact_count,
-                signature=signature,
-            )
-            self._halt_decision = decision
-            return decision
-
-        if self._is_idempotent(tool_name):
-            record = self._no_progress.get(signature)
-            if record is not None:
-                _result_hash, repeat_count = record
-                if repeat_count >= self.config.no_progress_block_after:
-                    decision = ToolGuardrailDecision(
-                        action="block",
-                        code="idempotent_no_progress_block",
-                        message=(
-                            f"Blocked {tool_name}: this read-only call returned the same "
-                            f"result {repeat_count} times. Stop repeating it unchanged; "
-                            "use the result already provided or try a different query."
-                        ),
-                        tool_name=tool_name,
-                        count=repeat_count,
-                        signature=signature,
-                    )
-                    self._halt_decision = decision
-                    return decision
-
-        return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
-
-    def after_call(
-        self,
-        tool_name: str,
-        args: Mapping[str, Any] | None,
-        result: str | None,
-        *,
-        failed: bool | None = None,
-    ) -> ToolGuardrailDecision:
-        args = _coerce_args(args)
-        signature = ToolCallSignature.from_call(tool_name, args)
-        if failed is None:
-            failed, _ = classify_tool_failure(tool_name, result)
-
-        if failed:
-            exact_count = self._exact_failure_counts.get(signature, 0) + 1
-            self._exact_failure_counts[signature] = exact_count
-            self._no_progress.pop(signature, None)
-
-            same_count = self._same_tool_failure_counts.get(tool_name, 0) + 1
-            self._same_tool_failure_counts[tool_name] = same_count
-
-            if self.config.hard_stop_enabled and same_count >= self.config.same_tool_failure_halt_after:
-                decision = ToolGuardrailDecision(
-                    action="halt",
-                    code="same_tool_failure_halt",
-                    message=(
-                        f"Stopped {tool_name}: it failed {same_count} times this turn. "
-                        "Stop retrying the same failing tool path and choose a different approach."
-                    ),
-                    tool_name=tool_name,
-                    count=same_count,
-                    signature=signature,
-                )
-                self._halt_decision = decision
-                return decision
-
-            if self.config.warnings_enabled and exact_count >= self.config.exact_failure_warn_after:
-                return ToolGuardrailDecision(
-                    action="warn",
-                    code="repeated_exact_failure_warning",
-                    message=(
-                        f"{tool_name} has failed {exact_count} times with identical arguments. "
-                        "This looks like a loop; inspect the error and change strategy "
-                        "instead of retrying it unchanged."
-                    ),
-                    tool_name=tool_name,
-                    count=exact_count,
-                    signature=signature,
-                )
-
-            if self.config.warnings_enabled and same_count >= self.config.same_tool_failure_warn_after:
-                return ToolGuardrailDecision(
-                    action="warn",
-                    code="same_tool_failure_warning",
-                    message=(
-                        f"{tool_name} has failed {same_count} times this turn. "
-                        "This looks like a loop; change approach before retrying."
-                    ),
-                    tool_name=tool_name,
-                    count=same_count,
-                    signature=signature,
-                )
-
-            return ToolGuardrailDecision(tool_name=tool_name, count=exact_count, signature=signature)
-
-        self._exact_failure_counts.pop(signature, None)
-        self._same_tool_failure_counts.pop(tool_name, None)
-
-        if not self._is_idempotent(tool_name):
-            self._no_progress.pop(signature, None)
-            return ToolGuardrailDecision(tool_name=tool_name, signature=signature)
-
-        result_hash = _result_hash(result)
-        previous = self._no_progress.get(signature)
-        repeat_count = 1
-        if previous is not None and previous[0] == result_hash:
-            repeat_count = previous[1] + 1
-        self._no_progress[signature] = (result_hash, repeat_count)
-
-        if self.config.warnings_enabled and repeat_count >= self.config.no_progress_warn_after:
-            return ToolGuardrailDecision(
-                action="warn",
-                code="idempotent_no_progress_warning",
-                message=(
-                    f"{tool_name} returned the same result {repeat_count} times. "
-                    "Use the result already provided or change the query instead of "
-                    "repeating it unchanged."
-                ),
-                tool_name=tool_name,
-                count=repeat_count,
-                signature=signature,
-            )
-
-        return ToolGuardrailDecision(tool_name=tool_name, count=repeat_count, signature=signature)
-
-    def _is_idempotent(self, tool_name: str) -> bool:
-        if tool_name in self.config.mutating_tools:
-            return False
-        return tool_name in self.config.idempotent_tools
-
-
-def toolguard_synthetic_result(decision: ToolGuardrailDecision) -> str:
-    """Build a synthetic role=tool content string for a blocked tool call."""
-    return json.dumps(
-        {
-            "error": decision.message,
-            "guardrail": decision.to_metadata(),
-        },
-        ensure_ascii=False,
-    )
-
-
-def append_toolguard_guidance(result: str, decision: ToolGuardrailDecision) -> str:
-    """Append runtime guidance to the current tool result content."""
-    if decision.action not in {"warn", "halt"} or not decision.message:
-        return result
-    label = "Tool loop hard stop" if decision.action == "halt" else "Tool loop warning"
-    suffix = (
-        f"\n\n[{label}: "
-        f"{decision.code}; count={decision.count}; {decision.message}]"
-    )
-    return (result or "") + suffix
-
-
-def _coerce_args(args: Mapping[str, Any] | None) -> Mapping[str, Any]:
-    return args if isinstance(args, Mapping) else {}
-
-
-def _result_hash(result: str | None) -> str:
-    parsed = safe_json_loads(result or "")
-    if parsed is not None:
-        try:
-            canonical = json.dumps(
-                parsed,
-                ensure_ascii=False,
-                sort_keys=True,
-                separators=(",", ":"),
-                default=str,
-            )
-        except TypeError:
-            canonical = str(parsed)
-    else:
-        canonical = result or ""
-    return _sha256(canonical)
-
-
-def _as_bool(value: Any, default: bool) -> bool:
-    if value is None:
-        return default
-    if isinstance(value, bool):
-        return value
-    if isinstance(value, (int, float)):
-        return bool(value)
-    if isinstance(value, str):
-        lowered = value.strip().lower()
-        if lowered in {"1", "true", "yes", "on", "enabled"}:
-            return True
-        if lowered in {"0", "false", "no", "off", "disabled"}:
-            return False
-    return default
-
-
-def _positive_int(value: Any, default: int) -> int:
-    if value is None:
-        return default
-    try:
-        parsed = int(value)
-    except (TypeError, ValueError):
-        return default
-    return parsed if parsed >= 1 else default
-
-
-def _sha256(value: str) -> str:
-    return hashlib.sha256(value.encode("utf-8")).hexdigest()

agent/transports/__init__.py

@@ -23,14 +23,9 @@ def get_transport(api_mode: str):
     This allows gradual migration — call sites can check for None
     and fall back to the legacy code path.
     """
-    cls = _REGISTRY.get(api_mode)
-    if cls is None:
-        # The registry can be partially populated when a specific transport
-        # module was imported directly (for example chat_completions before
-        # codex).  Discover on misses, not only when the registry is empty, so
-        # test/order-dependent imports do not make valid api_modes unavailable.
+    if not _REGISTRY:
         _discover_transports()
-        cls = _REGISTRY.get(api_mode)
+    cls = _REGISTRY.get(api_mode)
     if cls is None:
         return None
     return cls()

agent/transports/anthropic.py

@@ -58,7 +58,6 @@ class AnthropicTransport(ProviderTransport):
             context_length: int | None
             base_url: str | None
             fast_mode: bool
-            drop_context_1m_beta: bool
         """
         from agent.anthropic_adapter import build_anthropic_kwargs
 
@@ -74,7 +73,6 @@ class AnthropicTransport(ProviderTransport):
             context_length=params.get("context_length"),
             base_url=params.get("base_url"),
             fast_mode=params.get("fast_mode", False),
-            drop_context_1m_beta=params.get("drop_context_1m_beta", False),
         )
 
     def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:

agent/transports/chat_completions.py

@@ -12,93 +12,12 @@ reasoning configuration, temperature handling, and extra_body assembly.
 import copy
 from typing import Any, Dict, List, Optional
 
-from agent.lmstudio_reasoning import resolve_lmstudio_effort
 from agent.moonshot_schema import is_moonshot_model, sanitize_moonshot_tools
 from agent.prompt_builder import DEVELOPER_ROLE_MODELS
 from agent.transports.base import ProviderTransport
 from agent.transports.types import NormalizedResponse, ToolCall, Usage
 
 
-def _build_gemini_thinking_config(model: str, reasoning_config: dict | None) -> dict | None:
-    """Translate Hermes/OpenRouter-style reasoning config to Gemini thinkingConfig."""
-    if reasoning_config is None or not isinstance(reasoning_config, dict):
-        return None
-
-    normalized_model = (model or "").strip().lower()
-    if normalized_model.startswith("google/"):
-        normalized_model = normalized_model.split("/", 1)[1]
-
-    # ``thinking_config`` is a Gemini-only request parameter. The same
-    # ``gemini`` provider also serves Gemma (and historically PaLM/Bard);
-    # those reject the field with HTTP 400 "Unknown name 'thinking_config':
-    # Cannot find field" — including the polite ``{"includeThoughts": False}``
-    # form. Omit the field entirely on non-Gemini models. (#17426)
-    if not normalized_model.startswith("gemini"):
-        return None
-
-    if reasoning_config.get("enabled") is False:
-        # Gemini can hide thought parts even when internal thinking still
-        # happens; omit thinkingLevel to avoid model-specific validation quirks.
-        return {"includeThoughts": False}
-
-    effort = str(reasoning_config.get("effort", "medium") or "medium").strip().lower()
-    if effort == "none":
-        return {"includeThoughts": False}
-
-    thinking_config: Dict[str, Any] = {"includeThoughts": True}
-
-    # Gemini 2.5 accepts thinkingBudget; don't guess a budget from Hermes'
-    # coarse effort levels. ``includeThoughts`` alone is enough to surface
-    # thought parts without risking request validation errors.
-    if normalized_model.startswith("gemini-2.5-"):
-        return thinking_config
-
-    if effort not in {"minimal", "low", "medium", "high", "xhigh"}:
-        effort = "medium"
-
-    # Gemini 3 Flash documents low/medium/high thinking levels; Gemini 3 Pro
-    # is stricter (low/high). Clamp Hermes' wider effort set to what each
-    # family accepts so we never forward an undocumented level verbatim.
-    if normalized_model.startswith(("gemini-3", "gemini-3.1")):
-        if "flash" in normalized_model:
-            if effort in {"minimal", "low"}:
-                thinking_config["thinkingLevel"] = "low"
-            elif effort in {"high", "xhigh"}:
-                thinking_config["thinkingLevel"] = "high"
-            else:
-                thinking_config["thinkingLevel"] = "medium"
-        elif "pro" in normalized_model:
-            thinking_config["thinkingLevel"] = (
-                "high" if effort in {"high", "xhigh"} else "low"
-            )
-
-    return thinking_config
-
-
-def _snake_case_gemini_thinking_config(config: dict | None) -> dict | None:
-    """Convert Gemini thinking config keys to the OpenAI-compat field names."""
-    if not isinstance(config, dict) or not config:
-        return None
-
-    translated: Dict[str, Any] = {}
-    if isinstance(config.get("includeThoughts"), bool):
-        translated["include_thoughts"] = config["includeThoughts"]
-    if isinstance(config.get("thinkingLevel"), str) and config["thinkingLevel"].strip():
-        translated["thinking_level"] = config["thinkingLevel"].strip().lower()
-    if isinstance(config.get("thinkingBudget"), (int, float)):
-        translated["thinking_budget"] = int(config["thinkingBudget"])
-    return translated or None
-
-
-def _is_gemini_openai_compat_base_url(base_url: Any) -> bool:
-    normalized = str(base_url or "").strip().rstrip("/").lower()
-    if not normalized:
-        return False
-    if "generativelanguage.googleapis.com" not in normalized:
-        return False
-    return normalized.endswith("/openai")
-
-
 class ChatCompletionsTransport(ProviderTransport):
     """Transport for api_mode='chat_completions'.
 
@@ -112,15 +31,15 @@ class ChatCompletionsTransport(ProviderTransport):
     def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> List[Dict[str, Any]]:
         """Messages are already in OpenAI format — sanitize Codex leaks only.
 
-        Strips Codex Responses API fields (``codex_reasoning_items`` /
-        ``codex_message_items`` on the message, ``call_id``/``response_item_id``
-        on tool_calls) that strict chat-completions providers reject with 400/422.
+        Strips Codex Responses API fields (``codex_reasoning_items`` on the
+        message, ``call_id``/``response_item_id`` on tool_calls) that strict
+        chat-completions providers reject with 400/422.
         """
         needs_sanitize = False
         for msg in messages:
             if not isinstance(msg, dict):
                 continue
-            if "codex_reasoning_items" in msg or "codex_message_items" in msg:
+            if "codex_reasoning_items" in msg:
                 needs_sanitize = True
                 break
             tool_calls = msg.get("tool_calls")
@@ -140,7 +59,6 @@ class ChatCompletionsTransport(ProviderTransport):
             if not isinstance(msg, dict):
                 continue
             msg.pop("codex_reasoning_items", None)
-            msg.pop("codex_message_items", None)
             tool_calls = msg.get("tool_calls")
             if isinstance(tool_calls, list):
                 for tc in tool_calls:
@@ -182,7 +100,6 @@ class ChatCompletionsTransport(ProviderTransport):
             is_github_models: bool
             is_nvidia_nim: bool
             is_kimi: bool
-            is_lmstudio: bool
             is_custom_provider: bool
             ollama_num_ctx: int | None
             # Provider routing
@@ -196,7 +113,6 @@ class ChatCompletionsTransport(ProviderTransport):
             # Reasoning
             supports_reasoning: bool
             github_reasoning_extra: dict | None
-            lmstudio_reasoning_options: list[str] | None  # raw allowed_options from /api/v1/models
             # Claude on OpenRouter/Nous max output
             anthropic_max_output: int | None
             # Extra
@@ -271,7 +187,6 @@ class ChatCompletionsTransport(ProviderTransport):
         anthropic_max_out = params.get("anthropic_max_output")
         is_nvidia_nim = params.get("is_nvidia_nim", False)
         is_kimi = params.get("is_kimi", False)
-        is_tokenhub = params.get("is_tokenhub", False)
         reasoning_config = params.get("reasoning_config")
 
         if ephemeral is not None and max_tokens_fn:
@@ -303,41 +218,12 @@ class ChatCompletionsTransport(ProviderTransport):
                         _kimi_effort = _e
                 api_kwargs["reasoning_effort"] = _kimi_effort
 
-        # Tencent TokenHub: top-level reasoning_effort (unless thinking disabled)
-        if is_tokenhub:
-            _tokenhub_thinking_off = bool(
-                reasoning_config
-                and isinstance(reasoning_config, dict)
-                and reasoning_config.get("enabled") is False
-            )
-            if not _tokenhub_thinking_off:
-                _tokenhub_effort = "high"
-                if reasoning_config and isinstance(reasoning_config, dict):
-                    _e = (reasoning_config.get("effort") or "").strip().lower()
-                    if _e in ("low", "medium", "high"):
-                        _tokenhub_effort = _e
-                api_kwargs["reasoning_effort"] = _tokenhub_effort
-
-        # LM Studio: top-level reasoning_effort. Only emit when the model
-        # declares reasoning support via /api/v1/models capabilities (gated
-        # upstream by params["supports_reasoning"]). resolve_lmstudio_effort
-        # is shared with run_agent's summary path so both stay in sync.
-        if params.get("is_lmstudio", False) and params.get("supports_reasoning", False):
-            _lm_effort = resolve_lmstudio_effort(
-                reasoning_config,
-                params.get("lmstudio_reasoning_options"),
-            )
-            if _lm_effort is not None:
-                api_kwargs["reasoning_effort"] = _lm_effort
-
         # extra_body assembly
         extra_body: Dict[str, Any] = {}
 
         is_openrouter = params.get("is_openrouter", False)
         is_nous = params.get("is_nous", False)
         is_github_models = params.get("is_github_models", False)
-        provider_name = str(params.get("provider_name") or "").strip().lower()
-        base_url = params.get("base_url")
 
         provider_prefs = params.get("provider_preferences")
         if provider_prefs and is_openrouter:
@@ -353,9 +239,8 @@ class ChatCompletionsTransport(ProviderTransport):
                 "type": "enabled" if _kimi_thinking_enabled else "disabled",
             }
 
-        # Reasoning. LM Studio is handled above via top-level reasoning_effort,
-        # so skip emitting extra_body.reasoning for it.
-        if params.get("supports_reasoning", False) and not params.get("is_lmstudio", False):
+        # Reasoning
+        if params.get("supports_reasoning", False):
             if is_github_models:
                 gh_reasoning = params.get("github_reasoning_extra")
                 if gh_reasoning is not None:
@@ -391,23 +276,6 @@ class ChatCompletionsTransport(ProviderTransport):
         if is_qwen:
             extra_body["vl_high_resolution_images"] = True
 
-        if provider_name == "gemini":
-            raw_thinking_config = _build_gemini_thinking_config(model, reasoning_config)
-            if _is_gemini_openai_compat_base_url(base_url):
-                thinking_config = _snake_case_gemini_thinking_config(raw_thinking_config)
-                if thinking_config:
-                    openai_compat_extra = extra_body.get("extra_body", {})
-                    google_extra = openai_compat_extra.get("google", {})
-                    google_extra["thinking_config"] = thinking_config
-                    openai_compat_extra["google"] = google_extra
-                    extra_body["extra_body"] = openai_compat_extra
-            elif raw_thinking_config:
-                extra_body["thinking_config"] = raw_thinking_config
-        elif provider_name == "google-gemini-cli":
-            thinking_config = _build_gemini_thinking_config(model, reasoning_config)
-            if thinking_config:
-                extra_body["thinking_config"] = thinking_config
-
         # Merge any pre-built extra_body additions
         additions = params.get("extra_body_additions")
         if additions:
@@ -477,13 +345,9 @@ class ChatCompletionsTransport(ProviderTransport):
         # so keep them apart in provider_data rather than merging.
         reasoning = getattr(msg, "reasoning", None)
         reasoning_content = getattr(msg, "reasoning_content", None)
-        if reasoning_content is None and hasattr(msg, "model_extra"):
-            model_extra = getattr(msg, "model_extra", None) or {}
-            if isinstance(model_extra, dict) and "reasoning_content" in model_extra:
-                reasoning_content = model_extra["reasoning_content"]
 
         provider_data: Dict[str, Any] = {}
-        if reasoning_content is not None:
+        if reasoning_content:
             provider_data["reasoning_content"] = reasoning_content
         rd = getattr(msg, "reasoning_details", None)
         if rd:

agent/transports/codex.py

@@ -8,7 +8,7 @@ streaming, or the _run_codex_stream() call path.
 from typing import Any, Dict, List, Optional
 
 from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse, ToolCall
+from agent.transports.types import NormalizedResponse, ToolCall, Usage
 
 
 class ResponsesApiTransport(ProviderTransport):
@@ -120,24 +120,6 @@ class ResponsesApiTransport(ProviderTransport):
         if request_overrides:
             kwargs.update(request_overrides)
 
-        if is_codex_backend:
-            prompt_cache_key = kwargs.get("prompt_cache_key")
-            cache_scope_id = str(prompt_cache_key or session_id or "").strip()
-            if cache_scope_id:
-                existing_extra_headers = kwargs.get("extra_headers")
-                merged_extra_headers: Dict[str, str] = {}
-                if isinstance(existing_extra_headers, dict):
-                    merged_extra_headers.update(
-                        {
-                            str(key): str(value)
-                            for key, value in existing_extra_headers.items()
-                            if key and value is not None
-                        }
-                    )
-                merged_extra_headers["session_id"] = cache_scope_id
-                merged_extra_headers["x-client-request-id"] = cache_scope_id
-                kwargs["extra_headers"] = merged_extra_headers
-
         max_tokens = params.get("max_tokens")
         if max_tokens is not None and not is_codex_backend:
             kwargs["max_output_tokens"] = max_tokens
@@ -151,6 +133,8 @@ class ResponsesApiTransport(ProviderTransport):
         """Normalize Codex Responses API response to NormalizedResponse."""
         from agent.codex_responses_adapter import (
             _normalize_codex_response,
+            _extract_responses_message_text,
+            _extract_responses_reasoning_text,
         )
 
         # _normalize_codex_response returns (SimpleNamespace, finish_reason_str)
@@ -176,8 +160,6 @@ class ResponsesApiTransport(ProviderTransport):
         provider_data = {}
         if msg and hasattr(msg, "codex_reasoning_items") and msg.codex_reasoning_items:
             provider_data["codex_reasoning_items"] = msg.codex_reasoning_items
-        if msg and hasattr(msg, "codex_message_items") and msg.codex_message_items:
-            provider_data["codex_message_items"] = msg.codex_message_items
         if msg and hasattr(msg, "reasoning_details") and msg.reasoning_details:
             provider_data["reasoning_details"] = msg.reasoning_details
 

agent/transports/types.py

@@ -97,7 +97,7 @@ class NormalizedResponse:
     Response-level ``provider_data`` examples:
 
