fix(file-sync): rollback _pushed_hashes on sync failure

Snapshot _pushed_hashes alongside _synced_files before the try block so both are restored atomically on failure. Previously a mid-sync exception (e.g. host file deleted between upload and hash) would leave _pushed_hashes partially updated while _synced_files rolled back, causing sync_back() to make wrong change-detection decisions.
fix(file-sync): resolve 4 bugbot findings in sync-back
2026-05-07 19:26:56 +08:00 · 2026-04-11 18:22:31 -07:00 · 2026-04-11 18:06:15 -07:00 · 2026-04-11 17:56:44 -07:00
1326 changed files with 23028 additions and 230502 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -5,7 +5,6 @@

 # Dependencies
 node_modules
-.venv

 # CI/CD
 .github
--- a/.env.example
+++ b/.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)
@@ -154,10 +136,6 @@
 # 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
--- a/.envrc
+++ b/.envrc
@@ -1,5 +1 @@
-watch_file pyproject.toml uv.lock
-watch_file ui-tui/package-lock.json ui-tui/package.json
-watch_file flake.nix flake.lock nix/devShell.nix nix/tui.nix nix/package.nix nix/python.nix
-
 use flake
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,2 +0,0 @@
-# Auto-generated files — collapse diffs and exclude from language stats
-web/package-lock.json linguist-generated=true
--- a/.github/ISSUE_TEMPLATE/bug_report.yml
+++ b/.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
--- a/.github/ISSUE_TEMPLATE/feature_request.yml
+++ b/.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
--- a/.github/ISSUE_TEMPLATE/setup_help.yml
+++ b/.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
--- a/.github/actions/nix-setup/action.yml
+++ b/.github/actions/nix-setup/action.yml
@@ -1,8 +0,0 @@
-name: 'Setup Nix'
-description: 'Install Nix with DeterminateSystems and enable magic-nix-cache'
-
-runs:
-  using: composite
-  steps:
-    - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25 # v22
-    - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39 # v13
--- a/.github/workflows/contributor-check.yml
+++ b/.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
--- a/.github/workflows/deploy-site.yml
+++ b/.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
--- a/.github/workflows/docker-publish.yml
+++ b/.github/workflows/docker-publish.yml
@@ -3,13 +3,8 @@ name: Docker Build and Publish
 on:
  push:
    branches: [main]
-    paths:
-      - '**/*.py'
-      - 'pyproject.toml'
-      - 'uv.lock'
-      - 'Dockerfile'
-      - 'docker/**'
-      - '.github/workflows/docker-publish.yml'
+  pull_request:
+    branches: [main]
  release:
    types: [published]

@@ -28,21 +23,21 @@ jobs:
    timeout-minutes: 60
    steps:
      - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
        with:
          submodules: recursive

      - name: Set up QEMU
-        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130  # v3
+        uses: docker/setup-qemu-action@v3

      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
+        uses: docker/setup-buildx-action@v3

      # Build amd64 only so we can `load` the image for smoke testing.
      # `load: true` cannot export a multi-arch manifest to the local daemon.
      # The multi-arch build follows on push to main / release.
      - name: Build image (amd64, smoke test)
-        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
+        uses: docker/build-push-action@v6
        with:
          context: .
          file: Dockerfile
@@ -54,14 +49,6 @@ jobs:

      - name: Test image starts
        run: |
-          # The image runs as the hermes user (UID 10000).  GitHub Actions
-          # creates /tmp/hermes-test root-owned by default, which hermes
-          # can't write to — chown it to match the in-container UID before
-          # bind-mounting.  Real users doing `docker run -v ~/.hermes:...`
-          # with their own UID hit the same issue and have their own
-          # remediations (HERMES_UID env var, or chown locally).
-          mkdir -p /tmp/hermes-test
-          sudo chown -R 10000:10000 /tmp/hermes-test
          docker run --rm \
            -v /tmp/hermes-test:/opt/data \
            --entrypoint /opt/hermes/docker/entrypoint.sh \
@@ -69,31 +56,36 @@ jobs:

      - name: Log in to Docker Hub
        if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
-        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9  # v3
+        uses: docker/login-action@v3
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}

      - name: Push multi-arch image (main branch)
        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
+        uses: docker/build-push-action@v6
        with:
          context: .
          file: Dockerfile
          push: true
          platforms: linux/amd64,linux/arm64
-          tags: nousresearch/hermes-agent:latest
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.sha }}
          cache-from: type=gha
          cache-to: type=gha,mode=max

      - name: Push multi-arch image (release)
        if: github.event_name == 'release'
-        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
+        uses: docker/build-push-action@v6
        with:
          context: .
          file: Dockerfile
          push: true
          platforms: linux/amd64,linux/arm64
-          tags: nousresearch/hermes-agent:${{ github.event.release.tag_name }}
+          tags: |
+            nousresearch/hermes-agent:latest
+            nousresearch/hermes-agent:${{ github.event.release.tag_name }}
+            nousresearch/hermes-agent:${{ github.sha }}
          cache-from: type=gha
          cache-to: type=gha,mode=max
--- a/.github/workflows/docs-site-checks.yml
+++ b/.github/workflows/docs-site-checks.yml
@@ -7,16 +7,13 @@ on:
      - '.github/workflows/docs-site-checks.yml'
  workflow_dispatch:

-permissions:
-  contents: read
-
 jobs:
  docs-site-checks:
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+      - uses: actions/checkout@v4

-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
+      - uses: actions/setup-node@v4
        with:
          node-version: 20
          cache: npm
@@ -26,7 +23,7 @@ jobs:
        run: npm ci
        working-directory: website

-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
+      - uses: actions/setup-python@v5
        with:
          python-version: '3.11'

--- a/.github/workflows/nix-lockfile-check.yml
+++ b/.github/workflows/nix-lockfile-check.yml
@@ -1,68 +0,0 @@
-name: Nix Lockfile Check
-
-on:
-  pull_request:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-  pull-requests: write
-
-concurrency:
-  group: nix-lockfile-check-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  check:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-
-      - uses: ./.github/actions/nix-setup
-
-      - name: Resolve head SHA
-        id: sha
-        shell: bash
-        run: |
-          FULL="${{ github.event.pull_request.head.sha || github.sha }}"
-          echo "full=$FULL" >> "$GITHUB_OUTPUT"
-          echo "short=${FULL:0:7}" >> "$GITHUB_OUTPUT"
-
-      - name: Check lockfile hashes
-        id: check
-        continue-on-error: true
-        env:
-          LINK_SHA: ${{ steps.sha.outputs.full }}
-        run: nix run .#fix-lockfiles -- --check
-
-      - name: Post sticky PR comment (stale)
-        if: steps.check.outputs.stale == 'true' && github.event_name == 'pull_request'
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          message: |
-            ### ⚠️ npm lockfile hash out of date
-
-            Checked against commit [`${{ steps.sha.outputs.short }}`](${{ github.server_url }}/${{ github.repository }}/commit/${{ steps.sha.outputs.full }}) (PR head at check time).
-
-            The `hash = "sha256-..."` line in these nix files no longer matches the committed `package-lock.json`:
-
-            ${{ steps.check.outputs.report }}
-
-            #### Apply the fix
-
-            - [ ] **Apply lockfile fix** — tick to push a commit with the correct hashes to this PR branch
-            - Or [run the Nix Lockfile Fix workflow](${{ github.server_url }}/${{ github.repository }}/actions/workflows/nix-lockfile-fix.yml) manually (pass PR `#${{ github.event.pull_request.number }}`)
-            - Or locally: `nix run .#fix-lockfiles -- --apply` and commit the diff
-
-      - name: Clear sticky PR comment (resolved)
-        if: steps.check.outputs.stale == 'false' && github.event_name == 'pull_request'
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          delete: true
-
-      - name: Fail if stale
-        if: steps.check.outputs.stale == 'true'
-        run: exit 1
--- a/.github/workflows/nix-lockfile-fix.yml
+++ b/.github/workflows/nix-lockfile-fix.yml
@@ -1,149 +0,0 @@
-name: Nix Lockfile Fix
-
-on:
-  workflow_dispatch:
-    inputs:
-      pr_number:
-        description: 'PR number to fix (leave empty to run on the selected branch)'
-        required: false
-        type: string
-  issue_comment:
-    types: [edited]
-
-permissions:
-  contents: write
-  pull-requests: write
-
-concurrency:
-  group: nix-lockfile-fix-${{ github.event.issue.number || github.event.inputs.pr_number || github.ref }}
-  cancel-in-progress: false
-
-jobs:
-  fix:
-    # Run on manual dispatch OR when a task-list checkbox in the sticky
-    # lockfile-check comment flips from `[ ]` to `[x]`.
-    if: |
-      github.event_name == 'workflow_dispatch' ||
-      (github.event_name == 'issue_comment'
-       && github.event.issue.pull_request != null
-       && contains(github.event.comment.body, '[x] **Apply lockfile fix**')
-       && !contains(github.event.changes.body.from, '[x] **Apply lockfile fix**'))
-    runs-on: ubuntu-latest
-    timeout-minutes: 25
-    steps:
-      - name: Authorize & resolve PR
-        id: resolve
-        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea  # v7.0.1
-        with:
-          script: |
-            // 1. Verify the actor has write access — applies to both checkbox
-            //    clicks and manual dispatch.
-            const { data: perm } =
-              await github.rest.repos.getCollaboratorPermissionLevel({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                username: context.actor,
-              });
-            if (!['admin', 'write', 'maintain'].includes(perm.permission)) {
-              core.setFailed(
-                `${context.actor} lacks write access (has: ${perm.permission})`
-              );
-              return;
-            }
-
-            // 2. Resolve which ref to check out.
-            let prNumber = '';
-            if (context.eventName === 'issue_comment') {
-              prNumber = String(context.payload.issue.number);
-            } else if (context.eventName === 'workflow_dispatch') {
-              prNumber = context.payload.inputs.pr_number || '';
-            }
-
-            if (!prNumber) {
-              core.setOutput('ref', context.ref.replace(/^refs\/heads\//, ''));
-              core.setOutput('repo', context.repo.repo);
-              core.setOutput('owner', context.repo.owner);
-              core.setOutput('pr', '');
-              return;
-            }
-
-            const { data: pr } = await github.rest.pulls.get({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              pull_number: Number(prNumber),
-            });
-            core.setOutput('ref', pr.head.ref);
-            core.setOutput('repo', pr.head.repo.name);
-            core.setOutput('owner', pr.head.repo.owner.login);
-            core.setOutput('pr', String(pr.number));
-
-      # Wipe the sticky lockfile-check comment to a "running" state as soon
-      # as the job is authorized, so the user sees their click was picked up
-      # before the ~minute of nix build work.
-      - name: Mark sticky as running
-        if: steps.resolve.outputs.pr != ''
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          number: ${{ steps.resolve.outputs.pr }}
-          message: |
-            ### 🔄 Applying lockfile fix…
-
-            Triggered by @${{ github.actor }} — [workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}).
-
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          repository: ${{ steps.resolve.outputs.owner }}/${{ steps.resolve.outputs.repo }}
-          ref: ${{ steps.resolve.outputs.ref }}
-          token: ${{ secrets.GITHUB_TOKEN }}
-          fetch-depth: 0
-
-      - uses: ./.github/actions/nix-setup
-
-      - name: Apply lockfile hashes
-        id: apply
-        run: nix run .#fix-lockfiles -- --apply
-
-      - name: Commit & push
-        if: steps.apply.outputs.changed == 'true'
-        shell: bash
-        run: |
-          set -euo pipefail
-          git config user.name 'github-actions[bot]'
-          git config user.email '41898282+github-actions[bot]@users.noreply.github.com'
-          git add nix/tui.nix nix/web.nix
-          git commit -m "fix(nix): refresh npm lockfile hashes"
-          git push
-
-      - name: Update sticky (applied)
-        if: steps.apply.outputs.changed == 'true' && steps.resolve.outputs.pr != ''
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          number: ${{ steps.resolve.outputs.pr }}
-          message: |
-            ### ✅ Lockfile fix applied
-
-            Pushed a commit refreshing the npm lockfile hashes — [workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}).
-
-      - name: Update sticky (already current)
-        if: steps.apply.outputs.changed == 'false' && steps.resolve.outputs.pr != ''
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          number: ${{ steps.resolve.outputs.pr }}
-          message: |
-            ### ✅ Lockfile hashes already current
-
-            Nothing to commit — [workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}).
-
-      - name: Update sticky (failed)
-        if: failure() && steps.resolve.outputs.pr != ''
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728  # v2.9.1
-        with:
-          header: nix-lockfile-check
-          number: ${{ steps.resolve.outputs.pr }}
-          message: |
-            ### ❌ Lockfile fix failed
-
-            See the [workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}) for logs.
--- a/.github/workflows/nix.yml
+++ b/.github/workflows/nix.yml
@@ -4,9 +4,15 @@ on:
  push:
    branches: [main]
  pull_request:
-
-permissions:
-  contents: read
+    paths:
+      - 'flake.nix'
+      - 'flake.lock'
+      - 'nix/**'
+      - 'pyproject.toml'
+      - 'uv.lock'
+      - 'hermes_cli/**'
+      - 'run_agent.py'
+      - 'acp_adapter/**'

 concurrency:
  group: nix-${{ github.ref }}
@@ -20,8 +26,9 @@ jobs:
    runs-on: ${{ matrix.os }}
    timeout-minutes: 30
    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
-      - uses: ./.github/actions/nix-setup
+      - uses: actions/checkout@v4
+      - uses: DeterminateSystems/nix-installer-action@ef8a148080ab6020fd15196c2084a2eea5ff2d25  # v22
+      - uses: DeterminateSystems/magic-nix-cache-action@565684385bcd71bad329742eefe8d12f2e765b39  # v13
      - name: Check flake
        if: runner.os == 'Linux'
        run: nix flake check --print-build-logs
--- a/.github/workflows/skills-index.yml
+++ b/.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
--- a/.github/workflows/supply-chain-audit.yml
+++ b/.github/workflows/supply-chain-audit.yml
@@ -3,39 +3,22 @@ name: Supply Chain Audit
 on:
  pull_request:
    types: [opened, synchronize, reopened]
-    paths:
-      - '**/*.py'
-      - '**/*.pth'
-      - '**/setup.py'
-      - '**/setup.cfg'
-      - '**/sitecustomize.py'
-      - '**/usercustomize.py'
-      - '**/__init__.pth'

 permissions:
  pull-requests: write
  contents: read

-# Narrow, high-signal scanner. Only fires on critical indicators of supply
-# chain attacks (e.g. the litellm-style payloads). Low-signal heuristics
-# (plain base64, plain exec/eval, dependency/Dockerfile/workflow edits,
-# Actions version unpinning, outbound POST/PUT) were intentionally
-# removed — they fired on nearly every PR and trained reviewers to ignore
-# the scanner. Keep this file's checks ruthlessly narrow: if you find
-# yourself adding WARNING-tier patterns here again, make a separate
-# advisory-only workflow instead.
-
 jobs:
  scan:
-    name: Scan PR for critical supply chain risks
+    name: Scan PR for supply chain risks
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4
        with:
          fetch-depth: 0

-      - name: Scan diff for critical patterns
+      - name: Scan diff for suspicious patterns
        id: scan
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -45,19 +28,19 @@ jobs:
          BASE="${{ github.event.pull_request.base.sha }}"
          HEAD="${{ github.event.pull_request.head.sha }}"

-          # Added lines only, excluding lockfiles.
+          # Get the full diff (added lines only)
          DIFF=$(git diff "$BASE".."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)

          FINDINGS=""
+          CRITICAL=false

          # --- .pth files (auto-execute on Python startup) ---
-          # The exact mechanism used in the litellm supply chain attack:
-          # https://github.com/BerriAI/litellm/issues/24512
          PTH_FILES=$(git diff --name-only "$BASE".."$HEAD" | grep '\.pth$' || true)
          if [ -n "$PTH_FILES" ]; then
+            CRITICAL=true
            FINDINGS="${FINDINGS}
          ### 🚨 CRITICAL: .pth file added or modified
-          Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required.
+          Python \`.pth\` files in \`site-packages/\` execute automatically when the interpreter starts — no import required. This is the exact mechanism used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512).

          **Files:**
          \`\`\`
@@ -66,12 +49,13 @@ jobs:
          "
          fi

-          # --- base64 decode + exec/eval on the same line (the litellm attack pattern) ---
+          # --- base64 + exec/eval combo (the litellm attack pattern) ---
          B64_EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|decodebytes|urlsafe_b64decode)' | grep -iE 'exec\(|eval\(' | head -10 || true)
          if [ -n "$B64_EXEC_HITS" ]; then
+            CRITICAL=true
            FINDINGS="${FINDINGS}
          ### 🚨 CRITICAL: base64 decode + exec/eval combo
-          Base64-decoded strings passed directly to exec/eval — the signature of hidden credential-stealing payloads.
+          This is the exact pattern used in the [litellm supply chain attack](https://github.com/BerriAI/litellm/issues/24512) — base64-decoded strings passed to exec/eval to hide credential-stealing payloads.

          **Matches:**
          \`\`\`
@@ -80,12 +64,41 @@ jobs:
          "
          fi

-          # --- subprocess with encoded/obfuscated command argument ---
-          PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|\\x[0-9a-f]{2}|chr\(' | head -10 || true)
+          # --- base64 decode/encode (alone — legitimate uses exist) ---
+          B64_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'base64\.(b64decode|b64encode|decodebytes|encodebytes|urlsafe_b64decode)|atob\(|btoa\(|Buffer\.from\(.*base64' | head -20 || true)
+          if [ -n "$B64_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: base64 encoding/decoding detected
+          Base64 has legitimate uses (images, JWT, etc.) but is also commonly used to obfuscate malicious payloads. Verify the usage is appropriate.
+
+          **Matches (first 20):**
+          \`\`\`
+          ${B64_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- exec/eval with string arguments ---
+          EXEC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E '(exec|eval)\s*\(' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert\|# ' | head -20 || true)
+          if [ -n "$EXEC_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: exec() or eval() usage
+          Dynamic code execution can hide malicious behavior, especially when combined with base64 or network fetches.
+
+          **Matches (first 20):**
+          \`\`\`
+          ${EXEC_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- subprocess with encoded/obfuscated commands ---
+          PROC_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -E 'subprocess\.(Popen|call|run)\s*\(' | grep -iE 'base64|decode|encode|\\x|chr\(' | head -10 || true)
          if [ -n "$PROC_HITS" ]; then
+            CRITICAL=true
            FINDINGS="${FINDINGS}
          ### 🚨 CRITICAL: subprocess with encoded/obfuscated command
-          Subprocess calls whose command strings are base64- or hex-encoded are a strong indicator of payload execution.
+          Subprocess calls with encoded arguments are a strong indicator of payload execution.

          **Matches:**
          \`\`\`
@@ -94,12 +107,25 @@ jobs:
          "
          fi

-          # --- Install-hook files (setup.py/sitecustomize/usercustomize/__init__.pth) ---
-          # These execute during pip install or interpreter startup.
-          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(^|/)(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
+          # --- Network calls to non-standard domains ---
+          EXFIL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'requests\.(post|put)\(|httpx\.(post|put)\(|urllib\.request\.urlopen' | grep -v '^\+\s*#' | grep -v 'test_\|mock\|assert' | head -10 || true)
+          if [ -n "$EXFIL_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: Outbound network calls (POST/PUT)
+          Outbound POST/PUT requests in new code could be data exfiltration. Verify the destination URLs are legitimate.
+
+          **Matches (first 10):**
+          \`\`\`
+          ${EXFIL_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- setup.py / setup.cfg install hooks ---
+          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(setup\.py|setup\.cfg|__init__\.pth|sitecustomize\.py|usercustomize\.py)$' || true)
          if [ -n "$SETUP_HITS" ]; then
            FINDINGS="${FINDINGS}
-          ### 🚨 CRITICAL: Install-hook file added or modified
+          ### ⚠️ WARNING: Install hook files modified
          These files can execute code during package installation or interpreter startup.

          **Files:**
@@ -109,31 +135,58 @@ jobs:
          "
          fi

+          # --- Compile/marshal/pickle (code object injection) ---
+          MARSHAL_HITS=$(echo "$DIFF" | grep -n '^\+' | grep -iE 'marshal\.loads|pickle\.loads|compile\(' | grep -v '^\+\s*#' | grep -v 'test_\|re\.compile\|ast\.compile' | head -10 || true)
+          if [ -n "$MARSHAL_HITS" ]; then
+            FINDINGS="${FINDINGS}
+          ### ⚠️ WARNING: marshal/pickle/compile usage
+          These can deserialize or construct executable code objects.
+
+          **Matches:**
+          \`\`\`
+          ${MARSHAL_HITS}
+          \`\`\`
+          "
+          fi
+
+          # --- Output results ---
          if [ -n "$FINDINGS" ]; then
            echo "found=true" >> "$GITHUB_OUTPUT"
+            if [ "$CRITICAL" = true ]; then
+              echo "critical=true" >> "$GITHUB_OUTPUT"
+            else
+              echo "critical=false" >> "$GITHUB_OUTPUT"
+            fi
+            # Write findings to a file (multiline env vars are fragile)
            echo "$FINDINGS" > /tmp/findings.md
          else
            echo "found=false" >> "$GITHUB_OUTPUT"
+            echo "critical=false" >> "$GITHUB_OUTPUT"
          fi

-      - name: Post critical finding comment
+      - name: Post warning comment
        if: steps.scan.outputs.found == 'true'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
-          BODY="## 🚨 CRITICAL Supply Chain Risk Detected
+          SEVERITY="⚠️ Supply Chain Risk Detected"
+          if [ "${{ steps.scan.outputs.critical }}" = "true" ]; then
+            SEVERITY="🚨 CRITICAL Supply Chain Risk Detected"
+          fi

-          This PR contains a pattern that has been used in real supply chain attacks. A maintainer must review the flagged code carefully before merging.
+          BODY="## ${SEVERITY}
+
+          This PR contains patterns commonly associated with supply chain attacks. This does **not** mean the PR is malicious — but these patterns require careful human review before merging.

          $(cat /tmp/findings.md)

          ---
-          *Scanner only fires on high-signal indicators: .pth files, base64+exec/eval combos, subprocess with encoded commands, or install-hook files. Low-signal warnings were removed intentionally — if you're seeing this comment, the finding is worth inspecting.*"
+          *Automated scan triggered by [supply-chain-audit](/.github/workflows/supply-chain-audit.yml). If this is a false positive, a maintainer can approve after manual review.*"

-          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY" || echo "::warning::Could not post PR comment (expected for fork PRs — GITHUB_TOKEN is read-only)"
+          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY"

      - name: Fail on critical findings
-        if: steps.scan.outputs.found == 'true'
+        if: steps.scan.outputs.critical == 'true'
        run: |
          echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the PR comment for details."
          exit 1
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -3,17 +3,8 @@ name: Tests
 on:
  push:
    branches: [main]
-    paths-ignore:
-      - '**/*.md'
-      - 'docs/**'
  pull_request:
    branches: [main]
-    paths-ignore:
-      - '**/*.md'
-      - 'docs/**'
-
-permissions:
-  contents: read

 # Cancel in-progress runs for the same PR/branch
 concurrency:
@@ -23,16 +14,16 @@ concurrency:
 jobs:
  test:
    runs-on: ubuntu-latest
-    timeout-minutes: 20
+    timeout-minutes: 10
    steps:
      - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4

      - name: Install system dependencies
        run: sudo apt-get update && sudo apt-get install -y ripgrep

      - name: Install uv
-        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
+        uses: astral-sh/setup-uv@v5

      - name: Set up Python 3.11
        run: uv python install 3.11
@@ -58,10 +49,10 @@ jobs:
    timeout-minutes: 10
    steps:
      - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
+        uses: actions/checkout@v4

      - name: Install uv
-        uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
+        uses: astral-sh/setup-uv@v5

      - name: Set up Python 3.11
        run: uv python install 3.11
--- a/.gitignore
+++ b/.gitignore
@@ -51,20 +51,10 @@ ignored/
 .worktrees/
 environments/benchmarks/evals/

-# Web UI build output
-hermes_cli/web_dist/
-
-# Web UI assets — synced from @nous-research/ui at build time via
-# `npm run sync-assets` (see web/package.json).
-web/public/fonts/
-web/public/ds-assets/
-
 # Release script temp files
 .release_notes.md
 mini-swe-agent/

 # Nix
 .direnv/
-.nix-stamps/
 result
-website/static/api/skills-index.json
--- a/.mailmap
+++ b/.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>
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -13,7 +13,7 @@ source venv/bin/activate  # ALWAYS activate before running Python
 ```
 hermes-agent/
 ├── run_agent.py          # AIAgent class — core conversation loop
-├── model_tools.py        # Tool orchestration, discover_builtin_tools(), handle_function_call()
+├── model_tools.py        # Tool orchestration, _discover_tools(), handle_function_call()
 ├── toolsets.py           # Toolset definitions, _HERMES_CORE_TOOLS list
 ├── cli.py                # HermesCLI class — interactive CLI orchestrator
 ├── hermes_state.py       # SessionDB — SQLite session store (FTS5 search)
@@ -55,20 +55,7 @@ hermes-agent/
 ├── gateway/              # Messaging platform gateway
 │   ├── run.py            # Main loop, slash commands, message dispatch
 │   ├── session.py        # SessionStore — conversation persistence
-│   └── platforms/        # Adapters: telegram, discord, slack, whatsapp, homeassistant, signal, qqbot
-├── ui-tui/               # Ink (React) terminal UI — `hermes --tui`
-│   ├── src/entry.tsx        # TTY gate + render()
-│   ├── src/app.tsx          # Main state machine and UI
-│   ├── src/gatewayClient.ts # Child process + JSON-RPC bridge
-│   ├── src/app/             # Decomposed app logic (event handler, slash handler, stores, hooks)
-│   ├── src/components/      # Ink components (branding, markdown, prompts, pickers, etc.)
-│   ├── src/hooks/           # useCompletion, useInputHistory, useQueue, useVirtualHistory
-│   └── src/lib/             # Pure helpers (history, osc52, text, rpc, messages)
-├── tui_gateway/          # Python JSON-RPC backend for the TUI
-│   ├── entry.py             # stdio entrypoint
-│   ├── server.py            # RPC handlers and session logic
-│   ├── render.py            # Optional rich/ANSI bridge
-│   └── slash_worker.py      # Persistent HermesCLI subprocess for slash commands
+│   └── platforms/        # Adapters: telegram, discord, slack, whatsapp, homeassistant, signal
 ├── acp_adapter/          # ACP server (VS Code / Zed / JetBrains integration)
 ├── cron/                 # Scheduler (jobs.py, scheduler.py)
 ├── environments/         # RL training environments (Atropos)
@@ -192,62 +179,9 @@ if canonical == "mycommand":

 ---

-## TUI Architecture (ui-tui + tui_gateway)
-
-The TUI is a full replacement for the classic (prompt_toolkit) CLI, activated via `hermes --tui` or `HERMES_TUI=1`.
-
-### Process Model
-
-```
-hermes --tui
-  └─ Node (Ink)  ──stdio JSON-RPC──  Python (tui_gateway)
-       │                                  └─ AIAgent + tools + sessions
-       └─ renders transcript, composer, prompts, activity
-```
-
-TypeScript owns the screen. Python owns sessions, tools, model calls, and slash command logic.
-
-### Transport
-
-Newline-delimited JSON-RPC over stdio. Requests from Ink, events from Python. See `tui_gateway/server.py` for the full method/event catalog.
-
-### Key Surfaces
-
-| Surface | Ink component | Gateway method |
-|---------|---------------|----------------|
-| Chat streaming | `app.tsx` + `messageLine.tsx` | `prompt.submit` → `message.delta/complete` |
-| Tool activity | `thinking.tsx` | `tool.start/progress/complete` |
-| Approvals | `prompts.tsx` | `approval.respond` ← `approval.request` |
-| Clarify/sudo/secret | `prompts.tsx`, `maskedPrompt.tsx` | `clarify/sudo/secret.respond` |
-| Session picker | `sessionPicker.tsx` | `session.list/resume` |
-| Slash commands | Local handler + fallthrough | `slash.exec` → `_SlashWorker`, `command.dispatch` |
-| Completions | `useCompletion` hook | `complete.slash`, `complete.path` |
-| Theming | `theme.ts` + `branding.tsx` | `gateway.ready` with skin data |
-
-### Slash Command Flow
-
-1. Built-in client commands (`/help`, `/quit`, `/clear`, `/resume`, `/copy`, `/paste`, etc.) handled locally in `app.tsx`
-2. Everything else → `slash.exec` (runs in persistent `_SlashWorker` subprocess) → `command.dispatch` fallback
-
-### Dev Commands
-
-```bash
-cd ui-tui
-npm install       # first time
-npm run dev       # watch mode (rebuilds hermes-ink + tsx --watch)
-npm start         # production
-npm run build     # full build (hermes-ink + tsc)
-npm run type-check # typecheck only (tsc --noEmit)
-npm run lint      # eslint
-npm run fmt       # prettier
-npm test          # vitest
-```
-
---
-
 ## Adding New Tools

-Requires changes in **2 files**:
+Requires changes in **3 files**:

 **1. Create `tools/your_tool.py`:**
 ```python
@@ -270,9 +204,9 @@ registry.register(
 )
 ```

-**2. Add to `toolsets.py`** — either `_HERMES_CORE_TOOLS` (all platforms) or a new toolset.
+**2. Add import** in `model_tools.py` `_discover_tools()` list.

-Auto-discovery: any `tools/*.py` file with a top-level `registry.register()` call is imported automatically — no manual import list to maintain.
+**3. Add to `toolsets.py`** — either `_HERMES_CORE_TOOLS` (all platforms) or a new toolset.

 The registry handles schema collection, dispatch, availability checking, and error wrapping. All handlers MUST return a JSON string.

@@ -524,94 +458,13 @@ def profile_env(tmp_path, monkeypatch):

 ## Testing

-**ALWAYS use `scripts/run_tests.sh`** — do not call `pytest` directly. The script enforces
-hermetic environment parity with CI (unset credential vars, TZ=UTC, LANG=C.UTF-8,
-4 xdist workers matching GHA ubuntu-latest). Direct `pytest` on a 16+ core
-developer machine with API keys set diverges from CI in ways that have caused
-multiple "works locally, fails in CI" incidents (and the reverse).
-
-```bash
-scripts/run_tests.sh                                  # full suite, CI-parity
-scripts/run_tests.sh tests/gateway/                   # one directory
-scripts/run_tests.sh tests/agent/test_foo.py::test_x  # one test
-scripts/run_tests.sh -v --tb=long                     # pass-through pytest flags
-```
-
-### Why the wrapper (and why the old "just call pytest" doesn't work)
-
-Five real sources of local-vs-CI drift the script closes:
-
-| | Without wrapper | With wrapper |
-|---|---|---|
-| Provider API keys | Whatever is in your env (auto-detects pool) | All `*_API_KEY`/`*_TOKEN`/etc. unset |
-| HOME / `~/.hermes/` | Your real config+auth.json | Temp dir per test |
-| Timezone | Local TZ (PDT etc.) | UTC |
-| Locale | Whatever is set | C.UTF-8 |
-| xdist workers | `-n auto` = all cores (20+ on a workstation) | `-n 4` matching CI |
-
-`tests/conftest.py` also enforces points 1-4 as an autouse fixture so ANY pytest
-invocation (including IDE integrations) gets hermetic behavior — but the wrapper
-is belt-and-suspenders.
-
-### Running without the wrapper (only if you must)
-
-If you can't use the wrapper (e.g. on Windows or inside an IDE that shells
-pytest directly), at minimum activate the venv and pass `-n 4`:
-
 ```bash
 source venv/bin/activate
-python -m pytest tests/ -q -n 4
+python -m pytest tests/ -q          # Full suite (~3000 tests, ~3 min)
+python -m pytest tests/test_model_tools.py -q   # Toolset resolution
+python -m pytest tests/test_cli_init.py -q       # CLI config loading
+python -m pytest tests/gateway/ -q               # Gateway tests
+python -m pytest tests/tools/ -q                 # Tool-level tests
 ```

-Worker count above 4 will surface test-ordering flakes that CI never sees.
-
 Always run the full suite before pushing changes.
-
-### Don't write change-detector tests
-
-A test is a **change-detector** if it fails whenever data that is **expected
-to change** gets updated — model catalogs, config version numbers,
-enumeration counts, hardcoded lists of provider models. These tests add no
-behavioral coverage; they just guarantee that routine source updates break
-CI and cost engineering time to "fix."
-
-**Do not write:**
-
-```python
-# catalog snapshot — breaks every model release
-assert "gemini-2.5-pro" in _PROVIDER_MODELS["gemini"]
-assert "MiniMax-M2.7" in models
-
-# config version literal — breaks every schema bump
-assert DEFAULT_CONFIG["_config_version"] == 21
-
-# enumeration count — breaks every time a skill/provider is added
-assert len(_PROVIDER_MODELS["huggingface"]) == 8
-```
-
-**Do write:**
-
-```python
-# behavior: does the catalog plumbing work at all?
-assert "gemini" in _PROVIDER_MODELS
-assert len(_PROVIDER_MODELS["gemini"]) >= 1
-
-# behavior: does migration bump the user's version to current latest?
-assert raw["_config_version"] == DEFAULT_CONFIG["_config_version"]
-
-# invariant: no plan-only model leaks into the legacy list
-assert not (set(moonshot_models) & coding_plan_only_models)
-
-# invariant: every model in the catalog has a context-length entry
-for m in _PROVIDER_MODELS["huggingface"]:
-    assert m.lower() in DEFAULT_CONTEXT_LENGTHS_LOWER
-```
-
-The rule: if the test reads like a snapshot of current data, delete it. If
-it reads like a contract about how two pieces of data must relate, keep it.
-When a PR adds a new provider/model and you want a test, make the test
-assert the relationship (e.g. "catalog entries all have context lengths"),
-not the specific names.
-
-Reviewers should reject new change-detector tests; authors should convert
-them into invariants before re-requesting review.
--- a/45
+++ b/45
@@ -1,54 +1,29 @@
-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 procps && \
    rm -rf /var/lib/apt/lists/*

-# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
-RUN useradd -u 10000 -m -d /opt/data hermes
-
-COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
-COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
-
+COPY . /opt/hermes
 WORKDIR /opt/hermes

-# ---------- Layer-cached dependency install ----------
-# Copy only package manifests first so npm install + Playwright are cached
-# unless the lockfiles themselves change.
-COPY package.json package-lock.json ./
-COPY web/package.json web/package-lock.json web/
-
-RUN npm install --prefer-offline --no-audit && \
+# Install Python and Node dependencies in one layer, no cache
+RUN pip install --no-cache-dir uv --break-system-packages && \
+    uv pip install --system --break-system-packages --no-cache -e ".[all]" && \
+    npm install --prefer-offline --no-audit && \
    npx playwright install --with-deps chromium --only-shell && \
-    (cd web && npm install --prefer-offline --no-audit) && \
+    cd /opt/hermes/scripts/whatsapp-bridge && \
+    npm install --prefer-offline --no-audit && \
    npm cache clean --force

-# ---------- Source code ----------
-# .dockerignore excludes node_modules, so the installs above survive.
-COPY --chown=hermes:hermes . .
+WORKDIR /opt/hermes
+RUN chmod +x /opt/hermes/docker/entrypoint.sh

-# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
-RUN cd web && npm run build
-
-# ---------- Python virtualenv ----------
-RUN chown hermes:hermes /opt/hermes
-USER hermes
-RUN uv venv && \
-    uv pip install --no-cache-dir -e ".[all]"
-
-# ---------- Runtime ----------
-ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
 ENV HERMES_HOME=/opt/data
 VOLUME [ "/opt/data" ]
 ENTRYPOINT [ "/opt/hermes/docker/entrypoint.sh" ]
--- a/README.md
+++ b/README.md
@@ -13,7 +13,7 @@

 **The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.

-Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
+Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.

 <table>
 <tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr>
@@ -141,18 +141,11 @@ See `hermes claw migrate --help` for all options, or use the `openclaw-migration

 We welcome contributions! See the [Contributing Guide](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) for development setup, code style, and PR process.

-Quick start for contributors — clone and go with `setup-hermes.sh`:
+Quick start for contributors:

 ```bash
 git clone https://github.com/NousResearch/hermes-agent.git
 cd hermes-agent
-./setup-hermes.sh     # installs uv, creates venv, installs .[all], symlinks ~/.local/bin/hermes
-./hermes              # auto-detects the venv, no need to `source` first
-```
-
-Manual path (equivalent to the above):
-
-```bash
 curl -LsSf https://astral.sh/uv/install.sh | sh
 uv venv venv --python 3.11
 source venv/bin/activate
@@ -174,7 +167,6 @@ 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.

 ---

--- a/RELEASE_v0.10.0.md
+++ b/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)
--- a/RELEASE_v0.9.0.md
+++ b/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)
--- a/SECURITY.md
+++ b/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.
--- a/acp_adapter/entry.py
+++ b/acp_adapter/entry.py
@@ -20,46 +20,6 @@ from pathlib import Path
 from hermes_constants import get_hermes_home


-# Methods clients send as periodic liveness probes. They are not part of the
-# ACP schema, so the acp router correctly returns JSON-RPC -32601 to the
-# caller — but the supervisor task that dispatches the request then surfaces
-# the raised RequestError via ``logging.exception("Background task failed")``,
-# which dumps a traceback to stderr every probe interval. Clients like
-# acp-bridge already treat the -32601 response as "agent alive", so the
-# traceback is pure noise. We keep the protocol response intact and only
-# silence the stderr noise for this specific benign case.
-_BENIGN_PROBE_METHODS = frozenset({"ping", "health", "healthcheck"})
-
-
-class _BenignProbeMethodFilter(logging.Filter):
-    """Suppress acp 'Background task failed' tracebacks caused by unknown
-    liveness-probe methods (e.g. ``ping``) while leaving every other
-    background-task error — including method_not_found for any non-probe
-    method — visible in stderr.
-    """
-
-    def filter(self, record: logging.LogRecord) -> bool:
-        if record.getMessage() != "Background task failed":
-            return True
-        exc_info = record.exc_info
-        if not exc_info:
-            return True
-        exc = exc_info[1]
-        # Imported lazily so this module stays importable when the optional
-        # ``agent-client-protocol`` dependency is not installed.
-        try:
-            from acp.exceptions import RequestError
-        except ImportError:
-            return True
-        if not isinstance(exc, RequestError):
-            return True
-        if getattr(exc, "code", None) != -32601:
-            return True
-        data = getattr(exc, "data", None)
-        method = data.get("method") if isinstance(data, dict) else None
-        return method not in _BENIGN_PROBE_METHODS
-
-
 def _setup_logging() -> None:
    """Route all logging to stderr so stdout stays clean for ACP stdio."""
    handler = logging.StreamHandler(sys.stderr)
@@ -69,7 +29,6 @@ def _setup_logging() -> None:
            datefmt="%Y-%m-%d %H:%M:%S",
        )
    )
-    handler.addFilter(_BenignProbeMethodFilter())
    root = logging.getLogger()
    root.handlers.clear()
    root.addHandler(handler)
--- a/acp_adapter/events.py
+++ b/acp_adapter/events.py
@@ -49,7 +49,6 @@ def make_tool_progress_cb(
    session_id: str,
    loop: asyncio.AbstractEventLoop,
    tool_call_ids: Dict[str, Deque[str]],
-    tool_call_meta: Dict[str, Dict[str, Any]],
 ) -> Callable:
    """Create a ``tool_progress_callback`` for AIAgent.

@@ -85,16 +84,6 @@ def make_tool_progress_cb(
            tool_call_ids[name] = queue
        queue.append(tc_id)

-        snapshot = None
-        if name in {"write_file", "patch", "skill_manage"}:
-            try:
-                from agent.display import capture_local_edit_snapshot
-
-                snapshot = capture_local_edit_snapshot(name, args)
-            except Exception:
-                logger.debug("Failed to capture ACP edit snapshot for %s", name, exc_info=True)
-        tool_call_meta[tc_id] = {"args": args, "snapshot": snapshot}
-
        update = build_tool_start(tc_id, name, args)
        _send_update(conn, session_id, loop, update)

@@ -130,7 +119,6 @@ def make_step_cb(
    session_id: str,
    loop: asyncio.AbstractEventLoop,
    tool_call_ids: Dict[str, Deque[str]],
-    tool_call_meta: Dict[str, Dict[str, Any]],
 ) -> Callable:
    """Create a ``step_callback`` for AIAgent.

@@ -144,12 +132,10 @@ def make_step_cb(
            for tool_info in prev_tools:
                tool_name = None
                result = None
-                function_args = None

                if isinstance(tool_info, dict):
                    tool_name = tool_info.get("name") or tool_info.get("function_name")
                    result = tool_info.get("result") or tool_info.get("output")
-                    function_args = tool_info.get("arguments") or tool_info.get("args")
                elif isinstance(tool_info, str):
                    tool_name = tool_info

@@ -159,13 +145,8 @@ def make_step_cb(
                    tool_call_ids[tool_name] = queue
                if tool_name and queue:
                    tc_id = queue.popleft()
-                    meta = tool_call_meta.pop(tc_id, {})
                    update = build_tool_complete(
-                        tc_id,
-                        tool_name,
-                        result=str(result) if result is not None else None,
-                        function_args=function_args or meta.get("args"),
-                        snapshot=meta.get("snapshot"),
+                        tc_id, tool_name, result=str(result) if result is not None else None
                    )
                    _send_update(conn, session_id, loop, update)
                    if not queue:
--- a/acp_adapter/permissions.py
+++ b/acp_adapter/permissions.py
@@ -63,9 +63,6 @@ def make_approval_callback(
            logger.warning("Permission request timed out or failed: %s", exc)
            return "deny"

-        if response is None:
-            return "deny"
-
        outcome = response.outcome
        if isinstance(outcome, AllowedOutcome):
            option_id = outcome.option_id
--- a/acp_adapter/server.py
+++ b/acp_adapter/server.py
@@ -4,7 +4,6 @@ from __future__ import annotations

 import asyncio
 import logging
-import os
 from collections import defaultdict, deque
 from concurrent.futures import ThreadPoolExecutor
 from typing import Any, Deque, Optional
@@ -27,7 +26,6 @@ from acp.schema import (
    McpServerHttp,
    McpServerSse,
    McpServerStdio,
-    ModelInfo,
    NewSessionResponse,
    PromptResponse,
    ResumeSessionResponse,
@@ -38,7 +36,6 @@ from acp.schema import (
    SessionCapabilities,
    SessionForkCapabilities,
    SessionListCapabilities,
-    SessionModelState,
    SessionResumeCapabilities,
    SessionInfo,
    TextContentBlock,
@@ -52,7 +49,7 @@ try:
 except ImportError:
    from acp.schema import AuthMethod as AuthMethodAgent  # type: ignore[attr-defined]

-from acp_adapter.auth import detect_provider
+from acp_adapter.auth import detect_provider, has_provider
 from acp_adapter.events import (
    make_message_cb,
    make_step_cb,
@@ -72,11 +69,6 @@ except Exception:
 # Thread pool for running AIAgent (synchronous) in parallel.
 _executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="acp-agent")

-# Server-side page size for list_sessions. The ACP ListSessionsRequest schema
-# does not expose a client-side limit, so this is a fixed cap that clients
-# paginate against using `cursor` / `next_cursor`.
-_LIST_SESSIONS_PAGE_SIZE = 50
-

 def _extract_text(
    prompt: list[
@@ -155,98 +147,6 @@ class HermesACPAgent(acp.Agent):
        self._conn = conn
        logger.info("ACP client connected")

-    @staticmethod
-    def _encode_model_choice(provider: str | None, model: str | None) -> str:
-        """Encode a model selection so ACP clients can keep provider context."""
-        raw_model = str(model or "").strip()
-        if not raw_model:
-            return ""
-        raw_provider = str(provider or "").strip().lower()
-        if not raw_provider:
-            return raw_model
-        return f"{raw_provider}:{raw_model}"
-
-    def _build_model_state(self, state: SessionState) -> SessionModelState | None:
-        """Return the ACP model selector payload for editors like Zed."""
-        model = str(state.model or getattr(state.agent, "model", "") or "").strip()
-        provider = getattr(state.agent, "provider", None) or detect_provider() or "openrouter"
-
-        try:
-            from hermes_cli.models import curated_models_for_provider, normalize_provider, provider_label
-
-            normalized_provider = normalize_provider(provider)
-            provider_name = provider_label(normalized_provider)
-            available_models: list[ModelInfo] = []
-            seen_ids: set[str] = set()
-
-            for model_id, description in curated_models_for_provider(normalized_provider):
-                rendered_model = str(model_id or "").strip()
-                if not rendered_model:
-                    continue
-                choice_id = self._encode_model_choice(normalized_provider, rendered_model)
-                if choice_id in seen_ids:
-                    continue
-                desc_parts = [f"Provider: {provider_name}"]
-                if description:
-                    desc_parts.append(str(description).strip())
-                if rendered_model == model:
-                    desc_parts.append("current")
-                available_models.append(
-                    ModelInfo(
-                        model_id=choice_id,
-                        name=rendered_model,
-                        description=" • ".join(part for part in desc_parts if part),
-                    )
-                )
-                seen_ids.add(choice_id)
-
-            current_model_id = self._encode_model_choice(normalized_provider, model)
-            if current_model_id and current_model_id not in seen_ids:
-                available_models.insert(
-                    0,
-                    ModelInfo(
-                        model_id=current_model_id,
-                        name=model,
-                        description=f"Provider: {provider_name} • current",
-                    ),
-                )
-
-            if available_models:
-                return SessionModelState(
-                    available_models=available_models,
-                    current_model_id=current_model_id or available_models[0].model_id,
-                )
-        except Exception:
-            logger.debug("Could not build ACP model state", exc_info=True)
-
-        if not model:
-            return None
-
-        fallback_choice = self._encode_model_choice(provider, model)
-        return SessionModelState(
-            available_models=[ModelInfo(model_id=fallback_choice, name=model)],
-            current_model_id=fallback_choice,
-        )
-
-    @staticmethod
-    def _resolve_model_selection(raw_model: str, current_provider: str) -> tuple[str, str]:
-        """Resolve ``provider:model`` input into the provider and normalized model id."""
-        target_provider = current_provider
-        new_model = raw_model.strip()
-
-        try:
-            from hermes_cli.models import detect_provider_for_model, parse_model_input
-
-            target_provider, new_model = parse_model_input(new_model, current_provider)
-            if target_provider == current_provider:
-                detected = detect_provider_for_model(new_model, current_provider)
-                if detected:
-                    target_provider, new_model = detected
-        except Exception:
-            logger.debug("Provider detection failed, using model as-is", exc_info=True)
-
-        return target_provider, new_model
-
    async def _register_session_mcp_servers(
        self,
        state: SessionState,
@@ -357,18 +257,9 @@ class HermesACPAgent(acp.Agent):
        )

    async def authenticate(self, method_id: str, **kwargs: Any) -> AuthenticateResponse | None:
-        # Only accept authenticate() calls whose method_id matches the
-        # provider we advertised in initialize(). Without this check,
-        # authenticate() would acknowledge any method_id as long as the
-        # server has provider credentials configured — harmless under
-        # Hermes' threat model (ACP is stdio-only, local-trust), but poor
-        # API hygiene and confusing if ACP ever grows multi-method auth.
-        provider = detect_provider()
-        if not provider:
-            return None
-        if not isinstance(method_id, str) or method_id.strip().lower() != provider:
-            return None
-        return AuthenticateResponse()
+        if has_provider():
+            return AuthenticateResponse()
+        return None

    # ---- Session management -------------------------------------------------

@@ -382,10 +273,7 @@ class HermesACPAgent(acp.Agent):
        await self._register_session_mcp_servers(state, mcp_servers)
        logger.info("New session %s (cwd=%s)", state.session_id, cwd)
        self._schedule_available_commands_update(state.session_id)
-        return NewSessionResponse(
-            session_id=state.session_id,
-            models=self._build_model_state(state),
-        )
+        return NewSessionResponse(session_id=state.session_id)

    async def load_session(
        self,
@@ -401,7 +289,7 @@ class HermesACPAgent(acp.Agent):
        await self._register_session_mcp_servers(state, mcp_servers)
        logger.info("Loaded session %s", session_id)
        self._schedule_available_commands_update(session_id)
-        return LoadSessionResponse(models=self._build_model_state(state))
+        return LoadSessionResponse()

    async def resume_session(
        self,
@@ -417,7 +305,7 @@ class HermesACPAgent(acp.Agent):
        await self._register_session_mcp_servers(state, mcp_servers)
        logger.info("Resumed session %s", state.session_id)
        self._schedule_available_commands_update(state.session_id)
-        return ResumeSessionResponse(models=self._build_model_state(state))
+        return ResumeSessionResponse()

    async def cancel(self, session_id: str, **kwargs: Any) -> None:
        state = self.session_manager.get_session(session_id)
@@ -452,44 +340,12 @@ class HermesACPAgent(acp.Agent):
        cwd: str | None = None,
        **kwargs: Any,
    ) -> ListSessionsResponse:
-        """List ACP sessions with optional ``cwd`` filtering and cursor pagination.
-
-        ``cwd`` is passed through to ``SessionManager.list_sessions`` which already
-        normalizes and filters by working directory. ``cursor`` is a ``session_id``
-        previously returned as ``next_cursor``; results resume after that entry.
-        Server-side page size is capped at ``_LIST_SESSIONS_PAGE_SIZE``; when more
-        results remain, ``next_cursor`` is set to the last returned ``session_id``.
-        """
-        infos = self.session_manager.list_sessions(cwd=cwd)
-
-        if cursor:
-            for idx, s in enumerate(infos):
-                if s["session_id"] == cursor:
-                    infos = infos[idx + 1:]
-                    break
-            else:
-                # Unknown cursor -> empty page (do not fall back to full list).
-                infos = []
-
-        has_more = len(infos) > _LIST_SESSIONS_PAGE_SIZE
-        infos = infos[:_LIST_SESSIONS_PAGE_SIZE]
-
-        sessions = []
-        for s in infos:
-            updated_at = s.get("updated_at")
-            if updated_at is not None and not isinstance(updated_at, str):
-                updated_at = str(updated_at)
-            sessions.append(
-                SessionInfo(
-                    session_id=s["session_id"],
-                    cwd=s["cwd"],
-                    title=s.get("title"),
-                    updated_at=updated_at,
-                )
-            )
-
-        next_cursor = sessions[-1].session_id if has_more and sessions else None
-        return ListSessionsResponse(sessions=sessions, next_cursor=next_cursor)
+        infos = self.session_manager.list_sessions()
+        sessions = [
+            SessionInfo(session_id=s["session_id"], cwd=s["cwd"])
+            for s in infos
+        ]
+        return ListSessionsResponse(sessions=sessions)

    # ---- Prompt (core) ------------------------------------------------------

@@ -533,13 +389,12 @@ class HermesACPAgent(acp.Agent):
            state.cancel_event.clear()

        tool_call_ids: dict[str, Deque[str]] = defaultdict(deque)
-        tool_call_meta: dict[str, dict[str, Any]] = {}
        previous_approval_cb = None

        if conn:
-            tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
+            tool_progress_cb = make_tool_progress_cb(conn, session_id, loop, tool_call_ids)
            thinking_cb = make_thinking_cb(conn, session_id, loop)
-            step_cb = make_step_cb(conn, session_id, loop, tool_call_ids, tool_call_meta)
+            step_cb = make_step_cb(conn, session_id, loop, tool_call_ids)
            message_cb = make_message_cb(conn, session_id, loop)
            approval_cb = make_approval_callback(conn.request_permission, loop, session_id)
        else:
@@ -555,32 +410,15 @@ class HermesACPAgent(acp.Agent):
        agent.step_callback = step_cb
        agent.message_callback = message_cb

-        # Approval callback is per-thread (thread-local, GHSA-qg5c-hvr5-hjgr).
-        # Set it INSIDE _run_agent so the TLS write happens in the executor
-        # thread — setting it here would write to the event-loop thread's TLS,
-        # not the executor's. Also set HERMES_INTERACTIVE so approval.py
-        # takes the CLI-interactive path (which calls the registered
-        # callback via prompt_dangerous_approval) instead of the
-        # non-interactive auto-approve branch (GHSA-96vc-wcxf-jjff).
-        # ACP's conn.request_permission maps cleanly to the interactive
-        # callback shape — not the gateway-queue HERMES_EXEC_ASK path,
-        # which requires a notify_cb registered in _gateway_notify_cbs.
-        previous_approval_cb = None
-        previous_interactive = None
+        if approval_cb:
+            try:
+                from tools import terminal_tool as _terminal_tool
+                previous_approval_cb = getattr(_terminal_tool, "_approval_callback", None)
+                _terminal_tool.set_approval_callback(approval_cb)
+            except Exception:
+                logger.debug("Could not set ACP approval callback", exc_info=True)

        def _run_agent() -> dict:
-            nonlocal previous_approval_cb, previous_interactive
-            if approval_cb:
-                try:
-                    from tools import terminal_tool as _terminal_tool
-                    previous_approval_cb = _terminal_tool._get_approval_callback()
-                    _terminal_tool.set_approval_callback(approval_cb)
-                except Exception:
-                    logger.debug("Could not set ACP approval callback", exc_info=True)
-            # Signal to tools.approval that we have an interactive callback
-            # and the non-interactive auto-approve path must not fire.
-            previous_interactive = os.environ.get("HERMES_INTERACTIVE")
-            os.environ["HERMES_INTERACTIVE"] = "1"
            try:
                result = agent.run_conversation(
                    user_message=user_text,
@@ -592,11 +430,6 @@ class HermesACPAgent(acp.Agent):
                logger.exception("Agent error in session %s", session_id)
                return {"final_response": f"Error: {e}", "messages": state.history}
            finally:
-                # Restore HERMES_INTERACTIVE.
-                if previous_interactive is None:
-                    os.environ.pop("HERMES_INTERACTIVE", None)
-                else:
-                    os.environ["HERMES_INTERACTIVE"] = previous_interactive
                if approval_cb:
                    try:
                        from tools import terminal_tool as _terminal_tool
@@ -616,19 +449,6 @@ class HermesACPAgent(acp.Agent):
            self.session_manager.save_session(session_id)

        final_response = result.get("final_response", "")
-        if final_response:
-            try:
-                from agent.title_generator import maybe_auto_title
-
-                maybe_auto_title(
-                    self.session_manager._get_db(),
-                    session_id,
-                    user_text,
-                    final_response,
-                    state.history,
-                )
-            except Exception:
-                logger.debug("Failed to auto-title ACP session %s", session_id, exc_info=True)
        if final_response and conn:
            update = acp.update_agent_message_text(final_response)
            await conn.session_update(session_id, update)
@@ -673,8 +493,8 @@ class HermesACPAgent(acp.Agent):
            await self._conn.session_update(
                session_id=session_id,
                update=AvailableCommandsUpdate(
-                    session_update="available_commands_update",
-                    available_commands=self._available_commands(),
+                    sessionUpdate="available_commands_update",
+                    availableCommands=self._available_commands(),
                ),
            )
        except Exception:
@@ -736,15 +556,27 @@ class HermesACPAgent(acp.Agent):
            provider = getattr(state.agent, "provider", None) or "auto"
            return f"Current model: {model}\nProvider: {provider}"

+        new_model = args.strip()
+        target_provider = None
        current_provider = getattr(state.agent, "provider", None) or "openrouter"
-        target_provider, new_model = self._resolve_model_selection(args, current_provider)
+
+        # Auto-detect provider for the requested model
+        try:
+            from hermes_cli.models import parse_model_input, detect_provider_for_model
+            target_provider, new_model = parse_model_input(new_model, current_provider)
+            if target_provider == current_provider:
+                detected = detect_provider_for_model(new_model, current_provider)
+                if detected:
+                    target_provider, new_model = detected
+        except Exception:
+            logger.debug("Provider detection failed, using model as-is", exc_info=True)

        state.model = new_model
        state.agent = self.session_manager._make_agent(
            session_id=state.session_id,
            cwd=state.cwd,
            model=new_model,
-            requested_provider=target_provider,
+            requested_provider=target_provider or current_provider,
        )
        self.session_manager.save_session(state.session_id)
        provider_label = getattr(state.agent, "provider", None) or target_provider or current_provider
@@ -846,30 +678,20 @@ class HermesACPAgent(acp.Agent):
        """Switch the model for a session (called by ACP protocol)."""
        state = self.session_manager.get_session(session_id)
        if state:
+            state.model = model_id
            current_provider = getattr(state.agent, "provider", None)
-            requested_provider, resolved_model = self._resolve_model_selection(
-                model_id,
-                current_provider or "openrouter",
-            )
-            state.model = resolved_model
-            provider_changed = bool(current_provider and requested_provider != current_provider)
-            current_base_url = None if provider_changed else getattr(state.agent, "base_url", None)
-            current_api_mode = None if provider_changed else getattr(state.agent, "api_mode", None)
+            current_base_url = getattr(state.agent, "base_url", None)
+            current_api_mode = getattr(state.agent, "api_mode", None)
            state.agent = self.session_manager._make_agent(
                session_id=session_id,
                cwd=state.cwd,
-                model=resolved_model,
-                requested_provider=requested_provider,
+                model=model_id,
+                requested_provider=current_provider,
                base_url=current_base_url,
                api_mode=current_api_mode,
            )
            self.session_manager.save_session(session_id)
-            logger.info(
-                "Session %s: model switched to %s via provider %s",
-                session_id,
-                resolved_model,
-                requested_provider,
-            )
+            logger.info("Session %s: model switched to %s", session_id, model_id)
            return SetSessionModelResponse()
        logger.warning("Session %s: model switch requested for missing session", session_id)
        return None
--- a/acp_adapter/session.py
+++ b/acp_adapter/session.py
@@ -13,12 +13,8 @@ from hermes_constants import get_hermes_home
 import copy
 import json
 import logging
-import os
-import re
 import sys
-import time
 import uuid
-from datetime import datetime, timezone
 from dataclasses import dataclass, field
 from threading import Lock
 from typing import Any, Dict, List, Optional
@@ -26,64 +22,6 @@ from typing import Any, Dict, List, Optional
 logger = logging.getLogger(__name__)


-def _normalize_cwd_for_compare(cwd: str | None) -> str:
-    raw = str(cwd or ".").strip()
-    if not raw:
-        raw = "."
-    expanded = os.path.expanduser(raw)
-
-    # Normalize Windows drive paths into the equivalent WSL mount form so
-    # ACP history filters match the same workspace across Windows and WSL.
-    match = re.match(r"^([A-Za-z]):[\\/](.*)$", expanded)
-    if match:
-        drive = match.group(1).lower()
-        tail = match.group(2).replace("\\", "/")
-        expanded = f"/mnt/{drive}/{tail}"
-    elif re.match(r"^/mnt/[A-Za-z]/", expanded):
-        expanded = f"/mnt/{expanded[5].lower()}/{expanded[7:]}"
-
-    return os.path.normpath(expanded)
-
-
-def _build_session_title(title: Any, preview: Any, cwd: str | None) -> str:
-    explicit = str(title or "").strip()
-    if explicit:
-        return explicit
-    preview_text = str(preview or "").strip()
-    if preview_text:
-        return preview_text
-    leaf = os.path.basename(str(cwd or "").rstrip("/\\"))
-    return leaf or "New thread"
-
-
-def _format_updated_at(value: Any) -> str | None:
-    if value is None:
-        return None
-    if isinstance(value, str) and value.strip():
-        return value
-    try:
-        return datetime.fromtimestamp(float(value), tz=timezone.utc).isoformat()
-    except Exception:
-        return None
-
-
-def _updated_at_sort_key(value: Any) -> float:
-    if value is None:
-        return float("-inf")
-    if isinstance(value, (int, float)):
-        return float(value)
-    raw = str(value).strip()
-    if not raw:
-        return float("-inf")
-    try:
-        return datetime.fromisoformat(raw.replace("Z", "+00:00")).timestamp()
-    except Exception:
-        try:
-            return float(raw)
-        except Exception:
-            return float("-inf")
-
-
 def _acp_stderr_print(*args, **kwargs) -> None:
    """Best-effort human-readable output sink for ACP stdio sessions.

