fix: clean up stale test references to removed attributes

Remove tests for deleted should_compress_preflight/get_status/last_total_tokens
from test_context_compressor.py. Remove stale _reasoning_deltas_fired references
from test_reasoning_command.py (attribute removed, tests were passing vacuously).

.dockerignore

@@ -5,7 +5,6 @@
 
 # Dependencies
 node_modules
-.venv
 
 # CI/CD
 .github

.env.example

@@ -24,15 +24,6 @@
 # Optional base URL override (default: Google's OpenAI-compatible endpoint)
 # GEMINI_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai
 
-# =============================================================================
-# LLM PROVIDER (Ollama Cloud)
-# =============================================================================
-# Cloud-hosted open models via Ollama's OpenAI-compatible endpoint.
-# Get your key at: https://ollama.com/settings
-# OLLAMA_API_KEY=your_ollama_key_here
-# Optional base URL override (default: https://ollama.com/v1)
-# OLLAMA_BASE_URL=https://ollama.com/v1
-
 # =============================================================================
 # LLM PROVIDER (z.ai / GLM)
 # =============================================================================
@@ -52,15 +43,6 @@
 # KIMI_BASE_URL=https://api.kimi.com/coding/v1  # Default for sk-kimi- keys
 # KIMI_BASE_URL=https://api.moonshot.ai/v1      # For legacy Moonshot keys
 # KIMI_BASE_URL=https://api.moonshot.cn/v1       # For Moonshot China keys
-# KIMI_CN_API_KEY=                               # Dedicated Moonshot China key
-
-# =============================================================================
-# LLM PROVIDER (Arcee AI)
-# =============================================================================
-# Arcee AI provides access to Trinity models (trinity-mini, trinity-large-*)
-# Get an Arcee key at: https://chat.arcee.ai/
-# ARCEEAI_API_KEY=
-# ARCEE_BASE_URL=                                 # Override default base URL
 
 # =============================================================================
 # LLM PROVIDER (MiniMax)
@@ -107,15 +89,6 @@
 # Optional base URL override:
 # HERMES_QWEN_BASE_URL=https://portal.qwen.ai/v1
 
-# =============================================================================
-# LLM PROVIDER (Xiaomi MiMo)
-# =============================================================================
-# Xiaomi MiMo models (mimo-v2-pro, mimo-v2-omni, mimo-v2-flash).
-# Get your key at: https://platform.xiaomimimo.com
-# XIAOMI_API_KEY=your_key_here
-# Optional base URL override:
-# XIAOMI_BASE_URL=https://api.xiaomimimo.com/v1
-
 # =============================================================================
 # TOOL API KEYS
 # =============================================================================
@@ -154,10 +127,6 @@
 # Only override here if you need to force a backend without touching config.yaml:
 # TERMINAL_ENV=local
 
-# Override the container runtime binary (e.g. to use Podman instead of Docker).
-# Useful on systems where Docker's storage driver is broken or unavailable.
-# HERMES_DOCKER_BINARY=/usr/local/bin/podman
-
 # Container images (for singularity/docker/modal backends)
 # TERMINAL_DOCKER_IMAGE=nikolaik/python-nodejs:python3.11-nodejs20
 # TERMINAL_SINGULARITY_IMAGE=docker://nikolaik/python-nodejs:python3.11-nodejs20

.envrc

@@ -1,5 +1 @@
-watch_file pyproject.toml uv.lock
-watch_file ui-tui/package-lock.json ui-tui/package.json
-watch_file flake.nix flake.lock nix/devShell.nix nix/tui.nix nix/package.nix nix/python.nix
-
 use flake

.gitattributes

@@ -1,2 +0,0 @@
-# Auto-generated files — collapse diffs and exclude from language stats
-web/package-lock.json linguist-generated=true

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -11,7 +11,6 @@ body:
         **Before submitting**, please:
         - [ ] Search [existing issues](https://github.com/NousResearch/hermes-agent/issues) to avoid duplicates
         - [ ] Update to the latest version (`hermes update`) and confirm the bug still exists
-        - [ ] Run `hermes debug share` and paste the links below (see Debug Report section)
 
   - type: textarea
     id: description
@@ -83,25 +82,6 @@ body:
         - Slack
         - WhatsApp
 
-  - type: textarea
-    id: debug-report
-    attributes:
-      label: Debug Report
-      description: |
-        Run `hermes debug share` from your terminal and paste the links it prints here.
-        This uploads your system info, config, and recent logs to a paste service automatically.
-
-        If you're in an interactive chat session, you can also use the `/debug` slash command — it does the same thing.
-
-        If the upload fails, run `hermes debug share --local` and paste the output directly.
-      placeholder: |
-        Report   https://paste.rs/abc123
-        agent.log   https://paste.rs/def456
-        gateway.log   https://paste.rs/ghi789
-      render: shell
-    validations:
-      required: true
-
   - type: input
     id: os
     attributes:
@@ -117,6 +97,8 @@ body:
       label: Python Version
       description: Output of `python --version`
       placeholder: "3.11.9"
+    validations:
+      required: true
 
   - type: input
     id: hermes-version
@@ -124,14 +106,14 @@ body:
       label: Hermes Version
       description: Output of `hermes version`
       placeholder: "2.1.0"
+    validations:
+      required: true
 
   - type: textarea
     id: logs
     attributes:
-      label: Additional Logs / Traceback (optional)
-      description: |
-        The debug report above covers most logs. Use this field for any extra error output, 
-        tracebacks, or screenshots not captured by `hermes debug share`.
+      label: Relevant Logs / Traceback
+      description: Paste any error output, traceback, or log messages. This will be auto-formatted as code.
       render: shell
 
   - type: textarea

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -71,15 +71,3 @@ body:
       label: Contribution
       options:
         - label: I'd like to implement this myself and submit a PR
-
-  - type: textarea
-    id: debug-report
-    attributes:
-      label: Debug Report (optional)
-      description: |
-        If this feature request is related to a problem you're experiencing, run `hermes debug share` and paste the links here.
-        In an interactive chat session, you can use `/debug` instead.
-        This helps us understand your environment and any related logs.
-      placeholder: |
-        Report   https://paste.rs/abc123
-      render: shell

.github/ISSUE_TEMPLATE/setup_help.yml

@@ -9,8 +9,7 @@ body:
         Sorry you're having trouble! Please fill out the details below so we can help.
 
         **Quick checks first:**
-        - Run `hermes debug share` and paste the links in the Debug Report section below
-        - If you're in a chat session, you can use `/debug` instead — it does the same thing
+        - Run `hermes doctor` and include the output below
         - Try `hermes update` to get the latest version
         - Check the [README troubleshooting section](https://github.com/NousResearch/hermes-agent#troubleshooting)
         - For general questions, consider the [Nous Research Discord](https://discord.gg/NousResearch) for faster help
@@ -75,21 +74,10 @@ body:
       placeholder: "2.1.0"
 
   - type: textarea
-    id: debug-report
+    id: doctor-output
     attributes:
-      label: Debug Report
-      description: |
-        Run `hermes debug share` from your terminal and paste the links it prints here.
-        This uploads your system info, config, and recent logs to a paste service automatically.
-
-        If you're in an interactive chat session, you can also use the `/debug` slash command — it does the same thing.
-
-        If the upload fails or install didn't get that far, run `hermes debug share --local` and paste the output directly.
-        If even that doesn't work, run `hermes doctor` and paste that output instead.
-      placeholder: |
-        Report   https://paste.rs/abc123
-        agent.log   https://paste.rs/def456
-        gateway.log   https://paste.rs/ghi789
+      label: Output of `hermes doctor`
+      description: Run `hermes doctor` and paste the full output. This will be auto-formatted.
       render: shell
 
   - type: textarea

.github/workflows/contributor-check.yml

@@ -1,73 +0,0 @@
-name: Contributor Attribution Check
-
-on:
-  pull_request:
-    branches: [main]
-    paths:
-      # Only run when code files change (not docs-only PRs)
-      - '*.py'
-      - '**/*.py'
-      - '.github/workflows/contributor-check.yml'
-
-permissions:
-  contents: read
-
-jobs:
-  check-attribution:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          fetch-depth: 0  # Full history needed for git log
-
-      - name: Check for unmapped contributor emails
-        run: |
-          # Get the merge base between this PR and main
-          MERGE_BASE=$(git merge-base origin/main HEAD)
-
-          # Find any new author emails in this PR's commits
-          NEW_EMAILS=$(git log ${MERGE_BASE}..HEAD --format='%ae' --no-merges | sort -u)
-
-          if [ -z "$NEW_EMAILS" ]; then
-            echo "No new commits to check."
-            exit 0
-          fi
-
-          # Check each email against AUTHOR_MAP in release.py
-          MISSING=""
-          while IFS= read -r email; do
-            # Skip teknium and bot emails
-            case "$email" in
-              *teknium*|*noreply@github.com*|*dependabot*|*github-actions*|*anthropic.com*|*cursor.com*)
-                continue ;;
-            esac
-
-            # Check if email is in AUTHOR_MAP (either as a key or matches noreply pattern)
-            if echo "$email" | grep -qP '\+.*@users\.noreply\.github\.com'; then
-              continue  # GitHub noreply emails auto-resolve
-            fi
-
-            if ! grep -qF "\"${email}\"" scripts/release.py 2>/dev/null; then
-              AUTHOR=$(git log --author="$email" --format='%an' -1)
-              MISSING="${MISSING}\n  ${email} (${AUTHOR})"
-            fi
-          done <<< "$NEW_EMAILS"
-
-          if [ -n "$MISSING" ]; then
-            echo ""
-            echo "⚠️  New contributor email(s) not in AUTHOR_MAP:"
-            echo -e "$MISSING"
-            echo ""
-            echo "Please add mappings to scripts/release.py AUTHOR_MAP:"
-            echo -e "$MISSING" | while read -r line; do
-              email=$(echo "$line" | sed 's/^ *//' | cut -d' ' -f1)
-              [ -z "$email" ] && continue
-              echo "    \"${email}\": \"<github-username>\","
-            done
-            echo ""
-            echo "To find the GitHub username for an email:"
-            echo "  gh api 'search/users?q=EMAIL+in:email' --jq '.items[0].login'"
-            exit 1
-          else
-            echo "✅ All contributor emails are mapped in AUTHOR_MAP."
-          fi

.github/workflows/deploy-site.yml

@@ -1,12 +1,11 @@
 name: Deploy Site
 
 on:
-  release:
-    types: [published]
   push:
     branches: [main]
     paths:
       - 'website/**'
+      - 'landingpage/**'
       - 'skills/**'
       - 'optional-skills/**'
       - '.github/workflows/deploy-site.yml'
@@ -21,46 +20,32 @@ concurrency:
   cancel-in-progress: false
 
 jobs:
-  deploy-vercel:
-    if: github.event_name == 'release'
-    runs-on: ubuntu-latest
-    steps:
-      - name: Trigger Vercel Deploy
-        run: curl -X POST "${{ secrets.VERCEL_DEPLOY_HOOK }}"
-
-  deploy-docs:
+  build-and-deploy:
+    # Only run on the upstream repository, not on forks
     if: github.repository == 'NousResearch/hermes-agent'
     runs-on: ubuntu-latest
     environment:
       name: github-pages
       url: ${{ steps.deploy.outputs.page_url }}
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: npm
           cache-dependency-path: website/package-lock.json
 
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.11'
 
       - name: Install PyYAML for skill extraction
-        run: pip install pyyaml==6.0.2 httpx==0.28.1
+        run: pip install pyyaml
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py
 
-      - name: Build skills index (if not already present)
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          if [ ! -f website/static/api/skills-index.json ]; then
-            python3 scripts/build_skills_index.py || echo "Skills index build failed (non-fatal)"
-          fi
-
       - name: Install dependencies
         run: npm ci
         working-directory: website
@@ -72,13 +57,18 @@ jobs:
       - name: Stage deployment
         run: |
           mkdir -p _site/docs
+          # Landing page at root
+          cp -r landingpage/* _site/
+          # Docusaurus at /docs/
           cp -r website/build/* _site/docs/
+          # CNAME so GitHub Pages keeps the custom domain between deploys
+          echo "hermes-agent.nousresearch.com" > _site/CNAME
 
       - name: Upload artifact
-        uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa  # v3
+        uses: actions/upload-pages-artifact@v3
         with:
           path: _site
 
       - name: Deploy to GitHub Pages
         id: deploy
-        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e  # v4
+        uses: actions/deploy-pages@v4

.github/workflows/docker-publish.yml

@@ -3,13 +3,8 @@ name: Docker Build and Publish
 on:
   push:
     branches: [main]
-    paths:
-      - '**/*.py'
-      - 'pyproject.toml'
-      - 'uv.lock'
-      - 'Dockerfile'
-      - 'docker/**'
-      - '.github/workflows/docker-publish.yml'
+  pull_request:
+    branches: [main]
   release:
     types: [published]
 
@@ -28,21 +23,21 @@ jobs:
     timeout-minutes: 60
     steps:
       - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130  # v3
+        uses: docker/setup-qemu-action@v3
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
+        uses: docker/setup-buildx-action@v3
 
       # Build amd64 only so we can `load` the image for smoke testing.
       # `load: true` cannot export a multi-arch manifest to the local daemon.
       # The multi-arch build follows on push to main / release.
       - name: Build image (amd64, smoke test)
-        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: Dockerfile
@@ -54,14 +49,6 @@ jobs:
 
       - name: Test image starts
         run: |
-          # The image runs as the hermes user (UID 10000).  GitHub Actions
-          # creates /tmp/hermes-test root-owned by default, which hermes
-          # can't write to — chown it to match the in-container UID before
-          # bind-mounting.  Real users doing `docker run -v ~/.hermes:...`
-          # with their own UID hit the same issue and have their own
-          # remediations (HERMES_UID env var, or chown locally).
-          mkdir -p /tmp/hermes-test
-          sudo chown -R 10000:10000 /tmp/hermes-test
           docker run --rm \
             -v /tmp/hermes-test:/opt/data \
             --entrypoint /opt/hermes/docker/entrypoint.sh \
@@ -69,31 +56,36 @@ jobs:
 
       - name: Log in to Docker Hub
         if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
-        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9  # v3
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Push multi-arch image (main branch)
         if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: Dockerfile
           push: true
           platforms: linux/amd64,linux/arm64
-          tags: nousresearch/hermes-agent:latest
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.sha }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
       - name: Push multi-arch image (release)
         if: github.event_name == 'release'
-        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: Dockerfile
           push: true
           platforms: linux/amd64,linux/arm64
-          tags: nousresearch/hermes-agent:${{ github.event.release.tag_name }}
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.event.release.tag_name }}
+            nousresearch/hermes-agent:${{ github.sha }}
           cache-from: type=gha
           cache-to: type=gha,mode=max

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

@@ -7,16 +7,13 @@ on:
       - '.github/workflows/docs-site-checks.yml'
   workflow_dispatch:
 
-permissions:
-  contents: read
-
 jobs:
   docs-site-checks:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: npm
@@ -26,7 +23,7 @@ jobs:
         run: npm ci
         working-directory: website
 
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.11'
 

.github/workflows/nix.yml

@@ -14,9 +14,6 @@ on:
       - 'run_agent.py'
       - 'acp_adapter/**'
 
-permissions:
-  contents: read
-
 concurrency:
   group: nix-${{ github.ref }}
   cancel-in-progress: true
@@ -29,7 +26,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     timeout-minutes: 30
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@v4
       - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
       - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
       - name: Check flake

.github/workflows/skills-index.yml

@@ -1,101 +0,0 @@
-name: Build Skills Index
-
-on:
-  schedule:
-    # Run twice daily: 6 AM and 6 PM UTC
-    - cron: '0 6,18 * * *'
-  workflow_dispatch:  # Manual trigger
-  push:
-    branches: [main]
-    paths:
-      - 'scripts/build_skills_index.py'
-      - '.github/workflows/skills-index.yml'
-
-permissions:
-  contents: read
-
-jobs:
-  build-index:
-    # Only run on the upstream repository, not on forks
-    if: github.repository == 'NousResearch/hermes-agent'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
-        with:
-          python-version: '3.11'
-
-      - name: Install dependencies
-        run: pip install httpx==0.28.1 pyyaml==6.0.2
-
-      - name: Build skills index
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: python scripts/build_skills_index.py
-
-      - name: Upload index artifact
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02  # v4
-        with:
-          name: skills-index
-          path: website/static/api/skills-index.json
-          retention-days: 7
-
-  deploy-with-index:
-    needs: build-index
-    runs-on: ubuntu-latest
-    permissions:
-      pages: write
-      id-token: write
-    environment:
-      name: github-pages
-      url: ${{ steps.deploy.outputs.page_url }}
-    # Only deploy on schedule or manual trigger (not on every push to the script)
-    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-
-      - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
-        with:
-          name: skills-index
-          path: website/static/api/
-
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
-        with:
-          node-version: 20
-          cache: npm
-          cache-dependency-path: website/package-lock.json
-
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
-        with:
-          python-version: '3.11'
-
-      - name: Install PyYAML for skill extraction
-        run: pip install pyyaml==6.0.2
-
-      - name: Extract skill metadata for dashboard
-        run: python3 website/scripts/extract-skills.py
-
-      - name: Install dependencies
-        run: npm ci
-        working-directory: website
-
-      - name: Build Docusaurus
-        run: npm run build
-        working-directory: website
-
-      - name: Stage deployment
-        run: |
-          mkdir -p _site/docs
-          cp -r landingpage/* _site/
-          cp -r website/build/* _site/docs/
-          echo "hermes-agent.nousresearch.com" > _site/CNAME
-
-      - name: Upload artifact
-        uses: actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa  # v3
-        with:
-          path: _site
-
-      - name: Deploy to GitHub Pages
-        id: deploy
-        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e  # v4

.github/workflows/supply-chain-audit.yml

@@ -3,39 +3,22 @@ name: Supply Chain Audit
 on:
   pull_request:
     types: [opened, synchronize, reopened]
-    paths:
-      - '**/*.py'
-      - '**/*.pth'
-      - '**/setup.py'
-      - '**/setup.cfg'
-      - '**/sitecustomize.py'
-      - '**/usercustomize.py'
-      - '**/__init__.pth'
 
 permissions:
   pull-requests: write
   contents: read
 
-# Narrow, high-signal scanner. Only fires on critical indicators of supply
-# chain attacks (e.g. the litellm-style payloads). Low-signal heuristics
-# (plain base64, plain exec/eval, dependency/Dockerfile/workflow edits,
-# Actions version unpinning, outbound POST/PUT) were intentionally
-# removed — they fired on nearly every PR and trained reviewers to ignore
-# the scanner. Keep this file's checks ruthlessly narrow: if you find
-# yourself adding WARNING-tier patterns here again, make a separate
-# advisory-only workflow instead.
-
 jobs:
   scan:
-    name: Scan PR for critical supply chain risks
+    name: Scan PR for supply chain risks
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      - name: Scan diff for critical patterns
+      - name: Scan diff for suspicious patterns
         id: scan
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -45,19 +28,19 @@ jobs:
           BASE="${{ github.event.pull_request.base.sha }}"
           HEAD="${{ github.event.pull_request.head.sha }}"
 
-          # Added lines only, excluding lockfiles.
+          # Get the full diff (added lines only)
           DIFF=$(git diff "$BASE".."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
 
           FINDINGS=""
+          CRITICAL=false
 
           # --- .pth files (auto-execute on Python startup) ---
-          # The exact mechanism used in the litellm supply chain attack:
-          # https://github.com/BerriAI/litellm/issues/24512
           PTH_FILES=$(git diff --name-only "$BASE".."$HEAD" | grep '\.pth$' || true)
           if [ -n "$PTH_FILES" ]; then
+            CRITICAL=true
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: .pth file added or modified
-          Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required.
+          Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required. This is the exact mechanism used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512).
 
           **Files:**
           \`\`\`
@@ -66,12 +49,13 @@ jobs:
           "
           fi
 
-          # --- base64 decode + exec/eval on the same line (the litellm attack pattern) ---
+          # --- base64 + exec/eval combo (the litellm attack pattern) ---
           B64_EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|decodebytes|urlsafe_b64decode)' | grep -iE 'exec\(|eval\(' | head -10 || true)
           if [ -n "$B64_EXEC_HITS" ]; then
+            CRITICAL=true
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: base64 decode + exec/eval combo
-          Base64-decoded strings passed directly to exec/eval — the signature of hidden credential-stealing payloads.
+          This is the exact pattern used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512) — base64-decoded strings passed to exec/eval to hide credential-stealing payloads.
 
           **Matches:**
           \`\`\`
@@ -80,12 +64,41 @@ jobs:
           "
           fi
 
-          # --- subprocess with encoded/obfuscated command argument ---
-          PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|\\x[0-9a-f]{2}|chr\(' | head -10 || true)
+          # --- base64 decode/encode (alone — legitimate uses exist) ---
+          B64_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|b64encode|decodebytes|encodebytes|urlsafe_b64decode)|atob\(|btoa\(|Buffer\.from\(.*base64' | head -20 || true)
+          if [ -n "$B64_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: base64 encoding/decoding detected
+          Base64 has legitimate uses (images, JWT, etc.) but is also commonly used to obfuscate malicious payloads. Verify the usage is appropriate.
+
+          **Matches (first 20):**
+          \`\`\`
+          ${B64_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- exec/eval with string arguments ---
+          EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E '(exec|eval)\s*\(' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert\|# ' | head -20 || true)
+          if [ -n "$EXEC_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: exec() or eval() usage
+          Dynamic code execution can hide malicious behavior, especially when combined with base64 or network fetches.
+
+          **Matches (first 20):**
+          \`\`\`
+          ${EXEC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- subprocess with encoded/obfuscated commands ---
+          PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|decode|encode|\\x|chr\(' | head -10 || true)
           if [ -n "$PROC_HITS" ]; then
+            CRITICAL=true
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: subprocess with encoded/obfuscated command
-          Subprocess calls whose command strings are base64- or hex-encoded are a strong indicator of payload execution.
+          Subprocess calls with encoded arguments are a strong indicator of payload execution.
 
           **Matches:**
           \`\`\`
@@ -94,12 +107,25 @@ jobs:
           "
           fi
 
-          # --- Install-hook files (setup.py/sitecustomize/usercustomize/__init__.pth) ---
-          # These execute during pip install or interpreter startup.
-          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(^|/)(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
+          # --- Network calls to non-standard domains ---
+          EXFIL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'requests\.(post|put)\(|httpx\.(post|put)\(|urllib\.request\.urlopen' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert' | head -10 || true)
+          if [ -n "$EXFIL_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: Outbound network calls (POST/PUT)
+          Outbound POST/PUT requests in new code could be data exfiltration. Verify the destination URLs are legitimate.
+
+          **Matches (first 10):**
+          \`\`\`
+          ${EXFIL_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- setup.py / setup.cfg install hooks ---
+          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(setup\.py|setup\.cfg|__init__\.pth|sitecustomize\.py|usercustomize\.py)$' || true)
           if [ -n "$SETUP_HITS" ]; then
             FINDINGS="${FINDINGS}
-          ### 🚨 CRITICAL: Install-hook file added or modified
+          ### ⚠️ WARNING: Install hook files modified
           These files can execute code during package installation or interpreter startup.
 
           **Files:**
@@ -109,31 +135,58 @@ jobs:
           "
           fi
 
+          # --- Compile/marshal/pickle (code object injection) ---
+          MARSHAL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'marshal\.loads|pickle\.loads|compile\(' | grep -v '^\+\s*#' | grep -v 'test_\|re\.compile\|ast\.compile' | head -10 || true)
+          if [ -n "$MARSHAL_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: marshal/pickle/compile usage
+          These can deserialize or construct executable code objects.
+
+          **Matches:**
+          \`\`\`
+          ${MARSHAL_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Output results ---
           if [ -n "$FINDINGS" ]; then
             echo "found=true" >> "$GITHUB_OUTPUT"
+            if [ "$CRITICAL" = true ]; then
+              echo "critical=true" >> "$GITHUB_OUTPUT"
+            else
+              echo "critical=false" >> "$GITHUB_OUTPUT"
+            fi
+            # Write findings to a file (multiline env vars are fragile)
             echo "$FINDINGS" > /tmp/findings.md
           else
             echo "found=false" >> "$GITHUB_OUTPUT"
+            echo "critical=false" >> "$GITHUB_OUTPUT"
           fi
 
-      - name: Post critical finding comment
+      - name: Post warning comment
         if: steps.scan.outputs.found == 'true'
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
-          BODY="## 🚨 CRITICAL Supply Chain Risk Detected
+          SEVERITY="⚠️ Supply Chain Risk Detected"
+          if [ "${{ steps.scan.outputs.critical }}" = "true" ]; then
+            SEVERITY="🚨 CRITICAL Supply Chain Risk Detected"
+          fi
 
-          This PR contains a pattern that has been used in real supply chain attacks. A maintainer must review the flagged code carefully before merging.
+          BODY="## ${SEVERITY}
+
+          This PR contains patterns commonly associated with supply chain attacks. This does **not** mean the PR is malicious — but these patterns require careful human review before merging.
 
           $(cat /tmp/findings.md)
 
           ---
-          *Scanner only fires on high-signal indicators: .pth files, base64+exec/eval combos, subprocess with encoded commands, or install-hook files. Low-signal warnings were removed intentionally — if you're seeing this comment, the finding is worth inspecting.*"
+          *Automated scan triggered by [supply-chain-audit](/.github/workflows/supply-chain-audit.yml). If this is a false positive, a maintainer can approve after manual review.*"
 
-          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY" || echo "::warning::Could not post PR comment (expected for fork PRs — GITHUB_TOKEN is read-only)"
+          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY"
 
       - name: Fail on critical findings
-        if: steps.scan.outputs.found == 'true'
+        if: steps.scan.outputs.critical == 'true'
         run: |
           echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the PR comment for details."
           exit 1

.github/workflows/tests.yml

@@ -3,17 +3,8 @@ name: Tests
 on:
   push:
     branches: [main]
-    paths-ignore:
-      - '**/*.md'
-      - 'docs/**'
   pull_request:
     branches: [main]
-    paths-ignore:
-      - '**/*.md'
-      - 'docs/**'
-
-permissions:
-  contents: read
 
 # Cancel in-progress runs for the same PR/branch
 concurrency:
@@ -23,16 +14,16 @@ concurrency:
 jobs:
   test:
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    timeout-minutes: 10
     steps:
       - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
 
       - name: Install system dependencies
         run: sudo apt-get update && sudo apt-get install -y ripgrep
 
       - name: Install uv
-        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
+        uses: astral-sh/setup-uv@v5
 
       - name: Set up Python 3.11
         run: uv python install 3.11
@@ -58,10 +49,10 @@ jobs:
     timeout-minutes: 10
     steps:
       - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
 
       - name: Install uv
-        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
+        uses: astral-sh/setup-uv@v5
 
       - name: Set up Python 3.11
         run: uv python install 3.11

.gitignore

@@ -51,20 +51,10 @@ ignored/
 .worktrees/
 environments/benchmarks/evals/
 
-# Web UI build output
-hermes_cli/web_dist/
-
-# Web UI assets — synced from @nous-research/ui at build time via
-# `npm run sync-assets` (see web/package.json).
-web/public/fonts/
-web/public/ds-assets/
-
 # Release script temp files
 .release_notes.md
 mini-swe-agent/
 
 # Nix
 .direnv/
-.nix-stamps/
 result
-website/static/api/skills-index.json

.mailmap

@@ -1,108 +0,0 @@
-# .mailmap — canonical author mapping for git shortlog / git log / GitHub
-# Format: Canonical Name <canonical@email> <commit@email>
-# See: https://git-scm.com/docs/gitmailmap
-#
-# This maps commit emails to GitHub noreply addresses so that:
-# 1. `git shortlog -sn` shows deduplicated contributor counts
-# 2. GitHub's contributor graph can attribute commits correctly
-# 3. Contributors with personal/work emails get proper credit
-#
-# When adding entries: use the contributor's GitHub noreply email as canonical
-# so GitHub can link commits to their profile.
-
-# === Teknium (multiple emails) ===
-Teknium <127238744+teknium1@users.noreply.github.com> <teknium1@gmail.com>
-Teknium <127238744+teknium1@users.noreply.github.com> <teknium@nousresearch.com>
-
-# === Contributors — personal/work emails mapped to GitHub noreply ===
-# Format: Canonical Name <GH-noreply> <commit-email>
-
-# Verified via GH API email search
-luyao618 <364939526@qq.com> <364939526@qq.com>
-ethernet8023 <arilotter@gmail.com> <arilotter@gmail.com>
-nicoloboschi <boschi1997@gmail.com> <boschi1997@gmail.com>
-cherifya <chef.ya@gmail.com> <chef.ya@gmail.com>
-BongSuCHOI <chlqhdtn98@gmail.com> <chlqhdtn98@gmail.com>
-dsocolobsky <dsocolobsky@gmail.com> <dsocolobsky@gmail.com>
-pefontana <fontana.pedro93@gmail.com> <fontana.pedro93@gmail.com>
-Helmi <frank@helmschrott.de> <frank@helmschrott.de>
-hata1234 <hata1234@gmail.com> <hata1234@gmail.com>
-
-# Verified via PR investigation / salvage PR bodies
-DeployFaith <agents@kylefrench.dev> <agents@kylefrench.dev>
-flobo3 <floptopbot33@gmail.com> <floptopbot33@gmail.com>
-gaixianggeng <gaixg94@gmail.com> <gaixg94@gmail.com>
-KUSH42 <xush@xush.org> <xush@xush.org>
-konsisumer <der@konsi.org> <der@konsi.org>
-WorldInnovationsDepartment <vorvul.danylo@gmail.com> <vorvul.danylo@gmail.com>
-m0n5t3r <iacobs@m0n5t3r.info> <iacobs@m0n5t3r.info>
-sprmn24 <oncuevtv@gmail.com> <oncuevtv@gmail.com>
-fancydirty <fancydirty@gmail.com> <fancydirty@gmail.com>
-fxfitz <francis.x.fitzpatrick@gmail.com> <francis.x.fitzpatrick@gmail.com>
-limars874 <limars874@gmail.com> <limars874@gmail.com>
-AaronWong1999 <aaronwong1999@icloud.com> <aaronwong1999@icloud.com>
-dippwho <dipp.who@gmail.com> <dipp.who@gmail.com>
-duerzy <duerzy@gmail.com> <duerzy@gmail.com>
-geoffwellman <geoff.wellman@gmail.com> <geoff.wellman@gmail.com>
-hcshen0111 <shenhaocheng19990111@gmail.com> <shenhaocheng19990111@gmail.com>
-jamesarch <han.shan@live.cn> <han.shan@live.cn>
-stephenschoettler <stephenschoettler@gmail.com> <stephenschoettler@gmail.com>
-Tranquil-Flow <tranquil_flow@protonmail.com> <tranquil_flow@protonmail.com>
-Dusk1e <yusufalweshdemir@gmail.com> <yusufalweshdemir@gmail.com>
-Awsh1 <ysfalweshcan@gmail.com> <ysfalweshcan@gmail.com>
-WAXLYY <ysfwaxlycan@gmail.com> <ysfwaxlycan@gmail.com>
-donrhmexe <don.rhm@gmail.com> <don.rhm@gmail.com>
-hqhq1025 <1506751656@qq.com> <1506751656@qq.com>
-BlackishGreen33 <s5460703@gmail.com> <s5460703@gmail.com>
-tomqiaozc <zqiao@microsoft.com> <zqiao@microsoft.com>
-MagicRay1217 <mingjwan@microsoft.com> <mingjwan@microsoft.com>
-aaronagent <1115117931@qq.com> <1115117931@qq.com>
-YoungYang963 <young@YoungdeMacBook-Pro.local> <young@YoungdeMacBook-Pro.local>
-LongOddCode <haolong@microsoft.com> <haolong@microsoft.com>
-Cafexss <coffeemjj@gmail.com> <coffeemjj@gmail.com>
-Cygra <sjtuwbh@gmail.com> <sjtuwbh@gmail.com>
-DomGrieco <dgrieco@redhat.com> <dgrieco@redhat.com>
-
-# Duplicate email mapping (same person, multiple emails)
-Sertug17 <104278804+Sertug17@users.noreply.github.com> <srhtsrht17@gmail.com>
-yyovil <birdiegyal@gmail.com> <tanishq231003@gmail.com>
-DomGrieco <dgrieco@redhat.com> <dgrieco@redhat.com>
-dsocolobsky <dsocolobsky@gmail.com> <dylan.socolobsky@lambdaclass.com>
-olafthiele <programming@olafthiele.com> <olafthiele@gmail.com>
-
-# Verified via git display name matching GH contributor username
-cokemine <aptx4561@gmail.com> <aptx4561@gmail.com>
-dalianmao000 <dalianmao0107@gmail.com> <dalianmao0107@gmail.com>
-emozilla <emozilla@nousresearch.com> <emozilla@nousresearch.com>
-jjovalle99 <juan.ovalle@mistral.ai> <juan.ovalle@mistral.ai>
-kagura-agent <kagura.chen28@gmail.com> <kagura.chen28@gmail.com>
-spniyant <niyant@spicefi.xyz> <niyant@spicefi.xyz>
-olafthiele <programming@olafthiele.com> <programming@olafthiele.com>
-r266-tech <r2668940489@gmail.com> <r2668940489@gmail.com>
-xingkongliang <tianliangjay@gmail.com> <tianliangjay@gmail.com>
-win4r <win4r@outlook.com> <win4r@outlook.com>
-zhouboli <zhouboli@gmail.com> <zhouboli@gmail.com>
-yongtenglei <yongtenglei@gmail.com> <yongtenglei@gmail.com>
-
-# Nous Research team
-benbarclay <ben@nousresearch.com> <ben@nousresearch.com>
-jquesnelle <jonny@nousresearch.com> <jonny@nousresearch.com>
-
-# GH contributor list verified
-spideystreet <dhicham.pro@gmail.com> <dhicham.pro@gmail.com>
-dorukardahan <dorukardahan@hotmail.com> <dorukardahan@hotmail.com>
-MustafaKara7 <karamusti912@gmail.com> <karamusti912@gmail.com>
-Hmbown <hmbown@gmail.com> <hmbown@gmail.com>
-kamil-gwozdz <kamil@gwozdz.me> <kamil@gwozdz.me>
-kira-ariaki <kira@ariaki.me> <kira@ariaki.me>
-knopki <knopki@duck.com> <knopki@duck.com>
-Unayung <unayung@gmail.com> <unayung@gmail.com>
-SeeYangZhi <yangzhi.see@gmail.com> <yangzhi.see@gmail.com>
-Julientalbot <julien.talbot@ergonomia.re> <julien.talbot@ergonomia.re>
-lesterli <lisicheng168@gmail.com> <lisicheng168@gmail.com>
-JiayuuWang <jiayuw794@gmail.com> <jiayuw794@gmail.com>
-tesseracttars-creator <tesseracttars@gmail.com> <tesseracttars@gmail.com>
-xinbenlv <zzn+pa@zzn.im> <zzn+pa@zzn.im>
-SaulJWu <saul.jj.wu@gmail.com> <saul.jj.wu@gmail.com>
-angelos <angelos@oikos.lan.home.malaiwah.com> <angelos@oikos.lan.home.malaiwah.com>
-MestreY0d4-Uninter <241404605+MestreY0d4-Uninter@users.noreply.github.com> <MestreY0d4-Uninter@users.noreply.github.com>

AGENTS.md

@@ -13,7 +13,7 @@ source venv/bin/activate  # ALWAYS activate before running Python
 ```
 hermes-agent/
 ├── run_agent.py          # AIAgent class — core conversation loop
-├── model_tools.py        # Tool orchestration, discover_builtin_tools(), handle_function_call()
+├── model_tools.py        # Tool orchestration, _discover_tools(), handle_function_call()
 ├── toolsets.py           # Toolset definitions, _HERMES_CORE_TOOLS list
 ├── cli.py                # HermesCLI class — interactive CLI orchestrator
 ├── hermes_state.py       # SessionDB — SQLite session store (FTS5 search)
@@ -55,20 +55,7 @@ hermes-agent/
 ├── gateway/              # Messaging platform gateway
 │   ├── run.py            # Main loop, slash commands, message dispatch
 │   ├── session.py        # SessionStore — conversation persistence
-│   └── platforms/        # Adapters: telegram, discord, slack, whatsapp, homeassistant, signal, qqbot
-├── ui-tui/               # Ink (React) terminal UI — `hermes --tui`
-│   ├── src/entry.tsx        # TTY gate + render()
-│   ├── src/app.tsx          # Main state machine and UI
-│   ├── src/gatewayClient.ts # Child process + JSON-RPC bridge
-│   ├── src/app/             # Decomposed app logic (event handler, slash handler, stores, hooks)
-│   ├── src/components/      # Ink components (branding, markdown, prompts, pickers, etc.)
-│   ├── src/hooks/           # useCompletion, useInputHistory, useQueue, useVirtualHistory
-│   └── src/lib/             # Pure helpers (history, osc52, text, rpc, messages)
-├── tui_gateway/          # Python JSON-RPC backend for the TUI
-│   ├── entry.py             # stdio entrypoint
-│   ├── server.py            # RPC handlers and session logic
-│   ├── render.py            # Optional rich/ANSI bridge
-│   └── slash_worker.py      # Persistent HermesCLI subprocess for slash commands
+│   └── platforms/        # Adapters: telegram, discord, slack, whatsapp, homeassistant, signal
 ├── acp_adapter/          # ACP server (VS Code / Zed / JetBrains integration)
 ├── cron/                 # Scheduler (jobs.py, scheduler.py)
 ├── environments/         # RL training environments (Atropos)
@@ -192,62 +179,9 @@ if canonical == "mycommand":
 
 ---
 
-## TUI Architecture (ui-tui + tui_gateway)
-
-The TUI is a full replacement for the classic (prompt_toolkit) CLI, activated via `hermes --tui` or `HERMES_TUI=1`.
-
-### Process Model
-
-```
-hermes --tui
-  └─ Node (Ink)  ──stdio JSON-RPC──  Python (tui_gateway)
-       │                                  └─ AIAgent + tools + sessions
-       └─ renders transcript, composer, prompts, activity
-```
-
-TypeScript owns the screen. Python owns sessions, tools, model calls, and slash command logic.
-
-### Transport
-
-Newline-delimited JSON-RPC over stdio. Requests from Ink, events from Python. See `tui_gateway/server.py` for the full method/event catalog.
-
-### Key Surfaces
-
-| Surface | Ink component | Gateway method |
-|---------|---------------|----------------|
-| Chat streaming | `app.tsx` + `messageLine.tsx` | `prompt.submit` → `message.delta/complete` |
-| Tool activity | `thinking.tsx` | `tool.start/progress/complete` |
-| Approvals | `prompts.tsx` | `approval.respond` ← `approval.request` |
-| Clarify/sudo/secret | `prompts.tsx`, `maskedPrompt.tsx` | `clarify/sudo/secret.respond` |
-| Session picker | `sessionPicker.tsx` | `session.list/resume` |
-| Slash commands | Local handler + fallthrough | `slash.exec` → `_SlashWorker`, `command.dispatch` |
-| Completions | `useCompletion` hook | `complete.slash`, `complete.path` |
-| Theming | `theme.ts` + `branding.tsx` | `gateway.ready` with skin data |
-
-### Slash Command Flow
-
-1. Built-in client commands (`/help`, `/quit`, `/clear`, `/resume`, `/copy`, `/paste`, etc.) handled locally in `app.tsx`
-2. Everything else → `slash.exec` (runs in persistent `_SlashWorker` subprocess) → `command.dispatch` fallback
-
-### Dev Commands
-
-```bash
-cd ui-tui
-npm install       # first time
-npm run dev       # watch mode (rebuilds hermes-ink + tsx --watch)
-npm start         # production
-npm run build     # full build (hermes-ink + tsc)
-npm run type-check # typecheck only (tsc --noEmit)
-npm run lint      # eslint
-npm run fmt       # prettier
-npm test          # vitest
-```
-
----
-
 ## Adding New Tools
 
-Requires changes in **2 files**:
+Requires changes in **3 files**:
 
 **1. Create `tools/your_tool.py`:**
 ```python
@@ -270,9 +204,9 @@ registry.register(
 )
 ```
 
-**2. Add to `toolsets.py`** — either `_HERMES_CORE_TOOLS` (all platforms) or a new toolset.
+**2. Add import** in `model_tools.py` `_discover_tools()` list.
 
-Auto-discovery: any `tools/*.py` file with a top-level `registry.register()` call is imported automatically — no manual import list to maintain.
+**3. Add to `toolsets.py`** — either `_HERMES_CORE_TOOLS` (all platforms) or a new toolset.
 
 The registry handles schema collection, dispatch, availability checking, and error wrapping. All handlers MUST return a JSON string.
 
@@ -417,9 +351,8 @@ Cache-breaking forces dramatically higher costs. The ONLY time we alter context
 
 ### Background Process Notifications (Gateway)
 
-When `terminal(background=true, notify_on_complete=true)` is used, the gateway runs a watcher that
-detects process completion and triggers a new agent turn. Control verbosity of background process
-messages with `display.background_process_notifications`
+When `terminal(background=true, check_interval=...)` is used, the gateway runs a watcher that
+pushes status updates to the user's chat. Control verbosity with `display.background_process_notifications`
 in config.yaml (or `HERMES_BACKGROUND_NOTIFICATIONS` env var):
 
 - `all` — running-output updates + final message (default)
@@ -524,45 +457,13 @@ def profile_env(tmp_path, monkeypatch):
 
 ## Testing
 
-**ALWAYS use `scripts/run_tests.sh`** — do not call `pytest` directly. The script enforces
-hermetic environment parity with CI (unset credential vars, TZ=UTC, LANG=C.UTF-8,
-4 xdist workers matching GHA ubuntu-latest). Direct `pytest` on a 16+ core
-developer machine with API keys set diverges from CI in ways that have caused
-multiple "works locally, fails in CI" incidents (and the reverse).
-
-```bash
-scripts/run_tests.sh                                  # full suite, CI-parity
-scripts/run_tests.sh tests/gateway/                   # one directory
-scripts/run_tests.sh tests/agent/test_foo.py::test_x  # one test
-scripts/run_tests.sh -v --tb=long                     # pass-through pytest flags
-```
-
-### Why the wrapper (and why the old "just call pytest" doesn't work)
-
-Five real sources of local-vs-CI drift the script closes:
-
-| | Without wrapper | With wrapper |
-|---|---|---|
-| Provider API keys | Whatever is in your env (auto-detects pool) | All `*_API_KEY`/`*_TOKEN`/etc. unset |
-| HOME / `~/.hermes/` | Your real config+auth.json | Temp dir per test |
-| Timezone | Local TZ (PDT etc.) | UTC |
-| Locale | Whatever is set | C.UTF-8 |
-| xdist workers | `-n auto` = all cores (20+ on a workstation) | `-n 4` matching CI |
-
-`tests/conftest.py` also enforces points 1-4 as an autouse fixture so ANY pytest
-invocation (including IDE integrations) gets hermetic behavior — but the wrapper
-is belt-and-suspenders.
-
-### Running without the wrapper (only if you must)
-
-If you can't use the wrapper (e.g. on Windows or inside an IDE that shells
-pytest directly), at minimum activate the venv and pass `-n 4`:
-
 ```bash
 source venv/bin/activate
-python -m pytest tests/ -q -n 4
+python -m pytest tests/ -q          # Full suite (~3000 tests, ~3 min)
+python -m pytest tests/test_model_tools.py -q   # Toolset resolution
+python -m pytest tests/test_cli_init.py -q       # CLI config loading
+python -m pytest tests/gateway/ -q               # Gateway tests
+python -m pytest tests/tools/ -q                 # Tool-level tests
 ```
 
-Worker count above 4 will surface test-ordering flakes that CI never sees.
-
 Always run the full suite before pushing changes.

Dockerfile

@@ -1,54 +1,28 @@
-FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
-FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
 FROM debian:13.4
 
 # Disable Python stdout buffering to ensure logs are printed immediately
 ENV PYTHONUNBUFFERED=1
 
-# Store Playwright browsers outside the volume mount so the build-time
-# install survives the /opt/data volume overlay at runtime.
-ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
-
 # Install system dependencies in one layer, clear APT cache
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git && \
+        build-essential nodejs npm python3 python3-pip ripgrep ffmpeg gcc python3-dev libffi-dev && \
     rm -rf /var/lib/apt/lists/*
 
-# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
-RUN useradd -u 10000 -m -d /opt/data hermes
-
-COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
-COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
-
+COPY . /opt/hermes
 WORKDIR /opt/hermes
 
-# ---------- Layer-cached dependency install ----------
-# Copy only package manifests first so npm install + Playwright are cached
-# unless the lockfiles themselves change.
-COPY package.json package-lock.json ./
-COPY web/package.json web/package-lock.json web/
-
-RUN npm install --prefer-offline --no-audit && \
+# Install Python and Node dependencies in one layer, no cache
+RUN pip install --no-cache-dir -e ".[all]" --break-system-packages && \
+    npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
-    (cd web && npm install --prefer-offline --no-audit) && \
+    cd /opt/hermes/scripts/whatsapp-bridge && \
+    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 . .
+WORKDIR /opt/hermes
+RUN chmod +x /opt/hermes/docker/entrypoint.sh
 
-# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
-RUN cd web && npm run build
-
-# ---------- Python virtualenv ----------
-RUN chown hermes:hermes /opt/hermes
-USER hermes
-RUN uv venv && \
-    uv pip install --no-cache-dir -e ".[all]"
-
-# ---------- Runtime ----------
-ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
 ENV HERMES_HOME=/opt/data
 VOLUME [ "/opt/data" ]
 ENTRYPOINT [ "/opt/hermes/docker/entrypoint.sh" ]

README.md

@@ -13,7 +13,7 @@
 
 **The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
 
-Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
+Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
 
 <table>
 <tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr>
@@ -33,10 +33,8 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), [Open
 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
 ```
 
-Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.
+Works on Linux, macOS, and WSL2. The installer handles everything — Python, Node.js, dependencies, and the `hermes` command. No prerequisites except git.
 
-> **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies.
->
 > **Windows:** Native Windows is not supported. Please install [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) and run the command above.
 
 After installation:
@@ -141,18 +139,11 @@ See `hermes claw migrate --help` for all options, or use the `openclaw-migration
 
 We welcome contributions! See the [Contributing Guide](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) for development setup, code style, and PR process.
 