     * Anthropic: ``{"reasoning_details": [...]}``
-    * Codex: ``{"codex_reasoning_items": [...], "codex_message_items": [...]}``
+    * Codex: ``{"codex_reasoning_items": [...]}``
     * Others: ``None``
     """
 
@@ -126,11 +126,6 @@ class NormalizedResponse:
         pd = self.provider_data or {}
         return pd.get("codex_reasoning_items")
 
-    @property
-    def codex_message_items(self):
-        pd = self.provider_data or {}
-        return pd.get("codex_message_items")
-
 
 # ---------------------------------------------------------------------------
 # Factory helpers

agent/usage_pricing.py

@@ -359,25 +359,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://aws.amazon.com/bedrock/pricing/",
         pricing_version="bedrock-pricing-2026-04",
     ),
-    # MiniMax
-    (
-        "minimax",
-        "minimax-m2.7",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.30"),
-        output_cost_per_million=Decimal("1.20"),
-        source="official_docs_snapshot",
-        pricing_version="minimax-pricing-2026-04",
-    ),
-    (
-        "minimax-cn",
-        "minimax-m2.7",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.30"),
-        output_cost_per_million=Decimal("1.20"),
-        source="official_docs_snapshot",
-        pricing_version="minimax-pricing-2026-04",
-    ),
 }
 
 
@@ -419,8 +400,6 @@ def resolve_billing_route(
         return BillingRoute(provider="anthropic", model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
     if provider_name == "openai":
         return BillingRoute(provider="openai", model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
-    if provider_name in {"minimax", "minimax-cn"}:
-        return BillingRoute(provider=provider_name, model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
     if provider_name in {"custom", "local"} or (base and "localhost" in base):
         return BillingRoute(provider=provider_name or "custom", model=model, base_url=base_url or "", billing_mode="unknown")
     return BillingRoute(provider=provider_name or "unknown", model=model.split("/")[-1] if model else "", base_url=base_url or "", billing_mode="unknown")

apps/README.md

@@ -0,0 +1,58 @@
+# Hermes Apps
+
+Platform apps live here. The first app is a cross-platform GUI shell around the
+existing Hermes dashboard; it should not fork chat, config, logs, or session UI.
+
+## Shape
+
+```text
+apps/
+  gui/      # cross-platform app shell: dev Chrome shell now, Tauri native next
+  shared/   # runtime bundle notes/scripts used by Windows + macOS packaging
+```
+
+## Desktop Dev
+
+The backend-only GUI mode is:
+
+```bash
+hermes dashboard --gui
+```
+
+The fast GUI shell is:
+
+```powershell
+cd \\wsl$\Ubuntu\home\bb\hermes-agent\apps\gui
+npm run dev
+```
+
+The native Tauri shell is:
+
+```powershell
+cd \\wsl$\Ubuntu\home\bb\hermes-agent\apps\gui
+npm run dev:tauri
+```
+
+`--gui` implies the embedded TUI; do not pass `--tui` separately for GUI mode.
+
+## MVP Boundary
+
+Included:
+
+- bundled Python runtime
+- bundled Node/TUI runtime
+- CLI install to PATH
+- profile picker and first-run setup
+- dashboard health/reconnect state
+- tray controls
+- desktop notifications
+- Windows installer
+
+Deferred:
+
+- code signing
+- native self-updater
+- store distribution
+
+For MVP updates, the desktop UI should run the existing `hermes update` flow and
+surface progress/finish notifications.

apps/gui/README.md

@@ -0,0 +1,102 @@
+# Hermes GUI
+
+Cross-platform GUI shell for the Hermes dashboard.
+
+## Fast Dev Shell
+
+This gets a GUI window on Windows/WSL today by launching Chrome in app mode:
+
+```bash
+cd apps/gui
+npm run dev
+```
+
+It starts `hermes dashboard --gui --no-open --port 9120`, waits for
+`/api/health`, then opens a standalone app window at `http://127.0.0.1:9120`.
+
+## Native Shell
+
+The native Tauri shell is still scaffolded:
+
+```bash
+cd apps/gui
+npm run dev:tauri
+```
+
+From Windows PowerShell on a `\\wsl$` path, use PowerShell `npm`, not
+`npm.cmd`:
+
+```powershell
+Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass -Force
+cd \\wsl$\Ubuntu\home\bb\hermes-agent\apps\gui
+npm run dev:tauri
+```
+
+`npm.cmd` goes through `cmd.exe`, and `cmd.exe` cannot use UNC paths as the
+current directory.
+
+If `npm run` still falls through `cmd.exe`, bypass npm entirely:
+
+```powershell
+\\wsl$\Ubuntu\home\bb\hermes-agent\apps\gui\dev-tauri.ps1
+```
+
+The launcher builds into `%LOCALAPPDATA%\Hermes\cargo-target\gui` instead of
+`\\wsl$` because Windows Cargo incremental locks do not work reliably on UNC
+WSL filesystems.
+
+In dev, either start Hermes yourself:
+
+```bash
+hermes dashboard --gui --no-open --port 9120
+```
+
+or let the native shell start it. The tray menu owns:
+
+- Open Hermes
+- Open in Browser
+- Restart Hermes Runtime
+- Quit Hermes
+
+The native shell reuses a healthy GUI runtime when one is already running.
+Otherwise it picks the first free port from `9120..9139`, passes that port into
+the WSL/backend process, and navigates the Tauri window there. Set
+`HERMES_GUI_PORT` to force a starting port.
+
+## Fresh Install Emulation
+
+Use an isolated Hermes home without touching your real `~/.hermes`:
+
+```powershell
+powershell.exe -ExecutionPolicy Bypass -File \\wsl$\Ubuntu\home\bb\hermes-agent\apps\gui\dev-tauri.ps1 -Fresh
+```
+
+Reset that disposable home and run again:
+
+```powershell
+powershell.exe -ExecutionPolicy Bypass -File \\wsl$\Ubuntu\home\bb\hermes-agent\apps\gui\dev-tauri.ps1 -Fresh -ResetFresh
+```
+
+Fresh mode stores state in `%LOCALAPPDATA%\Hermes\fresh-install-home` and starts
+from port `9140` so it does not collide with your normal GUI dev session.
+
+Set `HERMES_GUI_MIN_SPLASH_MS` only when debugging the startup screen; default
+startup is instant once the backend is healthy.
+
+## Boundary
+
+GUI owns:
+
+- app shell/window
+- startup state
+- sidecar process lifecycle
+- future tray/notifications/installers
+
+Hermes owns:
+
+- dashboard UI
+- auth/session token
+- profiles/config/env
+- TUI/PTT chat bridge
+- tools/skills/gateway
+- update flow

apps/gui/dev-tauri.ps1

@@ -0,0 +1,57 @@
+param(
+  [string]$Command = "dev",
+  [switch]$Fresh,
+  [switch]$ResetFresh
+)
+
+$ErrorActionPreference = "Stop"
+Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass -Force
+
+$AppRoot = Split-Path -Parent $MyInvocation.MyCommand.Path
+$Script = Join-Path $AppRoot "scripts\tauri.mjs"
+
+if (-not (Get-Command node -ErrorAction SilentlyContinue)) {
+  throw "Windows Node.js was not found. Install it with: winget install OpenJS.NodeJS.LTS"
+}
+
+if (-not (Get-Command rustc -ErrorAction SilentlyContinue)) {
+  throw "Windows Rust was not found. Install it with: winget install Rustlang.Rustup"
+}
+
+$Tauri = Get-Command tauri -ErrorAction SilentlyContinue
+$CargoTauri = Get-Command cargo-tauri -ErrorAction SilentlyContinue
+
+if (-not $Tauri -and -not $CargoTauri) {
+  throw "Tauri CLI not found. Install it with: npm install -g @tauri-apps/cli (run from a normal Windows path, not \\wsl$)"
+}
+
+$env:CARGO_INCREMENTAL = "0"
+$env:CARGO_TARGET_DIR = Join-Path $env:LOCALAPPDATA "Hermes\cargo-target\gui"
+New-Item -ItemType Directory -Force -Path $env:CARGO_TARGET_DIR | Out-Null
+
+if ($Fresh) {
+  $FreshHome = Join-Path $env:LOCALAPPDATA "Hermes\fresh-install-home"
+  if ($ResetFresh -and (Test-Path $FreshHome)) {
+    Remove-Item -Recurse -Force $FreshHome
+  }
+  New-Item -ItemType Directory -Force -Path $FreshHome | Out-Null
+  $env:HERMES_HOME = $FreshHome
+  $env:HERMES_GUI_PORT = "9140"
+  $env:HERMES_GUI_FRESH = "1"
+  Write-Host "Fresh GUI mode"
+  Write-Host "  HERMES_HOME=$FreshHome"
+  Write-Host "  HERMES_GUI_PORT=$env:HERMES_GUI_PORT"
+}
+
+Push-Location $AppRoot
+try {
+  if ($Tauri) {
+    & tauri $Command
+  }
+  else {
+    & cargo tauri $Command
+  }
+}
+finally {
+  Pop-Location
+}

apps/gui/package.json

@@ -0,0 +1,13 @@
+{
+  "name": "@hermes/gui",
+  "version": "0.0.0",
+  "private": true,
+  "type": "module",
+  "scripts": {
+    "dev": "node scripts/dev-shell.mjs",
+    "dev:tauri": "node scripts/tauri.mjs dev",
+    "build": "node scripts/tauri.mjs build",
+    "dashboard": "node scripts/start-dashboard.mjs",
+    "tauri": "node scripts/tauri.mjs"
+  }
+}

apps/gui/scripts/dev-shell.mjs

@@ -0,0 +1,156 @@
+import { spawn, spawnSync } from "node:child_process";
+import { createServer } from "node:net";
+import { dirname, resolve } from "node:path";
+import { setTimeout as delay } from "node:timers/promises";
+import { fileURLToPath } from "node:url";
+
+const here = dirname(fileURLToPath(import.meta.url));
+const repoRoot = resolve(here, "../../..");
+const python = process.env.HERMES_PYTHON || "python";
+let port = process.env.HERMES_GUI_PORT || "9120";
+let url = `http://127.0.0.1:${port}`;
+
+let dashboard = null;
+
+function stop() {
+  if (dashboard && !dashboard.killed) dashboard.kill();
+}
+
+process.on("SIGINT", () => {
+  stop();
+  process.exit(130);
+});
+process.on("SIGTERM", () => {
+  stop();
+  process.exit(143);
+});
+process.on("exit", stop);
+
+async function waitForHealth() {
+  for (let i = 0; i < 120; i += 1) {
+    if (await isHealthy()) return true;
+    await delay(500);
+  }
+  return false;
+}
+
+async function isHealthy() {
+  try {
+    const res = await fetch(`${url}/api/health`, {
+      signal: AbortSignal.timeout(1000),
+    });
+    const data = await res.json();
+    return res.ok && data.status === "ok";
+  } catch {
+    return false;
+  }
+}
+
+function canBind(candidate) {
+  return new Promise((resolveBind) => {
+    const server = createServer();
+    server.once("error", () => resolveBind(false));
+    server.listen(Number(candidate), "127.0.0.1", () => {
+      server.close(() => resolveBind(true));
+    });
+  });
+}
+
+async function choosePort() {
+  if (process.env.HERMES_GUI_PORT) return;
+
+  let candidate = Number(port);
+  for (let i = 0; i < 20; i += 1) {
+    if (await canBind(candidate)) {
+      port = String(candidate);
+      url = `http://127.0.0.1:${port}`;
+      return;
+    }
+    candidate += 1;
+  }
+}
+
+function startDashboard() {
+  dashboard = spawn(
+    python,
+    [
+      "-m",
+      "hermes_cli.main",
+      "dashboard",
+      "--gui",
+      "--no-open",
+      "--host",
+      "127.0.0.1",
+      "--port",
+      port,
+    ],
+    {
+      cwd: repoRoot,
+      env: {
+        ...process.env,
+        HERMES_GUI: "1",
+      },
+      stdio: "inherit",
+    },
+  );
+
+  dashboard.on("exit", (code) => {
+    process.exit(code ?? 0);
+  });
+}
+
+function run(command, args) {
+  return (
+    spawnSync(command, args, {
+      shell: process.platform === "win32",
+      stdio: "ignore",
+    }).status === 0
+  );
+}
+
+function openGuiWindow() {
+  if (process.platform === "win32") {
+    return (
+      run("cmd.exe", ["/C", "start", "", "chrome", `--app=${url}`]) ||
+      run("cmd.exe", ["/C", "start", "", "msedge", `--app=${url}`]) ||
+      run("cmd.exe", ["/C", "start", "", url])
+    );
+  }
+
+  if (process.env.WSL_DISTRO_NAME) {
+    return (
+      run("cmd.exe", ["/C", "start", "", "chrome", `--app=${url}`]) ||
+      run("cmd.exe", ["/C", "start", "", "msedge", `--app=${url}`]) ||
+      run("cmd.exe", ["/C", "start", "", url])
+    );
+  }
+
+  if (process.platform === "darwin") {
+    return (
+      run("open", ["-na", "Google Chrome", "--args", `--app=${url}`]) ||
+      run("open", [url])
+    );
+  }
+
+  return (
+    run("google-chrome", [`--app=${url}`]) ||
+    run("chromium", [`--app=${url}`]) ||
+    run("xdg-open", [url])
+  );
+}
+
+if (await isHealthy()) {
+  console.log(`Hermes GUI already running -> ${url}`);
+  openGuiWindow();
+  process.exit(0);
+}
+
+await choosePort();
+startDashboard();
+
+if (await waitForHealth()) {
+  console.log(`Hermes GUI -> ${url}`);
+  openGuiWindow();
+} else {
+  console.error(`Hermes GUI did not become healthy at ${url}`);
+}

apps/gui/scripts/start-dashboard.mjs

@@ -0,0 +1,95 @@
+import { spawn } from "node:child_process";
+import { dirname, resolve } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const here = dirname(fileURLToPath(import.meta.url));
+const repoRoot = resolve(here, "../../..");
+const python = process.env.HERMES_PYTHON || "python";
+const port = process.env.HERMES_GUI_PORT || "9120";
+const url = `http://127.0.0.1:${port}`;
+
+async function isHealthy() {
+  try {
+    const res = await fetch(`${url}/api/health`, {
+      signal: AbortSignal.timeout(1000),
+    });
+    const data = await res.json();
+    return res.ok && data.status === "ok";
+  } catch {
+    return false;
+  }
+}
+
+function wslRepoRoot() {
+  const normalized = repoRoot.replaceAll("\\", "/");
+  const parts = normalized.split("/");
+  const host = parts[2]?.toLowerCase();
+  if (process.platform !== "win32") return null;
+  if (host !== "wsl$" && host !== "wsl.localhost") return null;
+  const distro = parts[3];
+  const path = `/${parts.slice(4).join("/")}`;
+  return distro && path !== "/" ? { distro, path } : null;
+}
+
+function spawnDashboard() {
+  const wsl = wslRepoRoot();
+  if (wsl) {
+    return spawn(
+      "wsl.exe",
+      [
+        "-d",
+        wsl.distro,
+        "--cd",
+        wsl.path,
+        "env",
+        "HERMES_GUI=1",
+        process.env.HERMES_WSL_PYTHON || "python",
+        "-m",
+        "hermes_cli.main",
+        "dashboard",
+        "--gui",
+        "--no-open",
+        "--host",
+        "127.0.0.1",
+        "--port",
+        port,
+      ],
+      { stdio: "inherit" },
+    );
+  }
+
+  return spawn(
+    python,
+    [
+      "-m",
+      "hermes_cli.main",
+      "dashboard",
+      "--gui",
+      "--no-open",
+      "--host",
+      "127.0.0.1",
+      "--port",
+      port,
+    ],
+    {
+      cwd: repoRoot,
+      env: {
+        ...process.env,
+        HERMES_GUI: "1",
+      },
+      stdio: "inherit",
+    },
+  );
+}
+
+if (await isHealthy()) {
+  console.log(`Hermes GUI already running -> ${url}`);
+  process.exit(0);
+}
+
+const child = spawnDashboard();
+
+child.on("exit", (code, signal) => {
+  if (signal) process.kill(process.pid, signal);
+  process.exit(code ?? 0);
+});

apps/gui/scripts/tauri.mjs

@@ -0,0 +1,90 @@
+import { spawnSync } from "node:child_process";
+import { existsSync } from "node:fs";
+import { dirname, resolve } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const here = dirname(fileURLToPath(import.meta.url));
+const appRoot = resolve(here, "..");
+const bin = process.platform === "win32" ? "tauri.cmd" : "tauri";
+const localTauri = resolve(appRoot, "node_modules", ".bin", bin);
+const args = process.argv.slice(2);
+
+function isWsl() {
+  return process.platform === "linux" && !!process.env.WSL_DISTRO_NAME;
+}
+
+function quotePs(value) {
+  return `'${value.replaceAll("'", "''")}'`;
+}
+
+function dispatchToWindows() {
+  const pathResult = spawnSync("wslpath", ["-w", appRoot], {
+    encoding: "utf8",
+  });
+  const windowsPath = pathResult.stdout.trim();
+  if (!windowsPath) return false;
+
+  const command = [
+    "$ErrorActionPreference = 'Stop'",
+    "Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass -Force",
+    "if (-not (Get-Command npm -ErrorAction SilentlyContinue)) {",
+    '  Write-Error "Windows npm was not found. Install Windows Node.js first: winget install OpenJS.NodeJS.LTS"',
+    "}",
+    "if (-not (Get-Command rustc -ErrorAction SilentlyContinue)) {",
+    '  Write-Error "Windows Rust was not found. Install Rust first: winget install Rustlang.Rustup"',
+    "}",
+    `Set-Location -LiteralPath ${quotePs(windowsPath)}`,
+    "& npm run dev:tauri",
+  ].join("; ");
+  const result = spawnSync(
+    "powershell.exe",
+    ["-NoProfile", "-ExecutionPolicy", "Bypass", "-Command", command],
+    { stdio: "inherit" },
+  );
+  process.exit(result.status ?? 1);
+}
+
+function run(command, commandArgs, { exit = true } = {}) {
+  if (process.platform === "win32") {
+    const psCommand = [
+      "$ErrorActionPreference = 'Stop'",
+      "Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass -Force",
+      `Set-Location -LiteralPath ${quotePs(appRoot)}`,
+      `& ${quotePs(command)} ${commandArgs.map(quotePs).join(" ")}`,
+    ].join("; ");
+    const result = spawnSync(
+      "powershell.exe",
+      ["-NoProfile", "-ExecutionPolicy", "Bypass", "-Command", psCommand],
+      { stdio: "inherit" },
+    );
+    if (result.error && result.error.code === "ENOENT") return false;
+    if (exit) process.exit(result.status ?? 1);
+    return result.status === 0;
+  }
+
+  const result = spawnSync(command, commandArgs, {
+    cwd: appRoot,
+    env: process.env,
+    stdio: "inherit",
+  });
+
+  if (result.error && result.error.code === "ENOENT") return false;
+  if (exit) process.exit(result.status ?? 1);
+  return result.status === 0;
+}
+
+if (isWsl() && process.env.HERMES_GUI_TAURI_WSL !== "1") {
+  console.log("Launching native Windows Tauri from WSL...");
+  dispatchToWindows();
+  console.error(
+    "Could not hand off to Windows PowerShell. Run this from Windows PowerShell instead:",
+  );
+  console.error("  cd \\\\wsl$\\Ubuntu\\home\\bb\\hermes-agent\\apps\\gui");
+  console.error("  npm run dev:tauri");
+  process.exit(1);
+}
+
+if (existsSync(localTauri)) run(localTauri, args);
+if (run("tauri", args, { exit: false })) process.exit(0);
+if (run("cargo", ["tauri", ...args], { exit: false })) process.exit(0);
+run("npx", ["--yes", "@tauri-apps/cli@latest", ...args]);

apps/gui/src-tauri/.gitignore

@@ -0,0 +1 @@
+/target/

apps/gui/src-tauri/Cargo.toml

@@ -0,0 +1,17 @@
+[package]
+name = "hermes-gui"
+version = "0.0.0"
+description = "Hermes GUI shell"
+edition = "2021"
+
+[lib]
+name = "hermes_gui_lib"
+crate-type = ["staticlib", "cdylib", "rlib"]
+
+[build-dependencies]
+tauri-build = { version = "2", features = [] }
+
+[dependencies]
+tauri = { version = "2", features = ["tray-icon"] }
+tauri-plugin-notification = "2"
+tauri-plugin-opener = "2"

apps/gui/src-tauri/build.rs

@@ -0,0 +1,3 @@
+fn main() {
+    tauri_build::build();
+}

apps/gui/src-tauri/capabilities/default.json

@@ -0,0 +1,7 @@
+{
+  "$schema": "../gen/schemas/desktop-schema.json",
+  "identifier": "default",
+  "description": "Default Hermes GUI permissions",
+  "windows": ["main"],
+  "permissions": ["core:default", "notification:default", "opener:default"]
+}