@@ -224,78 +162,47 @@ class SessionManager:
        logger.info("Forked ACP session %s -> %s", session_id, new_id)
        return state

-    def list_sessions(self, cwd: str | None = None) -> List[Dict[str, Any]]:
+    def list_sessions(self) -> List[Dict[str, Any]]:
        """Return lightweight info dicts for all sessions (memory + database)."""
-        normalized_cwd = _normalize_cwd_for_compare(cwd) if cwd else None
-        db = self._get_db()
-        persisted_rows: dict[str, dict[str, Any]] = {}
-
-        if db is not None:
-            try:
-                for row in db.list_sessions_rich(source="acp", limit=1000):
-                    persisted_rows[str(row["id"])] = dict(row)
-            except Exception:
-                logger.debug("Failed to load ACP sessions from DB", exc_info=True)
-
        # Collect in-memory sessions first.
        with self._lock:
            seen_ids = set(self._sessions.keys())
-            results = []
-            for s in self._sessions.values():
-                history_len = len(s.history)
-                if history_len <= 0:
-                    continue
-                if normalized_cwd and _normalize_cwd_for_compare(s.cwd) != normalized_cwd:
-                    continue
-                persisted = persisted_rows.get(s.session_id, {})
-                preview = next(
-                    (
-                        str(msg.get("content") or "").strip()
-                        for msg in s.history
-                        if msg.get("role") == "user" and str(msg.get("content") or "").strip()
-                    ),
-                    persisted.get("preview") or "",
-                )
-                results.append(
-                    {
-                        "session_id": s.session_id,
-                        "cwd": s.cwd,
-                        "model": s.model,
-                        "history_len": history_len,
-                        "title": _build_session_title(persisted.get("title"), preview, s.cwd),
-                        "updated_at": _format_updated_at(
-                            persisted.get("last_active") or persisted.get("started_at") or time.time()
-                        ),
-                    }
-                )
+            results = [
+                {
+                    "session_id": s.session_id,
+                    "cwd": s.cwd,
+                    "model": s.model,
+                    "history_len": len(s.history),
+                }
+                for s in self._sessions.values()
+            ]

        # Merge any persisted sessions not currently in memory.
-        for sid, row in persisted_rows.items():
-            if sid in seen_ids:
-                continue
-            message_count = int(row.get("message_count") or 0)
-            if message_count <= 0:
-                continue
-            # Extract cwd from model_config JSON.
-            session_cwd = "."
-            mc = row.get("model_config")
-            if mc:
-                try:
-                    session_cwd = json.loads(mc).get("cwd", ".")
-                except (json.JSONDecodeError, TypeError):
-                    pass
-            if normalized_cwd and _normalize_cwd_for_compare(session_cwd) != normalized_cwd:
-                continue
-            results.append({
-                "session_id": sid,
-                "cwd": session_cwd,
-                "model": row.get("model") or "",
-                "history_len": message_count,
-                "title": _build_session_title(row.get("title"), row.get("preview"), session_cwd),
-                "updated_at": _format_updated_at(row.get("last_active") or row.get("started_at")),
-            })
+        db = self._get_db()
+        if db is not None:
+            try:
+                rows = db.search_sessions(source="acp", limit=1000)
+                for row in rows:
+                    sid = row["id"]
+                    if sid in seen_ids:
+                        continue
+                    # Extract cwd from model_config JSON.
+                    cwd = "."
+                    mc = row.get("model_config")
+                    if mc:
+                        try:
+                            cwd = json.loads(mc).get("cwd", ".")
+                        except (json.JSONDecodeError, TypeError):
+                            pass
+                    results.append({
+                        "session_id": sid,
+                        "cwd": cwd,
+                        "model": row.get("model") or "",
+                        "history_len": row.get("message_count") or 0,
+                    })
+            except Exception:
+                logger.debug("Failed to list ACP sessions from DB", exc_info=True)

-        results.sort(key=lambda item: _updated_at_sort_key(item.get("updated_at")), reverse=True)
        return results

    def update_cwd(self, session_id: str, cwd: str) -> Optional[SessionState]:
--- a/acp_adapter/tools.py
+++ b/acp_adapter/tools.py
@@ -2,7 +2,6 @@

 from __future__ import annotations

-import json
 import uuid
 from typing import Any, Dict, List, Optional

@@ -97,170 +96,6 @@ def build_tool_title(tool_name: str, args: Dict[str, Any]) -> str:
    return tool_name


-def _build_patch_mode_content(patch_text: str) -> List[Any]:
-    """Parse V4A patch mode input into ACP diff blocks when possible."""
-    if not patch_text:
-        return [acp.tool_content(acp.text_block(""))]
-
-    try:
-        from tools.patch_parser import OperationType, parse_v4a_patch
-
-        operations, error = parse_v4a_patch(patch_text)
-        if error or not operations:
-            return [acp.tool_content(acp.text_block(patch_text))]
-
-        content: List[Any] = []
-        for op in operations:
-            if op.operation == OperationType.UPDATE:
-                old_chunks: list[str] = []
-                new_chunks: list[str] = []
-                for hunk in op.hunks:
-                    old_lines = [line.content for line in hunk.lines if line.prefix in (" ", "-")]
-                    new_lines = [line.content for line in hunk.lines if line.prefix in (" ", "+")]
-                    if old_lines or new_lines:
-                        old_chunks.append("\n".join(old_lines))
-                        new_chunks.append("\n".join(new_lines))
-
-                old_text = "\n...\n".join(chunk for chunk in old_chunks if chunk)
-                new_text = "\n...\n".join(chunk for chunk in new_chunks if chunk)
-                if old_text or new_text:
-                    content.append(
-                        acp.tool_diff_content(
-                            path=op.file_path,
-                            old_text=old_text or None,
-                            new_text=new_text or "",
-                        )
-                    )
-                continue
-
-            if op.operation == OperationType.ADD:
-                added_lines = [line.content for hunk in op.hunks for line in hunk.lines if line.prefix == "+"]
-                content.append(
-                    acp.tool_diff_content(
-                        path=op.file_path,
-                        new_text="\n".join(added_lines),
-                    )
-                )
-                continue
-
-            if op.operation == OperationType.DELETE:
-                content.append(
-                    acp.tool_diff_content(
-                        path=op.file_path,
-                        old_text=f"Delete file: {op.file_path}",
-                        new_text="",
-                    )
-                )
-                continue
-
-            if op.operation == OperationType.MOVE:
-                content.append(
-                    acp.tool_content(acp.text_block(f"Move file: {op.file_path} -> {op.new_path}"))
-                )
-
-        return content or [acp.tool_content(acp.text_block(patch_text))]
-    except Exception:
-        return [acp.tool_content(acp.text_block(patch_text))]
-
-
-def _strip_diff_prefix(path: str) -> str:
-    raw = str(path or "").strip()
-    if raw.startswith(("a/", "b/")):
-        return raw[2:]
-    return raw
-
-
-def _parse_unified_diff_content(diff_text: str) -> List[Any]:
-    """Convert unified diff text into ACP diff content blocks."""
-    if not diff_text:
-        return []
-
-    content: List[Any] = []
-    current_old_path: Optional[str] = None
-    current_new_path: Optional[str] = None
-    old_lines: list[str] = []
-    new_lines: list[str] = []
-
-    def _flush() -> None:
-        nonlocal current_old_path, current_new_path, old_lines, new_lines
-        if current_old_path is None and current_new_path is None:
-            return
-        path = current_new_path if current_new_path and current_new_path != "/dev/null" else current_old_path
-        if not path or path == "/dev/null":
-            current_old_path = None
-            current_new_path = None
-            old_lines = []
-            new_lines = []
-            return
-        content.append(
-            acp.tool_diff_content(
-                path=_strip_diff_prefix(path),
-                old_text="\n".join(old_lines) if old_lines else None,
-                new_text="\n".join(new_lines),
-            )
-        )
-        current_old_path = None
-        current_new_path = None
-        old_lines = []
-        new_lines = []
-
-    for line in diff_text.splitlines():
-        if line.startswith("--- "):
-            _flush()
-            current_old_path = line[4:].strip()
-            continue
-        if line.startswith("+++ "):
-            current_new_path = line[4:].strip()
-            continue
-        if line.startswith("@@"):
-            continue
-        if current_old_path is None and current_new_path is None:
-            continue
-        if line.startswith("+"):
-            new_lines.append(line[1:])
-        elif line.startswith("-"):
-            old_lines.append(line[1:])
-        elif line.startswith(" "):
-            shared = line[1:]
-            old_lines.append(shared)
-            new_lines.append(shared)
-
-    _flush()
-    return content
-
-
-def _build_tool_complete_content(
-    tool_name: str,
-    result: Optional[str],
-    *,
-    function_args: Optional[Dict[str, Any]] = None,
-    snapshot: Any = None,
-) -> List[Any]:
-    """Build structured ACP completion content, falling back to plain text."""
-    display_result = result or ""
-    if len(display_result) > 5000:
-        display_result = display_result[:4900] + f"\n... ({len(result)} chars total, truncated)"
-
-    if tool_name in {"write_file", "patch", "skill_manage"}:
-        try:
-            from agent.display import extract_edit_diff
-
-            diff_text = extract_edit_diff(
-                tool_name,
-                result,
-                function_args=function_args,
-                snapshot=snapshot,
-            )
-            if isinstance(diff_text, str) and diff_text.strip():
-                diff_content = _parse_unified_diff_content(diff_text)
-                if diff_content:
-                    return diff_content
-        except Exception:
-            pass
-
-    return [acp.tool_content(acp.text_block(display_result))]
-
-
 # ---------------------------------------------------------------------------
 # Build ACP content objects for tool-call events
 # ---------------------------------------------------------------------------
@@ -284,8 +119,9 @@ def build_tool_start(
            new = arguments.get("new_string", "")
            content = [acp.tool_diff_content(path=path, new_text=new, old_text=old)]
        else:
+            # Patch mode — show the patch content as text
            patch_text = arguments.get("patch", "")
-            content = _build_patch_mode_content(patch_text)
+            content = [acp.tool_content(acp.text_block(patch_text))]
        return acp.start_tool_call(
            tool_call_id, title, kind=kind, content=content, locations=locations,
            raw_input=arguments,
@@ -342,17 +178,16 @@ def build_tool_complete(
    tool_call_id: str,
    tool_name: str,
    result: Optional[str] = None,
-    function_args: Optional[Dict[str, Any]] = None,
-    snapshot: Any = None,
 ) -> ToolCallProgress:
    """Create a ToolCallUpdate (progress) event for a completed tool call."""
    kind = get_tool_kind(tool_name)
-    content = _build_tool_complete_content(
-        tool_name,
-        result,
-        function_args=function_args,
-        snapshot=snapshot,
-    )
+
+    # Truncate very large results for the UI
+    display_result = result or ""
+    if len(display_result) > 5000:
+        display_result = display_result[:4900] + f"\n... ({len(result)} chars total, truncated)"
+
+    content = [acp.tool_content(acp.text_block(display_result))]
    return acp.update_tool_call(
        tool_call_id,
        kind=kind,
--- a/agent/account_usage.py
+++ b/agent/account_usage.py
@@ -1,326 +0,0 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-from datetime import datetime, timezone
-from typing import Any, Optional
-
-import httpx
-
-from agent.anthropic_adapter import _is_oauth_token, resolve_anthropic_token
-from hermes_cli.auth import _read_codex_tokens, resolve_codex_runtime_credentials
-from hermes_cli.runtime_provider import resolve_runtime_provider
-
-
-def _utc_now() -> datetime:
-    return datetime.now(timezone.utc)
-
-
-@dataclass(frozen=True)
-class AccountUsageWindow:
-    label: str
-    used_percent: Optional[float] = None
-    reset_at: Optional[datetime] = None
-    detail: Optional[str] = None
-
-
-@dataclass(frozen=True)
-class AccountUsageSnapshot:
-    provider: str
-    source: str
-    fetched_at: datetime
-    title: str = "Account limits"
-    plan: Optional[str] = None
-    windows: tuple[AccountUsageWindow, ...] = ()
-    details: tuple[str, ...] = ()
-    unavailable_reason: Optional[str] = None
-
-    @property
-    def available(self) -> bool:
-        return bool(self.windows or self.details) and not self.unavailable_reason
-
-
-def _title_case_slug(value: Optional[str]) -> Optional[str]:
-    cleaned = str(value or "").strip()
-    if not cleaned:
-        return None
-    return cleaned.replace("_", " ").replace("-", " ").title()
-
-
-def _parse_dt(value: Any) -> Optional[datetime]:
-    if value in (None, ""):
-        return None
-    if isinstance(value, (int, float)):
-        return datetime.fromtimestamp(float(value), tz=timezone.utc)
-    if isinstance(value, str):
-        text = value.strip()
-        if not text:
-            return None
-        if text.endswith("Z"):
-            text = text[:-1] + "+00:00"
-        try:
-            dt = datetime.fromisoformat(text)
-            return dt if dt.tzinfo else dt.replace(tzinfo=timezone.utc)
-        except ValueError:
-            return None
-    return None
-
-
-def _format_reset(dt: Optional[datetime]) -> str:
-    if not dt:
-        return "unknown"
-    local_dt = dt.astimezone()
-    delta = dt - _utc_now()
-    total_seconds = int(delta.total_seconds())
-    if total_seconds <= 0:
-        return f"now ({local_dt.strftime('%Y-%m-%d %H:%M %Z')})"
-    hours, rem = divmod(total_seconds, 3600)
-    minutes = rem // 60
-    if hours >= 24:
-        days, hours = divmod(hours, 24)
-        rel = f"in {days}d {hours}h"
-    elif hours > 0:
-        rel = f"in {hours}h {minutes}m"
-    else:
-        rel = f"in {minutes}m"
-    return f"{rel} ({local_dt.strftime('%Y-%m-%d %H:%M %Z')})"
-
-
-def render_account_usage_lines(snapshot: Optional[AccountUsageSnapshot], *, markdown: bool = False) -> list[str]:
-    if not snapshot:
-        return []
-    header = f"📈 {'**' if markdown else ''}{snapshot.title}{'**' if markdown else ''}"
-    lines = [header]
-    if snapshot.plan:
-        lines.append(f"Provider: {snapshot.provider} ({snapshot.plan})")
-    else:
-        lines.append(f"Provider: {snapshot.provider}")
-    for window in snapshot.windows:
-        if window.used_percent is None:
-            base = f"{window.label}: unavailable"
-        else:
-            remaining = max(0, round(100 - float(window.used_percent)))
-            used = max(0, round(float(window.used_percent)))
-            base = f"{window.label}: {remaining}% remaining ({used}% used)"
-        if window.reset_at:
-            base += f" • resets {_format_reset(window.reset_at)}"
-        elif window.detail:
-            base += f" • {window.detail}"
-        lines.append(base)
-    for detail in snapshot.details:
-        lines.append(detail)
-    if snapshot.unavailable_reason:
-        lines.append(f"Unavailable: {snapshot.unavailable_reason}")
-    return lines
-
-
-def _resolve_codex_usage_url(base_url: str) -> str:
-    normalized = (base_url or "").strip().rstrip("/")
-    if not normalized:
-        normalized = "https://chatgpt.com/backend-api/codex"
-    if normalized.endswith("/codex"):
-        normalized = normalized[: -len("/codex")]
-    if "/backend-api" in normalized:
-        return normalized + "/wham/usage"
-    return normalized + "/api/codex/usage"
-
-
-def _fetch_codex_account_usage() -> Optional[AccountUsageSnapshot]:
-    creds = resolve_codex_runtime_credentials(refresh_if_expiring=True)
-    token_data = _read_codex_tokens()
-    tokens = token_data.get("tokens") or {}
-    account_id = str(tokens.get("account_id", "") or "").strip() or None
-    headers = {
-        "Authorization": f"Bearer {creds['api_key']}",
-        "Accept": "application/json",
-        "User-Agent": "codex-cli",
-    }
-    if account_id:
-        headers["ChatGPT-Account-Id"] = account_id
-    with httpx.Client(timeout=15.0) as client:
-        response = client.get(_resolve_codex_usage_url(creds.get("base_url", "")), headers=headers)
-        response.raise_for_status()
-    payload = response.json() or {}
-    rate_limit = payload.get("rate_limit") or {}
-    windows: list[AccountUsageWindow] = []
-    for key, label in (("primary_window", "Session"), ("secondary_window", "Weekly")):
-        window = rate_limit.get(key) or {}
-        used = window.get("used_percent")
-        if used is None:
-            continue
-        windows.append(
-            AccountUsageWindow(
-                label=label,
-                used_percent=float(used),
-                reset_at=_parse_dt(window.get("reset_at")),
-            )
-        )
-    details: list[str] = []
-    credits = payload.get("credits") or {}
-    if credits.get("has_credits"):
-        balance = credits.get("balance")
-        if isinstance(balance, (int, float)):
-            details.append(f"Credits balance: ${float(balance):.2f}")
-        elif credits.get("unlimited"):
-            details.append("Credits balance: unlimited")
-    return AccountUsageSnapshot(
-        provider="openai-codex",
-        source="usage_api",
-        fetched_at=_utc_now(),
-        plan=_title_case_slug(payload.get("plan_type")),
-        windows=tuple(windows),
-        details=tuple(details),
-    )
-
-
-def _fetch_anthropic_account_usage() -> Optional[AccountUsageSnapshot]:
-    token = (resolve_anthropic_token() or "").strip()
-    if not token:
-        return None
-    if not _is_oauth_token(token):
-        return AccountUsageSnapshot(
-            provider="anthropic",
-            source="oauth_usage_api",
-            fetched_at=_utc_now(),
-            unavailable_reason="Anthropic account limits are only available for OAuth-backed Claude accounts.",
-        )
-    headers = {
-        "Authorization": f"Bearer {token}",
-        "Accept": "application/json",
-        "Content-Type": "application/json",
-        "anthropic-beta": "oauth-2025-04-20",
-        "User-Agent": "claude-code/2.1.0",
-    }
-    with httpx.Client(timeout=15.0) as client:
-        response = client.get("https://api.anthropic.com/api/oauth/usage", headers=headers)
-        response.raise_for_status()
-    payload = response.json() or {}
-    windows: list[AccountUsageWindow] = []
-    mapping = (
-        ("five_hour", "Current session"),
-        ("seven_day", "Current week"),
-        ("seven_day_opus", "Opus week"),
-        ("seven_day_sonnet", "Sonnet week"),
-    )
-    for key, label in mapping:
-        window = payload.get(key) or {}
-        util = window.get("utilization")
-        if util is None:
-            continue
-        used = float(util) * 100 if float(util) <= 1 else float(util)
-        windows.append(
-            AccountUsageWindow(
-                label=label,
-                used_percent=used,
-                reset_at=_parse_dt(window.get("resets_at")),
-            )
-        )
-    details: list[str] = []
-    extra = payload.get("extra_usage") or {}
-    if extra.get("is_enabled"):
-        used_credits = extra.get("used_credits")
-        monthly_limit = extra.get("monthly_limit")
-        currency = extra.get("currency") or "USD"
-        if isinstance(used_credits, (int, float)) and isinstance(monthly_limit, (int, float)):
-            details.append(
-                f"Extra usage: {used_credits:.2f} / {monthly_limit:.2f} {currency}"
-            )
-    return AccountUsageSnapshot(
-        provider="anthropic",
-        source="oauth_usage_api",
-        fetched_at=_utc_now(),
-        windows=tuple(windows),
-        details=tuple(details),
-    )
-
-
-def _fetch_openrouter_account_usage(base_url: Optional[str], api_key: Optional[str]) -> Optional[AccountUsageSnapshot]:
-    runtime = resolve_runtime_provider(
-        requested="openrouter",
-        explicit_base_url=base_url,
-        explicit_api_key=api_key,
-    )
-    token = str(runtime.get("api_key", "") or "").strip()
-    if not token:
-        return None
-    normalized = str(runtime.get("base_url", "") or "").rstrip("/")
-    credits_url = f"{normalized}/credits"
-    key_url = f"{normalized}/key"
-    headers = {
-        "Authorization": f"Bearer {token}",
-        "Accept": "application/json",
-    }
-    with httpx.Client(timeout=10.0) as client:
-        credits_resp = client.get(credits_url, headers=headers)
-        credits_resp.raise_for_status()
-        credits = (credits_resp.json() or {}).get("data") or {}
-        try:
-            key_resp = client.get(key_url, headers=headers)
-            key_resp.raise_for_status()
-            key_data = (key_resp.json() or {}).get("data") or {}
-        except Exception:
-            key_data = {}
-    total_credits = float(credits.get("total_credits") or 0.0)
-    total_usage = float(credits.get("total_usage") or 0.0)
-    details = [f"Credits balance: ${max(0.0, total_credits - total_usage):.2f}"]
-    windows: list[AccountUsageWindow] = []
-    limit = key_data.get("limit")
-    limit_remaining = key_data.get("limit_remaining")
-    limit_reset = str(key_data.get("limit_reset") or "").strip()
-    usage = key_data.get("usage")
-    if (
-        isinstance(limit, (int, float))
-        and float(limit) > 0
-        and isinstance(limit_remaining, (int, float))
-        and 0 <= float(limit_remaining) <= float(limit)
-    ):
-        limit_value = float(limit)
-        remaining_value = float(limit_remaining)
-        used_percent = ((limit_value - remaining_value) / limit_value) * 100
-        detail_parts = [f"${remaining_value:.2f} of ${limit_value:.2f} remaining"]
-        if limit_reset:
-            detail_parts.append(f"resets {limit_reset}")
-        windows.append(
-            AccountUsageWindow(
-                label="API key quota",
-                used_percent=used_percent,
-                detail=" • ".join(detail_parts),
-            )
-        )
-    if isinstance(usage, (int, float)):
-        usage_parts = [f"API key usage: ${float(usage):.2f} total"]
-        for value, label in (
-            (key_data.get("usage_daily"), "today"),
-            (key_data.get("usage_weekly"), "this week"),
-            (key_data.get("usage_monthly"), "this month"),
-        ):
-            if isinstance(value, (int, float)) and float(value) > 0:
-                usage_parts.append(f"${float(value):.2f} {label}")
-        details.append(" • ".join(usage_parts))
-    return AccountUsageSnapshot(
-        provider="openrouter",
-        source="credits_api",
-        fetched_at=_utc_now(),
-        windows=tuple(windows),
-        details=tuple(details),
-    )
-
-
-def fetch_account_usage(
-    provider: Optional[str],
-    *,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
-) -> Optional[AccountUsageSnapshot]:
-    normalized = str(provider or "").strip().lower()
-    if normalized in {"", "auto", "custom"}:
-        return None
-    try:
-        if normalized == "openai-codex":
-            return _fetch_codex_account_usage()
-        if normalized == "anthropic":
-            return _fetch_anthropic_account_usage()
-        if normalized == "openrouter":
-            return _fetch_openrouter_account_usage(base_url, api_key)
-    except Exception:
-        return None
-    return None
--- a/agent/anthropic_adapter.py
+++ b/agent/anthropic_adapter.py
@@ -19,7 +19,6 @@ from pathlib import Path
 from hermes_constants import get_hermes_home
 from types import SimpleNamespace
 from typing import Any, Dict, List, Optional, Tuple
-from utils import normalize_proxy_env_vars

 try:
    import anthropic as _anthropic_sdk
@@ -29,45 +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,
@@ -118,37 +91,11 @@ 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",
@@ -266,14 +213,6 @@ def _is_third_party_anthropic_endpoint(base_url: str | None) -> bool:
    return True  # Any other endpoint is a third-party proxy


-def _is_kimi_coding_endpoint(base_url: str | None) -> bool:
-    """Return True for Kimi's /coding endpoint that requires claude-code UA."""
-    normalized = _normalize_base_url_text(base_url)
-    if not normalized:
-        return False
-    return normalized.rstrip("/").lower().startswith("https://api.kimi.com/coding")
-
-
 def _requires_bearer_auth(base_url: str | None) -> bool:
    """Return True for Anthropic-compatible providers that require Bearer auth.

@@ -301,15 +240,9 @@ def _common_betas_for_base_url(base_url: str | None) -> list[str]:
    return _COMMON_BETAS


-def build_anthropic_client(api_key: str, base_url: str = None, timeout: float = None):
+def build_anthropic_client(api_key: str, base_url: str = None):
    """Create an Anthropic client, auto-detecting setup-tokens vs API keys.

-    If *timeout* is provided it overrides the default 900s read timeout.  The
-    connect timeout stays at 10s.  Callers pass this from the per-provider /
-    per-model ``request_timeout_seconds`` config so Anthropic-native and
-    Anthropic-compatible providers respect the same knob as OpenAI-wire
-    providers.
-
    Returns an anthropic.Anthropic instance.
    """
    if _anthropic_sdk is None:
@@ -317,32 +250,19 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
            "The 'anthropic' package is required for the Anthropic provider. "
            "Install it with: pip install 'anthropic>=0.39.0'"
        )
-
-    normalize_proxy_env_vars()
-
    from httpx import Timeout

    normalized_base_url = _normalize_base_url_text(base_url)
-    _read_timeout = timeout if (isinstance(timeout, (int, float)) and timeout > 0) else 900.0
    kwargs = {
-        "timeout": Timeout(timeout=float(_read_timeout), connect=10.0),
+        "timeout": Timeout(timeout=900.0, connect=10.0),
    }
    if normalized_base_url:
        kwargs["base_url"] = normalized_base_url
    common_betas = _common_betas_for_base_url(normalized_base_url)

-    if _is_kimi_coding_endpoint(base_url):
-        # Kimi's /coding endpoint requires User-Agent: claude-code/0.1.0
-        # to be recognized as a valid Coding Agent. Without it, returns 403.
-        # Check this BEFORE _requires_bearer_auth since both match api.kimi.com/coding.
-        kwargs["api_key"] = api_key
-        kwargs["default_headers"] = {
-            "User-Agent": "claude-code/0.1.0",
-            **( {"anthropic-beta": ",".join(common_betas)} if common_betas else {} )
-        }
-    elif _requires_bearer_auth(normalized_base_url):
+    if _requires_bearer_auth(normalized_base_url):
        # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
-        # Authorization: Bearer *** for regular API keys. Route those endpoints
+        # Authorization: Bearer even for regular API keys. Route those endpoints
        # through auth_token so the SDK sends Bearer auth instead of x-api-key.
        # Check this before OAuth token shape detection because MiniMax secrets do
        # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
@@ -378,33 +298,6 @@ def build_anthropic_client(api_key: str, base_url: str = None, timeout: float =
    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.

@@ -1337,10 +1230,9 @@ 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).
+    When *fast_mode* is True, adds ``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 []
@@ -1421,45 +1313,18 @@ 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.
-    #
-    # Kimi's /coding endpoint speaks the Anthropic Messages protocol but has
-    # its own thinking semantics: when ``thinking.enabled`` is sent, Kimi
-    # validates the message history and requires every prior assistant
-    # tool-call message to carry OpenAI-style ``reasoning_content``.  The
-    # Anthropic path never populates that field, and
-    # ``convert_messages_to_anthropic`` strips all Anthropic thinking blocks
-    # on third-party endpoints — so the request fails with HTTP 400
-    # "thinking is enabled but reasoning_content is missing in assistant
-    # tool call message at index N".  Kimi's reasoning is driven server-side
-    # on the /coding route, so skip Anthropic's thinking parameter entirely
-    # for that host.  (Kimi on chat_completions enables thinking via
-    # extra_body in the ChatCompletionsTransport — see #13503.)
-    #
-    # 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.
-    _is_kimi_coding = _is_kimi_coding_endpoint(base_url)
-    if reasoning_config and isinstance(reasoning_config, dict) and not _is_kimi_coding:
+    if reasoning_config and isinstance(reasoning_config, dict):
        if reasoning_config.get("enabled") is not False and "haiku" 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}
@@ -1467,21 +1332,12 @@ 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.
+    # Adds 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"
+        kwargs["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))
@@ -1533,20 +1389,12 @@ 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")

--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
--- a/agent/bedrock_adapter.py
+++ b/agent/bedrock_adapter.py
--- a/agent/codex_responses_adapter.py
+++ b/agent/codex_responses_adapter.py
@@ -1,813 +0,0 @@
-"""Codex Responses API adapter.
-
-Pure format-conversion and normalization logic for the OpenAI Responses API
-(used by OpenAI Codex, xAI, GitHub Models, and other Responses-compatible endpoints).
-
-Extracted from run_agent.py to isolate Responses API-specific logic from the
-core agent loop. All functions are stateless — they operate on the data passed
-in and return transformed results.
-"""
-
-from __future__ import annotations
-
-import hashlib
-import json
-import logging
-import re
-import uuid
-from types import SimpleNamespace
-from typing import Any, Dict, List, Optional
-
-from agent.prompt_builder import DEFAULT_AGENT_IDENTITY
-
-logger = logging.getLogger(__name__)
-
-
-# ---------------------------------------------------------------------------
-# Multimodal content helpers
-# ---------------------------------------------------------------------------
-
-def _chat_content_to_responses_parts(content: Any) -> List[Dict[str, Any]]:
-    """Convert chat-style multimodal content to Responses API input parts.
-
-    Input:  ``[{"type":"text"|"image_url", ...}]`` (native OpenAI Chat format)
-    Output: ``[{"type":"input_text"|"input_image", ...}]`` (Responses format)
-
-    Returns an empty list when ``content`` is not a list or contains no
-    recognized parts — callers fall back to the string path.
-    """
-    if not isinstance(content, list):
-        return []
-    converted: List[Dict[str, Any]] = []
-    for part in content:
-        if isinstance(part, str):
-            if part:
-                converted.append({"type": "input_text", "text": part})
-            continue
-        if not isinstance(part, dict):
-            continue
-        ptype = str(part.get("type") or "").strip().lower()
-        if ptype in {"text", "input_text", "output_text"}:
-            text = part.get("text")
-            if isinstance(text, str) and text:
-                converted.append({"type": "input_text", "text": text})
-            continue
-        if ptype in {"image_url", "input_image"}:
-            image_ref = part.get("image_url")
-            detail = part.get("detail")
-            if isinstance(image_ref, dict):
-                url = image_ref.get("url")
-                detail = image_ref.get("detail", detail)
-            else:
-                url = image_ref
-            if not isinstance(url, str) or not url:
-                continue
-            image_part: Dict[str, Any] = {"type": "input_image", "image_url": url}
-            if isinstance(detail, str) and detail.strip():
-                image_part["detail"] = detail.strip()
-            converted.append(image_part)
-    return converted
-
-
-def _summarize_user_message_for_log(content: Any) -> str:
-    """Return a short text summary of a user message for logging/trajectory.
-
-    Multimodal messages arrive as a list of ``{type:"text"|"image_url", ...}``
-    parts from the API server.  Logging, spinner previews, and trajectory
-    files all want a plain string — this helper extracts the first chunk of
-    text and notes any attached images.  Returns an empty string for empty
-    lists and ``str(content)`` for unexpected scalar types.
-    """
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        text_bits: List[str] = []
-        image_count = 0
-        for part in content:
-            if isinstance(part, str):
-                if part:
-                    text_bits.append(part)
-                continue
-            if not isinstance(part, dict):
-                continue
-            ptype = str(part.get("type") or "").strip().lower()
-            if ptype in {"text", "input_text", "output_text"}:
-                text = part.get("text")
-                if isinstance(text, str) and text:
-                    text_bits.append(text)
-            elif ptype in {"image_url", "input_image"}:
-                image_count += 1
-        summary = " ".join(text_bits).strip()
-        if image_count:
-            note = f"[{image_count} image{'s' if image_count != 1 else ''}]"
-            summary = f"{note} {summary}" if summary else note
-        return summary
-    try:
-        return str(content)
-    except Exception:
-        return ""
-
-
-# ---------------------------------------------------------------------------
-# ID helpers
-# ---------------------------------------------------------------------------
-
-def _deterministic_call_id(fn_name: str, arguments: str, index: int = 0) -> str:
-    """Generate a deterministic call_id from tool call content.
-
-    Used as a fallback when the API doesn't provide a call_id.
-    Deterministic IDs prevent cache invalidation — random UUIDs would
-    make every API call's prefix unique, breaking OpenAI's prompt cache.
-    """
-    seed = f"{fn_name}:{arguments}:{index}"
-    digest = hashlib.sha256(seed.encode("utf-8", errors="replace")).hexdigest()[:12]
-    return f"call_{digest}"
-
-
-def _split_responses_tool_id(raw_id: Any) -> tuple[Optional[str], Optional[str]]:
-    """Split a stored tool id into (call_id, response_item_id)."""
-    if not isinstance(raw_id, str):
-        return None, None
-    value = raw_id.strip()
-    if not value:
-        return None, None
-    if "|" in value:
-        call_id, response_item_id = value.split("|", 1)
-        call_id = call_id.strip() or None
-        response_item_id = response_item_id.strip() or None
-        return call_id, response_item_id
-    if value.startswith("fc_"):
-        return None, value
-    return value, None
-
-
-def _derive_responses_function_call_id(
-    call_id: str,
-    response_item_id: Optional[str] = None,
-) -> str:
-    """Build a valid Responses `function_call.id` (must start with `fc_`)."""
-    if isinstance(response_item_id, str):
-        candidate = response_item_id.strip()
-        if candidate.startswith("fc_"):
-            return candidate
-
-    source = (call_id or "").strip()
-    if source.startswith("fc_"):
-        return source
-    if source.startswith("call_") and len(source) > len("call_"):
-        return f"fc_{source[len('call_'):]}"
-
-    sanitized = re.sub(r"[^A-Za-z0-9_-]", "", source)
-    if sanitized.startswith("fc_"):
-        return sanitized
-    if sanitized.startswith("call_") and len(sanitized) > len("call_"):
-        return f"fc_{sanitized[len('call_'):]}"
-    if sanitized:
-        return f"fc_{sanitized[:48]}"
-
-    seed = source or str(response_item_id or "") or uuid.uuid4().hex
-    digest = hashlib.sha1(seed.encode("utf-8")).hexdigest()[:24]
-    return f"fc_{digest}"
-
-
-# ---------------------------------------------------------------------------
-# Schema conversion
-# ---------------------------------------------------------------------------
-
-def _responses_tools(tools: Optional[List[Dict[str, Any]]] = None) -> Optional[List[Dict[str, Any]]]:
-    """Convert chat-completions tool schemas to Responses function-tool schemas."""
-    if not tools:
-        return None
-
-    converted: List[Dict[str, Any]] = []
-    for item in tools:
-        fn = item.get("function", {}) if isinstance(item, dict) else {}
-        name = fn.get("name")
-        if not isinstance(name, str) or not name.strip():
-            continue
-        converted.append({
-            "type": "function",
-            "name": name,
-            "description": fn.get("description", ""),
-            "strict": False,
-            "parameters": fn.get("parameters", {"type": "object", "properties": {}}),
-        })
-    return converted or None
-
-
-# ---------------------------------------------------------------------------
-# Message format conversion
-# ---------------------------------------------------------------------------
-
-def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
-    """Convert internal chat-style messages to Responses input items."""
-    items: List[Dict[str, Any]] = []
-    seen_item_ids: set = set()
-
-    for msg in messages:
-        if not isinstance(msg, dict):
-            continue
-        role = msg.get("role")
-        if role == "system":
-            continue
-
-        if role in {"user", "assistant"}:
-            content = msg.get("content", "")
-            if isinstance(content, list):
-                content_parts = _chat_content_to_responses_parts(content)
-                content_text = "".join(
-                    p.get("text", "") for p in content_parts if p.get("type") == "input_text"
-                )
-            else:
-                content_parts = []
-                content_text = str(content) if content is not None else ""
-
-            if role == "assistant":
-                # Replay encrypted reasoning items from previous turns
-                # so the API can maintain coherent reasoning chains.
-                codex_reasoning = msg.get("codex_reasoning_items")
-                has_codex_reasoning = False
-                if isinstance(codex_reasoning, list):
-                    for ri in codex_reasoning:
-                        if isinstance(ri, dict) and ri.get("encrypted_content"):
-                            item_id = ri.get("id")
-                            if item_id and item_id in seen_item_ids:
-                                continue
-                            # Strip the "id" field — with store=False the
-                            # Responses API cannot look up items by ID and
-                            # returns 404.  The encrypted_content blob is
-                            # self-contained for reasoning chain continuity.
-                            replay_item = {k: v for k, v in ri.items() if k != "id"}
-                            items.append(replay_item)
-                            if item_id:
-                                seen_item_ids.add(item_id)
-                            has_codex_reasoning = True
-
-                if content_parts:
-                    items.append({"role": "assistant", "content": content_parts})
-                elif content_text.strip():
-                    items.append({"role": "assistant", "content": content_text})
-                elif has_codex_reasoning:
-                    # The Responses API requires a following item after each
-                    # reasoning item (otherwise: missing_following_item error).
-                    # When the assistant produced only reasoning with no visible
-                    # content, emit an empty assistant message as the required
-                    # following item.
-                    items.append({"role": "assistant", "content": ""})
-
-                tool_calls = msg.get("tool_calls")
-                if isinstance(tool_calls, list):
-                    for tc in tool_calls:
-                        if not isinstance(tc, dict):
-                            continue
-                        fn = tc.get("function", {})
-                        fn_name = fn.get("name")
-                        if not isinstance(fn_name, str) or not fn_name.strip():
-                            continue
-
-                        embedded_call_id, embedded_response_item_id = _split_responses_tool_id(
-                            tc.get("id")
-                        )
-                        call_id = tc.get("call_id")
-                        if not isinstance(call_id, str) or not call_id.strip():
-                            call_id = embedded_call_id
-                        if not isinstance(call_id, str) or not call_id.strip():
-                            if (
-                                isinstance(embedded_response_item_id, str)
-                                and embedded_response_item_id.startswith("fc_")
-                                and len(embedded_response_item_id) > len("fc_")
-                            ):
-                                call_id = f"call_{embedded_response_item_id[len('fc_'):]}"
-                            else:
-                                _raw_args = str(fn.get("arguments", "{}"))
-                                call_id = _deterministic_call_id(fn_name, _raw_args, len(items))
-                        call_id = call_id.strip()
-
-                        arguments = fn.get("arguments", "{}")
-                        if isinstance(arguments, dict):
-                            arguments = json.dumps(arguments, ensure_ascii=False)
-                        elif not isinstance(arguments, str):
-                            arguments = str(arguments)
-                        arguments = arguments.strip() or "{}"
-
-                        items.append({
-                            "type": "function_call",
-                            "call_id": call_id,
-                            "name": fn_name,
-                            "arguments": arguments,
-                        })
-                continue
-
-            # Non-assistant (user) role: emit multimodal parts when present,
-            # otherwise fall back to the text payload.
-            if content_parts:
-                items.append({"role": role, "content": content_parts})
-            else:
-                items.append({"role": role, "content": content_text})
-            continue
-
-        if role == "tool":
-            raw_tool_call_id = msg.get("tool_call_id")
-            call_id, _ = _split_responses_tool_id(raw_tool_call_id)
-            if not isinstance(call_id, str) or not call_id.strip():
-                if isinstance(raw_tool_call_id, str) and raw_tool_call_id.strip():
-                    call_id = raw_tool_call_id.strip()
-            if not isinstance(call_id, str) or not call_id.strip():
-                continue
-            items.append({
-                "type": "function_call_output",
-                "call_id": call_id,
-                "output": str(msg.get("content", "") or ""),
-            })
-
-    return items
-
-
-# ---------------------------------------------------------------------------
-# Input preflight / validation
-# ---------------------------------------------------------------------------
-
-def _preflight_codex_input_items(raw_items: Any) -> List[Dict[str, Any]]:
-    if not isinstance(raw_items, list):
-        raise ValueError("Codex Responses input must be a list of input items.")
-
-    normalized: List[Dict[str, Any]] = []
-    seen_ids: set = set()
-    for idx, item in enumerate(raw_items):
-        if not isinstance(item, dict):
-            raise ValueError(f"Codex Responses input[{idx}] must be an object.")
-
-        item_type = item.get("type")
-        if item_type == "function_call":
-            call_id = item.get("call_id")
-            name = item.get("name")
-            if not isinstance(call_id, str) or not call_id.strip():
-                raise ValueError(f"Codex Responses input[{idx}] function_call is missing call_id.")
-            if not isinstance(name, str) or not name.strip():
-                raise ValueError(f"Codex Responses input[{idx}] function_call is missing name.")
-
-            arguments = item.get("arguments", "{}")
-            if isinstance(arguments, dict):
-                arguments = json.dumps(arguments, ensure_ascii=False)
-            elif not isinstance(arguments, str):
-                arguments = str(arguments)
-            arguments = arguments.strip() or "{}"
-
-            normalized.append(
-                {
-                    "type": "function_call",
-                    "call_id": call_id.strip(),
-                    "name": name.strip(),
-                    "arguments": arguments,
-                }
-            )
-            continue
-
-        if item_type == "function_call_output":
-            call_id = item.get("call_id")
-            if not isinstance(call_id, str) or not call_id.strip():
-                raise ValueError(f"Codex Responses input[{idx}] function_call_output is missing call_id.")
-            output = item.get("output", "")
-            if output is None:
-                output = ""
-            if not isinstance(output, str):
-                output = str(output)
-
-            normalized.append(
-                {
-                    "type": "function_call_output",
-                    "call_id": call_id.strip(),
-                    "output": output,
-                }
-            )
-            continue
-
-        if item_type == "reasoning":
-            encrypted = item.get("encrypted_content")
-            if isinstance(encrypted, str) and encrypted:
-                item_id = item.get("id")
-                if isinstance(item_id, str) and item_id:
-                    if item_id in seen_ids:
-                        continue
-                    seen_ids.add(item_id)
-                reasoning_item = {"type": "reasoning", "encrypted_content": encrypted}
-                # Do NOT include the "id" in the outgoing item — with
-                # store=False (our default) the API tries to resolve the
-                # id server-side and returns 404.  The id is still used
-                # above for local deduplication via seen_ids.
-                summary = item.get("summary")
-                if isinstance(summary, list):
-                    reasoning_item["summary"] = summary
-                else:
-                    reasoning_item["summary"] = []
-                normalized.append(reasoning_item)
-            continue
-
-        role = item.get("role")
-        if role in {"user", "assistant"}:
-            content = item.get("content", "")
-            if content is None:
-                content = ""
-            if isinstance(content, list):
-                # Multimodal content from ``_chat_messages_to_responses_input``
-                # is already in Responses format (``input_text`` / ``input_image``).
-                # Validate each part and pass through.
-                validated: List[Dict[str, Any]] = []
-                for part_idx, part in enumerate(content):
-                    if isinstance(part, str):
-                        if part:
-                            validated.append({"type": "input_text", "text": part})
-                        continue
-                    if not isinstance(part, dict):
-                        raise ValueError(
-                            f"Codex Responses input[{idx}].content[{part_idx}] must be an object or string."
-                        )
-                    ptype = str(part.get("type") or "").strip().lower()
-                    if ptype in {"input_text", "text", "output_text"}:
-                        text = part.get("text", "")
-                        if not isinstance(text, str):
-                            text = str(text or "")
-                        validated.append({"type": "input_text", "text": text})
-                    elif ptype in {"input_image", "image_url"}:
-                        image_ref = part.get("image_url", "")
-                        detail = part.get("detail")
-                        if isinstance(image_ref, dict):
-                            url = image_ref.get("url", "")
-                            detail = image_ref.get("detail", detail)
-                        else:
-                            url = image_ref
-                        if not isinstance(url, str):
-                            url = str(url or "")
-                        image_part: Dict[str, Any] = {"type": "input_image", "image_url": url}
-                        if isinstance(detail, str) and detail.strip():
-                            image_part["detail"] = detail.strip()
-                        validated.append(image_part)
-                    else:
-                        raise ValueError(
-                            f"Codex Responses input[{idx}].content[{part_idx}] has unsupported type {part.get('type')!r}."
-                        )
-                normalized.append({"role": role, "content": validated})
-                continue
-            if not isinstance(content, str):
-                content = str(content)
-
-            normalized.append({"role": role, "content": content})
-            continue
-
-        raise ValueError(
-            f"Codex Responses input[{idx}] has unsupported item shape (type={item_type!r}, role={role!r})."
-        )
-
-    return normalized
-
-
-def _preflight_codex_api_kwargs(
-    api_kwargs: Any,
-    *,
-    allow_stream: bool = False,
-) -> Dict[str, Any]:
-    if not isinstance(api_kwargs, dict):
-        raise ValueError("Codex Responses request must be a dict.")
-
-    required = {"model", "instructions", "input"}
-    missing = [key for key in required if key not in api_kwargs]
-    if missing:
-        raise ValueError(f"Codex Responses request missing required field(s): {', '.join(sorted(missing))}.")
-
-    model = api_kwargs.get("model")
-    if not isinstance(model, str) or not model.strip():
-        raise ValueError("Codex Responses request 'model' must be a non-empty string.")
-    model = model.strip()
-
-    instructions = api_kwargs.get("instructions")
-    if instructions is None:
-        instructions = ""
-    if not isinstance(instructions, str):
-        instructions = str(instructions)
-    instructions = instructions.strip() or DEFAULT_AGENT_IDENTITY
-
-    normalized_input = _preflight_codex_input_items(api_kwargs.get("input"))
-
-    tools = api_kwargs.get("tools")
-    normalized_tools = None
-    if tools is not None:
-        if not isinstance(tools, list):
-            raise ValueError("Codex Responses request 'tools' must be a list when provided.")
-        normalized_tools = []
-        for idx, tool in enumerate(tools):
-            if not isinstance(tool, dict):
-                raise ValueError(f"Codex Responses tools[{idx}] must be an object.")
-            if tool.get("type") != "function":
-                raise ValueError(f"Codex Responses tools[{idx}] has unsupported type {tool.get('type')!r}.")
-
-            name = tool.get("name")
-            parameters = tool.get("parameters")
-            if not isinstance(name, str) or not name.strip():
-                raise ValueError(f"Codex Responses tools[{idx}] is missing a valid name.")
-            if not isinstance(parameters, dict):
-                raise ValueError(f"Codex Responses tools[{idx}] is missing valid parameters.")
-
-            description = tool.get("description", "")
-            if description is None:
-                description = ""
-            if not isinstance(description, str):
-                description = str(description)
-
-            strict = tool.get("strict", False)
-            if not isinstance(strict, bool):
-                strict = bool(strict)
-
-            normalized_tools.append(
-                {
-                    "type": "function",
-                    "name": name.strip(),
-                    "description": description,
-                    "strict": strict,
-                    "parameters": parameters,
-                }
-            )
-
-    store = api_kwargs.get("store", False)
-    if store is not False:
-        raise ValueError("Codex Responses contract requires 'store' to be false.")
-
-    allowed_keys = {
-        "model", "instructions", "input", "tools", "store",
-        "reasoning", "include", "max_output_tokens", "temperature",
-        "tool_choice", "parallel_tool_calls", "prompt_cache_key", "service_tier",
-        "extra_headers",
-    }
-    normalized: Dict[str, Any] = {
-        "model": model,
-        "instructions": instructions,
-        "input": normalized_input,
-        "store": False,
-    }
-    if normalized_tools is not None:
-        normalized["tools"] = normalized_tools
-
-    # Pass through reasoning config
-    reasoning = api_kwargs.get("reasoning")
-    if isinstance(reasoning, dict):
-        normalized["reasoning"] = reasoning
-    include = api_kwargs.get("include")
-    if isinstance(include, list):
-        normalized["include"] = include
-    service_tier = api_kwargs.get("service_tier")
-    if isinstance(service_tier, str) and service_tier.strip():
-        normalized["service_tier"] = service_tier.strip()
-
-    # Pass through max_output_tokens and temperature
-    max_output_tokens = api_kwargs.get("max_output_tokens")
-    if isinstance(max_output_tokens, (int, float)) and max_output_tokens > 0:
-        normalized["max_output_tokens"] = int(max_output_tokens)
-    temperature = api_kwargs.get("temperature")
-    if isinstance(temperature, (int, float)):
-        normalized["temperature"] = float(temperature)
-
-    # Pass through tool_choice, parallel_tool_calls, prompt_cache_key
-    for passthrough_key in ("tool_choice", "parallel_tool_calls", "prompt_cache_key"):
-        val = api_kwargs.get(passthrough_key)
-        if val is not None:
-            normalized[passthrough_key] = val
-
-    extra_headers = api_kwargs.get("extra_headers")
-    if extra_headers is not None:
-        if not isinstance(extra_headers, dict):
-            raise ValueError("Codex Responses request 'extra_headers' must be an object.")
-        normalized_headers: Dict[str, str] = {}
-        for key, value in extra_headers.items():
-            if not isinstance(key, str) or not key.strip():
-                raise ValueError("Codex Responses request 'extra_headers' keys must be non-empty strings.")
-            if value is None:
-                continue
-            normalized_headers[key.strip()] = str(value)
-        if normalized_headers:
-            normalized["extra_headers"] = normalized_headers
-
-    if allow_stream:
-        stream = api_kwargs.get("stream")
-        if stream is not None and stream is not True:
-            raise ValueError("Codex Responses 'stream' must be true when set.")
-        if stream is True:
-            normalized["stream"] = True
-        allowed_keys.add("stream")
-    elif "stream" in api_kwargs:
-        raise ValueError("Codex Responses stream flag is only allowed in fallback streaming requests.")
-
-    unexpected = sorted(key for key in api_kwargs if key not in allowed_keys)
-    if unexpected:
-        raise ValueError(
-            f"Codex Responses request has unsupported field(s): {', '.join(unexpected)}."
-        )
-
-    return normalized
-
-
-# ---------------------------------------------------------------------------
-# Response extraction helpers
-# ---------------------------------------------------------------------------
-
-def _extract_responses_message_text(item: Any) -> str:
-    """Extract assistant text from a Responses message output item."""
-    content = getattr(item, "content", None)
-    if not isinstance(content, list):
-        return ""
-
-    chunks: List[str] = []
-    for part in content:
-        ptype = getattr(part, "type", None)
-        if ptype not in {"output_text", "text"}:
-            continue
-        text = getattr(part, "text", None)
-        if isinstance(text, str) and text:
-            chunks.append(text)
-    return "".join(chunks).strip()
-
-
-def _extract_responses_reasoning_text(item: Any) -> str:
-    """Extract a compact reasoning text from a Responses reasoning item."""
-    summary = getattr(item, "summary", None)
-    if isinstance(summary, list):
-        chunks: List[str] = []
-        for part in summary:
-            text = getattr(part, "text", None)
-            if isinstance(text, str) and text:
-                chunks.append(text)
-        if chunks:
-            return "\n".join(chunks).strip()
-    text = getattr(item, "text", None)
-    if isinstance(text, str) and text:
-        return text.strip()
-    return ""
-
-
-# ---------------------------------------------------------------------------
-# Full response normalization
-# ---------------------------------------------------------------------------
-
-def _normalize_codex_response(response: Any) -> tuple[Any, str]:
-    """Normalize a Responses API object to an assistant_message-like object."""
-    output = getattr(response, "output", None)
-    if not isinstance(output, list) or not output:
-        # The Codex backend can return empty output when the answer was
-        # delivered entirely via stream events. Check output_text as a
-        # last-resort fallback before raising.
-        out_text = getattr(response, "output_text", None)
-        if isinstance(out_text, str) and out_text.strip():
-            logger.debug(
-                "Codex response has empty output but output_text is present (%d chars); "
-                "synthesizing output item.", len(out_text.strip()),
-            )
-            output = [SimpleNamespace(
-                type="message", role="assistant", status="completed",
-                content=[SimpleNamespace(type="output_text", text=out_text.strip())],
-            )]
-            response.output = output
-        else:
-            raise RuntimeError("Responses API returned no output items")
-
-    response_status = getattr(response, "status", None)
-    if isinstance(response_status, str):
-        response_status = response_status.strip().lower()
-    else:
-        response_status = None
-
-    if response_status in {"failed", "cancelled"}:
-        error_obj = getattr(response, "error", None)
-        if isinstance(error_obj, dict):
-            error_msg = error_obj.get("message") or str(error_obj)
-        else:
-            error_msg = str(error_obj) if error_obj else f"Responses API returned status '{response_status}'"
-        raise RuntimeError(error_msg)
-
-    content_parts: List[str] = []
-    reasoning_parts: List[str] = []
-    reasoning_items_raw: List[Dict[str, Any]] = []
-    tool_calls: List[Any] = []
-    has_incomplete_items = response_status in {"queued", "in_progress", "incomplete"}
-    saw_commentary_phase = False
-    saw_final_answer_phase = False
-
-    for item in output:
-        item_type = getattr(item, "type", None)
-        item_status = getattr(item, "status", None)
-        if isinstance(item_status, str):
-            item_status = item_status.strip().lower()
-        else:
-            item_status = None
-
-        if item_status in {"queued", "in_progress", "incomplete"}:
-            has_incomplete_items = True
-
-        if item_type == "message":
-            item_phase = getattr(item, "phase", None)
-            if isinstance(item_phase, str):
-                normalized_phase = item_phase.strip().lower()
-                if normalized_phase in {"commentary", "analysis"}:
-                    saw_commentary_phase = True
-                elif normalized_phase in {"final_answer", "final"}:
-                    saw_final_answer_phase = True
-            message_text = _extract_responses_message_text(item)
-            if message_text:
-                content_parts.append(message_text)
-        elif item_type == "reasoning":
-            reasoning_text = _extract_responses_reasoning_text(item)
-            if reasoning_text:
-                reasoning_parts.append(reasoning_text)
-            # Capture the full reasoning item for multi-turn continuity.
-            # encrypted_content is an opaque blob the API needs back on
-            # subsequent turns to maintain coherent reasoning chains.
-            encrypted = getattr(item, "encrypted_content", None)
-            if isinstance(encrypted, str) and encrypted:
-                raw_item = {"type": "reasoning", "encrypted_content": encrypted}
-                item_id = getattr(item, "id", None)
-                if isinstance(item_id, str) and item_id:
-                    raw_item["id"] = item_id
-                # Capture summary — required by the API when replaying reasoning items
-                summary = getattr(item, "summary", None)
-                if isinstance(summary, list):
-                    raw_summary = []
-                    for part in summary:
-                        text = getattr(part, "text", None)
-                        if isinstance(text, str):
-                            raw_summary.append({"type": "summary_text", "text": text})
-                    raw_item["summary"] = raw_summary
-                reasoning_items_raw.append(raw_item)
-        elif item_type == "function_call":
-            if item_status in {"queued", "in_progress", "incomplete"}:
-                continue
-            fn_name = getattr(item, "name", "") or ""
-            arguments = getattr(item, "arguments", "{}")
-            if not isinstance(arguments, str):
-                arguments = json.dumps(arguments, ensure_ascii=False)
-            raw_call_id = getattr(item, "call_id", None)
-            raw_item_id = getattr(item, "id", None)
-            embedded_call_id, _ = _split_responses_tool_id(raw_item_id)
-            call_id = raw_call_id if isinstance(raw_call_id, str) and raw_call_id.strip() else embedded_call_id
-            if not isinstance(call_id, str) or not call_id.strip():
-                call_id = _deterministic_call_id(fn_name, arguments, len(tool_calls))
-            call_id = call_id.strip()
-            response_item_id = raw_item_id if isinstance(raw_item_id, str) else None
-            response_item_id = _derive_responses_function_call_id(call_id, response_item_id)
-            tool_calls.append(SimpleNamespace(
-                id=call_id,
-                call_id=call_id,
-                response_item_id=response_item_id,
-                type="function",
-                function=SimpleNamespace(name=fn_name, arguments=arguments),
-            ))
-        elif item_type == "custom_tool_call":
-            fn_name = getattr(item, "name", "") or ""
-            arguments = getattr(item, "input", "{}")
-            if not isinstance(arguments, str):
-                arguments = json.dumps(arguments, ensure_ascii=False)
-            raw_call_id = getattr(item, "call_id", None)
-            raw_item_id = getattr(item, "id", None)
-            embedded_call_id, _ = _split_responses_tool_id(raw_item_id)
-            call_id = raw_call_id if isinstance(raw_call_id, str) and raw_call_id.strip() else embedded_call_id
-            if not isinstance(call_id, str) or not call_id.strip():
-                call_id = _deterministic_call_id(fn_name, arguments, len(tool_calls))
-            call_id = call_id.strip()
-            response_item_id = raw_item_id if isinstance(raw_item_id, str) else None
-            response_item_id = _derive_responses_function_call_id(call_id, response_item_id)
-            tool_calls.append(SimpleNamespace(
-                id=call_id,
-                call_id=call_id,
-                response_item_id=response_item_id,
-                type="function",
-                function=SimpleNamespace(name=fn_name, arguments=arguments),
-            ))
-
-    final_text = "\n".join([p for p in content_parts if p]).strip()
-    if not final_text and hasattr(response, "output_text"):
-        out_text = getattr(response, "output_text", "")
-        if isinstance(out_text, str):
-            final_text = out_text.strip()
-
-    assistant_message = SimpleNamespace(
-        content=final_text,
-        tool_calls=tool_calls,
-        reasoning="\n\n".join(reasoning_parts).strip() if reasoning_parts else None,
-        reasoning_content=None,
-        reasoning_details=None,
-        codex_reasoning_items=reasoning_items_raw or None,
-    )
-
-    if tool_calls:
-        finish_reason = "tool_calls"
-    elif has_incomplete_items or (saw_commentary_phase and not saw_final_answer_phase):
-        finish_reason = "incomplete"
-    elif reasoning_items_raw and not final_text:
-        # Response contains only reasoning (encrypted thinking state) with
-        # no visible content or tool calls.  The model is still thinking and
-        # needs another turn to produce the actual answer.  Marking this as
-        # "stop" would send it into the empty-content retry loop which burns
-        # 3 retries then fails — treat it as incomplete instead so the Codex
-        # continuation path handles it correctly.
-        finish_reason = "incomplete"
-    else:
-        finish_reason = "stop"
-    return assistant_message, finish_reason
--- a/agent/context_compressor.py
+++ b/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)
@@ -17,10 +13,7 @@ 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

@@ -31,21 +24,16 @@ from agent.model_metadata import (
    get_model_context_length,
    estimate_messages_tokens_rough,
 )
-from agent.redact import redact_sensitive_text

 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]:"

@@ -64,174 +52,6 @@ _CHARS_PER_TOKEN = 4
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600


-def _truncate_tool_call_args_json(args: str, head_chars: int = 200) -> str:
-    """Shrink long string values inside a tool-call arguments JSON blob while
-    preserving JSON validity.
-
-    The ``function.arguments`` field on a tool call is a JSON-encoded string
-    passed through to the LLM provider; downstream providers strictly
-    validate it and return a non-retryable 400 when it is not well-formed.
-    An earlier implementation sliced the raw JSON at a fixed byte offset and
-    appended ``...[truncated]`` — which routinely produced strings like::
-
-        {"path": "/foo/bar", "content": "# long markdown
-        ...[truncated]
-
-    i.e. an unterminated string and a missing closing brace. MiniMax, for
-    example, rejects this with ``invalid function arguments json string``
-    and the session gets stuck re-sending the same broken history on every
-    turn. See issue #11762 for the observed loop.
-
-    This helper parses the arguments, shrinks long string leaves inside the
-    parsed structure, and re-serialises. Non-string values (paths, ints,
-    booleans) are preserved intact. If the arguments are not valid JSON
-    to begin with — some model backends use non-JSON tool arguments — the
-    original string is returned unchanged rather than replaced with
-    something neither we nor the backend can parse.
-    """
-    try:
-        parsed = json.loads(args)
-    except (ValueError, TypeError):
-        return args
-
-    def _shrink(obj: Any) -> Any:
-        if isinstance(obj, str):
-            if len(obj) > head_chars:
-                return obj[:head_chars] + "...[truncated]"
-            return obj
-        if isinstance(obj, dict):
-            return {k: _shrink(v) for k, v in obj.items()}
-        if isinstance(obj, list):
-            return [_shrink(v) for v in obj]
-        return obj
-
-    shrunken = _shrink(parsed)
-    # ensure_ascii=False preserves CJK/emoji instead of bloating with \uXXXX
-    return json.dumps(shrunken, ensure_ascii=False)
-
-
-def _summarize_tool_result(tool_name: str, tool_args: str, tool_content: str) -> str:
-    """Create an informative 1-line summary of a tool call + result.
-
-    Used during the pre-compression pruning pass to replace large tool
-    outputs with a short but useful description of what the tool did,
-    rather than a generic placeholder that carries zero information.
-
-    Returns strings like::
-
-        [terminal] ran `npm test` -> exit 0, 47 lines output
-        [read_file] read config.py from line 1 (1,200 chars)
-        [search_files] content search for 'compress' in agent/ -> 12 matches
-    """
-    try:
-        args = json.loads(tool_args) if tool_args else {}
-    except (json.JSONDecodeError, TypeError):
-        args = {}
-
-    content = tool_content or ""
-    content_len = len(content)
-    line_count = content.count("\n") + 1 if content.strip() else 0
-
-    if tool_name == "terminal":
-        cmd = args.get("command", "")
-        if len(cmd) > 80:
-            cmd = cmd[:77] + "..."
-        exit_match = re.search(r'"exit_code"\s*:\s*(-?\d+)', content)
-        exit_code = exit_match.group(1) if exit_match else "?"
-        return f"[terminal] ran `{cmd}` -> exit {exit_code}, {line_count} lines output"
-
-    if tool_name == "read_file":
-        path = args.get("path", "?")
-        offset = args.get("offset", 1)
-        return f"[read_file] read {path} from line {offset} ({content_len:,} chars)"
-
-    if tool_name == "write_file":
-        path = args.get("path", "?")
-        written_lines = args.get("content", "").count("\n") + 1 if args.get("content") else "?"
-        return f"[write_file] wrote to {path} ({written_lines} lines)"
-
-    if tool_name == "search_files":
-        pattern = args.get("pattern", "?")
-        path = args.get("path", ".")
-        target = args.get("target", "content")
-        match_count = re.search(r'"total_count"\s*:\s*(\d+)', content)
-        count = match_count.group(1) if match_count else "?"
-        return f"[search_files] {target} search for '{pattern}' in {path} -> {count} matches"
-
-    if tool_name == "patch":
-        path = args.get("path", "?")
-        mode = args.get("mode", "replace")
-        return f"[patch] {mode} in {path} ({content_len:,} chars result)"
-
-    if tool_name in ("browser_navigate", "browser_click", "browser_snapshot",
-                     "browser_type", "browser_scroll", "browser_vision"):
-        url = args.get("url", "")
-        ref = args.get("ref", "")
-        detail = f" {url}" if url else (f" ref={ref}" if ref else "")
-        return f"[{tool_name}]{detail} ({content_len:,} chars)"
-
-    if tool_name == "web_search":
-        query = args.get("query", "?")
-        return f"[web_search] query='{query}' ({content_len:,} chars result)"
-
-    if tool_name == "web_extract":
-        urls = args.get("urls", [])
-        url_desc = urls[0] if isinstance(urls, list) and urls else "?"
-        if isinstance(urls, list) and len(urls) > 1:
-            url_desc += f" (+{len(urls) - 1} more)"
-        return f"[web_extract] {url_desc} ({content_len:,} chars)"
-
-    if tool_name == "delegate_task":
-        goal = args.get("goal", "")
-        if len(goal) > 60:
-            goal = goal[:57] + "..."
-        return f"[delegate_task] '{goal}' ({content_len:,} chars result)"
-
-    if tool_name == "execute_code":
-        code_preview = (args.get("code") or "")[:60].replace("\n", " ")
-        if len(args.get("code", "")) > 60:
-            code_preview += "..."
-        return f"[execute_code] `{code_preview}` ({line_count} lines output)"
-
-    if tool_name in ("skill_view", "skills_list", "skill_manage"):
-        name = args.get("name", "?")
-        return f"[{tool_name}] name={name} ({content_len:,} chars)"
-
-    if tool_name == "vision_analyze":
-        question = args.get("question", "")[:50]
-        return f"[vision_analyze] '{question}' ({content_len:,} chars)"
-
-    if tool_name == "memory":
-        action = args.get("action", "?")
-        target = args.get("target", "?")
-        return f"[memory] {action} on {target}"
-
-    if tool_name == "todo":
-        return "[todo] updated task list"
-
-    if tool_name == "clarify":
-        return "[clarify] asked user a question"
-
-    if tool_name == "text_to_speech":
-        return f"[text_to_speech] generated audio ({content_len:,} chars)"
-
-    if tool_name == "cronjob":
-        action = args.get("action", "?")
-        return f"[cronjob] {action}"
-
-    if tool_name == "process":
-        action = args.get("action", "?")
-        sid = args.get("session_id", "?")
-        return f"[process] {action} session={sid}"
-
-    # Generic fallback
-    first_arg = ""
-    for k, v in list(args.items())[:2]:
-        sv = str(v)[:40]
-        first_arg += f" {k}={sv}"
-    return f"[{tool_name}]{first_arg} ({content_len:,} chars result)"
-
-
 class ContextCompressor(ContextEngine):
    """Default context engine — compresses conversation context via lossy summarization.

@@ -253,8 +73,6 @@ class ContextCompressor(ContextEngine):
        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,
@@ -263,14 +81,12 @@ class ContextCompressor(ContextEngine):
        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),
@@ -290,13 +106,11 @@ 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
@@ -344,9 +158,6 @@ class ContextCompressor(ContextEngine):

        # Stores the previous compaction summary for iterative updates
        self._previous_summary: Optional[str] = None
-        # Anti-thrashing: track whether last compression was effective
-        self._last_compression_savings_pct: float = 100.0
-        self._ineffective_compression_count: int = 0
        self._summary_failure_cooldown_until: float = 0.0

    def update_from_response(self, usage: Dict[str, Any]):
@@ -355,26 +166,9 @@ class ContextCompressor(ContextEngine):
        self.last_completion_tokens = usage.get("completion_tokens", 0)

    def should_compress(self, prompt_tokens: int = None) -> bool:
-        """Check if context exceeds the compression threshold.
-
-        Includes anti-thrashing protection: if the last two compressions
-        each saved less than 10%, skip compression to avoid infinite loops
-        where each pass removes only 1-2 messages.
-        """
+        """Check if context exceeds the compression threshold."""
        tokens = prompt_tokens if prompt_tokens is not None else self.last_prompt_tokens
-        if tokens < self.threshold_tokens:
-            return False
-        # Anti-thrashing: back off if recent compressions were ineffective
-        if self._ineffective_compression_count >= 2:
-            if not self.quiet_mode:
-                logger.warning(
-                    "Compression skipped — last %d compressions saved <10%% each. "
-                    "Consider /new to start a fresh session, or /compress <topic> "
-                    "for focused compression.",
-                    self._ineffective_compression_count,
-                )
-            return False
-        return True
+        return tokens >= self.threshold_tokens

    # ------------------------------------------------------------------
    # Tool output pruning (cheap pre-pass, no LLM call)
@@ -384,16 +178,7 @@ 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
@@ -409,22 +194,6 @@ 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
@@ -433,8 +202,7 @@ 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):
@@ -449,76 +217,18 @@ class ContextCompressor(ContextEngine):
        else:
            prune_boundary = len(result) - protect_tail_count

-        # Pass 1: Deduplicate identical tool results.
-        # When the same file is read multiple times, keep only the most recent
-        # full copy and replace older duplicates with a back-reference.
-        content_hashes: dict = {}  # hash -> (index, tool_call_id)
-        for i in range(len(result) - 1, -1, -1):
-            msg = result[i]
-            if msg.get("role") != "tool":
-                continue
-            content = msg.get("content") or ""
-            # Skip multimodal content (list of content blocks)
-            if isinstance(content, list):
-                continue
-            if len(content) < 200:
-                continue
-            h = hashlib.md5(content.encode("utf-8", errors="replace")).hexdigest()[:12]
-            if h in content_hashes:
-                # This is an older duplicate — replace with back-reference
-                result[i] = {**msg, "content": "[Duplicate tool output — same content as a more recent call]"}
-                pruned += 1
-            else:
-                content_hashes[h] = (i, msg.get("tool_call_id", "?"))
-
-        # Pass 2: Replace old tool results with informative summaries
        for i in range(prune_boundary):
            msg = result[i]
            if msg.get("role") != "tool":
                continue
            content = msg.get("content", "")
-            # Skip multimodal content (list of content blocks)
-            if isinstance(content, list):
-                continue
            if not content or content == _PRUNED_TOOL_PLACEHOLDER:
                continue
-            # Skip already-deduplicated or previously-summarized results
-            if content.startswith("[Duplicate tool output"):
-                continue
            # Only prune if the content is substantial (>200 chars)
            if len(content) > 200:
-                call_id = msg.get("tool_call_id", "")
-                tool_name, tool_args = call_id_to_tool.get(call_id, ("unknown", ""))
-                summary = _summarize_tool_result(tool_name, tool_args, content)
-                result[i] = {**msg, "content": summary}
+                result[i] = {**msg, "content": _PRUNED_TOOL_PLACEHOLDER}
                pruned += 1

-        # Pass 3: Truncate large tool_call arguments in assistant messages
-        # outside the protected tail. write_file with 50KB content, for
-        # example, survives pruning entirely without this.
-        #
-        # The shrinking is done inside the parsed JSON structure so the
-        # result remains valid JSON — otherwise downstream providers 400
-        # on every subsequent turn until the broken call falls out of
-        # the window. See ``_truncate_tool_call_args_json`` docstring.
-        for i in range(prune_boundary):
-            msg = result[i]
-            if msg.get("role") != "assistant" or not msg.get("tool_calls"):
-                continue
-            new_tcs = []
-            modified = False
-            for tc in msg["tool_calls"]:
-                if isinstance(tc, dict):
-                    args = tc.get("function", {}).get("arguments", "")
-                    if len(args) > 500:
-                        new_args = _truncate_tool_call_args_json(args)
-                        if new_args != args:
-                            tc = {**tc, "function": {**tc["function"], "arguments": new_args}}
-                            modified = True
-                new_tcs.append(tc)
-            if modified:
-                result[i] = {**msg, "tool_calls": new_tcs}
-
        return result, pruned

    # ------------------------------------------------------------------
@@ -551,15 +261,11 @@ class ContextCompressor(ContextEngine):
        Includes tool call arguments and result content (up to
        ``_CONTENT_MAX`` chars per message) so the summarizer can preserve
        specific details like file paths, commands, and outputs.
-
-        All content is redacted before serialization to prevent secrets
-        (API keys, tokens, passwords) from leaking into the summary that
-        gets sent to the auxiliary model and persisted across compactions.
        """
        parts = []
        for msg in turns:
            role = msg.get("role", "unknown")
-            content = redact_sensitive_text(msg.get("content") or "")
+            content = msg.get("content") or ""

            # Tool results: keep enough content for the summarizer
            if role == "tool":
@@ -580,7 +286,7 @@ class ContextCompressor(ContextEngine):
                        if isinstance(tc, dict):
                            fn = tc.get("function", {})
                            name = fn.get("name", "?")
-                            args = redact_sensitive_text(fn.get("arguments", ""))
+                            args = fn.get("arguments", "")
                            # Truncate long arguments but keep enough for context
                            if len(args) > self._TOOL_ARGS_MAX:
                                args = args[:self._TOOL_ARGS_HEAD] + "..."
@@ -600,20 +306,13 @@ 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.
@@ -629,89 +328,9 @@ class ContextCompressor(ContextEngine):
        summary_budget = self._compute_summary_budget(turns_to_summarize)
        content_to_summarize = self._serialize_for_summary(turns_to_summarize)

-        # Preamble shared by both first-compaction and iterative-update prompts.
-        # Inspired by OpenCode's "do not respond to any questions" instruction
-        # and Codex's "another language model" framing.
-        _summarizer_preamble = (
-            "You are a summarization agent creating a context checkpoint. "
-            "Your output will be injected as reference material for a DIFFERENT "
-            "assistant that continues the conversation. "
-            "Do NOT respond to any questions or requests in the conversation — "
-            "only output the structured summary. "
-            "Do NOT include any preamble, greeting, or prefix. "
-            "Write the summary in the same language the user was using in the "
-            "conversation — do not translate or switch to English. "
-            "NEVER include API keys, tokens, passwords, secrets, credentials, "
-            "or connection strings in the summary — replace any that appear "
-            "with [REDACTED]. Note that the user had credentials present, but "
-            "do not preserve their values."
-        )
-
-        # 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. NEVER include API keys, tokens, passwords, or credentials — write [REDACTED] instead.]
-
-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}
@@ -719,42 +338,87 @@ 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. Even for the focus topic, NEVER preserve API keys, tokens, passwords, or credentials — use [REDACTED]."""
+## 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:
@@ -764,16 +428,12 @@ The user has requested that this compaction PRIORITISE preserving all informatio
            # Handle cases where content is not a string (e.g., dict from llama.cpp)
            if not isinstance(content, str):
                content = str(content) if content else ""
-            # Redact the summary output as well — the summarizer LLM may
-            # ignore prompt instructions and echo back secrets verbatim.
-            summary = redact_sensitive_text(content.strip())
+            summary = content.strip()
            # 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 "
@@ -781,42 +441,12 @@ 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(turns_to_summarize)  # 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

@@ -939,62 +569,6 @@ 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,
@@ -1012,8 +586,7 @@ 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
@@ -1052,17 +625,13 @@ 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:
@@ -1074,12 +643,6 @@ 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)
@@ -1137,17 +700,17 @@ The user has requested that this compaction PRIORITISE preserving all informatio
            )

        # Phase 3: Generate structured summary
-        summary = self._generate_summary(turns_to_summarize, focus_topic=focus_topic)
+        summary = self._generate_summary(turns_to_summarize)

        # Phase 4: Assemble compressed message list
        compressed = []
        for i in range(compress_start):
            msg = messages[i].copy()
-            if i == 0 and msg.get("role") == "system":
-                existing = msg.get("content") or ""
-                _compression_note = "[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
-                if _compression_note not in existing:
-                    msg["content"] = existing + "\n\n" + _compression_note
+            if i == 0 and msg.get("role") == "system" and self.compression_count == 0:
+                msg["content"] = (
+                    (msg.get("content") or "")
+                    + "\n\n[Note: Some earlier conversation turns have been compacted into a handoff summary to preserve context space. The current session state may still reflect earlier work, so build on that summary and state rather than re-doing work.]"
+                )
            compressed.append(msg)

        # If LLM summary failed, insert a static fallback so the model
@@ -1192,12 +755,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
            msg = messages[i].copy()
            if _merge_summary_into_tail and i == compress_end:
                original = msg.get("content") or ""
-                msg["content"] = (
-                    summary
-                    + "\n\n--- END OF CONTEXT SUMMARY — "
-                    "respond to the message below, not the summary above ---\n\n"
-                    + original
-                )
+                msg["content"] = summary + "\n\n" + original
                _merge_summary_into_tail = False
            compressed.append(msg)

@@ -1205,24 +763,14 @@ 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)

--- a/agent/context_engine.py
+++ b/agent/context_engine.py
@@ -26,7 +26,7 @@ Lifecycle:
 """

 from abc import ABC, abstractmethod
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional


 class ContextEngine(ABC):
--- a/agent/context_references.py
+++ b/agent/context_references.py
@@ -483,7 +483,9 @@ def _rg_files(path: Path, cwd: Path, limit: int) -> list[Path] | None:
            text=True,
            timeout=10,
        )
-    except (FileNotFoundError, OSError, subprocess.TimeoutExpired):
+    except FileNotFoundError:
+        return None
+    except subprocess.TimeoutExpired:
        return None
    if result.returncode != 0:
        return None
--- a/agent/copilot_acp_client.py
+++ b/agent/copilot_acp_client.py
@@ -21,9 +21,6 @@ from pathlib import Path
 from types import SimpleNamespace
 from typing import Any

-from agent.file_safety import get_read_block_error, is_write_denied
-from agent.redact import redact_sensitive_text
-
 ACP_MARKER_BASE_URL = "acp://copilot"
 _DEFAULT_TIMEOUT_SECONDS = 900.0

@@ -57,18 +54,6 @@ def _jsonrpc_error(message_id: Any, code: int, message: str) -> dict[str, Any]:
    }


-def _permission_denied(message_id: Any) -> dict[str, Any]:
-    return {
-        "jsonrpc": "2.0",
-        "id": message_id,
-        "result": {
-            "outcome": {
-                "outcome": "cancelled",
-            }
-        },
-    }
-
-
 def _format_messages_as_prompt(
    messages: list[dict[str, Any]],
    model: str | None = None,
@@ -328,25 +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)
@@ -401,8 +370,6 @@ class CopilotACPClient:
        stderr_tail: deque[str] = deque(maxlen=40)

        def _stdout_reader() -> None:
-            if proc.stdout is None:
-                return
            for line in proc.stdout:
                try:
                    inbox.put(json.loads(line))
@@ -550,13 +517,18 @@ class CopilotACPClient:
        params = msg.get("params") or {}

        if method == "session/request_permission":
-            response = _permission_denied(message_id)
+            response = {
+                "jsonrpc": "2.0",
+                "id": message_id,
+                "result": {
+                    "outcome": {
+                        "outcome": "allow_once",
+                    }
+                },
+            }
        elif method == "fs/read_text_file":
            try:
                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
-                block_error = get_read_block_error(str(path))
-                if block_error:
-                    raise PermissionError(block_error)
                content = path.read_text() if path.exists() else ""
                line = params.get("line")
                limit = params.get("limit")
@@ -565,8 +537,6 @@ class CopilotACPClient:
                    start = line - 1
                    end = start + limit if isinstance(limit, int) and limit > 0 else None
                    content = "".join(lines[start:end])
-                if content:
-                    content = redact_sensitive_text(content)
                response = {
                    "jsonrpc": "2.0",
                    "id": message_id,
@@ -579,10 +549,6 @@ class CopilotACPClient:
        elif method == "fs/write_text_file":
            try:
                path = _ensure_path_within_cwd(str(params.get("path") or ""), cwd)
-                if is_write_denied(str(path)):
-                    raise PermissionError(
-                        f"Write denied: '{path}' is a protected system/credential file."
-                    )
                path.parent.mkdir(parents=True, exist_ok=True)
                path.write_text(str(params.get("content") or ""))
                response = {
--- a/agent/credential_pool.py
+++ b/agent/credential_pool.py
@@ -18,10 +18,12 @@ import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
    CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
    DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
+    KIMI_CODE_BASE_URL,
    PROVIDER_REGISTRY,
    _auth_store_lock,
    _codex_access_token_is_expiring,
    _decode_jwt_claims,
+    _import_codex_cli_tokens,
    _load_auth_store,
    _load_provider_state,
    _resolve_kimi_base_url,
@@ -286,14 +288,6 @@ def _iter_custom_providers(config: Optional[dict] = None):
        return
    custom_providers = config.get("custom_providers")
    if not isinstance(custom_providers, list):
-        # Fall back to the v12+ providers dict via the compatibility layer
-        try:
-            from hermes_cli.config import get_compatible_custom_providers
-
-            custom_providers = get_compatible_custom_providers(config)
-        except Exception:
-            return
-    if not custom_providers:
        return
    for entry in custom_providers:
        if not isinstance(entry, dict):
@@ -455,6 +449,39 @@ class CredentialPool:
            logger.debug("Failed to sync from credentials file: %s", exc)
        return entry

+    def _sync_codex_entry_from_cli(self, entry: PooledCredential) -> PooledCredential:
+        """Sync an openai-codex pool entry from ~/.codex/auth.json if tokens differ.
+
+        OpenAI OAuth refresh tokens are single-use and rotate on every refresh.
+        When the Codex CLI (or another Hermes profile) refreshes its token,
+        the pool entry's refresh_token becomes stale.  This method detects that
+        by comparing against ~/.codex/auth.json and syncing the fresh pair.
+        """
+        if self.provider != "openai-codex":
+            return entry
+        try:
+            cli_tokens = _import_codex_cli_tokens()
+            if not cli_tokens:
+                return entry
+            cli_refresh = cli_tokens.get("refresh_token", "")
+            cli_access = cli_tokens.get("access_token", "")
+            if cli_refresh and cli_refresh != entry.refresh_token:
+                logger.debug("Pool entry %s: syncing tokens from ~/.codex/auth.json (refresh token changed)", entry.id)
+                updated = replace(
+                    entry,
+                    access_token=cli_access,
+                    refresh_token=cli_refresh,
+                    last_status=None,
+                    last_status_at=None,
+                    last_error_code=None,
+                )
+                self._replace_entry(entry, updated)
+                self._persist()
+                return updated
+        except Exception as exc:
+            logger.debug("Failed to sync 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.

@@ -550,6 +577,13 @@ 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,
@@ -635,6 +669,37 @@ 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)
+                        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

@@ -698,6 +763,16 @@ class CredentialPool:
                if synced is not entry:
                    entry = synced
                    cleared_any = True
+            # For openai-codex entries, sync from ~/.codex/auth.json before
+            # any status/refresh checks.  This picks up tokens refreshed by
+            # the Codex CLI or another Hermes profile.
+            if (self.provider == "openai-codex"
+                    and entry.last_status == STATUS_EXHAUSTED
+                    and entry.refresh_token):
+                synced = self._sync_codex_entry_from_cli(entry)
+                if synced is not entry:
+                    entry = synced
+                    cleared_any = True
            if entry.last_status == STATUS_EXHAUSTED:
                exhausted_until = _exhausted_until(entry)
                if exhausted_until is not None and now < exhausted_until:
@@ -983,14 +1058,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
    active_sources: Set[str] = set()
    auth_store = _load_auth_store()

-    # Shared suppression gate — used at every upsert site so
-    # `hermes auth remove <provider> <N>` is stable across all source types.
-    try:
-        from hermes_cli.auth import is_source_suppressed as _is_suppressed
-    except ImportError:
-        def _is_suppressed(_p, _s):  # type: ignore[misc]
-            return False
-
    if provider == "anthropic":
        # Only auto-discover external credentials (Claude Code, Hermes PKCE)
        # when the user has explicitly configured anthropic as their provider.
@@ -1010,8 +1077,13 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
            ("claude_code", read_claude_code_credentials()),
        ):
            if creds and creds.get("accessToken"):
-                if _is_suppressed(provider, source_name):
-                    continue
+                # 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,
@@ -1029,16 +1101,8 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup

    elif provider == "nous":
        state = _load_provider_state(auth_store, "nous")
-        if state and not _is_suppressed(provider, "device_code"):
+        if state:
            active_sources.add("device_code")
-            # Prefer a user-supplied label embedded in the singleton state
-            # (set by persist_nous_credentials(label=...) when the user ran
-            # `hermes auth add nous --label <name>`).  Fall back to the
-            # auto-derived token fingerprint for logins that didn't supply one.
-            custom_label = str(state.get("label") or "").strip()
-            seeded_label = custom_label or label_from_token(
-                state.get("access_token", ""), "device_code"
-            )
            changed |= _upsert_entry(
                entries,
                provider,
@@ -1057,83 +1121,13 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                    "agent_key": state.get("agent_key"),
                    "agent_key_expires_at": state.get("agent_key_expires_at"),
                    "tls": state.get("tls") if isinstance(state.get("tls"), dict) else None,
-                    "label": seeded_label,
+                    "label": label_from_token(state.get("access_token", ""), "device_code"),
                },
            )

-    elif provider == "copilot":
-        # Copilot tokens are resolved dynamically via `gh auth token` or
-        # env vars (COPILOT_GITHUB_TOKEN / GH_TOKEN).  They don't live in
-        # the auth store or credential pool, so we resolve them here.
-        try:
-            from hermes_cli.copilot_auth import resolve_copilot_token
-            token, source = resolve_copilot_token()
-            if token:
-                source_name = "gh_cli" if "gh" in source.lower() else f"env:{source}"
-                if not _is_suppressed(provider, source_name):
-                    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")
-                if not _is_suppressed(provider, source_name):
-                    active_sources.add(source_name)
-                    changed |= _upsert_entry(
-                        entries,
-                        provider,
-                        source_name,
-                        {
-                            "source": source_name,
-                            "auth_type": AUTH_TYPE_OAUTH,
-                            "access_token": token,
-                            "expires_at_ms": creds.get("expires_at_ms"),
-                            "base_url": creds.get("base_url", ""),
-                            "label": creds.get("auth_file", source_name),
-                        },
-                    )
-        except Exception as exc:
-            logger.debug("Qwen OAuth token seed failed: %s", exc)
-
    elif provider == "openai-codex":
-        # Respect user suppression — `hermes auth remove openai-codex` marks
-        # the device_code source as suppressed so it won't be re-seeded from
-        # the Hermes auth store.  Without this gate the removal is instantly
-        # undone on the next load_pool() call.
-        if _is_suppressed(provider, "device_code"):
-            return changed, active_sources
-
        state = _load_provider_state(auth_store, "openai-codex")
        tokens = state.get("tokens") if isinstance(state, dict) else None
-        # Hermes owns its own Codex auth state — we do NOT auto-import from
-        # ~/.codex/auth.json at pool-load time.  OAuth refresh tokens are
-        # single-use, so sharing them with Codex CLI / VS Code causes
-        # refresh_token_reused race failures.  Users who want to adopt
-        # existing Codex CLI credentials get a one-time, explicit prompt
-        # via `hermes auth openai-codex`.
        if isinstance(tokens, dict) and tokens.get("access_token"):
            active_sources.add("device_code")
            changed |= _upsert_entry(
@@ -1157,22 +1151,10 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
 def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool, Set[str]]:
    changed = False
    active_sources: Set[str] = set()
-    # Honour user suppression — `hermes auth remove <provider> <N>` for an
-    # env-seeded credential marks the env:<VAR> source as suppressed so it
-    # won't be re-seeded from the user's shell environment or ~/.hermes/.env.
-    # Without this gate the removal is silently undone on the next
-    # load_pool() call whenever the var is still exported by the shell.
-    try:
-        from hermes_cli.auth import is_source_suppressed as _is_source_suppressed
-    except ImportError:
-        def _is_source_suppressed(_p, _s):  # type: ignore[misc]
-            return False
    if provider == "openrouter":
        token = os.getenv("OPENROUTER_API_KEY", "").strip()
        if token:
            source = "env:OPENROUTER_API_KEY"
-            if _is_source_suppressed(provider, source):
-                return changed, active_sources
            active_sources.add(source)
            changed |= _upsert_entry(
                entries,
@@ -1209,8 +1191,6 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
        if not token:
            continue
        source = f"env:{env_var}"
-        if _is_source_suppressed(provider, source):
-            continue
        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
@@ -1255,13 +1235,6 @@ def _seed_custom_pool(pool_key: str, entries: List[PooledCredential]) -> Tuple[b
    changed = False
    active_sources: Set[str] = set()

-    # Shared suppression gate — same pattern as _seed_from_env/_seed_from_singletons.
-    try:
-        from hermes_cli.auth import is_source_suppressed as _is_suppressed
-    except ImportError:
-        def _is_suppressed(_p, _s):  # type: ignore[misc]
-            return False
-
    # Seed from the custom_providers config entry's api_key field
    cp_config = _get_custom_provider_config(pool_key)
    if cp_config:
@@ -1270,20 +1243,19 @@ def _seed_custom_pool(pool_key: str, entries: List[PooledCredential]) -> Tuple[b
        name = str(cp_config.get("name") or "").strip()
        if api_key:
            source = f"config:{name}"
-            if not _is_suppressed(pool_key, source):
-                active_sources.add(source)
-                changed |= _upsert_entry(
-                    entries,
-                    pool_key,
-                    source,
-                    {
-                        "source": source,
-                        "auth_type": AUTH_TYPE_API_KEY,
-                        "access_token": api_key,
-                        "base_url": base_url,
-                        "label": name or source,
-                    },
-                )
+            active_sources.add(source)
+            changed |= _upsert_entry(
+                entries,
+                pool_key,
+                source,
+                {
+                    "source": source,
+                    "auth_type": AUTH_TYPE_API_KEY,
+                    "access_token": api_key,
+                    "base_url": base_url,
+                    "label": name or source,
+                },
+            )

    # Seed from model.api_key if model.provider=='custom' and model.base_url matches
    try:
@@ -1303,20 +1275,19 @@ def _seed_custom_pool(pool_key: str, entries: List[PooledCredential]) -> Tuple[b
                matched_key = get_custom_provider_pool_key(model_base_url)
                if matched_key == pool_key:
                    source = "model_config"
-                    if not _is_suppressed(pool_key, source):
-                        active_sources.add(source)
-                        changed |= _upsert_entry(
-                            entries,
-                            pool_key,
-                            source,
-                            {
-                                "source": source,
-                                "auth_type": AUTH_TYPE_API_KEY,
-                                "access_token": model_api_key,
-                                "base_url": model_base_url,
-                                "label": "model_config",
-                            },
-                        )
+                    active_sources.add(source)
+                    changed |= _upsert_entry(
+                        entries,
+                        pool_key,
+                        source,
+                        {
+                            "source": source,
+                            "auth_type": AUTH_TYPE_API_KEY,
+                            "access_token": model_api_key,
+                            "base_url": model_base_url,
+                            "label": "model_config",
+                        },
+                    )
    except Exception:
        pass

--- a/agent/credential_sources.py
+++ b/agent/credential_sources.py
@@ -1,401 +0,0 @@
-"""Unified removal contract for every credential source Hermes reads from.
-
-Hermes seeds its credential pool from many places:
-
-    env:<VAR>     — os.environ / ~/.hermes/.env
-    claude_code   — ~/.claude/.credentials.json
-    hermes_pkce   — ~/.hermes/.anthropic_oauth.json
-    device_code   — auth.json providers.<provider> (nous, openai-codex, ...)
-    qwen-cli      — ~/.qwen/oauth_creds.json
-    gh_cli        — gh auth token
-    config:<name> — custom_providers config entry
-    model_config  — model.api_key when model.provider == "custom"
-    manual        — user ran `hermes auth add`
-
-Each source has its own reader inside ``agent.credential_pool._seed_from_*``
-(which keep their existing shape — we haven't restructured them).  What we
-unify here is **removal**:
-
-    ``hermes auth remove <provider> <N>`` must make the pool entry stay gone.
-
-Before this module, every source had an ad-hoc removal branch in
-``auth_remove_command``, and several sources had no branch at all — so
-``auth remove`` silently reverted on the next ``load_pool()`` call for
-qwen-cli, nous device_code (partial), hermes_pkce, copilot gh_cli, and
-custom-config sources.
-
-Now every source registers a ``RemovalStep`` that does exactly three things
-in the same shape:
-
-    1. Clean up whatever externally-readable state the source reads from
-       (.env line, auth.json block, OAuth file, etc.)
-    2. Suppress the ``(provider, source_id)`` in auth.json so the
-       corresponding ``_seed_from_*`` branch skips the upsert on re-load
-    3. Return ``RemovalResult`` describing what was cleaned and any
-       diagnostic hints the user should see (shell-exported env vars,
-       external credential files we deliberately don't delete, etc.)
-
-Adding a new credential source is:
-    - wire up a reader branch in ``_seed_from_*`` (existing pattern)
-    - gate that reader behind ``is_source_suppressed(provider, source_id)``
-    - register a ``RemovalStep`` here
-
-No more per-source if/elif chain in ``auth_remove_command``.
-"""
-
-from __future__ import annotations
-
-import os
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import Callable, List, Optional
-
-
-@dataclass
-class RemovalResult:
-    """Outcome of removing a credential source.
-
-    Attributes:
-        cleaned: Short strings describing external state that was actually
-            mutated (``"Cleared XAI_API_KEY from .env"``,
-            ``"Cleared openai-codex OAuth tokens from auth store"``).
-            Printed as plain lines to the user.
-        hints: Diagnostic lines ABOUT state the user may need to clean up
-            themselves or is deliberately left intact (shell-exported env
-            var, Claude Code credential file we don't delete, etc.).
-            Printed as plain lines to the user.  Always non-destructive.
-        suppress: Whether to call ``suppress_credential_source`` after
-            cleanup so future ``load_pool`` calls skip this source.
-            Default True — almost every source needs this to stay sticky.
-            The only legitimate False is ``manual`` entries, which aren't
-            seeded from anywhere external.
-    """
-
-    cleaned: List[str] = field(default_factory=list)
-    hints: List[str] = field(default_factory=list)
-    suppress: bool = True
-
-
-@dataclass
-class RemovalStep:
-    """How to remove one specific credential source cleanly.
-
-    Attributes:
-        provider: Provider pool key (``"xai"``, ``"anthropic"``, ``"nous"``, ...).
-            Special value ``"*"`` means "matches any provider" — used for
-            sources like ``manual`` that aren't provider-specific.
-        source_id: Source identifier as it appears in
-            ``PooledCredential.source``.  May be a literal (``"claude_code"``)
-            or a prefix pattern matched via ``match_fn``.
-        match_fn: Optional predicate overriding literal ``source_id``
-            matching.  Gets the removed entry's source string.  Used for
-            ``env:*`` (any env-seeded key), ``config:*`` (any custom
-            pool), and ``manual:*`` (any manual-source variant).
-        remove_fn: ``(provider, removed_entry) -> RemovalResult``.  Does the
-            actual cleanup and returns what happened for the user.
-        description: One-line human-readable description for docs / tests.
-    """
-
-    provider: str
-    source_id: str
-    remove_fn: Callable[..., RemovalResult]
-    match_fn: Optional[Callable[[str], bool]] = None
-    description: str = ""
-
-    def matches(self, provider: str, source: str) -> bool:
-        if self.provider != "*" and self.provider != provider:
-            return False
-        if self.match_fn is not None:
-            return self.match_fn(source)
-        return source == self.source_id
-
-
-_REGISTRY: List[RemovalStep] = []
-
-
-def register(step: RemovalStep) -> RemovalStep:
-    _REGISTRY.append(step)
-    return step
-
-
-def find_removal_step(provider: str, source: str) -> Optional[RemovalStep]:
-    """Return the first matching RemovalStep, or None if unregistered.
-
-    Unregistered sources fall through to the default remove path in
-    ``auth_remove_command``: the pool entry is already gone (that happens
-    before dispatch), no external cleanup, no suppression.  This is the
-    correct behaviour for ``manual`` entries — they were only ever stored
-    in the pool, nothing external to clean up.
-    """
-    for step in _REGISTRY:
-        if step.matches(provider, source):
-            return step
-    return None
-
-
-# ---------------------------------------------------------------------------
-# Individual RemovalStep implementations — one per source.
-# ---------------------------------------------------------------------------
-# Each remove_fn is intentionally small and single-purpose.  Adding a new
-# credential source means adding ONE entry here — no other changes to
-# auth_remove_command.
-
-
-def _remove_env_source(provider: str, removed) -> RemovalResult:
-    """env:<VAR> — the most common case.
-
-    Handles three user situations:
-      1. Var lives only in ~/.hermes/.env  → clear it
-      2. Var lives only in the user's shell (shell profile, systemd
-         EnvironmentFile, launchd plist) → hint them where to unset it
-      3. Var lives in both → clear from .env, hint about shell
-    """
-    from hermes_cli.config import get_env_path, remove_env_value
-
-    result = RemovalResult()
-    env_var = removed.source[len("env:"):]
-    if not env_var:
-        return result
-
-    # Detect shell vs .env BEFORE remove_env_value pops os.environ.
-    env_in_process = bool(os.getenv(env_var))
-    env_in_dotenv = False
-    try:
-        env_path = get_env_path()
-        if env_path.exists():
-            env_in_dotenv = any(
-                line.strip().startswith(f"{env_var}=")
-                for line in env_path.read_text(errors="replace").splitlines()
-            )
-    except OSError:
-        pass
-    shell_exported = env_in_process and not env_in_dotenv
-
-    cleared = remove_env_value(env_var)
-    if cleared:
-        result.cleaned.append(f"Cleared {env_var} from .env")
-
-    if shell_exported:
-        result.hints.extend([
-            f"Note: {env_var} is still set in your shell environment "
-            f"(not in ~/.hermes/.env).",
-            "  Unset it there (shell profile, systemd EnvironmentFile, "
-            "launchd plist, etc.) or it will keep being visible to Hermes.",
-            f"  The pool entry is now suppressed — Hermes will ignore "
-            f"{env_var} until you run `hermes auth add {provider}`.",
-        ])
-    else:
-        result.hints.append(
-            f"Suppressed env:{env_var} — it will not be re-seeded even "
-            f"if the variable is re-exported later."
-        )
-    return result
-
-
-def _remove_claude_code(provider: str, removed) -> RemovalResult:
-    """~/.claude/.credentials.json is owned by Claude Code itself.
-
-    We don't delete it — the user's Claude Code install still needs to
-    work.  We just suppress it so Hermes stops reading it.
-    """
-    return RemovalResult(hints=[
-        "Suppressed claude_code credential — it will not be re-seeded.",
-        "Note: Claude Code credentials still live in ~/.claude/.credentials.json",
-        "Run `hermes auth add anthropic` to re-enable if needed.",
-    ])
-
-
-def _remove_hermes_pkce(provider: str, removed) -> RemovalResult:
-    """~/.hermes/.anthropic_oauth.json is ours — delete it outright."""
-    from hermes_constants import get_hermes_home
-
-    result = RemovalResult()
-    oauth_file = get_hermes_home() / ".anthropic_oauth.json"
-    if oauth_file.exists():
-        try:
-            oauth_file.unlink()
-            result.cleaned.append("Cleared Hermes Anthropic OAuth credentials")
-        except OSError as exc:
-            result.hints.append(f"Could not delete {oauth_file}: {exc}")
-    return result
-
-
-def _clear_auth_store_provider(provider: str) -> bool:
-    """Delete auth_store.providers[provider].  Returns True if deleted."""
-    from hermes_cli.auth import (
-        _auth_store_lock,
-        _load_auth_store,
-        _save_auth_store,
-    )
-
-    with _auth_store_lock():
-        auth_store = _load_auth_store()
-        providers_dict = auth_store.get("providers")
-        if isinstance(providers_dict, dict) and provider in providers_dict:
-            del providers_dict[provider]
-            _save_auth_store(auth_store)
-            return True
-    return False
-
-
-def _remove_nous_device_code(provider: str, removed) -> RemovalResult:
-    """Nous OAuth lives in auth.json providers.nous — clear it and suppress.
-
-    We suppress in addition to clearing because nothing else stops the
-    user's next `hermes login` run from writing providers.nous again
-    before they decide to.  Suppression forces them to go through
-    `hermes auth add nous` to re-engage, which is the documented re-add
-    path and clears the suppression atomically.
-    """
-    result = RemovalResult()
-    if _clear_auth_store_provider(provider):
-        result.cleaned.append(f"Cleared {provider} OAuth tokens from auth store")
-    return result
-
-
-def _remove_codex_device_code(provider: str, removed) -> RemovalResult:
-    """Codex tokens live in TWO places: our auth store AND ~/.codex/auth.json.
-
-    refresh_codex_oauth_pure() writes both every time, so clearing only
-    the Hermes auth store is not enough — _seed_from_singletons() would
-    re-import from ~/.codex/auth.json on the next load_pool() call and
-    the removal would be instantly undone.  We suppress instead of
-    deleting Codex CLI's file, so the Codex CLI itself keeps working.
-
-    The canonical source name in ``_seed_from_singletons`` is
-    ``"device_code"`` (no prefix).  Entries may show up in the pool as
-    either ``"device_code"`` (seeded) or ``"manual:device_code"`` (added
-    via ``hermes auth add openai-codex``), but in both cases the re-seed
-    gate lives at the ``"device_code"`` suppression key.  We suppress
-    that canonical key here; the central dispatcher also suppresses
-    ``removed.source`` which is fine — belt-and-suspenders, idempotent.
-    """
-    from hermes_cli.auth import suppress_credential_source
-
-    result = RemovalResult()
-    if _clear_auth_store_provider(provider):
-        result.cleaned.append(f"Cleared {provider} OAuth tokens from auth store")
-    # Suppress the canonical re-seed source, not just whatever source the
-    # removed entry had.  Otherwise `manual:device_code` removals wouldn't
-    # block the `device_code` re-seed path.
-    suppress_credential_source(provider, "device_code")
-    result.hints.extend([
-        "Suppressed openai-codex device_code source — it will not be re-seeded.",
-        "Note: Codex CLI credentials still live in ~/.codex/auth.json",
-        "Run `hermes auth add openai-codex` to re-enable if needed.",
-    ])
-    return result
-
-
-def _remove_qwen_cli(provider: str, removed) -> RemovalResult:
-    """~/.qwen/oauth_creds.json is owned by the Qwen CLI.
-
-    Same pattern as claude_code — suppress, don't delete.  The user's
-    Qwen CLI install still reads from that file.
-    """
-    return RemovalResult(hints=[
-        "Suppressed qwen-cli credential — it will not be re-seeded.",
-        "Note: Qwen CLI credentials still live in ~/.qwen/oauth_creds.json",
-        "Run `hermes auth add qwen-oauth` to re-enable if needed.",
-    ])
-
-
-def _remove_copilot_gh(provider: str, removed) -> RemovalResult:
-    """Copilot token comes from `gh auth token` or COPILOT_GITHUB_TOKEN / GH_TOKEN / GITHUB_TOKEN.
-
-    Copilot is special: the same token can be seeded as multiple source
-    entries (gh_cli from ``_seed_from_singletons`` plus env:<VAR> from
-    ``_seed_from_env``), so removing one entry without suppressing the
-    others lets the duplicates resurrect.  We suppress ALL known copilot
-    sources here so removal is stable regardless of which entry the
-    user clicked.
-
-    We don't touch the user's gh CLI or shell state — just suppress so
-    Hermes stops picking the token up.
-    """
-    # Suppress ALL copilot source variants up-front so no path resurrects
-    # the pool entry.  The central dispatcher in auth_remove_command will
-    # ALSO suppress removed.source, but it's idempotent so double-calling
-    # is harmless.
-    from hermes_cli.auth import suppress_credential_source
-    suppress_credential_source(provider, "gh_cli")
-    for env_var in ("COPILOT_GITHUB_TOKEN", "GH_TOKEN", "GITHUB_TOKEN"):
-        suppress_credential_source(provider, f"env:{env_var}")
-
-    return RemovalResult(hints=[
-        "Suppressed all copilot token sources (gh_cli + env vars) — they will not be re-seeded.",
-        "Note: Your gh CLI / shell environment is unchanged.",
-        "Run `hermes auth add copilot` to re-enable if needed.",
-    ])
-
-
-def _remove_custom_config(provider: str, removed) -> RemovalResult:
-    """Custom provider pools are seeded from custom_providers config or
-    model.api_key.  Both are in config.yaml — modifying that from here
-    is more invasive than suppression.  We suppress; the user can edit
-    config.yaml if they want to remove the key from disk entirely.
-    """
-    source_label = removed.source
-    return RemovalResult(hints=[
-        f"Suppressed {source_label} — it will not be re-seeded.",
-        "Note: The underlying value in config.yaml is unchanged.  Edit it "
-        "directly if you want to remove the credential from disk.",
-    ])
-
-
-def _register_all_sources() -> None:
-    """Called once on module import.
-
-    ORDER MATTERS — ``find_removal_step`` returns the first match.  Put
-    provider-specific steps before the generic ``env:*`` step so that e.g.
-    copilot's ``env:GH_TOKEN`` goes through the copilot removal (which
-    doesn't touch the user's shell), not the generic env-var removal
-    (which would try to clear .env).
-    """
-    register(RemovalStep(
-        provider="copilot", source_id="gh_cli",
-        match_fn=lambda src: src == "gh_cli" or src.startswith("env:"),
-        remove_fn=_remove_copilot_gh,
-        description="gh auth token / COPILOT_GITHUB_TOKEN / GH_TOKEN",
-    ))
-    register(RemovalStep(
-        provider="*", source_id="env:",
-        match_fn=lambda src: src.startswith("env:"),
-        remove_fn=_remove_env_source,
-        description="Any env-seeded credential (XAI_API_KEY, DEEPSEEK_API_KEY, etc.)",
-    ))
-    register(RemovalStep(
-        provider="anthropic", source_id="claude_code",
-        remove_fn=_remove_claude_code,
-        description="~/.claude/.credentials.json",
-    ))
-    register(RemovalStep(
-        provider="anthropic", source_id="hermes_pkce",
-        remove_fn=_remove_hermes_pkce,
-        description="~/.hermes/.anthropic_oauth.json",
-    ))
-    register(RemovalStep(
-        provider="nous", source_id="device_code",
-        remove_fn=_remove_nous_device_code,
-        description="auth.json providers.nous",
-    ))
-    register(RemovalStep(
-        provider="openai-codex", source_id="device_code",
-        match_fn=lambda src: src == "device_code" or src.endswith(":device_code"),
-        remove_fn=_remove_codex_device_code,
-        description="auth.json providers.openai-codex + ~/.codex/auth.json",
-    ))
-    register(RemovalStep(
-        provider="qwen-oauth", source_id="qwen-cli",
-        remove_fn=_remove_qwen_cli,
-        description="~/.qwen/oauth_creds.json",
-    ))
-    register(RemovalStep(
-        provider="*", source_id="config:",
-        match_fn=lambda src: src.startswith("config:") or src == "model_config",
-        remove_fn=_remove_custom_config,
-        description="Custom provider config.yaml api_key field",
-    ))
-
-
-_register_all_sources()
--- a/agent/display.py
+++ b/agent/display.py
@@ -77,6 +77,12 @@ def _diff_ansi() -> dict[str, str]:
    return _diff_colors_cached


+def reset_diff_colors() -> None:
+    """Reset cached diff colors (call after /skin switch)."""
+    global _diff_colors_cached
+    _diff_colors_cached = None
+
+
 # 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"]
@@ -225,11 +231,9 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -
            content = _oneline(args.get("content", ""))
            return f"+{target}: \"{content[:25]}{'...' if len(content) > 25 else ''}\""
        elif action == "replace":
-            old = _oneline(args.get("old_text") or "") or "<missing old_text>"
-            return f"~{target}: \"{old[:20]}\""
+            return f"~{target}: \"{_oneline(args.get('old_text', '')[:20])}\""
        elif action == "remove":
-            old = _oneline(args.get("old_text") or "") or "<missing old_text>"
-            return f"-{target}: \"{old[:20]}\""
+            return f"-{target}: \"{_oneline(args.get('old_text', '')[:20])}\""
        return action

    if tool_name == "send_message":
@@ -602,45 +606,6 @@ 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'])
@@ -941,13 +906,9 @@ def get_cute_tool_message(
        if action == "add":
            return _wrap(f"┊ 🧠 memory    +{target}: \"{_trunc(args.get('content', ''), 30)}\"  {dur}")
        elif action == "replace":
-            old = args.get("old_text") or ""
-            old = old if old else "<missing old_text>"
-            return _wrap(f"┊ 🧠 memory    ~{target}: \"{_trunc(old, 20)}\"  {dur}")
+            return _wrap(f"┊ 🧠 memory    ~{target}: \"{_trunc(args.get('old_text', ''), 20)}\"  {dur}")
        elif action == "remove":
-            old = args.get("old_text") or ""
-            old = old if old else "<missing old_text>"
-            return _wrap(f"┊ 🧠 memory    -{target}: \"{_trunc(old, 20)}\"  {dur}")
+            return _wrap(f"┊ 🧠 memory    -{target}: \"{_trunc(args.get('old_text', ''), 20)}\"  {dur}")
        return _wrap(f"┊ 🧠 memory    {action}  {dur}")
    if tool_name == "skills_list":
        return _wrap(f"┊ 📚 skills    list {args.get('category', 'all')}  {dur}")
@@ -999,4 +960,84 @@ def get_cute_tool_message(
 # Honcho session line (one-liner with clickable OSC 8 hyperlink)
 # =========================================================================

+_DIM = "\033[2m"
+_SKY_BLUE = "\033[38;5;117m"
+_ANSI_RESET = "\033[0m"

+
+# =========================================================================
+# Context pressure display (CLI user-facing warnings)
+# =========================================================================
+
+# ANSI color codes for context pressure tiers
+_CYAN = "\033[36m"
+_YELLOW = "\033[33m"
+_BOLD = "\033[1m"
+_DIM_ANSI = "\033[2m"
+
+# Bar characters
+_BAR_FILLED = "▰"
+_BAR_EMPTY = "▱"
+_BAR_WIDTH = 20
+
+
+def format_context_pressure(
+    compaction_progress: float,
+    threshold_tokens: int,
+    threshold_percent: float,
+    compression_enabled: bool = True,
+) -> str:
+    """Build a formatted context pressure line for CLI display.
+
+    The bar and percentage show progress toward the compaction threshold,
+    NOT the raw context window.  100% = compaction fires.
+
+    Args:
+        compaction_progress: How close to compaction (0.0–1.0, 1.0 = fires).
+        threshold_tokens: Compaction threshold in tokens.
+        threshold_percent: Compaction threshold as a fraction of context window.
+        compression_enabled: Whether auto-compression is active.
+    """
+    pct_int = min(int(compaction_progress * 100), 100)
+    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
+    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)
+
+    threshold_k = f"{threshold_tokens // 1000}k" if threshold_tokens >= 1000 else str(threshold_tokens)
+    threshold_pct_int = int(threshold_percent * 100)
+
+    color = f"{_BOLD}{_YELLOW}"
+    icon = "⚠"
+    if compression_enabled:
+        hint = "compaction approaching"
+    else:
+        hint = "no auto-compaction"
+
+    return (
+        f"  {color}{icon} context {bar} {pct_int}% to compaction{_ANSI_RESET}"
+        f"  {_DIM_ANSI}{threshold_k} threshold ({threshold_pct_int}%) · {hint}{_ANSI_RESET}"
+    )
+
+
+def format_context_pressure_gateway(
+    compaction_progress: float,
+    threshold_percent: float,
+    compression_enabled: bool = True,
+) -> str:
+    """Build a plain-text context pressure notification for messaging platforms.
+
+    No ANSI — just Unicode and plain text suitable for Telegram/Discord/etc.
+    The percentage shows progress toward the compaction threshold.
+    """
+    pct_int = min(int(compaction_progress * 100), 100)
+    filled = min(int(compaction_progress * _BAR_WIDTH), _BAR_WIDTH)
+    bar = _BAR_FILLED * filled + _BAR_EMPTY * (_BAR_WIDTH - filled)
+
+    threshold_pct_int = int(threshold_percent * 100)
+
+    icon = "⚠️"
+    if compression_enabled:
+        hint = f"Context compaction approaching (threshold: {threshold_pct_int}% of window)."
+    else:
+        hint = "Auto-compaction is disabled — context may be truncated."
+
+    return f"{icon} Context: {bar} {pct_int}% to compaction\n{hint}"
--- a/agent/error_classifier.py
+++ b/agent/error_classifier.py
@@ -13,6 +13,7 @@ from __future__ import annotations

 import enum
 import logging
+import re
 from dataclasses import dataclass, field
 from typing import Any, Dict, Optional

@@ -112,10 +113,6 @@ _RATE_LIMIT_PATTERNS = [
    "please retry after",
    "resource_exhausted",
    "rate increased too quickly",  # Alibaba/DashScope throttling
-    # AWS Bedrock throttling
-    "throttlingexception",
-    "too many concurrent requests",
-    "servicequotaexceededexception",
 ]

 # Usage-limit patterns that need disambiguation (could be billing OR rate_limit)
@@ -160,26 +157,9 @@ _CONTEXT_OVERFLOW_PATTERNS = [
    "prompt exceeds max length",
    "max_tokens",
    "maximum number of tokens",
-    # vLLM / local inference server patterns
-    "exceeds the max_model_len",
-    "max_model_len",
-    "prompt length",             # "engine prompt length X exceeds"
-    "input is too long",
-    "maximum model length",
-    # Ollama patterns
-    "context length exceeded",
-    "truncating input",
-    # llama.cpp / llama-server patterns
-    "slot context",              # "slot context: N tokens, prompt N tokens"
-    "n_ctx_slot",
    # Chinese error messages (some providers return these)
    "超过最大长度",
    "上下文长度",
-    # AWS Bedrock Converse API error patterns
-    "input is too long",
-    "max input token",
-    "input token",
-    "exceeds the maximum number of input tokens",
 ]

 # Model not found patterns
@@ -290,7 +270,7 @@ def classify_api_error(
    if isinstance(body, dict):
        _err_obj = body.get("error", {})
        if isinstance(_err_obj, dict):
-            _body_msg = str(_err_obj.get("message") or "").lower()
+            _body_msg = (_err_obj.get("message") or "").lower()
            # Parse metadata.raw for wrapped provider errors
            _metadata = _err_obj.get("metadata", {})
            if isinstance(_metadata, dict):
@@ -302,11 +282,11 @@ def classify_api_error(
                        if isinstance(_inner, dict):
                            _inner_err = _inner.get("error", {})
                            if isinstance(_inner_err, dict):
-                                _metadata_msg = str(_inner_err.get("message") or "").lower()
+                                _metadata_msg = (_inner_err.get("message") or "").lower()
                    except (json.JSONDecodeError, TypeError):
                        pass
        if not _body_msg:
-            _body_msg = str(body.get("message") or "").lower()
+            _body_msg = (body.get("message") or "").lower()
    # Combine all message sources for pattern matching
    parts = [_raw_msg]
    if _body_msg and _body_msg not in _raw_msg:
@@ -606,10 +586,10 @@ def _classify_400(
    if isinstance(body, dict):
        err_obj = body.get("error", {})
        if isinstance(err_obj, dict):
-            err_body_msg = str(err_obj.get("message") or "").strip().lower()
+            err_body_msg = (err_obj.get("message") or "").strip().lower()
        # Responses API (and some providers) use flat body: {"message": "..."}
        if not err_body_msg:
-            err_body_msg = str(body.get("message") or "").strip().lower()
+            err_body_msg = (body.get("message") or "").strip().lower()
    is_generic = len(err_body_msg) < 30 or err_body_msg in ("error", "")
    is_large = approx_tokens > context_length * 0.4 or approx_tokens > 80000 or num_messages > 80

--- a/agent/file_safety.py
+++ b/agent/file_safety.py
@@ -1,111 +0,0 @@
-"""Shared file safety rules used by both tools and ACP shims."""
-
-from __future__ import annotations
-
-import os
-from pathlib import Path
-from typing import Optional
-
-
-def _hermes_home_path() -> Path:
-    """Resolve the active HERMES_HOME (profile-aware) without circular imports."""
-    try:
-        from hermes_constants import get_hermes_home  # local import to avoid cycles
-        return get_hermes_home()
-    except Exception:
-        return Path(os.path.expanduser("~/.hermes"))
-
-
-def build_write_denied_paths(home: str) -> set[str]:
-    """Return exact sensitive paths that must never be written."""
-    hermes_home = _hermes_home_path()
-    return {
-        os.path.realpath(p)
-        for p in [
-            os.path.join(home, ".ssh", "authorized_keys"),
-            os.path.join(home, ".ssh", "id_rsa"),
-            os.path.join(home, ".ssh", "id_ed25519"),
-            os.path.join(home, ".ssh", "config"),
-            str(hermes_home / ".env"),
-            os.path.join(home, ".bashrc"),
-            os.path.join(home, ".zshrc"),
-            os.path.join(home, ".profile"),
-            os.path.join(home, ".bash_profile"),
-            os.path.join(home, ".zprofile"),
-            os.path.join(home, ".netrc"),
-            os.path.join(home, ".pgpass"),
-            os.path.join(home, ".npmrc"),
-            os.path.join(home, ".pypirc"),
-            "/etc/sudoers",
-            "/etc/passwd",
-            "/etc/shadow",
-        ]
-    }
-
-
-def build_write_denied_prefixes(home: str) -> list[str]:
-    """Return sensitive directory prefixes that must never be written."""
-    return [
-        os.path.realpath(p) + os.sep
-        for p in [
-            os.path.join(home, ".ssh"),
-            os.path.join(home, ".aws"),
-            os.path.join(home, ".gnupg"),
-            os.path.join(home, ".kube"),
-            "/etc/sudoers.d",
-            "/etc/systemd",
-            os.path.join(home, ".docker"),
-            os.path.join(home, ".azure"),
-            os.path.join(home, ".config", "gh"),
-        ]
-    ]
-
-
-def get_safe_write_root() -> Optional[str]:
-    """Return the resolved HERMES_WRITE_SAFE_ROOT path, or None if unset."""
-    root = os.getenv("HERMES_WRITE_SAFE_ROOT", "")
-    if not root:
-        return None
-    try:
-        return os.path.realpath(os.path.expanduser(root))
-    except Exception:
-        return None
-
-
-def is_write_denied(path: str) -> bool:
-    """Return True if path is blocked by the write denylist or safe root."""
-    home = os.path.realpath(os.path.expanduser("~"))
-    resolved = os.path.realpath(os.path.expanduser(str(path)))
-
-    if resolved in build_write_denied_paths(home):
-        return True
-    for prefix in build_write_denied_prefixes(home):
-        if resolved.startswith(prefix):
-            return True
-
-    safe_root = get_safe_write_root()
-    if safe_root and not (resolved == safe_root or resolved.startswith(safe_root + os.sep)):
-        return True
-
-    return False
-
-
-def get_read_block_error(path: str) -> Optional[str]:
-    """Return an error message when a read targets internal Hermes cache files."""
-    resolved = Path(path).expanduser().resolve()
-    hermes_home = _hermes_home_path().resolve()
-    blocked_dirs = [
-        hermes_home / "skills" / ".hub" / "index-cache",
-        hermes_home / "skills" / ".hub",
-    ]
-    for blocked in blocked_dirs:
-        try:
-            resolved.relative_to(blocked)
-        except ValueError:
-            continue
-        return (
-            f"Access denied: {path} is an internal Hermes cache file "
-            "and cannot be read directly to prevent prompt injection. "
-            "Use the skills_list or skill_view tools instead."
-        )
-    return None
--- a/agent/gemini_cloudcode_adapter.py
+++ b/agent/gemini_cloudcode_adapter.py
@@ -1,905 +0,0 @@
-"""OpenAI-compatible facade that talks to Google's Cloud Code Assist backend.
-
-This adapter lets Hermes use the ``google-gemini-cli`` provider as if it were
-a standard OpenAI-shaped chat completion endpoint, while the underlying HTTP
-traffic goes to ``cloudcode-pa.googleapis.com/v1internal:{generateContent,
-streamGenerateContent}`` with a Bearer access token obtained via OAuth PKCE.
-
-Architecture
------------
- ``GeminiCloudCodeClient`` exposes ``.chat.completions.create(**kwargs)``
-  mirroring the subset of the OpenAI SDK that ``run_agent.py`` uses.
- Incoming OpenAI ``messages[]`` / ``tools[]`` / ``tool_choice`` are translated
-  to Gemini's native ``contents[]`` / ``tools[].functionDeclarations`` /
-  ``toolConfig`` / ``systemInstruction`` shape.
- The request body is wrapped ``{project, model, user_prompt_id, request}``
-  per Code Assist API expectations.
- Responses (``candidates[].content.parts[]``) are converted back to
-  OpenAI ``choices[0].message`` shape with ``content`` + ``tool_calls``.
- Streaming uses SSE (``?alt=sse``) and yields OpenAI-shaped delta chunks.
-
-Attribution
-----------
-Translation semantics follow jenslys/opencode-gemini-auth (MIT) and the public
-Gemini API docs. Request envelope shape
-(``{project, model, user_prompt_id, request}``) is documented nowhere; it is
-reverse-engineered from the opencode-gemini-auth and clawdbot implementations.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import time
-import uuid
-from types import SimpleNamespace
-from typing import Any, Dict, Iterator, List, Optional
-
-import httpx
-
-from agent import google_oauth
-from agent.gemini_schema import sanitize_gemini_tool_parameters
-from agent.google_code_assist import (
-    CODE_ASSIST_ENDPOINT,
-    FREE_TIER_ID,
-    CodeAssistError,
-    ProjectContext,
-    resolve_project_context,
-)
-
-logger = logging.getLogger(__name__)
-
-
-# =============================================================================
-# Request translation: OpenAI → Gemini
-# =============================================================================
-
-_ROLE_MAP_OPENAI_TO_GEMINI = {
-    "user": "user",
-    "assistant": "model",
-    "system": "user",   # handled separately via systemInstruction
-    "tool": "user",     # functionResponse is wrapped in a user-role turn
-    "function": "user",
-}
-
-
-def _coerce_content_to_text(content: Any) -> str:
-    """OpenAI content may be str or a list of parts; reduce to plain text."""
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        pieces: List[str] = []
-        for p in content:
-            if isinstance(p, str):
-                pieces.append(p)
-            elif isinstance(p, dict):
-                if p.get("type") == "text" and isinstance(p.get("text"), str):
-                    pieces.append(p["text"])
-                # Multimodal (image_url, etc.) — stub for now; log and skip
-                elif p.get("type") in ("image_url", "input_audio"):
-                    logger.debug("Dropping multimodal part (not yet supported): %s", p.get("type"))
-        return "\n".join(pieces)
-    return str(content)
-
-
-def _translate_tool_call_to_gemini(tool_call: Dict[str, Any]) -> Dict[str, Any]:
-    """OpenAI tool_call -> Gemini functionCall part."""
-    fn = tool_call.get("function") or {}
-    args_raw = fn.get("arguments", "")
-    try:
-        args = json.loads(args_raw) if isinstance(args_raw, str) and args_raw else {}
-    except json.JSONDecodeError:
-        args = {"_raw": args_raw}
-    if not isinstance(args, dict):
-        args = {"_value": args}
-    return {
-        "functionCall": {
-            "name": fn.get("name") or "",
-            "args": args,
-        },
-        # Sentinel signature — matches opencode-gemini-auth's approach.
-        # Without this, Code Assist rejects function calls that originated
-        # outside its own chain.
-        "thoughtSignature": "skip_thought_signature_validator",
-    }
-
-
-def _translate_tool_result_to_gemini(message: Dict[str, Any]) -> Dict[str, Any]:
-    """OpenAI tool-role message -> Gemini functionResponse part.
-
-    The function name isn't in the OpenAI tool message directly; it must be
-    passed via the assistant message that issued the call. For simplicity we
-    look up ``name`` on the message (OpenAI SDK copies it there) or on the
-    ``tool_call_id`` cross-reference.
-    """
-    name = str(message.get("name") or message.get("tool_call_id") or "tool")
-    content = _coerce_content_to_text(message.get("content"))
-    # Gemini expects the response as a dict under `response`. We wrap plain
-    # text in {"output": "..."}.
-    try:
-        parsed = json.loads(content) if content.strip().startswith(("{", "[")) else None
-    except json.JSONDecodeError:
-        parsed = None
-    response = parsed if isinstance(parsed, dict) else {"output": content}
-    return {
-        "functionResponse": {
-            "name": name,
-            "response": response,
-        },
-    }
-
-
-def _build_gemini_contents(
-    messages: List[Dict[str, Any]],
-) -> tuple[List[Dict[str, Any]], Optional[Dict[str, Any]]]:
-    """Convert OpenAI messages[] to Gemini contents[] + systemInstruction."""
-    system_text_parts: List[str] = []
-    contents: List[Dict[str, Any]] = []
-
-    for msg in messages:
-        if not isinstance(msg, dict):
-            continue
-        role = str(msg.get("role") or "user")
-
-        if role == "system":
-            system_text_parts.append(_coerce_content_to_text(msg.get("content")))
-            continue
-
-        # Tool result message — emit a user-role turn with functionResponse
-        if role == "tool" or role == "function":
-            contents.append({
-                "role": "user",
-                "parts": [_translate_tool_result_to_gemini(msg)],
-            })
-            continue
-
-        gemini_role = _ROLE_MAP_OPENAI_TO_GEMINI.get(role, "user")
-        parts: List[Dict[str, Any]] = []
-
-        text = _coerce_content_to_text(msg.get("content"))
-        if text:
-            parts.append({"text": text})
-
-        # Assistant messages can carry tool_calls
-        tool_calls = msg.get("tool_calls") or []
-        if isinstance(tool_calls, list):
-            for tc in tool_calls:
-                if isinstance(tc, dict):
-                    parts.append(_translate_tool_call_to_gemini(tc))
-
-        if not parts:
-            # Gemini rejects empty parts; skip the turn entirely
-            continue
-
-        contents.append({"role": gemini_role, "parts": parts})
-
-    system_instruction: Optional[Dict[str, Any]] = None
-    joined_system = "\n".join(p for p in system_text_parts if p).strip()
-    if joined_system:
-        system_instruction = {
-            "role": "system",
-            "parts": [{"text": joined_system}],
-        }
-
-    return contents, system_instruction
-
-
-def _translate_tools_to_gemini(tools: Any) -> List[Dict[str, Any]]:
-    """OpenAI tools[] -> Gemini tools[].functionDeclarations[]."""
-    if not isinstance(tools, list) or not tools:
-        return []
-    declarations: List[Dict[str, Any]] = []
-    for t in tools:
-        if not isinstance(t, dict):
-            continue
-        fn = t.get("function") or {}
-        if not isinstance(fn, dict):
-            continue
-        name = fn.get("name")
-        if not name:
-            continue
-        decl = {"name": str(name)}
-        if fn.get("description"):
-            decl["description"] = str(fn["description"])
-        params = fn.get("parameters")
-        if isinstance(params, dict):
-            decl["parameters"] = sanitize_gemini_tool_parameters(params)
-        declarations.append(decl)
-    if not declarations:
-        return []
-    return [{"functionDeclarations": declarations}]
-
-
-def _translate_tool_choice_to_gemini(tool_choice: Any) -> Optional[Dict[str, Any]]:
-    """OpenAI tool_choice -> Gemini toolConfig.functionCallingConfig."""
-    if tool_choice is None:
-        return None
-    if isinstance(tool_choice, str):
-        if tool_choice == "auto":
-            return {"functionCallingConfig": {"mode": "AUTO"}}
-        if tool_choice == "required":
-            return {"functionCallingConfig": {"mode": "ANY"}}
-        if tool_choice == "none":
-            return {"functionCallingConfig": {"mode": "NONE"}}
-    if isinstance(tool_choice, dict):
-        fn = tool_choice.get("function") or {}
-        name = fn.get("name")
-        if name:
-            return {
-                "functionCallingConfig": {
-                    "mode": "ANY",
-                    "allowedFunctionNames": [str(name)],
-                },
-            }
-    return None
-
-
-def _normalize_thinking_config(config: Any) -> Optional[Dict[str, Any]]:
-    """Accept thinkingBudget / thinkingLevel / includeThoughts (+ snake_case)."""
-    if not isinstance(config, dict) or not config:
-        return None
-    budget = config.get("thinkingBudget", config.get("thinking_budget"))
-    level = config.get("thinkingLevel", config.get("thinking_level"))
-    include = config.get("includeThoughts", config.get("include_thoughts"))
-    normalized: Dict[str, Any] = {}
-    if isinstance(budget, (int, float)):
-        normalized["thinkingBudget"] = int(budget)
-    if isinstance(level, str) and level.strip():
-        normalized["thinkingLevel"] = level.strip().lower()
-    if isinstance(include, bool):
-        normalized["includeThoughts"] = include
-    return normalized or None
-
-
-def build_gemini_request(
-    *,
-    messages: List[Dict[str, Any]],
-    tools: Any = None,
-    tool_choice: Any = None,
-    temperature: Optional[float] = None,
-    max_tokens: Optional[int] = None,
-    top_p: Optional[float] = None,
-    stop: Any = None,
-    thinking_config: Any = None,
-) -> Dict[str, Any]:
-    """Build the inner Gemini request body (goes inside ``request`` wrapper)."""
-    contents, system_instruction = _build_gemini_contents(messages)
-
-    body: Dict[str, Any] = {"contents": contents}
-    if system_instruction is not None:
-        body["systemInstruction"] = system_instruction
-
-    gemini_tools = _translate_tools_to_gemini(tools)
-    if gemini_tools:
-        body["tools"] = gemini_tools
-    tool_cfg = _translate_tool_choice_to_gemini(tool_choice)
-    if tool_cfg is not None:
-        body["toolConfig"] = tool_cfg
-
-    generation_config: Dict[str, Any] = {}
-    if isinstance(temperature, (int, float)):
-        generation_config["temperature"] = float(temperature)
-    if isinstance(max_tokens, int) and max_tokens > 0:
-        generation_config["maxOutputTokens"] = max_tokens
-    if isinstance(top_p, (int, float)):
-        generation_config["topP"] = float(top_p)
-    if isinstance(stop, str) and stop:
-        generation_config["stopSequences"] = [stop]
-    elif isinstance(stop, list) and stop:
-        generation_config["stopSequences"] = [str(s) for s in stop if s]
-    normalized_thinking = _normalize_thinking_config(thinking_config)
-    if normalized_thinking:
-        generation_config["thinkingConfig"] = normalized_thinking
-    if generation_config:
-        body["generationConfig"] = generation_config
-
-    return body
-
-
-def wrap_code_assist_request(
-    *,
-    project_id: str,
-    model: str,
-    inner_request: Dict[str, Any],
-    user_prompt_id: Optional[str] = None,
-) -> Dict[str, Any]:
-    """Wrap the inner Gemini request in the Code Assist envelope."""
-    return {
-        "project": project_id,
-        "model": model,
-        "user_prompt_id": user_prompt_id or str(uuid.uuid4()),
-        "request": inner_request,
-    }
-
-
-# =============================================================================
-# Response translation: Gemini → OpenAI
-# =============================================================================
-
-def _translate_gemini_response(
-    resp: Dict[str, Any],
-    model: str,
-) -> SimpleNamespace:
-    """Non-streaming Gemini response -> OpenAI-shaped SimpleNamespace.
-
-    Code Assist wraps the actual Gemini response inside ``response``, so we
-    unwrap it first if present.
-    """
-    inner = resp.get("response") if isinstance(resp.get("response"), dict) else resp
-
-    candidates = inner.get("candidates") or []
-    if not isinstance(candidates, list) or not candidates:
-        return _empty_response(model)
-
-    cand = candidates[0]
-    content_obj = cand.get("content") if isinstance(cand, dict) else {}
-    parts = content_obj.get("parts") if isinstance(content_obj, dict) else []
-
-    text_pieces: List[str] = []
-    reasoning_pieces: List[str] = []
-    tool_calls: List[SimpleNamespace] = []
-
-    for i, part in enumerate(parts or []):
-        if not isinstance(part, dict):
-            continue
-        # Thought parts are model's internal reasoning — surface as reasoning,
-        # don't mix into content.
-        if part.get("thought") is True:
-            if isinstance(part.get("text"), str):
-                reasoning_pieces.append(part["text"])
-            continue
-        if isinstance(part.get("text"), str):
-            text_pieces.append(part["text"])
-            continue
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            tool_calls.append(SimpleNamespace(
-                id=f"call_{uuid.uuid4().hex[:12]}",
-                type="function",
-                index=i,
-                function=SimpleNamespace(name=str(fc["name"]), arguments=args_str),
-            ))
-
-    finish_reason = "tool_calls" if tool_calls else _map_gemini_finish_reason(
-        str(cand.get("finishReason") or "")
-    )
-
-    usage_meta = inner.get("usageMetadata") or {}
-    usage = SimpleNamespace(
-        prompt_tokens=int(usage_meta.get("promptTokenCount") or 0),
-        completion_tokens=int(usage_meta.get("candidatesTokenCount") or 0),
-        total_tokens=int(usage_meta.get("totalTokenCount") or 0),
-        prompt_tokens_details=SimpleNamespace(
-            cached_tokens=int(usage_meta.get("cachedContentTokenCount") or 0),
-        ),
-    )
-
-    message = SimpleNamespace(
-        role="assistant",
-        content="".join(text_pieces) if text_pieces else None,
-        tool_calls=tool_calls or None,
-        reasoning="".join(reasoning_pieces) or None,
-        reasoning_content="".join(reasoning_pieces) or None,
-        reasoning_details=None,
-    )
-    choice = SimpleNamespace(
-        index=0,
-        message=message,
-        finish_reason=finish_reason,
-    )
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-def _empty_response(model: str) -> SimpleNamespace:
-    message = SimpleNamespace(
-        role="assistant", content="", tool_calls=None,
-        reasoning=None, reasoning_content=None, reasoning_details=None,
-    )
-    choice = SimpleNamespace(index=0, message=message, finish_reason="stop")
-    usage = SimpleNamespace(
-        prompt_tokens=0, completion_tokens=0, total_tokens=0,
-        prompt_tokens_details=SimpleNamespace(cached_tokens=0),
-    )
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-def _map_gemini_finish_reason(reason: str) -> str:
-    mapping = {
-        "STOP": "stop",
-        "MAX_TOKENS": "length",
-        "SAFETY": "content_filter",
-        "RECITATION": "content_filter",
-        "OTHER": "stop",
-    }
-    return mapping.get(reason.upper(), "stop")
-
-
-# =============================================================================
-# Streaming SSE iterator
-# =============================================================================
-
-class _GeminiStreamChunk(SimpleNamespace):
-    """Mimics an OpenAI ChatCompletionChunk with .choices[0].delta."""
-    pass
-
-
-def _make_stream_chunk(
-    *,
-    model: str,
-    content: str = "",
-    tool_call_delta: Optional[Dict[str, Any]] = None,
-    finish_reason: Optional[str] = None,
-    reasoning: str = "",
-) -> _GeminiStreamChunk:
-    delta_kwargs: Dict[str, Any] = {"role": "assistant"}
-    if content:
-        delta_kwargs["content"] = content
-    if tool_call_delta is not None:
-        delta_kwargs["tool_calls"] = [SimpleNamespace(
-            index=tool_call_delta.get("index", 0),
-            id=tool_call_delta.get("id") or f"call_{uuid.uuid4().hex[:12]}",
-            type="function",
-            function=SimpleNamespace(
-                name=tool_call_delta.get("name") or "",
-                arguments=tool_call_delta.get("arguments") or "",
-            ),
-        )]
-    if reasoning:
-        delta_kwargs["reasoning"] = reasoning
-        delta_kwargs["reasoning_content"] = reasoning
-    delta = SimpleNamespace(**delta_kwargs)
-    choice = SimpleNamespace(index=0, delta=delta, finish_reason=finish_reason)
-    return _GeminiStreamChunk(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion.chunk",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=None,
-    )
-
-
-def _iter_sse_events(response: httpx.Response) -> Iterator[Dict[str, Any]]:
-    """Parse Server-Sent Events from an httpx streaming response."""
-    buffer = ""
-    for chunk in response.iter_text():
-        if not chunk:
-            continue
-        buffer += chunk
-        while "\n" in buffer:
-            line, buffer = buffer.split("\n", 1)
-            line = line.rstrip("\r")
-            if not line:
-                continue
-            if line.startswith("data: "):
-                data = line[6:]
-                if data == "[DONE]":
-                    return
-                try:
-                    yield json.loads(data)
-                except json.JSONDecodeError:
-                    logger.debug("Non-JSON SSE line: %s", data[:200])
-
-
-def _translate_stream_event(
-    event: Dict[str, Any],
-    model: str,
-    tool_call_counter: List[int],
-) -> List[_GeminiStreamChunk]:
-    """Unwrap Code Assist envelope and emit OpenAI-shaped chunk(s).
-
-    ``tool_call_counter`` is a single-element list used as a mutable counter
-    across events in the same stream. Each ``functionCall`` part gets a
-    fresh, unique OpenAI ``index`` — keying by function name would collide
-    whenever the model issues parallel calls to the same tool (e.g. reading
-    three files in one turn).
-    """
-    inner = event.get("response") if isinstance(event.get("response"), dict) else event
-    candidates = inner.get("candidates") or []
-    if not candidates:
-        return []
-    cand = candidates[0]
-    if not isinstance(cand, dict):
-        return []
-
-    chunks: List[_GeminiStreamChunk] = []
-
-    content = cand.get("content") or {}
-    parts = content.get("parts") if isinstance(content, dict) else []
-    for part in parts or []:
-        if not isinstance(part, dict):
-            continue
-        if part.get("thought") is True and isinstance(part.get("text"), str):
-            chunks.append(_make_stream_chunk(
-                model=model, reasoning=part["text"],
-            ))
-            continue
-        if isinstance(part.get("text"), str) and part["text"]:
-            chunks.append(_make_stream_chunk(model=model, content=part["text"]))
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            name = str(fc["name"])
-            idx = tool_call_counter[0]
-            tool_call_counter[0] += 1
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            chunks.append(_make_stream_chunk(
-                model=model,
-                tool_call_delta={
-                    "index": idx,
-                    "name": name,
-                    "arguments": args_str,
-                },
-            ))
-
-    finish_reason_raw = str(cand.get("finishReason") or "")
-    if finish_reason_raw:
-        mapped = _map_gemini_finish_reason(finish_reason_raw)
-        if tool_call_counter[0] > 0:
-            mapped = "tool_calls"
-        chunks.append(_make_stream_chunk(model=model, finish_reason=mapped))
-    return chunks
-
-
-# =============================================================================
-# GeminiCloudCodeClient — OpenAI-compatible facade
-# =============================================================================
-
-MARKER_BASE_URL = "cloudcode-pa://google"
-
-
-class _GeminiChatCompletions:
-    def __init__(self, client: "GeminiCloudCodeClient"):
-        self._client = client
-
-    def create(self, **kwargs: Any) -> Any:
-        return self._client._create_chat_completion(**kwargs)
-
-
-class _GeminiChatNamespace:
-    def __init__(self, client: "GeminiCloudCodeClient"):
-        self.completions = _GeminiChatCompletions(client)
-
-
-class GeminiCloudCodeClient:
-    """Minimal OpenAI-SDK-compatible facade over Code Assist v1internal."""
-
-    def __init__(
-        self,
-        *,
-        api_key: Optional[str] = None,
-        base_url: Optional[str] = None,
-        default_headers: Optional[Dict[str, str]] = None,
-        project_id: str = "",
-        **_: Any,
-    ):
-        # `api_key` here is a dummy — real auth is the OAuth access token
-        # fetched on every call via agent.google_oauth.get_valid_access_token().
-        # We accept the kwarg for openai.OpenAI interface parity.
-        self.api_key = api_key or "google-oauth"
-        self.base_url = base_url or MARKER_BASE_URL
-        self._default_headers = dict(default_headers or {})
-        self._configured_project_id = project_id
-        self._project_context: Optional[ProjectContext] = None
-        self._project_context_lock = False  # simple single-thread guard
-        self.chat = _GeminiChatNamespace(self)
-        self.is_closed = False
-        self._http = httpx.Client(timeout=httpx.Timeout(connect=15.0, read=600.0, write=30.0, pool=30.0))
-
-    def close(self) -> None:
-        self.is_closed = True
-        try:
-            self._http.close()
-        except Exception:
-            pass
-
-    # Implement the OpenAI SDK's context-manager-ish closure check
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        self.close()
-
-    def _ensure_project_context(self, access_token: str, model: str) -> ProjectContext:
-        """Lazily resolve and cache the project context for this client."""
-        if self._project_context is not None:
-            return self._project_context
-
-        env_project = google_oauth.resolve_project_id_from_env()
-        creds = google_oauth.load_credentials()
-        stored_project = creds.project_id if creds else ""
-
-        # Prefer what's already baked into the creds
-        if stored_project:
-            self._project_context = ProjectContext(
-                project_id=stored_project,
-                managed_project_id=creds.managed_project_id if creds else "",
-                tier_id="",
-                source="stored",
-            )
-            return self._project_context
-
-        ctx = resolve_project_context(
-            access_token,
-            configured_project_id=self._configured_project_id,
-            env_project_id=env_project,
-            user_agent_model=model,
-        )
-        # Persist discovered project back to the creds file so the next
-        # session doesn't re-run the discovery.
-        if ctx.project_id or ctx.managed_project_id:
-            google_oauth.update_project_ids(
-                project_id=ctx.project_id,
-                managed_project_id=ctx.managed_project_id,
-            )
-        self._project_context = ctx
-        return ctx
-
-    def _create_chat_completion(
-        self,
-        *,
-        model: str = "gemini-2.5-flash",
-        messages: Optional[List[Dict[str, Any]]] = None,
-        stream: bool = False,
-        tools: Any = None,
-        tool_choice: Any = None,
-        temperature: Optional[float] = None,
-        max_tokens: Optional[int] = None,
-        top_p: Optional[float] = None,
-        stop: Any = None,
-        extra_body: Optional[Dict[str, Any]] = None,
-        timeout: Any = None,
-        **_: Any,
-    ) -> Any:
-        access_token = google_oauth.get_valid_access_token()
-        ctx = self._ensure_project_context(access_token, model)
-
-        thinking_config = None
-        if isinstance(extra_body, dict):
-            thinking_config = extra_body.get("thinking_config") or extra_body.get("thinkingConfig")
-
-        inner = build_gemini_request(
-            messages=messages or [],
-            tools=tools,
-            tool_choice=tool_choice,
-            temperature=temperature,
-            max_tokens=max_tokens,
-            top_p=top_p,
-            stop=stop,
-            thinking_config=thinking_config,
-        )
-        wrapped = wrap_code_assist_request(
-            project_id=ctx.project_id,
-            model=model,
-            inner_request=inner,
-        )
-
-        headers = {
-            "Content-Type": "application/json",
-            "Accept": "application/json",
-            "Authorization": f"Bearer {access_token}",
-            "User-Agent": "hermes-agent (gemini-cli-compat)",
-            "X-Goog-Api-Client": "gl-python/hermes",
-            "x-activity-request-id": str(uuid.uuid4()),
-        }
-        headers.update(self._default_headers)
-
-        if stream:
-            return self._stream_completion(model=model, wrapped=wrapped, headers=headers)
-
-        url = f"{CODE_ASSIST_ENDPOINT}/v1internal:generateContent"
-        response = self._http.post(url, json=wrapped, headers=headers)
-        if response.status_code != 200:
-            raise _gemini_http_error(response)
-        try:
-            payload = response.json()
-        except ValueError as exc:
-            raise CodeAssistError(
-                f"Invalid JSON from Code Assist: {exc}",
-                code="code_assist_invalid_json",
-            ) from exc
-        return _translate_gemini_response(payload, model=model)
-
-    def _stream_completion(
-        self,
-        *,
-        model: str,
-        wrapped: Dict[str, Any],
-        headers: Dict[str, str],
-    ) -> Iterator[_GeminiStreamChunk]:
-        """Generator that yields OpenAI-shaped streaming chunks."""
-        url = f"{CODE_ASSIST_ENDPOINT}/v1internal:streamGenerateContent?alt=sse"
-        stream_headers = dict(headers)
-        stream_headers["Accept"] = "text/event-stream"
-
-        def _generator() -> Iterator[_GeminiStreamChunk]:
-            try:
-                with self._http.stream("POST", url, json=wrapped, headers=stream_headers) as response:
-                    if response.status_code != 200:
-                        # Materialize error body for better diagnostics
-                        response.read()
-                        raise _gemini_http_error(response)
-                    tool_call_counter: List[int] = [0]
-                    for event in _iter_sse_events(response):
-                        for chunk in _translate_stream_event(event, model, tool_call_counter):
-                            yield chunk
-            except httpx.HTTPError as exc:
-                raise CodeAssistError(
-                    f"Streaming request failed: {exc}",
-                    code="code_assist_stream_error",
-                ) from exc
-
-        return _generator()
-
-
-def _gemini_http_error(response: httpx.Response) -> CodeAssistError:
-    """Translate an httpx response into a CodeAssistError with rich metadata.
-
-    Parses Google's error envelope (``{"error": {"code", "message", "status",
-    "details": [...]}}``) so the agent's error classifier can reason about
-    the failure — ``status_code`` enables the rate_limit / auth classification
-    paths, and ``response`` lets the main loop honor ``Retry-After`` just
-    like it does for OpenAI SDK exceptions.
-
-    Also lifts a few recognizable Google conditions into human-readable
-    messages so the user sees something better than a 500-char JSON dump:
-
-        MODEL_CAPACITY_EXHAUSTED → "Gemini model capacity exhausted for
-            <model>. This is a Google-side throttle..."
-        RESOURCE_EXHAUSTED w/o reason → quota-style message
-        404 → "Model <name> not found at cloudcode-pa..."
-    """
-    status = response.status_code
-
-    # Parse the body once, surviving any weird encodings.
-    body_text = ""
-    body_json: Dict[str, Any] = {}
-    try:
-        body_text = response.text
-    except Exception:
-        body_text = ""
-    if body_text:
-        try:
-            parsed = json.loads(body_text)
-            if isinstance(parsed, dict):
-                body_json = parsed
-        except (ValueError, TypeError):
-            body_json = {}
-
-    # Dig into Google's error envelope.  Shape is:
-    #   {"error": {"code": 429, "message": "...", "status": "RESOURCE_EXHAUSTED",
-    #              "details": [{"@type": ".../ErrorInfo", "reason": "MODEL_CAPACITY_EXHAUSTED",
-    #                           "metadata": {...}},
-    #                          {"@type": ".../RetryInfo", "retryDelay": "30s"}]}}
-    err_obj = body_json.get("error") if isinstance(body_json, dict) else None
-    if not isinstance(err_obj, dict):
-        err_obj = {}
-    err_status = str(err_obj.get("status") or "").strip()
-    err_message = str(err_obj.get("message") or "").strip()
-    _raw_details = err_obj.get("details")
-    err_details_list = _raw_details if isinstance(_raw_details, list) else []
-
-    # Extract google.rpc.ErrorInfo reason + metadata.  There may be more
-    # than one ErrorInfo (rare), so we pick the first one with a reason.
-    error_reason = ""
-    error_metadata: Dict[str, Any] = {}
-    retry_delay_seconds: Optional[float] = None
-    for detail in err_details_list:
-        if not isinstance(detail, dict):
-            continue
-        type_url = str(detail.get("@type") or "")
-        if not error_reason and type_url.endswith("/google.rpc.ErrorInfo"):
-            reason = detail.get("reason")
-            if isinstance(reason, str) and reason:
-                error_reason = reason
-            md = detail.get("metadata")
-            if isinstance(md, dict):
-                error_metadata = md
-        elif retry_delay_seconds is None and type_url.endswith("/google.rpc.RetryInfo"):
-            # retryDelay is a google.protobuf.Duration string like "30s" or "1.5s".
-            delay_raw = detail.get("retryDelay")
-            if isinstance(delay_raw, str) and delay_raw.endswith("s"):
-                try:
-                    retry_delay_seconds = float(delay_raw[:-1])
-                except ValueError:
-                    pass
-            elif isinstance(delay_raw, (int, float)):
-                retry_delay_seconds = float(delay_raw)
-
-    # Fall back to the Retry-After header if the body didn't include RetryInfo.
-    if retry_delay_seconds is None:
-        try:
-            header_val = response.headers.get("Retry-After") or response.headers.get("retry-after")
-        except Exception:
-            header_val = None
-        if header_val:
-            try:
-                retry_delay_seconds = float(header_val)
-            except (TypeError, ValueError):
-                retry_delay_seconds = None
-
-    # Classify the error code.  ``code_assist_rate_limited`` stays the default
-    # for 429s; a more specific reason tag helps downstream callers (e.g. tests,
-    # logs) without changing the rate_limit classification path.
-    code = f"code_assist_http_{status}"
-    if status == 401:
-        code = "code_assist_unauthorized"
-    elif status == 429:
-        code = "code_assist_rate_limited"
-        if error_reason == "MODEL_CAPACITY_EXHAUSTED":
-            code = "code_assist_capacity_exhausted"
-
-    # Build a human-readable message.  Keep the status + a raw-body tail for
-    # debugging, but lead with a friendlier summary when we recognize the
-    # Google signal.
-    model_hint = ""
-    if isinstance(error_metadata, dict):
-        model_hint = str(error_metadata.get("model") or error_metadata.get("modelId") or "").strip()
-
-    if status == 429 and error_reason == "MODEL_CAPACITY_EXHAUSTED":
-        target = model_hint or "this Gemini model"
-        message = (
-            f"Gemini capacity exhausted for {target} (Google-side throttle, "
-            f"not a Hermes issue). Try a different Gemini model or set a "
-            f"fallback_providers entry to a non-Gemini provider."
-        )
-        if retry_delay_seconds is not None:
-            message += f" Google suggests retrying in {retry_delay_seconds:g}s."
-    elif status == 429 and err_status == "RESOURCE_EXHAUSTED":
-        message = (
-            f"Gemini quota exhausted ({err_message or 'RESOURCE_EXHAUSTED'}). "
-            f"Check /gquota for remaining daily requests."
-        )
-        if retry_delay_seconds is not None:
-            message += f" Retry suggested in {retry_delay_seconds:g}s."
-    elif status == 404:
-        # Google returns 404 when a model has been retired or renamed.
-        target = model_hint or (err_message or "model")
-        message = (
-            f"Code Assist 404: {target} is not available at "
-            f"cloudcode-pa.googleapis.com. It may have been renamed or "
-            f"retired. Check hermes_cli/models.py for the current list."
-        )
-    elif err_message:
-        # Generic fallback with the parsed message.
-        message = f"Code Assist HTTP {status} ({err_status or 'error'}): {err_message}"
-    else:
-        # Last-ditch fallback — raw body snippet.
-        message = f"Code Assist returned HTTP {status}: {body_text[:500]}"
-
-    return CodeAssistError(
-        message,
-        code=code,
-        status_code=status,
-        response=response,
-        retry_after=retry_delay_seconds,
-        details={
-            "status": err_status,
-            "reason": error_reason,
-            "metadata": error_metadata,
-            "message": err_message,
-        },
-    )
--- a/agent/gemini_native_adapter.py
+++ b/agent/gemini_native_adapter.py
@@ -1,847 +0,0 @@
-"""OpenAI-compatible facade over Google AI Studio's native Gemini API.
-
-Hermes keeps ``api_mode='chat_completions'`` for the ``gemini`` provider so the
-main agent loop can keep using its existing OpenAI-shaped message flow.
-This adapter is the transport shim that converts those OpenAI-style
-``messages[]`` / ``tools[]`` requests into Gemini's native
-``models/{model}:generateContent`` schema and converts the responses back.
-
-Why this exists
---------------
-Google's OpenAI-compatible endpoint has been brittle for Hermes's multi-turn
-agent/tool loop (auth churn, tool-call replay quirks, thought-signature
-requirements).  The native Gemini API is the canonical path and avoids the
-OpenAI-compat layer entirely.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import base64
-import json
-import logging
-import time
-import uuid
-from types import SimpleNamespace
-from typing import Any, Dict, Iterator, List, Optional
-
-import httpx
-
-from agent.gemini_schema import sanitize_gemini_tool_parameters
-
-logger = logging.getLogger(__name__)
-
-DEFAULT_GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta"
-
-
-def is_native_gemini_base_url(base_url: str) -> bool:
-    """Return True when the endpoint speaks Gemini's native REST API."""
-    normalized = str(base_url or "").strip().rstrip("/").lower()
-    if not normalized:
-        return False
-    if "generativelanguage.googleapis.com" not in normalized:
-        return False
-    return not normalized.endswith("/openai")
-
-
-class GeminiAPIError(Exception):
-    """Error shape compatible with Hermes retry/error classification."""
-
-    def __init__(
-        self,
-        message: str,
-        *,
-        code: str = "gemini_api_error",
-        status_code: Optional[int] = None,
-        response: Optional[httpx.Response] = None,
-        retry_after: Optional[float] = None,
-        details: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        super().__init__(message)
-        self.code = code
-        self.status_code = status_code
-        self.response = response
-        self.retry_after = retry_after
-        self.details = details or {}
-
-
-def _coerce_content_to_text(content: Any) -> str:
-    if content is None:
-        return ""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        pieces: List[str] = []
-        for part in content:
-            if isinstance(part, str):
-                pieces.append(part)
-            elif isinstance(part, dict) and part.get("type") == "text":
-                text = part.get("text")
-                if isinstance(text, str):
-                    pieces.append(text)
-        return "\n".join(pieces)
-    return str(content)
-
-
-def _extract_multimodal_parts(content: Any) -> List[Dict[str, Any]]:
-    if not isinstance(content, list):
-        text = _coerce_content_to_text(content)
-        return [{"text": text}] if text else []
-
-    parts: List[Dict[str, Any]] = []
-    for item in content:
-        if isinstance(item, str):
-            parts.append({"text": item})
-            continue
-        if not isinstance(item, dict):
-            continue
-        ptype = item.get("type")
-        if ptype == "text":
-            text = item.get("text")
-            if isinstance(text, str) and text:
-                parts.append({"text": text})
-        elif ptype == "image_url":
-            url = ((item.get("image_url") or {}).get("url") or "")
-            if not isinstance(url, str) or not url.startswith("data:"):
-                continue
-            try:
-                header, encoded = url.split(",", 1)
-                mime = header.split(":", 1)[1].split(";", 1)[0]
-                raw = base64.b64decode(encoded)
-            except Exception:
-                continue
-            parts.append(
-                {
-                    "inlineData": {
-                        "mimeType": mime,
-                        "data": base64.b64encode(raw).decode("ascii"),
-                    }
-                }
-            )
-    return parts
-
-
-def _tool_call_extra_signature(tool_call: Dict[str, Any]) -> Optional[str]:
-    extra = tool_call.get("extra_content") or {}
-    if not isinstance(extra, dict):
-        return None
-    google = extra.get("google") or extra.get("thought_signature")
-    if isinstance(google, dict):
-        sig = google.get("thought_signature") or google.get("thoughtSignature")
-        return str(sig) if isinstance(sig, str) and sig else None
-    if isinstance(google, str) and google:
-        return google
-    return None
-
-
-def _translate_tool_call_to_gemini(tool_call: Dict[str, Any]) -> Dict[str, Any]:
-    fn = tool_call.get("function") or {}
-    args_raw = fn.get("arguments", "")
-    try:
-        args = json.loads(args_raw) if isinstance(args_raw, str) and args_raw else {}
-    except json.JSONDecodeError:
-        args = {"_raw": args_raw}
-    if not isinstance(args, dict):
-        args = {"_value": args}
-
-    part: Dict[str, Any] = {
-        "functionCall": {
-            "name": str(fn.get("name") or ""),
-            "args": args,
-        }
-    }
-    thought_signature = _tool_call_extra_signature(tool_call)
-    if thought_signature:
-        part["thoughtSignature"] = thought_signature
-    return part
-
-
-def _translate_tool_result_to_gemini(
-    message: Dict[str, Any],
-    tool_name_by_call_id: Optional[Dict[str, str]] = None,
-) -> Dict[str, Any]:
-    tool_name_by_call_id = tool_name_by_call_id or {}
-    tool_call_id = str(message.get("tool_call_id") or "")
-    name = str(
-        message.get("name")
-        or tool_name_by_call_id.get(tool_call_id)
-        or tool_call_id
-        or "tool"
-    )
-    content = _coerce_content_to_text(message.get("content"))
-    try:
-        parsed = json.loads(content) if content.strip().startswith(("{", "[")) else None
-    except json.JSONDecodeError:
-        parsed = None
-    response = parsed if isinstance(parsed, dict) else {"output": content}
-    return {
-        "functionResponse": {
-            "name": name,
-            "response": response,
-        }
-    }
-
-
-def _build_gemini_contents(messages: List[Dict[str, Any]]) -> tuple[List[Dict[str, Any]], Optional[Dict[str, Any]]]:
-    system_text_parts: List[str] = []
-    contents: List[Dict[str, Any]] = []
-    tool_name_by_call_id: Dict[str, str] = {}
-
-    for msg in messages:
-        if not isinstance(msg, dict):
-            continue
-        role = str(msg.get("role") or "user")
-
-        if role == "system":
-            system_text_parts.append(_coerce_content_to_text(msg.get("content")))
-            continue
-
-        if role in {"tool", "function"}:
-            contents.append(
-                {
-                    "role": "user",
-                    "parts": [
-                        _translate_tool_result_to_gemini(
-                            msg,
-                            tool_name_by_call_id=tool_name_by_call_id,
-                        )
-                    ],
-                }
-            )
-            continue
-
-        gemini_role = "model" if role == "assistant" else "user"
-        parts: List[Dict[str, Any]] = []
-
-        content_parts = _extract_multimodal_parts(msg.get("content"))
-        parts.extend(content_parts)
-
-        tool_calls = msg.get("tool_calls") or []
-        if isinstance(tool_calls, list):
-            for tool_call in tool_calls:
-                if isinstance(tool_call, dict):
-                    tool_call_id = str(tool_call.get("id") or tool_call.get("call_id") or "")
-                    tool_name = str(((tool_call.get("function") or {}).get("name") or ""))
-                    if tool_call_id and tool_name:
-                        tool_name_by_call_id[tool_call_id] = tool_name
-                    parts.append(_translate_tool_call_to_gemini(tool_call))
-
-        if parts:
-            contents.append({"role": gemini_role, "parts": parts})
-
-    system_instruction = None
-    joined_system = "\n".join(part for part in system_text_parts if part).strip()
-    if joined_system:
-        system_instruction = {"parts": [{"text": joined_system}]}
-    return contents, system_instruction
-
-
-def _translate_tools_to_gemini(tools: Any) -> List[Dict[str, Any]]:
-    if not isinstance(tools, list):
-        return []
-    declarations: List[Dict[str, Any]] = []
-    for tool in tools:
-        if not isinstance(tool, dict):
-            continue
-        fn = tool.get("function") or {}
-        if not isinstance(fn, dict):
-            continue
-        name = fn.get("name")
-        if not isinstance(name, str) or not name:
-            continue
-        decl: Dict[str, Any] = {"name": name}
-        description = fn.get("description")
-        if isinstance(description, str) and description:
-            decl["description"] = description
-        parameters = fn.get("parameters")
-        if isinstance(parameters, dict):
-            decl["parameters"] = sanitize_gemini_tool_parameters(parameters)
-        declarations.append(decl)
-    return [{"functionDeclarations": declarations}] if declarations else []
-
-
-def _translate_tool_choice_to_gemini(tool_choice: Any) -> Optional[Dict[str, Any]]:
-    if tool_choice is None:
-        return None
-    if isinstance(tool_choice, str):
-        if tool_choice == "auto":
-            return {"functionCallingConfig": {"mode": "AUTO"}}
-        if tool_choice == "required":
-            return {"functionCallingConfig": {"mode": "ANY"}}
-        if tool_choice == "none":
-            return {"functionCallingConfig": {"mode": "NONE"}}
-    if isinstance(tool_choice, dict):
-        fn = tool_choice.get("function") or {}
-        name = fn.get("name")
-        if isinstance(name, str) and name:
-            return {"functionCallingConfig": {"mode": "ANY", "allowedFunctionNames": [name]}}
-    return None
-
-
-def _normalize_thinking_config(config: Any) -> Optional[Dict[str, Any]]:
-    if not isinstance(config, dict) or not config:
-        return None
-    budget = config.get("thinkingBudget", config.get("thinking_budget"))
-    include = config.get("includeThoughts", config.get("include_thoughts"))
-    level = config.get("thinkingLevel", config.get("thinking_level"))
-    normalized: Dict[str, Any] = {}
-    if isinstance(budget, (int, float)):
-        normalized["thinkingBudget"] = int(budget)
-    if isinstance(include, bool):
-        normalized["includeThoughts"] = include
-    if isinstance(level, str) and level.strip():
-        normalized["thinkingLevel"] = level.strip().lower()
-    return normalized or None
-
-
-def build_gemini_request(
-    *,
-    messages: List[Dict[str, Any]],
-    tools: Any = None,
-    tool_choice: Any = None,
-    temperature: Optional[float] = None,
-    max_tokens: Optional[int] = None,
-    top_p: Optional[float] = None,
-    stop: Any = None,
-    thinking_config: Any = None,
-) -> Dict[str, Any]:
-    contents, system_instruction = _build_gemini_contents(messages)
-    request: Dict[str, Any] = {"contents": contents}
-    if system_instruction:
-        request["systemInstruction"] = system_instruction
-
-    gemini_tools = _translate_tools_to_gemini(tools)
-    if gemini_tools:
-        request["tools"] = gemini_tools
-
-    tool_config = _translate_tool_choice_to_gemini(tool_choice)
-    if tool_config:
-        request["toolConfig"] = tool_config
-
-    generation_config: Dict[str, Any] = {}
-    if temperature is not None:
-        generation_config["temperature"] = temperature
-    if max_tokens is not None:
-        generation_config["maxOutputTokens"] = max_tokens
-    if top_p is not None:
-        generation_config["topP"] = top_p
-    if stop:
-        generation_config["stopSequences"] = stop if isinstance(stop, list) else [str(stop)]
-    normalized_thinking = _normalize_thinking_config(thinking_config)
-    if normalized_thinking:
-        generation_config["thinkingConfig"] = normalized_thinking
-    if generation_config:
-        request["generationConfig"] = generation_config
-
-    return request
-
-
-def _map_gemini_finish_reason(reason: str) -> str:
-    mapping = {
-        "STOP": "stop",
-        "MAX_TOKENS": "length",
-        "SAFETY": "content_filter",
-        "RECITATION": "content_filter",
-        "OTHER": "stop",
-    }
-    return mapping.get(str(reason or "").upper(), "stop")
-
-
-def _tool_call_extra_from_part(part: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    sig = part.get("thoughtSignature")
-    if isinstance(sig, str) and sig:
-        return {"google": {"thought_signature": sig}}
-    return None
-
-
-def _empty_response(model: str) -> SimpleNamespace:
-    message = SimpleNamespace(
-        role="assistant",
-        content="",
-        tool_calls=None,
-        reasoning=None,
-        reasoning_content=None,
-        reasoning_details=None,
-    )
-    choice = SimpleNamespace(index=0, message=message, finish_reason="stop")
-    usage = SimpleNamespace(
-        prompt_tokens=0,
-        completion_tokens=0,
-        total_tokens=0,
-        prompt_tokens_details=SimpleNamespace(cached_tokens=0),
-    )
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-def translate_gemini_response(resp: Dict[str, Any], model: str) -> SimpleNamespace:
-    candidates = resp.get("candidates") or []
-    if not isinstance(candidates, list) or not candidates:
-        return _empty_response(model)
-
-    cand = candidates[0] if isinstance(candidates[0], dict) else {}
-    content_obj = cand.get("content") if isinstance(cand, dict) else {}
-    parts = content_obj.get("parts") if isinstance(content_obj, dict) else []
-
-    text_pieces: List[str] = []
-    reasoning_pieces: List[str] = []
-    tool_calls: List[SimpleNamespace] = []
-
-    for index, part in enumerate(parts or []):
-        if not isinstance(part, dict):
-            continue
-        if part.get("thought") is True and isinstance(part.get("text"), str):
-            reasoning_pieces.append(part["text"])
-            continue
-        if isinstance(part.get("text"), str):
-            text_pieces.append(part["text"])
-            continue
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            tool_call = SimpleNamespace(
-                id=f"call_{uuid.uuid4().hex[:12]}",
-                type="function",
-                index=index,
-                function=SimpleNamespace(name=str(fc["name"]), arguments=args_str),
-            )
-            extra_content = _tool_call_extra_from_part(part)
-            if extra_content:
-                tool_call.extra_content = extra_content
-            tool_calls.append(tool_call)
-
-    finish_reason = "tool_calls" if tool_calls else _map_gemini_finish_reason(str(cand.get("finishReason") or ""))
-    usage_meta = resp.get("usageMetadata") or {}
-    usage = SimpleNamespace(
-        prompt_tokens=int(usage_meta.get("promptTokenCount") or 0),
-        completion_tokens=int(usage_meta.get("candidatesTokenCount") or 0),
-        total_tokens=int(usage_meta.get("totalTokenCount") or 0),
-        prompt_tokens_details=SimpleNamespace(
-            cached_tokens=int(usage_meta.get("cachedContentTokenCount") or 0),
-        ),
-    )
-    reasoning = "".join(reasoning_pieces) or None
-    message = SimpleNamespace(
-        role="assistant",
-        content="".join(text_pieces) if text_pieces else None,
-        tool_calls=tool_calls or None,
-        reasoning=reasoning,
-        reasoning_content=reasoning,
-        reasoning_details=None,
-    )
-    choice = SimpleNamespace(index=0, message=message, finish_reason=finish_reason)
-    return SimpleNamespace(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=usage,
-    )
-
-
-class _GeminiStreamChunk(SimpleNamespace):
-    pass
-
-
-def _make_stream_chunk(
-    *,
-    model: str,
-    content: str = "",
-    tool_call_delta: Optional[Dict[str, Any]] = None,
-    finish_reason: Optional[str] = None,
-    reasoning: str = "",
-) -> _GeminiStreamChunk:
-    delta_kwargs: Dict[str, Any] = {
-        "role": "assistant",
-        "content": None,
-        "tool_calls": None,
-        "reasoning": None,
-        "reasoning_content": None,
-    }
-    if content:
-        delta_kwargs["content"] = content
-    if tool_call_delta is not None:
-        tool_delta = SimpleNamespace(
-            index=tool_call_delta.get("index", 0),
-            id=tool_call_delta.get("id") or f"call_{uuid.uuid4().hex[:12]}",
-            type="function",
-            function=SimpleNamespace(
-                name=tool_call_delta.get("name") or "",
-                arguments=tool_call_delta.get("arguments") or "",
-            ),
-        )
-        extra_content = tool_call_delta.get("extra_content")
-        if isinstance(extra_content, dict):
-            tool_delta.extra_content = extra_content
-        delta_kwargs["tool_calls"] = [tool_delta]
-    if reasoning:
-        delta_kwargs["reasoning"] = reasoning
-        delta_kwargs["reasoning_content"] = reasoning
-    delta = SimpleNamespace(**delta_kwargs)
-    choice = SimpleNamespace(index=0, delta=delta, finish_reason=finish_reason)
-    return _GeminiStreamChunk(
-        id=f"chatcmpl-{uuid.uuid4().hex[:12]}",
-        object="chat.completion.chunk",
-        created=int(time.time()),
-        model=model,
-        choices=[choice],
-        usage=None,
-    )
-
-
-def _iter_sse_events(response: httpx.Response) -> Iterator[Dict[str, Any]]:
-    buffer = ""
-    for chunk in response.iter_text():
-        if not chunk:
-            continue
-        buffer += chunk
-        while "\n" in buffer:
-            line, buffer = buffer.split("\n", 1)
-            line = line.rstrip("\r")
-            if not line:
-                continue
-            if not line.startswith("data: "):
-                continue
-            data = line[6:]
-            if data == "[DONE]":
-                return
-            try:
-                payload = json.loads(data)
-            except json.JSONDecodeError:
-                logger.debug("Non-JSON Gemini SSE line: %s", data[:200])
-                continue
-            if isinstance(payload, dict):
-                yield payload
-
-
-def translate_stream_event(event: Dict[str, Any], model: str, tool_call_indices: Dict[str, Dict[str, Any]]) -> List[_GeminiStreamChunk]:
-    candidates = event.get("candidates") or []
-    if not candidates:
-        return []
-    cand = candidates[0] if isinstance(candidates[0], dict) else {}
-    parts = ((cand.get("content") or {}).get("parts") or []) if isinstance(cand, dict) else []
-    chunks: List[_GeminiStreamChunk] = []
-
-    for part_index, part in enumerate(parts):
-        if not isinstance(part, dict):
-            continue
-        if part.get("thought") is True and isinstance(part.get("text"), str):
-            chunks.append(_make_stream_chunk(model=model, reasoning=part["text"]))
-            continue
-        if isinstance(part.get("text"), str) and part["text"]:
-            chunks.append(_make_stream_chunk(model=model, content=part["text"]))
-        fc = part.get("functionCall")
-        if isinstance(fc, dict) and fc.get("name"):
-            name = str(fc["name"])
-            try:
-                args_str = json.dumps(fc.get("args") or {}, ensure_ascii=False, sort_keys=True)
-            except (TypeError, ValueError):
-                args_str = "{}"
-            thought_signature = part.get("thoughtSignature") if isinstance(part.get("thoughtSignature"), str) else ""
-            call_key = json.dumps(
-                {
-                    "part_index": part_index,
-                    "name": name,
-                    "thought_signature": thought_signature,
-                },
-                sort_keys=True,
-            )
-            slot = tool_call_indices.get(call_key)
-            if slot is None:
-                slot = {
-                    "index": len(tool_call_indices),
-                    "id": f"call_{uuid.uuid4().hex[:12]}",
-                    "last_arguments": "",
-                }
-                tool_call_indices[call_key] = slot
-            emitted_arguments = args_str
-            last_arguments = str(slot.get("last_arguments") or "")
-            if last_arguments:
-                if args_str == last_arguments:
-                    emitted_arguments = ""
-                elif args_str.startswith(last_arguments):
-                    emitted_arguments = args_str[len(last_arguments):]
-            slot["last_arguments"] = args_str
-            chunks.append(
-                _make_stream_chunk(
-                    model=model,
-                    tool_call_delta={
-                        "index": slot["index"],
-                        "id": slot["id"],
-                        "name": name,
-                        "arguments": emitted_arguments,
-                        "extra_content": _tool_call_extra_from_part(part),
-                    },
-                )
-            )
-
-    finish_reason_raw = str(cand.get("finishReason") or "")
-    if finish_reason_raw:
-        mapped = "tool_calls" if tool_call_indices else _map_gemini_finish_reason(finish_reason_raw)
-        chunks.append(_make_stream_chunk(model=model, finish_reason=mapped))
-    return chunks
-
-
-def gemini_http_error(response: httpx.Response) -> GeminiAPIError:
-    status = response.status_code
-    body_text = ""
-    body_json: Dict[str, Any] = {}
-    try:
-        body_text = response.text
-    except Exception:
-        body_text = ""
-    if body_text:
-        try:
-            parsed = json.loads(body_text)
-            if isinstance(parsed, dict):
-                body_json = parsed
-        except (ValueError, TypeError):
-            body_json = {}
-
-    err_obj = body_json.get("error") if isinstance(body_json, dict) else None
-    if not isinstance(err_obj, dict):
-        err_obj = {}
-    err_status = str(err_obj.get("status") or "").strip()
-    err_message = str(err_obj.get("message") or "").strip()
-    _raw_details = err_obj.get("details")
-    details_list = _raw_details if isinstance(_raw_details, list) else []
-
-    reason = ""
-    retry_after: Optional[float] = None
-    metadata: Dict[str, Any] = {}
-    for detail in details_list:
-        if not isinstance(detail, dict):
-            continue
-        type_url = str(detail.get("@type") or "")
-        if not reason and type_url.endswith("/google.rpc.ErrorInfo"):
-            reason_value = detail.get("reason")
-            if isinstance(reason_value, str):
-                reason = reason_value
-            md = detail.get("metadata")
-            if isinstance(md, dict):
-                metadata = md
-    header_retry = response.headers.get("Retry-After") or response.headers.get("retry-after")
-    if header_retry:
-        try:
-            retry_after = float(header_retry)
-        except (TypeError, ValueError):
-            retry_after = None
-
-    code = f"gemini_http_{status}"
-    if status == 401:
-        code = "gemini_unauthorized"
-    elif status == 429:
-        code = "gemini_rate_limited"
-    elif status == 404:
-        code = "gemini_model_not_found"
-
-    if err_message:
-        message = f"Gemini HTTP {status} ({err_status or 'error'}): {err_message}"
-    else:
-        message = f"Gemini returned HTTP {status}: {body_text[:500]}"
-
-    return GeminiAPIError(
-        message,
-        code=code,
-        status_code=status,
-        response=response,
-        retry_after=retry_after,
-        details={
-            "status": err_status,
-            "reason": reason,
-            "metadata": metadata,
-            "message": err_message,
-        },
-    )
-
-
-class _GeminiChatCompletions:
-    def __init__(self, client: "GeminiNativeClient"):
-        self._client = client
-
-    def create(self, **kwargs: Any) -> Any:
-        return self._client._create_chat_completion(**kwargs)
-
-
-class _AsyncGeminiChatCompletions:
-    def __init__(self, client: "AsyncGeminiNativeClient"):
-        self._client = client
-
-    async def create(self, **kwargs: Any) -> Any:
-        return await self._client._create_chat_completion(**kwargs)
-
-
-class _GeminiChatNamespace:
-    def __init__(self, client: "GeminiNativeClient"):
-        self.completions = _GeminiChatCompletions(client)
-
-
-class _AsyncGeminiChatNamespace:
-    def __init__(self, client: "AsyncGeminiNativeClient"):
-        self.completions = _AsyncGeminiChatCompletions(client)
-
-
-class GeminiNativeClient:
-    """Minimal OpenAI-SDK-compatible facade over Gemini's native REST API."""
-
-    def __init__(
-        self,
-        *,
-        api_key: str,
-        base_url: Optional[str] = None,
-        default_headers: Optional[Dict[str, str]] = None,
-        timeout: Any = None,
-        http_client: Optional[httpx.Client] = None,
-        **_: Any,
-    ) -> None:
-        self.api_key = api_key
-        normalized_base = (base_url or DEFAULT_GEMINI_BASE_URL).rstrip("/")
-        if normalized_base.endswith("/openai"):
-            normalized_base = normalized_base[: -len("/openai")]
-        self.base_url = normalized_base
-        self._default_headers = dict(default_headers or {})
-        self.chat = _GeminiChatNamespace(self)
-        self.is_closed = False
-        self._http = http_client or httpx.Client(
-            timeout=timeout or httpx.Timeout(connect=15.0, read=600.0, write=30.0, pool=30.0)
-        )
-
-    def close(self) -> None:
-        self.is_closed = True
-        try:
-            self._http.close()
-        except Exception:
-            pass
-
-    def __enter__(self):
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        self.close()
-
-    def _headers(self) -> Dict[str, str]:
-        headers = {
-            "Content-Type": "application/json",
-            "Accept": "application/json",
-            "x-goog-api-key": self.api_key,
-            "User-Agent": "hermes-agent (gemini-native)",
-        }
-        headers.update(self._default_headers)
-        return headers
-
-    @staticmethod
-    def _advance_stream_iterator(iterator: Iterator[_GeminiStreamChunk]) -> tuple[bool, Optional[_GeminiStreamChunk]]:
-        try:
-            return False, next(iterator)
-        except StopIteration:
-            return True, None
-
-    def _create_chat_completion(
-        self,
-        *,
-        model: str = "gemini-2.5-flash",
-        messages: Optional[List[Dict[str, Any]]] = None,
-        stream: bool = False,
-        tools: Any = None,
-        tool_choice: Any = None,
-        temperature: Optional[float] = None,
-        max_tokens: Optional[int] = None,
-        top_p: Optional[float] = None,
-        stop: Any = None,
-        extra_body: Optional[Dict[str, Any]] = None,
-        timeout: Any = None,
-        **_: Any,
-    ) -> Any:
-        thinking_config = None
-        if isinstance(extra_body, dict):
-            thinking_config = extra_body.get("thinking_config") or extra_body.get("thinkingConfig")
-
-        request = build_gemini_request(
-            messages=messages or [],
-            tools=tools,
-            tool_choice=tool_choice,
-            temperature=temperature,
-            max_tokens=max_tokens,
-            top_p=top_p,
-            stop=stop,
-            thinking_config=thinking_config,
-        )
-
-        if stream:
-            return self._stream_completion(model=model, request=request, timeout=timeout)
-
-        url = f"{self.base_url}/models/{model}:generateContent"
-        response = self._http.post(url, json=request, headers=self._headers(), timeout=timeout)
-        if response.status_code != 200:
-            raise gemini_http_error(response)
-        try:
-            payload = response.json()
-        except ValueError as exc:
-            raise GeminiAPIError(
-                f"Invalid JSON from Gemini native API: {exc}",
-                code="gemini_invalid_json",
-                status_code=response.status_code,
-                response=response,
-            ) from exc
-        return translate_gemini_response(payload, model=model)
-
-    def _stream_completion(self, *, model: str, request: Dict[str, Any], timeout: Any = None) -> Iterator[_GeminiStreamChunk]:
-        url = f"{self.base_url}/models/{model}:streamGenerateContent?alt=sse"
-        stream_headers = dict(self._headers())
-        stream_headers["Accept"] = "text/event-stream"
-
-        def _generator() -> Iterator[_GeminiStreamChunk]:
-            try:
-                with self._http.stream("POST", url, json=request, headers=stream_headers, timeout=timeout) as response:
-                    if response.status_code != 200:
-                        response.read()
-                        raise gemini_http_error(response)
-                    tool_call_indices: Dict[str, Dict[str, Any]] = {}
-                    for event in _iter_sse_events(response):
-                        for chunk in translate_stream_event(event, model, tool_call_indices):
-                            yield chunk
-            except httpx.HTTPError as exc:
-                raise GeminiAPIError(
-                    f"Gemini streaming request failed: {exc}",
-                    code="gemini_stream_error",
-                ) from exc
-
-        return _generator()
-
-
-class AsyncGeminiNativeClient:
-    """Async wrapper used by auxiliary_client for native Gemini calls."""
-
-    def __init__(self, sync_client: GeminiNativeClient):
-        self._sync = sync_client
-        self.api_key = sync_client.api_key
-        self.base_url = sync_client.base_url
-        self.chat = _AsyncGeminiChatNamespace(self)
-
-    async def _create_chat_completion(self, **kwargs: Any) -> Any:
-        stream = bool(kwargs.get("stream"))
-        result = await asyncio.to_thread(self._sync.chat.completions.create, **kwargs)
-        if not stream:
-            return result
-
-        async def _async_stream() -> Any:
-            while True:
-                done, chunk = await asyncio.to_thread(self._sync._advance_stream_iterator, result)
-                if done:
-                    break
-                yield chunk
-
-        return _async_stream()
-
-    async def close(self) -> None:
-        await asyncio.to_thread(self._sync.close)
--- a/agent/gemini_schema.py
+++ b/agent/gemini_schema.py
@@ -1,85 +0,0 @@
-"""Helpers for translating OpenAI-style tool schemas to Gemini's schema subset."""
-
-from __future__ import annotations
-
-from typing import Any, Dict, List
-
-# Gemini's ``FunctionDeclaration.parameters`` field accepts the ``Schema``
-# object, which is only a subset of OpenAPI 3.0 / JSON Schema.  Strip fields
-# outside that subset before sending Hermes tool schemas to Google.
-_GEMINI_SCHEMA_ALLOWED_KEYS = {
-    "type",
-    "format",
-    "title",
-    "description",
-    "nullable",
-    "enum",
-    "maxItems",
-    "minItems",
-    "properties",
-    "required",
-    "minProperties",
-    "maxProperties",
-    "minLength",
-    "maxLength",
-    "pattern",
-    "example",
-    "anyOf",
-    "propertyOrdering",
-    "default",
-    "items",
-    "minimum",
-    "maximum",
-}
-
-
-def sanitize_gemini_schema(schema: Any) -> Dict[str, Any]:
-    """Return a Gemini-compatible copy of a tool parameter schema.
-
-    Hermes tool schemas are OpenAI-flavored JSON Schema and may contain keys
-    such as ``$schema`` or ``additionalProperties`` that Google's Gemini
-    ``Schema`` object rejects.  This helper preserves the documented Gemini
-    subset and recursively sanitizes nested ``properties`` / ``items`` /
-    ``anyOf`` definitions.
-    """
-
-    if not isinstance(schema, dict):
-        return {}
-
-    cleaned: Dict[str, Any] = {}
-    for key, value in schema.items():
-        if key not in _GEMINI_SCHEMA_ALLOWED_KEYS:
-            continue
-        if key == "properties":
-            if not isinstance(value, dict):
-                continue
-            props: Dict[str, Any] = {}
-            for prop_name, prop_schema in value.items():
-                if not isinstance(prop_name, str):
-                    continue
-                props[prop_name] = sanitize_gemini_schema(prop_schema)
-            cleaned[key] = props
-            continue
-        if key == "items":
-            cleaned[key] = sanitize_gemini_schema(value)
-            continue
-        if key == "anyOf":
-            if not isinstance(value, list):
-                continue
-            cleaned[key] = [
-                sanitize_gemini_schema(item)
-                for item in value
-                if isinstance(item, dict)
-            ]
-            continue
-        cleaned[key] = value
-    return cleaned
-
-
-def sanitize_gemini_tool_parameters(parameters: Any) -> Dict[str, Any]:
-    """Normalize tool parameters to a valid Gemini object schema."""
-
-    cleaned = sanitize_gemini_schema(parameters)
-    if not cleaned:
-        return {"type": "object", "properties": {}}
-    return cleaned
--- a/agent/google_code_assist.py
+++ b/agent/google_code_assist.py
@@ -1,453 +0,0 @@
-"""Google Code Assist API client — project discovery, onboarding, quota.
-
-The Code Assist API powers Google's official gemini-cli. It sits at
-``cloudcode-pa.googleapis.com`` and provides:
-
- Free tier access (generous daily quota) for personal Google accounts
- Paid tier access via GCP projects with billing / Workspace / Standard / Enterprise
-
-This module handles the control-plane dance needed before inference:
-
-1. ``load_code_assist()`` — probe the user's account to learn what tier they're on
-   and whether a ``cloudaicompanionProject`` is already assigned.
-2. ``onboard_user()`` — if the user hasn't been onboarded yet (new account, fresh
-   free tier, etc.), call this with the chosen tier + project id. Supports LRO
-   polling for slow provisioning.
-3. ``retrieve_user_quota()`` — fetch the ``buckets[]`` array showing remaining
-   quota per model, used by the ``/gquota`` slash command.
-
-VPC-SC handling: enterprise accounts under a VPC Service Controls perimeter
-will get ``SECURITY_POLICY_VIOLATED`` on ``load_code_assist``. We catch this
-and force the account to ``standard-tier`` so the call chain still succeeds.
-
-Derived from opencode-gemini-auth (MIT) and clawdbot/extensions/google. The
-request/response shapes are specific to Google's internal Code Assist API,
-documented nowhere public — we copy them from the reference implementations.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import time
-import urllib.error
-import urllib.parse
-import urllib.request
-import uuid
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-logger = logging.getLogger(__name__)
-
-
-# =============================================================================
-# Constants
-# =============================================================================
-
-CODE_ASSIST_ENDPOINT = "https://cloudcode-pa.googleapis.com"
-
-# Fallback endpoints tried when prod returns an error during project discovery
-FALLBACK_ENDPOINTS = [
-    "https://daily-cloudcode-pa.sandbox.googleapis.com",
-    "https://autopush-cloudcode-pa.sandbox.googleapis.com",
-]
-
-# Tier identifiers that Google's API uses
-FREE_TIER_ID = "free-tier"
-LEGACY_TIER_ID = "legacy-tier"
-STANDARD_TIER_ID = "standard-tier"
-
-# Default HTTP headers matching gemini-cli's fingerprint.
-# Google may reject unrecognized User-Agents on these internal endpoints.
-_GEMINI_CLI_USER_AGENT = "google-api-nodejs-client/9.15.1 (gzip)"
-_X_GOOG_API_CLIENT = "gl-node/24.0.0"
-_DEFAULT_REQUEST_TIMEOUT = 30.0
-_ONBOARDING_POLL_ATTEMPTS = 12
-_ONBOARDING_POLL_INTERVAL_SECONDS = 5.0
-
-
-class CodeAssistError(RuntimeError):
-    """Exception raised by the Code Assist (``cloudcode-pa``) integration.
-
-    Carries HTTP status / response / retry-after metadata so the agent's
-    ``error_classifier._extract_status_code`` and the main loop's Retry-After
-    handling (which walks ``error.response.headers``) pick up the right
-    signals.  Without these, 429s from the OAuth path look like opaque
-    ``RuntimeError`` and skip the rate-limit path.
-    """
-
-    def __init__(
-        self,
-        message: str,
-        *,
-        code: str = "code_assist_error",
-        status_code: Optional[int] = None,
-        response: Any = None,
-        retry_after: Optional[float] = None,
-        details: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        super().__init__(message)
-        self.code = code
-        # ``status_code`` is picked up by ``agent.error_classifier._extract_status_code``
-        # so a 429 from Code Assist classifies as FailoverReason.rate_limit and
-        # triggers the main loop's fallback_providers chain the same way SDK
-        # errors do.
-        self.status_code = status_code
-        # ``response`` is the underlying ``httpx.Response`` (or a shim with a
-        # ``.headers`` mapping and ``.json()`` method).  The main loop reads
-        # ``error.response.headers["Retry-After"]`` to honor Google's retry
-        # hints when the backend throttles us.
-        self.response = response
-        # Parsed ``Retry-After`` seconds (kept separately for convenience —
-        # Google returns retry hints in both the header and the error body's
-        # ``google.rpc.RetryInfo`` details, and we pick whichever we found).
-        self.retry_after = retry_after
-        # Parsed structured error details from the Google error envelope
-        # (e.g. ``{"reason": "MODEL_CAPACITY_EXHAUSTED", "status": "RESOURCE_EXHAUSTED"}``).
-        # Useful for logging and for tests that want to assert on specifics.
-        self.details = details or {}
-
-
-class ProjectIdRequiredError(CodeAssistError):
-    def __init__(self, message: str = "GCP project id required for this tier") -> None:
-        super().__init__(message, code="code_assist_project_id_required")
-
-
-# =============================================================================
-# HTTP primitive (auth via Bearer token passed per-call)
-# =============================================================================
-
-def _build_headers(access_token: str, *, user_agent_model: str = "") -> Dict[str, str]:
-    ua = _GEMINI_CLI_USER_AGENT
-    if user_agent_model:
-        ua = f"{ua} model/{user_agent_model}"
-    return {
-        "Content-Type": "application/json",
-        "Accept": "application/json",
-        "Authorization": f"Bearer {access_token}",
-        "User-Agent": ua,
-        "X-Goog-Api-Client": _X_GOOG_API_CLIENT,
-        "x-activity-request-id": str(uuid.uuid4()),
-    }
-
-
-def _client_metadata() -> Dict[str, str]:
-    """Match Google's gemini-cli exactly — unrecognized metadata may be rejected."""
-    return {
-        "ideType": "IDE_UNSPECIFIED",
-        "platform": "PLATFORM_UNSPECIFIED",
-        "pluginType": "GEMINI",
-    }
-
-
-def _post_json(
-    url: str,
-    body: Dict[str, Any],
-    access_token: str,
-    *,
-    timeout: float = _DEFAULT_REQUEST_TIMEOUT,
-    user_agent_model: str = "",
-) -> Dict[str, Any]:
-    data = json.dumps(body).encode("utf-8")
-    request = urllib.request.Request(
-        url, data=data, method="POST",
-        headers=_build_headers(access_token, user_agent_model=user_agent_model),
-    )
-    try:
-        with urllib.request.urlopen(request, timeout=timeout) as response:
-            raw = response.read().decode("utf-8", errors="replace")
-            return json.loads(raw) if raw else {}
-    except urllib.error.HTTPError as exc:
-        detail = ""
-        try:
-            detail = exc.read().decode("utf-8", errors="replace")
-        except Exception:
-            pass
-        # Special case: VPC-SC violation should be distinguishable
-        if _is_vpc_sc_violation(detail):
-            raise CodeAssistError(
-                f"VPC-SC policy violation: {detail}",
-                code="code_assist_vpc_sc",
-            ) from exc
-        raise CodeAssistError(
-            f"Code Assist HTTP {exc.code}: {detail or exc.reason}",
-            code=f"code_assist_http_{exc.code}",
-        ) from exc
-    except urllib.error.URLError as exc:
-        raise CodeAssistError(
-            f"Code Assist request failed: {exc}",
-            code="code_assist_network_error",
-        ) from exc
-
-
-def _is_vpc_sc_violation(body: str) -> bool:
-    """Detect a VPC Service Controls violation from a response body."""
-    if not body:
-        return False
-    try:
-        parsed = json.loads(body)
-    except (json.JSONDecodeError, ValueError):
-        return "SECURITY_POLICY_VIOLATED" in body
-    # Walk the nested error structure Google uses
-    error = parsed.get("error") if isinstance(parsed, dict) else None
-    if not isinstance(error, dict):
-        return False
-    details = error.get("details") or []
-    if isinstance(details, list):
-        for item in details:
-            if isinstance(item, dict):
-                reason = item.get("reason") or ""
-                if reason == "SECURITY_POLICY_VIOLATED":
-                    return True
-    msg = str(error.get("message", ""))
-    return "SECURITY_POLICY_VIOLATED" in msg
-
-
-# =============================================================================
-# load_code_assist — discovers current tier + assigned project
-# =============================================================================
-
-@dataclass
-class CodeAssistProjectInfo:
-    """Result from ``load_code_assist``."""
-    current_tier_id: str = ""
-    cloudaicompanion_project: str = ""   # Google-managed project (free tier)
-    allowed_tiers: List[str] = field(default_factory=list)
-    raw: Dict[str, Any] = field(default_factory=dict)
-
-
-def load_code_assist(
-    access_token: str,
-    *,
-    project_id: str = "",
-    user_agent_model: str = "",
-) -> CodeAssistProjectInfo:
-    """Call ``POST /v1internal:loadCodeAssist`` with prod → sandbox fallback.
-
-    Returns whatever tier + project info Google reports. On VPC-SC violations,
-    returns a synthetic ``standard-tier`` result so the chain can continue.
-    """
-    body: Dict[str, Any] = {
-        "metadata": {
-            "duetProject": project_id,
-            **_client_metadata(),
-        },
-    }
-    if project_id:
-        body["cloudaicompanionProject"] = project_id
-
-    endpoints = [CODE_ASSIST_ENDPOINT] + FALLBACK_ENDPOINTS
-    last_err: Optional[Exception] = None
-    for endpoint in endpoints:
-        url = f"{endpoint}/v1internal:loadCodeAssist"
-        try:
-            resp = _post_json(url, body, access_token, user_agent_model=user_agent_model)
-            return _parse_load_response(resp)
-        except CodeAssistError as exc:
-            if exc.code == "code_assist_vpc_sc":
-                logger.info("VPC-SC violation on %s — defaulting to standard-tier", endpoint)
-                return CodeAssistProjectInfo(
-                    current_tier_id=STANDARD_TIER_ID,
-                    cloudaicompanion_project=project_id,
-                )
-            last_err = exc
-            logger.warning("loadCodeAssist failed on %s: %s", endpoint, exc)
-            continue
-    if last_err:
-        raise last_err
-    return CodeAssistProjectInfo()
-
-
-def _parse_load_response(resp: Dict[str, Any]) -> CodeAssistProjectInfo:
-    current_tier = resp.get("currentTier") or {}
-    tier_id = str(current_tier.get("id") or "") if isinstance(current_tier, dict) else ""
-    project = str(resp.get("cloudaicompanionProject") or "")
-    allowed = resp.get("allowedTiers") or []
-    allowed_ids: List[str] = []
-    if isinstance(allowed, list):
-        for t in allowed:
-            if isinstance(t, dict):
-                tid = str(t.get("id") or "")
-                if tid:
-                    allowed_ids.append(tid)
-    return CodeAssistProjectInfo(
-        current_tier_id=tier_id,
-        cloudaicompanion_project=project,
-        allowed_tiers=allowed_ids,
-        raw=resp,
-    )
-
-
-# =============================================================================
-# onboard_user — provisions a new user on a tier (with LRO polling)
-# =============================================================================
-
-def onboard_user(
-    access_token: str,
-    *,
-    tier_id: str,
-    project_id: str = "",
-    user_agent_model: str = "",
-) -> Dict[str, Any]:
-    """Call ``POST /v1internal:onboardUser`` to provision the user.
-
-    For paid tiers, ``project_id`` is REQUIRED (raises ProjectIdRequiredError).
-    For free tiers, ``project_id`` is optional — Google will assign one.
-
-    Returns the final operation response. Polls ``/v1internal/<name>`` for up
-    to ``_ONBOARDING_POLL_ATTEMPTS`` × ``_ONBOARDING_POLL_INTERVAL_SECONDS``
-    (default: 12 × 5s = 1 min).
-    """
-    if tier_id != FREE_TIER_ID and tier_id != LEGACY_TIER_ID and not project_id:
-        raise ProjectIdRequiredError(
-            f"Tier {tier_id!r} requires a GCP project id. "
-            "Set HERMES_GEMINI_PROJECT_ID or GOOGLE_CLOUD_PROJECT."
-        )
-
-    body: Dict[str, Any] = {
-        "tierId": tier_id,
-        "metadata": _client_metadata(),
-    }
-    if project_id:
-        body["cloudaicompanionProject"] = project_id
-
-    endpoint = CODE_ASSIST_ENDPOINT
-    url = f"{endpoint}/v1internal:onboardUser"
-    resp = _post_json(url, body, access_token, user_agent_model=user_agent_model)
-
-    # Poll if LRO (long-running operation)
-    if not resp.get("done"):
-        op_name = resp.get("name", "")
-        if not op_name:
-            return resp
-        for attempt in range(_ONBOARDING_POLL_ATTEMPTS):
-            time.sleep(_ONBOARDING_POLL_INTERVAL_SECONDS)
-            poll_url = f"{endpoint}/v1internal/{op_name}"
-            try:
-                poll_resp = _post_json(poll_url, {}, access_token, user_agent_model=user_agent_model)
-            except CodeAssistError as exc:
-                logger.warning("Onboarding poll attempt %d failed: %s", attempt + 1, exc)
-                continue
-            if poll_resp.get("done"):
-                return poll_resp
-        logger.warning("Onboarding did not complete within %d attempts", _ONBOARDING_POLL_ATTEMPTS)
-    return resp
-
-
-# =============================================================================
-# retrieve_user_quota — for /gquota
-# =============================================================================
-
-@dataclass
-class QuotaBucket:
-    model_id: str
-    token_type: str = ""
-    remaining_fraction: float = 0.0
-    reset_time_iso: str = ""
-    raw: Dict[str, Any] = field(default_factory=dict)
-
-
-def retrieve_user_quota(
-    access_token: str,
-    *,
-    project_id: str = "",
-    user_agent_model: str = "",
-) -> List[QuotaBucket]:
-    """Call ``POST /v1internal:retrieveUserQuota`` and parse ``buckets[]``."""
-    body: Dict[str, Any] = {}
-    if project_id:
-        body["project"] = project_id
-    url = f"{CODE_ASSIST_ENDPOINT}/v1internal:retrieveUserQuota"
-    resp = _post_json(url, body, access_token, user_agent_model=user_agent_model)
-    raw_buckets = resp.get("buckets") or []
-    buckets: List[QuotaBucket] = []
-    if not isinstance(raw_buckets, list):
-        return buckets
-    for b in raw_buckets:
-        if not isinstance(b, dict):
-            continue
-        buckets.append(QuotaBucket(
-            model_id=str(b.get("modelId") or ""),
-            token_type=str(b.get("tokenType") or ""),
-            remaining_fraction=float(b.get("remainingFraction") or 0.0),
-            reset_time_iso=str(b.get("resetTime") or ""),
-            raw=b,
-        ))
-    return buckets
-
-
-# =============================================================================
-# Project context resolution
-# =============================================================================
-
-@dataclass
-class ProjectContext:
-    """Resolved state for a given OAuth session."""
-    project_id: str = ""           # effective project id sent on requests
-    managed_project_id: str = ""   # Google-assigned project (free tier)
-    tier_id: str = ""
-    source: str = ""               # "env", "config", "discovered", "onboarded"
-
-
-def resolve_project_context(
-    access_token: str,
-    *,
-    configured_project_id: str = "",
-    env_project_id: str = "",
-    user_agent_model: str = "",
-) -> ProjectContext:
-    """Figure out what project id + tier to use for requests.
-
-    Priority:
-      1. If configured_project_id or env_project_id is set, use that directly
-         and short-circuit (no discovery needed).
-      2. Otherwise call loadCodeAssist to see what Google says.
-      3. If no tier assigned yet, onboard the user (free tier default).
-    """
-    # Short-circuit: caller provided a project id
-    if configured_project_id:
-        return ProjectContext(
-            project_id=configured_project_id,
-            tier_id=STANDARD_TIER_ID,  # assume paid since they specified one
-            source="config",
-        )
-    if env_project_id:
-        return ProjectContext(
-            project_id=env_project_id,
-            tier_id=STANDARD_TIER_ID,
-            source="env",
-        )
-
-    # Discover via loadCodeAssist
-    info = load_code_assist(access_token, user_agent_model=user_agent_model)
-
-    effective_project = info.cloudaicompanion_project
-    tier = info.current_tier_id
-
-    if not tier:
-        # User hasn't been onboarded — provision them on free tier
-        onboard_resp = onboard_user(
-            access_token,
-            tier_id=FREE_TIER_ID,
-            project_id="",
-            user_agent_model=user_agent_model,
-        )
-        # Re-parse from the onboard response
-        response_body = onboard_resp.get("response") or {}
-        if isinstance(response_body, dict):
-            effective_project = (
-                effective_project
-                or str(response_body.get("cloudaicompanionProject") or "")
-            )
-        tier = FREE_TIER_ID
-        source = "onboarded"
-    else:
-        source = "discovered"
-
-    return ProjectContext(
-        project_id=effective_project,
-        managed_project_id=effective_project if tier == FREE_TIER_ID else "",
-        tier_id=tier,
-        source=source,
-    )
--- a/agent/google_oauth.py
+++ b/agent/google_oauth.py
--- a/agent/image_gen_provider.py
+++ b/agent/image_gen_provider.py
@@ -1,242 +0,0 @@
-"""
-Image Generation Provider ABC
-=============================
-
-Defines the pluggable-backend interface for image generation. Providers register
-instances via ``PluginContext.register_image_gen_provider()``; the active one
-(selected via ``image_gen.provider`` in ``config.yaml``) services every
-``image_generate`` tool call.
-
-Providers live in ``<repo>/plugins/image_gen/<name>/`` (built-in, auto-loaded
-as ``kind: backend``) or ``~/.hermes/plugins/image_gen/<name>/`` (user, opt-in
-via ``plugins.enabled``).
-
-Response shape
--------------
-All providers return a dict that :func:`success_response` / :func:`error_response`
-produce. The tool wrapper JSON-serializes it. Keys:
-
-    success        bool
-    image          str | None       URL or absolute file path
-    model          str              provider-specific model identifier
-    prompt         str              echoed prompt
-    aspect_ratio   str              "landscape" | "square" | "portrait"
-    provider       str              provider name (for diagnostics)
-    error          str              only when success=False
-    error_type     str              only when success=False
-"""
-
-from __future__ import annotations
-
-import abc
-import base64
-import datetime
-import logging
-import uuid
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-
-VALID_ASPECT_RATIOS: Tuple[str, ...] = ("landscape", "square", "portrait")
-DEFAULT_ASPECT_RATIO = "landscape"
-
-
-# ---------------------------------------------------------------------------
-# ABC
-# ---------------------------------------------------------------------------
-
-
-class ImageGenProvider(abc.ABC):
-    """Abstract base class for an image generation backend.
-
-    Subclasses must implement :meth:`generate`. Everything else has sane
-    defaults — override only what your provider needs.
-    """
-
-    @property
-    @abc.abstractmethod
-    def name(self) -> str:
-        """Stable short identifier used in ``image_gen.provider`` config.
-
-        Lowercase, no spaces. Examples: ``fal``, ``openai``, ``replicate``.
-        """
-
-    @property
-    def display_name(self) -> str:
-        """Human-readable label shown in ``hermes tools``. Defaults to ``name.title()``."""
-        return self.name.title()
-
-    def is_available(self) -> bool:
-        """Return True when this provider can service calls.
-
-        Typically checks for a required API key. Default: True
-        (providers with no external dependencies are always available).
-        """
-        return True
-
-    def list_models(self) -> List[Dict[str, Any]]:
-        """Return catalog entries for ``hermes tools`` model picker.
-
-        Each entry::
-
-            {
-                "id": "gpt-image-1.5",               # required
-                "display": "GPT Image 1.5",          # optional; defaults to id
-                "speed": "~10s",                     # optional
-                "strengths": "...",                  # optional
-                "price": "$...",                     # optional
-            }
-
-        Default: empty list (provider has no user-selectable models).
-        """
-        return []
-
-    def get_setup_schema(self) -> Dict[str, Any]:
-        """Return provider metadata for the ``hermes tools`` picker.
-
-        Used by ``tools_config.py`` to inject this provider as a row in
-        the Image Generation provider list. Shape::
-
-            {
-                "name": "OpenAI",                     # picker label
-                "badge": "paid",                      # optional short tag
-                "tag": "One-line description...",     # optional subtitle
-                "env_vars": [                         # keys to prompt for
-                    {"key": "OPENAI_API_KEY",
-                     "prompt": "OpenAI API key",
-                     "url": "https://platform.openai.com/api-keys"},
-                ],
-            }
-
-        Default: minimal entry derived from ``display_name``. Override to
-        expose API key prompts and custom badges.
-        """
-        return {
-            "name": self.display_name,
-            "badge": "",
-            "tag": "",
-            "env_vars": [],
-        }
-
-    def default_model(self) -> Optional[str]:
-        """Return the default model id, or None if not applicable."""
-        models = self.list_models()
-        if models:
-            return models[0].get("id")
-        return None
-
-    @abc.abstractmethod
-    def generate(
-        self,
-        prompt: str,
-        aspect_ratio: str = DEFAULT_ASPECT_RATIO,
-        **kwargs: Any,
-    ) -> Dict[str, Any]:
-        """Generate an image.
-
-        Implementations should return the dict from :func:`success_response`
-        or :func:`error_response`. ``kwargs`` may contain forward-compat
-        parameters future versions of the schema will expose — implementations
-        should ignore unknown keys.
-        """
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def resolve_aspect_ratio(value: Optional[str]) -> str:
-    """Clamp an aspect_ratio value to the valid set, defaulting to landscape.
-
-    Invalid values are coerced rather than rejected so the tool surface is
-    forgiving of agent mistakes.
-    """
-    if not isinstance(value, str):
-        return DEFAULT_ASPECT_RATIO
-    v = value.strip().lower()
-    if v in VALID_ASPECT_RATIOS:
-        return v
-    return DEFAULT_ASPECT_RATIO
-
-
-def _images_cache_dir() -> Path:
-    """Return ``$HERMES_HOME/cache/images/``, creating parents as needed."""
-    from hermes_constants import get_hermes_home
-
-    path = get_hermes_home() / "cache" / "images"
-    path.mkdir(parents=True, exist_ok=True)
-    return path
-
-
-def save_b64_image(
-    b64_data: str,
-    *,
-    prefix: str = "image",
-    extension: str = "png",
-) -> Path:
-    """Decode base64 image data and write it under ``$HERMES_HOME/cache/images/``.
-
-    Returns the absolute :class:`Path` to the saved file.
-
-    Filename format: ``<prefix>_<YYYYMMDD_HHMMSS>_<short-uuid>.<ext>``.
-    """
-    raw = base64.b64decode(b64_data)
-    ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
-    short = uuid.uuid4().hex[:8]
-    path = _images_cache_dir() / f"{prefix}_{ts}_{short}.{extension}"
-    path.write_bytes(raw)
-    return path
-
-
-def success_response(
-    *,
-    image: str,
-    model: str,
-    prompt: str,
-    aspect_ratio: str,
-    provider: str,
-    extra: Optional[Dict[str, Any]] = None,
-) -> Dict[str, Any]:
-    """Build a uniform success response dict.
-
-    ``image`` may be an HTTP URL or an absolute filesystem path (for b64
-    providers like OpenAI). Callers that need to pass through additional
-    backend-specific fields can supply ``extra``.
-    """
-    payload: Dict[str, Any] = {
-        "success": True,
-        "image": image,
-        "model": model,
-        "prompt": prompt,
-        "aspect_ratio": aspect_ratio,
-        "provider": provider,
-    }
-    if extra:
-        for k, v in extra.items():
-            payload.setdefault(k, v)
-    return payload
-
-
-def error_response(
-    *,
-    error: str,
-    error_type: str = "provider_error",
-    provider: str = "",
-    model: str = "",
-    prompt: str = "",
-    aspect_ratio: str = DEFAULT_ASPECT_RATIO,
-) -> Dict[str, Any]:
-    """Build a uniform error response dict."""
-    return {
-        "success": False,
-        "image": None,
-        "error": error,
-        "error_type": error_type,
-        "model": model,
-        "prompt": prompt,
-        "aspect_ratio": aspect_ratio,
-        "provider": provider,
-    }
--- a/agent/image_gen_registry.py
+++ b/agent/image_gen_registry.py
@@ -1,120 +0,0 @@
-"""
-Image Generation Provider Registry
-==================================
-
-Central map of registered providers. Populated by plugins at import-time via
-``PluginContext.register_image_gen_provider()``; consumed by the
-``image_generate`` tool to dispatch each call to the active backend.
-
-Active selection
----------------
-The active provider is chosen by ``image_gen.provider`` in ``config.yaml``.
-If unset, :func:`get_active_provider` applies fallback logic:
-
-1. If exactly one provider is registered, use it.
-2. Otherwise if a provider named ``fal`` is registered, use it (legacy
-   default — matches pre-plugin behavior).
-3. Otherwise return ``None`` (the tool surfaces a helpful error pointing
-   the user at ``hermes tools``).
-"""
-
-from __future__ import annotations
-
-import logging
-import threading
-from typing import Dict, List, Optional
-
-from agent.image_gen_provider import ImageGenProvider
-
-logger = logging.getLogger(__name__)
-
-
-_providers: Dict[str, ImageGenProvider] = {}
-_lock = threading.Lock()
-
-
-def register_provider(provider: ImageGenProvider) -> None:
-    """Register an image generation provider.
-
-    Re-registration (same ``name``) overwrites the previous entry and logs
-    a debug message — this makes hot-reload scenarios (tests, dev loops)
-    behave predictably.
-    """
-    if not isinstance(provider, ImageGenProvider):
-        raise TypeError(
-            f"register_provider() expects an ImageGenProvider instance, "
-            f"got {type(provider).__name__}"
-        )
-    name = provider.name
-    if not isinstance(name, str) or not name.strip():
-        raise ValueError("Image gen provider .name must be a non-empty string")
-    with _lock:
-        existing = _providers.get(name)
-        _providers[name] = provider
-    if existing is not None:
-        logger.debug("Image gen provider '%s' re-registered (was %r)", name, type(existing).__name__)
-    else:
-        logger.debug("Registered image gen provider '%s' (%s)", name, type(provider).__name__)
-
-
-def list_providers() -> List[ImageGenProvider]:
-    """Return all registered providers, sorted by name."""
-    with _lock:
-        items = list(_providers.values())
-    return sorted(items, key=lambda p: p.name)
-
-
-def get_provider(name: str) -> Optional[ImageGenProvider]:
-    """Return the provider registered under *name*, or None."""
-    if not isinstance(name, str):
-        return None
-    with _lock:
-        return _providers.get(name.strip())
-
-
-def get_active_provider() -> Optional[ImageGenProvider]:
-    """Resolve the currently-active provider.
-
-    Reads ``image_gen.provider`` from config.yaml; falls back per the
-    module docstring.
-    """
-    configured: Optional[str] = None
-    try:
-        from hermes_cli.config import load_config
-
-        cfg = load_config()
-        section = cfg.get("image_gen") if isinstance(cfg, dict) else None
-        if isinstance(section, dict):
-            raw = section.get("provider")
-            if isinstance(raw, str) and raw.strip():
-                configured = raw.strip()
-    except Exception as exc:
-        logger.debug("Could not read image_gen.provider from config: %s", exc)
-
-    with _lock:
-        snapshot = dict(_providers)
-
-    if configured:
-        provider = snapshot.get(configured)
-        if provider is not None:
-            return provider
-        logger.debug(
-            "image_gen.provider='%s' configured but not registered; falling back",
-            configured,
-        )
-
-    # Fallback: single-provider case
-    if len(snapshot) == 1:
-        return next(iter(snapshot.values()))
-
-    # Fallback: prefer legacy FAL for backward compat
-    if "fal" in snapshot:
-        return snapshot["fal"]
-
-    return None
-
-
-def _reset_for_tests() -> None:
-    """Clear the registry. **Test-only.**"""
-    with _lock:
-        _providers.clear()
--- a/agent/insights.py
+++ b/agent/insights.py
@@ -27,6 +27,7 @@ from agent.usage_pricing import (
    DEFAULT_PRICING,
    estimate_usage_cost,
    format_duration_compact,
+    get_pricing,
    has_known_pricing,
 )

@@ -124,7 +125,6 @@ class InsightsEngine:
        # Gather raw data
        sessions = self._get_sessions(cutoff, source)
        tool_usage = self._get_tool_usage(cutoff, source)
-        skill_usage = self._get_skill_usage(cutoff, source)
        message_stats = self._get_message_stats(cutoff, source)

        if not sessions:
@@ -136,15 +136,6 @@ class InsightsEngine:
                "models": [],
                "platforms": [],
                "tools": [],
-                "skills": {
-                    "summary": {
-                        "total_skill_loads": 0,
-                        "total_skill_edits": 0,
-                        "total_skill_actions": 0,
-                        "distinct_skills_used": 0,
-                    },
-                    "top_skills": [],
-                },
                "activity": {},
                "top_sessions": [],
            }
@@ -154,7 +145,6 @@ class InsightsEngine:
        models = self._compute_model_breakdown(sessions)
        platforms = self._compute_platform_breakdown(sessions)
        tools = self._compute_tool_breakdown(tool_usage)
-        skills = self._compute_skill_breakdown(skill_usage)
        activity = self._compute_activity_patterns(sessions)
        top_sessions = self._compute_top_sessions(sessions)

@@ -167,7 +157,6 @@ class InsightsEngine:
            "models": models,
            "platforms": platforms,
            "tools": tools,
-            "skills": skills,
            "activity": activity,
            "top_sessions": top_sessions,
        }
@@ -296,82 +285,6 @@ class InsightsEngine:
            for name, count in tool_counts.most_common()
        ]

-    def _get_skill_usage(self, cutoff: float, source: str = None) -> List[Dict]:
-        """Extract per-skill usage from assistant tool calls."""
-        skill_counts: Dict[str, Dict[str, Any]] = {}
-
-        if source:
-            cursor = self._conn.execute(
-                """SELECT m.tool_calls, m.timestamp
-                   FROM messages m
-                   JOIN sessions s ON s.id = m.session_id
-                   WHERE s.started_at >= ? AND s.source = ?
-                     AND m.role = 'assistant' AND m.tool_calls IS NOT NULL""",
-                (cutoff, source),
-            )
-        else:
-            cursor = self._conn.execute(
-                """SELECT m.tool_calls, m.timestamp
-                   FROM messages m
-                   JOIN sessions s ON s.id = m.session_id
-                   WHERE s.started_at >= ?
-                     AND m.role = 'assistant' AND m.tool_calls IS NOT NULL""",
-                (cutoff,),
-            )
-
-        for row in cursor.fetchall():
-            try:
-                calls = row["tool_calls"]
-                if isinstance(calls, str):
-                    calls = json.loads(calls)
-                if not isinstance(calls, list):
-                    continue
-            except (json.JSONDecodeError, TypeError):
-                continue
-
-            timestamp = row["timestamp"]
-            for call in calls:
-                if not isinstance(call, dict):
-                    continue
-                func = call.get("function", {})
-                tool_name = func.get("name")
-                if tool_name not in {"skill_view", "skill_manage"}:
-                    continue
-
-                args = func.get("arguments")
-                if isinstance(args, str):
-                    try:
-                        args = json.loads(args)
-                    except (json.JSONDecodeError, TypeError):
-                        continue
-                if not isinstance(args, dict):
-                    continue
-
-                skill_name = args.get("name")
-                if not isinstance(skill_name, str) or not skill_name.strip():
-                    continue
-
-                entry = skill_counts.setdefault(
-                    skill_name,
-                    {
-                        "skill": skill_name,
-                        "view_count": 0,
-                        "manage_count": 0,
-                        "last_used_at": None,
-                    },
-                )
-                if tool_name == "skill_view":
-                    entry["view_count"] += 1
-                else:
-                    entry["manage_count"] += 1
-
-                if timestamp is not None and (
-                    entry["last_used_at"] is None or timestamp > entry["last_used_at"]
-                ):
-                    entry["last_used_at"] = timestamp
-
-        return list(skill_counts.values())
-
    def _get_message_stats(self, cutoff: float, source: str = None) -> Dict:
        """Get aggregate message statistics."""
        if source:
@@ -563,46 +476,6 @@ class InsightsEngine:
            })
        return result

-    def _compute_skill_breakdown(self, skill_usage: List[Dict]) -> Dict[str, Any]:
-        """Process per-skill usage into summary + ranked list."""
-        total_skill_loads = sum(s["view_count"] for s in skill_usage) if skill_usage else 0
-        total_skill_edits = sum(s["manage_count"] for s in skill_usage) if skill_usage else 0
-        total_skill_actions = total_skill_loads + total_skill_edits
-
-        top_skills = []
-        for skill in skill_usage:
-            total_count = skill["view_count"] + skill["manage_count"]
-            percentage = (total_count / total_skill_actions * 100) if total_skill_actions else 0
-            top_skills.append({
-                "skill": skill["skill"],
-                "view_count": skill["view_count"],
-                "manage_count": skill["manage_count"],
-                "total_count": total_count,
-                "percentage": percentage,
-                "last_used_at": skill.get("last_used_at"),
-            })
-
-        top_skills.sort(
-            key=lambda s: (
-                s["total_count"],
-                s["view_count"],
-                s["manage_count"],
-                s["last_used_at"] or 0,
-                s["skill"],
-            ),
-            reverse=True,
-        )
-
-        return {
-            "summary": {
-                "total_skill_loads": total_skill_loads,
-                "total_skill_edits": total_skill_edits,
-                "total_skill_actions": total_skill_actions,
-                "distinct_skills_used": len(skill_usage),
-            },
-            "top_skills": top_skills,
-        }
-
    def _compute_activity_patterns(self, sessions: List[Dict]) -> Dict:
        """Analyze activity patterns by day of week and hour."""
        day_counts = Counter()  # 0=Monday ... 6=Sunday
@@ -762,7 +635,13 @@ class InsightsEngine:
        lines.append(f"  Sessions:          {o['total_sessions']:<12}  Messages:        {o['total_messages']:,}")
        lines.append(f"  Tool calls:        {o['total_tool_calls']:<12,}  User messages:   {o['user_messages']:,}")
        lines.append(f"  Input tokens:      {o['total_input_tokens']:<12,}  Output tokens:   {o['total_output_tokens']:,}")
-        lines.append(f"  Total tokens:      {o['total_tokens']:,}")
+        cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
+        if cache_total > 0:
+            lines.append(f"  Cache read:        {o['total_cache_read_tokens']:<12,}  Cache write:     {o['total_cache_write_tokens']:,}")
+        cost_str = f"${o['estimated_cost']:.2f}"
+        if o.get("models_without_pricing"):
+            cost_str += " *"
+        lines.append(f"  Total tokens:      {o['total_tokens']:<12,}  Est. cost:       {cost_str}")
        if o["total_hours"] > 0:
            lines.append(f"  Active time:       ~{_format_duration(o['total_hours'] * 3600):<11}  Avg session:     ~{_format_duration(o['avg_session_duration'])}")
        lines.append(f"  Avg msgs/session:  {o['avg_messages_per_session']:.1f}")
@@ -772,10 +651,16 @@ class InsightsEngine:
        if report["models"]:
            lines.append("  🤖 Models Used")
            lines.append("  " + "─" * 56)
-            lines.append(f"  {'Model':<30} {'Sessions':>8} {'Tokens':>12}")
+            lines.append(f"  {'Model':<30} {'Sessions':>8} {'Tokens':>12} {'Cost':>8}")
            for m in report["models"]:
                model_name = m["model"][:28]
-                lines.append(f"  {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,}")
+                if m.get("has_pricing"):
+                    cost_cell = f"${m['cost']:>6.2f}"
+                else:
+                    cost_cell = "     N/A"
+                lines.append(f"  {model_name:<30} {m['sessions']:>8} {m['total_tokens']:>12,} {cost_cell}")
+            if o.get("models_without_pricing"):
+                lines.append("  * Cost N/A for custom/self-hosted models")
            lines.append("")

        # Platform breakdown
@@ -798,28 +683,6 @@ class InsightsEngine:
                lines.append(f"  ... and {len(report['tools']) - 15} more tools")
            lines.append("")

-        # Skill usage
-        skills = report.get("skills", {})
-        top_skills = skills.get("top_skills", [])
-        if top_skills:
-            lines.append("  🧠 Top Skills")
-            lines.append("  " + "─" * 56)
-            lines.append(f"  {'Skill':<28} {'Loads':>7} {'Edits':>7} {'Last used':>11}")
-            for skill in top_skills[:10]:
-                last_used = "—"
-                if skill.get("last_used_at"):
-                    last_used = datetime.fromtimestamp(skill["last_used_at"]).strftime("%b %d")
-                lines.append(
-                    f"  {skill['skill'][:28]:<28} {skill['view_count']:>7,} {skill['manage_count']:>7,} {last_used:>11}"
-                )
-            summary = skills.get("summary", {})
-            lines.append(
-                f"  Distinct skills: {summary.get('distinct_skills_used', 0)}  "
-                f"Loads: {summary.get('total_skill_loads', 0):,}  "
-                f"Edits: {summary.get('total_skill_edits', 0):,}"
-            )
-            lines.append("")
-
        # Activity patterns
        act = report.get("activity", {})
        if act.get("by_day"):
@@ -877,7 +740,15 @@ class InsightsEngine:

        # Overview
        lines.append(f"**Sessions:** {o['total_sessions']} | **Messages:** {o['total_messages']:,} | **Tool calls:** {o['total_tool_calls']:,}")
-        lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
+        cache_total = o.get("total_cache_read_tokens", 0) + o.get("total_cache_write_tokens", 0)
+        if cache_total > 0:
+            lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,} / cache: {cache_total:,})")
+        else:
+            lines.append(f"**Tokens:** {o['total_tokens']:,} (in: {o['total_input_tokens']:,} / out: {o['total_output_tokens']:,})")
+        cost_note = ""
+        if o.get("models_without_pricing"):
+            cost_note = " _(excludes custom/self-hosted models)_"
+        lines.append(f"**Est. cost:** ${o['estimated_cost']:.2f}{cost_note}")
        if o["total_hours"] > 0:
            lines.append(f"**Active time:** ~{_format_duration(o['total_hours'] * 3600)} | **Avg session:** ~{_format_duration(o['avg_session_duration'])}")
        lines.append("")
@@ -886,7 +757,8 @@ class InsightsEngine:
        if report["models"]:
            lines.append("**🤖 Models:**")
            for m in report["models"][:5]:
-                lines.append(f"  {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens")
+                cost_str = f"${m['cost']:.2f}" if m.get("has_pricing") else "N/A"
+                lines.append(f"  {m['model'][:25]} — {m['sessions']} sessions, {m['total_tokens']:,} tokens, {cost_str}")
            lines.append("")

        # Platforms (if multi-platform)
@@ -903,18 +775,6 @@ class InsightsEngine:
                lines.append(f"  {t['tool']} — {t['count']:,} calls ({t['percentage']:.1f}%)")
            lines.append("")

-        skills = report.get("skills", {})
-        if skills.get("top_skills"):
-            lines.append("**🧠 Top Skills:**")
-            for skill in skills["top_skills"][:5]:
-                suffix = ""
-                if skill.get("last_used_at"):
-                    suffix = f", last used {datetime.fromtimestamp(skill['last_used_at']).strftime('%b %d')}"
-                lines.append(
-                    f"  {skill['skill']} — {skill['view_count']:,} loads, {skill['manage_count']:,} edits{suffix}"
-                )
-            lines.append("")
-
        # Activity summary
        act = report.get("activity", {})
        if act.get("busiest_day") and act.get("busiest_hour"):
--- a/agent/memory_manager.py
+++ b/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:
--- a/agent/model_metadata.py
+++ b/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
@@ -14,8 +15,6 @@ from urllib.parse import urlparse
 import requests
 import yaml

-from utils import base_url_host_matches, base_url_hostname
-
 from hermes_constants import OPENROUTER_MODELS_URL

 logger = logging.getLogger(__name__)
@@ -25,22 +24,17 @@ logger = logging.getLogger(__name__)
 # are preserved so the full model name reaches cache lookups and server queries.
 _PROVIDER_PREFIXES: frozenset[str] = frozenset({
    "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
-    "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "minimax", "minimax-cn", "anthropic", "deepseek",
+    "gemini", "zai", "kimi-coding", "minimax", "minimax-cn", "anthropic", "deepseek",
    "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
    "qwen-oauth",
    "xiaomi",
-    "arcee",
    "custom", "local",
    # Common aliases
    "google", "google-gemini", "google-ai-studio",
    "glm", "z-ai", "z.ai", "zhipu", "github", "github-copilot",
-    "github-models", "kimi", "moonshot", "kimi-cn", "moonshot-cn", "claude", "deep-seek",
-    "ollama",
+    "github-models", "kimi", "moonshot", "claude", "deep-seek",
    "opencode", "zen", "go", "vercel", "kilo", "dashscope", "aliyun", "qwen",
    "mimo", "xiaomi-mimo",
-    "arcee-ai", "arceeai",
-    "xai", "x-ai", "x.ai", "grok",
-    "nvidia", "nim", "nvidia-nim", "nemotron",
    "qwen-portal",
 })

@@ -105,27 +99,21 @@ DEFAULT_CONTEXT_LENGTHS = {
    # fuzzy-match collisions (e.g. "anthropic/claude-sonnet-4" is a
    # substring of "anthropic/claude-sonnet-4.6").
    # OpenRouter-prefixed models resolve via OpenRouter live API or models.dev.
-    "claude-opus-4-7": 1000000,
-    "claude-opus-4.7": 1000000,
    "claude-opus-4-6": 1000000,
    "claude-sonnet-4-6": 1000000,
    "claude-opus-4.6": 1000000,
    "claude-sonnet-4.6": 1000000,
    # Catch-all for older Claude models (must sort after specific entries)
    "claude": 200000,
-    # OpenAI — GPT-5 family (most have 400k; specific overrides first)
-    # Source: https://developers.openai.com/api/docs/models
-    "gpt-5.4-nano": 400000,           # 400k (not 1.05M like full 5.4)
-    "gpt-5.4-mini": 400000,           # 400k (not 1.05M like full 5.4)
-    "gpt-5.4": 1050000,               # GPT-5.4, GPT-5.4 Pro (1.05M context)
-    "gpt-5.1-chat": 128000,           # Chat variant has 128k context
-    "gpt-5": 400000,                  # GPT-5.x base, mini, codex variants (400k)
+    # OpenAI
    "gpt-4.1": 1047576,
+    "gpt-5": 128000,
    "gpt-4": 128000,
    # Google
    "gemini": 1048576,
    # Gemma (open models served via AI Studio)
    "gemma-4-31b": 256000,
+    "gemma-4-26b": 256000,
    "gemma-3": 131072,
    "gemma": 8192,  # fallback for older gemma models
    # DeepSeek
@@ -159,18 +147,13 @@ DEFAULT_CONTEXT_LENGTHS = {
    "grok": 131072,             # catch-all (grok-beta, unknown grok-*)
    # Kimi
    "kimi": 262144,
-    # Nemotron — NVIDIA's open-weights series (128K context across all sizes)
-    "nemotron": 131072,
    # Arcee
    "trinity": 262144,
-    # OpenRouter
-    "elephant": 262144,
    # Hugging Face Inference Providers — model IDs use org/name format
    "Qwen/Qwen3.5-397B-A17B": 131072,
    "Qwen/Qwen3.5-35B-A3B": 131072,
    "deepseek-ai/DeepSeek-V3.2": 65536,
    "moonshotai/Kimi-K2.5": 262144,
-    "moonshotai/Kimi-K2.6": 262144,
    "moonshotai/Kimi-K2-Thinking": 262144,
    "MiniMaxAI/MiniMax-M2.5": 204800,
    "XiaomiMiMo/MiMo-V2-Flash": 256000,
@@ -213,15 +196,8 @@ def _normalize_base_url(base_url: str) -> str:
    return (base_url or "").strip().rstrip("/")


-def _auth_headers(api_key: str = "") -> Dict[str, str]:
-    token = str(api_key or "").strip()
-    if not token:
-        return {}
-    return {"Authorization": f"Bearer {token}"}
-
-
 def _is_openrouter_base_url(base_url: str) -> bool:
-    return base_url_host_matches(base_url, "openrouter.ai")
+    return "openrouter.ai" in _normalize_base_url(base_url).lower()


 def _is_custom_endpoint(base_url: str) -> bool:
@@ -235,9 +211,7 @@ _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",
@@ -251,10 +225,8 @@ _URL_TO_PROVIDER: Dict[str, str] = {
    "api.fireworks.ai": "fireworks",
    "opencode.ai": "opencode-go",
    "api.x.ai": "xai",
-    "integrate.api.nvidia.com": "nvidia",
    "api.xiaomimimo.com": "xiaomi",
    "xiaomimimo.com": "xiaomi",
-    "ollama.com": "ollama-cloud",
 }


@@ -319,7 +291,7 @@ def is_local_endpoint(base_url: str) -> bool:
    return False


-def detect_local_server_type(base_url: str, api_key: str = "") -> Optional[str]:
+def detect_local_server_type(base_url: str) -> Optional[str]:
    """Detect which local server is running at base_url by probing known endpoints.

    Returns one of: "ollama", "lm-studio", "vllm", "llamacpp", or None.
@@ -331,10 +303,8 @@ def detect_local_server_type(base_url: str, api_key: str = "") -> Optional[str]:
    if server_url.endswith("/v1"):
        server_url = server_url[:-3]

-    headers = _auth_headers(api_key)
-
    try:
-        with httpx.Client(timeout=2.0, headers=headers) as client:
+        with httpx.Client(timeout=2.0) as client:
            # LM Studio exposes /api/v1/models — check first (most specific)
            try:
                r = client.get(f"{server_url}/api/v1/models")
@@ -521,59 +491,6 @@ def fetch_endpoint_model_metadata(
    headers = {"Authorization": f"Bearer {api_key}"} if api_key else {}
    last_error: Optional[Exception] = None

-    if is_local_endpoint(normalized):
-        try:
-            if detect_local_server_type(normalized, api_key=api_key) == "lm-studio":
-                server_url = normalized[:-3].rstrip("/") if normalized.endswith("/v1") else normalized
-                response = requests.get(
-                    server_url.rstrip("/") + "/api/v1/models",
-                    headers=headers,
-                    timeout=10,
-                )
-                response.raise_for_status()
-                payload = response.json()
-                cache: Dict[str, Dict[str, Any]] = {}
-                for model in payload.get("models", []):
-                    if not isinstance(model, dict):
-                        continue
-                    model_id = model.get("key") or model.get("id")
-                    if not model_id:
-                        continue
-                    entry: Dict[str, Any] = {"name": model.get("name", model_id)}
-
-                    context_length = None
-                    for inst in model.get("loaded_instances", []) or []:
-                        if not isinstance(inst, dict):
-                            continue
-                        cfg = inst.get("config", {})
-                        ctx = cfg.get("context_length") if isinstance(cfg, dict) else None
-                        if isinstance(ctx, int) and ctx > 0:
-                            context_length = ctx
-                            break
-                    if context_length is None:
-                        context_length = _extract_context_length(model)
-                    if context_length is not None:
-                        entry["context_length"] = context_length
-
-                    max_completion_tokens = _extract_max_completion_tokens(model)
-                    if max_completion_tokens is not None:
-                        entry["max_completion_tokens"] = max_completion_tokens
-
-                    pricing = _extract_pricing(model)
-                    if pricing:
-                        entry["pricing"] = pricing
-
-                    _add_model_aliases(cache, model_id, entry)
-                    alt_id = model.get("id")
-                    if isinstance(alt_id, str) and alt_id and alt_id != model_id:
-                        _add_model_aliases(cache, alt_id, entry)
-
-                _endpoint_model_metadata_cache[normalized] = cache
-                _endpoint_model_metadata_cache_time[normalized] = time.time()
-                return cache
-        except Exception as exc:
-            last_error = exc
-
    for candidate in candidates:
        url = candidate.rstrip("/") + "/models"
        try:
@@ -780,7 +697,7 @@ def _model_id_matches(candidate_id: str, lookup_model: str) -> bool:
    return False


-def query_ollama_num_ctx(model: str, base_url: str, api_key: str = "") -> Optional[int]:
+def query_ollama_num_ctx(model: str, base_url: str) -> Optional[int]:
    """Query an Ollama server for the model's context length.

    Returns the model's maximum context from GGUF metadata via ``/api/show``,
@@ -798,16 +715,14 @@ def query_ollama_num_ctx(model: str, base_url: str, api_key: str = "") -> Option
        server_url = server_url[:-3]

    try:
-        server_type = detect_local_server_type(base_url, api_key=api_key)
+        server_type = detect_local_server_type(base_url)
    except Exception:
        return None
    if server_type != "ollama":
        return None

-    headers = _auth_headers(api_key)
-
    try:
-        with httpx.Client(timeout=3.0, headers=headers) as client:
+        with httpx.Client(timeout=3.0) as client:
            resp = client.post(f"{server_url}/api/show", json={"name": bare_model})
            if resp.status_code != 200:
                return None
@@ -835,7 +750,7 @@ def query_ollama_num_ctx(model: str, base_url: str, api_key: str = "") -> Option
    return None


-def _query_local_context_length(model: str, base_url: str, api_key: str = "") -> Optional[int]:
+def _query_local_context_length(model: str, base_url: str) -> Optional[int]:
    """Query a local server for the model's context length."""
    import httpx

@@ -848,26 +763,24 @@ def _query_local_context_length(model: str, base_url: str, api_key: str = "") ->
    if server_url.endswith("/v1"):
        server_url = server_url[:-3]

-    headers = _auth_headers(api_key)
-
    try:
-        server_type = detect_local_server_type(base_url, api_key=api_key)
+        server_type = detect_local_server_type(base_url)
    except Exception:
        server_type = None

    try:
-        with httpx.Client(timeout=3.0, headers=headers) as client:
+        with httpx.Client(timeout=3.0) as client:
            # Ollama: /api/show returns model details with context info
            if server_type == "ollama":
                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"):
@@ -878,11 +791,6 @@ def _query_local_context_length(model: str, base_url: str, api_key: str = "") ->
                                        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
@@ -1067,7 +975,7 @@ def get_model_context_length(
        if not _is_known_provider_base_url(base_url):
            # 3. Try querying local server directly
            if is_local_endpoint(base_url):
-                local_ctx = _query_local_context_length(model, base_url, api_key=api_key)
+                local_ctx = _query_local_context_length(model, base_url)
                if local_ctx and local_ctx > 0:
                    save_context_length(model, base_url, local_ctx)
                    return local_ctx
@@ -1081,26 +989,12 @@ def get_model_context_length(

    # 4. Anthropic /v1/models API (only for regular API keys, not OAuth)
    if provider == "anthropic" or (
-        base_url and base_url_hostname(base_url) == "api.anthropic.com"
+        base_url and "api.anthropic.com" in base_url
    ):
        ctx = _query_anthropic_context_length(model, base_url or "https://api.anthropic.com", api_key)
        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 base_url_hostname(base_url).startswith("bedrock-runtime.")
-        and base_url_host_matches(base_url, "amazonaws.com")
-    ):
-        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
@@ -1141,7 +1035,7 @@ def get_model_context_length(

    # 9. Query local server as last resort
    if base_url and is_local_endpoint(base_url):
-        local_ctx = _query_local_context_length(model, base_url, api_key=api_key)
+        local_ctx = _query_local_context_length(model, base_url)
        if local_ctx and local_ctx > 0:
            save_context_length(model, base_url, local_ctx)
            return local_ctx
--- a/agent/models_dev.py
+++ b/agent/models_dev.py
@@ -18,8 +18,10 @@ Other modules should import the dataclasses and query functions from here
 rather than parsing the raw JSON themselves.
 """

+import difflib
 import json
 import logging
+import os
 import time
 from dataclasses import dataclass
 from pathlib import Path
@@ -142,11 +144,8 @@ class ProviderInfo:
 PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
    "openrouter": "openrouter",
    "anthropic": "anthropic",
-    "openai": "openai",
-    "openai-codex": "openai",
    "zai": "zai",
    "kimi-coding": "kimi-for-coding",
-    "kimi-coding-cn": "kimi-for-coding",
    "minimax": "minimax",
    "minimax-cn": "minimax-cn",
    "deepseek": "deepseek",
@@ -169,13 +168,19 @@ PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
    "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."""
@@ -420,10 +425,7 @@ def list_provider_models(provider: str) -> List[str]:
    models = _get_provider_models(provider)
    if models is None:
        return []
-    return [
-        mid for mid in models.keys()
-        if not _should_hide_from_provider_catalog(provider, mid)
-    ]
+    return list(models.keys())


 # Patterns that indicate non-agentic or noise models (TTS, embedding,
@@ -435,43 +437,6 @@ _NOISE_PATTERNS: re.Pattern = re.compile(
    re.IGNORECASE,
 )

-# Google's live Gemini catalogs currently include a mix of stale slugs and
-# Gemma models whose TPM quotas are too small for normal Hermes agent traffic.
-# Keep capability metadata available for direct/manual use, but hide these from
-# the Gemini model catalogs we surface in setup and model selection.
-_GOOGLE_HIDDEN_MODELS = frozenset({
-    # Low-TPM Gemma models that trip Google input-token quota walls under
-    # agent-style traffic despite advertising large context windows.
-    "gemma-4-31b-it",
-    "gemma-4-26b-it",
-    "gemma-4-26b-a4b-it",
-    "gemma-3-1b",
-    "gemma-3-1b-it",
-    "gemma-3-2b",
-    "gemma-3-2b-it",
-    "gemma-3-4b",
-    "gemma-3-4b-it",
-    "gemma-3-12b",
-    "gemma-3-12b-it",
-    "gemma-3-27b",
-    "gemma-3-27b-it",
-    # Stale/retired Google slugs that still surface through models.dev-backed
-    # Gemini selection but 404 on the current Google endpoints.
-    "gemini-1.5-flash",
-    "gemini-1.5-pro",
-    "gemini-1.5-flash-8b",
-    "gemini-2.0-flash",
-    "gemini-2.0-flash-lite",
-})
-
-
-def _should_hide_from_provider_catalog(provider: str, model_id: str) -> bool:
-    provider_lower = (provider or "").strip().lower()
-    model_lower = (model_id or "").strip().lower()
-    if provider_lower in {"gemini", "google"} and model_lower in _GOOGLE_HIDDEN_MODELS:
-        return True
-    return False
-

 def list_agentic_models(provider: str) -> List[str]:
    """Return model IDs suitable for agentic use from models.dev.
@@ -488,8 +453,6 @@ def list_agentic_models(provider: str) -> List[str]:
    for mid, entry in models.items():
        if not isinstance(entry, dict):
            continue
-        if _should_hide_from_provider_catalog(provider, mid):
-            continue
        if not entry.get("tool_call", False):
            continue
        if _NOISE_PATTERNS.search(mid):
@@ -498,6 +461,93 @@ def list_agentic_models(provider: str) -> List[str]:
    return result


+def search_models_dev(
+    query: str, provider: str = None, limit: int = 5
+) -> List[Dict[str, Any]]:
+    """Fuzzy search across models.dev catalog. Returns matching model entries.
+
+    Args:
+        query: Search string to match against model IDs.
+        provider: Optional Hermes provider ID to restrict search scope.
+                  If None, searches across all providers in PROVIDER_TO_MODELS_DEV.
+        limit: Maximum number of results to return.
+
+    Returns:
+        List of dicts, each containing 'provider', 'model_id', and the full
+        model 'entry' from models.dev.
+    """
+    data = fetch_models_dev()
+    if not data:
+        return []
+
+    # Build list of (provider_id, model_id, entry) candidates
+    candidates: List[tuple] = []
+
+    if provider is not None:
+        # Search only the specified provider
+        mdev_provider_id = PROVIDER_TO_MODELS_DEV.get(provider)
+        if not mdev_provider_id:
+            return []
+        provider_data = data.get(mdev_provider_id, {})
+        if isinstance(provider_data, dict):
+            models = provider_data.get("models", {})
+            if isinstance(models, dict):
+                for mid, mdata in models.items():
+                    candidates.append((provider, mid, mdata))
+    else:
+        # Search across all mapped providers
+        for hermes_prov, mdev_prov in PROVIDER_TO_MODELS_DEV.items():
+            provider_data = data.get(mdev_prov, {})
+            if isinstance(provider_data, dict):
+                models = provider_data.get("models", {})
+                if isinstance(models, dict):
+                    for mid, mdata in models.items():
+                        candidates.append((hermes_prov, mid, mdata))
+
+    if not candidates:
+        return []
+
+    # Use difflib for fuzzy matching — case-insensitive comparison
+    model_ids_lower = [c[1].lower() for c in candidates]
+    query_lower = query.lower()
+
+    # First try exact substring matches (more intuitive than pure edit-distance)
+    substring_matches = []
+    for prov, mid, mdata in candidates:
+        if query_lower in mid.lower():
+            substring_matches.append({"provider": prov, "model_id": mid, "entry": mdata})
+
+    # Then add difflib fuzzy matches for any remaining slots
+    fuzzy_ids = difflib.get_close_matches(
+        query_lower, model_ids_lower, n=limit * 2, cutoff=0.4
+    )
+
+    seen_ids: set = set()
+    results: List[Dict[str, Any]] = []
+
+    # Prioritize substring matches
+    for match in substring_matches:
+        key = (match["provider"], match["model_id"])
+        if key not in seen_ids:
+            seen_ids.add(key)
+            results.append(match)
+            if len(results) >= limit:
+                return results
+
+    # Add fuzzy matches
+    for fid in fuzzy_ids:
+        # Find original-case candidates matching this lowered ID
+        for prov, mid, mdata in candidates:
+            if mid.lower() == fid:
+                key = (prov, mid)
+                if key not in seen_ids:
+                    seen_ids.add(key)
+                    results.append({"provider": prov, "model_id": mid, "entry": mdata})
+                    if len(results) >= limit:
+                        return results
+
+    return results
+

 # ---------------------------------------------------------------------------
 # Rich dataclass constructors — parse raw models.dev JSON into dataclasses
@@ -624,3 +674,5 @@ def get_model_info(
            return _parse_model_info(mid, mdata, mdev_id)

    return None
+
+
--- a/agent/nous_rate_guard.py
+++ b/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"
--- a/agent/prompt_builder.py
+++ b/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, get_skills_dir
 from typing import Optional

 from agent.skill_utils import (
@@ -152,13 +152,7 @@ MEMORY_GUIDANCE = (
    "Do NOT save task progress, session outcomes, completed-work logs, or temporary TODO "
    "state to memory; use session_search to recall those from past transcripts. "
    "If you've discovered a new way to do something, solved a problem that could be "
-    "necessary later, save it as a skill with the skill tool.\n"
-    "Write memories as declarative facts, not instructions to yourself. "
-    "'User prefers concise responses' ✓ — 'Always respond concisely' ✗. "
-    "'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. "
-    "Imperative phrasing gets re-read as a directive in later sessions and can "
-    "cause repeated work or override the user's current request. Procedures and "
-    "workflows belong in skills, not memory."
+    "necessary later, save it as a skill with the skill tool."
 )

 SESSION_SEARCH_GUIDANCE = (
@@ -301,9 +295,7 @@ PLATFORM_HINTS = {
    ),
    "telegram": (
        "You are on a text messaging communication platform, Telegram. "
-        "Standard markdown is automatically converted to Telegram format. "
-        "Supported: **bold**, *italic*, ~~strikethrough~~, ||spoiler||, "
-        "`inline code`, ```code blocks```, [links](url), and ## headers. "
+        "Please do not use markdown as it does not render. "
        "You can send media files natively: to deliver a file to the user, "
        "include MEDIA:/absolute/path/to/file in your response. Images "
        "(.png, .jpg, .webp) appear as photos, audio (.ogg) sends as voice "
@@ -350,13 +342,7 @@ PLATFORM_HINTS = {
    ),
    "cli": (
        "You are a CLI AI Agent. Try not to use markdown but simple text "
-        "renderable inside a terminal. "
-        "File delivery: there is no attachment channel — the user reads your "
-        "response directly in their terminal. Do NOT emit MEDIA:/path tags "
-        "(those are only intercepted on messaging platforms like Telegram, "
-        "Discord, Slack, etc.; on the CLI they render as literal text). "
-        "When referring to a file you created or changed, just state its "
-        "absolute path in plain text; the user can open it from there."
+        "renderable inside a terminal."
    ),
    "sms": (
        "You are communicating via SMS. Keep responses concise and use plain text "
@@ -378,56 +364,8 @@ PLATFORM_HINTS = {
        "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
@@ -625,14 +563,12 @@ def build_skills_system_prompt(
        or get_session_env("HERMES_SESSION_PLATFORM")
        or ""
    )
-    disabled = get_disabled_skill_names()
    cache_key = (
        str(skills_dir.resolve()),
        tuple(str(d) for d in external_dirs),
        tuple(sorted(str(t) for t in (available_tools or set()))),
        tuple(sorted(str(ts) for ts in (available_toolsets or set()))),
        _platform_hint,
-        tuple(sorted(disabled)),
    )
    with _SKILLS_PROMPT_CACHE_LOCK:
        cached = _SKILLS_PROMPT_CACHE.get(cache_key)
@@ -640,6 +576,8 @@ def build_skills_system_prompt(
            _SKILLS_PROMPT_CACHE.move_to_end(cache_key)
            return cached

+    disabled = get_disabled_skill_names()
+
    # ── Layer 2: disk snapshot ────────────────────────────────────────
    snapshot = _load_skills_snapshot(skills_dir)

@@ -666,7 +604,7 @@ def build_skills_system_prompt(
            ):
                continue
            skills_by_category.setdefault(category, []).append(
-                (frontmatter_name, entry.get("description", ""))
+                (skill_name, entry.get("description", ""))
            )
        category_descriptions = {
            str(k): str(v)
@@ -691,7 +629,7 @@ def build_skills_system_prompt(
            ):
                continue
            skills_by_category.setdefault(entry["category"], []).append(
-                (entry["frontmatter_name"], entry["description"])
+                (skill_name, entry["description"])
            )

        # Read category-level DESCRIPTION.md files
@@ -734,10 +672,9 @@ def build_skills_system_prompt(
                    continue
                entry = _build_snapshot_entry(skill_file, ext_dir, frontmatter, desc)
                skill_name = entry["skill_name"]
-                frontmatter_name = entry["frontmatter_name"]
-                if frontmatter_name in seen_skill_names:
+                if skill_name in seen_skill_names:
                    continue
-                if frontmatter_name in disabled or skill_name in disabled:
+                if entry["frontmatter_name"] in disabled or skill_name in disabled:
                    continue
                if not _skill_should_show(
                    extract_skill_conditions(frontmatter),
@@ -745,9 +682,9 @@ def build_skills_system_prompt(
                    available_toolsets,
                ):
                    continue
-                seen_skill_names.add(frontmatter_name)
+                seen_skill_names.add(skill_name)
                skills_by_category.setdefault(entry["category"], []).append(
-                    (frontmatter_name, entry["description"])
+                    (skill_name, entry["description"])
                )
            except Exception as e:
                logger.debug("Error reading external skill %s: %s", skill_file, e)
@@ -789,16 +726,8 @@ 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 "
@@ -808,7 +737,7 @@ 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 ────────────────────────────────────────────
--- a/agent/rate_limit_tracker.py
+++ b/agent/rate_limit_tracker.py
@@ -24,7 +24,7 @@ from __future__ import annotations

 import time
 from dataclasses import dataclass, field
-from typing import Any, Mapping, Optional
+from typing import Any, Dict, Mapping, Optional


@dataclass
--- a/agent/redact.py
+++ b/agent/redact.py
@@ -13,48 +13,6 @@ import re

 logger = logging.getLogger(__name__)

-# Sensitive query-string parameter names (case-insensitive exact match).
-# Ported from nearai/ironclaw#2529 — catches tokens whose values don't match
-# any known vendor prefix regex (e.g. opaque tokens, short OAuth codes).
-_SENSITIVE_QUERY_PARAMS = frozenset({
-    "access_token",
-    "refresh_token",
-    "id_token",
-    "token",
-    "api_key",
-    "apikey",
-    "client_secret",
-    "password",
-    "auth",
-    "jwt",
-    "session",
-    "secret",
-    "key",
-    "code",           # OAuth authorization codes
-    "signature",      # pre-signed URL signatures
-    "x-amz-signature",
-})
-
-# Sensitive form-urlencoded / JSON body key names (case-insensitive exact match).
-# Exact match, NOT substring — "token_count" and "session_id" must NOT match.
-# Ported from nearai/ironclaw#2529.
-_SENSITIVE_BODY_KEYS = frozenset({
-    "access_token",
-    "refresh_token",
-    "id_token",
-    "token",
-    "api_key",
-    "apikey",
-    "client_secret",
-    "password",
-    "auth",
-    "jwt",
-    "secret",
-    "private_key",
-    "authorization",
-    "key",
-})
-
 # Snapshot at import time so runtime env mutations (e.g. LLM-generated
 # `export HERMES_REDACT_SECRETS=false`) cannot disable redaction mid-session.
 _REDACT_ENABLED = os.getenv("HERMES_REDACT_SECRETS", "").lower() not in ("0", "false", "no", "off")
@@ -135,45 +93,10 @@ _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])")

-# URLs containing query strings — matches `scheme://...?...[# or end]`.
-# Used to scan text for URLs whose query params may contain secrets.
-# Ported from nearai/ironclaw#2529.
-_URL_WITH_QUERY_RE = re.compile(
-    r"(https?|wss?|ftp)://"          # scheme
-    r"([^\s/?#]+)"                    # authority (may include userinfo)
-    r"([^\s?#]*)"                     # path
-    r"\?([^\s#]+)"                    # query (required)
-    r"(#\S*)?",                       # optional fragment
-)
-
-# URLs containing userinfo — `scheme://user:password@host` for ANY scheme
-# (not just DB protocols already covered by _DB_CONNSTR_RE above).
-# Catches things like `https://user:token@api.example.com/v1/foo`.
-_URL_USERINFO_RE = re.compile(
-    r"(https?|wss?|ftp)://([^/\s:@]+):([^/\s@]+)@",
-)
-
-# Form-urlencoded body detection: conservative — only applies when the entire
-# text looks like a query string (k=v&k=v pattern with no newlines).
-_FORM_BODY_RE = re.compile(
-    r"^[A-Za-z_][A-Za-z0-9_.-]*=[^&\s]*(?:&[A-Za-z_][A-Za-z0-9_.-]*=[^&\s]*)+$"
-)
-
 # Compile known prefix patterns into one alternation
 _PREFIX_RE = re.compile(
    r"(?<![A-Za-z0-9_-])(" + "|".join(_PREFIX_PATTERNS) + r")(?![A-Za-z0-9_-])"
@@ -187,72 +110,6 @@ def _mask_token(token: str) -> str:
    return f"{token[:6]}...{token[-4:]}"


-def _redact_query_string(query: str) -> str:
-    """Redact sensitive parameter values in a URL query string.
-
-    Handles `k=v&k=v` format. Sensitive keys (case-insensitive) have values
-    replaced with `***`. Non-sensitive keys pass through unchanged.
-    Empty or malformed pairs are preserved as-is.
-    """
-    if not query:
-        return query
-    parts = []
-    for pair in query.split("&"):
-        if "=" not in pair:
-            parts.append(pair)
-            continue
-        key, _, value = pair.partition("=")
-        if key.lower() in _SENSITIVE_QUERY_PARAMS:
-            parts.append(f"{key}=***")
-        else:
-            parts.append(pair)
-    return "&".join(parts)
-
-
-def _redact_url_query_params(text: str) -> str:
-    """Scan text for URLs with query strings and redact sensitive params.
-
-    Catches opaque tokens that don't match vendor prefix regexes, e.g.
-    `https://example.com/cb?code=ABC123&state=xyz` → `...?code=***&state=xyz`.
-    """
-    def _sub(m: re.Match) -> str:
-        scheme = m.group(1)
-        authority = m.group(2)
-        path = m.group(3)
-        query = _redact_query_string(m.group(4))
-        fragment = m.group(5) or ""
-        return f"{scheme}://{authority}{path}?{query}{fragment}"
-    return _URL_WITH_QUERY_RE.sub(_sub, text)
-
-
-def _redact_url_userinfo(text: str) -> str:
-    """Strip `user:password@` from HTTP/WS/FTP URLs.
-
-    DB protocols (postgres, mysql, mongodb, redis, amqp) are handled
-    separately by `_DB_CONNSTR_RE`.
-    """
-    return _URL_USERINFO_RE.sub(
-        lambda m: f"{m.group(1)}://{m.group(2)}:***@",
-        text,
-    )
-
-
-def _redact_form_body(text: str) -> str:
-    """Redact sensitive values in a form-urlencoded body.
-
-    Only applies when the entire input looks like a pure form body
-    (k=v&k=v with no newlines, no other text). Single-line non-form
-    text passes through unchanged. This is a conservative pass — the
-    `_redact_url_query_params` function handles embedded query strings.
-    """
-    if not text or "\n" in text or "&" not in text:
-        return text
-    # The body-body form check is strict: only trigger on clean k=v&k=v.
-    if not _FORM_BODY_RE.match(text.strip()):
-        return text
-    return _redact_query_string(text.strip())
-
-
 def redact_sensitive_text(text: str) -> str:
    """Apply all redaction patterns to a block of text.

@@ -302,22 +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)
-
-    # URL userinfo (http(s)://user:pass@host) — redact for non-DB schemes.
-    # DB schemes are handled above by _DB_CONNSTR_RE.
-    text = _redact_url_userinfo(text)
-
-    # URL query params containing opaque tokens (?access_token=…&code=…)
-    text = _redact_url_query_params(text)
-
-    # Form-urlencoded bodies (only triggers on clean k=v&k=v inputs).
-    text = _redact_form_body(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)
--- a/agent/shell_hooks.py
+++ b/agent/shell_hooks.py
@@ -1,831 +0,0 @@
-"""
-Shell-script hooks bridge.
-
-Reads the ``hooks:`` block from ``cli-config.yaml``, prompts the user for
-consent on first use of each ``(event, command)`` pair, and registers
-callbacks on the existing plugin hook manager so every existing
-``invoke_hook()`` site dispatches to the configured shell scripts — with
-zero changes to call sites.
-
-Design notes
------------
-* Python plugins and shell hooks compose naturally: both flow through
-  :func:`hermes_cli.plugins.invoke_hook` and its aggregators.  Python
-  plugins are registered first (via ``discover_and_load()``) so their
-  block decisions win ties over shell-hook blocks.
-* Subprocess execution uses ``shlex.split(os.path.expanduser(command))``
-  with ``shell=False`` — no shell injection footguns.  Users that need
-  pipes/redirection wrap their logic in a script.
-* First-use consent is gated by the allowlist under
-  ``~/.hermes/shell-hooks-allowlist.json``.  Non-TTY callers must pass
-  ``accept_hooks=True`` (resolved from ``--accept-hooks``,
-  ``HERMES_ACCEPT_HOOKS``, or ``hooks_auto_accept: true`` in config)
-  for registration to succeed without a prompt.
-* Registration is idempotent — safe to invoke from both the CLI entry
-  point (``hermes_cli/main.py``) and the gateway entry point
-  (``gateway/run.py``).
-
-Wire protocol
-------------
-**stdin** (JSON, piped to the script)::
-
-    {
-        "hook_event_name": "pre_tool_call",
-        "tool_name":       "terminal",
-        "tool_input":      {"command": "rm -rf /"},
-        "session_id":      "sess_abc123",
-        "cwd":             "/home/user/project",
-        "extra":           {...}   # event-specific kwargs
-    }
-
-**stdout** (JSON, optional — anything else is ignored)::
-
-    # Block a pre_tool_call (either shape accepted; normalised internally):
-    {"decision": "block", "reason":  "Forbidden command"}   # Claude-Code-style
-    {"action":   "block", "message": "Forbidden command"}   # Hermes-canonical
-
-    # Inject context for pre_llm_call:
-    {"context": "Today is Friday"}
-
-    # Silent no-op:
-    <empty or any non-matching JSON object>
-"""
-
-from __future__ import annotations
-
-import difflib
-import json
-import logging
-import os
-import re
-import shlex
-import subprocess
-import sys
-import tempfile
-import threading
-import time
-from contextlib import contextmanager
-from dataclasses import dataclass, field
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any, Callable, Dict, Iterator, List, Optional, Set, Tuple
-
-try:
-    import fcntl  # POSIX only; Windows falls back to best-effort without flock.
-except ImportError:  # pragma: no cover
-    fcntl = None  # type: ignore[assignment]
-
-from hermes_constants import get_hermes_home
-
-logger = logging.getLogger(__name__)
-
-DEFAULT_TIMEOUT_SECONDS = 60
-MAX_TIMEOUT_SECONDS = 300
-ALLOWLIST_FILENAME = "shell-hooks-allowlist.json"
-
-# (event, matcher, command) triples that have been wired to the plugin
-# manager in the current process.  Matcher is part of the key because
-# the same script can legitimately register for different matchers under
-# the same event (e.g. one entry per tool the user wants to gate).
-# Second registration attempts for the exact same triple become no-ops
-# so the CLI and gateway can both call register_from_config() safely.
-_registered: Set[Tuple[str, Optional[str], str]] = set()
-_registered_lock = threading.Lock()
-
-# Intra-process lock for allowlist read-modify-write on platforms that
-# lack ``fcntl`` (non-POSIX).  Kept separate from ``_registered_lock``
-# because ``register_from_config`` already holds ``_registered_lock`` when
-# it triggers ``_record_approval`` — reusing it here would self-deadlock
-# (``threading.Lock`` is non-reentrant).  POSIX callers use the sibling
-# ``.lock`` file via ``fcntl.flock`` and bypass this.
-_allowlist_write_lock = threading.Lock()
-
-
-@dataclass
-class ShellHookSpec:
-    """Parsed and validated representation of a single ``hooks:`` entry."""
-
-    event: str
-    command: str
-    matcher: Optional[str] = None
-    timeout: int = DEFAULT_TIMEOUT_SECONDS
-    compiled_matcher: Optional[re.Pattern] = field(default=None, repr=False)
-
-    def __post_init__(self) -> None:
-        # Strip whitespace introduced by YAML quirks (e.g. multi-line string
-        # folding) — a matcher of " terminal" would otherwise silently fail
-        # to match "terminal" without any diagnostic.
-        if isinstance(self.matcher, str):
-            stripped = self.matcher.strip()
-            self.matcher = stripped if stripped else None
-        if self.matcher:
-            try:
-                self.compiled_matcher = re.compile(self.matcher)
-            except re.error as exc:
-                logger.warning(
-                    "shell hook matcher %r is invalid (%s) — treating as "
-                    "literal equality", self.matcher, exc,
-                )
-                self.compiled_matcher = None
-
-    def matches_tool(self, tool_name: Optional[str]) -> bool:
-        if not self.matcher:
-            return True
-        if tool_name is None:
-            return False
-        if self.compiled_matcher is not None:
-            return self.compiled_matcher.fullmatch(tool_name) is not None
-        # compiled_matcher is None only when the regex failed to compile,
-        # in which case we already warned and fall back to literal equality.
-        return tool_name == self.matcher
-
-
-# ---------------------------------------------------------------------------
-# Public API
-# ---------------------------------------------------------------------------
-
-def register_from_config(
-    cfg: Optional[Dict[str, Any]],
-    *,
-    accept_hooks: bool = False,
-) -> List[ShellHookSpec]:
-    """Register every configured shell hook on the plugin manager.
-
-    ``cfg`` is the full parsed config dict (``hermes_cli.config.load_config``
-    output).  The ``hooks:`` key is read out of it.  Missing, empty, or
-    non-dict ``hooks`` is treated as zero configured hooks.
-
-    ``accept_hooks=True`` skips the TTY consent prompt — the caller is
-    promising that the user has opted in via a flag, env var, or config
-    setting.  ``HERMES_ACCEPT_HOOKS=1`` and ``hooks_auto_accept: true`` are
-    also honored inside this function so either CLI or gateway call sites
-    pick them up.
-
-    Returns the list of :class:`ShellHookSpec` entries that ended up wired
-    up on the plugin manager.  Skipped entries (unknown events, malformed,
-    not allowlisted, already registered) are logged but not returned.
-    """
-    if not isinstance(cfg, dict):
-        return []
-
-    effective_accept = _resolve_effective_accept(cfg, accept_hooks)
-
-    specs = _parse_hooks_block(cfg.get("hooks"))
-    if not specs:
-        return []
-
-    registered: List[ShellHookSpec] = []
-
-    # Import lazily — avoids circular imports at module-load time.
-    from hermes_cli.plugins import get_plugin_manager
-
-    manager = get_plugin_manager()
-
-    # Idempotence + allowlist read happen under the lock; the TTY
-    # prompt runs outside so other threads aren't parked on a blocking
-    # input().  Mutation re-takes the lock with a defensive idempotence
-    # re-check in case two callers ever race through the prompt.
-    for spec in specs:
-        key = (spec.event, spec.matcher, spec.command)
-        with _registered_lock:
-            if key in _registered:
-                continue
-            already_allowlisted = _is_allowlisted(spec.event, spec.command)
-
-        if not already_allowlisted:
-            if not _prompt_and_record(
-                spec.event, spec.command, accept_hooks=effective_accept,
-            ):
-                logger.warning(
-                    "shell hook for %s (%s) not allowlisted — skipped. "
-                    "Use --accept-hooks / HERMES_ACCEPT_HOOKS=1 / "
-                    "hooks_auto_accept: true, or approve at the TTY "
-                    "prompt next run.",
-                    spec.event, spec.command,
-                )
-                continue
-
-        with _registered_lock:
-            if key in _registered:
-                continue
-            manager._hooks.setdefault(spec.event, []).append(_make_callback(spec))
-            _registered.add(key)
-            registered.append(spec)
-            logger.info(
-                "shell hook registered: %s -> %s (matcher=%s, timeout=%ds)",
-                spec.event, spec.command, spec.matcher, spec.timeout,
-            )
-
-    return registered
-
-
-def iter_configured_hooks(cfg: Optional[Dict[str, Any]]) -> List[ShellHookSpec]:
-    """Return the parsed ``ShellHookSpec`` entries from config without
-    registering anything.  Used by ``hermes hooks list`` and ``doctor``."""
-    if not isinstance(cfg, dict):
-        return []
-    return _parse_hooks_block(cfg.get("hooks"))
-
-
-def reset_for_tests() -> None:
-    """Clear the idempotence set.  Test-only helper."""
-    with _registered_lock:
-        _registered.clear()
-
-
-# ---------------------------------------------------------------------------
-# Config parsing
-# ---------------------------------------------------------------------------
-
-def _parse_hooks_block(hooks_cfg: Any) -> List[ShellHookSpec]:
-    """Normalise the ``hooks:`` dict into a flat list of ``ShellHookSpec``.
-
-    Malformed entries warn-and-skip — we never raise from config parsing
-    because a broken hook must not crash the agent.
-    """
-    from hermes_cli.plugins import VALID_HOOKS
-
-    if not isinstance(hooks_cfg, dict):
-        return []
-
-    specs: List[ShellHookSpec] = []
-
-    for event_name, entries in hooks_cfg.items():
-        if event_name not in VALID_HOOKS:
-            suggestion = difflib.get_close_matches(
-                str(event_name), VALID_HOOKS, n=1, cutoff=0.6,
-            )
-            if suggestion:
-                logger.warning(
-                    "unknown hook event %r in hooks: config — did you mean %r?",
-                    event_name, suggestion[0],
-                )
-            else:
-                logger.warning(
-                    "unknown hook event %r in hooks: config (valid: %s)",
-                    event_name, ", ".join(sorted(VALID_HOOKS)),
-                )
-            continue
-
-        if entries is None:
-            continue
-
-        if not isinstance(entries, list):
-            logger.warning(
-                "hooks.%s must be a list of hook definitions; got %s",
-                event_name, type(entries).__name__,
-            )
-            continue
-
-        for i, raw in enumerate(entries):
-            spec = _parse_single_entry(event_name, i, raw)
-            if spec is not None:
-                specs.append(spec)
-
-    return specs
-
-
-def _parse_single_entry(
-    event: str, index: int, raw: Any,
-) -> Optional[ShellHookSpec]:
-    if not isinstance(raw, dict):
-        logger.warning(
-            "hooks.%s[%d] must be a mapping with a 'command' key; got %s",
-            event, index, type(raw).__name__,
-        )
-        return None
-
-    command = raw.get("command")
-    if not isinstance(command, str) or not command.strip():
-        logger.warning(
-            "hooks.%s[%d] is missing a non-empty 'command' field",
-            event, index,
-        )
-        return None
-
-    matcher = raw.get("matcher")
-    if matcher is not None and not isinstance(matcher, str):
-        logger.warning(
-            "hooks.%s[%d].matcher must be a string regex; ignoring",
-            event, index,
-        )
-        matcher = None
-
-    if matcher is not None and event not in ("pre_tool_call", "post_tool_call"):
-        logger.warning(
-            "hooks.%s[%d].matcher=%r will be ignored at runtime — the "
-            "matcher field is only honored for pre_tool_call / "
-            "post_tool_call.  The hook will fire on every %s event.",
-            event, index, matcher, event,
-        )
-        matcher = None
-
-    timeout_raw = raw.get("timeout", DEFAULT_TIMEOUT_SECONDS)
-    try:
-        timeout = int(timeout_raw)
-    except (TypeError, ValueError):
-        logger.warning(
-            "hooks.%s[%d].timeout must be an int (got %r); using default %ds",
-            event, index, timeout_raw, DEFAULT_TIMEOUT_SECONDS,
-        )
-        timeout = DEFAULT_TIMEOUT_SECONDS
-
-    if timeout < 1:
-        logger.warning(
-            "hooks.%s[%d].timeout must be >=1; using default %ds",
-            event, index, DEFAULT_TIMEOUT_SECONDS,
-        )
-        timeout = DEFAULT_TIMEOUT_SECONDS
-
-    if timeout > MAX_TIMEOUT_SECONDS:
-        logger.warning(
-            "hooks.%s[%d].timeout=%ds exceeds max %ds; clamping",
-            event, index, timeout, MAX_TIMEOUT_SECONDS,
-        )
-        timeout = MAX_TIMEOUT_SECONDS
-
-    return ShellHookSpec(
-        event=event,
-        command=command.strip(),
-        matcher=matcher,
-        timeout=timeout,
-    )
-
-
-# ---------------------------------------------------------------------------
-# Subprocess callback
-# ---------------------------------------------------------------------------
-
-_TOP_LEVEL_PAYLOAD_KEYS = {"tool_name", "args", "session_id", "parent_session_id"}
-
-
-def _spawn(spec: ShellHookSpec, stdin_json: str) -> Dict[str, Any]:
-    """Run ``spec.command`` as a subprocess with ``stdin_json`` on stdin.
-
-    Returns a diagnostic dict with the same keys for every outcome
-    (``returncode``, ``stdout``, ``stderr``, ``timed_out``,
-    ``elapsed_seconds``, ``error``).  This is the single place the
-    subprocess is actually invoked — both the live callback path
-    (:func:`_make_callback`) and the CLI test helper (:func:`run_once`)
-    go through it.
-    """
-    result: Dict[str, Any] = {
-        "returncode": None,
-        "stdout": "",
-        "stderr": "",
-        "timed_out": False,
-        "elapsed_seconds": 0.0,
-        "error": None,
-    }
-    try:
-        argv = shlex.split(os.path.expanduser(spec.command))
-    except ValueError as exc:
-        result["error"] = f"command {spec.command!r} cannot be parsed: {exc}"
-        return result
-    if not argv:
-        result["error"] = "empty command"
-        return result
-
-    t0 = time.monotonic()
-    try:
-        proc = subprocess.run(
-            argv,
-            input=stdin_json,
-            capture_output=True,
-            timeout=spec.timeout,
-            text=True,
-            shell=False,
-        )
-    except subprocess.TimeoutExpired:
-        result["timed_out"] = True
-        result["elapsed_seconds"] = round(time.monotonic() - t0, 3)
-        return result
-    except FileNotFoundError:
-        result["error"] = "command not found"
-        return result
-    except PermissionError:
-        result["error"] = "command not executable"
-        return result
-    except Exception as exc:  # pragma: no cover — defensive
-        result["error"] = str(exc)
-        return result
-
-    result["returncode"] = proc.returncode
-    result["stdout"] = proc.stdout or ""
-    result["stderr"] = proc.stderr or ""
-    result["elapsed_seconds"] = round(time.monotonic() - t0, 3)
-    return result
-
-
-def _make_callback(spec: ShellHookSpec) -> Callable[..., Optional[Dict[str, Any]]]:
-    """Build the closure that ``invoke_hook()`` will call per firing."""
-
-    def _callback(**kwargs: Any) -> Optional[Dict[str, Any]]:
-        # Matcher gate — only meaningful for tool-scoped events.
-        if spec.event in ("pre_tool_call", "post_tool_call"):
-            if not spec.matches_tool(kwargs.get("tool_name")):
-                return None
-
-        r = _spawn(spec, _serialize_payload(spec.event, kwargs))
-
-        if r["error"]:
-            logger.warning(
-                "shell hook failed (event=%s command=%s): %s",
-                spec.event, spec.command, r["error"],
-            )
-            return None
-        if r["timed_out"]:
-            logger.warning(
-                "shell hook timed out after %.2fs (event=%s command=%s)",
-                r["elapsed_seconds"], spec.event, spec.command,
-            )
-            return None
-
-        stderr = r["stderr"].strip()
-        if stderr:
-            logger.debug(
-                "shell hook stderr (event=%s command=%s): %s",
-                spec.event, spec.command, stderr[:400],
-            )
-        # Non-zero exits: log but still parse stdout so scripts that
-        # signal failure via exit code can also return a block directive.
-        if r["returncode"] != 0:
-            logger.warning(
-                "shell hook exited %d (event=%s command=%s); stderr=%s",
-                r["returncode"], spec.event, spec.command, stderr[:400],
-            )
-        return _parse_response(spec.event, r["stdout"])
-
-    _callback.__name__ = f"shell_hook[{spec.event}:{spec.command}]"
-    _callback.__qualname__ = _callback.__name__
-    return _callback
-
-
-def _serialize_payload(event: str, kwargs: Dict[str, Any]) -> str:
-    """Render the stdin JSON payload.  Unserialisable values are
-    stringified via ``default=str`` rather than dropped."""
-    extras = {k: v for k, v in kwargs.items() if k not in _TOP_LEVEL_PAYLOAD_KEYS}
-    try:
-        cwd = str(Path.cwd())
-    except OSError:
-        cwd = ""
-    payload = {
-        "hook_event_name": event,
-        "tool_name": kwargs.get("tool_name"),
-        "tool_input": kwargs.get("args") if isinstance(kwargs.get("args"), dict) else None,
-        "session_id": kwargs.get("session_id") or kwargs.get("parent_session_id") or "",
-        "cwd": cwd,
-        "extra": extras,
-    }
-    return json.dumps(payload, ensure_ascii=False, default=str)
-
-
-def _parse_response(event: str, stdout: str) -> Optional[Dict[str, Any]]:
-    """Translate stdout JSON into a Hermes wire-shape dict.
-
-    For ``pre_tool_call`` the Claude-Code-style ``{"decision": "block",
-    "reason": "..."}`` payload is translated into the canonical Hermes
-    ``{"action": "block", "message": "..."}`` shape expected by
-    :func:`hermes_cli.plugins.get_pre_tool_call_block_message`.  This is
-    the single most important correctness invariant in this module —
-    skipping the translation silently breaks every ``pre_tool_call``
-    block directive.
-
-    For ``pre_llm_call``, ``{"context": "..."}`` is passed through
-    unchanged to match the existing plugin-hook contract.
-
-    Anything else returns ``None``.
-    """
-    stdout = (stdout or "").strip()
-    if not stdout:
-        return None
-
-    try:
-        data = json.loads(stdout)
-    except json.JSONDecodeError:
-        logger.warning(
-            "shell hook stdout was not valid JSON (event=%s): %s",
-            event, stdout[:200],
-        )
-        return None
-
-    if not isinstance(data, dict):
-        return None
-
-    if event == "pre_tool_call":
-        if data.get("action") == "block":
-            message = data.get("message") or data.get("reason") or ""
-            if isinstance(message, str) and message:
-                return {"action": "block", "message": message}
-        if data.get("decision") == "block":
-            message = data.get("reason") or data.get("message") or ""
-            if isinstance(message, str) and message:
-                return {"action": "block", "message": message}
-        return None
-
-    context = data.get("context")
-    if isinstance(context, str) and context.strip():
-        return {"context": context}
-
-    return None
-
-
-# ---------------------------------------------------------------------------
-# Allowlist / consent
-# ---------------------------------------------------------------------------
-
-def allowlist_path() -> Path:
-    """Path to the per-user shell-hook allowlist file."""
-    return get_hermes_home() / ALLOWLIST_FILENAME
-
-
-def load_allowlist() -> Dict[str, Any]:
-    """Return the parsed allowlist, or an empty skeleton if absent."""
-    try:
-        raw = json.loads(allowlist_path().read_text())
-    except (FileNotFoundError, json.JSONDecodeError, OSError):
-        return {"approvals": []}
-    if not isinstance(raw, dict):
-        return {"approvals": []}
-    approvals = raw.get("approvals")
-    if not isinstance(approvals, list):
-        raw["approvals"] = []
-    return raw
-
-
-def save_allowlist(data: Dict[str, Any]) -> None:
-    """Atomically persist the allowlist via per-process ``mkstemp`` +
-    ``os.replace``.  Cross-process read-modify-write races are handled
-    by :func:`_locked_update_approvals` (``fcntl.flock``).  On OSError
-    the failure is logged; the in-process hook still registers but
-    the approval won't survive across runs."""
-    p = allowlist_path()
-    try:
-        p.parent.mkdir(parents=True, exist_ok=True)
-        fd, tmp_path = tempfile.mkstemp(
-            prefix=f"{p.name}.", suffix=".tmp", dir=str(p.parent),
-        )
-        try:
-            with os.fdopen(fd, "w") as fh:
-                fh.write(json.dumps(data, indent=2, sort_keys=True))
-            os.replace(tmp_path, p)
-        except Exception:
-            try:
-                os.unlink(tmp_path)
-            except OSError:
-                pass
-            raise
-    except OSError as exc:
-        logger.warning(
-            "Failed to persist shell hook allowlist to %s: %s. "
-            "The approval is in-memory for this run, but the next "
-            "startup will re-prompt (or skip registration on non-TTY "
-            "runs without --accept-hooks / HERMES_ACCEPT_HOOKS).",
-            p, exc,
-        )
-
-
-def _is_allowlisted(event: str, command: str) -> bool:
-    data = load_allowlist()
-    return any(
-        isinstance(e, dict)
-        and e.get("event") == event
-        and e.get("command") == command
-        for e in data.get("approvals", [])
-    )
-
-
-@contextmanager
-def _locked_update_approvals() -> Iterator[Dict[str, Any]]:
-    """Serialise read-modify-write on the allowlist across processes.
-
-    Holds an exclusive ``flock`` on a sibling lock file for the duration
-    of the update so concurrent ``_record_approval``/``revoke`` callers
-    cannot clobber each other's changes (the race Codex reproduced with
-    20–50 simultaneous writers).  Falls back to an in-process lock on
-    platforms without ``fcntl``.
-    """
-    p = allowlist_path()
-    p.parent.mkdir(parents=True, exist_ok=True)
-    lock_path = p.with_suffix(p.suffix + ".lock")
-
-    if fcntl is None:  # pragma: no cover — non-POSIX fallback
-        with _allowlist_write_lock:
-            data = load_allowlist()
-            yield data
-            save_allowlist(data)
-        return
-
-    with open(lock_path, "a+") as lock_fh:
-        fcntl.flock(lock_fh.fileno(), fcntl.LOCK_EX)
-        try:
-            data = load_allowlist()
-            yield data
-            save_allowlist(data)
-        finally:
-            fcntl.flock(lock_fh.fileno(), fcntl.LOCK_UN)
-
-
-def _prompt_and_record(
-    event: str, command: str, *, accept_hooks: bool,
-) -> bool:
-    """Decide whether to approve an unseen ``(event, command)`` pair.
-    Returns ``True`` iff the approval was granted and recorded.
-    """
-    if accept_hooks:
-        _record_approval(event, command)
-        logger.info(
-            "shell hook auto-approved via --accept-hooks / env / config: "
-            "%s -> %s", event, command,
-        )
-        return True
-
-    if not sys.stdin.isatty():
-        return False
-
-    print(
-        f"\n⚠ Hermes is about to register a shell hook that will run a\n"
-        f"  command on your behalf.\n\n"
-        f"    Event:   {event}\n"
-        f"    Command: {command}\n\n"
-        f"  Commands run with your full user credentials.  Only approve\n"
-        f"  commands you trust."
-    )
-    try:
-        answer = input("Allow this hook to run? [y/N]: ").strip().lower()
-    except (EOFError, KeyboardInterrupt):
-        print()  # keep the terminal tidy after ^C
-        return False
-
-    if answer in ("y", "yes"):
-        _record_approval(event, command)
-        return True
-
-    return False
-
-
-def _record_approval(event: str, command: str) -> None:
-    entry = {
-        "event": event,
-        "command": command,
-        "approved_at": _utc_now_iso(),
-        "script_mtime_at_approval": script_mtime_iso(command),
-    }
-    with _locked_update_approvals() as data:
-        data["approvals"] = [
-            e for e in data.get("approvals", [])
-            if not (
-                isinstance(e, dict)
-                and e.get("event") == event
-                and e.get("command") == command
-            )
-        ] + [entry]
-
-
-def _utc_now_iso() -> str:
-    return datetime.now(tz=timezone.utc).isoformat().replace("+00:00", "Z")
-
-
-def revoke(command: str) -> int:
-    """Remove every allowlist entry matching ``command``.
-
-    Returns the number of entries removed.  Does not unregister any
-    callbacks that are already live on the plugin manager in the current
-    process — restart the CLI / gateway to drop them.
-    """
-    with _locked_update_approvals() as data:
-        before = len(data.get("approvals", []))
-        data["approvals"] = [
-            e for e in data.get("approvals", [])
-            if not (isinstance(e, dict) and e.get("command") == command)
-        ]
-        after = len(data["approvals"])
-    return before - after
-
-
-_SCRIPT_EXTENSIONS: Tuple[str, ...] = (
-    ".sh", ".bash", ".zsh", ".fish",
-    ".py", ".pyw",
-    ".rb", ".pl", ".lua",
-    ".js", ".mjs", ".cjs", ".ts",
-)
-
-
-def _command_script_path(command: str) -> str:
-    """Return the script path from ``command`` for doctor / drift checks.
-
-    Prefers a token ending in a known script extension, then a token
-    containing ``/`` or leading ``~``, then the first token.  Handles
-    ``python3 /path/hook.py``, ``/usr/bin/env bash hook.sh``, and the
-    common bare-path form.
-    """
-    try:
-        parts = shlex.split(command)
-    except ValueError:
-        return command
-    if not parts:
-        return command
-    for part in parts:
-        if part.lower().endswith(_SCRIPT_EXTENSIONS):
-            return part
-    for part in parts:
-        if "/" in part or part.startswith("~"):
-            return part
-    return parts[0]
-
-
-# ---------------------------------------------------------------------------
-# Helpers for accept-hooks resolution
-# ---------------------------------------------------------------------------
-
-def _resolve_effective_accept(
-    cfg: Dict[str, Any], accept_hooks_arg: bool,
-) -> bool:
-    """Combine all three opt-in channels into a single boolean.
-
-    Precedence (any truthy source flips us on):
-      1. ``--accept-hooks`` flag (CLI) / explicit argument
-      2. ``HERMES_ACCEPT_HOOKS`` env var
-      3. ``hooks_auto_accept: true`` in ``cli-config.yaml``
-    """
-    if accept_hooks_arg:
-        return True
-    env = os.environ.get("HERMES_ACCEPT_HOOKS", "").strip().lower()
-    if env in ("1", "true", "yes", "on"):
-        return True
-    cfg_val = cfg.get("hooks_auto_accept", False)
-    return bool(cfg_val)
-
-
-# ---------------------------------------------------------------------------
-# Introspection (used by `hermes hooks` CLI)
-# ---------------------------------------------------------------------------
-
-def allowlist_entry_for(event: str, command: str) -> Optional[Dict[str, Any]]:
-    """Return the allowlist record for this pair, if any."""
-    for e in load_allowlist().get("approvals", []):
-        if (
-            isinstance(e, dict)
-            and e.get("event") == event
-            and e.get("command") == command
-        ):
-            return e
-    return None
-
-
-def script_mtime_iso(command: str) -> Optional[str]:
-    """ISO-8601 mtime of the resolved script path, or ``None`` if the
-    script is missing."""
-    path = _command_script_path(command)
-    if not path:
-        return None
-    try:
-        expanded = os.path.expanduser(path)
-        return datetime.fromtimestamp(
-            os.path.getmtime(expanded), tz=timezone.utc,
-        ).isoformat().replace("+00:00", "Z")
-    except OSError:
-        return None
-
-
-def script_is_executable(command: str) -> bool:
-    """Return ``True`` iff ``command`` is runnable as configured.
-
-    For a bare invocation (``/path/hook.sh``) the script itself must be
-    executable.  For interpreter-prefixed commands (``python3
-    /path/hook.py``, ``/usr/bin/env bash hook.sh``) the script just has
-    to be readable — the interpreter doesn't care about the ``X_OK``
-    bit.  Mirrors what ``_spawn`` would actually do at runtime."""
-    path = _command_script_path(command)
-    if not path:
-        return False
-    expanded = os.path.expanduser(path)
-    if not os.path.isfile(expanded):
-        return False
-    try:
-        argv = shlex.split(command)
-    except ValueError:
-        return False
-    is_bare_invocation = bool(argv) and argv[0] == path
-    required = os.X_OK if is_bare_invocation else os.R_OK
-    return os.access(expanded, required)
-
-
-def run_once(
-    spec: ShellHookSpec, kwargs: Dict[str, Any],
-) -> Dict[str, Any]:
-    """Fire a single shell-hook invocation with a synthetic payload.
-    Used by ``hermes hooks test`` and ``hermes hooks doctor``.
-
-    ``kwargs`` is the same dict that :func:`hermes_cli.plugins.invoke_hook`
-    would pass at runtime.  It is routed through :func:`_serialize_payload`
-    so the synthetic stdin exactly matches what a real hook firing would
-    produce — otherwise scripts tested via ``hermes hooks test`` could
-    diverge silently from production behaviour.
-
-    Returns the :func:`_spawn` diagnostic dict plus a ``parsed`` field
-    holding the canonical Hermes-wire-shape response."""
-    stdin_json = _serialize_payload(spec.event, kwargs)
-    result = _spawn(spec, stdin_json)
-    result["parsed"] = _parse_response(spec.event, result["stdout"])
-    return result
--- a/agent/skill_commands.py
+++ b/agent/skill_commands.py
@@ -8,13 +8,10 @@ can invoke skills via /skill-name commands and prompt-only built-ins like
 import json
 import logging
 import re
-import subprocess
 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]] = {}
@@ -23,110 +20,6 @@ _PLAN_SLUG_RE = re.compile(r"[^a-z0-9]+")
 _SKILL_INVALID_CHARS = re.compile(r"[^a-z0-9-]")
 _SKILL_MULTI_HYPHEN = re.compile(r"-{2,}")

-# Matches ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} tokens in SKILL.md.
-# Tokens that don't resolve (e.g. ${HERMES_SESSION_ID} with no session) are
-# left as-is so the user can debug them.
-_SKILL_TEMPLATE_RE = re.compile(r"\$\{(HERMES_SKILL_DIR|HERMES_SESSION_ID)\}")
-
-# Matches inline shell snippets like:  !`date +%Y-%m-%d`
-# Non-greedy, single-line only — no newlines inside the backticks.
-_INLINE_SHELL_RE = re.compile(r"!`([^`\n]+)`")
-
-# Cap inline-shell output so a runaway command can't blow out the context.
-_INLINE_SHELL_MAX_OUTPUT = 4000
-
-
-def _load_skills_config() -> dict:
-    """Load the ``skills`` section of config.yaml (best-effort)."""
-    try:
-        from hermes_cli.config import load_config
-
-        cfg = load_config() or {}
-        skills_cfg = cfg.get("skills")
-        if isinstance(skills_cfg, dict):
-            return skills_cfg
-    except Exception:
-        logger.debug("Could not read skills config", exc_info=True)
-    return {}
-
-
-def _substitute_template_vars(
-    content: str,
-    skill_dir: Path | None,
-    session_id: str | None,
-) -> str:
-    """Replace ${HERMES_SKILL_DIR} / ${HERMES_SESSION_ID} in skill content.
-
-    Only substitutes tokens for which a concrete value is available —
-    unresolved tokens are left in place so the author can spot them.
-    """
-    if not content:
-        return content
-
-    skill_dir_str = str(skill_dir) if skill_dir else None
-
-    def _replace(match: re.Match) -> str:
-        token = match.group(1)
-        if token == "HERMES_SKILL_DIR" and skill_dir_str:
-            return skill_dir_str
-        if token == "HERMES_SESSION_ID" and session_id:
-            return str(session_id)
-        return match.group(0)
-
-    return _SKILL_TEMPLATE_RE.sub(_replace, content)
-
-
-def _run_inline_shell(command: str, cwd: Path | None, timeout: int) -> str:
-    """Execute a single inline-shell snippet and return its stdout (trimmed).
-
-    Failures return a short ``[inline-shell error: ...]`` marker instead of
-    raising, so one bad snippet can't wreck the whole skill message.
-    """
-    try:
-        completed = subprocess.run(
-            ["bash", "-c", command],
-            cwd=str(cwd) if cwd else None,
-            capture_output=True,
-            text=True,
-            timeout=max(1, int(timeout)),
-            check=False,
-        )
-    except subprocess.TimeoutExpired:
-        return f"[inline-shell timeout after {timeout}s: {command}]"
-    except FileNotFoundError:
-        return f"[inline-shell error: bash not found]"
-    except Exception as exc:
-        return f"[inline-shell error: {exc}]"
-
-    output = (completed.stdout or "").rstrip("\n")
-    if not output and completed.stderr:
-        output = completed.stderr.rstrip("\n")
-    if len(output) > _INLINE_SHELL_MAX_OUTPUT:
-        output = output[:_INLINE_SHELL_MAX_OUTPUT] + "…[truncated]"
-    return output
-
-
-def _expand_inline_shell(
-    content: str,
-    skill_dir: Path | None,
-    timeout: int,
-) -> str:
-    """Replace every !`cmd` snippet in ``content`` with its stdout.
-
-    Runs each snippet with the skill directory as CWD so relative paths in
-    the snippet work the way the author expects.
-    """
-    if "!`" not in content:
-        return content
-
-    def _replace(match: re.Match) -> str:
-        cmd = match.group(1).strip()
-        if not cmd:
-            return ""
-        return _run_inline_shell(cmd, skill_dir, timeout)
-
-    return _INLINE_SHELL_RE.sub(_replace, content)
-

 def build_plan_path(
    user_instruction: str = "",
@@ -177,14 +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:
@@ -222,7 +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}")
@@ -238,36 +124,14 @@ def _build_skill_message(
    activation_note: str,
    user_instruction: str = "",
    runtime_note: str = "",
-    session_id: str | None = None,
 ) -> str:
    """Format a loaded skill into a user/system message payload."""
    from tools.skills_tool import SKILLS_DIR

    content = str(loaded_skill.get("content") or "")

-    # ── Template substitution and inline-shell expansion ──
-    # Done before anything else so downstream blocks (setup notes,
-    # supporting-file hints) see the expanded content.
-    skills_cfg = _load_skills_config()
-    if skills_cfg.get("template_vars", True):
-        content = _substitute_template_vars(content, skill_dir, session_id)
-    if skills_cfg.get("inline_shell", False):
-        timeout = int(skills_cfg.get("inline_shell_timeout", 10) or 10)
-        content = _expand_inline_shell(content, skill_dir, timeout)
-
    parts = [activation_note, "", content.strip()]

-    # ── Inject the absolute skill directory so the agent can reference
-    #    bundled scripts without an extra skill_view() round-trip. ──
-    if skill_dir:
-        parts.append("")
-        parts.append(f"[Skill directory: {skill_dir}]")
-        parts.append(
-            "Resolve any relative paths in this skill (e.g. `scripts/foo.js`, "
-            "`templates/config.yaml`) against that directory, then run them "
-            "with the terminal tool using the absolute path."
-        )
-
    # ── Inject resolved skill config values ──
    _inject_skill_config(loaded_skill, parts)

@@ -315,13 +179,11 @@ def _build_skill_message(
            # Skill is from an external dir — use the skill name instead
            skill_view_target = skill_dir.name
        parts.append("")
-        parts.append("[This skill has supporting files:]")
+        parts.append("[This skill has supporting files you can load with the skill_view tool:]")
        for sf in supporting:
-            parts.append(f"- {sf}  ->  {skill_dir / sf}")
+            parts.append(f"- {sf}")
        parts.append(
-            f'\nLoad any of these with skill_view(name="{skill_view_target}", '
-            f'file_path="<path>"), or run scripts directly by absolute path '
-            f"(e.g. `node {skill_dir}/scripts/foo.js`)."
+            f'\nTo view any of these, use: skill_view(name="{skill_view_target}", file_path="<path>")'
        )

    if user_instruction:
@@ -461,7 +323,6 @@ def build_skill_invocation_message(
        activation_note,
        user_instruction=user_instruction,
        runtime_note=runtime_note,
-        session_id=task_id,
    )


@@ -500,7 +361,6 @@ def build_preloaded_skills_prompt(
                loaded_skill,
                skill_dir,
                activation_note,
-                session_id=task_id,
            )
        )
        loaded_names.append(skill_name)
--- a/agent/skill_utils.py
+++ b/agent/skill_utils.py
@@ -10,7 +10,7 @@ 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

@@ -441,25 +441,3 @@ 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))
--- a/agent/smart_model_routing.py
+++ b/agent/smart_model_routing.py
@@ -0,0 +1,195 @@
+"""Helpers for optional cheap-vs-strong model routing."""
+
+from __future__ import annotations
+
+import os
+import re
+from typing import Any, Dict, Optional
+
+from utils import is_truthy_value
+
+_COMPLEX_KEYWORDS = {
+    "debug",
+    "debugging",
+    "implement",
+    "implementation",
+    "refactor",
+    "patch",
+    "traceback",
+    "stacktrace",
+    "exception",
+    "error",
+    "analyze",
+    "analysis",
+    "investigate",
+    "architecture",
+    "design",
+    "compare",
+    "benchmark",
+    "optimize",
+    "optimise",
+    "review",
+    "terminal",
+    "shell",
+    "tool",
+    "tools",
+    "pytest",
+    "test",
+    "tests",
+    "plan",
+    "planning",
+    "delegate",
+    "subagent",
+    "cron",
+    "docker",
+    "kubernetes",
+}
+
+_URL_RE = re.compile(r"https?://|www\.", re.IGNORECASE)
+
+
+def _coerce_bool(value: Any, default: bool = False) -> bool:
+    return is_truthy_value(value, default=default)
+
+
+def _coerce_int(value: Any, default: int) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def choose_cheap_model_route(user_message: str, routing_config: Optional[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
+    """Return the configured cheap-model route when a message looks simple.
+
+    Conservative by design: if the message has signs of code/tool/debugging/
+    long-form work, keep the primary model.
+    """
+    cfg = routing_config or {}
+    if not _coerce_bool(cfg.get("enabled"), False):
+        return None
+
+    cheap_model = cfg.get("cheap_model") or {}
+    if not isinstance(cheap_model, dict):
+        return None
+    provider = str(cheap_model.get("provider") or "").strip().lower()
+    model = str(cheap_model.get("model") or "").strip()
+    if not provider or not model:
+        return None
+
+    text = (user_message or "").strip()
+    if not text:
+        return None
+
+    max_chars = _coerce_int(cfg.get("max_simple_chars"), 160)
+    max_words = _coerce_int(cfg.get("max_simple_words"), 28)
+
+    if len(text) > max_chars:
+        return None
+    if len(text.split()) > max_words:
+        return None
+    if text.count("\n") > 1:
+        return None
+    if "```" in text or "`" in text:
+        return None
+    if _URL_RE.search(text):
+        return None
+
+    lowered = text.lower()
+    words = {token.strip(".,:;!?()[]{}\"'`") for token in lowered.split()}
+    if words & _COMPLEX_KEYWORDS:
+        return None
+
+    route = dict(cheap_model)
+    route["provider"] = provider
+    route["model"] = model
+    route["routing_reason"] = "simple_turn"
+    return route
+
+
+def resolve_turn_route(user_message: str, routing_config: Optional[Dict[str, Any]], primary: Dict[str, Any]) -> Dict[str, Any]:
+    """Resolve the effective model/runtime for one turn.
+
+    Returns a dict with model/runtime/signature/label fields.
+    """
+    route = choose_cheap_model_route(user_message, routing_config)
+    if not route:
+        return {
+            "model": primary.get("model"),
+            "runtime": {
+                "api_key": primary.get("api_key"),
+                "base_url": primary.get("base_url"),
+                "provider": primary.get("provider"),
+                "api_mode": primary.get("api_mode"),
+                "command": primary.get("command"),
+                "args": list(primary.get("args") or []),
+                "credential_pool": primary.get("credential_pool"),
+            },
+            "label": None,
+            "signature": (
+                primary.get("model"),
+                primary.get("provider"),
+                primary.get("base_url"),
+                primary.get("api_mode"),
+                primary.get("command"),
+                tuple(primary.get("args") or ()),
+            ),
+        }
+
+    from hermes_cli.runtime_provider import resolve_runtime_provider
+
+    explicit_api_key = None
+    api_key_env = str(route.get("api_key_env") or "").strip()
+    if api_key_env:
+        explicit_api_key = os.getenv(api_key_env) or None
+
+    try:
+        runtime = resolve_runtime_provider(
+            requested=route.get("provider"),
+            explicit_api_key=explicit_api_key,
+            explicit_base_url=route.get("base_url"),
+        )
+    except Exception:
+        return {
+            "model": primary.get("model"),
+            "runtime": {
+                "api_key": primary.get("api_key"),
+                "base_url": primary.get("base_url"),
+                "provider": primary.get("provider"),
+                "api_mode": primary.get("api_mode"),
+                "command": primary.get("command"),
+                "args": list(primary.get("args") or []),
+                "credential_pool": primary.get("credential_pool"),
+            },
+            "label": None,
+            "signature": (
+                primary.get("model"),
+                primary.get("provider"),
+                primary.get("base_url"),
+                primary.get("api_mode"),
+                primary.get("command"),
+                tuple(primary.get("args") or ()),
+            ),
+        }
+
+    return {
+        "model": route.get("model"),
+        "runtime": {
+            "api_key": runtime.get("api_key"),
+            "base_url": runtime.get("base_url"),
+            "provider": runtime.get("provider"),
+            "api_mode": runtime.get("api_mode"),
+            "command": runtime.get("command"),
+            "args": list(runtime.get("args") or []),
+            "credential_pool": runtime.get("credential_pool"),
+        },
+        "label": f"smart route → {route.get('model')} ({runtime.get('provider')})",
+        "signature": (
+            route.get("model"),
+            runtime.get("provider"),
+            runtime.get("base_url"),
+            runtime.get("api_mode"),
+            runtime.get("command"),
+            tuple(runtime.get("args") or ()),
+        ),
+    }
--- a/agent/title_generator.py
+++ b/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,
--- a/agent/transports/init.py
+++ b/agent/transports/init.py
@@ -1,51 +0,0 @@
-"""Transport layer types and registry for provider response normalization.
-
-Usage:
-    from agent.transports import get_transport
-    transport = get_transport("anthropic_messages")
-    result = transport.normalize_response(raw_response)
-"""
-
-from agent.transports.types import NormalizedResponse, ToolCall, Usage, build_tool_call, map_finish_reason  # noqa: F401
-
-_REGISTRY: dict = {}
-
-
-def register_transport(api_mode: str, transport_cls: type) -> None:
-    """Register a transport class for an api_mode string."""
-    _REGISTRY[api_mode] = transport_cls
-
-
-def get_transport(api_mode: str):
-    """Get a transport instance for the given api_mode.
-
-    Returns None if no transport is registered for this api_mode.
-    This allows gradual migration — call sites can check for None
-    and fall back to the legacy code path.
-    """
-    if not _REGISTRY:
-        _discover_transports()
-    cls = _REGISTRY.get(api_mode)
-    if cls is None:
-        return None
-    return cls()
-
-
-def _discover_transports() -> None:
-    """Import all transport modules to trigger auto-registration."""
-    try:
-        import agent.transports.anthropic  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.codex  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.chat_completions  # noqa: F401
-    except ImportError:
-        pass
-    try:
-        import agent.transports.bedrock  # noqa: F401
-    except ImportError:
-        pass
--- a/agent/transports/anthropic.py
+++ b/agent/transports/anthropic.py
@@ -1,150 +0,0 @@
-"""Anthropic Messages API transport.
-
-Delegates to the existing adapter functions in agent/anthropic_adapter.py.
-This transport owns format conversion and normalization — NOT client lifecycle.
-"""
-
-from typing import Any, Dict, List, Optional
-
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse
-
-
-class AnthropicTransport(ProviderTransport):
-    """Transport for api_mode='anthropic_messages'.
-
-    Wraps the existing functions in anthropic_adapter.py behind the
-    ProviderTransport ABC.  Each method delegates — no logic is duplicated.
-    """
-
-    @property
-    def api_mode(self) -> str:
-        return "anthropic_messages"
-
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI messages to Anthropic (system, messages) tuple.
-
-        kwargs:
-            base_url: Optional[str] — affects thinking signature handling.
-        """
-        from agent.anthropic_adapter import convert_messages_to_anthropic
-
-        base_url = kwargs.get("base_url")
-        return convert_messages_to_anthropic(messages, base_url=base_url)
-
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        """Convert OpenAI tool schemas to Anthropic input_schema format."""
-        from agent.anthropic_adapter import convert_tools_to_anthropic
-
-        return convert_tools_to_anthropic(tools)
-
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build Anthropic messages.create() kwargs.
-
-        Calls convert_messages and convert_tools internally.
-
-        params (all optional):
-            max_tokens: int
-            reasoning_config: dict | None
-            tool_choice: str | None
-            is_oauth: bool
-            preserve_dots: bool
-            context_length: int | None
-            base_url: str | None
-            fast_mode: bool
-        """
-        from agent.anthropic_adapter import build_anthropic_kwargs
-
-        return build_anthropic_kwargs(
-            model=model,
-            messages=messages,
-            tools=tools,
-            max_tokens=params.get("max_tokens", 16384),
-            reasoning_config=params.get("reasoning_config"),
-            tool_choice=params.get("tool_choice"),
-            is_oauth=params.get("is_oauth", False),
-            preserve_dots=params.get("preserve_dots", False),
-            context_length=params.get("context_length"),
-            base_url=params.get("base_url"),
-            fast_mode=params.get("fast_mode", False),
-        )
-
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize Anthropic response to NormalizedResponse.
-
-        Calls the adapter's v1 normalize and maps the (SimpleNamespace, finish_reason)
-        tuple to the shared NormalizedResponse type.
-        """
-        from agent.anthropic_adapter import normalize_anthropic_response
-        from agent.transports.types import build_tool_call
-
-        strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
-        assistant_msg, finish_reason = normalize_anthropic_response(response, strip_tool_prefix)
-
-        tool_calls = None
-        if assistant_msg.tool_calls:
-            tool_calls = [
-                build_tool_call(id=tc.id, name=tc.function.name, arguments=tc.function.arguments)
-                for tc in assistant_msg.tool_calls
-            ]
-
-        provider_data = {}
-        if getattr(assistant_msg, "reasoning_details", None):
-            provider_data["reasoning_details"] = assistant_msg.reasoning_details
-
-        return NormalizedResponse(
-            content=assistant_msg.content,
-            tool_calls=tool_calls,
-            finish_reason=finish_reason,
-            reasoning=getattr(assistant_msg, "reasoning", None),
-            usage=None,
-            provider_data=provider_data or None,
-        )
-
-    def validate_response(self, response: Any) -> bool:
-        """Check Anthropic response structure is valid."""
-        if response is None:
-            return False
-        content_blocks = getattr(response, "content", None)
-        if not isinstance(content_blocks, list):
-            return False
-        if not content_blocks:
-            return False
-        return True
-
-    def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
-        """Extract Anthropic cache_read and cache_creation token counts."""
-        usage = getattr(response, "usage", None)
-        if usage is None:
-            return None
-        cached = getattr(usage, "cache_read_input_tokens", 0) or 0
-        written = getattr(usage, "cache_creation_input_tokens", 0) or 0
-        if cached or written:
-            return {"cached_tokens": cached, "creation_tokens": written}
-        return None
-
-    # Promote the adapter's canonical mapping to module level so it's shared
-    _STOP_REASON_MAP = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
-    }
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        """Map Anthropic stop_reason to OpenAI finish_reason."""
-        return self._STOP_REASON_MAP.get(raw_reason, "stop")
-
-
-# Auto-register on import
-from agent.transports import register_transport  # noqa: E402
-
-register_transport("anthropic_messages", AnthropicTransport)
--- a/agent/transports/base.py
+++ b/agent/transports/base.py
@@ -1,89 +0,0 @@
-"""Abstract base for provider transports.
-
-A transport owns the data path for one api_mode:
-  convert_messages → convert_tools → build_kwargs → normalize_response
-
-It does NOT own: client construction, streaming, credential refresh,
-prompt caching, interrupt handling, or retry logic.  Those stay on AIAgent.
-"""
-
-from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
-
-from agent.transports.types import NormalizedResponse
-
-
-class ProviderTransport(ABC):
-    """Base class for provider-specific format conversion and normalization."""
-
-    @property
-    @abstractmethod
-    def api_mode(self) -> str:
-        """The api_mode string this transport handles (e.g. 'anthropic_messages')."""
-        ...
-
-    @abstractmethod
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI-format messages to provider-native format.
-
-        Returns provider-specific structure (e.g. (system, messages) for Anthropic,
-        or the messages list unchanged for chat_completions).
-        """
-        ...
-
-    @abstractmethod
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        """Convert OpenAI-format tool definitions to provider-native format.
-
-        Returns provider-specific tool list (e.g. Anthropic input_schema format).
-        """
-        ...
-
-    @abstractmethod
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build the complete API call kwargs dict.
-
-        This is the primary entry point — it typically calls convert_messages()
-        and convert_tools() internally, then adds model-specific config.
-
-        Returns a dict ready to be passed to the provider's SDK client.
-        """
-        ...
-
-    @abstractmethod
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize a raw provider response to the shared NormalizedResponse type.
-
-        This is the only method that returns a transport-layer type.
-        """
-        ...
-
-    def validate_response(self, response: Any) -> bool:
-        """Optional: check if the raw response is structurally valid.
-
-        Returns True if valid, False if the response should be treated as invalid.
-        Default implementation always returns True.
-        """
-        return True
-
-    def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
-        """Optional: extract provider-specific cache hit/creation stats.
-
-        Returns dict with 'cached_tokens' and 'creation_tokens', or None.
-        Default returns None.
-        """
-        return None
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        """Optional: map provider-specific stop reason to OpenAI equivalent.
-
-        Default returns the raw reason unchanged.  Override for providers
-        with different stop reason vocabularies.
-        """
-        return raw_reason
--- a/agent/transports/bedrock.py
+++ b/agent/transports/bedrock.py
@@ -1,154 +0,0 @@
-"""AWS Bedrock Converse API transport.
-
-Delegates to the existing adapter functions in agent/bedrock_adapter.py.
-Bedrock uses its own boto3 client (not the OpenAI SDK), so the transport
-owns format conversion and normalization, while client construction and
-boto3 calls stay on AIAgent.
-"""
-
-from typing import Any, Dict, List, Optional
-
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse, ToolCall, Usage
-
-
-class BedrockTransport(ProviderTransport):
-    """Transport for api_mode='bedrock_converse'."""
-
-    @property
-    def api_mode(self) -> str:
-        return "bedrock_converse"
-
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI messages to Bedrock Converse format."""
-        from agent.bedrock_adapter import convert_messages_to_converse
-        return convert_messages_to_converse(messages)
-
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        """Convert OpenAI tool schemas to Bedrock Converse toolConfig."""
-        from agent.bedrock_adapter import convert_tools_to_converse
-        return convert_tools_to_converse(tools)
-
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build Bedrock converse() kwargs.
-
-        Calls convert_messages and convert_tools internally.
-
-        params:
-            max_tokens: int — output token limit (default 4096)
-            temperature: float | None
-            guardrail_config: dict | None — Bedrock guardrails
-            region: str — AWS region (default 'us-east-1')
-        """
-        from agent.bedrock_adapter import build_converse_kwargs
-
-        region = params.get("region", "us-east-1")
-        guardrail = params.get("guardrail_config")
-
-        kwargs = build_converse_kwargs(
-            model=model,
-            messages=messages,
-            tools=tools,
-            max_tokens=params.get("max_tokens", 4096),
-            temperature=params.get("temperature"),
-            guardrail_config=guardrail,
-        )
-        # Sentinel keys for dispatch — agent pops these before the boto3 call
-        kwargs["__bedrock_converse__"] = True
-        kwargs["__bedrock_region__"] = region
-        return kwargs
-
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize Bedrock response to NormalizedResponse.
-
-        Handles two shapes:
-        1. Raw boto3 dict (from direct converse() calls)
-        2. Already-normalized SimpleNamespace with .choices (from dispatch site)
-        """
-        from agent.bedrock_adapter import normalize_converse_response
-
-        # Normalize to OpenAI-compatible SimpleNamespace
-        if hasattr(response, "choices") and response.choices:
-            # Already normalized at dispatch site
-            ns = response
-        else:
-            # Raw boto3 dict
-            ns = normalize_converse_response(response)
-
-        choice = ns.choices[0]
-        msg = choice.message
-        finish_reason = choice.finish_reason or "stop"
-
-        tool_calls = None
-        if msg.tool_calls:
-            tool_calls = [
-                ToolCall(
-                    id=tc.id,
-                    name=tc.function.name,
-                    arguments=tc.function.arguments,
-                )
-                for tc in msg.tool_calls
-            ]
-
-        usage = None
-        if hasattr(ns, "usage") and ns.usage:
-            u = ns.usage
-            usage = Usage(
-                prompt_tokens=getattr(u, "prompt_tokens", 0) or 0,
-                completion_tokens=getattr(u, "completion_tokens", 0) or 0,
-                total_tokens=getattr(u, "total_tokens", 0) or 0,
-            )
-
-        reasoning = getattr(msg, "reasoning", None) or getattr(msg, "reasoning_content", None)
-
-        return NormalizedResponse(
-            content=msg.content,
-            tool_calls=tool_calls,
-            finish_reason=finish_reason,
-            reasoning=reasoning,
-            usage=usage,
-        )
-
-    def validate_response(self, response: Any) -> bool:
-        """Check Bedrock response structure.
-
-        After normalize_converse_response, the response has OpenAI-compatible
-        .choices — same check as chat_completions.
-        """
-        if response is None:
-            return False
-        # Raw Bedrock dict response — check for 'output' key
-        if isinstance(response, dict):
-            return "output" in response
-        # Already-normalized SimpleNamespace
-        if hasattr(response, "choices"):
-            return bool(response.choices)
-        return False
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        """Map Bedrock stop reason to OpenAI finish_reason.
-
-        The adapter already does this mapping inside normalize_converse_response,
-        so this is only used for direct access to raw responses.
-        """
-        _MAP = {
-            "end_turn": "stop",
-            "tool_use": "tool_calls",
-            "max_tokens": "length",
-            "stop_sequence": "stop",
-            "guardrail_intervened": "content_filter",
-            "content_filtered": "content_filter",
-        }
-        return _MAP.get(raw_reason, "stop")
-
-
-# Auto-register on import
-from agent.transports import register_transport  # noqa: E402
-
-register_transport("bedrock_converse", BedrockTransport)
--- a/agent/transports/chat_completions.py
+++ b/agent/transports/chat_completions.py
@@ -1,387 +0,0 @@
-"""OpenAI Chat Completions transport.
-
-Handles the default api_mode ('chat_completions') used by ~16 OpenAI-compatible
-providers (OpenRouter, Nous, NVIDIA, Qwen, Ollama, DeepSeek, xAI, Kimi, etc.).
-
-Messages and tools are already in OpenAI format — convert_messages and
-convert_tools are near-identity.  The complexity lives in build_kwargs
-which has provider-specific conditionals for max_tokens defaults,
-reasoning configuration, temperature handling, and extra_body assembly.
-"""
-
-import copy
-from typing import Any, Dict, List, Optional
-
-from agent.prompt_builder import DEVELOPER_ROLE_MODELS
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse, ToolCall, Usage
-
-
-class ChatCompletionsTransport(ProviderTransport):
-    """Transport for api_mode='chat_completions'.
-
-    The default path for OpenAI-compatible providers.
-    """
-
-    @property
-    def api_mode(self) -> str:
-        return "chat_completions"
-
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> List[Dict[str, Any]]:
-        """Messages are already in OpenAI format — sanitize Codex leaks only.
-
-        Strips Codex Responses API fields (``codex_reasoning_items`` on the
-        message, ``call_id``/``response_item_id`` on tool_calls) that strict
-        chat-completions providers reject with 400/422.
-        """
-        needs_sanitize = False
-        for msg in messages:
-            if not isinstance(msg, dict):
-                continue
-            if "codex_reasoning_items" in msg:
-                needs_sanitize = True
-                break
-            tool_calls = msg.get("tool_calls")
-            if isinstance(tool_calls, list):
-                for tc in tool_calls:
-                    if isinstance(tc, dict) and ("call_id" in tc or "response_item_id" in tc):
-                        needs_sanitize = True
-                        break
-                if needs_sanitize:
-                    break
-
-        if not needs_sanitize:
-            return messages
-
-        sanitized = copy.deepcopy(messages)
-        for msg in sanitized:
-            if not isinstance(msg, dict):
-                continue
-            msg.pop("codex_reasoning_items", None)
-            tool_calls = msg.get("tool_calls")
-            if isinstance(tool_calls, list):
-                for tc in tool_calls:
-                    if isinstance(tc, dict):
-                        tc.pop("call_id", None)
-                        tc.pop("response_item_id", None)
-        return sanitized
-
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
-        """Tools are already in OpenAI format — identity."""
-        return tools
-
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build chat.completions.create() kwargs.
-
-        This is the most complex transport method — it handles ~16 providers
-        via params rather than subclasses.
-
-        params:
-            timeout: float — API call timeout
-            max_tokens: int | None — user-configured max tokens
-            ephemeral_max_output_tokens: int | None — one-shot override (error recovery)
-            max_tokens_param_fn: callable — returns {max_tokens: N} or {max_completion_tokens: N}
-            reasoning_config: dict | None
-            request_overrides: dict | None
-            session_id: str | None
-            qwen_session_metadata: dict | None — {sessionId, promptId} precomputed
-            model_lower: str — lowercase model name for pattern matching
-            # Provider detection flags (all optional, default False)
-            is_openrouter: bool
-            is_nous: bool
-            is_qwen_portal: bool
-            is_github_models: bool
-            is_nvidia_nim: bool
-            is_kimi: bool
-            is_custom_provider: bool
-            ollama_num_ctx: int | None
-            # Provider routing
-            provider_preferences: dict | None
-            # Qwen-specific
-            qwen_prepare_fn: callable | None — runs AFTER codex sanitization
-            qwen_prepare_inplace_fn: callable | None — in-place variant for deepcopied lists
-            # Temperature
-            fixed_temperature: Any — from _fixed_temperature_for_model()
-            omit_temperature: bool
-            # Reasoning
-            supports_reasoning: bool
-            github_reasoning_extra: dict | None
-            # Claude on OpenRouter/Nous max output
-            anthropic_max_output: int | None
-            # Extra
-            extra_body_additions: dict | None — pre-built extra_body entries
-        """
-        # Codex sanitization: drop reasoning_items / call_id / response_item_id
-        sanitized = self.convert_messages(messages)
-
-        # Qwen portal prep AFTER codex sanitization.  If sanitize already
-        # deepcopied, reuse that copy via the in-place variant to avoid a
-        # second deepcopy.
-        is_qwen = params.get("is_qwen_portal", False)
-        if is_qwen:
-            qwen_prep = params.get("qwen_prepare_fn")
-            qwen_prep_inplace = params.get("qwen_prepare_inplace_fn")
-            if sanitized is messages:
-                if qwen_prep is not None:
-                    sanitized = qwen_prep(sanitized)
-            else:
-                # Already deepcopied — transform in place
-                if qwen_prep_inplace is not None:
-                    qwen_prep_inplace(sanitized)
-                elif qwen_prep is not None:
-                    sanitized = qwen_prep(sanitized)
-
-        # Developer role swap for GPT-5/Codex models
-        model_lower = params.get("model_lower", (model or "").lower())
-        if (
-            sanitized
-            and isinstance(sanitized[0], dict)
-            and sanitized[0].get("role") == "system"
-            and any(p in model_lower for p in DEVELOPER_ROLE_MODELS)
-        ):
-            sanitized = list(sanitized)
-            sanitized[0] = {**sanitized[0], "role": "developer"}
-
-        api_kwargs: Dict[str, Any] = {
-            "model": model,
-            "messages": sanitized,
-        }
-
-        timeout = params.get("timeout")
-        if timeout is not None:
-            api_kwargs["timeout"] = timeout
-
-        # Temperature
-        fixed_temp = params.get("fixed_temperature")
-        omit_temp = params.get("omit_temperature", False)
-        if omit_temp:
-            api_kwargs.pop("temperature", None)
-        elif fixed_temp is not None:
-            api_kwargs["temperature"] = fixed_temp
-
-        # Qwen metadata (caller precomputes {sessionId, promptId})
-        qwen_meta = params.get("qwen_session_metadata")
-        if qwen_meta and is_qwen:
-            api_kwargs["metadata"] = qwen_meta
-
-        # Tools
-        if tools:
-            api_kwargs["tools"] = tools
-
-        # max_tokens resolution — priority: ephemeral > user > provider default
-        max_tokens_fn = params.get("max_tokens_param_fn")
-        ephemeral = params.get("ephemeral_max_output_tokens")
-        max_tokens = params.get("max_tokens")
-        anthropic_max_out = params.get("anthropic_max_output")
-        is_nvidia_nim = params.get("is_nvidia_nim", False)
-        is_kimi = params.get("is_kimi", False)
-        reasoning_config = params.get("reasoning_config")
-
-        if ephemeral is not None and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(ephemeral))
-        elif max_tokens is not None and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(max_tokens))
-        elif is_nvidia_nim and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(16384))
-        elif is_qwen and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(65536))
-        elif is_kimi and max_tokens_fn:
-            # Kimi/Moonshot: 32000 matches Kimi CLI's default
-            api_kwargs.update(max_tokens_fn(32000))
-        elif anthropic_max_out is not None:
-            api_kwargs["max_tokens"] = anthropic_max_out
-
-        # Kimi: top-level reasoning_effort (unless thinking disabled)
-        if is_kimi:
-            _kimi_thinking_off = bool(
-                reasoning_config
-                and isinstance(reasoning_config, dict)
-                and reasoning_config.get("enabled") is False
-            )
-            if not _kimi_thinking_off:
-                _kimi_effort = "medium"
-                if reasoning_config and isinstance(reasoning_config, dict):
-                    _e = (reasoning_config.get("effort") or "").strip().lower()
-                    if _e in ("low", "medium", "high"):
-                        _kimi_effort = _e
-                api_kwargs["reasoning_effort"] = _kimi_effort
-
-        # extra_body assembly
-        extra_body: Dict[str, Any] = {}
-
-        is_openrouter = params.get("is_openrouter", False)
-        is_nous = params.get("is_nous", False)
-        is_github_models = params.get("is_github_models", False)
-
-        provider_prefs = params.get("provider_preferences")
-        if provider_prefs and is_openrouter:
-            extra_body["provider"] = provider_prefs
-
-        # Kimi extra_body.thinking
-        if is_kimi:
-            _kimi_thinking_enabled = True
-            if reasoning_config and isinstance(reasoning_config, dict):
-                if reasoning_config.get("enabled") is False:
-                    _kimi_thinking_enabled = False
-            extra_body["thinking"] = {
-                "type": "enabled" if _kimi_thinking_enabled else "disabled",
-            }
-
-        # Reasoning
-        if params.get("supports_reasoning", False):
-            if is_github_models:
-                gh_reasoning = params.get("github_reasoning_extra")
-                if gh_reasoning is not None:
-                    extra_body["reasoning"] = gh_reasoning
-            else:
-                if reasoning_config is not None:
-                    rc = dict(reasoning_config)
-                    if is_nous and rc.get("enabled") is False:
-                        pass  # omit for Nous when disabled
-                    else:
-                        extra_body["reasoning"] = rc
-                else:
-                    extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
-
-        if is_nous:
-            extra_body["tags"] = ["product=hermes-agent"]
-
-        # Ollama num_ctx
-        ollama_ctx = params.get("ollama_num_ctx")
-        if ollama_ctx:
-            options = extra_body.get("options", {})
-            options["num_ctx"] = ollama_ctx
-            extra_body["options"] = options
-
-        # Ollama/custom think=false
-        if params.get("is_custom_provider", False):
-            if reasoning_config and isinstance(reasoning_config, dict):
-                _effort = (reasoning_config.get("effort") or "").strip().lower()
-                _enabled = reasoning_config.get("enabled", True)
-                if _effort == "none" or _enabled is False:
-                    extra_body["think"] = False
-
-        if is_qwen:
-            extra_body["vl_high_resolution_images"] = True
-
-        # Merge any pre-built extra_body additions
-        additions = params.get("extra_body_additions")
-        if additions:
-            extra_body.update(additions)
-
-        if extra_body:
-            api_kwargs["extra_body"] = extra_body
-
-        # Request overrides last (service_tier etc.)
-        overrides = params.get("request_overrides")
-        if overrides:
-            api_kwargs.update(overrides)
-
-        return api_kwargs
-
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize OpenAI ChatCompletion to NormalizedResponse.
-
-        For chat_completions, this is near-identity — the response is already
-        in OpenAI format.  extra_content on tool_calls (Gemini thought_signature)
-        is preserved via ToolCall.provider_data.  reasoning_details (OpenRouter
-        unified format) and reasoning_content (DeepSeek/Moonshot) are also
-        preserved for downstream replay.
-        """
-        choice = response.choices[0]
-        msg = choice.message
-        finish_reason = choice.finish_reason or "stop"
-
-        tool_calls = None
-        if msg.tool_calls:
-            tool_calls = []
-            for tc in msg.tool_calls:
-                # Preserve provider-specific extras on the tool call.
-                # Gemini 3 thinking models attach extra_content with
-                # thought_signature — without replay on the next turn the API
-                # rejects the request with 400.
-                tc_provider_data: Dict[str, Any] = {}
-                extra = getattr(tc, "extra_content", None)
-                if extra is None and hasattr(tc, "model_extra"):
-                    extra = (tc.model_extra or {}).get("extra_content")
-                if extra is not None:
-                    if hasattr(extra, "model_dump"):
-                        try:
-                            extra = extra.model_dump()
-                        except Exception:
-                            pass
-                    tc_provider_data["extra_content"] = extra
-                tool_calls.append(ToolCall(
-                    id=tc.id,
-                    name=tc.function.name,
-                    arguments=tc.function.arguments,
-                    provider_data=tc_provider_data or None,
-                ))
-
-        usage = None
-        if hasattr(response, "usage") and response.usage:
-            u = response.usage
-            usage = Usage(
-                prompt_tokens=getattr(u, "prompt_tokens", 0) or 0,
-                completion_tokens=getattr(u, "completion_tokens", 0) or 0,
-                total_tokens=getattr(u, "total_tokens", 0) or 0,
-            )
-
-        # Preserve reasoning fields separately.  DeepSeek/Moonshot use
-        # ``reasoning_content``; others use ``reasoning``.  Downstream code
-        # (_extract_reasoning, thinking-prefill retry) reads both distinctly,
-        # so keep them apart in provider_data rather than merging.
-        reasoning = getattr(msg, "reasoning", None)
-        reasoning_content = getattr(msg, "reasoning_content", None)
-
-        provider_data: Dict[str, Any] = {}
-        if reasoning_content:
-            provider_data["reasoning_content"] = reasoning_content
-        rd = getattr(msg, "reasoning_details", None)
-        if rd:
-            provider_data["reasoning_details"] = rd
-
-        return NormalizedResponse(
-            content=msg.content,
-            tool_calls=tool_calls,
-            finish_reason=finish_reason,
-            reasoning=reasoning,
-            usage=usage,
-            provider_data=provider_data or None,
-        )
-
-    def validate_response(self, response: Any) -> bool:
-        """Check that response has valid choices."""
-        if response is None:
-            return False
-        if not hasattr(response, "choices") or response.choices is None:
-            return False
-        if not response.choices:
-            return False
-        return True
-
-    def extract_cache_stats(self, response: Any) -> Optional[Dict[str, int]]:
-        """Extract OpenRouter/OpenAI cache stats from prompt_tokens_details."""
-        usage = getattr(response, "usage", None)
-        if usage is None:
-            return None
-        details = getattr(usage, "prompt_tokens_details", None)
-        if details is None:
-            return None
-        cached = getattr(details, "cached_tokens", 0) or 0
-        written = getattr(details, "cache_write_tokens", 0) or 0
-        if cached or written:
-            return {"cached_tokens": cached, "creation_tokens": written}
-        return None
-
-
-# Auto-register on import
-from agent.transports import register_transport  # noqa: E402
-
-register_transport("chat_completions", ChatCompletionsTransport)
--- a/agent/transports/codex.py
+++ b/agent/transports/codex.py
@@ -1,217 +0,0 @@
-"""OpenAI Responses API (Codex) transport.
-
-Delegates to the existing adapter functions in agent/codex_responses_adapter.py.
-This transport owns format conversion and normalization — NOT client lifecycle,
-streaming, or the _run_codex_stream() call path.
-"""
-
-from typing import Any, Dict, List, Optional
-
-from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse, ToolCall, Usage
-
-
-class ResponsesApiTransport(ProviderTransport):
-    """Transport for api_mode='codex_responses'.
-
-    Wraps the functions extracted into codex_responses_adapter.py (PR 1).
-    """
-
-    @property
-    def api_mode(self) -> str:
-        return "codex_responses"
-
-    def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI chat messages to Responses API input items."""
-        from agent.codex_responses_adapter import _chat_messages_to_responses_input
-        return _chat_messages_to_responses_input(messages)
-
-    def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
-        """Convert OpenAI tool schemas to Responses API function definitions."""
-        from agent.codex_responses_adapter import _responses_tools
-        return _responses_tools(tools)
-
-    def build_kwargs(
-        self,
-        model: str,
-        messages: List[Dict[str, Any]],
-        tools: Optional[List[Dict[str, Any]]] = None,
-        **params,
-    ) -> Dict[str, Any]:
-        """Build Responses API kwargs.
-
-        Calls convert_messages and convert_tools internally.
-
-        params:
-            instructions: str — system prompt (extracted from messages[0] if not given)
-            reasoning_config: dict | None — {effort, enabled}
-            session_id: str | None — used for prompt_cache_key + xAI conv header
-            max_tokens: int | None — max_output_tokens
-            request_overrides: dict | None — extra kwargs merged in
-            provider: str | None — provider name for backend-specific logic
-            base_url: str | None — endpoint URL
-            base_url_hostname: str | None — hostname for backend detection
-            is_github_responses: bool — Copilot/GitHub models backend
-            is_codex_backend: bool — chatgpt.com/backend-api/codex
-            is_xai_responses: bool — xAI/Grok backend
-            github_reasoning_extra: dict | None — Copilot reasoning params
-        """
-        from agent.codex_responses_adapter import (
-            _chat_messages_to_responses_input,
-            _responses_tools,
-        )
-
-        from run_agent import DEFAULT_AGENT_IDENTITY
-
-        instructions = params.get("instructions", "")
-        payload_messages = messages
-        if not instructions:
-            if messages and messages[0].get("role") == "system":
-                instructions = str(messages[0].get("content") or "").strip()
-                payload_messages = messages[1:]
-        if not instructions:
-            instructions = DEFAULT_AGENT_IDENTITY
-
-        is_github_responses = params.get("is_github_responses", False)
-        is_codex_backend = params.get("is_codex_backend", False)
-        is_xai_responses = params.get("is_xai_responses", False)
-
-        # Resolve reasoning effort
-        reasoning_effort = "medium"
-        reasoning_enabled = True
-        reasoning_config = params.get("reasoning_config")
-        if reasoning_config and isinstance(reasoning_config, dict):
-            if reasoning_config.get("enabled") is False:
-                reasoning_enabled = False
-            elif reasoning_config.get("effort"):
-                reasoning_effort = reasoning_config["effort"]
-
-        _effort_clamp = {"minimal": "low"}
-        reasoning_effort = _effort_clamp.get(reasoning_effort, reasoning_effort)
-
-        kwargs = {
-            "model": model,
-            "instructions": instructions,
-            "input": _chat_messages_to_responses_input(payload_messages),
-            "tools": _responses_tools(tools),
-            "tool_choice": "auto",
-            "parallel_tool_calls": True,
-            "store": False,
-        }
-
-        session_id = params.get("session_id")
-        if not is_github_responses and session_id:
-            kwargs["prompt_cache_key"] = session_id
-
-        if reasoning_enabled and is_xai_responses:
-            kwargs["include"] = ["reasoning.encrypted_content"]
-        elif reasoning_enabled:
-            if is_github_responses:
-                github_reasoning = params.get("github_reasoning_extra")
-                if github_reasoning is not None:
-                    kwargs["reasoning"] = github_reasoning
-            else:
-                kwargs["reasoning"] = {"effort": reasoning_effort, "summary": "auto"}
-                kwargs["include"] = ["reasoning.encrypted_content"]
-        elif not is_github_responses and not is_xai_responses:
-            kwargs["include"] = []
-
-        request_overrides = params.get("request_overrides")
-        if request_overrides:
-            kwargs.update(request_overrides)
-
-        max_tokens = params.get("max_tokens")
-        if max_tokens is not None and not is_codex_backend:
-            kwargs["max_output_tokens"] = max_tokens
-
-        if is_xai_responses and session_id:
-            kwargs["extra_headers"] = {"x-grok-conv-id": session_id}
-
-        return kwargs
-
-    def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize Codex Responses API response to NormalizedResponse."""
-        from agent.codex_responses_adapter import (
-            _normalize_codex_response,
-            _extract_responses_message_text,
-            _extract_responses_reasoning_text,
-        )
-
-        # _normalize_codex_response returns (SimpleNamespace, finish_reason_str)
-        msg, finish_reason = _normalize_codex_response(response)
-
-        tool_calls = None
-        if msg and msg.tool_calls:
-            tool_calls = []
-            for tc in msg.tool_calls:
-                provider_data = {}
-                if hasattr(tc, "call_id") and tc.call_id:
-                    provider_data["call_id"] = tc.call_id
-                if hasattr(tc, "response_item_id") and tc.response_item_id:
-                    provider_data["response_item_id"] = tc.response_item_id
-                tool_calls.append(ToolCall(
-                    id=tc.id if hasattr(tc, "id") else (tc.function.name if hasattr(tc, "function") else None),
-                    name=tc.function.name if hasattr(tc, "function") else getattr(tc, "name", ""),
-                    arguments=tc.function.arguments if hasattr(tc, "function") else getattr(tc, "arguments", "{}"),
-                    provider_data=provider_data or None,
-                ))
-
-        # Extract reasoning items for provider_data
-        provider_data = {}
-        if msg and hasattr(msg, "codex_reasoning_items") and msg.codex_reasoning_items:
-            provider_data["codex_reasoning_items"] = msg.codex_reasoning_items
-        if msg and hasattr(msg, "reasoning_details") and msg.reasoning_details:
-            provider_data["reasoning_details"] = msg.reasoning_details
-
-        return NormalizedResponse(
-            content=msg.content if msg else None,
-            tool_calls=tool_calls,
-            finish_reason=finish_reason or "stop",
-            reasoning=msg.reasoning if msg and hasattr(msg, "reasoning") else None,
-            usage=None,  # Codex usage is extracted separately in normalize_usage()
-            provider_data=provider_data or None,
-        )
-
-    def validate_response(self, response: Any) -> bool:
-        """Check Codex Responses API response has valid output structure.
-
-        Returns True only if response.output is a non-empty list.
-        Does NOT check output_text fallback — the caller handles that
-        with diagnostic logging for stream backfill recovery.
-        """
-        if response is None:
-            return False
-        output = getattr(response, "output", None)
-        if not isinstance(output, list) or not output:
-            return False
-        return True
-
-    def preflight_kwargs(self, api_kwargs: Any, *, allow_stream: bool = False) -> dict:
-        """Validate and sanitize Codex API kwargs before the call.
-
-        Normalizes input items, strips unsupported fields, validates structure.
-        """
-        from agent.codex_responses_adapter import _preflight_codex_api_kwargs
-        return _preflight_codex_api_kwargs(api_kwargs, allow_stream=allow_stream)
-
-    def map_finish_reason(self, raw_reason: str) -> str:
-        """Map Codex response.status to OpenAI finish_reason.
-
-        Codex uses response.status ('completed', 'incomplete') +
-        response.incomplete_details.reason for granular mapping.
-        This method handles the simple status string; the caller
-        should check incomplete_details separately for 'max_output_tokens'.
-        """
-        _MAP = {
-            "completed": "stop",
-            "incomplete": "length",
-            "failed": "stop",
-            "cancelled": "stop",
-        }
-        return _MAP.get(raw_reason, "stop")
-
-
-# Auto-register on import
-from agent.transports import register_transport  # noqa: E402
-
-register_transport("codex_responses", ResponsesApiTransport)
--- a/agent/transports/types.py
+++ b/agent/transports/types.py
@@ -1,100 +0,0 @@
-"""Shared types for normalized provider responses.
-
-These dataclasses define the canonical shape that all provider adapters
-normalize responses to.  The shared surface is intentionally minimal —
-only fields that every downstream consumer reads are top-level.
-Protocol-specific state goes in ``provider_data`` dicts (response-level
-and per-tool-call) so that protocol-aware code paths can access it
-without polluting the shared type.
-"""
-
-from __future__ import annotations
-
-import json
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
-
-
-@dataclass
-class ToolCall:
-    """A normalized tool call from any provider.
-
-    ``id`` is the protocol's canonical identifier — what gets used in
-    ``tool_call_id`` / ``tool_use_id`` when constructing tool result
-    messages.  May be ``None`` when the provider omits it; the agent
-    fills it via ``_deterministic_call_id()`` before storing in history.
-
-    ``provider_data`` carries per-tool-call protocol metadata that only
-    protocol-aware code reads:
-
-    * Codex: ``{"call_id": "call_XXX", "response_item_id": "fc_XXX"}``
-    * Gemini: ``{"extra_content": {"google": {"thought_signature": "..."}}}``
-    * Others: ``None``
-    """
-
-    id: Optional[str]
-    name: str
-    arguments: str  # JSON string
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-@dataclass
-class Usage:
-    """Token usage from an API response."""
-
-    prompt_tokens: int = 0
-    completion_tokens: int = 0
-    total_tokens: int = 0
-    cached_tokens: int = 0
-
-
-@dataclass
-class NormalizedResponse:
-    """Normalized API response from any provider.
-
-    Shared fields are truly cross-provider — every caller can rely on
-    them without branching on api_mode.  Protocol-specific state goes in
-    ``provider_data`` so that only protocol-aware code paths read it.
-
-    Response-level ``provider_data`` examples:
-
-    * Anthropic: ``{"reasoning_details": [...]}``
-    * Codex: ``{"codex_reasoning_items": [...]}``
-    * Others: ``None``
-    """
-
-    content: Optional[str]
-    tool_calls: Optional[List[ToolCall]]
-    finish_reason: str  # "stop", "tool_calls", "length", "content_filter"
-    reasoning: Optional[str] = None
-    usage: Optional[Usage] = None
-    provider_data: Optional[Dict[str, Any]] = field(default=None, repr=False)
-
-
-# ---------------------------------------------------------------------------
-# Factory helpers
-# ---------------------------------------------------------------------------
-
-def build_tool_call(
-    id: Optional[str],
-    name: str,
-    arguments: Any,
-    **provider_fields: Any,
-) -> ToolCall:
-    """Build a ``ToolCall``, auto-serialising *arguments* if it's a dict.
-
-    Any extra keyword arguments are collected into ``provider_data``.
-    """
-    args_str = json.dumps(arguments) if isinstance(arguments, dict) else str(arguments)
-    pd = dict(provider_fields) if provider_fields else None
-    return ToolCall(id=id, name=name, arguments=args_str, provider_data=pd)
-
-
-def map_finish_reason(reason: Optional[str], mapping: Dict[str, str]) -> str:
-    """Translate a provider-specific stop reason to the normalised set.
-
-    Falls back to ``"stop"`` for unknown or ``None`` reasons.
-    """
-    if reason is None:
-        return "stop"
-    return mapping.get(reason, "stop")
--- a/agent/usage_pricing.py
+++ b/agent/usage_pricing.py
@@ -6,7 +6,6 @@ from decimal import Decimal
 from typing import Any, Dict, Literal, Optional

 from agent.model_metadata import fetch_endpoint_model_metadata, fetch_model_metadata
-from utils import base_url_host_matches

 DEFAULT_PRICING = {"input": 0.0, "output": 0.0}

@@ -285,80 +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",
-    ),
 }


@@ -394,7 +319,7 @@ def resolve_billing_route(

    if provider_name == "openai-codex":
        return BillingRoute(provider="openai-codex", model=model, base_url=base_url or "", billing_mode="subscription_included")
-    if provider_name == "openrouter" or base_url_host_matches(base_url or "", "openrouter.ai"):
+    if provider_name == "openrouter" or "openrouter.ai" in base:
        return BillingRoute(provider="openrouter", model=model, base_url=base_url or "", billing_mode="official_models_api")
    if provider_name == "anthropic":
        return BillingRoute(provider="anthropic", model=model.split("/")[-1], base_url=base_url or "", billing_mode="official_docs_snapshot")
@@ -650,6 +575,25 @@ def has_known_pricing(
    return entry is not None


+def get_pricing(
+    model_name: str,
+    provider: Optional[str] = None,
+    base_url: Optional[str] = None,
+    api_key: Optional[str] = None,
+) -> Dict[str, float]:
+    """Backward-compatible thin wrapper for legacy callers.
+
+    Returns only non-cache input/output fields when a pricing entry exists.
+    Unknown routes return zeroes.
+    """
+    entry = get_pricing_entry(model_name, provider=provider, base_url=base_url, api_key=api_key)
+    if not entry:
+        return {"input": 0.0, "output": 0.0}
+    return {
+        "input": float(entry.input_cost_per_million or _ZERO),
+        "output": float(entry.output_cost_per_million or _ZERO),
+    }
+

 def format_duration_compact(seconds: float) -> str:
    if seconds < 60:
--- a/batch_runner.py
+++ b/batch_runner.py
@@ -444,7 +444,6 @@ def _process_batch_worker(args: Tuple) -> Dict[str, Any]:
            if not reasoning.get("has_any_reasoning", True):
                print(f"   🚫 Prompt {prompt_index} discarded (no reasoning in any turn)")
                discarded_no_reasoning += 1
-                completed_in_batch.append(prompt_index)
                continue
            
            # Get and normalize tool stats for consistent schema across all entries
@@ -562,10 +561,7 @@ class BatchRunner:
            provider_sort (str): Sort providers by price/throughput/latency (optional)
            max_tokens (int): Maximum tokens for model responses (optional, uses model default if not set)
            reasoning_config (Dict): OpenRouter reasoning config override (e.g. {"effort": "none"} to disable thinking)
-            prefill_messages (List[Dict]): Messages to prepend as prefilled conversation context (few-shot priming).
-                NOTE: Anthropic Sonnet 4.6+ and Opus 4.6+ reject a trailing assistant-role prefill
-                (400 error).  For those models use output_config.format or structured-output
-                schemas instead.  Safe here for user-role priming and for older Claude / non-Claude models.
+            prefill_messages (List[Dict]): Messages to prepend as prefilled conversation context (few-shot priming)
            max_samples (int): Only process the first N samples from the dataset (optional, processes all if not set)
        """
        self.dataset_file = Path(dataset_file)
@@ -1190,12 +1186,12 @@ def main(
    """
    # Handle list distributions
    if list_distributions:
-        from toolset_distributions import print_distribution_info
-
+        from toolset_distributions import list_distributions as get_all_dists, print_distribution_info
+        
        print("📊 Available Toolset Distributions")
        print("=" * 70)
-
-        all_dists = list_distributions()
+        
+        all_dists = get_all_dists()
        for dist_name in sorted(all_dists.keys()):
            print_distribution_info(dist_name)
        
--- a/cli-config.yaml.example
+++ b/cli-config.yaml.example
@@ -16,7 +16,7 @@ model:
  #   "nous"         - Nous Portal OAuth (requires: hermes login)
  #   "nous-api"     - Nous Portal API key (requires: NOUS_API_KEY)
  #   "anthropic"    - Direct Anthropic API (requires: ANTHROPIC_API_KEY)
-  #   "openai-codex" - OpenAI Codex (requires: hermes auth)
+  #   "openai-codex" - OpenAI Codex (requires: hermes login --provider openai-codex)
  #   "copilot"      - GitHub Copilot / GitHub Models (requires: GITHUB_TOKEN)
  #   "gemini"      - Use Google AI Studio direct (requires: GOOGLE_API_KEY or GEMINI_API_KEY)
  #   "zai"         - Use z.ai / ZhipuAI GLM models (requires: GLM_API_KEY)
@@ -24,10 +24,7 @@ model:
  #   "minimax"      - MiniMax global (requires: MINIMAX_API_KEY)
  #   "minimax-cn"   - MiniMax China (requires: MINIMAX_CN_API_KEY)
  #   "huggingface"  - Hugging Face Inference (requires: HF_TOKEN)
-  #   "nvidia"       - NVIDIA NIM / build.nvidia.com (requires: NVIDIA_API_KEY)
  #   "xiaomi"       - Xiaomi MiMo (requires: XIAOMI_API_KEY)
-  #   "arcee"        - Arcee AI Trinity models (requires: ARCEEAI_API_KEY)
-  #   "ollama-cloud" - Ollama Cloud (requires: OLLAMA_API_KEY — https://ollama.com/settings)
  #   "kilocode"     - KiloCode gateway (requires: KILOCODE_API_KEY)
  #   "ai-gateway"   - Vercel AI Gateway (requires: AI_GATEWAY_API_KEY)
  #
@@ -39,6 +36,12 @@ model:
  #     base_url: "http://localhost:1234/v1"
  #   No API key needed — local servers typically ignore auth.
  #
+  #   For Ollama Cloud (https://ollama.com/pricing):
+  #     provider: "custom"
+  #     base_url: "https://ollama.com/v1"
+  #   Set OLLAMA_API_KEY in .env — automatically picked up when base_url
+  #   points to ollama.com.
+  #
  # Can also be overridden with --provider flag or HERMES_INFERENCE_PROVIDER env var.
  provider: "auto"
  
@@ -63,38 +66,7 @@ model:
  #   Leave unset to use the model's native output ceiling (recommended).
  #   Set only if you want to deliberately limit individual response length.
  #
-# max_tokens: 8192
-
-# Named provider overrides (optional)
-# Use this for per-provider request timeouts, non-stream stale timeouts,
-# and per-model exceptions.
-# Applies to the primary turn client on every api_mode (OpenAI-wire, native
-# Anthropic, and Anthropic-compatible providers), the fallback chain, and
-# client rebuilds during credential rotation.  For OpenAI-wire chat
-# completions (streaming and non-streaming) the configured value is also
-# used as the per-request ``timeout=`` kwarg so it wins over the legacy
-# HERMES_API_TIMEOUT env var (which still applies when no config is set).
-# ``stale_timeout_seconds`` controls the non-streaming stale-call detector and
-# wins over the legacy HERMES_API_CALL_STALE_TIMEOUT env var. Leaving these
-# unset keeps the legacy defaults (HERMES_API_TIMEOUT=1800s,
-# HERMES_API_CALL_STALE_TIMEOUT=300s, native Anthropic 900s).
-#
-# Not currently wired for AWS Bedrock (bedrock_converse + AnthropicBedrock
-# SDK paths) — those use boto3 with its own timeout configuration.
-#
-# providers:
-#   ollama-local:
-#     request_timeout_seconds: 300   # Longer timeout for local cold-starts
-#     stale_timeout_seconds: 900     # Explicitly re-enable stale detection on local endpoints
-#   anthropic:
-#     request_timeout_seconds: 30    # Fast-fail cloud requests
-#     models:
-#       claude-opus-4.6:
-#         timeout_seconds: 600       # Longer timeout for extended-thinking Opus calls
-#   openai-codex:
-#     models:
-#       gpt-5.4:
-#         stale_timeout_seconds: 1800  # Longer non-stream stale timeout for slow large-context turns
+  # max_tokens: 8192

 # =============================================================================
 # OpenRouter Provider Routing (only applies when using OpenRouter)
@@ -122,6 +94,20 @@ model:
 #   # Data policy: "allow" (default) or "deny" to exclude providers that may store data
 #   # data_collection: "deny"

+# =============================================================================
+# Smart Model Routing (optional)
+# =============================================================================
+# Use a cheaper model for short/simple turns while keeping your main model for
+# more complex requests. Disabled by default.
+#
+# smart_model_routing:
+#   enabled: true
+#   max_simple_chars: 160
+#   max_simple_words: 28
+#   cheap_model:
+#     provider: openrouter
+#     model: google/gemini-2.5-flash
+
 # =============================================================================
 # Git Worktree Isolation
 # =============================================================================
@@ -323,8 +309,15 @@ compression:
  # compression of older turns.
  protect_last_n: 20

-  # To pin a specific model/provider for compression summaries, use the
-  # auxiliary section below (auxiliary.compression.provider / model).
+  # Model to use for generating summaries (fast/cheap recommended)
+  # This model compresses the middle turns into a concise summary.
+  # IMPORTANT: it receives the full middle section of the conversation, so it
+  # MUST support a context length at least as large as your main model's.
+  summary_model: "google/gemini-3-flash-preview"
+  
+  # Provider for the summary model (default: "auto")
+  # Options: "auto", "openrouter", "nous", "main"
+  # summary_provider: "auto"

 # =============================================================================
 # Auxiliary Models (Advanced — Experimental)
@@ -350,7 +343,6 @@ compression:
 #   "openrouter" - Force OpenRouter (requires OPENROUTER_API_KEY)
 #   "nous"       - Force Nous Portal (requires: hermes login)
 #   "gemini"      - Force Google AI Studio direct (requires: GOOGLE_API_KEY or GEMINI_API_KEY)
-#   "ollama-cloud" - Ollama Cloud (requires: OLLAMA_API_KEY)
 #   "codex"       - Force Codex OAuth (requires: hermes model → Codex).
 #                  Uses gpt-5.3-codex which supports vision.
 #   "main"       - Use your custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY).
@@ -374,18 +366,6 @@ compression:
 #   web_extract:
 #     provider: "auto"
 #     model: ""
-#
-#   # Session search — summarizes matching past sessions
-#   session_search:
-#     provider: "auto"
-#     model: ""
-#     timeout: 30
-#     max_concurrency: 3    # Limit parallel summaries to reduce request-burst 429s
-#     extra_body: {}        # Provider-specific OpenAI-compatible request fields
-#                           # Example for providers that support request-body
-#                           # reasoning controls:
-#                           # extra_body:
-#                           #   enable_thinking: false

 # =============================================================================
 # Persistent Memory
@@ -549,7 +529,7 @@ agent:
 #   - A preset like "hermes-cli" or "hermes-telegram" (curated tool set)
 #   - A list of individual toolsets to compose your own (see list below)
 #
-# Supported platform keys: cli, telegram, discord, whatsapp, slack, qqbot
+# Supported platform keys: cli, telegram, discord, whatsapp, slack
 #
 # Examples:
 #
@@ -578,7 +558,6 @@ agent:
 #   slack:         hermes-slack          (same as telegram)
 #   signal:        hermes-signal         (same as telegram)
 #   homeassistant: hermes-homeassistant  (same as telegram)
-#   qqbot:            hermes-qqbot            (same as telegram)
 #
 platform_toolsets:
  cli: [hermes-cli]
@@ -588,19 +567,6 @@ 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)
@@ -770,12 +736,10 @@ code_execution:
 # Subagent Delegation
 # =============================================================================
 # The delegate_task tool spawns child agents with isolated context.
-# Supports single tasks and batch mode (default 3 parallel, configurable).
+# Supports single tasks and batch mode (up to 3 parallel).
 delegation:
  max_iterations: 50                          # Max tool-calling turns per child (default: 50)
-  # max_concurrent_children: 3                # Max parallel child agents (default: 3)
-  # max_spawn_depth: 1                        # Tree depth cap (1-3, default: 1 = flat). Raise to 2 or 3 to allow orchestrator children to spawn their own workers.
-  # orchestrator_enabled: true                # Kill switch for role="orchestrator" children (default: true).
+  default_toolsets: ["terminal", "file", "web"]  # Default toolsets for subagents
  # model: "google/gemini-3-flash-preview"    # Override model for subagents (empty = inherit parent)
  # provider: "openrouter"                    # Override provider for subagents (empty = inherit parent)
  #                                           # Resolves full credentials (base_url, api_key) automatically.
@@ -919,39 +883,3 @@ display:
 #   # Names and usernames are NOT affected (user-chosen, publicly visible).
 #   # Routing/delivery still uses the original values internally.
 #   redact_pii: false
-
-# =============================================================================
-# Shell-script hooks
-# =============================================================================
-# Register shell scripts as plugin-hook callbacks.  Each entry is executed as
-# a subprocess (shell=False, shlex.split) with a JSON payload on stdin.  On
-# stdout the script may return JSON that either blocks the tool call or
-# injects context into the next LLM call.
-#
-# Valid events (mirror hermes_cli.plugins.VALID_HOOKS):
-#   pre_tool_call, post_tool_call, pre_llm_call, post_llm_call,
-#   pre_api_request, post_api_request, on_session_start, on_session_end,
-#   on_session_finalize, on_session_reset, subagent_stop
-#
-# First-use consent: each (event, command) pair prompts once on a TTY, then
-# is persisted to ~/.hermes/shell-hooks-allowlist.json.  Non-interactive
-# runs (gateway, cron) need --accept-hooks, HERMES_ACCEPT_HOOKS=1, or the
-# hooks_auto_accept key below.
-#
-# See website/docs/user-guide/features/hooks.md for the full JSON wire
-# protocol and worked examples.
-#
-# hooks:
-#   pre_tool_call:
-#     - matcher: "terminal"
-#       command: "~/.hermes/agent-hooks/block-rm-rf.sh"
-#       timeout: 10
-#   post_tool_call:
-#     - matcher: "write_file|patch"
-#       command: "~/.hermes/agent-hooks/auto-format.sh"
-#   pre_llm_call:
-#     - command: "~/.hermes/agent-hooks/inject-cwd-context.sh"
-#   subagent_stop:
-#     - command: "~/.hermes/agent-hooks/log-orchestration.sh"
-#
-# hooks_auto_accept: false
--- a/cli.py
+++ b/cli.py
--- a/cron/jobs.py
+++ b/cron/jobs.py
@@ -9,7 +9,6 @@ import copy
 import json
 import logging
 import tempfile
-import threading
 import os
 import re
 import uuid
@@ -35,11 +34,6 @@ except ImportError:
 HERMES_DIR = get_hermes_home().resolve()
 CRON_DIR = HERMES_DIR / "cron"
 JOBS_FILE = CRON_DIR / "jobs.json"
-
-# In-process lock protecting load_jobs→modify→save_jobs cycles.
-# Required when tick() runs jobs in parallel threads — without this,
-# concurrent mark_job_run / advance_next_run calls can clobber each other.
-_jobs_file_lock = threading.Lock()
 OUTPUT_DIR = CRON_DIR / "output"
 ONESHOT_GRACE_SECONDS = 120

@@ -507,12 +501,6 @@ 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")),
@@ -600,44 +588,43 @@ def mark_job_run(job_id: str, success: bool, error: Optional[str] = None,
    ``delivery_error`` is tracked separately from the agent error — a job
    can succeed (agent produced output) but fail delivery (platform down).
    """
-    with _jobs_file_lock:
-        jobs = load_jobs()
-        for i, job in enumerate(jobs):
-            if job["id"] == job_id:
-                now = _hermes_now().isoformat()
-                job["last_run_at"] = now
-                job["last_status"] = "ok" if success else "error"
-                job["last_error"] = error if not success else None
-                # Track delivery failures separately — cleared on successful delivery
-                job["last_delivery_error"] = delivery_error
+    jobs = load_jobs()
+    for i, job in enumerate(jobs):
+        if job["id"] == job_id:
+            now = _hermes_now().isoformat()
+            job["last_run_at"] = now
+            job["last_status"] = "ok" if success else "error"
+            job["last_error"] = error if not success else None
+            # Track delivery failures separately — cleared on successful delivery
+            job["last_delivery_error"] = delivery_error
+            
+            # Increment completed count
+            if job.get("repeat"):
+                job["repeat"]["completed"] = job["repeat"].get("completed", 0) + 1
                
-                # Increment completed count
-                if job.get("repeat"):
-                    job["repeat"]["completed"] = job["repeat"].get("completed", 0) + 1
-                    
-                    # Check if we've hit the repeat limit
-                    times = job["repeat"].get("times")
-                    completed = job["repeat"]["completed"]
-                    if times is not None and times > 0 and completed >= times:
-                        # Remove the job (limit reached)
-                        jobs.pop(i)
-                        save_jobs(jobs)
-                        return
-                
-                # Compute next run
-                job["next_run_at"] = compute_next_run(job["schedule"], now)
+                # Check if we've hit the repeat limit
+                times = job["repeat"].get("times")
+                completed = job["repeat"]["completed"]
+                if times is not None and times > 0 and completed >= times:
+                    # Remove the job (limit reached)
+                    jobs.pop(i)
+                    save_jobs(jobs)
+                    return
+            
+            # Compute next run
+            job["next_run_at"] = compute_next_run(job["schedule"], now)

-                # If no next run (one-shot completed), disable
-                if job["next_run_at"] is None:
-                    job["enabled"] = False
-                    job["state"] = "completed"
-                elif job.get("state") != "paused":
-                    job["state"] = "scheduled"
+            # If no next run (one-shot completed), disable
+            if job["next_run_at"] is None:
+                job["enabled"] = False
+                job["state"] = "completed"
+            elif job.get("state") != "paused":
+                job["state"] = "scheduled"

-                save_jobs(jobs)
-                return
+            save_jobs(jobs)
+            return

-        logger.warning("mark_job_run: job_id %s not found, skipping save", job_id)
+    logger.warning("mark_job_run: job_id %s not found, skipping save", job_id)


 def advance_next_run(job_id: str) -> bool:
@@ -652,21 +639,20 @@ def advance_next_run(job_id: str) -> bool:

    Returns True if next_run_at was advanced, False otherwise.
    """
-    with _jobs_file_lock:
-        jobs = load_jobs()
-        for job in jobs:
-            if job["id"] == job_id:
-                kind = job.get("schedule", {}).get("kind")
-                if kind not in ("cron", "interval"):
-                    return False
-                now = _hermes_now().isoformat()
-                new_next = compute_next_run(job["schedule"], now)
-                if new_next and new_next != job.get("next_run_at"):
-                    job["next_run_at"] = new_next
-                    save_jobs(jobs)
-                    return True
+    jobs = load_jobs()
+    for job in jobs:
+        if job["id"] == job_id:
+            kind = job.get("schedule", {}).get("kind")
+            if kind not in ("cron", "interval"):
                return False
-        return False
+            now = _hermes_now().isoformat()
+            new_next = compute_next_run(job["schedule"], now)
+            if new_next and new_next != job.get("next_run_at"):
+                job["next_run_at"] = new_next
+                save_jobs(jobs)
+                return True
+            return False
+    return False


 def get_due_jobs() -> List[Dict[str, Any]]:
--- a/cron/scheduler.py
+++ b/cron/scheduler.py
@@ -10,7 +10,6 @@ runs at a time if multiple processes overlap.

 import asyncio
 import concurrent.futures
-import contextvars
 import json
 import logging
 import os
@@ -27,7 +26,7 @@ except ImportError:
    except ImportError:
        msvcrt = None
 from pathlib import Path
-from typing import List, Optional
+from typing import Optional

 # Add parent directory to path for imports BEFORE repo-level imports.
 # Without this, standalone invocations (e.g. after `hermes update` reloads
@@ -46,36 +45,8 @@ _KNOWN_DELIVERY_PLATFORMS = frozenset({
    "telegram", "discord", "slack", "whatsapp", "signal",
    "matrix", "mattermost", "homeassistant", "dingtalk", "feishu",
    "wecom", "wecom_callback", "weixin", "sms", "email", "webhook", "bluebubbles",
-    "qqbot",
 })

-# Platforms that support a configured cron/notification home target, mapped to
-# the environment variable used by gateway setup/runtime config.
-_HOME_TARGET_ENV_VARS = {
-    "matrix": "MATRIX_HOME_ROOM",
-    "telegram": "TELEGRAM_HOME_CHANNEL",
-    "discord": "DISCORD_HOME_CHANNEL",
-    "slack": "SLACK_HOME_CHANNEL",
-    "signal": "SIGNAL_HOME_CHANNEL",
-    "mattermost": "MATTERMOST_HOME_CHANNEL",
-    "sms": "SMS_HOME_CHANNEL",
-    "email": "EMAIL_HOME_ADDRESS",
-    "dingtalk": "DINGTALK_HOME_CHANNEL",
-    "feishu": "FEISHU_HOME_CHANNEL",
-    "wecom": "WECOM_HOME_CHANNEL",
-    "weixin": "WEIXIN_HOME_CHANNEL",
-    "bluebubbles": "BLUEBUBBLES_HOME_CHANNEL",
-    "qqbot": "QQBOT_HOME_CHANNEL",
-}
-
-# Legacy env var names kept for back-compat.  Each entry is the current
-# primary env var → the previous name.  _get_home_target_chat_id falls
-# back to the legacy name if the primary is unset, so users who set the
-# old name before the rename keep working until they migrate.
-_LEGACY_HOME_TARGET_ENV_VARS = {
-    "QQBOT_HOME_CHANNEL": "QQ_HOME_CHANNEL",
-}
-
 from cron.jobs import get_due_jobs, mark_job_run, save_job_output, advance_next_run

 # Sentinel: when a cron agent has nothing new to report, it can start its
@@ -103,28 +74,15 @@ def _resolve_origin(job: dict) -> Optional[dict]:
    return None


-def _get_home_target_chat_id(platform_name: str) -> str:
-    """Return the configured home target chat/room ID for a delivery platform."""
-    env_var = _HOME_TARGET_ENV_VARS.get(platform_name.lower())
-    if not env_var:
-        return ""
-    value = os.getenv(env_var, "")
-    if not value:
-        legacy = _LEGACY_HOME_TARGET_ENV_VARS.get(env_var)
-        if legacy:
-            value = os.getenv(legacy, "")
-    return value
-
-
-def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[dict]:
-    """Resolve one concrete auto-delivery target for a cron job."""
-
+def _resolve_delivery_target(job: dict) -> Optional[dict]:
+    """Resolve the concrete auto-delivery target for a cron job, if any."""
+    deliver = job.get("deliver", "local")
    origin = _resolve_origin(job)

-    if deliver_value == "local":
+    if deliver == "local":
        return None

-    if deliver_value == "origin":
+    if deliver == "origin":
        if origin:
            return {
                "platform": origin["platform"],
@@ -133,8 +91,8 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
            }
        # Origin missing (e.g. job created via API/script) — try each
        # platform's home channel as a fallback instead of silently dropping.
-        for platform_name in _HOME_TARGET_ENV_VARS:
-            chat_id = _get_home_target_chat_id(platform_name)
+        for platform_name in ("matrix", "telegram", "discord", "slack", "bluebubbles"):
+            chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
            if chat_id:
                logger.info(
                    "Job '%s' has deliver=origin but no origin; falling back to %s home channel",
@@ -148,8 +106,8 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
                }
        return None

-    if ":" in deliver_value:
-        platform_name, rest = deliver_value.split(":", 1)
+    if ":" in deliver:
+        platform_name, rest = deliver.split(":", 1)
        platform_key = platform_name.lower()

        from tools.send_message_tool import _parse_target_ref
@@ -179,7 +137,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
            "thread_id": thread_id,
        }

-    platform_name = deliver_value
+    platform_name = deliver
    if origin and origin.get("platform") == platform_name:
        return {
            "platform": platform_name,
@@ -189,7 +147,7 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d

    if platform_name.lower() not in _KNOWN_DELIVERY_PLATFORMS:
        return None
-    chat_id = _get_home_target_chat_id(platform_name)
+    chat_id = os.getenv(f"{platform_name.upper()}_HOME_CHANNEL", "")
    if not chat_id:
        return None

@@ -200,30 +158,6 @@ def _resolve_single_delivery_target(job: dict, deliver_value: str) -> Optional[d
    }


-def _resolve_delivery_targets(job: dict) -> List[dict]:
-    """Resolve all concrete auto-delivery targets for a cron job (supports comma-separated deliver)."""
-    deliver = job.get("deliver", "local")
-    if deliver == "local":
-        return []
-    parts = [p.strip() for p in str(deliver).split(",") if p.strip()]
-    seen = set()
-    targets = []
-    for part in parts:
-        target = _resolve_single_delivery_target(job, part)
-        if target:
-            key = (target["platform"].lower(), str(target["chat_id"]), target.get("thread_id"))
-            if key not in seen:
-                seen.add(key)
-                targets.append(target)
-    return targets
-
-
-def _resolve_delivery_target(job: dict) -> Optional[dict]:
-    """Resolve the concrete auto-delivery target for a cron job, if any."""
-    targets = _resolve_delivery_targets(job)
-    return targets[0] if targets else None
-
-
 # Media extension sets — keep in sync with gateway/platforms/base.py:_process_message_background
 _AUDIO_EXTS = frozenset({'.ogg', '.opus', '.mp3', '.wav', '.m4a'})
 _VIDEO_EXTS = frozenset({'.mp4', '.mov', '.avi', '.mkv', '.webm', '.3gp'})
@@ -252,11 +186,7 @@ def _send_media_via_adapter(adapter, chat_id: str, media_files: list, metadata:
                coro = adapter.send_document(chat_id=chat_id, file_path=media_path, metadata=metadata)

            future = asyncio.run_coroutine_threadsafe(coro, loop)
-            try:
-                result = future.result(timeout=30)
-            except TimeoutError:
-                future.cancel()
-                raise
+            result = future.result(timeout=30)
            if result and not getattr(result, "success", True):
                logger.warning(
                    "Job '%s': media send failed for %s: %s",
@@ -268,7 +198,7 @@ def _send_media_via_adapter(adapter, chat_id: str, media_files: list, metadata:

 def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Optional[str]:
    """
-    Deliver job output to the configured target(s) (origin chat, specific platform, etc.).
+    Deliver job output to the configured target (origin chat, specific platform, etc.).

    When ``adapters`` and ``loop`` are provided (gateway is running), tries to
    use the live adapter first — this supports E2EE rooms (e.g. Matrix) where
@@ -277,14 +207,18 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option

    Returns None on success, or an error string on failure.
    """
-    targets = _resolve_delivery_targets(job)
-    if not targets:
+    target = _resolve_delivery_target(job)
+    if not target:
        if job.get("deliver", "local") != "local":
            msg = f"no delivery target resolved for deliver={job.get('deliver', 'local')}"
            logger.warning("Job '%s': %s", job["id"], msg)
            return msg
        return None  # local-only jobs don't deliver — not a failure

+    platform_name = target["platform"]
+    chat_id = target["chat_id"]
+    thread_id = target.get("thread_id")
+
    from tools.send_message_tool import _send_to_platform
    from gateway.config import load_gateway_config, Platform

@@ -305,8 +239,25 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
        "email": Platform.EMAIL,
        "sms": Platform.SMS,
        "bluebubbles": Platform.BLUEBUBBLES,
-        "qqbot": Platform.QQBOT,
    }
+    platform = platform_map.get(platform_name.lower())
+    if not platform:
+        msg = f"unknown platform '{platform_name}'"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg
+
+    try:
+        config = load_gateway_config()
+    except Exception as e:
+        msg = f"failed to load gateway config: {e}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg
+
+    pconfig = config.platforms.get(platform)
+    if not pconfig or not pconfig.enabled:
+        msg = f"platform '{platform_name}' not configured/enabled"
+        logger.warning("Job '%s': %s", job["id"], msg)
+        return msg

    # Optionally wrap the content with a header/footer so the user knows this
    # is a cron delivery.  Wrapping is on by default; set cron.wrap_response: false
@@ -320,13 +271,11 @@ 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
@@ -335,120 +284,67 @@ def _deliver_result(job: dict, content: str, adapters=None, loop=None) -> Option
    from gateway.platforms.base import BasePlatformAdapter
    media_files, cleaned_delivery_content = BasePlatformAdapter.extract_media(delivery_content)

+    # Prefer the live adapter when the gateway is running — this supports E2EE
+    # rooms (e.g. Matrix) where the standalone HTTP path cannot encrypt.
+    runtime_adapter = (adapters or {}).get(platform)
+    if runtime_adapter is not None and loop is not None and getattr(loop, "is_running", lambda: False)():
+        send_metadata = {"thread_id": thread_id} if thread_id else None
+        try:
+            # Send cleaned text (MEDIA tags stripped) — not the raw content
+            text_to_send = cleaned_delivery_content.strip()
+            adapter_ok = True
+            if text_to_send:
+                future = asyncio.run_coroutine_threadsafe(
+                    runtime_adapter.send(chat_id, text_to_send, metadata=send_metadata),
+                    loop,
+                )
+                send_result = future.result(timeout=60)
+                if send_result and not getattr(send_result, "success", True):
+                    err = getattr(send_result, "error", "unknown")
+                    logger.warning(
+                        "Job '%s': live adapter send to %s:%s failed (%s), falling back to standalone",
+                        job["id"], platform_name, chat_id, err,
+                    )
+                    adapter_ok = False  # fall through to standalone path
+
+            # Send extracted media files as native attachments via the live adapter
+            if adapter_ok and media_files:
+                _send_media_via_adapter(runtime_adapter, chat_id, media_files, send_metadata, loop, job)
+
+            if adapter_ok:
+                logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
+                return None
+        except Exception as e:
+            logger.warning(
+                "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
+                job["id"], platform_name, chat_id, e,
+            )
+
+    # Standalone path: run the async send in a fresh event loop (safe from any thread)
+    coro = _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files)
    try:
-        config = load_gateway_config()
+        result = asyncio.run(coro)
+    except RuntimeError:
+        # asyncio.run() checks for a running loop before awaiting the coroutine;
+        # when it raises, the original coro was never started — close it to
+        # prevent "coroutine was never awaited" RuntimeWarning, then retry in a
+        # fresh thread that has no running loop.
+        coro.close()
+        import concurrent.futures
+        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+            future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files))
+            result = future.result(timeout=30)
    except Exception as e:
-        msg = f"failed to load gateway config: {e}"
+        msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
        logger.error("Job '%s': %s", job["id"], msg)
        return msg

-    delivery_errors = []
+    if result and result.get("error"):
+        msg = f"delivery error: {result['error']}"
+        logger.error("Job '%s': %s", job["id"], msg)
+        return msg

-    for target in targets:
-        platform_name = target["platform"]
-        chat_id = target["chat_id"]
-        thread_id = target.get("thread_id")
-
-        # Diagnostic: log thread_id for topic-aware delivery debugging
-        origin = job.get("origin") or {}
-        origin_thread = origin.get("thread_id")
-        if origin_thread and not thread_id:
-            logger.warning(
-                "Job '%s': origin has thread_id=%s but delivery target lost it "
-                "(deliver=%s, target=%s)",
-                job["id"], origin_thread, job.get("deliver", "local"), target,
-            )
-        elif thread_id:
-            logger.debug(
-                "Job '%s': delivering to %s:%s thread_id=%s",
-                job["id"], platform_name, chat_id, thread_id,
-            )
-
-        platform = platform_map.get(platform_name.lower())
-        if not platform:
-            msg = f"unknown platform '{platform_name}'"
-            logger.warning("Job '%s': %s", job["id"], msg)
-            delivery_errors.append(msg)
-            continue
-
-        # Prefer the live adapter when the gateway is running — this supports E2EE
-        # rooms (e.g. Matrix) where the standalone HTTP path cannot encrypt.
-        runtime_adapter = (adapters or {}).get(platform)
-        delivered = False
-        if runtime_adapter is not None and loop is not None and getattr(loop, "is_running", lambda: False)():
-            send_metadata = {"thread_id": thread_id} if thread_id else None
-            try:
-                # Send cleaned text (MEDIA tags stripped) — not the raw content
-                text_to_send = cleaned_delivery_content.strip()
-                adapter_ok = True
-                if text_to_send:
-                    future = asyncio.run_coroutine_threadsafe(
-                        runtime_adapter.send(chat_id, text_to_send, metadata=send_metadata),
-                        loop,
-                    )
-                    try:
-                        send_result = future.result(timeout=60)
-                    except TimeoutError:
-                        future.cancel()
-                        raise
-                    if send_result and not getattr(send_result, "success", True):
-                        err = getattr(send_result, "error", "unknown")
-                        logger.warning(
-                            "Job '%s': live adapter send to %s:%s failed (%s), falling back to standalone",
-                            job["id"], platform_name, chat_id, err,
-                        )
-                        adapter_ok = False  # fall through to standalone path
-
-                # Send extracted media files as native attachments via the live adapter
-                if adapter_ok and media_files:
-                    _send_media_via_adapter(runtime_adapter, chat_id, media_files, send_metadata, loop, job)
-
-                if adapter_ok:
-                    logger.info("Job '%s': delivered to %s:%s via live adapter", job["id"], platform_name, chat_id)
-                    delivered = True
-            except Exception as e:
-                logger.warning(
-                    "Job '%s': live adapter delivery to %s:%s failed (%s), falling back to standalone",
-                    job["id"], platform_name, chat_id, e,
-                )
-
-        if not delivered:
-            pconfig = config.platforms.get(platform)
-            if not pconfig or not pconfig.enabled:
-                msg = f"platform '{platform_name}' not configured/enabled"
-                logger.warning("Job '%s': %s", job["id"], msg)
-                delivery_errors.append(msg)
-                continue
-
-            # Standalone path: run the async send in a fresh event loop (safe from any thread)
-            coro = _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files)
-            try:
-                result = asyncio.run(coro)
-            except RuntimeError:
-                # asyncio.run() checks for a running loop before awaiting the coroutine;
-                # when it raises, the original coro was never started — close it to
-                # prevent "coroutine was never awaited" RuntimeWarning, then retry in a
-                # fresh thread that has no running loop.
-                coro.close()
-                with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
-                    future = pool.submit(asyncio.run, _send_to_platform(platform, pconfig, chat_id, cleaned_delivery_content, thread_id=thread_id, media_files=media_files))
-                    result = future.result(timeout=30)
-            except Exception as e:
-                msg = f"delivery to {platform_name}:{chat_id} failed: {e}"
-                logger.error("Job '%s': %s", job["id"], msg)
-                delivery_errors.append(msg)
-                continue
-
-            if result and result.get("error"):
-                msg = f"delivery error: {result['error']}"
-                logger.error("Job '%s': %s", job["id"], msg)
-                delivery_errors.append(msg)
-                continue
-
-            logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
-
-    if delivery_errors:
-        return "; ".join(delivery_errors)
+    logger.info("Job '%s': delivered to %s:%s", job["id"], platform_name, chat_id)
    return None


@@ -571,53 +467,15 @@ def _run_job_script(script_path: str) -> tuple[bool, str]:
        return False, f"Script execution failed: {exc}"


-def _parse_wake_gate(script_output: str) -> bool:
-    """Parse the last non-empty stdout line of a cron job's pre-check script
-    as a wake gate.
-
-    The convention (ported from nanoclaw #1232): if the last stdout line is
-    JSON like ``{"wakeAgent": false}``, the agent is skipped entirely — no
-    LLM run, no delivery. Any other output (non-JSON, missing flag, gate
-    absent, or ``wakeAgent: true``) means wake the agent normally.
-
-    Returns True if the agent should wake, False to skip.
-    """
-    if not script_output:
-        return True
-    stripped_lines = [line for line in script_output.splitlines() if line.strip()]
-    if not stripped_lines:
-        return True
-    last_line = stripped_lines[-1].strip()
-    try:
-        gate = json.loads(last_line)
-    except (json.JSONDecodeError, ValueError):
-        return True
-    if not isinstance(gate, dict):
-        return True
-    return gate.get("wakeAgent", True) is not False
-
-
-def _build_job_prompt(job: dict, prerun_script: Optional[tuple] = None) -> str:
-    """Build the effective prompt for a cron job, optionally loading one or more skills first.
-
-    Args:
-        job: The cron job dict.
-        prerun_script: Optional ``(success, stdout)`` from a script that has
-            already been executed by the caller (e.g. for a wake-gate check).
-            When provided, the script is not re-executed and the cached
-            result is used for prompt injection. When omitted, the script
-            (if any) runs inline as before.
-    """
+def _build_job_prompt(job: dict) -> str:
+    """Build the effective prompt for a cron job, optionally loading one or more skills first."""
    prompt = job.get("prompt", "")
    skills = job.get("skills")

    # Run data-collection script if configured, inject output as context.
    script_path = job.get("script")
    if script_path:
-        if prerun_script is not None:
-            success, script_output = prerun_script
-        else:
-            success, script_output = _run_job_script(script_path)
+        success, script_output = _run_job_script(script_path)
        if success:
            if script_output:
                prompt = (
@@ -719,52 +577,21 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
    
    job_id = job["id"]
    job_name = job["name"]
-
-    # Wake-gate: if this job has a pre-check script, run it BEFORE building
-    # the prompt so a ``{"wakeAgent": false}`` response can short-circuit
-    # the whole agent run. We pass the result into _build_job_prompt so
-    # the script is only executed once.
-    prerun_script = None
-    script_path = job.get("script")
-    if script_path:
-        prerun_script = _run_job_script(script_path)
-        _ran_ok, _script_output = prerun_script
-        if _ran_ok and not _parse_wake_gate(_script_output):
-            logger.info(
-                "Job '%s' (ID: %s): wakeAgent=false, skipping agent run",
-                job_name, job_id,
-            )
-            silent_doc = (
-                f"# Cron Job: {job_name}\n\n"
-                f"**Job ID:** {job_id}\n"
-                f"**Run Time:** {_hermes_now().strftime('%Y-%m-%d %H:%M:%S')}\n\n"
-                "Script gate returned `wakeAgent=false` — agent skipped.\n"
-            )
-            return True, silent_doc, SILENT_MARKER, None
-
-    prompt = _build_job_prompt(job, prerun_script=prerun_script)
+    prompt = _build_job_prompt(job)
    origin = _resolve_origin(job)
    _cron_session_id = f"cron_{job_id}_{_hermes_now().strftime('%Y%m%d_%H%M%S')}"

    logger.info("Running job '%s' (ID: %s)", job_name, job_id)
    logger.info("Prompt: %s", prompt[:100])

-    # Mark this as a cron session so the approval system can apply cron_mode.
-    # This env var is process-wide and persists for the lifetime of the
-    # scheduler process — every job this process runs is a cron job.
-    os.environ["HERMES_CRON_SESSION"] = "1"
-
-    # Use ContextVars for per-job session/delivery state so parallel jobs
-    # don't clobber each other's targets (os.environ is process-global).
-    from gateway.session_context import set_session_vars, clear_session_vars, _VAR_MAP
-
-    _ctx_tokens = set_session_vars(
-        platform=origin["platform"] if origin else "",
-        chat_id=str(origin["chat_id"]) if origin else "",
-        chat_name=origin.get("chat_name", "") if origin else "",
-    )
-
    try:
+        # Inject origin context so the agent's send_message tool knows the chat.
+        # Must be INSIDE the try block so the finally cleanup always runs.
+        if origin:
+            os.environ["HERMES_SESSION_PLATFORM"] = origin["platform"]
+            os.environ["HERMES_SESSION_CHAT_ID"] = str(origin["chat_id"])
+            if origin.get("chat_name"):
+                os.environ["HERMES_SESSION_CHAT_NAME"] = origin["chat_name"]
        # Re-read .env and config.yaml fresh every run so provider/key
        # changes take effect without a gateway restart.
        from dotenv import load_dotenv
@@ -775,10 +602,10 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:

        delivery_target = _resolve_delivery_target(job)
        if delivery_target:
-            _VAR_MAP["HERMES_CRON_AUTO_DELIVER_PLATFORM"].set(delivery_target["platform"])
-            _VAR_MAP["HERMES_CRON_AUTO_DELIVER_CHAT_ID"].set(str(delivery_target["chat_id"]))
+            os.environ["HERMES_CRON_AUTO_DELIVER_PLATFORM"] = delivery_target["platform"]
+            os.environ["HERMES_CRON_AUTO_DELIVER_CHAT_ID"] = str(delivery_target["chat_id"])
            if delivery_target.get("thread_id") is not None:
-                _VAR_MAP["HERMES_CRON_AUTO_DELIVER_THREAD_ID"].set(str(delivery_target["thread_id"]))
+                os.environ["HERMES_CRON_AUTO_DELIVER_THREAD_ID"] = str(delivery_target["thread_id"])

        model = job.get("model") or os.getenv("HERMES_MODEL") or ""

@@ -799,15 +626,6 @@ 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()
@@ -817,13 +635,14 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
        prefill_messages = None
        prefill_file = os.getenv("HERMES_PREFILL_MESSAGES_FILE", "") or _cfg.get("prefill_messages_file", "")
        if prefill_file:
+            import json as _json
            pfpath = Path(prefill_file).expanduser()
            if not pfpath.is_absolute():
                pfpath = _hermes_home / pfpath
            if pfpath.exists():
                try:
                    with open(pfpath, "r", encoding="utf-8") as _pf:
-                        prefill_messages = json.load(_pf)
+                        prefill_messages = _json.load(_pf)
                    if not isinstance(prefill_messages, list):
                        prefill_messages = None
                except Exception as e:
@@ -835,6 +654,7 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:

        # Provider routing
        pr = _cfg.get("provider_routing", {})
+        smart_routing = _cfg.get("smart_model_routing", {}) or {}

        from hermes_cli.runtime_provider import (
            resolve_runtime_provider,
@@ -851,9 +671,24 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
            message = format_runtime_provider_error(exc)
            raise RuntimeError(message) from exc

+        from agent.smart_model_routing import resolve_turn_route
+        turn_route = resolve_turn_route(
+            prompt,
+            smart_routing,
+            {
+                "model": model,
+                "api_key": runtime.get("api_key"),
+                "base_url": runtime.get("base_url"),
+                "provider": runtime.get("provider"),
+                "api_mode": runtime.get("api_mode"),
+                "command": runtime.get("command"),
+                "args": list(runtime.get("args") or []),
+            },
+        )
+
        fallback_model = _cfg.get("fallback_providers") or _cfg.get("fallback_model") or None
        credential_pool = None
-        runtime_provider = str(runtime.get("provider") or "").strip().lower()
+        runtime_provider = str(turn_route["runtime"].get("provider") or "").strip().lower()
        if runtime_provider:
            try:
                from agent.credential_pool import load_pool
@@ -870,13 +705,13 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
                logger.debug("Job '%s': failed to load credential pool for %s: %s", job_id, runtime_provider, e)

        agent = AIAgent(
-            model=model,
-            api_key=runtime.get("api_key"),
-            base_url=runtime.get("base_url"),
-            provider=runtime.get("provider"),
-            api_mode=runtime.get("api_mode"),
-            acp_command=runtime.get("command"),
-            acp_args=runtime.get("args"),
+            model=turn_route["model"],
+            api_key=turn_route["runtime"].get("api_key"),
+            base_url=turn_route["runtime"].get("base_url"),
+            provider=turn_route["runtime"].get("provider"),
+            api_mode=turn_route["runtime"].get("api_mode"),
+            acp_command=turn_route["runtime"].get("command"),
+            acp_args=turn_route["runtime"].get("args"),
            max_iterations=max_iterations,
            reasoning_config=reasoning_config,
            prefill_messages=prefill_messages,
@@ -907,11 +742,7 @@ 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:
@@ -973,9 +804,6 @@ 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)"
@@ -1021,8 +849,16 @@ def run_job(job: dict) -> tuple[bool, str, str, Optional[str]]:
        return False, output, "", error_msg

    finally:
-        # Clean up ContextVar session/delivery state for this job.
-        clear_session_vars(_ctx_tokens)
+        # Clean up injected env vars so they don't leak to other jobs
+        for key in (
+            "HERMES_SESSION_PLATFORM",
+            "HERMES_SESSION_CHAT_ID",
+            "HERMES_SESSION_CHAT_NAME",
+            "HERMES_CRON_AUTO_DELIVER_PLATFORM",
+            "HERMES_CRON_AUTO_DELIVER_CHAT_ID",
+            "HERMES_CRON_AUTO_DELIVER_THREAD_ID",
+        ):
+            os.environ.pop(key, None)
        if _session_db:
            try:
                _session_db.end_session(_cron_session_id, "cron_complete")
@@ -1075,41 +911,15 @@ def tick(verbose: bool = True, adapters=None, loop=None) -> int:
        if verbose:
            logger.info("%s - %s job(s) due", _hermes_now().strftime('%H:%M:%S'), len(due_jobs))

-        # Advance next_run_at for all recurring jobs FIRST, under the file lock,
-        # before any execution begins.  This preserves at-most-once semantics.
+        executed = 0
        for job in due_jobs:
-            advance_next_run(job["id"])
-
-        # Resolve max parallel workers: env var > config.yaml > unbounded.
-        # Set HERMES_CRON_MAX_PARALLEL=1 to restore old serial behaviour.
-        _max_workers: Optional[int] = None
-        try:
-            _env_par = os.getenv("HERMES_CRON_MAX_PARALLEL", "").strip()
-            if _env_par:
-                _max_workers = int(_env_par) or None
-        except (ValueError, TypeError):
-            logger.warning("Invalid HERMES_CRON_MAX_PARALLEL value; defaulting to unbounded")
-        if _max_workers is None:
            try:
-                _ucfg = load_config() or {}
-                _cfg_par = (
-                    _ucfg.get("cron", {}) if isinstance(_ucfg, dict) else {}
-                ).get("max_parallel_jobs")
-                if _cfg_par is not None:
-                    _max_workers = int(_cfg_par) or None
-            except Exception:
-                pass
+                # For recurring jobs (cron/interval), advance next_run_at to the
+                # next future occurrence BEFORE execution.  This way, if the
+                # process crashes mid-run, the job won't re-fire on restart.
+                # One-shot jobs are left alone so they can retry on restart.
+                advance_next_run(job["id"])

-        if verbose:
-            logger.info(
-                "Running %d job(s) in parallel (max_workers=%s)",
-                len(due_jobs),
-                _max_workers if _max_workers else "unbounded",
-            )
-
-        def _process_job(job: dict) -> bool:
-            """Run one due job end-to-end: execute, save, deliver, mark."""
-            try:
                success, output, final_response, error = run_job(job)

                output_file = save_job_output(job["id"], output)
@@ -1133,31 +943,14 @@ 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)
-                return True
+                executed += 1

            except Exception as e:
                logger.error("Error processing job %s: %s", job['id'], e)
                mark_job_run(job["id"], False, str(e))
-                return False

-        # Run all due jobs concurrently, each in its own ContextVar copy
-        # so session/delivery state stays isolated per-thread.
-        with concurrent.futures.ThreadPoolExecutor(max_workers=_max_workers) as _tick_pool:
-            _futures = []
-            for job in due_jobs:
-                _ctx = contextvars.copy_context()
-                _futures.append(_tick_pool.submit(_ctx.run, _process_job, job))
-            _results = [f.result() for f in _futures]
-
-        return sum(_results)
+        return executed
    finally:
        if fcntl:
            fcntl.flock(lock_fd, fcntl.LOCK_UN)
--- a/docker/entrypoint.sh
+++ b/docker/entrypoint.sh
@@ -1,44 +1,10 @@
 #!/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
--- a/docs/acp-setup.md
+++ b/docs/acp-setup.md
@@ -0,0 +1,228 @@
+# Hermes Agent — ACP (Agent Client Protocol) Setup Guide
+
+Hermes Agent supports the **Agent Client Protocol (ACP)**, allowing it to run as
+a coding agent inside your editor. ACP lets your IDE send tasks to Hermes, and
+Hermes responds with file edits, terminal commands, and explanations — all shown
+natively in the editor UI.
+
+---
+
+## Prerequisites
+
+- Hermes Agent installed and configured (`hermes setup` completed)
+- An API key / provider set up in `~/.hermes/.env` or via `hermes login`
+- Python 3.11+
+
+Install the ACP extra:
+
+```bash
+pip install -e ".[acp]"
+```
+
+---
+
+## VS Code Setup
+
+### 1. Install the ACP Client extension
+
+Open VS Code and install **ACP Client** from the marketplace:
+
+- Press `Ctrl+Shift+X` (or `Cmd+Shift+X` on macOS)
+- Search for **"ACP Client"**
+- Click **Install**
+
+Or install from the command line:
+
+```bash
+code --install-extension anysphere.acp-client
+```
+
+### 2. Configure settings.json
+
+Open your VS Code settings (`Ctrl+,` → click the `{}` icon for JSON) and add:
+
+```json
+{
+  "acpClient.agents": [
+    {
+      "name": "hermes-agent",
+      "registryDir": "/path/to/hermes-agent/acp_registry"
+    }
+  ]
+}
+```
+
+Replace `/path/to/hermes-agent` with the actual path to your Hermes Agent
+installation (e.g. `~/.hermes/hermes-agent`).
+
+Alternatively, if `hermes` is on your PATH, the ACP Client can discover it
+automatically via the registry directory.
+
+### 3. Restart VS Code
+
+After configuring, restart VS Code. You should see **Hermes Agent** appear in
+the ACP agent picker in the chat/agent panel.
+
+---
+
+## Zed Setup
+
+Zed has built-in ACP support.
+
+### 1. Configure Zed settings
+
+Open Zed settings (`Cmd+,` on macOS or `Ctrl+,` on Linux) and add to your
+`settings.json`:
+
+```json
+{
+  "agent_servers": {
+    "hermes-agent": {
+      "type": "custom",
+      "command": "hermes",
+      "args": ["acp"],
+    },
+  },
+}
+```
+
+### 2. Restart Zed
+
+Hermes Agent will appear in the agent panel. Select it and start a conversation.
+
+---
+
+## JetBrains Setup (IntelliJ, PyCharm, WebStorm, etc.)
+
+### 1. Install the ACP plugin
+
+- Open **Settings** → **Plugins** → **Marketplace**
+- Search for **"ACP"** or **"Agent Client Protocol"**
+- Install and restart the IDE
+
+### 2. Configure the agent
+
+- Open **Settings** → **Tools** → **ACP Agents**
+- Click **+** to add a new agent
+- Set the registry directory to your `acp_registry/` folder:
+  `/path/to/hermes-agent/acp_registry`
+- Click **OK**
+
+### 3. Use the agent
+
+Open the ACP panel (usually in the right sidebar) and select **Hermes Agent**.
+
+---
+
+## What You Will See
+
+Once connected, your editor provides a native interface to Hermes Agent:
+
+### Chat Panel
+A conversational interface where you can describe tasks, ask questions, and
+give instructions. Hermes responds with explanations and actions.
+
+### File Diffs
+When Hermes edits files, you see standard diffs in the editor. You can:
+- **Accept** individual changes
+- **Reject** changes you don't want
+- **Review** the full diff before applying
+
+### Terminal Commands
+When Hermes needs to run shell commands (builds, tests, installs), the editor
+shows them in an integrated terminal. Depending on your settings:
+- Commands may run automatically
+- Or you may be prompted to **approve** each command
+
+### Approval Flow
+For potentially destructive operations, the editor will prompt you for
+approval before Hermes proceeds. This includes:
+- File deletions
+- Shell commands
+- Git operations
+
+---
+
+## Configuration
+
+Hermes Agent under ACP uses the **same configuration** as the CLI:
+
+- **API keys / providers**: `~/.hermes/.env`
+- **Agent config**: `~/.hermes/config.yaml`
+- **Skills**: `~/.hermes/skills/`
+- **Sessions**: `~/.hermes/state.db`
+
+You can run `hermes setup` to configure providers, or edit `~/.hermes/.env`
+directly.
+
+### Changing the model
+
+Edit `~/.hermes/config.yaml`:
+
+```yaml
+model: openrouter/nous/hermes-3-llama-3.1-70b
+```
+
+Or set the `HERMES_MODEL` environment variable.
+
+### Toolsets
+
+ACP sessions use the curated `hermes-acp` toolset by default. It is designed for editor workflows and intentionally excludes things like messaging delivery, cronjob management, and audio-first UX features.
+
+---
+
+## Troubleshooting
+
+### Agent doesn't appear in the editor
+
+1. **Check the registry path** — make sure the `acp_registry/` directory path
+   in your editor settings is correct and contains `agent.json`.
+2. **Check `hermes` is on PATH** — run `which hermes` in a terminal. If not
+   found, you may need to activate your virtualenv or add it to PATH.
+3. **Restart the editor** after changing settings.
+
+### Agent starts but errors immediately
+
+1. Run `hermes doctor` to check your configuration.
+2. Check that you have a valid API key: `hermes status`
+3. Try running `hermes acp` directly in a terminal to see error output.
+
+### "Module not found" errors
+
+Make sure you installed the ACP extra:
+
+```bash
+pip install -e ".[acp]"
+```
+
+### Slow responses
+
+- ACP streams responses, so you should see incremental output. If the agent
+  appears stuck, check your network connection and API provider status.
+- Some providers have rate limits. Try switching to a different model/provider.
+
+### Permission denied for terminal commands
+
+If the editor blocks terminal commands, check your ACP Client extension
+settings for auto-approval or manual-approval preferences.
+
+### Logs
+
+Hermes logs are written to stderr when running in ACP mode. Check:
+- VS Code: **Output** panel → select **ACP Client** or **Hermes Agent**
+- Zed: **View** → **Toggle Terminal** and check the process output
+- JetBrains: **Event Log** or the ACP tool window
+
+You can also enable verbose logging:
+
+```bash
+HERMES_LOG_LEVEL=DEBUG hermes acp
+```
+
+---
+
+## Further Reading
+
+- [ACP Specification](https://github.com/anysphere/acp)
+- [Hermes Agent Documentation](https://github.com/NousResearch/hermes-agent)
+- Run `hermes --help` for all CLI options
--- a/docs/honcho-integration-spec.html
+++ b/docs/honcho-integration-spec.html
@@ -0,0 +1,698 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>honcho-integration-spec</title>
+<style>
+  :root {
+    --bg:             #0b0e14;
+    --bg-surface:     #11151c;
+    --bg-elevated:    #181d27;
+    --bg-code:        #0d1018;
+    --fg:             #c9d1d9;
+    --fg-bright:      #e6edf3;
+    --fg-muted:       #6e7681;
+    --fg-subtle:      #484f58;
+    --accent:         #7eb8f6;
+    --accent-dim:     #3d6ea5;
+    --accent-glow:    rgba(126, 184, 246, 0.08);
+    --green:          #7ee6a8;
+    --green-dim:      #2ea04f;
+    --orange:         #e6a855;
+    --red:            #f47067;
+    --purple:         #bc8cff;
+    --cyan:           #56d4dd;
+    --border:         #21262d;
+    --border-subtle:  #161b22;
+    --radius:         6px;
+    --font-sans:      'New York', ui-serif, 'Iowan Old Style', 'Apple Garamond', Baskerville, 'Times New Roman', 'Noto Emoji', serif;
+    --font-mono:      'Departure Mono', 'Noto Emoji', monospace;
+  }
+
+  *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
+  html { scroll-behavior: smooth; scroll-padding-top: 2rem; }
+  body {
+    font-family: var(--font-sans);
+    background: var(--bg);
+    color: var(--fg);
+    line-height: 1.7;
+    font-size: 15px;
+    -webkit-font-smoothing: antialiased;
+  }
+
+  .container { max-width: 860px; margin: 0 auto; padding: 3rem 2rem 6rem; }
+
+  .hero {
+    text-align: center;
+    padding: 4rem 0 3rem;
+    border-bottom: 1px solid var(--border);
+    margin-bottom: 3rem;
+  }
+  .hero h1 { font-family: var(--font-mono); font-size: 2.2rem; font-weight: 700; color: var(--fg-bright); letter-spacing: -0.03em; margin-bottom: 0.5rem; }
+  .hero h1 span { color: var(--accent); }
+  .hero .subtitle { font-family: var(--font-sans); color: var(--fg-muted); font-size: 0.92rem; max-width: 560px; margin: 0 auto; line-height: 1.6; }
+  .hero .meta { margin-top: 1.5rem; display: flex; justify-content: center; gap: 1.5rem; flex-wrap: wrap; }
+  .hero .meta span { font-size: 0.8rem; color: var(--fg-subtle); font-family: var(--font-mono); }
+
+  .toc { background: var(--bg-surface); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.5rem 2rem; margin-bottom: 3rem; }
+  .toc h2 { font-size: 0.75rem; text-transform: uppercase; letter-spacing: 0.1em; color: var(--fg-muted); margin-bottom: 1rem; }
+  .toc ol { list-style: none; counter-reset: toc; columns: 2; column-gap: 2rem; }
+  .toc li { counter-increment: toc; break-inside: avoid; margin-bottom: 0.35rem; }
+  .toc li::before { content: counter(toc, decimal-leading-zero) " "; color: var(--fg-subtle); font-family: var(--font-mono); font-size: 0.75rem; margin-right: 0.25rem; }
+  .toc a { font-family: var(--font-mono); color: var(--fg); text-decoration: none; font-size: 0.82rem; transition: color 0.15s; }
+  .toc a:hover { color: var(--accent); }
+
+  section { margin-bottom: 4rem; }
+  section + section { padding-top: 1rem; }
+
+  h2 { font-family: var(--font-mono); font-size: 1.3rem; font-weight: 700; color: var(--fg-bright); letter-spacing: -0.01em; margin-bottom: 1.25rem; padding-bottom: 0.5rem; border-bottom: 1px solid var(--border); }
+  h3 { font-family: var(--font-mono); font-size: 1rem; font-weight: 600; color: var(--fg-bright); margin-top: 2rem; margin-bottom: 0.75rem; }
+  h4 { font-family: var(--font-mono); font-size: 0.9rem; font-weight: 600; color: var(--accent); margin-top: 1.5rem; margin-bottom: 0.5rem; }
+
+  p { margin-bottom: 1rem; font-size: 0.95rem; line-height: 1.75; }
+  strong { color: var(--fg-bright); font-weight: 600; }
+  a { color: var(--accent); text-decoration: none; }
+  a:hover { text-decoration: underline; }
+
+  ul, ol { margin-bottom: 1rem; padding-left: 1.5rem; font-size: 0.93rem; line-height: 1.7; }
+  li { margin-bottom: 0.35rem; }
+  li::marker { color: var(--fg-subtle); }
+
+  .table-wrap { overflow-x: auto; margin-bottom: 1.5rem; }
+  table { width: 100%; border-collapse: collapse; font-size: 0.88rem; }
+  th, td { text-align: left; padding: 0.6rem 1rem; border-bottom: 1px solid var(--border-subtle); }
+  th { font-family: var(--font-mono); font-size: 0.72rem; text-transform: uppercase; letter-spacing: 0.06em; color: var(--fg-muted); background: var(--bg-surface); border-bottom-color: var(--border); white-space: nowrap; }
+  td { font-family: var(--font-sans); font-size: 0.88rem; color: var(--fg); }
+  tr:hover td { background: var(--accent-glow); }
+  td code { background: var(--bg-elevated); padding: 0.15em 0.4em; border-radius: 3px; font-family: var(--font-mono); font-size: 0.82em; color: var(--cyan); }
+
+  pre { background: var(--bg-code); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.25rem 1.5rem; overflow-x: auto; margin-bottom: 1.5rem; font-family: var(--font-mono); font-size: 0.82rem; line-height: 1.65; color: var(--fg); }
+  pre code { background: none; padding: 0; color: inherit; font-size: inherit; }
+  code { font-family: var(--font-mono); font-size: 0.85em; }
+  p code, li code { background: var(--bg-elevated); padding: 0.15em 0.4em; border-radius: 3px; color: var(--cyan); font-size: 0.85em; }
+
+  .kw { color: var(--purple); }
+  .str { color: var(--green); }
+  .cm { color: var(--fg-subtle); font-style: italic; }
+  .num { color: var(--orange); }
+  .key { color: var(--accent); }
+
+  .mermaid { margin: 1.5rem 0 2rem; text-align: center; }
+  .mermaid svg { max-width: 100%; height: auto; }
+
+  .callout { font-family: var(--font-sans); background: var(--bg-surface); border-left: 3px solid var(--accent-dim); border-radius: 0 var(--radius) var(--radius) 0; padding: 1rem 1.25rem; margin-bottom: 1.5rem; font-size: 0.88rem; color: var(--fg-muted); line-height: 1.6; }
+  .callout strong { font-family: var(--font-mono); color: var(--fg-bright); }
+  .callout.success { border-left-color: var(--green-dim); }
+  .callout.warn { border-left-color: var(--orange); }
+
+  .badge { display: inline-block; font-family: var(--font-mono); font-size: 0.65rem; font-weight: 600; text-transform: uppercase; letter-spacing: 0.05em; padding: 0.2em 0.6em; border-radius: 3px; vertical-align: middle; margin-left: 0.4rem; }
+  .badge-done { background: var(--green-dim); color: #fff; }
+  .badge-wip { background: var(--orange); color: #0b0e14; }
+  .badge-todo { background: var(--fg-subtle); color: var(--fg); }
+
+  .checklist { list-style: none; padding-left: 0; }
+  .checklist li { padding-left: 1.5rem; position: relative; margin-bottom: 0.5rem; }
+  .checklist li::before { position: absolute; left: 0; font-family: var(--font-mono); font-size: 0.85rem; }
+  .checklist li.done { color: var(--fg-muted); }
+  .checklist li.done::before { content: "\2713"; color: var(--green); }
+  .checklist li.todo::before { content: "\25CB"; color: var(--fg-subtle); }
+  .checklist li.wip::before { content: "\25D4"; color: var(--orange); }
+
+  .compare { display: grid; grid-template-columns: 1fr 1fr; gap: 1rem; margin-bottom: 2rem; }
+  .compare-card { background: var(--bg-surface); border: 1px solid var(--border); border-radius: var(--radius); padding: 1.25rem; }
+  .compare-card h4 { margin-top: 0; font-size: 0.82rem; }
+  .compare-card.after { border-color: var(--accent-dim); }
+  .compare-card ul { font-family: var(--font-mono); padding-left: 1.25rem; font-size: 0.8rem; }
+
+  hr { border: none; border-top: 1px solid var(--border); margin: 3rem 0; }
+
+  .progress-bar { position: fixed; top: 0; left: 0; height: 2px; background: var(--accent); z-index: 999; transition: width 0.1s linear; }
+
+  @media (max-width: 640px) {
+    .container { padding: 2rem 1rem 4rem; }
+    .hero h1 { font-size: 1.6rem; }
+    .toc ol { columns: 1; }
+    .compare { grid-template-columns: 1fr; }
+    table { font-size: 0.8rem; }
+    th, td { padding: 0.4rem 0.6rem; }
+  }
+</style>
+<link rel="preconnect" href="https://fonts.googleapis.com">
+<link href="https://fonts.googleapis.com/css2?family=Noto+Emoji&display=swap" rel="stylesheet">
+<style>
+  @font-face {
+    font-family: 'Departure Mono';
+    src: url('https://cdn.jsdelivr.net/gh/rektdeckard/departure-mono@latest/fonts/DepartureMono-Regular.woff2') format('woff2');
+    font-weight: normal;
+    font-style: normal;
+    font-display: swap;
+  }
+</style>
+</head>
+<body>
+
+<div class="progress-bar" id="progress"></div>
+
+<div class="container">
+
+<header class="hero">
+  <h1>honcho<span>-integration-spec</span></h1>
+  <p class="subtitle">Comparison of Hermes Agent vs. openclaw-honcho — and a porting spec for bringing Hermes patterns into other Honcho integrations.</p>
+  <div class="meta">
+    <span>hermes-agent / openclaw-honcho</span>
+    <span>Python + TypeScript</span>
+    <span>2026-03-09</span>
+  </div>
+</header>
+
+<nav class="toc">
+  <h2>Contents</h2>
+  <ol>
+    <li><a href="#overview">Overview</a></li>
+    <li><a href="#architecture">Architecture comparison</a></li>
+    <li><a href="#diff-table">Diff table</a></li>
+    <li><a href="#patterns">Hermes patterns to port</a></li>
+    <li><a href="#spec-async">Spec: async prefetch</a></li>
+    <li><a href="#spec-reasoning">Spec: dynamic reasoning level</a></li>
+    <li><a href="#spec-modes">Spec: per-peer memory modes</a></li>
+    <li><a href="#spec-identity">Spec: AI peer identity formation</a></li>
+    <li><a href="#spec-sessions">Spec: session naming strategies</a></li>
+    <li><a href="#spec-cli">Spec: CLI surface injection</a></li>
+    <li><a href="#openclaw-checklist">openclaw-honcho checklist</a></li>
+    <li><a href="#nanobot-checklist">nanobot-honcho checklist</a></li>
+  </ol>
+</nav>
+
+<!-- OVERVIEW -->
+<section id="overview">
+  <h2>Overview</h2>
+
+  <p>Two independent Honcho integrations have been built for two different agent runtimes: <strong>Hermes Agent</strong> (Python, baked into the runner) and <strong>openclaw-honcho</strong> (TypeScript plugin via hook/tool API). Both use the same Honcho peer paradigm — dual peer model, <code>session.context()</code>, <code>peer.chat()</code> — but they made different tradeoffs at every layer.</p>
+
+  <p>This document maps those tradeoffs and defines a porting spec: a set of Hermes-originated patterns, each stated as an integration-agnostic interface, that any Honcho integration can adopt regardless of runtime or language.</p>
+
+  <div class="callout">
+    <strong>Scope</strong> Both integrations work correctly today. This spec is about the delta — patterns in Hermes that are worth propagating and patterns in openclaw-honcho that Hermes should eventually adopt. The spec is additive, not prescriptive.
+  </div>
+</section>
+
+<!-- ARCHITECTURE -->
+<section id="architecture">
+  <h2>Architecture comparison</h2>
+
+  <h3>Hermes: baked-in runner</h3>
+  <p>Honcho is initialised directly inside <code>AIAgent.__init__</code>. There is no plugin boundary. Session management, context injection, async prefetch, and CLI surface are all first-class concerns of the runner. Context is injected once per session (baked into <code>_cached_system_prompt</code>) and never re-fetched mid-session — this maximises prefix cache hits at the LLM provider.</p>
+
+  <div class="mermaid">
+%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1f3150', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#3d6ea5', 'lineColor': '#3d6ea5', 'secondaryColor': '#162030', 'tertiaryColor': '#11151c' }}}%%
+flowchart TD
+    U["user message"] --> P["_honcho_prefetch()<br/>(reads cache — no HTTP)"]
+    P --> SP["_build_system_prompt()<br/>(first turn only, cached)"]
+    SP --> LLM["LLM call"]
+    LLM --> R["response"]
+    R --> FP["_honcho_fire_prefetch()<br/>(daemon threads, turn end)"]
+    FP --> C1["prefetch_context() thread"]
+    FP --> C2["prefetch_dialectic() thread"]
+    C1 --> CACHE["_context_cache / _dialectic_cache"]
+    C2 --> CACHE
+
+    style U fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style P fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style SP fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style LLM fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style R fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style FP fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style C1 fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style C2 fill:#2a1a40,stroke:#bc8cff,color:#c9d1d9
+    style CACHE fill:#11151c,stroke:#484f58,color:#6e7681
+  </div>
+
+  <h3>openclaw-honcho: hook-based plugin</h3>
+  <p>The plugin registers hooks against OpenClaw's event bus. Context is fetched synchronously inside <code>before_prompt_build</code> on every turn. Message capture happens in <code>agent_end</code>. The multi-agent hierarchy is tracked via <code>subagent_spawned</code>. This model is correct but every turn pays a blocking Honcho round-trip before the LLM call can begin.</p>
+
+  <div class="mermaid">
+%%{init: {'theme': 'dark', 'themeVariables': { 'primaryColor': '#1f3150', 'primaryTextColor': '#c9d1d9', 'primaryBorderColor': '#3d6ea5', 'lineColor': '#3d6ea5', 'secondaryColor': '#162030', 'tertiaryColor': '#11151c' }}}%%
+flowchart TD
+    U2["user message"] --> BPB["before_prompt_build<br/>(BLOCKING HTTP — every turn)"]
+    BPB --> CTX["session.context()"]
+    CTX --> SP2["system prompt assembled"]
+    SP2 --> LLM2["LLM call"]
+    LLM2 --> R2["response"]
+    R2 --> AE["agent_end hook"]
+    AE --> SAVE["session.addMessages()<br/>session.setMetadata()"]
+
+    style U2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style BPB fill:#3a1515,stroke:#f47067,color:#c9d1d9
+    style CTX fill:#3a1515,stroke:#f47067,color:#c9d1d9
+    style SP2 fill:#1f3150,stroke:#3d6ea5,color:#c9d1d9
+    style LLM2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style R2 fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style AE fill:#162030,stroke:#3d6ea5,color:#c9d1d9
+    style SAVE fill:#11151c,stroke:#484f58,color:#6e7681
+  </div>
+</section>
+
+<!-- DIFF TABLE -->
+<section id="diff-table">
+  <h2>Diff table</h2>
+
+  <div class="table-wrap">
+    <table>
+      <thead>
+        <tr>
+          <th>Dimension</th>
+          <th>Hermes Agent</th>
+          <th>openclaw-honcho</th>
+        </tr>
+      </thead>
+      <tbody>
+        <tr>
+          <td><strong>Context injection timing</strong></td>
+          <td>Once per session (cached). Zero HTTP on response path after turn 1.</td>
+          <td>Every turn, blocking. Fresh context per turn but adds latency.</td>
+        </tr>
+        <tr>
+          <td><strong>Prefetch strategy</strong></td>
+          <td>Daemon threads fire at turn end; consumed next turn from cache.</td>
+          <td>None. Blocking call at prompt-build time.</td>
+        </tr>
+        <tr>
+          <td><strong>Dialectic (peer.chat)</strong></td>
+          <td>Prefetched async; result injected into system prompt next turn.</td>
+          <td>On-demand via <code>honcho_recall</code> / <code>honcho_analyze</code> tools.</td>
+        </tr>
+        <tr>
+          <td><strong>Reasoning level</strong></td>
+          <td>Dynamic: scales with message length. Floor = config default. Cap = "high".</td>
+          <td>Fixed per tool: recall=minimal, analyze=medium.</td>
+        </tr>
+        <tr>
+          <td><strong>Memory modes</strong></td>
+          <td><code>user_memory_mode</code> / <code>agent_memory_mode</code>: hybrid / honcho / local.</td>
+          <td>None. Always writes to Honcho.</td>
+        </tr>
+        <tr>
+          <td><strong>Write frequency</strong></td>
+          <td>async (background queue), turn, session, N turns.</td>
+          <td>After every agent_end (no control).</td>
+        </tr>
+        <tr>
+          <td><strong>AI peer identity</strong></td>
+          <td><code>observe_me=True</code>, <code>seed_ai_identity()</code>, <code>get_ai_representation()</code>, SOUL.md → AI peer.</td>
+          <td>Agent files uploaded to agent peer at setup. No ongoing self-observation seeding.</td>
+        </tr>
+        <tr>
+          <td><strong>Context scope</strong></td>
+          <td>User peer + AI peer representation, both injected.</td>
+          <td>User peer (owner) representation + conversation summary. <code>peerPerspective</code> on context call.</td>
+        </tr>
+        <tr>
+          <td><strong>Session naming</strong></td>
+          <td>per-directory / global / manual map / title-based.</td>
+          <td>Derived from platform session key.</td>
+        </tr>
+        <tr>
+          <td><strong>Multi-agent</strong></td>
+          <td>Single-agent only.</td>
+          <td>Parent observer hierarchy via <code>subagent_spawned</code>.</td>
+        </tr>
+        <tr>
+          <td><strong>Tool surface</strong></td>
+          <td>Single <code>query_user_context</code> tool (on-demand dialectic).</td>
+          <td>6 tools: session, profile, search, context (fast) + recall, analyze (LLM).</td>
+        </tr>
+        <tr>
+          <td><strong>Platform metadata</strong></td>
+          <td>Not stripped.</td>
+          <td>Explicitly stripped before Honcho storage.</td>
+        </tr>
+        <tr>
+          <td><strong>Message dedup</strong></td>
+          <td>None (sends on every save cycle).</td>
+          <td><code>lastSavedIndex</code> in session metadata prevents re-sending.</td>
+        </tr>
+        <tr>
+          <td><strong>CLI surface in prompt</strong></td>
+          <td>Management commands injected into system prompt. Agent knows its own CLI.</td>
+          <td>Not injected.</td>
+        </tr>
+        <tr>
+          <td><strong>AI peer name in identity</strong></td>
+          <td>Replaces "Hermes Agent" in DEFAULT_AGENT_IDENTITY when configured.</td>
+          <td>Not implemented.</td>
+        </tr>
+        <tr>
+          <td><strong>QMD / local file search</strong></td>
+          <td>Not implemented.</td>
+          <td>Passthrough tools when QMD backend configured.</td>
+        </tr>
+        <tr>
+          <td><strong>Workspace metadata</strong></td>
+          <td>Not implemented.</td>
+          <td><code>agentPeerMap</code> in workspace metadata tracks agent&#8594;peer ID.</td>
+        </tr>
+      </tbody>
+    </table>
+  </div>
+</section>
+
+<!-- PATTERNS -->
+<section id="patterns">
+  <h2>Hermes patterns to port</h2>
+
+  <p>Six patterns from Hermes are worth adopting in any Honcho integration. They are described below as integration-agnostic interfaces — the implementation will differ per runtime, but the contract is the same.</p>
+
+  <div class="compare">
+    <div class="compare-card">
+      <h4>Patterns Hermes contributes</h4>
+      <ul>
+        <li>Async prefetch (zero-latency)</li>
+        <li>Dynamic reasoning level</li>
+        <li>Per-peer memory modes</li>
+        <li>AI peer identity formation</li>
+        <li>Session naming strategies</li>
+        <li>CLI surface injection</li>
+      </ul>
+    </div>
+    <div class="compare-card after">
+      <h4>Patterns openclaw contributes back</h4>
+      <ul>
+        <li>lastSavedIndex dedup</li>
+        <li>Platform metadata stripping</li>
+        <li>Multi-agent observer hierarchy</li>
+        <li>peerPerspective on context()</li>
+        <li>Tiered tool surface (fast/LLM)</li>
+        <li>Workspace agentPeerMap</li>
+      </ul>
+    </div>
+  </div>
+</section>
+
+<!-- SPEC: ASYNC PREFETCH -->
+<section id="spec-async">
+  <h2>Spec: async prefetch</h2>
+
+  <h3>Problem</h3>
+  <p>Calling <code>session.context()</code> and <code>peer.chat()</code> synchronously before each LLM call adds 200–800ms of Honcho round-trip latency to every turn. Users experience this as the agent "thinking slowly."</p>
+
+  <h3>Pattern</h3>
+  <p>Fire both calls as non-blocking background work at the <strong>end</strong> of each turn. Store results in a per-session cache keyed by session ID. At the <strong>start</strong> of the next turn, pop from cache — the HTTP is already done. First turn is cold (empty cache); all subsequent turns are zero-latency on the response path.</p>
+
+  <h3>Interface contract</h3>
+  <pre><code><span class="cm">// TypeScript (openclaw / nanobot plugin shape)</span>
+
+<span class="kw">interface</span> <span class="key">AsyncPrefetch</span> {
+  <span class="cm">// Fire context + dialectic fetches at turn end. Non-blocking.</span>
+  firePrefetch(sessionId: <span class="str">string</span>, userMessage: <span class="str">string</span>): <span class="kw">void</span>;
+
+  <span class="cm">// Pop cached results at turn start. Returns empty if cache is cold.</span>
+  popContextResult(sessionId: <span class="str">string</span>): ContextResult | <span class="kw">null</span>;
+  popDialecticResult(sessionId: <span class="str">string</span>): <span class="str">string</span> | <span class="kw">null</span>;
+}
+
+<span class="kw">type</span> <span class="key">ContextResult</span> = {
+  representation: <span class="str">string</span>;
+  card: <span class="str">string</span>[];
+  aiRepresentation?: <span class="str">string</span>;  <span class="cm">// AI peer context if enabled</span>
+  summary?: <span class="str">string</span>;            <span class="cm">// conversation summary if fetched</span>
+};</code></pre>
+
+  <h3>Implementation notes</h3>
+  <ul>
+    <li>Python: <code>threading.Thread(daemon=True)</code>. Write to <code>dict[session_id, result]</code> — GIL makes this safe for simple writes.</li>
+    <li>TypeScript: <code>Promise</code> stored in <code>Map&lt;string, Promise&lt;ContextResult&gt;&gt;</code>. Await at pop time. If not resolved yet, skip (return null) — do not block.</li>
+    <li>The pop is destructive: clears the cache entry after reading so stale data never accumulates.</li>
+    <li>Prefetch should also fire on first turn (even though it won't be consumed until turn 2) — this ensures turn 2 is never cold.</li>
+  </ul>
+
+  <h3>openclaw-honcho adoption</h3>
+  <p>Move <code>session.context()</code> from <code>before_prompt_build</code> to a post-<code>agent_end</code> background task. Store result in <code>state.contextCache</code>. In <code>before_prompt_build</code>, read from cache instead of calling Honcho. If cache is empty (turn 1), inject nothing — the prompt is still valid without Honcho context on the first turn.</p>
+</section>
+
+<!-- SPEC: DYNAMIC REASONING LEVEL -->
+<section id="spec-reasoning">
+  <h2>Spec: dynamic reasoning level</h2>
+
+  <h3>Problem</h3>
+  <p>Honcho's dialectic endpoint supports reasoning levels from <code>minimal</code> to <code>max</code>. A fixed level per tool wastes budget on simple queries and under-serves complex ones.</p>
+
+  <h3>Pattern</h3>
+  <p>Select the reasoning level dynamically based on the user's message. Use the configured default as a floor. Bump by message length. Cap auto-selection at <code>high</code> — never select <code>max</code> automatically.</p>
+
+  <h3>Interface contract</h3>
+  <pre><code><span class="cm">// Shared helper — identical logic in any language</span>
+
+<span class="kw">const</span> LEVELS = [<span class="str">"minimal"</span>, <span class="str">"low"</span>, <span class="str">"medium"</span>, <span class="str">"high"</span>, <span class="str">"max"</span>];
+
+<span class="kw">function</span> <span class="key">dynamicReasoningLevel</span>(
+  query: <span class="str">string</span>,
+  configDefault: <span class="str">string</span> = <span class="str">"low"</span>
+): <span class="str">string</span> {
+  <span class="kw">const</span> baseIdx = Math.max(<span class="num">0</span>, LEVELS.indexOf(configDefault));
+  <span class="kw">const</span> n = query.length;
+  <span class="kw">const</span> bump = n &lt; <span class="num">120</span> ? <span class="num">0</span> : n &lt; <span class="num">400</span> ? <span class="num">1</span> : <span class="num">2</span>;
+  <span class="kw">return</span> LEVELS[Math.min(baseIdx + bump, <span class="num">3</span>)]; <span class="cm">// cap at "high" (idx 3)</span>
+}</code></pre>
+
+  <h3>Config key</h3>
+  <p>Add a <code>dialecticReasoningLevel</code> config field (string, default <code>"low"</code>). This sets the floor. Users can raise or lower it. The dynamic bump always applies on top.</p>
+
+  <h3>openclaw-honcho adoption</h3>
+  <p>Apply in <code>honcho_recall</code> and <code>honcho_analyze</code>: replace the fixed <code>reasoningLevel</code> with the dynamic selector. <code>honcho_recall</code> should use floor <code>"minimal"</code> and <code>honcho_analyze</code> floor <code>"medium"</code> — both still bump with message length.</p>
+</section>
+
+<!-- SPEC: PER-PEER MEMORY MODES -->
+<section id="spec-modes">
+  <h2>Spec: per-peer memory modes</h2>
+
+  <h3>Problem</h3>
+  <p>Users want independent control over whether user context and agent context are written locally, to Honcho, or both. A single <code>memoryMode</code> shorthand is not granular enough.</p>
+
+  <h3>Pattern</h3>
+  <p>Three modes per peer: <code>hybrid</code> (write both local + Honcho), <code>honcho</code> (Honcho only, disable local files), <code>local</code> (local files only, skip Honcho sync for this peer). Two orthogonal axes: user peer and agent peer.</p>
+
+  <h3>Config schema</h3>
+  <pre><code><span class="cm">// ~/.openclaw/openclaw.json  (or ~/.nanobot/config.json)</span>
+{
+  <span class="str">"plugins"</span>: {
+    <span class="str">"openclaw-honcho"</span>: {
+      <span class="str">"config"</span>: {
+        <span class="str">"apiKey"</span>: <span class="str">"..."</span>,
+        <span class="str">"memoryMode"</span>: <span class="str">"hybrid"</span>,          <span class="cm">// shorthand: both peers</span>
+        <span class="str">"userMemoryMode"</span>: <span class="str">"honcho"</span>,       <span class="cm">// override for user peer</span>
+        <span class="str">"agentMemoryMode"</span>: <span class="str">"hybrid"</span>       <span class="cm">// override for agent peer</span>
+      }
+    }
+  }
+}</code></pre>
+
+  <h3>Resolution order</h3>
+  <ol>
+    <li>Per-peer field (<code>userMemoryMode</code> / <code>agentMemoryMode</code>) — wins if present.</li>
+    <li>Shorthand <code>memoryMode</code> — applies to both peers as default.</li>
+    <li>Hardcoded default: <code>"hybrid"</code>.</li>
+  </ol>
+
+  <h3>Effect on Honcho sync</h3>
+  <ul>
+    <li><code>userMemoryMode=local</code>: skip adding user peer messages to Honcho.</li>
+    <li><code>agentMemoryMode=local</code>: skip adding assistant peer messages to Honcho.</li>
+    <li>Both local: skip <code>session.addMessages()</code> entirely.</li>
+    <li><code>userMemoryMode=honcho</code>: disable local USER.md writes.</li>
+    <li><code>agentMemoryMode=honcho</code>: disable local MEMORY.md / SOUL.md writes.</li>
+  </ul>
+</section>
+
+<!-- SPEC: AI PEER IDENTITY -->
+<section id="spec-identity">
+  <h2>Spec: AI peer identity formation</h2>
+
+  <h3>Problem</h3>
+  <p>Honcho builds the user's representation organically by observing what the user says. The same mechanism exists for the AI peer — but only if <code>observe_me=True</code> is set for the agent peer. Without it, the agent peer accumulates nothing and Honcho's AI-side model never forms.</p>
+
+  <p>Additionally, existing persona files (SOUL.md, IDENTITY.md) should seed the AI peer's Honcho representation at first activation, rather than waiting for it to emerge from scratch.</p>
+
+  <h3>Part A: observe_me=True for agent peer</h3>
+  <pre><code><span class="cm">// TypeScript — in session.addPeers() call</span>
+<span class="kw">await</span> session.addPeers([
+  [ownerPeer.id, { observeMe: <span class="kw">true</span>,  observeOthers: <span class="kw">false</span> }],
+  [agentPeer.id, { observeMe: <span class="kw">true</span>,  observeOthers: <span class="kw">true</span>  }], <span class="cm">// was false</span>
+]);</code></pre>
+
+  <p>This is a one-line change but foundational. Without it, Honcho's AI peer representation stays empty regardless of what the agent says.</p>
+
+  <h3>Part B: seedAiIdentity()</h3>
+  <pre><code><span class="kw">async function</span> <span class="key">seedAiIdentity</span>(
+  session: HonchoSession,
+  agentPeer: Peer,
+  content: <span class="str">string</span>,
+  source: <span class="str">string</span>
+): Promise&lt;<span class="kw">boolean</span>&gt; {
+  <span class="kw">const</span> wrapped = [
+    <span class="str">`&lt;ai_identity_seed&gt;`</span>,
+    <span class="str">`&lt;source&gt;${source}&lt;/source&gt;`</span>,
+    <span class="str">``</span>,
+    content.trim(),
+    <span class="str">`&lt;/ai_identity_seed&gt;`</span>,
+  ].join(<span class="str">"\n"</span>);
+
+  <span class="kw">await</span> agentPeer.addMessage(<span class="str">"assistant"</span>, wrapped);
+  <span class="kw">return true</span>;
+}</code></pre>
+
+  <h3>Part C: migrate agent files at setup</h3>
+  <p>During <code>openclaw honcho setup</code>, upload agent-self files (SOUL.md, IDENTITY.md, AGENTS.md, BOOTSTRAP.md) to the agent peer using <code>seedAiIdentity()</code> instead of <code>session.uploadFile()</code>. This routes the content through Honcho's observation pipeline rather than the file store.</p>
+
+  <h3>Part D: AI peer name in identity</h3>
+  <p>When the agent has a configured name (non-default), inject it into the agent's self-identity prefix. In OpenClaw this means adding to the injected system prompt section:</p>
+  <pre><code><span class="cm">// In context hook return value</span>
+<span class="kw">return</span> {
+  systemPrompt: [
+    agentName ? <span class="str">`You are ${agentName}.`</span> : <span class="str">""</span>,
+    <span class="str">"## User Memory Context"</span>,
+    ...sections,
+  ].filter(Boolean).join(<span class="str">"\n\n"</span>)
+};</code></pre>
+
+  <h3>CLI surface: honcho identity subcommand</h3>
+  <pre><code>openclaw honcho identity &lt;file&gt;    <span class="cm"># seed from file</span>
+openclaw honcho identity --show    <span class="cm"># show current AI peer representation</span></code></pre>
+</section>
+
+<!-- SPEC: SESSION NAMING -->
+<section id="spec-sessions">
+  <h2>Spec: session naming strategies</h2>
+
+  <h3>Problem</h3>
+  <p>When Honcho is used across multiple projects or directories, a single global session means every project shares the same context. Per-directory sessions provide isolation without requiring users to name sessions manually.</p>
+
+  <h3>Strategies</h3>
+  <div class="table-wrap">
+    <table>
+      <thead><tr><th>Strategy</th><th>Session key</th><th>When to use</th></tr></thead>
+      <tbody>
+        <tr><td><code>per-directory</code></td><td>basename of CWD</td><td>Default. Each project gets its own session.</td></tr>
+        <tr><td><code>global</code></td><td>fixed string <code>"global"</code></td><td>Single cross-project session.</td></tr>
+        <tr><td>manual map</td><td>user-configured per path</td><td><code>sessions</code> config map overrides directory basename.</td></tr>
+        <tr><td>title-based</td><td>sanitized session title</td><td>When agent supports named sessions; title set mid-conversation.</td></tr>
+      </tbody>
+    </table>
+  </div>
+
+  <h3>Config schema</h3>
+  <pre><code>{
+  <span class="str">"sessionStrategy"</span>: <span class="str">"per-directory"</span>,   <span class="cm">// "per-directory" | "global"</span>
+  <span class="str">"sessionPeerPrefix"</span>: <span class="kw">false</span>,            <span class="cm">// prepend peer name to session key</span>
+  <span class="str">"sessions"</span>: {                            <span class="cm">// manual overrides</span>
+    <span class="str">"/home/user/projects/foo"</span>: <span class="str">"foo-project"</span>
+  }
+}</code></pre>
+
+  <h3>CLI surface</h3>
+  <pre><code>openclaw honcho sessions              <span class="cm"># list all mappings</span>
+openclaw honcho map &lt;name&gt;           <span class="cm"># map cwd to session name</span>
+openclaw honcho map                   <span class="cm"># no-arg = list mappings</span></code></pre>
+
+  <p>Resolution order: manual map wins &rarr; session title &rarr; directory basename &rarr; platform key.</p>
+</section>
+
+<!-- SPEC: CLI SURFACE INJECTION -->
+<section id="spec-cli">
+  <h2>Spec: CLI surface injection</h2>
+
+  <h3>Problem</h3>
+  <p>When a user asks "how do I change my memory settings?" or "what Honcho commands are available?" the agent either hallucinates or says it doesn't know. The agent should know its own management interface.</p>
+
+  <h3>Pattern</h3>
+  <p>When Honcho is active, append a compact command reference to the system prompt. The agent can cite these commands directly instead of guessing.</p>
+
+  <pre><code><span class="cm">// In context hook, append to systemPrompt</span>
+<span class="kw">const</span> honchoSection = [
+  <span class="str">"# Honcho memory integration"</span>,
+  <span class="str">`Active. Session: ${sessionKey}. Mode: ${mode}.`</span>,
+  <span class="str">"Management commands:"</span>,
+  <span class="str">"  openclaw honcho status                    — show config + connection"</span>,
+  <span class="str">"  openclaw honcho mode [hybrid|honcho|local] — show or set memory mode"</span>,
+  <span class="str">"  openclaw honcho sessions                  — list session mappings"</span>,
+  <span class="str">"  openclaw honcho map &lt;name&gt;                — map directory to session"</span>,
+  <span class="str">"  openclaw honcho identity [file] [--show]  — seed or show AI identity"</span>,
+  <span class="str">"  openclaw honcho setup                     — full interactive wizard"</span>,
+].join(<span class="str">"\n"</span>);</code></pre>
+
+  <div class="callout warn">
+    <strong>Keep it compact.</strong> This section is injected every turn. Keep it under 300 chars of context. List commands, not explanations — the agent can explain them on request.
+  </div>
+</section>
+
+<!-- OPENCLAW CHECKLIST -->
+<section id="openclaw-checklist">
+  <h2>openclaw-honcho checklist</h2>
+
+  <p>Ordered by impact. Each item maps to a spec section above.</p>
+
+  <ul class="checklist">
+    <li class="todo"><strong>Async prefetch</strong> — move <code>session.context()</code> out of <code>before_prompt_build</code> into post-<code>agent_end</code> background Promise. Pop from cache at prompt build. (<a href="#spec-async">spec</a>)</li>
+    <li class="todo"><strong>observe_me=True for agent peer</strong> — one-line change in <code>session.addPeers()</code> config for agent peer. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>Dynamic reasoning level</strong> — add <code>dynamicReasoningLevel()</code> helper; apply in <code>honcho_recall</code> and <code>honcho_analyze</code>. Add <code>dialecticReasoningLevel</code> to config schema. (<a href="#spec-reasoning">spec</a>)</li>
+    <li class="todo"><strong>Per-peer memory modes</strong> — add <code>userMemoryMode</code> / <code>agentMemoryMode</code> to config; gate Honcho sync and local writes accordingly. (<a href="#spec-modes">spec</a>)</li>
+    <li class="todo"><strong>seedAiIdentity()</strong> — add helper; apply during setup migration for SOUL.md / IDENTITY.md instead of <code>session.uploadFile()</code>. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>Session naming strategies</strong> — add <code>sessionStrategy</code>, <code>sessions</code> map, <code>sessionPeerPrefix</code> to config; implement resolution function. (<a href="#spec-sessions">spec</a>)</li>
+    <li class="todo"><strong>CLI surface injection</strong> — append command reference to <code>before_prompt_build</code> return value when Honcho is active. (<a href="#spec-cli">spec</a>)</li>
+    <li class="todo"><strong>honcho identity subcommand</strong> — add <code>openclaw honcho identity</code> CLI command. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>AI peer name injection</strong> — if <code>aiPeer</code> name configured, prepend to injected system prompt. (<a href="#spec-identity">spec</a>)</li>
+    <li class="todo"><strong>honcho mode / honcho sessions / honcho map</strong> — CLI parity with Hermes. (<a href="#spec-sessions">spec</a>)</li>
+  </ul>
+
+  <div class="callout success">
+    <strong>Already done in openclaw-honcho (do not re-implement):</strong> lastSavedIndex dedup, platform metadata stripping, multi-agent parent observer hierarchy, peerPerspective on context(), tiered tool surface (fast/LLM), workspace agentPeerMap, QMD passthrough, self-hosted Honcho support.
+  </div>
+</section>
+
+<!-- NANOBOT CHECKLIST -->
+<section id="nanobot-checklist">
+  <h2>nanobot-honcho checklist</h2>
+
+  <p>nanobot-honcho is a greenfield integration. Start from openclaw-honcho's architecture (hook-based, dual peer) and apply all Hermes patterns from day one rather than retrofitting. Priority order:</p>
+
+  <h3>Phase 1 — core correctness</h3>
+  <ul class="checklist">
+    <li class="todo">Dual peer model (owner + agent peer), both with <code>observe_me=True</code></li>
+    <li class="todo">Message capture at turn end with <code>lastSavedIndex</code> dedup</li>
+    <li class="todo">Platform metadata stripping before Honcho storage</li>
+    <li class="todo">Async prefetch from day one — do not implement blocking context injection</li>
+    <li class="todo">Legacy file migration at first activation (USER.md → owner peer, SOUL.md → <code>seedAiIdentity()</code>)</li>
+  </ul>
+
+  <h3>Phase 2 — configuration</h3>
+  <ul class="checklist">
+    <li class="todo">Config schema: <code>apiKey</code>, <code>workspaceId</code>, <code>baseUrl</code>, <code>memoryMode</code>, <code>userMemoryMode</code>, <code>agentMemoryMode</code>, <code>dialecticReasoningLevel</code>, <code>sessionStrategy</code>, <code>sessions</code></li>
+    <li class="todo">Per-peer memory mode gating</li>
+    <li class="todo">Dynamic reasoning level</li>
+    <li class="todo">Session naming strategies</li>
+  </ul>
+
+  <h3>Phase 3 — tools and CLI</h3>
+  <ul class="checklist">
+    <li class="todo">Tool surface: <code>honcho_profile</code>, <code>honcho_recall</code>, <code>honcho_analyze</code>, <code>honcho_search</code>, <code>honcho_context</code></li>
+    <li class="todo">CLI: <code>setup</code>, <code>status</code>, <code>sessions</code>, <code>map</code>, <code>mode</code>, <code>identity</code></li>
+    <li class="todo">CLI surface injection into system prompt</li>
+    <li class="todo">AI peer name wired into agent identity</li>
+  </ul>
+</section>
+
+</div>
+
+<script type="module">
+  import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs';
+  mermaid.initialize({ startOnLoad: true, securityLevel: 'loose', fontFamily: 'Departure Mono, Noto Emoji, monospace' });
+</script>
+<script>
+  window.addEventListener('scroll', () => {
+    const bar = document.getElementById('progress');
+    const max = document.documentElement.scrollHeight - window.innerHeight;
+    bar.style.width = (max > 0 ? (window.scrollY / max) * 100 : 0) + '%';
+  });
+</script>
+</body>
+</html>
--- a/docs/honcho-integration-spec.md
+++ b/docs/honcho-integration-spec.md
@@ -0,0 +1,377 @@
+# honcho-integration-spec
+
+Comparison of Hermes Agent vs. openclaw-honcho — and a porting spec for bringing Hermes patterns into other Honcho integrations.
+
+---
+
+## Overview
+
+Two independent Honcho integrations have been built for two different agent runtimes: **Hermes Agent** (Python, baked into the runner) and **openclaw-honcho** (TypeScript plugin via hook/tool API). Both use the same Honcho peer paradigm — dual peer model, `session.context()`, `peer.chat()` — but they made different tradeoffs at every layer.
+
+This document maps those tradeoffs and defines a porting spec: a set of Hermes-originated patterns, each stated as an integration-agnostic interface, that any Honcho integration can adopt regardless of runtime or language.
+
+> **Scope** Both integrations work correctly today. This spec is about the delta — patterns in Hermes that are worth propagating and patterns in openclaw-honcho that Hermes should eventually adopt. The spec is additive, not prescriptive.
+
+---
+
+## Architecture comparison
+
+### Hermes: baked-in runner
+
+Honcho is initialised directly inside `AIAgent.__init__`. There is no plugin boundary. Session management, context injection, async prefetch, and CLI surface are all first-class concerns of the runner. Context is injected once per session (baked into `_cached_system_prompt`) and never re-fetched mid-session — this maximises prefix cache hits at the LLM provider.
+
+Turn flow:
+
+```
+user message
+  → _honcho_prefetch()       (reads cache — no HTTP)
+  → _build_system_prompt()   (first turn only, cached)
+  → LLM call
+  → response
+  → _honcho_fire_prefetch()  (daemon threads, turn end)
+       → prefetch_context() thread  ──┐
+       → prefetch_dialectic() thread ─┴→ _context_cache / _dialectic_cache
+```
+
+### openclaw-honcho: hook-based plugin
+
+The plugin registers hooks against OpenClaw's event bus. Context is fetched synchronously inside `before_prompt_build` on every turn. Message capture happens in `agent_end`. The multi-agent hierarchy is tracked via `subagent_spawned`. This model is correct but every turn pays a blocking Honcho round-trip before the LLM call can begin.
+
+Turn flow:
+
+```
+user message
+  → before_prompt_build (BLOCKING HTTP — every turn)
+       → session.context()
+  → system prompt assembled
+  → LLM call
+  → response
+  → agent_end hook
+       → session.addMessages()
+       → session.setMetadata()
+```
+
+---
+
+## Diff table
+
+| Dimension | Hermes Agent | openclaw-honcho |
+|---|---|---|
+| **Context injection timing** | Once per session (cached). Zero HTTP on response path after turn 1. | Every turn, blocking. Fresh context per turn but adds latency. |
+| **Prefetch strategy** | Daemon threads fire at turn end; consumed next turn from cache. | None. Blocking call at prompt-build time. |
+| **Dialectic (peer.chat)** | Prefetched async; result injected into system prompt next turn. | On-demand via `honcho_recall` / `honcho_analyze` tools. |
+| **Reasoning level** | Dynamic: scales with message length. Floor = config default. Cap = "high". | Fixed per tool: recall=minimal, analyze=medium. |
+| **Memory modes** | `user_memory_mode` / `agent_memory_mode`: hybrid / honcho / local. | None. Always writes to Honcho. |
+| **Write frequency** | async (background queue), turn, session, N turns. | After every agent_end (no control). |
+| **AI peer identity** | `observe_me=True`, `seed_ai_identity()`, `get_ai_representation()`, SOUL.md → AI peer. | Agent files uploaded to agent peer at setup. No ongoing self-observation. |
+| **Context scope** | User peer + AI peer representation, both injected. | User peer (owner) representation + conversation summary. `peerPerspective` on context call. |
+| **Session naming** | per-directory / global / manual map / title-based. | Derived from platform session key. |
+| **Multi-agent** | Single-agent only. | Parent observer hierarchy via `subagent_spawned`. |
+| **Tool surface** | Single `query_user_context` tool (on-demand dialectic). | 6 tools: session, profile, search, context (fast) + recall, analyze (LLM). |
+| **Platform metadata** | Not stripped. | Explicitly stripped before Honcho storage. |
+| **Message dedup** | None. | `lastSavedIndex` in session metadata prevents re-sending. |
+| **CLI surface in prompt** | Management commands injected into system prompt. Agent knows its own CLI. | Not injected. |
+| **AI peer name in identity** | Replaces "Hermes Agent" in DEFAULT_AGENT_IDENTITY when configured. | Not implemented. |
+| **QMD / local file search** | Not implemented. | Passthrough tools when QMD backend configured. |
+| **Workspace metadata** | Not implemented. | `agentPeerMap` in workspace metadata tracks agent→peer ID. |
+
+---
+
+## Patterns
+
+Six patterns from Hermes are worth adopting in any Honcho integration. Each is described as an integration-agnostic interface.
+
+**Hermes contributes:**
+- Async prefetch (zero-latency)
+- Dynamic reasoning level
+- Per-peer memory modes
+- AI peer identity formation
+- Session naming strategies
+- CLI surface injection
+
+**openclaw-honcho contributes back (Hermes should adopt):**
+- `lastSavedIndex` dedup
+- Platform metadata stripping
+- Multi-agent observer hierarchy
+- `peerPerspective` on `context()`
+- Tiered tool surface (fast/LLM)
+- Workspace `agentPeerMap`
+
+---
+
+## Spec: async prefetch
+
+### Problem
+
+Calling `session.context()` and `peer.chat()` synchronously before each LLM call adds 200–800ms of Honcho round-trip latency to every turn.
+
+### Pattern
+
+Fire both calls as non-blocking background work at the **end** of each turn. Store results in a per-session cache keyed by session ID. At the **start** of the next turn, pop from cache — the HTTP is already done. First turn is cold (empty cache); all subsequent turns are zero-latency on the response path.
+
+### Interface contract
+
+```typescript
+interface AsyncPrefetch {
+  // Fire context + dialectic fetches at turn end. Non-blocking.
+  firePrefetch(sessionId: string, userMessage: string): void;
+
+  // Pop cached results at turn start. Returns empty if cache is cold.
+  popContextResult(sessionId: string): ContextResult | null;
+  popDialecticResult(sessionId: string): string | null;
+}
+
+type ContextResult = {
+  representation: string;
+  card: string[];
+  aiRepresentation?: string;  // AI peer context if enabled
+  summary?: string;           // conversation summary if fetched
+};
+```
+
+### Implementation notes
+
+- **Python:** `threading.Thread(daemon=True)`. Write to `dict[session_id, result]` — GIL makes this safe for simple writes.
+- **TypeScript:** `Promise` stored in `Map<string, Promise<ContextResult>>`. Await at pop time. If not resolved yet, return null — do not block.
+- The pop is destructive: clears the cache entry after reading so stale data never accumulates.
+- Prefetch should also fire on first turn (even though it won't be consumed until turn 2).
+
+### openclaw-honcho adoption
+
+Move `session.context()` from `before_prompt_build` to a post-`agent_end` background task. Store result in `state.contextCache`. In `before_prompt_build`, read from cache instead of calling Honcho. If cache is empty (turn 1), inject nothing — the prompt is still valid without Honcho context on the first turn.
+
+---
+
+## Spec: dynamic reasoning level
+
+### Problem
+
+Honcho's dialectic endpoint supports reasoning levels from `minimal` to `max`. A fixed level per tool wastes budget on simple queries and under-serves complex ones.
+
+### Pattern
+
+Select the reasoning level dynamically based on the user's message. Use the configured default as a floor. Bump by message length. Cap auto-selection at `high` — never select `max` automatically.
+
+### Logic
+
+```
+< 120 chars  → default (typically "low")
+120–400 chars → one level above default (cap at "high")
+> 400 chars  → two levels above default (cap at "high")
+```
+
+### Config key
+
+Add `dialecticReasoningLevel` (string, default `"low"`). This sets the floor. The dynamic bump always applies on top.
+
+### openclaw-honcho adoption
+
+Apply in `honcho_recall` and `honcho_analyze`: replace fixed `reasoningLevel` with the dynamic selector. `honcho_recall` uses floor `"minimal"`, `honcho_analyze` uses floor `"medium"` — both still bump with message length.
+
+---
+
+## Spec: per-peer memory modes
+
+### Problem
+
+Users want independent control over whether user context and agent context are written locally, to Honcho, or both.
+
+### Modes
+
+| Mode | Effect |
+|---|---|
+| `hybrid` | Write to both local files and Honcho (default) |
+| `honcho` | Honcho only — disable corresponding local file writes |
+| `local` | Local files only — skip Honcho sync for this peer |
+
+### Config schema
+
+```json
+{
+  "memoryMode": "hybrid",
+  "userMemoryMode": "honcho",
+  "agentMemoryMode": "hybrid"
+}
+```
+
+Resolution order: per-peer field wins → shorthand `memoryMode` → default `"hybrid"`.
+
+### Effect on Honcho sync
+
+- `userMemoryMode=local`: skip adding user peer messages to Honcho
+- `agentMemoryMode=local`: skip adding assistant peer messages to Honcho
+- Both local: skip `session.addMessages()` entirely
+- `userMemoryMode=honcho`: disable local USER.md writes
+- `agentMemoryMode=honcho`: disable local MEMORY.md / SOUL.md writes
+
+---
+
+## Spec: AI peer identity formation
+
+### Problem
+
+Honcho builds the user's representation organically by observing what the user says. The same mechanism exists for the AI peer — but only if `observe_me=True` is set for the agent peer. Without it, the agent peer accumulates nothing.
+
+Additionally, existing persona files (SOUL.md, IDENTITY.md) should seed the AI peer's Honcho representation at first activation.
+
+### Part A: observe_me=True for agent peer
+
+```typescript
+await session.addPeers([
+  [ownerPeer.id, { observeMe: true,  observeOthers: false }],
+  [agentPeer.id, { observeMe: true,  observeOthers: true  }], // was false
+]);
+```
+
+One-line change. Foundational. Without it, the AI peer representation stays empty regardless of what the agent says.
+
+### Part B: seedAiIdentity()
+
+```typescript
+async function seedAiIdentity(
+  agentPeer: Peer,
+  content: string,
+  source: string
+): Promise<boolean> {
+  const wrapped = [
+    `<ai_identity_seed>`,
+    `<source>${source}</source>`,
+    ``,
+    content.trim(),
+    `</ai_identity_seed>`,
+  ].join("\n");
+
+  await agentPeer.addMessage("assistant", wrapped);
+  return true;
+}
+```
+
+### Part C: migrate agent files at setup
+
+During `honcho setup`, upload agent-self files (SOUL.md, IDENTITY.md, AGENTS.md) to the agent peer via `seedAiIdentity()` instead of `session.uploadFile()`. This routes content through Honcho's observation pipeline.
+
+### Part D: AI peer name in identity
+
+When the agent has a configured name, prepend it to the injected system prompt:
+
+```typescript
+const namePrefix = agentName ? `You are ${agentName}.\n\n` : "";
+return { systemPrompt: namePrefix + "## User Memory Context\n\n" + sections };
+```
+
+### CLI surface
+
+```
+honcho identity <file>    # seed from file
+honcho identity --show    # show current AI peer representation
+```
+
+---
+
+## Spec: session naming strategies
+
+### Problem
+
+A single global session means every project shares the same Honcho context. Per-directory sessions provide isolation without requiring users to name sessions manually.
+
+### Strategies
+
+| Strategy | Session key | When to use |
+|---|---|---|
+| `per-directory` | basename of CWD | Default. Each project gets its own session. |
+| `global` | fixed string `"global"` | Single cross-project session. |
+| manual map | user-configured per path | `sessions` config map overrides directory basename. |
+| title-based | sanitized session title | When agent supports named sessions set mid-conversation. |
+
+### Config schema
+
+```json
+{
+  "sessionStrategy": "per-directory",
+  "sessionPeerPrefix": false,
+  "sessions": {
+    "/home/user/projects/foo": "foo-project"
+  }
+}
+```
+
+### CLI surface
+
+```
+honcho sessions              # list all mappings
+honcho map <name>            # map cwd to session name
+honcho map                   # no-arg = list mappings
+```
+
+Resolution order: manual map → session title → directory basename → platform key.
+
+---
+
+## Spec: CLI surface injection
+
+### Problem
+
+When a user asks "how do I change my memory settings?" the agent either hallucinates or says it doesn't know. The agent should know its own management interface.
+
+### Pattern
+
+When Honcho is active, append a compact command reference to the system prompt. Keep it under 300 chars.
+
+```
+# Honcho memory integration
+Active. Session: {sessionKey}. Mode: {mode}.
+Management commands:
+  honcho status                    — show config + connection
+  honcho mode [hybrid|honcho|local] — show or set memory mode
+  honcho sessions                  — list session mappings
+  honcho map <name>                — map directory to session
+  honcho identity [file] [--show]  — seed or show AI identity
+  honcho setup                     — full interactive wizard
+```
+
+---
+
+## openclaw-honcho checklist
+
+Ordered by impact:
+
+- [ ] **Async prefetch** — move `session.context()` out of `before_prompt_build` into post-`agent_end` background Promise
+- [ ] **observe_me=True for agent peer** — one-line change in `session.addPeers()`
+- [ ] **Dynamic reasoning level** — add helper; apply in `honcho_recall` and `honcho_analyze`; add `dialecticReasoningLevel` to config
+- [ ] **Per-peer memory modes** — add `userMemoryMode` / `agentMemoryMode` to config; gate Honcho sync and local writes
+- [ ] **seedAiIdentity()** — add helper; use during setup migration for SOUL.md / IDENTITY.md
+- [ ] **Session naming strategies** — add `sessionStrategy`, `sessions` map, `sessionPeerPrefix`
+- [ ] **CLI surface injection** — append command reference to `before_prompt_build` return value
+- [ ] **honcho identity subcommand** — seed from file or `--show` current representation
+- [ ] **AI peer name injection** — if `aiPeer` name configured, prepend to injected system prompt
+- [ ] **honcho mode / sessions / map** — CLI parity with Hermes
+
+Already done in openclaw-honcho (do not re-implement): `lastSavedIndex` dedup, platform metadata stripping, multi-agent parent observer, `peerPerspective` on `context()`, tiered tool surface, workspace `agentPeerMap`, QMD passthrough, self-hosted Honcho.
+
+---
+
+## nanobot-honcho checklist
+
+Greenfield integration. Start from openclaw-honcho's architecture and apply all Hermes patterns from day one.
+
+### Phase 1 — core correctness
+
+- [ ] Dual peer model (owner + agent peer), both with `observe_me=True`
+- [ ] Message capture at turn end with `lastSavedIndex` dedup
+- [ ] Platform metadata stripping before Honcho storage
+- [ ] Async prefetch from day one — do not implement blocking context injection
+- [ ] Legacy file migration at first activation (USER.md → owner peer, SOUL.md → `seedAiIdentity()`)
+
+### Phase 2 — configuration
+
+- [ ] Config schema: `apiKey`, `workspaceId`, `baseUrl`, `memoryMode`, `userMemoryMode`, `agentMemoryMode`, `dialecticReasoningLevel`, `sessionStrategy`, `sessions`
+- [ ] Per-peer memory mode gating
+- [ ] Dynamic reasoning level
+- [ ] Session naming strategies
+
+### Phase 3 — tools and CLI
+
+- [ ] Tool surface: `honcho_profile`, `honcho_recall`, `honcho_analyze`, `honcho_search`, `honcho_context`
+- [ ] CLI: `setup`, `status`, `sessions`, `map`, `mode`, `identity`
+- [ ] CLI surface injection into system prompt
+- [ ] AI peer name wired into agent identity
--- a/docs/migration/openclaw.md
+++ b/docs/migration/openclaw.md
@@ -0,0 +1,142 @@
+# Migrating from OpenClaw to Hermes Agent
+
+This guide covers how to import your OpenClaw settings, memories, skills, and API keys into Hermes Agent.
+
+## Three Ways to Migrate
+
+### 1. Automatic (during first-time setup)
+
+When you run `hermes setup` for the first time and Hermes detects `~/.openclaw`, it automatically offers to import your OpenClaw data before configuration begins. Just accept the prompt and everything is handled for you.
+
+### 2. CLI Command (quick, scriptable)
+
+```bash
+hermes claw migrate                      # Preview then migrate (always shows preview first)
+hermes claw migrate --dry-run            # Preview only, no changes
+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 |
+|------|-------------|
+| `--source PATH` | Path to OpenClaw directory (default: `~/.openclaw`) |
+| `--dry-run` | Preview only — no files are modified |
+| `--preset {user-data,full}` | Migration preset (default: `full`). `user-data` excludes secrets |
+| `--overwrite` | Overwrite existing files (default: skip conflicts) |
+| `--migrate-secrets` | Include allowlisted secrets (auto-enabled with `full` preset) |
+| `--workspace-target PATH` | Copy workspace instructions (AGENTS.md) to this absolute path |
+| `--skill-conflict {skip,overwrite,rename}` | How to handle skill name conflicts (default: `skip`) |
+| `--yes`, `-y` | Skip confirmation prompts |
+
+### 3. Agent-Guided (interactive, with previews)
+
+Ask the agent to run the migration for you:
+
+```
+> Migrate my OpenClaw setup to Hermes
+```
+
+The agent will use the `openclaw-migration` skill to:
+1. Run a preview first to show what would change
+2. Ask about conflict resolution (SOUL.md, skills, etc.)
+3. Let you choose between `user-data` and `full` presets
+4. Execute the migration with your choices
+5. Print a detailed summary of what was migrated
+
+## What Gets Migrated
+
+### `user-data` preset
+| Item | Source | Destination |
+|------|--------|-------------|
+| SOUL.md | `~/.openclaw/workspace/SOUL.md` | `~/.hermes/SOUL.md` |
+| Memory entries | `~/.openclaw/workspace/MEMORY.md` | `~/.hermes/memories/MEMORY.md` |
+| User profile | `~/.openclaw/workspace/USER.md` | `~/.hermes/memories/USER.md` |
+| Skills | `~/.openclaw/workspace/skills/` | `~/.hermes/skills/openclaw-imports/` |
+| Command allowlist | `~/.openclaw/workspace/exec_approval_patterns.yaml` | Merged into `~/.hermes/config.yaml` |
+| Messaging settings | `~/.openclaw/config.yaml` (TELEGRAM_ALLOWED_USERS, MESSAGING_CWD) | `~/.hermes/.env` |
+| TTS assets | `~/.openclaw/workspace/tts/` | `~/.hermes/tts/` |
+
+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` |
+
+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.
+
+## Conflict Handling
+
+By default, the migration **will not overwrite** existing Hermes data:
+
+- **SOUL.md** — skipped if one already exists in `~/.hermes/`
+- **Memory entries** — skipped if memories already exist (to avoid duplicates)
+- **Skills** — skipped if a skill with the same name already exists
+- **API keys** — skipped if the key is already set in `~/.hermes/.env`
+
+To overwrite conflicts, use `--overwrite`. The migration creates backups before overwriting.
+
+For skills, you can also use `--skill-conflict rename` to import conflicting skills under a new name (e.g., `skill-name-imported`).
+
+## Migration Report
+
+Every migration 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.
+
+## Troubleshooting
+
+### "OpenClaw directory not found"
+The migration looks for `~/.openclaw` by default, then tries `~/.clawdbot` and `~/.moldbot`. If your OpenClaw is installed elsewhere, use `--source`:
+```bash
+hermes claw migrate --source /path/to/.openclaw
+```
+
+### "Migration script not found"
+The migration script ships with Hermes Agent. If you installed via pip (not git clone), the `optional-skills/` directory may not be present. Install the skill from the Skills Hub:
+```bash
+hermes skills install openclaw-migration
+```
+
+### Memory overflow
+If your OpenClaw MEMORY.md or USER.md exceeds Hermes' character limits, excess entries are exported to an overflow file in the migration report directory. You can manually review and add the most important ones.
+
+### 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`.
--- a/docs/plans/2026-03-16-pricing-accuracy-architecture-design.md
+++ b/docs/plans/2026-03-16-pricing-accuracy-architecture-design.md
@@ -0,0 +1,608 @@
+# Pricing Accuracy Architecture
+
+Date: 2026-03-16
+
+## Goal
+
+Hermes should only show dollar costs when they are backed by an official source for the user's actual billing path.
+
+This design replaces the current static, heuristic pricing flow in:
+
+- `run_agent.py`
+- `agent/usage_pricing.py`
+- `agent/insights.py`
+- `cli.py`
+
+with a provider-aware pricing system that:
+
+- handles cache billing correctly
+- distinguishes `actual` vs `estimated` vs `included` vs `unknown`
+- reconciles post-hoc costs when providers expose authoritative billing data
+- supports direct providers, OpenRouter, subscriptions, enterprise pricing, and custom endpoints
+
+## Problems In The Current Design
+
+Current Hermes behavior has four structural issues:
+
+1. It stores only `prompt_tokens` and `completion_tokens`, which is insufficient for providers that bill cache reads and cache writes separately.
+2. It uses a static model price table and fuzzy heuristics, which can drift from current official pricing.
+3. It assumes public API list pricing matches the user's real billing path.
+4. It has no distinction between live estimates and reconciled billed cost.
+
+## Design Principles
+
+1. Normalize usage before pricing.
+2. Never fold cached tokens into plain input cost.
+3. Track certainty explicitly.
+4. Treat the billing path as part of the model identity.
+5. Prefer official machine-readable sources over scraped docs.
+6. Use post-hoc provider cost APIs when available.
+7. Show `n/a` rather than inventing precision.
+
+## High-Level Architecture
+
+The new system has four layers:
+
+1. `usage_normalization`
+   Converts raw provider usage into a canonical usage record.
+2. `pricing_source_resolution`
+   Determines the billing path, source of truth, and applicable pricing source.
+3. `cost_estimation_and_reconciliation`
+   Produces an immediate estimate when possible, then replaces or annotates it with actual billed cost later.
+4. `presentation`
+   `/usage`, `/insights`, and the status bar display cost with certainty metadata.
+
+## Canonical Usage Record
+
+Add a canonical usage model that every provider path maps into before any pricing math happens.
+
+Suggested structure:
+
+```python
+@dataclass
+class CanonicalUsage:
+    provider: str
+    billing_provider: str
+    model: str
+    billing_route: str
+
+    input_tokens: int = 0
+    output_tokens: int = 0
+    cache_read_tokens: int = 0
+    cache_write_tokens: int = 0
+    reasoning_tokens: int = 0
+    request_count: int = 1
+
+    raw_usage: dict[str, Any] | None = None
+    raw_usage_fields: dict[str, str] | None = None
+    computed_fields: set[str] | None = None
+
+    provider_request_id: str | None = None
+    provider_generation_id: str | None = None
+    provider_response_id: str | None = None
+```
+
+Rules:
+
+- `input_tokens` means non-cached input only.
+- `cache_read_tokens` and `cache_write_tokens` are never merged into `input_tokens`.
+- `output_tokens` excludes cache metrics.
+- `reasoning_tokens` is telemetry unless a provider officially bills it separately.
+
+This is the same normalization pattern used by `opencode`, extended with provenance and reconciliation ids.
+
+## Provider Normalization Rules
+
+### OpenAI Direct
+
+Source usage fields:
+
+- `prompt_tokens`
+- `completion_tokens`
+- `prompt_tokens_details.cached_tokens`
+
+Normalization:
+
+- `cache_read_tokens = cached_tokens`
+- `input_tokens = prompt_tokens - cached_tokens`
+- `cache_write_tokens = 0` unless OpenAI exposes it in the relevant route
+- `output_tokens = completion_tokens`
+
+### Anthropic Direct
+
+Source usage fields:
+
+- `input_tokens`
+- `output_tokens`
+- `cache_read_input_tokens`
+- `cache_creation_input_tokens`
+
+Normalization:
+
+- `input_tokens = input_tokens`
+- `output_tokens = output_tokens`
+- `cache_read_tokens = cache_read_input_tokens`
+- `cache_write_tokens = cache_creation_input_tokens`
+
+### OpenRouter
+
+Estimate-time usage normalization should use the response usage payload with the same rules as the underlying provider when possible.
+
+Reconciliation-time records should also store:
+
+- OpenRouter generation id
+- native token fields when available
+- `total_cost`
+- `cache_discount`
+- `upstream_inference_cost`
+- `is_byok`
+
+### Gemini / Vertex
+
+Use official Gemini or Vertex usage fields where available.
+
+If cached content tokens are exposed:
+
+- map them to `cache_read_tokens`
+
+If a route exposes no cache creation metric:
+
+- store `cache_write_tokens = 0`
+- preserve the raw usage payload for later extension
+
+### DeepSeek And Other Direct Providers
+
+Normalize only the fields that are officially exposed.
+
+If a provider does not expose cache buckets:
+
+- do not infer them unless the provider explicitly documents how to derive them
+
+### Subscription / Included-Cost Routes
+
+These still use the canonical usage model.
+
+Tokens are tracked normally. Cost depends on billing mode, not on whether usage exists.
+
+## Billing Route Model
+
+Hermes must stop keying pricing solely by `model`.
+
+Introduce a billing route descriptor:
+
+```python
+@dataclass
+class BillingRoute:
+    provider: str
+    base_url: str | None
+    model: str
+    billing_mode: str
+    organization_hint: str | None = None
+```
+
+`billing_mode` values:
+
+- `official_cost_api`
+- `official_generation_api`
+- `official_models_api`
+- `official_docs_snapshot`
+- `subscription_included`
+- `user_override`
+- `custom_contract`
+- `unknown`
+
+Examples:
+
+- OpenAI direct API with Costs API access: `official_cost_api`
+- Anthropic direct API with Usage & Cost API access: `official_cost_api`
+- OpenRouter request before reconciliation: `official_models_api`
+- OpenRouter request after generation lookup: `official_generation_api`
+- GitHub Copilot style subscription route: `subscription_included`
+- local OpenAI-compatible server: `unknown`
+- enterprise contract with configured rates: `custom_contract`
+
+## Cost Status Model
+
+Every displayed cost should have:
+
+```python
+@dataclass
+class CostResult:
+    amount_usd: Decimal | None
+    status: Literal["actual", "estimated", "included", "unknown"]
+    source: Literal[
+        "provider_cost_api",
+        "provider_generation_api",
+        "provider_models_api",
+        "official_docs_snapshot",
+        "user_override",
+        "custom_contract",
+        "none",
+    ]
+    label: str
+    fetched_at: datetime | None
+    pricing_version: str | None
+    notes: list[str]
+```
+
+Presentation rules:
+
+- `actual`: show dollar amount as final
+- `estimated`: show dollar amount with estimate labeling
+- `included`: show `included` or `$0.00 (included)` depending on UX choice
+- `unknown`: show `n/a`
+
+## Official Source Hierarchy
+
+Resolve cost using this order:
+
+1. Request-level or account-level official billed cost
+2. Official machine-readable model pricing
+3. Official docs snapshot
+4. User override or custom contract
+5. Unknown
+
+The system must never skip to a lower level if a higher-confidence source exists for the current billing route.
+
+## Provider-Specific Truth Rules
+
+### OpenAI Direct
+
+Preferred truth:
+
+1. Costs API for reconciled spend
+2. Official pricing page for live estimate
+
+### Anthropic Direct
+
+Preferred truth:
+
+1. Usage & Cost API for reconciled spend
+2. Official pricing docs for live estimate
+
+### OpenRouter
+
+Preferred truth:
+
+1. `GET /api/v1/generation` for reconciled `total_cost`
+2. `GET /api/v1/models` pricing for live estimate
+
+Do not use underlying provider public pricing as the source of truth for OpenRouter billing.
+
+### Gemini / Vertex
+
+Preferred truth:
+
+1. official billing export or billing API for reconciled spend when available for the route
+2. official pricing docs for estimate
+
+### DeepSeek
+
+Preferred truth:
+
+1. official machine-readable cost source if available in the future
+2. official pricing docs snapshot today
+
+### Subscription-Included Routes
+
+Preferred truth:
+
+1. explicit route config marking the model as included in subscription
+
+These should display `included`, not an API list-price estimate.
+
+### Custom Endpoint / Local Model
+
+Preferred truth:
+
+1. user override
+2. custom contract config
+3. unknown
+
+These should default to `unknown`.
+
+## Pricing Catalog
+
+Replace the current `MODEL_PRICING` dict with a richer pricing catalog.
+
+Suggested record:
+
+```python
+@dataclass
+class PricingEntry:
+    provider: str
+    route_pattern: str
+    model_pattern: str
+
+    input_cost_per_million: Decimal | None = None
+    output_cost_per_million: Decimal | None = None
+    cache_read_cost_per_million: Decimal | None = None
+    cache_write_cost_per_million: Decimal | None = None
+    request_cost: Decimal | None = None
+    image_cost: Decimal | None = None
+
+    source: str = "official_docs_snapshot"
+    source_url: str | None = None
+    fetched_at: datetime | None = None
+    pricing_version: str | None = None
+```
+
+The catalog should be route-aware:
+
+- `openai:gpt-5`
+- `anthropic:claude-opus-4-6`
+- `openrouter:anthropic/claude-opus-4.6`
+- `copilot:gpt-4o`
+
+This avoids conflating direct-provider billing with aggregator billing.
+
+## Pricing Sync Architecture
+
+Introduce a pricing sync subsystem instead of manually maintaining a single hardcoded table.
+
+Suggested modules:
+
+- `agent/pricing/catalog.py`
+- `agent/pricing/sources.py`
+- `agent/pricing/sync.py`
+- `agent/pricing/reconcile.py`
+- `agent/pricing/types.py`
+
+### Sync Sources
+
+- OpenRouter models API
+- official provider docs snapshots where no API exists
+- user overrides from config
+
+### Sync Output
+
+Cache pricing entries locally with:
+
+- source URL
+- fetch timestamp
+- version/hash
+- confidence/source type
+
+### Sync Frequency
+
+- startup warm cache
+- background refresh every 6 to 24 hours depending on source
+- manual `hermes pricing sync`
+
+## Reconciliation Architecture
+
+Live requests may produce only an estimate initially. Hermes should reconcile them later when a provider exposes actual billed cost.
+
+Suggested flow:
+
+1. Agent call completes.
+2. Hermes stores canonical usage plus reconciliation ids.
+3. Hermes computes an immediate estimate if a pricing source exists.
+4. A reconciliation worker fetches actual cost when supported.
+5. Session and message records are updated with `actual` cost.
+
+This can run:
+
+- inline for cheap lookups
+- asynchronously for delayed provider accounting
+
+## Persistence Changes
+
+Session storage should stop storing only aggregate prompt/completion totals.
+
+Add fields for both usage and cost certainty:
+
+- `input_tokens`
+- `output_tokens`
+- `cache_read_tokens`
+- `cache_write_tokens`
+- `reasoning_tokens`
+- `estimated_cost_usd`
+- `actual_cost_usd`
+- `cost_status`
+- `cost_source`
+- `pricing_version`
+- `billing_provider`
+- `billing_mode`
+
+If schema expansion is too large for one PR, add a new pricing events table:
+
+```text
+session_cost_events
+  id
+  session_id
+  request_id
+  provider
+  model
+  billing_mode
+  input_tokens
+  output_tokens
+  cache_read_tokens
+  cache_write_tokens
+  estimated_cost_usd
+  actual_cost_usd
+  cost_status
+  cost_source
+  pricing_version
+  created_at
+  updated_at
+```
+
+## Hermes Touchpoints
+
+### `run_agent.py`
+
+Current responsibility:
+
+- parse raw provider usage
+- update session token counters
+
+New responsibility:
+
+- build `CanonicalUsage`
+- update canonical counters
+- store reconciliation ids
+- emit usage event to pricing subsystem
+
+### `agent/usage_pricing.py`
+
+Current responsibility:
+
+- static lookup table
+- direct cost arithmetic
+
+New responsibility:
+
+- move or replace with pricing catalog facade
+- no fuzzy model-family heuristics
+- no direct pricing without billing-route context
+
+### `cli.py`
+
+Current responsibility:
+
+- compute session cost directly from prompt/completion totals
+
+New responsibility:
+
+- display `CostResult`
+- show status badges:
+  - `actual`
+  - `estimated`
+  - `included`
+  - `n/a`
+
+### `agent/insights.py`
+
+Current responsibility:
+
+- recompute historical estimates from static pricing
+
+New responsibility:
+
+- aggregate stored pricing events
+- prefer actual cost over estimate
+- surface estimates only when reconciliation is unavailable
+
+## UX Rules
+
+### Status Bar
+
+Show one of:
+
+- `$1.42`
+- `~$1.42`
+- `included`
+- `cost n/a`
+
+Where:
+
+- `$1.42` means `actual`
+- `~$1.42` means `estimated`
+- `included` means subscription-backed or explicitly zero-cost route
+- `cost n/a` means unknown
+
+### `/usage`
+
+Show:
+
+- token buckets
+- estimated cost
+- actual cost if available
+- cost status
+- pricing source
+
+### `/insights`
+
+Aggregate:
+
+- actual cost totals
+- estimated-only totals
+- unknown-cost sessions count
+- included-cost sessions count
+
+## Config And Overrides
+
+Add user-configurable pricing overrides in config:
+
+```yaml
+pricing:
+  mode: hybrid
+  sync_on_startup: true
+  sync_interval_hours: 12
+  overrides:
+    - provider: openrouter
+      model: anthropic/claude-opus-4.6
+      billing_mode: custom_contract
+      input_cost_per_million: 4.25
+      output_cost_per_million: 22.0
+      cache_read_cost_per_million: 0.5
+      cache_write_cost_per_million: 6.0
+  included_routes:
+    - provider: copilot
+      model: "*"
+    - provider: codex-subscription
+      model: "*"
+```
+
+Overrides must win over catalog defaults for the matching billing route.
+
+## Rollout Plan
+
+### Phase 1
+
+- add canonical usage model
+- split cache token buckets in `run_agent.py`
+- stop pricing cache-inflated prompt totals
+- preserve current UI with improved backend math
+
+### Phase 2
+
+- add route-aware pricing catalog
+- integrate OpenRouter models API sync
+- add `estimated` vs `included` vs `unknown`
+
+### Phase 3
+
+- add reconciliation for OpenRouter generation cost
+- add actual cost persistence
+- update `/insights` to prefer actual cost
+
+### Phase 4
+
+- add direct OpenAI and Anthropic reconciliation paths
+- add user overrides and contract pricing
+- add pricing sync CLI command
+
+## Testing Strategy
+
+Add tests for:
+
+- OpenAI cached token subtraction
+- Anthropic cache read/write separation
+- OpenRouter estimated vs actual reconciliation
+- subscription-backed models showing `included`
+- custom endpoints showing `n/a`
+- override precedence
+- stale catalog fallback behavior
+
+Current tests that assume heuristic pricing should be replaced with route-aware expectations.
+
+## Non-Goals
+
+- exact enterprise billing reconstruction without an official source or user override
+- backfilling perfect historical cost for old sessions that lack cache bucket data
+- scraping arbitrary provider web pages at request time
+
+## Recommendation
+
+Do not expand the existing `MODEL_PRICING` dict.
+
+That path cannot satisfy the product requirement. Hermes should instead migrate to:
+
+- canonical usage normalization
+- route-aware pricing sources
+- estimate-then-reconcile cost lifecycle
+- explicit certainty states in the UI
+
+This is the minimum architecture that makes the statement "Hermes pricing is backed by official sources where possible, and otherwise clearly labeled" defensible.
--- a/docs/skins/example-skin.yaml
+++ b/docs/skins/example-skin.yaml
@@ -0,0 +1,89 @@
+# ============================================================================
+# Hermes Agent — Example Skin Template
+# ============================================================================
+#
+# Copy this file to ~/.hermes/skins/<name>.yaml to create a custom skin.
+# All fields are optional — missing values inherit from the default skin.
+# Activate with: /skin <name>  or  display.skin: <name> in config.yaml
+#
+# See hermes_cli/skin_engine.py for the full schema reference.
+# ============================================================================
+
+# Required: unique skin name (used in /skin command and config)
+name: example
+description: An example custom skin — copy and modify this template
+
+# ── Colors ──────────────────────────────────────────────────────────────────
+# Hex color values for Rich markup. These control the CLI's visual palette.
+colors:
+  # Banner panel (the startup welcome box)
+  banner_border: "#CD7F32"        # Panel border
+  banner_title: "#FFD700"         # Panel title text
+  banner_accent: "#FFBF00"        # Section headers (Available Tools, Skills, etc.)
+  banner_dim: "#B8860B"           # Dim/muted text (separators, model info)
+  banner_text: "#FFF8DC"          # Body text (tool names, skill names)
+
+  # UI elements
+  ui_accent: "#FFBF00"            # General accent color
+  ui_label: "#4dd0e1"             # Labels
+  ui_ok: "#4caf50"                # Success indicators
+  ui_error: "#ef5350"             # Error indicators
+  ui_warn: "#ffa726"              # Warning indicators
+
+  # Input area
+  prompt: "#FFF8DC"               # Prompt text color
+  input_rule: "#CD7F32"           # Horizontal rule around input
+
+  # Response box
+  response_border: "#FFD700"      # Response box border (ANSI color)
+
+  # Session display
+  session_label: "#DAA520"        # Session label
+  session_border: "#8B8682"       # Session ID dim color
+
+# ── Spinner ─────────────────────────────────────────────────────────────────
+# Customize the animated spinner shown during API calls and tool execution.
+spinner:
+  # Faces shown while waiting for the API response
+  waiting_faces:
+    - "(｡◕‿◕｡)"
+    - "(◕‿◕✿)"
+    - "٩(◕‿◕｡)۶"
+
+  # Faces shown during extended thinking/reasoning
+  thinking_faces:
+    - "(｡•́︿•̀｡)"
+    - "(◔_◔)"
+    - "(¬‿¬)"
+
+  # Verbs used in spinner messages (e.g., "pondering your request...")
+  thinking_verbs:
+    - "pondering"
+    - "contemplating"
+    - "musing"
+    - "ruminating"
+
+  # Optional: left/right decorations around the spinner
+  # Each entry is a [left, right] pair. Omit entirely for no wings.
+  # wings:
+  #   - ["⟪⚔", "⚔⟫"]
+  #   - ["⟪▲", "▲⟫"]
+
+# ── Branding ────────────────────────────────────────────────────────────────
+# Text strings used throughout the CLI interface.
+branding:
+  agent_name: "Hermes Agent"          # Banner title, about display
+  welcome: "Welcome! Type your message or /help for commands."
+  goodbye: "Goodbye! ⚕"              # Exit message
+  response_label: " ⚕ Hermes "       # Response box header label
+  prompt_symbol: "❯ "                 # Input prompt symbol
+  help_header: "(^_^)? Available Commands"  # /help header text
+
+# ── Tool Output ─────────────────────────────────────────────────────────────
+# Character used as the prefix for tool output lines.
+# Default is "┊" (thin dotted vertical line). Some alternatives:
+#   "╎" (light triple dash vertical)
+#   "▏" (left one-eighth block)
+#   "│" (box drawing light vertical)
+#   "┃" (box drawing heavy vertical)
+tool_prefix: "┊"
--- a/docs/specs/container-cli-review-fixes.md
+++ b/docs/specs/container-cli-review-fixes.md
@@ -0,0 +1,329 @@
+# 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`)
--- a/environments/tool_context.py
+++ b/environments/tool_context.py
@@ -53,6 +53,7 @@ def _run_tool_in_thread(tool_name: str, arguments: Dict[str, Any], task_id: str)
    try:
        loop = asyncio.get_running_loop()
        # We're in an async context -- need to run in thread
+        import concurrent.futures
        with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
            future = pool.submit(
                handle_function_call, tool_name, arguments, task_id
--- a/flake.lock
+++ b/flake.lock
@@ -36,26 +36,6 @@
        "type": "github"
      }
    },
-    "npm-lockfile-fix": {
-      "inputs": {
-        "nixpkgs": [
-          "nixpkgs"
-        ]
-      },
-      "locked": {
-        "lastModified": 1775903712,
-        "narHash": "sha256-2GV79U6iVH4gKAPWYrxUReB0S41ty/Y3dBLquU8AlaA=",
-        "owner": "jeslie0",
-        "repo": "npm-lockfile-fix",
-        "rev": "c6093acb0c0548e0f9b8b3d82918823721930fe8",
-        "type": "github"
-      },
-      "original": {
-        "owner": "jeslie0",
-        "repo": "npm-lockfile-fix",
-        "type": "github"
-      }
-    },
    "pyproject-build-systems": {
      "inputs": {
        "nixpkgs": [
@@ -144,7 +124,6 @@
      "inputs": {
        "flake-parts": "flake-parts",
        "nixpkgs": "nixpkgs",
-        "npm-lockfile-fix": "npm-lockfile-fix",
        "pyproject-build-systems": "pyproject-build-systems",
        "pyproject-nix": "pyproject-nix_2",
        "uv2nix": "uv2nix_2"
--- a/flake.nix
+++ b/flake.nix
@@ -19,20 +19,11 @@
      url = "github:pyproject-nix/build-system-pkgs";
      inputs.nixpkgs.follows = "nixpkgs";
    };
-    npm-lockfile-fix = {
-      url = "github:jeslie0/npm-lockfile-fix";
-      inputs.nixpkgs.follows = "nixpkgs";
-    };
  };

-  outputs =
-    inputs:
+  outputs = inputs:
    inputs.flake-parts.lib.mkFlake { inherit inputs; } {
-      systems = [
-        "x86_64-linux"
-        "aarch64-linux"
-        "aarch64-darwin"
-      ];
+      systems = [ "x86_64-linux" "aarch64-linux" "aarch64-darwin" ];

      imports = [
        ./nix/packages.nix
--- a/gateway/builtin_hooks/boot_md.py
+++ b/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")

--- a/gateway/channel_directory.py
+++ b/gateway/channel_directory.py
@@ -100,7 +100,7 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:


 def _build_discord(adapter) -> List[Dict[str, str]]:
-    """Enumerate all text channels and forum channels the Discord bot can see."""
+    """Enumerate all text channels the Discord bot can see."""
    channels = []
    client = getattr(adapter, "_client", None)
    if not client:
@@ -119,15 +119,6 @@ def _build_discord(adapter) -> List[Dict[str, str]]:
                "guild": guild.name,
                "type": "channel",
            })
-        # Forum channels (type 15) — creating a message auto-spawns a thread post.
-        forums = getattr(guild, "forum_channels", None) or []
-        for ch in forums:
-            channels.append({
-                "id": str(ch.id),
-                "name": ch.name,
-                "guild": guild.name,
-                "type": "forum",
-            })
        # Also include DM-capable users we've interacted with is not
        # feasible via guild enumeration; those come from sessions.

@@ -200,15 +191,6 @@ def load_directory() -> Dict[str, Any]:
        return {"updated_at": None, "platforms": {}}


-def lookup_channel_type(platform_name: str, chat_id: str) -> Optional[str]:
-    """Return the channel ``type`` string (e.g. ``"channel"``, ``"forum"``) for *chat_id*, or *None* if unknown."""
-    directory = load_directory()
-    for ch in directory.get("platforms", {}).get(platform_name, []):
-        if ch.get("id") == chat_id:
-            return ch.get("type")
-    return None
-
-
 def resolve_channel_name(platform_name: str, name: str) -> Optional[str]:
    """
    Resolve a human-friendly channel name to a numeric ID.
--- a/gateway/config.py
+++ b/gateway/config.py
@@ -66,7 +66,6 @@ class Platform(Enum):
    WECOM_CALLBACK = "wecom_callback"
    WEIXIN = "weixin"
    BLUEBUBBLES = "bluebubbles"
-    QQBOT = "qqbot"


@dataclass
@@ -258,13 +257,6 @@ class GatewayConfig:
    # Streaming configuration
    streaming: StreamingConfig = field(default_factory=StreamingConfig)

-    # Session store pruning: drop SessionEntry records older than this many
-    # days from the in-memory dict and sessions.json.  Keeps the store from
-    # growing unbounded in gateways serving many chats/threads/users over
-    # months.  Pruning is invisible to users — if they resume, they get a
-    # fresh session exactly as if the reset policy had fired.  0 = disabled.
-    session_store_max_age_days: int = 90
-
    def get_connected_platforms(self) -> List[Platform]:
        """Return list of platforms that are enabled and configured."""
        connected = []
@@ -311,17 +303,6 @@ class GatewayConfig:
            # BlueBubbles uses extra dict for local server config
            elif platform == Platform.BLUEBUBBLES and config.extra.get("server_url") and config.extra.get("password"):
                connected.append(platform)
-            # QQBot uses extra dict for app credentials
-            elif platform == Platform.QQBOT and config.extra.get("app_id") and config.extra.get("client_secret"):
-                connected.append(platform)
-            # DingTalk uses client_id/client_secret from config.extra or env vars
-            elif platform == Platform.DINGTALK and (
-                config.extra.get("client_id") or os.getenv("DINGTALK_CLIENT_ID")
-            ) and (
-                config.extra.get("client_secret") or os.getenv("DINGTALK_CLIENT_SECRET")
-            ):
-                connected.append(platform)
-        
        return connected
    
    def get_home_channel(self, platform: Platform) -> Optional[HomeChannel]:
@@ -372,7 +353,6 @@ class GatewayConfig:
            "thread_sessions_per_user": self.thread_sessions_per_user,
            "unauthorized_dm_behavior": self.unauthorized_dm_behavior,
            "streaming": self.streaming.to_dict(),
-            "session_store_max_age_days": self.session_store_max_age_days,
        }
    
    @classmethod
@@ -420,13 +400,6 @@ class GatewayConfig:
            "pair",
        )

-        try:
-            session_store_max_age_days = int(data.get("session_store_max_age_days", 90))
-            if session_store_max_age_days < 0:
-                session_store_max_age_days = 0
-        except (TypeError, ValueError):
-            session_store_max_age_days = 90
-
        return cls(
            platforms=platforms,
            default_reset_policy=default_policy,
@@ -441,7 +414,6 @@ class GatewayConfig:
            thread_sessions_per_user=_coerce_bool(thread_sessions_per_user, False),
            unauthorized_dm_behavior=unauthorized_dm_behavior,
            streaming=StreamingConfig.from_dict(data.get("streaming", {})),
-            session_store_max_age_days=session_store_max_age_days,
        )

    def get_unauthorized_dm_behavior(self, platform: Optional[Platform] = None) -> str:
@@ -576,22 +548,8 @@ def load_gateway_config() -> GatewayConfig:
                    bridged["free_response_channels"] = platform_cfg["free_response_channels"]
                if "mention_patterns" in platform_cfg:
                    bridged["mention_patterns"] = platform_cfg["mention_patterns"]
-                if "dm_policy" in platform_cfg:
-                    bridged["dm_policy"] = platform_cfg["dm_policy"]
-                if "allow_from" in platform_cfg:
-                    bridged["allow_from"] = platform_cfg["allow_from"]
-                if "group_policy" in platform_cfg:
-                    bridged["group_policy"] = platform_cfg["group_policy"]
-                if "group_allow_from" in platform_cfg:
-                    bridged["group_allow_from"] = platform_cfg["group_allow_from"]
                if plat == 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, {})
@@ -649,20 +607,6 @@ def load_gateway_config() -> GatewayConfig:
                    if isinstance(ntc, list):
                        ntc = ",".join(str(v) for v in ntc)
                    os.environ["DISCORD_NO_THREAD_CHANNELS"] = str(ntc)
-                # allow_mentions: granular control over what the bot can ping.
-                # Safe defaults (no @everyone/roles) are applied in the adapter;
-                # these YAML keys only override when set and let users opt back
-                # into unsafe modes (e.g. roles=true) if they actually want it.
-                allow_mentions_cfg = discord_cfg.get("allow_mentions")
-                if isinstance(allow_mentions_cfg, dict):
-                    for yaml_key, env_key in (
-                        ("everyone", "DISCORD_ALLOW_MENTION_EVERYONE"),
-                        ("roles", "DISCORD_ALLOW_MENTION_ROLES"),
-                        ("users", "DISCORD_ALLOW_MENTION_USERS"),
-                        ("replied_user", "DISCORD_ALLOW_MENTION_REPLIED_USER"),
-                    ):
-                        if yaml_key in allow_mentions_cfg and not os.getenv(env_key):
-                            os.environ[env_key] = str(allow_mentions_cfg[yaml_key]).lower()

            # Telegram settings → env vars (env vars take precedence)
            telegram_cfg = yaml_cfg.get("telegram", {})
@@ -670,31 +614,15 @@ def load_gateway_config() -> GatewayConfig:
                if "require_mention" in telegram_cfg and not os.getenv("TELEGRAM_REQUIRE_MENTION"):
                    os.environ["TELEGRAM_REQUIRE_MENTION"] = str(telegram_cfg["require_mention"]).lower()
                if "mention_patterns" in telegram_cfg and not os.getenv("TELEGRAM_MENTION_PATTERNS"):
-                    os.environ["TELEGRAM_MENTION_PATTERNS"] = json.dumps(telegram_cfg["mention_patterns"])
+                    import json as _json
+                    os.environ["TELEGRAM_MENTION_PATTERNS"] = _json.dumps(telegram_cfg["mention_patterns"])
                frc = telegram_cfg.get("free_response_chats")
                if frc is not None and not os.getenv("TELEGRAM_FREE_RESPONSE_CHATS"):
                    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):
@@ -707,38 +635,6 @@ def load_gateway_config() -> GatewayConfig:
                    if isinstance(frc, list):
                        frc = ",".join(str(v) for v in frc)
                    os.environ["WHATSAPP_FREE_RESPONSE_CHATS"] = str(frc)
-                if "dm_policy" in whatsapp_cfg and not os.getenv("WHATSAPP_DM_POLICY"):
-                    os.environ["WHATSAPP_DM_POLICY"] = str(whatsapp_cfg["dm_policy"]).lower()
-                af = whatsapp_cfg.get("allow_from")
-                if af is not None and not os.getenv("WHATSAPP_ALLOWED_USERS"):
-                    if isinstance(af, list):
-                        af = ",".join(str(v) for v in af)
-                    os.environ["WHATSAPP_ALLOWED_USERS"] = str(af)
-                if "group_policy" in whatsapp_cfg and not os.getenv("WHATSAPP_GROUP_POLICY"):
-                    os.environ["WHATSAPP_GROUP_POLICY"] = str(whatsapp_cfg["group_policy"]).lower()
-                gaf = whatsapp_cfg.get("group_allow_from")
-                if gaf is not None and not os.getenv("WHATSAPP_GROUP_ALLOWED_USERS"):
-                    if isinstance(gaf, list):
-                        gaf = ",".join(str(v) for v in gaf)
-                    os.environ["WHATSAPP_GROUP_ALLOWED_USERS"] = str(gaf)
-
-            # DingTalk settings → env vars (env vars take precedence)
-            dingtalk_cfg = yaml_cfg.get("dingtalk", {})
-            if isinstance(dingtalk_cfg, dict):
-                if "require_mention" in dingtalk_cfg and not os.getenv("DINGTALK_REQUIRE_MENTION"):
-                    os.environ["DINGTALK_REQUIRE_MENTION"] = str(dingtalk_cfg["require_mention"]).lower()
-                if "mention_patterns" in dingtalk_cfg and not os.getenv("DINGTALK_MENTION_PATTERNS"):
-                    os.environ["DINGTALK_MENTION_PATTERNS"] = json.dumps(dingtalk_cfg["mention_patterns"])
-                frc = dingtalk_cfg.get("free_response_chats")
-                if frc is not None and not os.getenv("DINGTALK_FREE_RESPONSE_CHATS"):
-                    if isinstance(frc, list):
-                        frc = ",".join(str(v) for v in frc)
-                    os.environ["DINGTALK_FREE_RESPONSE_CHATS"] = str(frc)
-                allowed = dingtalk_cfg.get("allowed_users")
-                if allowed is not None and not os.getenv("DINGTALK_ALLOWED_USERS"):
-                    if isinstance(allowed, list):
-                        allowed = ",".join(str(v) for v in allowed)
-                    os.environ["DINGTALK_ALLOWED_USERS"] = str(allowed)

            # Matrix settings → env vars (env vars take precedence)
            matrix_cfg = yaml_cfg.get("matrix", {})
@@ -769,17 +665,6 @@ 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):
@@ -816,31 +701,7 @@ 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:
@@ -1083,25 +944,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
        if webhook_secret:
            config.platforms[Platform.WEBHOOK].extra["secret"] = webhook_secret

-    # DingTalk
-    dingtalk_client_id = os.getenv("DINGTALK_CLIENT_ID")
-    dingtalk_client_secret = os.getenv("DINGTALK_CLIENT_SECRET")
-    if dingtalk_client_id and dingtalk_client_secret:
-        if Platform.DINGTALK not in config.platforms:
-            config.platforms[Platform.DINGTALK] = PlatformConfig()
-        config.platforms[Platform.DINGTALK].enabled = True
-        config.platforms[Platform.DINGTALK].extra.update({
-            "client_id": dingtalk_client_id,
-            "client_secret": dingtalk_client_secret,
-        })
-        dingtalk_home = os.getenv("DINGTALK_HOME_CHANNEL")
-        if dingtalk_home:
-            config.platforms[Platform.DINGTALK].home_channel = HomeChannel(
-                platform=Platform.DINGTALK,
-                chat_id=dingtalk_home,
-                name=os.getenv("DINGTALK_HOME_CHANNEL_NAME", "Home"),
-            )
-
    # Feishu / Lark
    feishu_app_id = os.getenv("FEISHU_APP_ID")
    feishu_app_secret = os.getenv("FEISHU_APP_SECRET")
@@ -1232,43 +1074,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
            name=os.getenv("BLUEBUBBLES_HOME_CHANNEL_NAME", "Home"),
        )

-    # QQ (Official Bot API v2)
-    qq_app_id = os.getenv("QQ_APP_ID")
-    qq_client_secret = os.getenv("QQ_CLIENT_SECRET")
-    if qq_app_id or qq_client_secret:
-        if Platform.QQBOT not in config.platforms:
-            config.platforms[Platform.QQBOT] = PlatformConfig()
-        config.platforms[Platform.QQBOT].enabled = True
-        extra = config.platforms[Platform.QQBOT].extra
-        if qq_app_id:
-            extra["app_id"] = qq_app_id
-        if qq_client_secret:
-            extra["client_secret"] = qq_client_secret
-        qq_allowed_users = os.getenv("QQ_ALLOWED_USERS", "").strip()
-        if qq_allowed_users:
-            extra["allow_from"] = qq_allowed_users
-        qq_group_allowed = os.getenv("QQ_GROUP_ALLOWED_USERS", "").strip()
-        if qq_group_allowed:
-            extra["group_allow_from"] = qq_group_allowed
-        qq_home = os.getenv("QQBOT_HOME_CHANNEL", "").strip()
-        qq_home_name_env = "QQBOT_HOME_CHANNEL_NAME"
-        if not qq_home:
-            # Back-compat: accept the pre-rename name and log a one-time warning.
-            legacy_home = os.getenv("QQ_HOME_CHANNEL", "").strip()
-            if legacy_home:
-                qq_home = legacy_home
-                qq_home_name_env = "QQ_HOME_CHANNEL_NAME"
-                logging.getLogger(__name__).warning(
-                    "QQ_HOME_CHANNEL is deprecated; rename to QQBOT_HOME_CHANNEL "
-                    "in your .env for consistency with the platform key."
-                )
-        if qq_home:
-            config.platforms[Platform.QQBOT].home_channel = HomeChannel(
-                platform=Platform.QQBOT,
-                chat_id=qq_home,
-                name=os.getenv("QQBOT_HOME_CHANNEL_NAME") or os.getenv(qq_home_name_env, "Home"),
-            )
-
    # Session settings
    idle_minutes = os.getenv("SESSION_IDLE_MINUTES")
    if idle_minutes:
--- a/gateway/delivery.py
+++ b/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

--- a/gateway/display_config.py
+++ b/gateway/display_config.py
@@ -9,10 +9,6 @@ Resolution order (first non-None wins):
    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
@@ -86,7 +82,7 @@ _PLATFORM_DEFAULTS: dict[str, dict[str, Any]] = {

    # Tier 3 — no edit support, progress messages are permanent
    "signal":          _TIER_LOW,
-    "whatsapp":        _TIER_MEDIUM,  # Baileys bridge supports /edit
+    "whatsapp":        _TIER_LOW,
    "bluebubbles":     _TIER_LOW,
    "weixin":          _TIER_LOW,
    "wecom":           _TIER_LOW,
@@ -147,13 +143,10 @@ def resolve_display_setting(
            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)
+    # 2. Global user setting (display.<key>)
+    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)
@@ -170,6 +163,25 @@ def resolve_display_setting(
    return fallback


+def get_platform_defaults(platform_key: str) -> dict[str, Any]:
+    """Return the built-in default display settings for a platform.
+
+    Falls back to ``_GLOBAL_DEFAULTS`` for unknown platforms.
+    """
+    return dict(_PLATFORM_DEFAULTS.get(platform_key, _GLOBAL_DEFAULTS))
+
+
+def get_effective_display(user_config: dict, platform_key: str) -> dict[str, Any]:
+    """Return the fully-resolved display settings for a platform.
+
+    Useful for status commands that want to show all effective settings.
+    """
+    return {
+        key: resolve_display_setting(user_config, platform_key, key)
+        for key in OVERRIDEABLE_KEYS
+    }
+
+
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
--- a/gateway/platforms/init.py
+++ b/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",
 ]
--- a/gateway/platforms/api_server.py
+++ b/gateway/platforms/api_server.py
--- a/gateway/platforms/base.py
+++ b/gateway/platforms/base.py
@@ -6,7 +6,6 @@ and implement the required methods.
 """

 import asyncio
-import inspect
 import ipaddress
 import logging
 import os
@@ -19,64 +18,9 @@ import uuid
 from abc import ABC, abstractmethod
 from urllib.parse import urlsplit

-from utils import normalize_proxy_url
-
 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.

@@ -161,13 +105,13 @@ def resolve_proxy_url(platform_env_var: str | None = None) -> str | None:
    if platform_env_var:
        value = (os.environ.get(platform_env_var) or "").strip()
        if value:
-            return normalize_proxy_url(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 normalize_proxy_url(value)
-    return normalize_proxy_url(_detect_macos_system_proxy())
+            return value
+    return _detect_macos_system_proxy()


 def proxy_kwargs_for_bot(proxy_url: str | None) -> dict:
@@ -393,9 +337,12 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
    if not is_safe_url(url):
        raise ValueError(f"Blocked unsafe URL (SSRF protection): {safe_url_for_log(url)}")

+    import asyncio
    import httpx
-    _log = logging.getLogger(__name__)
+    import logging as _logging
+    _log = _logging.getLogger(__name__)

+    last_exc = None
    async with httpx.AsyncClient(
        timeout=30.0,
        follow_redirects=True,
@@ -413,6 +360,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
                response.raise_for_status()
                return cache_image_from_bytes(response.content, ext)
            except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
+                last_exc = exc
                if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
                    raise
                if attempt < retries:
@@ -428,6 +376,7 @@ async def cache_image_from_url(url: str, ext: str = ".jpg", retries: int = 2) ->
                    await asyncio.sleep(wait)
                    continue
                raise
+    raise last_exc


 def cleanup_image_cache(max_age_hours: int = 24) -> int:
@@ -507,9 +456,12 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
    if not is_safe_url(url):
        raise ValueError(f"Blocked unsafe URL (SSRF protection): {safe_url_for_log(url)}")

+    import asyncio
    import httpx
-    _log = logging.getLogger(__name__)
+    import logging as _logging
+    _log = _logging.getLogger(__name__)

+    last_exc = None
    async with httpx.AsyncClient(
        timeout=30.0,
        follow_redirects=True,
@@ -527,6 +479,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
                response.raise_for_status()
                return cache_audio_from_bytes(response.content, ext)
            except (httpx.TimeoutException, httpx.HTTPStatusError) as exc:
+                last_exc = exc
                if isinstance(exc, httpx.HTTPStatusError) and exc.response.status_code < 429:
                    raise
                if attempt < retries:
@@ -542,39 +495,7 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg", retries: int = 2) ->
                    await asyncio.sleep(wait)
                    continue
                raise
-
-
-# ---------------------------------------------------------------------------
-# Video cache utilities
-#
-# Same pattern as image/audio cache -- videos from platforms are downloaded
-# here so the agent can reference them by local file path.
-# ---------------------------------------------------------------------------
-
-VIDEO_CACHE_DIR = get_hermes_dir("cache/videos", "video_cache")
-
-SUPPORTED_VIDEO_TYPES = {
-    ".mp4": "video/mp4",
-    ".mov": "video/quicktime",
-    ".webm": "video/webm",
-    ".mkv": "video/x-matroska",
-    ".avi": "video/x-msvideo",
-}
-
-
-def get_video_cache_dir() -> Path:
-    """Return the video cache directory, creating it if it doesn't exist."""
-    VIDEO_CACHE_DIR.mkdir(parents=True, exist_ok=True)
-    return VIDEO_CACHE_DIR
-
-
-def cache_video_from_bytes(data: bytes, ext: str = ".mp4") -> str:
-    """Save raw video bytes to the cache and return the absolute file path."""
-    cache_dir = get_video_cache_dir()
-    filename = f"video_{uuid.uuid4().hex[:12]}{ext}"
-    filepath = cache_dir / filename
-    filepath.write_bytes(data)
-    return str(filepath)
+    raise last_exc


 # ---------------------------------------------------------------------------
@@ -695,15 +616,6 @@ class MessageEvent:
    # Original platform data
    raw_message: Any = None
    message_id: Optional[str] = None
-
-    # Platform-specific update identifier.  For Telegram this is the
-    # ``update_id`` from the PTB Update wrapper; other platforms currently
-    # ignore it.  Used by ``/restart`` to record the triggering update so the
-    # new gateway can advance the Telegram offset past it and avoid processing
-    # the same ``/restart`` twice if PTB's graceful-shutdown ACK times out
-    # ("Error while calling `get_updates` one more time to mark all fetched
-    # updates" in gateway.log).
-    platform_update_id: Optional[int] = None
    
    # Media attachments
    # media_urls: local file paths (for vision tool access)
@@ -717,10 +629,6 @@ class MessageEvent:
    # 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
    
    # Internal flag — set for synthetic events (e.g. background process
    # completion notifications) that must bypass user authorization checks.
@@ -769,56 +677,25 @@ 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.
+    the whole burst, while non-photo follow-ups still replace the pending
+    event normally.
    """
    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
-
+    if (
+        existing
+        and getattr(existing, "message_type", None) == MessageType.PHOTO
+        and event.message_type == MessageType.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
    pending_messages[session_key] = event


@@ -846,36 +723,6 @@ _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.
@@ -905,12 +752,6 @@ class BasePlatformAdapter(ABC):
        # Gateway shutdown cancels these so an old gateway instance doesn't keep
        # working on a task after --replace or manual restarts.
        self._background_tasks: set[asyncio.Task] = set()
-        # One-shot callbacks to fire after the main response is delivered.
-        # Keyed by session_key. Values are either a bare callback (legacy) or
-        # a ``(generation, callback)`` tuple so GatewayRunner can make deferred
-        # deliveries generation-aware and avoid stale runs clearing callbacks
-        # registered by a fresher run for the same session.
-        self._post_delivery_callbacks: Dict[str, Any] = {}
        self._expected_cancelled_tasks: set[asyncio.Task] = set()
        self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
        # Chats where auto-TTS on voice input is disabled (set by /voice off)
@@ -1081,40 +922,16 @@ class BasePlatformAdapter(ABC):
        """
        pass

-    # Default: the adapter treats ``finalize=True`` on edit_message as a
-    # no-op and is happy to have the stream consumer skip redundant final
-    # edits.  Subclasses that *require* an explicit finalize call to close
-    # out the message lifecycle (e.g. rich card / AI assistant surfaces
-    # such as DingTalk AI Cards) override this to True (class attribute or
-    # property) so the stream consumer knows not to short-circuit.
-    REQUIRES_EDIT_FINALIZE: bool = False
-
    async def edit_message(
        self,
        chat_id: str,
        message_id: str,
        content: str,
-        *,
-        finalize: bool = False,
    ) -> SendResult:
        """
        Edit a previously sent message. Optional — platforms that don't
        support editing return success=False and callers fall back to
        sending a new message.
-
-        ``finalize`` signals that this is the last edit in a streaming
-        sequence.  Most platforms (Telegram, Slack, Discord, Matrix,
-        etc.) treat it as a no-op because their edit APIs have no notion
-        of message lifecycle state — an edit is an edit.  Platforms that
-        render streaming updates with a distinct "in progress" state and
-        require explicit closure (e.g. rich card / AI assistant surfaces
-        such as DingTalk AI Cards) use it to finalize the message and
-        transition the UI out of the streaming indicator — those should
-        also set ``REQUIRES_EDIT_FINALIZE = True`` so callers route a
-        final edit through even when content is unchanged.  Callers
-        should set ``finalize=True`` on the final edit of a streamed
-        response (typically when ``got_done`` fires in the stream
-        consumer) and leave it ``False`` on intermediate edits.
        """
        return SendResult(success=False, error="Not supported")

@@ -1343,7 +1160,7 @@ class BasePlatformAdapter(ABC):
        # Extract MEDIA:<path> tags, allowing optional whitespace after the colon
        # and quoted/backticked paths for LLM-formatted outputs.
        media_pattern = re.compile(
-            r'''[`"']?MEDIA:\s*(?P<path>`[^`\n]+`|"[^"\n]+"|'[^'\n]+'|(?:~/|/)\S+(?:[^\S\n]+\S+)*?\.(?:png|jpe?g|gif|webp|mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a|pdf)(?=[\s`"',;:)\]}]|$)|\S+)[`"']?'''
+            r'''[`"']?MEDIA:\s*(?P<path>`[^`\n]+`|"[^"\n]+"|'[^'\n]+'|(?:~/|/)\S+(?:[^\S\n]+\S+)*?\.(?:png|jpe?g|gif|webp|mp4|mov|avi|mkv|webm|ogg|opus|mp3|wav|m4a)(?=[\s`"',;:)\]}]|$)|\S+)[`"']?'''
        )
        for match in media_pattern.finditer(content):
            path = match.group("path").strip()
@@ -1351,7 +1168,7 @@ 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:
@@ -1428,13 +1245,7 @@ class BasePlatformAdapter(ABC):

        return paths, cleaned

-    async def _keep_typing(
-        self,
-        chat_id: str,
-        interval: float = 2.0,
-        metadata=None,
-        stop_event: asyncio.Event | None = None,
-    ) -> None:
+    async def _keep_typing(self, chat_id: str, interval: float = 2.0, metadata=None) -> None:
        """
        Continuously send typing indicator until cancelled.
        
@@ -1448,18 +1259,9 @@ class BasePlatformAdapter(ABC):
        """
        try:
            while True:
-                if stop_event is not None and stop_event.is_set():
-                    return
                if chat_id not in self._typing_paused:
                    await self.send_typing(chat_id, metadata=metadata)
-                if stop_event is None:
-                    await asyncio.sleep(interval)
-                    continue
-                try:
-                    await asyncio.wait_for(stop_event.wait(), timeout=interval)
-                except asyncio.TimeoutError:
-                    continue
-                return
+                await asyncio.sleep(interval)
        except asyncio.CancelledError:
            pass  # Normal cancellation when handler completes
        finally:
@@ -1486,59 +1288,6 @@ class BasePlatformAdapter(ABC):
        """Resume typing indicator for a chat after approval resolves."""
        self._typing_paused.discard(chat_id)

-    async def interrupt_session_activity(self, session_key: str, chat_id: str) -> None:
-        """Signal the active session loop to stop and clear typing immediately."""
-        if session_key:
-            interrupt_event = self._active_sessions.get(session_key)
-            if interrupt_event is not None:
-                interrupt_event.set()
-        try:
-            await self.stop_typing(chat_id)
-        except Exception:
-            pass
-
-    def register_post_delivery_callback(
-        self,
-        session_key: str,
-        callback: Callable,
-        *,
-        generation: int | None = None,
-    ) -> None:
-        """Register a deferred callback to fire after the main response.
-
-        ``generation`` lets callers tie the callback to a specific gateway run
-        generation so stale runs cannot clear callbacks owned by a fresher run.
-        """
-        if not session_key or not callable(callback):
-            return
-        if generation is None:
-            self._post_delivery_callbacks[session_key] = callback
-        else:
-            self._post_delivery_callbacks[session_key] = (int(generation), callback)
-
-    def pop_post_delivery_callback(
-        self,
-        session_key: str,
-        *,
-        generation: int | None = None,
-    ) -> Callable | None:
-        """Pop a deferred callback, optionally requiring generation ownership."""
-        if not session_key:
-            return None
-        entry = self._post_delivery_callbacks.get(session_key)
-        if entry is None:
-            return None
-        if isinstance(entry, tuple) and len(entry) == 2:
-            entry_generation, callback = entry
-            if generation is not None and int(entry_generation) != int(generation):
-                return None
-            self._post_delivery_callbacks.pop(session_key, None)
-            return callback if callable(callback) else None
-        if generation is not None:
-            return None
-        self._post_delivery_callbacks.pop(session_key, None)
-        return entry if callable(entry) else None
-
    # ── Processing lifecycle hooks ──────────────────────────────────────────
    # Subclasses override these to react to message processing events
    # (e.g. Discord adds 👀/✅/❌ reactions).
@@ -1707,9 +1456,7 @@ class BasePlatformAdapter(ABC):
            # session lifecycle and its cleanup races with the running task
            # (see PR #4926).
            cmd = event.get_command()
-            from hermes_cli.commands import should_bypass_active_session
-
-            if should_bypass_active_session(cmd):
+            if cmd in ("approve", "deny", "status", "stop", "new", "reset", "background", "restart"):
                logger.debug(
                    "[%s] Command '/%s' bypassing active-session guard for %s",
                    self.name, cmd, session_key,
@@ -1779,6 +1526,8 @@ class BasePlatformAdapter(ABC):
          HERMES_HUMAN_DELAY_MIN_MS: minimum delay in ms (default 800, custom mode)
          HERMES_HUMAN_DELAY_MAX_MS: maximum delay in ms (default 2500, custom mode)
        """
+        import random
+
        mode = os.getenv("HERMES_HUMAN_DELAY_MODE", "off").lower()
        if mode == "off":
            return 0.0
@@ -1807,23 +1556,10 @@ class BasePlatformAdapter(ABC):
        # Fall back to a new Event only if the entry was removed externally.
        interrupt_event = self._active_sessions.get(session_key) or asyncio.Event()
        self._active_sessions[session_key] = interrupt_event
-        callback_generation = getattr(interrupt_event, "_hermes_run_generation", None)
        
        # Start continuous typing indicator (refreshes every 2 seconds)
        _thread_metadata = {"thread_id": event.source.thread_id} if event.source.thread_id else None
-        _keep_typing_kwargs = {"metadata": _thread_metadata}
-        try:
-            _keep_typing_sig = inspect.signature(self._keep_typing)
-        except (TypeError, ValueError):
-            _keep_typing_sig = None
-        if _keep_typing_sig is None or "stop_event" in _keep_typing_sig.parameters:
-            _keep_typing_kwargs["stop_event"] = interrupt_event
-        typing_task = asyncio.create_task(
-            self._keep_typing(
-                event.source.chat_id,
-                **_keep_typing_kwargs,
-            )
-        )
+        typing_task = asyncio.create_task(self._keep_typing(event.source.chat_id, metadata=_thread_metadata))
        
        try:
            await self._run_processing_hook("on_processing_start", event)
@@ -1835,21 +1571,6 @@ 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:
@@ -2032,18 +1753,9 @@ class BasePlatformAdapter(ABC):
            if session_key in self._pending_messages:
                pending_event = self._pending_messages.pop(session_key)
                logger.debug("[%s] Processing queued message from interrupt", self.name)
-                # Keep the _active_sessions entry live across the turn chain
-                # and only CLEAR the interrupt Event — do NOT delete the entry.
-                # If we deleted here, a concurrent inbound message arriving
-                # during the awaits below would pass the Level-1 guard, spawn
-                # its own _process_message_background, and run simultaneously
-                # with the recursive drain below.  Two agents on one
-                # session_key = duplicate responses, duplicate tool calls.
-                # Clearing the Event keeps the guard live so follow-ups take
-                # the busy-handler path (queue + interrupt) as intended.
-                _active = self._active_sessions.get(session_key)
-                if _active is not None:
-                    _active.clear()
+                # Clean up current session before processing pending
+                if session_key in self._active_sessions:
+                    del self._active_sessions[session_key]
                typing_task.cancel()
                try:
                    await typing_task
@@ -2080,21 +1792,6 @@ class BasePlatformAdapter(ABC):
            except Exception:
                pass  # Last resort — don't let error reporting crash the handler
        finally:
-            # Fire any one-shot post-delivery callback registered for this
-            # session (e.g. deferred background-review notifications).
-            _callback_generation = callback_generation
-            if hasattr(self, "pop_post_delivery_callback"):
-                _post_cb = self.pop_post_delivery_callback(
-                    session_key,
-                    generation=_callback_generation,
-                )
-            else:
-                _post_cb = getattr(self, "_post_delivery_callbacks", {}).pop(session_key, None)
-            if callable(_post_cb):
-                try:
-                    _post_cb()
-                except Exception:
-                    pass
            # Stop typing indicator
            typing_task.cancel()
            try:
@@ -2108,37 +1805,9 @@ class BasePlatformAdapter(ABC):
                    await self.stop_typing(event.source.chat_id)
            except Exception:
                pass
-            # Late-arrival drain: a message may have arrived during the
-            # cleanup awaits above (typing_task cancel, stop_typing).  Such
-            # messages passed the Level-1 guard (entry still live, Event
-            # possibly set) and landed in _pending_messages via the
-            # busy-handler path.  Without this block, we would delete the
-            # active-session entry and the queued message would be silently
-            # dropped (user never gets a reply).
-            late_pending = self._pending_messages.pop(session_key, None)
-            if late_pending is not None:
-                logger.debug(
-                    "[%s] Late-arrival pending message during cleanup — spawning drain task",
-                    self.name,
-                )
-                _active = self._active_sessions.get(session_key)
-                if _active is not None:
-                    _active.clear()
-                drain_task = asyncio.create_task(
-                    self._process_message_background(late_pending, session_key)
-                )
-                try:
-                    self._background_tasks.add(drain_task)
-                    drain_task.add_done_callback(self._background_tasks.discard)
-                except TypeError:
-                    # Tests stub create_task() with non-hashable sentinels; tolerate.
-                    pass
-                # Leave _active_sessions[session_key] populated — the drain
-                # task's own lifecycle will clean it up.
-            else:
-                # Clean up session tracking
-                if session_key in self._active_sessions:
-                    del self._active_sessions[session_key]
+            # Clean up session tracking
+            if session_key in self._active_sessions:
+                del self._active_sessions[session_key]
    
    async def cancel_background_tasks(self) -> None:
        """Cancel any in-flight background message-processing tasks.
@@ -2146,26 +1815,12 @@ class BasePlatformAdapter(ABC):
        Used during gateway shutdown/replacement so active sessions from the old
        process do not keep running after adapters are being torn down.
        """
-        # Loop until no new tasks appear.  Without this, a message
-        # arriving during the `await asyncio.gather` below would spawn
-        # a fresh _process_message_background task (added to
-        # self._background_tasks at line ~1668 via handle_message),
-        # and the _background_tasks.clear() at the end of this method
-        # would drop the reference — the task runs untracked against a
-        # disconnecting adapter, logs send-failures, and may linger
-        # until it completes on its own.  Retrying the drain until the
-        # task set stabilizes closes the window.
-        MAX_DRAIN_ROUNDS = 5
-        for _ in range(MAX_DRAIN_ROUNDS):
-            tasks = [task for task in self._background_tasks if not task.done()]
-            if not tasks:
-                break
-            for task in tasks:
-                self._expected_cancelled_tasks.add(task)
-                task.cancel()
+        tasks = [task for task in self._background_tasks if not task.done()]
+        for task in tasks:
+            self._expected_cancelled_tasks.add(task)
+            task.cancel()
+        if tasks:
            await asyncio.gather(*tasks, return_exceptions=True)
-            # Loop: late-arrival tasks spawned during the gather above
-            # will be in self._background_tasks now.  Re-check.
        self._background_tasks.clear()
        self._expected_cancelled_tasks.clear()
        self._pending_messages.clear()
@@ -2190,7 +1845,6 @@ class BasePlatformAdapter(ABC):
        chat_topic: Optional[str] = None,
        user_id_alt: Optional[str] = None,
        chat_id_alt: Optional[str] = None,
-        is_bot: bool = False,
    ) -> SessionSource:
        """Helper to build a SessionSource for this platform."""
        # Normalize empty topic to None
@@ -2207,7 +1861,6 @@ class BasePlatformAdapter(ABC):
            chat_topic=chat_topic.strip() if chat_topic else None,
            user_id_alt=user_id_alt,
            chat_id_alt=chat_id_alt,
-            is_bot=is_bot,
        )
    
    @abstractmethod
@@ -2233,11 +1886,7 @@ 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.

@@ -2249,16 +1898,11 @@ 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)"
@@ -2277,33 +1921,22 @@ 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
@@ -2323,7 +1956,7 @@ 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]
--- a/gateway/platforms/bluebubbles.py
+++ b/gateway/platforms/bluebubbles.py
@@ -75,7 +75,7 @@ def _redact(text: str) -> str:
 def check_bluebubbles_requirements() -> bool:
    try:
        import aiohttp  # noqa: F401
-        import httpx  # noqa: F401
+        import httpx as _httpx  # noqa: F401
    except ImportError:
        return False
    return True
@@ -224,21 +224,6 @@ class BlueBubblesAdapter(BasePlatformAdapter):
            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:
@@ -260,7 +245,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
        if not self.client:
            return False

-        webhook_url = self._webhook_register_url
+        webhook_url = self._webhook_url

        # Crash resilience — reuse an existing registration if present
        existing = await self._find_registered_webhooks(webhook_url)
@@ -272,7 +257,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):

        payload = {
            "url": webhook_url,
-            "events": ["new-message", "updated-message"],
+            "events": ["new-message", "updated-message", "message"],
        }

        try:
@@ -307,7 +292,7 @@ class BlueBubblesAdapter(BasePlatformAdapter):
        if not self.client:
            return False

-        webhook_url = self._webhook_register_url
+        webhook_url = self._webhook_url
        removed = False

        try:
@@ -619,6 +604,35 @@ 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
    # ------------------------------------------------------------------
@@ -850,12 +864,6 @@ 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"),
--- a/gateway/platforms/dingtalk.py
+++ b/gateway/platforms/dingtalk.py
--- a/Show More
+++ b/Show More