-Quick start for contributors — clone and go with `setup-hermes.sh`:
+Quick start for contributors:
 
 ```bash
 git clone https://github.com/NousResearch/hermes-agent.git
 cd hermes-agent
-./setup-hermes.sh     # installs uv, creates venv, installs .[all], symlinks ~/.local/bin/hermes
-./hermes              # auto-detects the venv, no need to `source` first
-```
-
-Manual path (equivalent to the above):
-
-```bash
 curl -LsSf https://astral.sh/uv/install.sh | sh
 uv venv venv --python 3.11
 source venv/bin/activate
@@ -174,7 +165,6 @@ python -m pytest tests/ -q
 - 📚 [Skills Hub](https://agentskills.io)
 - 🐛 [Issues](https://github.com/NousResearch/hermes-agent/issues)
 - 💡 [Discussions](https://github.com/NousResearch/hermes-agent/discussions)
-- 🔌 [HermesClaw](https://github.com/AaronWong1999/hermesclaw) — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account.
 
 ---
 

RELEASE_v0.10.0.md

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

RELEASE_v0.9.0.md

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

SECURITY.md

@@ -1,84 +0,0 @@
-# Hermes Agent Security Policy
-
-This document outlines the security protocols, trust model, and deployment hardening guidelines for the **Hermes Agent** project.
-
-## 1. Vulnerability Reporting
-
-Hermes Agent does **not** operate a bug bounty program. Security issues should be reported via [GitHub Security Advisories (GHSA)](https://github.com/NousResearch/hermes-agent/security/advisories/new) or by emailing **security@nousresearch.com**. Do not open public issues for security vulnerabilities.
-
-### Required Submission Details
-- **Title & Severity:** Concise description and CVSS score/rating.
-- **Affected Component:** Exact file path and line range (e.g., `tools/approval.py:120-145`).
-- **Environment:** Output of `hermes version`, commit SHA, OS, and Python version.
-- **Reproduction:** Step-by-step Proof-of-Concept (PoC) against `main` or the latest release.
-- **Impact:** Explanation of what trust boundary was crossed.
-
----
-
-## 2. Trust Model
-
-The core assumption is that Hermes is a **personal agent** with one trusted operator.
-
-### Operator & Session Trust
-- **Single Tenant:** The system protects the operator from LLM actions, not from malicious co-tenants. Multi-user isolation must happen at the OS/host level.
-- **Gateway Security:** Authorized callers (Telegram, Discord, Slack, etc.) receive equal trust. Session keys are used for routing, not as authorization boundaries.
-- **Execution:** Defaults to `terminal.backend: local` (direct host execution). Container isolation (Docker, Modal, Daytona) is opt-in for sandboxing.
-
-### Dangerous Command Approval
-The approval system (`tools/approval.py`) is a core security boundary. Terminal commands, file operations, and other potentially destructive actions are gated behind explicit user confirmation before execution. The approval mode is configurable via `approvals.mode` in `config.yaml`:
-- `"on"` (default) — prompts the user to approve dangerous commands.
-- `"auto"` — auto-approves after a configurable delay.
-- `"off"` — disables the gate entirely (break-glass; see Section 3).
-
-### Output Redaction
-`agent/redact.py` strips secret-like patterns (API keys, tokens, credentials) from all display output before it reaches the terminal or gateway platform. This prevents accidental credential leakage in chat logs, tool previews, and response text. Redaction operates on the display layer only — underlying values remain intact for internal agent operations.
-
-### Skills vs. MCP Servers
-- **Installed Skills:** High trust. Equivalent to local host code; skills can read environment variables and run arbitrary commands.
-- **MCP Servers:** Lower trust. MCP subprocesses receive a filtered environment (`_build_safe_env()` in `tools/mcp_tool.py`) — only safe baseline variables (`PATH`, `HOME`, `XDG_*`) plus variables explicitly declared in the server's `env` config block are passed through. Host credentials are stripped by default. Additionally, packages invoked via `npx`/`uvx` are checked against the OSV malware database before spawning.
-
-### Code Execution Sandbox
-The `execute_code` tool (`tools/code_execution_tool.py`) runs LLM-generated Python scripts in a child process with API keys and tokens stripped from the environment to prevent credential exfiltration. Only environment variables explicitly declared by loaded skills (via `env_passthrough`) or by the user in `config.yaml` (`terminal.env_passthrough`) are passed through. The child accesses Hermes tools via RPC, not direct API calls.
-
-### Subagents
-- **No recursive delegation:** The `delegate_task` tool is disabled for child agents.
-- **Depth limit:** `MAX_DEPTH = 2` — parent (depth 0) can spawn a child (depth 1); grandchildren are rejected.
-- **Memory isolation:** Subagents run with `skip_memory=True` and do not have access to the parent's persistent memory provider. The parent receives only the task prompt and final response as an observation.
-
----
-
-## 3. Out of Scope (Non-Vulnerabilities)
-
-The following scenarios are **not** considered security breaches:
-- **Prompt Injection:** Unless it results in a concrete bypass of the approval system, toolset restrictions, or container sandbox.
-- **Public Exposure:** Deploying the gateway to the public internet without external authentication or network protection.
-- **Trusted State Access:** Reports that require pre-existing write access to `~/.hermes/`, `.env`, or `config.yaml` (these are operator-owned files).
-- **Default Behavior:** Host-level command execution when `terminal.backend` is set to `local` — this is the documented default, not a vulnerability.
-- **Configuration Trade-offs:** Intentional break-glass settings such as `approvals.mode: "off"` or `terminal.backend: local` in production.
-- **Tool-level read/access restrictions:** The agent has unrestricted shell access via the `terminal` tool by design. Reports that a specific tool (e.g., `read_file`) can access a resource are not vulnerabilities if the same access is available through `terminal`. Tool-level deny lists only constitute a meaningful security boundary when paired with equivalent restrictions on the terminal side (as with write operations, where `WRITE_DENIED_PATHS` is paired with the dangerous command approval system).
-
----
-
-## 4. Deployment Hardening & Best Practices
-
-### Filesystem & Network
-- **Production sandboxing:** Use container backends (`docker`, `modal`, `daytona`) instead of `local` for untrusted workloads.
-- **File permissions:** Run as non-root (the Docker image uses UID 10000); protect credentials with `chmod 600 ~/.hermes/.env` on local installs.
-- **Network exposure:** Do not expose the gateway or API server to the public internet without VPN, Tailscale, or firewall protection. SSRF protection is enabled by default across all gateway platform adapters (Telegram, Discord, Slack, Matrix, Mattermost, etc.) with redirect validation. Note: the local terminal backend does not apply SSRF filtering, as it operates within the trusted operator's environment.
-
-### Skills & Supply Chain
-- **Skill installation:** Review Skills Guard reports (`tools/skills_guard.py`) before installing third-party skills. The audit log at `~/.hermes/skills/.hub/audit.log` tracks every install and removal.
-- **MCP safety:** OSV malware checking runs automatically for `npx`/`uvx` packages before MCP server processes are spawned.
-- **CI/CD:** GitHub Actions are pinned to full commit SHAs. The `supply-chain-audit.yml` workflow blocks PRs containing `.pth` files or suspicious `base64`+`exec` patterns.
-
-### Credential Storage
-- API keys and tokens belong exclusively in `~/.hermes/.env` — never in `config.yaml` or checked into version control.
-- The credential pool system (`agent/credential_pool.py`) handles key rotation and fallback. Credentials are resolved from environment variables, not stored in plaintext databases.
-
----
-
-## 5. Disclosure Process
-
-- **Coordinated Disclosure:** 90-day window or until a fix is released, whichever comes first.
-- **Communication:** All updates occur via the GHSA thread or email correspondence with security@nousresearch.com.
-- **Credits:** Reporters are credited in release notes unless anonymity is requested.

acp_adapter/entry.py

@@ -20,46 +20,6 @@ from pathlib import Path
 from hermes_constants import get_hermes_home
 
 
-# Methods clients send as periodic liveness probes. They are not part of the
-# ACP schema, so the acp router correctly returns JSON-RPC -32601 to the
-# caller — but the supervisor task that dispatches the request then surfaces
-# the raised RequestError via ``logging.exception("Background task failed")``,
-# which dumps a traceback to stderr every probe interval. Clients like
-# acp-bridge already treat the -32601 response as "agent alive", so the
-# traceback is pure noise. We keep the protocol response intact and only
-# silence the stderr noise for this specific benign case.
-_BENIGN_PROBE_METHODS = frozenset({"ping", "health", "healthcheck"})
-
-
-class _BenignProbeMethodFilter(logging.Filter):
-    """Suppress acp 'Background task failed' tracebacks caused by unknown
-    liveness-probe methods (e.g. ``ping``) while leaving every other
-    background-task error — including method_not_found for any non-probe
-    method — visible in stderr.
-    """
-
-    def filter(self, record: logging.LogRecord) -> bool:
-        if record.getMessage() != "Background task failed":
-            return True
-        exc_info = record.exc_info
-        if not exc_info:
-            return True
-        exc = exc_info[1]
-        # Imported lazily so this module stays importable when the optional
-        # ``agent-client-protocol`` dependency is not installed.
-        try:
-            from acp.exceptions import RequestError
-        except ImportError:
-            return True
-        if not isinstance(exc, RequestError):
-            return True
-        if getattr(exc, "code", None) != -32601:
-            return True
-        data = getattr(exc, "data", None)
-        method = data.get("method") if isinstance(data, dict) else None
-        return method not in _BENIGN_PROBE_METHODS
-
-
 def _setup_logging() -> None:
     """Route all logging to stderr so stdout stays clean for ACP stdio."""
     handler = logging.StreamHandler(sys.stderr)
@@ -69,7 +29,6 @@ def _setup_logging() -> None:
             datefmt="%Y-%m-%d %H:%M:%S",
         )
     )
-    handler.addFilter(_BenignProbeMethodFilter())
     root = logging.getLogger()
     root.handlers.clear()
     root.addHandler(handler)

acp_adapter/events.py

@@ -49,7 +49,6 @@ def make_tool_progress_cb(
     session_id: str,
     loop: asyncio.AbstractEventLoop,
     tool_call_ids: Dict[str, Deque[str]],
-    tool_call_meta: Dict[str, Dict[str, Any]],
 ) -> Callable:
     """Create a ``tool_progress_callback`` for AIAgent.
 
@@ -85,16 +84,6 @@ def make_tool_progress_cb(
             tool_call_ids[name] = queue
         queue.append(tc_id)
 
-        snapshot = None
-        if name in {"write_file", "patch", "skill_manage"}:
-            try:
-                from agent.display import capture_local_edit_snapshot
-
-                snapshot = capture_local_edit_snapshot(name, args)
-            except Exception:
-                logger.debug("Failed to capture ACP edit snapshot for %s", name, exc_info=True)
-        tool_call_meta[tc_id] = {"args": args, "snapshot": snapshot}
-
         update = build_tool_start(tc_id, name, args)
         _send_update(conn, session_id, loop, update)
 
@@ -130,7 +119,6 @@ def make_step_cb(
     session_id: str,
     loop: asyncio.AbstractEventLoop,
     tool_call_ids: Dict[str, Deque[str]],
-    tool_call_meta: Dict[str, Dict[str, Any]],
 ) -> Callable:
     """Create a ``step_callback`` for AIAgent.
 
@@ -144,12 +132,10 @@ def make_step_cb(
             for tool_info in prev_tools:
                 tool_name = None
                 result = None
-                function_args = None
 
                 if isinstance(tool_info, dict):
                     tool_name = tool_info.get("name") or tool_info.get("function_name")
                     result = tool_info.get("result") or tool_info.get("output")
-                    function_args = tool_info.get("arguments") or tool_info.get("args")
                 elif isinstance(tool_info, str):
                     tool_name = tool_info
 
@@ -159,13 +145,8 @@ def make_step_cb(
                     tool_call_ids[tool_name] = queue
                 if tool_name and queue:
                     tc_id = queue.popleft()
-                    meta = tool_call_meta.pop(tc_id, {})
                     update = build_tool_complete(
-                        tc_id,
-                        tool_name,
-                        result=str(result) if result is not None else None,
-                        function_args=function_args or meta.get("args"),
-                        snapshot=meta.get("snapshot"),
+                        tc_id, tool_name, result=str(result) if result is not None else None
                     )
                     _send_update(conn, session_id, loop, update)
                     if not queue:

acp_adapter/server.py

@@ -26,7 +26,6 @@ from acp.schema import (
     McpServerHttp,
     McpServerSse,
     McpServerStdio,
-    ModelInfo,
     NewSessionResponse,
     PromptResponse,
     ResumeSessionResponse,
@@ -37,8 +36,6 @@ from acp.schema import (
     SessionCapabilities,
     SessionForkCapabilities,
     SessionListCapabilities,
-    SessionModelState,
-    SessionResumeCapabilities,
     SessionInfo,
     TextContentBlock,
     UnstructuredCommandInput,
@@ -149,98 +146,6 @@ class HermesACPAgent(acp.Agent):
         self._conn = conn
         logger.info("ACP client connected")
 
-    @staticmethod
-    def _encode_model_choice(provider: str | None, model: str | None) -> str:
-        """Encode a model selection so ACP clients can keep provider context."""
-        raw_model = str(model or "").strip()
-        if not raw_model:
-            return ""
-        raw_provider = str(provider or "").strip().lower()
-        if not raw_provider:
-            return raw_model
-        return f"{raw_provider}:{raw_model}"
-
-    def _build_model_state(self, state: SessionState) -> SessionModelState | None:
-        """Return the ACP model selector payload for editors like Zed."""
-        model = str(state.model or getattr(state.agent, "model", "") or "").strip()
-        provider = getattr(state.agent, "provider", None) or detect_provider() or "openrouter"
-
-        try:
-            from hermes_cli.models import curated_models_for_provider, normalize_provider, provider_label
-
-            normalized_provider = normalize_provider(provider)
-            provider_name = provider_label(normalized_provider)
-            available_models: list[ModelInfo] = []
-            seen_ids: set[str] = set()
-
-            for model_id, description in curated_models_for_provider(normalized_provider):
-                rendered_model = str(model_id or "").strip()
-                if not rendered_model:
-                    continue
-                choice_id = self._encode_model_choice(normalized_provider, rendered_model)
-                if choice_id in seen_ids:
-                    continue
-                desc_parts = [f"Provider: {provider_name}"]
-                if description:
-                    desc_parts.append(str(description).strip())
-                if rendered_model == model:
-                    desc_parts.append("current")
-                available_models.append(
-                    ModelInfo(
-                        model_id=choice_id,
-                        name=rendered_model,
-                        description=" • ".join(part for part in desc_parts if part),
-                    )
-                )
-                seen_ids.add(choice_id)
-
-            current_model_id = self._encode_model_choice(normalized_provider, model)
-            if current_model_id and current_model_id not in seen_ids:
-                available_models.insert(
-                    0,
-                    ModelInfo(
-                        model_id=current_model_id,
-                        name=model,
-                        description=f"Provider: {provider_name} • current",
-                    ),
-                )
-
-            if available_models:
-                return SessionModelState(
-                    available_models=available_models,
-                    current_model_id=current_model_id or available_models[0].model_id,
-                )
-        except Exception:
-            logger.debug("Could not build ACP model state", exc_info=True)
-
-        if not model:
-            return None
-
-        fallback_choice = self._encode_model_choice(provider, model)
-        return SessionModelState(
-            available_models=[ModelInfo(model_id=fallback_choice, name=model)],
-            current_model_id=fallback_choice,
-        )
-
-    @staticmethod
-    def _resolve_model_selection(raw_model: str, current_provider: str) -> tuple[str, str]:
-        """Resolve ``provider:model`` input into the provider and normalized model id."""
-        target_provider = current_provider
-        new_model = raw_model.strip()
-
-        try:
-            from hermes_cli.models import detect_provider_for_model, parse_model_input
-
-            target_provider, new_model = parse_model_input(new_model, current_provider)
-            if target_provider == current_provider:
-                detected = detect_provider_for_model(new_model, current_provider)
-                if detected:
-                    target_provider, new_model = detected
-        except Exception:
-            logger.debug("Provider detection failed, using model as-is", exc_info=True)
-
-        return target_provider, new_model
-
     async def _register_session_mcp_servers(
         self,
         state: SessionState,
@@ -340,11 +245,9 @@ class HermesACPAgent(acp.Agent):
             protocol_version=acp.PROTOCOL_VERSION,
             agent_info=Implementation(name="hermes-agent", version=HERMES_VERSION),
             agent_capabilities=AgentCapabilities(
-                load_session=True,
                 session_capabilities=SessionCapabilities(
                     fork=SessionForkCapabilities(),
                     list=SessionListCapabilities(),
-                    resume=SessionResumeCapabilities(),
                 ),
             ),
             auth_methods=auth_methods,
@@ -367,10 +270,7 @@ class HermesACPAgent(acp.Agent):
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("New session %s (cwd=%s)", state.session_id, cwd)
         self._schedule_available_commands_update(state.session_id)
-        return NewSessionResponse(
-            session_id=state.session_id,
-            models=self._build_model_state(state),
-        )
+        return NewSessionResponse(session_id=state.session_id)
 
     async def load_session(
         self,
@@ -386,7 +286,7 @@ class HermesACPAgent(acp.Agent):
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Loaded session %s", session_id)
         self._schedule_available_commands_update(session_id)
-        return LoadSessionResponse(models=self._build_model_state(state))
+        return LoadSessionResponse()
 
     async def resume_session(
         self,
@@ -402,7 +302,7 @@ class HermesACPAgent(acp.Agent):
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Resumed session %s", state.session_id)
         self._schedule_available_commands_update(state.session_id)
-        return ResumeSessionResponse(models=self._build_model_state(state))
+        return ResumeSessionResponse()
 
     async def cancel(self, session_id: str, **kwargs: Any) -> None:
         state = self.session_manager.get_session(session_id)
@@ -437,20 +337,11 @@ class HermesACPAgent(acp.Agent):
         cwd: str | None = None,
         **kwargs: Any,
     ) -> ListSessionsResponse:
-        infos = self.session_manager.list_sessions(cwd=cwd)
-        sessions = []
-        for s in infos:
-            updated_at = s.get("updated_at")
-            if updated_at is not None and not isinstance(updated_at, str):
-                updated_at = str(updated_at)
-            sessions.append(
-                SessionInfo(
-                    session_id=s["session_id"],
-                    cwd=s["cwd"],
-                    title=s.get("title"),
-                    updated_at=updated_at,
-                )
-            )
+        infos = self.session_manager.list_sessions()
+        sessions = [
+            SessionInfo(session_id=s["session_id"], cwd=s["cwd"])
+            for s in infos
+        ]
         return ListSessionsResponse(sessions=sessions)
 
     # ---- Prompt (core) ------------------------------------------------------
@@ -495,13 +386,12 @@ class HermesACPAgent(acp.Agent):
             state.cancel_event.clear()
 
         tool_call_ids: dict[str, Deque[str]] = defaultdict(deque)
-        tool_call_meta: dict[str, dict[str, Any]] = {}
         previous_approval_cb = None
 
         if conn:
-            tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
+            tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids)
             thinking_cb = make_thinking_cb(conn, session_id, loop)
-            step_cb = make_step_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
+            step_cb = make_step_cb(conn, session_id, loop, tool_call_ids)
             message_cb = make_message_cb(conn, session_id, loop)
             approval_cb = make_approval_callback(conn.request_permission, loop, session_id)
         else:
@@ -556,31 +446,19 @@ class HermesACPAgent(acp.Agent):
             self.session_manager.save_session(session_id)
 
         final_response = result.get("final_response", "")
-        if final_response:
-            try:
-                from agent.title_generator import maybe_auto_title
-
-                maybe_auto_title(
-                    self.session_manager._get_db(),
-                    session_id,
-                    user_text,
-                    final_response,
-                    state.history,
-                )
-            except Exception:
-                logger.debug("Failed to auto-title ACP session %s", session_id, exc_info=True)
         if final_response and conn:
             update = acp.update_agent_message_text(final_response)
             await conn.session_update(session_id, update)
 
         usage = None
-        if any(result.get(key) is not None for key in ("prompt_tokens", "completion_tokens", "total_tokens")):
+        usage_data = result.get("usage")
+        if usage_data and isinstance(usage_data, dict):
             usage = Usage(
-                input_tokens=result.get("prompt_tokens", 0),
-                output_tokens=result.get("completion_tokens", 0),
-                total_tokens=result.get("total_tokens", 0),
-                thought_tokens=result.get("reasoning_tokens"),
-                cached_read_tokens=result.get("cache_read_tokens"),
+                input_tokens=usage_data.get("prompt_tokens", 0),
+                output_tokens=usage_data.get("completion_tokens", 0),
+                total_tokens=usage_data.get("total_tokens", 0),
+                thought_tokens=usage_data.get("reasoning_tokens"),
+                cached_read_tokens=usage_data.get("cached_tokens"),
             )
 
         stop_reason = "cancelled" if state.cancel_event and state.cancel_event.is_set() else "end_turn"
@@ -676,15 +554,27 @@ class HermesACPAgent(acp.Agent):
             provider = getattr(state.agent, "provider", None) or "auto"
             return f"Current model: {model}\nProvider: {provider}"
 
+        new_model = args.strip()
+        target_provider = None
         current_provider = getattr(state.agent, "provider", None) or "openrouter"
-        target_provider, new_model = self._resolve_model_selection(args, current_provider)
+
+        # Auto-detect provider for the requested model
+        try:
+            from hermes_cli.models import parse_model_input, detect_provider_for_model
+            target_provider, new_model = parse_model_input(new_model, current_provider)
+            if target_provider == current_provider:
+                detected = detect_provider_for_model(new_model, current_provider)
+                if detected:
+                    target_provider, new_model = detected
+        except Exception:
+            logger.debug("Provider detection failed, using model as-is", exc_info=True)
 
         state.model = new_model
         state.agent = self.session_manager._make_agent(
             session_id=state.session_id,
             cwd=state.cwd,
             model=new_model,
-            requested_provider=target_provider,
+            requested_provider=target_provider or current_provider,
         )
         self.session_manager.save_session(state.session_id)
         provider_label = getattr(state.agent, "provider", None) or target_provider or current_provider
@@ -786,30 +676,20 @@ class HermesACPAgent(acp.Agent):
         """Switch the model for a session (called by ACP protocol)."""
         state = self.session_manager.get_session(session_id)
         if state:
+            state.model = model_id
             current_provider = getattr(state.agent, "provider", None)
-            requested_provider, resolved_model = self._resolve_model_selection(
-                model_id,
-                current_provider or "openrouter",
-            )
-            state.model = resolved_model
-            provider_changed = bool(current_provider and requested_provider != current_provider)
-            current_base_url = None if provider_changed else getattr(state.agent, "base_url", None)
-            current_api_mode = None if provider_changed else getattr(state.agent, "api_mode", None)
+            current_base_url = getattr(state.agent, "base_url", None)
+            current_api_mode = getattr(state.agent, "api_mode", None)
             state.agent = self.session_manager._make_agent(
                 session_id=session_id,
                 cwd=state.cwd,
-                model=resolved_model,
-                requested_provider=requested_provider,
+                model=model_id,
+                requested_provider=current_provider,
                 base_url=current_base_url,
                 api_mode=current_api_mode,
             )
             self.session_manager.save_session(session_id)
-            logger.info(
-                "Session %s: model switched to %s via provider %s",
-                session_id,
-                resolved_model,
-                requested_provider,
-            )
+            logger.info("Session %s: model switched to %s", session_id, model_id)
             return SetSessionModelResponse()
         logger.warning("Session %s: model switch requested for missing session", session_id)
         return None

acp_adapter/session.py

@@ -13,12 +13,8 @@ from hermes_constants import get_hermes_home
 import copy
 import json
 import logging
-import os
-import re
 import sys
-import time
 import uuid
-from datetime import datetime, timezone
 from dataclasses import dataclass, field
 from threading import Lock
 from typing import Any, Dict, List, Optional
@@ -26,64 +22,6 @@ from typing import Any, Dict, List, Optional
 logger = logging.getLogger(__name__)
 
 
-def _normalize_cwd_for_compare(cwd: str | None) -> str:
-    raw = str(cwd or ".").strip()
-    if not raw:
-        raw = "."
-    expanded = os.path.expanduser(raw)
-
-    # Normalize Windows drive paths into the equivalent WSL mount form so
-    # ACP history filters match the same workspace across Windows and WSL.
-    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:]}"
-
-    return os.path.normpath(expanded)
-
-
-def _build_session_title(title: Any, preview: Any, cwd: str | None) -> str:
-    explicit = str(title or "").strip()
-    if explicit:
-        return explicit
-    preview_text = str(preview or "").strip()
-    if preview_text:
-        return preview_text
-    leaf = os.path.basename(str(cwd or "").rstrip("/\\"))
-    return leaf or "New thread"
-
-
-def _format_updated_at(value: Any) -> str | None:
-    if value is None:
-        return None
-    if isinstance(value, str) and value.strip():
-        return value
-    try:
-        return datetime.fromtimestamp(float(value), tz=timezone.utc).isoformat()
-    except Exception:
-        return None
-
-
-def _updated_at_sort_key(value: Any) -> float:
-    if value is None:
-        return float("-inf")
-    if isinstance(value, (int, float)):
-        return float(value)
-    raw = str(value).strip()
-    if not raw:
-        return float("-inf")
-    try:
-        return datetime.fromisoformat(raw.replace("Z", "+00:00")).timestamp()
-    except Exception:
-        try:
-            return float(raw)
-        except Exception:
-            return float("-inf")
-
-
 def _acp_stderr_print(*args, **kwargs) -> None:
     """Best-effort human-readable output sink for ACP stdio sessions.
 
@@ -224,78 +162,47 @@ class SessionManager:
         logger.info("Forked ACP session %s -> %s", session_id, new_id)
         return state
 
-    def list_sessions(self, cwd: str | None = None) -> List[Dict[str, Any]]:
+    def list_sessions(self) -> List[Dict[str, Any]]:
         """Return lightweight info dicts for all sessions (memory + database)."""
-        normalized_cwd = _normalize_cwd_for_compare(cwd) if cwd else None
-        db = self._get_db()
-        persisted_rows: dict[str, dict[str, Any]] = {}
-
-        if db is not None:
-            try:
-                for row in db.list_sessions_rich(source="acp", limit=1000):
-                    persisted_rows[str(row["id"])] = dict(row)
-            except Exception:
-                logger.debug("Failed to load ACP sessions from DB", exc_info=True)
-
         # Collect in-memory sessions first.
         with self._lock:
             seen_ids = set(self._sessions.keys())
-            results = []
-            for s in self._sessions.values():
-                history_len = len(s.history)
-                if history_len <= 0:
-                    continue
-                if normalized_cwd and _normalize_cwd_for_compare(s.cwd) != normalized_cwd:
-                    continue
-                persisted = persisted_rows.get(s.session_id, {})
-                preview = next(
-                    (
-                        str(msg.get("content") or "").strip()
-                        for msg in s.history
-                        if msg.get("role") == "user" and str(msg.get("content") or "").strip()
-                    ),
-                    persisted.get("preview") or "",
-                )
-                results.append(
-                    {
-                        "session_id": s.session_id,
-                        "cwd": s.cwd,
-                        "model": s.model,
-                        "history_len": history_len,
-                        "title": _build_session_title(persisted.get("title"), preview, s.cwd),
-                        "updated_at": _format_updated_at(
-                            persisted.get("last_active") or persisted.get("started_at") or time.time()
-                        ),
-                    }
-                )
+            results = [
+                {
+                    "session_id": s.session_id,
+                    "cwd": s.cwd,
+                    "model": s.model,
+                    "history_len": len(s.history),
+                }
+                for s in self._sessions.values()
+            ]
 
         # Merge any persisted sessions not currently in memory.
-        for sid, row in persisted_rows.items():
-            if sid in seen_ids:
-                continue
-            message_count = int(row.get("message_count") or 0)
-            if message_count <= 0:
-                continue
-            # Extract cwd from model_config JSON.
-            session_cwd = "."
-            mc = row.get("model_config")
-            if mc:
-                try:
-                    session_cwd = json.loads(mc).get("cwd", ".")
-                except (json.JSONDecodeError, TypeError):
-                    pass
-            if normalized_cwd and _normalize_cwd_for_compare(session_cwd) != normalized_cwd:
-                continue
-            results.append({
-                "session_id": sid,
-                "cwd": session_cwd,
-                "model": row.get("model") or "",
-                "history_len": message_count,
-                "title": _build_session_title(row.get("title"), row.get("preview"), session_cwd),
-                "updated_at": _format_updated_at(row.get("last_active") or row.get("started_at")),
-            })
+        db = self._get_db()
+        if db is not None:
+            try:
+                rows = db.search_sessions(source="acp", limit=1000)
+                for row in rows:
+                    sid = row["id"]
+                    if sid in seen_ids:
+                        continue
+                    # Extract cwd from model_config JSON.
+                    cwd = "."
+                    mc = row.get("model_config")
+                    if mc:
+                        try:
+                            cwd = json.loads(mc).get("cwd", ".")
+                        except (json.JSONDecodeError, TypeError):
+                            pass
+                    results.append({
+                        "session_id": sid,
+                        "cwd": cwd,
+                        "model": row.get("model") or "",
+                        "history_len": row.get("message_count") or 0,
+                    })
+            except Exception:
+                logger.debug("Failed to list ACP sessions from DB", exc_info=True)
 
-        results.sort(key=lambda item: _updated_at_sort_key(item.get("updated_at")), reverse=True)
         return results
 
     def update_cwd(self, session_id: str, cwd: str) -> Optional[SessionState]:

acp_adapter/tools.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import json
 import uuid
 from typing import Any, Dict, List, Optional
 
@@ -97,170 +96,6 @@ def build_tool_title(tool_name: str, args: Dict[str, Any]) -> str:
     return tool_name
 
 
-def _build_patch_mode_content(patch_text: str) -> List[Any]:
-    """Parse V4A patch mode input into ACP diff blocks when possible."""
-    if not patch_text:
-        return [acp.tool_content(acp.text_block(""))]
-
-    try:
-        from tools.patch_parser import OperationType, parse_v4a_patch
-
-        operations, error = parse_v4a_patch(patch_text)
-        if error or not operations:
-            return [acp.tool_content(acp.text_block(patch_text))]
-
-        content: List[Any] = []
-        for op in operations:
-            if op.operation == OperationType.UPDATE:
-                old_chunks: list[str] = []
-                new_chunks: list[str] = []
-                for hunk in op.hunks:
-                    old_lines = [line.content for line in hunk.lines if line.prefix in (" ", "-")]
-                    new_lines = [line.content for line in hunk.lines if line.prefix in (" ", "+")]
-                    if old_lines or new_lines:
-                        old_chunks.append("\n".join(old_lines))
-                        new_chunks.append("\n".join(new_lines))
-
-                old_text = "\n...\n".join(chunk for chunk in old_chunks if chunk)
-                new_text = "\n...\n".join(chunk for chunk in new_chunks if chunk)
-                if old_text or new_text:
-                    content.append(
-                        acp.tool_diff_content(
-                            path=op.file_path,
-                            old_text=old_text or None,
-                            new_text=new_text or "",
-                        )
-                    )
-                continue
-
-            if op.operation == OperationType.ADD:
-                added_lines = [line.content for hunk in op.hunks for line in hunk.lines if line.prefix == "+"]
-                content.append(
-                    acp.tool_diff_content(
-                        path=op.file_path,
-                        new_text="\n".join(added_lines),
-                    )
-                )
-                continue
-
-            if op.operation == OperationType.DELETE:
-                content.append(
-                    acp.tool_diff_content(
-                        path=op.file_path,
-                        old_text=f"Delete file: {op.file_path}",
-                        new_text="",
-                    )
-                )
-                continue
-
-            if op.operation == OperationType.MOVE:
-                content.append(
-                    acp.tool_content(acp.text_block(f"Move file: {op.file_path} -> {op.new_path}"))
-                )
-
-        return content or [acp.tool_content(acp.text_block(patch_text))]
-    except Exception:
-        return [acp.tool_content(acp.text_block(patch_text))]
-
-
-def _strip_diff_prefix(path: str) -> str:
-    raw = str(path or "").strip()
-    if raw.startswith(("a/", "b/")):
-        return raw[2:]
-    return raw
-
-
-def _parse_unified_diff_content(diff_text: str) -> List[Any]:
-    """Convert unified diff text into ACP diff content blocks."""
-    if not diff_text:
-        return []
-
-    content: List[Any] = []
-    current_old_path: Optional[str] = None
-    current_new_path: Optional[str] = None
-    old_lines: list[str] = []
-    new_lines: list[str] = []
-
-    def _flush() -> None:
-        nonlocal current_old_path, current_new_path, old_lines, new_lines
-        if current_old_path is None and current_new_path is None:
-            return
-        path = current_new_path if current_new_path and current_new_path != "/dev/null" else current_old_path
-        if not path or path == "/dev/null":
-            current_old_path = None
-            current_new_path = None
-            old_lines = []
-            new_lines = []
-            return
-        content.append(
-            acp.tool_diff_content(
-                path=_strip_diff_prefix(path),
-                old_text="\n".join(old_lines) if old_lines else None,
-                new_text="\n".join(new_lines),
-            )
-        )
-        current_old_path = None
-        current_new_path = None
-        old_lines = []
-        new_lines = []
-
-    for line in diff_text.splitlines():
-        if line.startswith("--- "):
-            _flush()
-            current_old_path = line[4:].strip()
-            continue
-        if line.startswith("+++ "):
-            current_new_path = line[4:].strip()
-            continue
-        if line.startswith("@@"):
-            continue
-        if current_old_path is None and current_new_path is None:
-            continue
-        if line.startswith("+"):
-            new_lines.append(line[1:])
-        elif line.startswith("-"):
-            old_lines.append(line[1:])
-        elif line.startswith(" "):
-            shared = line[1:]
-            old_lines.append(shared)
-            new_lines.append(shared)
-
-    _flush()
-    return content
-
-
-def _build_tool_complete_content(
-    tool_name: str,
-    result: Optional[str],
-    *,
-    function_args: Optional[Dict[str, Any]] = None,
-    snapshot: Any = None,
-) -> List[Any]:
-    """Build structured ACP completion content, falling back to plain text."""
-    display_result = result or ""
-    if len(display_result) > 5000:
-        display_result = display_result[:4900] + f"\n... ({len(result)} chars total, truncated)"
-
-    if tool_name in {"write_file", "patch", "skill_manage"}:
-        try:
-            from agent.display import extract_edit_diff
-
-            diff_text = extract_edit_diff(
-                tool_name,
-                result,
-                function_args=function_args,
-                snapshot=snapshot,
-            )
-            if isinstance(diff_text, str) and diff_text.strip():
-                diff_content = _parse_unified_diff_content(diff_text)
-                if diff_content:
-                    return diff_content
-        except Exception:
-            pass
-
-    return [acp.tool_content(acp.text_block(display_result))]
-
-
 # ---------------------------------------------------------------------------
 # Build ACP content objects for tool-call events
 # ---------------------------------------------------------------------------
@@ -284,8 +119,9 @@ def build_tool_start(
             new = arguments.get("new_string", "")
             content = [acp.tool_diff_content(path=path, new_text=new, old_text=old)]
         else:
+            # Patch mode — show the patch content as text
             patch_text = arguments.get("patch", "")
-            content = _build_patch_mode_content(patch_text)
+            content = [acp.tool_content(acp.text_block(patch_text))]
         return acp.start_tool_call(
             tool_call_id, title, kind=kind, content=content, locations=locations,
             raw_input=arguments,
@@ -342,17 +178,16 @@ def build_tool_complete(
     tool_call_id: str,
     tool_name: str,
     result: Optional[str] = None,
-    function_args: Optional[Dict[str, Any]] = None,
-    snapshot: Any = None,
 ) -> ToolCallProgress:
     """Create a ToolCallUpdate (progress) event for a completed tool call."""
     kind = get_tool_kind(tool_name)
-    content = _build_tool_complete_content(
-        tool_name,
-        result,
-        function_args=function_args,
-        snapshot=snapshot,
-    )
+
+    # Truncate very large results for the UI
+    display_result = result or ""
+    if len(display_result) > 5000:
+        display_result = display_result[:4900] + f"\n... ({len(result)} chars total, truncated)"
+
+    content = [acp.tool_content(acp.text_block(display_result))]
     return acp.update_tool_call(
         tool_call_id,
         kind=kind,

agent/anthropic_adapter.py

@@ -28,45 +28,19 @@ except ImportError:
 logger = logging.getLogger(__name__)
 
 THINKING_BUDGET = {"xhigh": 32000, "high": 16000, "medium": 8000, "low": 4000}
-# Hermes effort → Anthropic adaptive-thinking effort (output_config.effort).
-# Anthropic exposes 5 levels on 4.7+: low, medium, high, xhigh, max.
-# Opus/Sonnet 4.6 only expose 4 levels: low, medium, high, max — no xhigh.
-# We preserve xhigh as xhigh on 4.7+ (the recommended default for coding/
-# agentic work) and downgrade it to max on pre-4.7 adaptive models (which
-# is the strongest level they accept).  "minimal" is a legacy alias that
-# maps to low on every model.  See:
-# https://platform.claude.com/docs/en/about-claude/models/migration-guide
 ADAPTIVE_EFFORT_MAP = {
-    "max":     "max",
-    "xhigh":   "xhigh",
-    "high":    "high",
-    "medium":  "medium",
-    "low":     "low",
+    "xhigh": "max",
+    "high": "high",
+    "medium": "medium",
+    "low": "low",
     "minimal": "low",
 }
 
-# Models that accept the "xhigh" output_config.effort level.  Opus 4.7 added
-# xhigh as a distinct level between high and max; older adaptive-thinking
-# models (4.6) reject it with a 400.  Keep this substring list in sync with
-# the Anthropic migration guide as new model families ship.
-_XHIGH_EFFORT_SUBSTRINGS = ("4-7", "4.7")
-
-# Models where extended thinking is deprecated/removed (4.6+ behavior: adaptive
-# is the only supported mode; 4.7 additionally forbids manual thinking entirely
-# and drops temperature/top_p/top_k).
-_ADAPTIVE_THINKING_SUBSTRINGS = ("4-6", "4.6", "4-7", "4.7")
-
-# Models where temperature/top_p/top_k return 400 if set to non-default values.
-# This is the Opus 4.7 contract; future 4.x+ models are expected to follow it.
-_NO_SAMPLING_PARAMS_SUBSTRINGS = ("4-7", "4.7")
-
 # ── Max output token limits per Anthropic model ───────────────────────
 # Source: Anthropic docs + Cline model catalog.  Anthropic's API requires
 # max_tokens as a mandatory field.  Previously we hardcoded 16384, which
 # starves thinking-enabled models (thinking tokens count toward the limit).
 _ANTHROPIC_OUTPUT_LIMITS = {
-    # Claude 4.7
-    "claude-opus-4-7":   128_000,
     # Claude 4.6
     "claude-opus-4-6":   128_000,
     "claude-sonnet-4-6":  64_000,
@@ -86,8 +60,6 @@ _ANTHROPIC_OUTPUT_LIMITS = {
     "claude-3-opus":       4_096,
     "claude-3-sonnet":     4_096,
     "claude-3-haiku":      4_096,
-    # Third-party Anthropic-compatible providers
-    "minimax":            131_072,
 }
 
 # For any model not in the table, assume the highest current limit.
@@ -102,11 +74,8 @@ def _get_anthropic_max_output(model: str) -> int:
     model IDs (claude-sonnet-4-5-20250929) and variant suffixes (:1m, :fast)
     resolve correctly.  Longest-prefix match wins to avoid e.g. "claude-3-5"
     matching before "claude-3-5-sonnet".
-
-    Normalizes dots to hyphens so that model names like
-    ``anthropic/claude-opus-4.6`` match the ``claude-opus-4-6`` table key.
     """
-    m = model.lower().replace(".", "-")
+    m = model.lower()
     best_key = ""
     best_val = _ANTHROPIC_DEFAULT_OUTPUT_LIMIT
     for key, val in _ANTHROPIC_OUTPUT_LIMITS.items():
@@ -117,50 +86,15 @@ def _get_anthropic_max_output(model: str) -> int:
 
 
 def _supports_adaptive_thinking(model: str) -> bool:
-    """Return True for Claude 4.6+ models that support adaptive thinking."""
-    return any(v in model for v in _ADAPTIVE_THINKING_SUBSTRINGS)
+    """Return True for Claude 4.6 models that support adaptive thinking."""
+    return any(v in model for v in ("4-6", "4.6"))
 
 
-def _supports_xhigh_effort(model: str) -> bool:
-    """Return True for models that accept the 'xhigh' adaptive effort level.
-
-    Opus 4.7 introduced xhigh as a distinct level between high and max.
-    Pre-4.7 adaptive models (Opus/Sonnet 4.6) only accept low/medium/high/max
-    and reject xhigh with an HTTP 400. Callers should downgrade xhigh→max
-    when this returns False.
-    """
-    return any(v in model for v in _XHIGH_EFFORT_SUBSTRINGS)
-
-
-def _forbids_sampling_params(model: str) -> bool:
-    """Return True for models that 400 on any non-default temperature/top_p/top_k.
-
-    Opus 4.7 explicitly rejects sampling parameters; later Claude releases are
-    expected to follow suit.  Callers should omit these fields entirely rather
-    than passing zero/default values (the API rejects anything non-null).
-    """
-    return any(v in model for v in _NO_SAMPLING_PARAMS_SUBSTRINGS)
-
-
-# Beta headers for enhanced features (sent with ALL auth types).
-# 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.
-# Migration guide: remove these if you no longer support ≤4.5 models.
+# Beta headers for enhanced features (sent with ALL auth types)
 _COMMON_BETAS = [
     "interleaved-thinking-2025-05-14",
     "fine-grained-tool-streaming-2025-05-14",
 ]
-# 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"
-
-# Fast mode beta — enables the ``speed: "fast"`` request parameter for
-# significantly higher output token throughput on Opus 4.6 (~2.5x).
-# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
-_FAST_MODE_BETA = "fast-mode-2026-02-01"
 
 # Additional beta headers required for OAuth/subscription auth.
 # Matches what Claude Code (and pi-ai / OpenCode) send.
@@ -215,27 +149,18 @@ def _get_claude_code_version() -> str:
 
 
 def _is_oauth_token(key: str) -> bool:
-    """Check if the key is an Anthropic OAuth/setup token.
+    """Check if the key is an OAuth/setup token (not a regular Console API key).
 
-    Positively identifies Anthropic OAuth tokens by their key format:
-    - ``sk-ant-`` prefix (but NOT ``sk-ant-api``) → setup tokens, managed keys
-    - ``eyJ`` prefix → JWTs from the Anthropic OAuth flow
-
-    Non-Anthropic keys (MiniMax, Alibaba, etc.) don't match either pattern
-    and correctly return False.
+    Regular API keys start with 'sk-ant-api'. Everything else (setup-tokens
+    starting with 'sk-ant-oat', managed keys, JWTs, etc.) needs Bearer auth.
     """
     if not key:
         return False
-    # Regular Anthropic Console API keys — x-api-key auth, never OAuth
+    # Regular Console API keys use x-api-key header
     if key.startswith("sk-ant-api"):
         return False
-    # Anthropic-issued tokens (setup-tokens sk-ant-oat-*, managed keys)
-    if key.startswith("sk-ant-"):
-        return True
-    # JWTs from Anthropic OAuth flow
-    if key.startswith("eyJ"):
-        return True
-    return False
+    # Everything else (setup-tokens, managed keys, JWTs) uses Bearer auth
+    return True
 
 
 def _normalize_base_url_text(base_url) -> str:
@@ -279,28 +204,9 @@ 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) -> 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.
-    """
-    if _requires_bearer_auth(base_url):
-        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):
+def build_anthropic_client(api_key: str, base_url: str = None):
     """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
 
-    If *timeout* is provided it overrides the default 900s read timeout.  The
-    connect timeout stays at 10s.  Callers pass this from the per-provider /
-    per-model ``request_timeout_seconds`` config so Anthropic-native and
-    Anthropic-compatible providers respect the same knob as OpenAI-wire
-    providers.
-
     Returns an anthropic.Anthropic instance.
     """
     if _anthropic_sdk is None:
@@ -311,13 +217,11 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
     from httpx import Timeout
 
     normalized_base_url = _normalize_base_url_text(base_url)
-    _read_timeout = timeout if (isinstance(timeout, (int, float)) and timeout > 0) else 900.0
     kwargs = {
-        "timeout": Timeout(timeout=float(_read_timeout), connect=10.0),
+        "timeout": Timeout(timeout=900.0, connect=10.0),
     }
     if normalized_base_url:
         kwargs["base_url"] = normalized_base_url
-    common_betas = _common_betas_for_base_url(normalized_base_url)
 
     if _requires_bearer_auth(normalized_base_url):
         # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
@@ -327,21 +231,21 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
         # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
         # Anthropic OAuth/setup tokens.
         kwargs["auth_token"] = api_key
-        if common_betas:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
     elif _is_third_party_anthropic_endpoint(base_url):
         # Third-party proxies (Azure AI Foundry, AWS Bedrock, etc.) use their
         # own API keys with x-api-key auth. Skip OAuth detection — their keys
         # don't follow Anthropic's sk-ant-* prefix convention and would be
         # misclassified as OAuth tokens.
         kwargs["api_key"] = api_key
-        if common_betas:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
     elif _is_oauth_token(api_key):
         # OAuth access token / setup-token → Bearer auth + Claude Code identity.
         # Anthropic routes OAuth requests based on user-agent and headers;
         # without Claude Code's fingerprint, requests get intermittent 500s.
-        all_betas = common_betas + _OAUTH_ONLY_BETAS
+        all_betas = _COMMON_BETAS + _OAUTH_ONLY_BETAS
         kwargs["auth_token"] = api_key
         kwargs["default_headers"] = {
             "anthropic-beta": ",".join(all_betas),
@@ -351,39 +255,12 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
     else:
         # Regular API key → x-api-key header + common betas
         kwargs["api_key"] = api_key
-        if common_betas:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
 
     return _anthropic_sdk.Anthropic(**kwargs)
 
 
-def build_anthropic_bedrock_client(region: str):
-    """Create an AnthropicBedrock client for Bedrock Claude models.
-
-    Uses the Anthropic SDK's native Bedrock adapter, which provides full
-    Claude feature parity: prompt caching, thinking budgets, adaptive
-    thinking, fast mode — features not available via the Converse API.
-
-    Auth uses the boto3 default credential chain (IAM roles, SSO, env vars).
-    """
-    if _anthropic_sdk is None:
-        raise ImportError(
-            "The 'anthropic' package is required for the Bedrock provider. "
-            "Install it with: pip install 'anthropic>=0.39.0'"
-        )
-    if not hasattr(_anthropic_sdk, "AnthropicBedrock"):
-        raise ImportError(
-            "anthropic.AnthropicBedrock not available. "
-            "Upgrade with: pip install 'anthropic>=0.39.0'"
-        )
-    from httpx import Timeout
-
-    return _anthropic_sdk.AnthropicBedrock(
-        aws_region=region,
-        timeout=Timeout(timeout=900.0, connect=10.0),
-    )
-
-
 def read_claude_code_credentials() -> Optional[Dict[str, Any]]:
     """Read refreshable Claude Code OAuth credentials from ~/.claude/.credentials.json.
 
@@ -1281,7 +1158,6 @@ def build_anthropic_kwargs(
     preserve_dots: bool = False,
     context_length: Optional[int] = None,
     base_url: str | None = None,
-    fast_mode: bool = False,
 ) -> Dict[str, Any]:
     """Build kwargs for anthropic.messages.create().
 
@@ -1315,11 +1191,6 @@ def build_anthropic_kwargs(
 
     When *base_url* points to a third-party Anthropic-compatible endpoint,
     thinking block signatures are stripped (they are Anthropic-proprietary).
-
-    When *fast_mode* is True, adds ``extra_body["speed"] = "fast"`` and the
-    fast-mode beta header for ~2.5x faster output throughput on Opus 4.6.
-    Currently only supported on native Anthropic endpoints (not third-party
-    compatible ones).
     """
     system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
     anthropic_tools = convert_tools_to_anthropic(tools) if tools else []
@@ -1400,31 +1271,17 @@ def build_anthropic_kwargs(
             kwargs["tool_choice"] = {"type": "tool", "name": tool_choice}
 
     # Map reasoning_config to Anthropic's thinking parameter.
-    # Claude 4.6+ models use adaptive thinking + output_config.effort.
+    # Claude 4.6 models use adaptive thinking + output_config.effort.
     # Older models use manual thinking with budget_tokens.
-    # MiniMax Anthropic-compat endpoints support thinking (manual mode only,
-    # not adaptive).  Haiku does NOT support extended thinking — skip entirely.
-    #
-    # On 4.7+ the `thinking.display` field defaults to "omitted", which
-    # 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.
+    # Haiku and MiniMax models do NOT support extended thinking — skip entirely.
     if reasoning_config and isinstance(reasoning_config, dict):
-        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower():
+        if reasoning_config.get("enabled") is not False and "haiku" not in model.lower() and "minimax" not in model.lower():
             effort = str(reasoning_config.get("effort", "medium")).lower()
             budget = THINKING_BUDGET.get(effort, 8000)
             if _supports_adaptive_thinking(model):
-                kwargs["thinking"] = {
-                    "type": "adaptive",
-                    "display": "summarized",
-                }
-                adaptive_effort = ADAPTIVE_EFFORT_MAP.get(effort, "medium")
-                # Downgrade xhigh→max on models that don't list xhigh as a
-                # supported level (Opus/Sonnet 4.6). Opus 4.7+ keeps xhigh.
-                if adaptive_effort == "xhigh" and not _supports_xhigh_effort(model):
-                    adaptive_effort = "max"
+                kwargs["thinking"] = {"type": "adaptive"}
                 kwargs["output_config"] = {
-                    "effort": adaptive_effort,
+                    "effort": ADAPTIVE_EFFORT_MAP.get(effort, "medium")
                 }
             else:
                 kwargs["thinking"] = {"type": "enabled", "budget_tokens": budget}
@@ -1432,29 +1289,6 @@ def build_anthropic_kwargs(
                 kwargs["temperature"] = 1
                 kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
 
-    # ── Strip sampling params on 4.7+ ─────────────────────────────────
-    # Opus 4.7 rejects any non-default temperature/top_p/top_k with a 400.
-    # Callers (auxiliary_client, flush_memories, etc.) may set these for
-    # older models; drop them here as a safety net so upstream 4.6 → 4.7
-    # migrations don't require coordinated edits everywhere.
-    if _forbids_sampling_params(model):
-        for _sampling_key in ("temperature", "top_p", "top_k"):
-            kwargs.pop(_sampling_key, None)
-
-    # ── Fast mode (Opus 4.6 only) ────────────────────────────────────
-    # Adds extra_body.speed="fast" + the fast-mode beta header for ~2.5x
-    # output speed. Only for native Anthropic endpoints — third-party
-    # providers would reject the unknown beta header and speed parameter.
-    if fast_mode and not _is_third_party_anthropic_endpoint(base_url):
-        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))
-        if is_oauth:
-            betas.extend(_OAUTH_ONLY_BETAS)
-        betas.append(_FAST_MODE_BETA)
-        kwargs["extra_headers"] = {"anthropic-beta": ",".join(betas)}
-
     return kwargs
 
 
@@ -1498,20 +1332,12 @@ def normalize_anthropic_response(
                 )
             )
 
-    # Map Anthropic stop_reason to OpenAI finish_reason.
-    # Newer stop reasons added in Claude 4.5+ / 4.7:
-    #   - refusal: the model declined to answer (cyber safeguards, CSAM, etc.)
-    #   - model_context_window_exceeded: hit context limit (not max_tokens)
-    # Both need distinct handling upstream — a refusal should surface to the
-    # user with a clear message, and a context-window overflow should trigger
-    # compression/truncation rather than be treated as normal end-of-turn.
+    # Map Anthropic stop_reason to OpenAI finish_reason
     stop_reason_map = {
         "end_turn": "stop",
         "tool_use": "tool_calls",
         "max_tokens": "length",
         "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
     }
     finish_reason = stop_reason_map.get(response.stop_reason, "stop")
 
@@ -1524,43 +1350,4 @@ def normalize_anthropic_response(
             reasoning_details=reasoning_details or None,
         ),
         finish_reason,
-    )
-
-
-def normalize_anthropic_response_v2(
-    response,
-    strip_tool_prefix: bool = False,
-) -> "NormalizedResponse":
-    """Normalize Anthropic response to NormalizedResponse.
-
-    Wraps the existing normalize_anthropic_response() and maps its output
-    to the shared transport types.  This allows incremental migration —
-    one call site at a time — without changing the original function.
-    """
-    from agent.transports.types import NormalizedResponse, build_tool_call
-
-    assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
-
-    tool_calls = None
-    if assistant_msg.tool_calls:
-        tool_calls = [
-            build_tool_call(
-                id=tc.id,
-                name=tc.function.name,
-                arguments=tc.function.arguments,
-            )
-            for tc in assistant_msg.tool_calls
-        ]
-
-    provider_data = {}
-    if getattr(assistant_msg, "reasoning_details", None):
-        provider_data["reasoning_details"] = assistant_msg.reasoning_details
-
-    return NormalizedResponse(
-        content=assistant_msg.content,
-        tool_calls=tool_calls,
-        finish_reason=finish_reason,
-        reasoning=getattr(assistant_msg, "reasoning", None),
-        usage=None,  # Anthropic usage is on the raw response, not the normaliser
-        provider_data=provider_data or None,
-    )
+    )

agent/context_compressor.py

@@ -4,12 +4,8 @@ Self-contained class with its own OpenAI client for summarization.
 Uses auxiliary model (cheap/fast) to summarize middle turns while
 protecting head and tail context.
 
-Improvements over v2:
-  - Structured summary template with Resolved/Pending question tracking
-  - Summarizer preamble: "Do not respond to any questions" (from OpenCode)
-  - Handoff framing: "different assistant" (from Codex) to create separation
-  - "Remaining Work" replaces "Next Steps" to avoid reading as active instructions
-  - Clear separator when summary merges into tail message
+Improvements over v1:
+  - Structured summary template (Goal, Progress, Decisions, Files, Next Steps)
   - Iterative summary updates (preserves info across multiple compactions)
   - Token-budget tail protection instead of fixed message count
   - Tool output pruning before LLM summarization (cheap pre-pass)
@@ -17,17 +13,12 @@ Improvements over v2:
   - Richer tool call/result detail in summarizer input
 """
 
-import hashlib
-import json
 import logging
-import re
 import time
 from typing import Any, Dict, List, Optional
 
 from agent.auxiliary_client import call_llm
-from agent.context_engine import ContextEngine
 from agent.model_metadata import (
-    MINIMUM_CONTEXT_LENGTH,
     get_model_context_length,
     estimate_messages_tokens_rough,
 )
@@ -35,16 +26,12 @@ from agent.model_metadata import (
 logger = logging.getLogger(__name__)
 
 SUMMARY_PREFIX = (
-    "[CONTEXT COMPACTION — REFERENCE ONLY] Earlier turns were compacted "
-    "into the summary below. This is a handoff from a previous context "
-    "window — treat it as background reference, NOT as active instructions. "
-    "Do NOT answer questions or fulfill requests mentioned in this summary; "
-    "they were already addressed. "
-    "Your current task is identified in the '## Active Task' section of the "
-    "summary — resume exactly from there. "
-    "Respond ONLY to the latest user message "
-    "that appears AFTER this summary. The current session state (files, "
-    "config, etc.) may reflect work described here — avoid repeating it:"
+    "[CONTEXT COMPACTION] Earlier turns in this conversation were compacted "
+    "to save context space. The summary below describes work that was "
+    "already completed, and the current session state may still reflect "
+    "that work (for example, files may already be changed). Use the summary "
+    "and the current state to continue from where things left off, and "
+    "avoid repeating work:"
 )
 LEGACY_SUMMARY_PREFIX = "[CONTEXT SUMMARY]:"
 
@@ -63,176 +50,8 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
-def _truncate_tool_call_args_json(args: str, head_chars: int = 200) -> str:
-    """Shrink long string values inside a tool-call arguments JSON blob while
-    preserving JSON validity.
-
-    The ``function.arguments`` field on a tool call is a JSON-encoded string
-    passed through to the LLM provider; downstream providers strictly
-    validate it and return a non-retryable 400 when it is not well-formed.
-    An earlier implementation sliced the raw JSON at a fixed byte offset and
-    appended ``...[truncated]`` — which routinely produced strings like::
-
-        {"path": "/foo/bar", "content": "# long markdown
-        ...[truncated]
-
-    i.e. an unterminated string and a missing closing brace. MiniMax, for
-    example, rejects this with ``invalid function arguments json string``
-    and the session gets stuck re-sending the same broken history on every
-    turn. See issue #11762 for the observed loop.
-
-    This helper parses the arguments, shrinks long string leaves inside the
-    parsed structure, and re-serialises. Non-string values (paths, ints,
-    booleans) are preserved intact. If the arguments are not valid JSON
-    to begin with — some model backends use non-JSON tool arguments — the
-    original string is returned unchanged rather than replaced with
-    something neither we nor the backend can parse.
-    """
-    try:
-        parsed = json.loads(args)
-    except (ValueError, TypeError):
-        return args
-
-    def _shrink(obj: Any) -> Any:
-        if isinstance(obj, str):
-            if len(obj) > head_chars:
-                return obj[:head_chars] + "...[truncated]"
-            return obj
-        if isinstance(obj, dict):
-            return {k: _shrink(v) for k, v in obj.items()}
-        if isinstance(obj, list):
-            return [_shrink(v) for v in obj]
-        return obj
-
-    shrunken = _shrink(parsed)
-    # ensure_ascii=False preserves CJK/emoji instead of bloating with \uXXXX
-    return json.dumps(shrunken, ensure_ascii=False)
-
-
-def _summarize_tool_result(tool_name: str, tool_args: str, tool_content: str) -> str:
-    """Create an informative 1-line summary of a tool call + result.
-
-    Used during the pre-compression pruning pass to replace large tool
-    outputs with a short but useful description of what the tool did,
-    rather than a generic placeholder that carries zero information.
-
-    Returns strings like::
-
-        [terminal] ran `npm test` -> exit 0, 47 lines output
-        [read_file] read config.py from line 1 (1,200 chars)
-        [search_files] content search for 'compress' in agent/ -> 12 matches
-    """
-    try:
-        args = json.loads(tool_args) if tool_args else {}
-    except (json.JSONDecodeError, TypeError):
-        args = {}
-
-    content = tool_content or ""
-    content_len = len(content)
-    line_count = content.count("\n") + 1 if content.strip() else 0
-
-    if tool_name == "terminal":
-        cmd = args.get("command", "")
-        if len(cmd) > 80:
-            cmd = cmd[:77] + "..."
-        exit_match = re.search(r'"exit_code"\s*:\s*(-?\d+)', content)
-        exit_code = exit_match.group(1) if exit_match else "?"
-        return f"[terminal] ran `{cmd}` -> exit {exit_code}, {line_count} lines output"
-
-    if tool_name == "read_file":
-        path = args.get("path", "?")
-        offset = args.get("offset", 1)
-        return f"[read_file] read {path} from line {offset} ({content_len:,} chars)"
-
-    if tool_name == "write_file":
-        path = args.get("path", "?")
-        written_lines = args.get("content", "").count("\n") + 1 if args.get("content") else "?"
-        return f"[write_file] wrote to {path} ({written_lines} lines)"
-
-    if tool_name == "search_files":
-        pattern = args.get("pattern", "?")
-        path = args.get("path", ".")
-        target = args.get("target", "content")
-        match_count = re.search(r'"total_count"\s*:\s*(\d+)', content)
-        count = match_count.group(1) if match_count else "?"
-        return f"[search_files] {target} search for '{pattern}' in {path} -> {count} matches"
-
-    if tool_name == "patch":
-        path = args.get("path", "?")
-        mode = args.get("mode", "replace")
-        return f"[patch] {mode} in {path} ({content_len:,} chars result)"
-
-    if tool_name in ("browser_navigate", "browser_click", "browser_snapshot",
-                     "browser_type", "browser_scroll", "browser_vision"):
-        url = args.get("url", "")
-        ref = args.get("ref", "")
-        detail = f" {url}" if url else (f" ref={ref}" if ref else "")
-        return f"[{tool_name}]{detail} ({content_len:,} chars)"
-
-    if tool_name == "web_search":
-        query = args.get("query", "?")
-        return f"[web_search] query='{query}' ({content_len:,} chars result)"
-
-    if tool_name == "web_extract":
-        urls = args.get("urls", [])
-        url_desc = urls[0] if isinstance(urls, list) and urls else "?"
-        if isinstance(urls, list) and len(urls) > 1:
-            url_desc += f" (+{len(urls) - 1} more)"
-        return f"[web_extract] {url_desc} ({content_len:,} chars)"
-
-    if tool_name == "delegate_task":
-        goal = args.get("goal", "")
-        if len(goal) > 60:
-            goal = goal[:57] + "..."
-        return f"[delegate_task] '{goal}' ({content_len:,} chars result)"
-
-    if tool_name == "execute_code":
-        code_preview = (args.get("code") or "")[:60].replace("\n", " ")
-        if len(args.get("code", "")) > 60:
-            code_preview += "..."
-        return f"[execute_code] `{code_preview}` ({line_count} lines output)"
-
-    if tool_name in ("skill_view", "skills_list", "skill_manage"):
-        name = args.get("name", "?")
-        return f"[{tool_name}] name={name} ({content_len:,} chars)"
-
-    if tool_name == "vision_analyze":
-        question = args.get("question", "")[:50]
-        return f"[vision_analyze] '{question}' ({content_len:,} chars)"
-
-    if tool_name == "memory":
-        action = args.get("action", "?")
-        target = args.get("target", "?")
-        return f"[memory] {action} on {target}"
-
-    if tool_name == "todo":
-        return "[todo] updated task list"
-
-    if tool_name == "clarify":
-        return "[clarify] asked user a question"
-
-    if tool_name == "text_to_speech":
-        return f"[text_to_speech] generated audio ({content_len:,} chars)"
-
-    if tool_name == "cronjob":
-        action = args.get("action", "?")
-        return f"[cronjob] {action}"
-
-    if tool_name == "process":
-        action = args.get("action", "?")
-        sid = args.get("session_id", "?")
-        return f"[process] {action} session={sid}"
-
-    # Generic fallback
-    first_arg = ""
-    for k, v in list(args.items())[:2]:
-        sv = str(v)[:40]
-        first_arg += f" {k}={sv}"
-    return f"[{tool_name}]{first_arg} ({content_len:,} chars result)"
-
-
-class ContextCompressor(ContextEngine):
-    """Default context engine — compresses conversation context via lossy summarization.
+class ContextCompressor:
+    """Compresses conversation context when approaching the model's context limit.
 
     Algorithm:
       1. Prune old tool results (cheap, no LLM call)
@@ -242,40 +61,6 @@ class ContextCompressor(ContextEngine):
       5. On subsequent compactions, iteratively update the previous summary
     """
 
-    @property
-    def name(self) -> str:
-        return "compressor"
-
-    def on_session_reset(self) -> None:
-        """Reset all per-session state for /new or /reset."""
-        super().on_session_reset()
-        self._context_probed = False
-        self._context_probe_persistable = False
-        self._previous_summary = None
-        self._last_compression_savings_pct = 100.0
-        self._ineffective_compression_count = 0
-
-    def update_model(
-        self,
-        model: str,
-        context_length: int,
-        base_url: str = "",
-        api_key: str = "",
-        provider: str = "",
-        api_mode: str = "",
-    ) -> None:
-        """Update model info after a model switch or fallback activation."""
-        self.model = model
-        self.base_url = base_url
-        self.api_key = api_key
-        self.provider = provider
-        self.api_mode = api_mode
-        self.context_length = context_length
-        self.threshold_tokens = max(
-            int(context_length * self.threshold_percent),
-            MINIMUM_CONTEXT_LENGTH,
-        )
-
     def __init__(
         self,
         model: str,
@@ -289,13 +74,11 @@ class ContextCompressor(ContextEngine):
         api_key: str = "",
         config_context_length: int | None = None,
         provider: str = "",
-        api_mode: str = "",
     ):
         self.model = model
         self.base_url = base_url
         self.api_key = api_key
         self.provider = provider
-        self.api_mode = api_mode
         self.threshold_percent = threshold_percent
         self.protect_first_n = protect_first_n
         self.protect_last_n = protect_last_n
@@ -307,14 +90,7 @@ class ContextCompressor(ContextEngine):
             config_context_length=config_context_length,
             provider=provider,
         )
-        # Floor: never compress below MINIMUM_CONTEXT_LENGTH tokens even if
-        # the percentage would suggest a lower value.  This prevents premature
-        # compression on large-context models at 50% while keeping the % sane
-        # for models right at the minimum.
-        self.threshold_tokens = max(
-            int(self.context_length * threshold_percent),
-            MINIMUM_CONTEXT_LENGTH,
-        )
+        self.threshold_tokens = int(self.context_length * threshold_percent)
         self.compression_count = 0
 
         # Derive token budgets: ratio is relative to the threshold, not total context
@@ -343,9 +119,6 @@ class ContextCompressor(ContextEngine):
 
         # Stores the previous compaction summary for iterative updates
         self._previous_summary: Optional[str] = None
-        # Anti-thrashing: track whether last compression was effective
-        self._last_compression_savings_pct: float = 100.0
-        self._ineffective_compression_count: int = 0
         self._summary_failure_cooldown_until: float = 0.0
 
     def update_from_response(self, usage: Dict[str, Any]):
@@ -354,26 +127,9 @@ class ContextCompressor(ContextEngine):
         self.last_completion_tokens = usage.get("completion_tokens", 0)
 
     def should_compress(self, prompt_tokens: int = None) -> bool:
-        """Check if context exceeds the compression threshold.
-
-        Includes anti-thrashing protection: if the last two compressions
-        each saved less than 10%, skip compression to avoid infinite loops
-        where each pass removes only 1-2 messages.
-        """
+        """Check if context exceeds the compression threshold."""
         tokens = prompt_tokens if prompt_tokens is not None else self.last_prompt_tokens
-        if tokens < self.threshold_tokens:
-            return False
-        # Anti-thrashing: back off if recent compressions were ineffective
-        if self._ineffective_compression_count >= 2:
-            if not self.quiet_mode:
-                logger.warning(
-                    "Compression skipped — last %d compressions saved <10%% each. "
-                    "Consider /new to start a fresh session, or /compress <topic> "
-                    "for focused compression.",
-                    self._ineffective_compression_count,
-                )
-            return False
-        return True
+        return tokens >= self.threshold_tokens
 
     # ------------------------------------------------------------------
     # Tool output pruning (cheap pre-pass, no LLM call)
@@ -383,16 +139,7 @@ class ContextCompressor(ContextEngine):
         self, messages: List[Dict[str, Any]], protect_tail_count: int,
         protect_tail_tokens: int | None = None,
     ) -> tuple[List[Dict[str, Any]], int]:
-        """Replace old tool result contents with informative 1-line summaries.
-
-        Instead of a generic placeholder, generates a summary like::
-
-            [terminal] ran `npm test` -> exit 0, 47 lines output
-            [read_file] read config.py from line 1 (3,400 chars)
-
-        Also deduplicates identical tool results (e.g. reading the same file
-        5x keeps only the newest full copy) and truncates large tool_call
-        arguments in assistant messages outside the protected tail.
+        """Replace old tool result contents with a short placeholder.
 
         Walks backward from the end, protecting the most recent messages that
         fall within ``protect_tail_tokens`` (when provided) OR the last
@@ -408,22 +155,6 @@ class ContextCompressor(ContextEngine):
         result = [m.copy() for m in messages]
         pruned = 0
 
-        # Build index: tool_call_id -> (tool_name, arguments_json)
-        call_id_to_tool: Dict[str, tuple] = {}
-        for msg in result:
-            if msg.get("role") == "assistant":
-                for tc in msg.get("tool_calls") or []:
-                    if isinstance(tc, dict):
-                        cid = tc.get("id", "")
-                        fn = tc.get("function", {})
-                        call_id_to_tool[cid] = (fn.get("name", "unknown"), fn.get("arguments", ""))
-                    else:
-                        cid = getattr(tc, "id", "") or ""
-                        fn = getattr(tc, "function", None)
-                        name = getattr(fn, "name", "unknown") if fn else "unknown"
-                        args_str = getattr(fn, "arguments", "") if fn else ""
-                        call_id_to_tool[cid] = (name, args_str)
-
         # Determine the prune boundary
         if protect_tail_tokens is not None and protect_tail_tokens > 0:
             # Token-budget approach: walk backward accumulating tokens
@@ -432,8 +163,7 @@ class ContextCompressor(ContextEngine):
             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 = sum(len(p.get("text", "")) for p in raw_content) if isinstance(raw_content, list) else len(raw_content)
+                content_len = len(msg.get("content") or "")
                 msg_tokens = content_len // _CHARS_PER_TOKEN + 10
                 for tc in msg.get("tool_calls") or []:
                     if isinstance(tc, dict):
@@ -448,76 +178,18 @@ class ContextCompressor(ContextEngine):
         else:
             prune_boundary = len(result) - protect_tail_count
 
-        # Pass 1: Deduplicate identical tool results.
-        # When the same file is read multiple times, keep only the most recent
-        # full copy and replace older duplicates with a back-reference.
-        content_hashes: dict = {}  # hash -> (index, tool_call_id)
-        for i in range(len(result) - 1, -1, -1):
-            msg = result[i]
-            if msg.get("role") != "tool":
-                continue
-            content = msg.get("content") or ""
-            # Skip multimodal content (list of content blocks)
-            if isinstance(content, list):
-                continue
-            if len(content) < 200:
-                continue
-            h = hashlib.md5(content.encode("utf-8", errors="replace")).hexdigest()[:12]
-            if h in content_hashes:
-                # This is an older duplicate — replace with back-reference
-                result[i] = {**msg, "content": "[Duplicate tool output — same content as a more recent call]"}
-                pruned += 1
-            else:
-                content_hashes[h] = (i, msg.get("tool_call_id", "?"))
-
-        # Pass 2: Replace old tool results with informative summaries
         for i in range(prune_boundary):
             msg = result[i]
             if msg.get("role") != "tool":
                 continue
             content = msg.get("content", "")
-            # Skip multimodal content (list of content blocks)
-            if isinstance(content, list):
-                continue
             if not content or content == _PRUNED_TOOL_PLACEHOLDER:
                 continue
-            # Skip already-deduplicated or previously-summarized results
-            if content.startswith("[Duplicate tool output"):
-                continue
             # Only prune if the content is substantial (>200 chars)
             if len(content) > 200:
-                call_id = msg.get("tool_call_id", "")
-                tool_name, tool_args = call_id_to_tool.get(call_id, ("unknown", ""))
-                summary = _summarize_tool_result(tool_name, tool_args, content)
-                result[i] = {**msg, "content": summary}
+                result[i] = {**msg, "content": _PRUNED_TOOL_PLACEHOLDER}
                 pruned += 1
 
-        # Pass 3: Truncate large tool_call arguments in assistant messages
-        # outside the protected tail. write_file with 50KB content, for
-        # example, survives pruning entirely without this.
-        #
-        # The shrinking is done inside the parsed JSON structure so the
-        # result remains valid JSON — otherwise downstream providers 400
-        # on every subsequent turn until the broken call falls out of
-        # the window. See ``_truncate_tool_call_args_json`` docstring.
-        for i in range(prune_boundary):
-            msg = result[i]