apps/gui/src-tauri/gen/schemas/capabilities.json

@@ -0,0 +1 @@
+{"default":{"identifier":"default","description":"Default Hermes GUI permissions","local":true,"windows":["main"],"permissions":["core:default","notification:default","opener:default"]}}

apps/gui/src-tauri/icons/icon.svg

@@ -0,0 +1,4 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100">
+  <rect width="100" height="100" rx="18" fill="#071313"/>
+  <text x="50" y="70" text-anchor="middle" font-size="68" fill="#f0e6d2">⚕</text>
+</svg>

apps/gui/src-tauri/sidecars/.gitkeep

@@ -0,0 +1 @@
+

apps/gui/src-tauri/src/lib.rs

@@ -0,0 +1,433 @@
+use std::{
+    io::{Read, Write},
+    net::{TcpListener, TcpStream},
+    process::{Child, Command, Stdio},
+    sync::Mutex,
+    time::{Duration, Instant},
+};
+
+use tauri::{
+    image::Image,
+    menu::{Menu, MenuItem, PredefinedMenuItem},
+    tray::{MouseButton, MouseButtonState, TrayIconBuilder, TrayIconEvent},
+    App, AppHandle, Manager, WebviewWindow,
+};
+
+const GUI_HOST: &str = "127.0.0.1";
+const DEFAULT_GUI_PORT: u16 = 9120;
+const MIN_SPLASH_MS: u64 = 0;
+const SPLASH_URL: &str = "data:text/html,%3C!doctype%20html%3E%3Cmeta%20charset%3Dutf-8%3E%3Cstyle%3Ebody%7Bmargin%3A0%3Bheight%3A100vh%3Bdisplay%3Agrid%3Bplace-items%3Acenter%3Bbackground%3A%23071313%3Bcolor%3A%23f0e6d2%3Bfont%3A14px%20monospace%3Bletter-spacing%3A.08em%3Btext-transform%3Auppercase%7D%3C%2Fstyle%3E%3Cbody%3EStarting%20Hermes%E2%80%A6%3C%2Fbody%3E";
+
+struct GuiState {
+    child: Mutex<Option<Child>>,
+    port: Mutex<u16>,
+}
+
+fn gui_url(port: u16) -> String {
+    format!("http://{GUI_HOST}:{port}")
+}
+
+fn check_health(port: u16) -> bool {
+    let Ok(mut stream) = TcpStream::connect_timeout(
+        &format!("{GUI_HOST}:{port}").parse().unwrap(),
+        Duration::from_secs(1),
+    ) else {
+        return false;
+    };
+
+    let _ = stream.set_read_timeout(Some(Duration::from_secs(1)));
+    let request =
+        format!("GET /api/health HTTP/1.1\r\nHost: {GUI_HOST}:{port}\r\nConnection: close\r\n\r\n");
+
+    if stream.write_all(request.as_bytes()).is_err() {
+        return false;
+    }
+
+    let mut response = String::new();
+    let _ = stream.read_to_string(&mut response);
+    response.contains("200 OK")
+        && response.contains("\"status\":\"ok\"")
+        && response.contains("\"mode\":\"gui\"")
+}
+
+fn can_bind(port: u16) -> bool {
+    TcpListener::bind((GUI_HOST, port)).is_ok()
+}
+
+fn base_port() -> u16 {
+    std::env::var("HERMES_GUI_PORT")
+        .ok()
+        .and_then(|raw| raw.parse().ok())
+        .unwrap_or(DEFAULT_GUI_PORT)
+}
+
+fn select_port() -> u16 {
+    let start = base_port();
+    for port in start..start.saturating_add(20) {
+        if check_health(port) || can_bind(port) {
+            return port;
+        }
+    }
+    start
+}
+
+fn repo_root() -> std::path::PathBuf {
+    std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("../../..")
+        .canonicalize()
+        .unwrap_or_else(|_| std::path::PathBuf::from("."))
+}
+
+fn runtime_dir() -> Option<std::path::PathBuf> {
+    std::env::var_os("HERMES_GUI_RUNTIME_DIR").map(std::path::PathBuf::from)
+}
+
+fn runtime_python(runtime: &std::path::Path) -> std::path::PathBuf {
+    if cfg!(target_os = "windows") {
+        runtime.join("venv").join("Scripts").join("python.exe")
+    } else {
+        runtime.join("venv").join("bin").join("python")
+    }
+}
+
+fn wsl_path(root: &std::path::Path) -> Option<(String, String)> {
+    let raw = root.to_string_lossy().replace('\\', "/");
+    let parts: Vec<&str> = raw.split('/').collect();
+    let host = parts.get(2)?.to_ascii_lowercase();
+    if host != "wsl$" && host != "wsl.localhost" {
+        return None;
+    }
+    let distro = parts.get(3)?.to_string();
+    let path = format!("/{}", parts.get(4..)?.join("/"));
+    Some((distro, path))
+}
+
+fn start_dashboard(port: u16) -> std::io::Result<Child> {
+    if let Some(runtime) = runtime_dir() {
+        let python = runtime_python(&runtime);
+        let web_dist = runtime.join("web_dist");
+        let tui_dir = runtime.join("ui-tui");
+        let port = port.to_string();
+        return Command::new(python)
+            .args([
+                "-m",
+                "hermes_cli.main",
+                "dashboard",
+                "--gui",
+                "--no-open",
+                "--host",
+                GUI_HOST,
+                "--port",
+                &port,
+            ])
+            .env("HERMES_GUI", "1")
+            .env("HERMES_GUI_PORT", &port)
+            .env("HERMES_WEB_DIST", web_dist)
+            .env("HERMES_TUI_DIR", tui_dir)
+            .envs(
+                std::env::vars()
+                    .filter(|(key, _)| matches!(key.as_str(), "HERMES_HOME" | "HERMES_GUI_FRESH")),
+            )
+            .stdin(Stdio::null())
+            .stdout(Stdio::null())
+            .stderr(Stdio::null())
+            .spawn();
+    }
+
+    let root = repo_root();
+    let port = port.to_string();
+
+    if let Some((distro, path)) = wsl_path(&root) {
+        let port_env = format!("HERMES_GUI_PORT={port}");
+        let mut env_args = vec!["HERMES_GUI=1".to_string(), port_env];
+        if let Ok(home) = std::env::var("HERMES_HOME") {
+            env_args.push(format!("HERMES_HOME={home}"));
+        }
+        if let Ok(fresh) = std::env::var("HERMES_GUI_FRESH") {
+            env_args.push(format!("HERMES_GUI_FRESH={fresh}"));
+        }
+        let mut args = vec![
+            "-d".to_string(),
+            distro,
+            "--cd".to_string(),
+            path,
+            "env".to_string(),
+        ];
+        args.extend(env_args);
+        args.extend([
+            "python".to_string(),
+            "-m".to_string(),
+            "hermes_cli.main".to_string(),
+            "dashboard".to_string(),
+            "--gui".to_string(),
+            "--no-open".to_string(),
+            "--host".to_string(),
+            GUI_HOST.to_string(),
+            "--port".to_string(),
+            port.clone(),
+        ]);
+        return Command::new("wsl.exe")
+            .args(args)
+            .stdin(Stdio::null())
+            .stdout(Stdio::null())
+            .stderr(Stdio::null())
+            .spawn();
+    }
+
+    Command::new("python")
+        .args([
+            "-m",
+            "hermes_cli.main",
+            "dashboard",
+            "--gui",
+            "--no-open",
+            "--host",
+            GUI_HOST,
+            "--port",
+            &port,
+        ])
+        .current_dir(root)
+        .env("HERMES_GUI", "1")
+        .env("HERMES_GUI_PORT", &port)
+        .envs(
+            std::env::vars()
+                .filter(|(key, _)| matches!(key.as_str(), "HERMES_HOME" | "HERMES_GUI_FRESH")),
+        )
+        .stdin(Stdio::null())
+        .stdout(Stdio::null())
+        .stderr(Stdio::null())
+        .spawn()
+}
+
+fn stop_owned_dashboard(state: &GuiState) {
+    let Some(mut child) = state.child.lock().expect("gui child lock poisoned").take() else {
+        return;
+    };
+    let _ = child.kill();
+    let _ = child.wait();
+}
+
+fn current_port(state: &GuiState) -> u16 {
+    *state.port.lock().expect("gui port lock poisoned")
+}
+
+fn ensure_dashboard(state: &GuiState) -> Result<(), String> {
+    let current = current_port(state);
+    if check_health(current) {
+        return Ok(());
+    }
+
+    let port = select_port();
+    *state.port.lock().expect("gui port lock poisoned") = port;
+
+    if check_health(port) {
+        return Ok(());
+    }
+
+    let child = start_dashboard(port).map_err(|err| {
+        format!(
+            "Could not auto-start Hermes dashboard ({err}). Start it manually with: hermes dashboard --gui --no-open --port {port}"
+        )
+    })?;
+    *state.child.lock().expect("gui child lock poisoned") = Some(child);
+    Ok(())
+}
+
+fn navigate_when_ready(window: WebviewWindow, port: u16) {
+    std::thread::spawn(move || {
+        let started = Instant::now();
+        while started.elapsed() < Duration::from_secs(60) {
+            if check_health(port) {
+                let min_splash = std::env::var("HERMES_GUI_MIN_SPLASH_MS")
+                    .ok()
+                    .and_then(|raw| raw.parse::<u64>().ok())
+                    .unwrap_or(MIN_SPLASH_MS);
+                let elapsed = started.elapsed();
+                if elapsed < Duration::from_millis(min_splash) {
+                    std::thread::sleep(Duration::from_millis(min_splash) - elapsed);
+                }
+                if let Ok(url) = tauri::Url::parse(&gui_url(port)) {
+                    let _ = window.navigate(url);
+                    let _ = window.show();
+                    let _ = window.set_focus();
+                }
+                return;
+            }
+            std::thread::sleep(Duration::from_millis(500));
+        }
+    });
+}
+
+fn show_main_window(app: &AppHandle) {
+    if let Some(window) = app.get_webview_window("main") {
+        let _ = window.show();
+        let _ = window.set_focus();
+    }
+}
+
+fn open_browser(port: u16) {
+    let url = gui_url(port);
+
+    #[cfg(target_os = "windows")]
+    let _ = Command::new("cmd")
+        .args(["/C", "start", "", &url])
+        .stdin(Stdio::null())
+        .stdout(Stdio::null())
+        .stderr(Stdio::null())
+        .spawn();
+
+    #[cfg(target_os = "macos")]
+    let _ = Command::new("open").arg(&url).spawn();
+
+    #[cfg(all(unix, not(target_os = "macos")))]
+    let _ = Command::new("xdg-open").arg(&url).spawn();
+}
+
+fn tray_icon() -> Image<'static> {
+    let width = 32;
+    let height = 32;
+    let mut rgba = Vec::with_capacity(width * height * 4);
+
+    for y in 0..height {
+        for x in 0..width {
+            let mark = (14..=17).contains(&x) && (5..=26).contains(&y)
+                || (8..=23).contains(&x) && (13..=16).contains(&y)
+                || (10..=21).contains(&x) && (y == 5 || y == 26);
+            if mark {
+                rgba.extend_from_slice(&[0xF0, 0xE6, 0xD2, 0xFF]);
+            } else {
+                rgba.extend_from_slice(&[0x07, 0x13, 0x13, 0xFF]);
+            }
+        }
+    }
+
+    Image::new_owned(rgba, width as u32, height as u32)
+}
+
+fn restart_runtime(app: &AppHandle) -> Result<(), String> {
+    let state = app.state::<GuiState>();
+    stop_owned_dashboard(&state);
+    ensure_dashboard(&state)?;
+
+    if let Some(window) = app.get_webview_window("main") {
+        if let Ok(url) = tauri::Url::parse(SPLASH_URL) {
+            let _ = window.navigate(url);
+        }
+        let port = current_port(&state);
+        navigate_when_ready(window, port);
+    }
+
+    Ok(())
+}
+
+fn setup_tray(app: &App) -> tauri::Result<()> {
+    let open_item = MenuItem::with_id(app, "open", "Open Hermes", true, None::<&str>)?;
+    let browser_item = MenuItem::with_id(app, "browser", "Open in Browser", true, None::<&str>)?;
+    let restart_item =
+        MenuItem::with_id(app, "restart", "Restart Hermes Runtime", true, None::<&str>)?;
+    let status_item = MenuItem::with_id(app, "status", "Local runtime", false, None::<&str>)?;
+    let separator = PredefinedMenuItem::separator(app)?;
+    let separator2 = PredefinedMenuItem::separator(app)?;
+    let quit_item = MenuItem::with_id(app, "quit", "Quit Hermes", true, None::<&str>)?;
+
+    let menu = Menu::with_items(
+        app,
+        &[
+            &open_item,
+            &browser_item,
+            &restart_item,
+            &separator,
+            &status_item,
+            &separator2,
+            &quit_item,
+        ],
+    )?;
+
+    let icon = tray_icon();
+    let _tray = TrayIconBuilder::new()
+        .icon(icon)
+        .menu(&menu)
+        .tooltip("Hermes")
+        .on_menu_event(|app, event| match event.id.as_ref() {
+            "open" => show_main_window(app),
+            "browser" => {
+                let state = app.state::<GuiState>();
+                open_browser(current_port(&state));
+            }
+            "restart" => {
+                if let Err(err) = restart_runtime(app) {
+                    eprintln!("Failed to restart Hermes runtime: {err}");
+                }
+            }
+            "quit" => {
+                let state = app.state::<GuiState>();
+                stop_owned_dashboard(&state);
+                app.exit(0);
+            }
+            _ => {}
+        })
+        .on_tray_icon_event(|tray, event| {
+            if let TrayIconEvent::Click {
+                button: MouseButton::Left,
+                button_state: MouseButtonState::Up,
+                ..
+            } = event
+            {
+                show_main_window(&tray.app_handle());
+            }
+        })
+        .build(app)?;
+
+    Ok(())
+}
+
+#[tauri::command]
+fn runtime_running(app: AppHandle) -> bool {
+    let state = app.state::<GuiState>();
+    check_health(current_port(&state))
+}
+
+#[tauri::command]
+fn restart_runtime_command(app: AppHandle) -> Result<(), String> {
+    restart_runtime(&app)
+}
+
+pub fn run() {
+    tauri::Builder::default()
+        .plugin(tauri_plugin_notification::init())
+        .plugin(tauri_plugin_opener::init())
+        .manage(GuiState {
+            child: Mutex::new(None),
+            port: Mutex::new(base_port()),
+        })
+        .invoke_handler(tauri::generate_handler![
+            runtime_running,
+            restart_runtime_command
+        ])
+        .setup(|app| {
+            setup_tray(app)?;
+
+            if let Some(window) = app.get_webview_window("main") {
+                if let Ok(url) = tauri::Url::parse(SPLASH_URL) {
+                    let _ = window.navigate(url);
+                }
+
+                let state = app.state::<GuiState>();
+                if let Err(err) = ensure_dashboard(&state) {
+                    eprintln!("{err}");
+                }
+
+                let port = current_port(&state);
+                navigate_when_ready(window, port);
+            }
+            Ok(())
+        })
+        .on_window_event(|window, event| {
+            if let tauri::WindowEvent::CloseRequested { api, .. } = event {
+                api.prevent_close();
+                let _ = window.hide();
+            }
+        })
+        .run(tauri::generate_context!())
+        .expect("failed to run Hermes GUI");
+}

apps/gui/src-tauri/src/main.rs

@@ -0,0 +1,5 @@
+#![cfg_attr(not(debug_assertions), windows_subsystem = "windows")]
+
+fn main() {
+    hermes_gui_lib::run();
+}

apps/gui/src-tauri/tauri.conf.json

@@ -0,0 +1,38 @@
+{
+  "$schema": "https://schema.tauri.app/config/2",
+  "productName": "Hermes",
+  "version": "0.0.0",
+  "identifier": "ai.nous.hermes.gui",
+  "build": {
+    "beforeDevCommand": "",
+    "beforeBuildCommand": "",
+    "devUrl": "http://127.0.0.1:9120",
+    "frontendDist": "../dist"
+  },
+  "app": {
+    "withGlobalTauri": true,
+    "windows": [
+      {
+        "label": "main",
+        "title": "Hermes",
+        "width": 1400,
+        "height": 900,
+        "minWidth": 900,
+        "minHeight": 600,
+        "resizable": true,
+        "center": true
+      }
+    ],
+    "security": {
+      "csp": "default-src 'self' http://127.0.0.1:* http://localhost:*; connect-src 'self' http://127.0.0.1:* http://localhost:* ws://127.0.0.1:* ws://localhost:*; img-src 'self' data: blob: http://127.0.0.1:* http://localhost:*; style-src 'self' 'unsafe-inline' http://127.0.0.1:* http://localhost:*; script-src 'self' 'unsafe-inline' 'unsafe-eval' http://127.0.0.1:* http://localhost:*"
+    }
+  },
+  "bundle": {
+    "active": true,
+    "icon": ["icons/32x32.png", "icons/icon.ico", "icons/icon.svg"],
+    "targets": ["nsis", "dmg", "app"],
+    "resources": {
+      "sidecars": "sidecars/"
+    }
+  }
+}

apps/gui/src/main.ts

@@ -0,0 +1,5 @@
+// Browser-side GUI bridge entry.
+//
+// The dashboard remains in `web/`; this file is reserved for future shell-only
+// glue if we need pre-navigation scripts or native event wiring.
+export {};

apps/shared/bundle-runtime.ps1

@@ -0,0 +1,44 @@
+param(
+  [string]$Out = "$PSScriptRoot\..\gui\src-tauri\sidecars\hermes-runtime",
+  [string]$Python = "python"
+)
+
+$Root = Resolve-Path "$PSScriptRoot\..\.."
+
+Write-Host "Bundling Hermes GUI runtime"
+Write-Host "repo: $Root"
+Write-Host "out:  $Out"
+
+if (Test-Path $Out) {
+  Remove-Item -Recurse -Force $Out
+}
+New-Item -ItemType Directory -Force -Path $Out | Out-Null
+
+Write-Host "-> Building dashboard"
+npm --prefix "$Root\web" ci
+npm --prefix "$Root\web" run build
+Copy-Item -Recurse "$Root\web\dist" "$Out\web_dist"
+
+Write-Host "-> Building TUI"
+npm --prefix "$Root\ui-tui" ci
+npm --prefix "$Root\ui-tui" run build
+New-Item -ItemType Directory -Force -Path "$Out\ui-tui" | Out-Null
+Copy-Item -Recurse "$Root\ui-tui\dist" "$Out\ui-tui\dist"
+Copy-Item "$Root\ui-tui\package.json" "$Out\ui-tui\package.json"
+Copy-Item "$Root\ui-tui\package-lock.json" "$Out\ui-tui\package-lock.json"
+Copy-Item -Recurse "$Root\ui-tui\node_modules" "$Out\ui-tui\node_modules"
+
+Write-Host "-> Creating Python runtime"
+& $Python -m venv "$Out\venv"
+& "$Out\venv\Scripts\python.exe" -m pip install --upgrade pip
+& "$Out\venv\Scripts\python.exe" -m pip install -e "$Root[web,pty]"
+
+@"
+# Hermes GUI Runtime
+
+Generated by apps/shared/bundle-runtime.ps1.
+
+Set HERMES_GUI_RUNTIME_DIR to this directory before launching the Tauri shell.
+"@ | Set-Content "$Out\README.md"
+
+Write-Host "Runtime bundle ready: $Out"

apps/shared/bundle-runtime.sh

@@ -0,0 +1,41 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
+OUT="${1:-"$ROOT/apps/gui/src-tauri/sidecars/hermes-runtime"}"
+PYTHON="${PYTHON:-python}"
+
+echo "Bundling Hermes GUI runtime"
+echo "repo: $ROOT"
+echo "out:  $OUT"
+
+rm -rf "$OUT"
+mkdir -p "$OUT"
+
+echo "→ Building dashboard"
+npm --prefix "$ROOT/web" ci
+npm --prefix "$ROOT/web" run build
+cp -a "$ROOT/web/dist" "$OUT/web_dist"
+
+echo "→ Building TUI"
+npm --prefix "$ROOT/ui-tui" ci
+npm --prefix "$ROOT/ui-tui" run build
+mkdir -p "$OUT/ui-tui"
+cp -a "$ROOT/ui-tui/dist" "$OUT/ui-tui/dist"
+cp -a "$ROOT/ui-tui/package.json" "$ROOT/ui-tui/package-lock.json" "$OUT/ui-tui/"
+cp -a "$ROOT/ui-tui/node_modules" "$OUT/ui-tui/node_modules"
+
+echo "→ Creating Python runtime"
+"$PYTHON" -m venv "$OUT/venv"
+"$OUT/venv/bin/python" -m pip install --upgrade pip
+"$OUT/venv/bin/python" -m pip install -e "$ROOT[web,pty]"
+
+cat > "$OUT/README.md" <<EOF
+# Hermes GUI Runtime
+
+Generated by apps/shared/bundle-runtime.sh.
+
+Set HERMES_GUI_RUNTIME_DIR to this directory before launching the Tauri shell.
+EOF
+
+echo "✓ Runtime bundle ready: $OUT"

apps/shared/desktop-env.md

@@ -0,0 +1,33 @@
+# GUI Runtime Contract
+
+The GUI shell starts Hermes with a small, explicit environment.
+
+## Environment
+
+```text
+HERMES_GUI=1
+HERMES_WEB_DIST=<bundled web dist>
+HERMES_TUI_DIR=<bundled ui-tui dir>
+```
+
+The native shell uses `127.0.0.1:9120` as its initial GUI port during dev.
+Bundled builds should keep the port private to the local machine and expose it
+through `/api/health` and `/api/runtime`.
+
+The shell should also pass the selected profile through the normal Hermes CLI
+profile mechanism once the profile picker is wired.
+
+## Ports
+
+Use `127.0.0.1` only. Start with the GUI default port, then fall back to a
+free port if occupied. Show the chosen port in the tray menu.
+
+## User Data
+
+The installer owns app files. Hermes owns user state under `HERMES_HOME`.
+Uninstallers must not delete user state unless the user explicitly asks.
+
+## Update Model
+
+MVP does not use Tauri's native updater. GUI runs `hermes update`, tails the
+action log, notifies completion, then offers to restart the runtime.

