fix(skills): archive OpenClaw cron store without config

.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

.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

@@ -23,21 +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
@@ -56,31 +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
@@ -26,12 +23,12 @@ jobs:
         run: npm ci
         working-directory: website
 
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
+      - uses: actions/setup-python@v5
         with:
           python-version: '3.11'
 
-      - name: Install ascii-guard
-        run: python -m pip install ascii-guard==2.3.0 pyyaml==6.0.3
+      - name: Install Python dependencies
+        run: python -m pip install ascii-guard pyyaml
 
       - name: Extract skill metadata for dashboard
         run: python3 website/scripts/extract-skills.py

.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
@@ -29,9 +26,9 @@ jobs:
     runs-on: ${{ matrix.os }}
     timeout-minutes: 30
     steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-      - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
-      - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
+      - uses: actions/checkout@v4
+      - uses: DeterminateSystems/nix-installer-action@main
+      - uses: DeterminateSystems/magic-nix-cache-action@main
       - name: Check flake
         if: runner.os == 'Linux'
         run: nix flake check --print-build-logs

.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

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
@@ -149,62 +149,6 @@ jobs:
           "
           fi
 
-          # --- CI/CD workflow files modified ---
-          WORKFLOW_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '\.github/workflows/.*\.ya?ml$' || true)
-          if [ -n "$WORKFLOW_HITS" ]; then
-            FINDINGS="${FINDINGS}
-          ### ⚠️ WARNING: CI/CD workflow files modified
-          Changes to workflow files can alter build pipelines, inject steps, or modify permissions. Verify no unauthorized actions or secrets access were added.
-
-          **Files:**
-          \`\`\`
-          ${WORKFLOW_HITS}
-          \`\`\`
-          "
-          fi
-
-          # --- Dockerfile / container build files modified ---
-          DOCKER_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -iE '(Dockerfile|\.dockerignore|docker-compose)' || true)
-          if [ -n "$DOCKER_HITS" ]; then
-            FINDINGS="${FINDINGS}
-          ### ⚠️ WARNING: Container build files modified
-          Changes to Dockerfiles or compose files can alter base images, add build steps, or expose ports. Verify base image pins and build commands.
-
-          **Files:**
-          \`\`\`
-          ${DOCKER_HITS}
-          \`\`\`
-          "
-          fi
-
-          # --- Dependency manifest files modified ---
-          DEP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(pyproject\.toml|requirements.*\.txt|package\.json|Gemfile|go\.mod|Cargo\.toml)$' || true)
-          if [ -n "$DEP_HITS" ]; then
-            FINDINGS="${FINDINGS}
-          ### ⚠️ WARNING: Dependency manifest files modified
-          Changes to dependency files can introduce new packages or change version pins. Verify all dependency changes are intentional and from trusted sources.
-
-          **Files:**
-          \`\`\`
-          ${DEP_HITS}
-          \`\`\`
-          "
-          fi
-
-          # --- GitHub Actions version unpinning (mutable tags instead of SHAs) ---
-          ACTIONS_UNPIN=$(echo "$DIFF" | grep -n '^\+' | grep 'uses:' | grep -v '#' | grep -E '@v[0-9]' | head -10 || true)
-          if [ -n "$ACTIONS_UNPIN" ]; then
-            FINDINGS="${FINDINGS}
-          ### ⚠️ WARNING: GitHub Actions with mutable version tags
-          Actions should be pinned to full commit SHAs (not \`@v4\`, \`@v5\`). Mutable tags can be retargeted silently if a maintainer account is compromised.
-
-          **Matches:**
-          \`\`\`
-          ${ACTIONS_UNPIN}
-          \`\`\`
-          "
-          fi
-
           # --- Output results ---
           if [ -n "$FINDINGS" ]; then
             echo "found=true" >> "$GITHUB_OUTPUT"
@@ -239,7 +183,7 @@ jobs:
           ---
           *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.critical == 'true'

.github/workflows/tests.yml

@@ -6,9 +6,6 @@ on:
   pull_request:
     branches: [main]
 
-permissions:
-  contents: read
-
 # Cancel in-progress runs for the same PR/branch
 concurrency:
   group: tests-${{ github.ref }}
@@ -16,22 +13,17 @@ concurrency:
 
 jobs:
   test:
-    name: test (${{ matrix.group }}/4)
     runs-on: ubuntu-latest
     timeout-minutes: 10
-    strategy:
-      fail-fast: false
-      matrix:
-        group: [1, 2, 3, 4]
     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
@@ -42,11 +34,10 @@ jobs:
           source .venv/bin/activate
           uv pip install -e ".[all,dev]"
 
-      - name: Run tests (shard ${{ matrix.group }}/4)
+      - name: Run tests
         run: |
           source .venv/bin/activate
-          python -m pytest tests/ -q --ignore=tests/integration --ignore=tests/e2e --tb=short \
-            --splits 4 --group ${{ matrix.group }}
+          python -m pytest tests/ -q --ignore=tests/integration --ignore=tests/e2e --tb=short -n auto
         env:
           # Ensure tests don't accidentally call real APIs
           OPENROUTER_API_KEY: ""
@@ -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

@@ -51,9 +51,6 @@ ignored/
 .worktrees/
 environments/benchmarks/evals/
 
-# Web UI build output
-hermes_cli/web_dist/
-
 # Release script temp files
 .release_notes.md
 mini-swe-agent/
@@ -61,4 +58,3 @@ mini-swe-agent/
 # Nix
 .direnv/
 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)
@@ -55,7 +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
+│   └── 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)
@@ -181,7 +181,7 @@ if canonical == "mycommand":
 
 ## Adding New Tools
 
-Requires changes in **2 files**:
+Requires changes in **3 files**:
 
 **1. Create `tools/your_tool.py`:**
 ```python
@@ -204,9 +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.
 
@@ -351,9 +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)

Dockerfile

@@ -1,44 +1,23 @@
-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
 
-# Install Node dependencies and Playwright as root (--with-deps needs apt)
-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 /opt/hermes/scripts/whatsapp-bridge && \
     npm install --prefer-offline --no-audit && \
     npm cache clean --force
 
-# Hand ownership to hermes user, then install Python deps in a virtualenv
-RUN chown -R hermes:hermes /opt/hermes
-USER hermes
-
-RUN uv venv && \
-    uv pip install --no-cache-dir -e ".[all]"
-
-USER root
+WORKDIR /opt/hermes
 RUN chmod +x /opt/hermes/docker/entrypoint.sh
 
 ENV HERMES_HOME=/opt/data

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), [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:
@@ -167,7 +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/server.py

@@ -36,7 +36,6 @@ from acp.schema import (
     SessionCapabilities,
     SessionForkCapabilities,
     SessionListCapabilities,
-    SessionResumeCapabilities,
     SessionInfo,
     TextContentBlock,
     UnstructuredCommandInput,
@@ -246,11 +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,
@@ -454,13 +451,14 @@ class HermesACPAgent(acp.Agent):
             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"

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:
@@ -279,19 +204,6 @@ 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):
     """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
 
@@ -310,7 +222,6 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     }
     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
@@ -320,21 +231,21 @@ def build_anthropic_client(api_key: str, base_url: str = None):
         # 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),
@@ -344,39 +255,12 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     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.
 
@@ -601,6 +485,35 @@ def _prefer_refreshable_claude_code_token(env_token: str, creds: Optional[Dict[s
     return None
 
 
+def get_anthropic_token_source(token: Optional[str] = None) -> str:
+    """Best-effort source classification for an Anthropic credential token."""
+    token = (token or "").strip()
+    if not token:
+        return "none"
+
+    env_token = os.getenv("ANTHROPIC_TOKEN", "").strip()
+    if env_token and env_token == token:
+        return "anthropic_token_env"
+
+    cc_env_token = os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "").strip()
+    if cc_env_token and cc_env_token == token:
+        return "claude_code_oauth_token_env"
+
+    creds = read_claude_code_credentials()
+    if creds and creds.get("accessToken") == token:
+        return str(creds.get("source") or "claude_code_credentials")
+
+    managed_key = read_claude_managed_key()
+    if managed_key and managed_key == token:
+        return "claude_json_primary_api_key"
+
+    api_key = os.getenv("ANTHROPIC_API_KEY", "").strip()
+    if api_key and api_key == token:
+        return "anthropic_api_key_env"
+
+    return "unknown"
+
+
 def resolve_anthropic_token() -> Optional[str]:
     """Resolve an Anthropic token from all available sources.
 
@@ -807,6 +720,21 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
     }
 
 
+def _save_hermes_oauth_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
+    """Save OAuth credentials to ~/.hermes/.anthropic_oauth.json."""
+    data = {
+        "accessToken": access_token,
+        "refreshToken": refresh_token,
+        "expiresAt": expires_at_ms,
+    }
+    try:
+        _HERMES_OAUTH_FILE.parent.mkdir(parents=True, exist_ok=True)
+        _HERMES_OAUTH_FILE.write_text(json.dumps(data, indent=2), encoding="utf-8")
+        _HERMES_OAUTH_FILE.chmod(0o600)
+    except (OSError, IOError) as e:
+        logger.debug("Failed to save Hermes OAuth credentials: %s", e)
+
+
 def read_hermes_oauth_credentials() -> Optional[Dict[str, Any]]:
     """Read Hermes-managed OAuth credentials from ~/.hermes/.anthropic_oauth.json."""
     if _HERMES_OAUTH_FILE.exists():
@@ -855,6 +783,39 @@ def _sanitize_tool_id(tool_id: str) -> str:
     return sanitized or "tool_0"
 
 
+def _convert_openai_image_part_to_anthropic(part: Dict[str, Any]) -> Optional[Dict[str, Any]]:
+    """Convert an OpenAI-style image block to Anthropic's image source format."""
+    image_data = part.get("image_url", {})
+    url = image_data.get("url", "") if isinstance(image_data, dict) else str(image_data)
+    if not isinstance(url, str) or not url.strip():
+        return None
+    url = url.strip()
+
+    if url.startswith("data:"):
+        header, sep, data = url.partition(",")
+        if sep and ";base64" in header:
+            media_type = header[5:].split(";", 1)[0] or "image/png"
+            return {
+                "type": "image",
+                "source": {
+                    "type": "base64",
+                    "media_type": media_type,
+                    "data": data,
+                },
+            }
+
+    if url.startswith(("http://", "https://")):
+        return {
+            "type": "image",
+            "source": {
+                "type": "url",
+                "url": url,
+            },
+        }
+
+    return None
+
+
 def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
     """Convert OpenAI tool definitions to Anthropic format."""
     if not tools:
@@ -1274,31 +1235,13 @@ 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().
 
-    Naming note — two distinct concepts, easily confused:
-      max_tokens     = OUTPUT token cap for a single response.
-                       Anthropic's API calls this "max_tokens" but it only
-                       limits the *output*.  Anthropic's own native SDK
-                       renamed it "max_output_tokens" for clarity.
-      context_length = TOTAL context window (input tokens + output tokens).
-                       The API enforces: input_tokens + max_tokens ≤ context_length.
-                       Stored on the ContextCompressor; reduced on overflow errors.
-
-    When *max_tokens* is None the model's native output ceiling is used
-    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).
-
-    When *context_length* is provided and the model's native output ceiling
-    exceeds it (e.g. a local endpoint with an 8K window), the output cap is
-    clamped to context_length − 1.  This only kicks in for unusually small
-    context windows; for full-size models the native output cap is always
-    smaller than the context window so no clamping happens.
-    NOTE: this clamping does not account for prompt size — if the prompt is
-    large, Anthropic may still reject the request.  The caller must detect
-    "max_tokens too large given prompt" errors and retry with a smaller cap
-    (see parse_available_output_tokens_from_error + _ephemeral_max_output_tokens).
+    When *max_tokens* is None, the model's native output limit is used
+    (e.g. 128K for Opus 4.6, 64K for Sonnet 4.6).  If *context_length*
+    is provided, the effective limit is clamped so it doesn't exceed
+    the context window.
 
     When *is_oauth* is True, applies Claude Code compatibility transforms:
     system prompt prefix, tool name prefixing, and prompt sanitization.
@@ -1308,24 +1251,15 @@ 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 []
 
     model = normalize_model_name(model, preserve_dots=preserve_dots)
-    # effective_max_tokens = output cap for this call (≠ total context window)
     effective_max_tokens = max_tokens or _get_anthropic_max_output(model)
 
-    # Clamp output cap to fit inside the total context window.
-    # Only matters for small custom endpoints where context_length < native
-    # output ceiling.  For standard Anthropic models context_length (e.g.
-    # 200K) is always larger than the output ceiling (e.g. 128K), so this
-    # branch is not taken.
+    # Clamp to context window if the user set a lower context_length
+    # (e.g. custom endpoint with limited capacity).
     if context_length and effective_max_tokens > context_length:
         effective_max_tokens = max(context_length - 1, 1)
 
@@ -1393,31 +1327,17 @@ 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}
@@ -1425,29 +1345,6 @@ 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
 
 
@@ -1491,20 +1388,12 @@ 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")
 
@@ -1517,4 +1406,4 @@ def normalize_anthropic_response(
             reasoning_details=reasoning_details or None,
         ),
         finish_reason,
-    )
+    )

agent/builtin_memory_provider.py

@@ -0,0 +1,114 @@
+"""BuiltinMemoryProvider — wraps MEMORY.md / USER.md as a MemoryProvider.
+
+Always registered as the first provider. Cannot be disabled or removed.
+This is the existing Hermes memory system exposed through the provider
+interface for compatibility with the MemoryManager.
+
+The actual storage logic lives in tools/memory_tool.py (MemoryStore).
+This provider is a thin adapter that delegates to MemoryStore and
+exposes the memory tool schema.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+from typing import Any, Dict, List
+
+from agent.memory_provider import MemoryProvider
+from tools.registry import tool_error
+
+logger = logging.getLogger(__name__)
+
+
+class BuiltinMemoryProvider(MemoryProvider):
+    """Built-in file-backed memory (MEMORY.md + USER.md).
+
+    Always active, never disabled by other providers. The `memory` tool
+    is handled by run_agent.py's agent-level tool interception (not through
+    the normal registry), so get_tool_schemas() returns an empty list —
+    the memory tool is already wired separately.
+    """
+
+    def __init__(
+        self,
+        memory_store=None,
+        memory_enabled: bool = False,
+        user_profile_enabled: bool = False,
+    ):
+        self._store = memory_store
+        self._memory_enabled = memory_enabled
+        self._user_profile_enabled = user_profile_enabled
+
+    @property
+    def name(self) -> str:
+        return "builtin"
+
+    def is_available(self) -> bool:
+        """Built-in memory is always available."""
+        return True
+
+    def initialize(self, session_id: str, **kwargs) -> None:
+        """Load memory from disk if not already loaded."""
+        if self._store is not None:
+            self._store.load_from_disk()
+
+    def system_prompt_block(self) -> str:
+        """Return MEMORY.md and USER.md content for the system prompt.
+
+        Uses the frozen snapshot captured at load time. This ensures the
+        system prompt stays stable throughout a session (preserving the
+        prompt cache), even though the live entries may change via tool calls.
+        """
+        if not self._store:
+            return ""
+
+        parts = []
+        if self._memory_enabled:
+            mem_block = self._store.format_for_system_prompt("memory")
+            if mem_block:
+                parts.append(mem_block)
+        if self._user_profile_enabled:
+            user_block = self._store.format_for_system_prompt("user")
+            if user_block:
+                parts.append(user_block)
+
+        return "\n\n".join(parts)
+
+    def prefetch(self, query: str, *, session_id: str = "") -> str:
+        """Built-in memory doesn't do query-based recall — it's injected via system_prompt_block."""
+        return ""
+
+    def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
+        """Built-in memory doesn't auto-sync turns — writes happen via the memory tool."""
+
+    def get_tool_schemas(self) -> List[Dict[str, Any]]:
+        """Return empty list.
+
+        The `memory` tool is an agent-level intercepted tool, handled
+        specially in run_agent.py before normal tool dispatch. It's not
+        part of the standard tool registry. We don't duplicate it here.
+        """
+        return []
+
+    def handle_tool_call(self, tool_name: str, args: Dict[str, Any], **kwargs) -> str:
+        """Not used — the memory tool is intercepted in run_agent.py."""
+        return tool_error("Built-in memory tool is handled by the agent loop")
+
+    def shutdown(self) -> None:
+        """No cleanup needed — files are saved on every write."""
+
+    # -- Property access for backward compatibility --------------------------
+
+    @property
+    def store(self):
+        """Access the underlying MemoryStore for legacy code paths."""
+        return self._store
+
+    @property
+    def memory_enabled(self) -> bool:
+        return self._memory_enabled
+
+    @property
+    def user_profile_enabled(self) -> bool:
+        return self._user_profile_enabled

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]:"
 
@@ -63,130 +50,8 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
 
-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)
@@ -196,40 +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,
@@ -243,13 +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
@@ -261,14 +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
@@ -292,42 +114,39 @@ class ContextCompressor(ContextEngine):
 
         self.last_prompt_tokens = 0
         self.last_completion_tokens = 0
+        self.last_total_tokens = 0
 
         self.summary_model = summary_model_override or ""
 
         # 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]):
         """Update tracked token usage from API response."""
         self.last_prompt_tokens = usage.get("prompt_tokens", 0)
         self.last_completion_tokens = usage.get("completion_tokens", 0)
+        self.last_total_tokens = usage.get("total_tokens", 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
+
+    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
+        """Quick pre-flight check using rough estimate (before API call)."""
+        rough_estimate = estimate_messages_tokens_rough(messages)
+        return rough_estimate >= self.threshold_tokens
+
+    def get_status(self) -> Dict[str, Any]:
+        """Get current compression status for display/logging."""
+        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,
+        }
 
     # ------------------------------------------------------------------
     # Tool output pruning (cheap pre-pass, no LLM call)
@@ -337,16 +156,7 @@ 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
@@ -362,22 +172,6 @@ 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
@@ -386,8 +180,7 @@ 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):
@@ -402,69 +195,18 @@ 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.
-        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:
-                        tc = {**tc, "function": {**tc["function"], "arguments": args[:200] + "...[truncated]"}}
-                        modified = True
-                new_tcs.append(tc)
-            if modified:
-                result[i] = {**msg, "tool_calls": new_tcs}
-
         return result, pruned
 
     # ------------------------------------------------------------------
@@ -542,20 +284,13 @@ 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.
@@ -571,83 +306,9 @@ 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."
-        )
-
-        # 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}
@@ -655,42 +316,87 @@ 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:
@@ -704,10 +410,8 @@ 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 "
@@ -715,42 +419,12 @@ 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
 
@@ -873,62 +547,6 @@ 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,
@@ -946,8 +564,7 @@ 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
@@ -986,17 +603,13 @@ 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:
@@ -1008,12 +621,6 @@ 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)
@@ -1071,67 +678,52 @@ 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
-        # knows context was lost rather than silently dropping everything.
-        if not summary:
-            if not self.quiet_mode:
-                logger.warning("Summary generation failed — inserting static fallback context marker")
-            n_dropped = compress_end - compress_start
-            summary = (
-                f"{SUMMARY_PREFIX}\n"
-                f"Summary generation was unavailable. {n_dropped} conversation turns were "
-                f"removed to free context space but could not be summarized. The removed "
-                f"turns contained earlier work in this session. Continue based on the "
-                f"recent messages below and the current state of any files or resources."
-            )
-
         _merge_summary_into_tail = False
-        last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
-        first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
-        # Pick a role that avoids consecutive same-role with both neighbors.
-        # Priority: avoid colliding with head (already committed), then tail.
-        if last_head_role in ("assistant", "tool"):
-            summary_role = "user"
-        else:
-            summary_role = "assistant"
-        # If the chosen role collides with the tail AND flipping wouldn't
-        # collide with the head, flip it.
-        if summary_role == first_tail_role:
-            flipped = "assistant" if summary_role == "user" else "user"
-            if flipped != last_head_role:
-                summary_role = flipped
+        if summary:
+            last_head_role = messages[compress_start - 1].get("role", "user") if compress_start > 0 else "user"
+            first_tail_role = messages[compress_end].get("role", "user") if compress_end < n_messages else "user"
+            # Pick a role that avoids consecutive same-role with both neighbors.
+            # Priority: avoid colliding with head (already committed), then tail.
+            if last_head_role in ("assistant", "tool"):
+                summary_role = "user"
             else:
-                # Both roles would create consecutive same-role messages
-                # (e.g. head=assistant, tail=user — neither role works).
-                # Merge the summary into the first tail message instead
-                # of inserting a standalone message that breaks alternation.
-                _merge_summary_into_tail = True
-        if not _merge_summary_into_tail:
-            compressed.append({"role": summary_role, "content": summary})
+                summary_role = "assistant"
+            # If the chosen role collides with the tail AND flipping wouldn't
+            # collide with the head, flip it.
+            if summary_role == first_tail_role:
+                flipped = "assistant" if summary_role == "user" else "user"
+                if flipped != last_head_role:
+                    summary_role = flipped
+                else:
+                    # Both roles would create consecutive same-role messages
+                    # (e.g. head=assistant, tail=user — neither role works).
+                    # Merge the summary into the first tail message instead
+                    # of inserting a standalone message that breaks alternation.
+                    _merge_summary_into_tail = True
+            if not _merge_summary_into_tail:
+                compressed.append({"role": summary_role, "content": summary})
+        else:
+            if not self.quiet_mode:
+                logger.debug("No summary model available — middle turns dropped without summary")
 
         for i in range(compress_end, n_messages):
             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)
 
@@ -1139,24 +731,14 @@ 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

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

@@ -19,17 +19,12 @@ from hermes_cli.auth import (
     CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
     DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
     PROVIDER_REGISTRY,
-    _auth_store_lock,
     _codex_access_token_is_expiring,
     _decode_jwt_claims,
     _import_codex_cli_tokens,
-    _write_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,
 )
@@ -288,14 +283,6 @@ 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):
@@ -490,67 +477,6 @@ class CredentialPool:
             logger.debug("Failed to sync from ~/.codex/auth.json: %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.
-
-        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).
-        """
-        if entry.source != "device_code":
-            return
-        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)
-        except Exception as exc:
-            logger.debug("Failed to sync %s pool entry back to auth store: %s", self.provider, exc)
-
     def _refresh_entry(self, entry: PooledCredential, *, force: bool) -> Optional[PooledCredential]:
         if entry.auth_type != AUTH_TYPE_OAUTH or not entry.refresh_token:
             if force:
@@ -585,13 +511,6 @@ class CredentialPool:
                     except Exception as wexc:
                         logger.debug("Failed to write refreshed token to credentials file: %s", wexc)
             elif self.provider == "openai-codex":
-                # Proactively sync from ~/.codex/auth.json before refresh.
-                # The Codex CLI (or another Hermes profile) may have already
-                # consumed our refresh_token.  Syncing first avoids a
-                # "refresh_token_reused" error when the CLI has a newer pair.
-                synced = self._sync_codex_entry_from_cli(entry)
-                if synced is not entry:
-                    entry = synced
                 refreshed = auth_mod.refresh_codex_oauth_pure(
                     entry.access_token,
                     entry.refresh_token,
@@ -677,45 +596,6 @@ class CredentialPool:
                     # Credentials file had a valid (non-expired) token — use it directly
                     logger.debug("Credentials file has valid token, using without refresh")
                     return synced
-            # For openai-codex: the refresh_token may have been consumed by
-            # the Codex CLI between our proactive sync and the refresh call.
-            # Re-sync and retry once.
-            if self.provider == "openai-codex":
-                synced = self._sync_codex_entry_from_cli(entry)
-                if synced.refresh_token != entry.refresh_token:
-                    logger.debug("Retrying Codex refresh with synced token from ~/.codex/auth.json")
-                    try:
-                        refreshed = auth_mod.refresh_codex_oauth_pure(
-                            synced.access_token,
-                            synced.refresh_token,
-                        )
-                        updated = replace(
-                            synced,
-                            access_token=refreshed["access_token"],
-                            refresh_token=refreshed["refresh_token"],
-                            last_refresh=refreshed.get("last_refresh"),
-                            last_status=STATUS_OK,
-                            last_status_at=None,
-                            last_error_code=None,
-                        )
-                        self._replace_entry(synced, updated)
-                        self._persist()
-                        self._sync_device_code_entry_to_auth_store(updated)
-                        try:
-                            _write_codex_cli_tokens(
-                                updated.access_token,
-                                updated.refresh_token,
-                                last_refresh=updated.last_refresh,
-                            )
-                        except Exception as wexc:
-                            logger.debug("Failed to write refreshed Codex tokens to CLI file (retry): %s", wexc)
-                        return updated
-                    except Exception as retry_exc:
-                        logger.debug("Codex retry refresh also failed: %s", retry_exc)
-                elif not self._entry_needs_refresh(synced):
-                    logger.debug("Codex CLI has valid token, using without refresh")
-                    self._sync_device_code_entry_to_auth_store(synced)
-                    return synced
             self._mark_exhausted(entry, None)
             return None
 
@@ -730,21 +610,6 @@ 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)
-        # Write refreshed tokens back to ~/.codex/auth.json so Codex CLI
-        # and VS Code don't hit "refresh_token_reused" on their next refresh.
-        if self.provider == "openai-codex":
-            try:
-                _write_codex_cli_tokens(
-                    updated.access_token,
-                    updated.refresh_token,
-                    last_refresh=updated.last_refresh,
-                )
-            except Exception as wexc:
-                logger.debug("Failed to write refreshed Codex tokens to CLI file: %s", wexc)
         return updated
 
     def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -766,6 +631,17 @@ class CredentialPool:
             return False
         return False
 
+    def mark_used(self, entry_id: Optional[str] = None) -> None:
+        """Increment request_count for tracking. Used by least_used strategy."""
+        target_id = entry_id or self._current_id
+        if not target_id:
+            return
+        with self._lock:
+            for idx, entry in enumerate(self._entries):
+                if entry.id == target_id:
+                    self._entries[idx] = replace(entry, request_count=entry.request_count + 1)
+                    return
+
     def select(self) -> Optional[PooledCredential]:
         with self._lock:
             return self._select_unlocked()
@@ -927,6 +803,11 @@ class CredentialPool:
             else:
                 self._active_leases[credential_id] = count - 1
 
+    def active_lease_count(self, credential_id: str) -> int:
+        """Return the number of active leases for a credential."""
+        with self._lock:
+            return self._active_leases.get(credential_id, 0)
+
     def try_refresh_current(self) -> Optional[PooledCredential]:
         with self._lock:
             return self._try_refresh_current_unlocked()
@@ -1086,17 +967,6 @@ 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 (
@@ -1104,13 +974,6 @@ 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,
@@ -1152,81 +1015,9 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                 },
             )
 
-    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":
         state = _load_provider_state(auth_store, "openai-codex")
         tokens = state.get("tokens") if isinstance(state, dict) else None
-        # Fallback: import from Codex CLI (~/.codex/auth.json) if Hermes auth
-        # store has no tokens.  This mirrors resolve_codex_runtime_credentials()
-        # so that load_pool() and list_authenticated_providers() detect tokens
-        # that only exist in the Codex CLI shared file.
-        if not (isinstance(tokens, dict) and tokens.get("access_token")):
-            try:
-                from hermes_cli.auth import _import_codex_cli_tokens, _save_codex_tokens
-                cli_tokens = _import_codex_cli_tokens()
-                if cli_tokens:
-                    logger.info("Importing Codex CLI tokens into Hermes auth store.")
-                    _save_codex_tokens(cli_tokens)
-                    # Re-read state after import
-                    auth_store = _load_auth_store()
-                    state = _load_provider_state(auth_store, "openai-codex")
-                    tokens = state.get("tokens") if isinstance(state, dict) else None
-            except Exception as exc:
-                logger.debug("Codex CLI token import failed: %s", exc)
         if isinstance(tokens, dict) and tokens.get("access_token"):
             active_sources.add("device_code")
             changed |= _upsert_entry(
@@ -1293,9 +1084,7 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         active_sources.add(source)
         auth_type = AUTH_TYPE_OAUTH if provider == "anthropic" and not token.startswith("sk-ant-api") else AUTH_TYPE_API_KEY
         base_url = env_url or pconfig.inference_base_url
-        if provider == "kimi-coding":
-            base_url = _resolve_kimi_base_url(token, pconfig.inference_base_url, env_url)
-        elif provider == "zai":
+        if provider == "zai":
             base_url = _resolve_zai_base_url(token, pconfig.inference_base_url, env_url)
         changed |= _upsert_entry(
             entries,

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
 
@@ -124,6 +67,26 @@ def _get_skin():
         return None
 
 
+def get_skin_faces(key: str, default: list) -> list:
+    """Get spinner face list from active skin, falling back to default."""
+    skin = _get_skin()
+    if skin:
+        faces = skin.get_spinner_list(key)
+        if faces:
+            return faces
+    return default
+
+
+def get_skin_verbs() -> list:
+    """Get thinking verbs from active skin."""
+    skin = _get_skin()
+    if skin:
+        verbs = skin.get_spinner_list("thinking_verbs")
+        if verbs:
+            return verbs
+    return KawaiiSpinner.THINKING_VERBS
+
+
 def get_skin_tool_prefix() -> str:
     """Get tool output prefix character from active skin."""
     skin = _get_skin()
@@ -367,8 +330,9 @@ 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
@@ -417,7 +381,10 @@ 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():
@@ -456,19 +423,19 @@ 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)
@@ -534,7 +501,7 @@ 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
 
@@ -600,45 +567,6 @@ 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'])
@@ -795,6 +723,46 @@ class KawaiiSpinner:
         return False
 
 
+# =========================================================================
+# Kawaii face arrays (used by AIAgent._execute_tool_calls for spinner text)
+# =========================================================================
+
+KAWAII_SEARCH = [
+    "♪(´ε` )", "(｡◕‿◕｡)", "ヾ(＾∇＾)", "(◕ᴗ◕✿)", "( ˘▽˘)っ",
+    "٩(◕‿◕｡)۶", "(✿◠‿◠)", "♪～(´ε｀ )", "(ノ´ヮ`)ノ*:・゚✧", "＼(◎o◎)／",
+]
+KAWAII_READ = [
+    "φ(゜▽゜*)♪", "( ˘▽˘)っ", "(⌐■_■)", "٩(｡•́‿•̀｡)۶", "(◕‿◕✿)",
+    "ヾ(＠⌒ー⌒＠)ノ", "(✧ω✧)", "♪(๑ᴖ◡ᴖ๑)♪", "(≧◡≦)", "( ´ ▽ ` )ノ",
+]
+KAWAII_TERMINAL = [
+    "ヽ(>∀<☆)ノ", "(ノ°∀°)ノ", "٩(^ᴗ^)۶", "ヾ(⌐■_■)ノ♪", "(•̀ᴗ•́)و",
+    "┗(＾0＾)┓", "(｀・ω・´)", "＼(￣▽￣)／", "(ง •̀_•́)ง", "ヽ(´▽`)/",
+]
+KAWAII_BROWSER = [
+    "(ノ°∀°)ノ", "(☞゚ヮ゚)☞", "( ͡° ͜ʖ ͡°)", "┌( ಠ_ಠ)┘", "(⊙_⊙)？",
+    "ヾ(•ω•`)o", "(￣ω￣)", "( ˇωˇ )", "(ᵔᴥᵔ)", "＼(◎o◎)／",
+]
+KAWAII_CREATE = [
+    "✧*。٩(ˊᗜˋ*)و✧", "(ﾉ◕ヮ◕)ﾉ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "٩(♡ε♡)۶", "(◕‿◕)♡",
+    "✿◕ ‿ ◕✿", "(*≧▽≦)", "ヾ(＾-＾)ノ", "(☆▽☆)", "°˖✧◝(⁰▿⁰)◜✧˖°",
+]
+KAWAII_SKILL = [
+    "ヾ(＠⌒ー⌒＠)ノ", "(๑˃ᴗ˂)ﻭ", "٩(◕‿◕｡)۶", "(✿╹◡╹)", "ヽ(・∀・)ノ",
+    "(ノ´ヮ`)ノ*:・ﾟ✧", "♪(๑ᴖ◡ᴖ๑)♪", "(◠‿◠)", "٩(ˊᗜˋ*)و", "(＾▽＾)",
+    "ヾ(＾∇＾)", "(★ω★)/", "٩(｡•́‿•̀｡)۶", "(◕ᴗ◕✿)", "＼(◎o◎)／",
+    "(✧ω✧)", "ヽ(>∀<☆)ノ", "( ˘▽˘)っ", "(≧◡≦) ♡", "ヾ(￣▽￣)",
+]
+KAWAII_THINK = [
+    "(っ°Д°;)っ", "(；′⌒`)", "(・_・ヾ", "( ´_ゝ`)", "(￣ヘ￣)",
+    "(。-`ω´-)", "( ˘︹˘ )", "(¬_¬)", "ヽ(ー_ー )ノ", "(；一_一)",
+]
+KAWAII_GENERIC = [
+    "♪(´ε` )", "(◕‿◕✿)", "ヾ(＾∇＾)", "٩(◕‿◕｡)۶", "(✿◠‿◠)",
+    "(ノ´ヮ`)ノ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "(☆▽☆)", "( ˘▽˘)っ", "(≧◡≦)",
+]
+
+
 # =========================================================================
 # Cute tool message (completion line that replaces the spinner)
 # =========================================================================
@@ -810,19 +778,23 @@ 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()
@@ -993,4 +965,100 @@ 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"
 
+
+def honcho_session_url(workspace: str, session_name: str) -> str:
+    """Build a Honcho app URL for a session."""
+    from urllib.parse import quote
+    return (
+        f"https://app.honcho.dev/explore"
+        f"?workspace={quote(workspace, safe='')}"
+        f"&view=sessions"
+        f"&session={quote(session_name, safe='')}"
+    )
+
+
+def _osc8_link(url: str, text: str) -> str:
+    """OSC 8 terminal hyperlink (clickable in iTerm2, Ghostty, WezTerm, etc.)."""
+    return f"\033]8;;{url}\033\\{text}\033]8;;\033\\"
+
+
+# =========================================================================
+# 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

@@ -1,829 +0,0 @@
-"""API error classification for smart failover and recovery.
-
-Provides a structured taxonomy of API errors and a priority-ordered
-classification pipeline that determines the correct recovery action
-(retry, rotate credential, fallback to another provider, compress
-context, or abort).
-
-Replaces scattered inline string-matching with a centralized classifier
-that the main retry loop in run_agent.py consults for every API failure.
-"""
-
-from __future__ import annotations
-
-import enum
-import logging
-from dataclasses import dataclass, field
-from typing import Any, Dict, Optional
-
-logger = logging.getLogger(__name__)
-
-
-# ── Error taxonomy ──────────────────────────────────────────────────────
-
-class FailoverReason(enum.Enum):
-    """Why an API call failed — determines recovery strategy."""
-
-    # Authentication / authorization
-    auth = "auth"                        # Transient auth (401/403) — refresh/rotate
-    auth_permanent = "auth_permanent"    # Auth failed after refresh — abort
-
-    # Billing / quota
-    billing = "billing"                  # 402 or confirmed credit exhaustion — rotate immediately
-    rate_limit = "rate_limit"            # 429 or quota-based throttling — backoff then rotate
-
-    # Server-side
-    overloaded = "overloaded"            # 503/529 — provider overloaded, backoff
-    server_error = "server_error"        # 500/502 — internal server error, retry
-
-    # Transport
-    timeout = "timeout"                  # Connection/read timeout — rebuild client + retry
-
-    # Context / payload
-    context_overflow = "context_overflow"  # Context too large — compress, not failover
-    payload_too_large = "payload_too_large"  # 413 — compress payload
-
-    # Model
-    model_not_found = "model_not_found"  # 404 or invalid model — fallback to different model
-
-    # Request format
-    format_error = "format_error"        # 400 bad request — abort or strip + retry
-
-    # Provider-specific
-    thinking_signature = "thinking_signature"  # Anthropic thinking block sig invalid
-    long_context_tier = "long_context_tier"    # Anthropic "extra usage" tier gate
-
-    # Catch-all
-    unknown = "unknown"                  # Unclassifiable — retry with backoff
-
-
-# ── Classification result ───────────────────────────────────────────────
-
-@dataclass
-class ClassifiedError:
-    """Structured classification of an API error with recovery hints."""
-
-    reason: FailoverReason
-    status_code: Optional[int] = None
-    provider: Optional[str] = None
-    model: Optional[str] = None
-    message: str = ""
-    error_context: Dict[str, Any] = field(default_factory=dict)
-
-    # Recovery action hints — the retry loop checks these instead of
-    # re-classifying the error itself.
-    retryable: bool = True
-    should_compress: bool = False
-    should_rotate_credential: bool = False
-    should_fallback: bool = False
-
-    @property
-    def is_auth(self) -> bool:
-        return self.reason in (FailoverReason.auth, FailoverReason.auth_permanent)
-
-
-
-# ── Provider-specific patterns ──────────────────────────────────────────
-
-# Patterns that indicate billing exhaustion (not transient rate limit)
-_BILLING_PATTERNS = [
-    "insufficient credits",
-    "insufficient_quota",
-    "credit balance",
-    "credits have been exhausted",
-    "top up your credits",
-    "payment required",
-    "billing hard limit",
-    "exceeded your current quota",
-    "account is deactivated",
-    "plan does not include",
-]
-
-# Patterns that indicate rate limiting (transient, will resolve)
-_RATE_LIMIT_PATTERNS = [
-    "rate limit",
-    "rate_limit",
-    "too many requests",
-    "throttled",
-    "requests per minute",
-    "tokens per minute",
-    "requests per day",
-    "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)
-_USAGE_LIMIT_PATTERNS = [
-    "usage limit",
-    "quota",
-    "limit exceeded",
-    "key limit exceeded",
-]
-
-# Patterns confirming usage limit is transient (not billing)
-_USAGE_LIMIT_TRANSIENT_SIGNALS = [
-    "try again",
-    "retry",
-    "resets at",
-    "reset in",
-    "wait",
-    "requests remaining",
-    "periodic",
-    "window",
-]
-
-# Payload-too-large patterns detected from message text (no status_code attr).
-# Proxies and some backends embed the HTTP status in the error message.
-_PAYLOAD_TOO_LARGE_PATTERNS = [
-    "request entity too large",
-    "payload too large",
-    "error code: 413",
-]
-
-# Context overflow patterns
-_CONTEXT_OVERFLOW_PATTERNS = [
-    "context length",
-    "context size",
-    "maximum context",
-    "token limit",
-    "too many tokens",
-    "reduce the length",
-    "exceeds the limit",
-    "context window",
-    "prompt is too long",
-    "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
-_MODEL_NOT_FOUND_PATTERNS = [
-    "is not a valid model",
-    "invalid model",
-    "model not found",
-    "model_not_found",
-    "does not exist",
-    "no such model",
-    "unknown model",
-    "unsupported model",
-]
-
-# Auth patterns (non-status-code signals)
-_AUTH_PATTERNS = [
-    "invalid api key",
-    "invalid_api_key",
-    "authentication",
-    "unauthorized",
-    "forbidden",
-    "invalid token",
-    "token expired",
-    "token revoked",
-    "access denied",
-]
-
-# Anthropic thinking block signature patterns
-_THINKING_SIG_PATTERNS = [
-    "signature",  # Combined with "thinking" check
-]
-
-# Transport error type names
-_TRANSPORT_ERROR_TYPES = frozenset({
-    "ReadTimeout", "ConnectTimeout", "PoolTimeout",
-    "ConnectError", "RemoteProtocolError",
-    "ConnectionError", "ConnectionResetError",
-    "ConnectionAbortedError", "BrokenPipeError",
-    "TimeoutError", "ReadError",
-    "ServerDisconnectedError",
-    # OpenAI SDK errors (not subclasses of Python builtins)
-    "APIConnectionError",
-    "APITimeoutError",
-})
-
-# Server disconnect patterns (no status code, but transport-level)
-_SERVER_DISCONNECT_PATTERNS = [
-    "server disconnected",
-    "peer closed connection",
-    "connection reset by peer",
-    "connection was closed",
-    "network connection lost",
-    "unexpected eof",
-    "incomplete chunked read",
-]
-
-
-# ── Classification pipeline ─────────────────────────────────────────────
-
-def classify_api_error(
-    error: Exception,
-    *,
-    provider: str = "",
-    model: str = "",
-    approx_tokens: int = 0,
-    context_length: int = 200000,
-    num_messages: int = 0,
-) -> ClassifiedError:
-    """Classify an API error into a structured recovery recommendation.
-
-    Priority-ordered pipeline:
-      1. Special-case provider-specific patterns (thinking sigs, tier gates)
-      2. HTTP status code + message-aware refinement
-      3. Error code classification (from body)
-      4. Message pattern matching (billing vs rate_limit vs context vs auth)
-      5. Transport error heuristics
-      6. Server disconnect + large session → context overflow
-      7. Fallback: unknown (retryable with backoff)
-
-    Args:
-        error: The exception from the API call.
-        provider: Current provider name (e.g. "openrouter", "anthropic").
-        model: Current model slug.
-        approx_tokens: Approximate token count of the current context.
-        context_length: Maximum context length for the current model.
-
-    Returns:
-        ClassifiedError with reason and recovery action hints.
-    """
-    status_code = _extract_status_code(error)
-    error_type = type(error).__name__
-    body = _extract_error_body(error)
-    error_code = _extract_error_code(body)
-
-    # Build a comprehensive error message string for pattern matching.
-    # str(error) alone may not include the body message (e.g. OpenAI SDK's
-    # APIStatusError.__str__ returns the first arg, not the body).  Append
-    # the body message so patterns like "try again" in 402 disambiguation
-    # are detected even when only present in the structured body.
-    #
-    # Also extract metadata.raw — OpenRouter wraps upstream provider errors
-    # inside {"error": {"message": "Provider returned error", "metadata":
-    # {"raw": "<actual error JSON>"}}} and the real error message (e.g.
-    # "context length exceeded") is only in the inner JSON.
-    _raw_msg = str(error).lower()
-    _body_msg = ""
-    _metadata_msg = ""
-    if isinstance(body, dict):
-        _err_obj = body.get("error", {})
-        if isinstance(_err_obj, dict):
-            _body_msg = (_err_obj.get("message") or "").lower()
-            # Parse metadata.raw for wrapped provider errors
-            _metadata = _err_obj.get("metadata", {})
-            if isinstance(_metadata, dict):
-                _raw_json = _metadata.get("raw") or ""
-                if isinstance(_raw_json, str) and _raw_json.strip():
-                    try:
-                        import json
-                        _inner = json.loads(_raw_json)
-                        if isinstance(_inner, dict):
-                            _inner_err = _inner.get("error", {})
-                            if isinstance(_inner_err, dict):
-                                _metadata_msg = (_inner_err.get("message") or "").lower()
-                    except (json.JSONDecodeError, TypeError):
-                        pass
-        if not _body_msg:
-            _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:
-        parts.append(_body_msg)
-    if _metadata_msg and _metadata_msg not in _raw_msg and _metadata_msg not in _body_msg:
-        parts.append(_metadata_msg)
-    error_msg = " ".join(parts)
-    provider_lower = (provider or "").strip().lower()
-    model_lower = (model or "").strip().lower()
-
-    def _result(reason: FailoverReason, **overrides) -> ClassifiedError:
-        defaults = {
-            "reason": reason,
-            "status_code": status_code,
-            "provider": provider,
-            "model": model,
-            "message": _extract_message(error, body),
-        }
-        defaults.update(overrides)
-        return ClassifiedError(**defaults)
-
-    # ── 1. Provider-specific patterns (highest priority) ────────────
-
-    # Anthropic thinking block signature invalid (400).
-    # Don't gate on provider — OpenRouter proxies Anthropic errors, so the
-    # provider may be "openrouter" even though the error is Anthropic-specific.
-    # The message pattern ("signature" + "thinking") is unique enough.
-    if (
-        status_code == 400
-        and "signature" in error_msg
-        and "thinking" in error_msg
-    ):
-        return _result(
-            FailoverReason.thinking_signature,
-            retryable=True,
-            should_compress=False,
-        )
-
-    # Anthropic long-context tier gate (429 "extra usage" + "long context")
-    if (
-        status_code == 429
-        and "extra usage" in error_msg
-        and "long context" in error_msg
-    ):
-        return _result(
-            FailoverReason.long_context_tier,
-            retryable=True,
-            should_compress=True,
-        )
-
-    # ── 2. HTTP status code classification ──────────────────────────
-
-    if status_code is not None:
-        classified = _classify_by_status(
-            status_code, error_msg, error_code, body,
-            provider=provider_lower, model=model_lower,
-            approx_tokens=approx_tokens, context_length=context_length,
-            num_messages=num_messages,
-            result_fn=_result,
-        )
-        if classified is not None:
-            return classified
-
-    # ── 3. Error code classification ────────────────────────────────
-
-    if error_code:
-        classified = _classify_by_error_code(error_code, error_msg, _result)
-        if classified is not None:
-            return classified
-
-    # ── 4. Message pattern matching (no status code) ────────────────
-
-    classified = _classify_by_message(
-        error_msg, error_type,
-        approx_tokens=approx_tokens,
-        context_length=context_length,
-        result_fn=_result,
-    )
-    if classified is not None:
-        return classified
-
-    # ── 5. Server disconnect + large session → context overflow ─────
-    # Must come BEFORE generic transport error catch — a disconnect on
-    # a large session is more likely context overflow than a transient
-    # transport hiccup.  Without this ordering, RemoteProtocolError
-    # always maps to timeout regardless of session size.
-
-    is_disconnect = any(p in error_msg for p in _SERVER_DISCONNECT_PATTERNS)
-    if is_disconnect and not status_code:
-        is_large = approx_tokens > context_length * 0.6 or approx_tokens > 120000 or num_messages > 200
-        if is_large:
-            return _result(
-                FailoverReason.context_overflow,
-                retryable=True,
-                should_compress=True,
-            )
-        return _result(FailoverReason.timeout, retryable=True)
-
-    # ── 6. Transport / timeout heuristics ───────────────────────────
-
-    if error_type in _TRANSPORT_ERROR_TYPES or isinstance(error, (TimeoutError, ConnectionError, OSError)):
-        return _result(FailoverReason.timeout, retryable=True)
-
-    # ── 7. Fallback: unknown ────────────────────────────────────────
-
-    return _result(FailoverReason.unknown, retryable=True)
-
-
-# ── Status code classification ──────────────────────────────────────────
-
-def _classify_by_status(
-    status_code: int,
-    error_msg: str,
-    error_code: str,
-    body: dict,
-    *,
-    provider: str,
-    model: str,
-    approx_tokens: int,
-    context_length: int,
-    num_messages: int = 0,
-    result_fn,
-) -> Optional[ClassifiedError]:
-    """Classify based on HTTP status code with message-aware refinement."""
-
-    if status_code == 401:
-        # Not retryable on its own — credential pool rotation and
-        # provider-specific refresh (Codex, Anthropic, Nous) run before
-        # the retryability check in run_agent.py.  If those succeed, the
-        # loop `continue`s.  If they fail, retryable=False ensures we
-        # hit the client-error abort path (which tries fallback first).
-        return result_fn(
-            FailoverReason.auth,
-            retryable=False,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    if status_code == 403:
-        # OpenRouter 403 "key limit exceeded" is actually billing
-        if "key limit exceeded" in error_msg or "spending limit" in error_msg:
-            return result_fn(
-                FailoverReason.billing,
-                retryable=False,
-                should_rotate_credential=True,
-                should_fallback=True,
-            )
-        return result_fn(
-            FailoverReason.auth,
-            retryable=False,
-            should_fallback=True,
-        )
-
-    if status_code == 402:
-        return _classify_402(error_msg, result_fn)
-
-    if status_code == 404:
-        if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
-            return result_fn(
-                FailoverReason.model_not_found,
-                retryable=False,
-                should_fallback=True,
-            )
-        # Generic 404 — could be model or endpoint
-        return result_fn(
-            FailoverReason.model_not_found,
-            retryable=False,
-            should_fallback=True,
-        )
-
-    if status_code == 413:
-        return result_fn(
-            FailoverReason.payload_too_large,
-            retryable=True,
-            should_compress=True,
-        )
-
-    if status_code == 429:
-        # Already checked long_context_tier above; this is a normal rate limit
-        return result_fn(
-            FailoverReason.rate_limit,
-            retryable=True,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    if status_code == 400:
-        return _classify_400(
-            error_msg, error_code, body,
-            provider=provider, model=model,
-            approx_tokens=approx_tokens,
-            context_length=context_length,
-            num_messages=num_messages,
-            result_fn=result_fn,
-        )
-
-    if status_code in (500, 502):
-        return result_fn(FailoverReason.server_error, retryable=True)
-
-    if status_code in (503, 529):
-        return result_fn(FailoverReason.overloaded, retryable=True)
-
-    # Other 4xx — non-retryable
-    if 400 <= status_code < 500:
-        return result_fn(
-            FailoverReason.format_error,
-            retryable=False,
-            should_fallback=True,
-        )
-
-    # Other 5xx — retryable
-    if 500 <= status_code < 600:
-        return result_fn(FailoverReason.server_error, retryable=True)
-
-    return None
-
-
-def _classify_402(error_msg: str, result_fn) -> ClassifiedError:
-    """Disambiguate 402: billing exhaustion vs transient usage limit.
-
-    The key insight from OpenClaw: some 402s are transient rate limits
-    disguised as payment errors.  "Usage limit, try again in 5 minutes"
-    is NOT a billing problem — it's a periodic quota that resets.
-    """
-    # Check for transient usage-limit signals first
-    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
-    has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
-
-    if has_usage_limit and has_transient_signal:
-        # Transient quota — treat as rate limit, not billing
-        return result_fn(
-            FailoverReason.rate_limit,
-            retryable=True,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    # Confirmed billing exhaustion
-    return result_fn(
-        FailoverReason.billing,
-        retryable=False,
-        should_rotate_credential=True,
-        should_fallback=True,
-    )
-
-
-def _classify_400(
-    error_msg: str,
-    error_code: str,
-    body: dict,
-    *,
-    provider: str,
-    model: str,
-    approx_tokens: int,
-    context_length: int,
-    num_messages: int = 0,
-    result_fn,
-) -> ClassifiedError:
-    """Classify 400 Bad Request — context overflow, format error, or generic."""
-
-    # Context overflow from 400
-    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
-        return result_fn(
-            FailoverReason.context_overflow,
-            retryable=True,
-            should_compress=True,
-        )
-
-    # Some providers return model-not-found as 400 instead of 404 (e.g. OpenRouter).
-    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
-        return result_fn(
-            FailoverReason.model_not_found,
-            retryable=False,
-            should_fallback=True,
-        )
-
-    # Some providers return rate limit / billing errors as 400 instead of 429/402.
-    # Check these patterns before falling through to format_error.
-    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
-        return result_fn(
-            FailoverReason.rate_limit,
-            retryable=True,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-    if any(p in error_msg for p in _BILLING_PATTERNS):
-        return result_fn(
-            FailoverReason.billing,
-            retryable=False,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    # Generic 400 + large session → probable context overflow
-    # Anthropic sometimes returns a bare "Error" message when context is too large
-    err_body_msg = ""
-    if isinstance(body, dict):
-        err_obj = body.get("error", {})
-        if isinstance(err_obj, dict):
-            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 = (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
-
-    if is_generic and is_large:
-        return result_fn(
-            FailoverReason.context_overflow,
-            retryable=True,
-            should_compress=True,
-        )
-
-    # Non-retryable format error
-    return result_fn(
-        FailoverReason.format_error,
-        retryable=False,
-        should_fallback=True,
-    )
-
-
-# ── Error code classification ───────────────────────────────────────────
-
-def _classify_by_error_code(
-    error_code: str, error_msg: str, result_fn,
-) -> Optional[ClassifiedError]:
-    """Classify by structured error codes from the response body."""
-    code_lower = error_code.lower()
-
-    if code_lower in ("resource_exhausted", "throttled", "rate_limit_exceeded"):
-        return result_fn(
-            FailoverReason.rate_limit,
-            retryable=True,
-            should_rotate_credential=True,
-        )
-
-    if code_lower in ("insufficient_quota", "billing_not_active", "payment_required"):
-        return result_fn(
-            FailoverReason.billing,
-            retryable=False,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    if code_lower in ("model_not_found", "model_not_available", "invalid_model"):
-        return result_fn(
-            FailoverReason.model_not_found,
-            retryable=False,
-            should_fallback=True,
-        )
-
-    if code_lower in ("context_length_exceeded", "max_tokens_exceeded"):
-        return result_fn(
-            FailoverReason.context_overflow,
-            retryable=True,
-            should_compress=True,
-        )
-
-    return None
-
-
-# ── Message pattern classification ──────────────────────────────────────
-
-def _classify_by_message(
-    error_msg: str,
-    error_type: str,
-    *,
-    approx_tokens: int,
-    context_length: int,
-    result_fn,
-) -> Optional[ClassifiedError]:
-    """Classify based on error message patterns when no status code is available."""
-
-    # Payload-too-large patterns (from message text when no status_code)
-    if any(p in error_msg for p in _PAYLOAD_TOO_LARGE_PATTERNS):
-        return result_fn(
-            FailoverReason.payload_too_large,
-            retryable=True,
-            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(
-            FailoverReason.billing,
-            retryable=False,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    # Rate limit patterns
-    if any(p in error_msg for p in _RATE_LIMIT_PATTERNS):
-        return result_fn(
-            FailoverReason.rate_limit,
-            retryable=True,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    # Context overflow patterns
-    if any(p in error_msg for p in _CONTEXT_OVERFLOW_PATTERNS):
-        return result_fn(
-            FailoverReason.context_overflow,
-            retryable=True,
-            should_compress=True,
-        )
-
-    # 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,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
-    # Model not found patterns
-    if any(p in error_msg for p in _MODEL_NOT_FOUND_PATTERNS):
-        return result_fn(
-            FailoverReason.model_not_found,
-            retryable=False,
-            should_fallback=True,
-        )
-
-    return None
-
-
-# ── Helpers ─────────────────────────────────────────────────────────────
-
-def _extract_status_code(error: Exception) -> Optional[int]:
-    """Walk the error and its cause chain to find an HTTP status code."""
-    current = error
-    for _ in range(5):  # Max depth to prevent infinite loops
-        code = getattr(current, "status_code", None)
-        if isinstance(code, int):
-            return code
-        # Some SDKs use .status instead of .status_code
-        code = getattr(current, "status", None)
-        if isinstance(code, int) and 100 <= code < 600:
-            return code
-        # Walk cause chain
-        cause = getattr(current, "__cause__", None) or getattr(current, "__context__", None)
-        if cause is None or cause is current:
-            break
-        current = cause
-    return None
-
-
-def _extract_error_body(error: Exception) -> dict:
-    """Extract the structured error body from an SDK exception."""
-    body = getattr(error, "body", None)
-    if isinstance(body, dict):
-        return body
-    # Some errors have .response.json()
-    response = getattr(error, "response", None)
-    if response is not None:
-        try:
-            json_body = response.json()
-            if isinstance(json_body, dict):
-                return json_body
-        except Exception:
-            pass
-    return {}
-
-
-def _extract_error_code(body: dict) -> str:
-    """Extract an error code string from the response body."""
-    if not body:
-        return ""
-    error_obj = body.get("error", {})
-    if isinstance(error_obj, dict):
-        code = error_obj.get("code") or error_obj.get("type") or ""
-        if isinstance(code, str) and code.strip():
-            return code.strip()
-    # Top-level code
-    code = body.get("code") or body.get("error_code") or ""
-    if isinstance(code, (str, int)):
-        return str(code).strip()
-    return ""
-
-
-def _extract_message(error: Exception, body: dict) -> str:
-    """Extract the most informative error message."""
-    # Try structured body first
-    if body:
-        error_obj = body.get("error", {})
-        if isinstance(error_obj, dict):
-            msg = error_obj.get("message", "")
-            if isinstance(msg, str) and msg.strip():
-                return msg.strip()[:500]
-        msg = body.get("message", "")
-        if isinstance(msg, str) and msg.strip():
-            return msg.strip()[:500]
-    # Fallback to str(error)
-    return str(error)[:500]

agent/gemini_cloudcode_adapter.py

@@ -1,764 +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.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"] = 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_indices: Dict[str, int],
-) -> List[_GeminiStreamChunk]:
-    """Unwrap Code Assist envelope and emit OpenAI-shaped chunk(s)."""
-    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_indices.setdefault(name, len(tool_call_indices))
-            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_indices:
-            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_indices: Dict[str, int] = {}
-                    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 CodeAssistError(
-                    f"Streaming request failed: {exc}",
-                    code="code_assist_stream_error",
-                ) from exc
-
-        return _generator()
-
-
-def _gemini_http_error(response: httpx.Response) -> CodeAssistError:
-    status = response.status_code
-    try:
-        body = response.text[:500]
-    except Exception:
-        body = ""
-    # Let run_agent's retry logic see auth errors as rotatable via `api_key`
-    code = f"code_assist_http_{status}"
-    if status == 401:
-        code = "code_assist_unauthorized"
-    elif status == 429:
-        code = "code_assist_rate_limited"
-    return CodeAssistError(
-        f"Code Assist returned HTTP {status}: {body}",
-        code=code,
-    )

agent/google_code_assist.py

@@ -1,417 +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):
-    def __init__(self, message: str, *, code: str = "code_assist_error") -> None:
-        super().__init__(message)
-        self.code = code
-
-
-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,
 )
 
@@ -38,6 +39,15 @@ def _has_known_pricing(model_name: str, provider: str = None, base_url: str = No
     return has_known_pricing(model_name, provider=provider, base_url=base_url)
 
 
+def _get_pricing(model_name: str) -> Dict[str, float]:
+    """Look up pricing for a model. Uses fuzzy matching on model name.
+
+    Returns _DEFAULT_PRICING (zero cost) for unknown/custom models —
+    we can't assume costs for self-hosted endpoints, local inference, etc.
+    """
+    return get_pricing(model_name)
+
+
 def _estimate_cost(
     session_or_model: Dict[str, Any] | str,
     input_tokens: int = 0,
@@ -634,7 +644,13 @@ 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"${o['estimated_cost']:.2f}"
+        if o.get("models_without_pricing"):
+            cost_str += " *"
+        lines.append(f"  Total tokens:      {o['total_tokens']:<12,}  Est. cost:       {cost_str}")
         if o["total_hours"] > 0:
             lines.append(f"  Active time:       ~{_format_duration(o['total_hours'] * 3600):<11}  Avg session:     ~{_format_duration(o['avg_session_duration'])}")
         lines.append(f"  Avg msgs/session:  {o['avg_messages_per_session']:.1f}")
@@ -644,10 +660,16 @@ class InsightsEngine:
         if report["models"]:
             lines.append("  🤖 Models Used")
             lines.append("  " + "─" * 56)
-            lines.append(f"  {'Model':<30} {'Sessions':>8} {'Tokens':>12}")
+            lines.append(f"  {'Model':<30} {'Sessions':>8} {'Tokens':>12} {'Cost':>8}")
             for m in report["models"]:
                 model_name = m["model"][:28]
-                lines.append(f"  {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,}")
+                if m.get("has_pricing"):
+                    cost_cell = f"${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
@@ -727,7 +749,15 @@ 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:** ${o['estimated_cost']:.2f}{cost_note}")
         if o["total_hours"] > 0:
             lines.append(f"**Active time:** ~{_format_duration(o['total_hours'] * 3600)} | **Avg session:** ~{_format_duration(o['avg_session_duration'])}")
         lines.append("")
@@ -736,7 +766,8 @@ class InsightsEngine:
         if report["models"]:
             lines.append("**🤖 Models:**")
             for m in report["models"][:5]:
-                lines.append(f"  {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens")
+                cost_str = f"${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)

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:
@@ -145,6 +134,11 @@ class MemoryManager:
         """All registered providers in order."""
         return list(self._providers)
 
+    @property
+    def provider_names(self) -> List[str]:
+        """Names of all registered providers."""
+        return [p.name for p in self._providers]
+
     def get_provider(self, name: str) -> Optional[MemoryProvider]:
         """Get a provider by name, or None if not registered."""
         for p in self._providers:

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
@@ -23,21 +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",
     "qwen-portal",
 })
 
@@ -88,11 +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.
@@ -102,23 +92,15 @@ 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-5.3-codex-spark": 128000,    # Spark variant has reduced 128k 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,
@@ -131,48 +113,33 @@ DEFAULT_CONTEXT_LENGTHS = {
     "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,
     # 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,
 }
 
@@ -197,12 +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:
@@ -224,9 +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",
@@ -239,10 +198,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "models.github.ai": "copilot",
     "api.fireworks.ai": "fireworks",
     "opencode.ai": "opencode-go",
-    "api.x.ai": "xai",
-    "api.xiaomimimo.com": "xiaomi",
-    "xiaomimimo.com": "xiaomi",
-    "ollama.com": "ollama-cloud",
 }
 
 
@@ -281,9 +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:
@@ -651,49 +603,6 @@ def parse_context_limit_from_error(error_msg: str) -> Optional[int]:
     return None
 
 
-def parse_available_output_tokens_from_error(error_msg: str) -> Optional[int]:
-    """Detect an "output cap too large" error and return how many output tokens are available.
-
-    Background — two distinct context errors exist:
-      1. "Prompt too long"  — the INPUT itself exceeds the context window.
-           Fix: compress history and/or halve context_length.
-      2. "max_tokens too large" — input is fine, but input + requested_output > window.
-           Fix: reduce max_tokens (the output cap) for this call.
-           Do NOT touch context_length — the window hasn't shrunk.
-
-    Anthropic's API returns errors like:
-      "max_tokens: 32768 > context_window: 200000 - input_tokens: 190000 = available_tokens: 10000"
-
-    Returns the number of output tokens that would fit (e.g. 10000 above), or None if
-    the error does not look like a max_tokens-too-large error.
-    """
-    error_lower = error_msg.lower()
-
-    # Must look like an output-cap error, not a prompt-length error.
-    is_output_cap_error = (
-        "max_tokens" in error_lower
-        and ("available_tokens" in error_lower or "available tokens" in error_lower)
-    )
-    if not is_output_cap_error:
-        return None
-
-    # Extract the available_tokens figure.
-    # Anthropic format: "… = available_tokens: 10000"
-    patterns = [
-        r'available_tokens[:\s]+(\d+)',
-        r'available\s+tokens[:\s]+(\d+)',
-        # fallback: last number after "=" in expressions like "200000 - 190000 = 10000"
-        r'=\s*(\d+)\s*$',
-    ]
-    for pattern in patterns:
-        match = re.search(pattern, error_lower)
-        if match:
-            tokens = int(match.group(1))
-            if tokens >= 1:
-                return tokens
-    return None
-
-
 def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
     """Return True if *candidate_id* (from server) matches *lookup_model* (configured).
 
@@ -791,12 +700,12 @@ 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"):
@@ -807,11 +716,6 @@ 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
@@ -1016,16 +920,6 @@ 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
@@ -1076,21 +970,16 @@ 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(
@@ -1113,4 +1002,4 @@ 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
@@ -133,6 +135,9 @@ class ProviderInfo:
     doc: str = ""                   # documentation URL
     model_count: int = 0
 
+    def has_api_url(self) -> bool:
+        return bool(self.api)
+
 
 # ---------------------------------------------------------------------------
 # Provider ID mapping: Hermes ↔ models.dev
@@ -142,11 +147,8 @@ 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 +164,25 @@ 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 +386,7 @@ 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
@@ -456,6 +456,93 @@ 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
@@ -547,6 +634,43 @@ def get_provider_info(provider_id: str) -> Optional[ProviderInfo]:
     return _parse_provider_info(mdev_id, raw)
 
 
+def list_all_providers() -> Dict[str, ProviderInfo]:
+    """Return all providers from models.dev as {provider_id: ProviderInfo}.
+
+    Returns the full catalog — 109+ providers.  For providers that have
+    a Hermes alias, both the models.dev ID and the Hermes ID are included.
+    """
+    data = fetch_models_dev()
+    result: Dict[str, ProviderInfo] = {}
+
+    for pid, pdata in data.items():
+        if isinstance(pdata, dict):
+            info = _parse_provider_info(pid, pdata)
+            result[pid] = info
+
+    return result
+
+
+def get_providers_for_env_var(env_var: str) -> List[str]:
+    """Reverse lookup: find all providers that use a given env var.
+
+    Useful for auto-detection: "user has ANTHROPIC_API_KEY set, which
+    providers does that enable?"
+
+    Returns list of models.dev provider IDs.
+    """
+    data = fetch_models_dev()
+    matches: List[str] = []
+
+    for pid, pdata in data.items():
+        if isinstance(pdata, dict):
+            env = pdata.get("env", [])
+            if isinstance(env, list) and env_var in env:
+                matches.append(pid)
+
+    return matches
+
+
 # ---------------------------------------------------------------------------
 # Model-level queries (rich ModelInfo)
 # ---------------------------------------------------------------------------
@@ -584,3 +708,74 @@ def get_model_info(
     return None
 
 
+def get_model_info_any_provider(model_id: str) -> Optional[ModelInfo]:
+    """Search all providers for a model by ID.
+
+    Useful when you have a full slug like "anthropic/claude-sonnet-4.6" or
+    a bare name and want to find it anywhere.  Checks Hermes-mapped providers
+    first, then falls back to all models.dev providers.
+    """
+    data = fetch_models_dev()
+
+    # Try Hermes-mapped providers first (more likely what the user wants)
+    for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
+        pdata = data.get(mdev_id)
+        if not isinstance(pdata, dict):
+            continue
+        models = pdata.get("models", {})
+        if not isinstance(models, dict):
+            continue
+
+        raw = models.get(model_id)
+        if isinstance(raw, dict):
+            return _parse_model_info(model_id, raw, mdev_id)
+
+        # Case-insensitive
+        model_lower = model_id.lower()
+        for mid, mdata in models.items():
+            if mid.lower() == model_lower and isinstance(mdata, dict):
+                return _parse_model_info(mid, mdata, mdev_id)
+
+    # Fall back to ALL providers
+    for pid, pdata in data.items():
+        if pid in _get_reverse_mapping():
+            continue  # already checked
+        if not isinstance(pdata, dict):
+            continue
+        models = pdata.get("models", {})
+        if not isinstance(models, dict):
+            continue
+
+        raw = models.get(model_id)
+        if isinstance(raw, dict):
+            return _parse_model_info(model_id, raw, pid)
+
+    return None
+
+
+def list_provider_model_infos(provider_id: str) -> List[ModelInfo]:
+    """Return all models for a provider as ModelInfo objects.
+
+    Filters out deprecated models by default.
+    """
+    mdev_id = PROVIDER_TO_MODELS_DEV.get(provider_id, provider_id)
+
+    data = fetch_models_dev()
+    pdata = data.get(mdev_id)
+    if not isinstance(pdata, dict):
+        return []
+
+    models = pdata.get("models", {})
+    if not isinstance(models, dict):
+        return []
+
+    result: List[ModelInfo] = []
+    for mid, mdata in models.items():
+        if not isinstance(mdata, dict):
+            continue
+        status = mdata.get("status", "")
+        if status == "deprecated":
+            continue
+        result.append(_parse_model_info(mid, mdata, mdev_id))
+
+    return result

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"),
@@ -295,9 +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 "
@@ -358,64 +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
@@ -537,7 +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):
@@ -545,10 +487,21 @@ 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, {}, ""
 
 
+def _read_skill_conditions(skill_file: Path) -> dict:
+    """Extract conditional activation fields from SKILL.md frontmatter."""
+    try:
+        raw = skill_file.read_text(encoding="utf-8")[:2000]
+        frontmatter, _ = parse_frontmatter(raw)
+        return extract_skill_conditions(frontmatter)
+    except Exception as e:
+        logger.debug("Failed to read skill conditions from %s: %s", skill_file, e)
+        return {}
+
+
 def _skill_should_show(
     conditions: dict,
     available_tools: "set[str] | None",
@@ -598,7 +551,8 @@ 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:
@@ -607,10 +561,9 @@ 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 ""
     )
     cache_key = (
@@ -776,16 +729,8 @@ 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 "
@@ -795,7 +740,7 @@ 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

@@ -1,246 +0,0 @@
-"""Rate limit tracking for inference API responses.
-
-Captures x-ratelimit-* headers from provider responses and provides
-formatted display for the /usage slash command.  Currently supports
-the Nous Portal header format (also used by OpenRouter and OpenAI-compatible
-APIs that follow the same convention).
-
-Header schema (12 headers total):
-    x-ratelimit-limit-requests          RPM cap
-    x-ratelimit-limit-requests-1h       RPH cap
-    x-ratelimit-limit-tokens            TPM cap
-    x-ratelimit-limit-tokens-1h         TPH cap
-    x-ratelimit-remaining-requests      requests left in minute window
-    x-ratelimit-remaining-requests-1h   requests left in hour window
-    x-ratelimit-remaining-tokens        tokens left in minute window
-    x-ratelimit-remaining-tokens-1h     tokens left in hour window
-    x-ratelimit-reset-requests          seconds until minute request window resets
-    x-ratelimit-reset-requests-1h       seconds until hour request window resets
-    x-ratelimit-reset-tokens            seconds until minute token window resets
-    x-ratelimit-reset-tokens-1h         seconds until hour token window resets
-"""
-
-from __future__ import annotations
-
-import time
-from dataclasses import dataclass, field
-from typing import Any, Mapping, Optional
-
-
-@dataclass
-class RateLimitBucket:
-    """One rate-limit window (e.g. requests per minute)."""
-
-    limit: int = 0
-    remaining: int = 0
-    reset_seconds: float = 0.0
-    captured_at: float = 0.0  # time.time() when this was captured
-
-    @property
-    def used(self) -> int:
-        return max(0, self.limit - self.remaining)
-
-    @property
-    def usage_pct(self) -> float:
-        if self.limit <= 0:
-            return 0.0
-        return (self.used / self.limit) * 100.0
-
-    @property
-    def remaining_seconds_now(self) -> float:
-        """Estimated seconds remaining until reset, adjusted for elapsed time."""
-        elapsed = time.time() - self.captured_at
-        return max(0.0, self.reset_seconds - elapsed)
-
-
-@dataclass
-class RateLimitState:
-    """Full rate-limit state parsed from response headers."""
-
-    requests_min: RateLimitBucket = field(default_factory=RateLimitBucket)
-    requests_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
-    tokens_min: RateLimitBucket = field(default_factory=RateLimitBucket)
-    tokens_hour: RateLimitBucket = field(default_factory=RateLimitBucket)
-    captured_at: float = 0.0  # when the headers were captured
-    provider: str = ""
-
-    @property
-    def has_data(self) -> bool:
-        return self.captured_at > 0
-
-    @property
-    def age_seconds(self) -> float:
-        if not self.has_data:
-            return float("inf")
-        return time.time() - self.captured_at
-
-
-def _safe_int(value: Any, default: int = 0) -> int:
-    try:
-        return int(float(value))
-    except (TypeError, ValueError):
-        return default
-
-
-def _safe_float(value: Any, default: float = 0.0) -> float:
-    try:
-        return float(value)
-    except (TypeError, ValueError):
-        return default
-
-
-def parse_rate_limit_headers(
-    headers: Mapping[str, str],
-    provider: str = "",
-) -> Optional[RateLimitState]:
-    """Parse x-ratelimit-* headers into a RateLimitState.
-
-    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)
-    if not has_any:
-        return None
-
-    now = time.time()
-
-    def _bucket(resource: str, suffix: str = "") -> RateLimitBucket:
-        # e.g. resource="requests", suffix="" -> per-minute
-        #      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}")),
-            captured_at=now,
-        )
-
-    return RateLimitState(
-        requests_min=_bucket("requests"),
-        requests_hour=_bucket("requests", "-1h"),
-        tokens_min=_bucket("tokens"),
-        tokens_hour=_bucket("tokens", "-1h"),
-        captured_at=now,
-        provider=provider,
-    )
-
-
-# ── Formatting ──────────────────────────────────────────────────────────
-
-
-def _fmt_count(n: int) -> str:
-    """Human-friendly number: 7999856 -> '8.0M', 33599 -> '33.6K', 799 -> '799'."""
-    if n >= 1_000_000:
-        return f"{n / 1_000_000:.1f}M"
-    if n >= 10_000:
-        return f"{n / 1_000:.1f}K"
-    if n >= 1_000:
-        return f"{n / 1_000:.1f}K"
-    return str(n)
-
-
-def _fmt_seconds(seconds: float) -> str:
-    """Seconds -> human-friendly duration: '58s', '2m 14s', '58m 57s', '1h 2m'."""
-    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"
-
-
-def _bar(pct: float, width: int = 20) -> str:
-    """ASCII progress bar: [████████░░░░░░░░░░░░] 40%."""
-    filled = int(pct / 100.0 * width)
-    filled = max(0, min(width, filled))
-    empty = width - filled
-    return f"[{'█' * filled}{'░' * empty}]"
-
-
-def _bucket_line(label: str, bucket: RateLimitBucket, label_width: int = 14) -> str:
-    """Format one bucket as a single line."""
-    if bucket.limit <= 0:
-        return f"  {label:<{label_width}}  (no data)"
-
-    pct = bucket.usage_pct
-    used = _fmt_count(bucket.used)
-    limit = _fmt_count(bucket.limit)
-    remaining = _fmt_count(bucket.remaining)
-    reset = _fmt_seconds(bucket.remaining_seconds_now)
-
-    bar = _bar(pct)
-    return f"  {label:<{label_width}} {bar} {pct:5.1f}%  {used}/{limit} used  ({remaining} left, resets in {reset})"
-
-
-def format_rate_limit_display(state: RateLimitState) -> str:
-    """Format rate limit state for terminal/chat display."""
-    if not state.has_data:
-        return "No rate limit data yet — make an API request first."
-
-    age = state.age_seconds
-    if age < 5:
-        freshness = "just now"
-    elif age < 60:
-        freshness = f"{int(age)}s ago"
-    else:
-        freshness = f"{_fmt_seconds(age)} ago"
-
-    provider_label = state.provider.title() if state.provider else "Provider"
-
-    lines = [
-        f"{provider_label} Rate Limits (captured {freshness}):",
-        "",
-        _bucket_line("Requests/min", state.requests_min),
-        _bucket_line("Requests/hr", state.requests_hour),
-        "",
-        _bucket_line("Tokens/min", state.tokens_min),
-        _bucket_line("Tokens/hr", state.tokens_hour),
-    ]
-
-    # Add warnings if any bucket is getting hot
-    warnings = []
-    for label, bucket in [
-        ("requests/min", state.requests_min),
-        ("requests/hr", state.requests_hour),
-        ("tokens/min", state.tokens_min),
-        ("tokens/hr", state.tokens_hour),
-    ]:
-        if bucket.limit > 0 and bucket.usage_pct >= 80:
-            reset = _fmt_seconds(bucket.remaining_seconds_now)
-            warnings.append(f"  ⚠ {label} at {bucket.usage_pct:.0f}% — resets in {reset}")
-
-    if warnings:
-        lines.append("")
-        lines.extend(warnings)
-
-    return "\n".join(lines)
-
-
-def format_rate_limit_compact(state: RateLimitState) -> str:
-    """One-line compact summary for status bars / gateway messages."""
-    if not state.has_data:
-        return "No rate limit data."
-
-    rm = state.requests_min
-    tm = state.tokens_min
-    rh = state.requests_hour
-    th = state.tokens_hour
-
-    parts = []
-    if rm.limit > 0:
-        parts.append(f"RPM: {rm.remaining}/{rm.limit}")
-    if rh.limit > 0:
-        parts.append(f"RPH: {_fmt_count(rh.remaining)}/{_fmt_count(rh.limit)} (resets {_fmt_seconds(rh.remaining_seconds_now)})")
-    if tm.limit > 0:
-        parts.append(f"TPM: {_fmt_count(tm.remaining)}/{_fmt_count(tm.limit)}")
-    if th.limit > 0:
-        parts.append(f"TPH: {_fmt_count(th.remaining)}/{_fmt_count(th.limit)} (resets {_fmt_seconds(th.remaining_seconds_now)})")
-
-    return " | ".join(parts)

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

@@ -181,7 +181,6 @@ def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any
             "api_mode": runtime.get("api_mode"),
             "command": runtime.get("command"),
             "args": list(runtime.get("args") or []),
-            "credential_pool": runtime.get("credential_pool"),
         },
         "label": f"smart route → {route.get('model')} ({runtime.get('provider')})",
         "signature": (

agent/subdirectory_hints.py

@@ -159,10 +159,7 @@ class SubdirectoryHintTracker:
 
     def _is_valid_subdir(self, path: Path) -> bool:
         """Check if path is a valid directory to scan for hints."""
-        try:
-            if not path.is_dir():
-                return False
-        except OSError:
+        if not path.is_dir():
             return False
         if path in self._loaded_dirs:
             return False
@@ -175,10 +172,7 @@ class SubdirectoryHintTracker:
         found_hints = []
         for filename in _HINT_FILENAMES:
             hint_path = directory / filename
-            try:
-                if not hint_path.is_file():
-                    continue
-            except OSError:
+            if not hint_path.is_file():
                 continue
             try:
                 content = hint_path.read_text(encoding="utf-8").strip()

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/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 +575,49 @@ 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 estimate_cost_usd(
+    model: str,
+    input_tokens: int,
+    output_tokens: int,
+    *,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> float:
+    """Backward-compatible helper for legacy callers.
+
+    This uses non-cached input/output only. New code should call
+    `estimate_usage_cost()` with canonical usage buckets.
+    """
+    result = estimate_usage_cost(
+        model,
+        CanonicalUsage(input_tokens=input_tokens, output_tokens=output_tokens),
+        provider=provider,
+        base_url=base_url,
+        api_key=api_key,
+    )
+    return float(result.amount_usd or _ZERO)
+
 
 def format_duration_compact(seconds: float) -> str:
     if seconds < 60:

batch_runner.py

@@ -561,10 +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)
@@ -1161,7 +1158,7 @@ def main(
         providers_order (str): Comma-separated list of OpenRouter providers to try in order (e.g. "anthropic,openai,google")
         provider_sort (str): Sort providers by "price", "throughput", or "latency" (OpenRouter only)
         max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
-        reasoning_effort (str): OpenRouter reasoning effort level: "none", "minimal", "low", "medium", "high", "xhigh" (default: "medium")
+        reasoning_effort (str): OpenRouter reasoning effort level: "xhigh", "high", "medium", "low", "minimal", "none" (default: "medium")
         reasoning_disabled (bool): Completely disable reasoning/thinking tokens (default: False)
         prefill_messages_file (str): Path to JSON file containing prefill messages (list of {role, content} dicts)
         max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
@@ -1230,7 +1227,7 @@ def main(
         print("🧠 Reasoning: DISABLED (effort=none)")
     elif reasoning_effort:
         # Use specified effort level
-        valid_efforts = ["none", "minimal", "low", "medium", "high", "xhigh"]
+        valid_efforts = ["xhigh", "high", "medium", "low", "minimal", "none"]
         if reasoning_effort not in valid_efforts:
             print(f"❌ Error: --reasoning_effort must be one of: {', '.join(valid_efforts)}")
             return

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)
@@ -24,9 +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)
-  #   "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)
   #
@@ -38,6 +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"
   
@@ -45,25 +48,6 @@ model:
   # api_key: "your-key-here"  # Uncomment to set here instead of .env
   base_url: "https://openrouter.ai/api/v1"
 
-  # ── Token limits — two settings, easy to confuse ──────────────────────────
-  #
-  # context_length: TOTAL context window (input + output tokens combined).
-  #   Controls when Hermes compresses history and validates requests.
-  #   Leave unset — Hermes auto-detects the correct value from the provider.
-  #   Set manually only when auto-detection is wrong (e.g. a local server with
-  #   a custom num_ctx, or a proxy that doesn't expose /v1/models).
-  #
-  # context_length: 131072
-  #
-  # max_tokens: OUTPUT cap — maximum tokens the model may generate per response.
-  #   Unrelated to how long your conversation history can be.
-  #   The OpenAI-standard name "max_tokens" is a misnomer; Anthropic's native
-  #   API has since renamed it "max_output_tokens" for clarity.
-  #   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
-
 # =============================================================================
 # OpenRouter Provider Routing (only applies when using OpenRouter)
 # =============================================================================
@@ -133,8 +117,7 @@ terminal:
   timeout: 180
   docker_mount_cwd_to_workspace: false  # SECURITY: off by default. Opt in to mount the launch cwd into Docker /workspace.
   lifetime_seconds: 300
-  # sudo_password: "hunter2"  # Optional: pipe a sudo password via sudo -S. SECURITY WARNING: plaintext.
-  # sudo_password: ""         # Explicit empty password: try empty and never open the interactive sudo prompt.
+  # sudo_password: ""  # Enable sudo commands (pipes via sudo -S) - SECURITY WARNING: plaintext!
 
 # -----------------------------------------------------------------------------
 # OPTION 2: SSH remote execution
@@ -225,18 +208,13 @@ terminal:
 #
 # SECURITY WARNING: Password stored in plaintext!
 #
-# INTERACTIVE PROMPT: If sudo_password is unset and the CLI is running,
+# INTERACTIVE PROMPT: If no sudo_password is set and the CLI is running,
 # you'll be prompted to enter your password when sudo is needed:
 # - 45-second timeout (auto-skips if no input)
 # - Press Enter to skip (command fails gracefully)
 # - Password is hidden while typing
 # - Password is cached for the session
 #
-# EMPTY PASSWORDS: Setting sudo_password to an explicit empty string is different
-# from leaving it unset. Hermes will try an empty password via `sudo -S` and
-# will not open the interactive prompt. This is useful for passwordless sudo,
-# Touch ID sudo setups, and environments where prompting is just noise.
-#
 # ALTERNATIVES:
 # - SSH backend: Configure passwordless sudo on the remote server
 # - Containers: Run as root inside the container (no sudo needed)
@@ -305,8 +283,15 @@ 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)
@@ -332,7 +317,6 @@ 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).
@@ -471,12 +455,6 @@ 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
@@ -519,7 +497,7 @@ 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:
 #
@@ -548,7 +526,6 @@ 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]
@@ -558,19 +535,6 @@ 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)
@@ -593,7 +557,7 @@ 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)
 #
@@ -622,7 +586,7 @@ 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)
 #
@@ -695,11 +659,7 @@ 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
 
@@ -778,11 +738,6 @@ 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
@@ -791,7 +746,7 @@ 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
@@ -45,8 +44,7 @@ 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",
 })
 
 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run
@@ -221,21 +219,6 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     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,
-        )
-
     from tools.send_message_tool import _send_to_platform
     from gateway.config import load_gateway_config, Platform
 
@@ -251,12 +234,9 @@ 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:
@@ -289,13 +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
@@ -368,42 +346,7 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
     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]:
@@ -450,27 +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:
@@ -479,10 +412,17 @@ 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}"
 
@@ -646,15 +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()
@@ -715,24 +646,6 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             },
         )
 
-        fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
-        credential_pool = None
-        runtime_provider = str(turn_route["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)
-
         agent = AIAgent(
             model=turn_route["model"],
             api_key=turn_route["runtime"].get("api_key"),
@@ -744,15 +657,12 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
             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,
@@ -771,11 +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:
@@ -805,7 +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.
@@ -837,9 +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)"
@@ -979,13 +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/migration/openclaw.md

@@ -11,14 +11,12 @@ When you run `hermes setup` for the first time and Hermes detects `~/.openclaw`,
 ### 2. CLI Command (quick, scriptable)
 
 ```bash
-hermes claw migrate                      # Preview then migrate (always shows preview first)
-hermes claw migrate --dry-run            # Preview only, no changes
+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
 ```
 
-The migration always shows a full preview of what will be imported before making any changes. You review the preview and confirm before anything is written.
-
 **All options:**
 
 | Flag | Description |
@@ -41,7 +39,7 @@ Ask the agent to run the migration for you:
 ```
 
 The agent will use the `openclaw-migration` skill to:
-1. Run a preview first to show what would change
+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
@@ -60,31 +58,16 @@ The agent will use the `openclaw-migration` skill to:
 | Messaging settings | `~/.openclaw/config.yaml` (TELEGRAM_ALLOWED_USERS, MESSAGING_CWD) | `~/.hermes/.env` |
 | TTS assets | `~/.openclaw/workspace/tts/` | `~/.hermes/tts/` |
 
-Workspace files are also checked at `workspace.default/` and `workspace-main/` as fallback paths (OpenClaw renamed `workspace/` to `workspace-main/` in recent versions).
-
 ### `full` preset (adds to `user-data`)
 | Item | Source | Destination |
 |------|--------|-------------|
-| Telegram bot token | `openclaw.json` channels config | `~/.hermes/.env` |
-| OpenRouter API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
-| OpenAI API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
-| Anthropic API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
-| ElevenLabs API key | `.env`, `openclaw.json`, or `openclaw.json["env"]` | `~/.hermes/.env` |
+| 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` |
 
-API keys are searched across four sources: inline config values, `~/.openclaw/.env`, the `openclaw.json` `"env"` sub-object, and per-agent auth profiles.
-
-Only allowlisted secrets are ever imported. Other credentials are skipped and reported.
-
-## OpenClaw Schema Compatibility
-
-The migration handles both old and current OpenClaw config layouts:
-
-- **Channel tokens**: Reads from flat paths (`channels.telegram.botToken`) and the newer `accounts.default` layout (`channels.telegram.accounts.default.botToken`)
-- **TTS provider**: OpenClaw renamed "edge" to "microsoft" — both are recognized and mapped to Hermes' "edge"
-- **Provider API types**: Both short (`openai`, `anthropic`) and hyphenated (`openai-completions`, `anthropic-messages`, `google-generative-ai`) values are mapped correctly
-- **thinkingDefault**: All enum values are handled including newer ones (`minimal`, `xhigh`, `adaptive`)
-- **Matrix**: Uses `accessToken` field (not `botToken`)
-- **SecretRef formats**: Plain strings, env templates (`${VAR}`), and `source: "env"` SecretRefs are resolved. `source: "file"` and `source: "exec"` SecretRefs produce a warning — add those keys manually after migration.
+Only these 6 allowlisted secrets are ever imported. Other credentials are skipped and reported.
 
 ## Conflict Handling
 
@@ -101,24 +84,18 @@ For skills, you can also use `--skill-conflict rename` to import conflicting ski
 
 ## Migration Report
 
-Every migration produces a report showing:
+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 executed migrations, the full report is saved to `~/.hermes/migration/openclaw/<timestamp>/`.
-
-## Post-Migration Notes
-
-- **Skills require a new session** — imported skills take effect after restarting your agent or starting a new chat.
-- **WhatsApp requires re-pairing** — WhatsApp uses QR-code pairing, not token-based auth. Run `hermes whatsapp` to pair.
-- **Archive cleanup** — after migration, you'll be offered to rename `~/.openclaw/` to `.openclaw.pre-migration/` to prevent state confusion. You can also run `hermes claw cleanup` later.
+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, then tries `~/.clawdbot` and `~/.moltbot`. If your OpenClaw is installed elsewhere, use `--source`:
+The migration looks for `~/.openclaw` by default. If your OpenClaw is installed elsewhere, use `--source`:
 ```bash
 hermes claw migrate --source /path/to/.openclaw
 ```
@@ -131,12 +108,3 @@ 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.
-
-### API keys not found
-Keys might be stored in different places depending on your OpenClaw setup:
-- `~/.openclaw/.env` file
-- Inline in `openclaw.json` under `models.providers.*.apiKey`
-- In `openclaw.json` under the `"env"` or `"env.vars"` sub-objects
-- In `~/.openclaw/agents/main/agent/auth-profiles.json`
-
-The migration checks all four. If keys use `source: "file"` or `source: "exec"` SecretRefs, they can't be resolved automatically — add them via `hermes config set`.

docs/skins/example-skin.yaml

@@ -41,14 +41,6 @@ colors:
   session_label: "#DAA520"        # Session label
   session_border: "#8B8682"       # Session ID dim color
 
-  # TUI surfaces
-  status_bar_bg: "#1a1a2e"              # Status / usage bar background
-  voice_status_bg: "#1a1a2e"            # Voice-mode badge background
-  completion_menu_bg: "#1a1a2e"         # Completion list background
-  completion_menu_current_bg: "#333355" # Active completion row background
-  completion_menu_meta_bg: "#1a1a2e"    # Completion meta column background
-  completion_menu_meta_current_bg: "#333355"  # Active completion meta background
-
 # ── Spinner ─────────────────────────────────────────────────────────────────
 # Customize the animated spinner shown during API calls and tool execution.
 spinner:

docs/specs/container-cli-review-fixes.md

@@ -1,329 +0,0 @@
-# Container-Aware CLI Review Fixes Spec
-
-**PR:** NousResearch/hermes-agent#7543
-**Review:** cursor[bot] bugbot review (4094049442) + two prior rounds
-**Date:** 2026-04-12
-**Branch:** `feat/container-aware-cli-clean`
-
-## Review Issues Summary
-
-Six issues were raised across three bugbot review rounds. Three were fixed in intermediate commits (38277a6a, 726cf90f). This spec addresses remaining design concerns surfaced by those reviews and simplifies the implementation based on interview decisions.
-
-| # | Issue | Severity | Status |
-|---|-------|----------|--------|
-| 1 | `os.execvp` retry loop unreachable | Medium | Fixed in 79e8cd12 (switched to subprocess.run) |
-| 2 | Redundant `shutil.which("sudo")` | Medium | Fixed in 38277a6a (reuses `sudo` var) |
-| 3 | Missing `chown -h` on symlink update | Low | Fixed in 38277a6a |
-| 4 | Container routing after `parse_args()` | High | Fixed in 726cf90f |
-| 5 | Hardcoded `/home/${user}` | Medium | Fixed in 726cf90f |
-| 6 | Group membership not gated on `container.enable` | Low | Fixed in 726cf90f |
-
-The mechanical fixes are in place but the overall design needs revision. The retry loop, error swallowing, and process model have deeper issues than what the bugbot flagged.
-
----
-
-## Spec: Revised `_exec_in_container`
-
-### Design Principles
-
-1. **Let it crash.** No silent fallbacks. If `.container-mode` exists but something goes wrong, the error propagates naturally (Python traceback). The only case where container routing is skipped is when `.container-mode` doesn't exist or `HERMES_DEV=1`.
-2. **No retries.** Probe once for sudo, exec once. If it fails, docker/podman's stderr reaches the user verbatim.
-3. **Completely transparent.** No error wrapping, no prefixes, no spinners. Docker's output goes straight through.
-4. **`os.execvp` on the happy path.** Replace the Python process entirely so there's no idle parent during interactive sessions. Note: `execvp` never returns on success (process is replaced) and raises `OSError` on failure (it does not return a value). The container process's exit code becomes the process exit code by definition — no explicit propagation needed.
-5. **One human-readable exception to "let it crash".** `subprocess.TimeoutExpired` from the sudo probe gets a specific catch with a readable message, since a raw traceback for "your Docker daemon is slow" is confusing. All other exceptions propagate naturally.
-
-### Execution Flow
-
-```
-1. get_container_exec_info()
-   - HERMES_DEV=1 → return None (skip routing)
-   - Inside container → return None (skip routing)
-   - .container-mode doesn't exist → return None (skip routing)
-   - .container-mode exists → parse and return dict
-   - .container-mode exists but malformed/unreadable → LET IT CRASH (no try/except)
-
-2. _exec_in_container(container_info, sys.argv[1:])
-   a. shutil.which(backend) → if None, print "{backend} not found on PATH" and sys.exit(1)
-   b. Sudo probe: subprocess.run([runtime, "inspect", "--format", "ok", container_name], timeout=15)
-      - If succeeds → needs_sudo = False
-      - If fails → try subprocess.run([sudo, "-n", runtime, "inspect", ...], timeout=15)
-        - If succeeds → needs_sudo = True
-        - If fails → print error with sudoers hint (including why -n is required) and sys.exit(1)
-      - If TimeoutExpired → catch specifically, print human-readable message about slow daemon
-   c. Build exec_cmd: [sudo? + runtime, "exec", tty_flags, "-u", exec_user, env_flags, container, hermes_bin, *cli_args]
-   d. os.execvp(exec_cmd[0], exec_cmd)
-      - On success: process is replaced — Python is gone, container exit code IS the process exit code
-      - On OSError: let it crash (natural traceback)
-```
-
-### Changes to `hermes_cli/main.py`
-
-#### `_exec_in_container` — rewrite
-
-Remove:
-- The entire retry loop (`max_retries`, `for attempt in range(...)`)
-- Spinner logic (`"Waiting for container..."`, dots)
-- Exit code classification (125/126/127 handling)
-- `subprocess.run` for the exec call (keep it only for the sudo probe)
-- Special TTY vs non-TTY retry counts
-- The `time` import (no longer needed)
-
-Change:
-- Use `os.execvp(exec_cmd[0], exec_cmd)` as the final call
-- Keep the `subprocess` import only for the sudo probe
-- Keep TTY detection for the `-it` vs `-i` flag
-- Keep env var forwarding (TERM, COLORTERM, LANG, LC_ALL)
-- Keep the sudo probe as-is (it's the one "smart" part)
-- Bump probe `timeout` from 5s to 15s — cold podman on a loaded machine needs headroom
-- Catch `subprocess.TimeoutExpired` specifically on both probe calls — print a readable message about the daemon being unresponsive instead of a raw traceback
-- Expand the sudoers hint error message to explain *why* `-n` (non-interactive) is required: a password prompt would hang the CLI or break piped commands
-
-The function becomes roughly:
-
-```python
-def _exec_in_container(container_info: dict, cli_args: list):
-    """Replace the current process with a command inside the managed container.
-
-    Probes whether sudo is needed (rootful containers), then os.execvp
-    into the container. If exec fails, the OS error propagates naturally.
-    """
-    import shutil
-    import subprocess
-
-    backend = container_info["backend"]
-    container_name = container_info["container_name"]
-    exec_user = container_info["exec_user"]
-    hermes_bin = container_info["hermes_bin"]
-
-    runtime = shutil.which(backend)
-    if not runtime:
-        print(f"Error: {backend} not found on PATH. Cannot route to container.",
-              file=sys.stderr)
-        sys.exit(1)
-
-    # Probe whether we need sudo to see the rootful container.
-    # Timeout is 15s — cold podman on a loaded machine can take a while.
-    # TimeoutExpired is caught specifically for a human-readable message;
-    # all other exceptions propagate naturally.
-    needs_sudo = False
-    sudo = None
-    try:
-        probe = subprocess.run(
-            [runtime, "inspect", "--format", "ok", container_name],
-            capture_output=True, text=True, timeout=15,
-        )
-    except subprocess.TimeoutExpired:
-        print(
-            f"Error: timed out waiting for {backend} to respond.\n"
-            f"The {backend} daemon may be unresponsive or starting up.",
-            file=sys.stderr,
-        )
-        sys.exit(1)
-
-    if probe.returncode != 0:
-        sudo = shutil.which("sudo")
-        if sudo:
-            try:
-                probe2 = subprocess.run(
-                    [sudo, "-n", runtime, "inspect", "--format", "ok", container_name],
-                    capture_output=True, text=True, timeout=15,
-                )
-            except subprocess.TimeoutExpired:
-                print(
-                    f"Error: timed out waiting for sudo {backend} to respond.",
-                    file=sys.stderr,
-                )
-                sys.exit(1)
-
-            if probe2.returncode == 0:
-                needs_sudo = True
-            else:
-                print(
-                    f"Error: container '{container_name}' not found via {backend}.\n"
-                    f"\n"
-                    f"The NixOS service runs the container as root. Your user cannot\n"
-                    f"see it because {backend} uses per-user namespaces.\n"
-                    f"\n"
-                    f"Fix: grant passwordless sudo for {backend}. The -n (non-interactive)\n"
-                    f"flag is required because the CLI calls sudo non-interactively —\n"
-                    f"a password prompt would hang or break piped commands:\n"
-                    f"\n"
-                    f'  security.sudo.extraRules = [{{\n'
-                    f'    users = [ "{os.getenv("USER", "your-user")}" ];\n'
-                    f'    commands = [{{ command = "{runtime}"; options = [ "NOPASSWD" ]; }}];\n'
-                    f'  }}];\n'
-                    f"\n"
-                    f"Or run: sudo hermes {' '.join(cli_args)}",
-                    file=sys.stderr,
-                )
-                sys.exit(1)
-        else:
-            print(
-                f"Error: container '{container_name}' not found via {backend}.\n"
-                f"The container may be running under root. Try: sudo hermes {' '.join(cli_args)}",
-                file=sys.stderr,
-            )
-            sys.exit(1)
-
-    is_tty = sys.stdin.isatty()
-    tty_flags = ["-it"] if is_tty else ["-i"]
-
-    env_flags = []
-    for var in ("TERM", "COLORTERM", "LANG", "LC_ALL"):
-        val = os.environ.get(var)
-        if val:
-            env_flags.extend(["-e", f"{var}={val}"])
-
-    cmd_prefix = [sudo, "-n", runtime] if needs_sudo else [runtime]
-    exec_cmd = (
-        cmd_prefix + ["exec"]
-        + tty_flags
-        + ["-u", exec_user]
-        + env_flags
-        + [container_name, hermes_bin]
-        + cli_args
-    )
-
-    # execvp replaces this process entirely — it never returns on success.
-    # On failure it raises OSError, which propagates naturally.
-    os.execvp(exec_cmd[0], exec_cmd)
-```
-
-#### Container routing call site in `main()` — remove try/except
-
-Current:
-```python
-try:
-    from hermes_cli.config import get_container_exec_info
-    container_info = get_container_exec_info()
-    if container_info:
-        _exec_in_container(container_info, sys.argv[1:])
-        sys.exit(1)  # exec failed if we reach here
-except SystemExit:
-    raise
-except Exception:
-    pass  # Container routing unavailable, proceed locally
-```
-
-Revised:
-```python
-from hermes_cli.config import get_container_exec_info
-container_info = get_container_exec_info()
-if container_info:
-    _exec_in_container(container_info, sys.argv[1:])
-    # Unreachable: os.execvp never returns on success (process is replaced)
-    # and raises OSError on failure (which propagates as a traceback).
-    # This line exists only as a defensive assertion.
-    sys.exit(1)
-```
-
-No try/except. If `.container-mode` doesn't exist, `get_container_exec_info()` returns `None` and we skip routing. If it exists but is broken, the exception propagates with a natural traceback.
-
-Note: `sys.exit(1)` after `_exec_in_container` is dead code in all paths — `os.execvp` either replaces the process or raises. It's kept as a belt-and-suspenders assertion with a comment marking it unreachable, not as actual error handling.
-
-### Changes to `hermes_cli/config.py`
-
-#### `get_container_exec_info` — remove inner try/except
-
-Current code catches `(OSError, IOError)` and returns `None`. This silently hides permission errors, corrupt files, etc.
-
-Change: Remove the try/except around file reading. Keep the early returns for `HERMES_DEV=1` and `_is_inside_container()`. The `FileNotFoundError` from `open()` when `.container-mode` doesn't exist should still return `None` (this is the "container mode not enabled" case). All other exceptions propagate.
-
-```python
-def get_container_exec_info() -> Optional[dict]:
-    if os.environ.get("HERMES_DEV") == "1":
-        return None
-    if _is_inside_container():
-        return None
-
-    container_mode_file = get_hermes_home() / ".container-mode"
-
-    try:
-        with open(container_mode_file, "r") as f:
-            # ... parse key=value lines ...
-    except FileNotFoundError:
-        return None
-    # All other exceptions (PermissionError, malformed data, etc.) propagate
-
-    return { ... }
-```
-
----
-
-## Spec: NixOS Module Changes
-
-### Symlink creation — simplify to two branches
-
-Current: 4 branches (symlink exists, directory exists, other file, doesn't exist).
-
-Revised: 2 branches.
-
-```bash
-if [ -d "${symlinkPath}" ] && [ ! -L "${symlinkPath}" ]; then
-  # Real directory — back it up, then create symlink
-  _backup="${symlinkPath}.bak.$(date +%s)"
-  echo "hermes-agent: backing up existing ${symlinkPath} to $_backup"
-  mv "${symlinkPath}" "$_backup"
-fi
-# For everything else (symlink, doesn't exist, etc.) — just force-create
-ln -sfn "${target}" "${symlinkPath}"
-chown -h ${user}:${cfg.group} "${symlinkPath}"
-```
-
-`ln -sfn` handles: existing symlink (replaces), doesn't exist (creates), and after the `mv` above (creates). The only case that needs special handling is a real directory, because `ln -sfn` cannot atomically replace a directory.
-
-Note: there is a theoretical race between the `[ -d ... ]` check and the `mv` (something could create/remove the directory in between). In practice this is a NixOS activation script running as root during `nixos-rebuild switch` — no other process should be touching `~/.hermes` at that moment. Not worth adding locking for.
-
-### Sudoers — document, don't auto-configure
-
-Do NOT add `security.sudo.extraRules` to the module. Document the sudoers requirement in the module's description/comments and in the error message the CLI prints when sudo probe fails.
-
-### Group membership gating — keep as-is
-
-The fix in 726cf90f (`cfg.container.enable && cfg.container.hostUsers != []`) is correct. Leftover group membership when container mode is disabled is harmless. No cleanup needed.
-
----
-
-## Spec: Test Rewrite
-
-The existing test file (`tests/hermes_cli/test_container_aware_cli.py`) has 16 tests. With the simplified exec model, several are obsolete.
-
-### Tests to keep (update as needed)
-
-- `test_is_inside_container_dockerenv` — unchanged
-- `test_is_inside_container_containerenv` — unchanged
-- `test_is_inside_container_cgroup_docker` — unchanged
-- `test_is_inside_container_false_on_host` — unchanged
-- `test_get_container_exec_info_returns_metadata` — unchanged
-- `test_get_container_exec_info_none_inside_container` — unchanged
-- `test_get_container_exec_info_none_without_file` — unchanged
-- `test_get_container_exec_info_skipped_when_hermes_dev` — unchanged
-- `test_get_container_exec_info_not_skipped_when_hermes_dev_zero` — unchanged
-- `test_get_container_exec_info_defaults` — unchanged
-- `test_get_container_exec_info_docker_backend` — unchanged
-
-### Tests to add
-
-- `test_get_container_exec_info_crashes_on_permission_error` — verify that `PermissionError` propagates (no silent `None` return)
-- `test_exec_in_container_calls_execvp` — verify `os.execvp` is called with correct args (runtime, tty flags, user, env, container, binary, cli args)
-- `test_exec_in_container_sudo_probe_sets_prefix` — verify that when first probe fails and sudo probe succeeds, `os.execvp` is called with `sudo -n` prefix
-- `test_exec_in_container_no_runtime_hard_fails` — keep existing, verify `sys.exit(1)` when `shutil.which` returns None
-- `test_exec_in_container_non_tty_uses_i_only` — update to check `os.execvp` args instead of `subprocess.run` args
-- `test_exec_in_container_probe_timeout_prints_message` — verify that `subprocess.TimeoutExpired` from the probe produces a human-readable error and `sys.exit(1)`, not a raw traceback
-- `test_exec_in_container_container_not_running_no_sudo` — verify the path where runtime exists (`shutil.which` returns a path) but probe returns non-zero and no sudo is available. Should print the "container may be running under root" error. This is distinct from `no_runtime_hard_fails` which covers `shutil.which` returning None.
-
-### Tests to delete
-
-- `test_exec_in_container_tty_retries_on_container_failure` — retry loop removed
-- `test_exec_in_container_non_tty_retries_silently_exits_126` — retry loop removed
-- `test_exec_in_container_propagates_hermes_exit_code` — no subprocess.run to check exit codes; execvp replaces the process. Note: exit code propagation still works correctly — when `os.execvp` succeeds, the container's process *becomes* this process, so its exit code is the process exit code by OS semantics. No application code needed, no test needed. A comment in the function docstring documents this intent for future readers.
-
----
-
-## Out of Scope
-
-- Auto-configuring sudoers rules in the NixOS module
-- Any changes to `get_container_exec_info` parsing logic beyond the try/except narrowing
-- Changes to `.container-mode` file format
-- Changes to the `HERMES_DEV=1` bypass
-- Changes to container detection logic (`_is_inside_container`)

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

@@ -22,16 +22,16 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1775036866,
-        "narHash": "sha256-ZojAnPuCdy657PbTq5V0Y+AHKhZAIwSIT2cb8UgAz/U=",
+        "lastModified": 1751274312,
+        "narHash": "sha256-/bVBlRpECLVzjV19t5KMdMFWSwKLtb5RyXdjz3LJT+g=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "6201e203d09599479a3b3450ed24fa81537ebc4e",
+        "rev": "50ab793786d9de88ee30ec4e4c24fb4236fc2674",
         "type": "github"
       },
       "original": {
         "owner": "NixOS",
-        "ref": "nixos-unstable",
+        "ref": "nixos-24.11",
         "repo": "nixpkgs",
         "type": "github"
       }

flake.nix

@@ -2,7 +2,7 @@
   description = "Hermes Agent - AI agent framework by Nous Research";
 
   inputs = {
-    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
+    nixpkgs.url = "github:NixOS/nixpkgs/nixos-24.11";
     flake-parts = {
       url = "github:hercules-ci/flake-parts";
       inputs.nixpkgs-lib.follows = "nixpkgs";

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(),

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", " ▉"),
         )
@@ -264,11 +261,6 @@ class GatewayConfig:
         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)
@@ -293,20 +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)
         return connected
     
     def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -548,18 +532,8 @@ def load_gateway_config() -> GatewayConfig:
                     bridged["reply_prefix"] = platform_cfg["reply_prefix"]
                 if "require_mention" in platform_cfg:
                     bridged["require_mention"] = platform_cfg["require_mention"]
-                if "free_response_channels" in platform_cfg:
-                    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, {})
@@ -572,19 +546,6 @@ def load_gateway_config() -> GatewayConfig:
                     plat_data["extra"] = extra
                 extra.update(bridged)
 
-            # Slack settings → env vars (env vars take precedence)
-            slack_cfg = yaml_cfg.get("slack", {})
-            if isinstance(slack_cfg, dict):
-                if "require_mention" in slack_cfg and not os.getenv("SLACK_REQUIRE_MENTION"):
-                    os.environ["SLACK_REQUIRE_MENTION"] = str(slack_cfg["require_mention"]).lower()
-                if "allow_bots" in slack_cfg and not os.getenv("SLACK_ALLOW_BOTS"):
-                    os.environ["SLACK_ALLOW_BOTS"] = str(slack_cfg["allow_bots"]).lower()
-                frc = slack_cfg.get("free_response_channels")
-                if frc is not None and not os.getenv("SLACK_FREE_RESPONSE_CHANNELS"):
-                    if isinstance(frc, list):
-                        frc = ",".join(str(v) for v in frc)
-                    os.environ["SLACK_FREE_RESPONSE_CHANNELS"] = str(frc)
-
             # Discord settings → env vars (env vars take precedence)
             discord_cfg = yaml_cfg.get("discord", {})
             if isinstance(discord_cfg, dict):
@@ -605,12 +566,6 @@ 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"):
@@ -631,25 +586,8 @@ 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):
@@ -675,8 +613,6 @@ 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(
@@ -692,17 +628,6 @@ 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):
@@ -726,7 +651,6 @@ 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:
@@ -739,31 +663,7 @@ 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:
@@ -986,9 +886,6 @@ 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")
@@ -1055,64 +952,6 @@ 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")
@@ -1136,32 +975,6 @@ 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("QQ_HOME_CHANNEL", "").strip()
-        if qq_home:
-            config.platforms[Platform.QQBOT].home_channel = HomeChannel(
-                platform=Platform.QQBOT,
-                chat_id=qq_home,
-                name=os.getenv("QQ_HOME_CHANNEL_NAME", "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
 
@@ -124,6 +124,53 @@ class DeliveryRouter:
         self.adapters = adapters or {}
         self.output_dir = get_hermes_home() / "cron" / "output"
     
+    def resolve_targets(
+        self,
+        deliver: Union[str, List[str]],
+        origin: Optional[SessionSource] = None
+    ) -> List[DeliveryTarget]:
+        """
+        Resolve delivery specification to concrete targets.
+        
+        Args:
+            deliver: Delivery spec - "origin", "telegram", ["local", "discord"], etc.
+            origin: The source where the request originated (for "origin" target)
+        
+        Returns:
+            List of resolved delivery targets
+        """
+        if isinstance(deliver, str):
+            deliver = [deliver]
+        
+        targets = []
+        seen_platforms = set()
+        
+        for target_str in deliver:
+            target = DeliveryTarget.parse(target_str, origin)
+            
+            # Resolve home channel if needed
+            if target.chat_id is None and target.platform != Platform.LOCAL:
+                home = self.config.get_home_channel(target.platform)
+                if home:
+                    target.chat_id = home.chat_id
+                else:
+                    # No home channel configured, skip this platform
+                    continue
+            
+            # Deduplicate
+            key = (target.platform, target.chat_id, target.thread_id)
+            if key not in seen_platforms:
+                seen_platforms.add(key)
+                targets.append(target)
+        
+        # Always include local if configured
+        if self.config.always_log_local:
+            local_key = (Platform.LOCAL, None, None)
+            if local_key not in seen_platforms:
+                targets.append(DeliveryTarget(platform=Platform.LOCAL))
+        
+        return targets
+    
     async def deliver(
         self,
         content: str,
@@ -252,5 +299,19 @@ class DeliveryRouter:
         return await adapter.send(target.chat_id, content, metadata=send_metadata or None)
 
 
+def parse_deliver_spec(
+    deliver: Optional[Union[str, List[str]]],
+    origin: Optional[SessionSource] = None,
+    default: str = "origin"
+) -> Union[str, List[str]]:
+    """
+    Normalize a delivery specification.
+    
+    If None or empty, returns the default.
+    """
+    if not deliver:
+        return default
+    return deliver
+
 
 

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

@@ -6,236 +6,22 @@ and implement the required methods.
 """
 
 import asyncio
-import ipaddress
 import logging
 import os
 import random
 import re
-import socket as _socket
-import subprocess
-import sys
 import uuid
 from abc import ABC, abstractmethod
 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``.
-
-    Returns an ``http://host:port`` URL string if an HTTP or HTTPS proxy is
-    enabled, otherwise *None*.  Falls back silently on non-macOS or on any
-    subprocess error.
-    """
-    if sys.platform != "darwin":
-        return None
-    try:
-        out = subprocess.check_output(
-            ["scutil", "--proxy"], timeout=3, text=True, stderr=subprocess.DEVNULL,
-        )
-    except Exception:
-        return None
-
-    props: dict[str, str] = {}
-    for line in out.splitlines():
-        line = line.strip()
-        if " : " in line:
-            key, _, val = line.partition(" : ")
-            props[key.strip()] = val.strip()
-
-    # Prefer HTTPS, fall back to HTTP
-    for enable_key, host_key, port_key in (
-        ("HTTPSEnable", "HTTPSProxy", "HTTPSPort"),
-        ("HTTPEnable", "HTTPProxy", "HTTPPort"),
-    ):
-        if props.get(enable_key) == "1":
-            host = props.get(host_key)
-            port = props.get(port_key)
-            if host and port:
-                return f"http://{host}:{port}"
-    return None
-
-
-def resolve_proxy_url(platform_env_var: str | None = None) -> str | None:
-    """Return a proxy URL from env vars, or macOS system proxy.
-
-    Check order:
-      0. *platform_env_var* (e.g. ``DISCORD_PROXY``) — highest priority
-      1. HTTPS_PROXY / HTTP_PROXY / ALL_PROXY (and lowercase variants)
-      2. macOS system proxy via ``scutil --proxy`` (auto-detect)
-
-    Returns *None* if no proxy is found.
-    """
-    if platform_env_var:
-        value = (os.environ.get(platform_env_var) or "").strip()
-        if value:
-            return value
-    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY",
-                "https_proxy", "http_proxy", "all_proxy"):
-        value = (os.environ.get(key) or "").strip()
-        if value:
-            return value
-    return _detect_macos_system_proxy()
-
-
-def proxy_kwargs_for_bot(proxy_url: str | None) -> dict:
-    """Build kwargs for ``commands.Bot()`` / ``discord.Client()`` with proxy.
-
-    Returns:
-      - SOCKS URL  → ``{"connector": ProxyConnector(..., rdns=True)}``
-      - HTTP URL   → ``{"proxy": url}``
-      - *None*     → ``{}``
-
-    ``rdns=True`` forces remote DNS resolution through the proxy — required
-    by many SOCKS implementations (Shadowrocket, Clash) and essential for
-    bypassing DNS pollution behind the GFW.
-    """
-    if not proxy_url:
-        return {}
-    if proxy_url.lower().startswith("socks"):
-        try:
-            from aiohttp_socks import ProxyConnector
-
-            connector = ProxyConnector.from_url(proxy_url, rdns=True)
-            return {"connector": connector}
-        except ImportError:
-            logger.warning(
-                "aiohttp_socks not installed — SOCKS proxy %s ignored. "
-                "Run: pip install aiohttp-socks",
-                proxy_url,
-            )
-            return {}
-    return {"proxy": proxy_url}
-
-
-def proxy_kwargs_for_aiohttp(proxy_url: str | None) -> tuple[dict, dict]:
-    """Build kwargs for standalone ``aiohttp.ClientSession`` with proxy.
-
-    Returns ``(session_kwargs, request_kwargs)`` where:
-      - SOCKS → ``({"connector": ProxyConnector(...)}, {})``
-      - HTTP  → ``({}, {"proxy": url})``
-      - None  → ``({}, {})``
-
-    Usage::
-
-        sess_kw, req_kw = proxy_kwargs_for_aiohttp(proxy_url)
-        async with aiohttp.ClientSession(**sess_kw) as session:
-            async with session.get(url, **req_kw) as resp:
-                ...
-    """
-    if not proxy_url:
-        return {}, {}
-    if proxy_url.lower().startswith("socks"):
-        try:
-            from aiohttp_socks import ProxyConnector
-
-            connector = ProxyConnector.from_url(proxy_url, rdns=True)
-            return {"connector": connector}, {}
-        except ImportError:
-            logger.warning(
-                "aiohttp_socks not installed — SOCKS proxy %s ignored. "
-                "Run: pip install aiohttp-socks",
-                proxy_url,
-            )
-            return {}, {}
-    return {}, {"proxy": proxy_url}
-
-
 from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 from typing import Dict, List, Optional, Any, Callable, Awaitable, Tuple
 from enum import Enum
 
+import sys
 from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
@@ -250,7 +36,7 @@ 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 ""
@@ -287,23 +73,6 @@ 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
 #
@@ -323,23 +92,6 @@ 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.
@@ -350,17 +102,7 @@ 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
@@ -388,7 +130,7 @@ 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
@@ -396,11 +138,7 @@ 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(
@@ -422,7 +160,7 @@ 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,
                     )
@@ -507,7 +245,7 @@ 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
@@ -515,11 +253,7 @@ 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(
@@ -541,7 +275,7 @@ 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,
                     )
@@ -644,14 +378,6 @@ 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:
     """
@@ -679,13 +405,8 @@ 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.
@@ -707,9 +428,6 @@ 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:
@@ -730,63 +448,6 @@ 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)
@@ -811,36 +472,6 @@ _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.
@@ -870,13 +501,6 @@ 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.  GatewayRunner uses this to defer
-        # background-review notifications ("💾 Skill created") until the
-        # primary reply has been sent.
-        self._post_delivery_callbacks: Dict[str, Callable] = {}
-        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).
@@ -946,36 +570,7 @@ 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."""
@@ -994,10 +589,6 @@ 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:
         """
@@ -1291,7 +882,7 @@ 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:
@@ -1418,7 +1009,7 @@ 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:
@@ -1579,7 +1170,7 @@ class BasePlatformAdapter(ABC):
             # session lifecycle and its cleanup races with the running task
             # (see PR #4926).
             cmd = event.get_command()
-            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background", "restart", "queue", "q"):
+            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,
@@ -1598,19 +1189,19 @@ 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
@@ -1637,7 +1228,6 @@ 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:
@@ -1694,21 +1284,6 @@ 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:
@@ -1789,7 +1364,7 @@ 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
@@ -1881,11 +1456,7 @@ 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:
@@ -1904,14 +1475,10 @@ 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:
@@ -1930,14 +1497,6 @@ 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).
-            _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:
@@ -1963,12 +1522,10 @@ class BasePlatformAdapter(ABC):
         """
         tasks = [task for task in self._background_tasks if not task.done()]
         for task in tasks:
-            self._expected_cancelled_tasks.add(task)
             task.cancel()
         if tasks:
             await asyncio.gather(*tasks, return_exceptions=True)
         self._background_tasks.clear()
-        self._expected_cancelled_tasks.clear()
         self._pending_messages.clear()
         self._active_sessions.clear()
 
@@ -2032,11 +1589,7 @@ 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.
 
@@ -2048,16 +1601,11 @@ 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)"
@@ -2076,33 +1624,22 @@ 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
@@ -2122,7 +1659,7 @@ 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/dingtalk.py

@@ -20,7 +20,7 @@ Configuration in config.yaml:
 import asyncio
 import logging
 import os
-import re
+import time
 import uuid
 from datetime import datetime, timezone
 from typing import Any, Dict, Optional
@@ -41,7 +41,6 @@ except ImportError:
     httpx = None  # type: ignore[assignment]
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -52,9 +51,9 @@ from gateway.platforms.base import (
 logger = logging.getLogger(__name__)
 
 MAX_MESSAGE_LENGTH = 20000
+DEDUP_WINDOW_SECONDS = 300
+DEDUP_MAX_SIZE = 1000
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
-_SESSION_WEBHOOKS_MAX = 500
-_DINGTALK_WEBHOOK_RE = re.compile(r'^https://(?:api|oapi)\.dingtalk\.com/')
 
 
 def check_dingtalk_requirements() -> bool:
@@ -87,8 +86,8 @@ class DingTalkAdapter(BasePlatformAdapter):
         self._stream_task: Optional[asyncio.Task] = None
         self._http_client: Optional["httpx.AsyncClient"] = None
 
-        # Message deduplication
-        self._dedup = MessageDeduplicator(max_size=1000)
+        # Message deduplication: msg_id -> timestamp
+        self._seen_messages: Dict[str, float] = {}
         # Map chat_id -> session_webhook for reply routing
         self._session_webhooks: Dict[str, str] = {}
 
@@ -128,12 +127,12 @@ class DingTalkAdapter(BasePlatformAdapter):
             return False
 
     async def _run_stream(self) -> None:
-        """Run the stream client with auto-reconnection."""
+        """Run the blocking stream client with auto-reconnection."""
         backoff_idx = 0
         while self._running:
             try:
                 logger.debug("[%s] Starting stream client...", self.name)
-                await self._stream_client.start()
+                await asyncio.to_thread(self._stream_client.start)
             except asyncio.CancelledError:
                 return
             except Exception as e:
@@ -168,7 +167,7 @@ class DingTalkAdapter(BasePlatformAdapter):
 
         self._stream_client = None
         self._session_webhooks.clear()
-        self._dedup.clear()
+        self._seen_messages.clear()
         logger.info("[%s] Disconnected", self.name)
 
     # -- Inbound message processing -----------------------------------------
@@ -176,7 +175,7 @@ class DingTalkAdapter(BasePlatformAdapter):
     async def _on_message(self, message: "ChatbotMessage") -> None:
         """Process an incoming DingTalk chatbot message."""
         msg_id = getattr(message, "message_id", None) or uuid.uuid4().hex
-        if self._dedup.is_duplicate(msg_id):
+        if self._is_duplicate(msg_id):
             logger.debug("[%s] Duplicate message %s, skipping", self.name, msg_id)
             return
 
@@ -196,15 +195,9 @@ class DingTalkAdapter(BasePlatformAdapter):
         chat_id = conversation_id or sender_id
         chat_type = "group" if is_group else "dm"
 
-        # Store session webhook for reply routing (validate origin to prevent SSRF)
+        # Store session webhook for reply routing
         session_webhook = getattr(message, "session_webhook", None) or ""
-        if session_webhook and chat_id and _DINGTALK_WEBHOOK_RE.match(session_webhook):
-            if len(self._session_webhooks) >= _SESSION_WEBHOOKS_MAX:
-                # Evict oldest entry to cap memory growth
-                try:
-                    self._session_webhooks.pop(next(iter(self._session_webhooks)))
-                except StopIteration:
-                    pass
+        if session_webhook and chat_id:
             self._session_webhooks[chat_id] = session_webhook
 
         source = self.build_source(
@@ -238,39 +231,36 @@ class DingTalkAdapter(BasePlatformAdapter):
 
     @staticmethod
     def _extract_text(message: "ChatbotMessage") -> str:
-        """Extract plain text from a DingTalk chatbot message.
-
-        Handles both legacy and current dingtalk-stream SDK payload shapes:
-          * legacy: ``message.text`` was a dict ``{"content": "..."}``
-          * >= 0.20: ``message.text`` is a ``TextContent`` dataclass whose
-            ``__str__`` returns ``"TextContent(content=...)"`` — never fall
-            back to ``str(text)`` without extracting ``.content`` first.
-          * rich text moved from ``message.rich_text`` (list) to
-            ``message.rich_text_content.rich_text_list`` (list of dicts).
-        """
-        text = getattr(message, "text", None)
-        content = ""
-        if text is not None:
-            if isinstance(text, dict):
-                content = (text.get("content") or "").strip()
-            elif hasattr(text, "content"):
-                content = str(text.content or "").strip()
-            else:
-                content = str(text).strip()
+        """Extract plain text from a DingTalk chatbot message."""
+        text = getattr(message, "text", None) or ""
+        if isinstance(text, dict):
+            content = text.get("content", "").strip()
+        else:
+            content = str(text).strip()
 
+        # Fall back to rich text if present
         if not content:
-            rich_list = None
-            rtc = getattr(message, "rich_text_content", None)
-            if rtc is not None and hasattr(rtc, "rich_text_list"):
-                rich_list = rtc.rich_text_list
-            if rich_list is None:
-                rich_list = getattr(message, "rich_text", None)
-            if rich_list and isinstance(rich_list, list):
-                parts = [item["text"] for item in rich_list
+            rich_text = getattr(message, "rich_text", None)
+            if rich_text and isinstance(rich_text, list):
+                parts = [item["text"] for item in rich_text
                          if isinstance(item, dict) and item.get("text")]
                 content = " ".join(parts).strip()
         return content
 
+    # -- Deduplication ------------------------------------------------------
+
+    def _is_duplicate(self, msg_id: str) -> bool:
+        """Check and record a message ID. Returns True if already seen."""
+        now = time.time()
+        if len(self._seen_messages) > DEDUP_MAX_SIZE:
+            cutoff = now - DEDUP_WINDOW_SECONDS
+            self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
+
+        if msg_id in self._seen_messages:
+            return True
+        self._seen_messages[msg_id] = now
+        return False
+
     # -- Outbound messaging -------------------------------------------------
 
     async def send(
@@ -331,16 +321,19 @@ class _IncomingHandler(ChatbotHandler if DINGTALK_STREAM_AVAILABLE else object):
         self._adapter = adapter
         self._loop = loop
 
-    async def process(self, callback_message):
-        """Called by dingtalk-stream when a message arrives.
+    def process(self, message: "ChatbotMessage"):
+        """Called by dingtalk-stream in its thread when a message arrives.
 
-        dingtalk-stream >= 0.24 passes a CallbackMessage whose `.data` contains
-        the chatbot payload. Convert it to ChatbotMessage and await the adapter
-        handler directly on the main event loop.
+        Schedules the async handler on the main event loop.
         """
+        loop = self._loop
+        if loop is None or loop.is_closed():
+            logger.error("[DingTalk] Event loop unavailable, cannot dispatch message")
+            return dingtalk_stream.AckMessage.STATUS_OK, "OK"
+
+        future = asyncio.run_coroutine_threadsafe(self._adapter._on_message(message), loop)
         try:
-            chatbot_msg = ChatbotMessage.from_dict(callback_message.data)
-            await self._adapter._on_message(chatbot_msg)
+            future.result(timeout=60)
         except Exception:
             logger.exception("[DingTalk] Error processing incoming message")
 

gateway/platforms/discord.py

@@ -10,6 +10,7 @@ Uses discord.py library for:
 """
 
 import asyncio
+import json
 import logging
 import os
 import struct
@@ -18,6 +19,7 @@ import tempfile
 import threading
 import time
 from collections import defaultdict
+from pathlib import Path
 from typing import Callable, Dict, Optional, Any
 
 logger = logging.getLogger(__name__)
@@ -43,12 +45,10 @@ sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 from gateway.config import Platform, PlatformConfig
 import re
 
-from gateway.platforms.helpers import MessageDeduplicator, ThreadParticipationTracker
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
-    ProcessingOutcome,
     SendResult,
     cache_image_from_url,
     cache_audio_from_url,
@@ -235,7 +235,6 @@ class VoiceReceiver:
         # Calculate dynamic RTP header size (RFC 9335 / rtpsize mode)
         cc = first_byte & 0x0F  # CSRC count
         has_extension = bool(first_byte & 0x10)  # extension bit
-        has_padding = bool(first_byte & 0x20)  # padding bit (RFC 3550 §5.1)
         header_size = 12 + (4 * cc) + (4 if has_extension else 0)
 
         if len(data) < header_size + 4:  # need at least header + nonce
@@ -279,31 +278,6 @@ class VoiceReceiver:
         if ext_data_len and len(decrypted) > ext_data_len:
             decrypted = decrypted[ext_data_len:]
 
-        # --- Strip RTP padding (RFC 3550 §5.1) ---
-        # When the P bit is set, the last payload byte holds the count of
-        # trailing padding bytes (including itself) that must be removed
-        # before further processing. Skipping this passes padding-contaminated
-        # bytes into DAVE/Opus and corrupts inbound audio.
-        if has_padding:
-            if not decrypted:
-                if self._packet_debug_count <= 10:
-                    logger.warning(
-                        "RTP padding bit set but no payload (ssrc=%d)", ssrc,
-                    )
-                return
-            pad_len = decrypted[-1]
-            if pad_len == 0 or pad_len > len(decrypted):
-                if self._packet_debug_count <= 10:
-                    logger.warning(
-                        "Invalid RTP padding length %d for payload size %d (ssrc=%d)",
-                        pad_len, len(decrypted), ssrc,
-                    )
-                return
-            decrypted = decrypted[:-pad_len]
-            if not decrypted:
-                # Padding consumed entire payload — nothing to decode
-                return
-
         # --- DAVE E2EE decrypt ---
         if self._dave_session:
             with self._lock:
@@ -448,7 +422,6 @@ class DiscordAdapter(BasePlatformAdapter):
 
     # Discord message limits
     MAX_MESSAGE_LENGTH = 2000
-    _SPLIT_THRESHOLD = 1900  # near the 2000-char split point
 
     # Auto-disconnect from voice channel after this many seconds of inactivity
     VOICE_TIMEOUT = 300
@@ -460,13 +433,7 @@ class DiscordAdapter(BasePlatformAdapter):
         self._allowed_user_ids: set = set()  # For button approval authorization
         # Voice channel state (per-guild)
         self._voice_clients: Dict[int, Any] = {}  # guild_id -> VoiceClient
-        # Text batching: merge rapid successive messages (Telegram-style)
-        self._text_batch_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
-        self._pending_text_batches: Dict[str, MessageEvent] = {}
-        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
         self._voice_text_channels: Dict[int, int] = {}  # guild_id -> text_channel_id
-        self._voice_sources: Dict[int, Dict[str, Any]] = {}  # guild_id -> linked text channel source metadata
         self._voice_timeout_tasks: Dict[int, asyncio.Task] = {}  # guild_id -> timeout task
         # Phase 2: voice listening
         self._voice_receivers: Dict[int, VoiceReceiver] = {}  # guild_id -> VoiceReceiver
@@ -476,15 +443,18 @@ class DiscordAdapter(BasePlatformAdapter):
         # Track threads where the bot has participated so follow-up messages
         # in those threads don't require @mention.  Persisted to disk so the
         # set survives gateway restarts.
-        self._threads = ThreadParticipationTracker("discord")
+        self._bot_participated_threads: set = self._load_participated_threads()
         # Persistent typing indicator loops per channel (DMs don't reliably
         # show the standard typing gateway event for bots)
         self._typing_tasks: Dict[str, asyncio.Task] = {}
         self._bot_task: Optional[asyncio.Task] = None
-        self._post_connect_task: Optional[asyncio.Task] = None
-        # Dedup cache: prevents duplicate bot responses when Discord
-        # RESUME replays events after reconnects.
-        self._dedup = MessageDeduplicator()
+        # Cap to prevent unbounded growth (Discord threads get archived).
+        self._MAX_TRACKED_THREADS = 500
+        # Dedup cache: message_id → timestamp.  Prevents duplicate bot
+        # responses when Discord RESUME replays events after reconnects.
+        self._seen_messages: Dict[str, float] = {}
+        self._SEEN_TTL = 300   # 5 minutes
+        self._SEEN_MAX = 2000  # prune threshold
         # Reply threading mode: "off" (no replies), "first" (reply on first
         # chunk only, default), "all" (reply-reference on every chunk).
         self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
@@ -525,9 +495,18 @@ class DiscordAdapter(BasePlatformAdapter):
             return False
 
         try:
-            if not self._acquire_platform_lock('discord-bot-token', self.config.token, 'Discord bot token'):
+            # Acquire scoped lock to prevent duplicate bot token usage
+            from gateway.status import acquire_scoped_lock
+            self._token_lock_identity = self.config.token
+            acquired, existing = acquire_scoped_lock('discord-bot-token', self._token_lock_identity, metadata={'platform': 'discord'})
+            if not acquired:
+                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
+                message = f'Discord bot token 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('discord_token_lock', message, retryable=False)
                 return False
 
+
             # Parse allowed user entries (may contain usernames or IDs)
             allowed_env = os.getenv("DISCORD_ALLOWED_USERS", "")
             if allowed_env:
@@ -550,17 +529,10 @@ class DiscordAdapter(BasePlatformAdapter):
             intents.members = any(not entry.isdigit() for entry in self._allowed_user_ids)
             intents.voice_states = True
 
-            # Resolve proxy (DISCORD_PROXY > generic env vars > macOS system proxy)
-            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_bot
-            proxy_url = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
-            if proxy_url:
-                logger.info("[%s] Using proxy for Discord: %s", self.name, proxy_url)
-
-            # Create bot — proxy= for HTTP, connector= for SOCKS
+            # Create bot
             self._client = commands.Bot(
                 command_prefix="!",  # Not really used, we handle raw messages
                 intents=intents,
-                **proxy_kwargs_for_bot(proxy_url),
             )
             adapter_self = self  # capture for closure
 
@@ -571,19 +543,29 @@ class DiscordAdapter(BasePlatformAdapter):
 
                 # Resolve any usernames in the allowed list to numeric IDs
                 await adapter_self._resolve_allowed_usernames()
-                adapter_self._ready_event.set()
 
-                if adapter_self._post_connect_task and not adapter_self._post_connect_task.done():
-                    adapter_self._post_connect_task.cancel()
-                adapter_self._post_connect_task = asyncio.create_task(
-                    adapter_self._run_post_connect_initialization()
-                )
+                # Sync slash commands with Discord
+                try:
+                    synced = await adapter_self._client.tree.sync()
+                    logger.info("[%s] Synced %d slash command(s)", adapter_self.name, len(synced))
+                except Exception as e:  # pragma: no cover - defensive logging
+                    logger.warning("[%s] Slash command sync failed: %s", adapter_self.name, e, exc_info=True)
+                adapter_self._ready_event.set()
 
             @self._client.event
             async def on_message(message: DiscordMessage):
                 # Dedup: Discord RESUME replays events after reconnects (#4777)
-                if adapter_self._dedup.is_duplicate(str(message.id)):
+                msg_id = str(message.id)
+                now = time.time()
+                if msg_id in adapter_self._seen_messages:
                     return
+                adapter_self._seen_messages[msg_id] = now
+                if len(adapter_self._seen_messages) > adapter_self._SEEN_MAX:
+                    cutoff = now - adapter_self._SEEN_TTL
+                    adapter_self._seen_messages = {
+                        k: v for k, v in adapter_self._seen_messages.items()
+                        if v > cutoff
+                    }
 
                 # Always ignore our own messages
                 if message.author == self._client.user:
@@ -610,35 +592,22 @@ class DiscordAdapter(BasePlatformAdapter):
                         if not self._client.user or self._client.user not in message.mentions:
                             return
                     # "all" falls through to handle_message
-                
-                # Multi-agent filtering: if the message mentions specific bots
-                # but NOT this bot, the sender is talking to another agent —
-                # stay silent.  Messages with no bot mentions (general chat)
-                # still fall through to _handle_message for the existing
-                # DISCORD_REQUIRE_MENTION check.
-                #
-                # This replaces the older DISCORD_IGNORE_NO_MENTION logic
-                # with bot-aware filtering that works correctly when multiple
-                # agents share a channel.
-                if not isinstance(message.channel, discord.DMChannel) and message.mentions:
-                    _self_mentioned = (
+
+                # If the message @mentions other users but NOT the bot, the
+                # sender is talking to someone else — stay silent.  Only
+                # applies in server channels; in DMs the user is always
+                # talking to the bot (mentions are just references).
+                # Controlled by DISCORD_IGNORE_NO_MENTION (default: true).
+                _ignore_no_mention = os.getenv(
+                    "DISCORD_IGNORE_NO_MENTION", "true"
+                ).lower() in ("true", "1", "yes")
+                if _ignore_no_mention and message.mentions and not isinstance(message.channel, discord.DMChannel):
+                    _bot_mentioned = (
                         self._client.user is not None
                         and self._client.user in message.mentions
                     )
-                    _other_bots_mentioned = any(
-                        m.bot and m != self._client.user
-                        for m in message.mentions
-                    )
-                    # If other bots are mentioned but we're not → not for us
-                    if _other_bots_mentioned and not _self_mentioned:
-                        return
-                    # If humans are mentioned but we're not → not for us
-                    # (preserves old DISCORD_IGNORE_NO_MENTION=true behavior)
-                    _ignore_no_mention = os.getenv(
-                        "DISCORD_IGNORE_NO_MENTION", "true"
-                    ).lower() in ("true", "1", "yes")
-                    if _ignore_no_mention and not _self_mentioned and not _other_bots_mentioned:
-                        return
+                    if not _bot_mentioned:
+                        return  # Talking to someone else, don't interrupt
 
                 await self._handle_message(message)
 
@@ -689,11 +658,23 @@ class DiscordAdapter(BasePlatformAdapter):
 
         except asyncio.TimeoutError:
             logger.error("[%s] Timeout waiting for connection to Discord", self.name, exc_info=True)
-            self._release_platform_lock()
+            try:
+                from gateway.status import release_scoped_lock
+                if getattr(self, '_token_lock_identity', None):
+                    release_scoped_lock('discord-bot-token', self._token_lock_identity)
+                    self._token_lock_identity = None
+            except Exception:
+                pass
             return False
         except Exception as e:  # pragma: no cover - defensive logging
             logger.error("[%s] Failed to connect to Discord: %s", self.name, e, exc_info=True)
-            self._release_platform_lock()
+            try:
+                from gateway.status import release_scoped_lock
+                if getattr(self, '_token_lock_identity', None):
+                    release_scoped_lock('discord-bot-token', self._token_lock_identity)
+                    self._token_lock_identity = None
+            except Exception:
+                pass
             return False
 
     async def disconnect(self) -> None:
@@ -711,36 +692,21 @@ class DiscordAdapter(BasePlatformAdapter):
             except Exception as e:  # pragma: no cover - defensive logging
                 logger.warning("[%s] Error during disconnect: %s", self.name, e, exc_info=True)
 
-        if self._post_connect_task and not self._post_connect_task.done():
-            self._post_connect_task.cancel()
-            try:
-                await self._post_connect_task
-            except asyncio.CancelledError:
-                pass
-
         self._running = False
         self._client = None
         self._ready_event.clear()
-        self._post_connect_task = None
 
-        self._release_platform_lock()
+        # Release the token lock
+        try:
+            from gateway.status import release_scoped_lock
+            if getattr(self, '_token_lock_identity', None):
+                release_scoped_lock('discord-bot-token', self._token_lock_identity)
+                self._token_lock_identity = None
+        except Exception:
+            pass
 
         logger.info("[%s] Disconnected", self.name)
 
-    async def _run_post_connect_initialization(self) -> None:
-        """Finish non-critical startup work after Discord is connected."""
-        if not self._client:
-            return
-        try:
-            synced = await asyncio.wait_for(self._client.tree.sync(), timeout=30)
-            logger.info("[%s] Synced %d slash command(s)", self.name, len(synced))
-        except asyncio.TimeoutError:
-            logger.warning("[%s] Slash command sync timed out after 30s", self.name)
-        except asyncio.CancelledError:
-            raise
-        except Exception as e:  # pragma: no cover - defensive logging
-            logger.warning("[%s] Slash command sync failed: %s", self.name, e, exc_info=True)
-
     async def _add_reaction(self, message: Any, emoji: str) -> bool:
         """Add an emoji reaction to a Discord message."""
         if not message or not hasattr(message, "add_reaction"):
@@ -775,17 +741,14 @@ class DiscordAdapter(BasePlatformAdapter):
         if hasattr(message, "add_reaction"):
             await self._add_reaction(message, "👀")
 
-    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
+    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
         """Swap the in-progress reaction for a final success/failure reaction."""
         if not self._reactions_enabled():
             return
         message = event.raw_message
         if hasattr(message, "add_reaction"):
             await self._remove_reaction(message, "👀")
-            if outcome == ProcessingOutcome.SUCCESS:
-                await self._add_reaction(message, "✅")
-            elif outcome == ProcessingOutcome.FAILURE:
-                await self._add_reaction(message, "❌")
+            await self._add_reaction(message, "✅" if success else "❌")
 
     async def send(
         self,
@@ -794,34 +757,18 @@ class DiscordAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None
     ) -> SendResult:
-        """Send a message to a Discord channel or thread.
-
-        When metadata contains a thread_id, the message is sent to that
-        thread instead of the parent channel identified by chat_id.
-        """
+        """Send a message to a Discord channel."""
         if not self._client:
             return SendResult(success=False, error="Not connected")
 
         try:
-            # Determine target channel: thread_id in metadata takes precedence.
-            thread_id = None
-            if metadata and metadata.get("thread_id"):
-                thread_id = metadata["thread_id"]
+            # Get the channel
+            channel = self._client.get_channel(int(chat_id))
+            if not channel:
+                channel = await self._client.fetch_channel(int(chat_id))
 
-            if thread_id:
-                # Fetch the thread directly — threads are addressed by their own ID.
-                channel = self._client.get_channel(int(thread_id))
-                if not channel:
-                    channel = await self._client.fetch_channel(int(thread_id))
-                if not channel:
-                    return SendResult(success=False, error=f"Thread {thread_id} not found")
-            else:
-                # Get the parent channel
-                channel = self._client.get_channel(int(chat_id))
-                if not channel:
-                    channel = await self._client.fetch_channel(int(chat_id))
-                if not channel:
-                    return SendResult(success=False, error=f"Channel {chat_id} not found")
+            if not channel:
+                return SendResult(success=False, error=f"Channel {chat_id} not found")
 
             # Format and split message if needed
             formatted = self.format_message(content)
@@ -1070,7 +1017,6 @@ class DiscordAdapter(BasePlatformAdapter):
         if task:
             task.cancel()
         self._voice_text_channels.pop(guild_id, None)
-        self._voice_sources.pop(guild_id, None)
 
     # Maximum seconds to wait for voice playback before giving up
     PLAYBACK_TIMEOUT = 120
@@ -1285,8 +1231,9 @@ class DiscordAdapter(BasePlatformAdapter):
         try:
             await asyncio.to_thread(VoiceReceiver.pcm_to_wav, pcm_data, wav_path)
 
-            from tools.transcription_tools import transcribe_audio
-            result = await asyncio.to_thread(transcribe_audio, wav_path)
+            from tools.transcription_tools import transcribe_audio, get_stt_model_from_config
+            stt_model = get_stt_model_from_config()
+            result = await asyncio.to_thread(transcribe_audio, wav_path, model=stt_model)
 
             if not result.get("success"):
                 return
@@ -1360,11 +1307,8 @@ class DiscordAdapter(BasePlatformAdapter):
 
             # Download the image and send as a Discord file attachment
             # (Discord renders attachments inline, unlike plain URLs)
-            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
-            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
-            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
-            async with aiohttp.ClientSession(**_sess_kw) as session:
-                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30), **_req_kw) as resp:
+            async with aiohttp.ClientSession() as session:
+                async with session.get(image_url, timeout=aiohttp.ClientTimeout(total=30)) as resp:
                     if resp.status != 200:
                         raise Exception(f"Failed to download image: HTTP {resp.status}")
 
@@ -1405,68 +1349,6 @@ class DiscordAdapter(BasePlatformAdapter):
             )
             return await super().send_image(chat_id, image_url, caption, reply_to)
 
-    async def send_animation(
-        self,
-        chat_id: str,
-        animation_url: str,
-        caption: Optional[str] = None,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        """Send an animated GIF natively as a Discord file attachment."""
-        if not self._client:
-            return SendResult(success=False, error="Not connected")
-
-        if not is_safe_url(animation_url):
-            logger.warning("[%s] Blocked unsafe animation URL during Discord send_animation", self.name)
-            return await super().send_animation(chat_id, animation_url, caption, reply_to, metadata=metadata)
-
-        try:
-            import aiohttp
-
-            channel = self._client.get_channel(int(chat_id))
-            if not channel:
-                channel = await self._client.fetch_channel(int(chat_id))
-            if not channel:
-                return SendResult(success=False, error=f"Channel {chat_id} not found")
-
-            # Download the GIF and send as a Discord file attachment
-            # (Discord renders .gif attachments as auto-playing animations inline)
-            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
-            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
-            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
-            async with aiohttp.ClientSession(**_sess_kw) as session:
-                async with session.get(animation_url, timeout=aiohttp.ClientTimeout(total=30), **_req_kw) as resp:
-                    if resp.status != 200:
-                        raise Exception(f"Failed to download animation: HTTP {resp.status}")
-
-                    animation_data = await resp.read()
-
-                    import io
-                    file = discord.File(io.BytesIO(animation_data), filename="animation.gif")
-
-                    msg = await channel.send(
-                        content=caption if caption else None,
-                        file=file,
-                    )
-                    return SendResult(success=True, message_id=str(msg.id))
-
-        except ImportError:
-            logger.warning(
-                "[%s] aiohttp not installed, falling back to URL. Run: pip install aiohttp",
-                self.name,
-                exc_info=True,
-            )
-            return await super().send_animation(chat_id, animation_url, caption, reply_to, metadata=metadata)
-        except Exception as e:  # pragma: no cover - defensive logging
-            logger.error(
-                "[%s] Failed to send animation attachment, falling back to URL: %s",
-                self.name,
-                e,
-                exc_info=True,
-            )
-            return await super().send_animation(chat_id, animation_url, caption, reply_to, metadata=metadata)
-
     async def send_video(
         self,
         chat_id: str,
@@ -1703,7 +1585,7 @@ class DiscordAdapter(BasePlatformAdapter):
             await self._run_simple_slash(interaction, f"/model {name}".strip())
 
         @tree.command(name="reasoning", description="Show or change reasoning effort")
-        @discord.app_commands.describe(effort="Reasoning effort: none, minimal, low, medium, high, or xhigh.")
+        @discord.app_commands.describe(effort="Reasoning effort: xhigh, high, medium, low, minimal, or none.")
         async def slash_reasoning(interaction: discord.Interaction, effort: str = ""):
             await self._run_simple_slash(interaction, f"/reasoning {effort}".strip())
 
@@ -1784,10 +1666,6 @@ class DiscordAdapter(BasePlatformAdapter):
         async def slash_update(interaction: discord.Interaction):
             await self._run_simple_slash(interaction, "/update", "Update initiated~")
 
-        @tree.command(name="restart", description="Gracefully restart the Hermes gateway")
-        async def slash_restart(interaction: discord.Interaction):
-            await self._run_simple_slash(interaction, "/restart", "Restart requested~")
-
         @tree.command(name="approve", description="Approve a pending dangerous command")
         @discord.app_commands.describe(scope="Optional: 'all', 'session', 'always', 'all session', 'all always'")
         async def slash_approve(interaction: discord.Interaction, scope: str = ""):
@@ -1828,160 +1706,46 @@ class DiscordAdapter(BasePlatformAdapter):
         async def slash_btw(interaction: discord.Interaction, question: str):
             await self._run_simple_slash(interaction, f"/btw {question}")
 
-        # ── Auto-register any gateway-available commands not yet on the tree ──
-        # This ensures new commands added to COMMAND_REGISTRY in
-        # hermes_cli/commands.py automatically appear as Discord slash
-        # commands without needing a manual entry here.
+        # Register installed skills as native slash commands (parity with
+        # Telegram, which uses telegram_menu_commands() in commands.py).
+        # Discord allows up to 100 application commands globally.
+        _DISCORD_CMD_LIMIT = 100
         try:
-            from hermes_cli.commands import COMMAND_REGISTRY, _is_gateway_available, _resolve_config_gates
+            from hermes_cli.commands import discord_skill_commands
 
-            already_registered = set()
-            try:
-                already_registered = {cmd.name for cmd in tree.get_commands()}
-            except Exception:
-                pass
+            existing_names = {cmd.name for cmd in tree.get_commands()}
+            remaining_slots = max(0, _DISCORD_CMD_LIMIT - len(existing_names))
 
-            config_overrides = _resolve_config_gates()
-
-            for cmd_def in COMMAND_REGISTRY:
-                if not _is_gateway_available(cmd_def, config_overrides):
-                    continue
-                # Discord command names: lowercase, hyphens OK, max 32 chars.
-                discord_name = cmd_def.name.lower()[:32]
-                if discord_name in already_registered:
-                    continue
-                # Skip aliases that overlap with already-registered names
-                # (aliases for explicitly registered commands are handled above).
-                desc = (cmd_def.description or f"Run /{cmd_def.name}")[:100]
-                has_args = bool(cmd_def.args_hint)
-
-                if has_args:
-                    # Command takes optional arguments — create handler with
-                    # an optional ``args`` string parameter.
-                    def _make_args_handler(_name: str, _hint: str):
-                        @discord.app_commands.describe(args=f"Arguments: {_hint}"[:100])
-                        async def _handler(interaction: discord.Interaction, args: str = ""):
-                            await self._run_simple_slash(
-                                interaction, f"/{_name} {args}".strip()
-                            )
-                        _handler.__name__ = f"auto_slash_{_name.replace('-', '_')}"
-                        return _handler
-
-                    handler = _make_args_handler(cmd_def.name, cmd_def.args_hint)
-                else:
-                    # Parameterless command.
-                    def _make_simple_handler(_name: str):
-                        async def _handler(interaction: discord.Interaction):
-                            await self._run_simple_slash(interaction, f"/{_name}")
-                        _handler.__name__ = f"auto_slash_{_name.replace('-', '_')}"
-                        return _handler
-
-                    handler = _make_simple_handler(cmd_def.name)
-
-                auto_cmd = discord.app_commands.Command(
-                    name=discord_name,
-                    description=desc,
-                    callback=handler,
-                )
-                try:
-                    tree.add_command(auto_cmd)
-                    already_registered.add(discord_name)
-                except Exception:
-                    # Silently skip commands that fail registration (e.g.
-                    # name conflict with a subcommand group).
-                    pass
-
-            logger.debug(
-                "Discord auto-registered %d commands from COMMAND_REGISTRY",
-                len(already_registered),
-            )
-        except Exception as e:
-            logger.warning("Discord auto-register from COMMAND_REGISTRY failed: %s", e)
-
-        # Register skills under a single /skill command group with category
-        # subcommand groups.  This uses 1 top-level slot instead of N,
-        # supporting up to 25 categories × 25 skills = 625 skills.
-        self._register_skill_group(tree)
-
-    def _register_skill_group(self, tree) -> None:
-        """Register a ``/skill`` command group with category subcommand groups.
-
-        Skills are organized by their directory category under ``SKILLS_DIR``.
-        Each category becomes a subcommand group; root-level skills become
-        direct subcommands.  Discord supports 25 subcommand groups × 25
-        subcommands each = 625 skills — well beyond the old 100-command cap.
-        """
-        try:
-            from hermes_cli.commands import discord_skill_commands_by_category
-
-            existing_names = set()
-            try:
-                existing_names = {cmd.name for cmd in tree.get_commands()}
-            except Exception:
-                pass
-
-            categories, uncategorized, hidden = discord_skill_commands_by_category(
+            skill_entries, skipped = discord_skill_commands(
+                max_slots=remaining_slots,
                 reserved_names=existing_names,
             )
 
-            if not categories and not uncategorized:
-                return
+            for discord_name, description, cmd_key in skill_entries:
+                # Closure factory to capture cmd_key per iteration
+                def _make_skill_handler(_key: str):
+                    async def _skill_slash(interaction: discord.Interaction, args: str = ""):
+                        await self._run_simple_slash(interaction, f"{_key} {args}".strip())
+                    return _skill_slash
 
-            skill_group = discord.app_commands.Group(
-                name="skill",
-                description="Run a Hermes skill",
-            )
+                handler = _make_skill_handler(cmd_key)
+                handler.__name__ = f"skill_{discord_name.replace('-', '_')}"
 
-            # ── Helper: build a callback for a skill command key ──
-            def _make_handler(_key: str):
-                @discord.app_commands.describe(args="Optional arguments for the skill")
-                async def _handler(interaction: discord.Interaction, args: str = ""):
-                    await self._run_simple_slash(interaction, f"{_key} {args}".strip())
-                _handler.__name__ = f"skill_{_key.lstrip('/').replace('-', '_')}"
-                return _handler
-
-            # ── Uncategorized (root-level) skills → direct subcommands ──
-            for discord_name, description, cmd_key in uncategorized:
                 cmd = discord.app_commands.Command(
                     name=discord_name,
-                    description=description or f"Run the {discord_name} skill",
-                    callback=_make_handler(cmd_key),
+                    description=description,
+                    callback=handler,
                 )
-                skill_group.add_command(cmd)
+                discord.app_commands.describe(args="Optional arguments for the skill")(cmd)
+                tree.add_command(cmd)
 
-            # ── Category subcommand groups ──
-            for cat_name in sorted(categories):
-                cat_desc = f"{cat_name.replace('-', ' ').title()} skills"
-                if len(cat_desc) > 100:
-                    cat_desc = cat_desc[:97] + "..."
-                cat_group = discord.app_commands.Group(
-                    name=cat_name,
-                    description=cat_desc,
-                    parent=skill_group,
-                )
-                for discord_name, description, cmd_key in categories[cat_name]:
-                    cmd = discord.app_commands.Command(
-                        name=discord_name,
-                        description=description or f"Run the {discord_name} skill",
-                        callback=_make_handler(cmd_key),
-                    )
-                    cat_group.add_command(cmd)
-
-            tree.add_command(skill_group)
-
-            total = sum(len(v) for v in categories.values()) + len(uncategorized)
-            logger.info(
-                "[%s] Registered /skill group: %d skill(s) across %d categories"
-                " + %d uncategorized",
-                self.name, total, len(categories), len(uncategorized),
-            )
-            if hidden:
+            if skipped:
                 logger.warning(
-                    "[%s] %d skill(s) not registered (Discord subcommand limits)",
-                    self.name, hidden,
+                    "[%s] Discord slash command limit reached (%d): %d skill(s) not registered",
+                    self.name, _DISCORD_CMD_LIMIT, skipped,
                 )
         except Exception as exc:
-            logger.warning("[%s] Failed to register /skill group: %s", self.name, exc)
+            logger.warning("[%s] Failed to register skill slash commands: %s", self.name, exc)
 
     def _build_slash_event(self, interaction: discord.Interaction, text: str) -> MessageEvent:
         """Build a MessageEvent from a Discord slash command interaction."""
@@ -2018,14 +1782,11 @@ class DiscordAdapter(BasePlatformAdapter):
         )
 
         msg_type = MessageType.COMMAND if text.startswith("/") else MessageType.TEXT
-        channel_id = str(interaction.channel_id)
-        parent_id = str(getattr(getattr(interaction, "channel", None), "parent_id", "") or "")
         return MessageEvent(
             text=text,
             message_type=msg_type,
             source=source,
             raw_message=interaction,
-            channel_prompt=self._resolve_channel_prompt(channel_id, parent_id or None),
         )
 
     # ------------------------------------------------------------------
@@ -2061,7 +1822,7 @@ class DiscordAdapter(BasePlatformAdapter):
 
         # Track thread participation so follow-ups don't require @mention
         if thread_id:
-            self._threads.mark(thread_id)
+            self._track_thread(thread_id)
 
         # If a message was provided, kick off a new Hermes session in the thread
         starter = (message or "").strip()
@@ -2096,50 +1857,14 @@ class DiscordAdapter(BasePlatformAdapter):
             chat_topic=chat_topic,
         )
 
-        _parent_channel = self._thread_parent_channel(getattr(interaction, "channel", None))
-        _parent_id = str(getattr(_parent_channel, "id", "") or "")
-        _skills = self._resolve_channel_skills(thread_id, _parent_id or None)
-        _channel_prompt = self._resolve_channel_prompt(thread_id, _parent_id or None)
         event = MessageEvent(
             text=text,
             message_type=MessageType.TEXT,
             source=source,
             raw_message=interaction,
-            auto_skill=_skills,
-            channel_prompt=_channel_prompt,
         )
         await self.handle_message(event)
 
-    def _resolve_channel_skills(self, channel_id: str, parent_id: str | None = None) -> list[str] | None:
-        """Look up auto-skill bindings for a Discord channel/forum thread.
-
-        Config format (in platform extra):
-            channel_skill_bindings:
-              - id: "123456"
-                skills: ["skill-a", "skill-b"]
-        Also checks parent_id so forum threads inherit the forum's bindings.
-        """
-        bindings = self.config.extra.get("channel_skill_bindings", [])
-        if not bindings:
-            return None
-        ids_to_check = {channel_id}
-        if parent_id:
-            ids_to_check.add(parent_id)
-        for entry in bindings:
-            entry_id = str(entry.get("id", ""))
-            if entry_id in ids_to_check:
-                skills = entry.get("skills") or entry.get("skill")
-                if isinstance(skills, str):
-                    return [skills]
-                if isinstance(skills, list) and skills:
-                    return list(dict.fromkeys(skills))  # dedup, preserve order
-        return None
-
-    def _resolve_channel_prompt(self, channel_id: str, parent_id: str | None = None) -> str | None:
-        """Resolve a Discord per-channel prompt, preferring the exact channel over its parent."""
-        from gateway.platforms.base import resolve_channel_prompt
-        return resolve_channel_prompt(self.config.extra, channel_id, parent_id)
-
     def _thread_parent_channel(self, channel: Any) -> Any:
         """Return the parent text channel when invoked from a thread."""
         return getattr(channel, "parent", None) or channel
@@ -2440,6 +2165,49 @@ class DiscordAdapter(BasePlatformAdapter):
             return f"{parent_name} / {thread_name}"
         return thread_name
 
+    # ------------------------------------------------------------------
+    # Thread participation persistence
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _thread_state_path() -> Path:
+        """Path to the persisted thread participation set."""
+        from hermes_cli.config import get_hermes_home
+        return get_hermes_home() / "discord_threads.json"
+
+    @classmethod
+    def _load_participated_threads(cls) -> set:
+        """Load persisted thread IDs from disk."""
+        path = cls._thread_state_path()
+        try:
+            if path.exists():
+                data = json.loads(path.read_text(encoding="utf-8"))
+                if isinstance(data, list):
+                    return set(data)
+        except Exception as e:
+            logger.debug("Could not load discord thread state: %s", e)
+        return set()
+
+    def _save_participated_threads(self) -> None:
+        """Persist the current thread set to disk (best-effort)."""
+        path = self._thread_state_path()
+        try:
+            # Trim to most recent entries if over cap
+            thread_list = list(self._bot_participated_threads)
+            if len(thread_list) > self._MAX_TRACKED_THREADS:
+                thread_list = thread_list[-self._MAX_TRACKED_THREADS:]
+                self._bot_participated_threads = set(thread_list)
+            path.parent.mkdir(parents=True, exist_ok=True)
+            path.write_text(json.dumps(thread_list), encoding="utf-8")
+        except Exception as e:
+            logger.debug("Could not save discord thread state: %s", e)
+
+    def _track_thread(self, thread_id: str) -> None:
+        """Add a thread to the participation set and persist."""
+        if thread_id not in self._bot_participated_threads:
+            self._bot_participated_threads.add(thread_id)
+            self._save_participated_threads()
+
     async def _handle_message(self, message: DiscordMessage) -> None:
         """Handle incoming Discord messages."""
         # In server channels (not DMs), require the bot to be @mentioned
@@ -2450,7 +2218,6 @@ class DiscordAdapter(BasePlatformAdapter):
         #   discord.require_mention: Require @mention in server channels (default: true)
         #   discord.free_response_channels: Channel IDs where bot responds without mention
         #   discord.ignored_channels: Channel IDs where bot NEVER responds (even when mentioned)
-        #   discord.allowed_channels: If set, bot ONLY responds in these channels (whitelist)
         #   discord.no_thread_channels: Channel IDs where bot responds directly without creating thread
         #   discord.auto_thread: Auto-create thread on @mention in channels (default: true)
 
@@ -2461,23 +2228,13 @@ class DiscordAdapter(BasePlatformAdapter):
             thread_id = str(message.channel.id)
             parent_channel_id = self._get_parent_channel_id(message.channel)
 
-        is_voice_linked_channel = False
         if not isinstance(message.channel, discord.DMChannel):
+            # Check ignored channels first - never respond even when mentioned
+            ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
+            ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
             channel_ids = {str(message.channel.id)}
             if parent_channel_id:
                 channel_ids.add(parent_channel_id)
-
-            # Check allowed channels - if set, only respond in these channels
-            allowed_channels_raw = os.getenv("DISCORD_ALLOWED_CHANNELS", "")
-            if allowed_channels_raw:
-                allowed_channels = {ch.strip() for ch in allowed_channels_raw.split(",") if ch.strip()}
-                if not (channel_ids & allowed_channels):
-                    logger.debug("[%s] Ignoring message in non-allowed channel: %s", self.name, channel_ids)
-                    return
-
-            # Check ignored channels - never respond even when mentioned
-            ignored_channels_raw = os.getenv("DISCORD_IGNORED_CHANNELS", "")
-            ignored_channels = {ch.strip() for ch in ignored_channels_raw.split(",") if ch.strip()}
             if channel_ids & ignored_channels:
                 logger.debug("[%s] Ignoring message in ignored channel: %s", self.name, channel_ids)
                 return
@@ -2488,16 +2245,11 @@ class DiscordAdapter(BasePlatformAdapter):
                 channel_ids.add(parent_channel_id)
 
             require_mention = os.getenv("DISCORD_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no")
-            # Voice-linked text channels act as free-response while voice is active.
-            # Only the exact bound channel gets the exemption, not sibling threads.
-            voice_linked_ids = {str(ch_id) for ch_id in self._voice_text_channels.values()}
-            current_channel_id = str(message.channel.id)
-            is_voice_linked_channel = current_channel_id in voice_linked_ids
-            is_free_channel = bool(channel_ids & free_channels) or is_voice_linked_channel
+            is_free_channel = bool(channel_ids & free_channels)
 
             # Skip the mention check if the message is in a thread where
             # the bot has previously participated (auto-created or replied in).
-            in_bot_thread = is_thread and thread_id in self._threads
+            in_bot_thread = is_thread and thread_id in self._bot_participated_threads
 
             if require_mention and not is_free_channel and not in_bot_thread:
                 if self._client.user not in message.mentions:
@@ -2517,13 +2269,13 @@ class DiscordAdapter(BasePlatformAdapter):
             no_thread_channels = {ch.strip() for ch in no_thread_channels_raw.split(",") if ch.strip()}
             skip_thread = bool(channel_ids & no_thread_channels)
             auto_thread = os.getenv("DISCORD_AUTO_THREAD", "true").lower() in ("true", "1", "yes")
-            if auto_thread and not skip_thread and not is_voice_linked_channel:
+            if auto_thread and not skip_thread:
                 thread = await self._auto_create_thread(message)
                 if thread:
                     is_thread = True
                     thread_id = str(thread.id)
                     auto_threaded_channel = thread
-                    self._threads.mark(thread_id)
+                    self._track_thread(thread_id)
 
         # Determine message type
         msg_type = MessageType.TEXT
@@ -2639,14 +2391,10 @@ class DiscordAdapter(BasePlatformAdapter):
                     else:
                         try:
                             import aiohttp
-                            from gateway.platforms.base import resolve_proxy_url, proxy_kwargs_for_aiohttp
-                            _proxy = resolve_proxy_url(platform_env_var="DISCORD_PROXY")
-                            _sess_kw, _req_kw = proxy_kwargs_for_aiohttp(_proxy)
-                            async with aiohttp.ClientSession(**_sess_kw) as session:
+                            async with aiohttp.ClientSession() as session:
                                 async with session.get(
                                     att.url,
                                     timeout=aiohttp.ClientTimeout(total=30),
-                                    **_req_kw,
                                 ) as resp:
                                     if resp.status != 200:
                                         raise Exception(f"HTTP {resp.status}")
@@ -2687,19 +2435,6 @@ class DiscordAdapter(BasePlatformAdapter):
         if not event_text or not event_text.strip():
             event_text = "(The user sent a message with no text content)"
 
-        _chan = message.channel
-        _parent_id = str(getattr(_chan, "parent_id", "") or "")
-        _chan_id = str(getattr(_chan, "id", ""))
-        _skills = self._resolve_channel_skills(_chan_id, _parent_id or None)
-        _channel_prompt = self._resolve_channel_prompt(_chan_id, _parent_id or None)
-
-        reply_to_id = None
-        reply_to_text = None
-        if message.reference:
-            reply_to_id = str(message.reference.message_id)
-            if message.reference.resolved:
-                reply_to_text = getattr(message.reference.resolved, "content", None) or None
-
         event = MessageEvent(
             text=event_text,
             message_type=msg_type,
@@ -2708,92 +2443,16 @@ class DiscordAdapter(BasePlatformAdapter):
             message_id=str(message.id),
             media_urls=media_urls,
             media_types=media_types,
-            reply_to_message_id=reply_to_id,
-            reply_to_text=reply_to_text,
+            reply_to_message_id=str(message.reference.message_id) if message.reference else None,
             timestamp=message.created_at,
-            auto_skill=_skills,
-            channel_prompt=_channel_prompt,
         )
 
         # Track thread participation so the bot won't require @mention for
         # follow-up messages in threads it has already engaged in.
         if thread_id:
-            self._threads.mark(thread_id)
+            self._track_thread(thread_id)
 
-        # Only batch plain text messages — commands, media, etc. dispatch
-        # immediately since they won't be split by the Discord client.
-        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
-            self._enqueue_text_event(event)
-        else:
-            await self.handle_message(event)
-
-    # ------------------------------------------------------------------
-    # Text message aggregation (handles Discord client-side splits)
-    # ------------------------------------------------------------------
-
-    def _text_batch_key(self, event: MessageEvent) -> str:
-        """Session-scoped key for text message batching."""
-        from gateway.session import build_session_key
-        return build_session_key(
-            event.source,
-            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
-            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
-        )
-
-    def _enqueue_text_event(self, event: MessageEvent) -> None:
-        """Buffer a text event and reset the flush timer.
-
-        When Discord splits a long user message at 2000 chars, the chunks
-        arrive within a few hundred milliseconds.  This merges them into
-        a single event before dispatching.
-        """
-        key = self._text_batch_key(event)
-        existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
-        if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending_text_batches[key] = event
-        else:
-            if event.text:
-                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            if event.media_urls:
-                existing.media_urls.extend(event.media_urls)
-                existing.media_types.extend(event.media_types)
-
-        prior_task = self._pending_text_batch_tasks.get(key)
-        if prior_task and not prior_task.done():
-            prior_task.cancel()
-        self._pending_text_batch_tasks[key] = asyncio.create_task(
-            self._flush_text_batch(key)
-        )
-
-    async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near Discord's 2000-char
-        split point, since a continuation chunk is almost certain.
-        """
-        current_task = asyncio.current_task()
-        try:
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
-            event = self._pending_text_batches.pop(key, None)
-            if not event:
-                return
-            logger.info(
-                "[Discord] Flushing text batch %s (%d chars)",
-                key, len(event.text or ""),
-            )
-            await self.handle_message(event)
-        finally:
-            if self._pending_text_batch_tasks.get(key) is current_task:
-                self._pending_text_batch_tasks.pop(key, None)
+        await self.handle_message(event)
 
 
 # ---------------------------------------------------------------------------

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.py

@@ -34,9 +34,6 @@ from datetime import datetime
 from pathlib import Path
 from types import SimpleNamespace
 from typing import Any, Dict, List, Optional
-from urllib.error import HTTPError, URLError
-from urllib.parse import urlencode
-from urllib.request import Request, urlopen
 
 # aiohttp/websockets are independent optional deps — import outside lark_oapi
 # so they remain available for tests and webhook mode even if lark_oapi is missing.
@@ -72,10 +69,7 @@ try:
         UpdateMessageRequestBody,
     )
     from lark_oapi.core.const import FEISHU_DOMAIN, LARK_DOMAIN
-    from lark_oapi.event.callback.model.p2_card_action_trigger import (
-        CallBackCard,
-        P2CardActionTriggerResponse,
-    )
+    from lark_oapi.event.callback.model.p2_card_action_trigger import P2CardActionTriggerResponse
     from lark_oapi.event.dispatcher_handler import EventDispatcherHandler
     from lark_oapi.ws import Client as FeishuWSClient
 
@@ -83,7 +77,6 @@ try:
 except ImportError:
     FEISHU_AVAILABLE = False
     lark = None  # type: ignore[assignment]
-    CallBackCard = None  # type: ignore[assignment]
     P2CardActionTriggerResponse = None  # type: ignore[assignment]
     EventDispatcherHandler = None  # type: ignore[assignment]
     FeishuWSClient = None  # type: ignore[assignment]
@@ -173,35 +166,9 @@ _FEISHU_WEBHOOK_BODY_TIMEOUT_SECONDS = 30          # max seconds to read request
 _FEISHU_WEBHOOK_ANOMALY_THRESHOLD = 25             # consecutive error responses before WARNING log
 _FEISHU_WEBHOOK_ANOMALY_TTL_SECONDS = 6 * 60 * 60  # anomaly tracker TTL (6 hours) — matches openclaw
 _FEISHU_CARD_ACTION_DEDUP_TTL_SECONDS = 15 * 60    # card action token dedup window (15 min)
-
-_APPROVAL_CHOICE_MAP: Dict[str, str] = {
-    "approve_once": "once",
-    "approve_session": "session",
-    "approve_always": "always",
-    "deny": "deny",
-}
-_APPROVAL_LABEL_MAP: Dict[str, str] = {
-    "once": "Approved once",
-    "session": "Approved for session",
-    "always": "Approved permanently",
-    "deny": "Denied",
-}
 _FEISHU_BOT_MSG_TRACK_SIZE = 512                   # LRU size for tracking sent message IDs
 _FEISHU_REPLY_FALLBACK_CODES = frozenset({230011, 231003})  # reply target withdrawn/missing → create fallback
 _FEISHU_ACK_EMOJI = "OK"
-
-# QR onboarding constants
-_ONBOARD_ACCOUNTS_URLS = {
-    "feishu": "https://accounts.feishu.cn",
-    "lark": "https://accounts.larksuite.com",
-}
-_ONBOARD_OPEN_URLS = {
-    "feishu": "https://open.feishu.cn",
-    "lark": "https://open.larksuite.com",
-}
-_REGISTRATION_PATH = "/oauth/v1/app/registration"
-_ONBOARD_REQUEST_TIMEOUT_S = 10
-
 # ---------------------------------------------------------------------------
 # Fallback display strings
 # ---------------------------------------------------------------------------
@@ -297,7 +264,6 @@ class FeishuAdapterSettings:
     bot_name: str
     dedup_cache_size: int
     text_batch_delay_seconds: float
-    text_batch_split_delay_seconds: float
     text_batch_max_messages: int
     text_batch_max_chars: int
     media_batch_delay_seconds: float
@@ -393,21 +359,19 @@ def _render_code_block_element(element: Dict[str, Any]) -> str:
 
 
 def _strip_markdown_to_plain_text(text: str) -> str:
-    """Strip markdown formatting to plain text for Feishu text fallbacks.
-
-    Delegates common markdown stripping to the shared helper and adds
-    Feishu-specific patterns (blockquotes, strikethrough, underline tags,
-    horizontal rules, \\r\\n normalisation).
-    """
-    from gateway.platforms.helpers import strip_markdown
     plain = text.replace("\r\n", "\n")
     plain = _MARKDOWN_LINK_RE.sub(lambda m: f"{m.group(1)} ({m.group(2).strip()})", plain)
+    plain = re.sub(r"^#{1,6}\s+", "", plain, flags=re.MULTILINE)
     plain = re.sub(r"^>\s?", "", plain, flags=re.MULTILINE)
     plain = re.sub(r"^\s*---+\s*$", "---", plain, flags=re.MULTILINE)
+    plain = re.sub(r"```(?:[^\n]*\n)?([\s\S]*?)```", lambda m: m.group(1).strip("\n"), plain)
+    plain = re.sub(r"`([^`\n]+)`", r"\1", plain)
+    plain = re.sub(r"\*\*([^*\n]+)\*\*", r"\1", plain)
+    plain = re.sub(r"\*([^*\n]+)\*", r"\1", plain)
     plain = re.sub(r"~~([^~\n]+)~~", r"\1", plain)
     plain = re.sub(r"<u>([\s\S]*?)</u>", r"\1", plain)
-    plain = strip_markdown(plain)
-    return plain
+    plain = re.sub(r"\n{3,}", "\n\n", plain)
+    return plain.strip()
 
 
 def _coerce_int(value: Any, default: Optional[int] = None, min_value: int = 0) -> Optional[int]:
@@ -447,6 +411,14 @@ def _build_markdown_post_payload(content: str) -> str:
     )
 
 
+def parse_feishu_post_content(raw_content: str) -> FeishuPostParseResult:
+    try:
+        parsed = json.loads(raw_content) if raw_content else {}
+    except json.JSONDecodeError:
+        return FeishuPostParseResult(text_content=FALLBACK_POST_TEXT)
+    return parse_feishu_post_payload(parsed)
+
+
 def parse_feishu_post_payload(payload: Any) -> FeishuPostParseResult:
     resolved = _resolve_post_payload(payload)
     if not resolved:
@@ -1000,8 +972,7 @@ def _run_official_feishu_ws_client(ws_client: Any, adapter: Any) -> None:
         return await original_connect(*args, **kwargs)
 
     def _configure_with_overrides(conf: Any) -> Any:
-        if original_configure is None:
-            raise RuntimeError("Feishu _configure_with_overrides called but original_configure is None")
+        assert original_configure is not None
         result = original_configure(conf)
         _apply_runtime_ws_overrides()
         return result
@@ -1043,10 +1014,6 @@ class FeishuAdapter(BasePlatformAdapter):
     """Feishu/Lark bot adapter."""
 
     MAX_MESSAGE_LENGTH = 8000
-    # Threshold for detecting Feishu client-side message splits.
-    # When a chunk is near the ~4096-char practical limit, a continuation
-    # is almost certain.
-    _SPLIT_THRESHOLD = 4000
 
     # =========================================================================
     # Lifecycle — init / settings / connect / disconnect
@@ -1073,13 +1040,6 @@ class FeishuAdapter(BasePlatformAdapter):
         self._webhook_rate_counts: Dict[str, tuple[int, float]] = {}  # rate_key → (count, window_start)
         self._webhook_anomaly_counts: Dict[str, tuple[int, str, float]] = {}  # ip → (count, last_status, first_seen)
         self._card_action_tokens: Dict[str, float] = {}  # token → first_seen_time
-        # Inbound events that arrived before the adapter loop was ready
-        # (e.g. during startup/restart or network-flap reconnect). A single
-        # drainer thread replays them as soon as the loop becomes available.
-        self._pending_inbound_events: List[Any] = []
-        self._pending_inbound_lock = threading.Lock()
-        self._pending_drain_scheduled = False
-        self._pending_inbound_max_depth = 1000  # cap queue; drop oldest beyond
         self._chat_locks: Dict[str, asyncio.Lock] = {}  # chat_id → lock (per-chat serial processing)
         self._sent_message_ids_to_chat: Dict[str, str] = {}  # message_id → chat_id (for reaction routing)
         self._sent_message_id_order: List[str] = []  # LRU order for _sent_message_ids_to_chat
@@ -1145,9 +1105,6 @@ class FeishuAdapter(BasePlatformAdapter):
             text_batch_delay_seconds=float(
                 os.getenv("HERMES_FEISHU_TEXT_BATCH_DELAY_SECONDS", str(_DEFAULT_TEXT_BATCH_DELAY_SECONDS))
             ),
-            text_batch_split_delay_seconds=float(
-                os.getenv("HERMES_FEISHU_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0")
-            ),
             text_batch_max_messages=max(
                 1,
                 int(os.getenv("HERMES_FEISHU_TEXT_BATCH_MAX_MESSAGES", str(_DEFAULT_TEXT_BATCH_MAX_MESSAGES))),
@@ -1195,7 +1152,6 @@ class FeishuAdapter(BasePlatformAdapter):
         self._bot_name = settings.bot_name
         self._dedup_cache_size = settings.dedup_cache_size
         self._text_batch_delay_seconds = settings.text_batch_delay_seconds
-        self._text_batch_split_delay_seconds = settings.text_batch_split_delay_seconds
         self._text_batch_max_messages = settings.text_batch_max_messages
         self._text_batch_max_chars = settings.text_batch_max_chars
         self._media_batch_delay_seconds = settings.media_batch_delay_seconds
@@ -1224,10 +1180,6 @@ class FeishuAdapter(BasePlatformAdapter):
                 lambda data: self._on_reaction_event("im.message.reaction.deleted_v1", data)
             )
             .register_p2_card_action_trigger(self._on_card_action_trigger)
-            .register_p2_im_chat_member_bot_added_v1(self._on_bot_added_to_chat)
-            .register_p2_im_chat_member_bot_deleted_v1(self._on_bot_removed_from_chat)
-            .register_p2_im_chat_access_event_bot_p2p_chat_entered_v1(self._on_p2p_chat_entered)
-            .register_p2_im_message_recalled_v1(self._on_message_recalled)
             .build()
         )
 
@@ -1516,12 +1468,14 @@ class FeishuAdapter(BasePlatformAdapter):
             logger.warning("[Feishu] send_exec_approval failed: %s", exc)
             return SendResult(success=False, error=str(exc))
 
-    @staticmethod
-    def _build_resolved_approval_card(*, choice: str, user_name: str) -> Dict[str, Any]:
-        """Build raw card JSON for a resolved approval action."""
+    async def _update_approval_card(
+        self, message_id: str, label: str, user_name: str, choice: str,
+    ) -> None:
+        """Replace the approval card with a resolved status card."""
+        if not self._client or not message_id:
+            return
         icon = "❌" if choice == "deny" else "✅"
-        label = _APPROVAL_LABEL_MAP.get(choice, "Resolved")
-        return {
+        card = {
             "config": {"wide_screen_mode": True},
             "header": {
                 "title": {"content": f"{icon} {label}", "tag": "plain_text"},
@@ -1534,6 +1488,13 @@ class FeishuAdapter(BasePlatformAdapter):
                 },
             ],
         }
+        try:
+            payload = json.dumps(card, ensure_ascii=False)
+            body = self._build_update_message_body(msg_type="interactive", content=payload)
+            request = self._build_update_message_request(message_id=message_id, request_body=body)
+            await asyncio.to_thread(self._client.im.v1.message.update, request)
+        except Exception as exc:
+            logger.warning("[Feishu] Failed to update approval card %s: %s", message_id, exc)
 
     async def send_voice(
         self,
@@ -1609,18 +1570,13 @@ class FeishuAdapter(BasePlatformAdapter):
             return SendResult(success=False, error=f"Image file not found: {image_path}")
 
         try:
-            import io as _io
-            with open(image_path, "rb") as f:
-                image_bytes = f.read()
-            # Wrap in BytesIO so lark SDK's MultipartEncoder can read .name and .tell()
-            image_file = _io.BytesIO(image_bytes)
-            image_file.name = os.path.basename(image_path)
-            body = self._build_image_upload_body(
-                image_type=_FEISHU_IMAGE_UPLOAD_TYPE,
-                image=image_file,
-            )
-            request = self._build_image_upload_request(body)
-            upload_response = await asyncio.to_thread(self._client.im.v1.image.create, request)
+            with open(image_path, "rb") as image_file:
+                body = self._build_image_upload_body(
+                    image_type=_FEISHU_IMAGE_UPLOAD_TYPE,
+                    image=image_file,
+                )
+                request = self._build_image_upload_request(body)
+                upload_response = await asyncio.to_thread(self._client.im.v1.image.create, request)
             image_key = self._extract_response_field(upload_response, "image_key")
             if not image_key:
                 return self._response_error_result(
@@ -1766,22 +1722,10 @@ class FeishuAdapter(BasePlatformAdapter):
     # =========================================================================
 
     def _on_message_event(self, data: Any) -> None:
-        """Normalize Feishu inbound events into MessageEvent.
-
-        Called by the lark_oapi SDK's event dispatcher on a background thread.
-        If the adapter loop is not currently accepting callbacks (brief window
-        during startup/restart or network-flap reconnect), the event is queued
-        for replay instead of dropped.
-        """
+        """Normalize Feishu inbound events into MessageEvent."""
         loop = self._loop
-        if not self._loop_accepts_callbacks(loop):
-            start_drainer = self._enqueue_pending_inbound_event(data)
-            if start_drainer:
-                threading.Thread(
-                    target=self._drain_pending_inbound_events,
-                    name="feishu-pending-inbound-drainer",
-                    daemon=True,
-                ).start()
+        if loop is None or bool(getattr(loop, "is_closed", lambda: False)()):
+            logger.warning("[Feishu] Dropping inbound message before adapter loop is ready")
             return
         future = asyncio.run_coroutine_threadsafe(
             self._handle_message_event_data(data),
@@ -1789,124 +1733,6 @@ class FeishuAdapter(BasePlatformAdapter):
         )
         future.add_done_callback(self._log_background_failure)
 
-    def _enqueue_pending_inbound_event(self, data: Any) -> bool:
-        """Append an event to the pending-inbound queue.
-
-        Returns True if the caller should spawn a drainer thread (no drainer
-        currently scheduled), False if a drainer is already running and will
-        pick up the new event on its next pass.
-        """
-        with self._pending_inbound_lock:
-            if len(self._pending_inbound_events) >= self._pending_inbound_max_depth:
-                # Queue full — drop the oldest to make room. This happens only
-                # if the loop stays unavailable for an extended period AND the
-                # WS keeps firing callbacks. Still better than silent drops.
-                dropped = self._pending_inbound_events.pop(0)
-                try:
-                    event = getattr(dropped, "event", None)
-                    message = getattr(event, "message", None)
-                    message_id = str(getattr(message, "message_id", "") or "unknown")
-                except Exception:
-                    message_id = "unknown"
-                logger.error(
-                    "[Feishu] Pending-inbound queue full (%d); dropped oldest event %s",
-                    self._pending_inbound_max_depth,
-                    message_id,
-                )
-            self._pending_inbound_events.append(data)
-            depth = len(self._pending_inbound_events)
-            should_start = not self._pending_drain_scheduled
-            if should_start:
-                self._pending_drain_scheduled = True
-        logger.warning(
-            "[Feishu] Queued inbound event for replay (loop not ready, queue depth=%d)",
-            depth,
-        )
-        return should_start
-
-    def _drain_pending_inbound_events(self) -> None:
-        """Replay queued inbound events once the adapter loop is ready.
-
-        Runs in a dedicated daemon thread. Polls ``_running`` and
-        ``_loop_accepts_callbacks`` until events can be dispatched or the
-        adapter shuts down. A single drainer handles the entire queue;
-        concurrent ``_on_message_event`` calls just append.
-        """
-        poll_interval = 0.25
-        max_wait_seconds = 120.0  # safety cap: drop queue after 2 minutes
-        waited = 0.0
-        try:
-            while True:
-                if not getattr(self, "_running", True):
-                    # Adapter shutting down — drop queued events rather than
-                    # holding them against a closed loop.
-                    with self._pending_inbound_lock:
-                        dropped = len(self._pending_inbound_events)
-                        self._pending_inbound_events.clear()
-                    if dropped:
-                        logger.warning(
-                            "[Feishu] Dropped %d queued inbound event(s) during shutdown",
-                            dropped,
-                        )
-                    return
-                loop = self._loop
-                if self._loop_accepts_callbacks(loop):
-                    with self._pending_inbound_lock:
-                        batch = self._pending_inbound_events[:]
-                        self._pending_inbound_events.clear()
-                    if not batch:
-                        # Queue emptied between check and grab; done.
-                        with self._pending_inbound_lock:
-                            if not self._pending_inbound_events:
-                                return
-                        continue
-                    dispatched = 0
-                    requeue: List[Any] = []
-                    for event in batch:
-                        try:
-                            fut = asyncio.run_coroutine_threadsafe(
-                                self._handle_message_event_data(event),
-                                loop,
-                            )
-                            fut.add_done_callback(self._log_background_failure)
-                            dispatched += 1
-                        except RuntimeError:
-                            # Loop closed between check and submit — requeue
-                            # and poll again.
-                            requeue.append(event)
-                    if requeue:
-                        with self._pending_inbound_lock:
-                            self._pending_inbound_events[:0] = requeue
-                    if dispatched:
-                        logger.info(
-                            "[Feishu] Replayed %d queued inbound event(s)",
-                            dispatched,
-                        )
-                    if not requeue:
-                        # Successfully drained; check if more arrived while
-                        # we were dispatching and exit if not.
-                        with self._pending_inbound_lock:
-                            if not self._pending_inbound_events:
-                                return
-                    # More events queued or requeue pending — loop again.
-                    continue
-                if waited >= max_wait_seconds:
-                    with self._pending_inbound_lock:
-                        dropped = len(self._pending_inbound_events)
-                        self._pending_inbound_events.clear()
-                    logger.error(
-                        "[Feishu] Adapter loop unavailable for %.0fs; "
-                        "dropped %d queued inbound event(s)",
-                        max_wait_seconds,
-                        dropped,
-                    )
-                    return
-                time.sleep(poll_interval)
-                waited += poll_interval
-        finally:
-            with self._pending_inbound_lock:
-                self._pending_drain_scheduled = False
-
     async def _handle_message_event_data(self, data: Any) -> None:
         """Shared inbound message handling for websocket and webhook transports."""
         event = getattr(data, "event", None)
@@ -1959,12 +1785,6 @@ class FeishuAdapter(BasePlatformAdapter):
         logger.info("[Feishu] Bot removed from chat: %s", chat_id)
         self._chat_info_cache.pop(chat_id, None)
 
-    def _on_p2p_chat_entered(self, data: Any) -> None:
-        logger.debug("[Feishu] User entered P2P chat with bot")
-
-    def _on_message_recalled(self, data: Any) -> None:
-        logger.debug("[Feishu] Message recalled by user")
-
     def _on_reaction_event(self, event_type: str, data: Any) -> None:
         """Route user reactions on bot messages as synthetic text events."""
         event = getattr(data, "event", None)
@@ -1998,82 +1818,20 @@ class FeishuAdapter(BasePlatformAdapter):
         future.add_done_callback(self._log_background_failure)
 
     def _on_card_action_trigger(self, data: Any) -> Any:
-        """Handle card-action callback from the Feishu SDK (synchronous).
-
-        For approval actions: parses the event once, returns the resolved card
-        inline (the only reliable way to sync all clients), and schedules a
-        lightweight async method to actually unblock the agent.
-
-        For other card actions: delegates to ``_handle_card_action_event``.
-        """
+        """Schedule Feishu card actions on the adapter loop and acknowledge immediately."""
         loop = self._loop
-        if not self._loop_accepts_callbacks(loop):
+        if loop is None or bool(getattr(loop, "is_closed", lambda: False)()):
             logger.warning("[Feishu] Dropping card action before adapter loop is ready")
-            return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
-
-        event = getattr(data, "event", None)
-        action = getattr(event, "action", None)
-        action_value = getattr(action, "value", {}) or {}
-        hermes_action = action_value.get("hermes_action") if isinstance(action_value, dict) else None
-
-        if hermes_action:
-            return self._handle_approval_card_action(event=event, action_value=action_value, loop=loop)
-
-        self._submit_on_loop(loop, self._handle_card_action_event(data))
+        else:
+            future = asyncio.run_coroutine_threadsafe(
+                self._handle_card_action_event(data),
+                loop,
+            )
+            future.add_done_callback(self._log_background_failure)
         if P2CardActionTriggerResponse is None:
             return None
         return P2CardActionTriggerResponse()
 
-    @staticmethod
-    def _loop_accepts_callbacks(loop: Any) -> bool:
-        """Return True when the adapter loop can accept thread-safe submissions."""
-        return loop is not None and not bool(getattr(loop, "is_closed", lambda: False)())
-
-    def _submit_on_loop(self, loop: Any, coro: Any) -> None:
-        """Schedule background work on the adapter loop with shared failure logging."""
-        future = asyncio.run_coroutine_threadsafe(coro, loop)
-        future.add_done_callback(self._log_background_failure)
-
-    def _handle_approval_card_action(self, *, event: Any, action_value: Dict[str, Any], loop: Any) -> Any:
-        """Schedule approval resolution and build the synchronous callback response."""
-        approval_id = action_value.get("approval_id")
-        if approval_id is None:
-            logger.debug("[Feishu] Card action missing approval_id, ignoring")
-            return P2CardActionTriggerResponse() if P2CardActionTriggerResponse else None
-        choice = _APPROVAL_CHOICE_MAP.get(action_value.get("hermes_action"), "deny")
-
-        operator = getattr(event, "operator", None)
-        open_id = str(getattr(operator, "open_id", "") or "")
-        user_name = self._get_cached_sender_name(open_id) or open_id
-
-        self._submit_on_loop(loop, self._resolve_approval(approval_id, choice, user_name))
-
-        if P2CardActionTriggerResponse is None:
-            return None
-        response = P2CardActionTriggerResponse()
-        if CallBackCard is not None:
-            card = CallBackCard()
-            card.type = "raw"
-            card.data = self._build_resolved_approval_card(choice=choice, user_name=user_name)
-            response.card = card
-        return response
-
-    async def _resolve_approval(self, approval_id: Any, choice: str, user_name: str) -> None:
-        """Pop approval state and unblock the waiting agent thread."""
-        state = self._approval_state.pop(approval_id, None)
-        if not state:
-            logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
-            return
-        try:
-            from tools.approval import resolve_gateway_approval
-            count = resolve_gateway_approval(state["session_key"], choice)
-            logger.info(
-                "Feishu button resolved %d approval(s) for session %s (choice=%s, user=%s)",
-                count, state["session_key"], choice, user_name,
-            )
-        except Exception as exc:
-            logger.error("Failed to resolve gateway approval from Feishu button: %s", exc)
-
     async def _handle_reaction_event(self, event_type: str, data: Any) -> None:
         """Fetch the reacted-to message; if it was sent by this bot, emit a synthetic text event."""
         if not self._client:
@@ -2165,6 +1923,51 @@ class FeishuAdapter(BasePlatformAdapter):
         action_tag = str(getattr(action, "tag", "") or "button")
         action_value = getattr(action, "value", {}) or {}
 
+        # --- Exec approval button intercept ---
+        hermes_action = action_value.get("hermes_action") if isinstance(action_value, dict) else None
+        if hermes_action:
+            approval_id = action_value.get("approval_id")
+            state = self._approval_state.pop(approval_id, None)
+            if not state:
+                logger.debug("[Feishu] Approval %s already resolved or unknown", approval_id)
+                return
+
+            choice_map = {
+                "approve_once": "once",
+                "approve_session": "session",
+                "approve_always": "always",
+                "deny": "deny",
+            }
+            choice = choice_map.get(hermes_action, "deny")
+
+            label_map = {
+                "once": "Approved once",
+                "session": "Approved for session",
+                "always": "Approved permanently",
+                "deny": "Denied",
+            }
+            label = label_map.get(choice, "Resolved")
+
+            # Resolve sender name for the status card
+            sender_id = SimpleNamespace(open_id=open_id, user_id=None, union_id=None)
+            sender_profile = await self._resolve_sender_profile(sender_id)
+            user_name = sender_profile.get("user_name") or open_id
+
+            # Resolve the approval — unblocks the agent thread
+            try:
+                from tools.approval import resolve_gateway_approval
+                count = resolve_gateway_approval(state["session_key"], choice)
+                logger.info(
+                    "Feishu button resolved %d approval(s) for session %s (choice=%s, user=%s)",
+                    count, state["session_key"], choice, user_name,
+                )
+            except Exception as exc:
+                logger.error("Failed to resolve gateway approval from Feishu button: %s", exc)
+
+            # Update the card to show the decision
+            await self._update_approval_card(state.get("message_id", ""), label, user_name, choice)
+            return
+
         synthetic_text = f"/card {action_tag}"
         if action_value:
             try:
@@ -2675,10 +2478,8 @@ class FeishuAdapter(BasePlatformAdapter):
     async def _enqueue_text_event(self, event: MessageEvent) -> None:
         """Debounce rapid Feishu text bursts into a single MessageEvent."""
         key = self._text_batch_key(event)
-        chunk_len = len(event.text or "")
         existing = self._pending_text_batches.get(key)
         if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             self._pending_text_batches[key] = event
             self._pending_text_batch_counts[key] = 1
             self._schedule_text_batch_flush(key)
@@ -2703,7 +2504,6 @@ class FeishuAdapter(BasePlatformAdapter):
             return
 
         existing.text = next_text
-        existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
         existing.timestamp = event.timestamp
         if event.message_id:
             existing.message_id = event.message_id
@@ -2730,22 +2530,10 @@ class FeishuAdapter(BasePlatformAdapter):
         task_map[key] = asyncio.create_task(flush_fn(key))
 
     async def _flush_text_batch(self, key: str) -> None:
-        """Flush a pending text batch after the quiet period.
-
-        Uses a longer delay when the latest chunk is near Feishu's ~4096-char
-        split point, since a continuation chunk is almost certain.
-        """
+        """Flush a pending text batch after the quiet period."""
         current_task = asyncio.current_task()
         try:
-            # Adaptive delay: if the latest chunk is near the split threshold,
-            # a continuation is almost certain — wait longer.
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
+            await asyncio.sleep(self._text_batch_delay_seconds)
             await self._flush_text_batch_now(key)
         finally:
             if self._pending_text_batch_tasks.get(key) is current_task:
@@ -2850,6 +2638,12 @@ class FeishuAdapter(BasePlatformAdapter):
             return self._resolve_media_message_type(media_types[0] if media_types else "", default=MessageType.DOCUMENT)
         return MessageType.TEXT
 
+    def _normalize_inbound_text(self, text: str) -> str:
+        """Strip Feishu mention placeholders from inbound text."""
+        text = _MENTION_RE.sub(" ", text or "")
+        text = _MULTISPACE_RE.sub(" ", text)
+        return text.strip()
+
     async def _maybe_extract_text_document(self, cached_path: str, media_type: str) -> str:
         if not cached_path or not media_type.startswith("text/"):
             return ""
@@ -3067,19 +2861,6 @@ class FeishuAdapter(BasePlatformAdapter):
             "user_id_alt": union_id,
         }
 
-    def _get_cached_sender_name(self, sender_id: Optional[str]) -> Optional[str]:
-        """Return a cached sender name only while its TTL is still valid."""
-        if not sender_id:
-            return None
-        cached = self._sender_name_cache.get(sender_id)
-        if cached is None:
-            return None
-        name, expire_at = cached
-        if time.time() < expire_at:
-            return name
-        self._sender_name_cache.pop(sender_id, None)
-        return None
-
     async def _resolve_sender_name_from_api(self, sender_id: Optional[str]) -> Optional[str]:
         """Fetch the sender's display name from the Feishu contact API with a 10-minute cache.
 
@@ -3092,9 +2873,11 @@ class FeishuAdapter(BasePlatformAdapter):
         if not trimmed:
             return None
         now = time.time()
-        cached_name = self._get_cached_sender_name(trimmed)
-        if cached_name is not None:
-            return cached_name
+        cached = self._sender_name_cache.get(trimmed)
+        if cached is not None:
+            name, expire_at = cached
+            if now < expire_at:
+                return name
         try:
             from lark_oapi.api.contact.v3 import GetUserRequest  # lazy import
             if trimmed.startswith("ou_"):
@@ -3804,328 +3587,3 @@ class FeishuAdapter(BasePlatformAdapter):
             return _FEISHU_FILE_UPLOAD_TYPE, "file"
 
         return _FEISHU_FILE_UPLOAD_TYPE, "file"
-
-
-# =============================================================================
-# QR scan-to-create onboarding
-#
-# Device-code flow: user scans a QR code with Feishu/Lark mobile app and the
-# platform creates a fully configured bot application automatically.
-# Called by `hermes gateway setup` via _setup_feishu() in hermes_cli/gateway.py.
-# =============================================================================
-
-
-def _accounts_base_url(domain: str) -> str:
-    return _ONBOARD_ACCOUNTS_URLS.get(domain, _ONBOARD_ACCOUNTS_URLS["feishu"])
-
-
-def _onboard_open_base_url(domain: str) -> str:
-    return _ONBOARD_OPEN_URLS.get(domain, _ONBOARD_OPEN_URLS["feishu"])
-
-
-def _post_registration(base_url: str, body: Dict[str, str]) -> dict:
-    """POST form-encoded data to the registration endpoint, return parsed JSON.
-
-    The registration endpoint returns JSON even on 4xx (e.g. poll returns
-    authorization_pending as a 400). We always parse the body regardless of
-    HTTP status.
-    """
-    url = f"{base_url}{_REGISTRATION_PATH}"
-    data = urlencode(body).encode("utf-8")
-    req = Request(url, data=data, headers={"Content-Type": "application/x-www-form-urlencoded"})
-    try:
-        with urlopen(req, timeout=_ONBOARD_REQUEST_TIMEOUT_S) as resp:
-            return json.loads(resp.read().decode("utf-8"))
-    except HTTPError as exc:
-        body_bytes = exc.read()
-        if body_bytes:
-            try:
-                return json.loads(body_bytes.decode("utf-8"))
-            except (ValueError, json.JSONDecodeError):
-                raise exc from None
-        raise
-
-
-def _init_registration(domain: str = "feishu") -> None:
-    """Verify the environment supports client_secret auth.
-
-    Raises RuntimeError if not supported.
-    """
-    base_url = _accounts_base_url(domain)
-    res = _post_registration(base_url, {"action": "init"})
-    methods = res.get("supported_auth_methods") or []
-    if "client_secret" not in methods:
-        raise RuntimeError(
-            f"Feishu / Lark registration environment does not support client_secret auth. "
-            f"Supported: {methods}"
-        )
-
-
-def _begin_registration(domain: str = "feishu") -> dict:
-    """Start the device-code flow. Returns device_code, qr_url, user_code, interval, expire_in."""
-    base_url = _accounts_base_url(domain)
-    res = _post_registration(base_url, {
-        "action": "begin",
-        "archetype": "PersonalAgent",
-        "auth_method": "client_secret",
-        "request_user_info": "open_id",
-    })
-    device_code = res.get("device_code")
-    if not device_code:
-        raise RuntimeError("Feishu / Lark registration did not return a device_code")
-    qr_url = res.get("verification_uri_complete", "")
-    if "?" in qr_url:
-        qr_url += "&from=hermes&tp=hermes"
-    else:
-        qr_url += "?from=hermes&tp=hermes"
-    return {
-        "device_code": device_code,
-        "qr_url": qr_url,
-        "user_code": res.get("user_code", ""),
-        "interval": res.get("interval") or 5,
-        "expire_in": res.get("expire_in") or 600,
-    }
-
-
-def _poll_registration(
-    *,
-    device_code: str,
-    interval: int,
-    expire_in: int,
-    domain: str = "feishu",
-) -> Optional[dict]:
-    """Poll until the user scans the QR code, or timeout/denial.
-
-    Returns dict with app_id, app_secret, domain, open_id on success.
-    Returns None on failure.
-    """
-    deadline = time.time() + expire_in
-    current_domain = domain
-    domain_switched = False
-    poll_count = 0
-
-    while time.time() < deadline:
-        base_url = _accounts_base_url(current_domain)
-        try:
-            res = _post_registration(base_url, {
-                "action": "poll",
-                "device_code": device_code,
-                "tp": "ob_app",
-            })
-        except (URLError, OSError, json.JSONDecodeError):
-            time.sleep(interval)
-            continue
-
-        poll_count += 1
-        if poll_count == 1:
-            print("  Fetching configuration results...", end="", flush=True)
-        elif poll_count % 6 == 0:
-            print(".", end="", flush=True)
-
-        # Domain auto-detection
-        user_info = res.get("user_info") or {}
-        tenant_brand = user_info.get("tenant_brand")
-        if tenant_brand == "lark" and not domain_switched:
-            current_domain = "lark"
-            domain_switched = True
-            # Fall through — server may return credentials in this same response.
-
-        # Success
-        if res.get("client_id") and res.get("client_secret"):
-            if poll_count > 0:
-                print()  # newline after "Fetching configuration results..." dots
-            return {
-                "app_id": res["client_id"],
-                "app_secret": res["client_secret"],
-                "domain": current_domain,
-                "open_id": user_info.get("open_id"),
-            }
-
-        # Terminal errors
-        error = res.get("error", "")
-        if error in ("access_denied", "expired_token"):
-            if poll_count > 0:
-                print()
-            logger.warning("[Feishu onboard] Registration %s", error)
-            return None
-
-        # authorization_pending or unknown — keep polling
-        time.sleep(interval)
-
-    if poll_count > 0:
-        print()
-    logger.warning("[Feishu onboard] Poll timed out after %ds", expire_in)
-    return None
-
-
-try:
-    import qrcode as _qrcode_mod
-except (ImportError, TypeError):
-    _qrcode_mod = None  # type: ignore[assignment]
-
-
-def _render_qr(url: str) -> bool:
-    """Try to render a QR code in the terminal. Returns True if successful."""
-    if _qrcode_mod is None:
-        return False
-    try:
-        qr = _qrcode_mod.QRCode()
-        qr.add_data(url)
-        qr.make(fit=True)
-        qr.print_ascii(invert=True)
-        return True
-    except Exception:
-        return False
-
-
-def probe_bot(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
-    """Verify bot connectivity via /open-apis/bot/v3/info.
-
-    Uses lark_oapi SDK when available, falls back to raw HTTP otherwise.
-    Returns {"bot_name": ..., "bot_open_id": ...} on success, None on failure.
-    """
-    if FEISHU_AVAILABLE:
-        return _probe_bot_sdk(app_id, app_secret, domain)
-    return _probe_bot_http(app_id, app_secret, domain)
-
-
-def _build_onboard_client(app_id: str, app_secret: str, domain: str) -> Any:
-    """Build a lark Client for the given credentials and domain."""
-    sdk_domain = LARK_DOMAIN if domain == "lark" else FEISHU_DOMAIN
-    return (
-        lark.Client.builder()
-        .app_id(app_id)
-        .app_secret(app_secret)
-        .domain(sdk_domain)
-        .log_level(lark.LogLevel.WARNING)
-        .build()
-    )
-
-
-def _parse_bot_response(data: dict) -> Optional[dict]:
-    """Extract bot_name and bot_open_id from a /bot/v3/info response."""
-    if data.get("code") != 0:
-        return None
-    bot = data.get("bot") or data.get("data", {}).get("bot") or {}
-    return {
-        "bot_name": bot.get("bot_name"),
-        "bot_open_id": bot.get("open_id"),
-    }
-
-
-def _probe_bot_sdk(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
-    """Probe bot info using lark_oapi SDK."""
-    try:
-        client = _build_onboard_client(app_id, app_secret, domain)
-        resp = client.request(
-            method="GET",
-            url="/open-apis/bot/v3/info",
-            body=None,
-            raw_response=True,
-        )
-        return _parse_bot_response(json.loads(resp.content))
-    except Exception as exc:
-        logger.debug("[Feishu onboard] SDK probe failed: %s", exc)
-        return None
-
-
-def _probe_bot_http(app_id: str, app_secret: str, domain: str) -> Optional[dict]:
-    """Fallback probe using raw HTTP (when lark_oapi is not installed)."""
-    base_url = _onboard_open_base_url(domain)
-    try:
-        token_data = json.dumps({"app_id": app_id, "app_secret": app_secret}).encode("utf-8")
-        token_req = Request(
-            f"{base_url}/open-apis/auth/v3/tenant_access_token/internal",
-            data=token_data,
-            headers={"Content-Type": "application/json"},
-        )
-        with urlopen(token_req, timeout=_ONBOARD_REQUEST_TIMEOUT_S) as resp:
-            token_res = json.loads(resp.read().decode("utf-8"))
-
-        access_token = token_res.get("tenant_access_token")
-        if not access_token:
-            return None
-
-        bot_req = Request(
-            f"{base_url}/open-apis/bot/v3/info",
-            headers={
-                "Authorization": f"Bearer {access_token}",
-                "Content-Type": "application/json",
-            },
-        )
-        with urlopen(bot_req, timeout=_ONBOARD_REQUEST_TIMEOUT_S) as resp:
-            bot_res = json.loads(resp.read().decode("utf-8"))
-
-        return _parse_bot_response(bot_res)
-    except (URLError, OSError, KeyError, json.JSONDecodeError) as exc:
-        logger.debug("[Feishu onboard] HTTP probe failed: %s", exc)
-        return None
-
-
-def qr_register(
-    *,
-    initial_domain: str = "feishu",
-    timeout_seconds: int = 600,
-) -> Optional[dict]:
-    """Run the Feishu / Lark scan-to-create QR registration flow.
-
-    Returns on success::
-
-        {
-            "app_id": str,
-            "app_secret": str,
-            "domain": "feishu" | "lark",
-            "open_id": str | None,
-            "bot_name": str | None,
-            "bot_open_id": str | None,
-        }
-
-    Returns None on expected failures (network, auth denied, timeout).
-    Unexpected errors (bugs, protocol regressions) propagate to the caller.
-    """
-    try:
-        return _qr_register_inner(initial_domain=initial_domain, timeout_seconds=timeout_seconds)
-    except (RuntimeError, URLError, OSError, json.JSONDecodeError) as exc:
-        logger.warning("[Feishu onboard] Registration failed: %s", exc)
-        return None
-
-
-def _qr_register_inner(
-    *,
-    initial_domain: str,
-    timeout_seconds: int,
-) -> Optional[dict]:
-    """Run init → begin → poll → probe. Raises on network/protocol errors."""
-    print("  Connecting to Feishu / Lark...", end="", flush=True)
-    _init_registration(initial_domain)
-    begin = _begin_registration(initial_domain)
-    print(" done.")
-
-    print()
-    qr_url = begin["qr_url"]
-    if _render_qr(qr_url):
-        print(f"\n  Scan the QR code above, or open this URL directly:\n  {qr_url}")
-    else:
-        print(f"  Open this URL in Feishu / Lark on your phone:\n\n  {qr_url}\n")
-        print("  Tip: pip install qrcode  to display a scannable QR code here next time")
-    print()
-
-    result = _poll_registration(
-        device_code=begin["device_code"],
-        interval=begin["interval"],
-        expire_in=min(begin["expire_in"], timeout_seconds),
-        domain=initial_domain,
-    )
-    if not result:
-        return None
-
-    # Probe bot — best-effort, don't fail the registration
-    bot_info = probe_bot(result["app_id"], result["app_secret"], result["domain"])
-    if bot_info:
-        result["bot_name"] = bot_info.get("bot_name")
-        result["bot_open_id"] = bot_info.get("bot_open_id")
-    else:
-        result["bot_name"] = None
-        result["bot_open_id"] = None
-
-    return result

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
@@ -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/signal.py

@@ -17,6 +17,7 @@ import json
 import logging
 import os
 import random
+import re
 import time
 from datetime import datetime, timezone
 from pathlib import Path
@@ -36,7 +37,6 @@ from gateway.platforms.base import (
     cache_document_from_bytes,
     cache_image_from_url,
 )
-from gateway.platforms.helpers import redact_phone
 
 logger = logging.getLogger(__name__)
 
@@ -51,10 +51,22 @@ SSE_RETRY_DELAY_MAX = 60.0
 HEALTH_CHECK_INTERVAL = 30.0  # seconds between health checks
 HEALTH_CHECK_STALE_THRESHOLD = 120.0  # seconds without SSE activity before concern
 
+# E.164 phone number pattern for redaction
+_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
 
+def _redact_phone(phone: str) -> str:
+    """Redact a phone number for logging: +15551234567 -> +155****4567."""
+    if not phone:
+        return "<none>"
+    if len(phone) <= 8:
+        return phone[:2] + "****" + phone[-2:] if len(phone) > 4 else "****"
+    return phone[:4] + "****" + phone[-4:]
+
 
 def _parse_comma_list(value: str) -> List[str]:
     """Split a comma-separated string into a list, stripping whitespace."""
@@ -172,8 +184,10 @@ class SignalAdapter(BasePlatformAdapter):
         self._recent_sent_timestamps: set = set()
         self._max_recent_timestamps = 50
 
+        self._phone_lock_identity: Optional[str] = None
+
         logger.info("Signal adapter initialized: url=%s account=%s groups=%s",
-                     self.http_url, redact_phone(self.account),
+                     self.http_url, _redact_phone(self.account),
                      "enabled" if self.group_allow_from else "disabled")
 
     # ------------------------------------------------------------------
@@ -188,7 +202,23 @@ class SignalAdapter(BasePlatformAdapter):
 
         # Acquire scoped lock to prevent duplicate Signal listeners for the same phone
         try:
-            if not self._acquire_platform_lock('signal-phone', self.account, 'Signal account'):
+            from gateway.status import acquire_scoped_lock
+
+            self._phone_lock_identity = self.account
+            acquired, existing = acquire_scoped_lock(
+                "signal-phone",
+                self._phone_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this Signal account"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second Signal listener."
+                )
+                logger.error("Signal: %s", message)
+                self._set_fatal_error("signal_phone_lock", message, retryable=False)
                 return False
         except Exception as e:
             logger.warning("Signal: Could not acquire phone lock (non-fatal): %s", e)
@@ -240,7 +270,13 @@ class SignalAdapter(BasePlatformAdapter):
             await self.client.aclose()
             self.client = None
 
-        self._release_platform_lock()
+        if self._phone_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("signal-phone", self._phone_lock_identity)
+            except Exception as e:
+                logger.warning("Signal: Error releasing phone lock: %s", e, exc_info=True)
+            self._phone_lock_identity = None
 
         logger.info("Signal: disconnected")
 
@@ -506,7 +542,7 @@ class SignalAdapter(BasePlatformAdapter):
         )
 
         logger.debug("Signal: message from %s in %s: %s",
-                      redact_phone(sender), chat_id[:20], (text or "")[:50])
+                      _redact_phone(sender), chat_id[:20], (text or "")[:50])
 
         await self.handle_message(event)
 
@@ -780,6 +816,21 @@ class SignalAdapter(BasePlatformAdapter):
     # Typing Indicators
     # ------------------------------------------------------------------
 
+    async def _start_typing_indicator(self, chat_id: str) -> None:
+        """Start a typing indicator loop for a chat."""
+        if chat_id in self._typing_tasks:
+            return  # Already running
+
+        async def _typing_loop():
+            try:
+                while True:
+                    await self.send_typing(chat_id)
+                    await asyncio.sleep(TYPING_INTERVAL)
+            except asyncio.CancelledError:
+                pass
+
+        self._typing_tasks[chat_id] = asyncio.create_task(_typing_loop())
+
     async def _stop_typing_indicator(self, chat_id: str) -> None:
         """Stop a typing indicator loop for a chat."""
         task = self._typing_tasks.pop(chat_id, None)

gateway/platforms/slack.py

@@ -14,7 +14,6 @@ import logging
 import os
 import re
 import time
-from dataclasses import dataclass, field
 from typing import Dict, Optional, Any, Tuple
 
 try:
@@ -33,14 +32,12 @@ from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
     SendResult,
     SUPPORTED_DOCUMENT_TYPES,
-    safe_url_for_log,
     cache_document_from_bytes,
 )
 
@@ -48,14 +45,6 @@ from gateway.platforms.base import (
 logger = logging.getLogger(__name__)
 
 
-@dataclass
-class _ThreadContextCache:
-    """Cache entry for fetched thread context."""
-    content: str
-    fetched_at: float = field(default_factory=time.monotonic)
-    message_count: int = 0
-
-
 def check_slack_requirements() -> bool:
     """Check if Slack dependencies are available."""
     return SLACK_AVAILABLE
@@ -90,9 +79,11 @@ class SlackAdapter(BasePlatformAdapter):
         self._team_clients: Dict[str, AsyncWebClient] = {}   # team_id → WebClient
         self._team_bot_user_ids: Dict[str, str] = {}          # team_id → bot_user_id
         self._channel_team: Dict[str, str] = {}                # channel_id → team_id
-        # Dedup cache: prevents duplicate bot responses when Socket Mode
-        # reconnects redeliver events.
-        self._dedup = MessageDeduplicator()
+        # Dedup cache: event_ts → timestamp.  Prevents duplicate bot
+        # responses when Socket Mode reconnects redeliver events.
+        self._seen_messages: Dict[str, float] = {}
+        self._SEEN_TTL = 300   # 5 minutes
+        self._SEEN_MAX = 2000  # prune threshold
         # Track pending approval message_ts → resolved flag to prevent
         # double-clicks on approval buttons.
         self._approval_resolved: Dict[str, bool] = {}
@@ -110,9 +101,6 @@ class SlackAdapter(BasePlatformAdapter):
         # session + memory scoping.
         self._assistant_threads: Dict[Tuple[str, str], Dict[str, str]] = {}
         self._ASSISTANT_THREADS_MAX = 5000
-        # Cache for _fetch_thread_context results: cache_key → _ThreadContextCache
-        self._thread_context_cache: Dict[str, _ThreadContextCache] = {}
-        self._THREAD_CACHE_TTL = 60.0
 
     async def connect(self) -> bool:
         """Connect to Slack via Socket Mode."""
@@ -151,7 +139,15 @@ class SlackAdapter(BasePlatformAdapter):
                 logger.warning("[Slack] Failed to read %s: %s", tokens_file, e)
 
         try:
-            if not self._acquire_platform_lock('slack-app-token', app_token, 'Slack app token'):
+            # Acquire scoped lock to prevent duplicate app token usage
+            from gateway.status import acquire_scoped_lock
+            self._token_lock_identity = app_token
+            acquired, existing = acquire_scoped_lock('slack-app-token', app_token, metadata={'platform': 'slack'})
+            if not acquired:
+                owner_pid = existing.get('pid') if isinstance(existing, dict) else None
+                message = f'Slack app token 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('slack_token_lock', message, retryable=False)
                 return False
 
             # First token is the primary — used for AsyncApp / Socket Mode
@@ -238,7 +234,14 @@ class SlackAdapter(BasePlatformAdapter):
                 logger.warning("[Slack] Error while closing Socket Mode handler: %s", e, exc_info=True)
         self._running = False
 
-        self._release_platform_lock()
+        # Release the token lock (use stored identity, not re-read env)
+        try:
+            from gateway.status import release_scoped_lock
+            if getattr(self, '_token_lock_identity', None):
+                release_scoped_lock('slack-app-token', self._token_lock_identity)
+                self._token_lock_identity = None
+        except Exception:
+            pass
 
         logger.info("[Slack] Disconnected")
 
@@ -278,7 +281,6 @@ class SlackAdapter(BasePlatformAdapter):
                 kwargs = {
                     "channel": chat_id,
                     "text": chunk,
-                    "mrkdwn": True,
                 }
                 if thread_ts:
                     kwargs["thread_ts"] = thread_ts
@@ -321,7 +323,9 @@ class SlackAdapter(BasePlatformAdapter):
         if not self._app:
             return SendResult(success=False, error="Not connected")
         try:
+            # Convert standard markdown → Slack mrkdwn
             formatted = self.format_message(content)
+
             await self._get_client(chat_id).chat_update(
                 channel=chat_id,
                 ts=message_id,
@@ -366,20 +370,6 @@ class SlackAdapter(BasePlatformAdapter):
             # in an assistant-enabled context. Falls back to reactions.
             logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
 
-    def _dm_top_level_threads_as_sessions(self) -> bool:
-        """Whether top-level Slack DMs get per-message session threads.
-
-        Defaults to ``True`` so each visible DM reply thread is isolated as its
-        own Hermes session — matching the per-thread behavior channels already
-        have.  Set ``platforms.slack.extra.dm_top_level_threads_as_sessions``
-        to ``false`` in config.yaml to revert to the legacy behavior where all
-        top-level DMs share one continuous session.
-        """
-        raw = self.config.extra.get("dm_top_level_threads_as_sessions")
-        if raw is None:
-            return True  # default: each DM thread is its own session
-        return str(raw).strip().lower() in ("1", "true", "yes", "on")
-
     def _resolve_thread_ts(
         self,
         reply_to: Optional[str] = None,
@@ -467,36 +457,13 @@ class SlackAdapter(BasePlatformAdapter):
         text = re.sub(r'(`[^`]+`)', lambda m: _ph(m.group(0)), text)
 
         # 3) Convert markdown links [text](url) → <url|text>
-        def _convert_markdown_link(m):
-            label = m.group(1)
-            url = m.group(2).strip()
-            if url.startswith('<') and url.endswith('>'):
-                url = url[1:-1].strip()
-            return _ph(f'<{url}|{label}>')
-
         text = re.sub(
-            r'\[([^\]]+)\]\(([^()]*(?:\([^()]*\)[^()]*)*)\)',
-            _convert_markdown_link,
+            r'\[([^\]]+)\]\(([^)]+)\)',
+            lambda m: _ph(f'<{m.group(2)}|{m.group(1)}>'),
             text,
         )
 
-        # 4) Protect existing Slack entities/manual links so escaping and later
-        #    formatting passes don't break them.
-        text = re.sub(
-            r'(<(?:[@#!]|(?:https?|mailto|tel):)[^>\n]+>)',
-            lambda m: _ph(m.group(1)),
-            text,
-        )
-
-        # 5) Protect blockquote markers before escaping
-        text = re.sub(r'^(>+\s)', lambda m: _ph(m.group(0)), text, flags=re.MULTILINE)
-
-        # 6) Escape Slack control characters in remaining plain text.
-        # Unescape first so already-escaped input doesn't get double-escaped.
-        text = text.replace('&amp;', '&').replace('&lt;', '<').replace('&gt;', '>')
-        text = text.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;')
-
-        # 7) Convert headers (## Title) → *Title* (bold)
+        # 4) Convert headers (## Title) → *Title* (bold)
         def _convert_header(m):
             inner = m.group(1).strip()
             # Strip redundant bold markers inside a header
@@ -507,39 +474,34 @@ class SlackAdapter(BasePlatformAdapter):
             r'^#{1,6}\s+(.+)$', _convert_header, text, flags=re.MULTILINE
         )
 
-        # 8) Convert bold+italic: ***text*** → *_text_* (Slack bold wrapping italic)
-        text = re.sub(
-            r'\*\*\*(.+?)\*\*\*',
-            lambda m: _ph(f'*_{m.group(1)}_*'),
-            text,
-        )
-
-        # 9) Convert bold: **text** → *text* (Slack bold)
+        # 5) Convert bold: **text** → *text* (Slack bold)
         text = re.sub(
             r'\*\*(.+?)\*\*',
             lambda m: _ph(f'*{m.group(1)}*'),
             text,
         )
 
-        # 10) Convert italic: _text_ stays as _text_ (already Slack italic)
-        #     Single *text* → _text_ (Slack italic)
+        # 6) Convert italic: _text_ stays as _text_ (already Slack italic)
+        #    Single *text* → _text_ (Slack italic)
         text = re.sub(
             r'(?<!\*)\*([^*\n]+)\*(?!\*)',
             lambda m: _ph(f'_{m.group(1)}_'),
             text,
         )
 
-        # 11) Convert strikethrough: ~~text~~ → ~text~
+        # 7) Convert strikethrough: ~~text~~ → ~text~
         text = re.sub(
             r'~~(.+?)~~',
             lambda m: _ph(f'~{m.group(1)}~'),
             text,
         )
 
-        # 12) Blockquotes: > prefix is already protected by step 5 above.
+        # 8) Convert blockquotes: > text → > text (same syntax, just ensure
+        #    no extra escaping happens to the > character)
+        # Slack uses the same > prefix, so this is a no-op for content.
 
-        # 13) Restore placeholders in reverse order
-        for key in reversed(placeholders):
+        # 9) Restore placeholders in reverse order
+        for key in reversed(list(placeholders.keys())):
             text = text.replace(key, placeholders[key])
 
         return text
@@ -655,19 +617,8 @@ class SlackAdapter(BasePlatformAdapter):
         try:
             import httpx
 
-            async def _ssrf_redirect_guard(response):
-                """Re-check redirect targets so public URLs cannot bounce into private IPs."""
-                if response.is_redirect and response.next_request:
-                    redirect_url = str(response.next_request.url)
-                    if not is_safe_url(redirect_url):
-                        raise ValueError("Blocked redirect to private/internal address")
-
             # Download the image first
-            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:
                 response = await client.get(image_url)
                 response.raise_for_status()
 
@@ -684,7 +635,7 @@ class SlackAdapter(BasePlatformAdapter):
         except Exception as e:  # pragma: no cover - defensive logging
             logger.warning(
                 "[Slack] Failed to upload image from URL %s, falling back to text: %s",
-                safe_url_for_log(image_url),
+                image_url,
                 e,
                 exc_info=True,
             )
@@ -951,29 +902,21 @@ class SlackAdapter(BasePlatformAdapter):
         """Handle an incoming Slack message event."""
         # Dedup: Slack Socket Mode can redeliver events after reconnects (#4777)
         event_ts = event.get("ts", "")
-        if event_ts and self._dedup.is_duplicate(event_ts):
-            return
+        if event_ts:
+            now = time.time()
+            if event_ts in self._seen_messages:
+                return
+            self._seen_messages[event_ts] = now
+            if len(self._seen_messages) > self._SEEN_MAX:
+                cutoff = now - self._SEEN_TTL
+                self._seen_messages = {
+                    k: v for k, v in self._seen_messages.items()
+                    if v > cutoff
+                }
 
-        # Bot message filtering (SLACK_ALLOW_BOTS / config allow_bots):
-        #   "none"     — ignore all bot messages (default, backward-compatible)
-        #   "mentions" — accept bot messages only when they @mention us
-        #   "all"      — accept all bot messages (except our own)
+        # Ignore bot messages (including our own)
         if event.get("bot_id") or event.get("subtype") == "bot_message":
-            allow_bots = self.config.extra.get("allow_bots", "")
-            if not allow_bots:
-                allow_bots = os.getenv("SLACK_ALLOW_BOTS", "none")
-            allow_bots = str(allow_bots).lower().strip()
-            if allow_bots == "none":
-                return
-            elif allow_bots == "mentions":
-                text_check = event.get("text", "")
-                if self._bot_user_id and f"<@{self._bot_user_id}>" not in text_check:
-                    return
-            # "all" falls through to process the message
-            # Always ignore our own messages to prevent echo loops
-            msg_user = event.get("user", "")
-            if msg_user and self._bot_user_id and msg_user == self._bot_user_id:
-                return
+            return
 
         # Ignore message edits and deletions
         subtype = event.get("subtype")
@@ -1005,25 +948,19 @@ class SlackAdapter(BasePlatformAdapter):
         channel_type = event.get("channel_type", "")
         if not channel_type and channel_id.startswith("D"):
             channel_type = "im"
-        is_dm = channel_type in ("im", "mpim")  # Both 1:1 and group DMs
+        is_dm = channel_type == "im"
 
         # Build thread_ts for session keying.
         # In channels: fall back to ts so each top-level @mention starts a
         #   new thread/session (the bot always replies in a thread).
-        # In DMs: fall back to ts so each top-level DM reply thread gets
-        #   its own session key (matching channel behavior). Set
-        #   dm_top_level_threads_as_sessions: false in config to revert to
-        #   legacy single-session-per-DM-channel behavior.
+        # In DMs: only use the real thread_ts — top-level DMs should share
+        #   one continuous session, threaded DMs get their own session.
         if is_dm:
-            thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")
-            if not thread_ts and self._dm_top_level_threads_as_sessions():
-                thread_ts = ts
+            thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")  # None for top-level DMs
         else:
             thread_ts = event.get("thread_ts") or ts  # ts fallback for channels
 
         # In channels, respond if:
-        #   0. Channel is in free_response_channels, OR require_mention is
-        #      disabled — always process regardless of mention.
         #   1. The bot is @mentioned in this message, OR
         #   2. The message is a reply in a thread the bot started/participated in, OR
         #   3. The message is in a thread where the bot was previously @mentioned, OR
@@ -1033,29 +970,24 @@ class SlackAdapter(BasePlatformAdapter):
         event_thread_ts = event.get("thread_ts")
         is_thread_reply = bool(event_thread_ts and event_thread_ts != ts)
 
-        if not is_dm and bot_uid:
-            if channel_id in self._slack_free_response_channels():
-                pass  # Free-response channel — always process
-            elif not self._slack_require_mention():
-                pass  # Mention requirement disabled globally for Slack
-            elif not is_mentioned:
-                reply_to_bot_thread = (
-                    is_thread_reply and event_thread_ts in self._bot_message_ts
+        if not is_dm and bot_uid and not is_mentioned:
+            reply_to_bot_thread = (
+                is_thread_reply and event_thread_ts in self._bot_message_ts
+            )
+            in_mentioned_thread = (
+                event_thread_ts is not None
+                and event_thread_ts in self._mentioned_threads
+            )
+            has_session = (
+                is_thread_reply
+                and self._has_active_session_for_thread(
+                    channel_id=channel_id,
+                    thread_ts=event_thread_ts,
+                    user_id=user_id,
                 )
-                in_mentioned_thread = (
-                    event_thread_ts is not None
-                    and event_thread_ts in self._mentioned_threads
-                )
-                has_session = (
-                    is_thread_reply
-                    and self._has_active_session_for_thread(
-                        channel_id=channel_id,
-                        thread_ts=event_thread_ts,
-                        user_id=user_id,
-                    )
-                )
-                if not reply_to_bot_thread and not in_mentioned_thread and not has_session:
-                    return
+            )
+            if not reply_to_bot_thread and not in_mentioned_thread and not has_session:
+                return
 
         if is_mentioned:
             # Strip the bot mention from the text
@@ -1185,12 +1117,6 @@ class SlackAdapter(BasePlatformAdapter):
             thread_id=thread_ts,
         )
 
-        # 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=text,
             message_type=msg_type,
@@ -1200,22 +1126,16 @@ class SlackAdapter(BasePlatformAdapter):
             media_urls=media_urls,
             media_types=media_types,
             reply_to_message_id=thread_ts if thread_ts != ts else None,
-            channel_prompt=_channel_prompt,
         )
 
-        # Only react when bot is directly addressed (DM or @mention).
-        # In listen-all channels (require_mention=false), reacting to every
-        # casual message would be noisy.
-        _should_react = is_dm or is_mentioned
-
-        if _should_react:
-            await self._add_reaction(channel_id, ts, "eyes")
+        # Add 👀 reaction to acknowledge receipt
+        await self._add_reaction(channel_id, ts, "eyes")
 
         await self.handle_message(msg_event)
 
-        if _should_react:
-            await self._remove_reaction(channel_id, ts, "eyes")
-            await self._add_reaction(channel_id, ts, "white_check_mark")
+        # Replace 👀 with ✅ when done
+        await self._remove_reaction(channel_id, ts, "eyes")
+        await self._add_reaction(channel_id, ts, "white_check_mark")
 
     # ----- Approval button support (Block Kit) -----
 
@@ -1309,20 +1229,6 @@ class SlackAdapter(BasePlatformAdapter):
         msg_ts = message.get("ts", "")
         channel_id = body.get("channel", {}).get("id", "")
         user_name = body.get("user", {}).get("name", "unknown")
-        user_id = body.get("user", {}).get("id", "")
-
-        # Only authorized users may click approval buttons.  Button clicks
-        # bypass the normal message auth flow in gateway/run.py, so we must
-        # check here as well.
-        allowed_csv = os.getenv("SLACK_ALLOWED_USERS", "").strip()
-        if allowed_csv:
-            allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
-            if "*" not in allowed_ids and user_id not in allowed_ids:
-                logger.warning(
-                    "[Slack] Unauthorized approval click by %s (%s) — ignoring",
-                    user_name, user_id,
-                )
-                return
 
         # Map action_id to approval choice
         choice_map = {
@@ -1333,9 +1239,10 @@ class SlackAdapter(BasePlatformAdapter):
         }
         choice = choice_map.get(action_id, "deny")
 
-        # Prevent double-clicks — atomic pop; first caller gets False, others get True (default)
-        if self._approval_resolved.pop(msg_ts, True):
+        # Prevent double-clicks
+        if self._approval_resolved.get(msg_ts, False):
             return
+        self._approval_resolved[msg_ts] = True
 
         # Update the message to show the decision and remove buttons
         label_map = {
@@ -1390,7 +1297,8 @@ class SlackAdapter(BasePlatformAdapter):
         except Exception as exc:
             logger.error("Failed to resolve gateway approval from Slack button: %s", exc)
 
-        # (approval state already consumed by atomic pop above)
+        # Clean up stale approval state
+        self._approval_resolved.pop(msg_ts, None)
 
     # ----- Thread context fetching -----
 
@@ -1401,104 +1309,57 @@ class SlackAdapter(BasePlatformAdapter):
         """Fetch recent thread messages to provide context when the bot is
         mentioned mid-thread for the first time.
 
-        This method is only called when there is NO active session for the
-        thread (guarded at the call site by _has_active_session_for_thread).
-        That guard ensures thread messages are prepended only on the very
-        first turn — after that the session history already holds them, so
-        there is no duplication across subsequent turns.
-
-        Results are cached for _THREAD_CACHE_TTL seconds per thread to avoid
-        hammering conversations.replies (Tier 3, ~50 req/min).
-
-        Returns a formatted string with prior thread history, or empty string
-        on failure or if the thread has no prior messages.
+        Returns a formatted string with thread history, or empty string on
+        failure or if the thread is empty (just the parent message).
         """
-        cache_key = f"{channel_id}:{thread_ts}"
-        now = time.monotonic()
-        cached = self._thread_context_cache.get(cache_key)
-        if cached and (now - cached.fetched_at) < self._THREAD_CACHE_TTL:
-            return cached.content
-
         try:
             client = self._get_client(channel_id)
-
-            # Retry with exponential backoff for Tier-3 rate limits (429).
-            result = None
-            for attempt in range(3):
-                try:
-                    result = await client.conversations_replies(
-                        channel=channel_id,
-                        ts=thread_ts,
-                        limit=limit + 1,  # +1 because it includes the current message
-                        inclusive=True,
-                    )
-                    break
-                except Exception as exc:
-                    # Check for rate-limit error from slack_sdk
-                    err_str = str(exc).lower()
-                    is_rate_limit = (
-                        "ratelimited" in err_str
-                        or "429" in err_str
-                        or "rate_limited" in err_str
-                    )
-                    if is_rate_limit and attempt < 2:
-                        retry_after = 1.0 * (2 ** attempt)  # 1s, 2s
-                        logger.warning(
-                            "[Slack] conversations.replies rate limited; retrying in %.1fs (attempt %d/3)",
-                            retry_after, attempt + 1,
-                        )
-                        await asyncio.sleep(retry_after)
-                        continue
-                    raise
-
-            if result is None:
-                return ""
-
+            result = await client.conversations_replies(
+                channel=channel_id,
+                ts=thread_ts,
+                limit=limit + 1,  # +1 because it includes the current message
+                inclusive=True,
+            )
             messages = result.get("messages", [])
             if not messages:
                 return ""
 
-            bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
             context_parts = []
             for msg in messages:
                 msg_ts = msg.get("ts", "")
-                # Exclude the current triggering message — it will be delivered
-                # as the user message itself, so including it here would duplicate it.
+                # Skip the current message (the one that triggered this fetch)
                 if msg_ts == current_ts:
                     continue
-                # Exclude our own bot messages to avoid circular context.
+                # Skip bot messages from ourselves
                 if msg.get("bot_id") or msg.get("subtype") == "bot_message":
                     continue
 
+                msg_user = msg.get("user", "unknown")
                 msg_text = msg.get("text", "").strip()
                 if not msg_text:
                     continue
 
                 # Strip bot mentions from context messages
+                bot_uid = self._team_bot_user_ids.get(team_id, self._bot_user_id)
                 if bot_uid:
                     msg_text = msg_text.replace(f"<@{bot_uid}>", "").strip()
 
-                msg_user = msg.get("user", "unknown")
+                # Mark the thread parent
                 is_parent = msg_ts == thread_ts
                 prefix = "[thread parent] " if is_parent else ""
+
+                # Resolve user name (cached)
                 name = await self._resolve_user_name(msg_user, chat_id=channel_id)
                 context_parts.append(f"{prefix}{name}: {msg_text}")
 
-            content = ""
-            if context_parts:
-                content = (
-                    "[Thread context — prior messages in this thread (not yet in conversation history):]\n"
-                    + "\n".join(context_parts)
-                    + "\n[End of thread context]\n\n"
-                )
+            if not context_parts:
+                return ""
 
-            self._thread_context_cache[cache_key] = _ThreadContextCache(
-                content=content,
-                fetched_at=now,
-                message_count=len(context_parts),
+            return (
+                "[Thread context — previous messages in this thread:]\n"
+                + "\n".join(context_parts)
+                + "\n[End of thread context]\n\n"
             )
-            return content
-
         except Exception as e:
             logger.warning("[Slack] Failed to fetch thread context: %s", e)
             return ""
@@ -1608,18 +1469,6 @@ class SlackAdapter(BasePlatformAdapter):
                     )
                     response.raise_for_status()
 
-                    # Slack may return an HTML sign-in/redirect page
-                    # instead of actual media bytes (e.g. expired token,
-                    # restricted file access).  Detect this early so we
-                    # don't cache bogus data and confuse downstream tools.
-                    ct = response.headers.get("content-type", "")
-                    if "text/html" in ct:
-                        raise ValueError(
-                            "Slack returned HTML instead of media "
-                            f"(content-type: {ct}); "
-                            "check bot token scopes and file permissions"
-                        )
-
                     if audio:
                         from gateway.platforms.base import cache_audio_from_bytes
                         return cache_audio_from_bytes(response.content, ext)
@@ -1666,30 +1515,3 @@ class SlackAdapter(BasePlatformAdapter):
                         continue
                     raise
         raise last_exc
-
-    # ── Channel mention gating ─────────────────────────────────────────────
-
-    def _slack_require_mention(self) -> bool:
-        """Return whether channel messages require an explicit bot mention.
-
-        Uses explicit-false parsing (like Discord/Matrix) rather than
-        truthy parsing, since the safe default is True (gating on).
-        Unrecognised or empty values keep gating enabled.
-        """
-        configured = self.config.extra.get("require_mention")
-        if configured is not None:
-            if isinstance(configured, str):
-                return configured.lower() not in ("false", "0", "no", "off")
-            return bool(configured)
-        return os.getenv("SLACK_REQUIRE_MENTION", "true").lower() not in ("false", "0", "no", "off")
-
-    def _slack_free_response_channels(self) -> set:
-        """Return channel IDs where no @mention is required."""
-        raw = self.config.extra.get("free_response_channels")
-        if raw is None:
-            raw = os.getenv("SLACK_FREE_RESPONSE_CHANNELS", "")
-        if isinstance(raw, list):
-            return {str(part).strip() for part in raw if str(part).strip()}
-        if isinstance(raw, str) and raw.strip():
-            return {part.strip() for part in raw.split(",") if part.strip()}
-        return set()

gateway/platforms/sms.py

@@ -10,9 +10,6 @@ Shares credentials with the optional telephony skill — same env vars:
 
 Gateway-specific env vars:
   - SMS_WEBHOOK_PORT     (default 8080)
-  - SMS_WEBHOOK_HOST     (default 0.0.0.0)
-  - SMS_WEBHOOK_URL      (public URL for Twilio signature validation — required)
-  - SMS_INSECURE_NO_SIGNATURE  (true to disable signature validation — dev only)
   - SMS_ALLOWED_USERS    (comma-separated E.164 phone numbers)
   - SMS_ALLOW_ALL_USERS  (true/false)
   - SMS_HOME_CHANNEL     (phone number for cron delivery)
@@ -20,10 +17,9 @@ Gateway-specific env vars:
 
 import asyncio
 import base64
-import hashlib
-import hmac
 import logging
 import os
+import re
 import urllib.parse
 from typing import Any, Dict, Optional
 
@@ -34,14 +30,24 @@ from gateway.platforms.base import (
     MessageType,
     SendResult,
 )
-from gateway.platforms.helpers import redact_phone, strip_markdown
 
 logger = logging.getLogger(__name__)
 
 TWILIO_API_BASE = "https://api.twilio.com/2010-04-01/Accounts"
 MAX_SMS_LENGTH = 1600  # ~10 SMS segments
 DEFAULT_WEBHOOK_PORT = 8080
-DEFAULT_WEBHOOK_HOST = "0.0.0.0"
+
+# E.164 phone number pattern for redaction
+_PHONE_RE = re.compile(r"\+[1-9]\d{6,14}")
+
+
+def _redact_phone(phone: str) -> str:
+    """Redact a phone number for logging: +15551234567 -> +1555***4567."""
+    if not phone:
+        return "<none>"
+    if len(phone) <= 8:
+        return phone[:2] + "***" + phone[-2:] if len(phone) > 4 else "****"
+    return phone[:5] + "***" + phone[-4:]
 
 
 def check_sms_requirements() -> bool:
@@ -71,8 +77,6 @@ class SmsAdapter(BasePlatformAdapter):
         self._webhook_port: int = int(
             os.getenv("SMS_WEBHOOK_PORT", str(DEFAULT_WEBHOOK_PORT))
         )
-        self._webhook_host: str = os.getenv("SMS_WEBHOOK_HOST", DEFAULT_WEBHOOK_HOST)
-        self._webhook_url: str = os.getenv("SMS_WEBHOOK_URL", "").strip()
         self._runner = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
 
@@ -94,33 +98,13 @@ class SmsAdapter(BasePlatformAdapter):
             logger.error("[sms] TWILIO_PHONE_NUMBER not set — cannot send replies")
             return False
 
-        insecure_no_sig = os.getenv("SMS_INSECURE_NO_SIGNATURE", "").lower() == "true"
-
-        if not self._webhook_url and not insecure_no_sig:
-            logger.error(
-                "[sms] Refusing to start: SMS_WEBHOOK_URL is required for Twilio "
-                "signature validation. Set it to the public URL configured in your "
-                "Twilio console (e.g. https://example.com/webhooks/twilio). "
-                "For local development without validation, set "
-                "SMS_INSECURE_NO_SIGNATURE=true (NOT recommended for production).",
-            )
-            return False
-
-        if insecure_no_sig and not self._webhook_url:
-            logger.warning(
-                "[sms] SMS_INSECURE_NO_SIGNATURE=true — Twilio signature validation "
-                "is DISABLED. Any client that can reach port %d can inject messages. "
-                "Do NOT use this in production.",
-                self._webhook_port,
-            )
-
         app = web.Application()
         app.router.add_post("/webhooks/twilio", self._handle_webhook)
         app.router.add_get("/health", lambda _: web.Response(text="ok"))
 
         self._runner = web.AppRunner(app)
         await self._runner.setup()
-        site = web.TCPSite(self._runner, self._webhook_host, self._webhook_port)
+        site = web.TCPSite(self._runner, "0.0.0.0", self._webhook_port)
         await site.start()
         self._http_session = aiohttp.ClientSession(
             timeout=aiohttp.ClientTimeout(total=30),
@@ -128,10 +112,9 @@ class SmsAdapter(BasePlatformAdapter):
         self._running = True
 
         logger.info(
-            "[sms] Twilio webhook server listening on %s:%d, from: %s",
-            self._webhook_host,
+            "[sms] Twilio webhook server listening on port %d, from: %s",
             self._webhook_port,
-            redact_phone(self._from_number),
+            _redact_phone(self._from_number),
         )
         return True
 
@@ -180,7 +163,7 @@ class SmsAdapter(BasePlatformAdapter):
                             error_msg = body.get("message", str(body))
                             logger.error(
                                 "[sms] send failed to %s: %s %s",
-                                redact_phone(chat_id),
+                                _redact_phone(chat_id),
                                 resp.status,
                                 error_msg,
                             )
@@ -191,7 +174,7 @@ class SmsAdapter(BasePlatformAdapter):
                         msg_sid = body.get("sid", "")
                         last_result = SendResult(success=True, message_id=msg_sid)
                 except Exception as e:
-                    logger.error("[sms] send error to %s: %s", redact_phone(chat_id), e)
+                    logger.error("[sms] send error to %s: %s", _redact_phone(chat_id), e)
                     return SendResult(success=False, error=str(e))
         finally:
             # Close session only if we created a fallback (no persistent session)
@@ -209,75 +192,16 @@ class SmsAdapter(BasePlatformAdapter):
 
     def format_message(self, content: str) -> str:
         """Strip markdown — SMS renders it as literal characters."""
-        return strip_markdown(content)
-
-    # ------------------------------------------------------------------
-    # Twilio signature validation
-    # ------------------------------------------------------------------
-
-    def _validate_twilio_signature(
-        self, url: str, post_params: dict, signature: str,
-    ) -> bool:
-        """Validate ``X-Twilio-Signature`` header (HMAC-SHA1, base64).
-
-        Tries both with and without the default port for the URL scheme,
-        since Twilio may sign with either variant.
-
-        Algorithm: https://www.twilio.com/docs/usage/security#validating-requests
-        """
-        if self._check_signature(url, post_params, signature):
-            return True
-
-        variant = self._port_variant_url(url)
-        if variant and self._check_signature(variant, post_params, signature):
-            return True
-
-        return False
-
-    def _check_signature(
-        self, url: str, post_params: dict, signature: str,
-    ) -> bool:
-        """Compute and compare a single Twilio signature."""
-        data_to_sign = url
-        for key in sorted(post_params.keys()):
-            data_to_sign += key + post_params[key]
-        mac = hmac.new(
-            self._auth_token.encode("utf-8"),
-            data_to_sign.encode("utf-8"),
-            hashlib.sha1,
-        )
-        computed = base64.b64encode(mac.digest()).decode("utf-8")
-        return hmac.compare_digest(computed, signature)
-
-    @staticmethod
-    def _port_variant_url(url: str) -> str | None:
-        """Return the URL with the default port toggled, or None.
-
-        Only toggles default ports (443 for https, 80 for http).
-        Non-standard ports are never modified.
-        """
-        parsed = urllib.parse.urlparse(url)
-        default_ports = {"https": 443, "http": 80}
-        default_port = default_ports.get(parsed.scheme)
-        if default_port is None:
-            return None
-
-        if parsed.port == default_port:
-            # Has explicit default port → strip it
-            return urllib.parse.urlunparse(
-                (parsed.scheme, parsed.hostname, parsed.path,
-                 parsed.params, parsed.query, parsed.fragment)
-            )
-        elif parsed.port is None:
-            # No port → add default
-            netloc = f"{parsed.hostname}:{default_port}"
-            return urllib.parse.urlunparse(
-                (parsed.scheme, netloc, parsed.path,
-                 parsed.params, parsed.query, parsed.fragment)
-            )
-
-        # Non-standard port — no variant
-        return None
+        content = re.sub(r"\*\*(.+?)\*\*", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"\*(.+?)\*", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"__(.+?)__", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"_(.+?)_", r"\1", content, flags=re.DOTALL)
+        content = re.sub(r"```[a-z]*\n?", "", content)
+        content = re.sub(r"`(.+?)`", r"\1", content)
+        content = re.sub(r"^#{1,6}\s+", "", content, flags=re.MULTILINE)
+        content = re.sub(r"\[([^\]]+)\]\([^\)]+\)", r"\1", content)
+        content = re.sub(r"\n{3,}", "\n\n", content)
+        return content.strip()
 
     # ------------------------------------------------------------------
     # Twilio webhook handler
@@ -289,7 +213,7 @@ class SmsAdapter(BasePlatformAdapter):
         try:
             raw = await request.read()
             # Twilio sends form-encoded data, not JSON
-            form = urllib.parse.parse_qs(raw.decode("utf-8"), keep_blank_values=True)
+            form = urllib.parse.parse_qs(raw.decode("utf-8"))
         except Exception as e:
             logger.error("[sms] webhook parse error: %s", e)
             return web.Response(
@@ -298,27 +222,6 @@ class SmsAdapter(BasePlatformAdapter):
                 status=400,
             )
 
-        # Validate Twilio request signature when SMS_WEBHOOK_URL is configured
-        if self._webhook_url:
-            twilio_sig = request.headers.get("X-Twilio-Signature", "")
-            if not twilio_sig:
-                logger.warning("[sms] Rejected: missing X-Twilio-Signature header")
-                return web.Response(
-                    text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
-                    content_type="application/xml",
-                    status=403,
-                )
-            flat_params = {k: v[0] for k, v in form.items() if v}
-            if not self._validate_twilio_signature(
-                self._webhook_url, flat_params, twilio_sig
-            ):
-                logger.warning("[sms] Rejected: invalid Twilio signature")
-                return web.Response(
-                    text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
-                    content_type="application/xml",
-                    status=403,
-                )
-
         # Extract fields (parse_qs returns lists)
         from_number = (form.get("From", [""]))[0].strip()
         to_number = (form.get("To", [""]))[0].strip()
@@ -333,7 +236,7 @@ class SmsAdapter(BasePlatformAdapter):
 
         # Ignore messages from our own number (echo prevention)
         if from_number == self._from_number:
-            logger.debug("[sms] ignoring echo from own number %s", redact_phone(from_number))
+            logger.debug("[sms] ignoring echo from own number %s", _redact_phone(from_number))
             return web.Response(
                 text='<?xml version="1.0" encoding="UTF-8"?><Response></Response>',
                 content_type="application/xml",
@@ -341,8 +244,8 @@ class SmsAdapter(BasePlatformAdapter):
 
         logger.info(
             "[sms] inbound from %s -> %s: %s",
-            redact_phone(from_number),
-            redact_phone(to_number),
+            _redact_phone(from_number),
+            _redact_phone(to_number),
             text[:80],
         )
 

gateway/platforms/telegram.py

@@ -11,7 +11,6 @@ import asyncio
 import json
 import logging
 import os
-import html as _html
 import re
 from typing import Dict, List, Optional, Any
 
@@ -19,10 +18,6 @@ logger = logging.getLogger(__name__)
 
 try:
     from telegram import Update, Bot, Message, InlineKeyboardButton, InlineKeyboardMarkup
-    try:
-        from telegram import LinkPreviewOptions
-    except ImportError:
-        LinkPreviewOptions = None
     from telegram.ext import (
         Application,
         CommandHandler,
@@ -41,7 +36,6 @@ except ImportError:
     Message = Any
     InlineKeyboardButton = Any
     InlineKeyboardMarkup = Any
-    LinkPreviewOptions = None
     Application = Any
     CommandHandler = Any
     CallbackQueryHandler = Any
@@ -66,15 +60,11 @@ from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
     MessageType,
-    ProcessingOutcome,
     SendResult,
     cache_image_from_bytes,
     cache_audio_from_bytes,
     cache_document_from_bytes,
-    resolve_proxy_url,
     SUPPORTED_DOCUMENT_TYPES,
-    utf16_len,
-    _prefix_within_utf16_limit,
 )
 from gateway.platforms.telegram_network import (
     TelegramFallbackTransport,
@@ -131,11 +121,7 @@ class TelegramAdapter(BasePlatformAdapter):
     
     # Telegram message limits
     MAX_MESSAGE_LENGTH = 4096
-    # Threshold for detecting Telegram client-side message splits.
-    # When a chunk is near this limit, a continuation is almost certain.
-    _SPLIT_THRESHOLD = 4000
     MEDIA_GROUP_WAIT_SECONDS = 0.8
-    _GENERAL_TOPIC_THREAD_ID = "1"
     
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.TELEGRAM)
@@ -144,7 +130,6 @@ class TelegramAdapter(BasePlatformAdapter):
         self._webhook_mode: bool = False
         self._mention_patterns = self._compile_mention_patterns()
         self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
-        self._disable_link_previews: bool = self._coerce_bool_extra("disable_link_previews", False)
         # Buffer rapid/album photo updates so Telegram image bursts are handled
         # as a single MessageEvent instead of self-interrupting multiple turns.
         self._media_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_MEDIA_BATCH_DELAY_SECONDS", "0.8"))
@@ -155,9 +140,9 @@ class TelegramAdapter(BasePlatformAdapter):
         # Buffer rapid text messages so Telegram client-side splits of long
         # messages are aggregated into a single MessageEvent.
         self._text_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
         self._pending_text_batches: Dict[str, MessageEvent] = {}
         self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
+        self._token_lock_identity: Optional[str] = None
         self._polling_error_task: Optional[asyncio.Task] = None
         self._polling_conflict_count: int = 0
         self._polling_network_error_count: int = 0
@@ -171,38 +156,6 @@ class TelegramAdapter(BasePlatformAdapter):
         # Approval button state: message_id → session_key
         self._approval_state: Dict[int, str] = {}
 
-    @staticmethod
-    def _is_callback_user_authorized(user_id: str) -> bool:
-        """Return whether a Telegram inline-button caller may perform gated actions."""
-        allowed_csv = os.getenv("TELEGRAM_ALLOWED_USERS", "").strip()
-        if not allowed_csv:
-            return True
-        allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
-        return "*" in allowed_ids or user_id in allowed_ids
-
-    @classmethod
-    def _metadata_thread_id(cls, metadata: Optional[Dict[str, Any]]) -> Optional[str]:
-        if not metadata:
-            return None
-        thread_id = metadata.get("thread_id") or metadata.get("message_thread_id")
-        return str(thread_id) if thread_id is not None else None
-
-    @classmethod
-    def _message_thread_id_for_send(cls, thread_id: Optional[str]) -> Optional[int]:
-        if not thread_id or str(thread_id) == cls._GENERAL_TOPIC_THREAD_ID:
-            return None
-        return int(thread_id)
-
-    @classmethod
-    def _message_thread_id_for_typing(cls, thread_id: Optional[str]) -> Optional[int]:
-        if not thread_id:
-            return None
-        return int(thread_id)
-
-    @staticmethod
-    def _is_thread_not_found_error(error: Exception) -> bool:
-        return "thread not found" in str(error).lower()
-
     def _fallback_ips(self) -> list[str]:
         """Return validated fallback IPs from config (populated by _apply_env_overrides)."""
         configured = self.config.extra.get("fallback_ips", []) if getattr(self.config, "extra", None) else []
@@ -233,26 +186,6 @@ class TelegramAdapter(BasePlatformAdapter):
             pass
         return isinstance(error, OSError)
 
-    def _coerce_bool_extra(self, key: str, default: bool = False) -> bool:
-        value = self.config.extra.get(key) if getattr(self.config, "extra", None) else None
-        if value is None:
-            return default
-        if isinstance(value, str):
-            lowered = value.strip().lower()
-            if lowered in ("true", "1", "yes", "on"):
-                return True
-            if lowered in ("false", "0", "no", "off"):
-                return False
-            return default
-        return bool(value)
-
-    def _link_preview_kwargs(self) -> Dict[str, Any]:
-        if not getattr(self, "_disable_link_previews", False):
-            return {}
-        if LinkPreviewOptions is not None:
-            return {"link_preview_options": LinkPreviewOptions(is_disabled=True)}
-        return {"disable_web_page_preview": True}
-
     async def _handle_polling_network_error(self, error: Exception) -> None:
         """Reconnect polling after a transient network interruption.
 
@@ -362,11 +295,9 @@ class TelegramAdapter(BasePlatformAdapter):
 
         # Exhausted retries — fatal
         message = (
-            "Another process is already polling this Telegram bot token "
-            "(possibly OpenClaw or another Hermes instance). "
+            "Another Telegram bot poller is already using this token. "
             "Hermes stopped Telegram polling after %d retries. "
-            "Only one poller can run per token — stop the other process "
-            "and restart with 'hermes start'."
+            "Make sure only one gateway instance is running for this bot token."
             % MAX_CONFLICT_RETRIES
         )
         logger.error("[%s] %s Original error: %s", self.name, message, error)
@@ -561,47 +492,27 @@ class TelegramAdapter(BasePlatformAdapter):
             return False
         
         try:
-            if not self._acquire_platform_lock('telegram-bot-token', self.config.token, 'Telegram bot token'):
+            from gateway.status import acquire_scoped_lock
+
+            self._token_lock_identity = self.config.token
+            acquired, existing = acquire_scoped_lock(
+                "telegram-bot-token",
+                self._token_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this Telegram bot token"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second Telegram poller."
+                )
+                logger.error("[%s] %s", self.name, message)
+                self._set_fatal_error("telegram_token_lock", message, retryable=False)
                 return False
 
             # Build the application
             builder = Application.builder().token(self.config.token)
-            custom_base_url = self.config.extra.get("base_url")
-            if custom_base_url:
-                builder = builder.base_url(custom_base_url)
-                builder = builder.base_file_url(
-                    self.config.extra.get("base_file_url", custom_base_url)
-                )
-                logger.info(
-                    "[%s] Using custom Telegram base_url: %s",
-                    self.name, custom_base_url,
-                )
-
-            # PTB defaults (pool_timeout=1s) are too aggressive on flaky networks and
-            # can trigger "Pool timeout: All connections in the connection pool are occupied"
-            # during reconnect/bootstrap. Use safer defaults and allow env overrides.
-            def _env_int(name: str, default: int) -> int:
-                try:
-                    return int(os.getenv(name, str(default)))
-                except (TypeError, ValueError):
-                    return default
-
-            def _env_float(name: str, default: float) -> float:
-                try:
-                    return float(os.getenv(name, str(default)))
-                except (TypeError, ValueError):
-                    return default
-
-            request_kwargs = {
-                "connection_pool_size": _env_int("HERMES_TELEGRAM_HTTP_POOL_SIZE", 512),
-                "pool_timeout": _env_float("HERMES_TELEGRAM_HTTP_POOL_TIMEOUT", 8.0),
-                "connect_timeout": _env_float("HERMES_TELEGRAM_HTTP_CONNECT_TIMEOUT", 10.0),
-                "read_timeout": _env_float("HERMES_TELEGRAM_HTTP_READ_TIMEOUT", 20.0),
-                "write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
-            }
-
-            proxy_url = resolve_proxy_url("TELEGRAM_PROXY")
-            disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
             fallback_ips = self._fallback_ips()
             if not fallback_ips:
                 fallback_ips = await discover_fallback_ips()
@@ -610,34 +521,16 @@ class TelegramAdapter(BasePlatformAdapter):
                     self.name,
                     ", ".join(fallback_ips),
                 )
-
-            if fallback_ips and not proxy_url and not disable_fallback:
+            if fallback_ips:
                 logger.info(
                     "[%s] Telegram fallback IPs active: %s",
                     self.name,
                     ", ".join(fallback_ips),
                 )
-                # Keep request/update pools separate to reduce contention during
-                # polling reconnect + bot API bootstrap/delete_webhook calls.
-                request = HTTPXRequest(
-                    **request_kwargs,
-                    httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
-                )
-                get_updates_request = HTTPXRequest(
-                    **request_kwargs,
-                    httpx_kwargs={"transport": TelegramFallbackTransport(fallback_ips)},
-                )
-            elif proxy_url:
-                logger.info("[%s] Proxy detected; passing explicitly to HTTPXRequest: %s", self.name, proxy_url)
-                request = HTTPXRequest(**request_kwargs, proxy=proxy_url)
-                get_updates_request = HTTPXRequest(**request_kwargs, proxy=proxy_url)
-            else:
-                if disable_fallback:
-                    logger.info("[%s] Telegram fallback-IP transport disabled via env", self.name)
-                request = HTTPXRequest(**request_kwargs)
-                get_updates_request = HTTPXRequest(**request_kwargs)
-
-            builder = builder.request(request).get_updates_request(get_updates_request)
+                transport = TelegramFallbackTransport(fallback_ips)
+                request = HTTPXRequest(httpx_kwargs={"transport": transport})
+                get_updates_request = HTTPXRequest(httpx_kwargs={"transport": transport})
+                builder = builder.request(request).get_updates_request(get_updates_request)
             self._app = builder.build()
             self._bot = self._app.bot
             
@@ -666,14 +559,14 @@ class TelegramAdapter(BasePlatformAdapter):
                 from telegram.error import NetworkError, TimedOut
             except ImportError:
                 NetworkError = TimedOut = OSError  # type: ignore[misc,assignment]
-            _max_connect = 8
+            _max_connect = 3
             for _attempt in range(_max_connect):
                 try:
                     await self._app.initialize()
                     break
                 except (NetworkError, TimedOut, OSError) as init_err:
                     if _attempt < _max_connect - 1:
-                        wait = min(2 ** _attempt, 15)
+                        wait = 2 ** _attempt
                         logger.warning(
                             "[%s] Connect attempt %d/%d failed: %s — retrying in %ds",
                             self.name, _attempt + 1, _max_connect, init_err, wait,
@@ -784,7 +677,12 @@ class TelegramAdapter(BasePlatformAdapter):
             return True
             
         except Exception as e:
-            self._release_platform_lock()
+            if self._token_lock_identity:
+                try:
+                    from gateway.status import release_scoped_lock
+                    release_scoped_lock("telegram-bot-token", self._token_lock_identity)
+                except Exception:
+                    pass
             message = f"Telegram startup failed: {e}"
             self._set_fatal_error("telegram_connect_error", message, retryable=True)
             logger.error("[%s] Failed to connect to Telegram: %s", self.name, e, exc_info=True)
@@ -810,7 +708,12 @@ class TelegramAdapter(BasePlatformAdapter):
                 await self._app.shutdown()
             except Exception as e:
                 logger.warning("[%s] Error during Telegram disconnect: %s", self.name, e, exc_info=True)
-        self._release_platform_lock()
+        if self._token_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("telegram-bot-token", self._token_lock_identity)
+            except Exception as e:
+                logger.warning("[%s] Error releasing Telegram token lock: %s", self.name, e, exc_info=True)
 
         for task in self._pending_photo_batch_tasks.values():
             if task and not task.done():
@@ -821,6 +724,7 @@ class TelegramAdapter(BasePlatformAdapter):
         self._mark_disconnected()
         self._app = None
         self._bot = None
+        self._token_lock_identity = None
         logger.info("[%s] Disconnected from Telegram", self.name)
 
     def _should_thread_reply(self, reply_to: Optional[str], chunk_index: int) -> bool:
@@ -861,9 +765,7 @@ class TelegramAdapter(BasePlatformAdapter):
         try:
             # Format and split message if needed
             formatted = self.format_message(content)
-            chunks = self.truncate_message(
-                formatted, self.MAX_MESSAGE_LENGTH, len_fn=utf16_len,
-            )
+            chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
             if len(chunks) > 1:
                 # truncate_message appends a raw " (1/2)" suffix. Escape the
                 # MarkdownV2-special parentheses so Telegram doesn't reject the
@@ -874,7 +776,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 ]
             
             message_ids = []
-            thread_id = self._metadata_thread_id(metadata)
+            thread_id = metadata.get("thread_id") if metadata else None
             
             try:
                 from telegram.error import NetworkError as _NetErr
@@ -894,7 +796,7 @@ class TelegramAdapter(BasePlatformAdapter):
             for i, chunk in enumerate(chunks):
                 should_thread = self._should_thread_reply(reply_to, i)
                 reply_to_id = int(reply_to) if should_thread else None
-                effective_thread_id = self._message_thread_id_for_send(thread_id)
+                effective_thread_id = int(thread_id) if thread_id else None
 
                 msg = None
                 for _send_attempt in range(3):
@@ -907,7 +809,6 @@ class TelegramAdapter(BasePlatformAdapter):
                                 parse_mode=ParseMode.MARKDOWN_V2,
                                 reply_to_message_id=reply_to_id,
                                 message_thread_id=effective_thread_id,
-                                **self._link_preview_kwargs(),
                             )
                         except Exception as md_error:
                             # Markdown parsing failed, try plain text
@@ -920,7 +821,6 @@ class TelegramAdapter(BasePlatformAdapter):
                                     parse_mode=None,
                                     reply_to_message_id=reply_to_id,
                                     message_thread_id=effective_thread_id,
-                                    **self._link_preview_kwargs(),
                                 )
                             else:
                                 raise
@@ -931,7 +831,8 @@ class TelegramAdapter(BasePlatformAdapter):
                         # (not transient network issues). Detect and handle
                         # specific cases instead of blindly retrying.
                         if _BadReq and isinstance(send_err, _BadReq):
-                            if self._is_thread_not_found_error(send_err) and effective_thread_id is not None:
+                            err_lower = str(send_err).lower()
+                            if "thread not found" in err_lower and effective_thread_id is not None:
                                 # Thread doesn't exist — retry without
                                 # message_thread_id so the message still
                                 # reaches the chat.
@@ -941,7 +842,6 @@ class TelegramAdapter(BasePlatformAdapter):
                                 )
                                 effective_thread_id = None
                                 continue
-                            err_lower = str(send_err).lower()
                             if "message to be replied not found" in err_lower and reply_to_id is not None:
                                 # Original message was deleted before we
                                 # could reply — clear reply target and retry
@@ -1036,9 +936,7 @@ class TelegramAdapter(BasePlatformAdapter):
             # streaming).  Truncate and succeed so the stream consumer can
             # split the overflow into a new message instead of dying.
             if "message_too_long" in err_str or "too long" in err_str:
-                truncated = _prefix_within_utf16_limit(
-                    content, self.MAX_MESSAGE_LENGTH - 20
-                ) + "…"
+                truncated = content[: self.MAX_MESSAGE_LENGTH - 20] + "…"
                 try:
                     await self._bot.edit_message_text(
                         chat_id=int(chat_id),
@@ -1108,7 +1006,6 @@ class TelegramAdapter(BasePlatformAdapter):
                 text=text,
                 parse_mode=ParseMode.MARKDOWN,
                 reply_markup=keyboard,
-                **self._link_preview_kwargs(),
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1131,13 +1028,15 @@ class TelegramAdapter(BasePlatformAdapter):
         try:
             cmd_preview = command[:3800] + "..." if len(command) > 3800 else command
             text = (
-                f"⚠️ <b>Command Approval Required</b>\n\n"
-                f"<pre>{_html.escape(cmd_preview)}</pre>\n\n"
-                f"Reason: {_html.escape(description)}"
+                f"⚠️ *Command Approval Required*\n\n"
+                f"`{cmd_preview}`\n\n"
+                f"Reason: {description}"
             )
 
             # Resolve thread context for thread replies
-            thread_id = self._metadata_thread_id(metadata)
+            thread_id = None
+            if metadata:
+                thread_id = metadata.get("thread_id") or metadata.get("message_thread_id")
 
             # We'll use the message_id as part of callback_data to look up session_key
             # Send a placeholder first, then update — or use a counter.
@@ -1161,13 +1060,11 @@ class TelegramAdapter(BasePlatformAdapter):
             kwargs: Dict[str, Any] = {
                 "chat_id": int(chat_id),
                 "text": text,
-                "parse_mode": ParseMode.HTML,
+                "parse_mode": ParseMode.MARKDOWN,
                 "reply_markup": keyboard,
-                **self._link_preview_kwargs(),
             }
-            message_thread_id = self._message_thread_id_for_send(thread_id)
-            if message_thread_id is not None:
-                kwargs["message_thread_id"] = message_thread_id
+            if thread_id:
+                kwargs["message_thread_id"] = int(thread_id)
 
             msg = await self._bot.send_message(**kwargs)
 
@@ -1235,7 +1132,6 @@ class TelegramAdapter(BasePlatformAdapter):
                 parse_mode=ParseMode.MARKDOWN,
                 reply_markup=keyboard,
                 message_thread_id=int(thread_id) if thread_id else None,
-                **self._link_preview_kwargs(),
             )
 
             # Store picker state keyed by chat_id
@@ -1502,12 +1398,6 @@ class TelegramAdapter(BasePlatformAdapter):
                     await query.answer(text="Invalid approval data.")
                     return
 
-                # Only authorized users may click approval buttons.
-                caller_id = str(getattr(query.from_user, "id", ""))
-                if not self._is_callback_user_authorized(caller_id):
-                    await query.answer(text="⛔ You are not authorized to approve commands.")
-                    return
-
                 session_key = self._approval_state.pop(approval_id, None)
                 if not session_key:
                     await query.answer(text="This approval has already been resolved.")
@@ -1551,10 +1441,6 @@ class TelegramAdapter(BasePlatformAdapter):
         if not data.startswith("update_prompt:"):
             return
         answer = data.split(":", 1)[1]  # "y" or "n"
-        caller_id = str(getattr(query.from_user, "id", ""))
-        if not self._is_callback_user_authorized(caller_id):
-            await query.answer(text="⛔ You are not authorized to answer update prompts.")
-            return
         await query.answer(text=f"Sent '{answer}' to the update process.")
         # Edit the message to show the choice and remove buttons
         label = "Yes" if answer == "y" else "No"
@@ -1600,23 +1486,23 @@ class TelegramAdapter(BasePlatformAdapter):
             with open(audio_path, "rb") as audio_file:
                 # .ogg files -> send as voice (round playable bubble)
                 if audio_path.endswith((".ogg", ".opus")):
-                    _voice_thread = self._metadata_thread_id(metadata)
+                    _voice_thread = metadata.get("thread_id") if metadata else None
                     msg = await self._bot.send_voice(
                         chat_id=int(chat_id),
                         voice=audio_file,
                         caption=caption[:1024] if caption else None,
                         reply_to_message_id=int(reply_to) if reply_to else None,
-                        message_thread_id=self._message_thread_id_for_send(_voice_thread),
+                        message_thread_id=int(_voice_thread) if _voice_thread else None,
                     )
                 else:
                     # .mp3 and others -> send as audio file
-                    _audio_thread = self._metadata_thread_id(metadata)
+                    _audio_thread = metadata.get("thread_id") if metadata else None
                     msg = await self._bot.send_audio(
                         chat_id=int(chat_id),
                         audio=audio_file,
                         caption=caption[:1024] if caption else None,
                         reply_to_message_id=int(reply_to) if reply_to else None,
-                        message_thread_id=self._message_thread_id_for_send(_audio_thread),
+                        message_thread_id=int(_audio_thread) if _audio_thread else None,
                     )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1646,14 +1532,14 @@ class TelegramAdapter(BasePlatformAdapter):
             if not os.path.exists(image_path):
                 return SendResult(success=False, error=f"Image file not found: {image_path}")
 
-            _thread = self._metadata_thread_id(metadata)
+            _thread = metadata.get("thread_id") if metadata else None
             with open(image_path, "rb") as image_file:
                 msg = await self._bot.send_photo(
                     chat_id=int(chat_id),
                     photo=image_file,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=self._message_thread_id_for_send(_thread),
+                    message_thread_id=int(_thread) if _thread else None,
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1684,7 +1570,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 return SendResult(success=False, error=f"File not found: {file_path}")
 
             display_name = file_name or os.path.basename(file_path)
-            _thread = self._metadata_thread_id(metadata)
+            _thread = metadata.get("thread_id") if metadata else None
 
             with open(file_path, "rb") as f:
                 msg = await self._bot.send_document(
@@ -1693,7 +1579,7 @@ class TelegramAdapter(BasePlatformAdapter):
                     filename=display_name,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=self._message_thread_id_for_send(_thread),
+                    message_thread_id=int(_thread) if _thread else None,
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1717,14 +1603,14 @@ class TelegramAdapter(BasePlatformAdapter):
             if not os.path.exists(video_path):
                 return SendResult(success=False, error=f"Video file not found: {video_path}")
 
-            _thread = self._metadata_thread_id(metadata)
+            _thread = metadata.get("thread_id") if metadata else None
             with open(video_path, "rb") as f:
                 msg = await self._bot.send_video(
                     chat_id=int(chat_id),
                     video=f,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=self._message_thread_id_for_send(_thread),
+                    message_thread_id=int(_thread) if _thread else None,
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1754,13 +1640,13 @@ class TelegramAdapter(BasePlatformAdapter):
 
         try:
             # Telegram can send photos directly from URLs (up to ~5MB)
-            _photo_thread = self._metadata_thread_id(metadata)
+            _photo_thread = metadata.get("thread_id") if metadata else None
             msg = await self._bot.send_photo(
                 chat_id=int(chat_id),
                 photo=image_url,
                 caption=caption[:1024] if caption else None,  # Telegram caption limit
                 reply_to_message_id=int(reply_to) if reply_to else None,
-                message_thread_id=self._message_thread_id_for_send(_photo_thread),
+                message_thread_id=int(_photo_thread) if _photo_thread else None,
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1783,7 +1669,6 @@ class TelegramAdapter(BasePlatformAdapter):
                     photo=image_data,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=self._message_thread_id_for_send(_photo_thread),
                 )
                 return SendResult(success=True, message_id=str(msg.message_id))
             except Exception as e2:
@@ -1809,13 +1694,13 @@ class TelegramAdapter(BasePlatformAdapter):
             return SendResult(success=False, error="Not connected")
         
         try:
-            _anim_thread = self._metadata_thread_id(metadata)
+            _anim_thread = metadata.get("thread_id") if metadata else None
             msg = await self._bot.send_animation(
                 chat_id=int(chat_id),
                 animation=animation_url,
                 caption=caption[:1024] if caption else None,
                 reply_to_message_id=int(reply_to) if reply_to else None,
-                message_thread_id=self._message_thread_id_for_send(_anim_thread),
+                message_thread_id=int(_anim_thread) if _anim_thread else None,
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1832,23 +1717,12 @@ class TelegramAdapter(BasePlatformAdapter):
         """Send typing indicator."""
         if self._bot:
             try:
-                _typing_thread = self._metadata_thread_id(metadata)
-                message_thread_id = self._message_thread_id_for_typing(_typing_thread)
-                try:
-                    await self._bot.send_chat_action(
-                        chat_id=int(chat_id),
-                        action="typing",
-                        message_thread_id=message_thread_id,
-                    )
-                except Exception as e:
-                    if message_thread_id is not None and self._is_thread_not_found_error(e):
-                        await self._bot.send_chat_action(
-                            chat_id=int(chat_id),
-                            action="typing",
-                            message_thread_id=None,
-                        )
-                    else:
-                        raise
+                _typing_thread = metadata.get("thread_id") if metadata else None
+                await self._bot.send_chat_action(
+                    chat_id=int(chat_id),
+                    action="typing",
+                    message_thread_id=int(_typing_thread) if _typing_thread else None,
+                )
             except Exception as e:
                 # Typing failures are non-fatal; log at debug level only.
                 logger.debug(
@@ -1993,20 +1867,9 @@ class TelegramAdapter(BasePlatformAdapter):
         )
 
         # 9) Convert blockquotes: > at line start → protect > from escaping
-        #    Handle both regular blockquotes (> text) and expandable blockquotes
-        #    (Telegram MarkdownV2: **> for expandable start, || to end the quote)
-        def _convert_blockquote(m):
-            prefix = m.group(1)  # >, >>, >>>, **>, or **>> etc.
-            content = m.group(2)
-            # Check if content ends with || (expandable blockquote end marker)
-            # In this case, preserve the trailing || unescaped for Telegram
-            if prefix.startswith('**') and content.endswith('||'):
-                return _ph(f'{prefix} {_escape_mdv2(content[:-2])}||')
-            return _ph(f'{prefix} {_escape_mdv2(content)}')
-
         text = re.sub(
-            r'^((?:\*\*)?>{1,3}) (.+)$',
-            _convert_blockquote,
+            r'^(>{1,3}) (.+)$',
+            lambda m: _ph(m.group(1) + ' ' + _escape_mdv2(m.group(2))),
             text,
             flags=re.MULTILINE,
         )
@@ -2079,27 +1942,6 @@ class TelegramAdapter(BasePlatformAdapter):
             return {str(part).strip() for part in raw if str(part).strip()}
         return {part.strip() for part in str(raw).split(",") if part.strip()}
 
-    def _telegram_ignored_threads(self) -> set[int]:
-        raw = self.config.extra.get("ignored_threads")
-        if raw is None:
-            raw = os.getenv("TELEGRAM_IGNORED_THREADS", "")
-
-        if isinstance(raw, list):
-            values = raw
-        else:
-            values = str(raw).split(",")
-
-        ignored: set[int] = set()
-        for value in values:
-            text = str(value).strip()
-            if not text:
-                continue
-            try:
-                ignored.add(int(text))
-            except (TypeError, ValueError):
-                logger.warning("[%s] Ignoring invalid Telegram thread id: %r", self.name, value)
-        return ignored
-
     def _compile_mention_patterns(self) -> List[re.Pattern]:
         """Compile optional regex wake-word patterns for group triggers."""
         patterns = self.config.extra.get("mention_patterns")
@@ -2211,13 +2053,6 @@ class TelegramAdapter(BasePlatformAdapter):
         """
         if not self._is_group_chat(message):
             return True
-        thread_id = getattr(message, "message_thread_id", None)
-        if thread_id is not None:
-            try:
-                if int(thread_id) in self._telegram_ignored_threads():
-                    return False
-            except (TypeError, ValueError):
-                logger.warning("[%s] Ignoring non-numeric Telegram message_thread_id: %r", self.name, thread_id)
         if str(getattr(getattr(message, "chat", None), "id", "")) in self._telegram_free_response_chats():
             return True
         if not self._telegram_require_mention():
@@ -2316,15 +2151,12 @@ class TelegramAdapter(BasePlatformAdapter):
         """
         key = self._text_batch_key(event)
         existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
         if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             self._pending_text_batches[key] = event
         else:
             # Append text from the follow-up chunk
             if event.text:
                 existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             # Merge any media that might be attached
             if event.media_urls:
                 existing.media_urls.extend(event.media_urls)
@@ -2339,22 +2171,10 @@ class TelegramAdapter(BasePlatformAdapter):
         )
 
     async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near Telegram's 4096-char
-        split point, since a continuation chunk is almost certain.
-        """
+        """Wait for the quiet period then dispatch the aggregated text."""
         current_task = asyncio.current_task()
         try:
-            # Adaptive delay: if the latest chunk is near Telegram's 4096-char
-            # split point, a continuation is almost certain — wait longer.
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
+            await asyncio.sleep(self._text_batch_delay_seconds)
             event = self._pending_text_batches.pop(key, None)
             if not event:
                 return
@@ -2793,9 +2613,7 @@ class TelegramAdapter(BasePlatformAdapter):
 
         # Resolve DM topic name and skill binding
         thread_id_raw = message.message_thread_id
-        thread_id_str = str(thread_id_raw) if thread_id_raw is not None else None
-        if chat_type == "group" and thread_id_str is None and getattr(chat, "is_forum", False):
-            thread_id_str = self._GENERAL_TOPIC_THREAD_ID
+        thread_id_str = str(thread_id_raw) if thread_id_raw else None
         chat_topic = None
         topic_skill = None
 
@@ -2844,15 +2662,6 @@ class TelegramAdapter(BasePlatformAdapter):
             reply_to_id = str(message.reply_to_message.message_id)
             reply_to_text = message.reply_to_message.text or message.reply_to_message.caption or None
 
-        # Per-channel/topic ephemeral prompt
-        from gateway.platforms.base import resolve_channel_prompt
-        _chat_id_str = str(chat.id)
-        _channel_prompt = resolve_channel_prompt(
-            self.config.extra,
-            thread_id_str or _chat_id_str,
-            _chat_id_str if thread_id_str else None,
-        )
-
         return MessageEvent(
             text=message.text or "",
             message_type=msg_type,
@@ -2862,7 +2671,6 @@ class TelegramAdapter(BasePlatformAdapter):
             reply_to_message_id=reply_to_id,
             reply_to_text=reply_to_text,
             auto_skill=topic_skill,
-            channel_prompt=_channel_prompt,
             timestamp=message.date,
         )
 
@@ -2896,7 +2704,7 @@ class TelegramAdapter(BasePlatformAdapter):
         if chat_id and message_id:
             await self._set_reaction(chat_id, message_id, "\U0001f440")
 
-    async def on_processing_complete(self, event: MessageEvent, outcome: ProcessingOutcome) -> None:
+    async def on_processing_complete(self, event: MessageEvent, success: bool) -> None:
         """Swap the in-progress reaction for a final success/failure reaction.
 
         Unlike Discord (additive reactions), Telegram's set_message_reaction
@@ -2906,9 +2714,5 @@ class TelegramAdapter(BasePlatformAdapter):
             return
         chat_id = getattr(event.source, "chat_id", None)
         message_id = getattr(event, "message_id", None)
-        if chat_id and message_id and outcome != ProcessingOutcome.CANCELLED:
-            await self._set_reaction(
-                chat_id,
-                message_id,
-                "\U0001f44d" if outcome == ProcessingOutcome.SUCCESS else "\U0001f44e",
-            )
+        if chat_id and message_id:
+            await self._set_reaction(chat_id, message_id, "\u2705" if success else "\u274c")

gateway/platforms/telegram_network.py

@@ -12,6 +12,7 @@ from __future__ import annotations
 import asyncio
 import ipaddress
 import logging
+import os
 import socket
 from typing import Iterable, Optional
 
@@ -44,9 +45,11 @@ _SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
 
 
 def _resolve_proxy_url() -> str | None:
-    # Delegate to shared implementation (env vars + macOS system proxy detection)
-    from gateway.platforms.base import resolve_proxy_url
-    return resolve_proxy_url("TELEGRAM_PROXY")
+    for key in ("HTTPS_PROXY", "HTTP_PROXY", "ALL_PROXY", "https_proxy", "http_proxy", "all_proxy"):
+        value = (os.environ.get(key) or "").strip()
+        if value:
+            return value
+    return None
 
 
 class TelegramFallbackTransport(httpx.AsyncBaseTransport):
@@ -109,8 +112,7 @@ class TelegramFallbackTransport(httpx.AsyncBaseTransport):
                 logger.warning("[Telegram] Fallback IP %s failed: %s", ip, exc)
                 continue
 
-        if last_error is None:
-            raise RuntimeError("All Telegram fallback IPs exhausted but no error was recorded")
+        assert last_error is not None
         raise last_error
 
     async def aclose(self) -> None:

gateway/platforms/webhook.py

@@ -27,6 +27,7 @@ import hashlib
 import hmac
 import json
 import logging
+import os
 import re
 import subprocess
 import time
@@ -185,25 +186,13 @@ class WebhookAdapter(BasePlatformAdapter):
         if deliver_type == "github_comment":
             return await self._deliver_github_comment(content, delivery)
 
-        # Cross-platform delivery — any platform with a gateway adapter
+        # Cross-platform delivery (telegram, discord, etc.)
         if self.gateway_runner and deliver_type in (
             "telegram",
             "discord",
             "slack",
             "signal",
             "sms",
-            "whatsapp",
-            "matrix",
-            "mattermost",
-            "homeassistant",
-            "email",
-            "dingtalk",
-            "feishu",
-            "wecom",
-            "wecom_callback",
-            "weixin",
-            "bluebubbles",
-            "qqbot",
         ):
             return await self._deliver_cross_platform(
                 deliver_type, content, delivery
@@ -273,7 +262,7 @@ class WebhookAdapter(BasePlatformAdapter):
                 ", ".join(self._dynamic_routes.keys()) or "(none)",
             )
         except Exception as e:
-            logger.error("[webhook] Failed to reload dynamic routes: %s", e)
+            logger.warning("[webhook] Failed to reload dynamic routes: %s", e)
 
     async def _handle_webhook(self, request: "web.Request") -> "web.Response":
         """POST /webhooks/{route_name} — receive and process a webhook event."""

gateway/platforms/wecom.py

@@ -37,6 +37,7 @@ import logging
 import mimetypes
 import os
 import re
+import time
 import uuid
 from datetime import datetime, timezone
 from pathlib import Path
@@ -58,7 +59,6 @@ except ImportError:
     httpx = None  # type: ignore[assignment]
 
 from gateway.config import Platform, PlatformConfig
-from gateway.platforms.helpers import MessageDeduplicator
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -92,6 +92,7 @@ REQUEST_TIMEOUT_SECONDS = 15.0
 HEARTBEAT_INTERVAL_SECONDS = 30.0
 RECONNECT_BACKOFF = [2, 5, 10, 30, 60]
 
+DEDUP_WINDOW_SECONDS = 300
 DEDUP_MAX_SIZE = 1000
 
 IMAGE_MAX_BYTES = 10 * 1024 * 1024
@@ -142,9 +143,6 @@ class WeComAdapter(BasePlatformAdapter):
     """WeCom AI Bot adapter backed by a persistent WebSocket connection."""
 
     MAX_MESSAGE_LENGTH = MAX_MESSAGE_LENGTH
-    # Threshold for detecting WeCom client-side message splits.
-    # When a chunk is near the 4000-char limit, a continuation is almost certain.
-    _SPLIT_THRESHOLD = 3900
 
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.WECOM)
@@ -171,16 +169,9 @@ class WeComAdapter(BasePlatformAdapter):
         self._listen_task: Optional[asyncio.Task] = None
         self._heartbeat_task: Optional[asyncio.Task] = None
         self._pending_responses: Dict[str, asyncio.Future] = {}
-        self._dedup = MessageDeduplicator(max_size=DEDUP_MAX_SIZE)
+        self._seen_messages: Dict[str, float] = {}
         self._reply_req_ids: Dict[str, str] = {}
 
-        # Text batching: merge rapid successive messages (Telegram-style).
-        # WeCom clients split long messages around 4000 chars.
-        self._text_batch_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
-        self._pending_text_batches: Dict[str, MessageEvent] = {}
-        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
-
     # ------------------------------------------------------------------
     # Connection lifecycle
     # ------------------------------------------------------------------
@@ -249,7 +240,7 @@ class WeComAdapter(BasePlatformAdapter):
             await self._http_client.aclose()
             self._http_client = None
 
-        self._dedup.clear()
+        self._seen_messages.clear()
         logger.info("[%s] Disconnected", self.name)
 
     async def _cleanup_ws(self) -> None:
@@ -265,7 +256,7 @@ class WeComAdapter(BasePlatformAdapter):
     async def _open_connection(self) -> None:
         """Open and authenticate a websocket connection."""
         await self._cleanup_ws()
-        self._session = aiohttp.ClientSession(trust_env=True)
+        self._session = aiohttp.ClientSession()
         self._ws = await self._session.ws_connect(
             self._ws_url,
             heartbeat=HEARTBEAT_INTERVAL_SECONDS * 2,
@@ -475,7 +466,7 @@ class WeComAdapter(BasePlatformAdapter):
             return
 
         msg_id = str(body.get("msgid") or self._payload_req_id(payload) or uuid.uuid4().hex)
-        if self._dedup.is_duplicate(msg_id):
+        if self._is_duplicate(msg_id):
             logger.debug("[%s] Duplicate message %s ignored", self.name, msg_id)
             return
         self._remember_reply_req_id(msg_id, self._payload_req_id(payload))
@@ -528,82 +519,7 @@ class WeComAdapter(BasePlatformAdapter):
             timestamp=datetime.now(tz=timezone.utc),
         )
 
-        # Only batch plain text messages — commands, media, etc. dispatch
-        # immediately since they won't be split by the WeCom client.
-        if message_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
-            self._enqueue_text_event(event)
-        else:
-            await self.handle_message(event)
-
-    # ------------------------------------------------------------------
-    # Text message aggregation (handles WeCom client-side splits)
-    # ------------------------------------------------------------------
-
-    def _text_batch_key(self, event: MessageEvent) -> str:
-        """Session-scoped key for text message batching."""
-        from gateway.session import build_session_key
-        return build_session_key(
-            event.source,
-            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
-            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
-        )
-
-    def _enqueue_text_event(self, event: MessageEvent) -> None:
-        """Buffer a text event and reset the flush timer.
-
-        When WeCom splits a long user message at 4000 chars, the chunks
-        arrive within a few hundred milliseconds.  This merges them into
-        a single event before dispatching.
-        """
-        key = self._text_batch_key(event)
-        existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
-        if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending_text_batches[key] = event
-        else:
-            if event.text:
-                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            # Merge any media that might be attached
-            if event.media_urls:
-                existing.media_urls.extend(event.media_urls)
-                existing.media_types.extend(event.media_types)
-
-        # Cancel any pending flush and restart the timer
-        prior_task = self._pending_text_batch_tasks.get(key)
-        if prior_task and not prior_task.done():
-            prior_task.cancel()
-        self._pending_text_batch_tasks[key] = asyncio.create_task(
-            self._flush_text_batch(key)
-        )
-
-    async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near WeCom's 4000-char
-        split point, since a continuation chunk is almost certain.
-        """
-        current_task = asyncio.current_task()
-        try:
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
-            event = self._pending_text_batches.pop(key, None)
-            if not event:
-                return
-            logger.info(
-                "[WeCom] Flushing text batch %s (%d chars)",
-                key, len(event.text or ""),
-            )
-            await self.handle_message(event)
-        finally:
-            if self._pending_text_batch_tasks.get(key) is current_task:
-                self._pending_text_batch_tasks.pop(key, None)
+        await self.handle_message(event)
 
     @staticmethod
     def _extract_text(body: Dict[str, Any]) -> Tuple[str, Optional[str]]:
@@ -635,13 +551,6 @@ class WeComAdapter(BasePlatformAdapter):
                 if voice_text:
                     text_parts.append(voice_text)
 
-            # Extract appmsg title (filename) for WeCom AI Bot attachments
-            if msgtype == "appmsg":
-                appmsg = body.get("appmsg") if isinstance(body.get("appmsg"), dict) else {}
-                title = str(appmsg.get("title") or "").strip()
-                if title:
-                    text_parts.append(title)
-
         quote = body.get("quote") if isinstance(body.get("quote"), dict) else {}
         quote_type = str(quote.get("msgtype") or "").lower()
         if quote_type == "text":
@@ -674,13 +583,6 @@ class WeComAdapter(BasePlatformAdapter):
                 refs.append(("image", body["image"]))
             if msgtype == "file" and isinstance(body.get("file"), dict):
                 refs.append(("file", body["file"]))
-            # Handle appmsg (WeCom AI Bot attachments with PDF/Word/Excel)
-            if msgtype == "appmsg" and isinstance(body.get("appmsg"), dict):
-                appmsg = body["appmsg"]
-                if isinstance(appmsg.get("file"), dict):
-                    refs.append(("file", appmsg["file"]))
-                elif isinstance(appmsg.get("image"), dict):
-                    refs.append(("image", appmsg["image"]))
 
         quote = body.get("quote") if isinstance(body.get("quote"), dict) else {}
         quote_type = str(quote.get("msgtype") or "").lower()
@@ -709,11 +611,7 @@ class WeComAdapter(BasePlatformAdapter):
 
             if kind == "image":
                 ext = self._detect_image_ext(raw)
-                try:
-                    return cache_image_from_bytes(raw, ext), self._mime_for_ext(ext, fallback="image/jpeg")
-                except ValueError as exc:
-                    logger.warning("[%s] Rejected non-image bytes: %s", self.name, exc)
-                    return None
+                return cache_image_from_bytes(raw, ext), self._mime_for_ext(ext, fallback="image/jpeg")
 
             filename = str(media.get("filename") or media.get("name") or "wecom_file")
             return cache_document_from_bytes(raw, filename), mimetypes.guess_type(filename)[0] or "application/octet-stream"
@@ -739,11 +637,7 @@ class WeComAdapter(BasePlatformAdapter):
         content_type = str(headers.get("content-type") or "").split(";", 1)[0].strip() or "application/octet-stream"
         if kind == "image":
             ext = self._guess_extension(url, content_type, fallback=self._detect_image_ext(raw))
-            try:
-                return cache_image_from_bytes(raw, ext), content_type or self._mime_for_ext(ext, fallback="image/jpeg")
-            except ValueError as exc:
-                logger.warning("[%s] Rejected non-image bytes from %s: %s", self.name, url, exc)
-                return None
+            return cache_image_from_bytes(raw, ext), content_type or self._mime_for_ext(ext, fallback="image/jpeg")
 
         filename = self._guess_filename(url, headers.get("content-disposition"), content_type)
         return cache_document_from_bytes(raw, filename), content_type
@@ -838,6 +732,24 @@ class WeComAdapter(BasePlatformAdapter):
         wildcard = self._groups.get("*")
         return wildcard if isinstance(wildcard, dict) else {}
 
+    def _is_duplicate(self, msg_id: str) -> bool:
+        now = time.time()
+        if len(self._seen_messages) > DEDUP_MAX_SIZE:
+            cutoff = now - DEDUP_WINDOW_SECONDS
+            self._seen_messages = {
+                key: ts for key, ts in self._seen_messages.items() if ts > cutoff
+            }
+            if self._reply_req_ids:
+                self._reply_req_ids = {
+                    key: value for key, value in self._reply_req_ids.items() if key in self._seen_messages
+                }
+
+        if msg_id in self._seen_messages:
+            return True
+
+        self._seen_messages[msg_id] = now
+        return False
+
     def _remember_reply_req_id(self, message_id: str, req_id: str) -> None:
         normalized_message_id = str(message_id or "").strip()
         normalized_req_id = str(req_id or "").strip()

gateway/platforms/wecom_callback.py

@@ -1,401 +0,0 @@
-"""WeCom callback-mode adapter for self-built enterprise applications.
-
-Unlike the bot/websocket adapter in ``wecom.py``, this handles the standard
-WeCom callback flow: WeCom POSTs encrypted XML to an HTTP endpoint, the
-adapter decrypts it, queues the message for the agent, and immediately
-acknowledges.  The agent's reply is delivered later via the proactive
-``message/send`` API using an access-token.
-
-Supports multiple self-built apps under one gateway instance, scoped by
-``corp_id:user_id`` to avoid cross-corp collisions.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-import socket as _socket
-import time
-from typing import Any, Dict, List, Optional
-from xml.etree import ElementTree as ET
-
-try:
-    from aiohttp import web
-
-    AIOHTTP_AVAILABLE = True
-except ImportError:
-    web = None  # type: ignore[assignment]
-    AIOHTTP_AVAILABLE = False
-
-try:
-    import httpx
-
-    HTTPX_AVAILABLE = True
-except ImportError:
-    httpx = None  # type: ignore[assignment]
-    HTTPX_AVAILABLE = False
-
-from gateway.config import Platform, PlatformConfig
-from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType, SendResult
-from gateway.platforms.wecom_crypto import WXBizMsgCrypt, WeComCryptoError
-
-logger = logging.getLogger(__name__)
-
-DEFAULT_HOST = "0.0.0.0"
-DEFAULT_PORT = 8645
-DEFAULT_PATH = "/wecom/callback"
-ACCESS_TOKEN_TTL_SECONDS = 7200
-MESSAGE_DEDUP_TTL_SECONDS = 300
-
-
-def check_wecom_callback_requirements() -> bool:
-    return AIOHTTP_AVAILABLE and HTTPX_AVAILABLE
-
-
-class WecomCallbackAdapter(BasePlatformAdapter):
-    def __init__(self, config: PlatformConfig):
-        super().__init__(config, Platform.WECOM_CALLBACK)
-        extra = config.extra or {}
-        self._host = str(extra.get("host") or DEFAULT_HOST)
-        self._port = int(extra.get("port") or DEFAULT_PORT)
-        self._path = str(extra.get("path") or DEFAULT_PATH)
-        self._apps: List[Dict[str, Any]] = self._normalize_apps(extra)
-        self._runner: Optional[web.AppRunner] = None
-        self._site: Optional[web.TCPSite] = None
-        self._app: Optional[web.Application] = None
-        self._http_client: Optional[httpx.AsyncClient] = None
-        self._message_queue: asyncio.Queue[MessageEvent] = asyncio.Queue()
-        self._poll_task: Optional[asyncio.Task] = None
-        self._seen_messages: Dict[str, float] = {}
-        self._user_app_map: Dict[str, str] = {}
-        self._access_tokens: Dict[str, Dict[str, Any]] = {}
-
-    # ------------------------------------------------------------------
-    # App normalisation
-    # ------------------------------------------------------------------
-
-    @staticmethod
-    def _user_app_key(corp_id: str, user_id: str) -> str:
-        return f"{corp_id}:{user_id}" if corp_id else user_id
-
-    @staticmethod
-    def _normalize_apps(extra: Dict[str, Any]) -> List[Dict[str, Any]]:
-        apps = extra.get("apps")
-        if isinstance(apps, list) and apps:
-            return [dict(app) for app in apps if isinstance(app, dict)]
-        if extra.get("corp_id"):
-            return [
-                {
-                    "name": extra.get("name") or "default",
-                    "corp_id": extra.get("corp_id", ""),
-                    "corp_secret": extra.get("corp_secret", ""),
-                    "agent_id": str(extra.get("agent_id", "")),
-                    "token": extra.get("token", ""),
-                    "encoding_aes_key": extra.get("encoding_aes_key", ""),
-                }
-            ]
-        return []
-
-    # ------------------------------------------------------------------
-    # Lifecycle
-    # ------------------------------------------------------------------
-
-    async def connect(self) -> bool:
-        if not self._apps:
-            logger.warning("[WecomCallback] No callback apps configured")
-            return False
-        if not check_wecom_callback_requirements():
-            logger.warning("[WecomCallback] aiohttp/httpx not installed")
-            return False
-
-        # Quick port-in-use check.
-        try:
-            with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as sock:
-                sock.settimeout(1)
-                sock.connect(("127.0.0.1", self._port))
-            logger.error("[WecomCallback] Port %d already in use", self._port)
-            return False
-        except (ConnectionRefusedError, OSError):
-            pass
-
-        try:
-            self._http_client = httpx.AsyncClient(timeout=20.0)
-            self._app = web.Application()
-            self._app.router.add_get("/health", self._handle_health)
-            self._app.router.add_get(self._path, self._handle_verify)
-            self._app.router.add_post(self._path, self._handle_callback)
-            self._runner = web.AppRunner(self._app)
-            await self._runner.setup()
-            self._site = web.TCPSite(self._runner, self._host, self._port)
-            await self._site.start()
-            self._poll_task = asyncio.create_task(self._poll_loop())
-            self._mark_connected()
-            logger.info(
-                "[WecomCallback] HTTP server listening on %s:%s%s",
-                self._host, self._port, self._path,
-            )
-            for app in self._apps:
-                try:
-                    await self._refresh_access_token(app)
-                except Exception as exc:
-                    logger.warning(
-                        "[WecomCallback] Initial token refresh failed for app '%s': %s",
-                        app.get("name", "default"), exc,
-                    )
-            return True
-        except Exception:
-            await self._cleanup()
-            logger.exception("[WecomCallback] Failed to start")
-            return False
-
-    async def disconnect(self) -> None:
-        self._running = False
-        if self._poll_task:
-            self._poll_task.cancel()
-            try:
-                await self._poll_task
-            except asyncio.CancelledError:
-                pass
-            self._poll_task = None
-        await self._cleanup()
-        self._mark_disconnected()
-        logger.info("[WecomCallback] Disconnected")
-
-    async def _cleanup(self) -> None:
-        self._site = None
-        if self._runner:
-            await self._runner.cleanup()
-            self._runner = None
-        self._app = None
-        if self._http_client:
-            await self._http_client.aclose()
-            self._http_client = None
-
-    # ------------------------------------------------------------------
-    # Outbound: proactive send via access-token API
-    # ------------------------------------------------------------------
-
-    async def send(
-        self,
-        chat_id: str,
-        content: str,
-        reply_to: Optional[str] = None,
-        metadata: Optional[Dict[str, Any]] = None,
-    ) -> SendResult:
-        app = self._resolve_app_for_chat(chat_id)
-        touser = chat_id.split(":", 1)[1] if ":" in chat_id else chat_id
-        try:
-            token = await self._get_access_token(app)
-            payload = {
-                "touser": touser,
-                "msgtype": "text",
-                "agentid": int(str(app.get("agent_id") or 0)),
-                "text": {"content": content[:2048]},
-                "safe": 0,
-            }
-            resp = await self._http_client.post(
-                f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
-                json=payload,
-            )
-            data = resp.json()
-            if data.get("errcode") != 0:
-                return SendResult(success=False, error=str(data))
-            return SendResult(
-                success=True,
-                message_id=str(data.get("msgid", "")),
-                raw_response=data,
-            )
-        except Exception as exc:
-            return SendResult(success=False, error=str(exc))
-
-    def _resolve_app_for_chat(self, chat_id: str) -> Dict[str, Any]:
-        """Pick the app associated with *chat_id*, falling back sensibly."""
-        app_name = self._user_app_map.get(chat_id)
-        if not app_name and ":" not in chat_id:
-            # Legacy bare user_id — try to find a unique match.
-            matching = [k for k in self._user_app_map if k.endswith(f":{chat_id}")]
-            if len(matching) == 1:
-                app_name = self._user_app_map.get(matching[0])
-        app = self._get_app_by_name(app_name) if app_name else None
-        return app or self._apps[0]
-
-    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
-        return {"name": chat_id, "type": "dm"}
-
-    # ------------------------------------------------------------------
-    # Inbound: HTTP callback handlers
-    # ------------------------------------------------------------------
-
-    async def _handle_health(self, request: web.Request) -> web.Response:
-        return web.json_response({"status": "ok", "platform": "wecom_callback"})
-
-    async def _handle_verify(self, request: web.Request) -> web.Response:
-        """GET endpoint — WeCom URL verification handshake."""
-        msg_signature = request.query.get("msg_signature", "")
-        timestamp = request.query.get("timestamp", "")
-        nonce = request.query.get("nonce", "")
-        echostr = request.query.get("echostr", "")
-        for app in self._apps:
-            try:
-                crypt = self._crypt_for_app(app)
-                plain = crypt.verify_url(msg_signature, timestamp, nonce, echostr)
-                return web.Response(text=plain, content_type="text/plain")
-            except Exception:
-                continue
-        return web.Response(status=403, text="signature verification failed")
-
-    async def _handle_callback(self, request: web.Request) -> web.Response:
-        """POST endpoint — receive an encrypted message callback."""
-        msg_signature = request.query.get("msg_signature", "")
-        timestamp = request.query.get("timestamp", "")
-        nonce = request.query.get("nonce", "")
-        body = await request.text()
-
-        for app in self._apps:
-            try:
-                decrypted = self._decrypt_request(
-                    app, body, msg_signature, timestamp, nonce,
-                )
-                event = self._build_event(app, decrypted)
-                if event is not None:
-                    # Deduplicate: WeCom retries callbacks on timeout,
-                    # producing duplicate inbound messages (#10305).
-                    if event.message_id:
-                        now = time.time()
-                        if event.message_id in self._seen_messages:
-                            if now - self._seen_messages[event.message_id] < MESSAGE_DEDUP_TTL_SECONDS:
-                                logger.debug("[WecomCallback] Duplicate MsgId %s, skipping", event.message_id)
-                                return web.Response(text="success", content_type="text/plain")
-                            del self._seen_messages[event.message_id]
-                        self._seen_messages[event.message_id] = now
-                        # Prune expired entries when cache grows large
-                        if len(self._seen_messages) > 2000:
-                            cutoff = now - MESSAGE_DEDUP_TTL_SECONDS
-                            self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
-                    # Record which app this user belongs to.
-                    if event.source and event.source.user_id:
-                        map_key = self._user_app_key(
-                            str(app.get("corp_id") or ""), event.source.user_id,
-                        )
-                        self._user_app_map[map_key] = app["name"]
-                    await self._message_queue.put(event)
-                # Immediately acknowledge — the agent's reply will arrive
-                # later via the proactive message/send API.
-                return web.Response(text="success", content_type="text/plain")
-            except WeComCryptoError:
-                continue
-            except Exception:
-                logger.exception("[WecomCallback] Error handling message")
-                break
-        return web.Response(status=400, text="invalid callback payload")
-
-    async def _poll_loop(self) -> None:
-        """Drain the message queue and dispatch to the gateway runner."""
-        while True:
-            event = await self._message_queue.get()
-            try:
-                task = asyncio.create_task(self.handle_message(event))
-                self._background_tasks.add(task)
-                task.add_done_callback(self._background_tasks.discard)
-            except Exception:
-                logger.exception("[WecomCallback] Failed to enqueue event")
-
-    # ------------------------------------------------------------------
-    # XML / crypto helpers
-    # ------------------------------------------------------------------
-
-    def _decrypt_request(
-        self, app: Dict[str, Any], body: str,
-        msg_signature: str, timestamp: str, nonce: str,
-    ) -> str:
-        root = ET.fromstring(body)
-        encrypt = root.findtext("Encrypt", default="")
-        crypt = self._crypt_for_app(app)
-        return crypt.decrypt(msg_signature, timestamp, nonce, encrypt).decode("utf-8")
-
-    def _build_event(self, app: Dict[str, Any], xml_text: str) -> Optional[MessageEvent]:
-        root = ET.fromstring(xml_text)
-        msg_type = (root.findtext("MsgType") or "").lower()
-        # Silently acknowledge lifecycle events.
-        if msg_type == "event":
-            event_name = (root.findtext("Event") or "").lower()
-            if event_name in {"enter_agent", "subscribe"}:
-                return None
-        if msg_type not in {"text", "event"}:
-            return None
-
-        user_id = root.findtext("FromUserName", default="")
-        corp_id = root.findtext("ToUserName", default=app.get("corp_id", ""))
-        scoped_chat_id = self._user_app_key(corp_id, user_id)
-        content = root.findtext("Content", default="").strip()
-        if not content and msg_type == "event":
-            content = "/start"
-        msg_id = (
-            root.findtext("MsgId")
-            or f"{user_id}:{root.findtext('CreateTime', default='0')}"
-        )
-        source = self.build_source(
-            chat_id=scoped_chat_id,
-            chat_name=user_id,
-            chat_type="dm",
-            user_id=user_id,
-            user_name=user_id,
-        )
-        return MessageEvent(
-            text=content,
-            message_type=MessageType.TEXT,
-            source=source,
-            raw_message=xml_text,
-            message_id=msg_id,
-        )
-
-    def _crypt_for_app(self, app: Dict[str, Any]) -> WXBizMsgCrypt:
-        return WXBizMsgCrypt(
-            token=str(app.get("token") or ""),
-            encoding_aes_key=str(app.get("encoding_aes_key") or ""),
-            receive_id=str(app.get("corp_id") or ""),
-        )
-
-    def _get_app_by_name(self, name: Optional[str]) -> Optional[Dict[str, Any]]:
-        if not name:
-            return None
-        for app in self._apps:
-            if app.get("name") == name:
-                return app
-        return None
-
-    # ------------------------------------------------------------------
-    # Access-token management
-    # ------------------------------------------------------------------
-
-    async def _get_access_token(self, app: Dict[str, Any]) -> str:
-        cached = self._access_tokens.get(app["name"])
-        now = time.time()
-        if cached and cached.get("expires_at", 0) > now + 60:
-            return cached["token"]
-        return await self._refresh_access_token(app)
-
-    async def _refresh_access_token(self, app: Dict[str, Any]) -> str:
-        resp = await self._http_client.get(
-            "https://qyapi.weixin.qq.com/cgi-bin/gettoken",
-            params={
-                "corpid": app.get("corp_id"),
-                "corpsecret": app.get("corp_secret"),
-            },
-        )
-        data = resp.json()
-        if data.get("errcode") != 0:
-            raise RuntimeError(f"WeCom token refresh failed: {data}")
-        token = data["access_token"]
-        expires_in = int(data.get("expires_in", ACCESS_TOKEN_TTL_SECONDS))
-        self._access_tokens[app["name"]] = {
-            "token": token,
-            "expires_at": time.time() + expires_in,
-        }
-        logger.info(
-            "[WecomCallback] Token refreshed for app '%s' (corp=%s), expires in %ss",
-            app.get("name", "default"),
-            app.get("corp_id", ""),
-            expires_in,
-        )
-        return token

gateway/platforms/wecom_crypto.py

@@ -1,142 +0,0 @@
-"""WeCom BizMsgCrypt-compatible AES-CBC encryption for callback mode.
-
-Implements the same wire format as Tencent's official ``WXBizMsgCrypt``
-SDK so that WeCom can verify, encrypt, and decrypt callback payloads.
-"""
-
-from __future__ import annotations
-
-import base64
-import hashlib
-import os
-import secrets
-import socket
-import struct
-from typing import Optional
-from xml.etree import ElementTree as ET
-
-from cryptography.hazmat.backends import default_backend
-from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
-
-
-class WeComCryptoError(Exception):
-    pass
-
-
-class SignatureError(WeComCryptoError):
-    pass
-
-
-class DecryptError(WeComCryptoError):
-    pass
-
-
-class EncryptError(WeComCryptoError):
-    pass
-
-
-class PKCS7Encoder:
-    block_size = 32
-
-    @classmethod
-    def encode(cls, text: bytes) -> bytes:
-        amount_to_pad = cls.block_size - (len(text) % cls.block_size)
-        if amount_to_pad == 0:
-            amount_to_pad = cls.block_size
-        pad = bytes([amount_to_pad]) * amount_to_pad
-        return text + pad
-
-    @classmethod
-    def decode(cls, decrypted: bytes) -> bytes:
-        if not decrypted:
-            raise DecryptError("empty decrypted payload")
-        pad = decrypted[-1]
-        if pad < 1 or pad > cls.block_size:
-            raise DecryptError("invalid PKCS7 padding")
-        if decrypted[-pad:] != bytes([pad]) * pad:
-            raise DecryptError("malformed PKCS7 padding")
-        return decrypted[:-pad]
-
-
-def _sha1_signature(token: str, timestamp: str, nonce: str, encrypt: str) -> str:
-    parts = sorted([token, timestamp, nonce, encrypt])
-    return hashlib.sha1("".join(parts).encode("utf-8")).hexdigest()
-
-
-class WXBizMsgCrypt:
-    """Minimal WeCom callback crypto helper compatible with BizMsgCrypt semantics."""
-
-    def __init__(self, token: str, encoding_aes_key: str, receive_id: str):
-        if not token:
-            raise ValueError("token is required")
-        if not encoding_aes_key:
-            raise ValueError("encoding_aes_key is required")
-        if len(encoding_aes_key) != 43:
-            raise ValueError("encoding_aes_key must be 43 chars")
-        if not receive_id:
-            raise ValueError("receive_id is required")
-
-        self.token = token
-        self.receive_id = receive_id
-        self.key = base64.b64decode(encoding_aes_key + "=")
-        self.iv = self.key[:16]
-
-    def verify_url(self, msg_signature: str, timestamp: str, nonce: str, echostr: str) -> str:
-        plain = self.decrypt(msg_signature, timestamp, nonce, echostr)
-        return plain.decode("utf-8")
-
-    def decrypt(self, msg_signature: str, timestamp: str, nonce: str, encrypt: str) -> bytes:
-        expected = _sha1_signature(self.token, timestamp, nonce, encrypt)
-        if expected != msg_signature:
-            raise SignatureError("signature mismatch")
-        try:
-            cipher_text = base64.b64decode(encrypt)
-        except Exception as exc:
-            raise DecryptError(f"invalid base64 payload: {exc}") from exc
-        try:
-            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
-            decryptor = cipher.decryptor()
-            padded = decryptor.update(cipher_text) + decryptor.finalize()
-            plain = PKCS7Encoder.decode(padded)
-            content = plain[16:]  # skip 16-byte random prefix
-            xml_length = socket.ntohl(struct.unpack("I", content[:4])[0])
-            xml_content = content[4:4 + xml_length]
-            receive_id = content[4 + xml_length:].decode("utf-8")
-        except WeComCryptoError:
-            raise
-        except Exception as exc:
-            raise DecryptError(f"decrypt failed: {exc}") from exc
-
-        if receive_id != self.receive_id:
-            raise DecryptError("receive_id mismatch")
-        return xml_content
-
-    def encrypt(self, plaintext: str, nonce: Optional[str] = None, timestamp: Optional[str] = None) -> str:
-        nonce = nonce or self._random_nonce()
-        timestamp = timestamp or str(int(__import__("time").time()))
-        encrypt = self._encrypt_bytes(plaintext.encode("utf-8"))
-        signature = _sha1_signature(self.token, timestamp, nonce, encrypt)
-        root = ET.Element("xml")
-        ET.SubElement(root, "Encrypt").text = encrypt
-        ET.SubElement(root, "MsgSignature").text = signature
-        ET.SubElement(root, "TimeStamp").text = timestamp
-        ET.SubElement(root, "Nonce").text = nonce
-        return ET.tostring(root, encoding="unicode")
-
-    def _encrypt_bytes(self, raw: bytes) -> str:
-        try:
-            random_prefix = os.urandom(16)
-            msg_len = struct.pack("I", socket.htonl(len(raw)))
-            payload = random_prefix + msg_len + raw + self.receive_id.encode("utf-8")
-            padded = PKCS7Encoder.encode(payload)
-            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
-            encryptor = cipher.encryptor()
-            encrypted = encryptor.update(padded) + encryptor.finalize()
-            return base64.b64encode(encrypted).decode("utf-8")
-        except Exception as exc:
-            raise EncryptError(f"encrypt failed: {exc}") from exc
-
-    @staticmethod
-    def _random_nonce(length: int = 10) -> str:
-        alphabet = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
-        return "".join(secrets.choice(alphabet) for _ in range(length))

gateway/platforms/whatsapp.py

@@ -120,9 +120,8 @@ class WhatsAppAdapter(BasePlatformAdapter):
     - session_path: Path to store WhatsApp session data
     """
     
-    # WhatsApp message limits — practical UX limit, not protocol max.
-    # WhatsApp allows ~65K but long messages are unreadable on mobile.
-    MAX_MESSAGE_LENGTH = 4096
+    # WhatsApp message limits
+    MAX_MESSAGE_LENGTH = 65536  # WhatsApp allows longer messages
     
     # Default bridge location relative to the hermes-agent install
     _DEFAULT_BRIDGE_DIR = Path(__file__).resolve().parents[2] / "scripts" / "whatsapp-bridge"
@@ -146,6 +145,7 @@ class WhatsAppAdapter(BasePlatformAdapter):
         self._bridge_log: Optional[Path] = None
         self._poll_task: Optional[asyncio.Task] = None
         self._http_session: Optional["aiohttp.ClientSession"] = None
+        self._session_lock_identity: Optional[str] = None
 
     def _whatsapp_require_mention(self) -> bool:
         configured = self.config.extra.get("require_mention")
@@ -290,7 +290,23 @@ class WhatsAppAdapter(BasePlatformAdapter):
         
         # Acquire scoped lock to prevent duplicate sessions
         try:
-            if not self._acquire_platform_lock('whatsapp-session', str(self._session_path), 'WhatsApp session'):
+            from gateway.status import acquire_scoped_lock
+
+            self._session_lock_identity = str(self._session_path)
+            acquired, existing = acquire_scoped_lock(
+                "whatsapp-session",
+                self._session_lock_identity,
+                metadata={"platform": self.platform.value},
+            )
+            if not acquired:
+                owner_pid = existing.get("pid") if isinstance(existing, dict) else None
+                message = (
+                    "Another local Hermes gateway is already using this WhatsApp session"
+                    + (f" (PID {owner_pid})." if owner_pid else ".")
+                    + " Stop the other gateway before starting a second WhatsApp bridge."
+                )
+                logger.error("[%s] %s", self.name, message)
+                self._set_fatal_error("whatsapp_session_lock", message, retryable=False)
                 return False
         except Exception as e:
             logger.warning("[%s] Could not acquire session lock (non-fatal): %s", self.name, e)
@@ -452,7 +468,12 @@ class WhatsAppAdapter(BasePlatformAdapter):
             return True
             
         except Exception as e:
-            self._release_platform_lock()
+            if self._session_lock_identity:
+                try:
+                    from gateway.status import release_scoped_lock
+                    release_scoped_lock("whatsapp-session", self._session_lock_identity)
+                except Exception:
+                    pass
             logger.error("[%s] Failed to start bridge: %s", self.name, e, exc_info=True)
             self._close_bridge_log()
             return False
@@ -525,70 +546,19 @@ class WhatsAppAdapter(BasePlatformAdapter):
             await self._http_session.close()
         self._http_session = None
 
-        self._release_platform_lock()
+        if self._session_lock_identity:
+            try:
+                from gateway.status import release_scoped_lock
+                release_scoped_lock("whatsapp-session", self._session_lock_identity)
+            except Exception as e:
+                logger.warning("[%s] Error releasing WhatsApp session lock: %s", self.name, e, exc_info=True)
 
         self._mark_disconnected()
         self._bridge_process = None
         self._close_bridge_log()
+        self._session_lock_identity = None
         print(f"[{self.name}] Disconnected")
     
-    def format_message(self, content: str) -> str:
-        """Convert standard markdown to WhatsApp-compatible formatting.
-
-        WhatsApp supports: *bold*, _italic_, ~strikethrough~, ```code```,
-        and monospaced `inline`. Standard markdown uses different syntax
-        for bold/italic/strikethrough, so we convert here.
-
-        Code blocks (``` fenced) and inline code (`) are protected from
-        conversion via placeholder substitution.
-        """
-        if not content:
-            return content
-
-        # --- 1. Protect fenced code blocks from formatting changes ---
-        _FENCE_PH = "\x00FENCE"
-        fences: list[str] = []
-
-        def _save_fence(m: re.Match) -> str:
-            fences.append(m.group(0))
-            return f"{_FENCE_PH}{len(fences) - 1}\x00"
-
-        result = re.sub(r"```[\s\S]*?```", _save_fence, content)
-
-        # --- 2. Protect inline code ---
-        _CODE_PH = "\x00CODE"
-        codes: list[str] = []
-
-        def _save_code(m: re.Match) -> str:
-            codes.append(m.group(0))
-            return f"{_CODE_PH}{len(codes) - 1}\x00"
-
-        result = re.sub(r"`[^`\n]+`", _save_code, result)
-
-        # --- 3. Convert markdown formatting to WhatsApp syntax ---
-        # Bold: **text** or __text__ → *text*
-        result = re.sub(r"\*\*(.+?)\*\*", r"*\1*", result)
-        result = re.sub(r"__(.+?)__", r"*\1*", result)
-        # Strikethrough: ~~text~~ → ~text~
-        result = re.sub(r"~~(.+?)~~", r"~\1~", result)
-        # Italic: *text* is already WhatsApp italic — leave as-is
-        # _text_ is already WhatsApp italic — leave as-is
-
-        # --- 4. Convert markdown headers to bold text ---
-        # # Header → *Header*
-        result = re.sub(r"^#{1,6}\s+(.+)$", r"*\1*", result, flags=re.MULTILINE)
-
-        # --- 5. Convert markdown links: [text](url) → text (url) ---
-        result = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", r"\1 (\2)", result)
-
-        # --- 6. Restore protected sections ---
-        for i, fence in enumerate(fences):
-            result = result.replace(f"{_FENCE_PH}{i}\x00", fence)
-        for i, code in enumerate(codes):
-            result = result.replace(f"{_CODE_PH}{i}\x00", code)
-
-        return result
-
     async def send(
         self,
         chat_id: str,
@@ -596,57 +566,38 @@ class WhatsAppAdapter(BasePlatformAdapter):
         reply_to: Optional[str] = None,
         metadata: Optional[Dict[str, Any]] = None
     ) -> SendResult:
-        """Send a message via the WhatsApp bridge.
-
-        Formats markdown for WhatsApp, splits long messages into chunks
-        that preserve code block boundaries, and sends each chunk sequentially.
-        """
+        """Send a message via the WhatsApp bridge."""
         if not self._running or not self._http_session:
             return SendResult(success=False, error="Not connected")
         bridge_exit = await self._check_managed_bridge_exit()
         if bridge_exit:
             return SendResult(success=False, error=bridge_exit)
-
-        if not content or not content.strip():
-            return SendResult(success=True, message_id=None)
-
+        
         try:
             import aiohttp
 
-            # Format and chunk the message
-            formatted = self.format_message(content)
-            chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
-
-            last_message_id = None
-            for chunk in chunks:
-                payload: Dict[str, Any] = {
-                    "chatId": chat_id,
-                    "message": chunk,
-                }
-                if reply_to and last_message_id is None:
-                    # Only reply-to on the first chunk
-                    payload["replyTo"] = reply_to
-
-                async with self._http_session.post(
-                    f"http://127.0.0.1:{self._bridge_port}/send",
-                    json=payload,
-                    timeout=aiohttp.ClientTimeout(total=30)
-                ) as resp:
-                    if resp.status == 200:
-                        data = await resp.json()
-                        last_message_id = data.get("messageId")
-                    else:
-                        error = await resp.text()
-                        return SendResult(success=False, error=error)
-
-                # Small delay between chunks to avoid rate limiting
-                if len(chunks) > 1:
-                    await asyncio.sleep(0.3)
-
-            return SendResult(
-                success=True,
-                message_id=last_message_id,
-            )
+            payload = {
+                "chatId": chat_id,
+                "message": content,
+            }
+            if reply_to:
+                payload["replyTo"] = reply_to
+            
+            async with self._http_session.post(
+                f"http://127.0.0.1:{self._bridge_port}/send",
+                json=payload,
+                timeout=aiohttp.ClientTimeout(total=30)
+            ) as resp:
+                if resp.status == 200:
+                    data = await resp.json()
+                    return SendResult(
+                        success=True,
+                        message_id=data.get("messageId"),
+                        raw_response=data
+                    )
+                else:
+                    error = await resp.text()
+                    return SendResult(success=False, error=error)
         except Exception as e:
             return SendResult(success=False, error=str(e))
 

gateway/restart.py

@@ -1,20 +0,0 @@
-"""Shared gateway restart constants and parsing helpers."""
-
-from hermes_cli.config import DEFAULT_CONFIG
-
-# EX_TEMPFAIL from sysexits.h — used to ask the service manager to restart
-# the gateway after a graceful drain/reload path completes.
-GATEWAY_SERVICE_RESTART_EXIT_CODE = 75
-
-DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT = float(
-    DEFAULT_CONFIG["agent"]["restart_drain_timeout"]
-)
-
-
-def parse_restart_drain_timeout(raw: object) -> float:
-    """Parse a configured drain timeout, falling back to the shared default."""
-    try:
-        value = float(raw) if str(raw or "").strip() else DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
-    except (TypeError, ValueError):
-        return DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
-    return max(0.0, value)

gateway/session.py

@@ -12,6 +12,7 @@ import hashlib
 import logging
 import os
 import json
+import re
 import threading
 import uuid
 from pathlib import Path
@@ -31,6 +32,9 @@ def _now() -> datetime:
 # PII redaction helpers
 # ---------------------------------------------------------------------------
 
+_PHONE_RE = re.compile(r"^\+?\d[\d\-\s]{6,}$")
+
+
 def _hash_id(value: str) -> str:
     """Deterministic 12-char hex hash of an identifier."""
     return hashlib.sha256(value.encode("utf-8")).hexdigest()[:12]
@@ -54,6 +58,10 @@ def _hash_chat_id(value: str) -> str:
     return _hash_id(value)
 
 
+def _looks_like_phone(value: str) -> bool:
+    """Return True if *value* looks like a phone number (E.164 or similar)."""
+    return bool(_PHONE_RE.match(value.strip()))
+
 from .config import (
     Platform,
     GatewayConfig,
@@ -136,6 +144,15 @@ class SessionSource:
             chat_id_alt=data.get("chat_id_alt"),
         )
     
+    @classmethod
+    def local_cli(cls) -> "SessionSource":
+        """Create a source representing the local CLI."""
+        return cls(
+            platform=Platform.LOCAL,
+            chat_id="cli",
+            chat_name="CLI terminal",
+            chat_type="dm",
+        )
 
 
 @dataclass
@@ -301,8 +318,6 @@ def build_session_context_prompt(
     lines.append("")
     lines.append("**Delivery options for scheduled tasks:**")
     
-    from hermes_constants import display_hermes_home
-
     # Origin delivery
     if context.source.platform == Platform.LOCAL:
         lines.append("- `\"origin\"` → Local output (saved to files)")
@@ -311,11 +326,9 @@ def build_session_context_prompt(
             _hash_chat_id(context.source.chat_id) if redact_pii else context.source.chat_id
         )
         lines.append(f"- `\"origin\"` → Back to this chat ({_origin_label})")
-
+    
     # Local always available
-    lines.append(
-        f"- `\"local\"` → Save to local files only ({display_hermes_home()}/cron/output/)"
-    )
+    lines.append("- `\"local\"` → Save to local files only (~/.hermes/cron/output/)")
     
     # Platform home channels
     for platform, home in context.home_channels.items():
@@ -371,11 +384,6 @@ class SessionEntry:
     # survives gateway restarts (the old in-memory _pre_flushed_sessions
     # set was lost on restart, causing redundant re-flushes).
     memory_flushed: bool = False
-
-    # When True the next call to get_or_create_session() will auto-reset
-    # this session (create a new session_id) so the user starts fresh.
-    # Set by /stop to break stuck-resume loops (#7536).
-    suspended: bool = False
     
     def to_dict(self) -> Dict[str, Any]:
         result = {
@@ -395,7 +403,6 @@ class SessionEntry:
             "estimated_cost_usd": self.estimated_cost_usd,
             "cost_status": self.cost_status,
             "memory_flushed": self.memory_flushed,
-            "suspended": self.suspended,
         }
         if self.origin:
             result["origin"] = self.origin.to_dict()
@@ -432,7 +439,6 @@ class SessionEntry:
             estimated_cost_usd=data.get("estimated_cost_usd", 0.0),
             cost_status=data.get("cost_status", "unknown"),
             memory_flushed=data.get("memory_flushed", False),
-            suspended=data.get("suspended", False),
         )
 
 
@@ -504,7 +510,8 @@ class SessionStore:
     """
     
     def __init__(self, sessions_dir: Path, config: GatewayConfig,
-                 has_active_processes_fn=None):
+                 has_active_processes_fn=None,
+                 on_auto_reset=None):
         self.sessions_dir = sessions_dir
         self.config = config
         self._entries: Dict[str, SessionEntry] = {}
@@ -708,12 +715,7 @@ class SessionStore:
             if session_key in self._entries and not force_new:
                 entry = self._entries[session_key]
 
-                # Auto-reset sessions marked as suspended (e.g. after /stop
-                # broke a stuck loop — #7536).
-                if entry.suspended:
-                    reset_reason = "suspended"
-                else:
-                    reset_reason = self._should_reset(entry, source)
+                reset_reason = self._should_reset(entry, source)
                 if not reset_reason:
                     entry.updated_at = now
                     self._save()
@@ -768,6 +770,41 @@ class SessionStore:
             except Exception as e:
                 print(f"[gateway] Warning: Failed to create SQLite session: {e}")
 
+        # Seed new DM thread sessions with parent DM session history.
+        # When a bot reply creates a Slack thread and the user responds in it,
+        # the thread gets a new session (keyed by thread_ts).  Without seeding,
+        # the thread session starts with zero context — the user's original
+        # question and the bot's answer are invisible.  Fix: copy the parent
+        # DM session's transcript into the new thread session so context carries
+        # over while still keeping threads isolated from each other.
+        if (
+            source.chat_type == "dm"
+            and source.thread_id
+            and entry.created_at == entry.updated_at  # brand-new session
+            and not was_auto_reset
+        ):
+            parent_source = SessionSource(
+                platform=source.platform,
+                chat_id=source.chat_id,
+                chat_type="dm",
+                user_id=source.user_id,
+                # no thread_id — this is the parent DM session
+            )
+            parent_key = self._generate_session_key(parent_source)
+            with self._lock:
+                parent_entry = self._entries.get(parent_key)
+            if parent_entry and parent_entry.session_id != entry.session_id:
+                try:
+                    parent_history = self.load_transcript(parent_entry.session_id)
+                    if parent_history:
+                        self.rewrite_transcript(entry.session_id, parent_history)
+                        logger.info(
+                            "[Session] Seeded DM thread session %s with %d messages from parent %s",
+                            entry.session_id, len(parent_history), parent_entry.session_id,
+                        )
+                except Exception as e:
+                    logger.warning("[Session] Failed to seed thread session: %s", e)
+
         return entry
 
     def update_session(
@@ -786,44 +823,6 @@ class SessionStore:
                     entry.last_prompt_tokens = last_prompt_tokens
                 self._save()
 
-    def suspend_session(self, session_key: str) -> bool:
-        """Mark a session as suspended so it auto-resets on next access.
-
-        Used by ``/stop`` to prevent stuck sessions from being resumed
-        after a gateway restart (#7536).  Returns True if the session
-        existed and was marked.
-        """
-        with self._lock:
-            self._ensure_loaded_locked()
-            if session_key in self._entries:
-                self._entries[session_key].suspended = True
-                self._save()
-                return True
-        return False
-
-    def suspend_recently_active(self, max_age_seconds: int = 120) -> int:
-        """Mark recently-active sessions as suspended.
-
-        Called on gateway startup to prevent sessions that were likely
-        in-flight when the gateway last exited from being blindly resumed
-        (#7536).  Only suspends sessions updated within *max_age_seconds*
-        to avoid resetting long-idle sessions that are harmless to resume.
-        Returns the number of sessions that were suspended.
-        """
-        from datetime import timedelta
-
-        cutoff = _now() - timedelta(seconds=max_age_seconds)
-        count = 0
-        with self._lock:
-            self._ensure_loaded_locked()
-            for entry in self._entries.values():
-                if not entry.suspended and entry.updated_at >= cutoff:
-                    entry.suspended = True
-                    count += 1
-            if count:
-                self._save()
-        return count
-
     def reset_session(self, session_key: str) -> Optional[SessionEntry]:
         """Force reset a session, creating a new session ID."""
         db_end_session_id = None
@@ -881,8 +880,7 @@ class SessionStore:
         Used by ``/resume`` to restore a previously-named session.
         Ends the current session in SQLite (like reset), but instead of
         generating a fresh session ID, re-uses ``target_session_id`` so the
-        old transcript is loaded on the next message. If the target session was
-        previously ended, re-open it so gateway resume semantics match the CLI.
+        old transcript is loaded on the next message.
         """
         db_end_session_id = None
         new_entry = None
@@ -922,12 +920,6 @@ class SessionStore:
             except Exception as e:
                 logger.debug("Session DB end_session failed: %s", e)
 
-        if self._db:
-            try:
-                self._db.reopen_session(target_session_id)
-            except Exception as e:
-                logger.debug("Session DB reopen_session failed: %s", e)
-
         return new_entry
 
     def list_sessions(self, active_minutes: Optional[int] = None) -> List[SessionEntry]:

gateway/session_context.py

@@ -1,145 +0,0 @@
-"""
-Session-scoped context variables for the Hermes gateway.
-
-Replaces the previous ``os.environ``-based session state
-(``HERMES_SESSION_PLATFORM``, ``HERMES_SESSION_CHAT_ID``, etc.) with
-Python's ``contextvars.ContextVar``.
-
-**Why this matters**
-
-The gateway processes messages concurrently via ``asyncio``.  When two
-messages arrive at the same time the old code did:
-
-    os.environ["HERMES_SESSION_THREAD_ID"] = str(context.source.thread_id)
-
-Because ``os.environ`` is *process-global*, Message A's value was
-silently overwritten by Message B before Message A's agent finished
-running.  Background-task notifications and tool calls therefore routed
-to the wrong thread.
-
-``contextvars.ContextVar`` values are *task-local*: each ``asyncio``
-task (and any ``run_in_executor`` thread it spawns) gets its own copy,
-so concurrent messages never interfere.
-
-**Backward compatibility**
-
-The public helper ``get_session_env(name, default="")`` mirrors the old
-``os.getenv("HERMES_SESSION_*", ...)`` calls.  Existing tool code only
-needs to replace the import + call site:
-
-    # before
-    import os
-    platform = os.getenv("HERMES_SESSION_PLATFORM", "")
-
-    # after
-    from gateway.session_context import get_session_env
-    platform = get_session_env("HERMES_SESSION_PLATFORM", "")
-"""
-
-from contextvars import ContextVar
-from typing import Any
-
-# Sentinel to distinguish "never set in this context" from "explicitly set to empty".
-# When a contextvar holds _UNSET, we fall back to os.environ (CLI/cron compat).
-# When it holds "" (after clear_session_vars resets it), we return "" — no fallback.
-_UNSET: Any = object()
-
-# ---------------------------------------------------------------------------
-# Per-task session variables
-# ---------------------------------------------------------------------------
-
-_SESSION_PLATFORM: ContextVar = ContextVar("HERMES_SESSION_PLATFORM", default=_UNSET)
-_SESSION_CHAT_ID: ContextVar = ContextVar("HERMES_SESSION_CHAT_ID", default=_UNSET)
-_SESSION_CHAT_NAME: ContextVar = ContextVar("HERMES_SESSION_CHAT_NAME", default=_UNSET)
-_SESSION_THREAD_ID: ContextVar = ContextVar("HERMES_SESSION_THREAD_ID", default=_UNSET)
-_SESSION_USER_ID: ContextVar = ContextVar("HERMES_SESSION_USER_ID", default=_UNSET)
-_SESSION_USER_NAME: ContextVar = ContextVar("HERMES_SESSION_USER_NAME", default=_UNSET)
-_SESSION_KEY: ContextVar = ContextVar("HERMES_SESSION_KEY", default=_UNSET)
-
-_VAR_MAP = {
-    "HERMES_SESSION_PLATFORM": _SESSION_PLATFORM,
-    "HERMES_SESSION_CHAT_ID": _SESSION_CHAT_ID,
-    "HERMES_SESSION_CHAT_NAME": _SESSION_CHAT_NAME,
-    "HERMES_SESSION_THREAD_ID": _SESSION_THREAD_ID,
-    "HERMES_SESSION_USER_ID": _SESSION_USER_ID,
-    "HERMES_SESSION_USER_NAME": _SESSION_USER_NAME,
-    "HERMES_SESSION_KEY": _SESSION_KEY,
-}
-
-
-def set_session_vars(
-    platform: str = "",
-    chat_id: str = "",
-    chat_name: str = "",
-    thread_id: str = "",
-    user_id: str = "",
-    user_name: str = "",
-    session_key: str = "",
-) -> list:
-    """Set all session context variables and return reset tokens.
-
-    Call ``clear_session_vars(tokens)`` in a ``finally`` block to restore
-    the previous values when the handler exits.
-
-    Returns a list of ``Token`` objects (one per variable) that can be
-    passed to ``clear_session_vars``.
-    """
-    tokens = [
-        _SESSION_PLATFORM.set(platform),
-        _SESSION_CHAT_ID.set(chat_id),
-        _SESSION_CHAT_NAME.set(chat_name),
-        _SESSION_THREAD_ID.set(thread_id),
-        _SESSION_USER_ID.set(user_id),
-        _SESSION_USER_NAME.set(user_name),
-        _SESSION_KEY.set(session_key),
-    ]
-    return tokens
-
-
-def clear_session_vars(tokens: list) -> None:
-    """Mark session context variables as explicitly cleared.
-
-    Sets all variables to ``""`` so that ``get_session_env`` returns an empty
-    string instead of falling back to (potentially stale) ``os.environ``
-    values.  The *tokens* argument is accepted for API compatibility with
-    callers that saved the return value of ``set_session_vars``, but the
-    actual clearing uses ``var.set("")`` rather than ``var.reset(token)``
-    to ensure the "explicitly cleared" state is distinguishable from
-    "never set" (which holds the ``_UNSET`` sentinel).
-    """
-    for var in (
-        _SESSION_PLATFORM,
-        _SESSION_CHAT_ID,
-        _SESSION_CHAT_NAME,
-        _SESSION_THREAD_ID,
-        _SESSION_USER_ID,
-        _SESSION_USER_NAME,
-        _SESSION_KEY,
-    ):
-        var.set("")
-
-
-def get_session_env(name: str, default: str = "") -> str:
-    """Read a session context variable by its legacy ``HERMES_SESSION_*`` name.
-
-    Drop-in replacement for ``os.getenv("HERMES_SESSION_*", default)``.
-
-    Resolution order:
-    1. Context variable (set by the gateway for concurrency-safe access).
-       If the variable was explicitly set (even to ``""``) via
-       ``set_session_vars`` or ``clear_session_vars``, that value is
-       returned — **no fallback to os.environ**.
-    2. ``os.environ`` (only when the context variable was never set in
-       this context — i.e. CLI, cron scheduler, and test processes that
-       don't use ``set_session_vars`` at all).
-    3. *default*
-    """
-    import os
-
-    var = _VAR_MAP.get(name)
-    if var is not None:
-        value = var.get()
-        if value is not _UNSET:
-            return value
-    # Fall back to os.environ for CLI, cron, and test compatibility
-    return os.getenv(name, default)

gateway/status.py

@@ -14,8 +14,6 @@ concurrently under distinct configurations).
 import hashlib
 import json
 import os
-import signal
-import subprocess
 import sys
 from datetime import datetime, timezone
 from pathlib import Path
@@ -25,8 +23,6 @@ from typing import Any, Optional
 _GATEWAY_KIND = "hermes-gateway"
 _RUNTIME_STATUS_FILE = "gateway_state.json"
 _LOCKS_DIRNAME = "gateway-locks"
-_IS_WINDOWS = sys.platform == "win32"
-_UNSET = object()
 
 
 def _get_pid_path() -> Path:
@@ -53,33 +49,6 @@ def _utc_now_iso() -> str:
     return datetime.now(timezone.utc).isoformat()
 
 
-def terminate_pid(pid: int, *, force: bool = False) -> None:
-    """Terminate a PID with platform-appropriate force semantics.
-
-    POSIX uses SIGTERM/SIGKILL. Windows uses taskkill /T /F for true force-kill
-    because os.kill(..., SIGTERM) is not equivalent to a tree-killing hard stop.
-    """
-    if force and _IS_WINDOWS:
-        try:
-            result = subprocess.run(
-                ["taskkill", "/PID", str(pid), "/T", "/F"],
-                capture_output=True,
-                text=True,
-                timeout=10,
-            )
-        except FileNotFoundError:
-            os.kill(pid, signal.SIGTERM)
-            return
-
-        if result.returncode != 0:
-            details = (result.stderr or result.stdout or "").strip()
-            raise OSError(details or f"taskkill failed for PID {pid}")
-        return
-
-    sig = signal.SIGTERM if not force else getattr(signal, "SIGKILL", signal.SIGTERM)
-    os.kill(pid, sig)
-
-
 def _scope_hash(identity: str) -> str:
     return hashlib.sha256(identity.encode("utf-8")).hexdigest()[:16]
 
@@ -159,8 +128,6 @@ def _build_runtime_status_record() -> dict[str, Any]:
     payload.update({
         "gateway_state": "starting",
         "exit_reason": None,
-        "restart_requested": False,
-        "active_agents": 0,
         "platforms": {},
         "updated_at": _utc_now_iso(),
     })
@@ -219,14 +186,12 @@ def write_pid_file() -> None:
 
 def write_runtime_status(
     *,
-    gateway_state: Any = _UNSET,
-    exit_reason: Any = _UNSET,
-    restart_requested: Any = _UNSET,
-    active_agents: Any = _UNSET,
-    platform: Any = _UNSET,
-    platform_state: Any = _UNSET,
-    error_code: Any = _UNSET,
-    error_message: Any = _UNSET,
+    gateway_state: Optional[str] = None,
+    exit_reason: Optional[str] = None,
+    platform: Optional[str] = None,
+    platform_state: Optional[str] = None,
+    error_code: Optional[str] = None,
+    error_message: Optional[str] = None,
 ) -> None:
     """Persist gateway runtime health information for diagnostics/status."""
     path = _get_runtime_status_path()
@@ -237,22 +202,18 @@ def write_runtime_status(
     payload["start_time"] = _get_process_start_time(os.getpid())
     payload["updated_at"] = _utc_now_iso()
 
-    if gateway_state is not _UNSET:
+    if gateway_state is not None:
         payload["gateway_state"] = gateway_state
-    if exit_reason is not _UNSET:
+    if exit_reason is not None:
         payload["exit_reason"] = exit_reason
-    if restart_requested is not _UNSET:
-        payload["restart_requested"] = bool(restart_requested)
-    if active_agents is not _UNSET:
-        payload["active_agents"] = max(0, int(active_agents))
 
-    if platform is not _UNSET:
+    if platform is not None:
         platform_payload = payload["platforms"].get(platform, {})
-        if platform_state is not _UNSET:
+        if platform_state is not None:
             platform_payload["state"] = platform_state
-        if error_code is not _UNSET:
+        if error_code is not None:
             platform_payload["error_code"] = error_code
-        if error_message is not _UNSET:
+        if error_message is not None:
             platform_payload["error_message"] = error_message
         platform_payload["updated_at"] = _utc_now_iso()
         payload["platforms"][platform] = platform_payload
@@ -266,25 +227,9 @@ def read_runtime_status() -> Optional[dict[str, Any]]:
 
 
 def remove_pid_file() -> None:
-    """Remove the gateway PID file, but only if it belongs to this process.
-
-    During --replace handoffs, the old process's atexit handler can fire AFTER
-    the new process has written its own PID file.  Blindly removing the file
-    would delete the new process's record, leaving the gateway running with no
-    PID file (invisible to ``get_running_pid()``).
-    """
+    """Remove the gateway PID file if it exists."""
     try:
-        path = _get_pid_path()
-        record = _read_json_file(path)
-        if record is not None:
-            try:
-                file_pid = int(record["pid"])
-            except (KeyError, TypeError, ValueError):
-                file_pid = None
-            if file_pid is not None and file_pid != os.getpid():
-                # PID file belongs to a different process — leave it alone.
-                return
-        path.unlink(missing_ok=True)
+        _get_pid_path().unlink(missing_ok=True)
     except Exception:
         pass
 
@@ -306,15 +251,6 @@ def acquire_scoped_lock(scope: str, identity: str, metadata: Optional[dict[str,
     }
 
     existing = _read_json_file(lock_path)
-    if existing is None and lock_path.exists():
-        # Lock file exists but is empty or contains invalid JSON — treat as
-        # stale.  This happens when a previous process was killed between
-        # O_CREAT|O_EXCL and the subsequent json.dump() (e.g. DNS failure
-        # during rapid Slack reconnect retries).
-        try:
-            lock_path.unlink(missing_ok=True)
-        except OSError:
-            pass
     if existing:
         try:
             existing_pid = int(existing["pid"])

gateway/stream_consumer.py

@@ -32,18 +32,13 @@ _DONE = object()
 # new one so that subsequent text appears below tool progress messages.
 _NEW_SEGMENT = object()
 
-# Queue marker for a completed assistant commentary message emitted between
-# API/tool iterations (for example: "I'll inspect the repo first.").
-_COMMENTARY = object()
-
 
 @dataclass
 class StreamConsumerConfig:
     """Runtime config for a single stream consumer instance."""
-    edit_interval: float = 1.0
+    edit_interval: float = 0.3
     buffer_threshold: int = 40
     cursor: str = " ▉"
-    buffer_only: bool = False
 
 
 class GatewayStreamConsumer:
@@ -61,22 +56,6 @@ class GatewayStreamConsumer:
         await task         # wait for final edit
     """
 
-    # After this many consecutive flood-control failures, permanently disable
-    # progressive edits for the remainder of the stream.
-    _MAX_FLOOD_STRIKES = 3
-
-    # Reasoning/thinking tags that models emit inline in content.
-    # Must stay in sync with cli.py _OPEN_TAGS/_CLOSE_TAGS and
-    # run_agent.py _strip_think_blocks() tag variants.
-    _OPEN_THINK_TAGS = (
-        "<REASONING_SCRATCHPAD>", "<think>", "<reasoning>",
-        "<THINKING>", "<thinking>", "<thought>",
-    )
-    _CLOSE_THINK_TAGS = (
-        "</REASONING_SCRATCHPAD>", "</think>", "</reasoning>",
-        "</THINKING>", "</thinking>", "</thought>",
-    )
-
     def __init__(
         self,
         adapter: Any,
@@ -92,47 +71,18 @@ class GatewayStreamConsumer:
         self._accumulated = ""
         self._message_id: Optional[str] = None
         self._already_sent = False
-        self._edit_supported = True  # Disabled when progressive edits are no longer usable
+        self._edit_supported = True  # Disabled on first edit failure (Signal/Email/HA)
         self._last_edit_time = 0.0
         self._last_sent_text = ""   # Track last-sent text to skip redundant edits
         self._fallback_final_send = False
         self._fallback_prefix = ""
-        self._flood_strikes = 0         # Consecutive flood-control edit failures
-        self._current_edit_interval = self.cfg.edit_interval  # Adaptive backoff
-        self._final_response_sent = False
-
-        # Think-block filter state (mirrors CLI's _stream_delta tag suppression)
-        self._in_think_block = False
-        self._think_buffer = ""
 
     @property
     def already_sent(self) -> bool:
-        """True if at least one message was sent or edited during the run."""
+        """True if at least one message was sent/edited — signals the base
+        adapter to skip re-sending the final response."""
         return self._already_sent
 
-    @property
-    def final_response_sent(self) -> bool:
-        """True when the stream consumer delivered the final assistant reply."""
-        return self._final_response_sent
-
-    def on_segment_break(self) -> None:
-        """Finalize the current stream segment and start a fresh message."""
-        self._queue.put(_NEW_SEGMENT)
-
-    def on_commentary(self, text: str) -> None:
-        """Queue a completed interim assistant commentary message."""
-        if text:
-            self._queue.put((_COMMENTARY, text))
-
-    def _reset_segment_state(self, *, preserve_no_edit: bool = False) -> None:
-        if preserve_no_edit and self._message_id == "__no_edit__":
-            return
-        self._message_id = None
-        self._accumulated = ""
-        self._last_sent_text = ""
-        self._fallback_final_send = False
-        self._fallback_prefix = ""
-
     def on_delta(self, text: str) -> None:
         """Thread-safe callback — called from the agent's worker thread.
 
@@ -143,118 +93,12 @@ class GatewayStreamConsumer:
         if text:
             self._queue.put(text)
         elif text is None:
-            self.on_segment_break()
+            self._queue.put(_NEW_SEGMENT)
 
     def finish(self) -> None:
         """Signal that the stream is complete."""
         self._queue.put(_DONE)
 
-    # ── Think-block filtering ────────────────────────────────────────
-    # Models like MiniMax emit inline <think>...</think> blocks in their
-    # content.  The CLI's _stream_delta suppresses these via a state
-    # machine; we do the same here so gateway users never see raw
-    # reasoning tags.  The agent also strips them from the final
-    # response (run_agent.py _strip_think_blocks), but the stream
-    # consumer sends intermediate edits before that stripping happens.
-
-    def _filter_and_accumulate(self, text: str) -> None:
-        """Add a text delta to the accumulated buffer, suppressing think blocks.
-
-        Uses a state machine that tracks whether we are inside a
-        reasoning/thinking block.  Text inside such blocks is silently
-        discarded.  Partial tags at buffer boundaries are held back in
-        ``_think_buffer`` until enough characters arrive to decide.
-        """
-        buf = self._think_buffer + text
-        self._think_buffer = ""
-
-        while buf:
-            if self._in_think_block:
-                # Look for the earliest closing tag
-                best_idx = -1
-                best_len = 0
-                for tag in self._CLOSE_THINK_TAGS:
-                    idx = buf.find(tag)
-                    if idx != -1 and (best_idx == -1 or idx < best_idx):
-                        best_idx = idx
-                        best_len = len(tag)
-
-                if best_len:
-                    # Found closing tag — discard block, process remainder
-                    self._in_think_block = False
-                    buf = buf[best_idx + best_len:]
-                else:
-                    # No closing tag yet — hold tail that could be a
-                    # partial closing tag prefix, discard the rest.
-                    max_tag = max(len(t) for t in self._CLOSE_THINK_TAGS)
-                    self._think_buffer = buf[-max_tag:] if len(buf) > max_tag else buf
-                    return
-            else:
-                # Look for earliest opening tag at a block boundary
-                # (start of text / preceded by newline + optional whitespace).
-                # This prevents false positives when models *mention* tags
-                # in prose (e.g. "the <think> tag is used for…").
-                best_idx = -1
-                best_len = 0
-                for tag in self._OPEN_THINK_TAGS:
-                    search_start = 0
-                    while True:
-                        idx = buf.find(tag, search_start)
-                        if idx == -1:
-                            break
-                        # Block-boundary check (mirrors cli.py logic)
-                        if idx == 0:
-                            is_boundary = (
-                                not self._accumulated
-                                or self._accumulated.endswith("\n")
-                            )
-                        else:
-                            preceding = buf[:idx]
-                            last_nl = preceding.rfind("\n")
-                            if last_nl == -1:
-                                is_boundary = (
-                                    (not self._accumulated
-                                     or self._accumulated.endswith("\n"))
-                                    and preceding.strip() == ""
-                                )
-                            else:
-                                is_boundary = preceding[last_nl + 1:].strip() == ""
-
-                        if is_boundary and (best_idx == -1 or idx < best_idx):
-                            best_idx = idx
-                            best_len = len(tag)
-                            break  # first boundary hit for this tag is enough
-                        search_start = idx + 1
-
-                if best_len:
-                    # Emit text before the tag, enter think block
-                    self._accumulated += buf[:best_idx]
-                    self._in_think_block = True
-                    buf = buf[best_idx + best_len:]
-                else:
-                    # No opening tag — check for a partial tag at the tail
-                    held_back = 0
-                    for tag in self._OPEN_THINK_TAGS:
-                        for i in range(1, len(tag)):
-                            if buf.endswith(tag[:i]) and i > held_back:
-                                held_back = i
-                    if held_back:
-                        self._accumulated += buf[:-held_back]
-                        self._think_buffer = buf[-held_back:]
-                    else:
-                        self._accumulated += buf
-                    return
-
-    def _flush_think_buffer(self) -> None:
-        """Flush any held-back partial-tag buffer into accumulated text.
-
-        Called when the stream ends (got_done) so that partial text that
-        was held back waiting for a possible opening tag is not lost.
-        """
-        if self._think_buffer and not self._in_think_block:
-            self._accumulated += self._think_buffer
-            self._think_buffer = ""
-
     async def run(self) -> None:
         """Async task that drains the queue and edits the platform message."""
         # Platform message length limit — leave room for cursor + formatting
@@ -266,7 +110,6 @@ class GatewayStreamConsumer:
                 # Drain all available items from the queue
                 got_done = False
                 got_segment_break = False
-                commentary_text = None
                 while True:
                     try:
                         item = self._queue.get_nowait()
@@ -276,66 +119,24 @@ class GatewayStreamConsumer:
                         if item is _NEW_SEGMENT:
                             got_segment_break = True
                             break
-                        if isinstance(item, tuple) and len(item) == 2 and item[0] is _COMMENTARY:
-                            commentary_text = item[1]
-                            break
-                        self._filter_and_accumulate(item)
+                        self._accumulated += item
                     except queue.Empty:
                         break
 
-                # Flush any held-back partial-tag buffer on stream end
-                # so trailing text that was waiting for a potential open
-                # tag is not lost.
-                if got_done:
-                    self._flush_think_buffer()
-
                 # Decide whether to flush an edit
                 now = time.monotonic()
                 elapsed = now - self._last_edit_time
                 should_edit = (
                     got_done
                     or got_segment_break
-                    or commentary_text is not None
+                    or (elapsed >= self.cfg.edit_interval
+                        and self._accumulated)
+                    or len(self._accumulated) >= self.cfg.buffer_threshold
                 )
-                if not self.cfg.buffer_only:
-                    should_edit = should_edit or (
-                        (elapsed >= self._current_edit_interval
-                            and self._accumulated)
-                        or len(self._accumulated) >= self.cfg.buffer_threshold
-                    )
 
-                current_update_visible = False
                 if should_edit and self._accumulated:
                     # Split overflow: if accumulated text exceeds the platform
-                    # limit, split into properly sized chunks.
-                    if (
-                        len(self._accumulated) > _safe_limit
-                        and self._message_id is None
-                    ):
-                        # No existing message to edit (first message or after a
-                        # segment break).  Use truncate_message — the same
-                        # helper the non-streaming path uses — to split with
-                        # proper word/code-fence boundaries and chunk
-                        # indicators like "(1/2)".
-                        chunks = self.adapter.truncate_message(
-                            self._accumulated, _safe_limit
-                        )
-                        for chunk in chunks:
-                            await self._send_new_chunk(chunk, self._message_id)
-                        self._accumulated = ""
-                        self._last_sent_text = ""
-                        self._last_edit_time = time.monotonic()
-                        if got_done:
-                            self._final_response_sent = self._already_sent
-                            return
-                        if got_segment_break:
-                            self._message_id = None
-                            self._fallback_final_send = False
-                            self._fallback_prefix = ""
-                        continue
-
-                    # Existing message: edit it with the first chunk, then
-                    # start a new message for the overflow remainder.
+                    # limit, finalize the current message and start a new one.
                     while (
                         len(self._accumulated) > _safe_limit
                         and self._message_id is not None
@@ -345,23 +146,22 @@ class GatewayStreamConsumer:
                         if split_at < _safe_limit // 2:
                             split_at = _safe_limit
                         chunk = self._accumulated[:split_at]
-                        ok = await self._send_or_edit(chunk)
-                        if self._fallback_final_send or not ok:
-                            # Edit failed (or backed off due to flood control)
-                            # while attempting to split an oversized message.
-                            # Keep the full accumulated text intact so the
-                            # fallback final-send path can deliver the remaining
-                            # continuation without dropping content.
+                        await self._send_or_edit(chunk)
+                        if self._fallback_final_send:
+                            # Edit failed while attempting to split an oversized
+                            # message. Keep the full accumulated text intact so
+                            # the fallback final-send path can deliver the
+                            # remaining continuation without dropping content.
                             break
                         self._accumulated = self._accumulated[split_at:].lstrip("\n")
                         self._message_id = None
                         self._last_sent_text = ""
 
                     display_text = self._accumulated
-                    if not got_done and not got_segment_break and commentary_text is None:
+                    if not got_done and not got_segment_break:
                         display_text += self.cfg.cursor
 
-                    current_update_visible = await self._send_or_edit(display_text)
+                    await self._send_or_edit(display_text)
                     self._last_edit_time = time.monotonic()
 
                 if got_done:
@@ -372,56 +172,32 @@ class GatewayStreamConsumer:
                     if self._accumulated:
                         if self._fallback_final_send:
                             await self._send_fallback_final(self._accumulated)
-                        elif current_update_visible:
-                            self._final_response_sent = True
                         elif self._message_id:
-                            self._final_response_sent = await self._send_or_edit(self._accumulated)
+                            await self._send_or_edit(self._accumulated)
                         elif not self._already_sent:
-                            self._final_response_sent = await self._send_or_edit(self._accumulated)
+                            await self._send_or_edit(self._accumulated)
                     return
 
-                if commentary_text is not None:
-                    self._reset_segment_state()
-                    await self._send_commentary(commentary_text)
-                    self._last_edit_time = time.monotonic()
-                    self._reset_segment_state()
-
-                # Tool boundary: reset message state so the next text chunk
-                # creates a fresh message below any tool-progress messages.
-                #
-                # Exception: when _message_id is "__no_edit__" the platform
-                # never returned a real message ID (e.g. Signal, webhook with
-                # github_comment delivery).  Resetting to None would re-enter
-                # the "first send" path on every tool boundary and post one
-                # platform message per tool call — that is what caused 155
-                # comments under a single PR.  Instead, preserve the sentinel
-                # so the full continuation is delivered once via
-                # _send_fallback_final.
-                # (When editing fails mid-stream due to flood control the id is
-                # a real string like "msg_1", not "__no_edit__", so that case
-                # still resets and creates a fresh segment as intended.)
+                # Tool boundary: the should_edit block above already flushed
+                # accumulated text without a cursor.  Reset state so the next
+                # text chunk creates a fresh message below any tool-progress
+                # messages the gateway sent in between.
                 if got_segment_break:
-                    self._reset_segment_state(preserve_no_edit=True)
+                    self._message_id = None
+                    self._accumulated = ""
+                    self._last_sent_text = ""
+                    self._fallback_final_send = False
+                    self._fallback_prefix = ""
 
                 await asyncio.sleep(0.05)  # Small yield to not busy-loop
 
         except asyncio.CancelledError:
             # Best-effort final edit on cancellation
-            _best_effort_ok = False
             if self._accumulated and self._message_id:
                 try:
-                    _best_effort_ok = bool(await self._send_or_edit(self._accumulated))
+                    await self._send_or_edit(self._accumulated)
                 except Exception:
                     pass
-            # Only confirm final delivery if the best-effort send above
-            # actually succeeded OR if the final response was already
-            # confirmed before we were cancelled.  Previously this
-            # promoted any partial send (already_sent=True) to
-            # final_response_sent — which suppressed the gateway's
-            # fallback send even when only intermediate text (e.g.
-            # "Let me search…") had been delivered, not the real answer.
-            if _best_effort_ok and not self._final_response_sent:
-                self._final_response_sent = True
         except Exception as e:
             logger.error("Stream consumer error: %s", e)
 
@@ -450,34 +226,6 @@ class GatewayStreamConsumer:
         # Strip trailing whitespace/newlines but preserve leading content
         return cleaned.rstrip()
 
-    async def _send_new_chunk(self, text: str, reply_to_id: Optional[str]) -> Optional[str]:
-        """Send a new message chunk, optionally threaded to a previous message.
-
-        Returns the message_id so callers can thread subsequent chunks.
-        """
-        text = self._clean_for_display(text)
-        if not text.strip():
-            return reply_to_id
-        try:
-            meta = dict(self.metadata) if self.metadata else {}
-            result = await self.adapter.send(
-                chat_id=self.chat_id,
-                content=text,
-                reply_to=reply_to_id,
-                metadata=meta,
-            )
-            if result.success and result.message_id:
-                self._message_id = str(result.message_id)
-                self._already_sent = True
-                self._last_sent_text = text
-                return str(result.message_id)
-            else:
-                self._edit_supported = False
-                return reply_to_id
-        except Exception as e:
-            logger.error("Stream send chunk error: %s", e)
-            return reply_to_id
-
     def _visible_prefix(self) -> str:
         """Return the visible text already shown in the streamed message."""
         prefix = self._last_sent_text or ""
@@ -510,26 +258,14 @@ class GatewayStreamConsumer:
         return chunks
 
     async def _send_fallback_final(self, text: str) -> None:
-        """Send the final continuation after streaming edits stop working.
-
-        Retries each chunk once on flood-control failures with a short delay.
-        """
+        """Send the final continuation after streaming edits stop working."""
         final_text = self._clean_for_display(text)
         continuation = self._continuation_text(final_text)
         self._fallback_final_send = False
         if not continuation.strip():
             # Nothing new to send — the visible partial already matches final text.
-            # BUT: if final_text itself has meaningful content (e.g. a timeout
-            # message after a long tool call), the prefix-based continuation
-            # calculation may wrongly conclude "already shown" because the
-            # streamed prefix was from a *previous* segment (before the tool
-            # boundary).  In that case, send the full final_text as-is (#10807).
-            if final_text.strip() and final_text != self._visible_prefix():
-                continuation = final_text
-            else:
-                self._already_sent = True
-                self._final_response_sent = True
-                return
+            self._already_sent = True
+            return
 
         raw_limit = getattr(self.adapter, "MAX_MESSAGE_LENGTH", 4096)
         safe_limit = max(500, raw_limit - 100)
@@ -539,31 +275,17 @@ class GatewayStreamConsumer:
         last_successful_chunk = ""
         sent_any_chunk = False
         for chunk in chunks:
-            # Try sending with one retry on flood-control errors.
-            result = None
-            for attempt in range(2):
-                result = await self.adapter.send(
-                    chat_id=self.chat_id,
-                    content=chunk,
-                    metadata=self.metadata,
-                )
-                if result.success:
-                    break
-                if attempt == 0 and self._is_flood_error(result):
-                    logger.debug(
-                        "Flood control on fallback send, retrying in 3s"
-                    )
-                    await asyncio.sleep(3.0)
-                else:
-                    break  # non-flood error or second attempt failed
-
-            if not result or not result.success:
+            result = await self.adapter.send(
+                chat_id=self.chat_id,
+                content=chunk,
+                metadata=self.metadata,
+            )
+            if not result.success:
                 if sent_any_chunk:
                     # Some continuation text already reached the user. Suppress
                     # the base gateway final-send path so we don't resend the
                     # full response and create another duplicate.
                     self._already_sent = True
-                    self._final_response_sent = True
                     self._message_id = last_message_id
                     self._last_sent_text = last_successful_chunk
                     self._fallback_prefix = ""
@@ -581,100 +303,23 @@ class GatewayStreamConsumer:
 
         self._message_id = last_message_id
         self._already_sent = True
-        self._final_response_sent = True
         self._last_sent_text = chunks[-1]
         self._fallback_prefix = ""
 
-    def _is_flood_error(self, result) -> bool:
-        """Check if a SendResult failure is due to flood control / rate limiting."""
-        err = getattr(result, "error", "") or ""
-        err_lower = err.lower()
-        return "flood" in err_lower or "retry after" in err_lower or "rate" in err_lower
-
-    async def _try_strip_cursor(self) -> None:
-        """Best-effort edit to remove the cursor from the last visible message.
-
-        Called when entering fallback mode so the user doesn't see a stuck
-        cursor (▉) in the partial message.
-        """
-        if not self._message_id or self._message_id == "__no_edit__":
-            return
-        prefix = self._visible_prefix()
-        if not prefix or not prefix.strip():
-            return
-        try:
-            await self.adapter.edit_message(
-                chat_id=self.chat_id,
-                message_id=self._message_id,
-                content=prefix,
-            )
-            self._last_sent_text = prefix
-        except Exception:
-            pass  # best-effort — don't let this block the fallback path
-
-    async def _send_commentary(self, text: str) -> bool:
-        """Send a completed interim assistant commentary message."""
-        text = self._clean_for_display(text)
-        if not text.strip():
-            return False
-        try:
-            result = await self.adapter.send(
-                chat_id=self.chat_id,
-                content=text,
-                metadata=self.metadata,
-            )
-            # Note: do NOT set _already_sent = True here.
-            # Commentary messages are interim status updates (e.g. "Using browser
-            # tool..."), not the final response. Setting already_sent would cause
-            # the final response to be incorrectly suppressed when there are
-            # multiple tool calls. See: https://github.com/NousResearch/hermes-agent/issues/10454
-            return result.success
-        except Exception as e:
-            logger.error("Commentary send error: %s", e)
-            return False
-
-    async def _send_or_edit(self, text: str) -> bool:
-        """Send or edit the streaming message.
-
-        Returns True if the text was successfully delivered (sent or edited),
-        False otherwise.  Callers like the overflow split loop use this to
-        decide whether to advance past the delivered chunk.
-        """
+    async def _send_or_edit(self, text: str) -> None:
+        """Send or edit the streaming message."""
         # Strip MEDIA: directives so they don't appear as visible text.
         # Media files are delivered as native attachments after the stream
         # finishes (via _deliver_media_from_response in gateway/run.py).
         text = self._clean_for_display(text)
-        # A bare streaming cursor is not meaningful user-visible content and
-        # can render as a stray tofu/white-box message on some clients.
-        visible_without_cursor = text
-        if self.cfg.cursor:
-            visible_without_cursor = visible_without_cursor.replace(self.cfg.cursor, "")
-        _visible_stripped = visible_without_cursor.strip()
-        if not _visible_stripped:
-            return True  # cursor-only / whitespace-only update
         if not text.strip():
-            return True  # nothing to send is "success"
-        # Guard: do not create a brand-new standalone message when the only
-        # visible content is a handful of characters alongside the streaming
-        # cursor.  During rapid tool-calling the model often emits 1-2 tokens
-        # before switching to tool calls; the resulting "X ▉" message risks
-        # leaving the cursor permanently visible if the follow-up edit (to
-        # strip the cursor on segment break) is rate-limited by the platform.
-        # This was reported on Telegram, Matrix, and other clients where the
-        # ▉ block character renders as a visible white box ("tofu").
-        # Existing messages (edits) are unaffected — only first sends gated.
-        _MIN_NEW_MSG_CHARS = 4
-        if (self._message_id is None
-                and self.cfg.cursor
-                and self.cfg.cursor in text
-                and len(_visible_stripped) < _MIN_NEW_MSG_CHARS):
-            return True  # too short for a standalone message — accumulate more
+            return
         try:
             if self._message_id is not None:
                 if self._edit_supported:
                     # Skip if text is identical to what we last sent
                     if text == self._last_sent_text:
-                        return True
+                        return
                     # Edit existing message
                     result = await self.adapter.edit_message(
                         chat_id=self.chat_id,
@@ -684,52 +329,19 @@ class GatewayStreamConsumer:
                     if result.success:
                         self._already_sent = True
                         self._last_sent_text = text
-                        # Successful edit — reset flood strike counter
-                        self._flood_strikes = 0
-                        return True
                     else:
-                        # Edit failed.  If this looks like flood control / rate
-                        # limiting, use adaptive backoff: double the edit interval
-                        # and retry on the next cycle.  Only permanently disable
-                        # edits after _MAX_FLOOD_STRIKES consecutive failures.
-                        if self._is_flood_error(result):
-                            self._flood_strikes += 1
-                            self._current_edit_interval = min(
-                                self._current_edit_interval * 2, 10.0,
-                            )
-                            logger.debug(
-                                "Flood control on edit (strike %d/%d), "
-                                "backoff interval → %.1fs",
-                                self._flood_strikes,
-                                self._MAX_FLOOD_STRIKES,
-                                self._current_edit_interval,
-                            )
-                            if self._flood_strikes < self._MAX_FLOOD_STRIKES:
-                                # Don't disable edits yet — just slow down.
-                                # Update _last_edit_time so the next edit
-                                # respects the new interval.
-                                self._last_edit_time = time.monotonic()
-                                return False
-
-                        # Non-flood error OR flood strikes exhausted: enter
-                        # fallback mode — send only the missing tail once the
+                        # If an edit fails mid-stream (especially Telegram flood control),
+                        # stop progressive edits and send only the missing tail once the
                         # final response is available.
-                        logger.debug(
-                            "Edit failed (strikes=%d), entering fallback mode",
-                            self._flood_strikes,
-                        )
+                        logger.debug("Edit failed, disabling streaming for this adapter")
                         self._fallback_prefix = self._visible_prefix()
                         self._fallback_final_send = True
                         self._edit_supported = False
                         self._already_sent = True
-                        # Best-effort: strip the cursor from the last visible
-                        # message so the user doesn't see a stuck ▉.
-                        await self._try_strip_cursor()
-                        return False
                 else:
                     # Editing not supported — skip intermediate updates.
                     # The final response will be sent by the fallback path.
-                    return False
+                    pass
             else:
                 # First message — send new
                 result = await self.adapter.send(
@@ -737,25 +349,23 @@ class GatewayStreamConsumer:
                     content=text,
                     metadata=self.metadata,
                 )
-                if result.success:
-                    if result.message_id:
-                        self._message_id = result.message_id
-                    else:
-                        self._edit_supported = False
+                if result.success and result.message_id:
+                    self._message_id = result.message_id
                     self._already_sent = True
                     self._last_sent_text = text
-                    if not result.message_id:
-                        self._fallback_prefix = self._visible_prefix()
-                        self._fallback_final_send = True
-                        # Sentinel prevents re-entering the first-send path on
-                        # every delta/tool boundary when platforms accept a
-                        # message but do not return an editable message id.
-                        self._message_id = "__no_edit__"
-                    return True
+                elif result.success:
+                    # Platform accepted the message but returned no message_id
+                    # (e.g. Signal).  Can't edit without an ID — switch to
+                    # fallback mode: suppress intermediate deltas, send only
+                    # the missing tail once the final response is ready.
+                    self._already_sent = True
+                    self._edit_supported = False
+                    self._fallback_prefix = self._clean_for_display(text)
+                    self._fallback_final_send = True
+                    # Sentinel prevents re-entering this branch on every delta
+                    self._message_id = "__no_edit__"
                 else:
                     # Initial send failed — disable streaming for this session
                     self._edit_supported = False
-                    return False
         except Exception as e:
             logger.error("Stream send/edit error: %s", e)
-            return False