-            if msg.get("role") != "assistant" or not msg.get("tool_calls"):
-                continue
-            new_tcs = []
-            modified = False
-            for tc in msg["tool_calls"]:
-                if isinstance(tc, dict):
-                    args = tc.get("function", {}).get("arguments", "")
-                    if len(args) > 500:
-                        new_args = _truncate_tool_call_args_json(args)
-                        if new_args != args:
-                            tc = {**tc, "function": {**tc["function"], "arguments": new_args}}
-                            modified = True
-                new_tcs.append(tc)
-            if modified:
-                result[i] = {**msg, "tool_calls": new_tcs}
-
         return result, pruned
 
     # ------------------------------------------------------------------
@@ -595,20 +267,13 @@ class ContextCompressor(ContextEngine):
 
         return "\n\n".join(parts)
 
-    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]], focus_topic: str = None) -> Optional[str]:
+    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]]) -> Optional[str]:
         """Generate a structured summary of conversation turns.
 
-        Uses a structured template (Goal, Progress, Decisions, Resolved/Pending
-        Questions, Files, Remaining Work) with explicit preamble telling the
-        summarizer not to answer questions.  When a previous summary exists,
+        Uses a structured template (Goal, Progress, Decisions, Files, Next Steps)
+        inspired by Pi-mono and OpenCode. When a previous summary exists,
         generates an iterative update instead of summarizing from scratch.
 
-        Args:
-            focus_topic: Optional focus string for guided compression.  When
-                provided, the summariser prioritises preserving information
-                related to this topic and is more aggressive about compressing
-                everything else.  Inspired by Claude Code's ``/compact``.
-
         Returns None if all attempts fail — the caller should drop
         the middle turns without a summary rather than inject a useless
         placeholder.
@@ -624,85 +289,9 @@ class ContextCompressor(ContextEngine):
         summary_budget = self._compute_summary_budget(turns_to_summarize)
         content_to_summarize = self._serialize_for_summary(turns_to_summarize)
 
-        # Preamble shared by both first-compaction and iterative-update prompts.
-        # Inspired by OpenCode's "do not respond to any questions" instruction
-        # and Codex's "another language model" framing.
-        _summarizer_preamble = (
-            "You are a summarization agent creating a context checkpoint. "
-            "Your output will be injected as reference material for a DIFFERENT "
-            "assistant that continues the conversation. "
-            "Do NOT respond to any questions or requests in the conversation — "
-            "only output the structured summary. "
-            "Do NOT include any preamble, greeting, or prefix. "
-            "Write the summary in the same language the user was using in the "
-            "conversation — do not translate or switch to English."
-        )
-
-        # Shared structured template (used by both paths).
-        _template_sections = f"""## Active Task
-[THE SINGLE MOST IMPORTANT FIELD. Copy the user's most recent request or
-task assignment verbatim — the exact words they used. If multiple tasks
-were requested and only some are done, list only the ones NOT yet completed.
-The next assistant must pick up exactly here. Example:
-"User asked: 'Now refactor the auth module to use JWT instead of sessions'"
-If no outstanding task exists, write "None."]
-
-## Goal
-[What the user is trying to accomplish overall]
-
-## Constraints & Preferences
-[User preferences, coding style, constraints, important decisions]
-
-## Completed Actions
-[Numbered list of concrete actions taken — include tool used, target, and outcome.
-Format each as: N. ACTION target — outcome [tool: name]
-Example:
-1. READ config.py:45 — found `==` should be `!=` [tool: read_file]
-2. PATCH config.py:45 — changed `==` to `!=` [tool: patch]
-3. TEST `pytest tests/` — 3/50 failed: test_parse, test_validate, test_edge [tool: terminal]
-Be specific with file paths, commands, line numbers, and results.]
-
-## Active State
-[Current working state — include:
-- Working directory and branch (if applicable)
-- Modified/created files with brief note on each
-- Test status (X/Y passing)
-- Any running processes or servers
-- Environment details that matter]
-
-## In Progress
-[Work currently underway — what was being done when compaction fired]
-
-## Blocked
-[Any blockers, errors, or issues not yet resolved. Include exact error messages.]
-
-## Key Decisions
-[Important technical decisions and WHY they were made]
-
-## Resolved Questions
-[Questions the user asked that were ALREADY answered — include the answer so the next assistant does not re-answer them]
-
-## Pending User Asks
-[Questions or requests from the user that have NOT yet been answered or fulfilled. If none, write "None."]
-
-## Relevant Files
-[Files read, modified, or created — with brief note on each]
-
-## Remaining Work
-[What remains to be done — framed as context, not instructions]
-
-## Critical Context
-[Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
-
-Target ~{summary_budget} tokens. Be CONCRETE — include file paths, command outputs, error messages, line numbers, and specific values. Avoid vague descriptions like "made some changes" — say exactly what changed.
-
-Write only the summary body. Do not include any preamble or prefix."""
-
         if self._previous_summary:
             # Iterative update: preserve existing info, add new progress
-            prompt = f"""{_summarizer_preamble}
-
-You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
+            prompt = f"""You are updating a context compaction summary. A previous compaction produced the summary below. New conversation turns have occurred since then and need to be incorporated.
 
 PREVIOUS SUMMARY:
 {self._previous_summary}
@@ -710,42 +299,87 @@ PREVIOUS SUMMARY:
 NEW TURNS TO INCORPORATE:
 {content_to_summarize}
 
-Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new completed actions to the numbered list (continue numbering). Move items from "In Progress" to "Completed Actions" when done. Move answered questions to "Resolved Questions". Update "Active State" to reflect current state. Remove information only if it is clearly obsolete. CRITICAL: Update "## Active Task" to reflect the user's most recent unfulfilled request — this is the most important field for task continuity.
+Update the summary using this exact structure. PRESERVE all existing information that is still relevant. ADD new progress. Move items from "In Progress" to "Done" when completed. Remove information only if it is clearly obsolete.
 
-{_template_sections}"""
+## Goal
+[What the user is trying to accomplish — preserve from previous summary, update if goal evolved]
+
+## Constraints & Preferences
+[User preferences, coding style, constraints, important decisions — accumulate across compactions]
+
+## Progress
+### Done
+[Completed work — include specific file paths, commands run, results obtained]
+### In Progress
+[Work currently underway]
+### Blocked
+[Any blockers or issues encountered]
+
+## Key Decisions
+[Important technical decisions and why they were made]
+
+## Relevant Files
+[Files read, modified, or created — with brief note on each. Accumulate across compactions.]
+
+## Next Steps
+[What needs to happen next to continue the work]
+
+## Critical Context
+[Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
+
+## Tools & Patterns
+[Which tools were used, how they were used effectively, and any tool-specific discoveries. Accumulate across compactions.]
+
+Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions.
+
+Write only the summary body. Do not include any preamble or prefix."""
         else:
             # First compaction: summarize from scratch
-            prompt = f"""{_summarizer_preamble}
-
-Create a structured handoff summary for a different assistant that will continue this conversation after earlier turns are compacted. The next assistant should be able to understand what happened without re-reading the original turns.
+            prompt = f"""Create a structured handoff summary for a later assistant that will continue this conversation after earlier turns are compacted.
 
 TURNS TO SUMMARIZE:
 {content_to_summarize}
 
 Use this exact structure:
 
-{_template_sections}"""
+## Goal
+[What the user is trying to accomplish]
 
-        # Inject focus topic guidance when the user provides one via /compress <focus>.
-        # This goes at the end of the prompt so it takes precedence.
-        if focus_topic:
-            prompt += f"""
+## Constraints & Preferences
+[User preferences, coding style, constraints, important decisions]
 
-FOCUS TOPIC: "{focus_topic}"
-The user has requested that this compaction PRIORITISE preserving all information related to the focus topic above. For content related to "{focus_topic}", include full detail — exact values, file paths, command outputs, error messages, and decisions. For content NOT related to the focus topic, summarise more aggressively (brief one-liners or omit if truly irrelevant). The focus topic sections should receive roughly 60-70% of the summary token budget."""
+## Progress
+### Done
+[Completed work — include specific file paths, commands run, results obtained]
+### In Progress
+[Work currently underway]
+### Blocked
+[Any blockers or issues encountered]
+
+## Key Decisions
+[Important technical decisions and why they were made]
+
+## Relevant Files
+[Files read, modified, or created — with brief note on each]
+
+## Next Steps
+[What needs to happen next to continue the work]
+
+## Critical Context
+[Any specific values, error messages, configuration details, or data that would be lost without explicit preservation]
+
+## Tools & Patterns
+[Which tools were used, how they were used effectively, and any tool-specific discoveries (e.g., preferred flags, working invocations, successful command patterns)]
+
+Target ~{summary_budget} tokens. Be specific — include file paths, command outputs, error messages, and concrete values rather than vague descriptions. The goal is to prevent the next assistant from repeating work or losing important details.
+
+Write only the summary body. Do not include any preamble or prefix."""
 
         try:
             call_kwargs = {
                 "task": "compression",
-                "main_runtime": {
-                    "model": self.model,
-                    "provider": self.provider,
-                    "base_url": self.base_url,
-                    "api_key": self.api_key,
-                    "api_mode": self.api_mode,
-                },
                 "messages": [{"role": "user", "content": prompt}],
-                "max_tokens": int(summary_budget * 1.3),
+                "max_tokens": summary_budget * 2,
                 # timeout resolved from auxiliary.compression.timeout config by call_llm
             }
             if self.summary_model:
@@ -759,10 +393,8 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             # Store for iterative updates on next compaction
             self._previous_summary = summary
             self._summary_failure_cooldown_until = 0.0
-            self._summary_model_fallen_back = False
             return self._with_summary_prefix(summary)
         except RuntimeError:
-            # No provider configured — long cooldown, unlikely to self-resolve
             self._summary_failure_cooldown_until = time.monotonic() + _SUMMARY_FAILURE_COOLDOWN_SECONDS
             logging.warning("Context compression: no provider available for "
                             "summary. Middle turns will be dropped without summary "
@@ -770,42 +402,12 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                             _SUMMARY_FAILURE_COOLDOWN_SECONDS)
             return None
         except Exception as e:
-            # If the summary model is different from the main model and the
-            # error looks permanent (model not found, 503, 404), fall back to
-            # using the main model instead of entering cooldown that leaves
-            # context growing unbounded.  (#8620 sub-issue 4)
-            _status = getattr(e, "status_code", None) or getattr(getattr(e, "response", None), "status_code", None)
-            _err_str = str(e).lower()
-            _is_model_not_found = (
-                _status in (404, 503)
-                or "model_not_found" in _err_str
-                or "does not exist" in _err_str
-                or "no available channel" in _err_str
-            )
-            if (
-                _is_model_not_found
-                and 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' not available (%s). "
-                    "Falling back to main model '%s' for compression.",
-                    self.summary_model, e, self.model,
-                )
-                self.summary_model = ""  # empty = use main model
-                self._summary_failure_cooldown_until = 0.0  # no cooldown
-                return self._generate_summary(messages, summary_budget)  # retry immediately
-
-            # Transient errors (timeout, rate limit, network) — shorter cooldown
-            _transient_cooldown = 60
-            self._summary_failure_cooldown_until = time.monotonic() + _transient_cooldown
+            self._summary_failure_cooldown_until = time.monotonic() + _SUMMARY_FAILURE_COOLDOWN_SECONDS
             logging.warning(
                 "Failed to generate context summary: %s. "
                 "Further summary attempts paused for %d seconds.",
                 e,
-                _transient_cooldown,
+                _SUMMARY_FAILURE_COOLDOWN_SECONDS,
             )
             return None
 
@@ -928,62 +530,6 @@ The user has requested that this compaction PRIORITISE preserving all informatio
     # Tail protection by token budget
     # ------------------------------------------------------------------
 
-    def _find_last_user_message_idx(
-        self, messages: List[Dict[str, Any]], head_end: int
-    ) -> int:
-        """Return the index of the last user-role message at or after *head_end*, or -1."""
-        for i in range(len(messages) - 1, head_end - 1, -1):
-            if messages[i].get("role") == "user":
-                return i
-        return -1
-
-    def _ensure_last_user_message_in_tail(
-        self,
-        messages: List[Dict[str, Any]],
-        cut_idx: int,
-        head_end: int,
-    ) -> int:
-        """Guarantee the most recent user message is in the protected tail.
-
-        Context compressor bug (#10896): ``_align_boundary_backward`` can pull
-        ``cut_idx`` past a user message when it tries to keep tool_call/result
-        groups together.  If the last user message ends up in the *compressed*
-        middle region the LLM summariser writes it into "Pending User Asks",
-        but ``SUMMARY_PREFIX`` tells the next model to respond only to user
-        messages *after* the summary — so the task effectively disappears from
-        the active context, causing the agent to stall, repeat completed work,
-        or silently drop the user's latest request.
-
-        Fix: if the last user-role message is not already in the tail
-        (``messages[cut_idx:]``), walk ``cut_idx`` back to include it.  We
-        then re-align backward one more time to avoid splitting any
-        tool_call/result group that immediately precedes the user message.
-        """
-        last_user_idx = self._find_last_user_message_idx(messages, head_end)
-        if last_user_idx < 0:
-            # No user message found beyond head — nothing to anchor.
-            return cut_idx
-
-        if last_user_idx >= cut_idx:
-            # Already in the tail; nothing to do.
-            return cut_idx
-
-        # The last user message is in the middle (compressed) region.
-        # Pull cut_idx back to it directly — a user message is already a
-        # clean boundary (no tool_call/result splitting risk), so there is no
-        # need to call _align_boundary_backward here; doing so would
-        # unnecessarily pull the cut further back into the preceding
-        # assistant + tool_calls group.
-        if not self.quiet_mode:
-            logger.debug(
-                "Anchoring tail cut to last user message at index %d "
-                "(was %d) to prevent active-task loss after compression",
-                last_user_idx,
-                cut_idx,
-            )
-        # Safety: never go back into the head region.
-        return max(last_user_idx, head_end + 1)
-
     def _find_tail_cut_by_tokens(
         self, messages: List[Dict[str, Any]], head_end: int,
         token_budget: int | None = None,
@@ -1001,8 +547,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         read, etc.).  If even the minimum 3 messages exceed 1.5x the budget
         the cut is placed right after the head so compression still runs.
 
-        Never cuts inside a tool_call/result group.  Always ensures the most
-        recent user message is in the tail (see ``_ensure_last_user_message_in_tail``).
+        Never cuts inside a tool_call/result group.
         """
         if token_budget is None:
             token_budget = self.tail_token_budget
@@ -1041,17 +586,13 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         # Align to avoid splitting tool groups
         cut_idx = self._align_boundary_backward(messages, cut_idx)
 
-        # Ensure the most recent user message is always in the tail so the
-        # active task is never lost to compression (fixes #10896).
-        cut_idx = self._ensure_last_user_message_in_tail(messages, cut_idx, head_end)
-
         return max(cut_idx, head_end + 1)
 
     # ------------------------------------------------------------------
     # Main compression entry point
     # ------------------------------------------------------------------
 
-    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None, focus_topic: str = None) -> List[Dict[str, Any]]:
+    def compress(self, messages: List[Dict[str, Any]], current_tokens: int = None) -> List[Dict[str, Any]]:
         """Compress conversation messages by summarizing middle turns.
 
         Algorithm:
@@ -1063,12 +604,6 @@ The user has requested that this compaction PRIORITISE preserving all informatio
 
         After compression, orphaned tool_call / tool_result pairs are cleaned
         up so the API never receives mismatched IDs.
-
-        Args:
-            focus_topic: Optional focus string for guided compression.  When
-                provided, the summariser will prioritise preserving information
-                related to this topic and be more aggressive about compressing
-                everything else.  Inspired by Claude Code's ``/compact``.
         """
         n_messages = len(messages)
         # Only need head + 3 tail messages minimum (token budget decides the real tail size)
@@ -1126,17 +661,17 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             )
 
         # Phase 3: Generate structured summary
-        summary = self._generate_summary(turns_to_summarize, focus_topic=focus_topic)
+        summary = self._generate_summary(turns_to_summarize)
 
         # Phase 4: Assemble compressed message list
         compressed = []
         for i in range(compress_start):
             msg = messages[i].copy()
-            if i == 0 and msg.get("role") == "system":
-                existing = msg.get("content") or ""
-                _compression_note = "[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
-                if _compression_note not in existing:
-                    msg["content"] = existing + "\n\n" + _compression_note
+            if i == 0 and msg.get("role") == "system" and self.compression_count == 0:
+                msg["content"] = (
+                    (msg.get("content") or "")
+                    + "\n\n[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
+                )
             compressed.append(msg)
 
         # If LLM summary failed, insert a static fallback so the model
@@ -1181,12 +716,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             msg = messages[i].copy()
             if _merge_summary_into_tail and i == compress_end:
                 original = msg.get("content") or ""
-                msg["content"] = (
-                    summary
-                    + "\n\n--- END OF CONTEXT SUMMARY — "
-                    "respond to the message below, not the summary above ---\n\n"
-                    + original
-                )
+                msg["content"] = summary + "\n\n" + original
                 _merge_summary_into_tail = False
             compressed.append(msg)
 
@@ -1194,24 +724,14 @@ The user has requested that this compaction PRIORITISE preserving all informatio
 
         compressed = self._sanitize_tool_pairs(compressed)
 
-        new_estimate = estimate_messages_tokens_rough(compressed)
-        saved_estimate = display_tokens - new_estimate
-
-        # Anti-thrashing: track compression effectiveness
-        savings_pct = (saved_estimate / display_tokens * 100) if display_tokens > 0 else 0
-        self._last_compression_savings_pct = savings_pct
-        if savings_pct < 10:
-            self._ineffective_compression_count += 1
-        else:
-            self._ineffective_compression_count = 0
-
         if not self.quiet_mode:
+            new_estimate = estimate_messages_tokens_rough(compressed)
+            saved_estimate = display_tokens - new_estimate
             logger.info(
-                "Compressed: %d -> %d messages (~%d tokens saved, %.0f%%)",
+                "Compressed: %d -> %d messages (~%d tokens saved)",
                 n_messages,
                 len(compressed),
                 saved_estimate,
-                savings_pct,
             )
             logger.info("Compression #%d complete", self.compression_count)
 

agent/context_engine.py

@@ -1,184 +0,0 @@
-"""Abstract base class for pluggable context engines.
-
-A context engine controls how conversation context is managed when
-approaching the model's token limit. The built-in ContextCompressor
-is the default implementation. Third-party engines (e.g. LCM) can
-replace it via the plugin system or by being placed in the
-``plugins/context_engine/<name>/`` directory.
-
-Selection is config-driven: ``context.engine`` in config.yaml.
-Default is ``"compressor"`` (the built-in). Only one engine is active.
-
-The engine is responsible for:
-  - Deciding when compaction should fire
-  - Performing compaction (summarization, DAG construction, etc.)
-  - Optionally exposing tools the agent can call (e.g. lcm_grep)
-  - Tracking token usage from API responses
-
-Lifecycle:
-  1. Engine is instantiated and registered (plugin register() or default)
-  2. on_session_start() called when a conversation begins
-  3. update_from_response() called after each API response with usage data
-  4. should_compress() checked after each turn
-  5. compress() called when should_compress() returns True
-  6. on_session_end() called at real session boundaries (CLI exit, /reset,
-     gateway session expiry) — NOT per-turn
-"""
-
-from abc import ABC, abstractmethod
-from typing import Any, Dict, List
-
-
-class ContextEngine(ABC):
-    """Base class all context engines must implement."""
-
-    # -- Identity ----------------------------------------------------------
-
-    @property
-    @abstractmethod
-    def name(self) -> str:
-        """Short identifier (e.g. 'compressor', 'lcm')."""
-
-    # -- Token state (read by run_agent.py for display/logging) ------------
-    #
-    # Engines MUST maintain these. run_agent.py reads them directly.
-
-    last_prompt_tokens: int = 0
-    last_completion_tokens: int = 0
-    last_total_tokens: int = 0
-    threshold_tokens: int = 0
-    context_length: int = 0
-    compression_count: int = 0
-
-    # -- Compaction parameters (read by run_agent.py for preflight) --------
-    #
-    # These control the preflight compression check.  Subclasses may
-    # override via __init__ or property; defaults are sensible for most
-    # engines.
-
-    threshold_percent: float = 0.75
-    protect_first_n: int = 3
-    protect_last_n: int = 6
-
-    # -- Core interface ----------------------------------------------------
-
-    @abstractmethod
-    def update_from_response(self, usage: Dict[str, Any]) -> None:
-        """Update tracked token usage from an API response.
-
-        Called after every LLM call with the usage dict from the response.
-        """
-
-    @abstractmethod
-    def should_compress(self, prompt_tokens: int = None) -> bool:
-        """Return True if compaction should fire this turn."""
-
-    @abstractmethod
-    def compress(
-        self,
-        messages: List[Dict[str, Any]],
-        current_tokens: int = None,
-    ) -> List[Dict[str, Any]]:
-        """Compact the message list and return the new message list.
-
-        This is the main entry point. The engine receives the full message
-        list and returns a (possibly shorter) list that fits within the
-        context budget. The implementation is free to summarize, build a
-        DAG, or do anything else — as long as the returned list is a valid
-        OpenAI-format message sequence.
-        """
-
-    # -- Optional: pre-flight check ----------------------------------------
-
-    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
-        """Quick rough check before the API call (no real token count yet).
-
-        Default returns False (skip pre-flight). Override if your engine
-        can do a cheap estimate.
-        """
-        return False
-
-    # -- Optional: session lifecycle ---------------------------------------
-
-    def on_session_start(self, session_id: str, **kwargs) -> None:
-        """Called when a new conversation session begins.
-
-        Use this to load persisted state (DAG, store) for the session.
-        kwargs may include hermes_home, platform, model, etc.
-        """
-
-    def on_session_end(self, session_id: str, messages: List[Dict[str, Any]]) -> None:
-        """Called at real session boundaries (CLI exit, /reset, gateway expiry).
-
-        Use this to flush state, close DB connections, etc.
-        NOT called per-turn — only when the session truly ends.
-        """
-
-    def on_session_reset(self) -> None:
-        """Called on /new or /reset. Reset per-session state.
-
-        Default resets compression_count and token tracking.
-        """
-        self.last_prompt_tokens = 0
-        self.last_completion_tokens = 0
-        self.last_total_tokens = 0
-        self.compression_count = 0
-
-    # -- Optional: tools ---------------------------------------------------
-
-    def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        """Return tool schemas this engine provides to the agent.
-
-        Default returns empty list (no tools). LCM would return schemas
-        for lcm_grep, lcm_describe, lcm_expand here.
-        """
-        return []
-
-    def handle_tool_call(self, name: str, args: Dict[str, Any], **kwargs) -> str:
-        """Handle a tool call from the agent.
-
-        Only called for tool names returned by get_tool_schemas().
-        Must return a JSON string.
-
-        kwargs may include:
-          messages: the current in-memory message list (for live ingestion)
-        """
-        import json
-        return json.dumps({"error": f"Unknown context engine tool: {name}"})
-
-    # -- Optional: status / display ----------------------------------------
-
-    def get_status(self) -> Dict[str, Any]:
-        """Return status dict for display/logging.
-
-        Default returns the standard fields run_agent.py expects.
-        """
-        return {
-            "last_prompt_tokens": self.last_prompt_tokens,
-            "threshold_tokens": self.threshold_tokens,
-            "context_length": self.context_length,
-            "usage_percent": (
-                min(100, self.last_prompt_tokens / self.context_length * 100)
-                if self.context_length else 0
-            ),
-            "compression_count": self.compression_count,
-        }
-
-    # -- Optional: model switch support ------------------------------------
-
-    def update_model(
-        self,
-        model: str,
-        context_length: int,
-        base_url: str = "",
-        api_key: str = "",
-        provider: str = "",
-    ) -> None:
-        """Called when the user switches models or on fallback activation.
-
-        Default updates context_length and recalculates threshold_tokens
-        from threshold_percent. Override if your engine needs more
-        (e.g. recalculate DAG budgets, switch summary models).
-        """
-        self.context_length = context_length
-        self.threshold_tokens = int(context_length * self.threshold_percent)

agent/context_references.py

@@ -13,9 +13,8 @@ from typing import Awaitable, Callable
 
 from agent.model_metadata import estimate_tokens_rough
 
-_QUOTED_REFERENCE_VALUE = r'(?:`[^`\n]+`|"[^"\n]+"|\'[^\'\n]+\')'
 REFERENCE_PATTERN = re.compile(
-    rf"(?<![\w/])@(?:(?P<simple>diff|staged)\b|(?P<kind>file|folder|git|url):(?P<value>{_QUOTED_REFERENCE_VALUE}(?::\d+(?:-\d+)?)?|\S+))"
+    r"(?<![\w/])@(?:(?P<simple>diff|staged)\b|(?P<kind>file|folder|git|url):(?P<value>\S+))"
 )
 TRAILING_PUNCTUATION = ",.;!?"
 _SENSITIVE_HOME_DIRS = (".ssh", ".aws", ".gnupg", ".kube", ".docker", ".azure", ".config/gh")
@@ -82,10 +81,14 @@ def parse_context_references(message: str) -> list[ContextReference]:
         value = _strip_trailing_punctuation(match.group("value") or "")
         line_start = None
         line_end = None
-        target = _strip_reference_wrappers(value)
+        target = value
 
         if kind == "file":
-            target, line_start, line_end = _parse_file_reference_value(value)
+            range_match = re.match(r"^(?P<path>.+?):(?P<start>\d+)(?:-(?P<end>\d+))?$", value)
+            if range_match:
+                target = range_match.group("path")
+                line_start = int(range_match.group("start"))
+                line_end = int(range_match.group("end") or range_match.group("start"))
 
         refs.append(
             ContextReference(
@@ -372,38 +375,6 @@ def _strip_trailing_punctuation(value: str) -> str:
     return stripped
 
 
-def _strip_reference_wrappers(value: str) -> str:
-    if len(value) >= 2 and value[0] == value[-1] and value[0] in "`\"'":
-        return value[1:-1]
-    return value
-
-
-def _parse_file_reference_value(value: str) -> tuple[str, int | None, int | None]:
-    quoted_match = re.match(
-        r'^(?P<quote>`|"|\')(?P<path>.+?)(?P=quote)(?::(?P<start>\d+)(?:-(?P<end>\d+))?)?$',
-        value,
-    )
-    if quoted_match:
-        line_start = quoted_match.group("start")
-        line_end = quoted_match.group("end")
-        return (
-            quoted_match.group("path"),
-            int(line_start) if line_start is not None else None,
-            int(line_end or line_start) if line_start is not None else None,
-        )
-
-    range_match = re.match(r"^(?P<path>.+?):(?P<start>\d+)(?:-(?P<end>\d+))?$", value)
-    if range_match:
-        line_start = int(range_match.group("start"))
-        return (
-            range_match.group("path"),
-            line_start,
-            int(range_match.group("end") or range_match.group("start")),
-        )
-
-    return _strip_reference_wrappers(value), None, None
-
-
 def _remove_reference_tokens(message: str, refs: list[ContextReference]) -> str:
     pieces: list[str] = []
     cursor = 0
@@ -483,7 +454,9 @@ def _rg_files(path: Path, cwd: Path, limit: int) -> list[Path] | None:
             text=True,
             timeout=10,
         )
-    except (FileNotFoundError, OSError, subprocess.TimeoutExpired):
+    except FileNotFoundError:
+        return None
+    except subprocess.TimeoutExpired:
         return None
     if result.returncode != 0:
         return None

agent/copilot_acp_client.py

@@ -313,25 +313,9 @@ class CopilotACPClient:
             tools=tools,
             tool_choice=tool_choice,
         )
-        # Normalise timeout: run_agent.py may pass an httpx.Timeout object
-        # (used natively by the OpenAI SDK) rather than a plain float.
-        if timeout is None:
-            _effective_timeout = _DEFAULT_TIMEOUT_SECONDS
-        elif isinstance(timeout, (int, float)):
-            _effective_timeout = float(timeout)
-        else:
-            # httpx.Timeout or similar — pick the largest component so the
-            # subprocess has enough wall-clock time for the full response.
-            _candidates = [
-                getattr(timeout, attr, None)
-                for attr in ("read", "write", "connect", "pool", "timeout")
-            ]
-            _numeric = [float(v) for v in _candidates if isinstance(v, (int, float))]
-            _effective_timeout = max(_numeric) if _numeric else _DEFAULT_TIMEOUT_SECONDS
-
         response_text, reasoning_text = self._run_prompt(
             prompt_text,
-            timeout_seconds=_effective_timeout,
+            timeout_seconds=float(timeout or _DEFAULT_TIMEOUT_SECONDS),
         )
 
         tool_calls, cleaned_text = _extract_tool_calls_from_text(response_text)

agent/credential_pool.py

@@ -18,16 +18,15 @@ import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
     CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
     DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
+    KIMI_CODE_BASE_URL,
     PROVIDER_REGISTRY,
-    _auth_store_lock,
     _codex_access_token_is_expiring,
     _decode_jwt_claims,
+    _import_codex_cli_tokens,
     _load_auth_store,
     _load_provider_state,
     _resolve_kimi_base_url,
     _resolve_zai_base_url,
-    _save_auth_store,
-    _save_provider_state,
     read_credential_pool,
     write_credential_pool,
 )
@@ -286,14 +285,6 @@ def _iter_custom_providers(config: Optional[dict] = None):
         return
     custom_providers = config.get("custom_providers")
     if not isinstance(custom_providers, list):
-        # Fall back to the v12+ providers dict via the compatibility layer
-        try:
-            from hermes_cli.config import get_compatible_custom_providers
-
-            custom_providers = get_compatible_custom_providers(config)
-        except Exception:
-            return
-    if not custom_providers:
         return
     for entry in custom_providers:
         if not isinstance(entry, dict):
@@ -455,66 +446,38 @@ class CredentialPool:
             logger.debug("Failed to sync from credentials file: %s", exc)
         return entry
 
-    def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
-        """Write refreshed pool entry tokens back to auth.json providers.
+    def _sync_codex_entry_from_cli(self, entry: PooledCredential) -> PooledCredential:
+        """Sync an openai-codex pool entry from ~/.codex/auth.json if tokens differ.
 
-        After a pool-level refresh, the pool entry has fresh tokens but
-        auth.json's ``providers.<id>`` still holds the pre-refresh state.
-        On the next ``load_pool()``, ``_seed_from_singletons()`` reads that
-        stale state and can overwrite the fresh pool entry — potentially
-        re-seeding a consumed single-use refresh token.
-
-        Applies to any OAuth provider whose singleton lives in auth.json
-        (currently Nous and OpenAI Codex).
+        OpenAI OAuth refresh tokens are single-use and rotate on every refresh.
+        When the Codex CLI (or another Hermes profile) refreshes its token,
+        the pool entry's refresh_token becomes stale.  This method detects that
+        by comparing against ~/.codex/auth.json and syncing the fresh pair.
         """
-        if entry.source != "device_code":
-            return
+        if self.provider != "openai-codex":
+            return entry
         try:
-            with _auth_store_lock():
-                auth_store = _load_auth_store()
-                if self.provider == "nous":
-                    state = _load_provider_state(auth_store, "nous")
-                    if state is None:
-                        return
-                    state["access_token"] = entry.access_token
-                    if entry.refresh_token:
-                        state["refresh_token"] = entry.refresh_token
-                    if entry.expires_at:
-                        state["expires_at"] = entry.expires_at
-                    if entry.agent_key:
-                        state["agent_key"] = entry.agent_key
-                    if entry.agent_key_expires_at:
-                        state["agent_key_expires_at"] = entry.agent_key_expires_at
-                    for extra_key in ("obtained_at", "expires_in", "agent_key_id",
-                                      "agent_key_expires_in", "agent_key_reused",
-                                      "agent_key_obtained_at"):
-                        val = entry.extra.get(extra_key)
-                        if val is not None:
-                            state[extra_key] = val
-                    if entry.inference_base_url:
-                        state["inference_base_url"] = entry.inference_base_url
-                    _save_provider_state(auth_store, "nous", state)
-
-                elif self.provider == "openai-codex":
-                    state = _load_provider_state(auth_store, "openai-codex")
-                    if not isinstance(state, dict):
-                        return
-                    tokens = state.get("tokens")
-                    if not isinstance(tokens, dict):
-                        return
-                    tokens["access_token"] = entry.access_token
-                    if entry.refresh_token:
-                        tokens["refresh_token"] = entry.refresh_token
-                    if entry.last_refresh:
-                        state["last_refresh"] = entry.last_refresh
-                    _save_provider_state(auth_store, "openai-codex", state)
-
-                else:
-                    return
-
-                _save_auth_store(auth_store)
+            cli_tokens = _import_codex_cli_tokens()
+            if not cli_tokens:
+                return entry
+            cli_refresh = cli_tokens.get("refresh_token", "")
+            cli_access = cli_tokens.get("access_token", "")
+            if cli_refresh and cli_refresh != entry.refresh_token:
+                logger.debug("Pool entry %s: syncing tokens from ~/.codex/auth.json (refresh token changed)", entry.id)
+                updated = replace(
+                    entry,
+                    access_token=cli_access,
+                    refresh_token=cli_refresh,
+                    last_status=None,
+                    last_status_at=None,
+                    last_error_code=None,
+                )
+                self._replace_entry(entry, updated)
+                self._persist()
+                return updated
         except Exception as exc:
-            logger.debug("Failed to sync %s pool entry back to auth store: %s", self.provider, exc)
+            logger.debug("Failed to sync from ~/.codex/auth.json: %s", exc)
+        return entry
 
     def _refresh_entry(self, entry: PooledCredential, *, force: bool) -> Optional[PooledCredential]:
         if entry.auth_type != AUTH_TYPE_OAUTH or not entry.refresh_token:
@@ -649,10 +612,6 @@ class CredentialPool:
         )
         self._replace_entry(entry, updated)
         self._persist()
-        # Sync refreshed tokens back to auth.json providers so that
-        # _seed_from_singletons() on the next load_pool() sees fresh state
-        # instead of re-seeding stale/consumed tokens.
-        self._sync_device_code_entry_to_auth_store(updated)
         return updated
 
     def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -698,6 +657,16 @@ class CredentialPool:
                 if synced is not entry:
                     entry = synced
                     cleared_any = True
+            # For openai-codex entries, sync from ~/.codex/auth.json before
+            # any status/refresh checks.  This picks up tokens refreshed by
+            # the Codex CLI or another Hermes profile.
+            if (self.provider == "openai-codex"
+                    and entry.last_status == STATUS_EXHAUSTED
+                    and entry.refresh_token):
+                synced = self._sync_codex_entry_from_cli(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:
@@ -984,17 +953,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
     auth_store = _load_auth_store()
 
     if provider == "anthropic":
-        # Only auto-discover external credentials (Claude Code, Hermes PKCE)
-        # when the user has explicitly configured anthropic as their provider.
-        # Without this gate, auxiliary client fallback chains silently read
-        # ~/.claude/.credentials.json without user consent.  See PR #4210.
-        try:
-            from hermes_cli.auth import is_provider_explicitly_configured
-            if not is_provider_explicitly_configured("anthropic"):
-                return changed, active_sources
-        except ImportError:
-            pass
-
         from agent.anthropic_adapter import read_claude_code_credentials, read_hermes_oauth_credentials
 
         for source_name, creds in (
@@ -1002,13 +960,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
             ("claude_code", read_claude_code_credentials()),
         ):
             if creds and creds.get("accessToken"):
-                # Check if user explicitly removed this source
-                try:
-                    from hermes_cli.auth import is_source_suppressed
-                    if is_source_suppressed(provider, source_name):
-                        continue
-                except ImportError:
-                    pass
                 active_sources.add(source_name)
                 changed |= _upsert_entry(
                     entries,
@@ -1028,14 +979,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
         state = _load_provider_state(auth_store, "nous")
         if state:
             active_sources.add("device_code")
-            # Prefer a user-supplied label embedded in the singleton state
-            # (set by persist_nous_credentials(label=...) when the user ran
-            # `hermes auth add nous --label <name>`).  Fall back to the
-            # auto-derived token fingerprint for logins that didn't supply one.
-            custom_label = str(state.get("label") or "").strip()
-            seeded_label = custom_label or label_from_token(
-                state.get("access_token", ""), "device_code"
-            )
             changed |= _upsert_entry(
                 entries,
                 provider,
@@ -1054,87 +997,13 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                     "agent_key": state.get("agent_key"),
                     "agent_key_expires_at": state.get("agent_key_expires_at"),
                     "tls": state.get("tls") if isinstance(state.get("tls"), dict) else None,
-                    "label": seeded_label,
+                    "label": label_from_token(state.get("access_token", ""), "device_code"),
                 },
             )
 
-    elif provider == "copilot":
-        # Copilot tokens are resolved dynamically via `gh auth token` or
-        # env vars (COPILOT_GITHUB_TOKEN / GH_TOKEN).  They don't live in
-        # the auth store or credential pool, so we resolve them here.
-        try:
-            from hermes_cli.copilot_auth import resolve_copilot_token
-            token, source = resolve_copilot_token()
-            if token:
-                source_name = "gh_cli" if "gh" in source.lower() else f"env:{source}"
-                active_sources.add(source_name)
-                pconfig = PROVIDER_REGISTRY.get(provider)
-                changed |= _upsert_entry(
-                    entries,
-                    provider,
-                    source_name,
-                    {
-                        "source": source_name,
-                        "auth_type": AUTH_TYPE_API_KEY,
-                        "access_token": token,
-                        "base_url": pconfig.inference_base_url if pconfig else "",
-                        "label": source,
-                    },
-                )
-        except Exception as exc:
-            logger.debug("Copilot token seed failed: %s", exc)
-
-    elif provider == "qwen-oauth":
-        # Qwen OAuth tokens live in ~/.qwen/oauth_creds.json, written by
-        # the Qwen CLI (`qwen auth qwen-oauth`).  They aren't in the
-        # Hermes auth store or env vars, so resolve them here.
-        # Use refresh_if_expiring=False to avoid network calls during
-        # pool loading / provider discovery.
-        try:
-            from hermes_cli.auth import resolve_qwen_runtime_credentials
-            creds = resolve_qwen_runtime_credentials(refresh_if_expiring=False)
-            token = creds.get("api_key", "")
-            if token:
-                source_name = creds.get("source", "qwen-cli")
-                active_sources.add(source_name)
-                changed |= _upsert_entry(
-                    entries,
-                    provider,
-                    source_name,
-                    {
-                        "source": source_name,
-                        "auth_type": AUTH_TYPE_OAUTH,
-                        "access_token": token,
-                        "expires_at_ms": creds.get("expires_at_ms"),
-                        "base_url": creds.get("base_url", ""),
-                        "label": creds.get("auth_file", source_name),
-                    },
-                )
-        except Exception as exc:
-            logger.debug("Qwen 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
-        # the Hermes auth store.  Without this gate the removal is instantly
-        # undone on the next load_pool() call.
-        codex_suppressed = False
-        try:
-            from hermes_cli.auth import is_source_suppressed
-            codex_suppressed = is_source_suppressed(provider, "device_code")
-        except ImportError:
-            pass
-        if codex_suppressed:
-            return changed, active_sources
-
         state = _load_provider_state(auth_store, "openai-codex")
         tokens = state.get("tokens") if isinstance(state, dict) else None
-        # Hermes owns its own Codex auth state — we do NOT auto-import from
-        # ~/.codex/auth.json at pool-load time.  OAuth refresh tokens are
-        # single-use, so sharing them with Codex CLI / VS Code causes
-        # refresh_token_reused race failures.  Users who want to adopt
-        # existing Codex CLI credentials get a one-time, explicit prompt
-        # via `hermes auth openai-codex`.
         if isinstance(tokens, dict) and tokens.get("access_token"):
             active_sources.add("device_code")
             changed |= _upsert_entry(

agent/display.py

@@ -4,6 +4,7 @@ Pure display functions and classes with no AIAgent dependency.
 Used by AIAgent._execute_tool_calls for CLI feedback.
 """
 
+import json
 import logging
 import os
 import sys
@@ -13,8 +14,6 @@ from dataclasses import dataclass, field
 from difflib import unified_diff
 from pathlib import Path
 
-from utils import safe_json_loads
-
 # ANSI escape codes for coloring tool failure indicators
 _RED = "\033[31m"
 _RESET = "\033[0m"
@@ -22,67 +21,11 @@ _RESET = "\033[0m"
 logger = logging.getLogger(__name__)
 
 _ANSI_RESET = "\033[0m"
-
-# Diff colors — resolved lazily from the skin engine so they adapt
-# to light/dark themes.  Falls back to sensible defaults on import
-# failure.  We cache after first resolution for performance.
-_diff_colors_cached: dict[str, str] | None = None
-
-
-def _diff_ansi() -> dict[str, str]:
-    """Return ANSI escapes for diff display, resolved from the active skin."""
-    global _diff_colors_cached
-    if _diff_colors_cached is not None:
-        return _diff_colors_cached
-
-    # Defaults that work on dark terminals
-    dim = "\033[38;2;150;150;150m"
-    file_c = "\033[38;2;180;160;255m"
-    hunk = "\033[38;2;120;120;140m"
-    minus = "\033[38;2;255;255;255;48;2;120;20;20m"
-    plus = "\033[38;2;255;255;255;48;2;20;90;20m"
-
-    try:
-        from hermes_cli.skin_engine import get_active_skin
-        skin = get_active_skin()
-
-        def _hex_fg(key: str, fallback_rgb: tuple[int, int, int]) -> str:
-            h = skin.get_color(key, "")
-            if h and len(h) == 7 and h[0] == "#":
-                r, g, b = int(h[1:3], 16), int(h[3:5], 16), int(h[5:7], 16)
-                return f"\033[38;2;{r};{g};{b}m"
-            r, g, b = fallback_rgb
-            return f"\033[38;2;{r};{g};{b}m"
-
-        dim = _hex_fg("banner_dim", (150, 150, 150))
-        file_c = _hex_fg("session_label", (180, 160, 255))
-        hunk = _hex_fg("session_border", (120, 120, 140))
-        # minus/plus use background colors — derive from ui_error/ui_ok
-        err_h = skin.get_color("ui_error", "#ef5350")
-        ok_h = skin.get_color("ui_ok", "#4caf50")
-        if err_h and len(err_h) == 7:
-            er, eg, eb = int(err_h[1:3], 16), int(err_h[3:5], 16), int(err_h[5:7], 16)
-            # Use a dark tinted version as background
-            minus = f"\033[38;2;255;255;255;48;2;{max(er//2,20)};{max(eg//4,10)};{max(eb//4,10)}m"
-        if ok_h and len(ok_h) == 7:
-            or_, og, ob = int(ok_h[1:3], 16), int(ok_h[3:5], 16), int(ok_h[5:7], 16)
-            plus = f"\033[38;2;255;255;255;48;2;{max(or_//4,10)};{max(og//2,20)};{max(ob//4,10)}m"
-    except Exception:
-        pass
-
-    _diff_colors_cached = {
-        "dim": dim, "file": file_c, "hunk": hunk,
-        "minus": minus, "plus": plus,
-    }
-    return _diff_colors_cached
-
-
-# Module-level helpers — each call resolves from the active skin lazily.
-def _diff_dim():   return _diff_ansi()["dim"]
-def _diff_file():  return _diff_ansi()["file"]
-def _diff_hunk():  return _diff_ansi()["hunk"]
-def _diff_minus(): return _diff_ansi()["minus"]
-def _diff_plus():  return _diff_ansi()["plus"]
+_ANSI_DIM = "\033[38;2;150;150;150m"
+_ANSI_FILE = "\033[38;2;180;160;255m"
+_ANSI_HUNK = "\033[38;2;120;120;140m"
+_ANSI_MINUS = "\033[38;2;255;255;255;48;2;120;20;20m"
+_ANSI_PLUS = "\033[38;2;255;255;255;48;2;20;90;20m"
 _MAX_INLINE_DIFF_FILES = 6
 _MAX_INLINE_DIFF_LINES = 80
 
@@ -225,11 +168,9 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -
             content = _oneline(args.get("content", ""))
             return f"+{target}: \"{content[:25]}{'...' if len(content) > 25 else ''}\""
         elif action == "replace":
-            old = _oneline(args.get("old_text") or "") or "<missing old_text>"
-            return f"~{target}: \"{old[:20]}\""
+            return f"~{target}: \"{_oneline(args.get('old_text', '')[:20])}\""
         elif action == "remove":
-            old = _oneline(args.get("old_text") or "") or "<missing old_text>"
-            return f"-{target}: \"{old[:20]}\""
+            return f"-{target}: \"{_oneline(args.get('old_text', '')[:20])}\""
         return action
 
     if tool_name == "send_message":
@@ -369,8 +310,9 @@ def _result_succeeded(result: str | None) -> bool:
     """Conservatively detect whether a tool result represents success."""
     if not result:
         return False
-    data = safe_json_loads(result)
-    if data is None:
+    try:
+        data = json.loads(result)
+    except (json.JSONDecodeError, TypeError):
         return False
     if not isinstance(data, dict):
         return False
@@ -419,7 +361,10 @@ def extract_edit_diff(
 ) -> str | None:
     """Extract a unified diff from a file-edit tool result."""
     if tool_name == "patch" and result:
-        data = safe_json_loads(result)
+        try:
+            data = json.loads(result)
+        except (json.JSONDecodeError, TypeError):
+            data = None
         if isinstance(data, dict):
             diff = data.get("diff")
             if isinstance(diff, str) and diff.strip():
@@ -458,19 +403,19 @@ def _render_inline_unified_diff(diff: str) -> list[str]:
         if raw_line.startswith("+++ "):
             to_file = raw_line[4:].strip()
             if from_file or to_file:
-                rendered.append(f"{_diff_file()}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
+                rendered.append(f"{_ANSI_FILE}{from_file or 'a/?'} → {to_file or 'b/?'}{_ANSI_RESET}")
             continue
         if raw_line.startswith("@@"):
-            rendered.append(f"{_diff_hunk()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_HUNK}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("-"):
-            rendered.append(f"{_diff_minus()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_MINUS}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith("+"):
-            rendered.append(f"{_diff_plus()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_PLUS}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line.startswith(" "):
-            rendered.append(f"{_diff_dim()}{raw_line}{_ANSI_RESET}")
+            rendered.append(f"{_ANSI_DIM}{raw_line}{_ANSI_RESET}")
             continue
         if raw_line:
             rendered.append(raw_line)
@@ -536,7 +481,7 @@ def _summarize_rendered_diff_sections(
         summary = f"… omitted {omitted_lines} diff line(s)"
         if omitted_files:
             summary += f" across {omitted_files} additional file(s)/section(s)"
-        rendered.append(f"{_diff_hunk()}{summary}{_ANSI_RESET}")
+        rendered.append(f"{_ANSI_HUNK}{summary}{_ANSI_RESET}")
 
     return rendered
 
@@ -602,45 +547,6 @@ class KawaiiSpinner:
         "analyzing", "computing", "synthesizing", "formulating", "brainstorming",
     ]
 
-    @classmethod
-    def get_waiting_faces(cls) -> list:
-        """Return waiting faces from the active skin, falling back to KAWAII_WAITING."""
-        try:
-            skin = _get_skin()
-            if skin:
-                faces = skin.spinner.get("waiting_faces", [])
-                if faces:
-                    return faces
-        except Exception:
-            pass
-        return cls.KAWAII_WAITING
-
-    @classmethod
-    def get_thinking_faces(cls) -> list:
-        """Return thinking faces from the active skin, falling back to KAWAII_THINKING."""
-        try:
-            skin = _get_skin()
-            if skin:
-                faces = skin.spinner.get("thinking_faces", [])
-                if faces:
-                    return faces
-        except Exception:
-            pass
-        return cls.KAWAII_THINKING
-
-    @classmethod
-    def get_thinking_verbs(cls) -> list:
-        """Return thinking verbs from the active skin, falling back to THINKING_VERBS."""
-        try:
-            skin = _get_skin()
-            if skin:
-                verbs = skin.spinner.get("thinking_verbs", [])
-                if verbs:
-                    return verbs
-        except Exception:
-            pass
-        return cls.THINKING_VERBS
-
     def __init__(self, message: str = "", spinner_type: str = 'dots', print_fn=None):
         self.message = message
         self.spinner_frames = self.SPINNERS.get(spinner_type, self.SPINNERS['dots'])
@@ -812,19 +718,23 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
         return False, ""
 
     if tool_name == "terminal":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
+        try:
+            data = json.loads(result)
             exit_code = data.get("exit_code")
             if exit_code is not None and exit_code != 0:
                 return True, f" [exit {exit_code}]"
+        except (json.JSONDecodeError, TypeError, AttributeError):
+            logger.debug("Could not parse terminal result as JSON for exit code check")
         return False, ""
 
     # Memory-specific: distinguish "full" from real errors
     if tool_name == "memory":
-        data = safe_json_loads(result)
-        if isinstance(data, dict):
+        try:
+            data = json.loads(result)
             if data.get("success") is False and "exceed the limit" in data.get("error", ""):
                 return True, " [full]"
+        except (json.JSONDecodeError, TypeError, AttributeError):
+            logger.debug("Could not parse memory result as JSON for capacity check")
 
     # Generic heuristic for non-terminal tools
     lower = result[:500].lower()
@@ -941,13 +851,9 @@ def get_cute_tool_message(
         if action == "add":
             return _wrap(f"┊ 🧠 memory    +{target}: \"{_trunc(args.get('content', ''), 30)}\"  {dur}")
         elif action == "replace":
-            old = args.get("old_text") or ""
-            old = old if old else "<missing old_text>"
-            return _wrap(f"┊ 🧠 memory    ~{target}: \"{_trunc(old, 20)}\"  {dur}")
+            return _wrap(f"┊ 🧠 memory    ~{target}: \"{_trunc(args.get('old_text', ''), 20)}\"  {dur}")
         elif action == "remove":
-            old = args.get("old_text") or ""
-            old = old if old else "<missing old_text>"
-            return _wrap(f"┊ 🧠 memory    -{target}: \"{_trunc(old, 20)}\"  {dur}")
+            return _wrap(f"┊ 🧠 memory    -{target}: \"{_trunc(args.get('old_text', ''), 20)}\"  {dur}")
         return _wrap(f"┊ 🧠 memory    {action}  {dur}")
     if tool_name == "skills_list":
         return _wrap(f"┊ 📚 skills    list {args.get('category', 'all')}  {dur}")
@@ -999,4 +905,84 @@ def get_cute_tool_message(
 # Honcho session line (one-liner with clickable OSC 8 hyperlink)
 # =========================================================================
 
+_DIM = "\033[2m"
+_SKY_BLUE = "\033[38;5;117m"
+_ANSI_RESET = "\033[0m"
 
+
+# =========================================================================
+# Context pressure display (CLI user-facing warnings)
+# =========================================================================
+
+# ANSI color codes for context pressure tiers
+_CYAN = "\033[36m"
+_YELLOW = "\033[33m"
+_BOLD = "\033[1m"
+_DIM_ANSI = "\033[2m"
+
+# Bar characters
+_BAR_FILLED = "▰"
+_BAR_EMPTY = "▱"
+_BAR_WIDTH = 20
+
+
+def format_context_pressure(
+    compaction_progress: float,
+    threshold_tokens: int,
+    threshold_percent: float,
+    compression_enabled: bool = True,
+) -> str:
+    """Build a formatted context pressure line for CLI display.
+
+    The bar and percentage show progress toward the compaction threshold,
+    NOT the raw context window.  100% = compaction fires.
+
+    Args:
+        compaction_progress: How close to compaction (0.0–1.0, 1.0 = fires).
+        threshold_tokens: Compaction threshold in tokens.
+        threshold_percent: Compaction threshold as a fraction of context window.
+        compression_enabled: Whether auto-compression is active.
+    """
+    pct_int = min(int(compaction_progress * 100), 100)
+    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
+    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)
+
+    threshold_k = f"{threshold_tokens // 1000}k" if threshold_tokens >= 1000 else str(threshold_tokens)
+    threshold_pct_int = int(threshold_percent * 100)
+
+    color = f"{_BOLD}{_YELLOW}"
+    icon = "⚠"
+    if compression_enabled:
+        hint = "compaction approaching"
+    else:
+        hint = "no auto-compaction"
+
+    return (
+        f"  {color}{icon} context {bar} {pct_int}% to compaction{_ANSI_RESET}"
+        f"  {_DIM_ANSI}{threshold_k} threshold ({threshold_pct_int}%) · {hint}{_ANSI_RESET}"
+    )
+
+
+def format_context_pressure_gateway(
+    compaction_progress: float,
+    threshold_percent: float,
+    compression_enabled: bool = True,
+) -> str:
+    """Build a plain-text context pressure notification for messaging platforms.
+
+    No ANSI — just Unicode and plain text suitable for Telegram/Discord/etc.
+    The percentage shows progress toward the compaction threshold.
+    """
+    pct_int = min(int(compaction_progress * 100), 100)
+    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
+    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)
+
+    threshold_pct_int = int(threshold_percent * 100)
+
+    icon = "⚠️"
+    if compression_enabled:
+        hint = f"Context compaction approaching (threshold: {threshold_pct_int}% of window)."
+    else:
+        hint = "Auto-compaction is disabled — context may be truncated."
+
+    return f"{icon} Context: {bar} {pct_int}% to compaction\n{hint}"

agent/error_classifier.py

@@ -13,6 +13,7 @@ from __future__ import annotations
 
 import enum
 import logging
+import re
 from dataclasses import dataclass, field
 from typing import Any, Dict, Optional
 
@@ -111,11 +112,6 @@ _RATE_LIMIT_PATTERNS = [
     "try again in",
     "please retry after",
     "resource_exhausted",
-    "rate increased too quickly",  # Alibaba/DashScope throttling
-    # AWS Bedrock throttling
-    "throttlingexception",
-    "too many concurrent requests",
-    "servicequotaexceededexception",
 ]
 
 # Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
@@ -160,26 +156,9 @@ _CONTEXT_OVERFLOW_PATTERNS = [
     "prompt exceeds max length",
     "max_tokens",
     "maximum number of tokens",
-    # vLLM / local inference server patterns
-    "exceeds the max_model_len",
-    "max_model_len",
-    "prompt length",             # "engine prompt length X exceeds"
-    "input is too long",
-    "maximum model length",
-    # Ollama patterns
-    "context length exceeded",
-    "truncating input",
-    # llama.cpp / llama-server patterns
-    "slot context",              # "slot context: N tokens, prompt N tokens"
-    "n_ctx_slot",
     # Chinese error messages (some providers return these)
     "超过最大长度",
     "上下文长度",
-    # AWS Bedrock Converse API error patterns
-    "input is too long",
-    "max input token",
-    "input token",
-    "exceeds the maximum number of input tokens",
 ]
 
 # Model not found patterns
@@ -290,7 +269,7 @@ def classify_api_error(
     if isinstance(body, dict):
         _err_obj = body.get("error", {})
         if isinstance(_err_obj, dict):
-            _body_msg = str(_err_obj.get("message") or "").lower()
+            _body_msg = (_err_obj.get("message") or "").lower()
             # Parse metadata.raw for wrapped provider errors
             _metadata = _err_obj.get("metadata", {})
             if isinstance(_metadata, dict):
@@ -302,11 +281,11 @@ def classify_api_error(
                         if isinstance(_inner, dict):
                             _inner_err = _inner.get("error", {})
                             if isinstance(_inner_err, dict):
-                                _metadata_msg = str(_inner_err.get("message") or "").lower()
+                                _metadata_msg = (_inner_err.get("message") or "").lower()
                     except (json.JSONDecodeError, TypeError):
                         pass
         if not _body_msg:
-            _body_msg = str(body.get("message") or "").lower()
+            _body_msg = (body.get("message") or "").lower()
     # Combine all message sources for pattern matching
     parts = [_raw_msg]
     if _body_msg and _body_msg not in _raw_msg:
@@ -606,10 +585,10 @@ def _classify_400(
     if isinstance(body, dict):
         err_obj = body.get("error", {})
         if isinstance(err_obj, dict):
-            err_body_msg = str(err_obj.get("message") or "").strip().lower()
+            err_body_msg = (err_obj.get("message") or "").strip().lower()
         # Responses API (and some providers) use flat body: {"message": "..."}
         if not err_body_msg:
-            err_body_msg = str(body.get("message") or "").strip().lower()
+            err_body_msg = (body.get("message") or "").strip().lower()
     is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
     is_large = approx_tokens > context_length * 0.4 or approx_tokens > 80000 or num_messages > 80
 
@@ -688,27 +667,6 @@ def _classify_by_message(
             should_compress=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
-    # billing exhaustion.
-    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
-    if has_usage_limit:
-        has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
-        if has_transient_signal:
-            return result_fn(
-                FailoverReason.rate_limit,
-                retryable=True,
-                should_rotate_credential=True,
-                should_fallback=True,
-            )
-        return result_fn(
-            FailoverReason.billing,
-            retryable=False,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
     # Billing patterns
     if any(p in error_msg for p in _BILLING_PATTERNS):
         return result_fn(
@@ -736,16 +694,11 @@ def _classify_by_message(
         )
 
     # Auth patterns
-    # Auth errors should NOT be retried directly — the credential is invalid and
-    # retrying with the same key will always fail.  Set retryable=False so the
-    # caller triggers credential rotation (should_rotate_credential=True) or
-    # provider fallback rather than an immediate retry loop.
     if any(p in error_msg for p in _AUTH_PATTERNS):
         return result_fn(
             FailoverReason.auth,
-            retryable=False,
+            retryable=True,
             should_rotate_credential=True,
-            should_fallback=True,
         )
 
     # Model not found patterns

agent/gemini_cloudcode_adapter.py

@@ -1,904 +0,0 @@
-"""OpenAI-compatible facade that talks to Google's Cloud Code Assist backend.
-
-This adapter lets Hermes use the ``google-gemini-cli`` provider as if it were
-a standard OpenAI-shaped chat completion endpoint, while the underlying HTTP
-traffic goes to ``cloudcode-pa.googleapis.com/v1internal:{generateContent,
-streamGenerateContent}`` with a Bearer access token obtained via OAuth PKCE.
-
-Architecture
-------------
-- ``GeminiCloudCodeClient`` exposes ``.chat.completions.create(**kwargs)``
-  mirroring the subset of the OpenAI SDK that ``run_agent.py`` uses.
-- Incoming OpenAI ``messages[]`` / ``tools[]`` / ``tool_choice`` are translated
-  to Gemini's native ``contents[]`` / ``tools[].functionDeclarations`` /
-  ``toolConfig`` / ``systemInstruction`` shape.
-- The request body is wrapped ``{project, model, user_prompt_id, request}``
-  per Code Assist API expectations.
-- Responses (``candidates[].content.parts[]``) are converted back to
-  OpenAI ``choices[0].message`` shape with ``content`` + ``tool_calls``.
-- Streaming uses SSE (``?alt=sse``) and yields OpenAI-shaped delta chunks.
-
-Attribution
------------
-Translation semantics follow jenslys/opencode-gemini-auth (MIT) and the public
-Gemini API docs. Request envelope shape
-(``{project, model, user_prompt_id, request}``) is documented nowhere; it is
-reverse-engineered from the opencode-gemini-auth and clawdbot implementations.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import time
-import uuid
-from types import SimpleNamespace
-from typing import Any, Dict, Iterator, List, Optional
-
-import httpx
-
-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,
-)
-
-logger = logging.getLogger(__name__)
-
-
-# =============================================================================
-# Request translation: OpenAI → Gemini
-# =============================================================================
-
-_ROLE_MAP_OPENAI_TO_GEMINI = {
-    "user": "user",
-    "assistant": "model",
-    "system": "user",   # handled separately via systemInstruction
-    "tool": "user",     # functionResponse is wrapped in a user-role turn
-    "function": "user",
-}
-
-
-def _coerce_content_to_text(content: Any) -> str:
-    """OpenAI content may be str or a list of parts; reduce to plain text."""
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        pieces: List[str] = []
-        for p in content:
-            if isinstance(p, str):
-                pieces.append(p)
-            elif isinstance(p, dict):
-                if p.get("type") == "text" and isinstance(p.get("text"), str):
-                    pieces.append(p["text"])
-                # Multimodal (image_url, etc.) — stub for now; log and skip
-                elif p.get("type") in ("image_url", "input_audio"):
-                    logger.debug("Dropping multimodal part (not yet supported): %s", p.get("type"))
-        return "\n".join(pieces)
-    return str(content)
-
-
-def _translate_tool_call_to_gemini(tool_call: Dict[str, Any]) -> Dict[str, Any]:
-    """OpenAI tool_call -> Gemini functionCall part."""
-    fn = tool_call.get("function") or {}
-    args_raw = fn.get("arguments", "")
-    try:
-        args = json.loads(args_raw) if isinstance(args_raw, str) and args_raw else {}
-    except json.JSONDecodeError:
-        args = {"_raw": args_raw}
-    if not isinstance(args, dict):
-        args = {"_value": args}
-    return {
-        "functionCall": {
-            "name": fn.get("name") or "",
-            "args": args,
-        },
-        # Sentinel signature — matches opencode-gemini-auth's approach.
-        # Without this, Code Assist rejects function calls that originated
-        # outside its own chain.
-        "thoughtSignature": "skip_thought_signature_validator",
-    }
-
-
-def _translate_tool_result_to_gemini(message: Dict[str, Any]) -> Dict[str, Any]:
-    """OpenAI tool-role message -> Gemini functionResponse part.
-
-    The function name isn't in the OpenAI tool message directly; it must be
-    passed via the assistant message that issued the call. For simplicity we
-    look up ``name`` on the message (OpenAI SDK copies it there) or on the
-    ``tool_call_id`` cross-reference.
-    """
-    name = str(message.get("name") or message.get("tool_call_id") or "tool")
-    content = _coerce_content_to_text(message.get("content"))
-    # Gemini expects the response as a dict under `response`. We wrap plain
-    # text in {"output": "..."}.
-    try:
-        parsed = json.loads(content) if content.strip().startswith(("{", "[")) else None
-    except json.JSONDecodeError:
-        parsed = None
-    response = parsed if isinstance(parsed, dict) else {"output": content}
-    return {
-        "functionResponse": {
-            "name": name,
-            "response": response,
-        },
-    }
-
-
-def _build_gemini_contents(
-    messages: List[Dict[str, Any]],
-) -> tuple[List[Dict[str, Any]], Optional[Dict[str, Any]]]:
-    """Convert OpenAI messages[] to Gemini contents[] + systemInstruction."""
-    system_text_parts: List[str] = []
-    contents: List[Dict[str, Any]] = []
-
-    for msg in messages:
-        if not isinstance(msg, dict):
-            continue
-        role = str(msg.get("role") or "user")
-
-        if role == "system":
-            system_text_parts.append(_coerce_content_to_text(msg.get("content")))
-            continue
-
-        # Tool result message — emit a user-role turn with functionResponse
-        if role == "tool" or role == "function":
-            contents.append({
-                "role": "user",
-                "parts": [_translate_tool_result_to_gemini(msg)],
-            })
-            continue
-
-        gemini_role = _ROLE_MAP_OPENAI_TO_GEMINI.get(role, "user")
-        parts: List[Dict[str, Any]] = []
-
-        text = _coerce_content_to_text(msg.get("content"))
-        if text:
-            parts.append({"text": text})
-
-        # Assistant messages can carry tool_calls
-        tool_calls = msg.get("tool_calls") or []
-        if isinstance(tool_calls, list):
-            for tc in tool_calls:
-                if isinstance(tc, dict):
-                    parts.append(_translate_tool_call_to_gemini(tc))
-
-        if not parts:
-            # Gemini rejects empty parts; skip the turn entirely
-            continue
-
-        contents.append({"role": gemini_role, "parts": parts})
-
-    system_instruction: Optional[Dict[str, Any]] = None
-    joined_system = "\n".join(p for p in system_text_parts if p).strip()
-    if joined_system:
-        system_instruction = {
-            "role": "system",
-            "parts": [{"text": joined_system}],
-        }
-
-    return contents, system_instruction
-
-
-def _translate_tools_to_gemini(tools: Any) -> List[Dict[str, Any]]:
-    """OpenAI tools[] -> Gemini tools[].functionDeclarations[]."""
-    if not isinstance(tools, list) or not tools:
-        return []
-    declarations: List[Dict[str, Any]] = []
-    for t in tools:
-        if not isinstance(t, dict):
-            continue
-        fn = t.get("function") or {}
-        if not isinstance(fn, dict):
-            continue
-        name = fn.get("name")
-        if not name:
-            continue
-        decl = {"name": str(name)}
-        if fn.get("description"):
-            decl["description"] = str(fn["description"])
-        params = fn.get("parameters")
-        if isinstance(params, dict):
-            decl["parameters"] = sanitize_gemini_tool_parameters(params)
-        declarations.append(decl)
-    if not declarations:
-        return []
-    return [{"functionDeclarations": declarations}]
-
-
-def _translate_tool_choice_to_gemini(tool_choice: Any) -> Optional[Dict[str, Any]]:
-    """OpenAI tool_choice -> Gemini toolConfig.functionCallingConfig."""
-    if tool_choice is None:
-        return None
-    if isinstance(tool_choice, str):
-        if tool_choice == "auto":
-            return {"functionCallingConfig": {"mode": "AUTO"}}
-        if tool_choice == "required":
-            return {"functionCallingConfig": {"mode": "ANY"}}
-        if tool_choice == "none":
-            return {"functionCallingConfig": {"mode": "NONE"}}
-    if isinstance(tool_choice, dict):
-        fn = tool_choice.get("function") or {}
-        name = fn.get("name")
-        if name:
-            return {
-                "functionCallingConfig": {
-                    "mode": "ANY",
-                    "allowedFunctionNames": [str(name)],
-                },
-            }
-    return None
-
-
-def _normalize_thinking_config(config: Any) -> Optional[Dict[str, Any]]:
-    """Accept thinkingBudget / thinkingLevel / includeThoughts (+ snake_case)."""
-    if not isinstance(config, dict) or not config:
-        return None
-    budget = config.get("thinkingBudget", config.get("thinking_budget"))
-    level = config.get("thinkingLevel", config.get("thinking_level"))
-    include = config.get("includeThoughts", config.get("include_thoughts"))
-    normalized: Dict[str, Any] = {}
-    if isinstance(budget, (int, float)):
-        normalized["thinkingBudget"] = int(budget)
-    if isinstance(level, str) and level.strip():
-        normalized["thinkingLevel"] = level.strip().lower()
-    if isinstance(include, bool):
-        normalized["includeThoughts"] = include
-    return normalized or None
-
-
-def build_gemini_request(
-    *,
-    messages: List[Dict[str, Any]],
-    tools: Any = None,
-    tool_choice: Any = None,
-    temperature: Optional[float] = None,
-    max_tokens: Optional[int] = None,
-    top_p: Optional[float] = None,
-    stop: Any = None,
-    thinking_config: Any = None,
-) -> Dict[str, Any]:
-    """Build the inner Gemini request body (goes inside ``request`` wrapper)."""
-    contents, system_instruction = _build_gemini_contents(messages)
-
-    body: Dict[str, Any] = {"contents": contents}
-    if system_instruction is not None:
-        body["systemInstruction"] = system_instruction
-
-    gemini_tools = _translate_tools_to_gemini(tools)
-    if gemini_tools:
-        body["tools"] = gemini_tools
-    tool_cfg = _translate_tool_choice_to_gemini(tool_choice)
-    if tool_cfg is not None:
-        body["toolConfig"] = tool_cfg
-
-    generation_config: Dict[str, Any] = {}
-    if isinstance(temperature, (int, float)):
-        generation_config["temperature"] = float(temperature)
-    if isinstance(max_tokens, int) and max_tokens > 0:
-        generation_config["maxOutputTokens"] = max_tokens
-    if isinstance(top_p, (int, float)):
-        generation_config["topP"] = float(top_p)
-    if isinstance(stop, str) and stop:
-        generation_config["stopSequences"] = [stop]
-    elif isinstance(stop, list) and stop:
-        generation_config["stopSequences"] = [str(s) for s in stop if s]
-    normalized_thinking = _normalize_thinking_config(thinking_config)
-    if normalized_thinking:
-        generation_config["thinkingConfig"] = normalized_thinking
-    if generation_config:
-        body["generationConfig"] = generation_config
-
-    return body
-
-
-def wrap_code_assist_request(
-    *,
-    project_id: str,
-    model: str,
-    inner_request: Dict[str, Any],
-    user_prompt_id: Optional[str] = None,
-) -> Dict[str, Any]:
-    """Wrap the inner Gemini request in the Code Assist envelope."""
-    return {
-        "project": project_id,
-        "model": model,
-        "user_prompt_id": user_prompt_id or str(uuid.uuid4()),
-        "request": inner_request,
-    }
-
-
-# =============================================================================
-# Response translation: Gemini → OpenAI
-# =============================================================================
-
-def _translate_gemini_response(
-    resp: Dict[str, Any],
-    model: str,
-) -> SimpleNamespace:
-    """Non-streaming Gemini response -> OpenAI-shaped SimpleNamespace.
-
-    Code Assist wraps the actual Gemini response inside ``response``, so we
-    unwrap it first if present.
-    """
-    inner = resp.get("response") if isinstance(resp.get("response"), dict) else resp
-
-    candidates = inner.get("candidates") or []
-    if not isinstance(candidates, list) or not candidates:
-        return _empty_response(model)
-
-    cand = candidates[0]
-    content_obj = cand.get("content") if isinstance(cand, dict) else {}
-    parts = content_obj.get("parts") if isinstance(content_obj, dict) else []
-
-    text_pieces: List[str] = []
-    reasoning_pieces: List[str] = []
-    tool_calls: List[SimpleNamespace] = []
-
-    for i, part in enumerate(parts or []):
-        if not isinstance(part, dict):
-            continue
-        # Thought parts are model's internal reasoning — surface as reasoning,
-        # don't mix into content.
-        if part.get("thought") is True:
-            if isinstance(part.get("text"), str):
-                reasoning_pieces.append(part["text"])
-            continue
-        if isinstance(part.get("text"), str):
-            text_pieces.append(part["text"])
-            continue
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            tool_calls.append(SimpleNamespace(
-                id=f"call_{uuid.uuid4().hex[:12]}",
-                type="function",
-                index=i,
-                function=SimpleNamespace(name=str(fc["name"]), arguments=args_str),
-            ))
-
-    finish_reason = "tool_calls" if tool_calls else _map_gemini_finish_reason(
-        str(cand.get("finishReason") or "")
-    )
-
-    usage_meta = inner.get("usageMetadata") or {}
-    usage = SimpleNamespace(
-        prompt_tokens=int(usage_meta.get("promptTokenCount") or 0),
-        completion_tokens=int(usage_meta.get("candidatesTokenCount") or 0),
-        total_tokens=int(usage_meta.get("totalTokenCount") or 0),
-        prompt_tokens_details=SimpleNamespace(