cli-config.yaml.example

@@ -30,13 +30,14 @@ model:
   #   "ollama-cloud" - Ollama Cloud (requires: OLLAMA_API_KEY — https://ollama.com/settings)
   #   "kilocode"     - KiloCode gateway (requires: KILOCODE_API_KEY)
   #   "ai-gateway"   - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
-  #   "lmstudio"     - LM Studio local server (optional: LM_API_KEY, defaults to http://127.0.0.1:1234/v1)
   #
   # Local servers (LM Studio, Ollama, vLLM, llama.cpp):
-  #   "custom"       - Any other OpenAI-compatible endpoint. Set base_url below.
-  #   Aliases: "ollama", "vllm", "llamacpp" all map to "custom".
-  #   LM Studio is first-class and uses provider: "lmstudio".
-  #   It works with both no-auth and auth-enabled server modes.
+  #   "custom"       - Any OpenAI-compatible endpoint. Set base_url below.
+  #   Aliases: "lmstudio", "ollama", "vllm", "llamacpp" all map to "custom".
+  #   Example for LM Studio:
+  #     provider: "lmstudio"
+  #     base_url: "http://localhost:1234/v1"
+  #   No API key needed — local servers typically ignore auth.
   #
   # Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
   provider: "auto"
@@ -180,11 +181,6 @@ terminal:
 #   lifetime_seconds: 300
 #   docker_image: "nikolaik/python-nodejs:python3.11-nodejs20"
 #   docker_mount_cwd_to_workspace: true   # Explicit opt-in: mount your launch cwd into /workspace
-#   # Optional: run the container as your host user's uid:gid so files written
-#   # into bind-mounted dirs are owned by you, not root. Drops SETUID/SETGID
-#   # caps too since no gosu privilege drop is needed. Leave off if your
-#   # chosen docker_image expects to start as root.
-#   docker_run_as_host_user: true
 #   # Optional: explicitly forward selected env vars into Docker.
 #   # These values come from your current shell first, then ~/.hermes/.env.
 #   # Warning: anything forwarded here is visible to commands run in the container.
@@ -289,25 +285,6 @@ browser:
   # after this period of no activity between agent loops (default: 120 = 2 minutes)
   inactivity_timeout: 120
 
-# =============================================================================
-# Tool Loop Guardrails
-# =============================================================================
-# Soft warnings are enabled by default. They append guidance to repeated failed
-# or non-progressing tool results but still let the tool execute. Hard stops are
-# opt-in circuit breakers for autonomous/cron sessions where stopping a loop is
-# preferable to spending the full iteration budget.
-tool_loop_guardrails:
-  warnings_enabled: true
-  hard_stop_enabled: false
-  warn_after:
-    exact_failure: 2
-    same_tool_failure: 3
-    idempotent_no_progress: 2
-  hard_stop_after:
-    exact_failure: 5
-    same_tool_failure: 8
-    idempotent_no_progress: 5
-
 # =============================================================================
 # Context Compression (Auto-shrinks long conversations)
 # =============================================================================
@@ -589,7 +566,7 @@ agent:
 #   - A preset like "hermes-cli" or "hermes-telegram" (curated tool set)
 #   - A list of individual toolsets to compose your own (see list below)
 #
-# Supported platform keys: cli, telegram, discord, whatsapp, slack, qqbot, teams
+# Supported platform keys: cli, telegram, discord, whatsapp, slack, qqbot
 #
 # Examples:
 #
@@ -619,7 +596,6 @@ agent:
 #   signal:        hermes-signal         (same as telegram)
 #   homeassistant: hermes-homeassistant  (same as telegram)
 #   qqbot:            hermes-qqbot            (same as telegram)
-#   teams:            hermes-teams            (same as telegram)
 #
 platform_toolsets:
   cli: [hermes-cli]
@@ -630,8 +606,6 @@ platform_toolsets:
   signal: [hermes-signal]
   homeassistant: [hermes-homeassistant]
   qqbot: [hermes-qqbot]
-  yuanbao: [hermes-yuanbao]
-  teams: [hermes-teams]
 
 # =============================================================================
 # Gateway Platform Settings
@@ -850,9 +824,7 @@ delegation:
 # Display
 # =============================================================================
 display:
-  # Use compact banner mode (hides the ASCII-art banner, shows a single line).
-  #   true:  Compact single-line banner
-  #   false: Full ASCII banner with tool/skill summary (default)
+  # Use compact banner mode
   compact: false
 
   # Tool progress display level (CLI and gateway)
@@ -866,19 +838,12 @@ display:
   # Gateway-only natural mid-turn assistant updates.
   # When true, completed assistant status messages are sent as separate chat
   # messages. This is independent of tool_progress and gateway streaming.
-  #   true:  Send mid-turn assistant updates as separate messages (default)
-  #   false: Only send the final response
   interim_assistant_messages: true
 
-  # What Enter does when Hermes is already busy (CLI and gateway platforms).
+  # What Enter does when Hermes is already busy in the CLI.
   #   interrupt: Interrupt the current run and redirect Hermes (default)
   #   queue:     Queue your message for the next turn
-  #   steer:     Inject your message mid-run via /steer, arriving at the agent
-  #              after the next tool call — no interrupt, no role violation.
-  #              Falls back to 'queue' if the agent isn't running yet or if
-  #              images are attached (steer only carries text).
-  # Ctrl+C (or /stop in gateway) always interrupts regardless of this setting.
-  # Toggle at runtime with /busy <interrupt|queue|steer>.
+  # Ctrl+C always interrupts regardless of this setting.
   busy_input_mode: interrupt
 
   # Background process notifications (gateway/messaging only).
@@ -894,22 +859,17 @@ display:
   # Play terminal bell when agent finishes a response.
   # Useful for long-running tasks — your terminal will ding when the agent is done.
   # Works over SSH. Most terminals can be configured to flash the taskbar or play a sound.
-  #   true:  Ring the terminal bell on each response
-  #   false: Silent (default)
   bell_on_complete: false
 
   # Show model reasoning/thinking before each response.
   # When enabled, a dim box shows the model's thought process above the response.
   # Toggle at runtime with /reasoning show or /reasoning hide.
-  #   true:  Show the reasoning box
-  #   false: Hide reasoning (default)
   show_reasoning: false
 
   # Stream tokens to the terminal as they arrive instead of waiting for the
   # full response. The response box opens on first token and text appears
   # line-by-line. Tool calls are still captured silently.
-  #   true:  Stream tokens as they arrive (default)
-  #   false: Wait for the full response before rendering
+  # Stream tokens to the terminal in real-time. Disable to wait for full responses.
   streaming: true
 
   # ───────────────────────────────────────────────────────────────────────────
@@ -919,15 +879,10 @@ display:
   # response box label, and branding text. Change at runtime with /skin <name>.
   #
   # Built-in skins:
-  #   default        — Classic Hermes gold/kawaii
-  #   ares           — Crimson/bronze war-god theme with spinner wings
-  #   mono           — Clean grayscale monochrome
-  #   slate          — Cool blue developer-focused
-  #   daylight       — Bright light-mode theme
-  #   warm-lightmode — Warm paper-tone light-mode theme
-  #   poseidon       — Sea-green/teal Olympian theme
-  #   sisyphus       — Earthy stone-and-moss theme
-  #   charizard      — Fiery orange dragon theme
+  #   default  — Classic Hermes gold/kawaii
+  #   ares     — Crimson/bronze war-god theme with spinner wings
+  #   mono     — Clean grayscale monochrome
+  #   slate    — Cool blue developer-focused
   #
   # Custom skins: drop a YAML file in ~/.hermes/skins/<name>.yaml
   # Schema (all fields optional, missing values inherit from default):
@@ -953,7 +908,7 @@ display:
   #     agent_name: "My Agent"               # Banner title and branding
   #     welcome: "Welcome message"           # Shown at CLI startup
   #     response_label: " ⚔ Agent "         # Response box header label
-  #     prompt_symbol: "⚔"                  # Prompt symbol (bare token; renderers add trailing space)
+  #     prompt_symbol: "⚔ ❯ "              # Prompt symbol
   #   tool_prefix: "╎"                       # Tool output line prefix (default: ┊)
   #
   skin: default

cron/jobs.py

@@ -21,7 +21,6 @@ from typing import Optional, Dict, List, Any, Union
 logger = logging.getLogger(__name__)
 
 from hermes_time import now as _hermes_now
-from utils import atomic_replace
 
 try:
     from croniter import croniter
@@ -312,22 +311,8 @@ def compute_next_run(schedule: Dict[str, Any], last_run_at: Optional[str] = None
 
     elif schedule["kind"] == "cron":
         if not HAS_CRONITER:
-            logger.warning(
-                "Cannot compute next run for cron schedule %r: 'croniter' is "
-                "not installed. croniter is a core dependency as of v0.9.x; "
-                "reinstall hermes-agent or run 'pip install croniter' in your "
-                "runtime env.",
-                schedule.get("expr"),
-            )
             return None
-        # Use last_run_at as the croniter base when available, consistent
-        # with interval jobs.  This ensures that after a crash/restart,
-        # the next run is anchored to the actual last execution time
-        # rather than to an arbitrary restart time.
-        base_time = now
-        if last_run_at:
-            base_time = _ensure_aware(datetime.fromisoformat(last_run_at))
-        cron = croniter(schedule["expr"], base_time)
+        cron = croniter(schedule["expr"], now)
         next_run = cron.get_next(datetime)
         return next_run.isoformat()
 
@@ -376,7 +361,7 @@ def save_jobs(jobs: List[Dict[str, Any]]):
             json.dump({"jobs": jobs, "updated_at": _hermes_now().isoformat()}, f, indent=2)
             f.flush()
             os.fsync(f.fileno())
-        atomic_replace(tmp_path, JOBS_FILE)
+        os.replace(tmp_path, JOBS_FILE)
         _secure_file(JOBS_FILE)
     except BaseException:
         try:
@@ -713,32 +698,10 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
                 # Compute next run
                 job["next_run_at"] = compute_next_run(job["schedule"], now)
 
-                # If no next run, decide whether this is terminal completion
-                # (one-shot) or a transient failure (recurring schedule couldn't
-                # compute — e.g. 'croniter' missing from the runtime env).
-                # Recurring jobs must NEVER be silently disabled: that turns a
-                # missing runtime dep into "job completed" and the user's
-                # schedule quietly goes off. See issue #16265.
+                # If no next run (one-shot completed), disable
                 if job["next_run_at"] is None:
-                    kind = job.get("schedule", {}).get("kind")
-                    if kind in ("cron", "interval"):
-                        job["state"] = "error"
-                        if not job.get("last_error"):
-                            job["last_error"] = (
-                                "Failed to compute next run for recurring "
-                                "schedule (is the 'croniter' package "
-                                "installed in the gateway's Python env?)"
-                            )
-                        logger.error(
-                            "Job '%s' (%s) could not compute next_run_at; "
-                            "leaving enabled and marking state=error so the "
-                            "job is not silently disabled.",
-                            job.get("name", job["id"]),
-                            kind,
-                        )
-                    else:
-                        job["enabled"] = False
-                        job["state"] = "completed"
+                    job["enabled"] = False
+                    job["state"] = "completed"
                 elif job.get("state") != "paused":
                     job["state"] = "scheduled"
 
@@ -872,7 +835,7 @@ def save_job_output(job_id: str, output: str):
             f.write(output)
             f.flush()
             os.fsync(f.fileno())
-        atomic_replace(tmp_path, output_file)
+        os.replace(tmp_path, output_file)
         _secure_file(output_file)
     except BaseException:
         try:
@@ -882,121 +845,3 @@ def save_job_output(job_id: str, output: str):
         raise
     
     return output_file
-
-
-# =============================================================================
-# Skill reference rewriting (curator integration)
-# =============================================================================
-
-def rewrite_skill_refs(
-    consolidated: Optional[Dict[str, str]] = None,
-    pruned: Optional[List[str]] = None,
-) -> Dict[str, Any]:
-    """Rewrite cron job skill references after a curator consolidation pass.
-
-    When the curator consolidates a skill X into umbrella Y (or archives X
-    as pruned), any cron job that lists ``X`` in its ``skills`` field will
-    fail to load ``X`` at run time — the scheduler logs a warning and
-    skips the skill, so the job runs without the instructions it was
-    scheduled to follow. See cron/scheduler.py where ``skill_view`` is
-    called per skill name.
-
-    This function repairs cron jobs in-place:
-
-    - A skill listed in ``consolidated`` is replaced with its umbrella
-      target (the ``into`` value). If the umbrella is already in the
-      job's skill list, the stale name is dropped without duplication.
-    - A skill listed in ``pruned`` is dropped outright — there is no
-      forwarding target.
-    - Ordering and other skills in the list are preserved.
-    - The legacy ``skill`` field is realigned via ``_apply_skill_fields``.
-
-    Args:
-        consolidated: mapping of ``old_skill_name -> umbrella_skill_name``.
-        pruned: list of skill names that were archived with no forwarding
-            target.
-
-    Returns a report dict::
-
-        {
-            "rewrites": [
-                {
-                    "job_id": ...,
-                    "job_name": ...,
-                    "before": [...],
-                    "after": [...],
-                    "mapped": {"old": "new", ...},
-                    "dropped": ["old", ...],
-                },
-                ...
-            ],
-            "jobs_updated": N,
-            "jobs_scanned": M,
-        }
-
-    Best-effort: exceptions from loading/saving propagate to the caller so
-    tests can assert behaviour; the curator invocation site wraps this
-    call in a try/except so a failure here never breaks the curator.
-    """
-    consolidated = dict(consolidated or {})
-    pruned_set = set(pruned or [])
-    # A skill listed in both wins as "consolidated" — it has a target,
-    # which is the more useful of the two outcomes.
-    pruned_set -= set(consolidated.keys())
-
-    if not consolidated and not pruned_set:
-        return {"rewrites": [], "jobs_updated": 0, "jobs_scanned": 0}
-
-    with _jobs_file_lock:
-        jobs = load_jobs()
-        rewrites: List[Dict[str, Any]] = []
-        changed = False
-
-        for job in jobs:
-            skills_before = _normalize_skill_list(job.get("skill"), job.get("skills"))
-            if not skills_before:
-                continue
-
-            mapped: Dict[str, str] = {}
-            dropped: List[str] = []
-            new_skills: List[str] = []
-
-            for name in skills_before:
-                if name in consolidated:
-                    target = consolidated[name]
-                    mapped[name] = target
-                    if target and target not in new_skills:
-                        new_skills.append(target)
-                elif name in pruned_set:
-                    dropped.append(name)
-                else:
-                    if name not in new_skills:
-                        new_skills.append(name)
-
-            if not mapped and not dropped:
-                continue
-
-            job["skills"] = new_skills
-            job["skill"] = new_skills[0] if new_skills else None
-            changed = True
-
-            rewrites.append({
-                "job_id": job.get("id"),
-                "job_name": job.get("name") or job.get("id"),
-                "before": list(skills_before),
-                "after": list(new_skills),
-                "mapped": mapped,
-                "dropped": dropped,
-            })
-
-        if changed:
-            save_jobs(jobs)
-            logger.info(
-                "Curator rewrote skill references in %d cron job(s)", len(rewrites)
-            )
-
-        return {
-            "rewrites": rewrites,
-            "jobs_updated": len(rewrites),
-            "jobs_scanned": len(jobs),
-        }

cron/scheduler.py

@@ -77,7 +77,7 @@ _KNOWN_DELIVERY_PLATFORMS = frozenset({
     "telegram", "discord", "slack", "whatsapp", "signal",
     "matrix", "mattermost", "homeassistant", "dingtalk", "feishu",
     "wecom", "wecom_callback", "weixin", "sms", "email", "webhook", "bluebubbles",
-    "qqbot", "yuanbao",
+    "qqbot",
 })
 
 # Platforms that support a configured cron/notification home target, mapped to
@@ -198,9 +198,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
             if resolved:
                 parsed_chat_id, parsed_thread_id, resolved_is_explicit = _parse_target_ref(platform_key, resolved)
                 if resolved_is_explicit:
-                    chat_id = parsed_chat_id
-                    if parsed_thread_id is not None:
-                        thread_id = parsed_thread_id
+                    chat_id, thread_id = parsed_chat_id, parsed_thread_id
                 else:
                     chat_id = resolved
         except Exception:
@@ -233,32 +231,12 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
     }
 
 
-def _normalize_deliver_value(deliver) -> str:
-    """Normalize a stored/submitted ``deliver`` value to its canonical string form.
-
-    The contract is that ``deliver`` is a string (``"local"``, ``"origin"``,
-    ``"telegram"``, ``"telegram:-1001:17"``, or comma-separated combinations).
-    Historically some callers — MCP clients passing an array, direct edits of
-    ``jobs.json``, or stale code paths — have stored a list/tuple like
-    ``["telegram"]``.  ``str(["telegram"])`` would serialize to the literal
-    string ``"['telegram']"``, which is not a known platform and fails
-    resolution silently.  Flatten lists/tuples into a comma-separated string
-    so both forms work.  Returns ``"local"`` for anything falsy.
-    """
-    if deliver is None or deliver == "":
-        return "local"
-    if isinstance(deliver, (list, tuple)):
-        parts = [str(p).strip() for p in deliver if str(p).strip()]
-        return ",".join(parts) if parts else "local"
-    return str(deliver)
-
-
 def _resolve_delivery_targets(job: dict) -> List[dict]:
     """Resolve all concrete auto-delivery targets for a cron job (supports comma-separated deliver)."""
-    deliver = _normalize_deliver_value(job.get("deliver", "local"))
+    deliver = job.get("deliver", "local")
     if deliver == "local":
         return []
-    parts = [p.strip() for p in deliver.split(",") if p.strip()]
+    parts = [p.strip() for p in str(deliver).split(",") if p.strip()]
     seen = set()
     targets = []
     for part in parts:
@@ -277,21 +255,13 @@ def _resolve_delivery_target(job: dict) -> Optional[dict]:
     return targets[0] if targets else None
 
 
-# Media extension sets — audio routing is centralized in gateway.platforms.base
-# via should_send_media_as_audio() so Telegram-specific rules stay in one place.
+# Media extension sets — keep in sync with gateway/platforms/base.py:_process_message_background
+_AUDIO_EXTS = frozenset({'.ogg', '.opus', '.mp3', '.wav', '.m4a'})
 _VIDEO_EXTS = frozenset({'.mp4', '.mov', '.avi', '.mkv', '.webm', '.3gp'})
 _IMAGE_EXTS = frozenset({'.jpg', '.jpeg', '.png', '.webp', '.gif'})
 
 
-def _send_media_via_adapter(
-    adapter,
-    chat_id: str,
-    media_files: list,
-    metadata: dict | None,
-    loop,
-    job: dict,
-    platform=None,
-) -> None:
+def _send_media_via_adapter(adapter, chat_id: str, media_files: list, metadata: dict | None, loop, job: dict) -> None:
     """Send extracted MEDIA files as native platform attachments via a live adapter.
 
     Routes each file to the appropriate adapter method (send_voice, send_image_file,
@@ -300,13 +270,10 @@ def _send_media_via_adapter(
     """
     from pathlib import Path
 
-    from gateway.platforms.base import should_send_media_as_audio
-
     for media_path, _is_voice in media_files:
         try:
             ext = Path(media_path).suffix.lower()
-            route_platform = platform if platform is not None else getattr(adapter, "platform", None)
-            if should_send_media_as_audio(route_platform, ext, is_voice=_is_voice):
+            if ext in _AUDIO_EXTS:
                 coro = adapter.send_voice(chat_id=chat_id, audio_path=media_path, metadata=metadata)
             elif ext in _VIDEO_EXTS:
                 coro = adapter.send_video(chat_id=chat_id, video_path=media_path, metadata=metadata)
@@ -352,6 +319,26 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     from tools.send_message_tool import _send_to_platform
     from gateway.config import load_gateway_config, Platform
 
+    platform_map = {
+        "telegram": Platform.TELEGRAM,
+        "discord": Platform.DISCORD,
+        "slack": Platform.SLACK,
+        "whatsapp": Platform.WHATSAPP,
+        "signal": Platform.SIGNAL,
+        "matrix": Platform.MATRIX,
+        "mattermost": Platform.MATTERMOST,
+        "homeassistant": Platform.HOMEASSISTANT,
+        "dingtalk": Platform.DINGTALK,
+        "feishu": Platform.FEISHU,
+        "wecom": Platform.WECOM,
+        "wecom_callback": Platform.WECOM_CALLBACK,
+        "weixin": Platform.WEIXIN,
+        "email": Platform.EMAIL,
+        "sms": Platform.SMS,
+        "bluebubbles": Platform.BLUEBUBBLES,
+        "qqbot": Platform.QQBOT,
+    }
+
     # Optionally wrap the content with a header/footer so the user knows this
     # is a cron delivery.  Wrapping is on by default; set cron.wrap_response: false
     # in config.yaml for clean output.
@@ -408,23 +395,13 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
                 job["id"], platform_name, chat_id, thread_id,
             )
 
-        # Built-in names resolve to their enum member; plugin platform names
-        # create dynamic members via Platform._missing_().
-        try:
-            platform = Platform(platform_name.lower())
-        except (ValueError, KeyError):
+        platform = platform_map.get(platform_name.lower())
+        if not platform:
             msg = f"unknown platform '{platform_name}'"
             logger.warning("Job '%s': %s", job["id"], msg)
             delivery_errors.append(msg)
             continue
 
-        pconfig = config.platforms.get(platform)
-        if not pconfig or not pconfig.enabled:
-            msg = f"platform '{platform_name}' not configured/enabled"
-            logger.warning("Job '%s': %s", job["id"], msg)
-            delivery_errors.append(msg)
-            continue
-
         # Prefer the live adapter when the gateway is running — this supports E2EE
         # rooms (e.g. Matrix) where the standalone HTTP path cannot encrypt.
         runtime_adapter = (adapters or {}).get(platform)
@@ -455,15 +432,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
 
                 # Send extracted media files as native attachments via the live adapter
                 if adapter_ok and media_files:
-                    _send_media_via_adapter(
-                        runtime_adapter,
-                        chat_id,
-                        media_files,
-                        send_metadata,
-                        loop,
-                        job,
-                        platform=platform,
-                    )
+                    _send_media_via_adapter(runtime_adapter, chat_id, media_files, send_metadata, loop, job)
 
                 if adapter_ok:
                     logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
@@ -475,6 +444,13 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
                 )
 
         if not delivered:
+            pconfig = config.platforms.get(platform)
+            if not pconfig or not pconfig.enabled:
+                msg = f"platform '{platform_name}' not configured/enabled"
+                logger.warning("Job '%s': %s", job["id"], msg)
+                delivery_errors.append(msg)
+                continue
+
             # Standalone path: run the async send in a fresh event loop (safe from any thread)
             coro = _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files)
             try:
@@ -739,7 +715,7 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
     # Always prepend cron execution guidance so the agent knows how
     # delivery works and can suppress delivery when appropriate.
     cron_hint = (
-        "[IMPORTANT: You are running as a scheduled cron job. "
+        "[SYSTEM: You are running as a scheduled cron job. "
         "DELIVERY: Your final response will be automatically delivered "
         "to the user — do NOT use send_message or try to deliver "
         "the output yourself. Just produce your report/output as your "
@@ -775,7 +751,7 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
             parts.append("")
         parts.extend(
             [
-                f'[IMPORTANT: The user has invoked the "{skill_name}" skill, indicating they want you to follow its instructions. The full skill content is loaded below.]',
+                f'[SYSTEM: The user has invoked the "{skill_name}" skill, indicating they want you to follow its instructions. The full skill content is loaded below.]',
                 "",
                 content,
             ]
@@ -783,7 +759,7 @@ def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
 
     if skipped:
         notice = (
-            f"[IMPORTANT: The following skill(s) were listed for this job but could not be found "
+            f"[SYSTEM: The following skill(s) were listed for this job but could not be found "
             f"and were skipped: {', '.join(skipped)}. "
             f"Start your response with a brief notice so the user is aware, e.g.: "
             f"'⚠️ Skill(s) not found and skipped: {', '.join(skipped)}']"
@@ -845,8 +821,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
     logger.info("Running job '%s' (ID: %s)", job_name, job_id)
     logger.info("Prompt: %s", prompt[:100])
 
-    agent = None
-
     # Mark this as a cron session so the approval system can apply cron_mode.
     # This env var is process-wide and persists for the lifetime of the
     # scheduler process — every job this process runs is a cron job.
@@ -861,13 +835,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         chat_id=str(origin["chat_id"]) if origin else "",
         chat_name=origin.get("chat_name", "") if origin else "",
     )
-    _cron_delivery_vars = (
-        "HERMES_CRON_AUTO_DELIVER_PLATFORM",
-        "HERMES_CRON_AUTO_DELIVER_CHAT_ID",
-        "HERMES_CRON_AUTO_DELIVER_THREAD_ID",
-    )
-    for _var_name in _cron_delivery_vars:
-        _VAR_MAP[_var_name].set("")
 
     # Per-job working directory.  When set (and validated at create/update
     # time), we point TERMINAL_CWD at it so:
@@ -906,11 +873,8 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         if delivery_target:
             _VAR_MAP["HERMES_CRON_AUTO_DELIVER_PLATFORM"].set(delivery_target["platform"])
             _VAR_MAP["HERMES_CRON_AUTO_DELIVER_CHAT_ID"].set(str(delivery_target["chat_id"]))
-            _VAR_MAP["HERMES_CRON_AUTO_DELIVER_THREAD_ID"].set(
-                ""
-                if delivery_target.get("thread_id") is None
-                else str(delivery_target["thread_id"])
-            )
+            if delivery_target.get("thread_id") is not None:
+                _VAR_MAP["HERMES_CRON_AUTO_DELIVER_THREAD_ID"].set(str(delivery_target["thread_id"]))
 
         model = job.get("model") or os.getenv("HERMES_MODEL") or ""
 
@@ -1044,12 +1008,10 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             enabled_toolsets=_resolve_cron_enabled_toolsets(job, _cfg),
             disabled_toolsets=["cronjob", "messaging", "clarify"],
             quiet_mode=True,
-            # Cron jobs should always inherit the user's SOUL.md identity from
-            # HERMES_HOME. When a workdir is configured, also inject project
-            # context files (AGENTS.md / CLAUDE.md / .cursorrules) from there.
-            # Without a workdir, keep cwd context discovery disabled.
+            # When a workdir is configured, inject AGENTS.md / CLAUDE.md /
+            # .cursorrules from that directory; otherwise preserve the old
+            # behaviour (don't inject SOUL.md/AGENTS.md from the scheduler cwd).
             skip_context_files=not bool(_job_workdir),
-            load_soul_identity=True,
             skip_memory=True,  # Cron system prompts would corrupt user representations
             platform="cron",
             session_id=_cron_session_id,
@@ -1064,18 +1026,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         #
         # Uses the agent's built-in activity tracker (updated by
         # _touch_activity() on every tool call, API call, and stream delta).
-        _raw_cron_timeout = os.getenv("HERMES_CRON_TIMEOUT", "").strip()
-        if _raw_cron_timeout:
-            try:
-                _cron_timeout = float(_raw_cron_timeout)
-            except (ValueError, TypeError):
-                logger.warning(
-                    "Invalid HERMES_CRON_TIMEOUT=%r; using default 600s",
-                    _raw_cron_timeout,
-                )
-                _cron_timeout = 600.0
-        else:
-            _cron_timeout = 600.0
+        _cron_timeout = float(os.getenv("HERMES_CRON_TIMEOUT", 600))
         _cron_inactivity_limit = _cron_timeout if _cron_timeout > 0 else None
         _POLL_INTERVAL = 5.0
         _cron_pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
@@ -1150,21 +1101,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                 f"agent.run_conversation returned {type(result).__name__} instead of dict: {result!r}"
             )
 
-        # If the agent itself reported failure (e.g. all retries exhausted on
-        # API errors, model abort, mid-run interrupt), do not silently mark the
-        # job as successful. run_agent populates `failed=True`/`completed=False`
-        # on these paths and may put the error into `final_response`, which
-        # would otherwise be delivered as if it were the agent's reply and the
-        # job's `last_status` set to "ok". Raise so the except handler below
-        # builds the proper failure tuple. (issue #17855)
-        if result.get("failed") is True or result.get("completed") is False:
-            _err_text = (
-                result.get("error")
-                or (result.get("final_response") or "").strip()
-                or "agent reported failure"
-            )
-            raise RuntimeError(_err_text)
-
         final_response = result.get("final_response", "") or ""
         # Strip leaked placeholder text that upstream may inject on empty completions.
         if final_response.strip() == "(No response generated)":
@@ -1224,8 +1160,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                 os.environ["TERMINAL_CWD"] = _prior_terminal_cwd
         # Clean up ContextVar session/delivery state for this job.
         clear_session_vars(_ctx_tokens)
-        for _var_name in _cron_delivery_vars:
-            _VAR_MAP[_var_name].set("")
         if _session_db:
             try:
                 _session_db.end_session(_cron_session_id, "cron_complete")
@@ -1235,24 +1169,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                 _session_db.close()
             except (Exception, KeyboardInterrupt) as e:
                 logger.debug("Job '%s': failed to close SQLite session store: %s", job_id, e)
-        # Release subprocesses, terminal sandboxes, browser daemons, and the
-        # main OpenAI/httpx client held by this ephemeral cron agent. Without
-        # this, a gateway that ticks cron every N minutes leaks fds per job
-        # until it hits EMFILE (#10200 / "too many open files").
-        try:
-            if agent is not None:
-                agent.close()
-        except (Exception, KeyboardInterrupt) as e:
-            logger.debug("Job '%s': failed to close agent resources: %s", job_id, e)
-        # Each cron run spins up a short-lived worker thread whose event loop
-        # dies as soon as the ``ThreadPoolExecutor`` shuts down. Any async
-        # httpx clients cached under that loop are now unusable — reap them
-        # so their transports don't accumulate in the process-global cache.
-        try:
-            from agent.auxiliary_client import cleanup_stale_async_clients
-            cleanup_stale_async_clients()
-        except Exception as e:
-            logger.debug("Job '%s': failed to reap stale auxiliary clients: %s", job_id, e)
 
 
 def tick(verbose: bool = True, adapters=None, loop=None) -> int:
@@ -1392,17 +1308,6 @@ def tick(verbose: bool = True, adapters=None, loop=None) -> int:
                     _futures.append(_tick_pool.submit(_ctx.run, _process_job, job))
                 _results.extend(f.result() for f in _futures)
 
-        # Best-effort sweep of MCP stdio subprocesses that survived their
-        # session teardown during this tick.  Runs AFTER every job has
-        # finished so active sessions (including live user chats) are
-        # never touched — only PIDs explicitly detected as orphans in
-        # tools.mcp_tool._run_stdio's finally block are reaped.
-        try:
-            from tools.mcp_tool import _kill_orphaned_mcp_children
-            _kill_orphaned_mcp_children()
-        except Exception as _e:
-            logger.debug("Post-tick MCP orphan cleanup failed: %s", _e)
-
         return sum(_results)
     finally:
         if fcntl:

docker-compose.yml

@@ -34,13 +34,6 @@ services:
       # uncomment BOTH lines (API_SERVER_KEY is mandatory for auth):
       # - API_SERVER_HOST=0.0.0.0
       # - API_SERVER_KEY=${API_SERVER_KEY}
-      # Microsoft Teams — uncomment and fill in to enable Teams gateway.
-      # Register your bot at https://dev.botframework.com/ to get these values.
-      # - TEAMS_CLIENT_ID=${TEAMS_CLIENT_ID}
-      # - TEAMS_CLIENT_SECRET=${TEAMS_CLIENT_SECRET}
-      # - TEAMS_TENANT_ID=${TEAMS_TENANT_ID}
-      # - TEAMS_ALLOWED_USERS=${TEAMS_ALLOWED_USERS}
-      # - TEAMS_PORT=${TEAMS_PORT:-3978}
     command: ["gateway", "run"]
 
   dashboard:

docker/entrypoint.sh

@@ -41,15 +41,6 @@ if [ "$(id -u)" = "0" ]; then
             echo "Warning: chown failed (rootless container?) — continuing anyway"
     fi
 
-    # Ensure config.yaml is readable by the hermes runtime user even if it was
-    # edited on the host after initial ownership setup. Must run here (as root)
-    # rather than after the gosu drop, otherwise a non-root caller like
-    # `docker run -u $(id -u):$(id -g)` hits "Operation not permitted" (#15865).
-    if [ -f "$HERMES_HOME/config.yaml" ]; then
-        chown hermes:hermes "$HERMES_HOME/config.yaml" 2>/dev/null || true
-        chmod 640 "$HERMES_HOME/config.yaml" 2>/dev/null || true
-    fi
-
     echo "Dropping root privileges"
     exec gosu hermes "$0" "$@"
 fi
@@ -76,6 +67,13 @@ if [ ! -f "$HERMES_HOME/config.yaml" ]; then
     cp "$INSTALL_DIR/cli-config.yaml.example" "$HERMES_HOME/config.yaml"
 fi
 
+# Ensure the main config file remains accessible to the hermes runtime user
+# even if it was edited on the host after initial ownership setup.
+if [ -f "$HERMES_HOME/config.yaml" ]; then
+    chown hermes:hermes "$HERMES_HOME/config.yaml"
+    chmod 640 "$HERMES_HOME/config.yaml"
+fi
+
 # SOUL.md
 if [ ! -f "$HERMES_HOME/SOUL.md" ]; then
     cp "$INSTALL_DIR/docker/SOUL.md" "$HERMES_HOME/SOUL.md"

flake.nix

@@ -36,7 +36,6 @@
 
       imports = [
         ./nix/packages.nix
-        ./nix/overlays.nix
         ./nix/nixosModules.nix
         ./nix/checks.nix
         ./nix/devShell.nix

gateway/builtin_hooks/boot_md.py

@@ -0,0 +1,85 @@
+"""Built-in boot-md hook — run ~/.hermes/BOOT.md on gateway startup.
+
+This hook is always registered. It silently skips if no BOOT.md exists.
+To activate, create ``~/.hermes/BOOT.md`` with instructions for the
+agent to execute on every gateway restart.
+
+Example BOOT.md::
+
+    # Startup Checklist
+
+    1. Check if any cron jobs failed overnight
+    2. Send a status update to Discord #general
+    3. If there are errors in /opt/app/deploy.log, summarize them
+
+The agent runs in a background thread so it doesn't block gateway
+startup. If nothing needs attention, it replies with [SILENT] to
+suppress delivery.
+"""
+
+import logging
+import threading
+
+logger = logging.getLogger("hooks.boot-md")
+
+from hermes_constants import get_hermes_home
+HERMES_HOME = get_hermes_home()
+BOOT_FILE = HERMES_HOME / "BOOT.md"
+
+
+def _build_boot_prompt(content: str) -> str:
+    """Wrap BOOT.md content in a system-level instruction."""
+    return (
+        "You are running a startup boot checklist. Follow the BOOT.md "
+        "instructions below exactly.\n\n"
+        "---\n"
+        f"{content}\n"
+        "---\n\n"
+        "Execute each instruction. If you need to send a message to a "
+        "platform, use the send_message tool.\n"
+        "If nothing needs attention and there is nothing to report, "
+        "reply with ONLY: [SILENT]"
+    )
+
+
+def _run_boot_agent(content: str) -> None:
+    """Spawn a one-shot agent session to execute the boot instructions."""
+    try:
+        from run_agent import AIAgent
+
+        prompt = _build_boot_prompt(content)
+        agent = AIAgent(
+            quiet_mode=True,
+            skip_context_files=True,
+            skip_memory=True,
+            max_iterations=20,
+        )
+        result = agent.run_conversation(prompt)
+        response = result.get("final_response", "")
+        if response and "[SILENT]" not in response:
+            logger.info("boot-md completed: %s", response[:200])
+        else:
+            logger.info("boot-md completed (nothing to report)")
+    except Exception as e:
+        logger.error("boot-md agent failed: %s", e)
+
+
+async def handle(event_type: str, context: dict) -> None:
+    """Gateway startup handler — run BOOT.md if it exists."""
+    if not BOOT_FILE.exists():
+        return
+
+    content = BOOT_FILE.read_text(encoding="utf-8").strip()
+    if not content:
+        return
+
+    logger.info("Running BOOT.md (%d chars)", len(content))
+
+    # Run in a background thread so we don't block gateway startup.
+    thread = threading.Thread(
+        target=_run_boot_agent,
+        args=(content,),
+        name="boot-md",
+        daemon=True,
+    )
+    thread.start()

gateway/channel_directory.py

@@ -57,7 +57,7 @@ def _session_entry_name(origin: Dict[str, Any]) -> str:
 # Build / refresh
 # ---------------------------------------------------------------------------
 
-async def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
+def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
     """
     Build a channel directory from connected platform adapters and session data.
 
@@ -72,7 +72,7 @@ async def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
             if platform == Platform.DISCORD:
                 platforms["discord"] = _build_discord(adapter)
             elif platform == Platform.SLACK:
-                platforms["slack"] = await _build_slack(adapter)
+                platforms["slack"] = _build_slack(adapter)
         except Exception as e:
             logger.warning("Channel directory: failed to build %s: %s", platform.value, e)
 
@@ -86,16 +86,6 @@ async def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
             continue
         platforms[plat_name] = _build_from_sessions(plat_name)
 
-    # Include plugin-registered platforms (dynamic enum members aren't in
-    # Platform.__members__, so the loop above misses them).
-    try:
-        from gateway.platform_registry import platform_registry
-        for entry in platform_registry.plugin_entries():
-            if entry.name not in _SKIP_SESSION_DISCOVERY and entry.name not in platforms:
-                platforms[entry.name] = _build_from_sessions(entry.name)
-    except Exception:
-        pass
-
     directory = {
         "updated_at": datetime.now().isoformat(),
         "platforms": platforms,
@@ -146,66 +136,21 @@ def _build_discord(adapter) -> List[Dict[str, str]]:
     return channels
 
 
-async def _build_slack(adapter) -> List[Dict[str, Any]]:
-    """List Slack channels the bot has joined across all workspaces.
-
-    Uses ``users.conversations`` against each workspace's web client. Pulls
-    public + private channels the bot is a member of, then merges in DMs
-    discovered from session history (IMs aren't useful to enumerate
-    proactively).
-    """
-    team_clients = getattr(adapter, "_team_clients", None) or {}
-    if not team_clients:
+def _build_slack(adapter) -> List[Dict[str, str]]:
+    """List Slack channels the bot has joined."""
+    # Slack adapter may expose a web client
+    client = getattr(adapter, "_app", None) or getattr(adapter, "_client", None)
+    if not client:
         return _build_from_sessions("slack")
 
-    channels: List[Dict[str, Any]] = []
-    seen_ids: set = set()
+    try:
+        from tools.send_message_tool import _send_slack  # noqa: F401
+        # Use the Slack Web API directly if available
+    except Exception:
+        pass
 
-    for team_id, client in team_clients.items():
-        try:
-            cursor: Optional[str] = None
-            for _page in range(20):  # safety cap on pagination
-                response = await client.users_conversations(
-                    types="public_channel,private_channel",
-                    exclude_archived=True,
-                    limit=200,
-                    cursor=cursor,
-                )
-                if not response.get("ok"):
-                    logger.warning(
-                        "Channel directory: users.conversations not ok for team %s: %s",
-                        team_id,
-                        response.get("error", "unknown"),
-                    )
-                    break
-                for ch in response.get("channels", []):
-                    cid = ch.get("id")
-                    name = ch.get("name")
-                    if not cid or not name or cid in seen_ids:
-                        continue
-                    seen_ids.add(cid)
-                    channels.append({
-                        "id": cid,
-                        "name": name,
-                        "type": "private" if ch.get("is_private") else "channel",
-                    })
-                cursor = (response.get("response_metadata") or {}).get("next_cursor")
-                if not cursor:
-                    break
-        except Exception as e:
-            logger.warning(
-                "Channel directory: failed to list Slack channels for team %s: %s",
-                team_id, e,
-            )
-            continue
-
-    # Merge in DM/group entries discovered from session history.
-    for entry in _build_from_sessions("slack"):
-        if entry.get("id") not in seen_ids:
-            channels.append(entry)
-            seen_ids.add(entry.get("id"))
-
-    return channels
+    # Fallback to session data
+    return _build_from_sessions("slack")
 
 
 def _build_from_sessions(platform_name: str) -> List[Dict[str, str]]:
@@ -278,14 +223,6 @@ def resolve_channel_name(platform_name: str, name: str) -> Optional[str]:
     if not channels:
         return None
 