-            cached_tokens=int(usage_meta.get("cachedContentTokenCount") or 0),
-        ),
-    )
-
-    message = SimpleNamespace(
-        role="assistant",
-        content="".join(text_pieces) if text_pieces else None,
-        tool_calls=tool_calls or None,
-        reasoning="".join(reasoning_pieces) or None,
-        reasoning_content="".join(reasoning_pieces) or None,
-        reasoning_details=None,
-    )
-    choice = SimpleNamespace(
-        index=0,
-        message=message,
-        finish_reason=finish_reason,
-    )
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-def _empty_response(model: str) -> SimpleNamespace:
-    message = SimpleNamespace(
-        role="assistant", content="", tool_calls=None,
-        reasoning=None, reasoning_content=None, reasoning_details=None,
-    )
-    choice = SimpleNamespace(index=0, message=message, finish_reason="stop")
-    usage = SimpleNamespace(
-        prompt_tokens=0, completion_tokens=0, total_tokens=0,
-        prompt_tokens_details=SimpleNamespace(cached_tokens=0),
-    )
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-def _map_gemini_finish_reason(reason: str) -> str:
-    mapping = {
-        "STOP": "stop",
-        "MAX_TOKENS": "length",
-        "SAFETY": "content_filter",
-        "RECITATION": "content_filter",
-        "OTHER": "stop",
-    }
-    return mapping.get(reason.upper(), "stop")
-
-
-# =============================================================================
-# Streaming SSE iterator
-# =============================================================================
-
-class _GeminiStreamChunk(SimpleNamespace):
-    """Mimics an OpenAI ChatCompletionChunk with .choices[0].delta."""
-    pass
-
-
-def _make_stream_chunk(
-    *,
-    model: str,
-    content: str = "",
-    tool_call_delta: Optional[Dict[str, Any]] = None,
-    finish_reason: Optional[str] = None,
-    reasoning: str = "",
-) -> _GeminiStreamChunk:
-    delta_kwargs: Dict[str, Any] = {"role": "assistant"}
-    if content:
-        delta_kwargs["content"] = content
-    if tool_call_delta is not None:
-        delta_kwargs["tool_calls"] = [SimpleNamespace(
-            index=tool_call_delta.get("index", 0),
-            id=tool_call_delta.get("id") or f"call_{uuid.uuid4().hex[:12]}",
-            type="function",
-            function=SimpleNamespace(
-                name=tool_call_delta.get("name") or "",
-                arguments=tool_call_delta.get("arguments") or "",
-            ),
-        )]
-    if reasoning:
-        delta_kwargs["reasoning"] = reasoning
-        delta_kwargs["reasoning_content"] = reasoning
-    delta = SimpleNamespace(**delta_kwargs)
-    choice = SimpleNamespace(index=0, delta=delta, finish_reason=finish_reason)
-    return _GeminiStreamChunk(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion.chunk",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=None,
-    )
-
-
-def _iter_sse_events(response: httpx.Response) -> Iterator[Dict[str, Any]]:
-    """Parse Server-Sent Events from an httpx streaming response."""
-    buffer = ""
-    for chunk in response.iter_text():
-        if not chunk:
-            continue
-        buffer += chunk
-        while "\n" in buffer:
-            line, buffer = buffer.split("\n", 1)
-            line = line.rstrip("\r")
-            if not line:
-                continue
-            if line.startswith("data: "):
-                data = line[6:]
-                if data == "[DONE]":
-                    return
-                try:
-                    yield json.loads(data)
-                except json.JSONDecodeError:
-                    logger.debug("Non-JSON SSE line: %s", data[:200])
-
-
-def _translate_stream_event(
-    event: Dict[str, Any],
-    model: str,
-    tool_call_counter: List[int],
-) -> List[_GeminiStreamChunk]:
-    """Unwrap Code Assist envelope and emit OpenAI-shaped chunk(s).
-
-    ``tool_call_counter`` is a single-element list used as a mutable counter
-    across events in the same stream. Each ``functionCall`` part gets a
-    fresh, unique OpenAI ``index`` — keying by function name would collide
-    whenever the model issues parallel calls to the same tool (e.g. reading
-    three files in one turn).
-    """
-    inner = event.get("response") if isinstance(event.get("response"), dict) else event
-    candidates = inner.get("candidates") or []
-    if not candidates:
-        return []
-    cand = candidates[0]
-    if not isinstance(cand, dict):
-        return []
-
-    chunks: List[_GeminiStreamChunk] = []
-
-    content = cand.get("content") or {}
-    parts = content.get("parts") if isinstance(content, dict) else []
-    for part in parts or []:
-        if not isinstance(part, dict):
-            continue
-        if part.get("thought") is True and isinstance(part.get("text"), str):
-            chunks.append(_make_stream_chunk(
-                model=model, reasoning=part["text"],
-            ))
-            continue
-        if isinstance(part.get("text"), str) and part["text"]:
-            chunks.append(_make_stream_chunk(model=model, content=part["text"]))
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            name = str(fc["name"])
-            idx = tool_call_counter[0]
-            tool_call_counter[0] += 1
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            chunks.append(_make_stream_chunk(
-                model=model,
-                tool_call_delta={
-                    "index": idx,
-                    "name": name,
-                    "arguments": args_str,
-                },
-            ))
-
-    finish_reason_raw = str(cand.get("finishReason") or "")
-    if finish_reason_raw:
-        mapped = _map_gemini_finish_reason(finish_reason_raw)
-        if tool_call_counter[0] > 0:
-            mapped = "tool_calls"
-        chunks.append(_make_stream_chunk(model=model, finish_reason=mapped))
-    return chunks
-
-
-# =============================================================================
-# GeminiCloudCodeClient — OpenAI-compatible facade
-# =============================================================================
-
-MARKER_BASE_URL = "cloudcode-pa://google"
-
-
-class _GeminiChatCompletions:
-    def __init__(self, client: "GeminiCloudCodeClient"):
-        self._client = client
-
-    def create(self, **kwargs: Any) -> Any:
-        return self._client._create_chat_completion(**kwargs)
-
-
-class _GeminiChatNamespace:
-    def __init__(self, client: "GeminiCloudCodeClient"):
-        self.completions = _GeminiChatCompletions(client)
-
-
-class GeminiCloudCodeClient:
-    """Minimal OpenAI-SDK-compatible facade over Code Assist v1internal."""
-
-    def __init__(
-        self,
-        *,
-        api_key: Optional[str] = None,
-        base_url: Optional[str] = None,
-        default_headers: Optional[Dict[str, str]] = None,
-        project_id: str = "",
-        **_: Any,
-    ):
-        # `api_key` here is a dummy — real auth is the OAuth access token
-        # fetched on every call via agent.google_oauth.get_valid_access_token().
-        # We accept the kwarg for openai.OpenAI interface parity.
-        self.api_key = api_key or "google-oauth"
-        self.base_url = base_url or MARKER_BASE_URL
-        self._default_headers = dict(default_headers or {})
-        self._configured_project_id = project_id
-        self._project_context: Optional[ProjectContext] = None
-        self._project_context_lock = False  # simple single-thread guard
-        self.chat = _GeminiChatNamespace(self)
-        self.is_closed = False
-        self._http = httpx.Client(timeout=httpx.Timeout(connect=15.0, read=600.0, write=30.0, pool=30.0))
-
-    def close(self) -> None:
-        self.is_closed = True
-        try:
-            self._http.close()
-        except Exception:
-            pass
-
-    # Implement the OpenAI SDK's context-manager-ish closure check
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        self.close()
-
-    def _ensure_project_context(self, access_token: str, model: str) -> ProjectContext:
-        """Lazily resolve and cache the project context for this client."""
-        if self._project_context is not None:
-            return self._project_context
-
-        env_project = google_oauth.resolve_project_id_from_env()
-        creds = google_oauth.load_credentials()
-        stored_project = creds.project_id if creds else ""
-
-        # Prefer what's already baked into the creds
-        if stored_project:
-            self._project_context = ProjectContext(
-                project_id=stored_project,
-                managed_project_id=creds.managed_project_id if creds else "",
-                tier_id="",
-                source="stored",
-            )
-            return self._project_context
-
-        ctx = resolve_project_context(
-            access_token,
-            configured_project_id=self._configured_project_id,
-            env_project_id=env_project,
-            user_agent_model=model,
-        )
-        # Persist discovered project back to the creds file so the next
-        # session doesn't re-run the discovery.
-        if ctx.project_id or ctx.managed_project_id:
-            google_oauth.update_project_ids(
-                project_id=ctx.project_id,
-                managed_project_id=ctx.managed_project_id,
-            )
-        self._project_context = ctx
-        return ctx
-
-    def _create_chat_completion(
-        self,
-        *,
-        model: str = "gemini-2.5-flash",
-        messages: Optional[List[Dict[str, Any]]] = None,
-        stream: bool = False,
-        tools: Any = None,
-        tool_choice: Any = None,
-        temperature: Optional[float] = None,
-        max_tokens: Optional[int] = None,
-        top_p: Optional[float] = None,
-        stop: Any = None,
-        extra_body: Optional[Dict[str, Any]] = None,
-        timeout: Any = None,
-        **_: Any,
-    ) -> Any:
-        access_token = google_oauth.get_valid_access_token()
-        ctx = self._ensure_project_context(access_token, model)
-
-        thinking_config = None
-        if isinstance(extra_body, dict):
-            thinking_config = extra_body.get("thinking_config") or extra_body.get("thinkingConfig")
-
-        inner = build_gemini_request(
-            messages=messages or [],
-            tools=tools,
-            tool_choice=tool_choice,
-            temperature=temperature,
-            max_tokens=max_tokens,
-            top_p=top_p,
-            stop=stop,
-            thinking_config=thinking_config,
-        )
-        wrapped = wrap_code_assist_request(
-            project_id=ctx.project_id,
-            model=model,
-            inner_request=inner,
-        )
-
-        headers = {
-            "Content-Type": "application/json",
-            "Accept": "application/json",
-            "Authorization": f"Bearer {access_token}",
-            "User-Agent": "hermes-agent (gemini-cli-compat)",
-            "X-Goog-Api-Client": "gl-python/hermes",
-            "x-activity-request-id": str(uuid.uuid4()),
-        }
-        headers.update(self._default_headers)
-
-        if stream:
-            return self._stream_completion(model=model, wrapped=wrapped, headers=headers)
-
-        url = f"{CODE_ASSIST_ENDPOINT}/v1internal:generateContent"
-        response = self._http.post(url, json=wrapped, headers=headers)
-        if response.status_code != 200:
-            raise _gemini_http_error(response)
-        try:
-            payload = response.json()
-        except ValueError as exc:
-            raise CodeAssistError(
-                f"Invalid JSON from Code Assist: {exc}",
-                code="code_assist_invalid_json",
-            ) from exc
-        return _translate_gemini_response(payload, model=model)
-
-    def _stream_completion(
-        self,
-        *,
-        model: str,
-        wrapped: Dict[str, Any],
-        headers: Dict[str, str],
-    ) -> Iterator[_GeminiStreamChunk]:
-        """Generator that yields OpenAI-shaped streaming chunks."""
-        url = f"{CODE_ASSIST_ENDPOINT}/v1internal:streamGenerateContent?alt=sse"
-        stream_headers = dict(headers)
-        stream_headers["Accept"] = "text/event-stream"
-
-        def _generator() -> Iterator[_GeminiStreamChunk]:
-            try:
-                with self._http.stream("POST", url, json=wrapped, headers=stream_headers) as response:
-                    if response.status_code != 200:
-                        # Materialize error body for better diagnostics
-                        response.read()
-                        raise _gemini_http_error(response)
-                    tool_call_counter: List[int] = [0]
-                    for event in _iter_sse_events(response):
-                        for chunk in _translate_stream_event(event, model, tool_call_counter):
-                            yield chunk
-            except httpx.HTTPError as exc:
-                raise CodeAssistError(
-                    f"Streaming request failed: {exc}",
-                    code="code_assist_stream_error",
-                ) from exc
-
-        return _generator()
-
-
-def _gemini_http_error(response: httpx.Response) -> CodeAssistError:
-    """Translate an httpx response into a CodeAssistError with rich metadata.
-
-    Parses Google's error envelope (``{"error": {"code", "message", "status",
-    "details": [...]}}``) so the agent's error classifier can reason about
-    the failure — ``status_code`` enables the rate_limit / auth classification
-    paths, and ``response`` lets the main loop honor ``Retry-After`` just
-    like it does for OpenAI SDK exceptions.
-
-    Also lifts a few recognizable Google conditions into human-readable
-    messages so the user sees something better than a 500-char JSON dump:
-
-        MODEL_CAPACITY_EXHAUSTED → "Gemini model capacity exhausted for
-            <model>. This is a Google-side throttle..."
-        RESOURCE_EXHAUSTED w/o reason → quota-style message
-        404 → "Model <name> not found at cloudcode-pa..."
-    """
-    status = response.status_code
-
-    # Parse the body once, surviving any weird encodings.
-    body_text = ""
-    body_json: Dict[str, Any] = {}
-    try:
-        body_text = response.text
-    except Exception:
-        body_text = ""
-    if body_text:
-        try:
-            parsed = json.loads(body_text)
-            if isinstance(parsed, dict):
-                body_json = parsed
-        except (ValueError, TypeError):
-            body_json = {}
-
-    # Dig into Google's error envelope.  Shape is:
-    #   {"error": {"code": 429, "message": "...", "status": "RESOURCE_EXHAUSTED",
-    #              "details": [{"@type": ".../ErrorInfo", "reason": "MODEL_CAPACITY_EXHAUSTED",
-    #                           "metadata": {...}},
-    #                          {"@type": ".../RetryInfo", "retryDelay": "30s"}]}}
-    err_obj = body_json.get("error") if isinstance(body_json, dict) else None
-    if not isinstance(err_obj, dict):
-        err_obj = {}
-    err_status = str(err_obj.get("status") or "").strip()
-    err_message = str(err_obj.get("message") or "").strip()
-    err_details_list = err_obj.get("details") if isinstance(err_obj.get("details"), list) else []
-
-    # Extract google.rpc.ErrorInfo reason + metadata.  There may be more
-    # than one ErrorInfo (rare), so we pick the first one with a reason.
-    error_reason = ""
-    error_metadata: Dict[str, Any] = {}
-    retry_delay_seconds: Optional[float] = None
-    for detail in err_details_list:
-        if not isinstance(detail, dict):
-            continue
-        type_url = str(detail.get("@type") or "")
-        if not error_reason and type_url.endswith("/google.rpc.ErrorInfo"):
-            reason = detail.get("reason")
-            if isinstance(reason, str) and reason:
-                error_reason = reason
-            md = detail.get("metadata")
-            if isinstance(md, dict):
-                error_metadata = md
-        elif retry_delay_seconds is None and type_url.endswith("/google.rpc.RetryInfo"):
-            # retryDelay is a google.protobuf.Duration string like "30s" or "1.5s".
-            delay_raw = detail.get("retryDelay")
-            if isinstance(delay_raw, str) and delay_raw.endswith("s"):
-                try:
-                    retry_delay_seconds = float(delay_raw[:-1])
-                except ValueError:
-                    pass
-            elif isinstance(delay_raw, (int, float)):
-                retry_delay_seconds = float(delay_raw)
-
-    # Fall back to the Retry-After header if the body didn't include RetryInfo.
-    if retry_delay_seconds is None:
-        try:
-            header_val = response.headers.get("Retry-After") or response.headers.get("retry-after")
-        except Exception:
-            header_val = None
-        if header_val:
-            try:
-                retry_delay_seconds = float(header_val)
-            except (TypeError, ValueError):
-                retry_delay_seconds = None
-
-    # Classify the error code.  ``code_assist_rate_limited`` stays the default
-    # for 429s; a more specific reason tag helps downstream callers (e.g. tests,
-    # logs) without changing the rate_limit classification path.
-    code = f"code_assist_http_{status}"
-    if status == 401:
-        code = "code_assist_unauthorized"
-    elif status == 429:
-        code = "code_assist_rate_limited"
-        if error_reason == "MODEL_CAPACITY_EXHAUSTED":
-            code = "code_assist_capacity_exhausted"
-
-    # Build a human-readable message.  Keep the status + a raw-body tail for
-    # debugging, but lead with a friendlier summary when we recognize the
-    # Google signal.
-    model_hint = ""
-    if isinstance(error_metadata, dict):
-        model_hint = str(error_metadata.get("model") or error_metadata.get("modelId") or "").strip()
-
-    if status == 429 and error_reason == "MODEL_CAPACITY_EXHAUSTED":
-        target = model_hint or "this Gemini model"
-        message = (
-            f"Gemini capacity exhausted for {target} (Google-side throttle, "
-            f"not a Hermes issue). Try a different Gemini model or set a "
-            f"fallback_providers entry to a non-Gemini provider."
-        )
-        if retry_delay_seconds is not None:
-            message += f" Google suggests retrying in {retry_delay_seconds:g}s."
-    elif status == 429 and err_status == "RESOURCE_EXHAUSTED":
-        message = (
-            f"Gemini quota exhausted ({err_message or 'RESOURCE_EXHAUSTED'}). "
-            f"Check /gquota for remaining daily requests."
-        )
-        if retry_delay_seconds is not None:
-            message += f" Retry suggested in {retry_delay_seconds:g}s."
-    elif status == 404:
-        # Google returns 404 when a model has been retired or renamed.
-        target = model_hint or (err_message or "model")
-        message = (
-            f"Code Assist 404: {target} is not available at "
-            f"cloudcode-pa.googleapis.com. It may have been renamed or "
-            f"retired. Check hermes_cli/models.py for the current list."
-        )
-    elif err_message:
-        # Generic fallback with the parsed message.
-        message = f"Code Assist HTTP {status} ({err_status or 'error'}): {err_message}"
-    else:
-        # Last-ditch fallback — raw body snippet.
-        message = f"Code Assist returned HTTP {status}: {body_text[:500]}"
-
-    return CodeAssistError(
-        message,
-        code=code,
-        status_code=status,
-        response=response,
-        retry_after=retry_delay_seconds,
-        details={
-            "status": err_status,
-            "reason": error_reason,
-            "metadata": error_metadata,
-            "message": err_message,
-        },
-    )

agent/gemini_native_adapter.py

@@ -1,846 +0,0 @@
-"""OpenAI-compatible facade over Google AI Studio's native Gemini API.
-
-Hermes keeps ``api_mode='chat_completions'`` for the ``gemini`` provider so the
-main agent loop can keep using its existing OpenAI-shaped message flow.
-This adapter is the transport shim that converts those OpenAI-style
-``messages[]`` / ``tools[]`` requests into Gemini's native
-``models/{model}:generateContent`` schema and converts the responses back.
-
-Why this exists
----------------
-Google's OpenAI-compatible endpoint has been brittle for Hermes's multi-turn
-agent/tool loop (auth churn, tool-call replay quirks, thought-signature
-requirements).  The native Gemini API is the canonical path and avoids the
-OpenAI-compat layer entirely.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import base64
-import json
-import logging
-import time
-import uuid
-from types import SimpleNamespace
-from typing import Any, Dict, Iterator, List, Optional
-
-import httpx
-
-from agent.gemini_schema import sanitize_gemini_tool_parameters
-
-logger = logging.getLogger(__name__)
-
-DEFAULT_GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta"
-
-
-def is_native_gemini_base_url(base_url: str) -> bool:
-    """Return True when the endpoint speaks Gemini's native REST API."""
-    normalized = str(base_url or "").strip().rstrip("/").lower()
-    if not normalized:
-        return False
-    if "generativelanguage.googleapis.com" not in normalized:
-        return False
-    return not normalized.endswith("/openai")
-
-
-class GeminiAPIError(Exception):
-    """Error shape compatible with Hermes retry/error classification."""
-
-    def __init__(
-        self,
-        message: str,
-        *,
-        code: str = "gemini_api_error",
-        status_code: Optional[int] = None,
-        response: Optional[httpx.Response] = None,
-        retry_after: Optional[float] = None,
-        details: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        super().__init__(message)
-        self.code = code
-        self.status_code = status_code
-        self.response = response
-        self.retry_after = retry_after
-        self.details = details or {}
-
-
-def _coerce_content_to_text(content: Any) -> str:
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        pieces: List[str] = []
-        for part in content:
-            if isinstance(part, str):
-                pieces.append(part)
-            elif isinstance(part, dict) and part.get("type") == "text":
-                text = part.get("text")
-                if isinstance(text, str):
-                    pieces.append(text)
-        return "\n".join(pieces)
-    return str(content)
-
-
-def _extract_multimodal_parts(content: Any) -> List[Dict[str, Any]]:
-    if not isinstance(content, list):
-        text = _coerce_content_to_text(content)
-        return [{"text": text}] if text else []
-
-    parts: List[Dict[str, Any]] = []
-    for item in content:
-        if isinstance(item, str):
-            parts.append({"text": item})
-            continue
-        if not isinstance(item, dict):
-            continue
-        ptype = item.get("type")
-        if ptype == "text":
-            text = item.get("text")
-            if isinstance(text, str) and text:
-                parts.append({"text": text})
-        elif ptype == "image_url":
-            url = ((item.get("image_url") or {}).get("url") or "")
-            if not isinstance(url, str) or not url.startswith("data:"):
-                continue
-            try:
-                header, encoded = url.split(",", 1)
-                mime = header.split(":", 1)[1].split(";", 1)[0]
-                raw = base64.b64decode(encoded)
-            except Exception:
-                continue
-            parts.append(
-                {
-                    "inlineData": {
-                        "mimeType": mime,
-                        "data": base64.b64encode(raw).decode("ascii"),
-                    }
-                }
-            )
-    return parts
-
-
-def _tool_call_extra_signature(tool_call: Dict[str, Any]) -> Optional[str]:
-    extra = tool_call.get("extra_content") or {}
-    if not isinstance(extra, dict):
-        return None
-    google = extra.get("google") or extra.get("thought_signature")
-    if isinstance(google, dict):
-        sig = google.get("thought_signature") or google.get("thoughtSignature")
-        return str(sig) if isinstance(sig, str) and sig else None
-    if isinstance(google, str) and google:
-        return google
-    return None
-
-
-def _translate_tool_call_to_gemini(tool_call: Dict[str, Any]) -> Dict[str, Any]:
-    fn = tool_call.get("function") or {}
-    args_raw = fn.get("arguments", "")
-    try:
-        args = json.loads(args_raw) if isinstance(args_raw, str) and args_raw else {}
-    except json.JSONDecodeError:
-        args = {"_raw": args_raw}
-    if not isinstance(args, dict):
-        args = {"_value": args}
-
-    part: Dict[str, Any] = {
-        "functionCall": {
-            "name": str(fn.get("name") or ""),
-            "args": args,
-        }
-    }
-    thought_signature = _tool_call_extra_signature(tool_call)
-    if thought_signature:
-        part["thoughtSignature"] = thought_signature
-    return part
-
-
-def _translate_tool_result_to_gemini(
-    message: Dict[str, Any],
-    tool_name_by_call_id: Optional[Dict[str, str]] = None,
-) -> Dict[str, Any]:
-    tool_name_by_call_id = tool_name_by_call_id or {}
-    tool_call_id = str(message.get("tool_call_id") or "")
-    name = str(
-        message.get("name")
-        or tool_name_by_call_id.get(tool_call_id)
-        or tool_call_id
-        or "tool"
-    )
-    content = _coerce_content_to_text(message.get("content"))
-    try:
-        parsed = json.loads(content) if content.strip().startswith(("{", "[")) else None
-    except json.JSONDecodeError:
-        parsed = None
-    response = parsed if isinstance(parsed, dict) else {"output": content}
-    return {
-        "functionResponse": {
-            "name": name,
-            "response": response,
-        }
-    }
-
-
-def _build_gemini_contents(messages: List[Dict[str, Any]]) -> tuple[List[Dict[str, Any]], Optional[Dict[str, Any]]]:
-    system_text_parts: List[str] = []
-    contents: List[Dict[str, Any]] = []
-    tool_name_by_call_id: Dict[str, str] = {}
-
-    for msg in messages:
-        if not isinstance(msg, dict):
-            continue
-        role = str(msg.get("role") or "user")
-
-        if role == "system":
-            system_text_parts.append(_coerce_content_to_text(msg.get("content")))
-            continue
-
-        if role in {"tool", "function"}:
-            contents.append(
-                {
-                    "role": "user",
-                    "parts": [
-                        _translate_tool_result_to_gemini(
-                            msg,
-                            tool_name_by_call_id=tool_name_by_call_id,
-                        )
-                    ],
-                }
-            )
-            continue
-
-        gemini_role = "model" if role == "assistant" else "user"
-        parts: List[Dict[str, Any]] = []
-
-        content_parts = _extract_multimodal_parts(msg.get("content"))
-        parts.extend(content_parts)
-
-        tool_calls = msg.get("tool_calls") or []
-        if isinstance(tool_calls, list):
-            for tool_call in tool_calls:
-                if isinstance(tool_call, dict):
-                    tool_call_id = str(tool_call.get("id") or tool_call.get("call_id") or "")
-                    tool_name = str(((tool_call.get("function") or {}).get("name") or ""))
-                    if tool_call_id and tool_name:
-                        tool_name_by_call_id[tool_call_id] = tool_name
-                    parts.append(_translate_tool_call_to_gemini(tool_call))
-
-        if parts:
-            contents.append({"role": gemini_role, "parts": parts})
-
-    system_instruction = None
-    joined_system = "\n".join(part for part in system_text_parts if part).strip()
-    if joined_system:
-        system_instruction = {"parts": [{"text": joined_system}]}
-    return contents, system_instruction
-
-
-def _translate_tools_to_gemini(tools: Any) -> List[Dict[str, Any]]:
-    if not isinstance(tools, list):
-        return []
-    declarations: List[Dict[str, Any]] = []
-    for tool in tools:
-        if not isinstance(tool, dict):
-            continue
-        fn = tool.get("function") or {}
-        if not isinstance(fn, dict):
-            continue
-        name = fn.get("name")
-        if not isinstance(name, str) or not name:
-            continue
-        decl: Dict[str, Any] = {"name": name}
-        description = fn.get("description")
-        if isinstance(description, str) and description:
-            decl["description"] = description
-        parameters = fn.get("parameters")
-        if isinstance(parameters, dict):
-            decl["parameters"] = sanitize_gemini_tool_parameters(parameters)
-        declarations.append(decl)
-    return [{"functionDeclarations": declarations}] if declarations else []
-
-
-def _translate_tool_choice_to_gemini(tool_choice: Any) -> Optional[Dict[str, Any]]:
-    if tool_choice is None:
-        return None
-    if isinstance(tool_choice, str):
-        if tool_choice == "auto":
-            return {"functionCallingConfig": {"mode": "AUTO"}}
-        if tool_choice == "required":
-            return {"functionCallingConfig": {"mode": "ANY"}}
-        if tool_choice == "none":
-            return {"functionCallingConfig": {"mode": "NONE"}}
-    if isinstance(tool_choice, dict):
-        fn = tool_choice.get("function") or {}
-        name = fn.get("name")
-        if isinstance(name, str) and name:
-            return {"functionCallingConfig": {"mode": "ANY", "allowedFunctionNames": [name]}}
-    return None
-
-
-def _normalize_thinking_config(config: Any) -> Optional[Dict[str, Any]]:
-    if not isinstance(config, dict) or not config:
-        return None
-    budget = config.get("thinkingBudget", config.get("thinking_budget"))
-    include = config.get("includeThoughts", config.get("include_thoughts"))
-    level = config.get("thinkingLevel", config.get("thinking_level"))
-    normalized: Dict[str, Any] = {}
-    if isinstance(budget, (int, float)):
-        normalized["thinkingBudget"] = int(budget)
-    if isinstance(include, bool):
-        normalized["includeThoughts"] = include
-    if isinstance(level, str) and level.strip():
-        normalized["thinkingLevel"] = level.strip().lower()
-    return normalized or None
-
-
-def build_gemini_request(
-    *,
-    messages: List[Dict[str, Any]],
-    tools: Any = None,
-    tool_choice: Any = None,
-    temperature: Optional[float] = None,
-    max_tokens: Optional[int] = None,
-    top_p: Optional[float] = None,
-    stop: Any = None,
-    thinking_config: Any = None,
-) -> Dict[str, Any]:
-    contents, system_instruction = _build_gemini_contents(messages)
-    request: Dict[str, Any] = {"contents": contents}
-    if system_instruction:
-        request["systemInstruction"] = system_instruction
-
-    gemini_tools = _translate_tools_to_gemini(tools)
-    if gemini_tools:
-        request["tools"] = gemini_tools
-
-    tool_config = _translate_tool_choice_to_gemini(tool_choice)
-    if tool_config:
-        request["toolConfig"] = tool_config
-
-    generation_config: Dict[str, Any] = {}
-    if temperature is not None:
-        generation_config["temperature"] = temperature
-    if max_tokens is not None:
-        generation_config["maxOutputTokens"] = max_tokens
-    if top_p is not None:
-        generation_config["topP"] = top_p
-    if stop:
-        generation_config["stopSequences"] = stop if isinstance(stop, list) else [str(stop)]
-    normalized_thinking = _normalize_thinking_config(thinking_config)
-    if normalized_thinking:
-        generation_config["thinkingConfig"] = normalized_thinking
-    if generation_config:
-        request["generationConfig"] = generation_config
-
-    return request
-
-
-def _map_gemini_finish_reason(reason: str) -> str:
-    mapping = {
-        "STOP": "stop",
-        "MAX_TOKENS": "length",
-        "SAFETY": "content_filter",
-        "RECITATION": "content_filter",
-        "OTHER": "stop",
-    }
-    return mapping.get(str(reason or "").upper(), "stop")
-
-
-def _tool_call_extra_from_part(part: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    sig = part.get("thoughtSignature")
-    if isinstance(sig, str) and sig:
-        return {"google": {"thought_signature": sig}}
-    return None
-
-
-def _empty_response(model: str) -> SimpleNamespace:
-    message = SimpleNamespace(
-        role="assistant",
-        content="",
-        tool_calls=None,
-        reasoning=None,
-        reasoning_content=None,
-        reasoning_details=None,
-    )
-    choice = SimpleNamespace(index=0, message=message, finish_reason="stop")
-    usage = SimpleNamespace(
-        prompt_tokens=0,
-        completion_tokens=0,
-        total_tokens=0,
-        prompt_tokens_details=SimpleNamespace(cached_tokens=0),
-    )
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-def translate_gemini_response(resp: Dict[str, Any], model: str) -> SimpleNamespace:
-    candidates = resp.get("candidates") or []
-    if not isinstance(candidates, list) or not candidates:
-        return _empty_response(model)
-
-    cand = candidates[0] if isinstance(candidates[0], dict) else {}
-    content_obj = cand.get("content") if isinstance(cand, dict) else {}
-    parts = content_obj.get("parts") if isinstance(content_obj, dict) else []
-
-    text_pieces: List[str] = []
-    reasoning_pieces: List[str] = []
-    tool_calls: List[SimpleNamespace] = []
-
-    for index, part in enumerate(parts or []):
-        if not isinstance(part, dict):
-            continue
-        if part.get("thought") is True and isinstance(part.get("text"), str):
-            reasoning_pieces.append(part["text"])
-            continue
-        if isinstance(part.get("text"), str):
-            text_pieces.append(part["text"])
-            continue
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            tool_call = SimpleNamespace(
-                id=f"call_{uuid.uuid4().hex[:12]}",
-                type="function",
-                index=index,
-                function=SimpleNamespace(name=str(fc["name"]), arguments=args_str),
-            )
-            extra_content = _tool_call_extra_from_part(part)
-            if extra_content:
-                tool_call.extra_content = extra_content
-            tool_calls.append(tool_call)
-
-    finish_reason = "tool_calls" if tool_calls else _map_gemini_finish_reason(str(cand.get("finishReason") or ""))
-    usage_meta = resp.get("usageMetadata") or {}
-    usage = SimpleNamespace(
-        prompt_tokens=int(usage_meta.get("promptTokenCount") or 0),
-        completion_tokens=int(usage_meta.get("candidatesTokenCount") or 0),
-        total_tokens=int(usage_meta.get("totalTokenCount") or 0),
-        prompt_tokens_details=SimpleNamespace(
-            cached_tokens=int(usage_meta.get("cachedContentTokenCount") or 0),
-        ),
-    )
-    reasoning = "".join(reasoning_pieces) or None
-    message = SimpleNamespace(
-        role="assistant",
-        content="".join(text_pieces) if text_pieces else None,
-        tool_calls=tool_calls or None,
-        reasoning=reasoning,
-        reasoning_content=reasoning,
-        reasoning_details=None,
-    )
-    choice = SimpleNamespace(index=0, message=message, finish_reason=finish_reason)
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-class _GeminiStreamChunk(SimpleNamespace):
-    pass
-
-
-def _make_stream_chunk(
-    *,
-    model: str,
-    content: str = "",
-    tool_call_delta: Optional[Dict[str, Any]] = None,
-    finish_reason: Optional[str] = None,
-    reasoning: str = "",
-) -> _GeminiStreamChunk:
-    delta_kwargs: Dict[str, Any] = {
-        "role": "assistant",
-        "content": None,
-        "tool_calls": None,
-        "reasoning": None,
-        "reasoning_content": None,
-    }
-    if content:
-        delta_kwargs["content"] = content
-    if tool_call_delta is not None:
-        tool_delta = SimpleNamespace(
-            index=tool_call_delta.get("index", 0),
-            id=tool_call_delta.get("id") or f"call_{uuid.uuid4().hex[:12]}",
-            type="function",
-            function=SimpleNamespace(
-                name=tool_call_delta.get("name") or "",
-                arguments=tool_call_delta.get("arguments") or "",
-            ),
-        )
-        extra_content = tool_call_delta.get("extra_content")
-        if isinstance(extra_content, dict):
-            tool_delta.extra_content = extra_content
-        delta_kwargs["tool_calls"] = [tool_delta]
-    if reasoning:
-        delta_kwargs["reasoning"] = reasoning
-        delta_kwargs["reasoning_content"] = reasoning
-    delta = SimpleNamespace(**delta_kwargs)
-    choice = SimpleNamespace(index=0, delta=delta, finish_reason=finish_reason)
-    return _GeminiStreamChunk(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion.chunk",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=None,
-    )
-
-
-def _iter_sse_events(response: httpx.Response) -> Iterator[Dict[str, Any]]:
-    buffer = ""
-    for chunk in response.iter_text():
-        if not chunk:
-            continue
-        buffer += chunk
-        while "\n" in buffer:
-            line, buffer = buffer.split("\n", 1)
-            line = line.rstrip("\r")
-            if not line:
-                continue
-            if not line.startswith("data: "):
-                continue
-            data = line[6:]
-            if data == "[DONE]":
-                return
-            try:
-                payload = json.loads(data)
-            except json.JSONDecodeError:
-                logger.debug("Non-JSON Gemini SSE line: %s", data[:200])
-                continue
-            if isinstance(payload, dict):
-                yield payload
-
-
-def translate_stream_event(event: Dict[str, Any], model: str, tool_call_indices: Dict[str, Dict[str, Any]]) -> List[_GeminiStreamChunk]:
-    candidates = event.get("candidates") or []
-    if not candidates:
-        return []
-    cand = candidates[0] if isinstance(candidates[0], dict) else {}
-    parts = ((cand.get("content") or {}).get("parts") or []) if isinstance(cand, dict) else []
-    chunks: List[_GeminiStreamChunk] = []
-
-    for part_index, part in enumerate(parts):
-        if not isinstance(part, dict):
-            continue
-        if part.get("thought") is True and isinstance(part.get("text"), str):
-            chunks.append(_make_stream_chunk(model=model, reasoning=part["text"]))
-            continue
-        if isinstance(part.get("text"), str) and part["text"]:
-            chunks.append(_make_stream_chunk(model=model, content=part["text"]))
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            name = str(fc["name"])
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False, sort_keys=True)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            thought_signature = part.get("thoughtSignature") if isinstance(part.get("thoughtSignature"), str) else ""
-            call_key = json.dumps(
-                {
-                    "part_index": part_index,
-                    "name": name,
-                    "thought_signature": thought_signature,
-                },
-                sort_keys=True,
-            )
-            slot = tool_call_indices.get(call_key)
-            if slot is None:
-                slot = {
-                    "index": len(tool_call_indices),
-                    "id": f"call_{uuid.uuid4().hex[:12]}",
-                    "last_arguments": "",
-                }
-                tool_call_indices[call_key] = slot
-            emitted_arguments = args_str
-            last_arguments = str(slot.get("last_arguments") or "")
-            if last_arguments:
-                if args_str == last_arguments:
-                    emitted_arguments = ""
-                elif args_str.startswith(last_arguments):
-                    emitted_arguments = args_str[len(last_arguments):]
-            slot["last_arguments"] = args_str
-            chunks.append(
-                _make_stream_chunk(
-                    model=model,
-                    tool_call_delta={
-                        "index": slot["index"],
-                        "id": slot["id"],
-                        "name": name,
-                        "arguments": emitted_arguments,
-                        "extra_content": _tool_call_extra_from_part(part),
-                    },
-                )
-            )
-
-    finish_reason_raw = str(cand.get("finishReason") or "")
-    if finish_reason_raw:
-        mapped = "tool_calls" if tool_call_indices else _map_gemini_finish_reason(finish_reason_raw)
-        chunks.append(_make_stream_chunk(model=model, finish_reason=mapped))
-    return chunks
-
-
-def gemini_http_error(response: httpx.Response) -> GeminiAPIError:
-    status = response.status_code
-    body_text = ""
-    body_json: Dict[str, Any] = {}
-    try:
-        body_text = response.text
-    except Exception:
-        body_text = ""
-    if body_text:
-        try:
-            parsed = json.loads(body_text)
-            if isinstance(parsed, dict):
-                body_json = parsed
-        except (ValueError, TypeError):
-            body_json = {}
-
-    err_obj = body_json.get("error") if isinstance(body_json, dict) else None
-    if not isinstance(err_obj, dict):
-        err_obj = {}
-    err_status = str(err_obj.get("status") or "").strip()
-    err_message = str(err_obj.get("message") or "").strip()
-    details_list = err_obj.get("details") if isinstance(err_obj.get("details"), list) else []
-
-    reason = ""
-    retry_after: Optional[float] = None
-    metadata: Dict[str, Any] = {}
-    for detail in details_list:
-        if not isinstance(detail, dict):
-            continue
-        type_url = str(detail.get("@type") or "")
-        if not reason and type_url.endswith("/google.rpc.ErrorInfo"):
-            reason_value = detail.get("reason")
-            if isinstance(reason_value, str):
-                reason = reason_value
-            md = detail.get("metadata")
-            if isinstance(md, dict):
-                metadata = md
-    header_retry = response.headers.get("Retry-After") or response.headers.get("retry-after")
-    if header_retry:
-        try:
-            retry_after = float(header_retry)
-        except (TypeError, ValueError):
-            retry_after = None
-
-    code = f"gemini_http_{status}"
-    if status == 401:
-        code = "gemini_unauthorized"
-    elif status == 429:
-        code = "gemini_rate_limited"
-    elif status == 404:
-        code = "gemini_model_not_found"
-
-    if err_message:
-        message = f"Gemini HTTP {status} ({err_status or 'error'}): {err_message}"
-    else:
-        message = f"Gemini returned HTTP {status}: {body_text[:500]}"
-
-    return GeminiAPIError(
-        message,
-        code=code,
-        status_code=status,
-        response=response,
-        retry_after=retry_after,
-        details={
-            "status": err_status,
-            "reason": reason,
-            "metadata": metadata,
-            "message": err_message,
-        },
-    )
-
-
-class _GeminiChatCompletions:
-    def __init__(self, client: "GeminiNativeClient"):
-        self._client = client
-
-    def create(self, **kwargs: Any) -> Any:
-        return self._client._create_chat_completion(**kwargs)
-
-
-class _AsyncGeminiChatCompletions:
-    def __init__(self, client: "AsyncGeminiNativeClient"):
-        self._client = client
-
-    async def create(self, **kwargs: Any) -> Any:
-        return await self._client._create_chat_completion(**kwargs)
-
-
-class _GeminiChatNamespace:
-    def __init__(self, client: "GeminiNativeClient"):
-        self.completions = _GeminiChatCompletions(client)
-
-
-class _AsyncGeminiChatNamespace:
-    def __init__(self, client: "AsyncGeminiNativeClient"):
-        self.completions = _AsyncGeminiChatCompletions(client)
-
-
-class GeminiNativeClient:
-    """Minimal OpenAI-SDK-compatible facade over Gemini's native REST API."""
-
-    def __init__(
-        self,
-        *,
-        api_key: str,
-        base_url: Optional[str] = None,
-        default_headers: Optional[Dict[str, str]] = None,
-        timeout: Any = None,
-        http_client: Optional[httpx.Client] = None,
-        **_: Any,
-    ) -> None:
-        self.api_key = api_key
-        normalized_base = (base_url or DEFAULT_GEMINI_BASE_URL).rstrip("/")
-        if normalized_base.endswith("/openai"):
-            normalized_base = normalized_base[: -len("/openai")]
-        self.base_url = normalized_base
-        self._default_headers = dict(default_headers or {})
-        self.chat = _GeminiChatNamespace(self)
-        self.is_closed = False
-        self._http = http_client or httpx.Client(
-            timeout=timeout or httpx.Timeout(connect=15.0, read=600.0, write=30.0, pool=30.0)
-        )
-
-    def close(self) -> None:
-        self.is_closed = True
-        try:
-            self._http.close()
-        except Exception:
-            pass
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        self.close()
-
-    def _headers(self) -> Dict[str, str]:
-        headers = {
-            "Content-Type": "application/json",
-            "Accept": "application/json",
-            "x-goog-api-key": self.api_key,
-            "User-Agent": "hermes-agent (gemini-native)",
-        }
-        headers.update(self._default_headers)
-        return headers
-
-    @staticmethod
-    def _advance_stream_iterator(iterator: Iterator[_GeminiStreamChunk]) -> tuple[bool, Optional[_GeminiStreamChunk]]:
-        try:
-            return False, next(iterator)
-        except StopIteration:
-            return True, None
-
-    def _create_chat_completion(
-        self,
-        *,
-        model: str = "gemini-2.5-flash",
-        messages: Optional[List[Dict[str, Any]]] = None,
-        stream: bool = False,
-        tools: Any = None,
-        tool_choice: Any = None,
-        temperature: Optional[float] = None,
-        max_tokens: Optional[int] = None,
-        top_p: Optional[float] = None,
-        stop: Any = None,
-        extra_body: Optional[Dict[str, Any]] = None,
-        timeout: Any = None,
-        **_: Any,
-    ) -> Any:
-        thinking_config = None
-        if isinstance(extra_body, dict):
-            thinking_config = extra_body.get("thinking_config") or extra_body.get("thinkingConfig")
-
-        request = build_gemini_request(
-            messages=messages or [],
-            tools=tools,
-            tool_choice=tool_choice,
-            temperature=temperature,
-            max_tokens=max_tokens,
-            top_p=top_p,
-            stop=stop,
-            thinking_config=thinking_config,
-        )
-
-        if stream:
-            return self._stream_completion(model=model, request=request, timeout=timeout)
-
-        url = f"{self.base_url}/models/{model}:generateContent"
-        response = self._http.post(url, json=request, headers=self._headers(), timeout=timeout)
-        if response.status_code != 200:
-            raise gemini_http_error(response)
-        try:
-            payload = response.json()
-        except ValueError as exc:
-            raise GeminiAPIError(
-                f"Invalid JSON from Gemini native API: {exc}",
-                code="gemini_invalid_json",
-                status_code=response.status_code,
-                response=response,
-            ) from exc
-        return translate_gemini_response(payload, model=model)
-
-    def _stream_completion(self, *, model: str, request: Dict[str, Any], timeout: Any = None) -> Iterator[_GeminiStreamChunk]:
-        url = f"{self.base_url}/models/{model}:streamGenerateContent?alt=sse"
-        stream_headers = dict(self._headers())
-        stream_headers["Accept"] = "text/event-stream"
-
-        def _generator() -> Iterator[_GeminiStreamChunk]:
-            try:
-                with self._http.stream("POST", url, json=request, headers=stream_headers, timeout=timeout) as response:
-                    if response.status_code != 200:
-                        response.read()
-                        raise gemini_http_error(response)
-                    tool_call_indices: Dict[str, Dict[str, Any]] = {}
-                    for event in _iter_sse_events(response):
-                        for chunk in translate_stream_event(event, model, tool_call_indices):
-                            yield chunk
-            except httpx.HTTPError as exc:
-                raise GeminiAPIError(
-                    f"Gemini streaming request failed: {exc}",
-                    code="gemini_stream_error",
-                ) from exc
-
-        return _generator()
-
-
-class AsyncGeminiNativeClient:
-    """Async wrapper used by auxiliary_client for native Gemini calls."""
-
-    def __init__(self, sync_client: GeminiNativeClient):
-        self._sync = sync_client
-        self.api_key = sync_client.api_key
-        self.base_url = sync_client.base_url
-        self.chat = _AsyncGeminiChatNamespace(self)
-
-    async def _create_chat_completion(self, **kwargs: Any) -> Any:
-        stream = bool(kwargs.get("stream"))
-        result = await asyncio.to_thread(self._sync.chat.completions.create, **kwargs)
-        if not stream:
-            return result
-
-        async def _async_stream() -> Any:
-            while True:
-                done, chunk = await asyncio.to_thread(self._sync._advance_stream_iterator, result)
-                if done:
-                    break
-                yield chunk
-
-        return _async_stream()
-
-    async def close(self) -> None:
-        await asyncio.to_thread(self._sync.close)

agent/gemini_schema.py

@@ -1,85 +0,0 @@
-"""Helpers for translating OpenAI-style tool schemas to Gemini's schema subset."""
-
-from __future__ import annotations
-
-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
-# outside that subset before sending Hermes tool schemas to Google.
-_GEMINI_SCHEMA_ALLOWED_KEYS = {
-    "type",
-    "format",
-    "title",
-    "description",
-    "nullable",
-    "enum",
-    "maxItems",
-    "minItems",
-    "properties",
-    "required",
-    "minProperties",
-    "maxProperties",
-    "minLength",
-    "maxLength",
-    "pattern",
-    "example",
-    "anyOf",
-    "propertyOrdering",
-    "default",
-    "items",
-    "minimum",
-    "maximum",
-}
-
-
-def sanitize_gemini_schema(schema: Any) -> Dict[str, Any]:
-    """Return a Gemini-compatible copy of a tool parameter schema.
-
-    Hermes tool schemas are OpenAI-flavored JSON Schema and may contain keys
-    such as ``$schema`` or ``additionalProperties`` that Google's Gemini
-    ``Schema`` object rejects.  This helper preserves the documented Gemini
-    subset and recursively sanitizes nested ``properties`` / ``items`` /
-    ``anyOf`` definitions.
-    """
-
-    if not isinstance(schema, dict):
-        return {}
-
-    cleaned: Dict[str, Any] = {}
-    for key, value in schema.items():
-        if key not in _GEMINI_SCHEMA_ALLOWED_KEYS:
-            continue
-        if key == "properties":
-            if not isinstance(value, dict):
-                continue
-            props: Dict[str, Any] = {}
-            for prop_name, prop_schema in value.items():
-                if not isinstance(prop_name, str):
-                    continue
-                props[prop_name] = sanitize_gemini_schema(prop_schema)
-            cleaned[key] = props
-            continue
-        if key == "items":
-            cleaned[key] = sanitize_gemini_schema(value)
-            continue
-        if key == "anyOf":
-            if not isinstance(value, list):
-                continue
-            cleaned[key] = [
-                sanitize_gemini_schema(item)
-                for item in value
-                if isinstance(item, dict)
-            ]
-            continue
-        cleaned[key] = value
-    return cleaned
-
-
-def sanitize_gemini_tool_parameters(parameters: Any) -> Dict[str, Any]:
-    """Normalize tool parameters to a valid Gemini object schema."""
-
-    cleaned = sanitize_gemini_schema(parameters)
-    if not cleaned:
-        return {"type": "object", "properties": {}}
-    return cleaned

agent/google_code_assist.py

@@ -1,453 +0,0 @@
-"""Google Code Assist API client — project discovery, onboarding, quota.
-
-The Code Assist API powers Google's official gemini-cli. It sits at
-``cloudcode-pa.googleapis.com`` and provides:
-
-- Free tier access (generous daily quota) for personal Google accounts
-- Paid tier access via GCP projects with billing / Workspace / Standard / Enterprise
-
-This module handles the control-plane dance needed before inference:
-
-1. ``load_code_assist()`` — probe the user's account to learn what tier they're on
-   and whether a ``cloudaicompanionProject`` is already assigned.
-2. ``onboard_user()`` — if the user hasn't been onboarded yet (new account, fresh
-   free tier, etc.), call this with the chosen tier + project id. Supports LRO
-   polling for slow provisioning.
-3. ``retrieve_user_quota()`` — fetch the ``buckets[]`` array showing remaining
-   quota per model, used by the ``/gquota`` slash command.
-
-VPC-SC handling: enterprise accounts under a VPC Service Controls perimeter
-will get ``SECURITY_POLICY_VIOLATED`` on ``load_code_assist``. We catch this
-and force the account to ``standard-tier`` so the call chain still succeeds.
-
-Derived from opencode-gemini-auth (MIT) and clawdbot/extensions/google. The
-request/response shapes are specific to Google's internal Code Assist API,
-documented nowhere public — we copy them from the reference implementations.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import time
-import urllib.error
-import urllib.parse
-import urllib.request
-import uuid
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-logger = logging.getLogger(__name__)
-
-
-# =============================================================================
-# Constants
-# =============================================================================
-
-CODE_ASSIST_ENDPOINT = "https://cloudcode-pa.googleapis.com"
-
-# Fallback endpoints tried when prod returns an error during project discovery
-FALLBACK_ENDPOINTS = [
-    "https://daily-cloudcode-pa.sandbox.googleapis.com",
-    "https://autopush-cloudcode-pa.sandbox.googleapis.com",
-]
-
-# Tier identifiers that Google's API uses
-FREE_TIER_ID = "free-tier"
-LEGACY_TIER_ID = "legacy-tier"
-STANDARD_TIER_ID = "standard-tier"
-
-# Default HTTP headers matching gemini-cli's fingerprint.
-# Google may reject unrecognized User-Agents on these internal endpoints.
-_GEMINI_CLI_USER_AGENT = "google-api-nodejs-client/9.15.1 (gzip)"
-_X_GOOG_API_CLIENT = "gl-node/24.0.0"
-_DEFAULT_REQUEST_TIMEOUT = 30.0
-_ONBOARDING_POLL_ATTEMPTS = 12
-_ONBOARDING_POLL_INTERVAL_SECONDS = 5.0
-
-
-class CodeAssistError(RuntimeError):
-    """Exception raised by the Code Assist (``cloudcode-pa``) integration.
-
-    Carries HTTP status / response / retry-after metadata so the agent's
-    ``error_classifier._extract_status_code`` and the main loop's Retry-After
-    handling (which walks ``error.response.headers``) pick up the right
-    signals.  Without these, 429s from the OAuth path look like opaque
-    ``RuntimeError`` and skip the rate-limit path.
-    """
-
-    def __init__(
-        self,
-        message: str,
-        *,
-        code: str = "code_assist_error",
-        status_code: Optional[int] = None,
-        response: Any = None,
-        retry_after: Optional[float] = None,
-        details: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        super().__init__(message)
-        self.code = code
-        # ``status_code`` is picked up by ``agent.error_classifier._extract_status_code``
-        # so a 429 from Code Assist classifies as FailoverReason.rate_limit and
-        # triggers the main loop's fallback_providers chain the same way SDK
-        # errors do.
-        self.status_code = status_code
-        # ``response`` is the underlying ``httpx.Response`` (or a shim with a
-        # ``.headers`` mapping and ``.json()`` method).  The main loop reads
-        # ``error.response.headers["Retry-After"]`` to honor Google's retry
-        # hints when the backend throttles us.
-        self.response = response
-        # Parsed ``Retry-After`` seconds (kept separately for convenience —
-        # Google returns retry hints in both the header and the error body's
-        # ``google.rpc.RetryInfo`` details, and we pick whichever we found).
-        self.retry_after = retry_after
-        # Parsed structured error details from the Google error envelope
-        # (e.g. ``{"reason": "MODEL_CAPACITY_EXHAUSTED", "status": "RESOURCE_EXHAUSTED"}``).
-        # Useful for logging and for tests that want to assert on specifics.
-        self.details = details or {}
-
-
-class ProjectIdRequiredError(CodeAssistError):
-    def __init__(self, message: str = "GCP project id required for this tier") -> None:
-        super().__init__(message, code="code_assist_project_id_required")
-
-
-# =============================================================================
-# HTTP primitive (auth via Bearer token passed per-call)
-# =============================================================================
-
-def _build_headers(access_token: str, *, user_agent_model: str = "") -> Dict[str, str]:
-    ua = _GEMINI_CLI_USER_AGENT
-    if user_agent_model:
-        ua = f"{ua} model/{user_agent_model}"
-    return {
-        "Content-Type": "application/json",
-        "Accept": "application/json",
-        "Authorization": f"Bearer {access_token}",
-        "User-Agent": ua,
-        "X-Goog-Api-Client": _X_GOOG_API_CLIENT,
-        "x-activity-request-id": str(uuid.uuid4()),
-    }
-
-
-def _client_metadata() -> Dict[str, str]:
-    """Match Google's gemini-cli exactly — unrecognized metadata may be rejected."""
-    return {
-        "ideType": "IDE_UNSPECIFIED",
-        "platform": "PLATFORM_UNSPECIFIED",
-        "pluginType": "GEMINI",
-    }
-
-
-def _post_json(
-    url: str,
-    body: Dict[str, Any],
-    access_token: str,
-    *,
-    timeout: float = _DEFAULT_REQUEST_TIMEOUT,
-    user_agent_model: str = "",
-) -> Dict[str, Any]:
-    data = json.dumps(body).encode("utf-8")
-    request = urllib.request.Request(
-        url, data=data, method="POST",
-        headers=_build_headers(access_token, user_agent_model=user_agent_model),
-    )
-    try:
-        with urllib.request.urlopen(request, timeout=timeout) as response:
-            raw = response.read().decode("utf-8", errors="replace")
-            return json.loads(raw) if raw else {}
-    except urllib.error.HTTPError as exc:
-        detail = ""
-        try:
-            detail = exc.read().decode("utf-8", errors="replace")
-        except Exception:
-            pass
-        # Special case: VPC-SC violation should be distinguishable
-        if _is_vpc_sc_violation(detail):
-            raise CodeAssistError(
-                f"VPC-SC policy violation: {detail}",
-                code="code_assist_vpc_sc",
-            ) from exc
-        raise CodeAssistError(
-            f"Code Assist HTTP {exc.code}: {detail or exc.reason}",
-            code=f"code_assist_http_{exc.code}",
-        ) from exc
-    except urllib.error.URLError as exc:
-        raise CodeAssistError(
-            f"Code Assist request failed: {exc}",
-            code="code_assist_network_error",
-        ) from exc
-
-
-def _is_vpc_sc_violation(body: str) -> bool:
-    """Detect a VPC Service Controls violation from a response body."""
-    if not body:
-        return False
-    try:
-        parsed = json.loads(body)
-    except (json.JSONDecodeError, ValueError):
-        return "SECURITY_POLICY_VIOLATED" in body
-    # Walk the nested error structure Google uses
-    error = parsed.get("error") if isinstance(parsed, dict) else None
-    if not isinstance(error, dict):
-        return False
-    details = error.get("details") or []
-    if isinstance(details, list):
-        for item in details:
-            if isinstance(item, dict):
-                reason = item.get("reason") or ""
-                if reason == "SECURITY_POLICY_VIOLATED":
-                    return True
-    msg = str(error.get("message", ""))
-    return "SECURITY_POLICY_VIOLATED" in msg
-
-
-# =============================================================================
-# load_code_assist — discovers current tier + assigned project
-# =============================================================================
-
-@dataclass
-class CodeAssistProjectInfo:
-    """Result from ``load_code_assist``."""
-    current_tier_id: str = ""
-    cloudaicompanion_project: str = ""   # Google-managed project (free tier)
-    allowed_tiers: List[str] = field(default_factory=list)
-    raw: Dict[str, Any] = field(default_factory=dict)
-
-
-def load_code_assist(
-    access_token: str,
-    *,
-    project_id: str = "",
-    user_agent_model: str = "",
-) -> CodeAssistProjectInfo:
-    """Call ``POST /v1internal:loadCodeAssist`` with prod → sandbox fallback.
-
-    Returns whatever tier + project info Google reports. On VPC-SC violations,
-    returns a synthetic ``standard-tier`` result so the chain can continue.
-    """
-    body: Dict[str, Any] = {
-        "metadata": {
-            "duetProject": project_id,
-            **_client_metadata(),
-        },
-    }
-    if project_id:
-        body["cloudaicompanionProject"] = project_id
-
-    endpoints = [CODE_ASSIST_ENDPOINT] + FALLBACK_ENDPOINTS
-    last_err: Optional[Exception] = None
-    for endpoint in endpoints:
-        url = f"{endpoint}/v1internal:loadCodeAssist"
-        try:
-            resp = _post_json(url, body, access_token, user_agent_model=user_agent_model)
-            return _parse_load_response(resp)
-        except CodeAssistError as exc:
-            if exc.code == "code_assist_vpc_sc":
-                logger.info("VPC-SC violation on %s — defaulting to standard-tier", endpoint)
-                return CodeAssistProjectInfo(
-                    current_tier_id=STANDARD_TIER_ID,
-                    cloudaicompanion_project=project_id,
-                )
-            last_err = exc
-            logger.warning("loadCodeAssist failed on %s: %s", endpoint, exc)
-            continue
-    if last_err:
-        raise last_err
-    return CodeAssistProjectInfo()
-
-
-def _parse_load_response(resp: Dict[str, Any]) -> CodeAssistProjectInfo:
-    current_tier = resp.get("currentTier") or {}
-    tier_id = str(current_tier.get("id") or "") if isinstance(current_tier, dict) else ""
-    project = str(resp.get("cloudaicompanionProject") or "")
-    allowed = resp.get("allowedTiers") or []
-    allowed_ids: List[str] = []
-    if isinstance(allowed, list):
-        for t in allowed:
-            if isinstance(t, dict):
-                tid = str(t.get("id") or "")
-                if tid:
-                    allowed_ids.append(tid)
-    return CodeAssistProjectInfo(
-        current_tier_id=tier_id,
-        cloudaicompanion_project=project,
-        allowed_tiers=allowed_ids,
-        raw=resp,
-    )
-
-
-# =============================================================================
-# onboard_user — provisions a new user on a tier (with LRO polling)
-# =============================================================================
-
-def onboard_user(
-    access_token: str,
-    *,
-    tier_id: str,
-    project_id: str = "",
-    user_agent_model: str = "",
-) -> Dict[str, Any]:
-    """Call ``POST /v1internal:onboardUser`` to provision the user.
-
-    For paid tiers, ``project_id`` is REQUIRED (raises ProjectIdRequiredError).
-    For free tiers, ``project_id`` is optional — Google will assign one.
-
-    Returns the final operation response. Polls ``/v1internal/<name>`` for up
-    to ``_ONBOARDING_POLL_ATTEMPTS`` × ``_ONBOARDING_POLL_INTERVAL_SECONDS``
-    (default: 12 × 5s = 1 min).
-    """
-    if tier_id != FREE_TIER_ID and tier_id != LEGACY_TIER_ID and not project_id:
-        raise ProjectIdRequiredError(
-            f"Tier {tier_id!r} requires a GCP project id. "
-            "Set HERMES_GEMINI_PROJECT_ID or GOOGLE_CLOUD_PROJECT."
-        )
-
-    body: Dict[str, Any] = {
-        "tierId": tier_id,
-        "metadata": _client_metadata(),
-    }
-    if project_id:
-        body["cloudaicompanionProject"] = project_id
-
-    endpoint = CODE_ASSIST_ENDPOINT
-    url = f"{endpoint}/v1internal:onboardUser"
-    resp = _post_json(url, body, access_token, user_agent_model=user_agent_model)
-
-    # Poll if LRO (long-running operation)
-    if not resp.get("done"):
-        op_name = resp.get("name", "")
-        if not op_name:
-            return resp
-        for attempt in range(_ONBOARDING_POLL_ATTEMPTS):
-            time.sleep(_ONBOARDING_POLL_INTERVAL_SECONDS)
-            poll_url = f"{endpoint}/v1internal/{op_name}"
-            try:
-                poll_resp = _post_json(poll_url, {}, access_token, user_agent_model=user_agent_model)
-            except CodeAssistError as exc:
-                logger.warning("Onboarding poll attempt %d failed: %s", attempt + 1, exc)
-                continue
-            if poll_resp.get("done"):
-                return poll_resp
-        logger.warning("Onboarding did not complete within %d attempts", _ONBOARDING_POLL_ATTEMPTS)
-    return resp
-
-
-# =============================================================================
-# retrieve_user_quota — for /gquota
-# =============================================================================
-
-@dataclass
-class QuotaBucket:
-    model_id: str
-    token_type: str = ""
-    remaining_fraction: float = 0.0
-    reset_time_iso: str = ""
-    raw: Dict[str, Any] = field(default_factory=dict)
-
-
-def retrieve_user_quota(
-    access_token: str,
-    *,
-    project_id: str = "",
-    user_agent_model: str = "",
-) -> List[QuotaBucket]:
-    """Call ``POST /v1internal:retrieveUserQuota`` and parse ``buckets[]``."""
-    body: Dict[str, Any] = {}
-    if project_id:
-        body["project"] = project_id
-    url = f"{CODE_ASSIST_ENDPOINT}/v1internal:retrieveUserQuota"
-    resp = _post_json(url, body, access_token, user_agent_model=user_agent_model)
-    raw_buckets = resp.get("buckets") or []
-    buckets: List[QuotaBucket] = []
-    if not isinstance(raw_buckets, list):
-        return buckets
-    for b in raw_buckets:
-        if not isinstance(b, dict):
-            continue
-        buckets.append(QuotaBucket(
-            model_id=str(b.get("modelId") or ""),
-            token_type=str(b.get("tokenType") or ""),
-            remaining_fraction=float(b.get("remainingFraction") or 0.0),
-            reset_time_iso=str(b.get("resetTime") or ""),
-            raw=b,
-        ))
-    return buckets
-
-
-# =============================================================================
-# Project context resolution
-# =============================================================================
-
-@dataclass
-class ProjectContext:
-    """Resolved state for a given OAuth session."""
-    project_id: str = ""           # effective project id sent on requests
-    managed_project_id: str = ""   # Google-assigned project (free tier)
-    tier_id: str = ""
-    source: str = ""               # "env", "config", "discovered", "onboarded"
-
-
-def resolve_project_context(
-    access_token: str,
-    *,
-    configured_project_id: str = "",
-    env_project_id: str = "",
-    user_agent_model: str = "",
-) -> ProjectContext:
-    """Figure out what project id + tier to use for requests.
-
-    Priority:
-      1. If configured_project_id or env_project_id is set, use that directly
-         and short-circuit (no discovery needed).
-      2. Otherwise call loadCodeAssist to see what Google says.
-      3. If no tier assigned yet, onboard the user (free tier default).
-    """
-    # Short-circuit: caller provided a project id
-    if configured_project_id:
-        return ProjectContext(
-            project_id=configured_project_id,
-            tier_id=STANDARD_TIER_ID,  # assume paid since they specified one
-            source="config",
-        )
-    if env_project_id:
-        return ProjectContext(
-            project_id=env_project_id,
-            tier_id=STANDARD_TIER_ID,
-            source="env",
-        )
-
-    # Discover via loadCodeAssist
-    info = load_code_assist(access_token, user_agent_model=user_agent_model)
-
-    effective_project = info.cloudaicompanion_project
-    tier = info.current_tier_id
-
-    if not tier:
-        # User hasn't been onboarded — provision them on free tier
-        onboard_resp = onboard_user(
-            access_token,
-            tier_id=FREE_TIER_ID,
-            project_id="",
-            user_agent_model=user_agent_model,
-        )
-        # Re-parse from the onboard response
-        response_body = onboard_resp.get("response") or {}
-        if isinstance(response_body, dict):
-            effective_project = (
-                effective_project
-                or str(response_body.get("cloudaicompanionProject") or "")
-            )
-        tier = FREE_TIER_ID
-        source = "onboarded"
-    else:
-        source = "discovered"
-
-    return ProjectContext(
-        project_id=effective_project,
-        managed_project_id=effective_project if tier == FREE_TIER_ID else "",
-        tier_id=tier,
-        source=source,
-    )

agent/insights.py

@@ -27,6 +27,7 @@ from agent.usage_pricing import (
     DEFAULT_PRICING,
     estimate_usage_cost,
     format_duration_compact,
+    get_pricing,
     has_known_pricing,
 )
 
@@ -124,7 +125,6 @@ class InsightsEngine:
         # Gather raw data
         sessions = self._get_sessions(cutoff, source)
         tool_usage = self._get_tool_usage(cutoff, source)
-        skill_usage = self._get_skill_usage(cutoff, source)
         message_stats = self._get_message_stats(cutoff, source)
 
         if not sessions:
@@ -136,15 +136,6 @@ class InsightsEngine:
                 "models": [],
                 "platforms": [],
                 "tools": [],
-                "skills": {
-                    "summary": {
-                        "total_skill_loads": 0,
-                        "total_skill_edits": 0,
-                        "total_skill_actions": 0,
-                        "distinct_skills_used": 0,
-                    },
-                    "top_skills": [],
-                },
                 "activity": {},
                 "top_sessions": [],
             }
@@ -154,7 +145,6 @@ class InsightsEngine:
         models = self._compute_model_breakdown(sessions)
         platforms = self._compute_platform_breakdown(sessions)
         tools = self._compute_tool_breakdown(tool_usage)
-        skills = self._compute_skill_breakdown(skill_usage)
         activity = self._compute_activity_patterns(sessions)
         top_sessions = self._compute_top_sessions(sessions)
 
@@ -167,7 +157,6 @@ class InsightsEngine:
             "models": models,
             "platforms": platforms,
             "tools": tools,
-            "skills": skills,
             "activity": activity,
             "top_sessions": top_sessions,
         }
@@ -296,82 +285,6 @@ class InsightsEngine:
             for name, count in tool_counts.most_common()
         ]
 
-    def _get_skill_usage(self, cutoff: float, source: str = None) -> List[Dict]:
-        """Extract per-skill usage from assistant tool calls."""
-        skill_counts: Dict[str, Dict[str, Any]] = {}
-
-        if source:
-            cursor = self._conn.execute(
-                """SELECT m.tool_calls, m.timestamp
-                   FROM messages m
-                   JOIN sessions s ON s.id = m.session_id
-                   WHERE s.started_at >= ? AND s.source = ?
-                     AND m.role = 'assistant' AND m.tool_calls IS NOT NULL""",
-                (cutoff, source),
-            )
-        else:
-            cursor = self._conn.execute(
-                """SELECT m.tool_calls, m.timestamp
-                   FROM messages m
-                   JOIN sessions s ON s.id = m.session_id
-                   WHERE s.started_at >= ?
-                     AND m.role = 'assistant' AND m.tool_calls IS NOT NULL""",
-                (cutoff,),
-            )
-
-        for row in cursor.fetchall():
-            try:
-                calls = row["tool_calls"]
-                if isinstance(calls, str):
-                    calls = json.loads(calls)
-                if not isinstance(calls, list):
-                    continue
-            except (json.JSONDecodeError, TypeError):
-                continue
-
-            timestamp = row["timestamp"]
-            for call in calls:
-                if not isinstance(call, dict):
-                    continue
-                func = call.get("function", {})
-                tool_name = func.get("name")
-                if tool_name not in {"skill_view", "skill_manage"}:
-                    continue
-
-                args = func.get("arguments")
-                if isinstance(args, str):
-                    try:
-                        args = json.loads(args)
-                    except (json.JSONDecodeError, TypeError):
-                        continue
-                if not isinstance(args, dict):
-                    continue
-
-                skill_name = args.get("name")
-                if not isinstance(skill_name, str) or not skill_name.strip():
-                    continue
-
-                entry = skill_counts.setdefault(
-                    skill_name,
-                    {
-                        "skill": skill_name,
-                        "view_count": 0,
-                        "manage_count": 0,
-                        "last_used_at": None,
-                    },
-                )
-                if tool_name == "skill_view":
-                    entry["view_count"] += 1
-                else:
-                    entry["manage_count"] += 1
-
-                if timestamp is not None and (
-                    entry["last_used_at"] is None or timestamp > entry["last_used_at"]
-                ):
-                    entry["last_used_at"] = timestamp
-
-        return list(skill_counts.values())
-
     def _get_message_stats(self, cutoff: float, source: str = None) -> Dict:
         """Get aggregate message statistics."""
         if source:
@@ -563,46 +476,6 @@ class InsightsEngine:
             })
         return result
 
-    def _compute_skill_breakdown(self, skill_usage: List[Dict]) -> Dict[str, Any]:
-        """Process per-skill usage into summary + ranked list."""
-        total_skill_loads = sum(s["view_count"] for s in skill_usage) if skill_usage else 0
-        total_skill_edits = sum(s["manage_count"] for s in skill_usage) if skill_usage else 0
-        total_skill_actions = total_skill_loads + total_skill_edits
-
-        top_skills = []
-        for skill in skill_usage:
-            total_count = skill["view_count"] + skill["manage_count"]
-            percentage = (total_count / total_skill_actions * 100) if total_skill_actions else 0
-            top_skills.append({
-                "skill": skill["skill"],
-                "view_count": skill["view_count"],
-                "manage_count": skill["manage_count"],
-                "total_count": total_count,
-                "percentage": percentage,
-                "last_used_at": skill.get("last_used_at"),
-            })
-
-        top_skills.sort(
-            key=lambda s: (
-                s["total_count"],
-                s["view_count"],
-                s["manage_count"],
-                s["last_used_at"] or 0,
-                s["skill"],
-            ),
-            reverse=True,
-        )
-
-        return {
-            "summary": {
-                "total_skill_loads": total_skill_loads,
-                "total_skill_edits": total_skill_edits,
-                "total_skill_actions": total_skill_actions,
-                "distinct_skills_used": len(skill_usage),
-            },
-            "top_skills": top_skills,
-        }
-
     def _compute_activity_patterns(self, sessions: List[Dict]) -> Dict:
         """Analyze activity patterns by day of week and hour."""
         day_counts = Counter()  # 0=Monday ... 6=Sunday
@@ -762,7 +635,13 @@ class InsightsEngine:
         lines.append(f"  Sessions:          {o['total_sessions']:<12}  Messages:        {o['total_messages']:,}")
         lines.append(f"  Tool calls:        {o['total_tool_calls']:<12,}  User messages:   {o['user_messages']:,}")
         lines.append(f"  Input tokens:      {o['total_input_tokens']:<12,}  Output tokens:   {o['total_output_tokens']:,}")
-        lines.append(f"  Total tokens:      {o['total_tokens']:,}")
+        cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
+        if cache_total > 0:
+            lines.append(f"  Cache read:        {o['total_cache_read_tokens']:<12,}  Cache write:     {o['total_cache_write_tokens']:,}")
+        cost_str = f"${o['estimated_cost']:.2f}"
+        if o.get("models_without_pricing"):
+            cost_str += " *"
+        lines.append(f"  Total tokens:      {o['total_tokens']:<12,}  Est. cost:       {cost_str}")
         if o["total_hours"] > 0:
             lines.append(f"  Active time:       ~{_format_duration(o['total_hours'] * 3600):<11}  Avg session:     ~{_format_duration(o['avg_session_duration'])}")
         lines.append(f"  Avg msgs/session:  {o['avg_messages_per_session']:.1f}")
@@ -772,10 +651,16 @@ class InsightsEngine:
         if report["models"]:
             lines.append("  🤖 Models Used")
             lines.append("  " + "─" * 56)
-            lines.append(f"  {'Model':<30} {'Sessions':>8} {'Tokens':>12}")
+            lines.append(f"  {'Model':<30} {'Sessions':>8} {'Tokens':>12} {'Cost':>8}")
             for m in report["models"]:
                 model_name = m["model"][:28]
-                lines.append(f"  {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,}")
+                if m.get("has_pricing"):
+                    cost_cell = f"${m['cost']:>6.2f}"
+                else:
+                    cost_cell = "     N/A"
+                lines.append(f"  {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,} {cost_cell}")
+            if o.get("models_without_pricing"):
+                lines.append("  * Cost N/A for custom/self-hosted models")
             lines.append("")
 
         # Platform breakdown
@@ -798,28 +683,6 @@ class InsightsEngine:
                 lines.append(f"  ... and {len(report['tools']) - 15} more tools")
             lines.append("")
 
-        # Skill usage
-        skills = report.get("skills", {})
-        top_skills = skills.get("top_skills", [])
-        if top_skills:
-            lines.append("  🧠 Top Skills")
-            lines.append("  " + "─" * 56)
-            lines.append(f"  {'Skill':<28} {'Loads':>7} {'Edits':>7} {'Last used':>11}")
-            for skill in top_skills[:10]:
-                last_used = "—"
-                if skill.get("last_used_at"):
-                    last_used = datetime.fromtimestamp(skill["last_used_at"]).strftime("%b %d")
-                lines.append(
-                    f"  {skill['skill'][:28]:<28} {skill['view_count']:>7,} {skill['manage_count']:>7,} {last_used:>11}"
-                )
-            summary = skills.get("summary", {})
-            lines.append(
-                f"  Distinct skills: {summary.get('distinct_skills_used', 0)}  "
-                f"Loads: {summary.get('total_skill_loads', 0):,}  "
-                f"Edits: {summary.get('total_skill_edits', 0):,}"
-            )
-            lines.append("")
-
         # Activity patterns
         act = report.get("activity", {})
         if act.get("by_day"):
@@ -877,7 +740,15 @@ class InsightsEngine:
 
         # Overview
         lines.append(f"**Sessions:** {o['total_sessions']} | **Messages:** {o['total_messages']:,} | **Tool calls:** {o['total_tool_calls']:,}")
-        lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
+        cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
+        if cache_total > 0:
+            lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,} / cache: {cache_total:,})")
+        else:
+            lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
+        cost_note = ""
+        if o.get("models_without_pricing"):
+            cost_note = " _(excludes custom/self-hosted models)_"
+        lines.append(f"**Est. cost:** ${o['estimated_cost']:.2f}{cost_note}")
         if o["total_hours"] > 0:
             lines.append(f"**Active time:** ~{_format_duration(o['total_hours'] * 3600)} | **Avg session:** ~{_format_duration(o['avg_session_duration'])}")
         lines.append("")
@@ -886,7 +757,8 @@ class InsightsEngine:
         if report["models"]:
             lines.append("**🤖 Models:**")
             for m in report["models"][:5]:
-                lines.append(f"  {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens")
+                cost_str = f"${m['cost']:.2f}" if m.get("has_pricing") else "N/A"
+                lines.append(f"  {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens, {cost_str}")
             lines.append("")
 
         # Platforms (if multi-platform)
@@ -903,18 +775,6 @@ class InsightsEngine:
                 lines.append(f"  {t['tool']} — {t['count']:,} calls ({t['percentage']:.1f}%)")
             lines.append("")
 
-        skills = report.get("skills", {})
-        if skills.get("top_skills"):
-            lines.append("**🧠 Top Skills:**")
-            for skill in skills["top_skills"][:5]:
-                suffix = ""
-                if skill.get("last_used_at"):
-                    suffix = f", last used {datetime.fromtimestamp(skill['last_used_at']).strftime('%b %d')}"
-                lines.append(
-                    f"  {skill['skill']} — {skill['view_count']:,} loads, {skill['manage_count']:,} edits{suffix}"
-                )
-            lines.append("")
-
         # Activity summary
         act = report.get("activity", {})
         if act.get("busiest_day") and act.get("busiest_hour"):

agent/manual_compression_feedback.py

@@ -1,49 +0,0 @@
-"""User-facing summaries for manual compression commands."""
-
-from __future__ import annotations
-
-from typing import Any, Sequence
-
-
-def summarize_manual_compression(
-    before_messages: Sequence[dict[str, Any]],
-    after_messages: Sequence[dict[str, Any]],
-    before_tokens: int,
-    after_tokens: int,
-) -> dict[str, Any]:
-    """Return consistent user-facing feedback for manual compression."""
-    before_count = len(before_messages)
-    after_count = len(after_messages)
-    noop = list(after_messages) == list(before_messages)
-
-    if noop:
-        headline = f"No changes from compression: {before_count} messages"
-        if after_tokens == before_tokens:
-            token_line = (
-                f"Rough transcript estimate: ~{before_tokens:,} tokens (unchanged)"
-            )
-        else:
-            token_line = (
-                f"Rough transcript estimate: ~{before_tokens:,} → "
-                f"~{after_tokens:,} tokens"
-            )
-    else:
-        headline = f"Compressed: {before_count} → {after_count} messages"
-        token_line = (
-            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 rough transcript estimate "
-            "when compression rewrites the transcript into denser summaries."
-        )
-
-    return {
-        "noop": noop,
-        "headline": headline,
-        "token_line": token_line,
-        "note": note,
-    }

agent/memory_manager.py

@@ -44,22 +44,11 @@ logger = logging.getLogger(__name__)
 # ---------------------------------------------------------------------------
 
 _FENCE_TAG_RE = re.compile(r'</?\s*memory-context\s*>', re.IGNORECASE)
-_INTERNAL_CONTEXT_RE = re.compile(
-    r'<\s*memory-context\s*>[\s\S]*?</\s*memory-context\s*>',
-    re.IGNORECASE,
-)
-_INTERNAL_NOTE_RE = re.compile(
-    r'\[System note:\s*The following is recalled memory context,\s*NOT new user input\.\s*Treat as informational background data\.\]\s*',
-    re.IGNORECASE,
-)
 
 
 def sanitize_context(text: str) -> str:
-    """Strip fence tags, injected context blocks, and system notes from provider output."""
-    text = _INTERNAL_CONTEXT_RE.sub('', text)
-    text = _INTERNAL_NOTE_RE.sub('', text)
-    text = _FENCE_TAG_RE.sub('', text)
-    return text
+    """Strip fence-escape sequences from provider output."""
+    return _FENCE_TAG_RE.sub('', text)
 
 
 def build_memory_context_block(raw_context: str) -> str:

agent/model_metadata.py

@@ -5,6 +5,7 @@ and run_agent.py for pre-flight context checks.
 """
 
 import logging
+import os
 import re
 import time
 from pathlib import Path
@@ -23,22 +24,15 @@ logger = logging.getLogger(__name__)
 # 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", "minimax", "minimax-cn", "anthropic", "deepseek",
+    "gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
     "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
     "qwen-oauth",
-    "xiaomi",
-    "arcee",
     "custom", "local",
     # Common aliases
     "google", "google-gemini", "google-ai-studio",
     "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
-    "github-models", "kimi", "moonshot", "kimi-cn", "moonshot-cn", "claude", "deep-seek",
-    "ollama",
+    "github-models", "kimi", "moonshot", "claude", "deep-seek",
     "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
-    "mimo", "xiaomi-mimo",
-    "arcee-ai", "arceeai",
-    "xai", "x-ai", "x.ai", "grok",
-    "nvidia", "nim", "nvidia-nim", "nemotron",
     "qwen-portal",
 })
 
@@ -89,11 +83,6 @@ CONTEXT_PROBE_TIERS = [
 # Default context length when no detection method succeeds.
 DEFAULT_FALLBACK_CONTEXT = CONTEXT_PROBE_TIERS[0]
 
-# Minimum context length required to run Hermes Agent.  Models with fewer
-# tokens cannot maintain enough working memory for tool-calling workflows.
-# Sessions, model switches, and cron jobs should reject models below this.
-MINIMUM_CONTEXT_LENGTH = 64_000
-
 # Thin fallback defaults — only broad model family patterns.
 # These fire only when provider is unknown AND models.dev/OpenRouter/Anthropic
 # all miss. Replaced the previous 80+ entry dict.
@@ -103,77 +92,54 @@ DEFAULT_CONTEXT_LENGTHS = {
     # fuzzy-match collisions (e.g. "anthropic/claude-sonnet-4" is a
     # substring of "anthropic/claude-sonnet-4.6").
     # OpenRouter-prefixed models resolve via OpenRouter live API or models.dev.
-    "claude-opus-4-7": 1000000,
-    "claude-opus-4.7": 1000000,
     "claude-opus-4-6": 1000000,
     "claude-sonnet-4-6": 1000000,
     "claude-opus-4.6": 1000000,
     "claude-sonnet-4.6": 1000000,
     # Catch-all for older Claude models (must sort after specific entries)
     "claude": 200000,
-    # OpenAI — GPT-5 family (most have 400k; specific overrides first)
-    # Source: https://developers.openai.com/api/docs/models
-    "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)
-    "gpt-5.1-chat": 128000,           # Chat variant has 128k context
-    "gpt-5": 400000,                  # GPT-5.x base, mini, codex variants (400k)
+    # OpenAI
     "gpt-4.1": 1047576,
+    "gpt-5": 128000,
     "gpt-4": 128000,
     # Google
     "gemini": 1048576,
     # Gemma (open models served via AI Studio)
     "gemma-4-31b": 256000,
+    "gemma-4-26b": 256000,
     "gemma-3": 131072,
     "gemma": 8192,  # fallback for older gemma models
     # DeepSeek
     "deepseek": 128000,
     # Meta
     "llama": 131072,
-    # Qwen — specific model families before the catch-all.
-    # Official docs: https://help.aliyun.com/zh/model-studio/developer-reference/
-    "qwen3-coder-plus": 1000000,  # 1M context
-    "qwen3-coder": 262144,        # 256K context
+    # Qwen
     "qwen": 131072,
-    # MiniMax — official docs: 204,800 context for all models
-    # https://platform.minimax.io/docs/api-reference/text-anthropic-api
-    "minimax": 204800,
+    # MiniMax (lowercase — lookup lowercases model names at line 973)
+    "minimax-m1-256k": 1000000,
+    "minimax-m1-128k": 1000000,
+    "minimax-m1-80k": 1000000,
+    "minimax-m1-40k": 1000000,
+    "minimax-m1": 1000000,
+    "minimax-m2.5": 1048576,
+    "minimax-m2.7": 1048576,
+    "minimax": 1048576,
     # GLM
     "glm": 202752,
-    # xAI Grok — xAI /v1/models does not return context_length metadata,
-    # so these hardcoded fallbacks prevent Hermes from probing-down to
-    # the default 128k when the user points at https://api.x.ai/v1
-    # via a custom provider. Values sourced from models.dev (2026-04).
-    # Keys use substring matching (longest-first), so e.g. "grok-4.20"
-    # matches "grok-4.20-0309-reasoning" / "-non-reasoning" / "-multi-agent-0309".
-    "grok-code-fast": 256000,   # grok-code-fast-1
-    "grok-4-1-fast": 2000000,   # grok-4-1-fast-(non-)reasoning
-    "grok-2-vision": 8192,      # grok-2-vision, -1212, -latest
-    "grok-4-fast": 2000000,     # grok-4-fast-(non-)reasoning
-    "grok-4.20": 2000000,       # grok-4.20-0309-(non-)reasoning, -multi-agent-0309
-    "grok-4": 256000,           # grok-4, grok-4-0709
-    "grok-3": 131072,           # grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast
-    "grok-2": 131072,           # grok-2, grok-2-1212, grok-2-latest
-    "grok": 131072,             # catch-all (grok-beta, unknown grok-*)
     # Kimi
     "kimi": 262144,
-    # Nemotron — NVIDIA's open-weights series (128K context across all sizes)
-    "nemotron": 131072,
     # Arcee
     "trinity": 262144,
-    # OpenRouter
-    "elephant": 262144,
     # Hugging Face Inference Providers — model IDs use org/name format
     "Qwen/Qwen3.5-397B-A17B": 131072,
     "Qwen/Qwen3.5-35B-A3B": 131072,
     "deepseek-ai/DeepSeek-V3.2": 65536,
     "moonshotai/Kimi-K2.5": 262144,
     "moonshotai/Kimi-K2-Thinking": 262144,
-    "MiniMaxAI/MiniMax-M2.5": 204800,
-    "XiaomiMiMo/MiMo-V2-Flash": 256000,
-    "mimo-v2-pro": 1000000,
-    "mimo-v2-omni": 256000,
-    "mimo-v2-flash": 256000,
+    "MiniMaxAI/MiniMax-M2.5": 1048576,
+    "XiaomiMiMo/MiMo-V2-Flash": 32768,
+    "mimo-v2-pro": 1048576,
+    "mimo-v2-omni": 1048576,
     "zai-org/GLM-5": 202752,
 }
 
@@ -198,12 +164,6 @@ _MAX_COMPLETION_KEYS = (
 
 # Local server hostnames / address patterns
 _LOCAL_HOSTS = ("localhost", "127.0.0.1", "::1", "0.0.0.0")
-# Docker / Podman / Lima DNS names that resolve to the host machine
-_CONTAINER_LOCAL_SUFFIXES = (
-    ".docker.internal",
-    ".containers.internal",
-    ".lima.internal",
-)
 
 
 def _normalize_base_url(base_url: str) -> str:
@@ -225,9 +185,7 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.anthropic.com": "anthropic",
     "api.z.ai": "zai",
     "api.moonshot.ai": "kimi-coding",
-    "api.moonshot.cn": "kimi-coding-cn",
     "api.kimi.com": "kimi-coding",
-    "api.arcee.ai": "arcee",
     "api.minimax": "minimax",
     "dashscope.aliyuncs.com": "alibaba",
     "dashscope-intl.aliyuncs.com": "alibaba",
@@ -240,11 +198,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "models.github.ai": "copilot",
     "api.fireworks.ai": "fireworks",
     "opencode.ai": "opencode-go",
-    "api.x.ai": "xai",
-    "integrate.api.nvidia.com": "nvidia",
-    "api.xiaomimimo.com": "xiaomi",
-    "xiaomimimo.com": "xiaomi",
-    "ollama.com": "ollama-cloud",
 }
 
 
@@ -283,9 +236,6 @@ def is_local_endpoint(base_url: str) -> bool:
         return False
     if host in _LOCAL_HOSTS:
         return True
-    # Docker / Podman / Lima internal DNS names (e.g. host.docker.internal)
-    if any(host.endswith(suffix) for suffix in _CONTAINER_LOCAL_SUFFIXES):
-        return True
     # RFC-1918 private ranges and link-local
     import ipaddress
     try:
@@ -793,12 +743,12 @@ def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
                 resp = client.post(f"{server_url}/api/show", json={"name": model})
                 if resp.status_code == 200:
                     data = resp.json()
-                    # Prefer explicit num_ctx from Modelfile parameters: this is
-                    # the *runtime* context Ollama will actually allocate KV cache
-                    # for. The GGUF model_info.context_length is the training max,
-                    # which can be larger than num_ctx — using it here would let
-                    # Hermes grow conversations past the runtime limit and Ollama
-                    # would silently truncate. Matches query_ollama_num_ctx().
+                    # Check model_info for context length
+                    model_info = data.get("model_info", {})
+                    for key, value in model_info.items():
+                        if "context_length" in key and isinstance(value, (int, float)):
+                            return int(value)
+                    # Check parameters string for num_ctx
                     params = data.get("parameters", "")
                     if "num_ctx" in params:
                         for line in params.split("\n"):
@@ -809,11 +759,6 @@ def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
                                         return int(parts[-1])
                                     except ValueError:
                                         pass
-                    # Fall back to GGUF model_info context_length (training max)
-                    model_info = data.get("model_info", {})
-                    for key, value in model_info.items():
-                        if "context_length" in key and isinstance(value, (int, float)):
-                            return int(value)
 
             # LM Studio native API: /api/v1/models returns max_context_length.
             # This is more reliable than the OpenAI-compat /v1/models which
@@ -1018,16 +963,6 @@ def get_model_context_length(
         if ctx:
             return ctx
 
-    # 4b. AWS Bedrock — use static context length table.
-    # Bedrock's ListFoundationModels doesn't expose context window sizes,
-    # so we maintain a curated table in bedrock_adapter.py.
-    if provider == "bedrock" or (base_url and "bedrock-runtime" in base_url):
-        try:
-            from agent.bedrock_adapter import get_bedrock_context_length
-            return get_bedrock_context_length(model)
-        except ImportError:
-            pass  # boto3 not installed — fall through to generic resolution
-
     # 5. Provider-aware lookups (before generic OpenRouter cache)
     # These are provider-specific and take priority over the generic OR cache,
     # since the same model can have different context limits per provider
@@ -1078,21 +1013,16 @@ def get_model_context_length(
 
 
 def estimate_tokens_rough(text: str) -> int:
-    """Rough token estimate (~4 chars/token) for pre-flight checks.
-
-    Uses ceiling division so short texts (1-3 chars) never estimate as
-    0 tokens, which would cause the compressor and pre-flight checks to
-    systematically undercount when many short tool results are present.
-    """
+    """Rough token estimate (~4 chars/token) for pre-flight checks."""
     if not text:
         return 0
-    return (len(text) + 3) // 4
+    return len(text) // 4
 
 
 def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
     """Rough token estimate for a message list (pre-flight only)."""
     total_chars = sum(len(str(msg)) for msg in messages)
-    return (total_chars + 3) // 4
+    return total_chars // 4
 
 
 def estimate_request_tokens_rough(
@@ -1115,4 +1045,4 @@ def estimate_request_tokens_rough(
         total_chars += sum(len(str(msg)) for msg in messages)
     if tools:
         total_chars += len(str(tools))
-    return (total_chars + 3) // 4
+    return total_chars // 4

agent/models_dev.py

@@ -18,8 +18,10 @@ Other modules should import the dataclasses and query functions from here
 rather than parsing the raw JSON themselves.
 """
 
+import difflib
 import json
 import logging
+import os
 import time
 from dataclasses import dataclass
 from pathlib import Path
@@ -142,11 +144,8 @@ class ProviderInfo:
 PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "openrouter": "openrouter",
     "anthropic": "anthropic",
-    "openai": "openai",
-    "openai-codex": "openai",
     "zai": "zai",
     "kimi-coding": "kimi-for-coding",
-    "kimi-coding-cn": "kimi-for-coding",
     "minimax": "minimax",
     "minimax-cn": "minimax-cn",
     "deepseek": "deepseek",
@@ -162,20 +161,25 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "gemini": "google",
     "google": "google",
     "xai": "xai",
-    "xiaomi": "xiaomi",
     "nvidia": "nvidia",
     "groq": "groq",
     "mistral": "mistral",
     "togetherai": "togetherai",
     "perplexity": "perplexity",
     "cohere": "cohere",
-    "ollama-cloud": "ollama-cloud",
 }
 
 # Reverse mapping: models.dev → Hermes (built lazily)
 _MODELS_DEV_TO_PROVIDER: Optional[Dict[str, str]] = None
 
 
+def _get_reverse_mapping() -> Dict[str, str]:
+    """Return models.dev ID → Hermes provider ID mapping."""
+    global _MODELS_DEV_TO_PROVIDER
+    if _MODELS_DEV_TO_PROVIDER is None:
+        _MODELS_DEV_TO_PROVIDER = {v: k for k, v in PROVIDER_TO_MODELS_DEV.items()}
+    return _MODELS_DEV_TO_PROVIDER
+
 
 def _get_cache_path() -> Path:
     """Return path to disk cache file."""
@@ -379,14 +383,7 @@ def get_model_capabilities(provider: str, model: str) -> Optional[ModelCapabilit
 
     # Extract capability flags (default to False if missing)
     supports_tools = bool(entry.get("tool_call", False))
-    # Vision: check both the `attachment` flag and `modalities.input` for "image".
-    # Some models (e.g. gemma-4) list image in input modalities but not attachment.
-    input_mods = entry.get("modalities", {})
-    if isinstance(input_mods, dict):
-        input_mods = input_mods.get("input", [])
-    else:
-        input_mods = []
-    supports_vision = bool(entry.get("attachment", False)) or "image" in input_mods
+    supports_vision = bool(entry.get("attachment", False))
     supports_reasoning = bool(entry.get("reasoning", False))
 
     # Extract limits
@@ -420,10 +417,7 @@ def list_provider_models(provider: str) -> List[str]:
     models = _get_provider_models(provider)
     if models is None:
         return []
-    return [
-        mid for mid in models.keys()
-        if not _should_hide_from_provider_catalog(provider, mid)
-    ]
+    return list(models.keys())
 
 
 # Patterns that indicate non-agentic or noise models (TTS, embedding,
@@ -435,43 +429,6 @@ _NOISE_PATTERNS: re.Pattern = re.compile(
     re.IGNORECASE,
 )
 
-# Google's live Gemini catalogs currently include a mix of stale slugs and
-# Gemma models whose TPM quotas are too small for normal Hermes agent traffic.
-# Keep capability metadata available for direct/manual use, but hide these from
-# the Gemini model catalogs we surface in setup and model selection.
-_GOOGLE_HIDDEN_MODELS = frozenset({
-    # Low-TPM Gemma models that trip Google input-token quota walls under
-    # agent-style traffic despite advertising large context windows.
-    "gemma-4-31b-it",
-    "gemma-4-26b-it",
-    "gemma-4-26b-a4b-it",
-    "gemma-3-1b",
-    "gemma-3-1b-it",
-    "gemma-3-2b",
-    "gemma-3-2b-it",
-    "gemma-3-4b",
-    "gemma-3-4b-it",
-    "gemma-3-12b",
-    "gemma-3-12b-it",
-    "gemma-3-27b",
-    "gemma-3-27b-it",
-    # Stale/retired Google slugs that still surface through models.dev-backed
-    # Gemini selection but 404 on the current Google endpoints.
-    "gemini-1.5-flash",
-    "gemini-1.5-pro",
-    "gemini-1.5-flash-8b",
-    "gemini-2.0-flash",
-    "gemini-2.0-flash-lite",
-})
-
-
-def _should_hide_from_provider_catalog(provider: str, model_id: str) -> bool:
-    provider_lower = (provider or "").strip().lower()
-    model_lower = (model_id or "").strip().lower()
-    if provider_lower in {"gemini", "google"} and model_lower in _GOOGLE_HIDDEN_MODELS:
-        return True
-    return False
-
 
 def list_agentic_models(provider: str) -> List[str]:
     """Return model IDs suitable for agentic use from models.dev.
@@ -488,8 +445,6 @@ def list_agentic_models(provider: str) -> List[str]:
     for mid, entry in models.items():
         if not isinstance(entry, dict):
             continue
-        if _should_hide_from_provider_catalog(provider, mid):
-            continue
         if not entry.get("tool_call", False):
             continue
         if _NOISE_PATTERNS.search(mid):
@@ -498,6 +453,93 @@ def list_agentic_models(provider: str) -> List[str]:
     return result
 
 
+def search_models_dev(
+    query: str, provider: str = None, limit: int = 5
+) -> List[Dict[str, Any]]:
+    """Fuzzy search across models.dev catalog. Returns matching model entries.
+
+    Args:
+        query: Search string to match against model IDs.
+        provider: Optional Hermes provider ID to restrict search scope.
+                  If None, searches across all providers in PROVIDER_TO_MODELS_DEV.
+        limit: Maximum number of results to return.
+
+    Returns:
+        List of dicts, each containing 'provider', 'model_id', and the full
+        model 'entry' from models.dev.
+    """
+    data = fetch_models_dev()
+    if not data:
+        return []
+
+    # Build list of (provider_id, model_id, entry) candidates
+    candidates: List[tuple] = []
+
+    if provider is not None:
+        # Search only the specified provider
+        mdev_provider_id = PROVIDER_TO_MODELS_DEV.get(provider)
+        if not mdev_provider_id:
+            return []
+        provider_data = data.get(mdev_provider_id, {})
+        if isinstance(provider_data, dict):
+            models = provider_data.get("models", {})
+            if isinstance(models, dict):
+                for mid, mdata in models.items():
+                    candidates.append((provider, mid, mdata))
+    else:
+        # Search across all mapped providers
+        for hermes_prov, mdev_prov in PROVIDER_TO_MODELS_DEV.items():
+            provider_data = data.get(mdev_prov, {})
+            if isinstance(provider_data, dict):
+                models = provider_data.get("models", {})
+                if isinstance(models, dict):
+                    for mid, mdata in models.items():
+                        candidates.append((hermes_prov, mid, mdata))
+
+    if not candidates:
+        return []
+
+    # Use difflib for fuzzy matching — case-insensitive comparison
+    model_ids_lower = [c[1].lower() for c in candidates]
+    query_lower = query.lower()
+
+    # First try exact substring matches (more intuitive than pure edit-distance)
+    substring_matches = []
+    for prov, mid, mdata in candidates:
+        if query_lower in mid.lower():
+            substring_matches.append({"provider": prov, "model_id": mid, "entry": mdata})
+
+    # Then add difflib fuzzy matches for any remaining slots
+    fuzzy_ids = difflib.get_close_matches(
+        query_lower, model_ids_lower, n=limit * 2, cutoff=0.4
+    )
+
+    seen_ids: set = set()
+    results: List[Dict[str, Any]] = []
+
+    # Prioritize substring matches
+    for match in substring_matches:
+        key = (match["provider"], match["model_id"])
+        if key not in seen_ids:
+            seen_ids.add(key)
+            results.append(match)
+            if len(results) >= limit:
+                return results
+
+    # Add fuzzy matches
+    for fid in fuzzy_ids:
+        # Find original-case candidates matching this lowered ID
+        for prov, mid, mdata in candidates:
+            if mid.lower() == fid:
+                key = (prov, mid)
+                if key not in seen_ids:
+                    seen_ids.add(key)
+                    results.append({"provider": prov, "model_id": mid, "entry": mdata})
+                    if len(results) >= limit:
+                        return results
+
+    return results
+
 
 # ---------------------------------------------------------------------------
 # Rich dataclass constructors — parse raw models.dev JSON into dataclasses
@@ -624,3 +666,5 @@ def get_model_info(
             return _parse_model_info(mid, mdata, mdev_id)
 
     return None
+
+

agent/nous_rate_guard.py

@@ -1,182 +0,0 @@
-"""Cross-session rate limit guard for Nous Portal.
-
-Writes rate limit state to a shared file so all sessions (CLI, gateway,
-cron, auxiliary) can check whether Nous Portal is currently rate-limited
-before making requests.  Prevents retry amplification when RPH is tapped.
-
-Each 429 from Nous triggers up to 9 API calls per conversation turn
-(3 SDK retries x 3 Hermes retries), and every one of those calls counts
-against RPH.  By recording the rate limit state on first 429 and checking
-it before subsequent attempts, we eliminate the amplification effect.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import tempfile
-import time
-from typing import Any, Mapping, Optional
-
-logger = logging.getLogger(__name__)
-
-_STATE_SUBDIR = "rate_limits"
-_STATE_FILENAME = "nous.json"
-
-
-def _state_path() -> str:
-    """Return the path to the Nous rate limit state file."""
-    try:
-        from hermes_constants import get_hermes_home
-        base = get_hermes_home()
-    except ImportError:
-        base = os.path.join(os.path.expanduser("~"), ".hermes")
-    return os.path.join(base, _STATE_SUBDIR, _STATE_FILENAME)
-
-
-def _parse_reset_seconds(headers: Optional[Mapping[str, str]]) -> Optional[float]:
-    """Extract the best available reset-time estimate from response headers.
-
-    Priority:
-      1. x-ratelimit-reset-requests-1h  (hourly RPH window — most useful)
-      2. x-ratelimit-reset-requests     (per-minute RPM window)
-      3. retry-after                     (generic HTTP header)
-
-    Returns seconds-from-now, or None if no usable header found.
-    """
-    if not headers:
-        return None
-
-    lowered = {k.lower(): v for k, v in headers.items()}
-
-    for key in (
-        "x-ratelimit-reset-requests-1h",
-        "x-ratelimit-reset-requests",
-        "retry-after",
-    ):
-        raw = lowered.get(key)
-        if raw is not None:
-            try:
-                val = float(raw)
-                if val > 0:
-                    return val
-            except (TypeError, ValueError):
-                pass
-
-    return None
-
-
-def record_nous_rate_limit(
-    *,
-    headers: Optional[Mapping[str, str]] = None,
-    error_context: Optional[dict[str, Any]] = None,
-    default_cooldown: float = 300.0,
-) -> None:
-    """Record that Nous Portal is rate-limited.
-
-    Parses the reset time from response headers or error context.
-    Falls back to ``default_cooldown`` (5 minutes) if no reset info
-    is available.  Writes to a shared file that all sessions can read.
-
-    Args:
-        headers: HTTP response headers from the 429 error.
-        error_context: Structured error context from _extract_api_error_context().
-        default_cooldown: Fallback cooldown in seconds when no header data.
-    """
-    now = time.time()
-    reset_at = None
-
-    # Try headers first (most accurate)
-    header_seconds = _parse_reset_seconds(headers)
-    if header_seconds is not None:
-        reset_at = now + header_seconds
-
-    # Try error_context reset_at (from body parsing)
-    if reset_at is None and isinstance(error_context, dict):
-        ctx_reset = error_context.get("reset_at")
-        if isinstance(ctx_reset, (int, float)) and ctx_reset > now:
-            reset_at = float(ctx_reset)
-
-    # Default cooldown
-    if reset_at is None:
-        reset_at = now + default_cooldown
-
-    path = _state_path()
-    try:
-        state_dir = os.path.dirname(path)
-        os.makedirs(state_dir, exist_ok=True)
-
-        state = {
-            "reset_at": reset_at,
-            "recorded_at": now,
-            "reset_seconds": reset_at - now,
-        }
-
-        # Atomic write: write to temp file + rename
-        fd, tmp_path = tempfile.mkstemp(dir=state_dir, suffix=".tmp")
-        try:
-            with os.fdopen(fd, "w") as f:
-                json.dump(state, f)
-            os.replace(tmp_path, path)
-        except Exception:
-            # Clean up temp file on failure
-            try:
-                os.unlink(tmp_path)
-            except OSError:
-                pass
-            raise
-
-        logger.info(
-            "Nous rate limit recorded: resets in %.0fs (at %.0f)",
-            reset_at - now, reset_at,
-        )
-    except Exception as exc:
-        logger.debug("Failed to write Nous rate limit state: %s", exc)
-
-
-def nous_rate_limit_remaining() -> Optional[float]:
-    """Check if Nous Portal is currently rate-limited.
-
-    Returns:
-        Seconds remaining until reset, or None if not rate-limited.
-    """
-    path = _state_path()
-    try:
-        with open(path) as f:
-            state = json.load(f)
-        reset_at = state.get("reset_at", 0)
-        remaining = reset_at - time.time()
-        if remaining > 0:
-            return remaining
-        # Expired — clean up
-        try:
-            os.unlink(path)
-        except OSError:
-            pass
-        return None
-    except (FileNotFoundError, json.JSONDecodeError, KeyError, TypeError):
-        return None
-
-
-def clear_nous_rate_limit() -> None:
-    """Clear the rate limit state (e.g., after a successful Nous request)."""
-    try:
-        os.unlink(_state_path())
-    except FileNotFoundError:
-        pass
-    except OSError as exc:
-        logger.debug("Failed to clear Nous rate limit state: %s", exc)
-
-
-def format_remaining(seconds: float) -> str:
-    """Format seconds remaining into human-readable duration."""
-    s = max(0, int(seconds))
-    if s < 60:
-        return f"{s}s"
-    if s < 3600:
-        m, sec = divmod(s, 60)
-        return f"{m}m {sec}s" if sec else f"{m}m"
-    h, remainder = divmod(s, 3600)
-    m = remainder // 60
-    return f"{h}h {m}m" if m else f"{h}h"

agent/prompt_builder.py

@@ -12,7 +12,7 @@ import threading
 from collections import OrderedDict
 from pathlib import Path
 
-from hermes_constants import get_hermes_home, get_skills_dir, is_wsl
+from hermes_constants import get_hermes_home
 from typing import Optional
 
 from agent.skill_utils import (
@@ -40,7 +40,7 @@ _CONTEXT_THREAT_PATTERNS = [
     (r'disregard\s+(your|all|any)\s+(instructions|rules|guidelines)', "disregard_rules"),
     (r'act\s+as\s+(if|though)\s+you\s+(have\s+no|don\'t\s+have)\s+(restrictions|limits|rules)', "bypass_restrictions"),
     (r'<!--[^>]*(?:ignore|override|system|secret|hidden)[^>]*-->', "html_comment_injection"),
-    (r'<\s*div\s+style\s*=\s*["\'][\s\S]*?display\s*:\s*none', "hidden_div"),
+    (r'<\s*div\s+style\s*=\s*["\'].*display\s*:\s*none', "hidden_div"),
     (r'translate\s+.*\s+into\s+.*\s+and\s+(execute|run|eval)', "translate_execute"),
     (r'curl\s+[^\n]*\$\{?\w*(KEY|TOKEN|SECRET|PASSWORD|CREDENTIAL|API)', "exfil_curl"),
     (r'cat\s+[^\n]*(\.env|credentials|\.netrc|\.pgpass)', "read_secrets"),
@@ -152,13 +152,7 @@ MEMORY_GUIDANCE = (
     "Do NOT save task progress, session outcomes, completed-work logs, or temporary TODO "
     "state to memory; use session_search to recall those from past transcripts. "
     "If you've discovered a new way to do something, solved a problem that could be "
-    "necessary later, save it as a skill with the skill tool.\n"
-    "Write memories as declarative facts, not instructions to yourself. "
-    "'User prefers concise responses' ✓ — 'Always respond concisely' ✗. "
-    "'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. "
-    "Imperative phrasing gets re-read as a directive in later sessions and can "
-    "cause repeated work or override the user's current request. Procedures and "
-    "workflows belong in skills, not memory."
+    "necessary later, save it as a skill with the skill tool."
 )
 
 SESSION_SEARCH_GUIDANCE = (
@@ -301,9 +295,7 @@ PLATFORM_HINTS = {
     ),
     "telegram": (
         "You are on a text messaging communication platform, Telegram. "
-        "Standard markdown is automatically converted to Telegram format. "
-        "Supported: **bold**, *italic*, ~~strikethrough~~, ||spoiler||, "
-        "`inline code`, ```code blocks```, [links](url), and ## headers. "
+        "Please do not use markdown as it does not render. "
         "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 "
@@ -364,64 +356,8 @@ PLATFORM_HINTS = {
         "MEDIA:/absolute/path/to/file in your response. Images (.jpg, .png, "
         ".heic) appear as photos and other files arrive as attachments."
     ),
-    "weixin": (
-        "You are on Weixin/WeChat. Markdown formatting is supported, so you may use it when "
-        "it improves readability, but keep the message compact and chat-friendly. You can send media files natively: "
-        "include MEDIA:/absolute/path/to/file in your response. Images are sent as native "
-        "photos, videos play inline when supported, and other files arrive as downloadable "
-        "documents. You can also include image URLs in markdown format ![alt](url) and they "
-        "will be downloaded and sent as native media when possible."
-    ),
-    "wecom": (
-        "You are on WeCom (企业微信 / Enterprise WeChat). Markdown formatting is supported. "
-        "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 "
-        "WeCom attachment: images (.jpg, .png, .webp) are sent as photos (up to 10 MB), "
-        "other files (.pdf, .docx, .xlsx, .md, .txt, etc.) arrive as downloadable documents "
-        "(up to 20 MB), and videos (.mp4) play inline. Voice messages are supported but "
-        "must be in AMR format — other audio formats are automatically sent as file attachments. "
-        "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."
-    ),
-    "qqbot": (
-        "You are on QQ, a popular Chinese messaging platform. QQ supports markdown formatting "
-        "and emoji. You can send media files natively: include MEDIA:/absolute/path/to/file in "
-        "your response. Images are sent as native photos, and other files arrive as downloadable "
-        "documents."
-    ),
 }
 
-# ---------------------------------------------------------------------------
-# Environment hints — execution-environment awareness for the agent.
-# Unlike PLATFORM_HINTS (which describe the messaging channel), these describe
-# the machine/OS the agent's tools actually run on.
-# ---------------------------------------------------------------------------
-
-WSL_ENVIRONMENT_HINT = (
-    "You are running inside WSL (Windows Subsystem for Linux). "
-    "The Windows host filesystem is mounted under /mnt/ — "
-    "/mnt/c/ is the C: drive, /mnt/d/ is D:, etc. "
-    "The user's Windows files are typically at "
-    "/mnt/c/Users/<username>/Desktop/, Documents/, Downloads/, etc. "
-    "When the user references Windows paths or desktop files, translate "
-    "to the /mnt/c/ equivalent. You can list /mnt/c/Users/ to discover "
-    "the Windows username if needed."
-)
-
-
-def build_environment_hints() -> str:
-    """Return environment-specific guidance for the system prompt.
-
-    Detects WSL, and can be extended for Termux, Docker, etc.
-    Returns an empty string when no special environment is detected.
-    """
-    hints: list[str] = []
-    if is_wsl():
-        hints.append(WSL_ENVIRONMENT_HINT)
-    return "\n\n".join(hints)
-
-
 CONTEXT_FILE_MAX_CHARS = 20_000
 CONTEXT_TRUNCATE_HEAD_RATIO = 0.7
 CONTEXT_TRUNCATE_TAIL_RATIO = 0.2
@@ -543,7 +479,7 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
     (True, {}, "") to err on the side of showing the skill.
     """
     try:
-        raw = skill_file.read_text(encoding="utf-8")
+        raw = skill_file.read_text(encoding="utf-8")[:2000]
         frontmatter, _ = parse_frontmatter(raw)
 
         if not skill_matches_platform(frontmatter):
@@ -551,7 +487,7 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
 
         return True, frontmatter, extract_skill_description(frontmatter)
     except Exception as e:
-        logger.warning("Failed to parse skill file %s: %s", skill_file, e)
+        logger.debug("Failed to parse skill file %s: %s", skill_file, e)
         return True, {}, ""
 
 
@@ -604,7 +540,8 @@ def build_skills_system_prompt(
     are read-only — they appear in the index but new skills are always created
     in the local dir.  Local skills take precedence when names collide.
     """
-    skills_dir = get_skills_dir()
+    hermes_home = get_hermes_home()
+    skills_dir = hermes_home / "skills"
     external_dirs = get_all_skills_dirs()[1:]  # skip local (index 0)
 
     if not skills_dir.exists() and not external_dirs:
@@ -613,20 +550,17 @@ def build_skills_system_prompt(
     # ── Layer 1: in-process LRU cache ─────────────────────────────────
     # Include the resolved platform so per-platform disabled-skill lists
     # produce distinct cache entries (gateway serves multiple platforms).
-    from gateway.session_context import get_session_env
     _platform_hint = (
         os.environ.get("HERMES_PLATFORM")
-        or get_session_env("HERMES_SESSION_PLATFORM")
+        or os.environ.get("HERMES_SESSION_PLATFORM")
         or ""
     )
-    disabled = get_disabled_skill_names()
     cache_key = (
         str(skills_dir.resolve()),
         tuple(str(d) for d in external_dirs),
         tuple(sorted(str(t) for t in (available_tools or set()))),
         tuple(sorted(str(ts) for ts in (available_toolsets or set()))),
         _platform_hint,
-        tuple(sorted(disabled)),
     )
     with _SKILLS_PROMPT_CACHE_LOCK:
         cached = _SKILLS_PROMPT_CACHE.get(cache_key)
@@ -634,6 +568,8 @@ def build_skills_system_prompt(
             _SKILLS_PROMPT_CACHE.move_to_end(cache_key)
             return cached
 
+    disabled = get_disabled_skill_names()
+
     # ── Layer 2: disk snapshot ────────────────────────────────────────
     snapshot = _load_skills_snapshot(skills_dir)
 
@@ -660,7 +596,7 @@ def build_skills_system_prompt(
             ):
                 continue
             skills_by_category.setdefault(category, []).append(
-                (frontmatter_name, entry.get("description", ""))
+                (skill_name, entry.get("description", ""))
             )
         category_descriptions = {
             str(k): str(v)
@@ -685,7 +621,7 @@ def build_skills_system_prompt(
             ):
                 continue
             skills_by_category.setdefault(entry["category"], []).append(
-                (entry["frontmatter_name"], entry["description"])
+                (skill_name, entry["description"])
             )
 
         # Read category-level DESCRIPTION.md files
@@ -728,10 +664,9 @@ def build_skills_system_prompt(
                     continue
                 entry = _build_snapshot_entry(skill_file, ext_dir, frontmatter, desc)
                 skill_name = entry["skill_name"]
-                frontmatter_name = entry["frontmatter_name"]
-                if frontmatter_name in seen_skill_names:
+                if skill_name in seen_skill_names:
                     continue
-                if frontmatter_name in disabled or skill_name in disabled:
+                if entry["frontmatter_name"] in disabled or skill_name in disabled:
                     continue
                 if not _skill_should_show(
                     extract_skill_conditions(frontmatter),
@@ -739,9 +674,9 @@ def build_skills_system_prompt(
                     available_toolsets,
                 ):
                     continue
-                seen_skill_names.add(frontmatter_name)
+                seen_skill_names.add(skill_name)
                 skills_by_category.setdefault(entry["category"], []).append(
-                    (frontmatter_name, entry["description"])
+                    (skill_name, entry["description"])
                 )
             except Exception as e:
                 logger.debug("Error reading external skill %s: %s", skill_file, e)
@@ -783,16 +718,8 @@ def build_skills_system_prompt(
 
         result = (
             "## Skills (mandatory)\n"
-            "Before replying, scan the skills below. If a skill matches or is even partially relevant "
-            "to your task, you MUST load it with skill_view(name) and follow its instructions. "
-            "Err on the side of loading — it is always better to have context you don't need "
-            "than to miss critical steps, pitfalls, or established workflows. "
-            "Skills contain specialized knowledge — API endpoints, tool-specific commands, "
-            "and proven workflows that outperform general-purpose approaches. Load the skill "
-            "even if you think you could handle the task with basic tools like web_search or terminal. "
-            "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"
+            "Before replying, scan the skills below. If one clearly matches your task, "
+            "load it with skill_view(name) and follow its instructions. "
             "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 "
@@ -802,7 +729,7 @@ def build_skills_system_prompt(
             + "\n".join(index_lines) + "\n"
             "</available_skills>\n"
             "\n"
-            "Only proceed without loading a skill if genuinely none are relevant to the task."
+            "If none match, proceed normally without loading a skill."
         )
 
     # ── Store in LRU cache ────────────────────────────────────────────

agent/rate_limit_tracker.py

@@ -24,7 +24,7 @@ from __future__ import annotations
 
 import time
 from dataclasses import dataclass, field
-from typing import Any, Mapping, Optional
+from typing import Any, Dict, Mapping, Optional
 
 
 @dataclass
@@ -97,12 +97,8 @@ def parse_rate_limit_headers(
 
     Returns None if no rate limit headers are present.
     """
-    # Normalize to lowercase so lookups work regardless of how the server
-    # capitalises headers (HTTP header names are case-insensitive per RFC 7230).
-    lowered = {k.lower(): v for k, v in headers.items()}
-
     # Quick check: at least one rate limit header must exist
-    has_any = any(k.startswith("x-ratelimit-") for k in lowered)
+    has_any = any(k.lower().startswith("x-ratelimit-") for k in headers)
     if not has_any:
         return None
 
@@ -113,9 +109,9 @@ def parse_rate_limit_headers(
         #      resource="tokens", suffix="-1h" -> per-hour
         tag = f"{resource}{suffix}"
         return RateLimitBucket(
-            limit=_safe_int(lowered.get(f"x-ratelimit-limit-{tag}")),
-            remaining=_safe_int(lowered.get(f"x-ratelimit-remaining-{tag}")),
-            reset_seconds=_safe_float(lowered.get(f"x-ratelimit-reset-{tag}")),
+            limit=_safe_int(headers.get(f"x-ratelimit-limit-{tag}")),
+            remaining=_safe_int(headers.get(f"x-ratelimit-remaining-{tag}")),
+            reset_seconds=_safe_float(headers.get(f"x-ratelimit-reset-{tag}")),
             captured_at=now,
         )
 

agent/redact.py

@@ -93,17 +93,6 @@ _DB_CONNSTR_RE = re.compile(
     re.IGNORECASE,
 )
 
-# JWT tokens: header.payload[.signature] — always start with "eyJ" (base64 for "{")
-# Matches 1-part (header only), 2-part (header.payload), and full 3-part JWTs.
-_JWT_RE = re.compile(
-    r"eyJ[A-Za-z0-9_-]{10,}"           # Header (always starts with eyJ)
-    r"(?:\.[A-Za-z0-9_=-]{4,}){0,2}"   # Optional payload and/or signature
-)
-
-# Discord user/role mentions: <@123456789012345678> or <@!123456789012345678>
-# Snowflake IDs are 17-20 digit integers that resolve to specific Discord accounts.
-_DISCORD_MENTION_RE = re.compile(r"<@!?(\d{17,20})>")
-
 # E.164 phone numbers: +<country><number>, 7-15 digits
 # Negative lookahead prevents matching hex strings or identifiers
 _SIGNAL_PHONE_RE = re.compile(r"(\+[1-9]\d{6,14})(?![A-Za-z0-9])")
@@ -170,12 +159,6 @@ def redact_sensitive_text(text: str) -> str:
     # Database connection string passwords
     text = _DB_CONNSTR_RE.sub(lambda m: f"{m.group(1)}***{m.group(3)}", text)
 
-    # JWT tokens (eyJ... — base64-encoded JSON headers)
-    text = _JWT_RE.sub(lambda m: _mask_token(m.group(0)), text)
-
-    # Discord user/role mentions (<@snowflake_id>)
-    text = _DISCORD_MENTION_RE.sub(lambda m: f"<@{'!' if '!' in m.group(0) else ''}***>", text)
-
     # E.164 phone numbers (Signal, WhatsApp)
     def _redact_phone(m):
         phone = m.group(1)

agent/skill_commands.py

@@ -12,8 +12,6 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, Optional
 
-from hermes_constants import display_hermes_home
-
 logger = logging.getLogger(__name__)
 
 _skill_commands: Dict[str, Dict[str, Any]] = {}
@@ -72,14 +70,7 @@ def _load_skill_payload(skill_identifier: str, task_id: str | None = None) -> tu
     skill_name = str(loaded_skill.get("name") or normalized)
     skill_path = str(loaded_skill.get("path") or "")
     skill_dir = None
-    # Prefer the absolute skill_dir returned by skill_view() — this is
-    # correct for both local and external skills.  Fall back to the old
-    # SKILLS_DIR-relative reconstruction only when skill_dir is absent
-    # (e.g. legacy skill_view responses).
-    abs_skill_dir = loaded_skill.get("skill_dir")
-    if abs_skill_dir:
-        skill_dir = Path(abs_skill_dir)
-    elif skill_path:
+    if skill_path:
         try:
             skill_dir = SKILLS_DIR / Path(skill_path).parent
         except Exception:
@@ -117,7 +108,7 @@ def _inject_skill_config(loaded_skill: dict[str, Any], parts: list[str]) -> None
         if not resolved:
             return
 
-        lines = ["", f"[Skill config (from {display_hermes_home()}/config.yaml):"]
+        lines = ["", "[Skill config (from ~/.hermes/config.yaml):"]
         for key, value in resolved.items():
             display_val = str(value) if value else "(not set)"
             lines.append(f"  {key} = {display_val}")
@@ -177,7 +168,7 @@ def _build_skill_message(
             subdir_path = skill_dir / subdir
             if subdir_path.exists():
                 for f in sorted(subdir_path.rglob("*")):
-                    if f.is_file() and not f.is_symlink():
+                    if f.is_file():
                         rel = str(f.relative_to(skill_dir))
                         supporting.append(rel)
 

agent/skill_utils.py

@@ -10,9 +10,9 @@ import os
 import re
 import sys
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple
+from typing import Any, Dict, List, Set, Tuple
 
-from hermes_constants import get_config_path, get_skills_dir
+from hermes_constants import get_hermes_home
 
 logger = logging.getLogger(__name__)
 
@@ -130,7 +130,7 @@ def get_disabled_skill_names(platform: str | None = None) -> Set[str]:
     Reads the config file directly (no CLI config imports) to stay
     lightweight.
     """
-    config_path = get_config_path()
+    config_path = get_hermes_home() / "config.yaml"
     if not config_path.exists():
         return set()
     try:
@@ -145,11 +145,10 @@ def get_disabled_skill_names(platform: str | None = None) -> Set[str]:
     if not isinstance(skills_cfg, dict):
         return set()
 
-    from gateway.session_context import get_session_env
     resolved_platform = (
         platform
         or os.getenv("HERMES_PLATFORM")
-        or get_session_env("HERMES_SESSION_PLATFORM")
+        or os.getenv("HERMES_SESSION_PLATFORM")
     )
     if resolved_platform:
         platform_disabled = (skills_cfg.get("platform_disabled") or {}).get(
@@ -178,7 +177,7 @@ def get_external_skills_dirs() -> List[Path]:
     path.  Only directories that actually exist are returned.  Duplicates and
     paths that resolve to the local ``~/.hermes/skills/`` are silently skipped.
     """
-    config_path = get_config_path()
+    config_path = get_hermes_home() / "config.yaml"
     if not config_path.exists():
         return []
     try:
@@ -200,7 +199,7 @@ def get_external_skills_dirs() -> List[Path]:
     if not isinstance(raw_dirs, list):
         return []
 
-    local_skills = get_skills_dir().resolve()
+    local_skills = (get_hermes_home() / "skills").resolve()
     seen: Set[Path] = set()
     result: List[Path] = []
 
@@ -230,7 +229,7 @@ def get_all_skills_dirs() -> List[Path]:
     The local dir is always first (and always included even if it doesn't exist
     yet — callers handle that).  External dirs follow in config order.
     """
-    dirs = [get_skills_dir()]
+    dirs = [get_hermes_home() / "skills"]
     dirs.extend(get_external_skills_dirs())
     return dirs
 
@@ -384,7 +383,7 @@ def resolve_skill_config_values(
     current values (or the declared default if the key isn't set).
     Path values are expanded via ``os.path.expanduser``.
     """
-    config_path = get_config_path()
+    config_path = get_hermes_home() / "config.yaml"
     config: Dict[str, Any] = {}
     if config_path.exists():
         try:
@@ -441,25 +440,3 @@ def iter_skill_index_files(skills_dir: Path, filename: str):
             matches.append(Path(root) / filename)
     for path in sorted(matches, key=lambda p: str(p.relative_to(skills_dir))):
         yield path
-
-
-# ── Namespace helpers for plugin-provided skills ───────────────────────────
-
-_NAMESPACE_RE = re.compile(r"^[a-zA-Z0-9_-]+$")
-
-
-def parse_qualified_name(name: str) -> Tuple[Optional[str], str]:
-    """Split ``'namespace:skill-name'`` into ``(namespace, bare_name)``.
-
-    Returns ``(None, name)`` when there is no ``':'``.
-    """
-    if ":" not in name:
-        return None, name
-    return tuple(name.split(":", 1))  # type: ignore[return-value]
-
-
-def is_valid_namespace(candidate: Optional[str]) -> bool:
-    """Check whether *candidate* is a valid namespace (``[a-zA-Z0-9_-]+``)."""
-    if not candidate:
-        return False
-    return bool(_NAMESPACE_RE.match(candidate))

agent/smart_model_routing.py

@@ -0,0 +1,194 @@
+"""Helpers for optional cheap-vs-strong model routing."""
+
+from __future__ import annotations
+
+import os
+import re
+from typing import Any, Dict, Optional
+
+from utils import is_truthy_value
+
+_COMPLEX_KEYWORDS = {
+    "debug",
+    "debugging",
+    "implement",
+    "implementation",
+    "refactor",
+    "patch",
+    "traceback",
+    "stacktrace",
+    "exception",
+    "error",
+    "analyze",
+    "analysis",
+    "investigate",
+    "architecture",
+    "design",
+    "compare",
+    "benchmark",
+    "optimize",
+    "optimise",
+    "review",
+    "terminal",
+    "shell",
+    "tool",
+    "tools",
+    "pytest",
+    "test",
+    "tests",
+    "plan",
+    "planning",
+    "delegate",
+    "subagent",
+    "cron",
+    "docker",
+    "kubernetes",
+}
+
+_URL_RE = re.compile(r"https?://|www\.", re.IGNORECASE)
+
+
+def _coerce_bool(value: Any, default: bool = False) -> bool:
+    return is_truthy_value(value, default=default)
+
+
+def _coerce_int(value: Any, default: int) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def choose_cheap_model_route(user_message: str, routing_config: Optional[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
+    """Return the configured cheap-model route when a message looks simple.
+
+    Conservative by design: if the message has signs of code/tool/debugging/
+    long-form work, keep the primary model.
+    """
+    cfg = routing_config or {}
+    if not _coerce_bool(cfg.get("enabled"), False):
+        return None
+
+    cheap_model = cfg.get("cheap_model") or {}
+    if not isinstance(cheap_model, dict):
+        return None
+    provider = str(cheap_model.get("provider") or "").strip().lower()
+    model = str(cheap_model.get("model") or "").strip()
+    if not provider or not model:
+        return None
+
+    text = (user_message or "").strip()
+    if not text:
+        return None
+
+    max_chars = _coerce_int(cfg.get("max_simple_chars"), 160)
+    max_words = _coerce_int(cfg.get("max_simple_words"), 28)
+
+    if len(text) > max_chars:
+        return None
+    if len(text.split()) > max_words:
+        return None
+    if text.count("\n") > 1:
+        return None
+    if "```" in text or "`" in text:
+        return None
+    if _URL_RE.search(text):
+        return None
+
+    lowered = text.lower()
+    words = {token.strip(".,:;!?()[]{}\"'`") for token in lowered.split()}
+    if words & _COMPLEX_KEYWORDS:
+        return None
+
+    route = dict(cheap_model)
+    route["provider"] = provider
+    route["model"] = model
+    route["routing_reason"] = "simple_turn"
+    return route
+
+
+def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any]], primary: Dict[str, Any]) -> Dict[str, Any]:
+    """Resolve the effective model/runtime for one turn.
+
+    Returns a dict with model/runtime/signature/label fields.
+    """
+    route = choose_cheap_model_route(user_message, routing_config)
+    if not route:
+        return {
+            "model": primary.get("model"),
+            "runtime": {
+                "api_key": primary.get("api_key"),
+                "base_url": primary.get("base_url"),
+                "provider": primary.get("provider"),
+                "api_mode": primary.get("api_mode"),
+                "command": primary.get("command"),
+                "args": list(primary.get("args") or []),
+                "credential_pool": primary.get("credential_pool"),
+            },
+            "label": None,
+            "signature": (
+                primary.get("model"),
+                primary.get("provider"),
+                primary.get("base_url"),
+                primary.get("api_mode"),
+                primary.get("command"),
+                tuple(primary.get("args") or ()),
+            ),
+        }
+
+    from hermes_cli.runtime_provider import resolve_runtime_provider
+
+    explicit_api_key = None
+    api_key_env = str(route.get("api_key_env") or "").strip()
+    if api_key_env:
+        explicit_api_key = os.getenv(api_key_env) or None
+
+    try:
+        runtime = resolve_runtime_provider(
+            requested=route.get("provider"),
+            explicit_api_key=explicit_api_key,
+            explicit_base_url=route.get("base_url"),
+        )
+    except Exception:
+        return {
+            "model": primary.get("model"),
+            "runtime": {
+                "api_key": primary.get("api_key"),
+                "base_url": primary.get("base_url"),
+                "provider": primary.get("provider"),
+                "api_mode": primary.get("api_mode"),
+                "command": primary.get("command"),
+                "args": list(primary.get("args") or []),
+                "credential_pool": primary.get("credential_pool"),
+            },
+            "label": None,
+            "signature": (
+                primary.get("model"),
+                primary.get("provider"),
+                primary.get("base_url"),
+                primary.get("api_mode"),
+                primary.get("command"),
+                tuple(primary.get("args") or ()),
+            ),
+        }
+
+    return {
+        "model": route.get("model"),
+        "runtime": {
+            "api_key": runtime.get("api_key"),
+            "base_url": runtime.get("base_url"),
+            "provider": runtime.get("provider"),
+            "api_mode": runtime.get("api_mode"),
+            "command": runtime.get("command"),
+            "args": list(runtime.get("args") or []),
+        },
+        "label": f"smart route → {route.get('model')} ({runtime.get('provider')})",
+        "signature": (
+            route.get("model"),
+            runtime.get("provider"),
+            runtime.get("base_url"),
+            runtime.get("api_mode"),
+            runtime.get("command"),
+            tuple(runtime.get("args") or ()),
+        ),
+    }

agent/title_generator.py

@@ -36,7 +36,7 @@ def generate_title(user_message: str, assistant_response: str, timeout: float =
 
     try:
         response = call_llm(
-            task="title_generation",
+            task="compression",  # reuse compression task config (cheap/fast model)
             messages=messages,
             max_tokens=30,
             temperature=0.3,

agent/transports/__init__.py

@@ -1 +0,0 @@
-"""Transport layer types for provider response normalization."""

agent/transports/types.py

@@ -1,100 +0,0 @@
-"""Shared types for normalized provider responses.
-
-These dataclasses define the canonical shape that all provider adapters
-normalize responses to.  The shared surface is intentionally minimal —
-only fields that every downstream consumer reads are top-level.
-Protocol-specific state goes in ``provider_data`` dicts (response-level
-and per-tool-call) so that protocol-aware code paths can access it
-without polluting the shared type.
-"""
-
-from __future__ import annotations
-
-import json
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-
-@dataclass
-class ToolCall:
-    """A normalized tool call from any provider.
-
-    ``id`` is the protocol's canonical identifier — what gets used in
-    ``tool_call_id`` / ``tool_use_id`` when constructing tool result
-    messages.  May be ``None`` when the provider omits it; the agent
-    fills it via ``_deterministic_call_id()`` before storing in history.
-
-    ``provider_data`` carries per-tool-call protocol metadata that only
-    protocol-aware code reads:
-
-    * Codex: ``{"call_id": "call_XXX", "response_item_id": "fc_XXX"}``
-    * Gemini: ``{"extra_content": {"google": {"thought_signature": "..."}}}``
-    * Others: ``None``
-    """
-
-    id: Optional[str]
-    name: str
-    arguments: str  # JSON string
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-@dataclass
-class Usage:
-    """Token usage from an API response."""
-
-    prompt_tokens: int = 0
-    completion_tokens: int = 0
-    total_tokens: int = 0
-    cached_tokens: int = 0
-
-
-@dataclass
-class NormalizedResponse:
-    """Normalized API response from any provider.
-
-    Shared fields are truly cross-provider — every caller can rely on
-    them without branching on api_mode.  Protocol-specific state goes in
-    ``provider_data`` so that only protocol-aware code paths read it.
-
-    Response-level ``provider_data`` examples:
-
-    * Anthropic: ``{"reasoning_details": [...]}``
-    * Codex: ``{"codex_reasoning_items": [...]}``
-    * Others: ``None``
-    """
-
-    content: Optional[str]
-    tool_calls: Optional[List[ToolCall]]
-    finish_reason: str  # "stop", "tool_calls", "length", "content_filter"
-    reasoning: Optional[str] = None
-    usage: Optional[Usage] = None
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-# ---------------------------------------------------------------------------
-# Factory helpers
-# ---------------------------------------------------------------------------
-
-def build_tool_call(
-    id: Optional[str],
-    name: str,
-    arguments: Any,
-    **provider_fields: Any,
-) -> ToolCall:
-    """Build a ``ToolCall``, auto-serialising *arguments* if it's a dict.
-
-    Any extra keyword arguments are collected into ``provider_data``.
-    """
-    args_str = json.dumps(arguments) if isinstance(arguments, dict) else str(arguments)
-    pd = dict(provider_fields) if provider_fields else None
-    return ToolCall(id=id, name=name, arguments=args_str, provider_data=pd)
-
-
-def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
-    """Translate a provider-specific stop reason to the normalised set.
-
-    Falls back to ``"stop"`` for unknown or ``None`` reasons.
-    """
-    if reason is None:
-        return "stop"
-    return mapping.get(reason, "stop")

agent/usage_pricing.py

@@ -284,80 +284,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://ai.google.dev/pricing",
         pricing_version="google-pricing-2026-03-16",
     ),
-    # AWS Bedrock — pricing per the Bedrock pricing page.
-    # Bedrock charges the same per-token rates as the model provider but
-    # through AWS billing.  These are the on-demand prices (no commitment).
-    # Source: https://aws.amazon.com/bedrock/pricing/
-    (
-        "bedrock",
-        "anthropic.claude-opus-4-6",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("15.00"),
-        output_cost_per_million=Decimal("75.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "anthropic.claude-sonnet-4-6",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("3.00"),
-        output_cost_per_million=Decimal("15.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "anthropic.claude-sonnet-4-5",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("3.00"),
-        output_cost_per_million=Decimal("15.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "anthropic.claude-haiku-4-5",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.80"),
-        output_cost_per_million=Decimal("4.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "amazon.nova-pro",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.80"),
-        output_cost_per_million=Decimal("3.20"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "amazon.nova-lite",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.06"),
-        output_cost_per_million=Decimal("0.24"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "amazon.nova-micro",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.035"),
-        output_cost_per_million=Decimal("0.14"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
 }
 
 
@@ -649,6 +575,25 @@ def has_known_pricing(
     return entry is not None
 
 
+def get_pricing(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> Dict[str, float]:
+    """Backward-compatible thin wrapper for legacy callers.
+
+    Returns only non-cache input/output fields when a pricing entry exists.
+    Unknown routes return zeroes.
+    """
+    entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
+    if not entry:
+        return {"input": 0.0, "output": 0.0}
+    return {
+        "input": float(entry.input_cost_per_million or _ZERO),
+        "output": float(entry.output_cost_per_million or _ZERO),
+    }
+
 
 def format_duration_compact(seconds: float) -> str:
     if seconds < 60:

batch_runner.py

@@ -444,7 +444,6 @@ def _process_batch_worker(args: Tuple) -> Dict[str, Any]:
             if not reasoning.get("has_any_reasoning", True):
                 print(f"   🚫 Prompt {prompt_index} discarded (no reasoning in any turn)")
                 discarded_no_reasoning += 1
-                completed_in_batch.append(prompt_index)
                 continue
             
             # Get and normalize tool stats for consistent schema across all entries
@@ -562,10 +561,7 @@ class BatchRunner:
             provider_sort (str): Sort providers by price/throughput/latency (optional)
             max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
             reasoning_config (Dict): OpenRouter reasoning config override (e.g. {"effort": "none"} to disable thinking)
-            prefill_messages (List[Dict]): Messages to prepend as prefilled conversation context (few-shot priming).
-                NOTE: Anthropic Sonnet 4.6+ and Opus 4.6+ reject a trailing assistant-role prefill
-                (400 error).  For those models use output_config.format or structured-output
-                schemas instead.  Safe here for user-role priming and for older Claude / non-Claude models.
+            prefill_messages (List[Dict]): Messages to prepend as prefilled conversation context (few-shot priming)
             max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
         """
         self.dataset_file = Path(dataset_file)

cli-config.yaml.example

@@ -16,7 +16,7 @@ model:
   #   "nous"         - Nous Portal OAuth (requires: hermes login)
   #   "nous-api"     - Nous Portal API key (requires: NOUS_API_KEY)
   #   "anthropic"    - Direct Anthropic API (requires: ANTHROPIC_API_KEY)
-  #   "openai-codex" - OpenAI Codex (requires: hermes auth)
+  #   "openai-codex" - OpenAI Codex (requires: hermes login --provider openai-codex)
   #   "copilot"      - GitHub Copilot / GitHub Models (requires: GITHUB_TOKEN)
   #   "gemini"      - Use Google AI Studio direct (requires: GOOGLE_API_KEY or GEMINI_API_KEY)
   #   "zai"         - Use z.ai / ZhipuAI GLM models (requires: GLM_API_KEY)
@@ -24,10 +24,6 @@ model:
   #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
   #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
   #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
-  #   "nvidia"       - NVIDIA NIM / build.nvidia.com (requires: NVIDIA_API_KEY)
-  #   "xiaomi"       - Xiaomi MiMo (requires: XIAOMI_API_KEY)
-  #   "arcee"        - Arcee AI Trinity models (requires: ARCEEAI_API_KEY)
-  #   "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)
   #
@@ -39,6 +35,12 @@ model:
   #     base_url: "http://localhost:1234/v1"
   #   No API key needed — local servers typically ignore auth.
   #
+  #   For Ollama Cloud (https://ollama.com/pricing):
+  #     provider: "custom"
+  #     base_url: "https://ollama.com/v1"
+  #   Set OLLAMA_API_KEY in .env — automatically picked up when base_url
+  #   points to ollama.com.
+  #
   # Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
   provider: "auto"
   
@@ -63,38 +65,7 @@ model:
   #   Leave unset to use the model's native output ceiling (recommended).
   #   Set only if you want to deliberately limit individual response length.
   #
-# max_tokens: 8192
-
-# Named provider overrides (optional)
-# Use this for per-provider request timeouts, non-stream stale timeouts,
-# and per-model exceptions.
-# Applies to the primary turn client on every api_mode (OpenAI-wire, native
-# Anthropic, and Anthropic-compatible providers), the fallback chain, and
-# client rebuilds during credential rotation.  For OpenAI-wire chat
-# completions (streaming and non-streaming) the configured value is also
-# used as the per-request ``timeout=`` kwarg so it wins over the legacy
-# HERMES_API_TIMEOUT env var (which still applies when no config is set).
-# ``stale_timeout_seconds`` controls the non-streaming stale-call detector and
-# wins over the legacy HERMES_API_CALL_STALE_TIMEOUT env var. Leaving these
-# unset keeps the legacy defaults (HERMES_API_TIMEOUT=1800s,
-# HERMES_API_CALL_STALE_TIMEOUT=300s, native Anthropic 900s).
-#
-# Not currently wired for AWS Bedrock (bedrock_converse + AnthropicBedrock
-# SDK paths) — those use boto3 with its own timeout configuration.
-#
-# providers:
-#   ollama-local:
-#     request_timeout_seconds: 300   # Longer timeout for local cold-starts
-#     stale_timeout_seconds: 900     # Explicitly re-enable stale detection on local endpoints
-#   anthropic:
-#     request_timeout_seconds: 30    # Fast-fail cloud requests
-#     models:
-#       claude-opus-4.6:
-#         timeout_seconds: 600       # Longer timeout for extended-thinking Opus calls
-#   openai-codex:
-#     models:
-#       gpt-5.4:
-#         stale_timeout_seconds: 1800  # Longer non-stream stale timeout for slow large-context turns
+  # max_tokens: 8192
 
 # =============================================================================
 # OpenRouter Provider Routing (only applies when using OpenRouter)
@@ -122,6 +93,20 @@ model:
 #   # Data policy: "allow" (default) or "deny" to exclude providers that may store data
 #   # data_collection: "deny"
 
+# =============================================================================
+# Smart Model Routing (optional)
+# =============================================================================
+# Use a cheaper model for short/simple turns while keeping your main model for
+# more complex requests. Disabled by default.
+#
+# smart_model_routing:
+#   enabled: true
+#   max_simple_chars: 160
+#   max_simple_words: 28
+#   cheap_model:
+#     provider: openrouter
+#     model: google/gemini-2.5-flash
+
 # =============================================================================
 # Git Worktree Isolation
 # =============================================================================
@@ -323,8 +308,15 @@ compression:
   # compression of older turns.
   protect_last_n: 20
 
-  # To pin a specific model/provider for compression summaries, use the
-  # auxiliary section below (auxiliary.compression.provider / model).
+  # Model to use for generating summaries (fast/cheap recommended)
+  # This model compresses the middle turns into a concise summary.
+  # IMPORTANT: it receives the full middle section of the conversation, so it
+  # MUST support a context length at least as large as your main model's.
+  summary_model: "google/gemini-3-flash-preview"
+  
+  # Provider for the summary model (default: "auto")
+  # Options: "auto", "openrouter", "nous", "main"
+  # summary_provider: "auto"
 
 # =============================================================================
 # Auxiliary Models (Advanced — Experimental)
@@ -350,7 +342,6 @@ compression:
 #   "openrouter" - Force OpenRouter (requires OPENROUTER_API_KEY)
 #   "nous"       - Force Nous Portal (requires: hermes login)
 #   "gemini"      - Force Google AI Studio direct (requires: GOOGLE_API_KEY or GEMINI_API_KEY)
-#   "ollama-cloud" - Ollama Cloud (requires: OLLAMA_API_KEY)
 #   "codex"       - Force Codex OAuth (requires: hermes model → Codex).
 #                  Uses gpt-5.3-codex which supports vision.
 #   "main"       - Use your custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY).
@@ -374,18 +365,6 @@ compression:
 #   web_extract:
 #     provider: "auto"
 #     model: ""
-#
-#   # Session search — summarizes matching past sessions
-#   session_search:
-#     provider: "auto"
-#     model: ""
-#     timeout: 30
-#     max_concurrency: 3    # Limit parallel summaries to reduce request-burst 429s
-#     extra_body: {}        # Provider-specific OpenAI-compatible request fields
-#                           # Example for providers that support request-body
-#                           # reasoning controls:
-#                           # extra_body:
-#                           #   enable_thinking: false
 
 # =============================================================================
 # Persistent Memory
@@ -501,12 +480,6 @@ agent:
   # Fires once per run when inactivity reaches this threshold (seconds).
   # Set to 0 to disable the warning.
   # gateway_timeout_warning: 900
-
-  # Graceful drain timeout for gateway stop/restart (seconds).
-  # The gateway stops accepting new work, waits for in-flight agents to
-  # finish, then interrupts anything still running after this timeout.
-  # 0 = no drain, interrupt immediately.
-  # restart_drain_timeout: 60
   
   # Enable verbose logging
   verbose: false
@@ -549,7 +522,7 @@ 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
+# Supported platform keys: cli, telegram, discord, whatsapp, slack
 #
 # Examples:
 #
@@ -578,7 +551,6 @@ agent:
 #   slack:         hermes-slack          (same as telegram)
 #   signal:        hermes-signal         (same as telegram)
 #   homeassistant: hermes-homeassistant  (same as telegram)
-#   qqbot:            hermes-qqbot            (same as telegram)
 #
 platform_toolsets:
   cli: [hermes-cli]
@@ -588,19 +560,6 @@ platform_toolsets:
   slack: [hermes-slack]
   signal: [hermes-signal]
   homeassistant: [hermes-homeassistant]
-  qqbot: [hermes-qqbot]
-
-# =============================================================================
-# Gateway Platform Settings
-# =============================================================================
-# Optional per-platform messaging settings.
-# Platform-specific knobs live under `extra`.
-#
-# platforms:
-#   telegram:
-#     reply_to_mode: "first"  # off | first | all
-#     extra:
-#       disable_link_previews: false  # Set true to suppress Telegram URL previews in bot messages
 
 # ─────────────────────────────────────────────────────────────────────────────
 # Available toolsets (use these names in platform_toolsets or the toolsets list)
@@ -623,7 +582,7 @@ platform_toolsets:
 #   skills_hub   - skill_hub (search/install/manage from online registries — user-driven only)
 #   moa          - mixture_of_agents  (requires OPENROUTER_API_KEY)
 #   todo         - todo (in-memory task planning, no deps)
-#   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI/MINIMAX/MISTRAL key)
+#   tts          - text_to_speech  (Edge TTS free, or ELEVENLABS/OPENAI/MINIMAX key)
 #   cronjob      - cronjob (create/list/update/pause/resume/run/remove scheduled tasks)
 #   rl           - rl_list_environments, rl_start_training, etc. (requires TINKER_API_KEY)
 #
@@ -652,7 +611,7 @@ platform_toolsets:
 #   todo         - Task planning and tracking for multi-step work
 #   memory       - Persistent memory across sessions (personal notes + user profile)
 #   session_search - Search and recall past conversations (FTS5 + Gemini Flash summarization)
-#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI, MiniMax, Mistral)
+#   tts          - Text-to-speech (Edge TTS free, ElevenLabs, OpenAI, MiniMax)
 #   cronjob      - Schedule and manage automated tasks (CLI-only)
 #   rl           - RL training tools (Tinker-Atropos)
 #
@@ -725,11 +684,7 @@ platform_toolsets:
 stt:
   enabled: true
   # provider: "local"          # auto-detected if omitted
-  local:
-    model: "base"              # tiny | base | small | medium | large-v3 | turbo
-    # language: ""             # auto-detect; set to "en", "es", "fr", etc. to force
-  openai:
-    model: "whisper-1"         # whisper-1 | gpt-4o-mini-transcribe | gpt-4o-transcribe
+  model: "whisper-1"  # whisper-1 (cheapest) | gpt-4o-mini-transcribe | gpt-4o-transcribe
   # mistral:
   #   model: "voxtral-mini-latest"  # voxtral-mini-latest | voxtral-mini-2602
 
@@ -808,11 +763,6 @@ display:
   # Toggle at runtime with /verbose in the CLI
   tool_progress: all
 
-  # 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.
-  interim_assistant_messages: true
-
   # 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
@@ -821,7 +771,7 @@ display:
 
   # Background process notifications (gateway/messaging only).
   # Controls how chatty the process watcher is when you use
-  # terminal(background=true, notify_on_complete=true) from Telegram/Discord/etc.
+  # terminal(background=true, check_interval=...) from Telegram/Discord/etc.
   #   off:     No watcher messages at all
   #   result:  Only the final completion message
   #   error:   Only the final message when exit code != 0

constraints-termux.txt

@@ -1,15 +0,0 @@
-# Termux / Android dependency constraints for Hermes Agent.
-#
-# Usage:
-#   python -m pip install -e '.[termux]' -c constraints-termux.txt
-#
-# These pins keep the tested Android install path stable when upstream packages
-# move faster than Termux-compatible wheels / sdists.
-
-ipython<10
-jedi>=0.18.1,<0.20
-parso>=0.8.4,<0.9
-stack-data>=0.6,<0.7
-pexpect>4.3,<5
-matplotlib-inline>=0.1.7,<0.2
-asttokens>=2.1,<3

cron/jobs.py

@@ -31,7 +31,7 @@ except ImportError:
 # Configuration
 # =============================================================================
 
-HERMES_DIR = get_hermes_home().resolve()
+HERMES_DIR = get_hermes_home()
 CRON_DIR = HERMES_DIR / "cron"
 JOBS_FILE = CRON_DIR / "jobs.json"
 OUTPUT_DIR = CRON_DIR / "output"
@@ -338,12 +338,10 @@ def load_jobs() -> List[Dict[str, Any]]:
                     save_jobs(jobs)
                     logger.warning("Auto-repaired jobs.json (had invalid control characters)")
                 return jobs
-        except Exception as e:
-            logger.error("Failed to auto-repair jobs.json: %s", e)
-            raise RuntimeError(f"Cron database corrupted and unrepairable: {e}") from e
-    except IOError as e:
-        logger.error("IOError reading jobs.json: %s", e)
-        raise RuntimeError(f"Failed to read cron database: {e}") from e
+        except Exception:
+            return []
+    except IOError:
+        return []
 
 
 def save_jobs(jobs: List[Dict[str, Any]]):
@@ -454,7 +452,6 @@ def create_job(
         "last_run_at": None,
         "last_status": None,
         "last_error": None,
-        "last_delivery_error": None,
         # Delivery configuration
         "deliver": deliver,
         "origin": origin,  # Tracks where job was created for "origin" delivery
@@ -501,12 +498,6 @@ def update_job(job_id: str, updates: Dict[str, Any]) -> Optional[Dict[str, Any]]
 
         if schedule_changed:
             updated_schedule = updated["schedule"]
-            # The API may pass schedule as a raw string (e.g. "every 10m")
-            # instead of a pre-parsed dict.  Normalize it the same way
-            # create_job() does so downstream code can call .get() safely.
-            if isinstance(updated_schedule, str):
-                updated_schedule = parse_schedule(updated_schedule)
-                updated["schedule"] = updated_schedule
             updated["schedule_display"] = updates.get(
                 "schedule_display",
                 updated_schedule.get("display", updated.get("schedule_display")),
@@ -629,8 +620,8 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
 
             save_jobs(jobs)
             return
-
-    logger.warning("mark_job_run: job_id %s not found, skipping save", job_id)
+    
+    save_jobs(jobs)
 
 
 def advance_next_run(job_id: str) -> bool:

cron/scheduler.py

@@ -10,7 +10,6 @@ runs at a time if multiple processes overlap.
 
 import asyncio
 import concurrent.futures
-import contextvars
 import json
 import logging
 import os
@@ -27,7 +26,7 @@ except ImportError:
     except ImportError:
         msvcrt = None
 from pathlib import Path
-from typing import List, Optional
+from typing import Optional
 
 # Add parent directory to path for imports BEFORE repo-level imports.
 # Without this, standalone invocations (e.g. after `hermes update` reloads
@@ -45,37 +44,9 @@ logger = logging.getLogger(__name__)
 _KNOWN_DELIVERY_PLATFORMS = frozenset({
     "telegram", "discord", "slack", "whatsapp", "signal",
     "matrix", "mattermost", "homeassistant", "dingtalk", "feishu",
-    "wecom", "wecom_callback", "weixin", "sms", "email", "webhook", "bluebubbles",
-    "qqbot",
+    "wecom", "sms", "email", "webhook", "bluebubbles",
 })
 
-# Platforms that support a configured cron/notification home target, mapped to
-# the environment variable used by gateway setup/runtime config.
-_HOME_TARGET_ENV_VARS = {
-    "matrix": "MATRIX_HOME_ROOM",
-    "telegram": "TELEGRAM_HOME_CHANNEL",
-    "discord": "DISCORD_HOME_CHANNEL",
-    "slack": "SLACK_HOME_CHANNEL",
-    "signal": "SIGNAL_HOME_CHANNEL",
-    "mattermost": "MATTERMOST_HOME_CHANNEL",
-    "sms": "SMS_HOME_CHANNEL",
-    "email": "EMAIL_HOME_ADDRESS",
-    "dingtalk": "DINGTALK_HOME_CHANNEL",
-    "feishu": "FEISHU_HOME_CHANNEL",
-    "wecom": "WECOM_HOME_CHANNEL",
-    "weixin": "WEIXIN_HOME_CHANNEL",
-    "bluebubbles": "BLUEBUBBLES_HOME_CHANNEL",
-    "qqbot": "QQBOT_HOME_CHANNEL",
-}
-
-# Legacy env var names kept for back-compat.  Each entry is the current
-# primary env var → the previous name.  _get_home_target_chat_id falls
-# back to the legacy name if the primary is unset, so users who set the
-# old name before the rename keep working until they migrate.
-_LEGACY_HOME_TARGET_ENV_VARS = {
-    "QQBOT_HOME_CHANNEL": "QQ_HOME_CHANNEL",
-}
-
 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
 
 # Sentinel: when a cron agent has nothing new to report, it can start its
@@ -103,28 +74,15 @@ def _resolve_origin(job: dict) -> Optional[dict]:
     return None
 
 
-def _get_home_target_chat_id(platform_name: str) -> str:
-    """Return the configured home target chat/room ID for a delivery platform."""
-    env_var = _HOME_TARGET_ENV_VARS.get(platform_name.lower())
-    if not env_var:
-        return ""
-    value = os.getenv(env_var, "")
-    if not value:
-        legacy = _LEGACY_HOME_TARGET_ENV_VARS.get(env_var)
-        if legacy:
-            value = os.getenv(legacy, "")
-    return value
-
-
-def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[dict]:
-    """Resolve one concrete auto-delivery target for a cron job."""
-
+def _resolve_delivery_target(job: dict) -> Optional[dict]:
+    """Resolve the concrete auto-delivery target for a cron job, if any."""
+    deliver = job.get("deliver", "local")
     origin = _resolve_origin(job)
 
-    if deliver_value == "local":
+    if deliver == "local":
         return None
 
-    if deliver_value == "origin":
+    if deliver == "origin":
         if origin:
             return {
                 "platform": origin["platform"],
@@ -133,8 +91,8 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
             }
         # Origin missing (e.g. job created via API/script) — try each
         # platform's home channel as a fallback instead of silently dropping.
-        for platform_name in _HOME_TARGET_ENV_VARS:
-            chat_id = _get_home_target_chat_id(platform_name)
+        for platform_name in ("matrix", "telegram", "discord", "slack", "bluebubbles"):
+            chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
             if chat_id:
                 logger.info(
                     "Job '%s' has deliver=origin but no origin; falling back to %s home channel",
@@ -148,8 +106,8 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
                 }
         return None
 
-    if ":" in deliver_value:
-        platform_name, rest = deliver_value.split(":", 1)
+    if ":" in deliver:
+        platform_name, rest = deliver.split(":", 1)
         platform_key = platform_name.lower()
 
         from tools.send_message_tool import _parse_target_ref
@@ -179,7 +137,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
             "thread_id": thread_id,
         }
 
-    platform_name = deliver_value
+    platform_name = deliver
     if origin and origin.get("platform") == platform_name:
         return {
             "platform": platform_name,
@@ -189,7 +147,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
 
     if platform_name.lower() not in _KNOWN_DELIVERY_PLATFORMS:
         return None
-    chat_id = _get_home_target_chat_id(platform_name)
+    chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
     if not chat_id:
         return None
 
@@ -200,30 +158,6 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
     }
 
 
-def _resolve_delivery_targets(job: dict) -> List[dict]:
-    """Resolve all concrete auto-delivery targets for a cron job (supports comma-separated deliver)."""
-    deliver = job.get("deliver", "local")
-    if deliver == "local":
-        return []
-    parts = [p.strip() for p in str(deliver).split(",") if p.strip()]
-    seen = set()
-    targets = []
-    for part in parts:
-        target = _resolve_single_delivery_target(job, part)
-        if target:
-            key = (target["platform"].lower(), str(target["chat_id"]), target.get("thread_id"))
-            if key not in seen:
-                seen.add(key)
-                targets.append(target)
-    return targets
-
-
-def _resolve_delivery_target(job: dict) -> Optional[dict]:
-    """Resolve the concrete auto-delivery target for a cron job, if any."""
-    targets = _resolve_delivery_targets(job)
-    return targets[0] if targets else None
-
-
 # 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'})
@@ -264,7 +198,7 @@ def _send_media_via_adapter(adapter, chat_id: str, media_files: list, metadata:
 
 def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Optional[str]:
     """
-    Deliver job output to the configured target(s) (origin chat, specific platform, etc.).
+    Deliver job output to the configured target (origin chat, specific platform, etc.).
 
     When ``adapters`` and ``loop`` are provided (gateway is running), tries to
     use the live adapter first — this supports E2EE rooms (e.g. Matrix) where
@@ -273,14 +207,18 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
 
     Returns None on success, or an error string on failure.
     """
-    targets = _resolve_delivery_targets(job)
-    if not targets:
+    target = _resolve_delivery_target(job)
+    if not target:
         if job.get("deliver", "local") != "local":
             msg = f"no delivery target resolved for deliver={job.get('deliver', 'local')}"
             logger.warning("Job '%s': %s", job["id"], msg)
             return msg
         return None  # local-only jobs don't deliver — not a failure
 
+    platform_name = target["platform"]
+    chat_id = target["chat_id"]
+    thread_id = target.get("thread_id")
+
     from tools.send_message_tool import _send_to_platform
     from gateway.config import load_gateway_config, Platform
 
@@ -296,13 +234,28 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
         "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,
     }
+    platform = platform_map.get(platform_name.lower())
+    if not platform:
+        msg = f"unknown platform '{platform_name}'"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg
+
+    try:
+        config = load_gateway_config()
+    except Exception as e:
+        msg = f"failed to load gateway config: {e}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
+
+    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)
+        return msg
 
     # 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
@@ -316,13 +269,11 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
 
     if wrap_response:
         task_name = job.get("name", job["id"])
-        job_id = job.get("id", "")
         delivery_content = (
             f"Cronjob Response: {task_name}\n"
-            f"(job_id: {job_id})\n"
             f"-------------\n\n"
             f"{content}\n\n"
-            f"To stop or manage this job, send me a new message (e.g. \"stop reminder {task_name}\")."
+            f"Note: The agent cannot see this message, and therefore cannot respond to it."
         )
     else:
         delivery_content = content
@@ -331,156 +282,71 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     from gateway.platforms.base import BasePlatformAdapter
     media_files, cleaned_delivery_content = BasePlatformAdapter.extract_media(delivery_content)
 
+    # 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)
+    if runtime_adapter is not None and loop is not None and getattr(loop, "is_running", lambda: False)():
+        send_metadata = {"thread_id": thread_id} if thread_id else None
+        try:
+            # Send cleaned text (MEDIA tags stripped) — not the raw content
+            text_to_send = cleaned_delivery_content.strip()
+            adapter_ok = True
+            if text_to_send:
+                future = asyncio.run_coroutine_threadsafe(
+                    runtime_adapter.send(chat_id, text_to_send, metadata=send_metadata),
+                    loop,
+                )
+                send_result = future.result(timeout=60)
+                if send_result and not getattr(send_result, "success", True):
+                    err = getattr(send_result, "error", "unknown")
+                    logger.warning(
+                        "Job '%s': live adapter send to %s:%s failed (%s), falling back to standalone",
+                        job["id"], platform_name, chat_id, err,
+                    )
+                    adapter_ok = False  # fall through to standalone path
+
+            # 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)
+
+            if adapter_ok:
+                logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
+                return None
+        except Exception as e:
+            logger.warning(
+                "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
+                job["id"], platform_name, chat_id, e,
+            )
+
+    # 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:
-        config = load_gateway_config()
+        result = asyncio.run(coro)
+    except RuntimeError:
+        # asyncio.run() checks for a running loop before awaiting the coroutine;
+        # when it raises, the original coro was never started — close it to
+        # prevent "coroutine was never awaited" RuntimeWarning, then retry in a
+        # fresh thread that has no running loop.
+        coro.close()
+        import concurrent.futures
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files))
+            result = future.result(timeout=30)
     except Exception as e:
-        msg = f"failed to load gateway config: {e}"
+        msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
         logger.error("Job '%s': %s", job["id"], msg)
         return msg
 
-    delivery_errors = []
+    if result and result.get("error"):
+        msg = f"delivery error: {result['error']}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
 
-    for target in targets:
-        platform_name = target["platform"]
-        chat_id = target["chat_id"]
-        thread_id = target.get("thread_id")
-
-        # Diagnostic: log thread_id for topic-aware delivery debugging
-        origin = job.get("origin") or {}
-        origin_thread = origin.get("thread_id")
-        if origin_thread and not thread_id:
-            logger.warning(
-                "Job '%s': origin has thread_id=%s but delivery target lost it "
-                "(deliver=%s, target=%s)",
-                job["id"], origin_thread, job.get("deliver", "local"), target,
-            )
-        elif thread_id:
-            logger.debug(
-                "Job '%s': delivering to %s:%s thread_id=%s",
-                job["id"], platform_name, chat_id, thread_id,
-            )
-
-        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
-
-        # 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)
-        delivered = False
-        if runtime_adapter is not None and loop is not None and getattr(loop, "is_running", lambda: False)():
-            send_metadata = {"thread_id": thread_id} if thread_id else None
-            try:
-                # Send cleaned text (MEDIA tags stripped) — not the raw content
-                text_to_send = cleaned_delivery_content.strip()
-                adapter_ok = True
-                if text_to_send:
-                    future = asyncio.run_coroutine_threadsafe(
-                        runtime_adapter.send(chat_id, text_to_send, metadata=send_metadata),
-                        loop,
-                    )
-                    send_result = future.result(timeout=60)
-                    if send_result and not getattr(send_result, "success", True):
-                        err = getattr(send_result, "error", "unknown")
-                        logger.warning(
-                            "Job '%s': live adapter send to %s:%s failed (%s), falling back to standalone",
-                            job["id"], platform_name, chat_id, err,
-                        )
-                        adapter_ok = False  # fall through to standalone path
-
-                # 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)
-
-                if adapter_ok:
-                    logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
-                    delivered = True
-            except Exception as e:
-                logger.warning(
-                    "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
-                    job["id"], platform_name, chat_id, e,
-                )
-
-        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:
-                result = asyncio.run(coro)
-            except RuntimeError:
-                # asyncio.run() checks for a running loop before awaiting the coroutine;
-                # when it raises, the original coro was never started — close it to
-                # prevent "coroutine was never awaited" RuntimeWarning, then retry in a
-                # fresh thread that has no running loop.
-                coro.close()
-                import concurrent.futures
-                with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-                    future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files))
-                    result = future.result(timeout=30)
-            except Exception as e:
-                msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
-                logger.error("Job '%s': %s", job["id"], msg)
-                delivery_errors.append(msg)
-                continue
-
-            if result and result.get("error"):
-                msg = f"delivery error: {result['error']}"
-                logger.error("Job '%s': %s", job["id"], msg)
-                delivery_errors.append(msg)
-                continue
-
-            logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
-
-    if delivery_errors:
-        return "; ".join(delivery_errors)
+    logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
     return None
 
 
-_DEFAULT_SCRIPT_TIMEOUT = 120  # seconds
-# Backward-compatible module override used by tests and emergency monkeypatches.
-_SCRIPT_TIMEOUT = _DEFAULT_SCRIPT_TIMEOUT
-
-
-def _get_script_timeout() -> int:
-    """Resolve cron pre-run script timeout from module/env/config with a safe default."""
-    if _SCRIPT_TIMEOUT != _DEFAULT_SCRIPT_TIMEOUT:
-        try:
-            timeout = int(float(_SCRIPT_TIMEOUT))
-            if timeout > 0:
-                return timeout
-        except Exception:
-            logger.warning("Invalid patched _SCRIPT_TIMEOUT=%r; using env/config/default", _SCRIPT_TIMEOUT)
-
-    env_value = os.getenv("HERMES_CRON_SCRIPT_TIMEOUT", "").strip()
-    if env_value:
-        try:
-            timeout = int(float(env_value))
-            if timeout > 0:
-                return timeout
-        except Exception:
-            logger.warning("Invalid HERMES_CRON_SCRIPT_TIMEOUT=%r; using config/default", env_value)
-
-    try:
-        cfg = load_config() or {}
-        cron_cfg = cfg.get("cron", {}) if isinstance(cfg, dict) else {}
-        configured = cron_cfg.get("script_timeout_seconds")
-        if configured is not None:
-            timeout = int(float(configured))
-            if timeout > 0:
-                return timeout
-    except Exception as exc:
-        logger.debug("Failed to load cron script timeout from config: %s", exc)
-
-    return _DEFAULT_SCRIPT_TIMEOUT
+_SCRIPT_TIMEOUT = 120  # seconds
 
 
 def _run_job_script(script_path: str) -> tuple[bool, str]:
@@ -527,27 +393,17 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
     if not path.is_file():
         return False, f"Script path is not a file: {path}"
 
-    script_timeout = _get_script_timeout()
-
     try:
         result = subprocess.run(
             [sys.executable, str(path)],
             capture_output=True,
             text=True,
-            timeout=script_timeout,
+            timeout=_SCRIPT_TIMEOUT,
             cwd=str(path.parent),
         )
         stdout = (result.stdout or "").strip()
         stderr = (result.stderr or "").strip()
 
-        # Redact secrets from both stdout and stderr before any return path.
-        try:
-            from agent.redact import redact_sensitive_text
-            stdout = redact_sensitive_text(stdout)
-            stderr = redact_sensitive_text(stderr)
-        except Exception:
-            pass
-
         if result.returncode != 0:
             parts = [f"Script exited with code {result.returncode}"]
             if stderr:
@@ -556,61 +412,30 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
                 parts.append(f"stdout:\n{stdout}")
             return False, "\n".join(parts)
 
+        # Redact any secrets that may appear in script output before
+        # they are injected into the LLM prompt context.
+        try:
+            from agent.redact import redact_sensitive_text
+            stdout = redact_sensitive_text(stdout)
+        except Exception:
+            pass
         return True, stdout
 
     except subprocess.TimeoutExpired:
-        return False, f"Script timed out after {script_timeout}s: {path}"
+        return False, f"Script timed out after {_SCRIPT_TIMEOUT}s: {path}"
     except Exception as exc:
         return False, f"Script execution failed: {exc}"
 
 
-def _parse_wake_gate(script_output: str) -> bool:
-    """Parse the last non-empty stdout line of a cron job's pre-check script
-    as a wake gate.
-
-    The convention (ported from nanoclaw #1232): if the last stdout line is
-    JSON like ``{"wakeAgent": false}``, the agent is skipped entirely — no
-    LLM run, no delivery. Any other output (non-JSON, missing flag, gate
-    absent, or ``wakeAgent: true``) means wake the agent normally.
-
-    Returns True if the agent should wake, False to skip.
-    """
-    if not script_output:
-        return True
-    stripped_lines = [line for line in script_output.splitlines() if line.strip()]
-    if not stripped_lines:
-        return True
-    last_line = stripped_lines[-1].strip()
-    try:
-        gate = json.loads(last_line)
-    except (json.JSONDecodeError, ValueError):
-        return True
-    if not isinstance(gate, dict):
-        return True
-    return gate.get("wakeAgent", True) is not False
-
-
-def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
-    """Build the effective prompt for a cron job, optionally loading one or more skills first.
-
-    Args:
-        job: The cron job dict.
-        prerun_script: Optional ``(success, stdout)`` from a script that has
-            already been executed by the caller (e.g. for a wake-gate check).
-            When provided, the script is not re-executed and the cached
-            result is used for prompt injection. When omitted, the script
-            (if any) runs inline as before.
-    """
+def _build_job_prompt(job: dict) -> str:
+    """Build the effective prompt for a cron job, optionally loading one or more skills first."""
     prompt = job.get("prompt", "")
     skills = job.get("skills")
 
     # Run data-collection script if configured, inject output as context.
     script_path = job.get("script")
     if script_path:
-        if prerun_script is not None:
-            success, script_output = prerun_script
-        else:
-            success, script_output = _run_job_script(script_path)
+        success, script_output = _run_job_script(script_path)
         if success:
             if script_output:
                 prompt = (
@@ -712,41 +537,13 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
     
     job_id = job["id"]
     job_name = job["name"]
-
-    # Wake-gate: if this job has a pre-check script, run it BEFORE building
-    # the prompt so a ``{"wakeAgent": false}`` response can short-circuit
-    # the whole agent run. We pass the result into _build_job_prompt so
-    # the script is only executed once.
-    prerun_script = None
-    script_path = job.get("script")
-    if script_path:
-        prerun_script = _run_job_script(script_path)
-        _ran_ok, _script_output = prerun_script
-        if _ran_ok and not _parse_wake_gate(_script_output):
-            logger.info(
-                "Job '%s' (ID: %s): wakeAgent=false, skipping agent run",
-                job_name, job_id,
-            )
-            silent_doc = (
-                f"# Cron Job: {job_name}\n\n"
-                f"**Job ID:** {job_id}\n"
-                f"**Run Time:** {_hermes_now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
-                "Script gate returned `wakeAgent=false` — agent skipped.\n"
-            )
-            return True, silent_doc, SILENT_MARKER, None
-
-    prompt = _build_job_prompt(job, prerun_script=prerun_script)
+    prompt = _build_job_prompt(job)
     origin = _resolve_origin(job)
     _cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"
 
     logger.info("Running job '%s' (ID: %s)", job_name, job_id)
     logger.info("Prompt: %s", prompt[:100])
 
-    # 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.
-    os.environ["HERMES_CRON_SESSION"] = "1"
-
     try:
         # Inject origin context so the agent's send_message tool knows the chat.
         # Must be INSIDE the try block so the finally cleanup always runs.
@@ -789,15 +586,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         except Exception as e:
             logger.warning("Job '%s': failed to load config.yaml, using defaults: %s", job_id, e)
 
-        # Apply IPv4 preference if configured.
-        try:
-            from hermes_constants import apply_ipv4_preference
-            _net_cfg = _cfg.get("network", {})
-            if isinstance(_net_cfg, dict) and _net_cfg.get("force_ipv4"):
-                apply_ipv4_preference(force=True)
-        except Exception:
-            pass
-
         # Reasoning config from config.yaml
         from hermes_constants import parse_reasoning_effort
         effort = str(_cfg.get("agent", {}).get("reasoning_effort", "")).strip()
@@ -826,6 +614,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
 
         # Provider routing
         pr = _cfg.get("provider_routing", {})
+        smart_routing = _cfg.get("smart_model_routing", {}) or {}
 
         from hermes_cli.runtime_provider import (
             resolve_runtime_provider,
@@ -842,44 +631,38 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             message = format_runtime_provider_error(exc)
             raise RuntimeError(message) from exc
 
-        fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
-        credential_pool = None
-        runtime_provider = str(runtime.get("provider") or "").strip().lower()
-        if runtime_provider:
-            try:
-                from agent.credential_pool import load_pool
-                pool = load_pool(runtime_provider)
-                if pool.has_credentials():
-                    credential_pool = pool
-                    logger.info(
-                        "Job '%s': loaded credential pool for provider %s with %d entries",
-                        job_id,
-                        runtime_provider,
-                        len(pool.entries()),
-                    )
-            except Exception as e:
-                logger.debug("Job '%s': failed to load credential pool for %s: %s", job_id, runtime_provider, e)
+        from agent.smart_model_routing import resolve_turn_route
+        turn_route = resolve_turn_route(
+            prompt,
+            smart_routing,
+            {
+                "model": model,
+                "api_key": runtime.get("api_key"),
+                "base_url": runtime.get("base_url"),
+                "provider": runtime.get("provider"),
+                "api_mode": runtime.get("api_mode"),
+                "command": runtime.get("command"),
+                "args": list(runtime.get("args") or []),
+            },
+        )
 
         agent = AIAgent(
-            model=model,
-            api_key=runtime.get("api_key"),
-            base_url=runtime.get("base_url"),
-            provider=runtime.get("provider"),
-            api_mode=runtime.get("api_mode"),
-            acp_command=runtime.get("command"),
-            acp_args=runtime.get("args"),
+            model=turn_route["model"],
+            api_key=turn_route["runtime"].get("api_key"),
+            base_url=turn_route["runtime"].get("base_url"),
+            provider=turn_route["runtime"].get("provider"),
+            api_mode=turn_route["runtime"].get("api_mode"),
+            acp_command=turn_route["runtime"].get("command"),
+            acp_args=turn_route["runtime"].get("args"),
             max_iterations=max_iterations,
             reasoning_config=reasoning_config,
             prefill_messages=prefill_messages,
-            fallback_model=fallback_model,
-            credential_pool=credential_pool,
             providers_allowed=pr.get("only"),
             providers_ignored=pr.get("ignore"),
             providers_order=pr.get("order"),
             provider_sort=pr.get("sort"),
             disabled_toolsets=["cronjob", "messaging", "clarify"],
             quiet_mode=True,
-            skip_context_files=True,  # Don't inject SOUL.md/AGENTS.md from scheduler cwd
             skip_memory=True,  # Cron system prompts would corrupt user representations
             platform="cron",
             session_id=_cron_session_id,
@@ -898,11 +681,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
         _cron_inactivity_limit = _cron_timeout if _cron_timeout > 0 else None
         _POLL_INTERVAL = 5.0
         _cron_pool = concurrent.futures.ThreadPoolExecutor(max_workers=1)
-        # Preserve scheduler-scoped ContextVar state (for example skill-declared
-        # env passthrough registrations) when the cron run hops into the worker
-        # thread used for inactivity timeout monitoring.
-        _cron_context = contextvars.copy_context()
-        _cron_future = _cron_pool.submit(_cron_context.run, agent.run_conversation, prompt)
+        _cron_future = _cron_pool.submit(agent.run_conversation, prompt)
         _inactivity_timeout = False
         try:
             if _cron_inactivity_limit is None:
@@ -932,7 +711,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             _cron_pool.shutdown(wait=False, cancel_futures=True)
             raise
         finally:
-            _cron_pool.shutdown(wait=False, cancel_futures=True)
+            _cron_pool.shutdown(wait=False)
 
         if _inactivity_timeout:
             # Build diagnostic summary from the agent's activity tracker.
@@ -964,9 +743,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             )
 
         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)":
-            final_response = ""
         # Use a separate variable for log display; keep final_response clean
         # for delivery logic (empty response = no delivery).
         logged_response = final_response if final_response else "(No response generated)"
@@ -1106,13 +882,6 @@ def tick(verbose: bool = True, adapters=None, loop=None) -> int:
                         delivery_error = str(de)
                         logger.error("Delivery failed for job %s: %s", job["id"], de)
 
-                # Treat empty final_response as a soft failure so last_status
-                # is not "ok" — the agent ran but produced nothing useful.
-                # (issue #8585)
-                if success and not final_response:
-                    success = False
-                    error = "Agent completed but produced empty response (model error, timeout, or misconfiguration)"
-
                 mark_job_run(job["id"], success, error, delivery_error=delivery_error)
                 executed += 1
 

docker/entrypoint.sh

@@ -1,52 +1,15 @@
 #!/bin/bash
-# Docker/Podman entrypoint: bootstrap config files into the mounted volume, then run hermes.
+# Docker entrypoint: bootstrap config files into the mounted volume, then run hermes.
 set -e
 
-HERMES_HOME="${HERMES_HOME:-/opt/data}"
+HERMES_HOME="/opt/data"
 INSTALL_DIR="/opt/hermes"
 
-# --- Privilege dropping via gosu ---
-# When started as root (the default for Docker, or fakeroot in rootless Podman),
-# optionally remap the hermes user/group to match host-side ownership, fix volume
-# permissions, then re-exec as hermes.
-if [ "$(id -u)" = "0" ]; then
-    if [ -n "$HERMES_UID" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
-        echo "Changing hermes UID to $HERMES_UID"
-        usermod -u "$HERMES_UID" hermes
-    fi
-
-    if [ -n "$HERMES_GID" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
-        echo "Changing hermes GID to $HERMES_GID"
-        # -o allows non-unique GID (e.g. macOS GID 20 "staff" may already exist
-        # as "dialout" in the Debian-based container image)
-        groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
-    fi
-
-    actual_hermes_uid=$(id -u hermes)
-    if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$actual_hermes_uid" ]; then
-        echo "$HERMES_HOME is not owned by $actual_hermes_uid, fixing"
-        # In rootless Podman the container's "root" is mapped to an unprivileged
-        # host UID — chown will fail.  That's fine: the volume is already owned
-        # by the mapped user on the host side.
-        chown -R hermes:hermes "$HERMES_HOME" 2>/dev/null || \
-            echo "Warning: chown failed (rootless container?) — continuing anyway"
-    fi
-
-    echo "Dropping root privileges"
-    exec gosu hermes "$0" "$@"
-fi
-
-# --- Running as hermes from here ---
-source "${INSTALL_DIR}/.venv/bin/activate"
-
 # Create essential directory structure.  Cache and platform directories
 # (cache/images, cache/audio, platforms/whatsapp, etc.) are created on
 # demand by the application — don't pre-create them here so new installs
 # get the consolidated layout from get_hermes_dir().
-# The "home/" subdirectory is a per-profile HOME for subprocesses (git,
-# ssh, gh, npm …).  Without it those tools write to /root which is
-# ephemeral and shared across profiles.  See issue #4426.
-mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills,skins,plans,workspace,home}
+mkdir -p "$HERMES_HOME"/{cron,sessions,logs,hooks,memories,skills}
 
 # .env
 if [ ! -f "$HERMES_HOME/.env" ]; then

docs/acp-setup.md

@@ -0,0 +1,228 @@
+# Hermes Agent — ACP (Agent Client Protocol) Setup Guide
+
+Hermes Agent supports the **Agent Client Protocol (ACP)**, allowing it to run as
+a coding agent inside your editor. ACP lets your IDE send tasks to Hermes, and
+Hermes responds with file edits, terminal commands, and explanations — all shown
+natively in the editor UI.
+
+---
+
+## Prerequisites
+
+- Hermes Agent installed and configured (`hermes setup` completed)
+- An API key / provider set up in `~/.hermes/.env` or via `hermes login`
+- Python 3.11+
+
+Install the ACP extra:
+
+```bash
+pip install -e ".[acp]"
+```
+
+---
+
+## VS Code Setup
+
+### 1. Install the ACP Client extension
+
+Open VS Code and install **ACP Client** from the marketplace:
+
+- Press `Ctrl+Shift+X` (or `Cmd+Shift+X` on macOS)
+- Search for **"ACP Client"**
+- Click **Install**
+
+Or install from the command line:
+
+```bash
+code --install-extension anysphere.acp-client
+```
+
+### 2. Configure settings.json
+
+Open your VS Code settings (`Ctrl+,` → click the `{}` icon for JSON) and add:
+
+```json
+{
+  "acpClient.agents": [
+    {
+      "name": "hermes-agent",
+      "registryDir": "/path/to/hermes-agent/acp_registry"
+    }
+  ]
+}
+```
+
+Replace `/path/to/hermes-agent` with the actual path to your Hermes Agent
+installation (e.g. `~/.hermes/hermes-agent`).
+
+Alternatively, if `hermes` is on your PATH, the ACP Client can discover it
+automatically via the registry directory.
+
+### 3. Restart VS Code
+
+After configuring, restart VS Code. You should see **Hermes Agent** appear in
+the ACP agent picker in the chat/agent panel.
+
+---
+
+## Zed Setup
+
+Zed has built-in ACP support.
+
+### 1. Configure Zed settings
+
+Open Zed settings (`Cmd+,` on macOS or `Ctrl+,` on Linux) and add to your
+`settings.json`:
+
+```json
+{
+  "agent_servers": {
+    "hermes-agent": {
+      "type": "custom",
+      "command": "hermes",
+      "args": ["acp"],
+    },
+  },
+}
+```
+
+### 2. Restart Zed
+
+Hermes Agent will appear in the agent panel. Select it and start a conversation.
+
+---
+
+## JetBrains Setup (IntelliJ, PyCharm, WebStorm, etc.)
+
+### 1. Install the ACP plugin
+
+- Open **Settings** → **Plugins** → **Marketplace**
+- Search for **"ACP"** or **"Agent Client Protocol"**
+- Install and restart the IDE
+
+### 2. Configure the agent
+
+- Open **Settings** → **Tools** → **ACP Agents**
+- Click **+** to add a new agent
+- Set the registry directory to your `acp_registry/` folder:
+  `/path/to/hermes-agent/acp_registry`
+- Click **OK**
+
+### 3. Use the agent
+
+Open the ACP panel (usually in the right sidebar) and select **Hermes Agent**.
+
+---
+
+## What You Will See
+
+Once connected, your editor provides a native interface to Hermes Agent:
+
+### Chat Panel
+A conversational interface where you can describe tasks, ask questions, and
+give instructions. Hermes responds with explanations and actions.
+
+### File Diffs
+When Hermes edits files, you see standard diffs in the editor. You can:
+- **Accept** individual changes
+- **Reject** changes you don't want
+- **Review** the full diff before applying
+
+### Terminal Commands
+When Hermes needs to run shell commands (builds, tests, installs), the editor
+shows them in an integrated terminal. Depending on your settings:
+- Commands may run automatically
+- Or you may be prompted to **approve** each command
+
+### Approval Flow
+For potentially destructive operations, the editor will prompt you for
+approval before Hermes proceeds. This includes:
+- File deletions
+- Shell commands
+- Git operations
+
+---
+
+## Configuration
+
+Hermes Agent under ACP uses the **same configuration** as the CLI:
+
+- **API keys / providers**: `~/.hermes/.env`
+- **Agent config**: `~/.hermes/config.yaml`
+- **Skills**: `~/.hermes/skills/`
+- **Sessions**: `~/.hermes/state.db`
+
+You can run `hermes setup` to configure providers, or edit `~/.hermes/.env`
+directly.
+
+### Changing the model
+
+Edit `~/.hermes/config.yaml`:
+
+```yaml
+model: openrouter/nous/hermes-3-llama-3.1-70b
+```
+
+Or set the `HERMES_MODEL` environment variable.
+
+### Toolsets
+
+ACP sessions use the curated `hermes-acp` toolset by default. It is designed for editor workflows and intentionally excludes things like messaging delivery, cronjob management, and audio-first UX features.
+
+---
+
+## Troubleshooting
+
+### Agent doesn't appear in the editor
+
+1. **Check the registry path** — make sure the `acp_registry/` directory path
+   in your editor settings is correct and contains `agent.json`.
+2. **Check `hermes` is on PATH** — run `which hermes` in a terminal. If not
+   found, you may need to activate your virtualenv or add it to PATH.
+3. **Restart the editor** after changing settings.
+
+### Agent starts but errors immediately
+
+1. Run `hermes doctor` to check your configuration.
+2. Check that you have a valid API key: `hermes status`
+3. Try running `hermes acp` directly in a terminal to see error output.
+
+### "Module not found" errors
+
+Make sure you installed the ACP extra:
+
+```bash
+pip install -e ".[acp]"
+```
+
+### Slow responses
+
+- ACP streams responses, so you should see incremental output. If the agent
+  appears stuck, check your network connection and API provider status.
+- Some providers have rate limits. Try switching to a different model/provider.
+
+### Permission denied for terminal commands
+
+If the editor blocks terminal commands, check your ACP Client extension
+settings for auto-approval or manual-approval preferences.
+
+### Logs
+
+Hermes logs are written to stderr when running in ACP mode. Check:
+- VS Code: **Output** panel → select **ACP Client** or **Hermes Agent**
+- Zed: **View** → **Toggle Terminal** and check the process output
+- JetBrains: **Event Log** or the ACP tool window
+
+You can also enable verbose logging:
+
+```bash
+HERMES_LOG_LEVEL=DEBUG hermes acp
+```
+
+---
+
+## Further Reading
+
+- [ACP Specification](https://github.com/anysphere/acp)
+- [Hermes Agent Documentation](https://github.com/NousResearch/hermes-agent)
+- Run `hermes --help` for all CLI options

docs/honcho-integration-spec.html

@@ -0,0 +1,698 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>honcho-integration-spec</title>
+<style>
+  :root {
+    --bg:             #0b0e14;
+    --bg-surface:     #11151c;
+    --bg-elevated:    #181d27;
+    --bg-code:        #0d1018;
+    --fg:             #c9d1d9;
+    --fg-bright:      #e6edf3;
+    --fg-muted:       #6e7681;
+    --fg-subtle:      #484f58;
+    --accent:         #7eb8f6;
+    --accent-dim:     #3d6ea5;
+    --accent-glow:    rgba(126, 184, 246, 0.08);
+    --green:          #7ee6a8;
+    --green-dim:      #2ea04f;
+    --orange:         #e6a855;
+    --red:            #f47067;
+    --purple:         #bc8cff;
+    --cyan:           #56d4dd;
+    --border:         #21262d;
+    --border-subtle:  #161b22;
+    --radius:         6px;
+    --font-sans:      'New York', ui-serif, 'Iowan Old Style', 'Apple Garamond', Baskerville, 'Times New Roman', 'Noto Emoji', serif;
+    --font-mono:      'Departure Mono', 'Noto Emoji', monospace;
+  }
+
+  *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
+  html { scroll-behavior: smooth; scroll-padding-top: 2rem; }
+  body {
+    font-family: var(--font-sans);
+    background: var(--bg);
+    color: var(--fg);
+    line-height: 1.7;
+    font-size: 15px;
+    -webkit-font-smoothing: antialiased;
+  }
+
+  .container { max-width: 860px; margin: 0 auto; padding: 3rem 2rem 6rem; }
+
+  .hero {
+    text-align: center;
+    padding: 4rem 0 3rem;
+    border-bottom: 1px solid var(--border);
+    margin-bottom: 3rem;
+  }
+  .hero h1 { font-family: var(--font-mono); font-size: 2.2rem; font-weight: 700; color: var(--fg-bright); letter-spacing: -0.03em; margin-bottom: 0.5rem; }
+  .hero h1 span { color: var(--accent); }
+  .hero .subtitle { font-family: var(--font-sans); color: var(--fg-muted); font-size: 0.92rem; max-width: 560px; margin: 0 auto; line-height: 1.6; }
+  .hero .meta { margin-top: 1.5rem; display: flex; justify-content: center; gap: 1.5rem; flex-wrap: wrap; }
+  .hero .meta span { font-size: 0.8rem; color: var(--fg-subtle); font-family: var(--font-mono); }
+
+  .toc { background: var(--bg-surface); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.5rem 2rem; margin-bottom: 3rem; }
+  .toc h2 { font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.1em; color: var(--fg-muted); margin-bottom: 1rem; }
+  .toc ol { list-style: none; counter-reset: toc; columns: 2; column-gap: 2rem; }
+  .toc li { counter-increment: toc; break-inside: avoid; margin-bottom: 0.35rem; }
+  .toc li::before { content: counter(toc, decimal-leading-zero) " "; color: var(--fg-subtle); font-family: var(--font-mono); font-size: 0.75rem; margin-right: 0.25rem; }
+  .toc a { font-family: var(--font-mono); color: var(--fg); text-decoration: none; font-size: 0.82rem; transition: color 0.15s; }
+  .toc a:hover { color: var(--accent); }
+
+  section { margin-bottom: 4rem; }
+  section + section { padding-top: 1rem; }
+
+  h2 { font-family: var(--font-mono); font-size: 1.3rem; font-weight: 700; color: var(--fg-bright); letter-spacing: -0.01em; margin-bottom: 1.25rem; padding-bottom: 0.5rem; border-bottom: 1px solid var(--border); }
+  h3 { font-family: var(--font-mono); font-size: 1rem; font-weight: 600; color: var(--fg-bright); margin-top: 2rem; margin-bottom: 0.75rem; }
+  h4 { font-family: var(--font-mono); font-size: 0.9rem; font-weight: 600; color: var(--accent); margin-top: 1.5rem; margin-bottom: 0.5rem; }
+
+  p { margin-bottom: 1rem; font-size: 0.95rem; line-height: 1.75; }
+  strong { color: var(--fg-bright); font-weight: 600; }
+  a { color: var(--accent); text-decoration: none; }
+  a:hover { text-decoration: underline; }
+
+  ul, ol { margin-bottom: 1rem; padding-left: 1.5rem; font-size: 0.93rem; line-height: 1.7; }
+  li { margin-bottom: 0.35rem; }
+  li::marker { color: var(--fg-subtle); }
+
+  .table-wrap { overflow-x: auto; margin-bottom: 1.5rem; }
+  table { width: 100%; border-collapse: collapse; font-size: 0.88rem; }
+  th, td { text-align: left; padding: 0.6rem 1rem; border-bottom: 1px solid var(--border-subtle); }
+  th { font-family: var(--font-mono); font-size: 0.72rem; text-transform: uppercase; letter-spacing: 0.06em; color: var(--fg-muted); background: var(--bg-surface); border-bottom-color: var(--border); white-space: nowrap; }
+  td { font-family: var(--font-sans); font-size: 0.88rem; color: var(--fg); }
+  tr:hover td { background: var(--accent-glow); }
+  td code { background: var(--bg-elevated); padding: 0.15em 0.4em; border-radius: 3px; font-family: var(--font-mono); font-size: 0.82em; color: var(--cyan); }
+
+  pre { background: var(--bg-code); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.25rem 1.5rem; overflow-x: auto; margin-bottom: 1.5rem; font-family: var(--font-mono); font-size: 0.82rem; line-height: 1.65; color: var(--fg); }
+  pre code { background: none; padding: 0; color: inherit; font-size: inherit; }
+  code { font-family: var(--font-mono); font-size: 0.85em; }
+  p code, li code { background: var(--bg-elevated); padding: 0.15em 0.4em; border-radius: 3px; color: var(--cyan); font-size: 0.85em; }
+
+  .kw { color: var(--purple); }
+  .str { color: var(--green); }
+  .cm { color: var(--fg-subtle); font-style: italic; }
+  .num { color: var(--orange); }
+  .key { color: var(--accent); }
+
+  .mermaid { margin: 1.5rem 0 2rem; text-align: center; }
+  .mermaid svg { max-width: 100%; height: auto; }
+
+  .callout { font-family: var(--font-sans); background: var(--bg-surface); border-left: 3px solid var(--accent-dim); border-radius: 0 var(--radius) var(--radius) 0; padding: 1rem 1.25rem; margin-bottom: 1.5rem; font-size: 0.88rem; color: var(--fg-muted); line-height: 1.6; }
+  .callout strong { font-family: var(--font-mono); color: var(--fg-bright); }
+  .callout.success { border-left-color: var(--green-dim); }
+  .callout.warn { border-left-color: var(--orange); }
+
+  .badge { display: inline-block; font-family: var(--font-mono); font-size: 0.65rem; font-weight: 600; text-transform: uppercase; letter-spacing: 0.05em; padding: 0.2em 0.6em; border-radius: 3px; vertical-align: middle; margin-left: 0.4rem; }
+  .badge-done { background: var(--green-dim); color: #fff; }
+  .badge-wip { background: var(--orange); color: #0b0e14; }
+  .badge-todo { background: var(--fg-subtle); color: var(--fg); }
+
+  .checklist { list-style: none; padding-left: 0; }
+  .checklist li { padding-left: 1.5rem; position: relative; margin-bottom: 0.5rem; }
+  .checklist li::before { position: absolute; left: 0; font-family: var(--font-mono); font-size: 0.85rem; }
+  .checklist li.done { color: var(--fg-muted); }
+  .checklist li.done::before { content: "\2713"; color: var(--green); }
+  .checklist li.todo::before { content: "\25CB"; color: var(--fg-subtle); }
+  .checklist li.wip::before { content: "\25D4"; color: var(--orange); }
+
+  .compare { display: grid; grid-template-columns: 1fr 1fr; gap: 1rem; margin-bottom: 2rem; }
+  .compare-card { background: var(--bg-surface); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.25rem; }
+  .compare-card h4 { margin-top: 0; font-size: 0.82rem; }
+  .compare-card.after { border-color: var(--accent-dim); }
+  .compare-card ul { font-family: var(--font-mono); padding-left: 1.25rem; font-size: 0.8rem; }
+
+  hr { border: none; border-top: 1px solid var(--border); margin: 3rem 0; }
+
+  .progress-bar { position: fixed; top: 0; left: 0; height: 2px; background: var(--accent); z-index: 999; transition: width 0.1s linear; }
+
+  @media (max-width: 640px) {
+    .container { padding: 2rem 1rem 4rem; }
+    .hero h1 { font-size: 1.6rem; }
+    .toc ol { columns: 1; }
+    .compare { grid-template-columns: 1fr; }
+    table { font-size: 0.8rem; }
+    th, td { padding: 0.4rem 0.6rem; }
+  }
+</style>
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link href="https://fonts.googleapis.com/css2?family=Noto+Emoji&display=swap" rel="stylesheet">
+<style>
+  @font-face {
+    font-family: 'Departure Mono';
+    src: url('https://cdn.jsdelivr.net/gh/rektdeckard/departure-mono@latest/fonts/DepartureMono-Regular.woff2') format('woff2');
+    font-weight: normal;
+    font-style: normal;
+    font-display: swap;
+  }
+</style>
+</head>
+<body>
+
+<div class="progress-bar" id="progress"></div>
+
+<div class="container">
+
+<header class="hero">
+  <h1>honcho<span>-integration-spec</span></h1>
+  <p class="subtitle">Comparison of Hermes Agent vs. openclaw-honcho — and a porting spec for bringing Hermes patterns into other Honcho integrations.</p>
+  <div class="meta">
+    <span>hermes-agent / openclaw-honcho</span>
+    <span>Python + TypeScript</span>
+    <span>2026-03-09</span>
+  </div>
+</header>
+
+<nav class="toc">
+  <h2>Contents</h2>
+  <ol>
+    <li><a href="#overview">Overview</a></li>
+    <li><a href="#architecture">Architecture comparison</a></li>
+    <li><a href="#diff-table">Diff table</a></li>
+    <li><a href="#patterns">Hermes patterns to port</a></li>
+    <li><a href="#spec-async">Spec: async prefetch</a></li>
+    <li><a href="#spec-reasoning">Spec: dynamic reasoning level</a></li>
+    <li><a href="#spec-modes">Spec: per-peer memory modes</a></li>
+    <li><a href="#spec-identity">Spec: AI peer identity formation</a></li>
+    <li><a href="#spec-sessions">Spec: session naming strategies</a></li>
+    <li><a href="#spec-cli">Spec: CLI surface injection</a></li>
+    <li><a href="#openclaw-checklist">openclaw-honcho checklist</a></li>
+    <li><a href="#nanobot-checklist">nanobot-honcho checklist</a></li>
+  </ol>
+</nav>
+
+<!-- OVERVIEW -->
+<section id="overview">
+  <h2>Overview</h2>
+
+  <p>Two independent Honcho integrations have been built for two different agent runtimes: <strong>Hermes Agent</strong> (Python, baked into the runner) and <strong>openclaw-honcho</strong> (TypeScript plugin via hook/tool API). Both use the same Honcho peer paradigm — dual peer model, <code>session.context()</code>, <code>peer.chat()</code> — but they made different tradeoffs at every layer.</p>
+
+  <p>This document maps those tradeoffs and defines a porting spec: a set of Hermes-originated patterns, each stated as an integration-agnostic interface, that any Honcho integration can adopt regardless of runtime or language.</p>
+
+  <div class="callout">
+    <strong>Scope</strong> Both integrations work correctly today. This spec is about the delta — patterns in Hermes that are worth propagating and patterns in openclaw-honcho that Hermes should eventually adopt. The spec is additive, not prescriptive.
+  </div>
+</section>
+
+<!-- ARCHITECTURE -->
+<section id="architecture">
+  <h2>Architecture comparison</h2>
+
+  <h3>Hermes: baked-in runner</h3>
+  <p>Honcho is initialised directly inside <code>AIAgent.__init__</code>. There is no plugin boundary. Session management, context injection, async prefetch, and CLI surface are all first-class concerns of the runner. Context is injected once per session (baked into <code>_cached_system_prompt</code>) and never re-fetched mid-session — this maximises prefix cache hits at the LLM provider.</p>
+
+  <div class="mermaid">
+%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1f3150', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#3d6ea5', 'lineColor': '#3d6ea5', 'secondaryColor': '#162030', 'tertiaryColor': '#11151c' }}}%%
+flowchart TD
+    U["user message"] --> P["_honcho_prefetch()<br/>(reads cache — no HTTP)"]
+    P --> SP["_build_system_prompt()<br/>(first turn only, cached)"]
+    SP --> LLM["LLM call"]
+    LLM --> R["response"]
+    R --> FP["_honcho_fire_prefetch()<br/>(daemon threads, turn end)"]
+    FP --> C1["prefetch_context() thread"]
+    FP --> C2["prefetch_dialectic() thread"]
+    C1 --> CACHE["_context_cache / _dialectic_cache"]
+    C2 --> CACHE
+
+    style U fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style P fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style SP fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style LLM fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style R fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style FP fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style C1 fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style C2 fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style CACHE fill:#11151c,stroke:#484f58,color:#6e7681
+  </div>
+
+  <h3>openclaw-honcho: hook-based plugin</h3>
+  <p>The plugin registers hooks against OpenClaw's event bus. Context is fetched synchronously inside <code>before_prompt_build</code> on every turn. Message capture happens in <code>agent_end</code>. The multi-agent hierarchy is tracked via <code>subagent_spawned</code>. This model is correct but every turn pays a blocking Honcho round-trip before the LLM call can begin.</p>
+
+  <div class="mermaid">
+%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1f3150', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#3d6ea5', 'lineColor': '#3d6ea5', 'secondaryColor': '#162030', 'tertiaryColor': '#11151c' }}}%%
+flowchart TD
+    U2["user message"] --> BPB["before_prompt_build<br/>(BLOCKING HTTP — every turn)"]
+    BPB --> CTX["session.context()"]
+    CTX --> SP2["system prompt assembled"]
+    SP2 --> LLM2["LLM call"]
+    LLM2 --> R2["response"]
+    R2 --> AE["agent_end hook"]
+    AE --> SAVE["session.addMessages()<br/>session.setMetadata()"]
+
+    style U2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style BPB fill:#3a1515,stroke:#f47067,color:#c9d1d9
+    style CTX fill:#3a1515,stroke:#f47067,color:#c9d1d9
+    style SP2 fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style LLM2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style R2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style AE fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style SAVE fill:#11151c,stroke:#484f58,color:#6e7681
+  </div>
+</section>
+
+<!-- DIFF TABLE -->
+<section id="diff-table">
+  <h2>Diff table</h2>
+
+  <div class="table-wrap">
+    <table>
+      <thead>
+        <tr>
+          <th>Dimension</th>
+          <th>Hermes Agent</th>
+          <th>openclaw-honcho</th>
+        </tr>
+      </thead>
+      <tbody>
+        <tr>
+          <td><strong>Context injection timing</strong></td>
+          <td>Once per session (cached). Zero HTTP on response path after turn 1.</td>
+          <td>Every turn, blocking. Fresh context per turn but adds latency.</td>
+        </tr>
+        <tr>
+          <td><strong>Prefetch strategy</strong></td>
+          <td>Daemon threads fire at turn end; consumed next turn from cache.</td>
+          <td>None. Blocking call at prompt-build time.</td>
+        </tr>
+        <tr>
+          <td><strong>Dialectic (peer.chat)</strong></td>
+          <td>Prefetched async; result injected into system prompt next turn.</td>
+          <td>On-demand via <code>honcho_recall</code> / <code>honcho_analyze</code> tools.</td>
+        </tr>
+        <tr>
+          <td><strong>Reasoning level</strong></td>
+          <td>Dynamic: scales with message length. Floor = config default. Cap = "high".</td>
+          <td>Fixed per tool: recall=minimal, analyze=medium.</td>
+        </tr>
+        <tr>
+          <td><strong>Memory modes</strong></td>
+          <td><code>user_memory_mode</code> / <code>agent_memory_mode</code>: hybrid / honcho / local.</td>
+          <td>None. Always writes to Honcho.</td>
+        </tr>
+        <tr>
+          <td><strong>Write frequency</strong></td>
+          <td>async (background queue), turn, session, N turns.</td>
+          <td>After every agent_end (no control).</td>
+        </tr>
+        <tr>
+          <td><strong>AI peer identity</strong></td>
+          <td><code>observe_me=True</code>, <code>seed_ai_identity()</code>, <code>get_ai_representation()</code>, SOUL.md → AI peer.</td>
+          <td>Agent files uploaded to agent peer at setup. No ongoing self-observation seeding.</td>
+        </tr>
+        <tr>
+          <td><strong>Context scope</strong></td>
+          <td>User peer + AI peer representation, both injected.</td>
+          <td>User peer (owner) representation + conversation summary. <code>peerPerspective</code> on context call.</td>
+        </tr>
+        <tr>
+          <td><strong>Session naming</strong></td>
+          <td>per-directory / global / manual map / title-based.</td>
+          <td>Derived from platform session key.</td>
+        </tr>
+        <tr>
+          <td><strong>Multi-agent</strong></td>
+          <td>Single-agent only.</td>
+          <td>Parent observer hierarchy via <code>subagent_spawned</code>.</td>
+        </tr>
+        <tr>
+          <td><strong>Tool surface</strong></td>
+          <td>Single <code>query_user_context</code> tool (on-demand dialectic).</td>
+          <td>6 tools: session, profile, search, context (fast) + recall, analyze (LLM).</td>
+        </tr>
+        <tr>
+          <td><strong>Platform metadata</strong></td>
+          <td>Not stripped.</td>
+          <td>Explicitly stripped before Honcho storage.</td>
+        </tr>
+        <tr>
+          <td><strong>Message dedup</strong></td>
+          <td>None (sends on every save cycle).</td>
+          <td><code>lastSavedIndex</code> in session metadata prevents re-sending.</td>
+        </tr>
+        <tr>
+          <td><strong>CLI surface in prompt</strong></td>
+          <td>Management commands injected into system prompt. Agent knows its own CLI.</td>
+          <td>Not injected.</td>
+        </tr>
+        <tr>
+          <td><strong>AI peer name in identity</strong></td>
+          <td>Replaces "Hermes Agent" in DEFAULT_AGENT_IDENTITY when configured.</td>
+          <td>Not implemented.</td>
+        </tr>
+        <tr>
+          <td><strong>QMD / local file search</strong></td>
+          <td>Not implemented.</td>
+          <td>Passthrough tools when QMD backend configured.</td>
+        </tr>
+        <tr>
+          <td><strong>Workspace metadata</strong></td>
+          <td>Not implemented.</td>
+          <td><code>agentPeerMap</code> in workspace metadata tracks agent&#8594;peer ID.</td>
+        </tr>
+      </tbody>
+    </table>
+  </div>
+</section>
+
+<!-- PATTERNS -->
+<section id="patterns">
+  <h2>Hermes patterns to port</h2>
+
+  <p>Six patterns from Hermes are worth adopting in any Honcho integration. They are described below as integration-agnostic interfaces — the implementation will differ per runtime, but the contract is the same.</p>
+
+  <div class="compare">
+    <div class="compare-card">
+      <h4>Patterns Hermes contributes</h4>
+      <ul>
+        <li>Async prefetch (zero-latency)</li>
+        <li>Dynamic reasoning level</li>
+        <li>Per-peer memory modes</li>
+        <li>AI peer identity formation</li>
+        <li>Session naming strategies</li>
+        <li>CLI surface injection</li>
+      </ul>
+    </div>
+    <div class="compare-card after">
+      <h4>Patterns openclaw contributes back</h4>
+      <ul>
+        <li>lastSavedIndex dedup</li>
+        <li>Platform metadata stripping</li>
+        <li>Multi-agent observer hierarchy</li>
+        <li>peerPerspective on context()</li>
+        <li>Tiered tool surface (fast/LLM)</li>
+        <li>Workspace agentPeerMap</li>
+      </ul>
+    </div>
+  </div>
+</section>
+
+<!-- SPEC: ASYNC PREFETCH -->
+<section id="spec-async">
+  <h2>Spec: async prefetch</h2>
+
+  <h3>Problem</h3>
+  <p>Calling <code>session.context()</code> and <code>peer.chat()</code> synchronously before each LLM call adds 200–800ms of Honcho round-trip latency to every turn. Users experience this as the agent "thinking slowly."</p>
+
+  <h3>Pattern</h3>
+  <p>Fire both calls as non-blocking background work at the <strong>end</strong> of each turn. Store results in a per-session cache keyed by session ID. At the <strong>start</strong> of the next turn, pop from cache — the HTTP is already done. First turn is cold (empty cache); all subsequent turns are zero-latency on the response path.</p>
+
+  <h3>Interface contract</h3>
+  <pre><code><span class="cm">// TypeScript (openclaw / nanobot plugin shape)</span>
+
+<span class="kw">interface</span> <span class="key">AsyncPrefetch</span> {
+  <span class="cm">// Fire context + dialectic fetches at turn end. Non-blocking.</span>
+  firePrefetch(sessionId: <span class="str">string</span>, userMessage: <span class="str">string</span>): <span class="kw">void</span>;
+
+  <span class="cm">// Pop cached results at turn start. Returns empty if cache is cold.</span>
+  popContextResult(sessionId: <span class="str">string</span>): ContextResult | <span class="kw">null</span>;
+  popDialecticResult(sessionId: <span class="str">string</span>): <span class="str">string</span> | <span class="kw">null</span>;
+}
+
+<span class="kw">type</span> <span class="key">ContextResult</span> = {
+  representation: <span class="str">string</span>;
+  card: <span class="str">string</span>[];
+  aiRepresentation?: <span class="str">string</span>;  <span class="cm">// AI peer context if enabled</span>
+  summary?: <span class="str">string</span>;            <span class="cm">// conversation summary if fetched</span>
+};</code></pre>
+
+  <h3>Implementation notes</h3>
+  <ul>
+    <li>Python: <code>threading.Thread(daemon=True)</code>. Write to <code>dict[session_id, result]</code> — GIL makes this safe for simple writes.</li>
+    <li>TypeScript: <code>Promise</code> stored in <code>Map&lt;string, Promise&lt;ContextResult&gt;&gt;</code>. Await at pop time. If not resolved yet, skip (return null) — do not block.</li>
+    <li>The pop is destructive: clears the cache entry after reading so stale data never accumulates.</li>
+    <li>Prefetch should also fire on first turn (even though it won't be consumed until turn 2) — this ensures turn 2 is never cold.</li>
+  </ul>
+
+  <h3>openclaw-honcho adoption</h3>
+  <p>Move <code>session.context()</code> from <code>before_prompt_build</code> to a post-<code>agent_end</code> background task. Store result in <code>state.contextCache</code>. In <code>before_prompt_build</code>, read from cache instead of calling Honcho. If cache is empty (turn 1), inject nothing — the prompt is still valid without Honcho context on the first turn.</p>
+</section>
+
+<!-- SPEC: DYNAMIC REASONING LEVEL -->
+<section id="spec-reasoning">
+  <h2>Spec: dynamic reasoning level</h2>
+
+  <h3>Problem</h3>
+  <p>Honcho's dialectic endpoint supports reasoning levels from <code>minimal</code> to <code>max</code>. A fixed level per tool wastes budget on simple queries and under-serves complex ones.</p>
+
+  <h3>Pattern</h3>
+  <p>Select the reasoning level dynamically based on the user's message. Use the configured default as a floor. Bump by message length. Cap auto-selection at <code>high</code> — never select <code>max</code> automatically.</p>
+
+  <h3>Interface contract</h3>
+  <pre><code><span class="cm">// Shared helper — identical logic in any language</span>
+
+<span class="kw">const</span> LEVELS = [<span class="str">"minimal"</span>, <span class="str">"low"</span>, <span class="str">"medium"</span>, <span class="str">"high"</span>, <span class="str">"max"</span>];
+
+<span class="kw">function</span> <span class="key">dynamicReasoningLevel</span>(
+  query: <span class="str">string</span>,
+  configDefault: <span class="str">string</span> = <span class="str">"low"</span>
+): <span class="str">string</span> {
+  <span class="kw">const</span> baseIdx = Math.max(<span class="num">0</span>, LEVELS.indexOf(configDefault));
+  <span class="kw">const</span> n = query.length;
+  <span class="kw">const</span> bump = n &lt; <span class="num">120</span> ? <span class="num">0</span> : n &lt; <span class="num">400</span> ? <span class="num">1</span> : <span class="num">2</span>;
+  <span class="kw">return</span> LEVELS[Math.min(baseIdx + bump, <span class="num">3</span>)]; <span class="cm">// cap at "high" (idx 3)</span>
+}</code></pre>
+
+  <h3>Config key</h3>
+  <p>Add a <code>dialecticReasoningLevel</code> config field (string, default <code>"low"</code>). This sets the floor. Users can raise or lower it. The dynamic bump always applies on top.</p>
+
+  <h3>openclaw-honcho adoption</h3>
+  <p>Apply in <code>honcho_recall</code> and <code>honcho_analyze</code>: replace the fixed <code>reasoningLevel</code> with the dynamic selector. <code>honcho_recall</code> should use floor <code>"minimal"</code> and <code>honcho_analyze</code> floor <code>"medium"</code> — both still bump with message length.</p>
+</section>
+
+<!-- SPEC: PER-PEER MEMORY MODES -->
+<section id="spec-modes">
+  <h2>Spec: per-peer memory modes</h2>
+
+  <h3>Problem</h3>
+  <p>Users want independent control over whether user context and agent context are written locally, to Honcho, or both. A single <code>memoryMode</code> shorthand is not granular enough.</p>
+
+  <h3>Pattern</h3>
+  <p>Three modes per peer: <code>hybrid</code> (write both local + Honcho), <code>honcho</code> (Honcho only, disable local files), <code>local</code> (local files only, skip Honcho sync for this peer). Two orthogonal axes: user peer and agent peer.</p>
+
+  <h3>Config schema</h3>
+  <pre><code><span class="cm">// ~/.openclaw/openclaw.json  (or ~/.nanobot/config.json)</span>
+{
+  <span class="str">"plugins"</span>: {
+    <span class="str">"openclaw-honcho"</span>: {
+      <span class="str">"config"</span>: {
+        <span class="str">"apiKey"</span>: <span class="str">"..."</span>,
+        <span class="str">"memoryMode"</span>: <span class="str">"hybrid"</span>,          <span class="cm">// shorthand: both peers</span>
+        <span class="str">"userMemoryMode"</span>: <span class="str">"honcho"</span>,       <span class="cm">// override for user peer</span>
+        <span class="str">"agentMemoryMode"</span>: <span class="str">"hybrid"</span>       <span class="cm">// override for agent peer</span>
+      }
+    }
+  }
+}</code></pre>
+
+  <h3>Resolution order</h3>
+  <ol>
+    <li>Per-peer field (<code>userMemoryMode</code> / <code>agentMemoryMode</code>) — wins if present.</li>
+    <li>Shorthand <code>memoryMode</code> — applies to both peers as default.</li>
+    <li>Hardcoded default: <code>"hybrid"</code>.</li>
+  </ol>
+
+  <h3>Effect on Honcho sync</h3>
+  <ul>
+    <li><code>userMemoryMode=local</code>: skip adding user peer messages to Honcho.</li>
+    <li><code>agentMemoryMode=local</code>: skip adding assistant peer messages to Honcho.</li>
+    <li>Both local: skip <code>session.addMessages()</code> entirely.</li>
+    <li><code>userMemoryMode=honcho</code>: disable local USER.md writes.</li>
+    <li><code>agentMemoryMode=honcho</code>: disable local MEMORY.md / SOUL.md writes.</li>
+  </ul>
+</section>
+
+<!-- SPEC: AI PEER IDENTITY -->
+<section id="spec-identity">
+  <h2>Spec: AI peer identity formation</h2>
+
+  <h3>Problem</h3>
+  <p>Honcho builds the user's representation organically by observing what the user says. The same mechanism exists for the AI peer — but only if <code>observe_me=True</code> is set for the agent peer. Without it, the agent peer accumulates nothing and Honcho's AI-side model never forms.</p>
+
+  <p>Additionally, existing persona files (SOUL.md, IDENTITY.md) should seed the AI peer's Honcho representation at first activation, rather than waiting for it to emerge from scratch.</p>
+
+  <h3>Part A: observe_me=True for agent peer</h3>
+  <pre><code><span class="cm">// TypeScript — in session.addPeers() call</span>
+<span class="kw">await</span> session.addPeers([
+  [ownerPeer.id, { observeMe: <span class="kw">true</span>,  observeOthers: <span class="kw">false</span> }],
+  [agentPeer.id, { observeMe: <span class="kw">true</span>,  observeOthers: <span class="kw">true</span>  }], <span class="cm">// was false</span>
+]);</code></pre>
+
+  <p>This is a one-line change but foundational. Without it, Honcho's AI peer representation stays empty regardless of what the agent says.</p>
+
+  <h3>Part B: seedAiIdentity()</h3>
+  <pre><code><span class="kw">async function</span> <span class="key">seedAiIdentity</span>(
+  session: HonchoSession,
+  agentPeer: Peer,
+  content: <span class="str">string</span>,
+  source: <span class="str">string</span>
+): Promise&lt;<span class="kw">boolean</span>&gt; {
+  <span class="kw">const</span> wrapped = [
+    <span class="str">`&lt;ai_identity_seed&gt;`</span>,
+    <span class="str">`&lt;source&gt;${source}&lt;/source&gt;`</span>,
+    <span class="str">``</span>,
+    content.trim(),
+    <span class="str">`&lt;/ai_identity_seed&gt;`</span>,
+  ].join(<span class="str">"\n"</span>);
+
+  <span class="kw">await</span> agentPeer.addMessage(<span class="str">"assistant"</span>, wrapped);
+  <span class="kw">return true</span>;
+}</code></pre>
+
+  <h3>Part C: migrate agent files at setup</h3>
+  <p>During <code>openclaw honcho setup</code>, upload agent-self files (SOUL.md, IDENTITY.md, AGENTS.md, BOOTSTRAP.md) to the agent peer using <code>seedAiIdentity()</code> instead of <code>session.uploadFile()</code>. This routes the content through Honcho's observation pipeline rather than the file store.</p>
+
+  <h3>Part D: AI peer name in identity</h3>
+  <p>When the agent has a configured name (non-default), inject it into the agent's self-identity prefix. In OpenClaw this means adding to the injected system prompt section:</p>
+  <pre><code><span class="cm">// In context hook return value</span>
+<span class="kw">return</span> {
+  systemPrompt: [
+    agentName ? <span class="str">`You are ${agentName}.`</span> : <span class="str">""</span>,
+    <span class="str">"## User Memory Context"</span>,
+    ...sections,
+  ].filter(Boolean).join(<span class="str">"\n\n"</span>)
+};</code></pre>
+
+  <h3>CLI surface: honcho identity subcommand</h3>
+  <pre><code>openclaw honcho identity &lt;file&gt;    <span class="cm"># seed from file</span>
+openclaw honcho identity --show    <span class="cm"># show current AI peer representation</span></code></pre>
+</section>
+
+<!-- SPEC: SESSION NAMING -->
+<section id="spec-sessions">
+  <h2>Spec: session naming strategies</h2>
+
+  <h3>Problem</h3>
+  <p>When Honcho is used across multiple projects or directories, a single global session means every project shares the same context. Per-directory sessions provide isolation without requiring users to name sessions manually.</p>
+
+  <h3>Strategies</h3>
+  <div class="table-wrap">
+    <table>
+      <thead><tr><th>Strategy</th><th>Session key</th><th>When to use</th></tr></thead>
+      <tbody>
+        <tr><td><code>per-directory</code></td><td>basename of CWD</td><td>Default. Each project gets its own session.</td></tr>
+        <tr><td><code>global</code></td><td>fixed string <code>"global"</code></td><td>Single cross-project session.</td></tr>
+        <tr><td>manual map</td><td>user-configured per path</td><td><code>sessions</code> config map overrides directory basename.</td></tr>
+        <tr><td>title-based</td><td>sanitized session title</td><td>When agent supports named sessions; title set mid-conversation.</td></tr>
+      </tbody>
+    </table>
+  </div>
+
+  <h3>Config schema</h3>
+  <pre><code>{
+  <span class="str">"sessionStrategy"</span>: <span class="str">"per-directory"</span>,   <span class="cm">// "per-directory" | "global"</span>
+  <span class="str">"sessionPeerPrefix"</span>: <span class="kw">false</span>,            <span class="cm">// prepend peer name to session key</span>
+  <span class="str">"sessions"</span>: {                            <span class="cm">// manual overrides</span>
+    <span class="str">"/home/user/projects/foo"</span>: <span class="str">"foo-project"</span>
+  }
+}</code></pre>
+
+  <h3>CLI surface</h3>
+  <pre><code>openclaw honcho sessions              <span class="cm"># list all mappings</span>
+openclaw honcho map &lt;name&gt;           <span class="cm"># map cwd to session name</span>
+openclaw honcho map                   <span class="cm"># no-arg = list mappings</span></code></pre>
+
+  <p>Resolution order: manual map wins &rarr; session title &rarr; directory basename &rarr; platform key.</p>
+</section>
+
+<!-- SPEC: CLI SURFACE INJECTION -->
+<section id="spec-cli">
+  <h2>Spec: CLI surface injection</h2>
+
+  <h3>Problem</h3>
+  <p>When a user asks "how do I change my memory settings?" or "what Honcho commands are available?" the agent either hallucinates or says it doesn't know. The agent should know its own management interface.</p>
+
+  <h3>Pattern</h3>
+  <p>When Honcho is active, append a compact command reference to the system prompt. The agent can cite these commands directly instead of guessing.</p>
+
+  <pre><code><span class="cm">// In context hook, append to systemPrompt</span>
+<span class="kw">const</span> honchoSection = [
+  <span class="str">"# Honcho memory integration"</span>,
+  <span class="str">`Active. Session: ${sessionKey}. Mode: ${mode}.`</span>,
+  <span class="str">"Management commands:"</span>,
+  <span class="str">"  openclaw honcho status                    — show config + connection"</span>,
+  <span class="str">"  openclaw honcho mode [hybrid|honcho|local] — show or set memory mode"</span>,
+  <span class="str">"  openclaw honcho sessions                  — list session mappings"</span>,
+  <span class="str">"  openclaw honcho map &lt;name&gt;                — map directory to session"</span>,
+  <span class="str">"  openclaw honcho identity [file] [--show]  — seed or show AI identity"</span>,
+  <span class="str">"  openclaw honcho setup                     — full interactive wizard"</span>,
+].join(<span class="str">"\n"</span>);</code></pre>
+
+  <div class="callout warn">
+    <strong>Keep it compact.</strong> This section is injected every turn. Keep it under 300 chars of context. List commands, not explanations — the agent can explain them on request.
+  </div>
+</section>
+
+<!-- OPENCLAW CHECKLIST -->
+<section id="openclaw-checklist">
+  <h2>openclaw-honcho checklist</h2>
+
+  <p>Ordered by impact. Each item maps to a spec section above.</p>
+
+  <ul class="checklist">
+    <li class="todo"><strong>Async prefetch</strong> — move <code>session.context()</code> out of <code>before_prompt_build</code> into post-<code>agent_end</code> background Promise. Pop from cache at prompt build. (<a href="#spec-async">spec</a>)</li>
+    <li class="todo"><strong>observe_me=True for agent peer</strong> — one-line change in <code>session.addPeers()</code> config for agent peer. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>Dynamic reasoning level</strong> — add <code>dynamicReasoningLevel()</code> helper; apply in <code>honcho_recall</code> and <code>honcho_analyze</code>. Add <code>dialecticReasoningLevel</code> to config schema. (<a href="#spec-reasoning">spec</a>)</li>
+    <li class="todo"><strong>Per-peer memory modes</strong> — add <code>userMemoryMode</code> / <code>agentMemoryMode</code> to config; gate Honcho sync and local writes accordingly. (<a href="#spec-modes">spec</a>)</li>
+    <li class="todo"><strong>seedAiIdentity()</strong> — add helper; apply during setup migration for SOUL.md / IDENTITY.md instead of <code>session.uploadFile()</code>. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>Session naming strategies</strong> — add <code>sessionStrategy</code>, <code>sessions</code> map, <code>sessionPeerPrefix</code> to config; implement resolution function. (<a href="#spec-sessions">spec</a>)</li>
+    <li class="todo"><strong>CLI surface injection</strong> — append command reference to <code>before_prompt_build</code> return value when Honcho is active. (<a href="#spec-cli">spec</a>)</li>
+    <li class="todo"><strong>honcho identity subcommand</strong> — add <code>openclaw honcho identity</code> CLI command. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>AI peer name injection</strong> — if <code>aiPeer</code> name configured, prepend to injected system prompt. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>honcho mode / honcho sessions / honcho map</strong> — CLI parity with Hermes. (<a href="#spec-sessions">spec</a>)</li>
+  </ul>
+
+  <div class="callout success">
+    <strong>Already done in openclaw-honcho (do not re-implement):</strong> lastSavedIndex dedup, platform metadata stripping, multi-agent parent observer hierarchy, peerPerspective on context(), tiered tool surface (fast/LLM), workspace agentPeerMap, QMD passthrough, self-hosted Honcho support.
+  </div>
+</section>
+
+<!-- NANOBOT CHECKLIST -->
+<section id="nanobot-checklist">
+  <h2>nanobot-honcho checklist</h2>
+
+  <p>nanobot-honcho is a greenfield integration. Start from openclaw-honcho's architecture (hook-based, dual peer) and apply all Hermes patterns from day one rather than retrofitting. Priority order:</p>
+
+  <h3>Phase 1 — core correctness</h3>
+  <ul class="checklist">
+    <li class="todo">Dual peer model (owner + agent peer), both with <code>observe_me=True</code></li>
+    <li class="todo">Message capture at turn end with <code>lastSavedIndex</code> dedup</li>
+    <li class="todo">Platform metadata stripping before Honcho storage</li>
+    <li class="todo">Async prefetch from day one — do not implement blocking context injection</li>
+    <li class="todo">Legacy file migration at first activation (USER.md → owner peer, SOUL.md → <code>seedAiIdentity()</code>)</li>
+  </ul>
+
+  <h3>Phase 2 — configuration</h3>
+  <ul class="checklist">
+    <li class="todo">Config schema: <code>apiKey</code>, <code>workspaceId</code>, <code>baseUrl</code>, <code>memoryMode</code>, <code>userMemoryMode</code>, <code>agentMemoryMode</code>, <code>dialecticReasoningLevel</code>, <code>sessionStrategy</code>, <code>sessions</code></li>
+    <li class="todo">Per-peer memory mode gating</li>
+    <li class="todo">Dynamic reasoning level</li>
+    <li class="todo">Session naming strategies</li>
+  </ul>
+
+  <h3>Phase 3 — tools and CLI</h3>
+  <ul class="checklist">
+    <li class="todo">Tool surface: <code>honcho_profile</code>, <code>honcho_recall</code>, <code>honcho_analyze</code>, <code>honcho_search</code>, <code>honcho_context</code></li>
+    <li class="todo">CLI: <code>setup</code>, <code>status</code>, <code>sessions</code>, <code>map</code>, <code>mode</code>, <code>identity</code></li>
+    <li class="todo">CLI surface injection into system prompt</li>
+    <li class="todo">AI peer name wired into agent identity</li>
+  </ul>
+</section>
+
+</div>
+
+<script type="module">
+  import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs';
+  mermaid.initialize({ startOnLoad: true, securityLevel: 'loose', fontFamily: 'Departure Mono, Noto Emoji, monospace' });
+</script>
+<script>
+  window.addEventListener('scroll', () => {
+    const bar = document.getElementById('progress');
+    const max = document.documentElement.scrollHeight - window.innerHeight;
+    bar.style.width = (max > 0 ? (window.scrollY / max) * 100 : 0) + '%';
+  });
+</script>
+</body>
+</html>

docs/honcho-integration-spec.md

@@ -0,0 +1,377 @@
+# honcho-integration-spec
+
+Comparison of Hermes Agent vs. openclaw-honcho — and a porting spec for bringing Hermes patterns into other Honcho integrations.
+
+---
+
+## Overview
+
+Two independent Honcho integrations have been built for two different agent runtimes: **Hermes Agent** (Python, baked into the runner) and **openclaw-honcho** (TypeScript plugin via hook/tool API). Both use the same Honcho peer paradigm — dual peer model, `session.context()`, `peer.chat()` — but they made different tradeoffs at every layer.
+
+This document maps those tradeoffs and defines a porting spec: a set of Hermes-originated patterns, each stated as an integration-agnostic interface, that any Honcho integration can adopt regardless of runtime or language.
+
+> **Scope** Both integrations work correctly today. This spec is about the delta — patterns in Hermes that are worth propagating and patterns in openclaw-honcho that Hermes should eventually adopt. The spec is additive, not prescriptive.
+
+---
+
+## Architecture comparison
+
+### Hermes: baked-in runner
+
+Honcho is initialised directly inside `AIAgent.__init__`. There is no plugin boundary. Session management, context injection, async prefetch, and CLI surface are all first-class concerns of the runner. Context is injected once per session (baked into `_cached_system_prompt`) and never re-fetched mid-session — this maximises prefix cache hits at the LLM provider.
+
+Turn flow:
+
+```
+user message
+  → _honcho_prefetch()       (reads cache — no HTTP)
+  → _build_system_prompt()   (first turn only, cached)
+  → LLM call
+  → response
+  → _honcho_fire_prefetch()  (daemon threads, turn end)
+       → prefetch_context() thread  ──┐
+       → prefetch_dialectic() thread ─┴→ _context_cache / _dialectic_cache
+```
+
+### openclaw-honcho: hook-based plugin
+
+The plugin registers hooks against OpenClaw's event bus. Context is fetched synchronously inside `before_prompt_build` on every turn. Message capture happens in `agent_end`. The multi-agent hierarchy is tracked via `subagent_spawned`. This model is correct but every turn pays a blocking Honcho round-trip before the LLM call can begin.
+
+Turn flow:
+
+```
+user message
+  → before_prompt_build (BLOCKING HTTP — every turn)
+       → session.context()
+  → system prompt assembled
+  → LLM call
+  → response
+  → agent_end hook
+       → session.addMessages()
+       → session.setMetadata()
+```
+
+---
+
+## Diff table
+
+| Dimension | Hermes Agent | openclaw-honcho |
+|---|---|---|
+| **Context injection timing** | Once per session (cached). Zero HTTP on response path after turn 1. | Every turn, blocking. Fresh context per turn but adds latency. |
+| **Prefetch strategy** | Daemon threads fire at turn end; consumed next turn from cache. | None. Blocking call at prompt-build time. |
+| **Dialectic (peer.chat)** | Prefetched async; result injected into system prompt next turn. | On-demand via `honcho_recall` / `honcho_analyze` tools. |
+| **Reasoning level** | Dynamic: scales with message length. Floor = config default. Cap = "high". | Fixed per tool: recall=minimal, analyze=medium. |
+| **Memory modes** | `user_memory_mode` / `agent_memory_mode`: hybrid / honcho / local. | None. Always writes to Honcho. |
+| **Write frequency** | async (background queue), turn, session, N turns. | After every agent_end (no control). |
+| **AI peer identity** | `observe_me=True`, `seed_ai_identity()`, `get_ai_representation()`, SOUL.md → AI peer. | Agent files uploaded to agent peer at setup. No ongoing self-observation. |
+| **Context scope** | User peer + AI peer representation, both injected. | User peer (owner) representation + conversation summary. `peerPerspective` on context call. |
+| **Session naming** | per-directory / global / manual map / title-based. | Derived from platform session key. |
+| **Multi-agent** | Single-agent only. | Parent observer hierarchy via `subagent_spawned`. |
+| **Tool surface** | Single `query_user_context` tool (on-demand dialectic). | 6 tools: session, profile, search, context (fast) + recall, analyze (LLM). |
+| **Platform metadata** | Not stripped. | Explicitly stripped before Honcho storage. |
+| **Message dedup** | None. | `lastSavedIndex` in session metadata prevents re-sending. |
+| **CLI surface in prompt** | Management commands injected into system prompt. Agent knows its own CLI. | Not injected. |
+| **AI peer name in identity** | Replaces "Hermes Agent" in DEFAULT_AGENT_IDENTITY when configured. | Not implemented. |
+| **QMD / local file search** | Not implemented. | Passthrough tools when QMD backend configured. |
+| **Workspace metadata** | Not implemented. | `agentPeerMap` in workspace metadata tracks agent→peer ID. |
+
+---
+
+## Patterns
+
+Six patterns from Hermes are worth adopting in any Honcho integration. Each is described as an integration-agnostic interface.
+
+**Hermes contributes:**
+- Async prefetch (zero-latency)
+- Dynamic reasoning level
+- Per-peer memory modes
+- AI peer identity formation
+- Session naming strategies
+- CLI surface injection
+
+**openclaw-honcho contributes back (Hermes should adopt):**
+- `lastSavedIndex` dedup
+- Platform metadata stripping
+- Multi-agent observer hierarchy
+- `peerPerspective` on `context()`
+- Tiered tool surface (fast/LLM)
+- Workspace `agentPeerMap`
+
+---
+
+## Spec: async prefetch
+
+### Problem
+
+Calling `session.context()` and `peer.chat()` synchronously before each LLM call adds 200–800ms of Honcho round-trip latency to every turn.
+
+### Pattern
+
+Fire both calls as non-blocking background work at the **end** of each turn. Store results in a per-session cache keyed by session ID. At the **start** of the next turn, pop from cache — the HTTP is already done. First turn is cold (empty cache); all subsequent turns are zero-latency on the response path.
+
+### Interface contract
+
+```typescript
+interface AsyncPrefetch {
+  // Fire context + dialectic fetches at turn end. Non-blocking.
+  firePrefetch(sessionId: string, userMessage: string): void;
+
+  // Pop cached results at turn start. Returns empty if cache is cold.
+  popContextResult(sessionId: string): ContextResult | null;
+  popDialecticResult(sessionId: string): string | null;
+}
+
+type ContextResult = {
+  representation: string;
+  card: string[];
+  aiRepresentation?: string;  // AI peer context if enabled
+  summary?: string;           // conversation summary if fetched
+};
+```
+
+### Implementation notes
+
+- **Python:** `threading.Thread(daemon=True)`. Write to `dict[session_id, result]` — GIL makes this safe for simple writes.
+- **TypeScript:** `Promise` stored in `Map<string, Promise<ContextResult>>`. Await at pop time. If not resolved yet, return null — do not block.
+- The pop is destructive: clears the cache entry after reading so stale data never accumulates.
+- Prefetch should also fire on first turn (even though it won't be consumed until turn 2).
+
+### openclaw-honcho adoption
+
+Move `session.context()` from `before_prompt_build` to a post-`agent_end` background task. Store result in `state.contextCache`. In `before_prompt_build`, read from cache instead of calling Honcho. If cache is empty (turn 1), inject nothing — the prompt is still valid without Honcho context on the first turn.
+
+---
+
+## Spec: dynamic reasoning level
+
+### Problem
+
+Honcho's dialectic endpoint supports reasoning levels from `minimal` to `max`. A fixed level per tool wastes budget on simple queries and under-serves complex ones.
+
+### Pattern
+
+Select the reasoning level dynamically based on the user's message. Use the configured default as a floor. Bump by message length. Cap auto-selection at `high` — never select `max` automatically.
+
+### Logic
+
+```
+< 120 chars  → default (typically "low")
+120–400 chars → one level above default (cap at "high")
+> 400 chars  → two levels above default (cap at "high")
+```
+
+### Config key
+
+Add `dialecticReasoningLevel` (string, default `"low"`). This sets the floor. The dynamic bump always applies on top.
+
+### openclaw-honcho adoption
+
+Apply in `honcho_recall` and `honcho_analyze`: replace fixed `reasoningLevel` with the dynamic selector. `honcho_recall` uses floor `"minimal"`, `honcho_analyze` uses floor `"medium"` — both still bump with message length.
+
+---
+
+## Spec: per-peer memory modes
+
+### Problem
+
+Users want independent control over whether user context and agent context are written locally, to Honcho, or both.
+
+### Modes
+
+| Mode | Effect |
+|---|---|
+| `hybrid` | Write to both local files and Honcho (default) |
+| `honcho` | Honcho only — disable corresponding local file writes |
+| `local` | Local files only — skip Honcho sync for this peer |
+
+### Config schema
+
+```json
+{
+  "memoryMode": "hybrid",
+  "userMemoryMode": "honcho",
+  "agentMemoryMode": "hybrid"
+}
+```
+
+Resolution order: per-peer field wins → shorthand `memoryMode` → default `"hybrid"`.
+
+### Effect on Honcho sync
+
+- `userMemoryMode=local`: skip adding user peer messages to Honcho
+- `agentMemoryMode=local`: skip adding assistant peer messages to Honcho
+- Both local: skip `session.addMessages()` entirely
+- `userMemoryMode=honcho`: disable local USER.md writes
+- `agentMemoryMode=honcho`: disable local MEMORY.md / SOUL.md writes
+
+---
+
+## Spec: AI peer identity formation
+
+### Problem
+
+Honcho builds the user's representation organically by observing what the user says. The same mechanism exists for the AI peer — but only if `observe_me=True` is set for the agent peer. Without it, the agent peer accumulates nothing.
+
+Additionally, existing persona files (SOUL.md, IDENTITY.md) should seed the AI peer's Honcho representation at first activation.
+
+### Part A: observe_me=True for agent peer
+
+```typescript
+await session.addPeers([
+  [ownerPeer.id, { observeMe: true,  observeOthers: false }],
+  [agentPeer.id, { observeMe: true,  observeOthers: true  }], // was false
+]);
+```
+
+One-line change. Foundational. Without it, the AI peer representation stays empty regardless of what the agent says.
+
+### Part B: seedAiIdentity()
+
+```typescript
+async function seedAiIdentity(
+  agentPeer: Peer,
+  content: string,
+  source: string
+): Promise<boolean> {
+  const wrapped = [
+    `<ai_identity_seed>`,
+    `<source>${source}</source>`,
+    ``,
+    content.trim(),
+    `</ai_identity_seed>`,
+  ].join("\n");
+
+  await agentPeer.addMessage("assistant", wrapped);
+  return true;
+}
+```
+
+### Part C: migrate agent files at setup
+
+During `honcho setup`, upload agent-self files (SOUL.md, IDENTITY.md, AGENTS.md) to the agent peer via `seedAiIdentity()` instead of `session.uploadFile()`. This routes content through Honcho's observation pipeline.
+
+### Part D: AI peer name in identity
+
+When the agent has a configured name, prepend it to the injected system prompt:
+
+```typescript
+const namePrefix = agentName ? `You are ${agentName}.\n\n` : "";
+return { systemPrompt: namePrefix + "## User Memory Context\n\n" + sections };
+```
+
+### CLI surface
+
+```
+honcho identity <file>    # seed from file
+honcho identity --show    # show current AI peer representation
+```
+
+---
+
+## Spec: session naming strategies
+
+### Problem
+
+A single global session means every project shares the same Honcho context. Per-directory sessions provide isolation without requiring users to name sessions manually.
+
+### Strategies
+
+| Strategy | Session key | When to use |
+|---|---|---|
+| `per-directory` | basename of CWD | Default. Each project gets its own session. |
+| `global` | fixed string `"global"` | Single cross-project session. |
+| manual map | user-configured per path | `sessions` config map overrides directory basename. |
+| title-based | sanitized session title | When agent supports named sessions set mid-conversation. |
+
+### Config schema
+
+```json
+{
+  "sessionStrategy": "per-directory",
+  "sessionPeerPrefix": false,
+  "sessions": {
+    "/home/user/projects/foo": "foo-project"
+  }
+}
+```
+
+### CLI surface
+
+```
+honcho sessions              # list all mappings
+honcho map <name>            # map cwd to session name
+honcho map                   # no-arg = list mappings
+```
+
+Resolution order: manual map → session title → directory basename → platform key.
+
+---
+
+## Spec: CLI surface injection
+
+### Problem
+
+When a user asks "how do I change my memory settings?" the agent either hallucinates or says it doesn't know. The agent should know its own management interface.
+
+### Pattern
+
+When Honcho is active, append a compact command reference to the system prompt. Keep it under 300 chars.
+
+```
+# Honcho memory integration
+Active. Session: {sessionKey}. Mode: {mode}.
+Management commands:
+  honcho status                    — show config + connection
+  honcho mode [hybrid|honcho|local] — show or set memory mode
+  honcho sessions                  — list session mappings
+  honcho map <name>                — map directory to session
+  honcho identity [file] [--show]  — seed or show AI identity
+  honcho setup                     — full interactive wizard
+```
+
+---
+
+## openclaw-honcho checklist
+
+Ordered by impact:
+
+- [ ] **Async prefetch** — move `session.context()` out of `before_prompt_build` into post-`agent_end` background Promise
+- [ ] **observe_me=True for agent peer** — one-line change in `session.addPeers()`
+- [ ] **Dynamic reasoning level** — add helper; apply in `honcho_recall` and `honcho_analyze`; add `dialecticReasoningLevel` to config
+- [ ] **Per-peer memory modes** — add `userMemoryMode` / `agentMemoryMode` to config; gate Honcho sync and local writes
+- [ ] **seedAiIdentity()** — add helper; use during setup migration for SOUL.md / IDENTITY.md
+- [ ] **Session naming strategies** — add `sessionStrategy`, `sessions` map, `sessionPeerPrefix`
+- [ ] **CLI surface injection** — append command reference to `before_prompt_build` return value
+- [ ] **honcho identity subcommand** — seed from file or `--show` current representation
+- [ ] **AI peer name injection** — if `aiPeer` name configured, prepend to injected system prompt
+- [ ] **honcho mode / sessions / map** — CLI parity with Hermes
+
+Already done in openclaw-honcho (do not re-implement): `lastSavedIndex` dedup, platform metadata stripping, multi-agent parent observer, `peerPerspective` on `context()`, tiered tool surface, workspace `agentPeerMap`, QMD passthrough, self-hosted Honcho.
+
+---
+
+## nanobot-honcho checklist
+
+Greenfield integration. Start from openclaw-honcho's architecture and apply all Hermes patterns from day one.
+
+### Phase 1 — core correctness
+
+- [ ] Dual peer model (owner + agent peer), both with `observe_me=True`
+- [ ] Message capture at turn end with `lastSavedIndex` dedup
+- [ ] Platform metadata stripping before Honcho storage
+- [ ] Async prefetch from day one — do not implement blocking context injection
+- [ ] Legacy file migration at first activation (USER.md → owner peer, SOUL.md → `seedAiIdentity()`)
+
+### Phase 2 — configuration
+
+- [ ] Config schema: `apiKey`, `workspaceId`, `baseUrl`, `memoryMode`, `userMemoryMode`, `agentMemoryMode`, `dialecticReasoningLevel`, `sessionStrategy`, `sessions`
+- [ ] Per-peer memory mode gating
+- [ ] Dynamic reasoning level
+- [ ] Session naming strategies
+
+### Phase 3 — tools and CLI
+
+- [ ] Tool surface: `honcho_profile`, `honcho_recall`, `honcho_analyze`, `honcho_search`, `honcho_context`
+- [ ] CLI: `setup`, `status`, `sessions`, `map`, `mode`, `identity`
+- [ ] CLI surface injection into system prompt
+- [ ] AI peer name wired into agent identity

docs/migration/openclaw.md

@@ -0,0 +1,110 @@
+# Migrating from OpenClaw to Hermes Agent
+
+This guide covers how to import your OpenClaw settings, memories, skills, and API keys into Hermes Agent.
+
+## Three Ways to Migrate
+
+### 1. Automatic (during first-time setup)
+
+When you run `hermes setup` for the first time and Hermes detects `~/.openclaw`, it automatically offers to import your OpenClaw data before configuration begins. Just accept the prompt and everything is handled for you.
+
+### 2. CLI Command (quick, scriptable)
+
+```bash
+hermes claw migrate                      # Full migration with confirmation prompt
+hermes claw migrate --dry-run            # Preview what would happen
+hermes claw migrate --preset user-data   # Migrate without API keys/secrets
+hermes claw migrate --yes                # Skip confirmation prompt
+```
+
+**All options:**
+
+| Flag | Description |
+|------|-------------|
+| `--source PATH` | Path to OpenClaw directory (default: `~/.openclaw`) |
+| `--dry-run` | Preview only — no files are modified |
+| `--preset {user-data,full}` | Migration preset (default: `full`). `user-data` excludes secrets |
+| `--overwrite` | Overwrite existing files (default: skip conflicts) |
+| `--migrate-secrets` | Include allowlisted secrets (auto-enabled with `full` preset) |
+| `--workspace-target PATH` | Copy workspace instructions (AGENTS.md) to this absolute path |
+| `--skill-conflict {skip,overwrite,rename}` | How to handle skill name conflicts (default: `skip`) |
+| `--yes`, `-y` | Skip confirmation prompts |
+
+### 3. Agent-Guided (interactive, with previews)
+
+Ask the agent to run the migration for you:
+
+```
+> Migrate my OpenClaw setup to Hermes
+```
+
+The agent will use the `openclaw-migration` skill to:
+1. Run a dry-run first to preview changes
+2. Ask about conflict resolution (SOUL.md, skills, etc.)
+3. Let you choose between `user-data` and `full` presets
+4. Execute the migration with your choices
+5. Print a detailed summary of what was migrated
+
+## What Gets Migrated
+
+### `user-data` preset
+| Item | Source | Destination |
+|------|--------|-------------|
+| SOUL.md | `~/.openclaw/workspace/SOUL.md` | `~/.hermes/SOUL.md` |
+| Memory entries | `~/.openclaw/workspace/MEMORY.md` | `~/.hermes/memories/MEMORY.md` |
+| User profile | `~/.openclaw/workspace/USER.md` | `~/.hermes/memories/USER.md` |
+| Skills | `~/.openclaw/workspace/skills/` | `~/.hermes/skills/openclaw-imports/` |
+| Command allowlist | `~/.openclaw/workspace/exec_approval_patterns.yaml` | Merged into `~/.hermes/config.yaml` |
+| Messaging settings | `~/.openclaw/config.yaml` (TELEGRAM_ALLOWED_USERS, MESSAGING_CWD) | `~/.hermes/.env` |
+| TTS assets | `~/.openclaw/workspace/tts/` | `~/.hermes/tts/` |
+
+### `full` preset (adds to `user-data`)
+| Item | Source | Destination |
+|------|--------|-------------|
+| Telegram bot token | `~/.openclaw/config.yaml` | `~/.hermes/.env` |
+| OpenRouter API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| OpenAI API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| Anthropic API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+| ElevenLabs API key | `~/.openclaw/.env` or config | `~/.hermes/.env` |
+
+Only these 6 allowlisted secrets are ever imported. Other credentials are skipped and reported.
+
+## Conflict Handling
+
+By default, the migration **will not overwrite** existing Hermes data:
+
+- **SOUL.md** — skipped if one already exists in `~/.hermes/`
+- **Memory entries** — skipped if memories already exist (to avoid duplicates)
+- **Skills** — skipped if a skill with the same name already exists
+- **API keys** — skipped if the key is already set in `~/.hermes/.env`
+
+To overwrite conflicts, use `--overwrite`. The migration creates backups before overwriting.
+
+For skills, you can also use `--skill-conflict rename` to import conflicting skills under a new name (e.g., `skill-name-imported`).
+
+## Migration Report
+
+Every migration (including dry runs) produces a report showing:
+- **Migrated items** — what was successfully imported
+- **Conflicts** — items skipped because they already exist
+- **Skipped items** — items not found in the source
+- **Errors** — items that failed to import
+
+For execute runs, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
+
+## Troubleshooting
+
+### "OpenClaw directory not found"
+The migration looks for `~/.openclaw` by default. If your OpenClaw is installed elsewhere, use `--source`:
+```bash
+hermes claw migrate --source /path/to/.openclaw
+```
+
+### "Migration script not found"
+The migration script ships with Hermes Agent. If you installed via pip (not git clone), the `optional-skills/` directory may not be present. Install the skill from the Skills Hub:
+```bash
+hermes skills install openclaw-migration
+```
+
+### Memory overflow
+If your OpenClaw MEMORY.md or USER.md exceeds Hermes' character limits, excess entries are exported to an overflow file in the migration report directory. You can manually review and add the most important ones.

docs/plans/2026-03-16-pricing-accuracy-architecture-design.md

@@ -0,0 +1,608 @@
+# Pricing Accuracy Architecture
+
+Date: 2026-03-16
+
+## Goal
+
+Hermes should only show dollar costs when they are backed by an official source for the user's actual billing path.
+
+This design replaces the current static, heuristic pricing flow in:
+
+- `run_agent.py`
+- `agent/usage_pricing.py`
+- `agent/insights.py`
+- `cli.py`
+
+with a provider-aware pricing system that:
+
+- handles cache billing correctly
+- distinguishes `actual` vs `estimated` vs `included` vs `unknown`
+- reconciles post-hoc costs when providers expose authoritative billing data
+- supports direct providers, OpenRouter, subscriptions, enterprise pricing, and custom endpoints
+
+## Problems In The Current Design
+
+Current Hermes behavior has four structural issues:
+
+1. It stores only `prompt_tokens` and `completion_tokens`, which is insufficient for providers that bill cache reads and cache writes separately.
+2. It uses a static model price table and fuzzy heuristics, which can drift from current official pricing.
+3. It assumes public API list pricing matches the user's real billing path.
+4. It has no distinction between live estimates and reconciled billed cost.
+
+## Design Principles
+
+1. Normalize usage before pricing.
+2. Never fold cached tokens into plain input cost.
+3. Track certainty explicitly.
+4. Treat the billing path as part of the model identity.
+5. Prefer official machine-readable sources over scraped docs.
+6. Use post-hoc provider cost APIs when available.
+7. Show `n/a` rather than inventing precision.
+
+## High-Level Architecture
+
+The new system has four layers:
+
+1. `usage_normalization`
+   Converts raw provider usage into a canonical usage record.
+2. `pricing_source_resolution`
+   Determines the billing path, source of truth, and applicable pricing source.
+3. `cost_estimation_and_reconciliation`
+   Produces an immediate estimate when possible, then replaces or annotates it with actual billed cost later.
+4. `presentation`
+   `/usage`, `/insights`, and the status bar display cost with certainty metadata.
+
+## Canonical Usage Record
+
+Add a canonical usage model that every provider path maps into before any pricing math happens.
+
+Suggested structure:
+
+```python
+@dataclass
+class CanonicalUsage:
+    provider: str
+    billing_provider: str
+    model: str
+    billing_route: str
+
+    input_tokens: int = 0
+    output_tokens: int = 0
+    cache_read_tokens: int = 0
+    cache_write_tokens: int = 0
+    reasoning_tokens: int = 0
+    request_count: int = 1
+
+    raw_usage: dict[str, Any] | None = None
+    raw_usage_fields: dict[str, str] | None = None
+    computed_fields: set[str] | None = None
+
+    provider_request_id: str | None = None
+    provider_generation_id: str | None = None
+    provider_response_id: str | None = None
+```
+
+Rules:
+
+- `input_tokens` means non-cached input only.
+- `cache_read_tokens` and `cache_write_tokens` are never merged into `input_tokens`.
+- `output_tokens` excludes cache metrics.
+- `reasoning_tokens` is telemetry unless a provider officially bills it separately.
+
+This is the same normalization pattern used by `opencode`, extended with provenance and reconciliation ids.
+
+## Provider Normalization Rules
+
+### OpenAI Direct
+
+Source usage fields:
+
+- `prompt_tokens`
+- `completion_tokens`
+- `prompt_tokens_details.cached_tokens`
+
+Normalization:
+
+- `cache_read_tokens = cached_tokens`
+- `input_tokens = prompt_tokens - cached_tokens`
+- `cache_write_tokens = 0` unless OpenAI exposes it in the relevant route
+- `output_tokens = completion_tokens`
+
+### Anthropic Direct
+
+Source usage fields:
+
+- `input_tokens`
+- `output_tokens`
+- `cache_read_input_tokens`
+- `cache_creation_input_tokens`
+
+Normalization:
+
+- `input_tokens = input_tokens`
+- `output_tokens = output_tokens`
+- `cache_read_tokens = cache_read_input_tokens`
+- `cache_write_tokens = cache_creation_input_tokens`
+
+### OpenRouter
+
+Estimate-time usage normalization should use the response usage payload with the same rules as the underlying provider when possible.
+
+Reconciliation-time records should also store:
+
+- OpenRouter generation id
+- native token fields when available
+- `total_cost`
+- `cache_discount`
+- `upstream_inference_cost`
+- `is_byok`
+
+### Gemini / Vertex
+
+Use official Gemini or Vertex usage fields where available.
+
+If cached content tokens are exposed:
+
+- map them to `cache_read_tokens`
+
+If a route exposes no cache creation metric:
+
+- store `cache_write_tokens = 0`
+- preserve the raw usage payload for later extension
+
+### DeepSeek And Other Direct Providers
+
+Normalize only the fields that are officially exposed.
+
+If a provider does not expose cache buckets:
+
+- do not infer them unless the provider explicitly documents how to derive them
+
+### Subscription / Included-Cost Routes
+
+These still use the canonical usage model.
+
+Tokens are tracked normally. Cost depends on billing mode, not on whether usage exists.
+
+## Billing Route Model
+
+Hermes must stop keying pricing solely by `model`.
+
+Introduce a billing route descriptor:
+
+```python
+@dataclass
+class BillingRoute:
+    provider: str
+    base_url: str | None
+    model: str
+    billing_mode: str
+    organization_hint: str | None = None
+```
+
+`billing_mode` values:
+
+- `official_cost_api`
+- `official_generation_api`
+- `official_models_api`
+- `official_docs_snapshot`
+- `subscription_included`
+- `user_override`
+- `custom_contract`
+- `unknown`
+
+Examples:
+
+- OpenAI direct API with Costs API access: `official_cost_api`
+- Anthropic direct API with Usage & Cost API access: `official_cost_api`
+- OpenRouter request before reconciliation: `official_models_api`
+- OpenRouter request after generation lookup: `official_generation_api`
+- GitHub Copilot style subscription route: `subscription_included`
+- local OpenAI-compatible server: `unknown`
+- enterprise contract with configured rates: `custom_contract`
+
+## Cost Status Model
+
+Every displayed cost should have:
+
+```python
+@dataclass
+class CostResult:
+    amount_usd: Decimal | None
+    status: Literal["actual", "estimated", "included", "unknown"]
+    source: Literal[
+        "provider_cost_api",
+        "provider_generation_api",
+        "provider_models_api",
+        "official_docs_snapshot",
+        "user_override",
+        "custom_contract",
+        "none",
+    ]
+    label: str
+    fetched_at: datetime | None
+    pricing_version: str | None
+    notes: list[str]
+```
+
+Presentation rules:
+
+- `actual`: show dollar amount as final
+- `estimated`: show dollar amount with estimate labeling
+- `included`: show `included` or `$0.00 (included)` depending on UX choice
+- `unknown`: show `n/a`
+
+## Official Source Hierarchy
+
+Resolve cost using this order:
+
+1. Request-level or account-level official billed cost
+2. Official machine-readable model pricing
+3. Official docs snapshot
+4. User override or custom contract
+5. Unknown
+
+The system must never skip to a lower level if a higher-confidence source exists for the current billing route.
+
+## Provider-Specific Truth Rules
+
+### OpenAI Direct
+
+Preferred truth:
+
+1. Costs API for reconciled spend
+2. Official pricing page for live estimate
+
+### Anthropic Direct
+
+Preferred truth:
+
+1. Usage & Cost API for reconciled spend
+2. Official pricing docs for live estimate
+
+### OpenRouter
+
+Preferred truth:
+
+1. `GET /api/v1/generation` for reconciled `total_cost`
+2. `GET /api/v1/models` pricing for live estimate
+
+Do not use underlying provider public pricing as the source of truth for OpenRouter billing.
+
+### Gemini / Vertex
+
+Preferred truth:
+
+1. official billing export or billing API for reconciled spend when available for the route
+2. official pricing docs for estimate
+
+### DeepSeek
+
+Preferred truth:
+
+1. official machine-readable cost source if available in the future
+2. official pricing docs snapshot today
+
+### Subscription-Included Routes
+
+Preferred truth:
+
+1. explicit route config marking the model as included in subscription
+
+These should display `included`, not an API list-price estimate.
+
+### Custom Endpoint / Local Model
+
+Preferred truth:
+
+1. user override
+2. custom contract config
+3. unknown
+
+These should default to `unknown`.
+
+## Pricing Catalog
+
+Replace the current `MODEL_PRICING` dict with a richer pricing catalog.
+
+Suggested record:
+
+```python
+@dataclass
+class PricingEntry:
+    provider: str
+    route_pattern: str
+    model_pattern: str
+
+    input_cost_per_million: Decimal | None = None
+    output_cost_per_million: Decimal | None = None
+    cache_read_cost_per_million: Decimal | None = None
+    cache_write_cost_per_million: Decimal | None = None
+    request_cost: Decimal | None = None
+    image_cost: Decimal | None = None
+
+    source: str = "official_docs_snapshot"
+    source_url: str | None = None
+    fetched_at: datetime | None = None
+    pricing_version: str | None = None
+```
+
+The catalog should be route-aware:
+
+- `openai:gpt-5`
+- `anthropic:claude-opus-4-6`
+- `openrouter:anthropic/claude-opus-4.6`
+- `copilot:gpt-4o`
+
+This avoids conflating direct-provider billing with aggregator billing.
+
+## Pricing Sync Architecture
+
+Introduce a pricing sync subsystem instead of manually maintaining a single hardcoded table.
+
+Suggested modules:
+
+- `agent/pricing/catalog.py`
+- `agent/pricing/sources.py`
+- `agent/pricing/sync.py`
+- `agent/pricing/reconcile.py`
+- `agent/pricing/types.py`
+
+### Sync Sources
+
+- OpenRouter models API
+- official provider docs snapshots where no API exists
+- user overrides from config
+
+### Sync Output
+
+Cache pricing entries locally with:
+
+- source URL
+- fetch timestamp
+- version/hash
+- confidence/source type
+
+### Sync Frequency
+
+- startup warm cache
+- background refresh every 6 to 24 hours depending on source
+- manual `hermes pricing sync`
+
+## Reconciliation Architecture
+
+Live requests may produce only an estimate initially. Hermes should reconcile them later when a provider exposes actual billed cost.
+
+Suggested flow:
+
+1. Agent call completes.
+2. Hermes stores canonical usage plus reconciliation ids.
+3. Hermes computes an immediate estimate if a pricing source exists.
+4. A reconciliation worker fetches actual cost when supported.
+5. Session and message records are updated with `actual` cost.
+
+This can run:
+
+- inline for cheap lookups
+- asynchronously for delayed provider accounting
+
+## Persistence Changes
+
+Session storage should stop storing only aggregate prompt/completion totals.
+
+Add fields for both usage and cost certainty:
+
+- `input_tokens`
+- `output_tokens`
+- `cache_read_tokens`
+- `cache_write_tokens`
+- `reasoning_tokens`
+- `estimated_cost_usd`
+- `actual_cost_usd`
+- `cost_status`
+- `cost_source`
+- `pricing_version`
+- `billing_provider`
+- `billing_mode`
+
+If schema expansion is too large for one PR, add a new pricing events table:
+
+```text
+session_cost_events
+  id
+  session_id
+  request_id
+  provider
+  model
+  billing_mode
+  input_tokens
+  output_tokens
+  cache_read_tokens
+  cache_write_tokens
+  estimated_cost_usd
+  actual_cost_usd
+  cost_status
+  cost_source
+  pricing_version
+  created_at
+  updated_at
+```
+
+## Hermes Touchpoints
+
+### `run_agent.py`
+
+Current responsibility:
+
+- parse raw provider usage
+- update session token counters
+
+New responsibility:
+
+- build `CanonicalUsage`
+- update canonical counters
+- store reconciliation ids
+- emit usage event to pricing subsystem
+
+### `agent/usage_pricing.py`
+
+Current responsibility:
+
+- static lookup table
+- direct cost arithmetic
+
+New responsibility:
+
+- move or replace with pricing catalog facade
+- no fuzzy model-family heuristics
+- no direct pricing without billing-route context
+
+### `cli.py`
+
+Current responsibility:
+
+- compute session cost directly from prompt/completion totals
+
+New responsibility:
+
+- display `CostResult`
+- show status badges:
+  - `actual`
+  - `estimated`
+  - `included`
+  - `n/a`
+
+### `agent/insights.py`
+
+Current responsibility:
+
+- recompute historical estimates from static pricing
+
+New responsibility:
+
+- aggregate stored pricing events
+- prefer actual cost over estimate
+- surface estimates only when reconciliation is unavailable
+
+## UX Rules
+
+### Status Bar
+
+Show one of:
+
+- `$1.42`
+- `~$1.42`
+- `included`
+- `cost n/a`
+
+Where:
+
+- `$1.42` means `actual`
+- `~$1.42` means `estimated`
+- `included` means subscription-backed or explicitly zero-cost route
+- `cost n/a` means unknown
+
+### `/usage`
+
+Show:
+
+- token buckets
+- estimated cost
+- actual cost if available
+- cost status
+- pricing source
+
+### `/insights`
+
+Aggregate:
+
+- actual cost totals
+- estimated-only totals
+- unknown-cost sessions count
+- included-cost sessions count
+
+## Config And Overrides
+
+Add user-configurable pricing overrides in config:
+
+```yaml
+pricing:
+  mode: hybrid
+  sync_on_startup: true
+  sync_interval_hours: 12
+  overrides:
+    - provider: openrouter
+      model: anthropic/claude-opus-4.6
+      billing_mode: custom_contract
+      input_cost_per_million: 4.25
+      output_cost_per_million: 22.0
+      cache_read_cost_per_million: 0.5
+      cache_write_cost_per_million: 6.0
+  included_routes:
+    - provider: copilot
+      model: "*"
+    - provider: codex-subscription
+      model: "*"
+```
+
+Overrides must win over catalog defaults for the matching billing route.
+
+## Rollout Plan
+
+### Phase 1
+
+- add canonical usage model
+- split cache token buckets in `run_agent.py`
+- stop pricing cache-inflated prompt totals
+- preserve current UI with improved backend math
+
+### Phase 2
+
+- add route-aware pricing catalog
+- integrate OpenRouter models API sync
+- add `estimated` vs `included` vs `unknown`
+
+### Phase 3
+
+- add reconciliation for OpenRouter generation cost
+- add actual cost persistence
+- update `/insights` to prefer actual cost
+
+### Phase 4
+
+- add direct OpenAI and Anthropic reconciliation paths
+- add user overrides and contract pricing
+- add pricing sync CLI command
+
+## Testing Strategy
+
+Add tests for:
+
+- OpenAI cached token subtraction
+- Anthropic cache read/write separation
+- OpenRouter estimated vs actual reconciliation
+- subscription-backed models showing `included`
+- custom endpoints showing `n/a`
+- override precedence
+- stale catalog fallback behavior
+
+Current tests that assume heuristic pricing should be replaced with route-aware expectations.
+
+## Non-Goals
+
+- exact enterprise billing reconstruction without an official source or user override
+- backfilling perfect historical cost for old sessions that lack cache bucket data
+- scraping arbitrary provider web pages at request time
+
+## Recommendation
+
+Do not expand the existing `MODEL_PRICING` dict.
+
+That path cannot satisfy the product requirement. Hermes should instead migrate to:
+
+- canonical usage normalization
+- route-aware pricing sources
+- estimate-then-reconcile cost lifecycle
+- explicit certainty states in the UI
+
+This is the minimum architecture that makes the statement "Hermes pricing is backed by official sources where possible, and otherwise clearly labeled" defensible.

docs/skins/example-skin.yaml

@@ -0,0 +1,89 @@
+# ============================================================================
+# Hermes Agent — Example Skin Template
+# ============================================================================
+#
+# Copy this file to ~/.hermes/skins/<name>.yaml to create a custom skin.
+# All fields are optional — missing values inherit from the default skin.
+# Activate with: /skin <name>  or  display.skin: <name> in config.yaml
+#
+# See hermes_cli/skin_engine.py for the full schema reference.
+# ============================================================================
+
+# Required: unique skin name (used in /skin command and config)
+name: example
+description: An example custom skin — copy and modify this template
+
+# ── Colors ──────────────────────────────────────────────────────────────────
+# Hex color values for Rich markup. These control the CLI's visual palette.
+colors:
+  # Banner panel (the startup welcome box)
+  banner_border: "#CD7F32"        # Panel border
+  banner_title: "#FFD700"         # Panel title text
+  banner_accent: "#FFBF00"        # Section headers (Available Tools, Skills, etc.)
+  banner_dim: "#B8860B"           # Dim/muted text (separators, model info)
+  banner_text: "#FFF8DC"          # Body text (tool names, skill names)
+
+  # UI elements
+  ui_accent: "#FFBF00"            # General accent color
+  ui_label: "#4dd0e1"             # Labels
+  ui_ok: "#4caf50"                # Success indicators
+  ui_error: "#ef5350"             # Error indicators
+  ui_warn: "#ffa726"              # Warning indicators
+
+  # Input area
+  prompt: "#FFF8DC"               # Prompt text color
+  input_rule: "#CD7F32"           # Horizontal rule around input
+
+  # Response box
+  response_border: "#FFD700"      # Response box border (ANSI color)
+
+  # Session display
+  session_label: "#DAA520"        # Session label
+  session_border: "#8B8682"       # Session ID dim color
+
+# ── Spinner ─────────────────────────────────────────────────────────────────
+# Customize the animated spinner shown during API calls and tool execution.
+spinner:
+  # Faces shown while waiting for the API response
+  waiting_faces:
+    - "(｡◕‿◕｡)"
+    - "(◕‿◕✿)"
+    - "٩(◕‿◕｡)۶"
+
+  # Faces shown during extended thinking/reasoning
+  thinking_faces:
+    - "(｡•́︿•̀｡)"
+    - "(◔_◔)"
+    - "(¬‿¬)"
+
+  # Verbs used in spinner messages (e.g., "pondering your request...")
+  thinking_verbs:
+    - "pondering"
+    - "contemplating"
+    - "musing"
+    - "ruminating"
+
+  # Optional: left/right decorations around the spinner
+  # Each entry is a [left, right] pair. Omit entirely for no wings.
+  # wings:
+  #   - ["⟪⚔", "⚔⟫"]
+  #   - ["⟪▲", "▲⟫"]
+
+# ── Branding ────────────────────────────────────────────────────────────────
+# Text strings used throughout the CLI interface.
+branding:
+  agent_name: "Hermes Agent"          # Banner title, about display
+  welcome: "Welcome! Type your message or /help for commands."
+  goodbye: "Goodbye! ⚕"              # Exit message
+  response_label: " ⚕ Hermes "       # Response box header label
+  prompt_symbol: "❯ "                 # Input prompt symbol
+  help_header: "(^_^)? Available Commands"  # /help header text
+
+# ── Tool Output ─────────────────────────────────────────────────────────────
+# Character used as the prefix for tool output lines.
+# Default is "┊" (thin dotted vertical line). Some alternatives:
+#   "╎" (light triple dash vertical)
+#   "▏" (left one-eighth block)
+#   "│" (box drawing light vertical)
+#   "┃" (box drawing heavy vertical)
+tool_prefix: "┊"

environments/tool_call_parsers/hermes_parser.py

@@ -49,8 +49,6 @@ class HermesToolCallParser(ToolCallParser):
                     continue
 
                 tc_data = json.loads(raw_json)
-                if "name" not in tc_data:
-                    continue
                 tool_calls.append(
                     ChatCompletionMessageToolCall(
                         id=f"call_{uuid.uuid4().hex[:8]}",

environments/tool_call_parsers/mistral_parser.py

@@ -89,8 +89,6 @@ class MistralToolCallParser(ToolCallParser):
                         parsed = [parsed]
 
                     for tc in parsed:
-                        if "name" not in tc:
-                            continue
                         args = tc.get("arguments", {})
                         if isinstance(args, dict):
                             args = json.dumps(args, ensure_ascii=False)

flake.lock

@@ -36,26 +36,6 @@
         "type": "github"
       }
     },
-    "npm-lockfile-fix": {
-      "inputs": {
-        "nixpkgs": [
-          "nixpkgs"
-        ]
-      },
-      "locked": {
-        "lastModified": 1775903712,
-        "narHash": "sha256-2GV79U6iVH4gKAPWYrxUReB0S41ty/Y3dBLquU8AlaA=",
-        "owner": "jeslie0",
-        "repo": "npm-lockfile-fix",
-        "rev": "c6093acb0c0548e0f9b8b3d82918823721930fe8",
-        "type": "github"
-      },
-      "original": {
-        "owner": "jeslie0",
-        "repo": "npm-lockfile-fix",
-        "type": "github"
-      }
-    },
     "pyproject-build-systems": {
       "inputs": {
         "nixpkgs": [
@@ -144,7 +124,6 @@
       "inputs": {
         "flake-parts": "flake-parts",
         "nixpkgs": "nixpkgs",
-        "npm-lockfile-fix": "npm-lockfile-fix",
         "pyproject-build-systems": "pyproject-build-systems",
         "pyproject-nix": "pyproject-nix_2",
         "uv2nix": "uv2nix_2"

flake.nix

@@ -19,20 +19,11 @@
       url = "github:pyproject-nix/build-system-pkgs";
       inputs.nixpkgs.follows = "nixpkgs";
     };
-    npm-lockfile-fix = {
-      url = "github:jeslie0/npm-lockfile-fix";
-      inputs.nixpkgs.follows = "nixpkgs";
-    };
   };
 
-  outputs =
-    inputs:
+  outputs = inputs:
     inputs.flake-parts.lib.mkFlake { inherit inputs; } {
-      systems = [
-        "x86_64-linux"
-        "aarch64-linux"
-        "aarch64-darwin"
-      ];
+      systems = [ "x86_64-linux" "aarch64-linux" "aarch64-darwin" ];
 
       imports = [
         ./nix/packages.nix

gateway/builtin_hooks/boot_md.py

@@ -18,7 +18,9 @@ suppress delivery.
 """
 
 import logging
+import os
 import threading
+from pathlib import Path
 
 logger = logging.getLogger("hooks.boot-md")
 

gateway/channel_directory.py

@@ -76,15 +76,10 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
         except Exception as e:
             logger.warning("Channel directory: failed to build %s: %s", platform.value, e)
 
-    # Platforms that don't support direct channel enumeration get session-based
-    # discovery automatically.  Skip infrastructure entries that aren't messaging
-    # platforms — everything else falls through to _build_from_sessions().
-    _SKIP_SESSION_DISCOVERY = frozenset({"local", "api_server", "webhook"})
-    for plat in Platform:
-        plat_name = plat.value
-        if plat_name in _SKIP_SESSION_DISCOVERY or plat_name in platforms:
-            continue
-        platforms[plat_name] = _build_from_sessions(plat_name)
+    # Telegram, WhatsApp & Signal can't enumerate chats -- pull from session history
+    for plat_name in ("telegram", "whatsapp", "signal", "email", "sms", "bluebubbles"):
+        if plat_name not in platforms:
+            platforms[plat_name] = _build_from_sessions(plat_name)
 
     directory = {
         "updated_at": datetime.now().isoformat(),
@@ -100,7 +95,7 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
 
 
 def _build_discord(adapter) -> List[Dict[str, str]]:
-    """Enumerate all text channels and forum channels the Discord bot can see."""
+    """Enumerate all text channels the Discord bot can see."""
     channels = []
     client = getattr(adapter, "_client", None)
     if not client:
@@ -119,15 +114,6 @@ def _build_discord(adapter) -> List[Dict[str, str]]:
                 "guild": guild.name,
                 "type": "channel",
             })
-        # Forum channels (type 15) — creating a message auto-spawns a thread post.
-        forums = getattr(guild, "forum_channels", None) or []
-        for ch in forums:
-            channels.append({
-                "id": str(ch.id),
-                "name": ch.name,
-                "guild": guild.name,
-                "type": "forum",
-            })
         # Also include DM-capable users we've interacted with is not
         # feasible via guild enumeration; those come from sessions.
 
@@ -200,15 +186,6 @@ def load_directory() -> Dict[str, Any]:
         return {"updated_at": None, "platforms": {}}
 
 
-def lookup_channel_type(platform_name: str, chat_id: str) -> Optional[str]:
-    """Return the channel ``type`` string (e.g. ``"channel"``, ``"forum"``) for *chat_id*, or *None* if unknown."""
-    directory = load_directory()
-    for ch in directory.get("platforms", {}).get(platform_name, []):
-        if ch.get("id") == chat_id:
-            return ch.get("type")
-    return None
-
-
 def resolve_channel_name(platform_name: str, name: str) -> Optional[str]:
     """
     Resolve a human-friendly channel name to a numeric ID.

gateway/config.py

@@ -63,10 +63,7 @@ class Platform(Enum):
     WEBHOOK = "webhook"
     FEISHU = "feishu"
     WECOM = "wecom"
-    WECOM_CALLBACK = "wecom_callback"
-    WEIXIN = "weixin"
     BLUEBUBBLES = "bluebubbles"
-    QQBOT = "qqbot"
 
 
 @dataclass
@@ -192,7 +189,7 @@ class StreamingConfig:
     """Configuration for real-time token streaming to messaging platforms."""
     enabled: bool = False
     transport: str = "edit"       # "edit" (progressive editMessageText) or "off"
-    edit_interval: float = 1.0    # Seconds between message edits (Telegram rate-limits at ~1/s)
+    edit_interval: float = 0.3    # Seconds between message edits
     buffer_threshold: int = 40    # Chars before forcing an edit
     cursor: str = " ▉"           # Cursor shown during streaming
 
@@ -212,7 +209,7 @@ class StreamingConfig:
         return cls(
             enabled=data.get("enabled", False),
             transport=data.get("transport", "edit"),
-            edit_interval=float(data.get("edit_interval", 1.0)),
+            edit_interval=float(data.get("edit_interval", 0.3)),
             buffer_threshold=int(data.get("buffer_threshold", 40)),
             cursor=data.get("cursor", " ▉"),
         )
@@ -258,24 +255,12 @@ class GatewayConfig:
     # Streaming configuration
     streaming: StreamingConfig = field(default_factory=StreamingConfig)
 
-    # Session store pruning: drop SessionEntry records older than this many
-    # days from the in-memory dict and sessions.json.  Keeps the store from
-    # growing unbounded in gateways serving many chats/threads/users over
-    # months.  Pruning is invisible to users — if they resume, they get a
-    # fresh session exactly as if the reset policy had fired.  0 = disabled.
-    session_store_max_age_days: int = 90
-
     def get_connected_platforms(self) -> List[Platform]:
         """Return list of platforms that are enabled and configured."""
         connected = []
         for platform, config in self.platforms.items():
             if not config.enabled:
                 continue
-            # 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)
@@ -300,28 +285,12 @@ class GatewayConfig:
             # 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
+            # WeCom 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 get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -372,7 +341,6 @@ class GatewayConfig:
             "thread_sessions_per_user": self.thread_sessions_per_user,
             "unauthorized_dm_behavior": self.unauthorized_dm_behavior,
             "streaming": self.streaming.to_dict(),
-            "session_store_max_age_days": self.session_store_max_age_days,
         }
     
     @classmethod
@@ -420,13 +388,6 @@ class GatewayConfig:
             "pair",
         )
 
-        try:
-            session_store_max_age_days = int(data.get("session_store_max_age_days", 90))
-            if session_store_max_age_days < 0:
-                session_store_max_age_days = 0
-        except (TypeError, ValueError):
-            session_store_max_age_days = 90
-
         return cls(
             platforms=platforms,
             default_reset_policy=default_policy,
@@ -441,7 +402,6 @@ class GatewayConfig:
             thread_sessions_per_user=_coerce_bool(thread_sessions_per_user, False),
             unauthorized_dm_behavior=unauthorized_dm_behavior,
             streaming=StreamingConfig.from_dict(data.get("streaming", {})),
-            session_store_max_age_days=session_store_max_age_days,
         )
 
     def get_unauthorized_dm_behavior(self, platform: Optional[Platform] = None) -> str:
@@ -576,14 +536,6 @@ def load_gateway_config() -> GatewayConfig:
                     bridged["free_response_channels"] = platform_cfg["free_response_channels"]
                 if "mention_patterns" in platform_cfg:
                     bridged["mention_patterns"] = platform_cfg["mention_patterns"]
-                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"]
-                    if isinstance(channel_prompts, dict):
-                        bridged["channel_prompts"] = {str(k): v for k, v in channel_prompts.items()}
-                    else:
-                        bridged["channel_prompts"] = channel_prompts
                 if not bridged:
                     continue
                 plat_data = platforms_data.setdefault(plat.value, {})
@@ -629,32 +581,12 @@ def load_gateway_config() -> GatewayConfig:
                     if isinstance(ic, list):
                         ic = ",".join(str(v) for v in ic)
                     os.environ["DISCORD_IGNORED_CHANNELS"] = str(ic)
-                # allowed_channels: if set, bot ONLY responds in these channels (whitelist)
-                ac = discord_cfg.get("allowed_channels")
-                if ac is not None and not os.getenv("DISCORD_ALLOWED_CHANNELS"):
-                    if isinstance(ac, list):
-                        ac = ",".join(str(v) for v in ac)
-                    os.environ["DISCORD_ALLOWED_CHANNELS"] = str(ac)
                 # no_thread_channels: channels where bot responds directly without creating thread
                 ntc = discord_cfg.get("no_thread_channels")
                 if ntc is not None and not os.getenv("DISCORD_NO_THREAD_CHANNELS"):
                     if isinstance(ntc, list):
                         ntc = ",".join(str(v) for v in ntc)
                     os.environ["DISCORD_NO_THREAD_CHANNELS"] = str(ntc)
-                # allow_mentions: granular control over what the bot can ping.
-                # Safe defaults (no @everyone/roles) are applied in the adapter;
-                # these YAML keys only override when set and let users opt back
-                # into unsafe modes (e.g. roles=true) if they actually want it.
-                allow_mentions_cfg = discord_cfg.get("allow_mentions")
-                if isinstance(allow_mentions_cfg, dict):
-                    for yaml_key, env_key in (
-                        ("everyone", "DISCORD_ALLOW_MENTION_EVERYONE"),
-                        ("roles", "DISCORD_ALLOW_MENTION_ROLES"),
-                        ("users", "DISCORD_ALLOW_MENTION_USERS"),
-                        ("replied_user", "DISCORD_ALLOW_MENTION_REPLIED_USER"),
-                    ):
-                        if yaml_key in allow_mentions_cfg and not os.getenv(env_key):
-                            os.environ[env_key] = str(allow_mentions_cfg[yaml_key]).lower()
 
             # Telegram settings → env vars (env vars take precedence)
             telegram_cfg = yaml_cfg.get("telegram", {})
@@ -669,25 +601,8 @@ def load_gateway_config() -> GatewayConfig:
                     if isinstance(frc, list):
                         frc = ",".join(str(v) for v in frc)
                     os.environ["TELEGRAM_FREE_RESPONSE_CHATS"] = str(frc)
-                ignored_threads = telegram_cfg.get("ignored_threads")
-                if ignored_threads is not None and not os.getenv("TELEGRAM_IGNORED_THREADS"):
-                    if isinstance(ignored_threads, list):
-                        ignored_threads = ",".join(str(v) for v in ignored_threads)
-                    os.environ["TELEGRAM_IGNORED_THREADS"] = str(ignored_threads)
                 if "reactions" in telegram_cfg and not os.getenv("TELEGRAM_REACTIONS"):
                     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()
-                if "disable_link_previews" in telegram_cfg:
-                    plat_data = platforms_data.setdefault(Platform.TELEGRAM.value, {})
-                    if not isinstance(plat_data, dict):
-                        plat_data = {}
-                        platforms_data[Platform.TELEGRAM.value] = plat_data
-                    extra = plat_data.setdefault("extra", {})
-                    if not isinstance(extra, dict):
-                        extra = {}
-                        plat_data["extra"] = extra
-                    extra["disable_link_previews"] = telegram_cfg["disable_link_previews"]
 
             whatsapp_cfg = yaml_cfg.get("whatsapp", {})
             if isinstance(whatsapp_cfg, dict):
@@ -701,24 +616,6 @@ def load_gateway_config() -> GatewayConfig:
                         frc = ",".join(str(v) for v in frc)
                     os.environ["WHATSAPP_FREE_RESPONSE_CHATS"] = str(frc)
 
-            # DingTalk settings → env vars (env vars take precedence)
-            dingtalk_cfg = yaml_cfg.get("dingtalk", {})
-            if isinstance(dingtalk_cfg, dict):
-                if "require_mention" in dingtalk_cfg and not os.getenv("DINGTALK_REQUIRE_MENTION"):
-                    os.environ["DINGTALK_REQUIRE_MENTION"] = str(dingtalk_cfg["require_mention"]).lower()
-                if "mention_patterns" in dingtalk_cfg and not os.getenv("DINGTALK_MENTION_PATTERNS"):
-                    os.environ["DINGTALK_MENTION_PATTERNS"] = json.dumps(dingtalk_cfg["mention_patterns"])
-                frc = dingtalk_cfg.get("free_response_chats")
-                if frc is not None and not os.getenv("DINGTALK_FREE_RESPONSE_CHATS"):
-                    if isinstance(frc, list):
-                        frc = ",".join(str(v) for v in frc)
-                    os.environ["DINGTALK_FREE_RESPONSE_CHATS"] = str(frc)
-                allowed = dingtalk_cfg.get("allowed_users")
-                if allowed is not None and not os.getenv("DINGTALK_ALLOWED_USERS"):
-                    if isinstance(allowed, list):
-                        allowed = ",".join(str(v) for v in allowed)
-                    os.environ["DINGTALK_ALLOWED_USERS"] = str(allowed)
-
             # Matrix settings → env vars (env vars take precedence)
             matrix_cfg = yaml_cfg.get("matrix", {})
             if isinstance(matrix_cfg, dict):
@@ -731,8 +628,6 @@ def load_gateway_config() -> GatewayConfig:
                     os.environ["MATRIX_FREE_RESPONSE_ROOMS"] = str(frc)
                 if "auto_thread" in matrix_cfg and not os.getenv("MATRIX_AUTO_THREAD"):
                     os.environ["MATRIX_AUTO_THREAD"] = str(matrix_cfg["auto_thread"]).lower()
-                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()
 
     except Exception as e:
         logger.warning(
@@ -748,17 +643,6 @@ def load_gateway_config() -> GatewayConfig:
     _apply_env_overrides(config)
     
     # --- Validate loaded values ---
-    _validate_gateway_config(config)
-
-    return config
-
-
-def _validate_gateway_config(config: "GatewayConfig") -> None:
-    """Validate and sanitize a loaded GatewayConfig in place.
-
-    Called by ``load_gateway_config()`` after all config sources are merged.
-    Extracted as a separate function for testability.
-    """
     policy = config.default_reset_policy
 
     if not (0 <= policy.at_hour <= 23):
@@ -782,7 +666,6 @@ def _validate_gateway_config(config: "GatewayConfig") -> None:
         Platform.SLACK: "SLACK_BOT_TOKEN",
         Platform.MATTERMOST: "MATTERMOST_TOKEN",
         Platform.MATRIX: "MATRIX_ACCESS_TOKEN",
-        Platform.WEIXIN: "WEIXIN_TOKEN",
     }
     for platform, pconfig in config.platforms.items():
         if not pconfig.enabled:
@@ -795,31 +678,7 @@ def _validate_gateway_config(config: "GatewayConfig") -> None:
                 platform.value, env_name,
             )
 
-    # Reject known-weak placeholder tokens.
-    # Ported from openclaw/openclaw#64586: users who copy .env.example
-    # without changing placeholder values get a clear startup error instead
-    # of a confusing "auth failed" from the platform API.
-    try:
-        from hermes_cli.auth import has_usable_secret
-    except ImportError:
-        has_usable_secret = None  # type: ignore[assignment]
-
-    if has_usable_secret is not None:
-        for platform, pconfig in config.platforms.items():
-            if not pconfig.enabled:
-                continue
-            env_name = _token_env_names.get(platform)
-            if not env_name:
-                continue
-            token = pconfig.token
-            if token and token.strip() and not has_usable_secret(token, min_length=4):
-                logger.error(
-                    "%s is enabled but %s is set to a placeholder value ('%s'). "
-                    "Set a real bot token before starting the gateway. "
-                    "The adapter will NOT be started.",
-                    platform.value, env_name, token.strip()[:6] + "...",
-                )
-                pconfig.enabled = False
+    return config
 
 
 def _apply_env_overrides(config: GatewayConfig) -> None:
@@ -1042,9 +901,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 pass
         if api_server_host:
             config.platforms[Platform.API_SERVER].extra["host"] = api_server_host
-        api_server_model_name = os.getenv("API_SERVER_MODEL_NAME", "")
-        if api_server_model_name:
-            config.platforms[Platform.API_SERVER].extra["model_name"] = api_server_model_name
 
     # Webhook platform
     webhook_enabled = os.getenv("WEBHOOK_ENABLED", "").lower() in ("true", "1", "yes")
@@ -1062,25 +918,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
         if webhook_secret:
             config.platforms[Platform.WEBHOOK].extra["secret"] = webhook_secret
 
-    # DingTalk
-    dingtalk_client_id = os.getenv("DINGTALK_CLIENT_ID")
-    dingtalk_client_secret = os.getenv("DINGTALK_CLIENT_SECRET")
-    if dingtalk_client_id and dingtalk_client_secret:
-        if Platform.DINGTALK not in config.platforms:
-            config.platforms[Platform.DINGTALK] = PlatformConfig()
-        config.platforms[Platform.DINGTALK].enabled = True
-        config.platforms[Platform.DINGTALK].extra.update({
-            "client_id": dingtalk_client_id,
-            "client_secret": dingtalk_client_secret,
-        })
-        dingtalk_home = os.getenv("DINGTALK_HOME_CHANNEL")
-        if dingtalk_home:
-            config.platforms[Platform.DINGTALK].home_channel = HomeChannel(
-                platform=Platform.DINGTALK,
-                chat_id=dingtalk_home,
-                name=os.getenv("DINGTALK_HOME_CHANNEL_NAME", "Home"),
-            )
-
     # Feishu / Lark
     feishu_app_id = os.getenv("FEISHU_APP_ID")
     feishu_app_secret = os.getenv("FEISHU_APP_SECRET")
@@ -1130,64 +967,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 name=os.getenv("WECOM_HOME_CHANNEL_NAME", "Home"),
             )
 
-    # WeCom callback mode (self-built apps)
-    wecom_callback_corp_id = os.getenv("WECOM_CALLBACK_CORP_ID")
-    wecom_callback_corp_secret = os.getenv("WECOM_CALLBACK_CORP_SECRET")
-    if wecom_callback_corp_id and wecom_callback_corp_secret:
-        if Platform.WECOM_CALLBACK not in config.platforms:
-            config.platforms[Platform.WECOM_CALLBACK] = PlatformConfig()
-        config.platforms[Platform.WECOM_CALLBACK].enabled = True
-        config.platforms[Platform.WECOM_CALLBACK].extra.update({
-            "corp_id": wecom_callback_corp_id,
-            "corp_secret": wecom_callback_corp_secret,
-            "agent_id": os.getenv("WECOM_CALLBACK_AGENT_ID", ""),
-            "token": os.getenv("WECOM_CALLBACK_TOKEN", ""),
-            "encoding_aes_key": os.getenv("WECOM_CALLBACK_ENCODING_AES_KEY", ""),
-            "host": os.getenv("WECOM_CALLBACK_HOST", "0.0.0.0"),
-            "port": int(os.getenv("WECOM_CALLBACK_PORT", "8645")),
-        })
-
-    # Weixin (personal WeChat via iLink Bot API)
-    weixin_token = os.getenv("WEIXIN_TOKEN")
-    weixin_account_id = os.getenv("WEIXIN_ACCOUNT_ID")
-    if weixin_token or weixin_account_id:
-        if Platform.WEIXIN not in config.platforms:
-            config.platforms[Platform.WEIXIN] = PlatformConfig()
-        config.platforms[Platform.WEIXIN].enabled = True
-        if weixin_token:
-            config.platforms[Platform.WEIXIN].token = weixin_token
-        extra = config.platforms[Platform.WEIXIN].extra
-        if weixin_account_id:
-            extra["account_id"] = weixin_account_id
-        weixin_base_url = os.getenv("WEIXIN_BASE_URL", "").strip()
-        if weixin_base_url:
-            extra["base_url"] = weixin_base_url.rstrip("/")
-        weixin_cdn_base_url = os.getenv("WEIXIN_CDN_BASE_URL", "").strip()
-        if weixin_cdn_base_url:
-            extra["cdn_base_url"] = weixin_cdn_base_url.rstrip("/")
-        weixin_dm_policy = os.getenv("WEIXIN_DM_POLICY", "").strip().lower()
-        if weixin_dm_policy:
-            extra["dm_policy"] = weixin_dm_policy
-        weixin_group_policy = os.getenv("WEIXIN_GROUP_POLICY", "").strip().lower()
-        if weixin_group_policy:
-            extra["group_policy"] = weixin_group_policy
-        weixin_allowed_users = os.getenv("WEIXIN_ALLOWED_USERS", "").strip()
-        if weixin_allowed_users:
-            extra["allow_from"] = weixin_allowed_users
-        weixin_group_allowed_users = os.getenv("WEIXIN_GROUP_ALLOWED_USERS", "").strip()
-        if weixin_group_allowed_users:
-            extra["group_allow_from"] = weixin_group_allowed_users
-        weixin_split_multiline = os.getenv("WEIXIN_SPLIT_MULTILINE_MESSAGES", "").strip()
-        if weixin_split_multiline:
-            extra["split_multiline_messages"] = weixin_split_multiline
-        weixin_home = os.getenv("WEIXIN_HOME_CHANNEL", "").strip()
-        if weixin_home:
-            config.platforms[Platform.WEIXIN].home_channel = HomeChannel(
-                platform=Platform.WEIXIN,
-                chat_id=weixin_home,
-                name=os.getenv("WEIXIN_HOME_CHANNEL_NAME", "Home"),
-            )
-
     # BlueBubbles (iMessage)
     bluebubbles_server_url = os.getenv("BLUEBUBBLES_SERVER_URL")
     bluebubbles_password = os.getenv("BLUEBUBBLES_PASSWORD")
@@ -1211,44 +990,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
             name=os.getenv("BLUEBUBBLES_HOME_CHANNEL_NAME", "Home"),
         )
 
-    # QQ (Official Bot API v2)
-    qq_app_id = os.getenv("QQ_APP_ID")
-    qq_client_secret = os.getenv("QQ_CLIENT_SECRET")
-    if qq_app_id or qq_client_secret:
-        if Platform.QQBOT not in config.platforms:
-            config.platforms[Platform.QQBOT] = PlatformConfig()
-        config.platforms[Platform.QQBOT].enabled = True
-        extra = config.platforms[Platform.QQBOT].extra
-        if qq_app_id:
-            extra["app_id"] = qq_app_id
-        if qq_client_secret:
-            extra["client_secret"] = qq_client_secret
-        qq_allowed_users = os.getenv("QQ_ALLOWED_USERS", "").strip()
-        if qq_allowed_users:
-            extra["allow_from"] = qq_allowed_users
-        qq_group_allowed = os.getenv("QQ_GROUP_ALLOWED_USERS", "").strip()
-        if qq_group_allowed:
-            extra["group_allow_from"] = qq_group_allowed
-        qq_home = os.getenv("QQBOT_HOME_CHANNEL", "").strip()
-        qq_home_name_env = "QQBOT_HOME_CHANNEL_NAME"
-        if not qq_home:
-            # Back-compat: accept the pre-rename name and log a one-time warning.
-            legacy_home = os.getenv("QQ_HOME_CHANNEL", "").strip()
-            if legacy_home:
-                qq_home = legacy_home
-                qq_home_name_env = "QQ_HOME_CHANNEL_NAME"
-                import logging
-                logging.getLogger(__name__).warning(
-                    "QQ_HOME_CHANNEL is deprecated; rename to QQBOT_HOME_CHANNEL "
-                    "in your .env for consistency with the platform key."
-                )
-        if qq_home:
-            config.platforms[Platform.QQBOT].home_channel = HomeChannel(
-                platform=Platform.QQBOT,
-                chat_id=qq_home,
-                name=os.getenv("QQBOT_HOME_CHANNEL_NAME") or os.getenv(qq_home_name_env, "Home"),
-            )
-
     # Session settings
     idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
     if idle_minutes:

gateway/delivery.py

@@ -12,7 +12,7 @@ import logging
 from pathlib import Path
 from datetime import datetime
 from dataclasses import dataclass
-from typing import Dict, List, Optional, Any
+from typing import Dict, List, Optional, Any, Union
 
 from hermes_cli.config import get_hermes_home
 

gateway/display_config.py

@@ -1,194 +0,0 @@
-"""Per-platform display/verbosity configuration resolver.
-
-Provides ``resolve_display_setting()`` — the single entry-point for reading
-display settings with platform-specific overrides and sensible defaults.
-
-Resolution order (first non-None wins):
-    1. ``display.platforms.<platform>.<key>``  — explicit per-platform user override
-    2. ``display.<key>``                       — global user setting
-    3. ``_PLATFORM_DEFAULTS[<platform>][<key>]``  — built-in sensible default
-    4. ``_GLOBAL_DEFAULTS[<key>]``              — built-in global default
-
-Exception: ``display.streaming`` is CLI-only.  Gateway streaming follows the
-top-level ``streaming`` config unless ``display.platforms.<platform>.streaming``
-sets an explicit per-platform override.
-
-Backward compatibility: ``display.tool_progress_overrides`` is still read as a
-fallback for ``tool_progress`` when no ``display.platforms`` entry exists.  A
-config migration (version bump) automatically moves the old format into the new
-``display.platforms`` structure.
-"""
-
-from __future__ import annotations
-
-from typing import Any
-
-# ---------------------------------------------------------------------------
-# Overrideable display settings and their global defaults
-# ---------------------------------------------------------------------------
-# These are the settings that can be configured per-platform.
-# Other display settings (compact, personality, skin, etc.) are CLI-only
-# and don't participate in per-platform resolution.
-
-_GLOBAL_DEFAULTS: dict[str, Any] = {
-    "tool_progress": "all",
-    "show_reasoning": False,
-    "tool_preview_length": 0,
-    "streaming": None,  # None = follow top-level streaming config
-}
-
-# ---------------------------------------------------------------------------
-# Sensible per-platform defaults — tiered by platform capability
-# ---------------------------------------------------------------------------
-# Tier 1 (high): Supports message editing, typically personal/team use
-# Tier 2 (medium): Supports editing but often workspace/customer-facing
-# Tier 3 (low): No edit support — each progress msg is permanent
-# Tier 4 (minimal): Batch/non-interactive delivery
-
-_TIER_HIGH = {
-    "tool_progress": "all",
-    "show_reasoning": False,
-    "tool_preview_length": 40,
-    "streaming": None,  # follow global
-}
-
-_TIER_MEDIUM = {
-    "tool_progress": "new",
-    "show_reasoning": False,
-    "tool_preview_length": 40,
-    "streaming": None,
-}
-
-_TIER_LOW = {
-    "tool_progress": "off",
-    "show_reasoning": False,
-    "tool_preview_length": 40,
-    "streaming": False,
-}
-
-_TIER_MINIMAL = {
-    "tool_progress": "off",
-    "show_reasoning": False,
-    "tool_preview_length": 0,
-    "streaming": False,
-}
-
-_PLATFORM_DEFAULTS: dict[str, dict[str, Any]] = {
-    # Tier 1 — full edit support, personal/team use
-    "telegram":    _TIER_HIGH,
-    "discord":     _TIER_HIGH,
-
-    # Tier 2 — edit support, often customer/workspace channels
-    "slack":           _TIER_MEDIUM,
-    "mattermost":      _TIER_MEDIUM,
-    "matrix":          _TIER_MEDIUM,
-    "feishu":          _TIER_MEDIUM,
-
-    # Tier 3 — no edit support, progress messages are permanent
-    "signal":          _TIER_LOW,
-    "whatsapp":        _TIER_MEDIUM,  # Baileys bridge supports /edit
-    "bluebubbles":     _TIER_LOW,
-    "weixin":          _TIER_LOW,
-    "wecom":           _TIER_LOW,
-    "wecom_callback":  _TIER_LOW,
-    "dingtalk":        _TIER_LOW,
-
-    # Tier 4 — batch or non-interactive delivery
-    "email":           _TIER_MINIMAL,
-    "sms":             _TIER_MINIMAL,
-    "webhook":         _TIER_MINIMAL,
-    "homeassistant":   _TIER_MINIMAL,
-    "api_server":      {**_TIER_HIGH, "tool_preview_length": 0},
-}
-
-# Canonical set of per-platform overrideable keys (for validation).
-OVERRIDEABLE_KEYS = frozenset(_GLOBAL_DEFAULTS.keys())
-
-
-def resolve_display_setting(
-    user_config: dict,
-    platform_key: str,
-    setting: str,
-    fallback: Any = None,
-) -> Any:
-    """Resolve a display setting with per-platform override support.
-
-    Parameters
-    ----------
-    user_config : dict
-        The full parsed config.yaml dict.
-    platform_key : str
-        Platform config key (e.g. ``"telegram"``, ``"slack"``).  Use
-        ``_platform_config_key(source.platform)`` from gateway/run.py.
-    setting : str
-        Display setting name (e.g. ``"tool_progress"``, ``"show_reasoning"``).
-    fallback : Any
-        Fallback value when the setting isn't found anywhere.
-
-    Returns
-    -------
-    The resolved value, or *fallback* if nothing is configured.
-    """
-    display_cfg = user_config.get("display") or {}
-
-    # 1. Explicit per-platform override (display.platforms.<platform>.<key>)
-    platforms = display_cfg.get("platforms") or {}
-    plat_overrides = platforms.get(platform_key)
-    if isinstance(plat_overrides, dict):
-        val = plat_overrides.get(setting)
-        if val is not None:
-            return _normalise(setting, val)
-
-    # 1b. Backward compat: display.tool_progress_overrides.<platform>
-    if setting == "tool_progress":
-        legacy = display_cfg.get("tool_progress_overrides")
-        if isinstance(legacy, dict):
-            val = legacy.get(platform_key)
-            if val is not None:
-                return _normalise(setting, val)
-
-    # 2. Global user setting (display.<key>).  Skip display.streaming because
-    # that key controls only CLI terminal streaming; gateway token streaming is
-    # governed by the top-level streaming config plus per-platform overrides.
-    if setting != "streaming":
-        val = display_cfg.get(setting)
-        if val is not None:
-            return _normalise(setting, val)
-
-    # 3. Built-in platform default
-    plat_defaults = _PLATFORM_DEFAULTS.get(platform_key)
-    if plat_defaults:
-        val = plat_defaults.get(setting)
-        if val is not None:
-            return val
-
-    # 4. Built-in global default
-    val = _GLOBAL_DEFAULTS.get(setting)
-    if val is not None:
-        return val
-
-    return fallback
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-def _normalise(setting: str, value: Any) -> Any:
-    """Normalise YAML quirks (bare ``off`` → False in YAML 1.1)."""
-    if setting == "tool_progress":
-        if value is False:
-            return "off"
-        if value is True:
-            return "all"
-        return str(value).lower()
-    if setting in ("show_reasoning", "streaming"):
-        if isinstance(value, str):
-            return value.lower() in ("true", "1", "yes", "on")
-        return bool(value)
-    if setting == "tool_preview_length":
-        try:
-            return int(value)
-        except (TypeError, ValueError):
-            return 0
-    return value

gateway/platforms/__init__.py

@@ -9,11 +9,9 @@ Each adapter handles:
 """
 
 from .base import BasePlatformAdapter, MessageEvent, SendResult
-from .qqbot import QQAdapter
 
 __all__ = [
     "BasePlatformAdapter",
     "MessageEvent",
     "SendResult",
-    "QQAdapter",
 ]

gateway/platforms/base.py

@@ -6,13 +6,10 @@ and implement the required methods.
 """
 
 import asyncio
-import inspect
-import ipaddress
 import logging
 import os
 import random
 import re
-import socket as _socket
 import subprocess
 import sys
 import uuid
@@ -22,94 +19,6 @@ from urllib.parse import urlsplit
 logger = logging.getLogger(__name__)
 
 
-def utf16_len(s: str) -> int:
-    """Count UTF-16 code units in *s*.
-
-    Telegram's message-length limit (4 096) is measured in UTF-16 code units,
-    **not** Unicode code-points.  Characters outside the Basic Multilingual
-    Plane (emoji like 😀, CJK Extension B, musical symbols, …) are encoded as
-    surrogate pairs and therefore consume **two** UTF-16 code units each, even
-    though Python's ``len()`` counts them as one.
-
-    Ported from nearai/ironclaw#2304 which discovered the same discrepancy in
-    Rust's ``chars().count()``.
-    """
-    return len(s.encode("utf-16-le")) // 2
-
-
-def _prefix_within_utf16_limit(s: str, limit: int) -> str:
-    """Return the longest prefix of *s* whose UTF-16 length ≤ *limit*.
-
-    Unlike a plain ``s[:limit]``, this respects surrogate-pair boundaries so
-    we never slice a multi-code-unit character in half.
-    """
-    if utf16_len(s) <= limit:
-        return s
-    # Binary search for the longest safe prefix
-    lo, hi = 0, len(s)
-    while lo < hi:
-        mid = (lo + hi + 1) // 2
-        if utf16_len(s[:mid]) <= limit:
-            lo = mid
-        else:
-            hi = mid - 1
-    return s[:lo]
-
-
-def _custom_unit_to_cp(s: str, budget: int, len_fn) -> int:
-    """Return the largest codepoint offset *n* such that ``len_fn(s[:n]) <= budget``.
-
-    Used by :meth:`BasePlatformAdapter.truncate_message` when *len_fn* measures
-    length in units different from Python codepoints (e.g. UTF-16 code units).
-    Falls back to binary search which is O(log n) calls to *len_fn*.
-    """
-    if len_fn(s) <= budget:
-        return len(s)
-    lo, hi = 0, len(s)
-    while lo < hi:
-        mid = (lo + hi + 1) // 2
-        if len_fn(s[:mid]) <= budget:
-            lo = mid
-        else:
-            hi = mid - 1
-    return lo
-
-
-def is_network_accessible(host: str) -> bool:
-    """Return True if *host* would expose the server beyond loopback.
-
-    Loopback addresses (127.0.0.1, ::1, IPv4-mapped ::ffff:127.0.0.1)
-    are local-only.  Unspecified addresses (0.0.0.0, ::) bind all
-    interfaces.  Hostnames are resolved; DNS failure fails closed.
-    """
-    try:
-        addr = ipaddress.ip_address(host)
-        if addr.is_loopback:
-            return False
-        # ::ffff:127.0.0.1 — Python reports is_loopback=False for mapped
-        # addresses, so check the underlying IPv4 explicitly.
-        if getattr(addr, "ipv4_mapped", None) and addr.ipv4_mapped.is_loopback:
-            return False
-        return True
-    except ValueError:
-        # when host variable is a hostname, we should try to resolve below
-        pass
-
-    try:
-        resolved = _socket.getaddrinfo(
-            host, None, _socket.AF_UNSPEC, _socket.SOCK_STREAM,
-        )
-        # if the hostname resolves into at least one non-loopback address,
-        # then we consider it to be network accessible
-        for _family, _type, _proto, _canonname, sockaddr in resolved:
-            addr = ipaddress.ip_address(sockaddr[0])
-            if not addr.is_loopback:
-                return True
-        return False
-    except (_socket.gaierror, OSError):
-        return True
-
-
 def _detect_macos_system_proxy() -> str | None:
     """Read the macOS system HTTP(S) proxy via ``scutil --proxy``.
 
@@ -251,7 +160,7 @@ GATEWAY_SECRET_CAPTURE_UNSUPPORTED_MESSAGE = (
 )
 
 
-def safe_url_for_log(url: str, max_len: int = 80) -> str:
+def _safe_url_for_log(url: str, max_len: int = 80) -> str:
     """Return a URL string safe for logs (no query/fragment/userinfo)."""
     if max_len <= 0:
         return ""
@@ -288,23 +197,6 @@ def safe_url_for_log(url: str, max_len: int = 80) -> str:
     return f"{safe[:max_len - 3]}..."
 
 
-async def _ssrf_redirect_guard(response):
-    """Re-validate each redirect target to prevent redirect-based SSRF.
-
-    Without this, an attacker can host a public URL that 302-redirects to
-    http://169.254.169.254/ and bypass the pre-flight is_safe_url() check.
-
-    Must be async because httpx.AsyncClient awaits response event hooks.
-    """
-    if response.is_redirect and response.next_request:
-        redirect_url = str(response.next_request.url)
-        from tools.url_safety import is_safe_url
-        if not is_safe_url(redirect_url):
-            raise ValueError(
-                f"Blocked redirect to private/internal address: {safe_url_for_log(redirect_url)}"
-            )
-
-
 # ---------------------------------------------------------------------------
 # Image cache utilities
 #
@@ -324,23 +216,6 @@ def get_image_cache_dir() -> Path:
     return IMAGE_CACHE_DIR
 
 
-def _looks_like_image(data: bytes) -> bool:
-    """Return True if *data* starts with a known image magic-byte sequence."""
-    if len(data) < 4:
-        return False
-    if data[:8] == b"\x89PNG\r\n\x1a\n":
-        return True
-    if data[:3] == b"\xff\xd8\xff":
-        return True
-    if data[:6] in (b"GIF87a", b"GIF89a"):
-        return True
-    if data[:2] == b"BM":
-        return True
-    if data[:4] == b"RIFF" and len(data) >= 12 and data[8:12] == b"WEBP":
-        return True
-    return False
-
-
 def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
     """
     Save raw image bytes to the cache and return the absolute file path.
@@ -351,17 +226,7 @@ def cache_image_from_bytes(data: bytes, ext: str = ".jpg") -> str:
 
     Returns:
         Absolute path to the cached image file as a string.
-
-    Raises:
-        ValueError: If *data* does not look like a valid image (e.g. an HTML
-            error page returned by the upstream server).
     """
-    if not _looks_like_image(data):
-        snippet = data[:80].decode("utf-8", errors="replace")
-        raise ValueError(
-            f"Refusing to cache non-image data as {ext} "
-            f"(starts with: {snippet!r})"
-        )
     cache_dir = get_image_cache_dir()
     filename = f"img_{uuid.uuid4().hex[:12]}{ext}"
     filepath = cache_dir / filename
@@ -389,7 +254,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
     """
     from tools.url_safety import is_safe_url
     if not is_safe_url(url):
-        raise ValueError(f"Blocked unsafe URL (SSRF protection): {safe_url_for_log(url)}")
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
 
     import asyncio
     import httpx
@@ -397,11 +262,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
     _log = _logging.getLogger(__name__)
 
     last_exc = None
-    async with httpx.AsyncClient(
-        timeout=30.0,
-        follow_redirects=True,
-        event_hooks={"response": [_ssrf_redirect_guard]},
-    ) as client:
+    async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
         for attempt in range(retries + 1):
             try:
                 response = await client.get(
@@ -423,7 +284,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
                         "Media cache retry %d/%d for %s (%.1fs): %s",
                         attempt + 1,
                         retries,
-                        safe_url_for_log(url),
+                        _safe_url_for_log(url),
                         wait,
                         exc,
                     )
@@ -508,7 +369,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
     """
     from tools.url_safety import is_safe_url
     if not is_safe_url(url):
-        raise ValueError(f"Blocked unsafe URL (SSRF protection): {safe_url_for_log(url)}")
+        raise ValueError(f"Blocked unsafe URL (SSRF protection): {_safe_url_for_log(url)}")
 
     import asyncio
     import httpx
@@ -516,11 +377,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
     _log = _logging.getLogger(__name__)
 
     last_exc = None
-    async with httpx.AsyncClient(
-        timeout=30.0,
-        follow_redirects=True,
-        event_hooks={"response": [_ssrf_redirect_guard]},
-    ) as client:
+    async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
         for attempt in range(retries + 1):
             try:
                 response = await client.get(
@@ -542,7 +399,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
                         "Audio cache retry %d/%d for %s (%.1fs): %s",
                         attempt + 1,
                         retries,
-                        safe_url_for_log(url),
+                        _safe_url_for_log(url),
                         wait,
                         exc,
                     )
@@ -552,39 +409,6 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
     raise last_exc
 
 
-# ---------------------------------------------------------------------------
-# Video cache utilities
-#
-# Same pattern as image/audio cache -- videos from platforms are downloaded
-# here so the agent can reference them by local file path.
-# ---------------------------------------------------------------------------
-
-VIDEO_CACHE_DIR = get_hermes_dir("cache/videos", "video_cache")
-
-SUPPORTED_VIDEO_TYPES = {
-    ".mp4": "video/mp4",
-    ".mov": "video/quicktime",
-    ".webm": "video/webm",
-    ".mkv": "video/x-matroska",
-    ".avi": "video/x-msvideo",
-}
-
-
-def get_video_cache_dir() -> Path:
-    """Return the video cache directory, creating it if it doesn't exist."""
-    VIDEO_CACHE_DIR.mkdir(parents=True, exist_ok=True)
-    return VIDEO_CACHE_DIR
-
-
-def cache_video_from_bytes(data: bytes, ext: str = ".mp4") -> str:
-    """Save raw video bytes to the cache and return the absolute file path."""
-    cache_dir = get_video_cache_dir()
-    filename = f"video_{uuid.uuid4().hex[:12]}{ext}"
-    filepath = cache_dir / filename
-    filepath.write_bytes(data)
-    return str(filepath)
-
-
 # ---------------------------------------------------------------------------
 # Document cache utilities
 #
@@ -678,14 +502,6 @@ class MessageType(Enum):
     COMMAND = "command"  # /command style
 
 
-class ProcessingOutcome(Enum):
-    """Result classification for message-processing lifecycle hooks."""
-
-    SUCCESS = "success"
-    FAILURE = "failure"
-    CANCELLED = "cancelled"
-
-
 @dataclass
 class MessageEvent:
     """
@@ -703,15 +519,6 @@ class MessageEvent:
     # Original platform data
     raw_message: Any = None
     message_id: Optional[str] = None
-
-    # Platform-specific update identifier.  For Telegram this is the
-    # ``update_id`` from the PTB Update wrapper; other platforms currently
-    # ignore it.  Used by ``/restart`` to record the triggering update so the
-    # new gateway can advance the Telegram offset past it and avoid processing
-    # the same ``/restart`` twice if PTB's graceful-shutdown ACK times out
-    # ("Error while calling `get_updates` one more time to mark all fetched
-    # updates" in gateway.log).
-    platform_update_id: Optional[int] = None
     
     # Media attachments
     # media_urls: local file paths (for vision tool access)
@@ -722,13 +529,8 @@ class MessageEvent:
     reply_to_message_id: Optional[str] = None
     reply_to_text: Optional[str] = None  # Text of the replied-to message (for context injection)
     
-    # Auto-loaded skill(s) for topic/channel bindings (e.g., Telegram DM Topics,
-    # Discord channel_skill_bindings).  A single name or ordered list.
-    auto_skill: Optional[str | list[str]] = None
-
-    # Per-channel ephemeral system prompt (e.g. Discord channel_prompts).
-    # Applied at API call time and never persisted to transcript history.
-    channel_prompt: Optional[str] = None
+    # Auto-loaded skill for topic/channel bindings (e.g., Telegram DM Topics)
+    auto_skill: Optional[str] = None
     
     # Internal flag — set for synthetic events (e.g. background process
     # completion notifications) that must bypass user authorization checks.
@@ -750,9 +552,6 @@ class MessageEvent:
         raw = parts[0][1:].lower() if parts else None
         if raw and "@" in raw:
             raw = raw.split("@", 1)[0]
-        # Reject file paths: valid command names never contain /
-        if raw and "/" in raw:
-            return None
         return raw
     
     def get_command_args(self) -> str:
@@ -773,63 +572,6 @@ class SendResult:
     retryable: bool = False  # True for transient connection errors — base will retry automatically
 
 
-def merge_pending_message_event(
-    pending_messages: Dict[str, MessageEvent],
-    session_key: str,
-    event: MessageEvent,
-    *,
-    merge_text: bool = False,
-) -> None:
-    """Store or merge a pending event for a session.
-
-    Photo bursts/albums often arrive as multiple near-simultaneous PHOTO
-    events. Merge those into the existing queued event so the next turn sees
-    the whole burst.
-
-    When ``merge_text`` is enabled, rapid follow-up TEXT events are appended
-    instead of replacing the pending turn. This is used for Telegram bursty
-    follow-ups so a multi-part user thought is not silently truncated to only
-    the last queued fragment.
-    """
-    existing = pending_messages.get(session_key)
-    if existing:
-        existing_is_photo = getattr(existing, "message_type", None) == MessageType.PHOTO
-        incoming_is_photo = event.message_type == MessageType.PHOTO
-        existing_has_media = bool(existing.media_urls)
-        incoming_has_media = bool(event.media_urls)
-
-        if existing_is_photo and incoming_is_photo:
-            existing.media_urls.extend(event.media_urls)
-            existing.media_types.extend(event.media_types)
-            if event.text:
-                existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
-            return
-
-        if existing_has_media or incoming_has_media:
-            if incoming_has_media:
-                existing.media_urls.extend(event.media_urls)
-                existing.media_types.extend(event.media_types)
-            if event.text:
-                if existing.text:
-                    existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
-                else:
-                    existing.text = event.text
-            if existing_is_photo or incoming_is_photo:
-                existing.message_type = MessageType.PHOTO
-            return
-
-        if (
-            merge_text
-            and getattr(existing, "message_type", None) == MessageType.TEXT
-            and event.message_type == MessageType.TEXT
-        ):
-            if event.text:
-                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            return
-
-    pending_messages[session_key] = event
-
-
 # Error substrings that indicate a transient *connection* failure worth retrying.
 # "timeout" / "timed out" / "readtimeout" / "writetimeout" are intentionally
 # excluded: a read/write timeout on a non-idempotent call (e.g. send_message)
@@ -854,36 +596,6 @@ _RETRYABLE_ERROR_PATTERNS = (
 MessageHandler = Callable[[MessageEvent], Awaitable[Optional[str]]]
 
 
-def resolve_channel_prompt(
-    config_extra: dict,
-    channel_id: str,
-    parent_id: str | None = None,
-) -> str | None:
-    """Resolve a per-channel ephemeral prompt from platform config.
-
-    Looks up ``channel_prompts`` in the adapter's ``config.extra`` dict.
-    Prefers an exact match on *channel_id*; falls back to *parent_id*
-    (useful for forum threads / child channels inheriting a parent prompt).
-
-    Returns the prompt string, or None if no match is found.  Blank/whitespace-
-    only prompts are treated as absent.
-    """
-    prompts = config_extra.get("channel_prompts") or {}
-    if not isinstance(prompts, dict):
-        return None
-
-    for key in (channel_id, parent_id):
-        if not key:
-            continue
-        prompt = prompts.get(key)
-        if prompt is None:
-            continue
-        prompt = str(prompt).strip()
-        if prompt:
-            return prompt
-    return None
-
-
 class BasePlatformAdapter(ABC):
     """
     Base class for platform adapters.
@@ -913,14 +625,6 @@ class BasePlatformAdapter(ABC):
         # Gateway shutdown cancels these so an old gateway instance doesn't keep
         # working on a task after --replace or manual restarts.
         self._background_tasks: set[asyncio.Task] = set()
-        # One-shot callbacks to fire after the main response is delivered.
-        # Keyed by session_key. Values are either a bare callback (legacy) or
-        # a ``(generation, callback)`` tuple so GatewayRunner can make deferred
-        # deliveries generation-aware and avoid stale runs clearing callbacks
-        # registered by a fresher run for the same session.
-        self._post_delivery_callbacks: Dict[str, Any] = {}
-        self._expected_cancelled_tasks: set[asyncio.Task] = set()
-        self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
         # Chats where auto-TTS on voice input is disabled (set by /voice off)
         self._auto_tts_disabled_chats: set = set()
         # Chats where typing indicator is paused (e.g. during approval waits).
@@ -990,36 +694,7 @@ class BasePlatformAdapter(ABC):
         result = handler(self)
         if asyncio.iscoroutine(result):
             await result
-
-    def _acquire_platform_lock(self, scope: str, identity: str, resource_desc: str) -> bool:
-        """Acquire a scoped lock for this adapter. Returns True on success."""
-        from gateway.status import acquire_scoped_lock
-        self._platform_lock_scope = scope
-        self._platform_lock_identity = identity
-        acquired, existing = acquire_scoped_lock(
-            scope, identity, metadata={'platform': self.platform.value}
-        )
-        if acquired:
-            return True
-        owner_pid = existing.get('pid') if isinstance(existing, dict) else None
-        message = (
-            f'{resource_desc} already in use'
-            + (f' (PID {owner_pid})' if owner_pid else '')
-            + '. Stop the other gateway first.'
-        )
-        logger.error('[%s] %s', self.name, message)
-        self._set_fatal_error(f'{scope}_lock', message, retryable=False)
-        return False
-
-    def _release_platform_lock(self) -> None:
-        """Release the scoped lock acquired by _acquire_platform_lock."""
-        identity = getattr(self, '_platform_lock_identity', None)
-        if not identity:
-            return
-        from gateway.status import release_scoped_lock
-        release_scoped_lock(self._platform_lock_scope, identity)
-        self._platform_lock_identity = None
-
+    
     @property
     def name(self) -> str:
         """Human-readable name for this adapter."""
@@ -1038,10 +713,6 @@ class BasePlatformAdapter(ABC):
         an optional response string.
         """
         self._message_handler = handler
-
-    def set_busy_session_handler(self, handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]]) -> None:
-        """Set an optional handler for messages arriving during active sessions."""
-        self._busy_session_handler = handler
     
     def set_session_store(self, session_store: Any) -> None:
         """
@@ -1089,40 +760,16 @@ class BasePlatformAdapter(ABC):
         """
         pass
 
-    # Default: the adapter treats ``finalize=True`` on edit_message as a
-    # no-op and is happy to have the stream consumer skip redundant final
-    # edits.  Subclasses that *require* an explicit finalize call to close
-    # out the message lifecycle (e.g. rich card / AI assistant surfaces
-    # such as DingTalk AI Cards) override this to True (class attribute or
-    # property) so the stream consumer knows not to short-circuit.
-    REQUIRES_EDIT_FINALIZE: bool = False
-
     async def edit_message(
         self,
         chat_id: str,
         message_id: str,
         content: str,
-        *,
-        finalize: bool = False,
     ) -> SendResult:
         """
         Edit a previously sent message. Optional — platforms that don't
         support editing return success=False and callers fall back to
         sending a new message.
-
-        ``finalize`` signals that this is the last edit in a streaming
-        sequence.  Most platforms (Telegram, Slack, Discord, Matrix,
-        etc.) treat it as a no-op because their edit APIs have no notion
-        of message lifecycle state — an edit is an edit.  Platforms that
-        render streaming updates with a distinct "in progress" state and
-        require explicit closure (e.g. rich card / AI assistant surfaces
-        such as DingTalk AI Cards) use it to finalize the message and
-        transition the UI out of the streaming indicator — those should
-        also set ``REQUIRES_EDIT_FINALIZE = True`` so callers route a
-        final edit through even when content is unchanged.  Callers
-        should set ``finalize=True`` on the final edit of a streamed
-        response (typically when ``got_done`` fires in the stream
-        consumer) and leave it ``False`` on intermediate edits.
         """
         return SendResult(success=False, error="Not supported")
 
@@ -1359,7 +1006,7 @@ class BasePlatformAdapter(ABC):
                 path = path[1:-1].strip()
             path = path.lstrip("`\"'").rstrip("`\"',.;:)}]")
             if path:
-                media.append((os.path.expanduser(path), has_voice_tag))
+                media.append((path, has_voice_tag))
 
         # Remove MEDIA tags from content (including surrounding quote/backtick wrappers)
         if media:
@@ -1436,13 +1083,7 @@ class BasePlatformAdapter(ABC):
 
         return paths, cleaned
 
-    async def _keep_typing(
-        self,
-        chat_id: str,
-        interval: float = 2.0,
-        metadata=None,
-        stop_event: asyncio.Event | None = None,
-    ) -> None:
+    async def _keep_typing(self, chat_id: str, interval: float = 2.0, metadata=None) -> None:
         """
         Continuously send typing indicator until cancelled.
         
@@ -1456,18 +1097,9 @@ class BasePlatformAdapter(ABC):
         """
         try:
             while True:
-                if stop_event is not None and stop_event.is_set():
-                    return
                 if chat_id not in self._typing_paused:
                     await self.send_typing(chat_id, metadata=metadata)
-                if stop_event is None:
-                    await asyncio.sleep(interval)
-                    continue
-                try:
-                    await asyncio.wait_for(stop_event.wait(), timeout=interval)
-                except asyncio.TimeoutError:
-                    continue
-                return
+                await asyncio.sleep(interval)
         except asyncio.CancelledError:
             pass  # Normal cancellation when handler completes
         finally:
@@ -1494,59 +1126,6 @@ class BasePlatformAdapter(ABC):
         """Resume typing indicator for a chat after approval resolves."""
         self._typing_paused.discard(chat_id)
 
-    async def interrupt_session_activity(self, session_key: str, chat_id: str) -> None:
-        """Signal the active session loop to stop and clear typing immediately."""
-        if session_key:
-            interrupt_event = self._active_sessions.get(session_key)
-            if interrupt_event is not None:
-                interrupt_event.set()
-        try:
-            await self.stop_typing(chat_id)
-        except Exception:
-            pass
-
-    def register_post_delivery_callback(
-        self,
-        session_key: str,
-        callback: Callable,
-        *,
-        generation: int | None = None,
-    ) -> None:
-        """Register a deferred callback to fire after the main response.
-
-        ``generation`` lets callers tie the callback to a specific gateway run
-        generation so stale runs cannot clear callbacks owned by a fresher run.
-        """
-        if not session_key or not callable(callback):
-            return
-        if generation is None:
-            self._post_delivery_callbacks[session_key] = callback
-        else:
-            self._post_delivery_callbacks[session_key] = (int(generation), callback)
-
-    def pop_post_delivery_callback(
-        self,
-        session_key: str,
-        *,
-        generation: int | None = None,
-    ) -> Callable | None:
-        """Pop a deferred callback, optionally requiring generation ownership."""
-        if not session_key:
-            return None
-        entry = self._post_delivery_callbacks.get(session_key)
-        if entry is None:
-            return None
-        if isinstance(entry, tuple) and len(entry) == 2:
-            entry_generation, callback = entry
-            if generation is not None and int(entry_generation) != int(generation):
-                return None
-            self._post_delivery_callbacks.pop(session_key, None)
-            return callback if callable(callback) else None
-        if generation is not None:
-            return None
-        self._post_delivery_callbacks.pop(session_key, None)
-        return entry if callable(entry) else None
-
     # ── Processing lifecycle hooks ──────────────────────────────────────────
     # Subclasses override these to react to message processing events
     # (e.g. Discord adds 👀/✅/❌ reactions).
@@ -1554,7 +1133,7 @@ class BasePlatformAdapter(ABC):
     async def on_processing_start(self, event: MessageEvent) -> None:
         """Hook called when background processing begins."""
 
-    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
+    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
         """Hook called when background processing completes."""
 
     async def _run_processing_hook(self, hook_name: str, *args: Any, **kwargs: Any) -> None:
@@ -1715,9 +1294,7 @@ class BasePlatformAdapter(ABC):
             # session lifecycle and its cleanup races with the running task
             # (see PR #4926).
             cmd = event.get_command()
-            from hermes_cli.commands import should_bypass_active_session
-
-            if should_bypass_active_session(cmd):
+            if cmd in ("approve", "deny", "status", "stop", "new", "reset"):
                 logger.debug(
                     "[%s] Command '/%s' bypassing active-session guard for %s",
                     self.name, cmd, session_key,
@@ -1736,19 +1313,19 @@ class BasePlatformAdapter(ABC):
                     logger.error("[%s] Command '/%s' dispatch failed: %s", self.name, cmd, e, exc_info=True)
                 return
 
-            if self._busy_session_handler is not None:
-                try:
-                    if await self._busy_session_handler(event, session_key):
-                        return
-                except Exception as e:
-                    logger.error("[%s] Busy-session handler failed: %s", self.name, e, exc_info=True)
-
             # Special case: photo bursts/albums frequently arrive as multiple near-
             # simultaneous messages. Queue them without interrupting the active run,
             # then process them immediately after the current task finishes.
             if event.message_type == MessageType.PHOTO:
                 logger.debug("[%s] Queuing photo follow-up for session %s without interrupt", self.name, session_key)
-                merge_pending_message_event(self._pending_messages, session_key, event)
+                existing = self._pending_messages.get(session_key)
+                if existing and existing.message_type == MessageType.PHOTO:
+                    existing.media_urls.extend(event.media_urls)
+                    existing.media_types.extend(event.media_types)
+                    if event.text:
+                        existing.text = self._merge_caption(existing.text, event.text)
+                else:
+                    self._pending_messages[session_key] = event
                 return  # Don't interrupt now - will run after current task completes
 
             # Default behavior for non-photo follow-ups: interrupt the running agent
@@ -1775,7 +1352,6 @@ class BasePlatformAdapter(ABC):
             return
         if hasattr(task, "add_done_callback"):
             task.add_done_callback(self._background_tasks.discard)
-            task.add_done_callback(self._expected_cancelled_tasks.discard)
     
     @staticmethod
     def _get_human_delay() -> float:
@@ -1817,23 +1393,10 @@ class BasePlatformAdapter(ABC):
         # Fall back to a new Event only if the entry was removed externally.
         interrupt_event = self._active_sessions.get(session_key) or asyncio.Event()
         self._active_sessions[session_key] = interrupt_event
-        callback_generation = getattr(interrupt_event, "_hermes_run_generation", None)
         
         # Start continuous typing indicator (refreshes every 2 seconds)
         _thread_metadata = {"thread_id": event.source.thread_id} if event.source.thread_id else None
-        _keep_typing_kwargs = {"metadata": _thread_metadata}
-        try:
-            _keep_typing_sig = inspect.signature(self._keep_typing)
-        except (TypeError, ValueError):
-            _keep_typing_sig = None
-        if _keep_typing_sig is None or "stop_event" in _keep_typing_sig.parameters:
-            _keep_typing_kwargs["stop_event"] = interrupt_event
-        typing_task = asyncio.create_task(
-            self._keep_typing(
-                event.source.chat_id,
-                **_keep_typing_kwargs,
-            )
-        )
+        typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id, metadata=_thread_metadata))
         
         try:
             await self._run_processing_hook("on_processing_start", event)
@@ -1845,21 +1408,6 @@ class BasePlatformAdapter(ABC):
             # streaming already delivered the text (already_sent=True) or
             # when the message was queued behind an active agent.  Log at
             # DEBUG to avoid noisy warnings for expected behavior.
-            #
-            # Suppress stale response when the session was interrupted by a
-            # new message that hasn't been consumed yet.  The pending message
-            # is processed by the pending-message handler below (#8221/#2483).
-            if (
-                response
-                and interrupt_event.is_set()
-                and session_key in self._pending_messages
-            ):
-                logger.info(
-                    "[%s] Suppressing stale response for interrupted session %s",
-                    self.name,
-                    session_key,
-                )
-                response = None
             if not response:
                 logger.debug("[%s] Handler returned empty/None response for %s", self.name, event.source.chat_id)
             if response:
@@ -1940,7 +1488,7 @@ class BasePlatformAdapter(ABC):
                         logger.info(
                             "[%s] Sending image: %s (alt=%s)",
                             self.name,
-                            safe_url_for_log(image_url),
+                            _safe_url_for_log(image_url),
                             alt_text[:30] if alt_text else "",
                         )
                         # Route animated GIFs through send_animation for proper playback
@@ -2032,28 +1580,15 @@ class BasePlatformAdapter(ABC):
 
             # Determine overall success for the processing hook
             processing_ok = delivery_succeeded if delivery_attempted else not bool(response)
-            await self._run_processing_hook(
-                "on_processing_complete",
-                event,
-                ProcessingOutcome.SUCCESS if processing_ok else ProcessingOutcome.FAILURE,
-            )
+            await self._run_processing_hook("on_processing_complete", event, processing_ok)
 
             # Check if there's a pending message that was queued during our processing
             if session_key in self._pending_messages:
                 pending_event = self._pending_messages.pop(session_key)
                 logger.debug("[%s] Processing queued message from interrupt", self.name)
-                # Keep the _active_sessions entry live across the turn chain
-                # and only CLEAR the interrupt Event — do NOT delete the entry.
-                # If we deleted here, a concurrent inbound message arriving
-                # during the awaits below would pass the Level-1 guard, spawn
-                # its own _process_message_background, and run simultaneously
-                # with the recursive drain below.  Two agents on one
-                # session_key = duplicate responses, duplicate tool calls.
-                # Clearing the Event keeps the guard live so follow-ups take
-                # the busy-handler path (queue + interrupt) as intended.
-                _active = self._active_sessions.get(session_key)
-                if _active is not None:
-                    _active.clear()
+                # Clean up current session before processing pending
+                if session_key in self._active_sessions:
+                    del self._active_sessions[session_key]
                 typing_task.cancel()
                 try:
                     await typing_task
@@ -2064,14 +1599,10 @@ class BasePlatformAdapter(ABC):
                 return  # Already cleaned up
                 
         except asyncio.CancelledError:
-            current_task = asyncio.current_task()
-            outcome = ProcessingOutcome.CANCELLED
-            if current_task is None or current_task not in self._expected_cancelled_tasks:
-                outcome = ProcessingOutcome.FAILURE
-            await self._run_processing_hook("on_processing_complete", event, outcome)
+            await self._run_processing_hook("on_processing_complete", event, False)
             raise
         except Exception as e:
-            await self._run_processing_hook("on_processing_complete", event, ProcessingOutcome.FAILURE)
+            await self._run_processing_hook("on_processing_complete", event, False)
             logger.error("[%s] Error handling message: %s", self.name, e, exc_info=True)
             # Send the error to the user so they aren't left with radio silence
             try:
@@ -2090,21 +1621,6 @@ class BasePlatformAdapter(ABC):
             except Exception:
                 pass  # Last resort — don't let error reporting crash the handler
         finally:
-            # Fire any one-shot post-delivery callback registered for this
-            # session (e.g. deferred background-review notifications).
-            _callback_generation = callback_generation
-            if hasattr(self, "pop_post_delivery_callback"):
-                _post_cb = self.pop_post_delivery_callback(
-                    session_key,
-                    generation=_callback_generation,
-                )
-            else:
-                _post_cb = getattr(self, "_post_delivery_callbacks", {}).pop(session_key, None)
-            if callable(_post_cb):
-                try:
-                    _post_cb()
-                except Exception:
-                    pass
             # Stop typing indicator
             typing_task.cancel()
             try:
@@ -2118,37 +1634,9 @@ class BasePlatformAdapter(ABC):
                     await self.stop_typing(event.source.chat_id)
             except Exception:
                 pass
-            # Late-arrival drain: a message may have arrived during the
-            # cleanup awaits above (typing_task cancel, stop_typing).  Such
-            # messages passed the Level-1 guard (entry still live, Event
-            # possibly set) and landed in _pending_messages via the
-            # busy-handler path.  Without this block, we would delete the
-            # active-session entry and the queued message would be silently
-            # dropped (user never gets a reply).
-            late_pending = self._pending_messages.pop(session_key, None)
-            if late_pending is not None:
-                logger.debug(
-                    "[%s] Late-arrival pending message during cleanup — spawning drain task",
-                    self.name,
-                )
-                _active = self._active_sessions.get(session_key)
-                if _active is not None:
-                    _active.clear()
-                drain_task = asyncio.create_task(
-                    self._process_message_background(late_pending, session_key)
-                )
-                try:
-                    self._background_tasks.add(drain_task)
-                    drain_task.add_done_callback(self._background_tasks.discard)
-                except TypeError:
-                    # Tests stub create_task() with non-hashable sentinels; tolerate.
-                    pass
-                # Leave _active_sessions[session_key] populated — the drain
-                # task's own lifecycle will clean it up.
-            else:
-                # Clean up session tracking
-                if session_key in self._active_sessions:
-                    del self._active_sessions[session_key]
+            # Clean up session tracking
+            if session_key in self._active_sessions:
+                del self._active_sessions[session_key]
     
     async def cancel_background_tasks(self) -> None:
         """Cancel any in-flight background message-processing tasks.
@@ -2156,28 +1644,12 @@ class BasePlatformAdapter(ABC):
         Used during gateway shutdown/replacement so active sessions from the old
         process do not keep running after adapters are being torn down.
         """
-        # Loop until no new tasks appear.  Without this, a message
-        # arriving during the `await asyncio.gather` below would spawn
-        # a fresh _process_message_background task (added to
-        # self._background_tasks at line ~1668 via handle_message),
-        # and the _background_tasks.clear() at the end of this method
-        # would drop the reference — the task runs untracked against a
-        # disconnecting adapter, logs send-failures, and may linger
-        # until it completes on its own.  Retrying the drain until the
-        # task set stabilizes closes the window.
-        MAX_DRAIN_ROUNDS = 5
-        for _ in range(MAX_DRAIN_ROUNDS):
-            tasks = [task for task in self._background_tasks if not task.done()]
-            if not tasks:
-                break
-            for task in tasks:
-                self._expected_cancelled_tasks.add(task)
-                task.cancel()
+        tasks = [task for task in self._background_tasks if not task.done()]
+        for task in tasks:
+            task.cancel()
+        if tasks:
             await asyncio.gather(*tasks, return_exceptions=True)
-            # Loop: late-arrival tasks spawned during the gather above
-            # will be in self._background_tasks now.  Re-check.
         self._background_tasks.clear()
-        self._expected_cancelled_tasks.clear()
         self._pending_messages.clear()
         self._active_sessions.clear()
 
@@ -2200,7 +1672,6 @@ class BasePlatformAdapter(ABC):
         chat_topic: Optional[str] = None,
         user_id_alt: Optional[str] = None,
         chat_id_alt: Optional[str] = None,
-        is_bot: bool = False,
     ) -> SessionSource:
         """Helper to build a SessionSource for this platform."""
         # Normalize empty topic to None
@@ -2217,7 +1688,6 @@ class BasePlatformAdapter(ABC):
             chat_topic=chat_topic.strip() if chat_topic else None,
             user_id_alt=user_id_alt,
             chat_id_alt=chat_id_alt,
-            is_bot=is_bot,
         )
     
     @abstractmethod
@@ -2243,11 +1713,7 @@ class BasePlatformAdapter(ABC):
         return content
     
     @staticmethod
-    def truncate_message(
-        content: str,
-        max_length: int = 4096,
-        len_fn: Optional["Callable[[str], int]"] = None,
-    ) -> List[str]:
+    def truncate_message(content: str, max_length: int = 4096) -> List[str]:
         """
         Split a long message into chunks, preserving code block boundaries.
 
@@ -2259,16 +1725,11 @@ class BasePlatformAdapter(ABC):
         Args:
             content: The full message content
             max_length: Maximum length per chunk (platform-specific)
-            len_fn: Optional length function for measuring string length.
-                     Defaults to ``len`` (Unicode code-points).  Pass
-                     ``utf16_len`` for platforms that measure message
-                     length in UTF-16 code units (e.g. Telegram).
 
         Returns:
             List of message chunks
         """
-        _len = len_fn or len
-        if _len(content) <= max_length:
+        if len(content) <= max_length:
             return [content]
 
         INDICATOR_RESERVE = 10   # room for " (XX/XX)"
@@ -2287,33 +1748,22 @@ class BasePlatformAdapter(ABC):
 
             # How much body text we can fit after accounting for the prefix,
             # a potential closing fence, and the chunk indicator.
-            headroom = max_length - INDICATOR_RESERVE - _len(prefix) - _len(FENCE_CLOSE)
+            headroom = max_length - INDICATOR_RESERVE - len(prefix) - len(FENCE_CLOSE)
             if headroom < 1:
                 headroom = max_length // 2
 
             # Everything remaining fits in one final chunk
-            if _len(prefix) + _len(remaining) <= max_length - INDICATOR_RESERVE:
+            if len(prefix) + len(remaining) <= max_length - INDICATOR_RESERVE:
                 chunks.append(prefix + remaining)
                 break
 
-            # Find a natural split point (prefer newlines, then spaces).
-            # When _len != len (e.g. utf16_len for Telegram), headroom is
-            # measured in the custom unit.  We need codepoint-based slice
-            # positions that stay within the custom-unit budget.
-            #
-            # _safe_slice_pos() maps a custom-unit budget to the largest
-            # codepoint offset whose custom length ≤ budget.
-            if _len is not len:
-                # Map headroom (custom units) → codepoint slice length
-                _cp_limit = _custom_unit_to_cp(remaining, headroom, _len)
-            else:
-                _cp_limit = headroom
-            region = remaining[:_cp_limit]
+            # Find a natural split point (prefer newlines, then spaces)
+            region = remaining[:headroom]
             split_at = region.rfind("\n")
-            if split_at < _cp_limit // 2:
+            if split_at < headroom // 2:
                 split_at = region.rfind(" ")
             if split_at < 1:
-                split_at = _cp_limit
+                split_at = headroom
 
             # Avoid splitting inside an inline code span (`...`).
             # If the text before split_at has an odd number of unescaped
@@ -2333,7 +1783,7 @@ class BasePlatformAdapter(ABC):
                     safe_split = candidate.rfind(" ", 0, last_bt)
                     nl_split = candidate.rfind("\n", 0, last_bt)
                     safe_split = max(safe_split, nl_split)
-                    if safe_split > _cp_limit // 4:
+                    if safe_split > headroom // 4:
                         split_at = safe_split
 
             chunk_body = remaining[:split_at]

gateway/platforms/bluebubbles.py

@@ -30,7 +30,6 @@ from gateway.platforms.base import (
     cache_audio_from_bytes,
     cache_document_from_bytes,
 )
-from gateway.platforms.helpers import strip_markdown
 
 logger = logging.getLogger(__name__)
 
@@ -90,7 +89,18 @@ def _normalize_server_url(raw: str) -> str:
     return value.rstrip("/")
 
 
-
+def _strip_markdown(text: str) -> str:
+    """Strip common markdown formatting for iMessage plain-text delivery."""
+    text = re.sub(r"\*\*(.+?)\*\*", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"\*(.+?)\*", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"__(.+?)__", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"_(.+?)_", r"\1", text, flags=re.DOTALL)
+    text = re.sub(r"```[a-zA-Z0-9_+-]*\n?", "", text)
+    text = re.sub(r"`(.+?)`", r"\1", text)
+    text = re.sub(r"^#{1,6}\s+", "", text, flags=re.MULTILINE)
+    text = re.sub(r"\[([^\]]+)\]\(([^\)]+)\)", r"\1", text)
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    return text.strip()
 
 
 # ---------------------------------------------------------------------------
@@ -197,17 +207,9 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             self.webhook_port,
             self.webhook_path,
         )
-
-        # Register webhook with BlueBubbles server
-        # This is required for the server to know where to send events
-        await self._register_webhook()
-
         return True
 
     async def disconnect(self) -> None:
-        # Unregister webhook before cleaning up
-        await self._unregister_webhook()
-
         if self.client:
             await self.client.aclose()
             self.client = None
@@ -216,120 +218,6 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             self._runner = None
         self._mark_disconnected()
 
-    @property
-    def _webhook_url(self) -> str:
-        """Compute the external webhook URL for BlueBubbles registration."""
-        host = self.webhook_host
-        if host in ("0.0.0.0", "127.0.0.1", "localhost", "::"):
-            host = "localhost"
-        return f"http://{host}:{self.webhook_port}{self.webhook_path}"
-
-    @property
-    def _webhook_register_url(self) -> str:
-        """Webhook URL registered with BlueBubbles, including the password as
-        a query param so inbound webhook POSTs carry credentials.
-
-        BlueBubbles posts events to the exact URL registered via
-        ``/api/v1/webhook``. Its webhook registration API does not support
-        custom headers, so embedding the password in the URL is the only
-        way to authenticate inbound webhooks without disabling auth.
-        """
-        base = self._webhook_url
-        if self.password:
-            return f"{base}?password={quote(self.password, safe='')}"
-        return base
-
-    async def _find_registered_webhooks(self, url: str) -> list:
-        """Return list of BB webhook entries matching *url*."""
-        try:
-            res = await self._api_get("/api/v1/webhook")
-            data = res.get("data")
-            if isinstance(data, list):
-                return [wh for wh in data if wh.get("url") == url]
-        except Exception:
-            pass
-        return []
-
-    async def _register_webhook(self) -> bool:
-        """Register this webhook URL with the BlueBubbles server.
-
-        BlueBubbles requires webhooks to be registered via API before
-        it will send events.  Checks for an existing registration first
-        to avoid duplicates (e.g. after a crash without clean shutdown).
-        """
-        if not self.client:
-            return False
-
-        webhook_url = self._webhook_register_url
-
-        # Crash resilience — reuse an existing registration if present
-        existing = await self._find_registered_webhooks(webhook_url)
-        if existing:
-            logger.info(
-                "[bluebubbles] webhook already registered: %s", webhook_url
-            )
-            return True
-
-        payload = {
-            "url": webhook_url,
-            "events": ["new-message", "updated-message"],
-        }
-
-        try:
-            res = await self._api_post("/api/v1/webhook", payload)
-            status = res.get("status", 0)
-            if 200 <= status < 300:
-                logger.info(
-                    "[bluebubbles] webhook registered with server: %s",
-                    webhook_url,
-                )
-                return True
-            else:
-                logger.warning(
-                    "[bluebubbles] webhook registration returned status %s: %s",
-                    status,
-                    res.get("message"),
-                )
-                return False
-        except Exception as exc:
-            logger.warning(
-                "[bluebubbles] failed to register webhook with server: %s",
-                exc,
-            )
-            return False
-
-    async def _unregister_webhook(self) -> bool:
-        """Unregister this webhook URL from the BlueBubbles server.
-
-        Removes *all* matching registrations to clean up any duplicates
-        left by prior crashes.
-        """
-        if not self.client:
-            return False
-
-        webhook_url = self._webhook_register_url
-        removed = False
-
-        try:
-            for wh in await self._find_registered_webhooks(webhook_url):
-                wh_id = wh.get("id")
-                if wh_id:
-                    res = await self.client.delete(
-                        self._api_url(f"/api/v1/webhook/{wh_id}")
-                    )
-                    res.raise_for_status()
-                    removed = True
-            if removed:
-                logger.info(
-                    "[bluebubbles] webhook unregistered: %s", webhook_url
-                )
-        except Exception as exc:
-            logger.debug(
-                "[bluebubbles] failed to unregister webhook (non-critical): %s",
-                exc,
-            )
-        return removed
-
     # ------------------------------------------------------------------
     # Chat GUID resolution
     # ------------------------------------------------------------------
@@ -398,7 +286,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None,
     ) -> SendResult:
-        text = strip_markdown(content or "")
+        text = _strip_markdown(content or "")
         if not text:
             return SendResult(success=False, error="BlueBubbles send requires text")
         chunks = self.truncate_message(text, max_length=self.MAX_MESSAGE_LENGTH)
@@ -619,6 +507,35 @@ class BlueBubblesAdapter(BasePlatformAdapter):
     # Tapback reactions
     # ------------------------------------------------------------------
 
+    async def send_reaction(
+        self,
+        chat_id: str,
+        message_guid: str,
+        reaction: str,
+        part_index: int = 0,
+    ) -> SendResult:
+        """Send a tapback reaction (requires Private API helper)."""
+        if not self._private_api_enabled or not self._helper_connected:
+            return SendResult(
+                success=False, error="Private API helper not connected"
+            )
+        guid = await self._resolve_chat_guid(chat_id)
+        if not guid:
+            return SendResult(success=False, error=f"Chat not found: {chat_id}")
+        try:
+            res = await self._api_post(
+                "/api/v1/message/react",
+                {
+                    "chatGuid": guid,
+                    "selectedMessageGuid": message_guid,
+                    "reaction": reaction,
+                    "partIndex": part_index,
+                },
+            )
+            return SendResult(success=True, raw_response=res)
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
     # ------------------------------------------------------------------
     # Chat info
     # ------------------------------------------------------------------
@@ -655,7 +572,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
         return info
 
     def format_message(self, content: str) -> str:
-        return strip_markdown(content)
+        return _strip_markdown(content)
 
     # ------------------------------------------------------------------
     # Inbound attachment downloading (from #4588)
@@ -850,12 +767,6 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             payload.get("chat_guid"),
             payload.get("guid"),
         )
-        # Fallback: BlueBubbles v1.9+ webhook payloads omit top-level chatGuid;
-        # the chat GUID is nested under data.chats[0].guid instead.
-        if not chat_guid:
-            _chats = record.get("chats") or []
-            if _chats and isinstance(_chats[0], dict):
-                chat_guid = _chats[0].get("guid") or _chats[0].get("chatGuid")
         chat_identifier = self._value(
             record.get("chatIdentifier"),
             record.get("identifier"),
@@ -915,4 +826,3 @@ class BlueBubblesAdapter(BasePlatformAdapter):
             asyncio.create_task(self.mark_read(session_chat_id))
 
         return web.Response(text="ok")
-

gateway/platforms/email.py

@@ -195,11 +195,7 @@ def _extract_attachments(
 
         ext = Path(filename).suffix.lower()
         if ext in _IMAGE_EXTS:
-            try:
-                cached_path = cache_image_from_bytes(payload, ext)
-            except ValueError:
-                logger.debug("Skipping non-image attachment %s (invalid magic bytes)", filename)
-                continue
+            cached_path = cache_image_from_bytes(payload, ext)
             attachments.append({
                 "path": cached_path,
                 "filename": filename,

gateway/platforms/feishu_comment_rules.py

@@ -1,429 +0,0 @@
-"""
-Feishu document comment access-control rules.
-
-3-tier rule resolution: exact doc > wildcard "*" > top-level > code defaults.
-Each field (enabled/policy/allow_from) falls back independently.
-Config: ~/.hermes/feishu_comment_rules.json (mtime-cached, hot-reload).
-Pairing store: ~/.hermes/feishu_comment_pairing.json.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import time
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Any, Dict, Optional
-
-from hermes_constants import get_hermes_home
-
-logger = logging.getLogger(__name__)
-
-# ---------------------------------------------------------------------------
-# Paths
-# ---------------------------------------------------------------------------
-#
-# Uses the canonical ``get_hermes_home()`` helper (HERMES_HOME-aware and
-# profile-safe). Resolved at import time; this module is lazy-imported by
-# the Feishu comment event handler, which runs long after profile overrides
-# have been applied, so freezing paths here is safe.
-
-RULES_FILE = get_hermes_home() / "feishu_comment_rules.json"
-PAIRING_FILE = get_hermes_home() / "feishu_comment_pairing.json"
-
-# ---------------------------------------------------------------------------
-# Data models
-# ---------------------------------------------------------------------------
-
-_VALID_POLICIES = ("allowlist", "pairing")
-
-
-@dataclass(frozen=True)
-class CommentDocumentRule:
-    """Per-document rule.  ``None`` means 'inherit from lower tier'."""
-    enabled: Optional[bool] = None
-    policy: Optional[str] = None
-    allow_from: Optional[frozenset] = None
-
-
-@dataclass(frozen=True)
-class CommentsConfig:
-    """Top-level comment access config."""
-    enabled: bool = True
-    policy: str = "pairing"
-    allow_from: frozenset = field(default_factory=frozenset)
-    documents: Dict[str, CommentDocumentRule] = field(default_factory=dict)
-
-
-@dataclass(frozen=True)
-class ResolvedCommentRule:
-    """Fully resolved rule after field-by-field fallback."""
-    enabled: bool
-    policy: str
-    allow_from: frozenset
-    match_source: str  # e.g. "exact:docx:xxx" | "wildcard" | "top" | "default"
-
-
-# ---------------------------------------------------------------------------
-# Mtime-cached file loading
-# ---------------------------------------------------------------------------
-
-class _MtimeCache:
-    """Generic mtime-based file cache.  ``stat()`` per access, re-read only on change."""
-
-    def __init__(self, path: Path):
-        self._path = path
-        self._mtime: float = 0.0
-        self._data: Optional[dict] = None
-
-    def load(self) -> dict:
-        try:
-            st = self._path.stat()
-            mtime = st.st_mtime
-        except FileNotFoundError:
-            self._mtime = 0.0
-            self._data = {}
-            return {}
-
-        if mtime == self._mtime and self._data is not None:
-            return self._data
-
-        try:
-            with open(self._path, "r", encoding="utf-8") as f:
-                data = json.load(f)
-            if not isinstance(data, dict):
-                data = {}
-        except (json.JSONDecodeError, OSError):
-            logger.warning("[Feishu-Rules] Failed to read %s, using empty config", self._path)
-            data = {}
-
-        self._mtime = mtime
-        self._data = data
-        return data
-
-
-_rules_cache = _MtimeCache(RULES_FILE)
-_pairing_cache = _MtimeCache(PAIRING_FILE)
-
-
-# ---------------------------------------------------------------------------
-# Config parsing
-# ---------------------------------------------------------------------------
-
-def _parse_frozenset(raw: Any) -> Optional[frozenset]:
-    """Parse a list of strings into a frozenset; return None if key absent."""
-    if raw is None:
-        return None
-    if isinstance(raw, (list, tuple)):
-        return frozenset(str(u).strip() for u in raw if str(u).strip())
-    return None
-
-
-def _parse_document_rule(raw: dict) -> CommentDocumentRule:
-    enabled = raw.get("enabled")
-    if enabled is not None:
-        enabled = bool(enabled)
-    policy = raw.get("policy")
-    if policy is not None:
-        policy = str(policy).strip().lower()
-        if policy not in _VALID_POLICIES:
-            policy = None
-    allow_from = _parse_frozenset(raw.get("allow_from"))
-    return CommentDocumentRule(enabled=enabled, policy=policy, allow_from=allow_from)
-
-
-def load_config() -> CommentsConfig:
-    """Load comment rules from disk (mtime-cached)."""
-    raw = _rules_cache.load()
-    if not raw:
-        return CommentsConfig()
-
-    documents: Dict[str, CommentDocumentRule] = {}
-    raw_docs = raw.get("documents", {})
-    if isinstance(raw_docs, dict):
-        for key, rule_raw in raw_docs.items():
-            if isinstance(rule_raw, dict):
-                documents[str(key)] = _parse_document_rule(rule_raw)
-
-    policy = str(raw.get("policy", "pairing")).strip().lower()
-    if policy not in _VALID_POLICIES:
-        policy = "pairing"
-
-    return CommentsConfig(
-        enabled=raw.get("enabled", True),
-        policy=policy,
-        allow_from=_parse_frozenset(raw.get("allow_from")) or frozenset(),
-        documents=documents,
-    )
-
-
-# ---------------------------------------------------------------------------
-# Rule resolution  (§8.4 field-by-field fallback)
-# ---------------------------------------------------------------------------
-
-def has_wiki_keys(cfg: CommentsConfig) -> bool:
-    """Check if any document rule key starts with 'wiki:'."""
-    return any(k.startswith("wiki:") for k in cfg.documents)
-
-
-def resolve_rule(
-    cfg: CommentsConfig,
-    file_type: str,
-    file_token: str,
-    wiki_token: str = "",
-) -> ResolvedCommentRule:
-    """Resolve effective rule: exact doc → wiki key → wildcard → top-level → defaults."""
-    exact_key = f"{file_type}:{file_token}"
-
-    exact = cfg.documents.get(exact_key)
-    exact_src = f"exact:{exact_key}"
-    if exact is None and wiki_token:
-        wiki_key = f"wiki:{wiki_token}"
-        exact = cfg.documents.get(wiki_key)
-        exact_src = f"exact:{wiki_key}"
-
-    wildcard = cfg.documents.get("*")
-
-    layers = []
-    if exact is not None:
-        layers.append((exact, exact_src))
-    if wildcard is not None:
-        layers.append((wildcard, "wildcard"))
-
-    def _pick(field_name: str):
-        for layer, source in layers:
-            val = getattr(layer, field_name)
-            if val is not None:
-                return val, source
-        return getattr(cfg, field_name), "top"
-
-    enabled, en_src = _pick("enabled")
-    policy, pol_src = _pick("policy")
-    allow_from, _ = _pick("allow_from")
-
-    # match_source = highest-priority tier that contributed any field
-    priority_order = {"exact": 0, "wildcard": 1, "top": 2}
-    best_src = min(
-        [en_src, pol_src],
-        key=lambda s: priority_order.get(s.split(":")[0], 3),
-    )
-
-    return ResolvedCommentRule(
-        enabled=enabled,
-        policy=policy,
-        allow_from=allow_from,
-        match_source=best_src,
-    )
-
-
-# ---------------------------------------------------------------------------
-# Pairing store
-# ---------------------------------------------------------------------------
-
-def _load_pairing_approved() -> set:
-    """Return set of approved user open_ids (mtime-cached)."""
-    data = _pairing_cache.load()
-    approved = data.get("approved", {})
-    if isinstance(approved, dict):
-        return set(approved.keys())
-    if isinstance(approved, list):
-        return set(str(u) for u in approved if u)
-    return set()
-
-
-def _save_pairing(data: dict) -> None:
-    PAIRING_FILE.parent.mkdir(parents=True, exist_ok=True)
-    tmp = PAIRING_FILE.with_suffix(".tmp")
-    with open(tmp, "w", encoding="utf-8") as f:
-        json.dump(data, f, indent=2, ensure_ascii=False)
-    tmp.replace(PAIRING_FILE)
-    # Invalidate cache so next load picks up change
-    _pairing_cache._mtime = 0.0
-    _pairing_cache._data = None
-
-
-def pairing_add(user_open_id: str) -> bool:
-    """Add a user to the pairing-approved list. Returns True if newly added."""
-    data = _pairing_cache.load()
-    approved = data.get("approved", {})
-    if not isinstance(approved, dict):
-        approved = {}
-    if user_open_id in approved:
-        return False
-    approved[user_open_id] = {"approved_at": time.time()}
-    data["approved"] = approved
-    _save_pairing(data)
-    return True
-
-
-def pairing_remove(user_open_id: str) -> bool:
-    """Remove a user from the pairing-approved list. Returns True if removed."""
-    data = _pairing_cache.load()
-    approved = data.get("approved", {})
-    if not isinstance(approved, dict):
-        return False
-    if user_open_id not in approved:
-        return False
-    del approved[user_open_id]
-    data["approved"] = approved
-    _save_pairing(data)
-    return True
-
-
-def pairing_list() -> Dict[str, Any]:
-    """Return the approved dict  {user_open_id: {approved_at: ...}}."""
-    data = _pairing_cache.load()
-    approved = data.get("approved", {})
-    return dict(approved) if isinstance(approved, dict) else {}
-
-
-# ---------------------------------------------------------------------------
-# Access check  (public API for feishu_comment.py)
-# ---------------------------------------------------------------------------
-
-def is_user_allowed(rule: ResolvedCommentRule, user_open_id: str) -> bool:
-    """Check if user passes the resolved rule's policy gate."""
-    if user_open_id in rule.allow_from:
-        return True
-    if rule.policy == "pairing":
-        return user_open_id in _load_pairing_approved()
-    return False
-
-
-# ---------------------------------------------------------------------------
-# CLI
-# ---------------------------------------------------------------------------
-
-def _print_status() -> None:
-    cfg = load_config()
-    print(f"Rules file: {RULES_FILE}")
-    print(f"  exists: {RULES_FILE.exists()}")
-    print(f"Pairing file: {PAIRING_FILE}")
-    print(f"  exists: {PAIRING_FILE.exists()}")
-    print()
-    print(f"Top-level:")
-    print(f"  enabled:    {cfg.enabled}")
-    print(f"  policy:     {cfg.policy}")
-    print(f"  allow_from: {sorted(cfg.allow_from) if cfg.allow_from else '[]'}")
-    print()
-    if cfg.documents:
-        print(f"Document rules ({len(cfg.documents)}):")
-        for key, rule in sorted(cfg.documents.items()):
-            parts = []
-            if rule.enabled is not None:
-                parts.append(f"enabled={rule.enabled}")
-            if rule.policy is not None:
-                parts.append(f"policy={rule.policy}")
-            if rule.allow_from is not None:
-                parts.append(f"allow_from={sorted(rule.allow_from)}")
-            print(f"  [{key}] {', '.join(parts) if parts else '(empty — inherits all)'}")
-    else:
-        print("Document rules: (none)")
-    print()
-    approved = pairing_list()
-    print(f"Pairing approved ({len(approved)}):")
-    for uid, meta in sorted(approved.items()):
-        ts = meta.get("approved_at", 0)
-        print(f"  {uid}  (approved_at={ts})")
-
-
-def _do_check(doc_key: str, user_open_id: str) -> None:
-    cfg = load_config()
-    parts = doc_key.split(":", 1)
-    if len(parts) != 2:
-        print(f"Error: doc_key must be 'fileType:fileToken', got '{doc_key}'")
-        return
-    file_type, file_token = parts
-    rule = resolve_rule(cfg, file_type, file_token)
-    allowed = is_user_allowed(rule, user_open_id)
-    print(f"Document:     {doc_key}")
-    print(f"User:         {user_open_id}")
-    print(f"Resolved rule:")
-    print(f"  enabled:      {rule.enabled}")
-    print(f"  policy:       {rule.policy}")
-    print(f"  allow_from:   {sorted(rule.allow_from) if rule.allow_from else '[]'}")
-    print(f"  match_source: {rule.match_source}")
-    print(f"Result:       {'ALLOWED' if allowed else 'DENIED'}")
-
-
-def _main() -> int:
-    import sys
-
-    try:
-        from hermes_cli.env_loader import load_hermes_dotenv
-        load_hermes_dotenv()
-    except Exception:
-        pass
-
-    usage = (
-        "Usage: python -m gateway.platforms.feishu_comment_rules <command> [args]\n"
-        "\n"
-        "Commands:\n"
-        "  status                              Show rules config and pairing state\n"
-        "  check <fileType:token> <user>        Simulate access check\n"
-        "  pairing add <user_open_id>           Add user to pairing-approved list\n"
-        "  pairing remove <user_open_id>        Remove user from pairing-approved list\n"
-        "  pairing list                         List pairing-approved users\n"
-        "\n"
-        f"Rules config file: {RULES_FILE}\n"
-        "  Edit this JSON file directly to configure policies and document rules.\n"
-        "  Changes take effect on the next comment event (no restart needed).\n"
-    )
-
-    args = sys.argv[1:]
-    if not args:
-        print(usage)
-        return 1
-
-    cmd = args[0]
-
-    if cmd == "status":
-        _print_status()
-
-    elif cmd == "check":
-        if len(args) < 3:
-            print("Usage: check <fileType:fileToken> <user_open_id>")
-            return 1
-        _do_check(args[1], args[2])
-
-    elif cmd == "pairing":
-        if len(args) < 2:
-            print("Usage: pairing <add|remove|list> [args]")
-            return 1
-        sub = args[1]
-        if sub == "add":
-            if len(args) < 3:
-                print("Usage: pairing add <user_open_id>")
-                return 1
-            if pairing_add(args[2]):
-                print(f"Added: {args[2]}")
-            else:
-                print(f"Already approved: {args[2]}")
-        elif sub == "remove":
-            if len(args) < 3:
-                print("Usage: pairing remove <user_open_id>")
-                return 1
-            if pairing_remove(args[2]):
-                print(f"Removed: {args[2]}")
-            else:
-                print(f"Not in approved list: {args[2]}")
-        elif sub == "list":
-            approved = pairing_list()
-            if not approved:
-                print("(no approved users)")
-            for uid, meta in sorted(approved.items()):
-                print(f"  {uid}  approved_at={meta.get('approved_at', '?')}")
-        else:
-            print(f"Unknown pairing subcommand: {sub}")
-            return 1
-    else:
-        print(f"Unknown command: {cmd}\n")
-        print(usage)
-        return 1
-    return 0
-
-
-if __name__ == "__main__":
-    import sys
-    sys.exit(_main())

gateway/platforms/helpers.py

@@ -1,264 +0,0 @@
-"""Shared helper classes for gateway platform adapters.
-
-Extracts common patterns that were duplicated across 5-7 adapters:
-message deduplication, text batch aggregation, markdown stripping,
-and thread participation tracking.
-"""
-
-import asyncio
-import json
-import logging
-import re
-import time
-from pathlib import Path
-from typing import TYPE_CHECKING, Dict, Optional
-
-if TYPE_CHECKING:
-    from gateway.platforms.base import BasePlatformAdapter, MessageEvent
-
-logger = logging.getLogger(__name__)
-
-
-# ─── Message Deduplication ────────────────────────────────────────────────────
-
-
-class MessageDeduplicator:
-    """TTL-based message deduplication cache.
-
-    Replaces the identical ``_seen_messages`` / ``_is_duplicate()`` pattern
-    previously duplicated in discord, slack, dingtalk, wecom, weixin,
-    mattermost, and feishu adapters.
-
-    Usage::
-
-        self._dedup = MessageDeduplicator()
-
-        # In message handler:
-        if self._dedup.is_duplicate(msg_id):
-            return
-    """
-
-    def __init__(self, max_size: int = 2000, ttl_seconds: float = 300):
-        self._seen: Dict[str, float] = {}
-        self._max_size = max_size
-        self._ttl = ttl_seconds
-
-    def is_duplicate(self, msg_id: str) -> bool:
-        """Return True if *msg_id* was already seen within the TTL window."""
-        if not msg_id:
-            return False
-        now = time.time()
-        if msg_id in self._seen:
-            if now - self._seen[msg_id] < self._ttl:
-                return True
-            # Entry has expired — remove it and treat as new
-            del self._seen[msg_id]
-        self._seen[msg_id] = now
-        if len(self._seen) > self._max_size:
-            cutoff = now - self._ttl
-            self._seen = {k: v for k, v in self._seen.items() if v > cutoff}
-        return False
-
-    def clear(self):
-        """Clear all tracked messages."""
-        self._seen.clear()
-
-
-# ─── Text Batch Aggregation ──────────────────────────────────────────────────
-
-
-class TextBatchAggregator:
-    """Aggregates rapid-fire text events into single messages.
-
-    Replaces the ``_enqueue_text_event`` / ``_flush_text_batch`` pattern
-    previously duplicated in telegram, discord, matrix, wecom, and feishu.
-
-    Usage::
-
-        self._text_batcher = TextBatchAggregator(
-            handler=self._message_handler,
-            batch_delay=0.6,
-            split_threshold=1900,
-        )
-
-        # In message dispatch:
-        if msg_type == MessageType.TEXT and self._text_batcher.is_enabled():
-            self._text_batcher.enqueue(event, session_key)
-            return
-    """
-
-    def __init__(
-        self,
-        handler,
-        *,
-        batch_delay: float = 0.6,
-        split_delay: float = 2.0,
-        split_threshold: int = 4000,
-    ):
-        self._handler = handler
-        self._batch_delay = batch_delay
-        self._split_delay = split_delay
-        self._split_threshold = split_threshold
-        self._pending: Dict[str, "MessageEvent"] = {}
-        self._pending_tasks: Dict[str, asyncio.Task] = {}
-
-    def is_enabled(self) -> bool:
-        """Return True if batching is active (delay > 0)."""
-        return self._batch_delay > 0
-
-    def enqueue(self, event: "MessageEvent", key: str) -> None:
-        """Add *event* to the pending batch for *key*."""
-        chunk_len = len(event.text or "")
-        existing = self._pending.get(key)
-        if not existing:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending[key] = event
-        else:
-            existing.text = f"{existing.text}\n{event.text}"
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-
-        # Cancel prior flush timer, start a new one
-        prior = self._pending_tasks.get(key)
-        if prior and not prior.done():
-            prior.cancel()
-        self._pending_tasks[key] = asyncio.create_task(self._flush(key))
-
-    async def _flush(self, key: str) -> None:
-        """Wait then dispatch the batched event for *key*."""
-        current_task = self._pending_tasks.get(key)
-        pending = self._pending.get(key)
-        last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-
-        # Use longer delay when the last chunk looks like a split message
-        delay = self._split_delay if last_len >= self._split_threshold else self._batch_delay
-        await asyncio.sleep(delay)
-
-        event = self._pending.pop(key, None)
-        if event:
-            try:
-                await self._handler(event)
-            except Exception:
-                logger.exception("[TextBatchAggregator] Error dispatching batched event for %s", key)
-
-        if self._pending_tasks.get(key) is current_task:
-            self._pending_tasks.pop(key, None)
-
-    def cancel_all(self) -> None:
-        """Cancel all pending flush tasks."""
-        for task in self._pending_tasks.values():
-            if not task.done():
-                task.cancel()
-        self._pending_tasks.clear()
-        self._pending.clear()
-
-
-# ─── Markdown Stripping ──────────────────────────────────────────────────────
-
-# Pre-compiled regexes for performance
-_RE_BOLD = re.compile(r"\*\*(.+?)\*\*", re.DOTALL)
-_RE_ITALIC_STAR = re.compile(r"\*(.+?)\*", re.DOTALL)
-_RE_BOLD_UNDER = re.compile(r"__(.+?)__", re.DOTALL)
-_RE_ITALIC_UNDER = re.compile(r"_(.+?)_", re.DOTALL)
-_RE_CODE_BLOCK = re.compile(r"```[a-zA-Z0-9_+-]*\n?")
-_RE_INLINE_CODE = re.compile(r"`(.+?)`")
-_RE_HEADING = re.compile(r"^#{1,6}\s+", re.MULTILINE)
-_RE_LINK = re.compile(r"\[([^\]]+)\]\([^\)]+\)")
-_RE_MULTI_NEWLINE = re.compile(r"\n{3,}")
-
-
-def strip_markdown(text: str) -> str:
-    """Strip markdown formatting for plain-text platforms (SMS, iMessage, etc.).
-
-    Replaces the identical ``_strip_markdown()`` functions previously
-    duplicated in sms.py, bluebubbles.py, and feishu.py.
-    """
-    text = _RE_BOLD.sub(r"\1", text)
-    text = _RE_ITALIC_STAR.sub(r"\1", text)
-    text = _RE_BOLD_UNDER.sub(r"\1", text)
-    text = _RE_ITALIC_UNDER.sub(r"\1", text)
-    text = _RE_CODE_BLOCK.sub("", text)
-    text = _RE_INLINE_CODE.sub(r"\1", text)
-    text = _RE_HEADING.sub("", text)
-    text = _RE_LINK.sub(r"\1", text)
-    text = _RE_MULTI_NEWLINE.sub("\n\n", text)
-    return text.strip()
-
-
-# ─── Thread Participation Tracking ───────────────────────────────────────────
-
-
-class ThreadParticipationTracker:
-    """Persistent tracking of threads the bot has participated in.
-
-    Replaces the identical ``_load/_save_participated_threads`` +
-    ``_mark_thread_participated`` pattern previously duplicated in
-    discord.py and matrix.py.
-
-    Usage::
-
-        self._threads = ThreadParticipationTracker("discord")
-
-        # Check membership:
-        if thread_id in self._threads:
-            ...
-
-        # Mark participation:
-        self._threads.mark(thread_id)
-    """
-
-    _MAX_TRACKED = 500
-
-    def __init__(self, platform_name: str, max_tracked: int = 500):
-        self._platform = platform_name
-        self._max_tracked = max_tracked
-        self._threads: set = self._load()
-
-    def _state_path(self) -> Path:
-        from hermes_constants import get_hermes_home
-        return get_hermes_home() / f"{self._platform}_threads.json"
-
-    def _load(self) -> set:
-        path = self._state_path()
-        if path.exists():
-            try:
-                return set(json.loads(path.read_text(encoding="utf-8")))
-            except Exception:
-                pass
-        return set()
-
-    def _save(self) -> None:
-        path = self._state_path()
-        path.parent.mkdir(parents=True, exist_ok=True)
-        thread_list = list(self._threads)
-        if len(thread_list) > self._max_tracked:
-            thread_list = thread_list[-self._max_tracked:]
-            self._threads = set(thread_list)
-        path.write_text(json.dumps(thread_list), encoding="utf-8")
-
-    def mark(self, thread_id: str) -> None:
-        """Mark *thread_id* as participated and persist."""
-        if thread_id not in self._threads:
-            self._threads.add(thread_id)
-            self._save()
-
-    def __contains__(self, thread_id: str) -> bool:
-        return thread_id in self._threads
-
-    def clear(self) -> None:
-        self._threads.clear()
-
-
-# ─── Phone Number Redaction ──────────────────────────────────────────────────
-
-
-def redact_phone(phone: str) -> str:
-    """Redact a phone number for logging, preserving country code and last 4.
-
-    Replaces the identical ``_redact_phone()`` functions in signal.py,
-    sms.py, and bluebubbles.py.
-    """
-    if not phone:
-        return "<none>"
-    if len(phone) <= 8:
-        return phone[:2] + "****" + phone[-2:] if len(phone) > 4 else "****"
-    return phone[:4] + "****" + phone[-4:]

gateway/platforms/mattermost.py

@@ -18,11 +18,11 @@ import json
 import logging
 import os
 import re
+import time
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -96,8 +96,10 @@ class MattermostAdapter(BasePlatformAdapter):
             or os.getenv("MATTERMOST_REPLY_MODE", "off")
         ).lower()
 
-        # Dedup cache (prevent reprocessing)
-        self._dedup = MessageDeduplicator()
+        # Dedup cache: post_id → timestamp (prevent reprocessing)
+        self._seen_posts: Dict[str, float] = {}
+        self._SEEN_MAX = 2000
+        self._SEEN_TTL = 300  # 5 minutes
 
     # ------------------------------------------------------------------
     # HTTP helpers
@@ -304,7 +306,7 @@ class MattermostAdapter(BasePlatformAdapter):
         )
 
     async def edit_message(
-        self, chat_id: str, message_id: str, content: str, *, finalize: bool = False
+        self, chat_id: str, message_id: str, content: str
     ) -> SendResult:
         """Edit an existing post."""
         formatted = self.format_message(content)
@@ -602,8 +604,10 @@ class MattermostAdapter(BasePlatformAdapter):
         post_id = post.get("id", "")
 
         # Dedup.
-        if self._dedup.is_duplicate(post_id):
+        self._prune_seen()
+        if post_id in self._seen_posts:
             return
+        self._seen_posts[post_id] = time.time()
 
         # Build message event.
         channel_id = post.get("channel_id", "")
@@ -718,12 +722,6 @@ class MattermostAdapter(BasePlatformAdapter):
             thread_id=thread_id,
         )
 
-        # Per-channel ephemeral prompt
-        from gateway.platforms.base import resolve_channel_prompt
-        _channel_prompt = resolve_channel_prompt(
-            self.config.extra, channel_id, None,
-        )
-
         msg_event = MessageEvent(
             text=message_text,
             message_type=msg_type,
@@ -732,9 +730,17 @@ class MattermostAdapter(BasePlatformAdapter):
             message_id=post_id,
             media_urls=media_urls if media_urls else None,
             media_types=media_types if media_types else None,
-            channel_prompt=_channel_prompt,
         )
 
         await self.handle_message(msg_event)
 
-
+    def _prune_seen(self) -> None:
+        """Remove expired entries from the dedup cache."""
+        if len(self._seen_posts) < self._SEEN_MAX:
+            return
+        now = time.time()
+        self._seen_posts = {
+            pid: ts
+            for pid, ts in self._seen_posts.items()
+            if now - ts < self._SEEN_TTL
+        }

gateway/platforms/qqbot/__init__.py

@@ -1,57 +0,0 @@
-"""
-QQBot platform package.
-
-Re-exports the main adapter symbols from ``adapter.py`` (the original
-``qqbot.py``) so that **all existing import paths remain unchanged**::
-
-    from gateway.platforms.qqbot import QQAdapter          # works
-    from gateway.platforms.qqbot import check_qq_requirements  # works
-
-New modules:
-    - ``constants`` — shared constants (API URLs, timeouts, message types)
-    - ``utils`` — User-Agent builder, config helpers
-    - ``crypto`` — AES-256-GCM key generation and decryption
-    - ``onboard`` — QR-code scan-to-configure flow
-"""
-
-# -- Adapter (original qqbot.py) ------------------------------------------
-from .adapter import (  # noqa: F401
-    QQAdapter,
-    QQCloseError,
-    check_qq_requirements,
-    _coerce_list,
-    _ssrf_redirect_guard,
-)
-
-# -- Onboard (QR-code scan-to-configure) -----------------------------------
-from .onboard import (  # noqa: F401
-    BindStatus,
-    create_bind_task,
-    poll_bind_result,
-    build_connect_url,
-)
-from .crypto import decrypt_secret, generate_bind_key  # noqa: F401
-
-# -- Utils -----------------------------------------------------------------
-from .utils import build_user_agent, get_api_headers, coerce_list  # noqa: F401
-
-__all__ = [
-    # adapter
-    "QQAdapter",
-    "QQCloseError",
-    "check_qq_requirements",
-    "_coerce_list",
-    "_ssrf_redirect_guard",
-    # onboard
-    "BindStatus",
-    "create_bind_task",
-    "poll_bind_result",
-    "build_connect_url",
-    # crypto
-    "decrypt_secret",
-    "generate_bind_key",
-    # utils
-    "build_user_agent",
-    "get_api_headers",
-    "coerce_list",
-]

gateway/platforms/qqbot/constants.py

@@ -1,74 +0,0 @@
-"""QQBot package-level constants shared across adapter, onboard, and other modules."""
-
-from __future__ import annotations
-
-import os
-
-# ---------------------------------------------------------------------------
-# QQBot adapter version — bump on functional changes to the adapter package.
-# ---------------------------------------------------------------------------
-
-QQBOT_VERSION = "1.1.0"
-
-# ---------------------------------------------------------------------------
-# API endpoints
-# ---------------------------------------------------------------------------
-
-# The portal domain is configurable via QQ_API_HOST for corporate proxies
-# or test environments.  Default: q.qq.com (production).
-PORTAL_HOST = os.getenv("QQ_PORTAL_HOST", "q.qq.com")
-
-API_BASE = "https://api.sgroup.qq.com"
-TOKEN_URL = "https://bots.qq.com/app/getAppAccessToken"
-GATEWAY_URL_PATH = "/gateway"
-
-# QR-code onboard endpoints (on the portal host)
-ONBOARD_CREATE_PATH = "/lite/create_bind_task"
-ONBOARD_POLL_PATH = "/lite/poll_bind_result"
-QR_URL_TEMPLATE = (
-    "https://q.qq.com/qqbot/openclaw/connect.html"
-    "?task_id={task_id}&_wv=2&source=hermes"
-)
-
-# ---------------------------------------------------------------------------
-# Timeouts & retry
-# ---------------------------------------------------------------------------
-
-DEFAULT_API_TIMEOUT = 30.0
-FILE_UPLOAD_TIMEOUT = 120.0
-CONNECT_TIMEOUT_SECONDS = 20.0
-
-RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
-MAX_RECONNECT_ATTEMPTS = 100
-RATE_LIMIT_DELAY = 60  # seconds
-QUICK_DISCONNECT_THRESHOLD = 5.0  # seconds
-MAX_QUICK_DISCONNECT_COUNT = 3
-
-ONBOARD_POLL_INTERVAL = 2.0  # seconds between poll_bind_result calls
-ONBOARD_API_TIMEOUT = 10.0
-
-# ---------------------------------------------------------------------------
-# Message limits
-# ---------------------------------------------------------------------------
-
-MAX_MESSAGE_LENGTH = 4000
-DEDUP_WINDOW_SECONDS = 300
-DEDUP_MAX_SIZE = 1000
-
-# ---------------------------------------------------------------------------
-# QQ Bot message types
-# ---------------------------------------------------------------------------
-
-MSG_TYPE_TEXT = 0
-MSG_TYPE_MARKDOWN = 2
-MSG_TYPE_MEDIA = 7
-MSG_TYPE_INPUT_NOTIFY = 6
-
-# ---------------------------------------------------------------------------
-# QQ Bot file media types
-# ---------------------------------------------------------------------------
-
-MEDIA_TYPE_IMAGE = 1
-MEDIA_TYPE_VIDEO = 2
-MEDIA_TYPE_VOICE = 3
-MEDIA_TYPE_FILE = 4

gateway/platforms/qqbot/crypto.py

@@ -1,45 +0,0 @@
-"""AES-256-GCM utilities for QQBot scan-to-configure credential decryption."""
-
-from __future__ import annotations
-
-import base64
-import os
-
-
-def generate_bind_key() -> str:
-    """Generate a 256-bit random AES key and return it as base64.
-
-    The key is passed to ``create_bind_task`` so the server can encrypt
-    the bot's *client_secret* before returning it.  Only this CLI holds
-    the key, ensuring the secret never travels in plaintext.
-    """
-    return base64.b64encode(os.urandom(32)).decode()
-
-
-def decrypt_secret(encrypted_base64: str, key_base64: str) -> str:
-    """Decrypt a base64-encoded AES-256-GCM ciphertext.
-
-    Ciphertext layout (after base64-decoding)::
-
-        IV (12 bytes) ‖ ciphertext (N bytes) ‖ AuthTag (16 bytes)
-
-    Args:
-        encrypted_base64: The ``bot_encrypt_secret`` value from
-            ``poll_bind_result``.
-        key_base64: The base64 AES key generated by
-            :func:`generate_bind_key`.
-
-    Returns:
-        The decrypted *client_secret* as a UTF-8 string.
-    """
-    from cryptography.hazmat.primitives.ciphers.aead import AESGCM
-
-    key = base64.b64decode(key_base64)
-    raw = base64.b64decode(encrypted_base64)
-
-    iv = raw[:12]
-    ciphertext_with_tag = raw[12:]  # AESGCM expects ciphertext + tag concatenated
-
-    aesgcm = AESGCM(key)
-    plaintext = aesgcm.decrypt(iv, ciphertext_with_tag, None)
-    return plaintext.decode("utf-8")

gateway/platforms/qqbot/onboard.py

@@ -1,124 +0,0 @@
-"""
-QQBot scan-to-configure (QR code onboard) module.
-
-Calls the ``q.qq.com`` ``create_bind_task`` / ``poll_bind_result`` APIs to
-generate a QR-code URL and poll for scan completion.  On success the caller
-receives the bot's *app_id*, *client_secret* (decrypted locally), and the
-scanner's *user_openid* — enough to fully configure the QQBot gateway.
-
-Reference: https://bot.q.qq.com/wiki/develop/api-v2/
-"""
-
-from __future__ import annotations
-
-import logging
-from enum import IntEnum
-from typing import Tuple
-from urllib.parse import quote
-
-from .constants import (
-    ONBOARD_API_TIMEOUT,
-    ONBOARD_CREATE_PATH,
-    ONBOARD_POLL_PATH,
-    PORTAL_HOST,
-    QR_URL_TEMPLATE,
-)
-from .crypto import generate_bind_key
-from .utils import get_api_headers
-
-logger = logging.getLogger(__name__)
-
-
-# ---------------------------------------------------------------------------
-# Bind status
-# ---------------------------------------------------------------------------
-
-
-class BindStatus(IntEnum):
-    """Status codes returned by ``poll_bind_result``."""
-
-    NONE = 0
-    PENDING = 1
-    COMPLETED = 2
-    EXPIRED = 3
-
-
-# ---------------------------------------------------------------------------
-# Public API
-# ---------------------------------------------------------------------------
-
-
-async def create_bind_task(
-    timeout: float = ONBOARD_API_TIMEOUT,
-) -> Tuple[str, str]:
-    """Create a bind task and return *(task_id, aes_key_base64)*.
-
-    The AES key is generated locally and sent to the server so it can
-    encrypt the bot credentials before returning them.
-
-    Raises:
-        RuntimeError: If the API returns a non-zero ``retcode``.
-    """
-    import httpx
-
-    url = f"https://{PORTAL_HOST}{ONBOARD_CREATE_PATH}"
-    key = generate_bind_key()
-
-    async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
-        resp = await client.post(url, json={"key": key}, headers=get_api_headers())
-        resp.raise_for_status()
-        data = resp.json()
-
-    if data.get("retcode") != 0:
-        raise RuntimeError(data.get("msg", "create_bind_task failed"))
-
-    task_id = data.get("data", {}).get("task_id")
-    if not task_id:
-        raise RuntimeError("create_bind_task: missing task_id in response")
-
-    logger.debug("create_bind_task ok: task_id=%s", task_id)
-    return task_id, key
-
-
-async def poll_bind_result(
-    task_id: str,
-    timeout: float = ONBOARD_API_TIMEOUT,
-) -> Tuple[BindStatus, str, str, str]:
-    """Poll the bind result for *task_id*.
-
-    Returns:
-        A 4-tuple of ``(status, bot_appid, bot_encrypt_secret, user_openid)``.
-
-        * ``bot_encrypt_secret`` is AES-256-GCM encrypted — decrypt it with
-          :func:`~gateway.platforms.qqbot.crypto.decrypt_secret` using the
-          key from :func:`create_bind_task`.
-        * ``user_openid`` is the OpenID of the person who scanned the code
-          (available when ``status == COMPLETED``).
-
-    Raises:
-        RuntimeError: If the API returns a non-zero ``retcode``.
-    """
-    import httpx
-
-    url = f"https://{PORTAL_HOST}{ONBOARD_POLL_PATH}"
-
-    async with httpx.AsyncClient(timeout=timeout, follow_redirects=True) as client:
-        resp = await client.post(url, json={"task_id": task_id}, headers=get_api_headers())
-        resp.raise_for_status()
-        data = resp.json()
-
-    if data.get("retcode") != 0:
-        raise RuntimeError(data.get("msg", "poll_bind_result failed"))
-
-    d = data.get("data", {})
-    return (
-        BindStatus(d.get("status", 0)),
-        str(d.get("bot_appid", "")),
-        d.get("bot_encrypt_secret", ""),
-        d.get("user_openid", ""),
-    )
-
-
-def build_connect_url(task_id: str) -> str:
-    """Build the QR-code target URL for a given *task_id*."""
-    return QR_URL_TEMPLATE.format(task_id=quote(task_id))

gateway/platforms/qqbot/utils.py

@@ -1,71 +0,0 @@
-"""QQBot shared utilities — User-Agent, HTTP helpers, config coercion."""
-
-from __future__ import annotations
-
-import platform
-import sys
-from typing import Any, Dict, List
-
-from .constants import QQBOT_VERSION
-
-
-# ---------------------------------------------------------------------------
-# User-Agent
-# ---------------------------------------------------------------------------
-
-def _get_hermes_version() -> str:
-    """Return the hermes-agent package version, or 'dev' if unavailable."""
-    try:
-        from importlib.metadata import version
-        return version("hermes-agent")
-    except Exception:
-        return "dev"
-
-
-def build_user_agent() -> str:
-    """Build a descriptive User-Agent string.
-
-    Format::
-
-        QQBotAdapter/<qqbot_version> (Python/<py_version>; <os>; Hermes/<hermes_version>)
-
-    Example::
-
-        QQBotAdapter/1.0.0 (Python/3.11.15; darwin; Hermes/0.9.0)
-    """
-    py_version = f"{sys.version_info.major}.{sys.version_info.minor}.{sys.version_info.micro}"
-    os_name = platform.system().lower()
-    hermes_version = _get_hermes_version()
-    return f"QQBotAdapter/{QQBOT_VERSION} (Python/{py_version}; {os_name}; Hermes/{hermes_version})"
-
-
-def get_api_headers() -> Dict[str, str]:
-    """Return standard HTTP headers for QQBot API requests.
-
-    Includes ``Content-Type``, ``Accept``, and a dynamic ``User-Agent``.
-    ``q.qq.com`` requires ``Accept: application/json`` — without it,
-    the server returns a JavaScript anti-bot challenge page.
-    """
-    return {
-        "Content-Type": "application/json",
-        "Accept": "application/json",
-        "User-Agent": build_user_agent(),
-    }
-
-
-# ---------------------------------------------------------------------------
-# Config helpers
-# ---------------------------------------------------------------------------
-
-def coerce_list(value: Any) -> List[str]:
-    """Coerce config values into a trimmed string list.
-
-    Accepts comma-separated strings, lists, tuples, sets, or single values.
-    """
-    if value is None:
-        return []
-    if isinstance(value, str):
-        return [item.strip() for item in value.split(",") if item.strip()]
-    if isinstance(value, (list, tuple, set)):
-        return [str(item).strip() for item in value if str(item).strip()]
-    return [str(value).strip()] if str(value).strip() else []