-    # 0. Exact ID match — case-sensitive, no normalization. Lets callers pass
-    # raw platform IDs (e.g. Slack "C0B0QV5434G") even when the format guard
-    # in _parse_target_ref hasn't recognized them as explicit.
-    raw = name.strip()
-    for ch in channels:
-        if ch.get("id") == raw:
-            return ch["id"]
-
     query = _normalize_channel_query(name)
 
     # 1. Exact name match, including the display labels shown by send_message(action="list")

gateway/config.py

@@ -13,7 +13,7 @@ import os
 import json
 from pathlib import Path
 from dataclasses import dataclass, field
-from typing import Dict, List, Optional, Any, Callable
+from typing import Dict, List, Optional, Any
 from enum import Enum
 
 from hermes_cli.config import get_hermes_home
@@ -36,26 +36,6 @@ def _coerce_bool(value: Any, default: bool = True) -> bool:
     return is_truthy_value(value, default=default)
 
 
-def _coerce_float(value: Any, default: float) -> float:
-    """Coerce numeric config values, falling back on malformed input."""
-    if value is None:
-        return default
-    try:
-        return float(value)
-    except (TypeError, ValueError):
-        return default
-
-
-def _coerce_int(value: Any, default: int) -> int:
-    """Coerce integer config values, falling back on malformed input."""
-    if value is None:
-        return default
-    try:
-        return int(value)
-    except (TypeError, ValueError):
-        return default
-
-
 def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> str:
     """Normalize unauthorized DM behavior to a supported value."""
     if isinstance(value, str):
@@ -65,28 +45,8 @@ def _normalize_unauthorized_dm_behavior(value: Any, default: str = "pair") -> st
     return default
 
 
-def _normalize_notice_delivery(value: Any, default: str = "public") -> str:
-    """Normalize notice delivery mode to a supported value."""
-    if isinstance(value, str):
-        normalized = value.strip().lower()
-        if normalized in {"public", "private"}:
-            return normalized
-    return default
-
-
-# Module-level cache for bundled platform plugin names (lives outside the
-# enum so it doesn't become an accidental enum member).
-_Platform__bundled_plugin_names: Optional[set] = None
-
-
 class Platform(Enum):
-    """Supported messaging platforms.
-
-    Built-in platforms have explicit members.  Plugin platforms use dynamic
-    members created on-demand by ``_missing_()`` so that
-    ``Platform("irc")`` works without modifying this enum.  Dynamic members
-    are cached in ``_value2member_map_`` for identity-stable comparisons.
-    """
+    """Supported messaging platforms."""
     LOCAL = "local"
     TELEGRAM = "telegram"
     DISCORD = "discord"
@@ -107,77 +67,6 @@ class Platform(Enum):
     WEIXIN = "weixin"
     BLUEBUBBLES = "bluebubbles"
     QQBOT = "qqbot"
-    YUANBAO = "yuanbao"
-    @classmethod
-    def _missing_(cls, value):
-        """Accept unknown platform names only for known plugin adapters.
-
-        Creates a pseudo-member cached in ``_value2member_map_`` so that
-        ``Platform("irc") is Platform("irc")`` holds True (identity-stable).
-        Arbitrary strings are rejected to prevent enum pollution.
-        """
-        if not isinstance(value, str) or not value.strip():
-            return None
-        # Normalise to lowercase to avoid case mismatches in config
-        value = value.strip().lower()
-        # Check cache first (another call may have created it already)
-        if value in cls._value2member_map_:
-            return cls._value2member_map_[value]
-
-        # Only create pseudo-members for bundled plugin platforms (discovered
-        # via filesystem scan) or runtime-registered plugin platforms.
-        global _Platform__bundled_plugin_names
-        if _Platform__bundled_plugin_names is None:
-            _Platform__bundled_plugin_names = cls._scan_bundled_plugin_platforms()
-        if value in _Platform__bundled_plugin_names:
-            pseudo = object.__new__(cls)
-            pseudo._value_ = value
-            pseudo._name_ = value.upper().replace("-", "_").replace(" ", "_")
-            cls._value2member_map_[value] = pseudo
-            cls._member_map_[pseudo._name_] = pseudo
-            return pseudo
-
-        # Runtime-registered plugins (e.g. user-installed, discovered after
-        # the enum was defined).
-        try:
-            from gateway.platform_registry import platform_registry
-            if platform_registry.is_registered(value):
-                pseudo = object.__new__(cls)
-                pseudo._value_ = value
-                pseudo._name_ = value.upper().replace("-", "_").replace(" ", "_")
-                cls._value2member_map_[value] = pseudo
-                cls._member_map_[pseudo._name_] = pseudo
-                return pseudo
-        except Exception:
-            pass
-
-        return None
-
-    @classmethod
-    def _scan_bundled_plugin_platforms(cls) -> set:
-        """Return names of bundled platform plugins under ``plugins/platforms/``."""
-        names: set = set()
-        try:
-            platforms_dir = Path(__file__).parent.parent / "plugins" / "platforms"
-            if platforms_dir.is_dir():
-                for child in platforms_dir.iterdir():
-                    if (
-                        child.is_dir()
-                        and (child / "__init__.py").exists()
-                        and (
-                            (child / "plugin.yaml").exists()
-                            or (child / "plugin.yml").exists()
-                        )
-                    ):
-                        names.add(child.name.lower())
-        except Exception:
-            pass
-        return names
-
-
-# Snapshot of built-in platform values before any dynamic _missing_ lookups.
-# Used to distinguish real platforms from arbitrary strings.
-_BUILTIN_PLATFORM_VALUES = frozenset(m.value for m in Platform.__members__.values())
 
 
 @dataclass
@@ -306,14 +195,6 @@ class StreamingConfig:
     edit_interval: float = 1.0    # Seconds between message edits (Telegram rate-limits at ~1/s)
     buffer_threshold: int = 40    # Chars before forcing an edit
     cursor: str = " ▉"           # Cursor shown during streaming
-    # Ported from openclaw/openclaw#72038.  When >0, the final edit for
-    # a long-running streamed response is delivered as a fresh message
-    # if the original preview has been visible for at least this many
-    # seconds, so the platform's visible timestamp reflects completion
-    # time instead of the preview creation time.  Currently applied to
-    # Telegram only (other platforms ignore the setting).  Default 60s
-    # matches the OpenClaw rollout.  Set to 0 to disable.
-    fresh_final_after_seconds: float = 60.0
 
     def to_dict(self) -> Dict[str, Any]:
         return {
@@ -322,7 +203,6 @@ class StreamingConfig:
             "edit_interval": self.edit_interval,
             "buffer_threshold": self.buffer_threshold,
             "cursor": self.cursor,
-            "fresh_final_after_seconds": self.fresh_final_after_seconds,
         }
 
     @classmethod
@@ -330,55 +210,14 @@ class StreamingConfig:
         if not data:
             return cls()
         return cls(
-            enabled=_coerce_bool(data.get("enabled"), False),
+            enabled=data.get("enabled", False),
             transport=data.get("transport", "edit"),
-            edit_interval=_coerce_float(data.get("edit_interval"), 1.0),
-            buffer_threshold=_coerce_int(data.get("buffer_threshold"), 40),
+            edit_interval=float(data.get("edit_interval", 1.0)),
+            buffer_threshold=int(data.get("buffer_threshold", 40)),
             cursor=data.get("cursor", " ▉"),
-            fresh_final_after_seconds=_coerce_float(
-                data.get("fresh_final_after_seconds"), 60.0
-            ),
         )
 
 
-# -----------------------------------------------------------------------------
-# Built-in platform connection checkers
-# -----------------------------------------------------------------------------
-# Each callable receives a ``PlatformConfig`` and returns ``True`` when the
-# platform is sufficiently configured to be considered "connected".  Platforms
-# that rely on the generic ``token or api_key`` check (Telegram, Discord,
-# Slack, Matrix, Mattermost, HomeAssistant) do not need an entry here.
-_PLATFORM_CONNECTED_CHECKERS: dict[Platform, Callable[[PlatformConfig], bool]] = {
-    Platform.WEIXIN: lambda cfg: bool(
-        cfg.extra.get("account_id") and (cfg.token or cfg.extra.get("token"))
-    ),
-    Platform.WHATSAPP: lambda cfg: True,  # bridge handles auth
-    Platform.SIGNAL: lambda cfg: bool(cfg.extra.get("http_url")),
-    Platform.EMAIL: lambda cfg: bool(cfg.extra.get("address")),
-    Platform.SMS: lambda cfg: bool(os.getenv("TWILIO_ACCOUNT_SID")),
-    Platform.API_SERVER: lambda cfg: True,
-    Platform.WEBHOOK: lambda cfg: True,
-    Platform.FEISHU: lambda cfg: bool(cfg.extra.get("app_id")),
-    Platform.WECOM: lambda cfg: bool(cfg.extra.get("bot_id")),
-    Platform.WECOM_CALLBACK: lambda cfg: bool(
-        cfg.extra.get("corp_id") or cfg.extra.get("apps")
-    ),
-    Platform.BLUEBUBBLES: lambda cfg: bool(
-        cfg.extra.get("server_url") and cfg.extra.get("password")
-    ),
-    Platform.QQBOT: lambda cfg: bool(
-        cfg.extra.get("app_id") and cfg.extra.get("client_secret")
-    ),
-    Platform.YUANBAO: lambda cfg: bool(
-        cfg.extra.get("app_id") and cfg.extra.get("app_secret")
-    ),
-    Platform.DINGTALK: lambda cfg: bool(
-        (cfg.extra.get("client_id") or os.getenv("DINGTALK_CLIENT_ID"))
-        and (cfg.extra.get("client_secret") or os.getenv("DINGTALK_CLIENT_SECRET"))
-    ),
-}
-
-
 @dataclass
 class GatewayConfig:
     """
@@ -432,43 +271,58 @@ class GatewayConfig:
         for platform, config in self.platforms.items():
             if not config.enabled:
                 continue
-            if self._is_platform_connected(platform, config):
+            # Weixin requires both a token and an account_id
+            if platform == Platform.WEIXIN:
+                if config.extra.get("account_id") and (config.token or config.extra.get("token")):
+                    connected.append(platform)
+                continue
+            # Platforms that use token/api_key auth
+            if config.token or config.api_key:
                 connected.append(platform)
+            # WhatsApp uses enabled flag only (bridge handles auth)
+            elif platform == Platform.WHATSAPP:
+                connected.append(platform)
+            # Signal uses extra dict for config (http_url + account)
+            elif platform == Platform.SIGNAL and config.extra.get("http_url"):
+                connected.append(platform)
+            # Email uses extra dict for config (address + imap_host + smtp_host)
+            elif platform == Platform.EMAIL and config.extra.get("address"):
+                connected.append(platform)
+            # SMS uses api_key (Twilio auth token) — SID checked via env
+            elif platform == Platform.SMS and os.getenv("TWILIO_ACCOUNT_SID"):
+                connected.append(platform)
+            # API Server uses enabled flag only (no token needed)
+            elif platform == Platform.API_SERVER:
+                connected.append(platform)
+            # Webhook uses enabled flag only (secrets are per-route)
+            elif platform == Platform.WEBHOOK:
+                connected.append(platform)
+            # Feishu uses extra dict for app credentials
+            elif platform == Platform.FEISHU and config.extra.get("app_id"):
+                connected.append(platform)
+            # WeCom bot mode uses extra dict for bot credentials
+            elif platform == Platform.WECOM and config.extra.get("bot_id"):
+                connected.append(platform)
+            # WeCom callback mode uses corp_id or apps list
+            elif platform == Platform.WECOM_CALLBACK and (
+                config.extra.get("corp_id") or config.extra.get("apps")
+            ):
+                connected.append(platform)
+            # BlueBubbles uses extra dict for local server config
+            elif platform == Platform.BLUEBUBBLES and config.extra.get("server_url") and config.extra.get("password"):
+                connected.append(platform)
+            # QQBot uses extra dict for app credentials
+            elif platform == Platform.QQBOT and config.extra.get("app_id") and config.extra.get("client_secret"):
+                connected.append(platform)
+            # DingTalk uses client_id/client_secret from config.extra or env vars
+            elif platform == Platform.DINGTALK and (
+                config.extra.get("client_id") or os.getenv("DINGTALK_CLIENT_ID")
+            ) and (
+                config.extra.get("client_secret") or os.getenv("DINGTALK_CLIENT_SECRET")
+            ):
+                connected.append(platform)
+        
         return connected
-
-    def _is_platform_connected(self, platform: Platform, config: PlatformConfig) -> bool:
-        """Check whether a single platform is sufficiently configured."""
-        # Weixin requires both a token and an account_id (checked first so
-        # the generic token branch doesn't let it through without account_id).
-        if platform == Platform.WEIXIN:
-            return bool(
-                config.extra.get("account_id")
-                and (config.token or config.extra.get("token"))
-            )
-
-        # Generic token/api_key auth covers Telegram, Discord, Slack, etc.
-        if config.token or config.api_key:
-            return True
-
-        # Platform-specific check
-        checker = _PLATFORM_CONNECTED_CHECKERS.get(platform)
-        if checker is not None:
-            return checker(config)
-
-        # Plugin-registered platforms
-        try:
-            from gateway.platform_registry import platform_registry
-            entry = platform_registry.get(platform.value)
-            if entry:
-                if entry.is_connected is not None:
-                    return entry.is_connected(config)
-                if entry.validate_config is not None:
-                    return entry.validate_config(config)
-                return True
-        except Exception:
-            pass  # Registry not yet initialised during early import
-
-        return False
     
     def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
         """Get the home channel for a platform."""
@@ -601,17 +455,6 @@ class GatewayConfig:
                 )
         return self.unauthorized_dm_behavior
 
-    def get_notice_delivery(self, platform: Optional[Platform] = None) -> str:
-        """Return the effective notice-delivery mode for a platform."""
-        if platform:
-            platform_cfg = self.platforms.get(platform)
-            if platform_cfg and "notice_delivery" in platform_cfg.extra:
-                return _normalize_notice_delivery(
-                    platform_cfg.extra.get("notice_delivery"),
-                    "public",
-                )
-        return "public"
-
 
 def load_gateway_config() -> GatewayConfig:
     """
@@ -707,8 +550,6 @@ def load_gateway_config() -> GatewayConfig:
                         existing = {}
                     # Deep-merge extra dicts so gateway.json defaults survive
                     merged_extra = {**existing.get("extra", {}), **plat_block.get("extra", {})}
-                    if plat_name == Platform.SLACK.value and "enabled" in plat_block:
-                        merged_extra["_enabled_explicit"] = True
                     merged = {**existing, **plat_block}
                     if merged_extra:
                         merged["extra"] = merged_extra
@@ -727,15 +568,8 @@ def load_gateway_config() -> GatewayConfig:
                         platform_cfg.get("unauthorized_dm_behavior"),
                         gw_data.get("unauthorized_dm_behavior", "pair"),
                     )
-                if "notice_delivery" in platform_cfg:
-                    bridged["notice_delivery"] = _normalize_notice_delivery(
-                        platform_cfg.get("notice_delivery"),
-                        "public",
-                    )
                 if "reply_prefix" in platform_cfg:
                     bridged["reply_prefix"] = platform_cfg["reply_prefix"]
-                if "reply_in_thread" in platform_cfg:
-                    bridged["reply_in_thread"] = platform_cfg["reply_in_thread"]
                 if "require_mention" in platform_cfg:
                     bridged["require_mention"] = platform_cfg["require_mention"]
                 if "free_response_channels" in platform_cfg:
@@ -750,7 +584,7 @@ def load_gateway_config() -> GatewayConfig:
                     bridged["group_policy"] = platform_cfg["group_policy"]
                 if "group_allow_from" in platform_cfg:
                     bridged["group_allow_from"] = platform_cfg["group_allow_from"]
-                if plat in (Platform.DISCORD, Platform.SLACK) and "channel_skill_bindings" in platform_cfg:
+                if plat == Platform.DISCORD and "channel_skill_bindings" in platform_cfg:
                     bridged["channel_skill_bindings"] = platform_cfg["channel_skill_bindings"]
                 if "channel_prompts" in platform_cfg:
                     channel_prompts = platform_cfg["channel_prompts"]
@@ -758,21 +592,16 @@ def load_gateway_config() -> GatewayConfig:
                         bridged["channel_prompts"] = {str(k): v for k, v in channel_prompts.items()}
                     else:
                         bridged["channel_prompts"] = channel_prompts
-                enabled_was_explicit = "enabled" in platform_cfg
-                if not bridged and not enabled_was_explicit:
+                if not bridged:
                     continue
                 plat_data = platforms_data.setdefault(plat.value, {})
                 if not isinstance(plat_data, dict):
                     plat_data = {}
                     platforms_data[plat.value] = plat_data
-                if enabled_was_explicit:
-                    plat_data["enabled"] = platform_cfg["enabled"]
                 extra = plat_data.setdefault("extra", {})
                 if not isinstance(extra, dict):
                     extra = {}
                     plat_data["extra"] = extra
-                if plat == Platform.SLACK and enabled_was_explicit:
-                    extra["_enabled_explicit"] = True
                 extra.update(bridged)
 
             # Slack settings → env vars (env vars take precedence)
@@ -780,8 +609,6 @@ def load_gateway_config() -> GatewayConfig:
             if isinstance(slack_cfg, dict):
                 if "require_mention" in slack_cfg and not os.getenv("SLACK_REQUIRE_MENTION"):
                     os.environ["SLACK_REQUIRE_MENTION"] = str(slack_cfg["require_mention"]).lower()
-                if "strict_mention" in slack_cfg and not os.getenv("SLACK_STRICT_MENTION"):
-                    os.environ["SLACK_STRICT_MENTION"] = str(slack_cfg["strict_mention"]).lower()
                 if "allow_bots" in slack_cfg and not os.getenv("SLACK_ALLOW_BOTS"):
                     os.environ["SLACK_ALLOW_BOTS"] = str(slack_cfg["allow_bots"]).lower()
                 frc = slack_cfg.get("free_response_channels")
@@ -860,21 +687,11 @@ def load_gateway_config() -> GatewayConfig:
                     os.environ["TELEGRAM_REACTIONS"] = str(telegram_cfg["reactions"]).lower()
                 if "proxy_url" in telegram_cfg and not os.getenv("TELEGRAM_PROXY"):
                     os.environ["TELEGRAM_PROXY"] = str(telegram_cfg["proxy_url"]).strip()
-                allowed_users = telegram_cfg.get("allow_from")
-                if allowed_users is not None and not os.getenv("TELEGRAM_ALLOWED_USERS"):
-                    if isinstance(allowed_users, list):
-                        allowed_users = ",".join(str(v) for v in allowed_users)
-                    os.environ["TELEGRAM_ALLOWED_USERS"] = str(allowed_users)
-                group_allowed_users = telegram_cfg.get("group_allow_from")
-                if group_allowed_users is not None and not os.getenv("TELEGRAM_GROUP_ALLOWED_USERS"):
-                    if isinstance(group_allowed_users, list):
-                        group_allowed_users = ",".join(str(v) for v in group_allowed_users)
-                    os.environ["TELEGRAM_GROUP_ALLOWED_USERS"] = str(group_allowed_users)
-                group_allowed_chats = telegram_cfg.get("group_allowed_chats")
-                if group_allowed_chats is not None and not os.getenv("TELEGRAM_GROUP_ALLOWED_CHATS"):
-                    if isinstance(group_allowed_chats, list):
-                        group_allowed_chats = ",".join(str(v) for v in group_allowed_chats)
-                    os.environ["TELEGRAM_GROUP_ALLOWED_CHATS"] = str(group_allowed_chats)
+                if "group_allowed_chats" in telegram_cfg and not os.getenv("TELEGRAM_GROUP_ALLOWED_USERS"):
+                    gac = telegram_cfg["group_allowed_chats"]
+                    if isinstance(gac, list):
+                        gac = ",".join(str(v) for v in gac)
+                    os.environ["TELEGRAM_GROUP_ALLOWED_USERS"] = str(gac)
                 if "disable_link_previews" in telegram_cfg:
                     plat_data = platforms_data.setdefault(Platform.TELEGRAM.value, {})
                     if not isinstance(plat_data, dict):
@@ -945,12 +762,6 @@ def load_gateway_config() -> GatewayConfig:
                 if "dm_mention_threads" in matrix_cfg and not os.getenv("MATRIX_DM_MENTION_THREADS"):
                     os.environ["MATRIX_DM_MENTION_THREADS"] = str(matrix_cfg["dm_mention_threads"]).lower()
 
-            # Feishu settings → env vars (env vars take precedence)
-            feishu_cfg = yaml_cfg.get("feishu", {})
-            if isinstance(feishu_cfg, dict):
-                if "allow_bots" in feishu_cfg and not os.getenv("FEISHU_ALLOW_BOTS"):
-                    os.environ["FEISHU_ALLOW_BOTS"] = str(feishu_cfg["allow_bots"]).lower()
-
     except Exception as e:
         logger.warning(
             "Failed to process config.yaml — falling back to .env / gateway.json values. "
@@ -1102,32 +913,13 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         if Platform.WHATSAPP not in config.platforms:
             config.platforms[Platform.WHATSAPP] = PlatformConfig()
         config.platforms[Platform.WHATSAPP].enabled = True
-    whatsapp_home = os.getenv("WHATSAPP_HOME_CHANNEL")
-    if whatsapp_home and Platform.WHATSAPP in config.platforms:
-        config.platforms[Platform.WHATSAPP].home_channel = HomeChannel(
-            platform=Platform.WHATSAPP,
-            chat_id=whatsapp_home,
-            name=os.getenv("WHATSAPP_HOME_CHANNEL_NAME", "Home"),
-        )
-
+    
     # Slack
     slack_token = os.getenv("SLACK_BOT_TOKEN")
     if slack_token:
         if Platform.SLACK not in config.platforms:
-            # No yaml config for Slack — env-only setup, enable it
             config.platforms[Platform.SLACK] = PlatformConfig()
-            config.platforms[Platform.SLACK].enabled = True
-        else:
-            slack_config = config.platforms[Platform.SLACK]
-            enabled_was_explicit = bool(slack_config.extra.pop("_enabled_explicit", False))
-            if not slack_config.enabled and not enabled_was_explicit:
-                # Top-level Slack settings such as channel prompts should not
-                # turn an env-token setup into a disabled platform. Only an
-                # explicit slack.enabled/platforms.slack.enabled false should.
-                slack_config.enabled = True
-        # If yaml config exists, respect its enabled flag (don't override
-        # explicit enabled: false). Token is still stored so skills that
-        # send Slack messages can use it without activating the gateway adapter.
+        config.platforms[Platform.SLACK].enabled = True
         config.platforms[Platform.SLACK].token = slack_token
     slack_home = os.getenv("SLACK_HOME_CHANNEL")
     if slack_home and Platform.SLACK in config.platforms:
@@ -1484,48 +1276,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 name=os.getenv("QQBOT_HOME_CHANNEL_NAME") or os.getenv(qq_home_name_env, "Home"),
             )
 
-    # Yuanbao — YUANBAO_APP_ID preferred
-    yuanbao_app_id = os.getenv("YUANBAO_APP_ID") or os.getenv("YUANBAO_APP_KEY")
-    yuanbao_app_secret = os.getenv("YUANBAO_APP_SECRET")
-    if yuanbao_app_id and yuanbao_app_secret:
-        if Platform.YUANBAO not in config.platforms:
-            config.platforms[Platform.YUANBAO] = PlatformConfig()
-        config.platforms[Platform.YUANBAO].enabled = True
-        extra = config.platforms[Platform.YUANBAO].extra
-        extra["app_id"] = yuanbao_app_id
-        extra["app_secret"] = yuanbao_app_secret
-        yuanbao_bot_id = os.getenv("YUANBAO_BOT_ID")
-        if yuanbao_bot_id:
-            extra["bot_id"] = yuanbao_bot_id
-        yuanbao_ws_url = os.getenv("YUANBAO_WS_URL")
-        if yuanbao_ws_url:
-            extra["ws_url"] = yuanbao_ws_url
-        yuanbao_api_domain = os.getenv("YUANBAO_API_DOMAIN")
-        if yuanbao_api_domain:
-            extra["api_domain"] = yuanbao_api_domain
-        yuanbao_route_env = os.getenv("YUANBAO_ROUTE_ENV")
-        if yuanbao_route_env:
-            extra["route_env"] = yuanbao_route_env
-        yuanbao_home = os.getenv("YUANBAO_HOME_CHANNEL")
-        if yuanbao_home:
-            config.platforms[Platform.YUANBAO].home_channel = HomeChannel(
-                platform=Platform.YUANBAO,
-                chat_id=yuanbao_home,
-                name=os.getenv("YUANBAO_HOME_CHANNEL_NAME", "Home"),
-            )
-        yuanbao_dm_policy = os.getenv("YUANBAO_DM_POLICY")
-        if yuanbao_dm_policy:
-            extra["dm_policy"] = yuanbao_dm_policy.strip().lower()
-        yuanbao_dm_allow_from = os.getenv("YUANBAO_DM_ALLOW_FROM")
-        if yuanbao_dm_allow_from:
-            extra["dm_allow_from"] = yuanbao_dm_allow_from
-        yuanbao_group_policy = os.getenv("YUANBAO_GROUP_POLICY")
-        if yuanbao_group_policy:
-            extra["group_policy"] = yuanbao_group_policy.strip().lower()
-        yuanbao_group_allow_from = os.getenv("YUANBAO_GROUP_ALLOW_FROM")
-        if yuanbao_group_allow_from:
-            extra["group_allow_from"] = yuanbao_group_allow_from
-
     # Session settings
     idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
     if idle_minutes:
@@ -1540,25 +1290,3 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
             config.default_reset_policy.at_hour = int(reset_hour)
         except ValueError:
             pass
-
-    # Registry-driven enable for plugin platforms.  Built-ins have explicit
-    # blocks above; plugins expose check_fn() which is the single source of
-    # truth for "are my env vars set?".  When it returns True, ensure the
-    # platform is enabled so start() will create its adapter.
-    try:
-        from hermes_cli.plugins import discover_plugins
-        discover_plugins()  # idempotent
-        from gateway.platform_registry import platform_registry
-        for entry in platform_registry.plugin_entries():
-            try:
-                if not entry.check_fn():
-                    continue
-            except Exception as e:
-                logger.debug("check_fn for %s raised: %s", entry.name, e)
-                continue
-            platform = Platform(entry.name)
-            if platform not in config.platforms:
-                config.platforms[platform] = PlatformConfig()
-            config.platforms[platform].enabled = True
-    except Exception as e:
-        logger.debug("Plugin platform enable pass failed: %s", e)

gateway/delivery.py

@@ -53,10 +53,9 @@ class DeliveryTarget:
         - "telegram" → Telegram home channel
         - "telegram:123456" → specific Telegram chat
         """
-        target_stripped = target.strip()
-        target_lower = target_stripped.lower()
+        target = target.strip().lower()
         
-        if target_lower == "origin":
+        if target == "origin":
             if origin:
                 return cls(
                     platform=origin.platform,
@@ -68,14 +67,13 @@ class DeliveryTarget:
                 # Fallback to local if no origin
                 return cls(platform=Platform.LOCAL, is_origin=True)
         
-        if target_lower == "local":
+        if target == "local":
             return cls(platform=Platform.LOCAL)
         
         # Check for platform:chat_id or platform:chat_id:thread_id format
-        # Use the original case for chat_id/thread_id to preserve case-sensitive IDs
-        if ":" in target_stripped:
-            parts = target_stripped.split(":", 2)
-            platform_str = parts[0].lower()  # Platform names are case-insensitive
+        if ":" in target:
+            parts = target.split(":", 2)
+            platform_str = parts[0]
             chat_id = parts[1] if len(parts) > 1 else None
             thread_id = parts[2] if len(parts) > 2 else None
             try:
@@ -87,7 +85,7 @@ class DeliveryTarget:
         
         # Just a platform name (use home channel)
         try:
-            platform = Platform(target_lower)
+            platform = Platform(target)
             return cls(platform=platform)
         except ValueError:
             # Unknown platform, treat as local

gateway/display_config.py

@@ -79,9 +79,7 @@ _PLATFORM_DEFAULTS: dict[str, dict[str, Any]] = {
     "discord":     _TIER_HIGH,
 
     # Tier 2 — edit support, often customer/workspace channels
-    # Slack: tool_progress off by default — Bolt posts cannot be edited like CLI;
-    # "new"/"all" spam permanent lines in channels (hermes-agent#14663).
-    "slack":           {**_TIER_MEDIUM, "tool_progress": "off"},
+    "slack":           _TIER_MEDIUM,
     "mattermost":      _TIER_MEDIUM,
     "matrix":          _TIER_MEDIUM,
     "feishu":          _TIER_MEDIUM,

gateway/hooks.py

@@ -21,7 +21,6 @@ Errors in hooks are caught and logged but never block the main pipeline.
 
 import asyncio
 import importlib.util
-import sys
 from typing import Any, Callable, Dict, List, Optional
 
 import yaml
@@ -53,13 +52,19 @@ class HookRegistry:
         return list(self._loaded_hooks)
 
     def _register_builtin_hooks(self) -> None:
-        """Register built-in hooks that are always active.
+        """Register built-in hooks that are always active."""
+        try:
+            from gateway.builtin_hooks.boot_md import handle as boot_md_handle
 
-        Currently empty — no shipped built-in hooks. Kept as the extension
-        point for future always-on gateway hooks so they drop in without
-        re-plumbing discover_and_load().
-        """
-        return
+            self._handlers.setdefault("gateway:startup", []).append(boot_md_handle)
+            self._loaded_hooks.append({
+                "name": "boot-md",
+                "description": "Run ~/.hermes/BOOT.md on gateway startup",
+                "events": ["gateway:startup"],
+                "path": "(builtin)",
+            })
+        except Exception as e:
+            print(f"[hooks] Could not load built-in boot-md hook: {e}", flush=True)
 
     def discover_and_load(self) -> None:
         """
@@ -98,28 +103,16 @@ class HookRegistry:
                     print(f"[hooks] Skipping {hook_name}: no events declared", flush=True)
                     continue
 
-                # Dynamically load the handler module.
-                # Register in sys.modules BEFORE exec_module so Pydantic /
-                # dataclasses / typing introspection can resolve forward
-                # references (triggered by `from __future__ import annotations`
-                # in the handler). Without this, a handler that declares a
-                # Pydantic BaseModel for webhook/event payloads fails at first
-                # dispatch with "TypeAdapter ... is not fully defined".
-                module_name = f"hermes_hook_{hook_name}"
+                # Dynamically load the handler module
                 spec = importlib.util.spec_from_file_location(
-                    module_name, handler_path
+                    f"hermes_hook_{hook_name}", handler_path
                 )
                 if spec is None or spec.loader is None:
                     print(f"[hooks] Skipping {hook_name}: could not load handler.py", flush=True)
                     continue
 
                 module = importlib.util.module_from_spec(spec)
-                sys.modules[module_name] = module
-                try:
-                    spec.loader.exec_module(module)
-                except Exception:
-                    sys.modules.pop(module_name, None)
-                    raise
+                spec.loader.exec_module(module)
 
                 handle_fn = getattr(module, "handle", None)
                 if handle_fn is None:

gateway/mirror.py

@@ -28,7 +28,6 @@ def mirror_to_session(
     message_text: str,
     source_label: str = "cli",
     thread_id: Optional[str] = None,
-    user_id: Optional[str] = None,
 ) -> bool:
     """
     Append a delivery-mirror message to the target session's transcript.
@@ -40,20 +39,9 @@ def mirror_to_session(
     All errors are caught -- this is never fatal.
     """
     try:
-        session_id = _find_session_id(
-            platform,
-            str(chat_id),
-            thread_id=thread_id,
-            user_id=user_id,
-        )
+        session_id = _find_session_id(platform, str(chat_id), thread_id=thread_id)
         if not session_id:
-            logger.debug(
-                "Mirror: no session found for %s:%s:%s:%s",
-                platform,
-                chat_id,
-                thread_id,
-                user_id,
-            )
+            logger.debug("Mirror: no session found for %s:%s:%s", platform, chat_id, thread_id)
             return False
 
         mirror_msg = {
@@ -71,33 +59,17 @@ def mirror_to_session(
         return True
 
     except Exception as e:
-        logger.debug(
-            "Mirror failed for %s:%s:%s:%s: %s",
-            platform,
-            chat_id,
-            thread_id,
-            user_id,
-            e,
-        )
+        logger.debug("Mirror failed for %s:%s:%s: %s", platform, chat_id, thread_id, e)
         return False
 
 
-def _find_session_id(
-    platform: str,
-    chat_id: str,
-    thread_id: Optional[str] = None,
-    user_id: Optional[str] = None,
-) -> Optional[str]:
+def _find_session_id(platform: str, chat_id: str, thread_id: Optional[str] = None) -> Optional[str]:
     """
     Find the active session_id for a platform + chat_id pair.
 
     Scans sessions.json entries and matches where origin.chat_id == chat_id
     on the right platform.  DM session keys don't embed the chat_id
     (e.g. "agent:main:telegram:dm"), so we check the origin dict.
-
-    When *user_id* is provided, prefer exact sender matches. If multiple
-    same-chat candidates exist and none matches the user, return None instead
-    of guessing and contaminating another participant's session.
     """
     if not _SESSIONS_INDEX.exists():
         return None
@@ -109,7 +81,8 @@ def _find_session_id(
         return None
 
     platform_lower = platform.lower()
-    candidates = []
+    best_match = None
+    best_updated = ""
 
     for _key, entry in data.items():
         origin = entry.get("origin") or {}
@@ -123,31 +96,12 @@ def _find_session_id(
             origin_thread_id = origin.get("thread_id")
             if thread_id is not None and str(origin_thread_id or "") != str(thread_id):
                 continue
-            candidates.append(entry)
+            updated = entry.get("updated_at", "")
+            if updated > best_updated:
+                best_updated = updated
+                best_match = entry.get("session_id")
 
-    if not candidates:
-        return None
-
-    if user_id:
-        exact_user_matches = [
-            entry for entry in candidates
-            if str((entry.get("origin") or {}).get("user_id") or "") == str(user_id)
-        ]
-        if exact_user_matches:
-            candidates = exact_user_matches
-        elif len(candidates) > 1:
-            return None
-    elif len(candidates) > 1:
-        distinct_user_ids = {
-            str((entry.get("origin") or {}).get("user_id") or "").strip()
-            for entry in candidates
-            if str((entry.get("origin") or {}).get("user_id") or "").strip()
-        }
-        if len(distinct_user_ids) > 1:
-            return None
-
-    best_entry = max(candidates, key=lambda entry: entry.get("updated_at", ""))
-    return best_entry.get("session_id")
+    return best_match
 
 
 def _append_to_jsonl(session_id: str, message: dict) -> None:

gateway/pairing.py

@@ -28,7 +28,6 @@ from pathlib import Path
 from typing import Optional
 
 from hermes_constants import get_hermes_dir
-from utils import atomic_replace
 
 
 # Unambiguous alphabet -- excludes 0/O, 1/I to prevent confusion
@@ -60,7 +59,7 @@ def _secure_write(path: Path, data: str) -> None:
             f.write(data)
             f.flush()
             os.fsync(f.fileno())
-        atomic_replace(tmp_path, path)
+        os.replace(tmp_path, str(path))
         try:
             os.chmod(path, 0o600)
         except OSError:

gateway/platform_registry.py

@@ -1,212 +0,0 @@
-"""
-Platform Adapter Registry
-
-Allows platform adapters (built-in and plugin) to self-register so the gateway
-can discover and instantiate them without hardcoded if/elif chains.
-
-Built-in adapters continue to use the existing if/elif in _create_adapter()
-for now.  Plugin adapters register here via PluginContext.register_platform()
-and are looked up first -- if nothing is found the gateway falls through to
-the legacy code path.
-
-Usage (plugin side):
-
-    from gateway.platform_registry import platform_registry, PlatformEntry
-
-    platform_registry.register(PlatformEntry(
-        name="irc",
-        label="IRC",
-        adapter_factory=lambda cfg: IRCAdapter(cfg),
-        check_fn=check_requirements,
-        validate_config=lambda cfg: bool(cfg.extra.get("server")),
-        required_env=["IRC_SERVER"],
-        install_hint="pip install irc",
-    ))
-
-Usage (gateway side):
-
-    adapter = platform_registry.create_adapter("irc", platform_config)
-"""
-
-import logging
-from dataclasses import dataclass, field
-from typing import Any, Callable, Optional
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class PlatformEntry:
-    """Metadata and factory for a single platform adapter."""
-
-    # Identifier used in config.yaml (e.g. "irc", "viber").
-    name: str
-
-    # Human-readable label (e.g. "IRC", "Viber").
-    label: str
-
-    # Factory callable: receives a PlatformConfig, returns an adapter instance.
-    # Using a factory instead of a bare class lets plugins do custom init
-    # (e.g. passing extra kwargs, wrapping in try/except).
-    adapter_factory: Callable[[Any], Any]
-
-    # Returns True when the platform's dependencies are available.
-    check_fn: Callable[[], bool]
-
-    # Optional: given a PlatformConfig, is it properly configured?
-    # If None, the registry skips config validation and lets the adapter
-    # fail at connect() time with a descriptive error.
-    validate_config: Optional[Callable[[Any], bool]] = None
-
-    # Optional: given a PlatformConfig, is the platform connected/enabled?
-    # Used by ``GatewayConfig.get_connected_platforms()`` and setup UI status.
-    # If None, falls back to ``validate_config`` or ``check_fn``.
-    is_connected: Optional[Callable[[Any], bool]] = None
-
-    # Env vars this platform needs (for ``hermes setup`` display).
-    required_env: list = field(default_factory=list)
-
-    # Hint shown when check_fn returns False.
-    install_hint: str = ""
-
-    # Optional setup function for interactive configuration.
-    # Signature: () -> None (prompts user, saves env vars).
-    # If None, falls back to _setup_standard_platform (needs token_var + vars)
-    # or a generic "set these env vars" display.
-    setup_fn: Optional[Callable[[], None]] = None
-
-    # "builtin" or "plugin"
-    source: str = "plugin"
-
-    # Name of the plugin manifest that registered this entry (empty for
-    # built-ins).  Used by ``hermes gateway setup`` to auto-enable the
-    # owning plugin when the user configures its platform.
-    plugin_name: str = ""
-
-    # ── Auth env var names (for _is_user_authorized integration) ──
-    # E.g. "IRC_ALLOWED_USERS" — checked for comma-separated user IDs.
-    allowed_users_env: str = ""
-    # E.g. "IRC_ALLOW_ALL_USERS" — if truthy, all users authorized.
-    allow_all_env: str = ""
-
-    # ── Message limits ──
-    # Max message length for smart-chunking.  0 = no limit.
-    max_message_length: int = 0
-
-    # ── Privacy ──
-    # If True, session descriptions redact PII (phone numbers, etc.)
-    pii_safe: bool = False
-
-    # ── Display ──
-    # Emoji for CLI/gateway display (e.g. "💬")
-    emoji: str = "🔌"
-
-    # Whether this platform should appear in _UPDATE_ALLOWED_PLATFORMS
-    # (allows /update command from this platform).
-    allow_update_command: bool = True
-
-    # ── LLM guidance ──
-    # Platform hint injected into the system prompt (e.g. "You are on IRC.
-    # Do not use markdown.").  Empty string = no hint.
-    platform_hint: str = ""
-
-
-class PlatformRegistry:
-    """Central registry of platform adapters.
-
-    Thread-safe for reads (dict lookups are atomic under GIL).
-    Writes happen at startup during sequential discovery.
-    """
-
-    def __init__(self) -> None:
-        self._entries: dict[str, PlatformEntry] = {}
-
-    def register(self, entry: PlatformEntry) -> None:
-        """Register a platform adapter entry.
-
-        If an entry with the same name exists, it is replaced (last writer
-        wins -- this lets plugins override built-in adapters if desired).
-        """
-        if entry.name in self._entries:
-            prev = self._entries[entry.name]
-            logger.info(
-                "Platform '%s' re-registered (was %s, now %s)",
-                entry.name,
-                prev.source,
-                entry.source,
-            )
-        self._entries[entry.name] = entry
-        logger.debug("Registered platform adapter: %s (%s)", entry.name, entry.source)
-
-    def unregister(self, name: str) -> bool:
-        """Remove a platform entry.  Returns True if it existed."""
-        return self._entries.pop(name, None) is not None
-
-    def get(self, name: str) -> Optional[PlatformEntry]:
-        """Look up a platform entry by name."""
-        return self._entries.get(name)
-
-    def all_entries(self) -> list[PlatformEntry]:
-        """Return all registered platform entries."""
-        return list(self._entries.values())
-
-    def plugin_entries(self) -> list[PlatformEntry]:
-        """Return only plugin-registered platform entries."""
-        return [e for e in self._entries.values() if e.source == "plugin"]
-
-    def is_registered(self, name: str) -> bool:
-        return name in self._entries
-
-    def create_adapter(self, name: str, config: Any) -> Optional[Any]:
-        """Create an adapter instance for the given platform name.
-
-        Returns None if:
-        - No entry registered for *name*
-        - check_fn() returns False (missing deps)
-        - validate_config() returns False (misconfigured)
-        - The factory raises an exception
-        """
-        entry = self._entries.get(name)
-        if entry is None:
-            return None
-
-        if not entry.check_fn():
-            hint = f" ({entry.install_hint})" if entry.install_hint else ""
-            logger.warning(
-                "Platform '%s' requirements not met%s",
-                entry.label,
-                hint,
-            )
-            return None
-
-        if entry.validate_config is not None:
-            try:
-                if not entry.validate_config(config):
-                    logger.warning(
-                        "Platform '%s' config validation failed",
-                        entry.label,
-                    )
-                    return None
-            except Exception as e:
-                logger.warning(
-                    "Platform '%s' config validation error: %s",
-                    entry.label,
-                    e,
-                )
-                return None
-
-        try:
-            adapter = entry.adapter_factory(config)
-            return adapter
-        except Exception as e:
-            logger.error(
-                "Failed to create adapter for platform '%s': %s",
-                entry.label,
-                e,
-                exc_info=True,
-            )
-            return None
-
-
-# Module-level singleton
-platform_registry = PlatformRegistry()

gateway/platforms/ADDING_A_PLATFORM.md

@@ -1,30 +1,9 @@
 # Adding a New Messaging Platform
 
-There are two ways to add a platform to the Hermes gateway:
-
-## Plugin Path (Recommended for Community/Third-Party)
-
-Create a plugin directory in `~/.hermes/plugins/` with a `PLUGIN.yaml` and
-`adapter.py`.  The adapter inherits from `BasePlatformAdapter` and registers
-via `ctx.register_platform()` in the `register(ctx)` entry point.  This
-requires **zero changes to core Hermes code**.
-
-The plugin system automatically handles: adapter creation, config parsing,
-user authorization, cron delivery, send_message routing, system prompt hints,
-status display, gateway setup, and more.
-
-See `plugins/platforms/irc/` for a complete reference implementation, and
-`website/docs/developer-guide/adding-platform-adapters.md` for the full
-plugin guide with code examples.
-
----
-
-## Built-in Path (Core Contributors Only)
-
-Checklist for integrating a platform directly into the Hermes core.
-Use this as a reference when building a built-in adapter — every item here
-is a real integration point. Missing any of them will cause broken
-functionality, missing features, or inconsistent behavior.
+Checklist for integrating a new messaging platform into the Hermes gateway.
+Use this as a reference when building a new adapter — every item here is a
+real integration point that exists in the codebase. Missing any of them will
+cause broken functionality, missing features, or inconsistent behavior.
 
 ---
 

gateway/platforms/__init__.py

@@ -10,12 +10,10 @@ Each adapter handles:
 
 from .base import BasePlatformAdapter, MessageEvent, SendResult
 from .qqbot import QQAdapter
-from .yuanbao import YuanbaoAdapter
 
 __all__ = [
     "BasePlatformAdapter",
     "MessageEvent",
     "SendResult",
     "QQAdapter",
-    "YuanbaoAdapter",
 ]

gateway/platforms/api_server.py

@@ -7,11 +7,8 @@ Exposes an HTTP server with endpoints:
 - GET  /v1/responses/{response_id} — Retrieve a stored response
 - DELETE /v1/responses/{response_id} — Delete a stored response
 - GET  /v1/models                  — lists hermes-agent as an available model
-- GET  /v1/capabilities            — machine-readable API capabilities for external UIs
 - POST /v1/runs                    — start a run, returns run_id immediately (202)
-- GET  /v1/runs/{run_id}           — retrieve current run status
 - GET  /v1/runs/{run_id}/events    — SSE stream of structured lifecycle events
-- POST /v1/runs/{run_id}/stop    — interrupt a running agent
 - GET  /health                     — health check
 - GET  /health/detailed            — rich status for cross-container dashboard probing
 
@@ -589,11 +586,6 @@ class APIServerAdapter(BasePlatformAdapter):
         self._run_streams: Dict[str, "asyncio.Queue[Optional[Dict]]"] = {}
         # Creation timestamps for orphaned-run TTL sweep
         self._run_streams_created: Dict[str, float] = {}
-        # Active run agent/task references for stop support
-        self._active_run_agents: Dict[str, Any] = {}
-        self._active_run_tasks: Dict[str, "asyncio.Task"] = {}
-        # Pollable run status for dashboards and external control-plane UIs.
-        self._run_statuses: Dict[str, Dict[str, Any]] = {}
         self._session_db: Optional[Any] = None  # Lazy-init SessionDB for session continuity
 
     @staticmethod
@@ -812,51 +804,6 @@ class APIServerAdapter(BasePlatformAdapter):
             ],
         })
 
-    async def _handle_capabilities(self, request: "web.Request") -> "web.Response":
-        """GET /v1/capabilities — advertise the stable API surface.
-
-        External UIs and orchestrators use this endpoint to discover the API
-        server's plugin-safe contract without scraping docs or assuming that
-        every Hermes version exposes the same endpoints.
-        """
-        auth_err = self._check_auth(request)
-        if auth_err:
-            return auth_err
-
-        return web.json_response({
-            "object": "hermes.api_server.capabilities",
-            "platform": "hermes-agent",
-            "model": self._model_name,
-            "auth": {
-                "type": "bearer",
-                "required": bool(self._api_key),
-            },
-            "features": {
-                "chat_completions": True,
-                "chat_completions_streaming": True,
-                "responses_api": True,
-                "responses_streaming": True,
-                "run_submission": True,
-                "run_status": True,
-                "run_events_sse": True,
-                "run_stop": True,
-                "tool_progress_events": True,
-                "session_continuity_header": "X-Hermes-Session-Id",
-                "cors": bool(self._cors_origins),
-            },
-            "endpoints": {
-                "health": {"method": "GET", "path": "/health"},
-                "health_detailed": {"method": "GET", "path": "/health/detailed"},
-                "models": {"method": "GET", "path": "/v1/models"},
-                "chat_completions": {"method": "POST", "path": "/v1/chat/completions"},
-                "responses": {"method": "POST", "path": "/v1/responses"},
-                "runs": {"method": "POST", "path": "/v1/runs"},
-                "run_status": {"method": "GET", "path": "/v1/runs/{run_id}"},
-                "run_events": {"method": "GET", "path": "/v1/runs/{run_id}/events"},
-                "run_stop": {"method": "POST", "path": "/v1/runs/{run_id}/stop"},
-            },
-        })
-
     async def _handle_chat_completions(self, request: "web.Request") -> "web.Response":
         """POST /v1/chat/completions — OpenAI Chat Completions format."""
         auth_err = self._check_auth(request)
@@ -981,62 +928,39 @@ class APIServerAdapter(BasePlatformAdapter):
                 if delta is not None:
                     _stream_q.put(delta)
 
-            # Track which tool_call_ids we've emitted a "running" lifecycle
-            # event for, so a "completed" event without a matching "running"
-            # (e.g. internal/filtered tools) is silently dropped instead of
-            # producing an orphaned event clients can't correlate.
-            _started_tool_call_ids: set[str] = set()
+            def _on_tool_progress(event_type, name, preview, args, **kwargs):
+                """Send tool progress as a separate SSE event.
 
-            def _on_tool_start(tool_call_id, function_name, function_args):
-                """Emit ``hermes.tool.progress`` with ``status: running``.
+                Previously, progress markers like ``⏰ list`` were injected
+                directly into ``delta.content``.  OpenAI-compatible frontends
+                (Open WebUI, LobeChat, …) store ``delta.content`` verbatim as
+                the assistant message and send it back on subsequent requests.
+                After enough turns the model learns to *emit* the markers as
+                plain text instead of issuing real tool calls — silently
+                hallucinating tool results.  See #6972.
 
-                Replaces the old ``tool_progress_callback("tool.started",
-                ...)`` emit so SSE consumers receive a single event per
-                tool start, carrying both the legacy ``tool``/``emoji``/
-                ``label`` payload (for #6972 frontends) and the new
-                ``toolCallId``/``status`` correlation fields (#16588).
-
-                Skips tools whose names start with ``_`` so internal
-                events (``_thinking``, …) stay off the wire — matching
-                the prior ``_on_tool_progress`` filter exactly.
+                The fix: push a tagged tuple ``("__tool_progress__", payload)``
+                onto the stream queue.  The SSE writer emits it as a custom
+                ``event: hermes.tool.progress`` line that compliant frontends
+                can render for UX but will *not* persist into conversation
+                history.  Clients that don't understand the custom event type
+                silently ignore it per the SSE specification.
                 """
-                if not tool_call_id or function_name.startswith("_"):
+                if event_type != "tool.started":
                     return
-                _started_tool_call_ids.add(tool_call_id)
-                from agent.display import build_tool_preview, get_tool_emoji
-                label = build_tool_preview(function_name, function_args) or function_name
+                if name.startswith("_"):
+                    return
+                from agent.display import get_tool_emoji
+                emoji = get_tool_emoji(name)
+                label = preview or name
                 _stream_q.put(("__tool_progress__", {
-                    "tool": function_name,
-                    "emoji": get_tool_emoji(function_name),
+                    "tool": name,
+                    "emoji": emoji,
                     "label": label,
-                    "toolCallId": tool_call_id,
-                    "status": "running",
-                }))
-
-            def _on_tool_complete(tool_call_id, function_name, function_args, function_result):
-                """Emit the matching ``status: completed`` event.
-
-                Dropped if the start was filtered (internal tool, missing
-                id, or never seen) so clients never get an orphaned
-                ``completed`` they can't correlate to a prior ``running``.
-                """
-                if not tool_call_id or tool_call_id not in _started_tool_call_ids:
-                    return
-                _started_tool_call_ids.discard(tool_call_id)
-                _stream_q.put(("__tool_progress__", {
-                    "tool": function_name,
-                    "toolCallId": tool_call_id,
-                    "status": "completed",
                 }))
 
             # Start agent in background.  agent_ref is a mutable container
             # so the SSE writer can interrupt the agent on client disconnect.
-            #
-            # ``tool_progress_callback`` is intentionally not wired here:
-            # it would duplicate every emit because ``run_agent`` fires it
-            # side-by-side with ``tool_start_callback``/``tool_complete_callback``.
-            # The structured callbacks are strictly richer (they carry the
-            # tool_call id), so they own the chat-completions SSE channel.
             agent_ref = [None]
             agent_task = asyncio.ensure_future(self._run_agent(
                 user_message=user_message,
@@ -1044,8 +968,7 @@ class APIServerAdapter(BasePlatformAdapter):
                 ephemeral_system_prompt=system_prompt,
                 session_id=session_id,
                 stream_delta_callback=_on_delta,
-                tool_start_callback=_on_tool_start,
-                tool_complete_callback=_on_tool_complete,
+                tool_progress_callback=_on_tool_progress,
                 agent_ref=agent_ref,
             ))
 
@@ -1160,8 +1083,7 @@ class APIServerAdapter(BasePlatformAdapter):
                 Tagged tuples ``("__tool_progress__", payload)`` are sent
                 as a custom ``event: hermes.tool.progress`` SSE event so
                 frontends can display them without storing the markers in
-                conversation history.  See #6972 for the original event,
-                #16588 for the ``toolCallId``/``status`` lifecycle fields.
+                conversation history.  See #6972.
                 """
                 if isinstance(item, tuple) and len(item) == 2 and item[0] == "__tool_progress__":
                     event_data = json.dumps(item[1])
@@ -2351,11 +2273,10 @@ class APIServerAdapter(BasePlatformAdapter):
             )
             if agent_ref is not None:
                 agent_ref[0] = agent
-            effective_task_id = session_id or str(uuid.uuid4())
             result = agent.run_conversation(
                 user_message=user_message,
                 conversation_history=conversation_history,
-                task_id=effective_task_id,
+                task_id="default",
             )
             usage = {
                 "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -2372,31 +2293,10 @@ class APIServerAdapter(BasePlatformAdapter):
 
     _MAX_CONCURRENT_RUNS = 10  # Prevent unbounded resource allocation
     _RUN_STREAM_TTL = 300  # seconds before orphaned runs are swept
-    _RUN_STATUS_TTL = 3600  # seconds to retain terminal run status for polling
-
-    def _set_run_status(self, run_id: str, status: str, **fields: Any) -> Dict[str, Any]:
-        """Update pollable run status without exposing private agent objects."""
-        now = time.time()
-        current = self._run_statuses.get(run_id, {})
-        current.update({
-            "object": "hermes.run",
-            "run_id": run_id,
-            "status": status,
-            "updated_at": now,
-        })
-        current.setdefault("created_at", fields.pop("created_at", now))
-        current.update(fields)
-        self._run_statuses[run_id] = current
-        return current
 
     def _make_run_event_callback(self, run_id: str, loop: "asyncio.AbstractEventLoop"):
         """Return a tool_progress_callback that pushes structured events to the run's SSE queue."""
         def _push(event: Dict[str, Any]) -> None:
-            self._set_run_status(
-                run_id,
-                self._run_statuses.get(run_id, {}).get("status", "running"),
-                last_event=event.get("event"),
-            )
             q = self._run_streams.get(run_id)
             if q is None:
                 return
@@ -2461,6 +2361,28 @@ class APIServerAdapter(BasePlatformAdapter):
         if not user_message:
             return web.json_response(_openai_error("No user message found in input"), status=400)
 
+        run_id = f"run_{uuid.uuid4().hex}"
+        loop = asyncio.get_running_loop()
+        q: "asyncio.Queue[Optional[Dict]]" = asyncio.Queue()
+        self._run_streams[run_id] = q
+        self._run_streams_created[run_id] = time.time()
+
+        event_cb = self._make_run_event_callback(run_id, loop)
+
+        # Also wire stream_delta_callback so message.delta events flow through
+        def _text_cb(delta: Optional[str]) -> None:
+            if delta is None:
+                return
+            try:
+                loop.call_soon_threadsafe(q.put_nowait, {
+                    "event": "message.delta",
+                    "run_id": run_id,
+                    "timestamp": time.time(),
+                    "delta": delta,
+                })
+            except Exception:
+                pass
+
         instructions = body.get("instructions")
         previous_response_id = body.get("previous_response_id")
 
@@ -2508,55 +2430,22 @@ class APIServerAdapter(BasePlatformAdapter):
                         )
                     conversation_history.append({"role": msg["role"], "content": str(content)})
 
-        run_id = f"run_{uuid.uuid4().hex}"
         session_id = body.get("session_id") or stored_session_id or run_id
         ephemeral_system_prompt = instructions
-        loop = asyncio.get_running_loop()
-        q: "asyncio.Queue[Optional[Dict]]" = asyncio.Queue()
-        created_at = time.time()
-        self._run_streams[run_id] = q
-        self._run_streams_created[run_id] = created_at
-
-        event_cb = self._make_run_event_callback(run_id, loop)
-
-        # Also wire stream_delta_callback so message.delta events flow through.
-        def _text_cb(delta: Optional[str]) -> None:
-            if delta is None:
-                return
-            try:
-                loop.call_soon_threadsafe(q.put_nowait, {
-                    "event": "message.delta",
-                    "run_id": run_id,
-                    "timestamp": time.time(),
-                    "delta": delta,
-                })
-            except Exception:
-                pass
-
-        self._set_run_status(
-            run_id,
-            "queued",
-            created_at=created_at,
-            session_id=session_id,
-            model=body.get("model", self._model_name),
-        )
 
         async def _run_and_close():
             try:
-                self._set_run_status(run_id, "running")
                 agent = self._create_agent(
                     ephemeral_system_prompt=ephemeral_system_prompt,
                     session_id=session_id,
                     stream_delta_callback=_text_cb,
                     tool_progress_callback=event_cb,
                 )
-                self._active_run_agents[run_id] = agent
                 def _run_sync():
-                    effective_task_id = session_id or run_id
                     r = agent.run_conversation(
                         user_message=user_message,
                         conversation_history=conversation_history,
-                        task_id=effective_task_id,
+                        task_id="default",
                     )
                     u = {
                         "input_tokens": getattr(agent, "session_prompt_tokens", 0) or 0,
@@ -2574,36 +2463,8 @@ class APIServerAdapter(BasePlatformAdapter):
                     "output": final_response,
                     "usage": usage,
                 })
-                self._set_run_status(
-                    run_id,
-                    "completed",
-                    output=final_response,
-                    usage=usage,
-                    last_event="run.completed",
-                )
-            except asyncio.CancelledError:
-                self._set_run_status(
-                    run_id,
-                    "cancelled",
-                    last_event="run.cancelled",
-                )
-                try:
-                    q.put_nowait({
-                        "event": "run.cancelled",
-                        "run_id": run_id,
-                        "timestamp": time.time(),
-                    })
-                except Exception:
-                    pass
-                raise
             except Exception as exc:
                 logger.exception("[api_server] run %s failed", run_id)
-                self._set_run_status(
-                    run_id,
-                    "failed",
-                    error=str(exc),
-                    last_event="run.failed",
-                )
                 try:
                     q.put_nowait({
                         "event": "run.failed",
@@ -2619,11 +2480,8 @@ class APIServerAdapter(BasePlatformAdapter):
                     q.put_nowait(None)
                 except Exception:
                     pass
-                self._active_run_agents.pop(run_id, None)
-                self._active_run_tasks.pop(run_id, None)
 
         task = asyncio.create_task(_run_and_close())
-        self._active_run_tasks[run_id] = task
         try:
             self._background_tasks.add(task)
         except TypeError:
@@ -2633,21 +2491,6 @@ class APIServerAdapter(BasePlatformAdapter):
 
         return web.json_response({"run_id": run_id, "status": "started"}, status=202)
 
-    async def _handle_get_run(self, request: "web.Request") -> "web.Response":
-        """GET /v1/runs/{run_id} — return pollable run status for external UIs."""
-        auth_err = self._check_auth(request)
-        if auth_err:
-            return auth_err
-
-        run_id = request.match_info["run_id"]
-        status = self._run_statuses.get(run_id)
-        if status is None:
-            return web.json_response(
-                _openai_error(f"Run not found: {run_id}", code="run_not_found"),
-                status=404,
-            )
-        return web.json_response(status)
-
     async def _handle_run_events(self, request: "web.Request") -> "web.StreamResponse":
         """GET /v1/runs/{run_id}/events — SSE stream of structured agent lifecycle events."""
         auth_err = self._check_auth(request)
@@ -2697,46 +2540,6 @@ class APIServerAdapter(BasePlatformAdapter):
 
         return response
 
-    async def _handle_stop_run(self, request: "web.Request") -> "web.Response":
-        """POST /v1/runs/{run_id}/stop — interrupt a running agent."""
-        auth_err = self._check_auth(request)
-        if auth_err:
-            return auth_err
-
-        run_id = request.match_info["run_id"]
-        agent = self._active_run_agents.get(run_id)
-        task = self._active_run_tasks.get(run_id)
-
-        if agent is None and task is None:
-            return web.json_response(_openai_error(f"Run not found: {run_id}", code="run_not_found"), status=404)
-
-        self._set_run_status(run_id, "stopping", last_event="run.stopping")
-
-        if agent is not None:
-            try:
-                agent.interrupt("Stop requested via API")
-            except Exception:
-                pass
-
-        if task is not None and not task.done():
-            task.cancel()
-            # Bounded wait: run_conversation() executes in the default
-            # executor thread which task.cancel() cannot preempt — we rely on
-            # agent.interrupt() above to break the loop. Cap the wait so a
-            # slow/unresponsive interrupt can't hang this handler.
-            try:
-                await asyncio.wait_for(asyncio.shield(task), timeout=5.0)
-            except asyncio.TimeoutError:
-                logger.warning(
-                    "[api_server] stop for run %s timed out after 5s; "
-                    "agent may still be finishing the current step",
-                    run_id,
-                )
-            except (asyncio.CancelledError, Exception):
-                pass
-
-        return web.json_response({"run_id": run_id, "status": "stopping"})
-
     async def _sweep_orphaned_runs(self) -> None:
         """Periodically clean up run streams that were never consumed."""
         while True:
@@ -2751,17 +2554,6 @@ class APIServerAdapter(BasePlatformAdapter):
                 logger.debug("[api_server] sweeping orphaned run %s", run_id)
                 self._run_streams.pop(run_id, None)
                 self._run_streams_created.pop(run_id, None)
-                self._active_run_agents.pop(run_id, None)
-                self._active_run_tasks.pop(run_id, None)
-
-            stale_statuses = [
-                run_id
-                for run_id, status in list(self._run_statuses.items())
-                if status.get("status") in {"completed", "failed", "cancelled"}
-                and now - float(status.get("updated_at", 0) or 0) > self._RUN_STATUS_TTL
-            ]
-            for run_id in stale_statuses:
-                self._run_statuses.pop(run_id, None)
 
     # ------------------------------------------------------------------
     # BasePlatformAdapter interface
@@ -2781,7 +2573,6 @@ class APIServerAdapter(BasePlatformAdapter):
             self._app.router.add_get("/health/detailed", self._handle_health_detailed)
             self._app.router.add_get("/v1/health", self._handle_health)
             self._app.router.add_get("/v1/models", self._handle_models)
-            self._app.router.add_get("/v1/capabilities", self._handle_capabilities)
             self._app.router.add_post("/v1/chat/completions", self._handle_chat_completions)
             self._app.router.add_post("/v1/responses", self._handle_responses)
             self._app.router.add_get("/v1/responses/{response_id}", self._handle_get_response)
@@ -2797,9 +2588,7 @@ class APIServerAdapter(BasePlatformAdapter):
             self._app.router.add_post("/api/jobs/{job_id}/run", self._handle_run_job)
             # Structured event streaming
             self._app.router.add_post("/v1/runs", self._handle_runs)
-            self._app.router.add_get("/v1/runs/{run_id}", self._handle_get_run)
             self._app.router.add_get("/v1/runs/{run_id}/events", self._handle_run_events)
-            self._app.router.add_post("/v1/runs/{run_id}/stop", self._handle_stop_run)
             # Start background sweep to clean up orphaned (unconsumed) run streams
             sweep_task = asyncio.create_task(self._sweep_orphaned_runs())
             try: