feat(skills): add optional react-best-practices skill

Hermes-native port of Vercel's official react-best-practices agent skill (vercel-labs/agent-skills, MIT). React/Next.js performance guidance from Vercel Engineering: waterfall elimination, bundle optimization, server-side patterns, re-render hygiene, and more. Core SKILL.md plus 8 on-demand reference files; upstream rule IDs preserved for traceability. Credit: Vercel (vercel-labs).
2026-07-21 03:20:13 -07:00
1543 changed files with 19862 additions and 185547 deletions
@@ -97,6 +97,9 @@ packaging/
 plans/
 .plans/

+# ACP registry manifest (icon + agent.json) — not consumed at runtime
+acp_registry/
+
 # Repo-level dotfiles that are git-only or dev-tooling config
 .env.example
 .envrc
@@ -39,9 +39,6 @@ outputs:
  ci_review:
    description: Require CI-sensitive file review label.
    value: ${{ steps.classify.outputs.ci_review }}
-  ci_review_files:
-    description: JSON list of CI-sensitive files changed by the pull request.
-    value: ${{ steps.classify.outputs.ci_review_files }}

 runs:
  using: composite
@@ -5,32 +5,24 @@ description: >-
  5,000 req/hr per installation (vs 1,000 for the default GITHUB_TOKEN)
  and are scoped to the App's installation permissions, not a user account.

-  Callers must source App credentials from a protected, main-only environment.
-  Never pass an App private key to a pull_request job, a local action, or a
-  reusable workflow resolved from an untrusted PR ref. The fallback keeps a
-  trusted caller functional when its protected environment is misconfigured.
+  Falls back to the built-in GITHUB_TOKEN when APP_CLIENT_ID is not set —
+  this happens on fork PRs where repo secrets are unavailable. The fallback
+  ensures classification, timings, and review comments still work on
+  forks (with the lower GITHUB_TOKEN rate limit).

-  Composite actions cannot access contexts directly, so callers pass the
-  public vars.APP_CLIENT_ID and protected secrets.APP_PRIVATE_KEY as inputs.
-  When the private key is empty, the fallback fires.
+  Composite actions cannot access the secrets context directly, so the
+  calling workflow must pass secrets.APP_CLIENT_ID and secrets.APP_PRIVATE_KEY
+  as inputs. When both are empty (fork PRs), the fallback fires.

 inputs:
  client-id:
-    description: GitHub App Client ID. Pass vars.APP_CLIENT_ID from the calling workflow.
+    description: GitHub App Client ID. Pass secrets.APP_CLIENT_ID from the calling workflow.
    required: false
    default: ''
  private-key:
    description: GitHub App private key PEM. Pass secrets.APP_PRIVATE_KEY from the calling workflow.
    required: false
    default: ''
-  owner:
-    description: GitHub App installation owner. Empty scopes the token to the current repository.
-    required: false
-    default: ''
-  repositories:
-    description: Comma- or newline-separated repositories to scope within the installation owner.
-    required: false
-    default: ''

 outputs:
  token:
@@ -59,8 +51,6 @@ runs:
      with:
        client-id: ${{ inputs.client-id }}
        private-key: ${{ inputs.private-key }}
-        owner: ${{ inputs.owner }}
-        repositories: ${{ inputs.repositories }}

    - name: Fall back to GITHUB_TOKEN
      id: fallback
@@ -9,10 +9,6 @@ name: CI
 # definitions, matrices, and concurrency settings. They no longer have
 # ``push:`` / ``pull_request:`` triggers of their own — everything flows
 # through this file.
-#
-# SECURITY: this workflow runs PR-controlled actions, workflows, and code.
-# Do not add ``secrets: inherit`` or GitHub App credentials here. Trusted
-# main-only automation uses protected environments in its own workflows.

 on:
  pull_request:
@@ -50,15 +46,22 @@ jobs:
      docker_meta: ${{ steps.classify.outputs.docker_meta }}
      mcp_catalog: ${{ steps.classify.outputs.mcp_catalog }}
      ci_review: ${{ steps.classify.outputs.ci_review }}
-      ci_review_files: ${{ steps.classify.outputs.ci_review_files }}
      event_name: ${{ github.event_name }}
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - name: Get GitHub App token
+        id: app-token
+        uses: ./.github/actions/get-app-token
+        with:
+          client-id: ${{ secrets.APP_CLIENT_ID }}
+          private-key: ${{ secrets.APP_PRIVATE_KEY }}
      - name: Detect affected areas
        id: classify
        uses: ./.github/actions/detect-changes
        with:
-          github-token: ${{ github.token }}
+          # The get-app-token composite action falls back to GITHUB_TOKEN
+          # on fork PRs where APP_ID is unavailable.
+          github-token: ${{ steps.app-token.outputs.token }}

  # ─────────────────────────────────────────────────────────────────────
  # Lane-gated sub-workflows. Each runs in parallel after detect finishes.
@@ -71,6 +74,7 @@ jobs:
    uses: ./.github/workflows/tests.yml
    with:
      slice_count: 8
+    secrets: inherit

  lint:
    name: Python lints
@@ -79,12 +83,14 @@ jobs:
    uses: ./.github/workflows/lint.yml
    with:
      event_name: ${{ needs.detect.outputs.event_name }}
+    secrets: inherit

  js-tests:
    name: JS & TS checks
    needs: detect
    if: needs.detect.outputs.frontend == 'true'
    uses: ./.github/workflows/js-tests.yml
+    secrets: inherit

  e2e-desktop:
    name: Desktop E2E
@@ -97,44 +103,48 @@ jobs:
    needs: detect
    if: needs.detect.outputs.site == 'true'
    uses: ./.github/workflows/docs-site-checks.yml
+    secrets: inherit

  history-check:
    name: Deny unrelated histories
    needs: detect
    if: needs.detect.outputs.event_name == 'pull_request'
    uses: ./.github/workflows/history-check.yml
+    secrets: inherit

  contributor-check:
    name: Check contributors
    needs: detect
    if: needs.detect.outputs.python == 'true'
    uses: ./.github/workflows/contributor-check.yml
+    secrets: inherit

  uv-lockfile:
    name: Check uv.lock
    needs: detect
    uses: ./.github/workflows/uv-lockfile-check.yml
+    secrets: inherit

  lockfile-diff:
    name: package-lock.json diff
    needs: detect
    if: needs.detect.outputs.event_name == 'pull_request' && needs.detect.outputs.npm_lock == 'true'
    uses: ./.github/workflows/lockfile-diff.yml
+    secrets: inherit

  docker-lint:
    name: Lint Docker scripts
    needs: detect
    if: needs.detect.outputs.docker_meta == 'true'
    uses: ./.github/workflows/docker-lint.yml
+    secrets: inherit

  docker:
    name: Build&Test Docker image
    needs: detect
-    # Trusted main pushes run docker.yml directly so its container-publish
-    # environment secrets never cross this reusable-workflow call. PR runs
-    # remain build/test-only and secret-free.
-    if: needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.python == 'true' || needs.detect.outputs.frontend == 'true' || needs.detect.outputs.docker_meta == 'true')
+    if: needs.detect.outputs.python == 'true' || needs.detect.outputs.frontend == 'true' || needs.detect.outputs.docker_meta == 'true'
    uses: ./.github/workflows/docker.yml
+    secrets: inherit

  supply-chain:
    name: Supply-chain scan
@@ -148,18 +158,18 @@ jobs:

  review-labels:
    name: Review label gate
-    needs: [detect, supply-chain]
-    if: always() && needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.ci_review == 'true' || needs.detect.outputs.mcp_catalog == 'true' || needs.supply-chain.outputs.critical_findings == 'true')
+    needs: detect
+    if: needs.detect.outputs.event_name == 'pull_request' && (needs.detect.outputs.ci_review == 'true' || needs.detect.outputs.mcp_catalog == 'true')
    uses: ./.github/workflows/review-labels.yml
    with:
      ci_review: ${{ needs.detect.outputs.ci_review == 'true' }}
-      ci_review_files: ${{ needs.detect.outputs.ci_review_files }}
      mcp_catalog: ${{ needs.detect.outputs.mcp_catalog == 'true' }}
-      supply_chain: ${{ needs.supply-chain.outputs.critical_findings == 'true' }}
+    secrets: inherit

  osv-scanner:
    name: OSV scan
    uses: ./.github/workflows/osv-scanner.yml
+    secrets: inherit

  # ─────────────────────────────────────────────────────────────────────
  # Live-updating PR review comment.
@@ -169,21 +179,19 @@ jobs:
  # whatever results are available, and upserts it via the
  # ``<!-- hermes-ci-review-bot -->`` marker.
  #
-  # When the visible job set goes quiet, the poller waits 10 seconds and polls
-  # once more so downstream jobs created by an aggregate gate get included.
+  # The poller exits when all non-infra jobs are completed (or on
+  # timeout). ci-timings' review_status is picked up automatically when
+  # its artifact becomes available — the poller downloads and merges it.
  # ─────────────────────────────────────────────────────────────────────
  comment-live:
    name: CI review comment (live)
-    needs: [detect, review-labels, lockfile-diff, supply-chain, osv-scanner, uv-lockfile, history-check, contributor-check, e2e-desktop]
+    needs: [detect, review-labels, lockfile-diff, supply-chain, osv-scanner, uv-lockfile, history-check, contributor-check]
    if: always() && github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork != true
    runs-on: ubuntu-latest
    timeout-minutes: 40
    steps:
      - name: Checkout code
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          ref: ${{ github.event.repository.default_branch }}
-          persist-credentials: false

      - name: Run live comment poller
        env:
@@ -304,8 +312,8 @@ jobs:
  # report with a gantt chart + per-step breakdown. The report is uploaded
  # as an artifact and a markdown summary is written to $GITHUB_STEP_SUMMARY.
  #
-  # The live comment poller can read the standalone review-status artifact
-  # after the HTML report is uploaded, so its link points straight at that report.
+  # The live comment poller picks up ci-timings' completion automatically —
+  # it reads review-status.json from the artifact when the job finishes.
  # ─────────────────────────────────────────────────────────────────────
  ci-timings:
    name: CI timing report
@@ -317,6 +325,13 @@ jobs:
      - name: Checkout code
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

+      - name: Get GitHub App token
+        id: app-token
+        uses: ./.github/actions/get-app-token
+        with:
+          client-id: ${{ secrets.APP_CLIENT_ID }}
+          private-key: ${{ secrets.APP_PRIVATE_KEY }}
+
      - name: Restore baseline cache (PR only)
        if: github.event_name == 'pull_request'
        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
@@ -330,52 +345,38 @@ jobs:

      - name: Collect timings and generate report
        env:
-          GITHUB_TOKEN: ${{ github.token }}
+          # Forks get no repo secrets (AUTOFIX_BOT_PAT is empty); fall back to
+          # the built-in read-only token so the timings API read still works
+          # there instead of hard-failing this advisory job on every fork PR.
+          # The get-app-token composite action falls back to GITHUB_TOKEN
+          # on fork PRs where APP_ID is unavailable.
+          GITHUB_TOKEN: ${{ steps.app-token.outputs.token }}
        run: |
          python3 scripts/ci/timings_report.py \
            --baseline ci-timings-baseline.json \
            --output ci-timings-report.html \
            --json-out ci-timings.json \
-            --summary-out ci-timings-summary.md
+            --summary-out ci-timings-summary.md \
+            --review-status-out review-status.json

-      - name: Upload HTML report
+      - name: Upload HTML report + review status
        # Advisory report — artifact-service blips must not fail the job.
        continue-on-error: true
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
-        id: ci-timings-html
+        id: ci-timings-artifact
        with:
          name: ci-timings-report
-          path: ci-timings-report.html
-          retention-days: 14
-
-      - name: Build linked review status
-        if: hashFiles('ci-timings.json') != ''
-        env:
-          CI_TIMINGS_REPORT_URL: ${{ steps.ci-timings-html.outputs.artifact-url }}
-        run: |
-          python3 scripts/ci/timings_report.py \
-            --from-json ci-timings.json \
-            --baseline ci-timings-baseline.json \
-            --review-status-out review-status.json \
-            --review-status-only
-
-      - name: Upload review status
-        if: hashFiles('review-status.json') != ''
-        continue-on-error: true
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
-        with:
-          name: ci-timings-review-status
-          path: review-status.json
+          path: |
+            ci-timings-report.html
+            review-status.json
          retention-days: 14

      - name: Output summary
        env:
-          REPORT_URL: ${{ steps.ci-timings-html.outputs.artifact-url}}
+          REPORT_URL: ${{ steps.ci-timings-artifact.outputs.artifact-url}}
        run: |
-          {
-            echo "# CI Timing report"
-            echo "[View the full interactive report]($REPORT_URL)"
-          } >> "$GITHUB_STEP_SUMMARY"
+          echo "# CI Timing report" >> "$GITHUB_STEP_SUMMARY"
+          echo "[View the full interactive report]($REPORT_URL)" >> "$GITHUB_STEP_SUMMARY"
          cat ci-timings-summary.md >> "$GITHUB_STEP_SUMMARY"

      - name: Save baseline cache (main only)
@@ -60,7 +60,7 @@ jobs:
        id: app-token
        uses: ./.github/actions/get-app-token
        with:
-          client-id: ${{ vars.APP_CLIENT_ID }}
+          client-id: ${{ secrets.APP_CLIENT_ID }}
          private-key: ${{ secrets.APP_PRIVATE_KEY }}

      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
@@ -1,15 +1,8 @@
 name: Docker Build, Test, and Publish

 on:
-  # Trusted main pushes run this workflow directly so environment-scoped
-  # Docker Hub secrets are resolved by the top-level workflow, never across
-  # a reusable-workflow boundary.
-  push:
-    branches: [main]
  release:
    types: [published]
-  # CI calls this only for untrusted PR build/test coverage. Those runs never
-  # reach the protected publish or merge jobs below.
  workflow_call:

 permissions:
@@ -27,9 +20,7 @@ env:
  IMAGE_NAME: nousresearch/hermes-agent

 jobs:
-  # Build and test the image for each architecture. This job runs PR code,
-  # so it must remain secret-free. Publishing happens in the separate,
-  # protected publish job after these tests pass.
+  # Build, test, and optionally push the image for each architecture.
  build:
    if: github.repository == 'NousResearch/hermes-agent'
    strategy:
@@ -71,6 +62,49 @@ jobs:
          cache-from: ${{ matrix.cache-from }}
          cache-to: ${{ (github.event_name != 'pull_request') && matrix.cache-to || '' }}

+      - name: Log in to Docker Hub
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      # Push by digest only (no tag).  The merge job assembles the
+      # tagged manifest list.  `push-by-digest=true` is docker's recommended
+      # pattern for multi-runner multi-platform builds.
+      - name: Push ${{ matrix.arch }} by digest
+        id: push
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        with:
+          context: .
+          file: Dockerfile
+          platforms: ${{ matrix.platform }}
+          labels: |
+            org.opencontainers.image.revision=${{ github.sha }}
+          build-args: |
+            HERMES_GIT_SHA=${{ github.sha }}
+          outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: ${{ matrix.cache-from }}
+          cache-to: ${{ matrix.cache-to }}
+
+      # Write the digest to a file and upload it as an artifact so the
+      # merge job can stitch both per-arch digests into a manifest list.
+      - name: Export digest
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.push.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest artifact
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: digest-${{ matrix.arch }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1

      # Run the docker-integration test suite against the freshly-built
      # image already loaded into the local daemon (`:test`).
@@ -113,74 +147,6 @@ jobs:
        run: |
          scripts/run_tests.sh tests/docker/ --file-timeout 600

-  # ---------------------------------------------------------------------------
-  # Rebuild and push each architecture only after the unprivileged build/test
-  # matrix passes. This job is the sole Docker Hub credential boundary.
-  # ---------------------------------------------------------------------------
-  publish:
-    if: github.repository == 'NousResearch/hermes-agent' && (github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release')
-    needs: [build]
-    environment: container-publish
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - arch: amd64
-            runner: ubuntu-latest
-            platform: linux/amd64
-            cache-from: type=gha,scope=docker-amd64
-            cache-to: type=gha,mode=max,scope=docker-amd64
-          - arch: arm64
-            runner: ubuntu-24.04-arm
-            platform: linux/arm64
-            cache-from: type=gha,scope=docker-arm64
-            cache-to: type=gha,mode=max,scope=docker-arm64
-    runs-on: ${{ matrix.runner }}
-    timeout-minutes: 30
-    steps:
-      - name: Checkout trusted source
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
-
-      - name: Log in to Docker Hub
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4.1.0
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      # Push by digest only (no tag). The merge job assembles the tagged
-      # manifest list after both architecture publishers complete.
-      - name: Push ${{ matrix.arch }} by digest
-        id: push
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
-        with:
-          context: .
-          file: Dockerfile
-          platforms: ${{ matrix.platform }}
-          labels: |
-            org.opencontainers.image.revision=${{ github.sha }}
-          build-args: |
-            HERMES_GIT_SHA=${{ github.sha }}
-          outputs: type=image,name=${{ env.IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
-          cache-from: ${{ matrix.cache-from }}
-          cache-to: ${{ matrix.cache-to }}
-
-      - name: Export digest
-        run: |
-          mkdir -p /tmp/digests
-          digest="${{ steps.push.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
-
-      - name: Upload digest artifact
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
-        with:
-          name: digest-${{ matrix.arch }}
-          path: /tmp/digests/*
-          if-no-files-found: error
-          retention-days: 1
-
  # ---------------------------------------------------------------------------
  # Stitch both per-arch digests into a single tagged multi-arch manifest.
  # This is a registry-side operation — no building, no layer re-push —
@@ -192,9 +158,8 @@ jobs:
  merge:
    if: github.repository == 'NousResearch/hermes-agent' && (github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release')
    runs-on: ubuntu-latest
-    needs: [publish]
+    needs: [build]
    timeout-minutes: 10
-    environment: container-publish
    steps:
      - name: Download digests
        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
@@ -2,10 +2,6 @@ name: E2E Desktop

 on:
  workflow_call:
-    outputs:
-      review_status:
-        description: Screenshot and visual-diff status for the CI review comment.
-        value: ${{ jobs.e2e.outputs.review_status }}

 permissions:
  contents: read
@@ -19,8 +15,6 @@ jobs:
    name: Playwright E2E (Linux)
    runs-on: ubuntu-latest
    timeout-minutes: 20
-    outputs:
-      review_status: ${{ steps.review-status.outputs.review_status }}
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

@@ -64,8 +58,7 @@ jobs:
          command: uv sync --locked --python 3.11 --extra all --extra dev

      # ── Build desktop app ─────────────────────────────────────────────
-      # The Playwright step below runs `npm run build` before testing so
-      # dist/ is always fresh — no separate build step needed here.
+      - run: npm run --prefix apps/desktop build

      # ── Restore visual baseline screenshots from main ──────────────────
      # Baselines are generated on main (via --update-snapshots) and cached.
@@ -86,18 +79,16 @@ jobs:
      # xvfb runs at a fixed 1280x1024 screen so the 1220x800 Electron
      # window always has a consistent viewport for screenshot comparison.
      # On main, we run with --update-snapshots to generate baselines.
-      # `npm run test:e2e` builds dist/ as a pretest hook so the renderer
-      # is always fresh — no separate build step needed.
      - name: Run Playwright E2E tests
        working-directory: apps/desktop
        run: |
          if [ "${{ github.ref_name }}" = "main" ]; then
            echo "On main — generating/updating baseline screenshots"
-            npm run build && xvfb-run -a --server-args="-screen 0 1280x1024x24" \
+            xvfb-run -a --server-args="-screen 0 1280x1024x24" \
              npx playwright test --reporter=list --update-snapshots
          else
            echo "On PR — comparing against cached baselines"
-            npm run build && xvfb-run -a --server-args="-screen 0 1280x1024x24" \
+            xvfb-run -a --server-args="-screen 0 1280x1024x24" \
              npx playwright test --reporter=list
          fi
        env:
@@ -152,38 +143,6 @@ jobs:
          overwrite: true
          if-no-files-found: ignore

-      - name: Build screenshot review status
-        id: review-status
-        if: always()
-        working-directory: apps/desktop
-        env:
-          RESULTS_URL: ${{ steps.upload-results.outputs.artifact-url }}
-        run: |
-          python3 ../../scripts/ci/e2e_screenshot_status.py \
-            --results-dir test-results \
-            --manifest-output /tmp/e2e-screenshot-manifest.json \
-            --evidence-dir /tmp/e2e-evidence \
-            --artifact-url "$RESULTS_URL" \
-            --output /tmp/e2e-review-status.json
-          {
-            echo 'review_status<<__E2E_REVIEW_STATUS__'
-            cat /tmp/e2e-review-status.json
-            echo '__E2E_REVIEW_STATUS__'
-          } >> "$GITHUB_OUTPUT"
-
-      # The trusted workflow_run publisher consumes only this flat, bounded
-      # artifact. It turns selected images into GitHub attachment URLs; it
-      # never checks out or runs this PR's code.
-      - name: Upload inline E2E evidence
-        if: always() && github.ref_name != 'main'
-        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        with:
-          name: e2e-evidence-${{ github.sha }}
-          path: /tmp/e2e-evidence
-          retention-days: 14
-          overwrite: true
-          if-no-files-found: error
-
      # ── Generate step summary with visual diff info ───────────────────
      # Parse the JSON report + scan for diff images, then post a summary
      # to the GitHub Actions step output so reviewers can see what changed
@@ -197,50 +156,49 @@ jobs:
          RESULTS_URL: ${{ steps.upload-results.outputs.artifact-url }}
          DIFFS_URL: ${{ steps.upload-diffs.outputs.artifact-url }}
        run: |
-          {
-          echo "## Desktop E2E — Visual Diff Report"
-          echo ""
+          echo "## Desktop E2E — Visual Diff Report" >> "$GITHUB_STEP_SUMMARY"
+          echo "" >> "$GITHUB_STEP_SUMMARY"

          # Count diff images (playwright writes *-diff.png on mismatch)
          DIFF_COUNT=$(find test-results -name '*-diff.png' 2>/dev/null | wc -l)
          ACTUAL_COUNT=$(find test-results -name '*-actual.png' 2>/dev/null | wc -l)

          if [ "$DIFF_COUNT" -eq 0 ]; then
-            echo "✅ All $ACTUAL_COUNT screenshot(s) matched their baselines (or no baselines existed yet)."
+            echo "✅ All $ACTUAL_COUNT screenshot(s) matched their baselines (or no baselines existed yet)." >> "$GITHUB_STEP_SUMMARY"
          else
-            echo "📸 **$DIFF_COUNT of $ACTUAL_COUNT screenshot(s) differ from baseline:**"
-            echo ""
-            echo "| Test | Diff | Actual | Expected |"
-            echo "|------|------|--------|----------|"
+            echo "📸 **$DIFF_COUNT of $ACTUAL_COUNT screenshot(s) differ from baseline:**" >> "$GITHUB_STEP_SUMMARY"
+            echo "" >> "$GITHUB_STEP_SUMMARY"
+            echo "| Test | Diff | Actual | Expected |" >> "$GITHUB_STEP_SUMMARY"
+            echo "|------|------|--------|----------|" >> "$GITHUB_STEP_SUMMARY"

            # List each diff image with a link to the artifact
            for diff in $(find test-results -name '*-diff.png' 2>/dev/null | sort); do
-              base=${diff%-diff.png}
+              base=$(echo "$diff" | sed 's/-diff\.png$//')
              test_name=$(basename "$base")
-              echo "| $test_name | [diff]($diff) | [actual](${base}-actual.png) | [expected](${base}-expected.png) |"
+              echo "| $test_name | [diff]($diff) | [actual](${base}-actual.png) | [expected](${base}-expected.png) |" >> "$GITHUB_STEP_SUMMARY"
            done
          fi

-          echo ""
-          echo "📥 **Artifacts:**"
-          echo ""
+          echo "" >> "$GITHUB_STEP_SUMMARY"
+          echo "📥 **Artifacts:**" >> "$GITHUB_STEP_SUMMARY"
+          echo "" >> "$GITHUB_STEP_SUMMARY"
          if [ -n "$RESULTS_URL" ]; then
-            echo "- [playwright-test-results]($RESULTS_URL) — all screenshots (actual + expected + diff) + traces"
+            echo "- [playwright-test-results]($RESULTS_URL) — all screenshots (actual + expected + diff) + traces" >> "$GITHUB_STEP_SUMMARY"
          fi
          if [ -n "$REPORT_URL" ]; then
-            echo "- [playwright-report]($REPORT_URL) — interactive HTML report"
+            echo "- [playwright-report]($REPORT_URL) — interactive HTML report" >> "$GITHUB_STEP_SUMMARY"
          fi
          if [ -n "$DIFFS_URL" ]; then
-            echo "- [visual-diffs]($DIFFS_URL) — just the diffed screenshots (small, fast to review)"
+            echo "- [visual-diffs]($DIFFS_URL) — just the diffed screenshots (small, fast to review)" >> "$GITHUB_STEP_SUMMARY"
          fi
-          echo ""
-          echo "**To update baselines:** merge to main (baselines auto-update on main runs) or run \`npx playwright test --update-snapshots\` locally."
+          echo "" >> "$GITHUB_STEP_SUMMARY"
+          echo "**To update baselines:** merge to main (baselines auto-update on main runs) or run \`npx playwright test --update-snapshots\` locally." >> "$GITHUB_STEP_SUMMARY"

          # Also parse the JSON report for pass/fail counts
          if [ -f playwright-report/results.json ]; then
-            echo ""
-            echo "### Test Results"
-            echo ""
+            echo "" >> "$GITHUB_STEP_SUMMARY"
+            echo "### Test Results" >> "$GITHUB_STEP_SUMMARY"
+            echo "" >> "$GITHUB_STEP_SUMMARY"
            node -e "
              const r = require('./playwright-report/results.json');
              const stats = r.stats || {};
@@ -250,6 +208,5 @@ jobs:
              console.log('| ❌ Failed | ' + (stats.unexpected || 0) + ' |');
              console.log('| ⏭️ Skipped | ' + (stats.skipped || 0) + ' |');
              console.log('| 🔄 Flaky | ' + (stats.flaky || 0) + ' |');
-            " 2>/dev/null || true
+            " >> "$GITHUB_STEP_SUMMARY" 2>/dev/null || true
          fi
-          } >> "$GITHUB_STEP_SUMMARY"
@@ -122,7 +122,6 @@ jobs:
    if: needs.generate-patch.outputs.has-fixes == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 15
-    environment: trusted-automation
    permissions:
      contents: write # needed to push to bot/js-autofix
      pull-requests: write # needed for PR creation + auto-merge
@@ -133,7 +132,7 @@ jobs:
        id: app-token
        uses: ./.github/actions/get-app-token
        with:
-          client-id: ${{ vars.APP_CLIENT_ID }}
+          client-id: ${{ secrets.APP_CLIENT_ID }}
          private-key: ${{ secrets.APP_PRIVATE_KEY }}

      - name: Download patch
@@ -10,7 +10,7 @@ jobs:
    runs-on: ubuntu-latest
    timeout-minutes: 20
    outputs:
-      checks: ${{ steps.set-matrix.outputs.checks }}
+      packages: ${{ steps.set-matrix.outputs.packages }}
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
@@ -22,40 +22,21 @@ jobs:
          command: npm ci --ignore-scripts
      - id: set-matrix
        run: |
-          node -e '
-          const { execSync } = require("child_process");
-          const pkgs = JSON.parse(execSync("npm query .workspace", { encoding: "utf-8" }));
-          if (pkgs.length === 0) {
-            console.error("::error::Workspace discovery produced an empty package list — refusing to emit a zero-length matrix (would skip all JS/TS checks silently).");
-            process.exit(1);
-          }
-          const checks = [];
-          for (const pkg of pkgs) {
-            const scripts = pkg.scripts || {};
-            const subs = Object.keys(scripts).filter(s => /^check:.+$/.test(s));
-            if (subs.length > 0) {
-              for (const script of subs) {
-                checks.push({ package: pkg.location, script });
-              }
-            } else if (scripts.check) {
-              checks.push({ package: pkg.location, script: "check" });
-            }
-          }
-          if (checks.length === 0) {
-            console.error("::error::No check scripts found in any workspace package.");
-            process.exit(1);
-          }
-          process.stdout.write("checks=" + JSON.stringify(checks) + "\n");
-          ' >> "$GITHUB_OUTPUT"
+          PACKAGES=$(npm query .workspace | jq -c '[.[].location]')
+          if [ "$PACKAGES" = "[]" ] || [ -z "$PACKAGES" ]; then
+            echo "::error::Workspace discovery produced an empty package list — refusing to emit a zero-length matrix (would skip all JS/TS checks silently)."
+            exit 1
+          fi
+          echo "packages=$PACKAGES" >> "$GITHUB_OUTPUT"

  check:
-    name: ${{ matrix.package }} / ${{ matrix.script }}
+    name: Typecheck & Test
    needs: workspaces
    runs-on: ubuntu-latest
    timeout-minutes: 20
    strategy:
      matrix:
-        include: ${{ fromJson(needs.workspaces.outputs.checks) }}
+        package: ${{ fromJson(needs.workspaces.outputs.packages) }}
      fail-fast: false # report all failures, not just the first one
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
@@ -66,4 +47,5 @@ jobs:
      - uses: ./.github/actions/retry
        with:
          command: npm ci
-      - run: npm run --prefix ${{ matrix.package }} ${{ matrix.script }}
+      - run: npm run --prefix ${{ matrix.package }} check
+      - run: npm run --prefix ${{ matrix.package }} fix
@@ -48,9 +48,6 @@ jobs:
        --lockfile=uv.lock
        --lockfile=package-lock.json
        --lockfile=website/package-lock.json
-      # The upstream reusable workflow uploads this exact file under its
-      # fixed artifact name, which the wrapper downloads below.
-      results-file-name: osv-results.sarif
      fail-on-vuln: false

  emit-status:
@@ -67,7 +64,7 @@ jobs:
      - name: Download SARIF result
        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
        with:
-          name: OSV Scanner SARIF file
+          name: osv-results
          path: /tmp/osv-results
        continue-on-error: true

@@ -1,71 +0,0 @@
-name: Publish E2E evidence
-
-# This runs only from the default branch after CI completes. It intentionally
-# checks out main, never the PR ref, and treats the downloaded artifact as
-# untrusted input before uploading validated GitHub attachments.
-on:
-  workflow_run:
-    workflows: [CI]
-    types: [completed]
-
-permissions:
-  actions: read
-  contents: read
-  pull-requests: write
-
-concurrency:
-  group: publish-e2e-evidence-${{ github.event.workflow_run.id }}
-  cancel-in-progress: false
-
-jobs:
-  publish:
-    name: Publish inline E2E evidence
-    if: github.event.workflow_run.event == 'pull_request'
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    environment: gh-image
-    steps:
-      - name: Check out trusted publisher
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-        with:
-          ref: ${{ github.event.repository.default_branch }}
-          persist-credentials: false
-
-      # v1.2.0 resolves to 44f4b93ecbbe22de6c45fa2f62f519aee564ca8c.
-      - name: Install gh-image
-        env:
-          GH_TOKEN: ${{ github.token }}
-        run: gh extension install drogers0/gh-image --pin v1.2.0
-
-      - name: Download and attach evidence
-        env:
-          GH_TOKEN: ${{ github.token }}
-          GITHUB_TOKEN: ${{ github.token }}
-          GH_SESSION_TOKEN: ${{ secrets.GH_IMAGE_SESSION_TOKEN }}
-          SOURCE_REPO: ${{ github.repository }}
-          SOURCE_RUN_ID: ${{ github.event.workflow_run.id }}
-        run: |
-          set -euo pipefail
-
-          PR_NUMBER=$(gh api "repos/$SOURCE_REPO/actions/runs/$SOURCE_RUN_ID" --jq '.pull_requests[0].number // empty')
-          if [ -z "$PR_NUMBER" ]; then
-            echo "No pull request is associated with CI run $SOURCE_RUN_ID."
-            exit 0
-          fi
-
-          ARTIFACT_NAME=$(gh api "repos/$SOURCE_REPO/actions/runs/$SOURCE_RUN_ID/artifacts" \
-            --jq '.artifacts[] | select(.expired == false and (.name | startswith("e2e-evidence-"))) | .name' \
-            | python3 -c 'import sys; print(next(iter(sys.stdin), "").strip())')
-          if [ -z "$ARTIFACT_NAME" ]; then
-            echo "No E2E evidence artifact was produced for CI run $SOURCE_RUN_ID."
-            exit 0
-          fi
-
-          EVIDENCE_DIR="$RUNNER_TEMP/e2e-evidence"
-          mkdir -p "$EVIDENCE_DIR"
-          gh run download "$SOURCE_RUN_ID" --repo "$SOURCE_REPO" --name "$ARTIFACT_NAME" --dir "$EVIDENCE_DIR"
-
-          python3 scripts/ci/publish_e2e_evidence.py \
-            --evidence-dir "$EVIDENCE_DIR" \
-            --source-repo "$SOURCE_REPO" \
-            --pr-number "$PR_NUMBER"
@@ -23,18 +23,10 @@ on:
        description: Whether CI-sensitive files (eslint config, workflows, actions) changed.
        type: boolean
        default: false
-      ci_review_files:
-        description: JSON list of CI-sensitive files changed by the pull request.
-        type: string
-        default: '[]'
      mcp_catalog:
        description: Whether the MCP catalog / installer changed.
        type: boolean
        default: false
-      supply_chain:
-        description: Whether the critical supply-chain scan found a risk requiring review.
-        type: boolean
-        default: false
    outputs:
      ci_reviewed:
        description: Whether the ci-reviewed label is present. Empty when neither input was true.
@@ -50,7 +42,7 @@ permissions:
 jobs:
  check:
    name: Review label gate
-    if: inputs.ci_review || inputs.mcp_catalog || inputs.supply_chain
+    if: inputs.ci_review || inputs.mcp_catalog
    runs-on: ubuntu-latest
    timeout-minutes: 2
    outputs:
@@ -82,25 +74,16 @@ jobs:
        id: build-status
        env:
          CI_REVIEW: ${{ inputs.ci_review }}
-          CI_REVIEW_FILES: ${{ inputs.ci_review_files }}
          MCP_CATALOG: ${{ inputs.mcp_catalog }}
-          SUPPLY_CHAIN: ${{ inputs.supply_chain }}
          LABEL_PRESENT: ${{ steps.label-check.outputs.ci_reviewed }}
-          REPO_URL: ${{ github.server_url }}/${{ github.repository }}
-          BASE_SHA: ${{ github.event.pull_request.base.sha }}
-          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
        run: |
          set -euo pipefail
-          args=()
-          if [ "$CI_REVIEW" = "true" ]; then args+=(--ci-review); fi
-          args+=(--ci-review-files "$CI_REVIEW_FILES")
-          if [ "$MCP_CATALOG" = "true" ]; then args+=(--mcp-catalog); fi
-          if [ "$SUPPLY_CHAIN" = "true" ]; then args+=(--supply-chain); fi
-          if [ "$LABEL_PRESENT" = "true" ]; then args+=(--label-present); fi
+          ARGS=""
+          if [ "$CI_REVIEW" = "true" ]; then ARGS="$ARGS --ci-review"; fi
+          if [ "$MCP_CATALOG" = "true" ]; then ARGS="$ARGS --mcp-catalog"; fi
+          if [ "$LABEL_PRESENT" = "true" ]; then ARGS="$ARGS --label-present"; fi

-          python3 scripts/ci/emit_review_status.py "${args[@]}" \
-            --repo-url "$REPO_URL" --base-sha "$BASE_SHA" --head-sha "$HEAD_SHA" \
-            --output "$GITHUB_OUTPUT"
+          python3 scripts/ci/emit_review_status.py $ARGS --output "$GITHUB_OUTPUT"

      - name: Fail on missing label
        if: steps.label-check.outputs.ci_reviewed != 'true'
@@ -21,7 +21,6 @@ jobs:
    if: github.repository == 'NousResearch/hermes-agent'
    runs-on: ubuntu-latest
    timeout-minutes: 10
-    environment: trusted-automation
    steps:
      - name: Probe live index
        id: probe
@@ -114,7 +113,7 @@ jobs:
        id: app-token
        uses: ./.github/actions/get-app-token
        with:
-          client-id: ${{ vars.APP_CLIENT_ID }}
+          client-id: ${{ secrets.APP_CLIENT_ID }}
          private-key: ${{ secrets.APP_PRIVATE_KEY }}

      - name: Open issue on degraded / failed probe
@@ -21,7 +21,6 @@ jobs:
    if: github.repository == 'NousResearch/hermes-agent'
    runs-on: ubuntu-latest
    timeout-minutes: 15
-    environment: trusted-automation
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

@@ -29,7 +28,7 @@ jobs:
        id: app-token
        uses: ./.github/actions/get-app-token
        with:
-          client-id: ${{ vars.APP_CLIENT_ID }}
+          client-id: ${{ secrets.APP_CLIENT_ID }}
          private-key: ${{ secrets.APP_PRIVATE_KEY }}

      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
@@ -61,13 +60,12 @@ jobs:
    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
    runs-on: ubuntu-latest
    timeout-minutes: 15
-    environment: trusted-automation
    steps:
      - name: Get GitHub App token
        id: app-token
        uses: ./.github/actions/get-app-token
        with:
-          client-id: ${{ vars.APP_CLIENT_ID }}
+          client-id: ${{ secrets.APP_CLIENT_ID }}
          private-key: ${{ secrets.APP_PRIVATE_KEY }}
      - name: Trigger Deploy Site workflow
        env:
@@ -16,12 +16,11 @@ name: Supply Chain Audit
 # ``review-labels.yml`` so it can be rerun independently.
 #
 # Outputs:
-#   review_status      — JSON array of status objects consumed by the review
-#                         comment assembler (scripts/ci/assemble_review_comment.py).
-#   critical_findings  — "true" when the narrow critical-pattern scan found
-#                         something. The review-label gate consumes this and
-#                         owns the action-required result, so adding
-#                         ``ci-reviewed`` can heal the run on rerun.
+#   review_status  — JSON array of status objects consumed by the review
+#                    comment assembler (scripts/ci/assemble_review_comment.py).
+#                    Each job (``scan``, ``dep-bounds``) emits its own
+#                    array; an ``aggregate`` job merges them into the
+#                    workflow-level output.

 on:
  workflow_call:
@@ -42,9 +41,6 @@ on:
      review_status:
        description: JSON array of review status objects for the review comment assembler.
        value: ${{ jobs.aggregate.outputs.review_status }}
-      critical_findings:
-        description: Whether the critical-pattern scan found a risk requiring maintainer review.
-        value: ${{ jobs.aggregate.outputs.critical_findings }}

 permissions:
  pull-requests: write
@@ -58,18 +54,23 @@ jobs:
    timeout-minutes: 15
    outputs:
      review_status: ${{ steps.emit-status.outputs.review_status }}
-      critical_findings: ${{ steps.scan.outputs.found }}
    steps:
      - name: Checkout
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          fetch-depth: 0

+      - name: Get GitHub App token
+        id: app-token
+        uses: ./.github/actions/get-app-token
+        with:
+          client-id: ${{ secrets.APP_CLIENT_ID }}
+          private-key: ${{ secrets.APP_PRIVATE_KEY }}
+
      - name: Scan diff for critical patterns
        id: scan
        env:
-          GH_TOKEN: ${{ github.token }}
-          CI_REVIEWED: ${{ contains(github.event.pull_request.labels.*.name, 'ci-reviewed') }}
+          GH_TOKEN: ${{ steps.app-token.outputs.token }}
        run: |
          set -euo pipefail

@@ -87,7 +88,7 @@ jobs:
          # --- .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=$(git diff --diff-filter=d --name-only "$BASE"..."$HEAD" | grep '\.pth$' || true)
+          PTH_FILES=$(git diff --name-only "$BASE"..."$HEAD" | grep '\.pth$' || true)
          if [ -n "$PTH_FILES" ]; then
            FINDINGS="${FINDINGS}
          ### 🚨 CRITICAL: .pth file added or modified
@@ -135,11 +136,8 @@ jobs:
          # auto-loaded by the interpreter via site.py. Any nested file with the
          # same name (e.g. hermes_cli/setup.py — the CLI setup wizard) is unrelated
          # and produced false positives that trained reviewers to ignore the scanner.
-          SETUP_HITS=$(git diff --diff-filter=d --name-only "$BASE"..."$HEAD" | grep -E '^(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
-          # A maintainer-applied ci-reviewed label records the manual review
-          # required for intentional changes to an install hook. The scanner
-          # still blocks every unreviewed addition or modification.
-          if [ -n "$SETUP_HITS" ] && [ "$CI_REVIEWED" != "true" ]; then
+          SETUP_HITS=$(git diff --name-only "$BASE"..."$HEAD" | grep -E '^(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
+          if [ -n "$SETUP_HITS" ]; then
            FINDINGS="${FINDINGS}
          ### 🚨 CRITICAL: Install-hook file added or modified
          These files can execute code during package installation or interpreter startup.
@@ -167,15 +165,33 @@ jobs:
          python3 - <<'PYEOF'
          import json, os

-          # The review-label gate renders and blocks critical findings. Keep
-          # this scan a fact-finder so adding ci-reviewed can rerun the gate
-          # without requiring the scanner itself to fail again.
-          status = []
+          found = os.environ.get("FOUND", "") == "true"
+
+          if found:
+              with open("/tmp/findings.md", encoding="utf-8") as f:
+                  detail = f.read()
+              status = [{
+                  "source": "supply chain",
+                  "results": [{
+                      "kind": "error",
+                      "title": "Critical supply chain risk",
+                      "summary": "Critical supply chain risk patterns detected in this PR.",
+                      "detail": detail,
+                      "how_to_fix": "Review the flagged code carefully. If intentional, add the `ci-reviewed` label."
+                  }]
+              }]
+          else:
+              status = []

          with open(os.environ["GITHUB_OUTPUT"], "a", encoding="utf-8") as f:
              f.write(f"review_status={json.dumps(status)}\n")
          PYEOF

+      - name: Fail on critical findings
+        if: steps.scan.outputs.found == 'true'
+        run: |
+          echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the review comment for details."
+          exit 1

  dep-bounds:
    name: Check PyPI dependency upper bounds
@@ -263,14 +279,12 @@ jobs:
    timeout-minutes: 15
    outputs:
      review_status: ${{ steps.merge.outputs.review_status }}
-      critical_findings: ${{ steps.merge.outputs.critical_findings }}
    steps:
      - name: Merge review statuses
        id: merge
        env:
          SCAN_STATUS: ${{ needs.scan.outputs.review_status }}
          DEP_STATUS: ${{ needs.dep-bounds.outputs.review_status }}
-          CRITICAL_FINDINGS: ${{ needs.scan.outputs.critical_findings }}
        run: |
          python3 - <<'PYEOF'
          import json, os
@@ -289,5 +303,4 @@ jobs:

          with open(os.environ["GITHUB_OUTPUT"], "a", encoding="utf-8") as f:
              f.write(f"review_status={json.dumps(merged)}\n")
-              f.write("critical_findings=" + os.environ.get("CRITICAL_FINDINGS", "false") + "\n")
          PYEOF
@@ -215,6 +215,11 @@ jobs:
        # re-download, keeping the persisted cache small and fast to restore.
        run: uv cache prune --ci

+      - name: Packaged-wheel i18n smoke test
+        run: |
+          source .venv/bin/activate
+          python -m pytest -m integration tests/test_wheel_locales_e2e.py -v
+
      - name: Run e2e tests
        run: |
          source .venv/bin/activate
@@ -0,0 +1,188 @@
+name: Publish to PyPI
+
+# Triggered by CalVer tag pushes from scripts/release.py (e.g. v2026.5.15)
+# Can also be triggered manually from the Actions tab as an escape hatch.
+on:
+  push:
+    tags:
+      - "v20*" # CalVer tags: v2026.5.15, v2026.5.15.2, etc.
+  workflow_dispatch:
+    inputs:
+      confirm_tag:
+        description: "Tag to publish (e.g. v2026.5.15). Must already exist."
+        required: true
+        type: string
+
+# Restrict default token to read-only; each job escalates as needed.
+permissions:
+  contents: read
+
+# Prevent overlapping publishes (e.g. two same-day tags pushed quickly).
+concurrency:
+  group: pypi-publish
+  cancel-in-progress: false
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+          # On workflow_dispatch, check out the confirmed tag.
+          ref: ${{ inputs.confirm_tag || github.ref }}
+          fetch-tags: true
+
+      - name: Validate tag exists
+        if: github.event_name == 'workflow_dispatch'
+        run: |
+          if ! git tag -l "${{ inputs.confirm_tag }}" | grep -q .; then
+            echo "::error::Tag '${{ inputs.confirm_tag }}' does not exist in the repo"
+            exit 1
+          fi
+
+      - name: Set up Python
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+        with:
+          python-version: "3.13"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # 8.2.0
+
+      - name: Set up Node.js
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
+        with:
+          node-version: "22"
+
+      - name: Build web dashboard
+        uses: ./.github/actions/retry
+        with:
+          command: npm ci
+          working-directory: web
+
+      - name: Compile web dashboard
+        run: npm run build
+        working-directory: web
+
+      - name: Build TUI bundle
+        uses: ./.github/actions/retry
+        with:
+          command: npm ci
+          working-directory: ui-tui
+
+      - name: Compile TUI bundle
+        run: npm run build
+        working-directory: ui-tui
+
+      - name: Bundle TUI into hermes_cli
+        run: |
+          mkdir -p hermes_cli/tui_dist
+          cp ui-tui/dist/entry.js hermes_cli/tui_dist/entry.js
+
+      - name: Verify frontend assets exist
+        run: |
+          test -f hermes_cli/web_dist/index.html || { echo "ERROR: web_dist not built"; exit 1; }
+          test -f hermes_cli/tui_dist/entry.js || { echo "ERROR: tui_dist not built"; exit 1; }
+
+      - name: Bundle install scripts into wheel
+        run: |
+          mkdir -p hermes_cli/scripts
+          cp scripts/install.sh hermes_cli/scripts/install.sh
+          cp scripts/install.ps1 hermes_cli/scripts/install.ps1
+
+      - name: Build wheel and sdist
+        run: uv build --sdist --wheel
+
+      - name: Upload distribution artifacts
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: python-package-distributions
+          path: dist/
+
+  publish:
+    name: Publish to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    environment:
+      name: pypi
+      url: https://pypi.org/p/hermes-agent
+    permissions:
+      id-token: write # OIDC trusted publishing
+
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@cef221092ed1bacb1cc03d23a2d87d1d172e277b # v1.14.0
+        with:
+          skip-existing: true
+
+  sign:
+    name: Sign and attach to GitHub Release
+    # Only runs on tag pushes — release.py creates the GitHub Release,
+    # and workflow_dispatch won't have a matching release to attach to.
+    if: startsWith(github.ref, 'refs/tags/')
+    needs: publish
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    permissions:
+      contents: write # attach assets to the existing release
+      id-token: write # sigstore signing
+
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4
+        with:
+          name: python-package-distributions
+          path: dist/
+
+      - name: Get GitHub App token
+        id: app-token
+        uses: ./.github/actions/get-app-token
+        with:
+          client-id: ${{ secrets.APP_CLIENT_ID }}
+          private-key: ${{ secrets.APP_PRIVATE_KEY }}
+
+      - name: Wait for GitHub Release to exist
+        env:
+          GITHUB_TOKEN: ${{ steps.app-token.outputs.token }}
+        # release.py creates the GitHub Release after pushing the tag,
+        # but this workflow starts from the tag push — wait for it.
+        run: |
+          for i in $(seq 1 30); do
+            if gh release view "$GITHUB_REF_NAME" --repo "$GITHUB_REPOSITORY" >/dev/null 2>&1; then
+              echo "Release $GITHUB_REF_NAME found"
+              exit 0
+            fi
+            echo "Waiting for release... ($i/30)"
+            sleep 10
+          done
+          echo "::warning::Release $GITHUB_REF_NAME not found after 5 minutes — skipping signature upload"
+          echo "skip_sign=true" >> "$GITHUB_ENV"
+
+      - name: Sign with Sigstore
+        if: env.skip_sign != 'true'
+        uses: sigstore/gh-action-sigstore-python@04cffa1d795717b140764e8b640de88853c92acc # v3.3.0
+        with:
+          inputs: >-
+            ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Attach signed artifacts to GitHub Release
+        if: env.skip_sign != 'true'
+        env:
+          GITHUB_TOKEN: ${{ steps.app-token.outputs.token }}
+        # release.py already created the GitHub Release — just upload
+        # the Sigstore signatures alongside the existing assets.
+        run: >-
+          gh release upload
+          "$GITHUB_REF_NAME" dist/*.sigstore.json
+          --repo "$GITHUB_REPOSITORY"
+          --clobber
@@ -44,10 +44,7 @@ run_datagen_sonnet.sh
 source-data/*
 run_datagen_megascience_glm4-6.sh
 data/*
-# No trailing slash: also matches node_modules SYMLINKS (worktrees often
-# symlink node_modules to the main checkout; the dir-only pattern let one
-# slip into a commit and break `npm ci` on CI with ENOTDIR).
-node_modules
+node_modules/
 browser-use/
 agent-browser/
 # Private keys
@@ -75,8 +72,6 @@ environments/benchmarks/evals/

 # Web UI build output
 hermes_cli/web_dist/
-# Cross-process web UI build lock (flock target, always empty)
-.web_ui_build.lock
 apps/desktop/build/
 apps/desktop/dist/

@@ -150,11 +145,6 @@ docs/superpowers/*
 .update-incomplete
 .update-incomplete.lock

-# Installer-written method stamp in the managed checkout root (scripts/install.sh).
-# Runtime metadata only — never a code change. Ignore so `git status` stays clean
-# and `hermes update`'s untracked autostash does not treat it as a local edit (#66189 / #54855).
-/.install_method
-
 # Tool Search live-test harness output — non-deterministic model transcripts,
 # regenerated by scripts/tool_search_livetest.py. Never an artifact of the repo.
 scripts/out/
@@ -174,4 +164,3 @@ apps/desktop/demo/
 # PR body is the archive. See the hermes-agent-dev skill's
 # pr-infographic-workflow reference (storage rule + lapse #8 / #COMMIT-1).
 infographic/
-native/fts5_cjk/*.so
@@ -998,8 +998,7 @@ Two shapes:
 Roles:

 - `role="leaf"` (default) — focused worker. Cannot call `delegate_task`,
-  `clarify`, `memory`, `send_message`, `cronjob`. Retains `execute_code`
-  (programmatic tool calling).
+  `clarify`, `memory`, `send_message`, `execute_code`.
 - `role="orchestrator"` — retains `delegate_task` so it can spawn its
  own workers. Gated by `delegation.orchestrator_enabled` (default true)
  and bounded by `delegation.max_spawn_depth` (default 2).
@@ -0,0 +1,13 @@
+graft skills
+graft optional-skills
+graft optional-mcps
+graft locales
+# Bundled plugin manifests (plugin.yaml / plugin.yml). Without these the
+# PluginManager scan (hermes_cli/plugins.py) finds zero plugins on installs
+# built from the sdist (e.g. Homebrew, downstream packagers). package-data
+# below covers the wheel; this covers the sdist. See #34034 / #28149.
+recursive-include plugins plugin.yaml plugin.yml
+# Gateway assets include images plus YAML catalogs such as status_phrases.yaml.
+recursive-include gateway/assets *
+global-exclude __pycache__
+global-exclude *.py[cod]
@@ -190,7 +190,7 @@ def _run_setup_browser(assume_yes: bool = False) -> int:
    """Bootstrap agent-browser + Chromium.

    Routes through dep_ensure -> install.{sh,ps1} --ensure, sharing code
-    with the runtime lazy installer.
+    with ``hermes postinstall`` and the runtime lazy installer.

    Returns 0 on success, 1 on failure.
    """
@@ -74,10 +74,6 @@ from acp_adapter.permissions import make_approval_callback
 from acp_adapter.provenance import session_provenance_meta
 from acp_adapter.session import SessionManager, SessionState, _expand_acp_enabled_toolsets
 from acp_adapter.tools import build_tool_complete, build_tool_start
-from agent.context_compressor import (
-    COMPRESSED_SUMMARY_METADATA_KEY,
-    ContextCompressor,
-)
 from tools.approval import (
    reset_hermes_interactive_context,
    set_hermes_interactive_context,
@@ -460,7 +456,7 @@ class HermesACPAgent(acp.Agent):
        "tools": "List available tools",
        "context": "Show conversation context info",
        "reset": "Clear conversation history",
-        "compress": "Compress conversation context",
+        "compact": "Compress conversation context",
        "steer": "Inject guidance into the currently running agent turn",
        "queue": "Queue a prompt to run after the current turn finishes",
        "version": "Show Hermes version",
@@ -489,7 +485,7 @@ class HermesACPAgent(acp.Agent):
            "description": "Clear conversation history",
        },
        {
-            "name": "compress",
+            "name": "compact",
            "description": "Compress conversation context",
        },
        {
@@ -973,49 +969,11 @@ class HermesACPAgent(acp.Agent):
                return text
        return ""

-    @staticmethod
-    def _history_summary_meta(message: dict[str, Any], text: str) -> dict[str, Any] | None:
-        """Build the ``_meta`` payload for a replayed compaction summary.
-
-        Compaction summaries are persisted as ordinary history messages —
-        standalone handoffs under ``role="user"`` OR ``role="assistant"``
-        (the compressor picks whichever role keeps alternation valid), and
-        merge-into-tail messages where the summary is appended after the
-        first preserved tail message's real content. Without a wire flag,
-        ACP frontends render all of these as ordinary turns.
-
-        Two distinct keys under ``_meta.hermes`` (ACP's extensibility
-        channel), so clients cannot accidentally hide real content:
-
-        * ``compactionSummary: true`` — the entire chunk is the handoff
-          summary. Safe to restyle or collapse wholesale.
-        * ``containsCompactionSummary: true`` — a merged-tail message: real
-          preserved turn content followed by the summary. Clients may style
-          it, but collapsing the whole chunk would hide the preserved
-          content, hence the separate key.
-
-        Detection honors the in-process ``_compressed_summary`` flag and
-        falls back to content classification, so it also works for a
-        DB-reloaded session that lost the in-memory flag.
-        """
-        kind = ContextCompressor.classify_summary_content(text)
-        if kind is None and message.get(COMPRESSED_SUMMARY_METADATA_KEY):
-            # Flagged in-process but content didn't classify (e.g. future
-            # prefix drift): treat as a standalone summary — the flag is only
-            # ever set on summary-bearing messages.
-            kind = "standalone"
-        if kind == "standalone":
-            return {"hermes": {"compactionSummary": True}}
-        if kind == "merged":
-            return {"hermes": {"containsCompactionSummary": True}}
-        return None
-
    @staticmethod
    def _history_message_update(
        *,
        role: str,
        text: str,
-        field_meta: dict[str, Any] | None = None,
    ) -> UserMessageChunk | AgentMessageChunk | None:
        """Build an ACP history replay update for a user/assistant message."""
        block = TextContentBlock(type="text", text=text)
@@ -1023,13 +981,11 @@ class HermesACPAgent(acp.Agent):
            return UserMessageChunk(
                session_update="user_message_chunk",
                content=block,
-                field_meta=field_meta,
            )
        if role == "assistant":
            return AgentMessageChunk(
                session_update="agent_message_chunk",
                content=block,
-                field_meta=field_meta,
            )
        return None

@@ -1100,11 +1056,7 @@ class HermesACPAgent(acp.Agent):
            if role == "user":
                text = self._history_message_text(message)
                if text:
-                    update = self._history_message_update(
-                        role=role,
-                        text=text,
-                        field_meta=self._history_summary_meta(message, text),
-                    )
+                    update = self._history_message_update(role=role, text=text)
                    if update is not None and not await _send(update):
                        return
                continue
@@ -1116,11 +1068,7 @@ class HermesACPAgent(acp.Agent):

                text = self._history_message_text(message)
                if text:
-                    update = self._history_message_update(
-                        role=role,
-                        text=text,
-                        field_meta=self._history_summary_meta(message, text),
-                    )
+                    update = self._history_message_update(role=role, text=text)
                    if update is not None and not await _send(update):
                        return

@@ -1270,19 +1218,12 @@ class HermesACPAgent(acp.Agent):
            with state.runtime_lock:
                if state.is_running and state.current_prompt_text:
                    state.interrupted_prompt_text = state.current_prompt_text
-                # Publish cancellation and hard-stop the agent before another
-                # prompt can acquire this lock and mistake the turn for
-                # redirectable work.
-                state.cancel_event.set()
-                try:
-                    if getattr(state, "agent", None) and hasattr(state.agent, "interrupt"):
-                        state.agent.interrupt()
-                except Exception:
-                    logger.debug(
-                        "Failed to interrupt ACP session %s",
-                        session_id,
-                        exc_info=True,
-                    )
+            state.cancel_event.set()
+            try:
+                if getattr(state, "agent", None) and hasattr(state.agent, "interrupt"):
+                    state.agent.interrupt()
+            except Exception:
+                logger.debug("Failed to interrupt ACP session %s", session_id, exc_info=True)
            logger.info("Cancelled session %s", session_id)

    async def fork_session(
@@ -1411,26 +1352,6 @@ class HermesACPAgent(acp.Agent):
            elif rewrite_idle:
                user_text = steer_text
                user_content = steer_text
-        elif (
-            text_only_prompt
-            and isinstance(user_content, str)
-            and not user_text.startswith("/")
-        ):
-            # Some ACP clients implement "stop and send" as two protocol calls:
-            # cancel the active prompt, then submit plain correction text. Keep
-            # the cancelled request attached so deictic follow-ups ("not that
-            # file") still have an explicit target.
-            interrupted_prompt = ""
-            with state.runtime_lock:
-                if not state.is_running and state.interrupted_prompt_text:
-                    interrupted_prompt = state.interrupted_prompt_text
-                    state.interrupted_prompt_text = ""
-            if interrupted_prompt:
-                user_text = (
-                    f"{interrupted_prompt}\n\n"
-                    f"User correction/guidance after interrupt: {user_text}"
-                )
-                user_content = user_text

        # Intercept slash commands — handle locally without calling the LLM.
        # Slash commands are text-only; if the client included images/resources,
@@ -1445,54 +1366,23 @@ class HermesACPAgent(acp.Agent):
                    await self._send_usage_update(state)
                return PromptResponse(stop_reason="end_turn")

-        # If the client sends another regular text prompt while this ACP session
-        # is running, route it through the core active-turn redirect. Rich media
-        # and older runtimes retain the proven next-turn queue fallback.
-        redirected = False
-        queued_depth: int | None = None
+        # If Zed sends another regular prompt while the same ACP session is
+        # still running, queue it instead of racing two AIAgent loops against
+        # the same state.history. /steer and /queue are handled above and can
+        # land immediately.
        with state.runtime_lock:
            if state.is_running:
-                if (
-                    text_only_prompt
-                    and isinstance(user_content, str)
-                    and getattr(
-                        state.agent,
-                        "_supports_active_turn_redirect",
-                        False,
+                queued_text = user_text or "[Image attachment]"
+                state.queued_prompts.append(queued_text)
+                depth = len(state.queued_prompts)
+                if self._conn:
+                    update = acp.update_agent_message_text(
+                        f"Queued for the next turn. ({depth} queued)"
                    )
-                    is True
-                    and hasattr(state.agent, "redirect")
-                ):
-                    try:
-                        redirected = bool(state.agent.redirect(user_content))
-                    except Exception:
-                        logger.debug(
-                            "ACP active-turn redirect failed for %s",
-                            session_id,
-                            exc_info=True,
-                        )
-                if not redirected:
-                    queued_text = user_text or "[Image attachment]"
-                    state.queued_prompts.append(queued_text)
-                    queued_depth = len(state.queued_prompts)
-            else:
-                state.is_running = True
-                state.current_prompt_text = user_text or "[Image attachment]"
-
-        if redirected:
-            if self._conn:
-                update = acp.update_agent_message_text(
-                    "Redirected the active turn with your correction."
-                )
-                await self._conn.session_update(session_id, update)
-            return PromptResponse(stop_reason="end_turn")
-        if queued_depth is not None:
-            if self._conn:
-                update = acp.update_agent_message_text(
-                    f"Queued for the next turn. ({queued_depth} queued)"
-                )
-                await self._conn.session_update(session_id, update)
-            return PromptResponse(stop_reason="end_turn")
+                    await self._conn.session_update(session_id, update)
+                return PromptResponse(stop_reason="end_turn")
+            state.is_running = True
+            state.current_prompt_text = user_text or "[Image attachment]"

        logger.info("Prompt on session %s: %s", session_id, user_text[:100])

@@ -1866,7 +1756,7 @@ class HermesACPAgent(acp.Agent):
            "tools": self._cmd_tools,
            "context": self._cmd_context,
            "reset": self._cmd_reset,
-            "compress": self._cmd_compress,
+            "compact": self._cmd_compact,
            "steer": self._cmd_steer,
            "queue": self._cmd_queue,
            "version": self._cmd_version,
@@ -1936,8 +1826,8 @@ class HermesACPAgent(acp.Agent):
                return "No tools available."
            lines = [f"Available tools ({len(tools)}):"]
            for t in tools:
-                name = (t.get("function") or {}).get("name", "?")
-                desc = (t.get("function") or {}).get("description", "")
+                name = t.get("function", {}).get("name", "?")
+                desc = t.get("function", {}).get("description", "")
                # Truncate long descriptions
                if len(desc) > 80:
                    desc = desc[:77] + "..."
@@ -2008,7 +1898,7 @@ class HermesACPAgent(acp.Agent):
                    lines.append(
                        f"Compression: due now (threshold ~{threshold_tokens:,}"
                        + (f", {threshold_pct:.0f}%" if threshold_pct else "")
-                        + "). Run /compress."
+                        + "). Run /compact."
                    )
                else:
                    lines.append(
@@ -2021,12 +1911,9 @@ class HermesACPAgent(acp.Agent):
                lines.append(f"Compression threshold: ~{threshold_tokens:,} tokens")

        if getattr(agent, "compression_enabled", True) is False:
-            lines.append(
-                "Auto-compaction is disabled (compression.enabled: false); "
-                "/compress still compresses manually."
-            )
+            lines.append("Compression is disabled for this agent.")
        else:
-            lines.append("Tip: run /compress to compress manually before the threshold.")
+            lines.append("Tip: run /compact to compress manually before the threshold.")

        return "\n".join(lines)

@@ -2046,14 +1933,13 @@ class HermesACPAgent(acp.Agent):
            return "Conversation history cleared. Agent session state reset failed; see logs."
        return "Conversation history cleared."

-    def _cmd_compress(self, args: str, state: SessionState) -> str:
+    def _cmd_compact(self, args: str, state: SessionState) -> str:
        if not state.history:
            return "Nothing to compress — conversation is empty."
        try:
            agent = state.agent
-            # No compression_enabled gate: the flag disables *automatic*
-            # compaction only; manual /compress must keep working (matches
-            # the CLI /compress and gateway handlers).
+            if not getattr(agent, "compression_enabled", True):
+                return "Context compression is disabled for this agent."
            if not hasattr(agent, "_compress_context"):
                return "Context compression not available for this agent."

@@ -2078,7 +1964,6 @@ class HermesACPAgent(acp.Agent):
                    getattr(agent, "_cached_system_prompt", "") or "",
                    approx_tokens=approx_tokens,
                    task_id=state.session_id,
-                    force=True,
                )
            finally:
                agent._session_db = original_session_db
@@ -0,0 +1,16 @@
+{
+  "id": "hermes-agent",
+  "name": "Hermes Agent",
+  "version": "0.19.0",
+  "description": "Self-improving open-source AI agent by Nous Research with ACP editor integration, persistent memory, skills, and rich tool support.",
+  "repository": "https://github.com/NousResearch/hermes-agent",
+  "website": "https://hermes-agent.nousresearch.com/docs/user-guide/features/acp",
+  "authors": ["Nous Research"],
+  "license": "MIT",
+  "distribution": {
+    "uvx": {
+      "package": "hermes-agent[acp]==0.19.0",
+      "args": ["hermes-acp"]
+    }
+  }
+}
@@ -0,0 +1,8 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16" width="16" height="16" fill="none">
+  <path d="M8 1.5v13" stroke="currentColor" stroke-width="1.5" stroke-linecap="round"/>
+  <path d="M8 3.25c-2.35-1.4-4.7-.95-6.25.35 1.85-.2 3.8.2 5.55 1.55" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
+  <path d="M8 3.25c2.35-1.4 4.7-.95 6.25.35-1.85-.2-3.8.2-5.55 1.55" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
+  <path d="M8 13.25c-2.3-1-3.05-2.65-1.35-4.15-2 .8-2.35 2.95-.35 4" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
+  <path d="M8 13.25c2.3-1 3.05-2.65 1.35-4.15 2 .8 2.35 2.95.35 4" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
+  <circle cx="8" cy="1.8" r="1.1" fill="currentColor"/>
+</svg>
@@ -701,18 +701,6 @@ def redeem_codex_reset_credit(
    remaining = max(0, available - 1)
    plural = "s" if remaining != 1 else ""
    if code == "reset":
-        # The redeemed reset restores the account's quota upstream — lift any
-        # persisted pool cooldowns so Hermes doesn't keep the credential
-        # frozen behind the now-stale ``last_error_reset_at`` (issue #43747).
-        try:
-            from hermes_cli.auth import clear_codex_pool_quota_cooldowns
-
-            clear_codex_pool_quota_cooldowns()
-        except Exception:
-            logger.debug(
-                "Failed to clear Codex pool cooldowns after reset redemption",
-                exc_info=True,
-            )
        return CodexResetRedeemResult(
            status="reset",
            message=(
@@ -28,7 +28,7 @@ import time
 import uuid
 from datetime import datetime
 from typing import Any, Callable, Dict, List, Optional
-from urllib.parse import parse_qs, urlparse, urlunparse
+from urllib.parse import urlparse, parse_qs, urlunparse

 from agent.context_compressor import ContextCompressor
 from agent.iteration_budget import IterationBudget
@@ -48,7 +48,6 @@ from agent.tool_guardrails import (
    ToolGuardrailDecision,
 )
 from hermes_cli.config import cfg_get
-from hermes_cli.route_identity import normalize_route_base_url
 from hermes_cli.timeouts import get_provider_request_timeout
 from hermes_constants import get_hermes_home
 from utils import base_url_host_matches, is_truthy_value
@@ -69,188 +68,18 @@ def _ra():
    return run_agent


-def _moa_reference_output_allowed(agent: Any) -> bool:
-    """Keep MoA display events off only the machine-readable ``-Q`` surface."""
-    return not (
-        getattr(agent, "platform", None) == "cli"
-        and getattr(agent, "tool_progress_mode", "all") == "off"
-    )
-
-
-def _relay_moa_reference_event(agent: Any, event: str, **kwargs: Any) -> None:
-    """Relay MoA display events while preserving the ``-Q`` stdout contract."""
-    if not _moa_reference_output_allowed(agent):
-        return
-    cb = getattr(agent, "tool_progress_callback", None)
-    if cb is None:
-        return
-    try:
-        if event == "moa.reference":
-            cb(
-                "moa.reference",
-                str(kwargs.get("label") or ""),
-                str(kwargs.get("text") or ""),
-                None,
-                moa_index=kwargs.get("index"),
-                moa_count=kwargs.get("count"),
-            )
-        elif event == "moa.aggregating":
-            cb(
-                "moa.aggregating",
-                str(kwargs.get("aggregator") or ""),
-                None,
-                None,
-                moa_ref_count=kwargs.get("ref_count"),
-            )
-    except Exception:
-        pass
-
-
-def _normalize_route_base_url(base_url: Any) -> str:
-    """Canonicalize an endpoint URL for model-route identity comparisons."""
-    return normalize_route_base_url(base_url)
-
-
-def _provider_default_routes(provider: str) -> set[str]:
-    """Return known exact default routes for a canonical provider id."""
-    routes: set[str] = set()
-    try:
-        from hermes_cli.providers import HERMES_OVERLAYS, get_provider
-
-        overlay = HERMES_OVERLAYS.get(provider)
-        provider_def = get_provider(provider)
-        for value in (
-            getattr(overlay, "base_url_override", ""),
-            getattr(provider_def, "base_url", ""),
-        ):
-            route = _normalize_route_base_url(value)
-            if route:
-                routes.add(route)
-    except Exception:
-        pass
-
-    try:
-        from providers import get_provider_profile
-
-        profile = get_provider_profile(provider)
-        route = _normalize_route_base_url(
-            getattr(profile, "base_url", "")
-        )
-        if route:
-            routes.add(route)
-    except Exception:
-        pass
-
-    try:
-        from hermes_cli.auth import PROVIDER_REGISTRY
-        from hermes_cli.models import normalize_provider as normalize_model_provider
-        from hermes_cli.providers import normalize_provider as normalize_registry_provider
-
-        for provider_id, config in PROVIDER_REGISTRY.items():
-            canonical_id = normalize_registry_provider(
-                normalize_model_provider(provider_id)
-            )
-            if canonical_id != provider:
-                continue
-            route = _normalize_route_base_url(
-                getattr(config, "inference_base_url", "")
-            )
-            if route:
-                routes.add(route)
-    except Exception:
-        pass
-
-    if provider == "gemini":
-        routes.update(
-            f"{route.rstrip('/')}/openai"
-            for route in list(routes)
-        )
-    return routes
-
-
-def _context_route_mismatch(
-    configured_base_url: Any,
-    active_base_url: Any,
-    configured_provider: Any,
-    active_provider: Any,
-    *,
-    already_normalized: bool = False,
-) -> bool:
-    """Return whether a context pin's configured route differs from runtime."""
-    if already_normalized:
-        configured_route = str(configured_base_url or "")
-        active_route = str(active_base_url or "")
-    else:
-        configured_route = _normalize_route_base_url(configured_base_url)
-        active_route = _normalize_route_base_url(active_base_url)
-    if configured_route:
-        return configured_route != active_route
-
-    configured_provider = str(configured_provider or "").strip()
-    active_provider = str(active_provider or "").strip()
-    if not configured_provider:
-        return False
-    try:
-        from hermes_cli.models import normalize_provider as normalize_model_provider
-
-        configured_provider = normalize_model_provider(configured_provider)
-        active_provider = normalize_model_provider(active_provider)
-    except Exception:
-        configured_provider = configured_provider.lower()
-        active_provider = active_provider.lower()
-    try:
-        from hermes_cli.providers import normalize_provider as normalize_registry_provider
-
-        configured_provider = normalize_registry_provider(configured_provider)
-        active_provider = normalize_registry_provider(active_provider)
-    except Exception:
-        pass
-
-    if active_route:
-        configured_routes = _provider_default_routes(configured_provider)
-        return not configured_routes or active_route not in configured_routes
-    return bool(
-        configured_provider
-        and active_provider
-        and configured_provider != active_provider
-    )
-
-
-def _normalize_custom_provider_name(value: Any) -> str:
-    """Mirror runtime normalization for a requested custom-provider identity."""
-    return str(value or "").strip().lower().replace(" ", "-")
-
-
-def _custom_provider_runtime_ids(value: Any) -> set[str]:
-    """Return raw/menu identities that runtime accepts for a configured name."""
-    normalized = _normalize_custom_provider_name(value)
-    if not normalized:
-        return set()
-    return {normalized, f"custom:{normalized}"}
-
-
-def _build_codex_gpt5_autoraise_notice(
-    autoraise: Dict[str, Any], context_length: Optional[int] = None
-) -> str:
+def _build_codex_gpt5_autoraise_notice(autoraise: Dict[str, Any]) -> str:
    """Build the one-time notice shown when Codex gpt-5.x raises compaction.

    ``autoraise`` is ``{"model": <slug>, "from": <old_ratio>, "to": <new_ratio>}``.
-    ``context_length`` is the live-resolved window from the context compressor
-    (Codex's /models catalog is authoritative and can change server-side, e.g.
-    the gpt-5.6 family's 272K → 372K → 272K shifts in July 2026), so the banner
-    reports what this session actually got rather than a hardcoded cap. The
-    same text is printed inline for CLI users and replayed via
+    The same text is printed inline for CLI users and replayed via
    ``status_callback`` for gateway users, so it must be self-contained and
    include the exact opt-back-out command.
    """
    model = str(autoraise.get("model") or "gpt-5.4/5.5").strip().lower().rsplit("/", 1)[-1]
-    if isinstance(context_length, int) and context_length > 0:
-        cap = f"{round(context_length / 1000)}K"
-    else:
-        # Static fallback when the resolved window isn't available:
-        # gpt-5.3-codex-spark has a native 128K window; the gpt-5.4/5.5/5.6
-        # family is capped at 272K by the Codex OAuth backend.
-        cap = "128K" if model.startswith("gpt-5.3-codex-spark") else "272K"
+    # gpt-5.3-codex-spark has a native 128K window; the gpt-5.4/5.5/5.6 family
+    # is capped at 272K by the Codex OAuth backend.
+    cap = "128K" if model.startswith("gpt-5.3-codex-spark") else "272K"
    from_pct = int(round(autoraise["from"] * 100))
    to_pct = int(round(autoraise["to"] * 100))
    return (
@@ -517,7 +346,6 @@ def init_agent(
    checkpoint_max_total_size_mb: int = 500,
    checkpoint_max_file_size_mb: int = 10,
    pass_session_id: bool = False,
-    requested_provider: str = None,
 ):
    """
    Initialize the AI Agent.
@@ -526,7 +354,6 @@ def init_agent(
        base_url (str): Base URL for the model API (optional)
        api_key (str): API key for authentication (optional, uses env var if not provided)
        provider (str): Provider identifier (optional; used for telemetry/routing hints)
-        requested_provider (str): Original provider identity before runtime canonicalization
        api_mode (str): API mode override: "chat_completions" or "codex_responses"
        model (str): Model name to use (default: "anthropic/claude-opus-4.6")
        max_iterations (int): Maximum number of tool calling iterations (default: 90)
@@ -607,11 +434,6 @@ def init_agent(
    agent.base_url = base_url or ""
    provider_name = provider.strip().lower() if isinstance(provider, str) and provider.strip() else None
    agent.provider = provider_name or ""
-    agent.requested_provider = (
-        requested_provider.strip().lower()
-        if isinstance(requested_provider, str) and requested_provider.strip()
-        else agent.provider
-    )
    agent._credential_pool = credential_pool
    agent.acp_command = acp_command or command
    agent.acp_args = list(acp_args or args or [])
@@ -764,8 +586,6 @@ def init_agent(
    agent._execution_thread_id: int | None = None  # Set at run_conversation() start
    agent._interrupt_thread_signal_pending = False
    agent._client_lock = threading.RLock()
-    agent._model_request_active = threading.Event()
-    agent._supports_active_turn_redirect = True

    # /steer mechanism — inject a user note into the next tool result
    # without interrupting the agent. Unlike interrupt(), steer() does
@@ -777,13 +597,6 @@ def init_agent(
    agent._pending_steer: Optional[str] = None
    agent._pending_steer_lock = threading.Lock()

-    # Active-turn redirect mechanism. A regular follow-up sent while the model
-    # is generating is different from a hard /stop: preserve the valid turn
-    # prefix, cancel only the in-flight model request, and rebuild its tail with
-    # the correction. The loop drains this slot at a role-safe boundary.
-    agent._pending_redirect: Optional[str] = None
-    agent._pending_redirect_lock = threading.Lock()
-
    # Concurrent-tool worker thread tracking.  `_execute_tool_calls_concurrent`
    # runs each tool on its own ThreadPoolExecutor worker — those worker
    # threads have tids distinct from `_execution_thread_id`, so
@@ -950,12 +763,6 @@ def init_agent(
    agent._stream_writer_tls = threading.local()
    agent._stream_writer_dropped = 0

-    # Displayed reasoning text streamed during the current model response,
-    # captured only when a surface consumed it via a reasoning callback. Used
-    # by active-turn redirect to checkpoint what the user actually saw without
-    # ever persisting hidden provider reasoning.
-    agent._current_streamed_reasoning_text = ""
-
    # Optional current-turn user-message override used when the API-facing
    # user message intentionally differs from the persisted transcript
    # (e.g. CLI voice mode adds a temporary prefix for the live call only).
@@ -1062,20 +869,49 @@ def init_agent(
                elif isinstance(effective_key, str) and len(effective_key) > 12:
                    print(f"🔑 Using token: {effective_key[:8]}...{effective_key[-4:]}")
    elif agent.provider == "moa":
-        from agent.moa_loop import build_moa_facade
+        from agent.moa_loop import MoAClient
        agent.api_mode = "chat_completions"

-        # build_moa_facade wires the reference relay that routes
-        # reference-model outputs to the agent's tool_progress_callback so
+        # Route reference-model outputs to the agent's tool_progress_callback so
        # every surface that already consumes it (CLI spinner/scrollback, TUI,
-        # desktop, gateway) can show each reference's answer as a labelled
-        # block before the aggregator acts. The facade emits "moa.reference",
-        # "moa.progress", "moa.phase", and "moa.aggregating" events, forwarded
-        # through the same callback the tool lifecycle uses. Best-effort and
-        # cache-safe — display-only events, they never touch the message
-        # history. The factory is shared with the fallback-restore/recovery
-        # paths so a restored facade keeps emitting these events (#53802).
-        agent.client = build_moa_facade(agent, agent.model)
+        # desktop, gateway) can show each reference's answer as a labelled block
+        # before the aggregator acts. The facade emits "moa.reference" and
+        # "moa.aggregating" events; we forward them through the same callback
+        # the tool lifecycle uses. Best-effort and cache-safe — these are
+        # display-only events, they never touch the message history.
+        def _moa_reference_relay(event: str, **kwargs: Any) -> None:
+            cb = getattr(agent, "tool_progress_callback", None)
+            if cb is None:
+                return
+            try:
+                if event == "moa.reference":
+                    label = str(kwargs.get("label") or "")
+                    text = str(kwargs.get("text") or "")
+                    idx = kwargs.get("index")
+                    count = kwargs.get("count")
+                    cb(
+                        "moa.reference",
+                        label,
+                        text,
+                        None,
+                        moa_index=idx,
+                        moa_count=count,
+                    )
+                elif event == "moa.aggregating":
+                    cb(
+                        "moa.aggregating",
+                        str(kwargs.get("aggregator") or ""),
+                        None,
+                        None,
+                        moa_ref_count=kwargs.get("ref_count"),
+                    )
+            except Exception:
+                pass
+
+        agent.client = MoAClient(
+            agent.model or "default",
+            reference_callback=_moa_reference_relay,
+        )
        agent._client_kwargs = {}
        agent.api_key = api_key or "moa-virtual-provider"
        agent.base_url = "moa://local"
@@ -1591,14 +1427,7 @@ def init_agent(
    agent._memory_nudge_interval = 10
    agent._turns_since_memory = 0
    agent._iters_since_skill = 0
-    # A flush/background agent may pass skip_memory=True to avoid spinning up an
-    # external memory *provider*, but if the caller also explicitly enables the
-    # "memory" toolset it still needs the built-in file-backed store — otherwise
-    # the memory tool dispatches with store=None and every call fails (#65429).
-    # So the built-in store is created unless memory is globally disabled, while
-    # the external-provider block below stays gated on skip_memory.
-    _memory_toolset_requested = "memory" in (agent.enabled_toolsets or [])
-    if not skip_memory or _memory_toolset_requested:
+    if not skip_memory:
        try:
            mem_config = _agent_cfg.get("memory", {})
            agent._memory_enabled = mem_config.get("memory_enabled", False)
@@ -1818,89 +1647,6 @@ def init_agent(
    compression_enabled = str(_compression_cfg.get("enabled", True)).lower() in {"true", "1", "yes"}
    compression_target_ratio = float(_compression_cfg.get("target_ratio", 0.20))
    compression_protect_last = int(_compression_cfg.get("protect_last_n", 20))
-    # Minimum REAL (actionable) user messages guaranteed to survive in the
-    # uncompressed tail (compression.min_tail_user_messages).  Default 1
-    # preserves current behavior exactly — the existing single-user tail
-    # anchor.  Values > 1 extend the guarantee to the last N actionable
-    # user turns.  Booleans rejected (bool subclasses int), non-int-like
-    # values fall back to 1, floor at 1.
-    _raw_min_tail_users = _compression_cfg.get("min_tail_user_messages", 1)
-    if isinstance(_raw_min_tail_users, bool):
-        compression_min_tail_users = 1
-    elif isinstance(_raw_min_tail_users, int):
-        compression_min_tail_users = _raw_min_tail_users
-    elif isinstance(_raw_min_tail_users, float):
-        compression_min_tail_users = (
-            int(_raw_min_tail_users) if _raw_min_tail_users.is_integer() else 1
-        )
-    else:
-        try:
-            compression_min_tail_users = int(str(_raw_min_tail_users).strip())
-        except (TypeError, ValueError):
-            compression_min_tail_users = 1
-    if compression_min_tail_users < 1:
-        compression_min_tail_users = 1
-    # Cap on compression retry rounds before a turn gives up with "max
-    # compression attempts reached" (compression.max_attempts).  Hardcoding 3
-    # strands sessions that legitimately need more rounds — e.g. a restart
-    # history reload whose incompressible tool schemas keep the request
-    # estimate above the threshold even though the messages compress fine
-    # (the #62605 failure class).  Default 3 preserves current behavior, so
-    # an unset key is behavior-neutral; validated >= 1, hard-capped at 10,
-    # and any non-int-like value falls back to 3.  Booleans are rejected
-    # (bool subclasses int, so int(True) would silently become 1) and
-    # fractional floats are rejected rather than truncated — "4.7 attempts"
-    # is a config mistake, not a request for 4.
-    _raw_max_attempts = _compression_cfg.get("max_attempts", 3)
-    if isinstance(_raw_max_attempts, bool):
-        compression_max_attempts = 3
-    elif isinstance(_raw_max_attempts, int):
-        compression_max_attempts = _raw_max_attempts
-    elif isinstance(_raw_max_attempts, float):
-        compression_max_attempts = (
-            int(_raw_max_attempts) if _raw_max_attempts.is_integer() else 3
-        )
-    else:
-        try:
-            compression_max_attempts = int(str(_raw_max_attempts).strip())
-        except (TypeError, ValueError):
-            compression_max_attempts = 3
-    if compression_max_attempts < 1:
-        compression_max_attempts = 3
-    compression_max_attempts = min(compression_max_attempts, 10)
-
-    def _parse_prune_int(raw, default):
-        # Same parser semantics as compression.max_attempts above: reject
-        # booleans (bool subclasses int — YAML `true` would coerce to 1),
-        # reject fractional floats rather than truncating them, accept
-        # integral floats and numeric strings, fall back to the default on
-        # anything else.
-        if isinstance(raw, bool):
-            return default
-        if isinstance(raw, int):
-            return raw
-        if isinstance(raw, float):
-            return int(raw) if raw.is_integer() else default
-        try:
-            return int(str(raw).strip())
-        except (TypeError, ValueError):
-            return default
-
-    # Opt-in proactive tool-result prune trigger (0 = disabled — the
-    # default, so an unset key is behavior-neutral).  Negative values are
-    # treated as disabled rather than erroring.
-    compression_proactive_prune_tokens = max(
-        0, _parse_prune_int(_compression_cfg.get("proactive_prune_tokens", 0), 0)
-    )
-    compression_proactive_prune_min_chars = _parse_prune_int(
-        _compression_cfg.get("proactive_prune_min_result_chars", 8000), 8000
-    )
-    compression_proactive_prune_min_reclaim = max(
-        0,
-        _parse_prune_int(
-            _compression_cfg.get("proactive_prune_min_reclaim_tokens", 4096), 4096
-        ),
-    )
    # protect_first_n is the number of non-system messages to protect at
    # the head, in addition to the system prompt (which is always
    # implicitly protected by the compressor).  Floor at 0 — a value of
@@ -1913,29 +1659,6 @@ def init_agent(
    compression_abort_on_summary_failure = str(
        _compression_cfg.get("abort_on_summary_failure", False)
    ).lower() in {"true", "1", "yes"}
-    # Per-model threshold overrides: keys are substring-matched against the
-    # model name (longest match wins). Empty dict = use the global threshold
-    # for all models (backward compatible).
-    _raw_model_thresholds = _compression_cfg.get("model_thresholds", {})
-    if isinstance(_raw_model_thresholds, dict):
-        compression_model_thresholds = {
-            str(k): float(v) for k, v in _raw_model_thresholds.items()
-            if isinstance(v, (int, float)) and not isinstance(v, bool)
-        }
-    else:
-        compression_model_thresholds = {}
-    # Absolute token cap: when set, compression triggers at the lower of
-    # the ratio-based threshold and this absolute count. Clamped to the
-    # model's context length at apply-time so a cap above the window is
-    # a no-op (ratio-based threshold wins).
-    compression_threshold_tokens = _compression_cfg.get("threshold_tokens")
-    if compression_threshold_tokens is not None:
-        try:
-            compression_threshold_tokens = int(compression_threshold_tokens)
-            if compression_threshold_tokens <= 0:
-                compression_threshold_tokens = None
-        except (TypeError, ValueError):
-            compression_threshold_tokens = None
    # In-place compaction: when True, compress_context() rewrites the message
    # list + rebuilds the system prompt WITHOUT rotating the session id (no
    # parent_session_id chain, no `name #N` renumber). See #38763 and
@@ -1954,12 +1677,6 @@ def init_agent(
            codex_app_server_auto_compaction,
        )
        codex_app_server_auto_compaction = "native"
-    # Opt-in idle compaction: compact a session up front when it resumes after
-    # this many seconds of inactivity (0 = disabled). Time-based, so it
-    # complements the size-based threshold above. Consumed by build_turn_context().
-    compression_idle_compact_after_seconds = max(
-        0, int(_compression_cfg.get("idle_compact_after_seconds", 0))
-    )

    # Read optional explicit context_length override for the auxiliary
    # compression model. Custom endpoints often cannot report this via
@@ -2030,9 +1747,8 @@ def init_agent(
            )
            _config_context_length = None

-    # Resolve custom_providers once before route-scoping a global context pin:
-    # a named custom provider may keep its base URL only in this list rather
-    # than repeating it under ``model``.
+    # Resolve custom_providers list once for reuse below (startup
+    # context-length override and plugin context-engine init).
    try:
        from hermes_cli.config import get_compatible_custom_providers
        _custom_providers = get_compatible_custom_providers(_agent_cfg)
@@ -2041,163 +1757,6 @@ def init_agent(
        if not isinstance(_custom_providers, list):
            _custom_providers = []

-    # ``model.context_length`` describes the configured default model. A
-    # process launched directly with ``--model`` / ``-m`` has already replaced
-    # ``agent.model`` before this initializer loads config, so carrying the
-    # default model's explicit window into that different runtime is stale. The
-    # live switch/fallback paths already clear this override; keep direct-start
-    # overrides consistent with them and let provider metadata resolve the
-    # active model's window instead.
-    if _config_context_length is not None and isinstance(_model_cfg, dict):
-        _configured_default_model = str(_model_cfg.get("default") or "").strip()
-        _configured_default_runtime_model = _configured_default_model
-        _active_runtime_model = agent.model
-        if _configured_default_model:
-            try:
-                from hermes_cli.model_normalize import normalize_model_for_provider
-
-                _configured_default_runtime_model = normalize_model_for_provider(
-                    _configured_default_model, agent.provider
-                )
-                _active_runtime_model = normalize_model_for_provider(
-                    agent.model, agent.provider
-                )
-            except Exception:
-                pass
-        _configured_provider = str(_model_cfg.get("provider") or "").strip()
-        _configured_base_url = _normalize_route_base_url(
-            _model_cfg.get("base_url")
-        )
-        _configured_provider_norm = _normalize_custom_provider_name(
-            _configured_provider
-        )
-        _custom_provider_candidate = bool(_configured_provider_norm)
-        _runtime_first_provider_ids = {
-            "auto",
-            "moa",
-            "vertex",
-            "google-vertex",
-            "vertex-ai",
-            "gcp-vertex",
-            "vertexai",
-        }
-        if _configured_provider_norm in _runtime_first_provider_ids:
-            _custom_provider_candidate = False
-        elif (
-            _custom_provider_candidate
-            and _configured_provider_norm != "custom"
-            and not _configured_provider_norm.startswith("custom:")
-        ):
-            try:
-                from hermes_cli.auth import resolve_provider as resolve_auth_provider
-
-                _resolved_auth_provider = resolve_auth_provider(
-                    _configured_provider_norm
-                )
-                _custom_provider_candidate = (
-                    str(_resolved_auth_provider or "").strip().lower()
-                    != _configured_provider_norm
-                )
-            except Exception:
-                pass
-        if not _configured_base_url and _custom_provider_candidate:
-            _configured_custom_provider = _normalize_custom_provider_name(
-                _configured_provider
-            )
-            _user_providers = _agent_cfg.get("providers")
-            _disabled_custom_provider_ids: set[str] = set()
-            if isinstance(_user_providers, dict):
-                from hermes_cli.config import is_provider_enabled
-
-                for _provider_key, _provider_entry in _user_providers.items():
-                    if not isinstance(_provider_entry, dict):
-                        continue
-                    _entry_name = str(
-                        _provider_entry.get("name") or ""
-                    ).strip()
-                    _entry_provider_ids = _custom_provider_runtime_ids(
-                        _provider_key
-                    ) | _custom_provider_runtime_ids(_entry_name)
-                    if not is_provider_enabled(_provider_entry):
-                        _disabled_custom_provider_ids.update(
-                            provider_id
-                            for provider_id in _entry_provider_ids
-                            if provider_id
-                        )
-                        continue
-                    if _configured_custom_provider not in _entry_provider_ids:
-                        continue
-                    _configured_base_url = _normalize_route_base_url(
-                        _provider_entry.get("api")
-                        or _provider_entry.get("url")
-                        or _provider_entry.get("base_url")
-                    )
-                    if _configured_base_url:
-                        break
-            if not _configured_base_url:
-                for _provider_entry in _custom_providers:
-                    if not isinstance(_provider_entry, dict):
-                        continue
-                    _entry_name = str(
-                        _provider_entry.get("name") or ""
-                    ).strip()
-                    _entry_provider_key = str(
-                        _provider_entry.get("provider_key") or ""
-                    ).strip().lower()
-                    _entry_provider_ids = _custom_provider_runtime_ids(
-                        _entry_name
-                    ) | _custom_provider_runtime_ids(_entry_provider_key)
-                    if (
-                        _entry_provider_key
-                        and _custom_provider_runtime_ids(_entry_provider_key)
-                        & _disabled_custom_provider_ids
-                    ):
-                        continue
-                    if _configured_custom_provider not in _entry_provider_ids:
-                        continue
-                    _configured_base_url = _normalize_route_base_url(
-                        _provider_entry.get("base_url")
-                    )
-                    if _configured_base_url:
-                        break
-        _active_route_url = str(agent.base_url or "")
-        _requested_route_url = str(base_url or "")
-        if "?" in _requested_route_url.split("#", 1)[0]:
-            try:
-                _requested_parts = urlparse(_requested_route_url)
-                _requested_without_query = urlunparse(
-                    _requested_parts._replace(query="")
-                )
-                if _normalize_route_base_url(
-                    _requested_without_query
-                ) == _normalize_route_base_url(_active_route_url):
-                    _active_route_url = _requested_route_url
-            except (TypeError, ValueError):
-                pass
-        _active_base_url = _normalize_route_base_url(_active_route_url)
-        _route_mismatch = _context_route_mismatch(
-            _configured_base_url,
-            _active_base_url,
-            _configured_provider,
-            agent.provider,
-            already_normalized=True,
-        )
-        _model_mismatch = bool(
-            _configured_default_runtime_model
-            and _configured_default_runtime_model != _active_runtime_model
-        )
-        if _model_mismatch or _route_mismatch:
-            _ra().logger.debug(
-                "Ignoring model.context_length=%s for startup runtime %s at %s "
-                "(configured default is %s at %s)",
-                _config_context_length,
-                agent.model,
-                _active_base_url or agent.provider,
-                _configured_default_model,
-                _configured_base_url or _model_cfg.get("provider"),
-            )
-            _config_context_length = None
-
    # Store for reuse by _check_compression_model_feasibility (auxiliary
    # compression model context-length detection needs the same list).
    agent._custom_providers = _custom_providers
@@ -2220,11 +1779,11 @@ def init_agent(
        # Surface a clear warning if the user set a context_length but it
        # wasn't a valid positive int — the helper silently skips those.
        if _config_context_length is None:
-            _target = _normalize_route_base_url(agent.base_url)
+            _target = agent.base_url.rstrip("/") if agent.base_url else ""
            for _cp_entry in _custom_providers:
                if not isinstance(_cp_entry, dict):
                    continue
-                _cp_url = _normalize_route_base_url(_cp_entry.get("base_url"))
+                _cp_url = (_cp_entry.get("base_url") or "").rstrip("/")
                if _target and _cp_url == _target:
                    _cp_models = _cp_entry.get("models", {})
                    if isinstance(_cp_models, dict):
@@ -2337,16 +1896,6 @@ def init_agent(
            provider=agent.provider,
            custom_providers=_custom_providers,
        )
-        # Per-model threshold overrides are part of the explicit
-        # context-engine contract: assign them BEFORE the initial
-        # update_model() call so the first resolution (which derives
-        # threshold_percent/threshold_tokens for the initial model) already
-        # sees the overrides. Assigning after update_model() left the initial
-        # model on the engine's global threshold until the first /model
-        # switch. Engines that override update_model() own their own policy
-        # and may ignore the attribute.
-        if compression_model_thresholds:
-            agent.context_compressor.model_thresholds = compression_model_thresholds
        agent.context_compressor.update_model(
            model=agent.model,
            context_length=_plugin_ctx_len,
@@ -2373,12 +1922,6 @@ def init_agent(
            api_mode=agent.api_mode,
            abort_on_summary_failure=compression_abort_on_summary_failure,
            max_tokens=agent.max_tokens,
-            model_thresholds=compression_model_thresholds,
-            threshold_tokens_cap=compression_threshold_tokens,
-            proactive_prune_tokens=compression_proactive_prune_tokens,
-            proactive_prune_min_result_chars=compression_proactive_prune_min_chars,
-            proactive_prune_min_reclaim_tokens=compression_proactive_prune_min_reclaim,
-            min_tail_user_messages=compression_min_tail_users,
        )
    _bind_session_state = getattr(agent.context_compressor, "bind_session_state", None)
    if callable(_bind_session_state):
@@ -2389,10 +1932,6 @@ def init_agent(
    agent.compression_enabled = compression_enabled
    agent.compression_in_place = compression_in_place
    agent.codex_app_server_auto_compaction = codex_app_server_auto_compaction
-    agent.max_compression_attempts = compression_max_attempts
-    agent.compression_idle_compact_after_seconds = (
-        compression_idle_compact_after_seconds
-    )

    # Reject models whose context window is below the minimum required
    # for reliable tool-calling workflows (64K tokens).
@@ -2577,7 +2116,7 @@ def init_agent(
    # autoraised model) updates the marker state and re-notifies once. The
    # config display gate (compression.codex_gpt55_autoraise_notice) still
    # suppresses the banner entirely without disabling the threshold autoraise.
-    _autoraise = getattr(agent, "_compression_threshold_autoraised", None) or {}
+    _autoraise = getattr(agent, "_compression_threshold_autoraised", None)
    _show_autoraise_notice = (
        bool(_autoraise)
        and compression_enabled
@@ -2593,21 +2132,14 @@ def init_agent(
            _active_threshold_pct = getattr(
                agent.context_compressor, "threshold_percent", compression_threshold
            )
-            _cap_note = ""
-            _cap = getattr(agent.context_compressor, "threshold_tokens_cap", None)
-            if _cap and _cap > 0:
-                _cap_note = f" (capped at {_cap:,} tokens)"
-            print(f"📊 Context limit: {agent.context_compressor.context_length:,} tokens (compress at {int(_active_threshold_pct*100)}% = {agent.context_compressor.threshold_tokens:,}{_cap_note})")
+            print(f"📊 Context limit: {agent.context_compressor.context_length:,} tokens (compress at {int(_active_threshold_pct*100)}% = {agent.context_compressor.threshold_tokens:,})")
        else:
            print(f"📊 Context limit: {agent.context_compressor.context_length:,} tokens (auto-compression disabled)")
        # Notice with the exact opt-back-out command. Printed inline at startup
        # for CLI users; gateway users get the same text replayed via
        # _compression_warning on turn 1 (set below).
        if _show_autoraise_notice:
-            print(_build_codex_gpt5_autoraise_notice(
-                _autoraise,
-                context_length=getattr(agent.context_compressor, "context_length", None),
-            ))
+            print(_build_codex_gpt5_autoraise_notice(_autoraise))

    # Check immediately so CLI users see the warning at startup.
    # Gateway status_callback is not yet wired, so any warning is stored
@@ -2617,10 +2149,7 @@ def init_agent(
    # above only reaches the CLI, so stash the same text here to be replayed
    # through status_callback on the first turn (Telegram/Discord/Slack/etc.).
    if _show_autoraise_notice:
-        agent._compression_warning = _build_codex_gpt5_autoraise_notice(
-            _autoraise,
-            context_length=getattr(agent.context_compressor, "context_length", None),
-        )
+        agent._compression_warning = _build_codex_gpt5_autoraise_notice(_autoraise)

    # Mark shown so repeated inits in this profile (e.g. every gateway message)
    # stay silent. Recorded once, whether the notice went to the CLI print or
@@ -2643,7 +2172,6 @@ def init_agent(
    agent._primary_runtime = {
        "model": agent.model,
        "provider": agent.provider,
-        "requested_provider": agent.requested_provider,
        "base_url": agent.base_url,
        "api_mode": agent.api_mode,
        "api_key": getattr(agent, "api_key", ""),
@@ -922,23 +922,6 @@ def recover_with_credential_pool(
            )
            return False, has_retried_429

-    # Attribute the failure to the API key the agent actually dispatched the
-    # request with, not to pool.current(). The current() pointer is shared,
-    # mutable state — round-robin select() advances it on every call, and
-    # concurrent turns or a second process (gateway/dashboard) reloading the
-    # pool reset it to None — so by the time recovery runs it routinely points
-    # at a DIFFERENT, healthy entry. Marking that entry exhausted copies this
-    # request's error/reset time onto it and can take the whole pool offline
-    # from a single rate-limited key (#43747). ``_swap_credential`` keeps
-    # ``agent.api_key`` in sync with the entry in use, so it identifies the
-    # failing entry exactly; fall back to current()'s key only when the agent
-    # carries no key at all.
-    _api_key_hint = getattr(agent, "api_key", None) or None
-    if not _api_key_hint:
-        _cur = pool.current()
-        if _cur:
-            _api_key_hint = getattr(_cur, "runtime_api_key", None)
-
    effective_reason = classified_reason
    if effective_reason is None:
        if status_code == 402:
@@ -969,13 +952,13 @@ def recover_with_credential_pool(

    if effective_reason == FailoverReason.billing:
        rotate_status = status_code if status_code is not None else 402
-        # Runtime credentials can be resolved by a separate pool instance,
-        # leaving this recovery pool without ``current_id``. Match the key
-        # that actually failed instead of quarantining a different account.
        next_entry = pool.mark_exhausted_and_rotate(
            status_code=rotate_status,
            error_context=error_context,
-            api_key_hint=_api_key_hint,
+            # Runtime credentials can be resolved by a separate pool instance,
+            # leaving this recovery pool without ``current_id``. Match the key
+            # that actually failed instead of quarantining a different account.
+            api_key_hint=getattr(agent, "api_key", None),
        )
        if next_entry is not None:
            _ra().logger.info(
@@ -992,16 +975,7 @@ def recover_with_credential_pool(
        # rotate immediately. This prevents the "cancel-between-429s" trap
        # where has_retried_429 (a local var) gets reset on each new prompt,
        # causing the pool to retry the same exhausted credential forever.
-        # Prefer the entry matching the failing key over the shared current()
-        # pointer, for the same attribution reason as above.
-        current_entry = None
-        if _api_key_hint:
-            current_entry = next(
-                (e for e in pool.entries() if e.runtime_api_key == _api_key_hint),
-                None,
-            )
-        if current_entry is None:
-            current_entry = pool.current()
+        current_entry = pool.current()
        current_last_status = getattr(current_entry, "last_status", None) if current_entry else None
        if current_last_status == STATUS_EXHAUSTED:
            _ra().logger.info(
@@ -1009,11 +983,7 @@ def recover_with_credential_pool(
                current_last_status,
            )
            rotate_status = status_code if status_code is not None else 429
-            next_entry = pool.mark_exhausted_and_rotate(
-                status_code=rotate_status,
-                error_context=error_context,
-                api_key_hint=_api_key_hint,
-            )
+            next_entry = pool.mark_exhausted_and_rotate(status_code=rotate_status, error_context=error_context)
            if next_entry is not None:
                _ra().logger.info(
                    "Credential %s (rate limit, pre-exhausted) — rotated to pool entry %s",
@@ -1037,11 +1007,7 @@ def recover_with_credential_pool(
        if not has_retried_429 and not usage_limit_reached:
            return False, True
        rotate_status = status_code if status_code is not None else 429
-        next_entry = pool.mark_exhausted_and_rotate(
-            status_code=rotate_status,
-            error_context=error_context,
-            api_key_hint=_api_key_hint,
-        )
+        next_entry = pool.mark_exhausted_and_rotate(status_code=rotate_status, error_context=error_context)
        if next_entry is not None:
            _ra().logger.info(
                "Credential %s (rate limit) — rotated to pool entry %s",
@@ -1056,7 +1022,7 @@ def recover_with_credential_pool(
        # Subscription/entitlement 403s look like auth failures on the wire
        # but refresh cannot fix them — the OAuth token is already valid,
        # the account simply lacks the entitlement.  Without this guard,
-        # the refresh path keeps minting fresh tokens against the
+        # ``try_refresh_current()`` keeps minting fresh tokens against the
        # same unsubscribed account and the main agent loop spins re-issuing
        # the same 403 until the user Ctrl+C's.
        #
@@ -1109,13 +1075,9 @@ def recover_with_credential_pool(
                agent.provider or "provider",
            )
            return False, has_retried_429
-        # Refresh the entry that supplied the failing key, not current():
-        # the shared pointer can reference a different, healthy entry, and
-        # refreshing it would consume that entry's single-use refresh token
-        # (or mark it exhausted on failure) for a failure it never had.
-        refreshed = pool.try_refresh_matching(api_key_hint=_api_key_hint)
+        refreshed = pool.try_refresh_current()
        if refreshed is not None:
-            # ``try_refresh_matching()`` re-mints a fresh OAuth token and reports
+            # ``try_refresh_current()`` re-mints a fresh OAuth token and reports
            # success even when the upstream keeps rejecting it — a single-entry
            # pool (common for OAuth/Max subscribers) has nothing to rotate to,
            # so a bare "refreshed → retry" loop spins forever on the same dead
@@ -1143,13 +1105,9 @@ def recover_with_credential_pool(
            agent._swap_credential(refreshed)
            return True, has_retried_429
        # Refresh failed — rotate to next credential instead of giving up.
-        # The failed entry is already marked exhausted by the refresh attempt.
+        # The failed entry is already marked exhausted by try_refresh_current().
        rotate_status = status_code if status_code is not None else 401
-        next_entry = pool.mark_exhausted_and_rotate(
-            status_code=rotate_status,
-            error_context=error_context,
-            api_key_hint=_api_key_hint,
-        )
+        next_entry = pool.mark_exhausted_and_rotate(status_code=rotate_status, error_context=error_context)
        if next_entry is not None:
            _ra().logger.info(
                "Credential %s (auth refresh failed) — rotated to pool entry %s",
@@ -1208,7 +1166,6 @@ def try_recover_primary_transport(
        agent._client_kwargs = dict(rt["client_kwargs"])
        agent.model = rt["model"]
        agent.provider = rt["provider"]
-        agent.requested_provider = rt.get("requested_provider", agent.provider)
        agent.base_url = rt["base_url"]
        agent.api_mode = rt["api_mode"]
        if hasattr(agent, "_transport_cache"):
@@ -1225,14 +1182,6 @@ def try_recover_primary_transport(
            )
            agent._is_anthropic_oauth = rt["is_anthropic_oauth"]
            agent.client = None
-        elif (agent.provider or "").strip().lower() == "moa":
-            # MoA is a virtual provider with empty client_kwargs — rebuilding
-            # via _create_openai_client would raise "api_key client option
-            # must be set". Recreate the facade through the shared factory so
-            # the reference_callback relay survives recovery (#53802).
-            from agent.moa_loop import build_moa_facade
-
-            agent.client = build_moa_facade(agent, agent.model)
        else:
            agent.client = agent._create_openai_client(
                dict(rt["client_kwargs"]),
@@ -1380,7 +1329,6 @@ def restore_primary_runtime(agent) -> bool:
        # ── Core runtime state ──
        agent.model = rt["model"]
        agent.provider = rt["provider"]
-        agent.requested_provider = rt.get("requested_provider", agent.provider)
        agent.base_url = rt["base_url"]           # setter updates _base_url_lower
        agent.api_mode = rt["api_mode"]
        if hasattr(agent, "_transport_cache"):
@@ -1396,18 +1344,7 @@ def restore_primary_runtime(agent) -> bool:
        )

        # ── Rebuild client for the primary provider ──
-        if agent.provider == "moa":
-            # MoA is a virtual chat-completions provider.  It never has real
-            # OpenAI client kwargs; restoring it after a fallback must recreate
-            # the facade, not call OpenAI() with an empty api_key.  Use the
-            # shared factory so the restored facade keeps the reference_callback
-            # relay wired at init — a bare MoAClient() would silently stop
-            # emitting moa.reference/moa.aggregating display events (#53802).
-            from agent.moa_loop import build_moa_facade
-
-            agent.client = build_moa_facade(agent, agent.model)
-            agent._anthropic_client = None
-        elif agent.api_mode == "anthropic_messages":
+        if agent.api_mode == "anthropic_messages":
            from agent.anthropic_adapter import build_anthropic_client
            agent._anthropic_api_key = rt["anthropic_api_key"]
            agent._anthropic_base_url = rt["anthropic_base_url"]
@@ -2056,7 +1993,6 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
        for name in (
            "model",
            "provider",
-            "requested_provider",
            "base_url",
            "api_mode",
            "api_key",
@@ -2085,7 +2021,6 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
        # ── Swap core runtime fields ──
        agent.model = new_model
        agent.provider = new_provider
-        agent.requested_provider = new_provider
        # Use the new base_url when provided. When it's empty AND the
        # provider is actually changing, do NOT fall back to the current
        # (old provider's) URL — that silently pairs the new provider label
@@ -2143,7 +2078,7 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo

        # ── Build new client ──
        if (new_provider or "").strip().lower() == "moa":
-            from agent.moa_loop import build_moa_facade
+            from agent.moa_loop import MoAClient

            # The MoA virtual provider speaks only chat.completions via the
            # MoAClient facade — the aggregator's real transport
@@ -2160,7 +2095,7 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
            agent.api_key = api_key or "moa-virtual-provider"
            agent.base_url = "moa://local"
            agent._client_kwargs = {}
-            agent.client = build_moa_facade(agent, agent.model)
+            agent.client = MoAClient(agent.model or "default")
        elif api_mode == "anthropic_messages":
            from agent.anthropic_adapter import (
                build_anthropic_client,
@@ -2335,7 +2270,6 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
    agent._primary_runtime = {
        "model": agent.model,
        "provider": agent.provider,
-        "requested_provider": agent.requested_provider,
        "base_url": agent.base_url,
        "api_mode": agent.api_mode,
        "api_key": getattr(agent, "api_key", ""),
@@ -1881,28 +1881,6 @@ def _content_parts_to_anthropic_blocks(parts: Any) -> List[Dict[str, Any]]:
    return out


-_EMPTY_TEXT_PLACEHOLDER = "(empty)"
-
-
-def _safe_text(text: Any) -> str:
-    """Return ``text`` if it's non-whitespace, else a non-whitespace placeholder.
-
-    The Anthropic Messages API rejects requests where a text content block is
-    empty or whitespace-only (HTTP 400 "text content blocks must contain
-    non-whitespace text"). When such a block gets stored in session history —
-    e.g. produced by context compression — it is replayed verbatim on every
-    subsequent turn, permanently wedging the session. Coercing to a
-    non-whitespace placeholder is self-healing: the next API call recovers.
-
-    Mirrors ``bedrock_adapter._safe_text`` (#9486); ref #69512.
-    """
-    if text is None:
-        return _EMPTY_TEXT_PLACEHOLDER
-    if not isinstance(text, str):
-        text = str(text)
-    return text if text.strip() else _EMPTY_TEXT_PLACEHOLDER
-
-
 def _sanitize_replay_block(b: Dict[str, Any]) -> Optional[Dict[str, Any]]:
    """Strip output-only fields from a stored Anthropic content block so it is
    valid as REQUEST input on replay.
@@ -1920,10 +1898,7 @@ def _sanitize_replay_block(b: Dict[str, Any]) -> Optional[Dict[str, Any]]:
        return None
    btype = b.get("type")
    if btype == "text":
-        # Coerce empty/whitespace-only text to a non-whitespace placeholder;
-        # the Messages input schema rejects blank text blocks (#69512), and a
-        # blank block stored in history replays on every turn → permanent 400.
-        out: Dict[str, Any] = {"type": "text", "text": _safe_text(b.get("text", ""))}
+        out: Dict[str, Any] = {"type": "text", "text": b.get("text", "")}
        # citations is input-valid ONLY when it's a non-empty list; the SDK
        # emits citations=None on responses, which the input schema rejects.
        cits = b.get("citations")
@@ -2083,16 +2058,7 @@ def _convert_assistant_message(m: Dict[str, Any]) -> Dict[str, Any]:
    # Anthropic rejects empty assistant content
    effective = blocks or content
    if not effective or effective == "":
-        effective = [{"type": "text", "text": _EMPTY_TEXT_PLACEHOLDER}]
-    elif isinstance(effective, list):
-        # The all-empty guard above misses a list that still contains a
-        # whitespace-only text block (e.g. from a content array of blank parts,
-        # or compression). Those also trip "text content blocks must contain
-        # non-whitespace text" (#69512). Coerce text blocks in place; other
-        # block types (thinking/tool_use/image) are left untouched.
-        for blk in effective:
-            if isinstance(blk, dict) and blk.get("type") == "text":
-                blk["text"] = _safe_text(blk.get("text", ""))
+        effective = [{"type": "text", "text": "(empty)"}]
    return {"role": "assistant", "content": effective}


@@ -2446,24 +2412,6 @@ def _evict_old_screenshots(result: List[Dict[str, Any]]) -> None:
                ]


-def _ensure_leading_user_turn(result: List[Dict[str, Any]]) -> None:
-    """Anthropic requires messages[0] to have role=user.
-
-    After a second context compaction on the auto path the summary can be
-    emitted as role=assistant with nothing in front of it (the system prompt
-    lives outside messages[] or is extracted into the separate ``system``
-    param), so messages[0] ends up assistant and the Messages API rejects
-    the request with HTTP 400 — often masked by a misleading
-    "tool_use ids were found without tool_result blocks" error (#52160).
-
-    Mirror the Bedrock Converse adapter, which unconditionally prepends a
-    minimal user turn when the first message is not user
-    (convert_messages_to_converse).
-    """
-    if result and result[0].get("role") != "user":
-        result.insert(0, {"role": "user", "content": [{"type": "text", "text": " "}]})
-
-
 def convert_messages_to_anthropic(
    messages: List[Dict],
    base_url: str | None = None,
@@ -2522,7 +2470,6 @@ def convert_messages_to_anthropic(

    _strip_orphaned_tool_blocks(result)
    result = _merge_consecutive_roles(result)
-    _ensure_leading_user_turn(result)
    _manage_thinking_signatures(result, base_url, model)
    _evict_old_screenshots(result)

@@ -2303,62 +2303,6 @@ def _read_main_base_url() -> str:
    return ""


-def _resolve_moa_aggregator(preset_name: Optional[str]) -> Tuple[Optional[str], Optional[str]]:
-    """Resolve a MoA preset to its aggregator (provider, model) pair.
-
-    "moa" is a virtual provider — the acting model of a preset is its
-    aggregator slot, and there is no real "moa" HTTP endpoint. Auxiliary
-    tasks (title generation, compression, vision, commit messages, …) don't
-    need the reference fan-out, so every aux resolution layer maps
-    provider="moa"/model=<preset> to the aggregator's real provider+model
-    through this single helper (shared by ``_resolve_auto``,
-    ``_resolve_task_provider_model``, and ``resolve_provider_client`` so the
-    preset lookup and validation cannot drift between paths).
-
-    Args:
-        preset_name: The MoA preset name (usually carried in the "model"
-            field), or None/"" to resolve the user's default preset.
-
-    Returns:
-        (aggregator_provider, aggregator_model), or (None, None) when the
-        preset cannot be resolved (missing config, renamed/deleted preset,
-        or a malformed aggregator slot).
-    """
-    try:
-        from hermes_cli.config import load_config
-        from hermes_cli.moa_config import resolve_moa_preset
-
-        preset = resolve_moa_preset(load_config().get("moa") or {}, preset_name or None)
-        agg = preset.get("aggregator") or {}
-        agg_provider = str(agg.get("provider") or "").strip()
-        agg_model = str(agg.get("model") or "").strip()
-        if agg_provider and agg_model and agg_provider.lower() != "moa":
-            return agg_provider, agg_model
-    except Exception:
-        logger.debug(
-            "MoA aggregator resolution failed for preset %r", preset_name, exc_info=True
-        )
-    return None, None
-
-
-def _read_main_model_for_aux() -> str:
-    """Main model with MoA presets unwrapped to the aggregator's model.
-
-    When the main provider is ``moa``, ``_read_main_model()`` returns a MoA
-    *preset name* (e.g. "opus-gpt") — never a valid wire model id on any
-    provider. Auxiliary fallback chains that pre-fill a missing model from
-    the main model must use this reader instead, so unset aux models default
-    to the preset's acting (aggregator) model. Returns "" when the main
-    provider is moa but the preset cannot be resolved — sending nothing is
-    strictly better than sending a preset name that 400s.
-    """
-    model = _read_main_model()
-    if (_read_main_provider() or "").strip().lower() == "moa":
-        _, agg_model = _resolve_moa_aggregator(model)
-        return agg_model or ""
-    return model
-
-
 def _read_main_api_key_if_same_host(aux_base_url: str) -> str:
    """Return the main api_key only when *aux_base_url* points at the same
    host as the main model's base_url.
@@ -2434,7 +2378,6 @@ def set_runtime_main(
    provider: str,
    model: str,
    *,
-    requested_provider: str = "",
    base_url: str = "",
    api_key: Any = "",
    api_mode: str = "",
@@ -2450,7 +2393,6 @@ def set_runtime_main(
    global _RUNTIME_MAIN_AUTH_MODE, _RUNTIME_MAIN_COMPAT_SNAPSHOT
    runtime = {
        "provider": (provider or "").strip().lower(),
-        "requested_provider": (requested_provider or "").strip().lower(),
        "model": (model or "").strip(),
        "base_url": (base_url or "").strip(),
        "api_key": (
@@ -2631,7 +2573,7 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
        return None, None
    if custom_base.lower().startswith(_CODEX_AUX_BASE_URL.lower()):
        return None, None
-    model = _read_main_model_for_aux() or "gpt-4o-mini"
+    model = _read_main_model() or "gpt-4o-mini"
    logger.debug("Auxiliary client: custom endpoint (%s, api_mode=%s)", model, custom_mode or "chat_completions")
    _clean_base, _dq = _extract_url_query_params(custom_base)
    _extra = {"default_query": _dq} if _dq else {}
@@ -2923,7 +2865,6 @@ _AUTO_PROVIDER_LABELS = {
 }

 _MAIN_RUNTIME_FIELDS = ("provider", "model", "base_url", "api_key", "api_mode", "auth_mode")
-_MAIN_RUNTIME_CONTEXT_FIELDS = _MAIN_RUNTIME_FIELDS + ("requested_provider",)


 def _normalize_main_runtime(main_runtime: Optional[Dict[str, Any]]) -> Dict[str, Any]:
@@ -2946,7 +2887,7 @@ def _normalize_main_runtime(main_runtime: Optional[Dict[str, Any]]) -> Dict[str,
    if not isinstance(main_runtime, dict):
        return {}
    normalized: Dict[str, Any] = {}
-    for field in _MAIN_RUNTIME_CONTEXT_FIELDS:
+    for field in _MAIN_RUNTIME_FIELDS:
        value = main_runtime.get(field)
        # Preserve a callable api_key (Entra ID bearer provider) unchanged.
        if field == "api_key" and callable(value) and not isinstance(value, str):
@@ -2954,10 +2895,9 @@ def _normalize_main_runtime(main_runtime: Optional[Dict[str, Any]]) -> Dict[str,
            continue
        if isinstance(value, str) and value.strip():
            normalized[field] = value.strip()
-    for identity_field in ("provider", "requested_provider"):
-        identity = normalized.get(identity_field)
-        if isinstance(identity, str):
-            normalized[identity_field] = identity.lower()
+    provider = normalized.get("provider")
+    if isinstance(provider, str):
+        normalized["provider"] = provider.lower()
    return normalized


@@ -3648,7 +3588,6 @@ def _retry_same_provider_sync(
    effective_timeout: float,
    effective_extra_body: dict,
    reasoning_config: Optional[dict],
-    extra_headers: Optional[Dict[str, str]] = None,
 ) -> Any:
    if task == "vision":
        _, retry_client, retry_model = resolve_vision_provider_client(
@@ -3684,13 +3623,7 @@ def _retry_same_provider_sync(
        extra_body=effective_extra_body,
        reasoning_config=reasoning_config,
        base_url=retry_base or resolved_base_url,
-        task=task,
    )
-    # Preserve per-request attribution headers (e.g. Copilot's
-    # ``x-initiator: user``) across the rebuilt-client retry — dropping them
-    # here would let a recovery retry silently lose capability gating (#60293).
-    if extra_headers:
-        retry_kwargs["extra_headers"] = dict(extra_headers)
    if _is_anthropic_compat_endpoint(resolved_provider, retry_base):
        retry_kwargs["messages"] = _convert_openai_images_to_anthropic(retry_kwargs["messages"])
    return _validate_llm_response(
@@ -3714,7 +3647,6 @@ async def _retry_same_provider_async(
    effective_timeout: float,
    effective_extra_body: dict,
    reasoning_config: Optional[dict],
-    extra_headers: Optional[Dict[str, str]] = None,
 ) -> Any:
    if task == "vision":
        _, retry_client, retry_model = resolve_vision_provider_client(
@@ -3750,12 +3682,7 @@ async def _retry_same_provider_async(
        extra_body=effective_extra_body,
        reasoning_config=reasoning_config,
        base_url=retry_base or resolved_base_url,
-        task=task,
    )
-    # Preserve per-request attribution headers across the rebuilt-client
-    # retry — see the sync variant above (#60293).
-    if extra_headers:
-        retry_kwargs["extra_headers"] = dict(extra_headers)
    if _is_anthropic_compat_endpoint(resolved_provider, retry_base):
        retry_kwargs["messages"] = _convert_openai_images_to_anthropic(retry_kwargs["messages"])
    return _validate_llm_response(
@@ -3830,24 +3757,6 @@ def _refresh_provider_credentials(provider: str) -> bool:
                return False
            _evict_cached_clients(normalized)
            return True
-        if normalized == "vertex":
-            # Mirrors run_agent.py's _try_refresh_vertex_client_credentials
-            # for the main conversation loop. Without this branch, an
-            # auxiliary Vertex client (vision, title generation, reflection,
-            # context compression, ...) that 401s on its ~1h token expiry
-            # falls through to the final `return False` below: the stale
-            # client is never evicted from _client_cache (whose cache key
-            # ignores the rotating bearer token), so every subsequent
-            # auxiliary Vertex call keeps 401ing until process restart.
-            from agent.vertex_adapter import get_vertex_config
-
-            token, base_url = get_vertex_config()
-            if not isinstance(token, str) or not token.strip():
-                return False
-            if not isinstance(base_url, str) or not base_url.strip():
-                return False
-            _evict_cached_clients(normalized)
-            return True
    except Exception as exc:
        logger.debug("Auxiliary provider credential refresh failed for %s: %s", normalized, exc)
        return False
@@ -3961,7 +3870,7 @@ def _call_fallback_candidate_sync(
        temperature=temperature, max_tokens=max_tokens,
        tools=tools, timeout=effective_timeout,
        extra_body=effective_extra_body, reasoning_config=reasoning_config,
-        base_url=fb_base, task=task)
+        base_url=fb_base)
    try:
        return _validate_llm_response(
            fb_client.chat.completions.create(**fb_kwargs), task)
@@ -3978,7 +3887,7 @@ def _call_fallback_candidate_sync(
                    tools=tools, timeout=effective_timeout,
                    extra_body=effective_extra_body,
                    reasoning_config=reasoning_config,
-                    base_url=str(getattr(retry_client, "base_url", "") or fb_base), task=task)
+                    base_url=str(getattr(retry_client, "base_url", "") or fb_base))
                try:
                    return _validate_llm_response(
                        retry_client.chat.completions.create(**retry_kwargs), task)
@@ -4027,7 +3936,7 @@ async def _call_fallback_candidate_async(
        temperature=temperature, max_tokens=max_tokens,
        tools=tools, timeout=effective_timeout,
        extra_body=effective_extra_body, reasoning_config=reasoning_config,
-        base_url=fb_base, task=task)
+        base_url=fb_base)
    try:
        return _validate_llm_response(
            await fb_client.chat.completions.create(**fb_kwargs), task)
@@ -4045,7 +3954,7 @@ async def _call_fallback_candidate_async(
                    tools=tools, timeout=effective_timeout,
                    extra_body=effective_extra_body,
                    reasoning_config=reasoning_config,
-                    base_url=str(getattr(retry_client, "base_url", "") or fb_base), task=task)
+                    base_url=str(getattr(retry_client, "base_url", "") or fb_base))
                try:
                    return _validate_llm_response(
                        await retry_client.chat.completions.create(**retry_kwargs), task)
@@ -4132,13 +4041,6 @@ def _try_main_agent_model_fallback(
    """
    main_provider = (_read_main_provider() or "").strip()
    main_model = (_read_main_model() or "").strip()
-    if main_provider.lower() == "moa":
-        # MoA virtual provider: fall back to the preset's aggregator — the
-        # acting model — instead of the unreachable "moa"/<preset-name> pair.
-        _agg_provider, _agg_model = _resolve_moa_aggregator(main_model)
-        if not _agg_provider or not _agg_model:
-            return None, None, ""
-        main_provider, main_model = _agg_provider, _agg_model
    if not main_provider or not main_model or main_provider.lower() in {"auto", ""}:
        return None, None, ""

@@ -4539,17 +4441,26 @@ def _resolve_auto(
    # model. Resolve the MoA preset to its aggregator slot and continue Step 1
    # with that real provider+model. Mirrors the MoA context-length resolution.
    if main_provider == "moa":
-        _agg_provider, _agg_model = _resolve_moa_aggregator(main_model)
-        if _agg_provider and _agg_model:
-            main_provider = _agg_provider
-            main_model = _agg_model
-            # The MoA virtual runtime carries a non-HTTP base_url
-            # ("moa://local") and a placeholder api_key; they belong to the
-            # facade, not the aggregator's real provider. Drop them so the
-            # aggregator resolves through its own provider credentials.
-            runtime_base_url = ""
-            runtime_api_key = ""
-            runtime_api_mode = ""
+        try:
+            from hermes_cli.config import load_config
+            from hermes_cli.moa_config import resolve_moa_preset
+
+            _preset = resolve_moa_preset(load_config().get("moa") or {}, main_model)
+            _agg = _preset.get("aggregator") or {}
+            _agg_provider = str(_agg.get("provider") or "").strip()
+            _agg_model = str(_agg.get("model") or "").strip()
+            if _agg_provider and _agg_model and _agg_provider.lower() != "moa":
+                main_provider = _agg_provider
+                main_model = _agg_model
+                # The MoA virtual runtime carries a non-HTTP base_url
+                # ("moa://local") and a placeholder api_key; they belong to the
+                # facade, not the aggregator's real provider. Drop them so the
+                # aggregator resolves through its own provider credentials.
+                runtime_base_url = ""
+                runtime_api_key = ""
+                runtime_api_mode = ""
+        except Exception:
+            logger.debug("MoA aux resolution to aggregator failed", exc_info=True)

    if (main_provider and main_model
            and main_provider not in {"auto", ""}):
@@ -4804,27 +4715,6 @@ def resolve_provider_client(
    # Normalise aliases
    provider = _normalize_aux_provider(provider)

-    # MoA virtual provider chokepoint: "moa" is not a real HTTP provider —
-    # its acting model is the preset's aggregator slot. The two resolver
-    # layers above (_resolve_auto, _resolve_task_provider_model) already
-    # unwrap their own paths, but callers that route here directly (vision
-    # auto-detect, _try_main_agent_model_fallback, get_available_vision_backends,
-    # plugin code) would otherwise dead-end in the unknown-provider branch.
-    # ``model`` carries the preset name for moa calls; when the preset can't
-    # be resolved we leave the call untouched and let the normal
-    # missing-provider handling produce its diagnostic.
-    if provider == "moa":
-        _agg_provider, _agg_model = _resolve_moa_aggregator(model)
-        if _agg_provider and _agg_model:
-            original_provider = _agg_provider.strip().lower()
-            provider = _normalize_aux_provider(_agg_provider)
-            model = _agg_model
-            # The moa:// facade endpoint and placeholder key belong to the
-            # virtual runtime, not the aggregator's real provider.
-            if explicit_base_url and str(explicit_base_url).lower().startswith("moa://"):
-                explicit_base_url = None
-                explicit_api_key = None
-
    # Universal model-resolution fallback for concrete providers. ``auto`` is
    # intentionally excluded: `_resolve_auto(main_runtime=...)` returns the
    # model paired with the provider it actually selected. Pre-filling an auto
@@ -4845,10 +4735,6 @@ def resolve_provider_client(
    #      the load-bearing step for OAuth providers: an xai-oauth user
    #      with grok-4.3 configured gets grok-4.3 for title generation
    #      instead of silently dropping to whatever Step-2 fallback (#31845).
-    #      When the main provider is MoA, ``_read_main_model_for_aux()``
-    #      substitutes the preset's aggregator model — the preset NAME is
-    #      never a valid wire model id, so unset aux models default to the
-    #      preset's acting model instead.
    #
    # Each provider branch below sees a non-empty ``model`` whenever the
    # user has *anything* configured — no provider-specific empty-model
@@ -4865,7 +4751,7 @@ def resolve_provider_client(
    # return the actual current runtime model when the caller did not explicitly
    # request one. (# compression-current-model)
    if not model and provider != "auto":
-        model = _get_aux_model_for_provider(provider) or _read_main_model_for_aux() or model
+        model = _get_aux_model_for_provider(provider) or _read_main_model() or model

    def _needs_codex_wrap(client_obj, base_url_str: str, model_str: str) -> bool:
        """Decide if a plain OpenAI client should be wrapped for Responses API.
@@ -5139,7 +5025,7 @@ def resolve_provider_client(
                    model
                    or custom_entry.get("model")
                    or (main_runtime.get("model") if main_runtime else None)
-                    or _read_main_model_for_aux()
+                    or _read_main_model()
                    or "gpt-4o-mini",
                    provider,
                )
@@ -5374,7 +5260,7 @@ def resolve_provider_client(
        final_model = _normalize_resolved_model(
            model
            or (main_runtime.get("model") if main_runtime else None)
-            or _read_main_model_for_aux(),
+            or _read_main_model(),
            provider,
        )
        if provider == "copilot-acp":
@@ -5742,24 +5628,7 @@ def resolve_vision_provider_client(
        #   5. Stop
        main_provider = str(runtime.get("provider") or _read_main_provider())
        main_model = str(runtime.get("model") or _read_main_model())
-        if main_provider.strip().lower() == "moa":
-            # MoA virtual provider: main_model is a preset NAME, and every
-            # capability probe below (_PROVIDERS_WITHOUT_VISION,
-            # _main_model_supports_vision, _resolve_provider_vision_default)
-            # would run against a provider/model pair that doesn't exist on
-            # any wire. Unwrap to the preset's aggregator slot first so the
-            # checks and the eventual client target the real acting model.
-            _agg_provider, _agg_model = _resolve_moa_aggregator(main_model)
-            if _agg_provider and _agg_model:
-                main_provider, main_model = _agg_provider, _agg_model
-                # Drop the moa:// facade endpoint from the runtime view used
-                # below — it belongs to the virtual provider, not the
-                # aggregator's real provider.
-                runtime = dict(runtime)
-                runtime["base_url"] = ""
-                runtime["api_key"] = ""
-                runtime["api_mode"] = ""
-        if main_provider and main_provider not in {"auto", "", "moa"}:
+        if main_provider and main_provider not in {"auto", ""}:
            # A provider-specific vision default wins over the user's chat model:
            # static overrides (xiaomi/zai) and catalog-backed discovery (the
            # DeepInfra profile hook) both yield a *known* vision-capable model,
@@ -6356,8 +6225,8 @@ def _resolve_task_provider_model(
    task: str = None,
    provider: str = None,
    model: str = None,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
+    base_url: str = None,
+    api_key: str = None,
 ) -> Tuple[str, Optional[str], Optional[str], Optional[str], Optional[str]]:
    """Determine provider + model for a call.

@@ -6400,57 +6269,12 @@ def _resolve_task_provider_model(
    # which downstream consumers like ContextCompressor accept as the task output.
    # The provider-side 'auto' is handled in _resolve_auto() via main_runtime
    # fallback, so dropping cfg_model to None here lets that path do its job.
-    #
-    # The explicit `model` kwarg needs the identical normalization: MoA slots
-    # (agent/moa_loop.py's _slot_runtime) forward a preset's `model:` field as
-    # this explicit argument rather than through auxiliary.<task> config, so a
-    # user-configured `model: auto` on a MoA reference/aggregator slot reaches
-    # this function here, not as cfg_model. Only normalizing cfg_model let that
-    # literal "auto" slip through via `model or cfg_model` below.
-    if model and model.lower() == "auto":
-        model = None
    if cfg_model and cfg_model.lower() == "auto":
        cfg_model = None

    resolved_model = model or cfg_model
    resolved_api_mode = cfg_api_mode

-    # MoA virtual provider: an *explicit* `provider: moa` override (either the
-    # caller-passed `provider` arg or `auxiliary.<task>.provider` in
-    # config.yaml) reaches this function directly — it never goes through
-    # _resolve_auto(), which only unwraps the *implicit* "main provider is
-    # moa" case (#53827). Left as-is, "moa" is returned verbatim and
-    # resolve_provider_client() looks it up in PROVIDER_REGISTRY (which has
-    # no "moa" entry — it's not a real HTTP provider), falls to the
-    # unknown-provider dead end, and call_llm surfaces a nonsensical
-    # "MOA_API_KEY environment variable" error for a provider that was never
-    # meant to be reached over the wire. Auxiliary tasks don't need the
-    # reference fan-out — resolve to the preset's aggregator slot instead,
-    # exactly like the implicit path does (shared helper: _resolve_moa_aggregator).
-    def _unwrap_moa_provider(prov: str, mdl: Optional[str]) -> Tuple[str, Optional[str]]:
-        if prov.strip().lower() != "moa":
-            return prov, mdl
-        agg_provider, agg_model = _resolve_moa_aggregator(mdl)
-        if agg_provider and agg_model:
-            return agg_provider, agg_model
-        return prov, mdl
-
-    if provider and str(provider).strip().lower() == "moa":
-        provider, resolved_model = _unwrap_moa_provider(provider, resolved_model)
-        # The moa:// virtual endpoint (if any explicit base_url/api_key was
-        # passed alongside provider="moa") belongs to the facade, not the
-        # aggregator's real provider — drop it so the aggregator resolves
-        # through its own provider credentials, mirroring _resolve_auto().
-        if provider and provider.lower() != "moa":
-            base_url = None
-            api_key = None
-    elif cfg_provider and str(cfg_provider).strip().lower() == "moa":
-        cfg_provider, cfg_model = _unwrap_moa_provider(cfg_provider, resolved_model)
-        if cfg_provider and cfg_provider.lower() != "moa":
-            resolved_model = cfg_model
-            cfg_base_url = None
-            cfg_api_key = None
-
    # Convenience aliases for direct API-key endpoints that aren't first-class
    # providers (e.g. ``provider: openai`` → custom + api.openai.com/v1).
    # Applied to both explicit args and config-derived values. When the user
@@ -6807,7 +6631,6 @@ def _build_call_kwargs(
    extra_body: Optional[dict] = None,
    reasoning_config: Optional[dict] = None,
    base_url: Optional[str] = None,
-    task: Optional[str] = None,
 ) -> dict:
    """Build kwargs for .chat.completions.create() with model/provider adjustments."""
    kwargs: Dict[str, Any] = {
@@ -6862,32 +6685,11 @@ def _build_call_kwargs(
            _provider_norm in {"nvidia", "nvidia-nim", "nim", "build-nvidia", "nemotron"}
            or base_url_host_matches(_effective_base, "integrate.api.nvidia.com")
        )
-        _is_moa = bool(task) and str(task) == "moa_reference"
-        # Gemini's native generateContent maps max_tokens → maxOutputTokens and,
-        # when it is omitted, applies a fixed 65,535-token ceiling rather than
-        # "the model's full budget" (see gemini_native_adapter.build_gemini_request).
-        # So an explicit cap is both safe and the ONLY way to honor it here —
-        # dropping max_tokens silently makes MoA's reference_max_tokens a no-op
-        # for gemini advisors (they run effectively uncapped).
-        _is_gemini_native = _provider_norm in {
-            "gemini", "google", "google-gemini", "google-ai-studio",
-        }
-        if not _is_gemini_native and _effective_base:
-            try:
-                from agent.gemini_native_adapter import is_native_gemini_base_url
-                _is_gemini_native = is_native_gemini_base_url(_effective_base)
-            except Exception:
-                pass
        if (
            _is_anthropic_compat_endpoint(provider, _effective_base)
            or _is_nvidia_nim
-            or _is_moa
-            or _is_gemini_native
        ):
-            # Use auxiliary_max_tokens_param() so models that require
-            # max_completion_tokens (GPT-5 family, Copilot) get the right
-            # parameter name instead of a hardcoded max_tokens that 400s.
-            kwargs.update(auxiliary_max_tokens_param(max_tokens, model=model))
+            kwargs["max_tokens"] = max_tokens

    if tools:
        # Defensive dedup: providers like Google Vertex, Azure, and Bedrock
@@ -7119,7 +6921,6 @@ def call_llm(
    timeout: float = None,
    extra_body: dict = None,
    reasoning_config: Optional[dict] = None,
-    extra_headers: Optional[Dict[str, str]] = None,
    api_mode: str = None,
    stream: bool = False,
    stream_options: dict = None,
@@ -7145,9 +6946,6 @@ def call_llm(
        extra_body: Additional request body fields.
        reasoning_config: Optional Hermes reasoning config for direct model calls
              such as MoA reference/aggregator slots.
-        extra_headers: Additional per-request HTTP headers. These override
-            client-level defaults for providers that gate capabilities on
-            request attribution (for example Copilot's ``x-initiator``).
        stream: When True, return the raw SDK streaming iterator instead of a
            validated complete response. The caller is responsible for consuming
            chunks (and for any fallback). Used by the MoA aggregator so its
@@ -7260,9 +7058,7 @@ def call_llm(
        temperature=temperature, max_tokens=max_tokens,
        tools=tools, timeout=effective_timeout, extra_body=effective_extra_body,
        reasoning_config=reasoning_config,
-        base_url=_base_info or resolved_base_url, task=task)
-    if extra_headers:
-        kwargs["extra_headers"] = dict(extra_headers)
+        base_url=_base_info or resolved_base_url)

    # Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
    _client_base = str(getattr(client, "base_url", "") or "")
@@ -7516,7 +7312,6 @@ def call_llm(
                    effective_timeout=effective_timeout,
                    effective_extra_body=effective_extra_body,
                    reasoning_config=reasoning_config,
-                    extra_headers=extra_headers,
                )

        # ── Same-provider credential-pool recovery ─────────────────────
@@ -7560,7 +7355,6 @@ def call_llm(
                        effective_timeout=effective_timeout,
                        effective_extra_body=effective_extra_body,
                        reasoning_config=reasoning_config,
-                        extra_headers=extra_headers,
                    )
                except Exception as retry2_err:
                    # The rotated key also hit a quota/auth wall.  Mark it
@@ -7880,7 +7674,7 @@ async def async_call_llm(
        temperature=temperature, max_tokens=max_tokens,
        tools=tools, timeout=effective_timeout, extra_body=effective_extra_body,
        reasoning_config=reasoning_config,
-        base_url=_client_base or resolved_base_url, task=task)
+        base_url=_client_base or resolved_base_url)

    # Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
    if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
@@ -1,131 +0,0 @@
-"""System-battery read-out for the CLI/TUI status bar.
-
-Reads the host battery through ``psutil`` (already a Hermes dependency) and
-exposes a compact, colour-coded label.  Everything degrades to "unavailable"
-when there is no battery (desktops, servers, VMs) or when the read fails, so
-callers can render the result unconditionally and simply show nothing.
-
-The status bar repaints often (every keystroke and on a ~1s idle refresh), so
-:func:`read_battery` memoises the last reading for a few seconds instead of
-hitting ``psutil`` on every frame.
-"""
-
-from __future__ import annotations
-
-import time
-from dataclasses import dataclass
-from typing import Optional
-
-
-@dataclass(frozen=True)
-class BatteryStatus:
-    """A single battery reading.
-
-    ``available`` is False on machines without a battery (or when the read
-    failed).  ``percent`` is clamped to 0-100.  ``plugged`` is True when on AC
-    power, False on battery, and None when the platform can't tell.
-    """
-
-    available: bool
-    percent: Optional[int] = None
-    plugged: Optional[bool] = None
-
-    @property
-    def charging(self) -> bool:
-        return bool(self.plugged)
-
-
-UNAVAILABLE = BatteryStatus(available=False)
-
-# Colour buckets, mirroring the status-bar context styles but inverted (a full
-# battery is "good", an empty one is "critical").
-CATEGORY_GOOD = "good"
-CATEGORY_WARN = "warn"
-CATEGORY_BAD = "bad"
-CATEGORY_CRITICAL = "critical"
-CATEGORY_DIM = "dim"
-
-_CACHE_TTL_SECONDS = 8.0
-_cache: Optional[tuple[float, BatteryStatus]] = None
-
-
-def _read_battery_uncached() -> BatteryStatus:
-    try:
-        import psutil
-    except Exception:
-        return UNAVAILABLE
-
-    # ``sensors_battery`` is missing on some platforms/builds of psutil.
-    reader = getattr(psutil, "sensors_battery", None)
-    if reader is None:
-        return UNAVAILABLE
-
-    try:
-        batt = reader()
-    except Exception:
-        return UNAVAILABLE
-
-    if batt is None:
-        return UNAVAILABLE
-
-    percent: Optional[int] = None
-    raw_percent = getattr(batt, "percent", None)
-    if raw_percent is not None:
-        try:
-            percent = max(0, min(100, int(round(float(raw_percent)))))
-        except (TypeError, ValueError):
-            percent = None
-
-    plugged = getattr(batt, "power_plugged", None)
-    if plugged is not None:
-        plugged = bool(plugged)
-
-    return BatteryStatus(available=True, percent=percent, plugged=plugged)
-
-
-def read_battery(use_cache: bool = True) -> BatteryStatus:
-    """Return the current battery status (cached for a few seconds)."""
-    global _cache
-    if use_cache and _cache is not None:
-        ts, cached = _cache
-        if time.monotonic() - ts < _CACHE_TTL_SECONDS:
-            return cached
-
-    status = _read_battery_uncached()
-    _cache = (time.monotonic(), status)
-    return status
-
-
-def clear_cache() -> None:
-    """Drop the memoised reading (used by tests)."""
-    global _cache
-    _cache = None
-
-
-def battery_category(status: BatteryStatus) -> str:
-    """Bucket a reading into a colour category: good/warn/bad/critical/dim."""
-    if not status.available or status.percent is None:
-        return CATEGORY_DIM
-    # On AC power the level isn't a concern — always read as healthy.
-    if status.charging:
-        return CATEGORY_GOOD
-    pct = status.percent
-    if pct <= 10:
-        return CATEGORY_CRITICAL
-    if pct <= 20:
-        return CATEGORY_BAD
-    if pct <= 50:
-        return CATEGORY_WARN
-    return CATEGORY_GOOD
-
-
-def battery_glyph(status: BatteryStatus) -> str:
-    """Return the leading glyph: a bolt while charging, else a battery."""
-    return "\u26a1" if status.charging else "\U0001f50b"  # ⚡ / 🔋
-
-
-def format_battery(status: BatteryStatus) -> str:
-    """Return a compact label like ``🔋 82%`` / ``⚡ 82%`` (empty if N/A)."""
-    if not status.available or status.percent is None:
-        return ""
-    return f"{battery_glyph(status)} {status.percent}%"
@@ -433,29 +433,6 @@ def _model_supports_tool_use(model_id: str) -> bool:
    return not any(pattern in model_lower for pattern in _NON_TOOL_CALLING_PATTERNS)


-# ---------------------------------------------------------------------------
-# Prompt-cache capability detection (Converse API cachePoint)
-# ---------------------------------------------------------------------------
-# Claude on Bedrock already gets prompt caching through the AnthropicBedrock
-# SDK path (see is_anthropic_bedrock_model / runtime_provider.py's dual-path
-# routing) — it never reaches build_converse_kwargs unless bearer-token auth
-# forces the Converse path (#28156). This allowlist covers the Converse API
-# itself: sending an unsupported model a cachePoint block raises a
-# ValidationException, so — like _model_supports_tool_use but inverted —
-# unknown models default to NOT receiving cache markers until confirmed.
-# Ref: https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html
-_CACHE_POINT_PATTERNS = [
-    "anthropic.claude",  # bearer-token fallback path
-    "amazon.nova",
-]
-
-
-def _model_supports_prompt_cache(model_id: str) -> bool:
-    """Return True if the model accepts a Converse API cachePoint block."""
-    model_lower = model_id.lower()
-    return any(pattern in model_lower for pattern in _CACHE_POINT_PATTERNS)
-
-
 def is_anthropic_bedrock_model(model_id: str) -> bool:
    """Return True if the model is an Anthropic Claude model on Bedrock.

@@ -787,22 +764,14 @@ def normalize_converse_response(response: Dict) -> SimpleNamespace:
        reasoning_content="\n\n".join(reasoning_parts) if reasoning_parts else None,
    )

-    # Build usage stats. Converse's inputTokens excludes cache read/write
-    # tokens (unlike OpenAI's prompt_tokens, which includes them) — restore
-    # the OpenAI-style "total includes cache" convention here so downstream
-    # normalize_usage() can subtract them back out consistently, and surface
-    # the Anthropic-named fields it already falls back to for cache reads.
+    # Build usage stats
    usage_data = response.get("usage", {})
-    input_tokens = usage_data.get("inputTokens", 0)
-    cache_read_tokens = usage_data.get("cacheReadInputTokens", 0)
-    cache_write_tokens = usage_data.get("cacheWriteInputTokens", 0)
-    output_tokens = usage_data.get("outputTokens", 0)
    usage = SimpleNamespace(
-        prompt_tokens=input_tokens + cache_read_tokens + cache_write_tokens,
-        completion_tokens=output_tokens,
-        total_tokens=input_tokens + cache_read_tokens + cache_write_tokens + output_tokens,
-        cache_read_input_tokens=cache_read_tokens,
-        cache_creation_input_tokens=cache_write_tokens,
+        prompt_tokens=usage_data.get("inputTokens", 0),
+        completion_tokens=usage_data.get("outputTokens", 0),
+        total_tokens=(
+            usage_data.get("inputTokens", 0) + usage_data.get("outputTokens", 0)
+        ),
    )

    finish_reason = _converse_stop_reason_to_openai(stop_reason)
@@ -967,8 +936,6 @@ def stream_converse_with_callbacks(
            usage_data = {
                "inputTokens": meta_usage.get("inputTokens", 0),
                "outputTokens": meta_usage.get("outputTokens", 0),
-                "cacheReadInputTokens": meta_usage.get("cacheReadInputTokens", 0),
-                "cacheWriteInputTokens": meta_usage.get("cacheWriteInputTokens", 0),
            }

    # Flush remaining text
@@ -982,16 +949,12 @@ def stream_converse_with_callbacks(
        reasoning_content="\n\n".join(reasoning_parts) if reasoning_parts else None,
    )

-    input_tokens = usage_data.get("inputTokens", 0)
-    cache_read_tokens = usage_data.get("cacheReadInputTokens", 0)
-    cache_write_tokens = usage_data.get("cacheWriteInputTokens", 0)
-    output_tokens = usage_data.get("outputTokens", 0)
    usage = SimpleNamespace(
-        prompt_tokens=input_tokens + cache_read_tokens + cache_write_tokens,
-        completion_tokens=output_tokens,
-        total_tokens=input_tokens + cache_read_tokens + cache_write_tokens + output_tokens,
-        cache_read_input_tokens=cache_read_tokens,
-        cache_creation_input_tokens=cache_write_tokens,
+        prompt_tokens=usage_data.get("inputTokens", 0),
+        completion_tokens=usage_data.get("outputTokens", 0),
+        total_tokens=(
+            usage_data.get("inputTokens", 0) + usage_data.get("outputTokens", 0)
+        ),
    )

    finish_reason = _converse_stop_reason_to_openai(stop_reason)
@@ -1030,7 +993,6 @@ def build_converse_kwargs(
    Converts OpenAI-format inputs to Converse API parameters.
    """
    system_prompt, converse_messages = convert_messages_to_converse(messages)
-    cache_enabled = _model_supports_prompt_cache(model)

    kwargs: Dict[str, Any] = {
        "modelId": model,
@@ -1041,8 +1003,6 @@ def build_converse_kwargs(
    }

    if system_prompt:
-        if cache_enabled:
-            system_prompt = system_prompt + [{"cachePoint": {"type": "default"}}]
        kwargs["system"] = system_prompt

    from agent.anthropic_adapter import _forbids_sampling_params
@@ -1066,8 +1026,6 @@ def build_converse_kwargs(
            # Strip tools for known non-tool-calling models and warn the user.
            # Ref: PR #7920 feedback from @ptlally, pattern from PR #4346.
            if _model_supports_tool_use(model):
-                if cache_enabled:
-                    converse_tools = converse_tools + [{"cachePoint": {"type": "default"}}]
                kwargs["toolConfig"] = {"tools": converse_tools}
            else:
                logger.warning(
@@ -1075,14 +1033,6 @@ def build_converse_kwargs(
                    "The agent will operate in text-only mode.", model
                )

-    if cache_enabled and len(converse_messages) >= 2:
-        # Checkpoint everything up to (not including) the newest turn, so the
-        # marker survives unchanged across requests as only the tail grows —
-        # mirroring the Anthropic system_and_3 strategy in prompt_caching.py.
-        content = converse_messages[-2].get("content")
-        if isinstance(content, list) and content:
-            content.append({"cachePoint": {"type": "default"}})
-
    if guardrail_config:
        kwargs["guardrailConfig"] = guardrail_config

@@ -1,124 +0,0 @@
-"""Provider-agnostic billing/credit recovery links.
-
-Maps a billing-classified failure onto a recovery link + label. *Detection*
-is not done here — that is :mod:`agent.error_classifier`
-(``FailoverReason.billing``), the single source of truth for "credit wall vs.
-rate limit / auth / transport". The resulting :class:`BillingBlock` rides the
-turn result and the gateway ``message.complete`` event so every surface (CLI,
-TUI, desktop) renders one structured signal instead of re-parsing error text.
-"""
-
-from __future__ import annotations
-
-from dataclasses import asdict, dataclass
-from typing import Optional
-
-from utils import base_url_host_matches
-
-
-@dataclass
-class BillingBlock:
-    """Structured billing-wall descriptor shared across every surface.
-
-    ``is_nous`` is the routing bit: Nous has a first-class in-app billing surface
-    (desktop Settings → Billing, TUI/CLI ``/topup``), so surfaces prefer that over
-    ``billing_url``; third-party providers have no in-app flow, so ``billing_url``
-    is the deep link the user actually needs.
-    """
-
-    provider: str
-    provider_label: str
-    model: str
-    billing_url: Optional[str]
-    is_nous: bool
-    message: str
-
-    def to_dict(self) -> dict:
-        return asdict(self)
-
-
-@dataclass(frozen=True)
-class _Provider:
-    label: str
-    url: str
-    slugs: tuple[str, ...]
-    hosts: tuple[str, ...] = ()
-
-
-# Single source of truth: internal slug(s) + base_url host(s) → billing page.
-# Curated "add credits / manage billing" landing pages, not marketing homes.
-# Hosts back the OpenAI-compatible fallback where the slug is a generic bucket
-# (e.g. "openai_compatible") but base_url reveals the real upstream. An unknown
-# provider degrades to a readable label with no invented URL.
-_PROVIDERS: tuple[_Provider, ...] = (
-    _Provider("OpenAI", "https://platform.openai.com/settings/organization/billing", ("openai",), ("api.openai.com",)),
-    _Provider("Anthropic", "https://console.anthropic.com/settings/billing", ("anthropic",), ("api.anthropic.com",)),
-    _Provider("OpenRouter", "https://openrouter.ai/settings/credits", ("openrouter",), ("openrouter.ai",)),
-    _Provider("xAI", "https://console.x.ai/team/default/billing", ("xai", "xai-oauth"), ("api.x.ai",)),
-    _Provider("DeepSeek", "https://platform.deepseek.com/top_up", ("deepseek",), ("api.deepseek.com",)),
-    _Provider("Groq", "https://console.groq.com/settings/billing", ("groq",), ("api.groq.com",)),
-    _Provider("Mistral", "https://console.mistral.ai/billing", ("mistral",), ("api.mistral.ai",)),
-    _Provider("Together AI", "https://api.together.ai/settings/billing", ("together",), ("api.together.ai", "api.together.xyz")),
-    _Provider("Fireworks AI", "https://fireworks.ai/account/billing", ("fireworks",), ("fireworks.ai",)),
-    _Provider("Perplexity", "https://www.perplexity.ai/settings/api", ("perplexity",), ("perplexity.ai",)),
-    _Provider("Google AI", "https://aistudio.google.com/app/billing", ("google", "gemini"), ("generativelanguage.googleapis.com",)),
-    _Provider("Cohere", "https://dashboard.cohere.com/billing", ("cohere",)),
-    _Provider("Moonshot AI", "https://platform.moonshot.ai/console/pay", ("moonshot",)),
-    _Provider("NVIDIA", "https://build.nvidia.com/settings/billing", ("nvidia",)),
-)
-
-_BY_SLUG: dict[str, _Provider] = {slug: p for p in _PROVIDERS for slug in p.slugs}
-
-
-def is_nous_inference_route(provider: str, base_url: str) -> bool:
-    """True when the failing route is the Nous-managed inference gateway."""
-    if (provider or "").strip().lower() == "nous":
-        return True
-    return base_url_host_matches(str(base_url or ""), "inference-api.nousresearch.com")
-
-
-def _nous_billing_url() -> Optional[str]:
-    """Best-effort Nous portal billing URL (text-surface fallback; Nous prefers the in-app flow)."""
-    try:
-        from hermes_cli.nous_account import nous_portal_billing_url
-
-        return nous_portal_billing_url(None)
-    except Exception:
-        return "https://portal.nousresearch.com/billing"
-
-
-def _resolve_provider_link(slug: str, base_url: str) -> tuple[str, Optional[str]]:
-    """Resolve ``(label, url)``: exact slug → base_url host → readable-label fallback."""
-    hit = _BY_SLUG.get(slug)
-    if hit:
-        return hit.label, hit.url
-
-    base = str(base_url or "")
-    for p in _PROVIDERS:
-        if any(base_url_host_matches(base, host) for host in p.hosts):
-            return p.label, p.url
-
-    return slug.replace("_", " ").replace("-", " ").strip().title() or "your provider", None
-
-
-def build_billing_block(
-    *,
-    provider: str,
-    base_url: str,
-    model: str,
-    message: str = "",
-) -> BillingBlock:
-    """Build the billing descriptor for a billing-classified failure.
-
-    ``message`` is the guidance already assembled by the agent loop
-    (:func:`agent.conversation_loop._billing_or_entitlement_message`), carried
-    through unchanged so every surface shows identical copy.
-    """
-    slug = (provider or "").strip().lower()
-    model = (model or "").strip()
-
-    if is_nous_inference_route(slug, base_url):
-        return BillingBlock(slug or "nous", "Nous Portal", model, _nous_billing_url(), True, message or "")
-
-    label, url = _resolve_provider_link(slug, base_url)
-    return BillingBlock(slug, label, model, url, False, message or "")
@@ -1712,7 +1712,6 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
        agent._config_context_length = None
        agent.model = fb_model
        agent.provider = fb_provider
-        agent.requested_provider = fb_provider
        agent.base_url = fb_base_url
        agent.api_mode = fb_api_mode
        if hasattr(agent, "_transport_cache"):
@@ -1946,17 +1945,7 @@ def handle_max_iterations(agent, messages: list, api_call_count: int) -> str:
            for internal_key in [k for k in api_msg if isinstance(k, str) and k.startswith("_")]:
                api_msg.pop(internal_key, None)
            if _needs_sanitize:
-                # In MoA mode, agent.model is the virtual preset name,
-                # not the actual aggregator model.  Resolve the real
-                # aggregator model so Gemini preserves thought_signature.
-                _sanitize_model = agent.model
-                if agent.provider == "moa":
-                    _moa_client = getattr(agent, "client", None)
-                    if _moa_client is not None:
-                        _agg_slot = getattr(_moa_client, "last_aggregator_slot", None)
-                        if _agg_slot and _agg_slot.get("model"):
-                            _sanitize_model = _agg_slot["model"]
-                agent._sanitize_tool_calls_for_strict_api(api_msg, model=_sanitize_model)
+                agent._sanitize_tool_calls_for_strict_api(api_msg, model=agent.model)
            api_messages.append(api_msg)

        effective_system = agent._cached_system_prompt or ""
@@ -2473,11 +2462,7 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
    request_client_holder = {"client": None, "diag": None, "owner_tid": None}
    # Transport kind of the registered request client — see the non-streaming
    # variant. Routes _close_request_client_once to anthropic vs openai abort/
-    # close helpers (#67142). ``kind="stream"`` registers a per-request
-    # *stream handle* instead of a client — used under the MoA facade, whose
-    # singleton client has no per-request sockets to abort
-    # (_abort_request_openai_client is a no-op on it), so interrupts must
-    # close the stream object itself (#57354).
+    # close helpers (#67142).
    request_client_kind = {"value": "openai"}
    request_client_lock = threading.Lock()
    # Request-local cancellation flag — see interruptible_api_call for the full
@@ -2497,44 +2482,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
            request_client_holder["owner_tid"] = threading.get_ident()
        return client

-    def _stream_close_callable(stream):
-        close = getattr(stream, "close", None)
-        if callable(close):
-            return close
-        response = getattr(stream, "response", None)
-        close = getattr(response, "close", None)
-        if callable(close):
-            return close
-        return None
-
-    def _set_request_stream_handle(stream):
-        # Register the per-request *stream* under kind="stream" so an
-        # interrupt closes the stream handle itself. Under the MoA facade the
-        # registered "client" is the shared facade singleton whose
-        # per-request abort helpers are no-ops, leaving the underlying HTTP
-        # stream open until the provider drained it (#57354).
-        if _stream_close_callable(stream) is None:
-            return stream
-        with request_client_lock:
-            request_client_holder["client"] = stream
-            request_client_kind["value"] = "stream"
-            request_client_holder["owner_tid"] = threading.get_ident()
-        return stream
-
-    def _close_request_stream_handle(stream, reason: str) -> None:
-        close = _stream_close_callable(stream)
-        if close is None:
-            return
-        try:
-            close()
-            logger.info("Streaming response handle closed (%s)", reason)
-        except Exception as exc:
-            logger.debug(
-                "Streaming response handle close failed (%s): %s",
-                reason,
-                exc,
-            )
-
    def _close_request_client_once(reason: str) -> None:
        # See #29507 explanation in the non-streaming variant above. A
        # stranger thread (the interrupt-check / stale-stream detector loop)
@@ -2542,15 +2489,9 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
        # so the worker thread retains ownership of the FD release.
        with request_client_lock:
            request_client = request_client_holder.get("client")
-            request_kind = request_client_kind.get("value", "openai")
            owner_tid = request_client_holder.get("owner_tid")
-            # A registered stream handle (kind="stream", MoA facade path) is
-            # safe to close from any thread — closing IS the abort — so the
-            # stranger-thread ownership carve-out only applies to real
-            # per-request clients (#57354).
            stranger_thread = (
-                request_kind != "stream"
-                and request_client is not None
+                request_client is not None
                and owner_tid is not None
                and owner_tid != threading.get_ident()
            )
@@ -2559,9 +2500,8 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
                request_client_holder["owner_tid"] = None
        if request_client is None:
            return
-        if request_kind == "stream":
-            _close_request_stream_handle(request_client, reason)
-        elif request_kind == "anthropic_messages":
+        kind = request_client_kind.get("value", "openai")
+        if kind == "anthropic_messages":
            if stranger_thread:
                agent._abort_request_anthropic_client(request_client, reason=reason)
            else:
@@ -2740,11 +2680,6 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
        _diag = agent._stream_diag_init()
        request_client_holder["diag"] = _diag
        stream = request_client.chat.completions.create(**stream_kwargs)
-        if agent.provider == "moa":
-            # The MoA facade is a shared singleton — abort/close of the
-            # registered client is a no-op, so register the stream handle
-            # itself for interrupt teardown (#57354).
-            stream = _set_request_stream_handle(stream)
        # Claim the delta sink for THIS attempt (#65991). If a prior attempt's
        # stream is somehow still alive (a stale-stream reconnect whose socket
        # abort raced), this claim supersedes it so its late chunks are fenced
@@ -702,16 +702,6 @@ def run_codex_app_server_turn(
        except Exception:
            pass
        agent._codex_session = None
-        _user_interrupted = bool(
-            getattr(agent, "_interrupt_requested", False)
-        )
-        _interrupt_message = (
-            getattr(agent, "_interrupt_message", None)
-            if _user_interrupted
-            else None
-        )
-        if _user_interrupted:
-            agent.clear_interrupt()
        return {
            "final_response": (
                f"Codex app-server turn failed: {exc}. "
@@ -721,27 +711,9 @@ def run_codex_app_server_turn(
            "api_calls": 0,
            "completed": False,
            "partial": True,
-            "interrupted": _user_interrupted,
-            **(
-                {"interrupt_message": _interrupt_message}
-                if _interrupt_message
-                else {}
-            ),
            "error": str(exc),
        }

-    # This runtime bypasses the normal conversation-loop finalizer. Mirror its
-    # interrupt handoff/cleanup so a hard stop cannot poison the next turn and a
-    # message-bearing compatibility interrupt can still be replayed by callers.
-    _user_interrupted = bool(
-        turn.interrupted and getattr(agent, "_interrupt_requested", False)
-    )
-    _interrupt_message = (
-        getattr(agent, "_interrupt_message", None) if _user_interrupted else None
-    )
-    if _user_interrupted:
-        agent.clear_interrupt()
-
    # If the turn signalled the underlying client is wedged (deadline
    # blown, post-tool watchdog tripped, OAuth refresh died, subprocess
    # exited), retire the session so the next turn respawns codex
@@ -847,12 +819,6 @@ def run_codex_app_server_turn(
        "api_calls": api_calls,
        "completed": not turn.interrupted and turn.error is None,
        "partial": turn.interrupted or turn.error is not None,
-        "interrupted": _user_interrupted,
-        **(
-            {"interrupt_message": _interrupt_message}
-            if _interrupt_message
-            else {}
-        ),
        "error": turn.error,
        # The codex app-server runtime IS an early-return path that bypasses
        # conversation_loop, but we flush the projected assistant/tool messages
@@ -55,12 +55,13 @@ import json
 import logging
 import os
 import re
+import subprocess
 import tempfile
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Optional

-from hermes_cli._subprocess_compat import bounded_git_probe
+from hermes_cli._subprocess_compat import IS_WINDOWS, windows_hide_flags

 logger = logging.getLogger("hermes.coding_context")

@@ -688,14 +689,18 @@ def _enabled_mcp_servers(config: Optional[dict[str, Any]]) -> list[str]:


 def _git(cwd: Path, *args: str) -> str:
-    """``git -C <cwd> <args>`` → stripped stdout, or ``""`` on any failure.
-
-    Uses the shared :func:`bounded_git_probe` so the post-kill cleanup is bounded
-    on Windows — a plain ``subprocess.run(timeout=...)`` here deadlocked the agent
-    turn inside ``build_coding_workspace_block`` when a killed git left a suspended
-    descendant holding the pipe handles (issue #66037).
-    """
-    return bounded_git_probe(["git", "-C", str(cwd), *args], timeout=_GIT_TIMEOUT)
+    _popen_kwargs = {"creationflags": windows_hide_flags()} if IS_WINDOWS else {}
+    try:
+        out = subprocess.run(
+            ["git", "-C", str(cwd), *args],
+            capture_output=True,
+            text=True,
+            timeout=_GIT_TIMEOUT,
+            **_popen_kwargs,
+        )
+    except (OSError, subprocess.SubprocessError):
+        return ""
+    return out.stdout.strip() if out.returncode == 0 else ""


 def _parse_status(porcelain: str) -> tuple[dict[str, str], dict[str, int]]:
@@ -53,39 +53,6 @@ def sanitize_memory_context(memory_context: str) -> str:
    )


-def automatic_compaction_status_message(
-    engine: Any,
-    *,
-    phase: str,
-    default_message: str,
-    **context: Any,
-) -> str | None:
-    """Resolve host-visible status for an automatic compaction event.
-
-    Engines can suppress routine automatic status with
-    ``emit_automatic_compaction_status = False`` or customize it by defining
-    ``get_automatic_compaction_status_message(...)``. Empty strings and
-    ``None`` mean "do not emit a lifecycle status".
-    """
-    if not getattr(engine, "emit_automatic_compaction_status", True):
-        return None
-
-    formatter = getattr(engine, "get_automatic_compaction_status_message", None)
-    if callable(formatter):
-        message = formatter(
-            phase=phase,
-            default_message=default_message,
-            **context,
-        )
-    else:
-        message = default_message
-
-    if message is None:
-        return None
-    message = str(message).strip()
-    return message or None
-
-
 class ContextEngine(ABC):
    """Base class all context engines must implement."""

@@ -122,12 +89,6 @@ class ContextEngine(ABC):
    protect_first_n: int = 3
    protect_last_n: int = 6

-    # User-visible lifecycle status for automatic host-triggered compaction.
-    # Alternative engines that treat compaction as routine background
-    # maintenance can set this false to keep successful automatic passes silent;
-    # warnings, errors, and explicit manual commands should still surface.
-    emit_automatic_compaction_status: bool = True
-
    # -- Core interface ----------------------------------------------------

    @abstractmethod
@@ -146,19 +107,6 @@ class ContextEngine(ABC):
    def should_compress(self, prompt_tokens: int = None) -> bool:
        """Return True if compaction should fire this turn."""

-    def should_compress_info(self, prompt_tokens: int = None) -> "tuple[bool, str | None]":
-        """Return ``(should_compress, reason)``.
-
-        The base implementation is backward-compatible: engines that only
-        implement ``should_compress`` get ``(should_compress(prompt_tokens),
-        None)``. Concrete engines with richer block reasons (e.g. a
-        summary-LLM cooldown or an anti-thrashing guard) override this to
-        surface a human-readable reason so callers can warn the user instead
-        of silently skipping compression. Added for the silent-overflow
-        warning fix (#62625) so plugin engines don't raise AttributeError.
-        """
-        return self.should_compress(prompt_tokens), None
-
    @abstractmethod
    def compress(
        self,
@@ -189,144 +137,6 @@ class ContextEngine(ABC):
                host filters unsupported optional arguments by signature.
        """

-    # -- Optional: proactive tool-result prune -----------------------------
-
-    def prune_tool_results_only(
-        self,
-        messages: List[Dict[str, Any]],
-        current_tokens: int | None = None,
-    ) -> tuple[List[Dict[str, Any]], int]:
-        """Deterministically trim old tool-result payloads without an LLM call.
-
-        Runs on a low, cost-oriented trigger independent of ``should_compress``
-        so large-window engines can reclaim re-sent tool output long before full
-        compaction would fire. Returns ``(messages, n_pruned)``.
-
-        Default is a safe no-op: the list is returned unchanged with ``0``
-        pruned. Engines that don't implement a cheap prune — and any engine that
-        predates this hook — inherit this default, so the agent loop's
-        post-tool-call prune path never raises ``AttributeError`` on them. The
-        built-in ContextCompressor overrides this with the real implementation.
-        """
-        return messages, 0
-
-    # -- Optional: per-turn context selection (distinct from compression) --
-
-    def select_context(
-        self,
-        request_messages: List[Dict[str, Any]],
-        *,
-        conversation_messages: List[Dict[str, Any]] = None,
-        incoming_message: Dict[str, Any] = None,
-        budget_tokens: int = 0,
-    ) -> List[Dict[str, Any]]:
-        """Optionally choose/replace the context for THIS request, pre-generation.
-
-        Called every turn after the request message list is assembled and
-        before it is dispatched to the provider — independent of
-        ``should_compress()``. This lets an engine *select* which context
-        enters the prompt (retrieval, topic routing, role/branch switching)
-        rather than *shrink* context that is already there. The two verbs are
-        orthogonal:
-
-          - ``compress()``      : context is too long  -> make it shorter.
-          - ``select_context()``: this turn belongs to a different context
-                                  -> use that one instead.
-
-        Without this hook, engines that need per-turn access to the message
-        list have to force ``should_compress()`` to return ``True`` so that
-        ``compress()`` is invoked every turn purely as a callback — which
-        conflates selection with compression and degrades behaviour when the
-        engine's backend is unavailable. ``select_context()`` removes the need
-        for that workaround.
-
-        The returned list is request-only: it replaces the messages sent to
-        the provider for this single call and MUST NOT be treated as persisted
-        transcript state. The conversation history in the session DB is left
-        untouched, so nothing leaks across turns. Return ``None`` to leave the
-        request unchanged.
-
-        Unlike the ``pre_llm_call`` plugin hook (which appends to the user
-        message and intentionally never rewrites the list, to preserve the
-        cache prefix), ``select_context()`` may *replace* the message list.
-
-        Ordering / cache contract: the host runs this hook **before** prompt
-        cache-control and **before** every request sanitizer (orphaned-tool
-        cleanup, thinking-only/role normalization, whitespace/JSON
-        normalization). So (a) whatever the hook returns still passes through
-        the same validation as any request — a malformed replacement cannot
-        reach the provider — and (b) prompt-cache stability (an AGENTS.md
-        invariant) is preserved: the default no-op leaves the request
-        byte-identical, so cache behaviour is unchanged for the built-in
-        compressor and any non-implementing engine. An engine that *does*
-        replace the list changes its own cache prefix by definition; that is
-        the engine's concern, and cache-control breakpoints are re-derived on
-        the selected list. The hook is evaluated per provider request (so it
-        re-runs on retries within a turn), consistent with "select the context
-        for THIS request".
-
-        Args:
-            request_messages: The assembled request message list (system
-                prompt + history + any ephemeral prefill), in OpenAI format.
-            conversation_messages: The unmodified persisted conversation
-                history, for reference only (do not mutate).
-            incoming_message: The current turn's user message, if available.
-            budget_tokens: The active model's context length, or 0 if unknown.
-
-        Default returns ``None`` (no-op) — zero impact on the built-in
-        compressor or any existing engine.
-        """
-        return None
-
-    def on_turn_complete(
-        self,
-        messages: List[Dict[str, Any]],
-        usage: Dict[str, Any] = None,
-        **kwargs: Any,
-    ) -> None:
-        """Observe a finished user turn (post-turn ingestion / observation).
-
-        Called from the standard turn-finalization path once the assistant/tool
-        loop completes, with the finalized in-memory transcript snapshot. This
-        is the complement to ``select_context()``: selection happens *before*
-        the request, while observation happens *after* the turn. It lets an
-        engine ingest, index, summarize, or update routing / topic / session
-        state from what actually happened — so the next ``select_context()``
-        can act on it.
-
-        Coverage: this fires from the normal finalization seam. Some abnormal
-        early-return paths in the loop (e.g. a content-policy block or a
-        provider terminal failure) persist and return without routing through
-        finalization, and therefore do not currently emit this hook. Treat it
-        as a best-effort post-turn observation for completed turns, not a
-        guaranteed callback for every possible early exit; unifying all
-        terminal paths behind one finalization seam is a separate follow-up.
-
-        Together the two hooks remove the need to abuse ``should_compress()`` /
-        ``compress()`` as a generic per-turn callback just to observe history,
-        and they cover the case where a turn finishes and there may be no next
-        request from which to infer the previous turn.
-
-        ``messages`` is a shallow copy and should be treated as read-only:
-        return values are ignored and this hook must not rely on transcript
-        mutation for persistence. ``kwargs`` may include ``turn_id``,
-        ``task_id``, ``api_call_count``, ``interrupted``, ``failed``, and
-        ``turn_exit_reason``.
-
-        ``usage`` carries the completed turn's canonical token usage (the same
-        dict shape passed to ``update_from_response`` — ``prompt_tokens`` /
-        ``completion_tokens`` / ``total_tokens`` plus the canonical
-        ``input_tokens`` / ``output_tokens`` / ``cache_read_tokens`` /
-        ``cache_write_tokens`` / ``reasoning_tokens`` buckets) so an engine can
-        weigh how large/expensive the selected context actually was when
-        deciding the next ``select_context()``. It is ``None`` on finalized
-        turns that never reached a provider response (e.g. interrupt); engines
-        must treat it as optional.
-
-        Default is a no-op.
-        """
-        return None
-
    # -- Optional: pre-flight check ----------------------------------------

    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
@@ -346,27 +156,6 @@ class ContextEngine(ABC):
        """
        return False

-    def get_automatic_compaction_status_message(
-        self,
-        *,
-        phase: str,
-        default_message: str,
-        **context: Any,
-    ) -> str | None:
-        """Return user-visible status for automatic host-triggered compaction.
-
-        Return ``None`` to suppress successful automatic lifecycle status for
-        this compaction event. ``phase`` identifies the host call site (for
-        example ``"preflight"`` or ``"compress"``). ``context`` contains
-        best-effort fields such as ``approx_tokens`` and ``threshold_tokens``.
-
-        This hook does not control warning/error messages or explicit manual
-        commands such as ``/compress``.
-        """
-        if not self.emit_automatic_compaction_status:
-            return None
-        return default_message
-
    # -- Optional: manual /compress preflight ------------------------------

    def has_content_to_compress(self, messages: List[Dict[str, Any]]) -> bool:
@@ -471,19 +260,4 @@ class ContextEngine(ABC):
        (e.g. recalculate DAG budgets, switch summary models).
        """
        self.context_length = context_length
-        # Apply per-model threshold overrides if set (longest substring match).
-        # Falls back to _config_threshold_percent (the raw config value) when
-        # no override matches. Plugin engines that override update_model() can
-        # call resolve_model_threshold() for the same logic.
-        from agent.context_compressor import resolve_model_threshold
-        if not hasattr(self, "_config_threshold_percent"):
-            # Snapshot the pre-override percent ONCE so repeated model
-            # switches fall back to the engine's configured value, not the
-            # previous model's override.
-            self._config_threshold_percent = self.threshold_percent
-        self._base_threshold_percent = resolve_model_threshold(
-            model, getattr(self, "model_thresholds", {}),
-            self._config_threshold_percent,
-        )
-        self.threshold_percent = self._base_threshold_percent
        self.threshold_tokens = int(context_length * self.threshold_percent)
@@ -503,10 +503,6 @@ class CopilotACPClient:

    def _run_prompt(self, prompt_text: str, *, timeout_seconds: float) -> tuple[str, str]:
        try:
-            # Hide the console the CLI child would otherwise flash on Windows
-            # (#56747). Hide-only — stdio pipes stay intact for the ACP wire.
-            from hermes_cli._subprocess_compat import windows_hide_flags
-
            proc = subprocess.Popen(
                [self._acp_command] + self._acp_args,
                stdin=subprocess.PIPE,
@@ -516,7 +512,6 @@ class CopilotACPClient:
                bufsize=1,
                cwd=self._acp_cwd,
                env=_build_subprocess_env(),
-                creationflags=windows_hide_flags(),
            )
        except FileNotFoundError as exc:
            raise RuntimeError(
@@ -596,32 +596,20 @@ class CredentialPool:
        self._last_no_entries_log_at: Optional[float] = None

    def has_credentials(self) -> bool:
-        with self._lock:
-            return bool(self._entries)
+        return bool(self._entries)

    def has_available(self) -> bool:
        """True if at least one entry is not currently in exhaustion cooldown."""
-        # ``_available_entries`` is not read-only: it prunes aged-out DEAD
-        # manual entries (rebinding ``self._entries``) and persists.  It must
-        # run under ``self._lock`` like every other caller (``select`` etc.),
-        # otherwise a status probe here can race a concurrent ``select`` /
-        # rotation and tear ``self._entries`` or double-write auth.json.
-        with self._lock:
-            return bool(self._available_entries())
+        return bool(self._available_entries())

    def entries(self) -> List[PooledCredential]:
-        with self._lock:
-            return list(self._entries)
+        return list(self._entries)

-    def _current_unlocked(self) -> Optional[PooledCredential]:
+    def current(self) -> Optional[PooledCredential]:
        if not self._current_id:
            return None
        return next((entry for entry in self._entries if entry.id == self._current_id), None)

-    def current(self) -> Optional[PooledCredential]:
-        with self._lock:
-            return self._current_unlocked()
-
    def _replace_entry(self, old: PooledCredential, new: PooledCredential) -> None:
        """Swap an entry in-place by id, preserving sort order."""
        for idx, entry in enumerate(self._entries):
@@ -664,8 +652,6 @@ class CredentialPool:
        entry: PooledCredential,
        status_code: Optional[int],
        error_context: Optional[Dict[str, Any]] = None,
-        *,
-        persist: bool = True,
    ) -> PooledCredential:
        normalized_error = _normalize_error_context(error_context)
        # Permanent OAuth failures (token_invalidated, token_revoked, etc.)
@@ -689,8 +675,7 @@ class CredentialPool:
            last_error_reset_at=normalized_error.get("reset_at"),
        )
        self._replace_entry(entry, updated)
-        if persist:
-            self._persist()
+        self._persist()
        return updated

    def _sync_anthropic_entry_from_credentials_file(self, entry: PooledCredential) -> PooledCredential:
@@ -1499,43 +1484,6 @@ class CredentialPool:
        self._sync_device_code_entry_to_auth_store(updated)
        return updated

-    def _codex_quota_restored_upstream(self, entry: PooledCredential) -> bool:
-        """Live-check whether an exhausted Codex entry's quota reset early.
-
-        A Codex 429 persists a ``last_error_reset_at`` that can be days in
-        the future (weekly windows), but the upstream window can reopen
-        before then — the user redeems a banked rate-limit reset via the
-        Codex CLI / ChatGPT UI, upgrades their plan, or OpenAI resets the
-        window.  Without this check the pool keeps the credential frozen
-        until the stale timestamp elapses even though the account is
-        usable (issue #43747).
-
-        Only fires for openai-codex entries frozen by a 429/quota-shaped
-        error.  The underlying probe is throttled per token (5 min) so this
-        is safe on the hot selection path.
-        """
-        if self.provider != "openai-codex" or entry.last_status != STATUS_EXHAUSTED:
-            return False
-        if not auth_mod._is_codex_rate_limit_shaped(
-            entry.last_error_code,
-            entry.last_error_reason,
-            entry.last_error_message,
-        ):
-            return False
-        token = entry.access_token or ""
-        if not token:
-            return False
-        try:
-            return bool(
-                auth_mod._probe_codex_quota_restored(
-                    token,
-                    base_url=entry.base_url,
-                )
-            )
-        except Exception:
-            logger.debug("Codex quota-restored probe failed", exc_info=True)
-            return False
-
    def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
        if entry.auth_type != AUTH_TYPE_OAUTH:
            return False
@@ -1657,18 +1605,7 @@ class CredentialPool:
            if entry.last_status == STATUS_EXHAUSTED:
                exhausted_until = _exhausted_until(entry)
                if exhausted_until is not None and now < exhausted_until:
-                    # Codex quota windows can reopen EARLY: the user redeems a
-                    # banked rate-limit reset (Codex CLI / ChatGPT UI), upgrades
-                    # their plan, or OpenAI resets the window.  The persisted
-                    # ``last_error_reset_at`` can then be days in the future
-                    # while the account is already usable again — a throttled
-                    # live probe of the Codex usage endpoint detects that and
-                    # lifts the stale cooldown (issue #43747).
-                    if not (
-                        clear_expired
-                        and self._codex_quota_restored_upstream(entry)
-                    ):
-                        continue
+                    continue
                if clear_expired:
                    cleared = replace(
                        entry,
@@ -1741,21 +1678,18 @@ class CredentialPool:
            self._entries = [replace(candidate, priority=idx) for idx, candidate in enumerate(rotated)]
            self._persist()
            self._current_id = entry.id
-            return self._current_unlocked() or entry
+            return self.current() or entry

        entry = available[0]
        self._current_id = entry.id
        return entry

    def peek(self) -> Optional[PooledCredential]:
-        # Single lock acquisition for the whole read; call the unlocked
-        # helpers so we don't re-enter the non-reentrant ``self._lock``.
-        with self._lock:
-            current = self._current_unlocked()
-            if current is not None:
-                return current
-            available = self._available_entries()
-            return available[0] if available else None
+        current = self.current()
+        if current is not None:
+            return current
+        available = self._available_entries()
+        return available[0] if available else None

    def mark_exhausted_and_rotate(
        self,
@@ -1775,49 +1709,12 @@ class CredentialPool:
                    (e for e in self._entries if e.runtime_api_key == api_key_hint),
                    None,
                )
-                if entry is None:
-                    # The failed key is identifiable but matches no entry
-                    # (rotated away, or a wrapper whose runtime key differs).
-                    # Falling through to current()/_select_unlocked() would
-                    # mark an INNOCENT healthy key exhausted for the full
-                    # cooldown TTL.  Don't guess — just hand back a fresh
-                    # selection so the caller can retry.
-                    logger.info(
-                        "credential pool: failed key hint matched no %s entry; "
-                        "rotating without marking any credential exhausted",
-                        self.provider,
-                    )
-                    self._current_id = None
-                    return self._select_unlocked()
            if entry is None:
-                entry = self._current_unlocked() or self._select_unlocked()
+                entry = self.current() or self._select_unlocked()
            if entry is None:
                return None
            _label = entry.label or entry.id[:8]
            self._mark_exhausted(entry, status_code, error_context)
-            # A 402/429/401 is an API-key–level failure: the account is out of
-            # balance, rate-limited, or its key is rejected.  The same key can
-            # back more than one pool entry (e.g. an explicit pool entry plus a
-            # ``model_config`` entry auto-seeded from ``model.api_key`` — both
-            # carry the identical ``runtime_api_key``).  Marking only the first
-            # match leaves the sibling entries OK, so ``_select_unlocked()``
-            # keeps handing back the same depleted key and rotation never
-            # converges — the caller ``continue``s forever until the client
-            # disconnects (a ~2.5min hang with no error surfaced to the user).
-            # Mark every entry sharing the failed key so the pool can reach the
-            # "no available entries" state and let the error propagate.
-            if api_key_hint:
-                siblings_marked = False
-                for sibling in self._entries:
-                    if sibling.id == entry.id:
-                        continue
-                    if sibling.runtime_api_key == api_key_hint:
-                        self._mark_exhausted(
-                            sibling, status_code, error_context, persist=False
-                        )
-                        siblings_marked = True
-                if siblings_marked:
-                    self._persist()
            # Re-read the updated entry to log the correct terminal state.
            updated_entry = next(
                (e for e in self._entries if e.id == entry.id), entry,
@@ -1907,14 +1804,14 @@ class CredentialPool:
                    None,
                )
            else:
-                entry = self._current_unlocked() or self._select_unlocked(refresh=False)
+                entry = self.current() or self._select_unlocked(refresh=False)
            if entry is None:
                return None
            self._current_id = entry.id
            return self._try_refresh_current_unlocked()

    def _try_refresh_current_unlocked(self) -> Optional[PooledCredential]:
-        entry = self._current_unlocked()
+        entry = self.current()
        if entry is None:
            return None
        refreshed = self._refresh_entry(entry, force=True)
@@ -1923,80 +1820,76 @@ class CredentialPool:
        return refreshed

    def reset_statuses(self) -> int:
-        with self._lock:
-            count = 0
-            new_entries = []
-            for entry in self._entries:
-                if entry.last_status or entry.last_status_at or entry.last_error_code:
-                    new_entries.append(
-                        replace(
-                            entry,
-                            last_status=None,
-                            last_status_at=None,
-                            last_error_code=None,
-                            last_error_reason=None,
-                            last_error_message=None,
-                            last_error_reset_at=None,
-                        )
+        count = 0
+        new_entries = []
+        for entry in self._entries:
+            if entry.last_status or entry.last_status_at or entry.last_error_code:
+                new_entries.append(
+                    replace(
+                        entry,
+                        last_status=None,
+                        last_status_at=None,
+                        last_error_code=None,
+                        last_error_reason=None,
+                        last_error_message=None,
+                        last_error_reset_at=None,
                    )
-                    count += 1
-                else:
-                    new_entries.append(entry)
-            if count:
-                self._entries = new_entries
-                self._persist()
-            return count
+                )
+                count += 1
+            else:
+                new_entries.append(entry)
+        if count:
+            self._entries = new_entries
+            self._persist()
+        return count

    def remove_index(self, index: int) -> Optional[PooledCredential]:
-        with self._lock:
-            if index < 1 or index > len(self._entries):
-                return None
-            removed = self._entries.pop(index - 1)
-            self._entries = [
-                replace(entry, priority=new_priority)
-                for new_priority, entry in enumerate(self._entries)
-            ]
-            write_credential_pool(
-                self.provider,
-                [entry.to_dict() for entry in self._entries],
-                removed_ids=[removed.id],
-            )
-            if self._current_id == removed.id:
-                self._current_id = None
-            return removed
+        if index < 1 or index > len(self._entries):
+            return None
+        removed = self._entries.pop(index - 1)
+        self._entries = [
+            replace(entry, priority=new_priority)
+            for new_priority, entry in enumerate(self._entries)
+        ]
+        write_credential_pool(
+            self.provider,
+            [entry.to_dict() for entry in self._entries],
+            removed_ids=[removed.id],
+        )
+        if self._current_id == removed.id:
+            self._current_id = None
+        return removed

    def resolve_target(self, target: Any) -> Tuple[Optional[int], Optional[PooledCredential], Optional[str]]:
        raw = str(target or "").strip()
        if not raw:
            return None, None, "No credential target provided."

-        with self._lock:
-            for idx, entry in enumerate(self._entries, start=1):
-                if entry.id == raw:
-                    return idx, entry, None
+        for idx, entry in enumerate(self._entries, start=1):
+            if entry.id == raw:
+                return idx, entry, None

-            label_matches = [
-                (idx, entry)
-                for idx, entry in enumerate(self._entries, start=1)
-                if entry.label.strip().lower() == raw.lower()
-            ]
-            if len(label_matches) == 1:
-                return label_matches[0][0], label_matches[0][1], None
-            if len(label_matches) > 1:
-                return None, None, f'Ambiguous credential label "{raw}". Use the numeric index or entry id instead.'
-            if raw.isdigit():
-                index = int(raw)
-                if 1 <= index <= len(self._entries):
-                    return index, self._entries[index - 1], None
-                return None, None, f"No credential #{index}."
-            return None, None, f'No credential matching "{raw}".'
+        label_matches = [
+            (idx, entry)
+            for idx, entry in enumerate(self._entries, start=1)
+            if entry.label.strip().lower() == raw.lower()
+        ]
+        if len(label_matches) == 1:
+            return label_matches[0][0], label_matches[0][1], None
+        if len(label_matches) > 1:
+            return None, None, f'Ambiguous credential label "{raw}". Use the numeric index or entry id instead.'
+        if raw.isdigit():
+            index = int(raw)
+            if 1 <= index <= len(self._entries):
+                return index, self._entries[index - 1], None
+            return None, None, f"No credential #{index}."
+        return None, None, f'No credential matching "{raw}".'

    def add_entry(self, entry: PooledCredential) -> PooledCredential:
-        with self._lock:
-            entry = replace(entry, priority=_next_priority(self._entries))
-            self._entries.append(entry)
-            self._persist()
-            return entry
+        entry = replace(entry, priority=_next_priority(self._entries))
+        self._entries.append(entry)
+        self._persist()
+        return entry


 def _upsert_entry(entries: List[PooledCredential], provider: str, source: str, payload: Dict[str, Any]) -> bool:
@@ -2416,10 +2309,9 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
    def _get_env_prefer_dotenv(key: str) -> str:
        env_file = load_env()
        raw = env_file.get(key, "").strip()
-        scoped_value = (_get_secret(key, "") or "").strip()
+        env_val = os.environ.get(key, "").strip()
        # If .env contains an unresolved op:// reference, prefer the
-        # already-resolved value supplied by the active secret scope (or by
-        # os.environ in legacy single-profile mode), set by
+        # already-resolved value from os.environ (set by
        # load_hermes_dotenv() -> apply_onepassword_secrets()).  The raw
        # "op://Vault/Item/field" string would otherwise win and every
        # provider auth attempt would receive a URL instead of a key.  This
@@ -2427,9 +2319,9 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
        # references straight into .env rather than the secrets.onepassword
        # config block.  For every non-op:// value the original
        # .env-takes-precedence behaviour is preserved unchanged.
-        if raw.startswith("op://") and scoped_value:
-            return scoped_value
-        return raw or scoped_value
+        if raw.startswith("op://") and env_val:
+            return env_val
+        return raw or _get_secret(key, "") or env_val

    # Honour user suppression — `hermes auth remove <provider> <N>` for an
    # env-seeded credential marks the env:<VAR> source as suppressed so it
@@ -316,21 +316,12 @@ def evaluate_credits_notices(
            active.discard(CREDITS_USAGE_KEY)
        if target_band is not None:
            # Belt-and-suspenders: a producer could set subscription_limit_micros
-            # without subscription_limit_usd. Render "$?" rather than "$None".
+            # without subscription_limit_usd. Render "$? cap" rather than "$None cap".
            _cap_usd = state.subscription_limit_usd or "?"
            _level = current_band[1]  # type: ignore[index]  (current_band set when target_band set)
-            # Report absolute dollars used, not a bare "N% used": the percentage is
-            # only meaningful against a Nous subscription cap (no cap → never fires),
-            # so dollars are clearer and don't imply a universal %. Used = cap −
-            # remaining (micros, money-safe), clamped to [0, cap]. Re-emits on band
-            # change (50 → 75 → 90), not every turn — a snapshot, not a live ticker.
-            _lim = state.subscription_limit_micros or 0
-            _used_micros = max(0, min(_lim, _lim - state.subscription_micros))
-            _used_usd = f"{_used_micros / 1_000_000:.2f}" if _lim else "?"
-            _glyph = "⚠" if _level == "warn" else "•"
            to_show.append(
                AgentNotice(
-                    text=f"{_glyph} You've used ${_used_usd} of your ${_cap_usd} cap",
+                    text=f"{'⚠' if _level == 'warn' else '•'} Credits {target_band}% used · ${_cap_usd} cap",
                    level=_level,
                    kind=CREDITS_NOTICE_KIND,
                    key=CREDITS_USAGE_KEY,
@@ -422,9 +422,7 @@ CURATOR_REVIEW_PROMPT = (
    "INSTRUCTIONS AND EXPERIENTIAL KNOWLEDGE. A collection of hundreds of "
    "narrow skills where each one captures one session's specific bug is "
    "a FAILURE of the library — not a feature. An agent searching skills "
-    "matches on descriptions, not on exact names (note: long descriptions "
-    "are truncated to 57 chars in the system prompt skill index — keep the "
-    "trigger class in that window). One broad umbrella "
+    "matches on descriptions, not on exact names; one broad umbrella "
    "skill with labeled subsections beats five narrow siblings for "
    "discoverability, not the other way around.\n\n"
    "The right target shape is CLASS-LEVEL skills with rich SKILL.md "
@@ -1,85 +0,0 @@
-"""Context-local state for delegate_task child execution.
-
-The parent Hermes process may itself be a Kanban dispatcher worker with
-HERMES_KANBAN_* variables in process env. delegate_task children run inside the
-same Python process, but they are not dispatcher-owned Kanban workers. This
-module lets code paths that resolve tool schemas or spawn subprocesses fail
-closed for delegated children without mutating global os.environ for the parent.
-"""
-from __future__ import annotations
-
-from contextlib import contextmanager
-from contextvars import ContextVar
-from typing import Iterator, Mapping, MutableMapping
-
-_DELEGATED_CHILD_CONTEXT: ContextVar[bool] = ContextVar(
-    "hermes_delegated_child_context",
-    default=False,
-)
-
-DELEGATED_CHILD_ENV_MARKER = "HERMES_DELEGATED_CHILD_CONTEXT"
-
-KANBAN_ENV_KEYS: tuple[str, ...] = (
-    "HERMES_KANBAN_TASK",
-    "HERMES_KANBAN_RUN_ID",
-    "HERMES_KANBAN_WORKSPACE",
-    "HERMES_KANBAN_WORKSPACES_ROOT",
-    "HERMES_KANBAN_CLAIM_LOCK",
-    "HERMES_KANBAN_BOARD",
-    "HERMES_KANBAN_DB",
-)
-
-
-@contextmanager
-def delegated_child_context() -> Iterator[None]:
-    """Mark the current execution context as a delegate_task child."""
-    token = _DELEGATED_CHILD_CONTEXT.set(True)
-    try:
-        yield
-    finally:
-        _DELEGATED_CHILD_CONTEXT.reset(token)
-
-
-def is_delegated_child_context() -> bool:
-    """Return True while code is running for a delegate_task child."""
-    return bool(_DELEGATED_CHILD_CONTEXT.get())
-
-
-def is_delegated_child_process_context() -> bool:
-    """Return True in this process or a subprocess spawned by a child."""
-    import os
-
-    return bool(_DELEGATED_CHILD_CONTEXT.get()) or bool(
-        os.environ.get(DELEGATED_CHILD_ENV_MARKER)
-    )
-
-
-def scrub_kanban_env(env: Mapping[str, str] | MutableMapping[str, str]) -> dict[str, str]:
-    """Return *env* with dispatcher-only Kanban variables removed."""
-    cleaned = dict(env)
-    for key in KANBAN_ENV_KEYS:
-        cleaned.pop(key, None)
-    cleaned[DELEGATED_CHILD_ENV_MARKER] = "1"
-    return cleaned
-
-
-def delegated_child_subprocess_env(
-    env: Mapping[str, str] | MutableMapping[str, str] | None = None,
-) -> dict[str, str] | None:
-    """Return an env override only when delegated-child lineage must cross fork.
-
-    Most subprocess call sites historically used ``env=None`` to inherit the
-    process environment.  In a ``delegate_task`` child, inheriting as-is leaks
-    parent dispatcher ``HERMES_KANBAN_*`` vars while losing the ContextVar in
-    the new process.  This helper preserves normal ``env=None`` semantics for
-    non-delegated calls, and only materializes a scrubbed env when the lineage
-    marker must be propagated across a child-process boundary.
-    """
-    if not is_delegated_child_process_context():
-        return None if env is None else dict(env)
-
-    if env is None:
-        import os
-
-        env = os.environ
-    return scrub_kanban_env(env)
@@ -413,7 +413,6 @@ _CONTENT_POLICY_BLOCKED_PATTERNS = [
 _AUTH_PATTERNS = [
    "invalid api key",
    "invalid_api_key",
-    "gateway_auth_failed",
    "authentication",
    "unauthorized",
    "forbidden",
@@ -46,9 +46,6 @@ def build_write_denied_paths(home: str) -> set[str]:
            # Top-level Anthropic PKCE credential store remains sensitive even
            # when a profile is active; default/non-profile sessions still read it.
            str(hermes_root / ".anthropic_oauth.json"),
-            # Bitwarden Secrets Manager encrypted disk cache.
-            str(hermes_home / "cache" / "bws_cache.enc.json"),
-            str(hermes_root / "cache" / "bws_cache.enc.json"),
            os.path.join(home, ".netrc"),
            os.path.join(home, ".pgpass"),
            os.path.join(home, ".npmrc"),
@@ -270,12 +270,8 @@ def _translate_tool_call_to_gemini(tool_call: Dict[str, Any]) -> Dict[str, Any]:
        }
    }
    thought_signature = _tool_call_extra_signature(tool_call)
-    # Fallback sentinel for cross-provider tool_calls (e.g. fallback from
-    # xAI/Anthropic to Gemini, where the original tool_call carries no
-    # Gemini thoughtSignature). Mirrors gemini_cloudcode_adapter.py:106.
-    # Without this, Gemini 3 thinking models reject replayed history with
-    # 400 INVALID_ARGUMENT on the missing thoughtSignature.
-    part["thoughtSignature"] = thought_signature or "skip_thought_signature_validator"
+    if thought_signature:
+        part["thoughtSignature"] = thought_signature
    return part


@@ -32,6 +32,7 @@ from __future__ import annotations

 import logging
 import os
+import sysconfig
 import threading
 from functools import lru_cache
 from pathlib import Path
@@ -91,8 +92,12 @@ def _locales_dir() -> Path:

    1. ``HERMES_BUNDLED_LOCALES`` env var -- set by the Nix wrapper (or any
       sealed-packaging system) to point at the installed catalog directory.
-    2. ``<repo-root>/locales`` -- source checkouts and editable installs,
+    2. ``<repo-root>/locales`` -- source checkouts and ``pip install -e .``,
       where the working tree sits next to ``agent/``.
+    3. ``<sysconfig data|purelib|platlib>/locales`` -- pip wheel installs.
+       setuptools ``data-files`` extracts ``locales/*.yaml`` under the
+       interpreter's ``data`` scheme; the other schemes are checked as a
+       safety net for nonstandard layouts.

    Falling through to the source-style path (even when missing) keeps
    ``_load_catalog`` error messages informative -- it logs the path it
@@ -111,6 +116,25 @@ def _locales_dir() -> Path:

    # agent/i18n.py -> agent/ -> repo root (source checkout, editable install)
    source_dir = Path(__file__).resolve().parent.parent / "locales"
+    if source_dir.is_dir():
+        return source_dir
+
+    # pip wheel install: data-files lands under the interpreter data scheme.
+    # ``data`` (== sys.prefix in a venv) is where setuptools data-files extract
+    # and is checked first. ``purelib``/``platlib`` (site-packages) are a safety
+    # net for nonstandard layouts. NOTE: this does NOT cover ``pip install
+    # --user`` (user scheme, ~/.local/locales) or ``pip install --target`` --
+    # both are out of scope; see the plan header.
+    for scheme in ("data", "purelib", "platlib"):
+        raw = sysconfig.get_path(scheme)
+        if not raw:
+            continue
+        candidate = Path(raw) / "locales"
+        if candidate.is_dir():
+            return candidate
+
+    # Last resort: return the source-style path so _load_catalog's catalog-missing
+    # log (logger.debug "i18n catalog missing for %s at %s") stays informative.
    return source_dir


@@ -181,8 +181,6 @@ def _supports_vision_override(
    cfg: Optional[Dict[str, Any]],
    provider: str,
    model: str,
-    *,
-    requested_provider: str = "",
 ) -> Optional[bool]:
    """Resolve user-declared vision capability from config.yaml.

@@ -190,14 +188,9 @@ def _supports_vision_override(
      1. ``model.supports_vision`` (top-level shortcut for the active model)
      2. ``providers.<provider>.models.<model>.supports_vision``
         (named custom providers — ``provider`` may be the runtime-resolved
-         value ``"custom"``, the runtime's originally requested provider,
-         and/or the user-declared name under ``model.provider``; all are
-         tried. For ``custom:<name>`` syntax, the stripped ``<name>`` is also
-         tried as a provider key.)
-      2b. ``custom_providers`` (legacy list form) ``.models.<model>``
-
-    Under (2) and (2b), the per-model capability key may be written as
-    either ``supports_vision`` or the shorter ``vision`` alias; both work.
+         value ``"custom"`` and/or the user-declared name under
+         ``model.provider``; both are tried. For ``custom:<name>`` syntax,
+         the stripped ``<name>`` is also tried as a provider key.)

    Returns None when no override is set, so the caller falls through to
    models.dev. Returns False explicitly only when the user wrote a
@@ -217,30 +210,23 @@ def _supports_vision_override(
    # get rewritten to provider="custom" at runtime
    # (hermes_cli/runtime_provider.py:_resolve_named_custom_runtime), so the
    # config still holds the user-declared name under model.provider. Try
-    # both as candidate provider keys. Either identity may use the
-    # "custom:<name>" form while providers: is keyed by bare <name>.
+    # both as candidate provider keys, plus the stripped suffix from
+    # "custom:<name>" (where <name> is the key under providers:).
    config_provider = str(model_cfg.get("provider") or "").strip()
-    provider_candidates: List[str] = []
-    for candidate in (requested_provider, provider, config_provider):
-        if not candidate:
-            continue
-        provider_candidates.append(candidate)
-        if candidate.startswith("custom:"):
-            stripped_candidate = candidate[len("custom:"):]
-            if stripped_candidate:
-                provider_candidates.append(stripped_candidate)
+    # Extract the stripped name from "custom:<name>" if present
+    stripped_suffix = ""
+    if config_provider.startswith("custom:"):
+        stripped_suffix = config_provider[len("custom:"):]
    providers_raw = cfg.get("providers")
    providers_cfg: Dict[str, Any] = providers_raw if isinstance(providers_raw, dict) else {}
-    for p in dict.fromkeys(provider_candidates):
+    for p in dict.fromkeys(filter(None, (provider, config_provider, stripped_suffix))):
        entry_raw = providers_cfg.get(p)
        entry: Dict[str, Any] = entry_raw if isinstance(entry_raw, dict) else {}
        models_raw = entry.get("models")
        models_cfg: Dict[str, Any] = models_raw if isinstance(models_raw, dict) else {}
        per_model_raw = models_cfg.get(model)
        per_model: Dict[str, Any] = per_model_raw if isinstance(per_model_raw, dict) else {}
-        coerced = _coerce_capability_bool(
-            per_model.get("supports_vision", per_model.get("vision"))
-        )
+        coerced = _coerce_capability_bool(per_model.get("supports_vision"))
        if coerced is not None:
            return coerced

@@ -249,26 +235,28 @@ def _supports_vision_override(
    # may appear as the raw name or "custom:<name>" at runtime).
    custom_providers = cfg.get("custom_providers")
    if isinstance(custom_providers, list):
-        # Candidate priority matters when the CLI-selected provider differs
-        # from model.provider. Walk identities first, then config entries, so
-        # list order cannot let the persisted default shadow the live route.
-        for candidate in dict.fromkeys(provider_candidates):
-            candidate_name = candidate.strip().lower()
-            for entry_raw in custom_providers:
-                if not isinstance(entry_raw, dict):
-                    continue
-                entry_name = str(entry_raw.get("name") or "").strip().lower()
-                if entry_name != candidate_name:
-                    continue
-                models_raw = entry_raw.get("models")
-                models_cfg = models_raw if isinstance(models_raw, dict) else {}
-                per_model_raw = models_cfg.get(model)
-                per_model = per_model_raw if isinstance(per_model_raw, dict) else {}
-                coerced = _coerce_capability_bool(
-                    per_model.get("supports_vision", per_model.get("vision"))
-                )
-                if coerced is not None:
-                    return coerced
+        # Build candidate names: the provider value and the config provider
+        # value, both raw and with "custom:" prefix stripped/added.
+        candidate_names: set = set()
+        for p in filter(None, (provider, config_provider)):
+            candidate_names.add(p)
+            if p.startswith("custom:"):
+                candidate_names.add(p[len("custom:"):])
+            else:
+                candidate_names.add(f"custom:{p}")
+        for entry_raw in custom_providers:
+            if not isinstance(entry_raw, dict):
+                continue
+            entry_name = str(entry_raw.get("name") or "").strip()
+            if entry_name not in candidate_names:
+                continue
+            models_raw = entry_raw.get("models")
+            models_cfg = models_raw if isinstance(models_raw, dict) else {}
+            per_model_raw = models_cfg.get(model)
+            per_model = per_model_raw if isinstance(per_model_raw, dict) else {}
+            coerced = _coerce_capability_bool(per_model.get("supports_vision"))
+            if coerced is not None:
+                return coerced

    return None

@@ -388,8 +376,6 @@ def _lookup_supports_vision(
    provider: str,
    model: str,
    cfg: Optional[Dict[str, Any]] = None,
-    *,
-    requested_provider: str = "",
 ) -> Optional[bool]:
    """Return True/False if we can resolve caps, None if unknown.

@@ -397,34 +383,7 @@ def _lookup_supports_vision(
    (so custom/local models declared as vision-capable don't fall through to
    text routing in ``auto`` mode), then falls back to models.dev.
    """
-    # Named custom providers are canonicalized to ``provider="custom"`` by
-    # runtime resolution.  The original CLI/config name is carried in the
-    # context-local main runtime so capability lookup can still select the
-    # exact custom_providers entry.  Require an exact provider+model match:
-    # background/auxiliary lookups must never borrow another turn's identity.
-    if not requested_provider:
-        try:
-            from agent.auxiliary_client import _runtime_main_value
-
-            runtime_provider = str(
-                _runtime_main_value("provider") or ""
-            ).strip().lower()
-            runtime_model = str(_runtime_main_value("model") or "").strip()
-            lookup_provider = str(provider or "").strip().lower()
-            lookup_model = str(model or "").strip()
-            if runtime_provider == lookup_provider and runtime_model == lookup_model:
-                requested_provider = str(
-                    _runtime_main_value("requested_provider") or ""
-                ).strip()
-        except Exception:
-            pass
-
-    override = _supports_vision_override(
-        cfg,
-        provider,
-        model,
-        requested_provider=requested_provider,
-    )
+    override = _supports_vision_override(cfg, provider, model)
    if override is not None:
        return override
    if not provider or not model:
@@ -462,8 +421,6 @@ def decide_image_input_mode(
    provider: str,
    model: str,
    cfg: Optional[Dict[str, Any]],
-    *,
-    requested_provider: str = "",
 ) -> str:
    """Return ``"native"`` or ``"text"`` for the given turn.

@@ -471,7 +428,6 @@ def decide_image_input_mode(
      provider: active inference provider ID (e.g. ``"anthropic"``, ``"openrouter"``).
      model:    active model slug as it would be sent to the provider.
      cfg:      loaded config.yaml dict, or None. When None, behaves as auto.
-      requested_provider: provider identity before runtime canonicalization.
    """
    mode_cfg = "auto"
    if isinstance(cfg, dict):
@@ -488,17 +444,7 @@ def decide_image_input_mode(
    # explicit auxiliary.vision config acts as a *fallback* for text-only
    # main models — it should not preempt native vision on a model that
    # can natively inspect the pixels (issue #29135).
-    if requested_provider:
-        supports = _lookup_supports_vision(
-            provider,
-            model,
-            cfg,
-            requested_provider=requested_provider,
-        )
-    else:
-        # Keep the long-standing three-argument call contract for callers and
-        # tests that replace the capability lookup hook.
-        supports = _lookup_supports_vision(provider, model, cfg)
+    supports = _lookup_supports_vision(provider, model, cfg)
    if supports is True:
        return "native"
    if _explicit_aux_vision_override(cfg):
@@ -56,8 +56,6 @@ from pathlib import Path
 from typing import Any, Awaitable, Callable, Dict, List, Optional, Set
 from urllib.parse import quote, unquote

-from hermes_cli._subprocess_compat import windows_hide_flags
-
 from agent.lsp.protocol import (
    ERROR_CONTENT_MODIFIED,
    ERROR_METHOD_NOT_FOUND,
@@ -296,12 +294,6 @@ class LSPClient:
        cmd = self._command
        if sys.platform == "win32":
            cmd = self._win_wrap_cmd(cmd)
-        # Suppress the cmd.exe console window that would otherwise flash
-        # every time we launch a ``.cmd``-wrapped language server
-        # (e.g. pyright-langserver.CMD) from a console-less host such as
-        # a VS Code/Zed extension running the ACP adapter.
-        # windows_hide_flags() is CREATE_NO_WINDOW on Windows, 0 on POSIX.
-        creationflags = windows_hide_flags()

        try:
            # start_new_session=True detaches the LSP server into its own
@@ -320,7 +312,6 @@ class LSPClient:
                env=env,
                cwd=self._cwd,
                start_new_session=True,
-                creationflags=creationflags,
            )
        except FileNotFoundError as e:
            raise LSPProtocolError(
@@ -35,8 +35,6 @@ import threading
 from pathlib import Path
 from typing import Any, Dict, Optional

-from hermes_cli._subprocess_compat import windows_hide_flags
-
 logger = logging.getLogger("agent.lsp.install")

 # Package-name → install-strategy hint registry.  Each entry is a
@@ -270,7 +268,6 @@ def _install_npm(
            text=True,
            timeout=300,
            stdin=subprocess.DEVNULL,
-            creationflags=windows_hide_flags(),
        )
        if proc.returncode != 0:
            logger.warning(
@@ -320,7 +317,6 @@ def _install_go(pkg: str, bin_name: str) -> Optional[str]:
            timeout=600,
            env=env,
            stdin=subprocess.DEVNULL,
-            creationflags=windows_hide_flags(),
        )
        if proc.returncode != 0:
            logger.warning(
@@ -7,36 +7,6 @@ from typing import Any, Sequence
 from agent.redact import redact_sensitive_text


-def describe_compression_lock_skip(lock_signal: Any) -> str:
-    """User-facing text for a manual /compress skipped by the compression lock.
-
-    ``lock_signal`` is ``agent._compression_skipped_due_to_lock`` (or the
-    ``holder`` carried by the TUI's ``CompressionLockHeld``): a descriptive
-    holder string when another compressor CONFIRMED holds the lock, or
-    ``True``/``None`` when acquisition failed without a confirmed holder
-    (``hermes_state.try_acquire_compression_lock`` catches ``sqlite3.Error``
-    internally and returns ``False``, so a failed acquire is NOT proof that
-    another compression is running). The two cases must be worded
-    differently: claiming "already in progress" on an unconfirmed failure
-    misdirects the user when the real problem is a broken lock subsystem.
-    """
-    holder = (
-        lock_signal
-        if isinstance(lock_signal, str) and lock_signal.strip()
-        else None
-    )
-    if holder:
-        return (
-            f"⏳ Compression already in progress for this session "
-            f"(holder: {holder}). Please wait for it to finish."
-        )
-    return (
-        "⏳ Compression skipped: could not acquire this session's "
-        "compression lock. Another compression may still be running, or "
-        "the lock check failed — try again shortly."
-    )
-
-
 def summarize_manual_compression(
    before_messages: Sequence[dict[str, Any]],
    after_messages: Sequence[dict[str, Any]],
@@ -4,8 +4,6 @@ Pure utility functions with no AIAgent dependency. Used by ContextCompressor
 and run_agent.py for pre-flight context checks.
 """

-import base64
-import hashlib
 import ipaddress
 import json
 import logging
@@ -583,13 +581,8 @@ def _skip_persistent_context_cache(base_url: str, provider: str) -> bool:

    LM Studio excludes caching because loaded context is transient — the user
    can reload the model with a different context_length at any time.
-
-    Codex OAuth excludes caching because its context window is account- and
-    entitlement-specific metadata supplied by the authenticated /models
-    endpoint. A fallback value written after a transient probe failure must
-    not prevent a later live probe from observing an updated allocation.
-    """
-    return (provider or "").strip().lower() in {"lmstudio", "openai-codex"}
+   """
+    return provider == "lmstudio"


 def _maybe_cache_local_context_length(
@@ -1925,72 +1918,32 @@ _CODEX_OAUTH_CONTEXT_FALLBACK: Dict[str, int] = {
 }


-_codex_oauth_context_cache: Dict[str, Tuple[Dict[str, int], float]] = {}
+_codex_oauth_context_cache: Dict[str, int] = {}
+_codex_oauth_context_cache_time: float = 0.0
 _CODEX_OAUTH_CONTEXT_CACHE_TTL = 3600  # 1 hour


-def _codex_oauth_token_fingerprint(access_token: str) -> str:
-    """Return a non-secret cache key for a Codex OAuth access token."""
-    return hashlib.sha256(access_token.encode("utf-8")).hexdigest()[:16]
+def _fetch_codex_oauth_context_lengths(access_token: str) -> Dict[str, int]:
+    """Probe the ChatGPT Codex /models endpoint for per-slug context windows.

+    Codex OAuth imposes its own context limits that differ from the direct
+    OpenAI API (e.g. gpt-5.5 is 1.05M on the API, 272K on Codex). The
+    `context_window` field in each model entry is the authoritative source.

-def _extract_chatgpt_account_id(access_token: str) -> Optional[str]:
-    """Extract ``chatgpt_account_id`` from the Codex OAuth JWT.
-
-    The Codex ``/backend-api/codex/models`` endpoint returns the per-account
-    catalog only when the ``ChatGPT-Account-Id`` header is present; without
-    it, the endpoint returns ``{"models":[]}`` (HTTP 200) and the context
-    probe falls back to the hardcoded defaults — which can be stale or
-    wrong for the active account's plan. Mirrors the same extraction done
-    in ``auxiliary_client.py`` for the request path.
-
-    Returns ``None`` on any parse error rather than raising, so a bad
-    token still surfaces as a normal probe failure instead of crashing
-    the metadata resolver.
+    Returns a ``{slug: context_window}`` dict. Empty on failure.
    """
-    try:
-        parts = access_token.split(".")
-        if len(parts) < 2:
-            return None
-        payload_b64 = parts[1] + "=" * (-len(parts[1]) % 4)
-        claims = json.loads(base64.urlsafe_b64decode(payload_b64))
-        if not isinstance(claims, dict):
-            return None
-        acct_id = claims.get("https://api.openai.com/auth", {}).get("chatgpt_account_id")
-        return acct_id if isinstance(acct_id, str) and acct_id else None
-    except Exception:
-        return None
-
-
-def _fetch_codex_oauth_context_lengths_with_source(
-    access_token: str,
-) -> Tuple[Dict[str, int], bool]:
-    """Fetch Codex catalogue data and report whether it came from HTTP.
-
-    The in-process cache is scoped by token fingerprint because Codex model
-    availability and context windows can vary by account entitlement. The raw
-    token is never retained in the cache key. The boolean is false for a
-    same-token in-process hit, which must not be treated as a fresh provider
-    confirmation when deciding whether to update persistent state.
-    """
-    global _codex_oauth_context_cache
+    global _codex_oauth_context_cache, _codex_oauth_context_cache_time
    now = time.time()
-    cache_key = _codex_oauth_token_fingerprint(access_token)
-    cached = _codex_oauth_context_cache.get(cache_key)
-    if cached is not None:
-        cached_models, cached_at = cached
-        if now - cached_at < _CODEX_OAUTH_CONTEXT_CACHE_TTL:
-            return cached_models, False
-
-    headers = {"Authorization": f"Bearer {access_token}"}
-    acct_id = _extract_chatgpt_account_id(access_token)
-    if acct_id:
-        headers["ChatGPT-Account-Id"] = acct_id
+    if (
+        _codex_oauth_context_cache
+        and now - _codex_oauth_context_cache_time < _CODEX_OAUTH_CONTEXT_CACHE_TTL
+    ):
+        return _codex_oauth_context_cache

    try:
        resp = requests.get(
            "https://chatgpt.com/backend-api/codex/models?client_version=1.0.0",
-            headers=headers,
+            headers={"Authorization": f"Bearer {access_token}"},
            timeout=(5, 10),
            verify=_resolve_requests_verify(),
        )
@@ -1999,11 +1952,11 @@ def _fetch_codex_oauth_context_lengths_with_source(
                "Codex /models probe returned HTTP %s; falling back to hardcoded defaults",
                resp.status_code,
            )
-            return {}, False
+            return {}
        data = resp.json()
    except Exception as exc:
        logger.debug("Codex /models probe failed: %s", exc)
-        return {}, False
+        return {}

    entries = data.get("models", []) if isinstance(data, dict) else []
    result: Dict[str, int] = {}
@@ -2016,50 +1969,32 @@ def _fetch_codex_oauth_context_lengths_with_source(
            result[slug.strip()] = ctx

    if result:
-        _codex_oauth_context_cache[cache_key] = (result, now)
-    return result, True
-
-
-def _fetch_codex_oauth_context_lengths(access_token: str) -> Dict[str, int]:
-    """Probe the ChatGPT Codex /models endpoint for per-slug context windows.
-
-    Codex OAuth imposes its own context limits that differ from the direct
-    OpenAI API (e.g. gpt-5.5 is 1.05M on the API, 272K on Codex). The
-    `context_window` field in each model entry is the authoritative source.
-
-    Returns a ``{slug: context_window}`` dict. Empty on failure.
-    """
-    result, _fresh = _fetch_codex_oauth_context_lengths_with_source(access_token)
+        _codex_oauth_context_cache = result
+        _codex_oauth_context_cache_time = now
    return result


-def _resolve_codex_oauth_context_length_with_source(
+def _resolve_codex_oauth_context_length(
    model: str, access_token: str = ""
-) -> Tuple[Optional[int], str]:
+) -> Optional[int]:
    """Resolve a Codex OAuth model's real context window.

    Prefers a live probe of chatgpt.com/backend-api/codex/models (when we
    have a bearer token), then falls back to ``_CODEX_OAUTH_CONTEXT_FALLBACK``.
-
-    Returns ``(context_length, source)`` where source is ``"live"`` for a
-    value returned by a fresh authenticated endpoint probe, ``"memory"`` for
-    a same-token in-process catalogue hit, or ``"fallback"`` for the static
-    conservative table. Only ``"live"`` is eligible for persistent writes.
    """
    model_bare = _strip_provider_prefix(model).strip()
    if not model_bare:
-        return None, ""
+        return None

    if access_token:
-        live, fresh_probe = _fetch_codex_oauth_context_lengths_with_source(access_token)
-        live_source = "live" if fresh_probe else "memory"
+        live = _fetch_codex_oauth_context_lengths(access_token)
        if model_bare in live:
-            return live[model_bare], live_source
+            return live[model_bare]
        # Case-insensitive match in case casing drifts
        model_lower = model_bare.lower()
        for slug, ctx in live.items():
            if slug.lower() == model_lower:
-                return ctx, live_source
+                return ctx

    # Fallback: longest-key-first substring match over hardcoded defaults.
    model_lower = model_bare.lower()
@@ -2067,19 +2002,9 @@ def _resolve_codex_oauth_context_length_with_source(
        _CODEX_OAUTH_CONTEXT_FALLBACK.items(), key=lambda x: len(x[0]), reverse=True
    ):
        if slug in model_lower:
-            return ctx, "fallback"
+            return ctx

-    return None, ""
-
-
-def _resolve_codex_oauth_context_length(
-    model: str, access_token: str = ""
-) -> Optional[int]:
-    """Resolve a Codex OAuth model's context length (compatibility wrapper)."""
-    context_length, _source = _resolve_codex_oauth_context_length_with_source(
-        model, access_token=access_token,
-    )
-    return context_length
+    return None


 def _resolve_nous_context_length(
@@ -2169,9 +2094,9 @@ def get_model_context_length(
    Resolution order:
    0. Explicit config override (model.context_length or custom_providers per-model)
    0c. Endpoint-scoped metadata for models validated on one multiplexed endpoint
-    1. Persistent cache (previously discovered via probing).  Nous URLs,
-       LM Studio, and Codex OAuth bypass the cache here so their provider
-       metadata can be reconciled against the authoritative live source.
+    1. Persistent cache (previously discovered via probing).  Nous URLs
+       bypass the cache here so step 5b can always reconcile against
+       the authoritative portal /v1/models response.
    1b. AWS Bedrock static table (must precede custom-endpoint probe)
    2. Active endpoint metadata (/models for explicit custom endpoints)
    3. Local server query (for local endpoints)
@@ -2201,18 +2126,11 @@ def get_model_context_length(
    # acting context, so they're ignored here.
    if (provider or "").strip().lower() == "moa":
        try:
-            from hermes_cli.config import (
-                get_compatible_custom_providers,
-                load_config,
-            )
+            from hermes_cli.config import load_config
            from hermes_cli.moa_config import resolve_moa_preset
            from hermes_cli.runtime_provider import resolve_runtime_provider

-            config = load_config()
-            effective_custom_providers = custom_providers
-            if effective_custom_providers is None:
-                effective_custom_providers = get_compatible_custom_providers(config)
-            preset = resolve_moa_preset(config.get("moa") or {}, model)
+            preset = resolve_moa_preset(load_config().get("moa") or {}, model)
            agg = preset.get("aggregator") or {}
            agg_provider = str(agg.get("provider") or "").strip()
            agg_model = str(agg.get("model") or "").strip()
@@ -2222,8 +2140,7 @@ def get_model_context_length(
                    agg_model,
                    base_url=rt.get("base_url", "") or "",
                    api_key=rt.get("api_key", "") or "",
-                    provider=rt.get("provider") or agg_provider,
-                    custom_providers=effective_custom_providers,
+                    provider=agg_provider,
                )
        except Exception:
            logger.debug("MoA aggregator context-length resolution failed", exc_info=True)
@@ -2279,13 +2196,24 @@ def get_model_context_length(
    # LM Studio is excluded — its loaded context length is transient (the
    # user can reload the model with a different context_length at any time
    # via /api/v1/models/load), so a stale cached value would mask reloads.
-    # Codex OAuth is excluded because the authenticated /models catalogue is
-    # account-specific and a fallback must never suppress later revalidation.
    if base_url and not _skip_persistent_context_cache(base_url, provider):
        cached = get_cached_context_length(model, base_url)
        if cached is not None:
+            # Invalidate stale Codex OAuth cache entries: pre-PR #14935 builds
+            # resolved gpt-5.x to the direct-API value (e.g. 1.05M) via
+            # models.dev and persisted it. Codex OAuth caps at 272K for every
+            # slug, so any cached Codex entry at or above 400K is a leftover
+            # from the old resolution path. Drop it and fall through to the
+            # live /models probe in step 5 below.
+            if provider == "openai-codex" and cached >= 400_000:
+                logger.info(
+                    "Dropping stale Codex cache entry %s@%s -> %s (pre-fix value); "
+                    "re-resolving via live /models probe",
+                    model, base_url, f"{cached:,}",
+                )
+                _invalidate_cached_context_length(model, base_url)
            # Invalidate stale 32k cache entries for Kimi-family models.
-            if cached <= 32768 and _model_name_suggests_kimi(model):
+            elif cached <= 32768 and _model_name_suggests_kimi(model):
                logger.info(
                    "Dropping stale Kimi cache entry %s@%s -> %s (OpenRouter underreport); "
                    "re-resolving via hardcoded defaults",
@@ -2524,14 +2452,9 @@ def get_model_context_length(
        # Codex OAuth enforces lower context limits than the direct OpenAI
        # API for the same slug (e.g. gpt-5.5 is 1.05M on the API but 272K
        # on Codex). Authoritative source is Codex's own /models endpoint.
-        codex_ctx, codex_source = _resolve_codex_oauth_context_length_with_source(
-            model, access_token=api_key or "",
-        )
+        codex_ctx = _resolve_codex_oauth_context_length(model, access_token=api_key or "")
        if codex_ctx:
-            # Only a successful authenticated catalogue response is safe to
-            # persist. The static fallback is deliberately runtime-only so a
-            # transient OAuth/network failure cannot poison future probes.
-            if base_url and codex_source == "live":
+            if base_url:
                save_context_length(model, base_url, codex_ctx)
            return codex_ctx
    if effective_provider == "gmi" and base_url:
@@ -2674,61 +2597,16 @@ async def get_model_context_length_async(
    )


-def _is_cjk_token_dense_char(ch: str) -> bool:
-    code = ord(ch)
-    return (
-        0x1100 <= code <= 0x11FF  # Hangul Jamo
-        or 0x2E80 <= code <= 0x9FFF  # CJK radicals/ideographs
-        or 0xA960 <= code <= 0xA97F  # Hangul Jamo Extended-A
-        or 0xAC00 <= code <= 0xD7AF  # Hangul Syllables
-        or 0xF900 <= code <= 0xFAFF  # CJK compatibility ideographs
-        or 0xFF00 <= code <= 0xFFEF  # Fullwidth forms / halfwidth kana
-    )
-
-
-# Same codepoint ranges as _is_cjk_token_dense_char, as a compiled character
-# class so dense-char counting runs in C (``len(text) - len(re.sub(...))``)
-# instead of a per-char Python loop.  MUST stay in sync with
-# _is_cjk_token_dense_char.
-_CJK_DENSE_RE = re.compile(
-    "[\u1100-\u11ff"  # Hangul Jamo
-    "\u2e80-\u9fff"  # CJK radicals/ideographs
-    "\ua960-\ua97f"  # Hangul Jamo Extended-A
-    "\uac00-\ud7af"  # Hangul Syllables
-    "\uf900-\ufaff"  # CJK compatibility ideographs
-    "\uff00-\uffef]"  # Fullwidth forms / halfwidth kana
-)
-
-
 def estimate_tokens_rough(text: str) -> int:
-    """Rough token estimate for pre-flight checks.
+    """Rough token estimate (~4 chars/token) for pre-flight checks.

    Uses ceiling division so short texts (1-3 chars) never estimate as
    0 tokens, which would cause the compressor and pre-flight checks to
    systematically undercount when many short tool results are present.
-    CJK/Hangul/Kana text is much denser than English under common LLM
-    tokenizers, so count those codepoints as roughly one token each instead
-    of applying the English-centric ~4 chars/token rule.
-
-    Perf: this runs on every message in every preflight/compaction walk,
-    including MB-scale tool outputs, so the common all-ASCII case must stay
-    O(1).  ``str.isascii()`` is a flag check on CPython's compact unicode
-    representation (no scan), and the CJK counting itself is a single
-    C-level ``re.findall`` rather than a per-character Python loop.
    """
    if not text:
        return 0
-    text = str(text)
-    if text.isascii():
-        # O(1) fast path — ASCII text cannot contain token-dense CJK chars.
-        return (len(text) + 3) // 4
-    dense = len(text) - len(_CJK_DENSE_RE.sub("", text))
-    if not dense:
-        # Non-ASCII but no CJK (accents, Cyrillic, emoji, ...): keep the
-        # classic ~4 chars/token rule.
-        return (len(text) + 3) // 4
-    sparse = len(text) - dense
-    return dense + ((sparse + 3) // 4)
+    return (len(text) + 3) // 4


 def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
@@ -2740,12 +2618,12 @@ def estimate_messages_tokens_rough(messages: List[Dict[str, Any]]) -> int:
    estimated at ~250K tokens and trigger premature context compression.
    """
    _IMAGE_TOKEN_COST = 1500
-    text_tokens = 0
+    total_chars = 0
    image_tokens = 0
    for msg in messages:
-        text_tokens += _estimate_message_tokens_without_images(msg)
+        total_chars += _estimate_message_chars(msg)
        image_tokens += _count_image_tokens(msg, _IMAGE_TOKEN_COST)
-    return text_tokens + image_tokens
+    return ((total_chars + 3) // 4) + image_tokens


 def _count_image_tokens(msg: Dict[str, Any], cost_per_image: int) -> int:
@@ -2807,35 +2685,6 @@ def _estimate_message_chars(msg: Dict[str, Any]) -> int:
    return len(str(shadow))


-def _estimate_message_tokens_without_images(msg: Dict[str, Any]) -> int:
-    """Token estimate for a message shadow with image payloads stripped."""
-    if not isinstance(msg, dict):
-        return estimate_tokens_rough(str(msg))
-    shadow: Dict[str, Any] = {}
-    for k, v in msg.items():
-        if k == "_anthropic_content_blocks":
-            continue
-        if k == "content":
-            if isinstance(v, list):
-                cleaned = []
-                for part in v:
-                    if isinstance(part, dict):
-                        if part.get("type") in {"image", "image_url", "input_image"}:
-                            cleaned.append({"type": part.get("type"), "image": "[stripped]"})
-                        else:
-                            cleaned.append(part)
-                    else:
-                        cleaned.append(part)
-                shadow[k] = cleaned
-            elif isinstance(v, dict) and v.get("_multimodal"):
-                shadow[k] = v.get("text_summary", "")
-            else:
-                shadow[k] = v
-        else:
-            shadow[k] = v
-    return estimate_tokens_rough(str(shadow))
-
-
 def estimate_request_tokens_rough(
    messages: List[Dict[str, Any]],
    *,
@@ -2852,7 +2701,7 @@ def estimate_request_tokens_rough(
    """
    total = 0
    if system_prompt:
-        total += estimate_tokens_rough(system_prompt)
+        total += (len(system_prompt) + 3) // 4
    if messages:
        total += estimate_messages_tokens_rough(messages)
    if tools:
@@ -52,13 +52,6 @@ def busy_input_hint_gateway(mode: str) -> str:
            "Send `/busy interrupt` or `/busy queue` to change this, or "
            "`/busy status` to check. This notice won't appear again."
        )
-    if mode == "redirect":
-        return (
-            "💡 First-time tip — I redirected the current run using your message. "
-            "Completed work stays in context, and `/stop` still cancels the task. "
-            "Send `/busy queue` to wait for a separate turn, or `/busy status` "
-            "to check. This notice won't appear again."
-        )
    return (
        "💡 First-time tip — I just interrupted my current task to answer you. "
        "Send `/busy queue` to queue follow-ups for after the current task instead, "
@@ -81,12 +74,6 @@ def busy_input_hint_cli(mode: str) -> str:
            "after the next tool call. Use /busy interrupt or /busy queue to "
            "change this. This tip only shows once."
        )
-    if mode == "redirect":
-        return (
-            "(tip) Your correction redirected the current run without discarding "
-            "completed work. Use /stop to cancel or /busy queue to wait for a "
-            "separate turn. This tip only shows once."
-        )
    return (
        "(tip) Your message interrupted the current run. "
        "Use /busy queue to queue messages for the next turn instead, "
@@ -192,13 +192,7 @@ SKILLS_GUIDANCE = (
    "skill with skill_manage so you can reuse it next time.\n"
    "When using a skill and finding it outdated, incomplete, or wrong, "
    "patch it immediately with skill_manage(action='patch') — don't wait to be asked. "
-    "Skills that aren't maintained become liabilities.\n"
-    "\n"
-    "## Skill Safety Rule\n"
-    "1. **UNAVAILABLE** — If a skill placeholder contains `[SKILL_PRUNED]`, the skill content was lost in compression and is inaccessible.\n"
-    "2. **RELOAD** — Before performing any action that depends on a skill, re-check its content with `skill_view(name='...')` if it shows `[SKILL_PRUNED]`.\n"
-    "3. **WAIT** — If a skill is loading or was just pruned, wait for the reload confirmation before proceeding.\n"
-    "4. **DEDUP** — After reloading a pruned skill, **ignore any remaining `[SKILL_PRUNED]` markers for that same skill** — they are historical artifacts from previous compactions and do not need further action."
+    "Skills that aren't maintained become liabilities."
 )

 KANBAN_GUIDANCE = (
@@ -890,14 +884,7 @@ PLATFORM_HINTS = {
        "You're responding through an API server. The rendering layer is unknown — "
        "assume plain text. No markdown formatting (no asterisks, bullets, headers, "
        "code fences). Treat this like a conversation, not a document. Keep responses "
-        "brief and natural. "
-        "File/media delivery: images referenced as MEDIA:/absolute/path tags "
-        "(.png/.jpg/.jpeg/.gif/.webp/.bmp, up to 5MB) are inlined as base64 data "
-        "URLs in responses on the chat, completions, and responses endpoints. "
-        "Non-image files are NOT intercepted anywhere, and the runs endpoint "
-        "intercepts nothing — a MEDIA: tag there renders as literal text exposing "
-        "a raw host filesystem path. For those cases, state the plain file path "
-        "in your response text instead of a MEDIA: tag."
+        "brief and natural."
    ),
    "webui": (
        "You are in the Hermes WebUI, a browser-based chat interface. "
@@ -127,16 +127,10 @@ def get_secret(name: str, default: Optional[str] = None) -> Optional[str]:

    1. Genuinely-global vars (``_is_global_env``) always read ``os.environ`` —
       they are deployment settings, not profile secrets.
-    2. When a secret scope is installed (multiplexed turn), read from it. Under
-       multiplexing the scope is authoritative — an absent key returns
-       ``default`` and we do NOT fall through to ``os.environ``, because in a
-       multiplexer ``os.environ`` may hold another profile's value. When
-       multiplexing is OFF, a scope miss falls through to ``os.environ``:
-       single-profile deployments legitimately provide credentials via the
-       process environment (systemd ``Environment=``, secret-manager wrappers
-       like ``pass-cli run`` / ``op run``, plain shell exports) rather than
-       ``<home>/.env``, and the scope — installed unconditionally around e.g.
-       every cron job — must stay a ``.env`` overlay, not a blindfold.
+    2. When a secret scope is installed (multiplexed turn), read from it; an
+       absent key returns ``default``. The scope is authoritative — we do NOT
+       fall through to ``os.environ``, because in a multiplexer ``os.environ``
+       may hold another profile's value.
    3. No scope installed:
       - multiplex INACTIVE (default deployment): read ``os.environ`` —
         identical to the legacy ``os.getenv`` behavior every caller had before.
@@ -150,17 +144,6 @@ def get_secret(name: str, default: Optional[str] = None) -> Optional[str]:
    scope = _SECRET_SCOPE.get()
    if scope is not None:
        val = scope.get(name)
-        if val is not None:
-            return val
-        if _MULTIPLEX_ACTIVE:
-            return default
-        # Multiplex off: the scope is an overlay over the process environment,
-        # not an isolation boundary — there is no other profile to leak from.
-        # Without this fallthrough, credentials injected only into the process
-        # environment vanish inside any set_secret_scope(...) block (the cron
-        # scheduler installs one around every job), so cron jobs send a
-        # placeholder API key and 401 while interactive turns keep working.
-        val = os.environ.get(name)
        return val if val is not None else default

    if _MULTIPLEX_ACTIVE:
@@ -218,18 +201,5 @@ def build_profile_secret_scope(hermes_home: Path) -> Dict[str, str]:
    global vars are intentionally NOT copied in — ``get_secret`` reads those
    from ``os.environ`` directly, so the scope holds only profile secrets.
    """
-    home = Path(hermes_home)
-    secrets = load_env_file(home / ".env")
+    return load_env_file(Path(hermes_home) / ".env")

-    try:
-        from hermes_cli.env_loader import get_secret_source_values
-        external_secrets = get_secret_source_values(home)
-    except Exception:
-        external_secrets = {}
-
-    for key, value in external_secrets.items():
-        if _is_global_env(key):
-            continue
-        secrets[key] = value
-
-    return secrets
@@ -190,45 +190,6 @@ class SecretSource(ABC):
        """
        return {}

-    def remediation(self, kind: Optional["ErrorKind"], cfg: dict) -> str:
-        """One-line, actionable next step for a failed fetch.
-
-        Called by the startup status printer (and ``hermes secrets ...
-        status``) right after a fetch error is surfaced, so the user sees
-        *what to run* next to fix it — not just what broke.  Sources
-        should override this to point at their own CLI verbs (e.g.
-        ``hermes secrets bitwarden token`` for AUTH_FAILED).  Return an
-        empty string to suppress the hint.
-
-        Must never raise and must not perform I/O — it's a pure
-        kind→string mapping on the startup path.
-        """
-        generic = {
-            ErrorKind.NOT_CONFIGURED: (
-                f"Run `hermes secrets {self.name} setup` to finish configuration."
-            ),
-            ErrorKind.BINARY_MISSING: (
-                f"Run `hermes secrets {self.name} setup` to install the helper CLI."
-            ),
-            ErrorKind.AUTH_FAILED: (
-                f"Credentials rejected — run `hermes secrets {self.name} setup` "
-                "to re-authenticate."
-            ),
-            ErrorKind.AUTH_EXPIRED: (
-                f"Credentials expired — run `hermes secrets {self.name} setup` "
-                "to re-authenticate."
-            ),
-            ErrorKind.NETWORK: (
-                "Network problem reaching the secrets backend — check "
-                "connectivity and retry."
-            ),
-            ErrorKind.TIMEOUT: (
-                f"Backend was slow — raise secrets.{self.name}.timeout_seconds "
-                "if this recurs."
-            ),
-        }
-        return generic.get(kind, "") if kind is not None else ""
-

 # ---------------------------------------------------------------------------
 # Shared helpers — use these instead of hand-rolling per backend
@@ -29,13 +29,11 @@ is easier to lazy-install than a wheels-with-Rust-extension dependency.

 from __future__ import annotations

-import base64
 import hashlib
 import json
 import logging
 import os
 import platform
-import re
 import shutil
 import stat
 import subprocess
@@ -47,10 +45,6 @@ import zipfile
 from pathlib import Path
 from typing import Dict, List, Optional, Tuple

-from cryptography.hazmat.primitives import hashes
-from cryptography.hazmat.primitives.ciphers.aead import AESGCM
-from cryptography.hazmat.primitives.kdf.hkdf import HKDF
-
 from agent.secret_sources._cache import (
    CachedFetch as _CachedFetch,
    DiskCache,
@@ -97,9 +91,6 @@ _CACHE: Dict[_CacheKey, _CachedFetch] = {}
 # accidentally commit BSM-sourced secrets. The atomic-write/0600/TTL mechanics
 # live in agent.secret_sources._cache.DiskCache, shared with the other backends.
 _DISK_CACHE_BASENAME = "bws_cache.json"
-_ENCRYPTED_CACHE_BASENAME = "bws_cache.enc.json"
-_ENCRYPTED_CACHE_VERSION = 1
-_ENCRYPTED_CACHE_INFO = b"hermes-bws-encrypted-cache-v1"


 def _cache_key_str(cache_key: _CacheKey) -> str:
@@ -122,13 +113,6 @@ def _disk_cache_path(home_path: Optional[Path] = None) -> Path:
    return _DISK_CACHE.path(home_path)


-def _encrypted_disk_cache_path(home_path: Optional[Path] = None) -> Path:
-    """Return the encrypted disk cache path under hermes_home/cache/."""
-    from agent.secret_sources._cache import resolve_cache_home
-
-    return resolve_cache_home(home_path) / "cache" / _ENCRYPTED_CACHE_BASENAME
-
-
 # ---------------------------------------------------------------------------
 # Binary discovery + lazy install
 # ---------------------------------------------------------------------------
@@ -364,134 +348,6 @@ def _token_fingerprint(token: str) -> str:
    return hashlib.sha256(token.encode("utf-8")).hexdigest()[:16]


-def _b64e(raw: bytes) -> str:
-    return base64.b64encode(raw).decode("ascii")
-
-
-def _b64d(text: str) -> bytes:
-    return base64.b64decode(text.encode("ascii"), validate=True)
-
-
-def _derive_encrypted_cache_key(access_token: str, salt: bytes) -> bytes:
-    """Derive the local cache encryption key from the bootstrap BWS token."""
-    return HKDF(
-        algorithm=hashes.SHA256(),
-        length=32,
-        salt=salt,
-        info=_ENCRYPTED_CACHE_INFO,
-    ).derive(access_token.encode("utf-8"))
-
-
-def _write_encrypted_disk_cache(
-    *,
-    cache_key: _CacheKey,
-    access_token: str,
-    entry: _CachedFetch,
-    home_path: Optional[Path] = None,
-) -> None:
-    """Persist an encrypted last-good cache entry atomically.
-
-    Best-effort by design: cache write failure must never block a fresh BWS
-    fetch.  The raw BWS access token is not stored; it only derives the AES key.
-    """
-    path = _encrypted_disk_cache_path(home_path)
-    try:
-        cache_dir = path.parent
-        cache_dir.mkdir(parents=True, exist_ok=True)
-        try:
-            os.chmod(cache_dir, 0o700)
-        except OSError:
-            pass
-        salt = os.urandom(16)
-        nonce = os.urandom(12)
-        serialized_key = _cache_key_str(cache_key)
-        key = _derive_encrypted_cache_key(access_token, salt)
-        plaintext = json.dumps(
-            {"secrets": entry.secrets, "fetched_at": entry.fetched_at},
-            separators=(",", ":"),
-        ).encode("utf-8")
-        ciphertext = AESGCM(key).encrypt(
-            nonce, plaintext, serialized_key.encode("utf-8")
-        )
-        payload = {
-            "version": _ENCRYPTED_CACHE_VERSION,
-            "key": serialized_key,
-            "salt": _b64e(salt),
-            "nonce": _b64e(nonce),
-            "ciphertext": _b64e(ciphertext),
-        }
-        fd, tmp = tempfile.mkstemp(
-            prefix=".bws_cache_enc_", suffix=".tmp", dir=str(cache_dir)
-        )
-        try:
-            with os.fdopen(fd, "w", encoding="utf-8") as f:
-                json.dump(payload, f)
-            os.chmod(tmp, 0o600)
-            os.replace(tmp, path)
-            # A successful encrypted write completes migration; remove the
-            # legacy plaintext cache so stale secrets cannot remain on disk.
-            try:
-                _disk_cache_path(home_path).unlink()
-            except FileNotFoundError:
-                pass
-            except OSError:
-                pass
-        except BaseException:
-            try:
-                os.unlink(tmp)
-            except OSError:
-                pass
-            raise
-    except Exception:  # noqa: BLE001 — best-effort cache only
-        return
-
-
-def _read_encrypted_disk_cache(
-    *,
-    cache_key: _CacheKey,
-    access_token: str,
-    max_age_seconds: float,
-    home_path: Optional[Path] = None,
-) -> Optional[_CachedFetch]:
-    """Return a decrypted encrypted-cache entry if it matches and is in-window."""
-    if max_age_seconds <= 0:
-        return None
-    path = _encrypted_disk_cache_path(home_path)
-    try:
-        payload = json.loads(path.read_text(encoding="utf-8"))
-        if not isinstance(payload, dict):
-            return None
-        serialized_key = _cache_key_str(cache_key)
-        if payload.get("version") != _ENCRYPTED_CACHE_VERSION:
-            return None
-        if payload.get("key") != serialized_key:
-            return None
-        salt = _b64d(str(payload.get("salt", "")))
-        nonce = _b64d(str(payload.get("nonce", "")))
-        ciphertext = _b64d(str(payload.get("ciphertext", "")))
-        key = _derive_encrypted_cache_key(access_token, salt)
-        raw = AESGCM(key).decrypt(
-            nonce, ciphertext, serialized_key.encode("utf-8")
-        )
-        inner = json.loads(raw.decode("utf-8"))
-        if not isinstance(inner, dict):
-            return None
-        secrets = inner.get("secrets")
-        inner_fetched_at = inner.get("fetched_at")
-        if not isinstance(secrets, dict) or not isinstance(inner_fetched_at, (int, float)):
-            return None
-        entry_age = time.time() - float(inner_fetched_at)
-        if entry_age < 0 or entry_age > max_age_seconds:
-            return None
-        typed = {
-            k: v for k, v in secrets.items()
-            if isinstance(k, str) and isinstance(v, str)
-        }
-        return _CachedFetch(secrets=typed, fetched_at=float(inner_fetched_at))
-    except Exception:  # noqa: BLE001 — cache miss on parse/decrypt/I/O errors
-        return None
-
-
 def fetch_bitwarden_secrets(
    *,
    access_token: str,
@@ -501,8 +357,6 @@ def fetch_bitwarden_secrets(
    use_cache: bool = True,
    server_url: str = "",
    home_path: Optional[Path] = None,
-    encrypted_cache_enabled: bool = False,
-    encrypted_cache_max_stale_seconds: float = 0,
 ) -> Tuple[Dict[str, str], List[str]]:
    """Pull the secrets for ``project_id`` from Bitwarden Secrets Manager.

@@ -514,13 +368,12 @@ def fetch_bitwarden_secrets(
    (``https://vault.bitwarden.com``, US Cloud).  This is plumbed into
    the subprocess as ``BWS_SERVER_URL``.

-    ``cache_ttl_seconds`` controls the normal fresh cache.  When
-    ``encrypted_cache_enabled`` is true, fresh cache entries are written as
-    AES-GCM encrypted JSON instead of plaintext, and a last-good encrypted
-    entry may be used after NETWORK/TIMEOUT failures for up to
-    ``encrypted_cache_max_stale_seconds``.  This stale fallback is separate
-    from the fresh-cache TTL so operators can set ``cache_ttl_seconds: 0``
-    while still keeping an encrypted break-glass cache for offline startup.
+    Caching is a two-layer LRU: an in-process dict (for hot-reload paths
+    inside one process) and a disk-persisted JSON file under
+    ``<hermes_home>/cache/bws_cache.json`` (for back-to-back CLI invocations).
+    Both share the same TTL.  Pass ``home_path`` so disk cache lookups find
+    the right directory in tests / non-standard installs; otherwise we fall
+    back to ``$HERMES_HOME`` / ``~/.hermes``.

    Raises :class:`RuntimeError` for fatal conditions (missing binary,
    auth failure, unparseable output).  Callers in the env_loader path
@@ -533,20 +386,12 @@ def fetch_bitwarden_secrets(
        raise RuntimeError("Bitwarden project_id is empty")

    cache_key = (_token_fingerprint(access_token), project_id, server_url or "")
-    if use_cache and cache_ttl_seconds > 0:
+    if use_cache:
        cached = _CACHE.get(cache_key)
        if cached and cached.is_fresh(cache_ttl_seconds):
            return cached.secrets, []
        # L2: disk cache. ~5ms on cache hit vs ~380ms for `bws secret list`.
-        if encrypted_cache_enabled:
-            disk_cached = _read_encrypted_disk_cache(
-                cache_key=cache_key,
-                access_token=access_token,
-                max_age_seconds=cache_ttl_seconds,
-                home_path=home_path,
-            )
-        else:
-            disk_cached = _DISK_CACHE.read(cache_key, cache_ttl_seconds, home_path)
+        disk_cached = _DISK_CACHE.read(cache_key, cache_ttl_seconds, home_path)
        if disk_cached is not None:
            # Promote into in-process cache so subsequent fetches in the
            # same process skip the disk read too.
@@ -562,107 +407,14 @@ def fetch_bitwarden_secrets(
            "`hermes secrets bitwarden setup`."
        )

-    try:
-        secrets, warnings = _run_bws_list(bws, access_token, project_id, server_url)
-    except RuntimeError as exc:
-        # Live fetch failed. Fall back to a stale disk cache ONLY for
-        # transport-level failures (network down, DNS error, transient BWS
-        # outage / timeout) — never for AUTH_FAILED or a malformed-output
-        # INTERNAL error, where serving old secrets would mask a real
-        # config/credential problem the caller needs to see.  Without this
-        # fallback a fleet of bots sharing one BWS project all stop working
-        # on a single network blip.
-        #
-        # Two fallback tiers share the transport-only gate:
-        # * encrypted cache (opt-in) — AES-GCM payload keyed off the
-        #   bootstrap token, with its own max_stale_seconds window.  When
-        #   enabled it is the ONLY fallback consulted: the whole point is
-        #   that the at-rest payload is never plaintext, so we don't
-        #   quietly serve the plaintext file alongside it.
-        # * plaintext disk cache (default) — the ordinary DiskCache file.
-        #   `cache_ttl_seconds <= 0` means the caller opted out of caching
-        #   entirely (DiskCache.read/write both short-circuit on it) —
-        #   honor that on the fallback path too.  `ttl_seconds=inf` on the
-        #   read bypasses freshness (we explicitly want a stale hit); the
-        #   caller's real TTL gates whether we even attempt the read.
-        kind = _classify_bws_error(str(exc))
-        if use_cache and kind in (ErrorKind.NETWORK, ErrorKind.TIMEOUT):
-            if encrypted_cache_enabled:
-                stale = _read_encrypted_disk_cache(
-                    cache_key=cache_key,
-                    access_token=access_token,
-                    max_age_seconds=encrypted_cache_max_stale_seconds,
-                    home_path=home_path,
-                )
-                if stale is not None:
-                    age = max(0.0, time.time() - stale.fetched_at)
-                    _CACHE[cache_key] = stale
-                    return stale.secrets, [
-                        f"bws live fetch failed ({exc}); falling back to "
-                        f"stale ENCRYPTED disk cache ({int(age)}s old)"
-                    ]
-            elif cache_ttl_seconds > 0:
-                stale = _DISK_CACHE.read(cache_key, float("inf"), home_path)
-                if stale is not None:
-                    age = max(0.0, time.time() - stale.fetched_at)
-                    _CACHE[cache_key] = stale
-                    return stale.secrets, [
-                        f"bws live fetch failed ({exc}); "
-                        f"falling back to stale disk cache ({int(age)}s old)"
-                    ]
-        raise
+    secrets, warnings = _run_bws_list(bws, access_token, project_id, server_url)
    entry = _CachedFetch(secrets=secrets, fetched_at=time.time())
+    _CACHE[cache_key] = entry
    if use_cache:
-        if cache_ttl_seconds > 0:
-            _CACHE[cache_key] = entry
-        if encrypted_cache_enabled:
-            # Encryption is the storage policy; max_stale_seconds only controls
-            # whether an outage may consume the last-good entry.  Never fall
-            # back to the plaintext cache just because stale fallback is off.
-            _write_encrypted_disk_cache(
-                cache_key=cache_key,
-                access_token=access_token,
-                entry=entry,
-                home_path=home_path,
-            )
-        elif cache_ttl_seconds > 0:
-            _DISK_CACHE.write(cache_key, entry, cache_ttl_seconds, home_path)
+        _DISK_CACHE.write(cache_key, entry, cache_ttl_seconds, home_path)
    return secrets, warnings


-def _summarize_bws_stderr(raw: str) -> str:
-    """Reduce a bws (Rust color-eyre) error dump to its cause line(s).
-
-    bws failures look like::
-
-        Error:
-           0: Received error message from server: [400 Bad Request] {"error":"invalid_client"}
-
-        Location:
-           crates/bws/src/main.rs:108
-        ...
-
-    Everything from ``Location:`` on is diagnostic noise for a Hermes
-    user.  Keep the numbered cause lines (joined), drop the rest, and
-    fall back to the stripped raw text when the shape is unrecognized.
-    """
-    text = raw.replace("\x1b", "").strip()
-    if not text:
-        return text
-    causes: List[str] = []
-    for line in text.splitlines():
-        stripped = line.strip()
-        if stripped.startswith(("Location:", "Backtrace omitted", "Run with ")):
-            break
-        if stripped in ("", "Error:"):
-            continue
-        # Cause lines are numbered "0: ...", "1: ..." — strip the index.
-        stripped = re.sub(r"^\d+:\s*", "", stripped)
-        if stripped:
-            causes.append(stripped)
-    return "; ".join(causes) if causes else text
-
-
 def _run_bws_list(
    bws: Path, access_token: str, project_id: str, server_url: str = ""
 ) -> Tuple[Dict[str, str], List[str]]:
@@ -696,11 +448,9 @@ def _run_bws_list(
        raise RuntimeError(f"failed to invoke bws: {exc}") from exc

    if proc.returncode != 0:
-        # bws writes auth/network errors to stderr as a Rust error-report
-        # dump (color-eyre): an "Error:" header, indented cause lines, then
-        # "Location:" / "Backtrace omitted" noise.  Strip ANSI and boil it
-        # down to the meaningful cause line(s) before surfacing.
-        err = _summarize_bws_stderr(proc.stderr or proc.stdout or "")
+        # bws writes auth/network errors to stderr in plain English.
+        # Strip ANSI just in case and surface the first 200 chars.
+        err = (proc.stderr or proc.stdout or "").strip().replace("\x1b", "")
        raise RuntimeError(
            f"bws exited {proc.returncode}: {err[:200]}"
        )
@@ -752,8 +502,6 @@ def apply_bitwarden_secrets(
    auto_install: bool = True,
    server_url: str = "",
    home_path: Optional[Path] = None,
-    encrypted_cache_enabled: bool = False,
-    encrypted_cache_max_stale_seconds: float = 0,
 ) -> FetchResult:
    """Pull secrets from BSM and set them on ``os.environ``.

@@ -805,8 +553,6 @@ def apply_bitwarden_secrets(
            cache_ttl_seconds=cache_ttl_seconds,
            server_url=server_url,
            home_path=home_path,
-            encrypted_cache_enabled=encrypted_cache_enabled,
-            encrypted_cache_max_stale_seconds=encrypted_cache_max_stale_seconds,
        )
    except RuntimeError as exc:
        result.error = str(exc)
@@ -876,16 +622,9 @@ class BitwardenSource(SecretSource):
            },
            "project_id": {"description": "BSM project UUID", "default": ""},
            "cache_ttl_seconds": {
-                "description": "Fresh disk+memory cache TTL; 0 disables fresh-cache reuse",
+                "description": "Disk+memory cache TTL; 0 disables",
                "default": 300,
            },
-            "encrypted_cache": {
-                "description": "Encrypted last-good cache for network/timeout fallback",
-                "default": {
-                    "enabled": False,
-                    "max_stale_seconds": 0,
-                },
-            },
            "override_existing": {
                "description": "BSM values overwrite .env/shell values",
                "default": True,
@@ -939,14 +678,6 @@ class BitwardenSource(SecretSource):
        except (TypeError, ValueError):
            ttl = 300.0

-        encrypted_cfg = cfg.get("encrypted_cache")
-        encrypted_cfg = encrypted_cfg if isinstance(encrypted_cfg, dict) else {}
-        encrypted_enabled = bool(encrypted_cfg.get("enabled", False))
-        try:
-            encrypted_max_stale = float(encrypted_cfg.get("max_stale_seconds", 0))
-        except (TypeError, ValueError):
-            encrypted_max_stale = 0.0
-
        try:
            secrets, warnings = fetch_bitwarden_secrets(
                access_token=access_token,
@@ -955,36 +686,16 @@ class BitwardenSource(SecretSource):
                cache_ttl_seconds=ttl,
                server_url=str(cfg.get("server_url", "") or "").strip(),
                home_path=home_path,
-                encrypted_cache_enabled=encrypted_enabled,
-                encrypted_cache_max_stale_seconds=encrypted_max_stale,
            )
        except RuntimeError as exc:
            result.error = str(exc)
            result.error_kind = _classify_bws_error(str(exc))
-            if result.error_kind == ErrorKind.AUTH_FAILED:
-                # Translate the raw OAuth reject into what it actually means
-                # for the user before the mechanics.
-                result.error = (
-                    "Bitwarden rejected the machine-account access token "
-                    f"({access_token_env}) — it was likely revoked, expired, "
-                    f"or belongs to another region.  ({result.error})"
-                )
            return result

        result.secrets = secrets
        result.warnings.extend(warnings)
        return result

-    def remediation(self, kind, cfg: dict) -> str:
-        if kind in (ErrorKind.AUTH_FAILED, ErrorKind.AUTH_EXPIRED):
-            return (
-                "Run `hermes secrets bitwarden token` to paste a fresh access "
-                "token (create one in the Bitwarden web app: Secrets Manager → "
-                "Machine accounts → Access tokens).  Wrong region?  Re-run "
-                "`hermes secrets bitwarden setup` and pick EU/self-hosted."
-            )
-        return super().remediation(kind, cfg)
-

 def _classify_bws_error(message: str) -> ErrorKind:
    """Best-effort mapping of bws failure text onto the shared taxonomy."""
@@ -994,13 +705,7 @@ def _classify_bws_error(message: str) -> ErrorKind:
    if "binary not available" in lowered or "failed to invoke" in lowered:
        return ErrorKind.BINARY_MISSING
    if any(tok in lowered for tok in ("unauthorized", "invalid token",
-                                      "access token", "401", "403",
-                                      # The BSM identity endpoint rejects a
-                                      # revoked/expired/deleted machine-account
-                                      # token with an OAuth-style
-                                      # `[400 Bad Request] {"error":"invalid_client"}`.
-                                      "invalid_client", "invalid_grant",
-                                      "400 bad request")):
+                                      "access token", "401", "403")):
        return ErrorKind.AUTH_FAILED
    if any(tok in lowered for tok in ("network", "connection", "resolve",
                                      "download", "dns")):
@@ -1013,22 +718,6 @@ def _classify_bws_error(message: str) -> ErrorKind:
 # ---------------------------------------------------------------------------


-def clear_caches(home_path: Optional[Path] = None) -> None:
-    """Drop in-process AND disk caches (plaintext and encrypted).
-
-    Used after a token rotation (`hermes secrets bitwarden token`) so the
-    next startup fetches fresh with the new credential instead of serving
-    a pull cached under the old token's fingerprint.  The encrypted cache
-    is keyed off the old token too, so it must go as well.
-    """
-    _CACHE.clear()
-    _DISK_CACHE.clear(home_path)
-    try:
-        _encrypted_disk_cache_path(home_path).unlink()
-    except (FileNotFoundError, OSError):
-        pass
-
-
 def _reset_cache_for_tests(home_path: Optional[Path] = None) -> None:
    """Clear in-process AND disk caches.

@@ -1036,4 +725,5 @@ def _reset_cache_for_tests(home_path: Optional[Path] = None) -> None:
    Without it we fall back to the same default resolution as the cache
    writer itself.
    """
-    clear_caches(home_path)
+    _CACHE.clear()
+    _DISK_CACHE.clear(home_path)
@@ -1,488 +0,0 @@
-"""``command`` secret source — resolve secrets via a user-configured helper.
-
-Ports the security semantics of the desktop app's TypeScript
-``CommandSecretsProvider`` (hermes-desktop ``src/main/secrets/commandProvider.ts``)
-to the Python agent.  The helper command (e.g. ``keepassxc-cli``,
-``secret-tool``, or a script that cats a tmpfs env file) comes from
-``secrets.command`` in ``config.yaml`` — NEVER from ``.env``, which holds
-only secret values.
-
-Security model (mirrors the TS provider line-for-line where it matters):
-
-* The command string is the USER'S OWN configuration (same trust level as
-  the ``.env`` file they control), so it is run via ``/bin/sh -c <command>``.
-* The requested key is passed to the child ONLY via the ``HERMES_SECRET_KEY``
-  environment variable — it is NEVER interpolated into the shell string, so
-  a hostile key name (e.g. ``"; rm -rf ~``) is inert data, not code.
-* Hard timeout (default 3s) + output cap (default 1 MiB); any failure
-  (non-zero exit, timeout, spawn failure, oversized output) degrades to
-  "no value" rather than raising.
-* Failures log ONLY structured fields (exit code / signal / errno) to
-  stderr — never the command string, the helper's stderr, or any secret
-  value.  The helper's stderr is captured via a pipe and DISCARDED so its
-  diagnostics (which can carry secret material) never reach our stderr.
-* The startup/apply path runs the helper exactly ONCE (with an empty
-  ``HERMES_SECRET_KEY``) — it is never called per-key in a loop, so a
-  helper that blocks (e.g. on a vault unlock prompt) can't be spawned
-  dozens of times.
-* PLATFORM: the provider is POSIX-only (needs ``/bin/sh``).  On Windows it
-  degrades to an empty result with a warning; Windows users stay on the
-  default ``env`` provider.
-"""
-
-from __future__ import annotations
-
-import os
-import platform
-import re
-import signal as _signal
-import subprocess
-import sys
-from pathlib import Path
-from typing import Dict, Optional
-
-# Reuse the exact result shape the bitwarden source returns so
-# hermes_cli.env_loader can consume both providers identically.
-from agent.secret_sources.base import ErrorKind, SecretSource
-from agent.secret_sources.bitwarden import FetchResult
-
-__all__ = [
-    "FetchResult",
-    "apply_command_secrets",
-    "get_command_secret",
-    "list_command_secrets",
-    "parse_secret_output",
-    "unquote_dotenv_value",
-]
-
-# Hard cap so a hung helper can never wedge startup.  Kept deliberately
-# TIGHT (3s) — a configured helper MUST be fast and NON-INTERACTIVE
-# (e.g. `keepassxc-cli` against an already-unlocked DB, `secret-tool
-# lookup`, or `cat`-ing a tmpfs env file), NOT something that prompts
-# for a touch/PIN.
-_COMMAND_TIMEOUT_SECONDS = 3.0
-# Defensive cap on helper output (1 MiB) — a misbehaving command can't OOM us.
-_MAX_OUTPUT_BYTES = 1024 * 1024
-
-# A line is treated as a KEY=VALUE pair only when it matches an env-key
-# shape before the '='.  Anchored; `.` does not cross newlines, so a
-# multi-line blob never matches as a single "env-shaped" value.
-_ENV_LINE = re.compile(r"^([A-Za-z_][A-Za-z0-9_]*)=(.*)$")
-
-
-def _is_windows() -> bool:
-    return os.name == "nt" or platform.system() == "Windows"
-
-
-def unquote_dotenv_value(raw: str) -> str:
-    """Strip a single layer of matching surrounding quotes from a dotenv value.
-
-    Requires length >= 2 so a lone quote (``"``) is left intact rather than
-    collapsing to empty, and ``""``/``''`` correctly yield an empty string.
-    Shared by the single-key parser and the list path so both unquote
-    identically.
-    """
-    t = raw.strip()
-    if len(t) >= 2 and (
-        (t.startswith('"') and t.endswith('"'))
-        or (t.startswith("'") and t.endswith("'"))
-    ):
-        return t[1:-1]
-    return t
-
-
-def parse_secret_output(stdout: str, wanted_key: str) -> Optional[str]:
-    """Parse a secret-fetch helper's stdout.  Supports BOTH shapes:
-
-    * a bare value (single secret): the whole trimmed stdout is the value.
-    * a dotenv blob (KEY=VALUE lines): parse them and return the entry for
-      ``wanted_key``.
-
-    Mirrors the TS ``parseSecretOutput`` exactly, including the cross-key
-    misroute guard and the base64-padding disambiguation.
-    """
-    text = stdout.replace("\r\n", "\n")
-    lines = text.split("\n")
-
-    # 1. Exact dotenv match wins: scan for a `wanted_key=...` line.  This
-    #    is deterministic and never returns another key's value.
-    dotenv_lines = [
-        line
-        for line in (raw.strip() for raw in lines)
-        if line and not line.startswith("#") and _ENV_LINE.match(line)
-    ]
-    for line in dotenv_lines:
-        m = _ENV_LINE.match(line)
-        assert m is not None  # filtered above
-        if m.group(1) == wanted_key:
-            value = unquote_dotenv_value(m.group(2))
-            # Whitespace-only (e.g. a quoted `K="  "` placeholder) is "no
-            # value": it would otherwise flow into an Authorization header
-            # → guaranteed 401.
-            return value if value.strip() != "" else None
-
-    # 2. The output is a multi-key dotenv dump that does NOT contain the
-    #    wanted key → None, rather than mis-returning an unrelated line as
-    #    a bare value.  Only >=2 env-shaped lines count as a dump: a SINGLE
-    #    non-matching env-shaped line falls through to the bare-value
-    #    branch, because a bare secret can itself match the KEY=VALUE shape
-    #    (e.g. base64 with '=' padding, "dGVzdA==") and must not be
-    #    misclassified as a dump.
-    if len(dotenv_lines) > 1:
-        return None
-
-    # 3. Otherwise treat the whole output as a single bare value (a per-key
-    #    helper that printed just the secret).  Trim first so whitespace-only
-    #    output (a ' '/'\t' placeholder entry) resolves to None, never a "key".
-    value = text.strip()
-    if value == "":
-        return None
-
-    # SECURITY (S2): a single env-shaped line for a DIFFERENT key must not
-    # be returned as the wanted secret.  A sloppy helper (e.g. `head -1
-    # env-file`, or a grep that matched the wrong line) emitting
-    # `OTHER_KEY=realvalue` would otherwise flow — key name, '=' and the
-    # OTHER key's value — into an Authorization header sent to the WANTED
-    # key's endpoint: cross-provider credential leakage, not just a 401.
-    # Disambiguation from a bare base64 secret: base64 padding only ever
-    # produces an env-shaped line whose "value" part is empty or all '='
-    # (`dGVzdA==` → key `dGVzdA`, value `=`), so a non-trivial value part
-    # after a non-matching key means a misrouted dotenv entry → None.
-    env_shaped = _ENV_LINE.match(value)
-    if (
-        env_shaped
-        and env_shaped.group(1) != wanted_key
-        and re.fullmatch(r"=*", env_shaped.group(2).strip()) is None
-    ):
-        return None
-    return value
-
-
-def _run_helper(
-    command: str,
-    secret_key: str,
-    timeout_seconds: float,
-    max_output_bytes: int,
-) -> Optional[str]:
-    """Run the helper via ``/bin/sh -c`` and return its stdout, or None.
-
-    The key is passed as DATA via ``HERMES_SECRET_KEY`` — never interpolated
-    into the command string.  Both stdout and stderr are captured via pipes
-    (never inherited); stderr is discarded.  Any failure logs structured
-    fields only and returns None — never raises.
-    """
-    if _is_windows():
-        print(
-            "[secrets:command] the 'command' provider is POSIX-only "
-            "(needs /bin/sh); resolving no value on Windows",
-            file=sys.stderr,
-        )
-        return None
-
-    env = os.environ.copy()
-    env["HERMES_SECRET_KEY"] = secret_key
-
-    try:
-        proc = subprocess.Popen(  # noqa: S602 — command is the user's own config
-            ["/bin/sh", "-c", command],
-            env=env,
-            stdin=subprocess.DEVNULL,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,  # captured and DISCARDED — never inherited
-            start_new_session=True,  # so the hard timeout can kill the whole group
-        )
-    except OSError as exc:
-        print(
-            f"[secrets:command] helper failed to spawn; resolving no value: "
-            f"errno={exc.errno}",
-            file=sys.stderr,
-        )
-        return None
-
-    try:
-        stdout_bytes, _stderr_discarded = proc.communicate(timeout=timeout_seconds)
-    except subprocess.TimeoutExpired:
-        # Hard timeout: kill the whole process group (a helper script may
-        # have forked children that would otherwise keep the pipe open).
-        # POSIX-only by construction: _run_helper early-returns on Windows
-        # before ever spawning, so this line can't execute there.
-        try:
-            os.killpg(os.getpgid(proc.pid), _signal.SIGKILL)  # windows-footgun: ok
-        except (ProcessLookupError, PermissionError, OSError):
-            proc.kill()
-        try:
-            proc.communicate(timeout=1.0)
-        except (subprocess.TimeoutExpired, ValueError, OSError):
-            pass
-        print(
-            f"[secrets:command] helper timed out after {timeout_seconds:g}s; "
-            f"resolving no value",
-            file=sys.stderr,
-        )
-        return None
-
-    if proc.returncode != 0:
-        # Structured fields ONLY — never the command string or the helper's
-        # stderr (either can carry secret material).
-        if proc.returncode < 0:
-            try:
-                sig = _signal.Signals(-proc.returncode).name
-            except ValueError:
-                sig = str(-proc.returncode)
-            code, signame = "?", sig
-        else:
-            code, signame = str(proc.returncode), "none"
-        print(
-            f"[secrets:command] helper failed; resolving no value: "
-            f"code={code} signal={signame}",
-            file=sys.stderr,
-        )
-        return None
-
-    if len(stdout_bytes) > max_output_bytes:
-        print(
-            f"[secrets:command] helper output exceeded the "
-            f"{max_output_bytes}-byte cap; resolving no value",
-            file=sys.stderr,
-        )
-        return None
-
-    return stdout_bytes.decode("utf-8", errors="replace")
-
-
-def _parse_dotenv_map(stdout: str) -> Dict[str, str]:
-    """Parse a KEY=VALUE blob into a map (the list/enumerate path).
-
-    Mirrors the TS ``list()``: only env-shaped lines contribute; comments
-    and non-matching lines are skipped.  A bare-value helper yields ``{}``
-    — per-key resolution via :func:`get_command_secret` still works.
-    """
-    out: Dict[str, str] = {}
-    for raw in stdout.replace("\r\n", "\n").split("\n"):
-        line = raw.strip()
-        if not line or line.startswith("#"):
-            continue
-        m = _ENV_LINE.match(line)
-        if not m:
-            continue
-        out[m.group(1)] = unquote_dotenv_value(m.group(2))
-    return out
-
-
-def get_command_secret(
-    *,
-    command: str,
-    key: str,
-    timeout_seconds: float = _COMMAND_TIMEOUT_SECONDS,
-    max_output_bytes: int = _MAX_OUTPUT_BYTES,
-) -> Optional[str]:
-    """Resolve a single secret by running the helper with the key in
-    ``HERMES_SECRET_KEY``.  Returns None on any failure — never raises."""
-    command = (command or "").strip()
-    if not command:
-        return None
-    stdout = _run_helper(command, key, timeout_seconds, max_output_bytes)
-    if stdout is None:
-        return None
-    return parse_secret_output(stdout, key)
-
-
-def list_command_secrets(
-    *,
-    command: str,
-    timeout_seconds: float = _COMMAND_TIMEOUT_SECONDS,
-    max_output_bytes: int = _MAX_OUTPUT_BYTES,
-) -> Dict[str, str]:
-    """Enumerate secrets by running the helper ONCE with an empty key.
-
-    Returns the dotenv map ONLY when the helper emits a KEY=VALUE blob;
-    a bare-value helper returns ``{}``.  Never raises.
-    """
-    command = (command or "").strip()
-    if not command:
-        return {}
-    stdout = _run_helper(command, "", timeout_seconds, max_output_bytes)
-    if stdout is None:
-        return {}
-    return _parse_dotenv_map(stdout)
-
-
-# ---------------------------------------------------------------------------
-# Public entry point — called from hermes_cli.env_loader
-# ---------------------------------------------------------------------------
-
-
-def apply_command_secrets(
-    *,
-    command: str,
-    override_existing: bool = False,
-    timeout_seconds: float = _COMMAND_TIMEOUT_SECONDS,
-    max_output_bytes: int = _MAX_OUTPUT_BYTES,
-    home_path: Optional[Path] = None,
-) -> FetchResult:
-    """Run the helper once at startup and set its KEY=VALUE output on
-    ``os.environ``.
-
-    LEGACY shim retained for API symmetry with ``apply_bitwarden_secrets``;
-    the startup path goes through :class:`CommandSource` + the registry
-    orchestrator instead (which owns precedence and the environ writes).
-    """
-    result = FetchResult()
-
-    command = (command or "").strip()
-    if not command:
-        result.error = (
-            "secrets.command.enabled is true but secrets.command.command is "
-            "empty.  Set the helper command in config.yaml."
-        )
-        return result
-
-    if _is_windows():
-        result.warnings.append(
-            "the 'command' secret source is POSIX-only (needs /bin/sh); "
-            "skipping on Windows"
-        )
-        return result
-
-    # The list/enumerate path: run the helper exactly ONCE with an empty
-    # HERMES_SECRET_KEY and parse its stdout as a dotenv blob.
-    stdout = _run_helper(command, "", timeout_seconds, max_output_bytes)
-    if stdout is None:
-        # _run_helper already logged structured fields to stderr.
-        result.warnings.append(
-            "helper command failed at startup; no secrets applied "
-            "(process env / .env values remain in effect)"
-        )
-        return result
-
-    secrets = _parse_dotenv_map(stdout)
-    result.secrets = secrets
-    if not secrets:
-        result.warnings.append(
-            "helper output was not a KEY=VALUE map; nothing applied at "
-            "startup (a bare-value helper still resolves single keys on demand)"
-        )
-        return result
-
-    for key, value in secrets.items():
-        if value.strip() == "":
-            # Whitespace-only placeholder entries are "no value" — applying
-            # them would flow into an Authorization header → guaranteed 401.
-            result.skipped.append(key)
-            continue
-        if not override_existing and os.environ.get(key):
-            # Process env / .env win — same precedence as bitwarden.
-            result.skipped.append(key)
-            continue
-        os.environ[key] = value
-        result.applied.append(key)
-
-    return result
-
-
-# ---------------------------------------------------------------------------
-# SecretSource adapter — the registry-facing wrapper around this module.
-# ---------------------------------------------------------------------------
-
-
-class CommandSource(SecretSource):
-    """User-configured helper command as a registered secret source.
-
-    Composes with the other sources (Bitwarden, 1Password, plugins) through
-    the ``apply_all()`` orchestrator — enable any combination simultaneously;
-    there is deliberately NO single-provider selector.  ``fetch()`` only
-    fetches: precedence, ``override_existing`` semantics, conflict warnings,
-    and the ``os.environ`` writes are the orchestrator's job.
-
-    Bulk shape: the helper enumerates a KEY=VALUE blob in one run.  Config::
-
-        secrets:
-          command:
-            enabled: true
-            command: "cat /run/user/1000/hermes-secrets.env"
-            # or per-vault CLIs: keepassxc-cli / secret-tool / pass / gpg —
-            # anything fast and NON-interactive.
-    """
-
-    name = "command"
-    label = "Command helper"
-    shape = "bulk"
-
-    def config_schema(self) -> dict:
-        return {
-            "enabled": {"description": "Master switch", "default": False},
-            "command": {
-                "description": "Helper run via /bin/sh -c; must print a "
-                               "KEY=VALUE blob on stdout",
-                "default": "",
-            },
-            "helper_timeout_seconds": {
-                "description": "Hard timeout for one helper run",
-                "default": _COMMAND_TIMEOUT_SECONDS,
-            },
-            "override_existing": {
-                "description": "Helper values overwrite .env/shell values",
-                "default": False,
-            },
-        }
-
-    def fetch(self, cfg: dict, home_path: Path) -> FetchResult:
-        cfg = cfg if isinstance(cfg, dict) else {}
-        result = FetchResult()
-
-        command = str(cfg.get("command") or "").strip()
-        if not command:
-            result.error = (
-                "secrets.command.enabled is true but secrets.command.command "
-                "is empty.  Set the helper command in config.yaml."
-            )
-            result.error_kind = ErrorKind.NOT_CONFIGURED
-            return result
-
-        if _is_windows():
-            result.error = (
-                "the 'command' secret source is POSIX-only (needs /bin/sh); "
-                "skipping on Windows"
-            )
-            result.error_kind = ErrorKind.NOT_CONFIGURED
-            return result
-
-        try:
-            timeout = float(cfg.get("helper_timeout_seconds",
-                                    _COMMAND_TIMEOUT_SECONDS))
-        except (TypeError, ValueError):
-            timeout = _COMMAND_TIMEOUT_SECONDS
-
-        stdout = _run_helper(command, "", timeout, _MAX_OUTPUT_BYTES)
-        if stdout is None:
-            # _run_helper already logged structured fields to stderr.
-            result.error = (
-                "helper command failed (see structured fields above); "
-                "no secrets applied"
-            )
-            result.error_kind = ErrorKind.INTERNAL
-            return result
-
-        secrets = _parse_dotenv_map(stdout)
-        if not secrets:
-            result.warnings.append(
-                "helper output was not a KEY=VALUE map; nothing to apply"
-            )
-            return result
-
-        result.secrets = secrets
-        return result
-
-    def remediation(self, kind, cfg: dict) -> str:
-        if kind == ErrorKind.NOT_CONFIGURED:
-            return (
-                "Set secrets.command.command in config.yaml to a fast, "
-                "non-interactive helper that prints KEY=VALUE lines."
-            )
-        if kind == ErrorKind.INTERNAL:
-            return (
-                "Run the helper manually in a shell to see its real error — "
-                "Hermes discards helper stderr so diagnostics can't leak "
-                "secret material."
-            )
-        return super().remediation(kind, cfg)
@@ -98,9 +98,6 @@ _OP_ENV_ALLOWLIST = (
    "OP_ACCOUNT",
    "OP_CONNECT_HOST",
    "OP_CONNECT_TOKEN",
-    # Lets a user skip op's desktop-app integration probe (which can hang with
-    # no timeout on a wedged desktop container) and go straight to token auth.
-    "OP_LOAD_DESKTOP_APP_SETTINGS",
 )


@@ -175,19 +172,16 @@ def _validate_references(
 def _auth_fingerprint(token_env: str) -> str:
    """SHA-256 prefix over the auth material `op` would use.

-    Folds in the service-account token, ``OP_ACCOUNT``, the 1Password Connect
-    ``OP_CONNECT_HOST``/``OP_CONNECT_TOKEN``, and *all* ``OP_SESSION_*`` vars
-    (the names `op` actually exports for interactive sessions —
-    ``OP_SESSION_<account_shorthand>``).  Signing out and into a different
-    identity therefore changes the cache key, so a value cached under a
-    previous identity is never served under a new one.  Never logged or
+    Folds in the service-account token, ``OP_ACCOUNT``, and *all*
+    ``OP_SESSION_*`` vars (the names `op` actually exports for interactive
+    sessions — ``OP_SESSION_<account_shorthand>``).  Signing out and into a
+    different identity therefore changes the cache key, so a value cached under
+    a previous identity is never served under a new one.  Never logged or
    displayed; the raw token never leaves this hash.
    """
    parts: List[str] = [
        f"token={os.environ.get(token_env, '')}",
        f"account={os.environ.get('OP_ACCOUNT', '')}",
-        f"connect_host={os.environ.get('OP_CONNECT_HOST', '')}",
-        f"connect_token={os.environ.get('OP_CONNECT_TOKEN', '')}",
    ]
    for key in sorted(os.environ):
        if key.startswith("OP_SESSION_"):
@@ -613,24 +607,6 @@ class OnePasswordSource(SecretSource):
        result.warnings.extend(fetch_warnings)
        return result

-    def remediation(self, kind, cfg: dict) -> str:
-        if kind in (ErrorKind.AUTH_FAILED, ErrorKind.AUTH_EXPIRED):
-            token_env = _DEFAULT_TOKEN_ENV
-            if isinstance(cfg, dict):
-                token_env = str(cfg.get("service_account_token_env") or token_env)
-            return (
-                "Run `hermes secrets onepassword token` to paste a fresh "
-                f"service-account token ({token_env}), or `op signin` for an "
-                "interactive session."
-            )
-        if kind == ErrorKind.BINARY_MISSING:
-            return (
-                "Install the 1Password CLI "
-                "(https://developer.1password.com/docs/cli/get-started/) or "
-                "set secrets.onepassword.binary_path."
-            )
-        return super().remediation(kind, cfg)
-

 def _classify_op_error(message: str) -> ErrorKind:
    """Best-effort mapping of op failure text onto the shared taxonomy."""
@@ -657,21 +633,11 @@ def _classify_op_error(message: str) -> ErrorKind:
 # ---------------------------------------------------------------------------


-def clear_caches(home_path: Optional[Path] = None) -> None:
-    """Drop in-process AND disk caches.
-
-    Used after a token rotation (`hermes secrets onepassword token`) so
-    the next startup resolves fresh with the new credential instead of
-    serving values cached under the old token's fingerprint.
-    """
-    _CACHE.clear()
-    _DISK_CACHE.clear(home_path)
-
-
 def _reset_cache_for_tests(home_path: Optional[Path] = None) -> None:
    """Clear in-process AND disk caches.

    Tests can pass ``home_path`` to scope the disk cleanup to a tmpdir.
    Without it we fall back to the same default resolution as the writer.
    """
-    clear_caches(home_path)
+    _CACHE.clear()
+    _DISK_CACHE.clear(home_path)
@@ -29,7 +29,6 @@ from __future__ import annotations

 import concurrent.futures
 import logging
-import os
 from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Dict, List, Optional
@@ -175,13 +174,6 @@ def _ensure_builtin_sources() -> None:
    except Exception:  # noqa: BLE001 — never block startup
        logger.warning("Failed to register bundled 1Password secret source",
                       exc_info=True)
-    try:
-        from agent.secret_sources.command import CommandSource
-
-        register_source(CommandSource())
-    except Exception:  # noqa: BLE001 — never block startup
-        logger.warning("Failed to register bundled command secret source",
-                       exc_info=True)


 def _reset_registry_for_tests() -> None:
@@ -283,43 +275,6 @@ def _ordered_enabled_sources(secrets_cfg: dict) -> List[SecretSource]:
    return enabled


-def _active_profile_name(home_path: Optional[Path]) -> str:
-    """Best-effort active profile name for profile-scoped secret aliases.
-
-    A named profile's HERMES_HOME is ``~/.hermes/profiles/<name>``; the
-    default profile (``~/.hermes``) returns "".
-    """
-    if home_path is not None:
-        resolved = Path(home_path)
-        if resolved.parent.name == "profiles" and resolved.name:
-            return resolved.name
-    for env_name in ("HERMES_PROFILE_NAME", "HERMES_PROFILE"):
-        value = os.environ.get(env_name, "").strip()
-        if value and value != "default":
-            return value
-    return ""
-
-
-# Only credential-shaped names get auto-aliased — a random profile-suffixed
-# var should not silently hydrate an unsuffixed name.
-_ALIAS_SUFFIXES = ("_API_KEY", "_TOKEN", "_SECRET", "_KEY", "_PASSWORD")
-
-
-def _profile_alias_target(var: str, profile: str) -> Optional[str]:
-    """Map ``FOO_<PROFILE>`` to ``FOO`` for the active profile when safe."""
-    if not profile:
-        return None
-    suffix = "_" + profile.replace("-", "_").upper()
-    if not var.endswith(suffix):
-        return None
-    alias = var[: -len(suffix)]
-    if not alias or not is_valid_env_name(alias):
-        return None
-    if not any(alias.endswith(s) for s in _ALIAS_SUFFIXES):
-        return None
-    return alias
-
-
 def apply_all(secrets_cfg: dict, home_path: Path,
              environ: Optional[Dict[str, str]] = None) -> ApplyReport:
    """Fetch from every enabled source and apply the merged result to env.
@@ -328,24 +283,14 @@ def apply_all(secrets_cfg: dict, home_path: Path,

    Precedence per env var (most-specific intent wins):

-    1. ``secrets.preserve_existing`` names — a pre-existing env value always
-       wins for these, even against a source with ``override_existing: true``
-       (escape hatch for profile-local platform secrets, #58073).
-    2. Pre-existing env (.env / shell) — unless the winning source has
+    1. Pre-existing env (.env / shell) — unless the winning source has
       ``override_existing: true``.
-    3. Mapped sources, in configured order.
-    4. Bulk sources, in configured order.
+    2. Mapped sources, in configured order.
+    3. Bulk sources, in configured order.

    First claim wins.  A later source that also carries the var gets a
    ``skipped_claimed`` entry and a conflict warning — never a silent
    clobber, and ``override_existing`` never applies across sources.
-
-    Profile aliasing (#51447): when running under a named profile, an applied
-    var ``FOO_<PROFILE>`` (credential-shaped suffixes only) also hydrates the
-    canonical ``FOO`` so platform adapters and plugins that read fixed env
-    names see the profile's value.  The alias obeys the same protected /
-    preserve / claimed / override guards and is disabled with
-    ``secrets.profile_alias: false``.
    """
    import os as _os

@@ -357,14 +302,6 @@ def apply_all(secrets_cfg: dict, home_path: Path,
    if not enabled:
        return report

-    preserve_raw = secrets_cfg.get("preserve_existing")
-    preserve: frozenset = frozenset(
-        n.strip() for n in preserve_raw if isinstance(n, str) and n.strip()
-    ) if isinstance(preserve_raw, list) else frozenset()
-
-    alias_enabled = bool(secrets_cfg.get("profile_alias", True))
-    profile = _active_profile_name(home_path) if alias_enabled else ""
-
    # Mapped sources outrank bulk sources regardless of list order:
    # an explicit VAR→ref binding is stronger intent than a project dump.
    ordered = ([s for s in enabled if s.shape == "mapped"]
@@ -384,15 +321,6 @@ def apply_all(secrets_cfg: dict, home_path: Path,
        except Exception:  # noqa: BLE001
            pass

-    # Every var any source supplies directly — an alias never shadows a
-    # var that some source will (or tried to) claim by its real name.
-    supplied_directly: set = set()
-    for _, _, result in fetches:
-        if result.ok:
-            supplied_directly.update(
-                v for v in result.secrets if isinstance(v, str)
-            )
-
    # Apply phase — sequential, first-wins, fully attributed.
    claimed: Dict[str, str] = {}  # var → source name that won it
    for source, cfg, result in fetches:
@@ -408,14 +336,15 @@ def apply_all(secrets_cfg: dict, home_path: Path,
        except Exception:  # noqa: BLE001
            override = False

-        def _try_apply(var: str, value: str, *, is_alias: bool = False) -> bool:
-            """Apply one var through the shared guard chain. True = applied."""
+        for var, value in result.secrets.items():
+            if not isinstance(var, str) or not isinstance(value, str):
+                continue
            if not is_valid_env_name(var):
                sr.skipped_invalid.append(var)
-                return False
+                continue
            if var in protected:
                sr.skipped_protected.append(var)
-                return False
+                continue
            if var in claimed:
                sr.skipped_claimed.append(var)
                report.conflicts.append(
@@ -423,14 +352,11 @@ def apply_all(secrets_cfg: dict, home_path: Path,
                    f"{source.name} also supplies it (first source wins — "
                    "remove one binding or reorder secrets.sources)"
                )
-                return False
+                continue
            existed = bool(env.get(var))
-            if existed and var in preserve:
-                sr.skipped_existing.append(var)
-                return False
            if existed and not override:
                sr.skipped_existing.append(var)
-                return False
+                continue
            env[var] = value
            claimed[var] = source.name
            sr.applied.append(var)
@@ -440,21 +366,5 @@ def apply_all(secrets_cfg: dict, home_path: Path,
                shape=source.shape,
                overrode_env=existed,
            )
-            return True
-
-        for var, value in result.secrets.items():
-            if not isinstance(var, str) or not isinstance(value, str):
-                continue
-            applied = _try_apply(var, value)
-
-            if not applied or not profile:
-                continue
-            alias = _profile_alias_target(var, profile)
-            if alias and alias not in supplied_directly and alias not in claimed:
-                if _try_apply(alias, value, is_alias=True):
-                    result.warnings.append(
-                        f"applied profile-scoped {var} as {alias} "
-                        f"(active profile {profile!r})"
-                    )

    return report
@@ -453,8 +453,8 @@ def reload_skills() -> Dict[str, Any]:
            }

        ``description`` is the skill's full SKILL.md frontmatter
-        ``description:`` field. Note: the system prompt skill index
-        truncates this to the first 57 chars; see ``extract_skill_description``.
+        ``description:`` field — the same string the system prompt renders
+        as ``    - name: description`` for pre-existing skills.
    """
    # Snapshot pre-reload state (name -> description) from the current
    # slash-command cache. Using dicts lets the post-rescan diff carry
@@ -779,31 +779,18 @@ def resolve_skill_config_values(

 # ── Description extraction ────────────────────────────────────────────────

-SKILL_PROMPT_DESC_LIMIT = 60
-
-
-def _normalize_skill_description(frontmatter: Dict[str, Any]) -> str:
-    """Normalize a skill's description field for comparison/truncation."""
-    raw_desc = frontmatter.get("description", "")
-    return str(raw_desc).strip().strip("'\"") if raw_desc else ""
-

 def extract_skill_description(frontmatter: Dict[str, Any]) -> str:
-    """Extract a system-prompt-length description from parsed frontmatter."""
-    desc = _normalize_skill_description(frontmatter)
-    if not desc:
+    """Extract a truncated description from parsed frontmatter."""
+    raw_desc = frontmatter.get("description", "")
+    if not raw_desc:
        return ""
-    if len(desc) > SKILL_PROMPT_DESC_LIMIT:
-        return desc[:SKILL_PROMPT_DESC_LIMIT - 3] + "..."
+    desc = str(raw_desc).strip().strip("'\"")
+    if len(desc) > 60:
+        return desc[:57] + "..."
    return desc


-def is_skill_description_truncated_for_prompt(frontmatter: Dict[str, Any]) -> bool:
-    """True when the description will be truncated in the system prompt skill index."""
-    desc = _normalize_skill_description(frontmatter)
-    return len(desc) > SKILL_PROMPT_DESC_LIMIT
-
-
 # ── File iteration ────────────────────────────────────────────────────────


@@ -300,22 +300,14 @@ def build_subscription_state(*, timeout: float = 15.0) -> SubscriptionState:
    return subscription_state_from_payload(payload, portal_url=portal_url)


-def subscription_manage_url(
-    state: SubscriptionState, tier_id: Optional[str] = None
-) -> Optional[str]:
-    """Build ``{portal_origin}/manage-subscription?org_id=<id>[&plan=<tier_id>]``.
+def subscription_manage_url(state: SubscriptionState) -> Optional[str]:
+    """Build ``{portal_origin}/manage-subscription?org_id=<id>`` from a state.

    Mirrors the TUI's ``buildManageUrl`` (``subscription.ts``): the deep-link
    target is NAS's OWN ``/manage-subscription`` page (NOT the Stripe Billing
    Portal — decided Jun 23), which routes upgrade→Checkout / downgrade→scheduled
    internally. ``org_id`` pins the page to the right account in multi-org
    situations. Returns ``None`` when no portal URL is resolvable.
-
-    ``tier_id`` (the stable ``tiers[]`` id, never a name/slug) is appended as
-    ``plan=`` so the portal preselects the picked plan — only for a NEW
-    subscription / upgrade the user chose. The portal validates it and simply
-    ignores an unknown tier, so the CLI appends unconditionally when a tier was
-    picked (parity with the TUI's ``?plan=``).
    """
    from urllib.parse import urlencode, urlsplit, urlunsplit

@@ -327,91 +319,13 @@ def subscription_manage_url(
    except Exception:
        return None

-    if parts.scheme not in ("http", "https") or not parts.netloc:
+    if not parts.scheme or not parts.netloc:
        return None

-    from urllib.parse import parse_qsl
-
-    # Preserve unrelated portal query params; org_id / plan are contract-owned
-    # (org_id before plan — insertion order is the emitted query order).
-    params = dict(parse_qsl(parts.query, keep_blank_values=True))
-    params.pop("org_id", None)
-    params.pop("plan", None)
-    if state.org_id:
-        params["org_id"] = state.org_id
-    if tier_id:
-        params["plan"] = tier_id
-    query = urlencode(params)
+    query = urlencode({"org_id": state.org_id}) if state.org_id else ""
    return urlunsplit((parts.scheme, parts.netloc, "/manage-subscription", query, ""))


-# =============================================================================
-# Shared plan-catalog helpers (consumed by the CLI Free catalog + paid picker)
-# =============================================================================
-
-
-def _format_dollars_grouped(value: Optional[Decimal]) -> str:
-    """``$1,000`` / ``$1,234.50`` — the whole-vs-fractional rule of
-    ``billing_view.format_money`` but thousands-grouped, matching the TUI's
-    ``toLocaleString('en-US')``.
-
-    The shared ``format_money`` is intentionally ungrouped (and asserted so across
-    other surfaces), so plan-catalog rows group locally to mirror the TUI.
-    """
-    if value is None:
-        return "—"
-    if value == value.to_integral_value():
-        return f"${format(value.to_integral_value(), ',f')}"
-    return f"${format(value.quantize(Decimal('0.01')), ',f')}"
-
-
-def selectable_tiers(state: SubscriptionState) -> list[SubscriptionTier]:
-    """Enabled paid tiers other than the current plan, cheapest first.
-
-    One derivation shared by the CLI Free catalog and the paid change picker:
-    ``is_enabled and not is_current and tier_order > 0`` (free / no-sub excluded —
-    dropping to free is a cancellation), sorted by ``tier_order``.
-    """
-    return sorted(
-        (
-            t
-            for t in (state.tiers or ())
-            if t.is_enabled and not t.is_current and (t.tier_order or 0) > 0
-        ),
-        key=lambda t: t.tier_order or 0,
-    )
-
-
-def format_tier_row(tier: SubscriptionTier) -> str:
-    """``name · $X/mo[ · $Y credits/mo]`` — the shared plan-catalog row.
-
-    Mirrors the TUI Free rows (``subscriptionOverlay.tsx``): thousands-grouped
-    money, and the ``$Y credits/mo`` suffix ONLY when monthly credits are present
-    and > 0 (a ``None`` / zero-credits tier hides it — never ``· — credits/mo`` or
-    ``· $0 credits/mo``).
-    """
-    row = f"{tier.name} · {_format_dollars_grouped(tier.dollars_per_month)}/mo"
-    mc = tier.monthly_credits
-    if mc is not None and mc > 0:
-        row += f" · {_format_dollars_grouped(mc)} credits/mo"
-    return row
-
-
-def is_upgrade(state: SubscriptionState, tier_id: str) -> bool:
-    """True when ``tier_id`` ranks above the current plan by ``tier_order``.
-
-    Prefers the active subscription's tier; falls back to the ``tiers[]``
-    ``is_current`` marker (what the picker derives from), else 0 (free).
-    """
-    orders = {t.tier_id: (t.tier_order or 0) for t in (state.tiers or ())}
-    cur_id = state.current.tier_id if state.current else None
-    if cur_id is not None and cur_id in orders:
-        cur_order = orders[cur_id]
-    else:
-        cur_order = next((t.tier_order or 0 for t in (state.tiers or ()) if t.is_current), 0)
-    return orders.get(tier_id, 0) > cur_order
-
-
 # =============================================================================
 # Dev fixtures (throwaway scaffolding — env-var driven, no live portal)
 # =============================================================================
@@ -127,10 +127,6 @@ class CodexAppServerClient:
        # Codex emits tracing to stderr; default WARN keeps it quiet for users.
        spawn_env.setdefault("RUST_LOG", "warn")

-        # Hide the console the codex child would otherwise flash on Windows
-        # (#56747). Hide-only — stdio pipes stay intact for the app-server wire.
-        from hermes_cli._subprocess_compat import windows_hide_flags
-
        self._proc = subprocess.Popen(
            cmd,
            stdin=subprocess.PIPE,
@@ -138,7 +134,6 @@ class CodexAppServerClient:
            stderr=subprocess.PIPE,
            bufsize=0,
            env=spawn_env,
-            creationflags=windows_hide_flags(),
        )
        self._next_id = 1
        self._pending: dict[int, _Pending] = {}
@@ -92,79 +92,6 @@ class TurnResult:
 _TURN_ABORTED_MARKERS = ("<turn_aborted>", "<turn_aborted/>")


-def _notification_scope_ids(
-    note: dict,
-) -> tuple[Optional[str], Optional[str]]:
-    """Extract the thread/turn identity carried by a notification."""
-    if not isinstance(note, dict):
-        return None, None
-    params = note.get("params") or {}
-    if not isinstance(params, dict):
-        return None, None
-
-    nested_turn = params.get("turn") or {}
-    nested_item = params.get("item") or {}
-
-    observed_thread_id = params.get("threadId") or params.get("thread_id")
-    if observed_thread_id is None and isinstance(nested_turn, dict):
-        observed_thread_id = (
-            nested_turn.get("threadId")
-            or nested_turn.get("thread_id")
-        )
-    if observed_thread_id is None and isinstance(nested_item, dict):
-        observed_thread_id = (
-            nested_item.get("threadId")
-            or nested_item.get("thread_id")
-        )
-
-    observed_turn_id = params.get("turnId") or params.get("turn_id")
-    if observed_turn_id is None and isinstance(nested_turn, dict):
-        observed_turn_id = nested_turn.get("id") or nested_turn.get("turnId")
-    if observed_turn_id is None and isinstance(nested_item, dict):
-        observed_turn_id = (
-            nested_item.get("turnId")
-            or nested_item.get("turn_id")
-        )
-
-    return observed_thread_id, observed_turn_id
-
-
-def _notification_belongs_to_turn(
-    note: dict,
-    *,
-    thread_id: Optional[str],
-    turn_id: Optional[str],
-) -> bool:
-    """Return whether a multiplexed notification belongs to this turn.
-
-    Codex app-server can carry parent and hosted subagent threads over one
-    JSON-RPC connection.  An explicitly foreign child or
-    stale-turn event must not mutate the active parent's transcript or mark
-    its turn complete.  Unscoped notifications remain accepted for protocol
-    compatibility.
-    """
-    if not isinstance(note, dict):
-        return False
-
-    observed_thread_id, observed_turn_id = _notification_scope_ids(note)
-
-    if (
-        thread_id is not None
-        and observed_thread_id is not None
-        and str(observed_thread_id) != str(thread_id)
-    ):
-        return False
-
-    if (
-        turn_id is not None
-        and observed_turn_id is not None
-        and str(observed_turn_id) != str(turn_id)
-    ):
-        return False
-
-    return True
-
-
 def _coerce_turn_input_text(user_input: Any) -> str:
    """Collapse Hermes/OpenAI rich content into app-server text input.

@@ -300,8 +227,6 @@ class CodexAppServerSession:
        self._client: Optional[CodexAppServerClient] = None
        self._thread_id: Optional[str] = None
        self._interrupt_event = threading.Event()
-        self._active_turn_id: Optional[str] = None
-        self._active_turn_lock = threading.Lock()
        # Pending file-change items, keyed by item id. Populated on
        # item/started for fileChange items; consumed by the approval
        # bridge when codex sends item/fileChange/requestApproval. The
@@ -376,8 +301,6 @@ class CodexAppServerSession:
        if self._closed:
            return
        self._closed = True
-        with self._active_turn_lock:
-            self._active_turn_id = None
        if self._client is not None:
            try:
                self._client.close()
@@ -399,33 +322,6 @@ class CodexAppServerSession:
        and unwind. Called by AIAgent's _interrupt_requested path."""
        self._interrupt_event.set()

-    def request_steer(self, text: str) -> bool:
-        """Append user guidance to the active Codex turn via ``turn/steer``."""
-        cleaned = str(text or "").strip()
-        if not cleaned:
-            return False
-        with self._active_turn_lock:
-            turn_id = self._active_turn_id
-            thread_id = self._thread_id
-            client = self._client
-        if not turn_id or not thread_id or client is None:
-            return False
-        try:
-            response = client.request(
-                "turn/steer",
-                {
-                    "threadId": thread_id,
-                    "input": [{"type": "text", "text": cleaned}],
-                    "expectedTurnId": turn_id,
-                },
-                timeout=10,
-            )
-        except (CodexAppServerError, TimeoutError):
-            logger.debug("turn/steer rejected for active Codex turn", exc_info=True)
-            return False
-        accepted_turn_id = response.get("turnId") if isinstance(response, dict) else None
-        return accepted_turn_id in {None, turn_id}
-
    # ---------- diagnostics ----------

    def _format_error_with_stderr(
@@ -500,18 +396,11 @@ class CodexAppServerSession:
            # Subprocess almost certainly unhealthy — retire so the next
            # turn re-spawns cleanly.
            result.should_retire = True
-            self._interrupt_event.clear()
            return result
        assert self._client is not None and self._thread_id is not None
        result.thread_id = self._thread_id

-        # Do not clear here: a hard stop can arrive while ensure_started() is
-        # spawning/initializing the subprocess. Honor it before launching a
-        # Codex turn instead of erasing the signal.
-        if self._interrupt_event.is_set():
-            result.interrupted = True
-            self._interrupt_event.clear()
-            return result
+        self._interrupt_event.clear()
        projector = CodexEventProjector()

        user_input_text = _coerce_turn_input_text(user_input)
@@ -543,7 +432,6 @@ class CodexAppServerSession:
                result.error = self._format_error_with_stderr(
                    "turn/start failed", exc
                )
-            self._interrupt_event.clear()
            return result
        except TimeoutError as exc:
            # turn/start hanging is a strong signal the subprocess is wedged.
@@ -553,12 +441,9 @@ class CodexAppServerSession:
                "turn/start timed out", exc
            )
            result.should_retire = True
-            self._interrupt_event.clear()
            return result

        result.turn_id = (ts.get("turn") or {}).get("id")
-        with self._active_turn_lock:
-            self._active_turn_id = result.turn_id
        deadline = time.monotonic() + turn_timeout
        turn_complete = False
        # Post-tool watchdog state. last_tool_completion_at is set whenever
@@ -620,17 +505,6 @@ class CodexAppServerSession:
                    pending = self._client.take_notification(timeout=0)
                    if pending is None:
                        break
-                    if not _notification_belongs_to_turn(
-                        pending,
-                        thread_id=self._thread_id,
-                        turn_id=result.turn_id,
-                    ):
-                        logger.debug(
-                            "ignoring foreign codex notification while draining "
-                            "server request: method=%s",
-                            pending.get("method"),
-                        )
-                        continue
                    # Mirror the main notification-handling block below so
                    # display events surface and stay in step with projector
                    # state. Without this, item/started / item/completed
@@ -676,16 +550,6 @@ class CodexAppServerSession:
                continue

            method = note.get("method", "")
-            if not _notification_belongs_to_turn(
-                note,
-                thread_id=self._thread_id,
-                turn_id=result.turn_id,
-            ):
-                logger.debug(
-                    "ignoring foreign codex notification: method=%s", method
-                )
-                continue
-
            if self._on_event is not None:
                try:
                    self._on_event(note)
@@ -783,9 +647,6 @@ class CodexAppServerSession:
                )
            result.should_retire = True

-        with self._active_turn_lock:
-            self._active_turn_id = None
-        self._interrupt_event.clear()
        return result

    def compact_thread(
@@ -876,48 +737,6 @@ class CodexAppServerSession:
                continue

            method = note.get("method", "")
-            observed_thread_id, observed_turn_id = _notification_scope_ids(note)
-            if result.turn_id is None:
-                if method == "turn/started":
-                    if (
-                        observed_thread_id is not None
-                        and str(observed_thread_id) != str(self._thread_id)
-                    ):
-                        logger.debug(
-                            "ignoring foreign compact turn/started: thread=%s",
-                            observed_thread_id,
-                        )
-                        continue
-                    if observed_turn_id is None:
-                        logger.debug(
-                            "ignoring compact turn/started without a turn id"
-                        )
-                        continue
-                    result.turn_id = str(observed_turn_id)
-                elif observed_turn_id is not None or method in {
-                    "item/completed",
-                    "turn/completed",
-                }:
-                    # thread/compact/start does not return a turn id. Until the
-                    # new turn/started arrives, any terminal/projectable event
-                    # is stale or cannot be safely attributed to this compaction.
-                    logger.debug(
-                        "ignoring codex notification before compact turn start: "
-                        "method=%s",
-                        method,
-                    )
-                    continue
-
-            if not _notification_belongs_to_turn(
-                note,
-                thread_id=self._thread_id,
-                turn_id=result.turn_id,
-            ):
-                logger.debug(
-                    "ignoring foreign codex notification: method=%s", method
-                )
-                continue
-
            if self._on_event is not None:
                try:
                    self._on_event(note)
@@ -26,18 +26,11 @@ from __future__ import annotations

 import logging
 import threading
-import time
 import uuid
 from dataclasses import dataclass
 from typing import Any, Dict, List, Mapping, Optional

-from agent.conversation_compression import (
-    IDLE_COMPACTION_STATUS_TEMPLATE,
-    PREFLIGHT_COMPRESSION_STATUS_TEMPLATE,
-    compression_skipped_due_to_lock,
-    conversation_history_after_compression,
-)
-from agent.context_engine import automatic_compaction_status_message
+from agent.conversation_compression import conversation_history_after_compression
 from agent.iteration_budget import IterationBudget
 from agent.memory_manager import build_memory_context_block
 from agent.model_metadata import (
@@ -217,23 +210,6 @@ def _compression_made_progress(
    return orig_tokens > 0 and new_tokens < orig_tokens * 0.95


-def _compression_warrants_another_preflight_pass(
-    orig_tokens: int, new_tokens: int, threshold_tokens: int
-) -> bool:
-    """Whether an over-threshold request merits another immediate summary.
-
-    Row-count progress is enough to prove that a compression boundary was real,
-    but not enough to justify another expensive pass before trying the provider.
-    Continue only when the request remains over threshold *and* the previous pass
-    materially reduced its estimated token pressure (>5%).
-    """
-    return (
-        new_tokens >= threshold_tokens
-        and orig_tokens > 0
-        and new_tokens < orig_tokens * 0.95
-    )
-
-
 def _should_run_preflight_estimate(
    messages: List[Dict[str, Any]],
    protect_first_n: int,
@@ -262,40 +238,6 @@ def _should_run_preflight_estimate(
    return estimate_messages_tokens_rough(messages) >= threshold_tokens


-def _should_idle_compact(
-    *,
-    enabled: bool,
-    idle_after_seconds: int,
-    idle_gap_seconds: float,
-    tokens: int,
-    floor_tokens: int,
-    cooldown_active: bool,
-) -> bool:
-    """Decide whether an idle-triggered compaction should run this turn.
-
-    Idle compaction is opt-in (``idle_after_seconds <= 0`` disables it). It
-    fires when a session resumes after a wall-clock gap of at least
-    ``idle_after_seconds`` since its last activity, so a long-lived thread
-    that is paused and later resumed compacts its accumulated history up
-    front instead of re-reading it on every subsequent turn.
-
-    It is orthogonal to the token-threshold trigger: it does NOT require the
-    context to exceed ``threshold_tokens``. It still skips work when the
-    context is at or below ``floor_tokens`` (the size compaction would reduce
-    *to*), so a small idle thread never pays for a summarisation that saves
-    nothing, and it defers to an active compression-failure cooldown.
-
-    Pure predicate so the policy is unit-testable without a live agent.
-    """
-    if not enabled or idle_after_seconds <= 0:
-        return False
-    if idle_gap_seconds < idle_after_seconds:
-        return False
-    if cooldown_active:
-        return False
-    return tokens > floor_tokens
-
-
@dataclass
 class TurnContext:
    """Values produced by the turn prologue and consumed by the turn loop."""
@@ -321,8 +263,6 @@ class TurnContext:
    plugin_user_context: str = ""
    # External-memory prefetch result, reused across loop iterations.
    ext_prefetch_cache: str = ""
-    # Turn-start preflight already proved an immediate retry ineffective.
-    preflight_compression_blocked: bool = False


 def build_turn_context(
@@ -377,7 +317,6 @@ def build_turn_context(
        set_runtime_main(
            getattr(agent, "provider", "") or "",
            getattr(agent, "model", "") or "",
-            requested_provider=getattr(agent, "requested_provider", "") or "",
            base_url=getattr(agent, "base_url", "") or "",
            api_key=getattr(agent, "api_key", "") or "",
            api_mode=getattr(agent, "api_mode", "") or "",
@@ -621,93 +560,11 @@ def build_turn_context(
        if not isinstance(pending_cli_message, dict) or pending_cli_message.get("_db_persisted"):
            agent._pending_cli_user_message = None

-    # ── Idle-triggered compaction (opt-in; ``idle_compact_after_seconds``) ──
-    # When a session resumes after a long idle gap, compact the accumulated
-    # history up front so the rest of the conversation does not keep re-reading
-    # a large stale context on every turn. This fires on elapsed wall-clock time
-    # rather than size, so it complements (does not replace) the token-threshold
-    # preflight below. ``_last_activity_ts`` is the last time this turn loop did
-    # work; nothing has touched it yet this turn, so it measures the gap since
-    # the previous turn finished. The cheap gap pre-check gates the (more
-    # expensive) token estimate, mirroring ``_should_run_preflight_estimate``.
-    _idle_after = getattr(agent, "compression_idle_compact_after_seconds", 0)
-    if agent.compression_enabled and _idle_after > 0 and messages:
-        _idle_gap = time.time() - getattr(agent, "_last_activity_ts", time.time())
-        if _idle_gap >= _idle_after:
-            _compressor = agent.context_compressor
-            _idle_tokens = estimate_request_tokens_rough(
-                messages,
-                system_prompt=active_system_prompt or "",
-                tools=agent.tools or None,
-            )
-            # Post-compression target size: don't summarise a thread already
-            # below what compaction would reduce it to.
-            _idle_floor = int(
-                _compressor.threshold_tokens * _compressor.summary_target_ratio
-            )
-            _idle_cooldown = getattr(
-                _compressor, "get_active_compression_failure_cooldown", lambda: None
-            )()
-            if _should_idle_compact(
-                enabled=agent.compression_enabled,
-                idle_after_seconds=_idle_after,
-                idle_gap_seconds=_idle_gap,
-                tokens=_idle_tokens,
-                floor_tokens=_idle_floor,
-                cooldown_active=bool(_idle_cooldown),
-            ):
-                logger.info(
-                    "Idle compaction: %ss idle >= %ss, ~%s tokens > %s floor "
-                    "(session %s)",
-                    int(_idle_gap),
-                    _idle_after,
-                    f"{_idle_tokens:,}",
-                    f"{_idle_floor:,}",
-                    agent.session_id or "none",
-                )
-                _idle_status = automatic_compaction_status_message(
-                    _compressor,
-                    phase="idle",
-                    default_message=IDLE_COMPACTION_STATUS_TEMPLATE.format(
-                        idle_seconds=int(_idle_gap), tokens=_idle_tokens
-                    ),
-                    approx_tokens=_idle_tokens,
-                    idle_seconds=int(_idle_gap),
-                    model=agent.model,
-                )
-                if _idle_status:
-                    agent._emit_status(_idle_status)
-                _idle_input = messages
-                messages, active_system_prompt = agent._compress_context(
-                    messages, system_message, approx_tokens=_idle_tokens,
-                    task_id=effective_task_id,
-                )
-                # ``_compress_context`` returns the INPUT list object when it
-                # skips (per-session lock held by another path, failure
-                # cooldown, anti-thrash breaker, codex-native routing). Only
-                # re-baseline + re-anchor after a real compaction — a skip
-                # must leave the turn's flush baseline and user-message index
-                # untouched.
-                if messages is not _idle_input:
-                    conversation_history = conversation_history_after_compression(
-                        agent, messages, conversation_history
-                    )
-                    # Compaction rebuilt the list, so the index of this turn's
-                    # just-appended user message is stale — re-anchor it the
-                    # same way the preflight path does below.
-                    current_turn_user_idx = reanchor_current_turn_user_idx(
-                        messages, user_message
-                    )
-                    agent._persist_user_message_idx = current_turn_user_idx
-
    # ── Preflight context compression ──
    # Gate the (expensive) full token estimate behind a cheap pre-check.
    # See ``_should_run_preflight_estimate`` for the OR semantics that fix
    # issue #27405 (a few very large messages slipping past the count gate).
    _preflight_compressed = False
-    _preflight_compression_blocked = False
-    agent._turn_received_provider_response = False
-    agent._turn_preflight_display_snapshot = None
    if agent.compression_enabled and _should_run_preflight_estimate(
        messages,
        agent.context_compressor.protect_first_n,
@@ -720,21 +577,6 @@ def build_turn_context(
            tools=agent.tools or None,
        )
        _compressor = agent.context_compressor
-        # getattr guard: minimal compressor doubles (SimpleNamespace in the
-        # engine-preflight tests) and plugin context engines lack this
-        # ContextCompressor-only method — absence means no snapshot, and the
-        # finalizer's rollback stays disarmed for the turn (display-only).
-        _snapshot_fn = getattr(
-            _compressor, "snapshot_preflight_display_tokens", None
-        )
-        if callable(_snapshot_fn):
-            _snapshot_val = _snapshot_fn()
-            # Type pin: MagicMock compressors return truthy Mock objects —
-            # only a real int snapshot may arm the interrupted-turn rollback.
-            if isinstance(_snapshot_val, int) and not isinstance(
-                _snapshot_val, bool
-            ):
-                agent._turn_preflight_display_snapshot = _snapshot_val
        _defer_preflight = getattr(
            _compressor,
            "should_defer_preflight_to_real_usage",
@@ -768,8 +610,6 @@ def build_turn_context(
            lambda: None,
        )()

-        _should_compress_now = False
-        _compress_block_reason = None
        if _preflight_deferred:
            logger.info(
                "Skipping preflight compression: rough estimate ~%s >= %s, "
@@ -785,42 +625,14 @@ def build_turn_context(
                int(_compression_cooldown.get("remaining_seconds", 0.0)),
                agent.session_id or "none",
            )
-            if _preflight_tokens >= _compressor.threshold_tokens:
-                # Context is over threshold but compression is blocked by the
-                # summary-LLM cooldown — surface a warning (see block below).
-                _cooldown_secs = _compression_cooldown.get("remaining_seconds", 0.0)
-                _compress_block_reason = f"cooldown:{_cooldown_secs:.0f}"
        elif _codex_native_auto:
            logger.info(
                "Skipping Hermes preflight compression for codex app-server "
                "(mode=%s); Hermes will not start thread compaction here.",
                getattr(agent, "codex_app_server_auto_compaction", "native"),
            )
-        else:
-            _should_compress_now = _compressor.should_compress(_preflight_tokens)
-            if not _should_compress_now:
-                # Context is over threshold but compression is blocked
-                # (summary-LLM cooldown or anti-thrashing). Ask should_compress_info
-                # for the human-readable reason so we can surface a warning below.
-                # getattr guard: minimal compressor doubles (SimpleNamespace in
-                # the engine-preflight tests) and older plugin engines lack the
-                # method — absence means no block reason, no warning.
-                _info = getattr(_compressor, "should_compress_info", None)
-                if callable(_info):
-                    try:
-                        _compress_block_reason = _info(_preflight_tokens)[1]
-                    except Exception:
-                        _compress_block_reason = None
-        if _should_compress_now:
+        elif _compressor.should_compress(_preflight_tokens):
            _preflight_compressed = True
-            # Compression is actually running (block cleared / was never
-            # blocked) — reset the dedup so a future blocked-over-threshold
-            # turn can warn again. Real session boundary.
-            # getattr guard: test doubles built via object.__new__ lack the
-            # method (gateway test-double pitfall) — treat absence as no-op.
-            _clear_warn = getattr(agent, "_clear_context_overflow_warn", None)
-            if callable(_clear_warn):
-                _clear_warn()
            logger.info(
                "Preflight compression: ~%s tokens >= %s threshold (model %s, ctx %s)",
                f"{_preflight_tokens:,}",
@@ -828,52 +640,18 @@ def build_turn_context(
                agent.model,
                f"{_compressor.context_length:,}",
            )
-            _preflight_status = automatic_compaction_status_message(
-                _compressor,
-                phase="preflight",
-                default_message=PREFLIGHT_COMPRESSION_STATUS_TEMPLATE.format(
-                    tokens=_preflight_tokens,
-                    threshold=_compressor.threshold_tokens,
-                ),
-                approx_tokens=_preflight_tokens,
-                threshold_tokens=_compressor.threshold_tokens,
-                context_length=_compressor.context_length,
-                model=agent.model,
+            agent._emit_status(
+                f"📦 Preflight compression: ~{_preflight_tokens:,} tokens "
+                f">= {_compressor.threshold_tokens:,} threshold. "
+                "This may take a moment."
            )
-            if _preflight_status:
-                agent._emit_status(_preflight_status)
-            # Preflight passes honor the same configured per-turn cap
-            # (compression.max_attempts) as the loop's compression sites;
-            # default 3 preserves the prior hardcoded behavior.
-            _max_preflight_passes = max(
-                1, int(getattr(agent, "max_compression_attempts", 3) or 3)
-            )
-            for _pass in range(_max_preflight_passes):
+            for _pass in range(3):
                _orig_len = len(messages)
                _orig_tokens = _preflight_tokens
-                _preflight_input = messages
                messages, active_system_prompt = agent._compress_context(
                    messages, system_message, approx_tokens=_preflight_tokens,
                    task_id=effective_task_id,
                )
-                if (
-                    messages is _preflight_input
-                    and compression_skipped_due_to_lock(agent)
-                ):
-                    # #69870 lock-skip: another path holds this session's
-                    # compression lock, so the pass no-oped. That is a
-                    # temporary DEFER, not proof the transcript cannot
-                    # compress — do NOT arm the insufficient-progress
-                    # blocker (the loop's error handlers must keep their
-                    # provider-proven retry budget) and stop preflight
-                    # passes for this turn; the lock winner is shrinking
-                    # the same session concurrently.
-                    logger.info(
-                        "Preflight compression deferred: compression lock "
-                        "held by another path (session %s)",
-                        agent.session_id or "none",
-                    )
-                    break
                # Re-estimate now so size-only compression (same row count,
                # lower token count — e.g. summarising tool outputs) is
                # recognised as progress instead of being misread as
@@ -886,10 +664,9 @@ def build_turn_context(
                if not _compression_made_progress(
                    _orig_len, len(messages), _orig_tokens, _preflight_tokens
                ):
-                    _preflight_compression_blocked = True
                    break  # Cannot compress further: neither rows nor tokens moved
                conversation_history = conversation_history_after_compression(
-                    agent, messages, conversation_history
+                    agent, messages
                )
                agent._empty_content_retries = 0
                agent._thinking_prefill_retries = 0
@@ -898,113 +675,6 @@ def build_turn_context(
                agent._mute_post_response = False
                if not _compressor.should_compress(_preflight_tokens):
                    break
-                if not _compression_warrants_another_preflight_pass(
-                    _orig_tokens,
-                    _preflight_tokens,
-                    _compressor.threshold_tokens,
-                ):
-                    _preflight_compression_blocked = True
-                    logger.warning(
-                        "Preflight compression made insufficient progress: "
-                        "~%s -> ~%s request tokens; skipping additional passes",
-                        f"{_orig_tokens:,}",
-                        f"{_preflight_tokens:,}",
-                    )
-                    break
-        elif _compress_block_reason:
-            # Context is already over the compression threshold, but compression
-            # is blocked (summary LLM cooldown or anti-thrashing). Without a
-            # signal the session keeps growing until the model silently stops
-            # answering — the conversation hits the hard provider token limit
-            # with no explanation. Surface a deduped warning so the user can
-            # take action (/new or /compress) instead of hitting a silent hang.
-            agent._warn_context_overflow_blocked(
-                _compress_block_reason,
-                _preflight_tokens,
-                _compressor.threshold_tokens,
-            )
-        else:
-            # Sub-threshold and unblocked — allow the overflow warning to fire
-            # again next time the context is over threshold but blocked.
-            # getattr guard: test doubles built via object.__new__ lack the
-            # method (gateway test-double pitfall) — treat absence as no-op.
-            _clear_warn = getattr(agent, "_clear_context_overflow_warn", None)
-            if callable(_clear_warn):
-                _clear_warn()
-            # Engine maintenance only when NO skip-branch fired: a failure
-            # cooldown, deferred estimate, or codex-native route must keep
-            # the engine hook un-consulted (#20316 contract — the cooldown
-            # exists precisely because compression recently failed).
-            if _compression_cooldown or _preflight_deferred or _codex_native_auto:
-                _engine_preflight = None
-            else:
-                _engine_preflight = getattr(
-                    _compressor, "should_compress_preflight", None
-                )
-            # ── Engine-driven sub-threshold preflight maintenance (#20316) ──
-            # None of the threshold-path branches fired (not deferred, no
-            # failure cooldown, not codex-native, and should_compress() said
-            # the request is under pressure). Context engines that override
-            # ``should_compress_preflight()`` (e.g. LCM-style incremental
-            # leaf-chunk compaction) can still request deferred maintenance
-            # below the token threshold. The default
-            # ``ContextEngine.should_compress_preflight()`` returns False, so
-            # the built-in ``ContextCompressor`` path is byte-identical.
-            #
-            # Attempt-cap integration: the engine gets exactly ONE
-            # ``compress()`` pass per turn. It is mutually exclusive with the
-            # threshold multi-pass loop above (if/elif), so turn-start
-            # preflight passes stay bounded by the resolved
-            # ``compression.max_attempts`` cap (floor 1) in every case.
-            #
-            # No-op-blocking integration: a sub-threshold engine pass that
-            # no-ops says nothing about over-threshold compressibility, so it
-            # must neither set nor clear ``_preflight_compression_blocked``
-            # (#64382) — and being in the ``else`` arm it can never run after
-            # the threshold loop has proven a retry ineffective.
-            # (resolved above, gated on no skip-branch having fired)
-            _wants_engine_preflight = False
-            if callable(_engine_preflight):
-                try:
-                    _wants_engine_preflight = bool(_engine_preflight(messages))
-                except Exception as _preflight_exc:
-                    # A buggy engine must never break an otherwise-healthy
-                    # turn: swallow at debug level and skip maintenance.
-                    logger.debug(
-                        "should_compress_preflight raised %s; skipping "
-                        "engine-driven preflight maintenance",
-                        _preflight_exc,
-                    )
-                    _wants_engine_preflight = False
-            if _wants_engine_preflight:
-                logger.info(
-                    "Engine-driven preflight maintenance: %s requested "
-                    "compress() at ~%s tokens (below %s threshold)",
-                    getattr(_compressor, "name", type(_compressor).__name__),
-                    f"{_preflight_tokens:,}",
-                    f"{getattr(_compressor, 'threshold_tokens', 0):,}",
-                )
-                _engine_input = messages
-                messages, active_system_prompt = agent._compress_context(
-                    messages, system_message, approx_tokens=_preflight_tokens,
-                    task_id=effective_task_id,
-                )
-                # ``_compress_context`` returns the INPUT list object on every
-                # skip path (per-session lock held elsewhere, cooldown,
-                # anti-thrash breaker, codex-native routing) and an engine may
-                # legitimately no-op. Only re-baseline the flush history and
-                # re-anchor the user row after a REAL compaction — a skip must
-                # leave the turn's bookkeeping untouched.
-                if messages is not _engine_input:
-                    _preflight_compressed = True
-                    conversation_history = conversation_history_after_compression(
-                        agent, messages
-                    )
-                    agent._empty_content_retries = 0
-                    agent._thinking_prefill_retries = 0
-                    agent._last_content_with_tools = None
-                    agent._last_content_tools_all_housekeeping = False
-                    agent._mute_post_response = False

    if _preflight_compressed:
        # Compression rebuilt the list (tail messages are fresh compaction
@@ -1229,5 +899,4 @@ def build_turn_context(
        should_review_memory=should_review_memory,
        plugin_user_context=plugin_user_context,
        ext_prefetch_cache=ext_prefetch_cache,
-        preflight_compression_blocked=_preflight_compression_blocked,
    )
@@ -201,36 +201,6 @@ def finalize_turn(
        )
    )

-    # Preflight can seed the display count before the provider receives the
-    # request. Roll that estimate back only when an interrupt wins the race
-    # before any successful provider response. Compaction state remains owned
-    # by the real-usage/post-compaction path, including its ``-1`` sentinel.
-    # Guard rules (test-double density on this path is high):
-    #  - snapshot is type-pinned to a real int — MagicMock agents auto-create
-    #    truthy Mock attributes that must never arm the rollback;
-    #  - the received-response flag is pinned to ``is not True`` — its real
-    #    domain is True/False, and only a literal True means a provider
-    #    response completed;
-    #  - the compressor method gets a getattr+callable guard — SimpleNamespace
-    #    compressor doubles and plugin context engines lack it.
-    _preflight_snapshot = getattr(
-        agent, "_turn_preflight_display_snapshot", None
-    )
-    if (
-        interrupted is True
-        and isinstance(_preflight_snapshot, int)
-        and not isinstance(_preflight_snapshot, bool)
-        and getattr(agent, "_turn_received_provider_response", False) is not True
-        and getattr(agent, "context_compressor", None) is not None
-    ):
-        _rollback_fn = getattr(
-            agent.context_compressor,
-            "rollback_interrupted_preflight_display_tokens",
-            None,
-        )
-        if callable(_rollback_fn):
-            _rollback_fn(_preflight_snapshot)
-
    # Post-loop cleanup must never lose the response.  Trajectory save,
    # resource teardown, and session persistence all touch fallible
    # surfaces — file I/O / JSON serialization (_save_trajectory), remote
@@ -525,34 +495,6 @@ def finalize_turn(
        except Exception as exc:
            logger.warning("post_llm_call hook failed: %s", exc)

-    # Context engine observation hook: notify the active engine that this
-    # turn has finished, with the finalized transcript. Complements the
-    # per-request select_context() hook (selection before the request;
-    # observation after the turn). No-op default, fail-open.
-    try:
-        from agent.conversation_loop import _notify_context_engine_turn_complete
-        # Forward the turn's canonical usage when the host has it. The loop
-        # stashes the most recent API response's usage dict (the same
-        # canonical buckets fed to ``update_from_response``) on the agent as
-        # ``_last_turn_usage``. It is ``None`` on turns that never reached a
-        # provider response (early failure / interrupt), which is exactly the
-        # contract: real usage when available, ``None`` otherwise.
-        _turn_usage = getattr(agent, "_last_turn_usage", None)
-        _notify_context_engine_turn_complete(
-            agent,
-            messages,
-            usage=_turn_usage,
-            logger=logger,
-            turn_id=turn_id,
-            task_id=effective_task_id,
-            api_call_count=api_call_count,
-            interrupted=interrupted,
-            failed=failed,
-            turn_exit_reason=_turn_exit_reason,
-        )
-    except Exception as exc:
-        logger.warning("on_turn_complete notification failed: %s", exc)
-
    # Extract reasoning from the CURRENT turn only.  Walk backwards
    # but stop at the user message that started this turn — anything
    # earlier is from a prior turn and must not leak into the reasoning
@@ -683,7 +625,4 @@ def finalize_turn(
    except Exception as exc:
        logger.warning("on_session_end hook failed: %s", exc)

-    agent._turn_preflight_display_snapshot = None
-    agent._turn_received_provider_response = False
-
    return result
@@ -73,10 +73,6 @@ class TurnRetryState:
    # was rolled back off ``messages`` and the loop should re-issue the API
    # call against the newly-activated provider (#32421).
    restart_with_rebuilt_messages: bool = False
-    # A user correction cancelled the in-flight provider request. The outer
-    # loop must append a role-safe checkpoint + user message, rebuild the API
-    # payload, and retry the same logical iteration.
-    restart_with_redirected_messages: bool = False

    def __iter__(self):
        # Convenience for debugging / tests: iterate (name, value) pairs.
@@ -60,12 +60,10 @@ def _db_path() -> Path:


 def _connect() -> sqlite3.Connection:
-    from hermes_state import apply_wal_with_fallback
-
    path = _db_path()
    path.parent.mkdir(parents=True, exist_ok=True)
    conn = sqlite3.connect(path)
-    apply_wal_with_fallback(conn, db_label="verification_evidence.db")
+    conn.execute("PRAGMA journal_mode=WAL")
    conn.execute("PRAGMA busy_timeout=5000")
    conn.row_factory = sqlite3.Row
    _ensure_schema(conn)
@@ -13,7 +13,7 @@
    "tauri:build": "tauri build",
    "tauri:build:debug": "tauri build --debug",
    "typecheck": "tsc -p . --noEmit",
-    "check": "npm run typecheck && npm run lint",
+    "check": "npm run typecheck",
    "lint": "eslint src/",
    "lint:fix": "eslint src/ --fix",
    "fix": "npm run lint:fix"
@@ -9,7 +9,7 @@
 * Prerequisite: `npm run build` must have been run so dist/ exists.
 */

-import { allowErrorBanners, test } from './test'
+import { test } from '@playwright/test'

 import {
  type DeadBackendFixture,
@@ -26,12 +26,6 @@ test.afterAll(async () => {
 })

 test.describe('boot failure with dead backend', () => {
-  test.beforeEach(() => {
-    // These tests deliberately trigger boot errors — error banners
-    // (notifyError → [role="alert"]) are expected, not failures.
-    allowErrorBanners()
-  })
-
  test('app shows error state', async () => {
    // Inject a fake boot error so the backend resolution "fails" with a
    // controlled error message. This is the only reliable way to trigger
@@ -11,7 +11,7 @@
 * Run from the nix devshell:
 *   npm exec playwright test e2e/boot.spec.ts --reporter=list
 */
-import { expect, test } from './test'
+import { expect, test } from '@playwright/test'

 import {
  type MockBackendFixture,
@@ -8,10 +8,13 @@
 * Prerequisite: `npm run build` must have been run so dist/ exists.
 */

-import { expect, test } from './test'
+import { test } from '@playwright/test'

-import { type MockBackendFixture, setupMockBackend, waitForAppReady } from './fixtures'
-import { BLOCKING_CLARIFY_QUESTION, BLOCKING_CLARIFY_TRIGGER } from './mock-server'
+import {
+  type MockBackendFixture,
+  setupMockBackend,
+  waitForAppReady,
+} from './fixtures'
 import { expectVisualSnapshot } from './visual-snapshot'

 let fixture: MockBackendFixture | null = null
@@ -58,7 +61,7 @@ test.describe('chat interaction with mock backend', () => {
        return (body.textContent ?? '').includes('Hello, can you hear me?')
      },
      undefined,
-      { timeout: 15_000 }
+      { timeout: 15_000 },
    )

    // Wait for the mock response to appear. The canned reply is:
@@ -78,61 +81,11 @@ test.describe('chat interaction with mock backend', () => {
        return text.includes('mock inference server') || text.includes('boot chain is working')
      },
      undefined,
-      { timeout: 60_000 }
+      { timeout: 60_000 },
    )
  })

  test('screenshot of chat with messages', async () => {
    await expectVisualSnapshot(fixture!.page, { name: 'chat-with-messages', app: fixture!.app })
  })
-
-  test('offers stop, steer, and queue actions while busy', async ({}, testInfo) => {
-    const page = fixture!.page
-    const composer = page.locator('[contenteditable="true"]').first()
-    const primary = page.locator('[data-slot="composer-root"] button[type="submit"]')
-    const queue = page.locator('[data-slot="composer-root"] button[aria-label="Queue message"]')
-    const dictation = page.locator('[data-slot="composer-root"] button[aria-label="Voice dictation"]')
-    const speakReplies = page.locator(
-      '[data-slot="composer-root"] button[aria-label="Read replies aloud"], [data-slot="composer-root"] button[aria-label="Stop reading replies aloud"]'
-    )
-
-    await composer.click()
-    await composer.type(BLOCKING_CLARIFY_TRIGGER)
-    await page.keyboard.press('Enter')
-    await page.getByText(BLOCKING_CLARIFY_QUESTION).waitFor({ state: 'visible', timeout: 30_000 })
-
-    await expect(primary).toHaveAttribute('aria-label', 'Stop')
-    await expect(primary.locator('span')).toHaveClass(/bg-current/)
-
-    await composer.click()
-    await composer.type('please answer tersely')
-    await expect(primary).toHaveAttribute('aria-label', /Steer/)
-    await expect(dictation).toBeVisible()
-    await expect(speakReplies).toBeVisible()
-    await expect(queue).toBeVisible()
-    await expect(queue.locator('svg.tabler-icon-layers-intersect-2')).toBeVisible()
-    const controlLabels = await page
-      .locator('[data-slot="composer-root"] button')
-      .evaluateAll(buttons => buttons.map(button => button.getAttribute('aria-label')))
-    const speakRepliesIndex = controlLabels.findIndex(
-      label => label === 'Read replies aloud' || label === 'Stop reading replies aloud'
-    )
-    expect(controlLabels.indexOf('Voice dictation')).toBeLessThan(speakRepliesIndex)
-    expect(speakRepliesIndex).toBeLessThan(controlLabels.indexOf('Queue message'))
-    expect(controlLabels.indexOf('Queue message')).toBeLessThan(
-      controlLabels.findIndex(label => label?.startsWith('Steer'))
-    )
-    await page.screenshot({ path: testInfo.outputPath('busy-composer-steer.png') })
-    await expect(primary.locator('svg.tabler-icon-steering-wheel')).toBeVisible()
-
-    await queue.click()
-    await expect(primary).toHaveAttribute('aria-label', 'Stop')
-    await expect(queue).toHaveCount(0)
-    await page.screenshot({ path: testInfo.outputPath('busy-composer-queue.png') })
-    await expect(page.getByText('1 Queued')).toBeVisible()
-
-    await primary.click()
-    await expect(page.getByText('1 Queued — paused')).toBeVisible()
-    await page.screenshot({ path: testInfo.outputPath('busy-composer-queue-paused.png') })
-  })
 })
@@ -1,210 +0,0 @@
-/**
- * Regression coverage for a correction sent during a live response, then a
- * warm session switch away and back. The correction is an accepted user turn,
- * not an optimistic duplicate of the original prompt, and its relative place
- * in the transcript must survive the resume reconciliation.
- */
-
-import { type TestInfo } from '@playwright/test'
-
-import { expect, test, type Page } from './test'
-
-import { type MockBackendFixture, setupMockBackend, waitForAppReady } from './fixtures'
-import { CORRECTION_SWITCH_TRIGGER, MOCK_REPLY } from './mock-server'
-
-const OTHER_SESSION_PROMPT = 'E2E persisted session used for a warm resume.'
-const ORIGINAL_PROMPT = `${CORRECTION_SWITCH_TRIGGER}: original prompt must remain singular after a correction.`
-const CORRECTION = 'E2E correction must stay after the original prompt.'
-const TOOL_STARTED = 'Checking the long-running task before I continue.'
-const CORRECTED_REPLY = 'The corrected task finished.'
-const INFERENCE_SWITCH_TRIGGER = 'E2E_INFERENCE_SWITCH_TRIGGER'
-const INFERENCE_PROMPT = `${INFERENCE_SWITCH_TRIGGER}: original inference prompt must remain singular.`
-const INFERENCE_CORRECTION = `${INFERENCE_SWITCH_TRIGGER}: correction sent while inference is live.`
-
-async function send(page: Page, text: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.waitFor({ state: 'visible', timeout: 15_000 })
-  await composer.click()
-  await composer.type(text, { delay: 5 })
-  await page.keyboard.press('Enter')
-}
-
-async function steer(page: Page, text: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  const primary = page.locator('[data-slot="composer-root"] button[type="submit"]')
-
-  await composer.waitFor({ state: 'visible', timeout: 15_000 })
-  await composer.click()
-  await composer.type(text, { delay: 5 })
-  await expect(primary).toHaveAttribute('aria-label', /Steer/)
-  await primary.click()
-}
-
-async function waitForTranscriptText(page: Page, text: string): Promise<void> {
-  await page.waitForFunction(
-    (expected: string) => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-    text,
-    { timeout: 30_000 },
-  )
-}
-
-async function textNodeOccurrences(page: Page, text: string): Promise<number> {
-  return page.evaluate((expected: string) => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    if (!viewport) return 0
-
-    const walker = document.createTreeWalker(viewport, NodeFilter.SHOW_TEXT)
-    let count = 0
-    while (walker.nextNode()) {
-      if (walker.currentNode.textContent?.includes(expected)) {
-        count += 1
-      }
-    }
-    return count
-  }, text)
-}
-
-async function transcriptTextOrder(page: Page): Promise<string[]> {
-  return page.evaluate(() => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    if (!viewport) return []
-
-    return Array.from(viewport.querySelectorAll<HTMLElement>('[data-role="message"], [data-message-id]'))
-      .map(message => message.textContent?.trim() ?? '')
-      .filter(Boolean)
-  })
-}
-
-async function transcriptMessageOrder(page: Page): Promise<string[]> {
-  return page.evaluate(() => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    if (!viewport) return []
-
-    return Array.from(viewport.querySelectorAll<HTMLElement>('[data-role="user"], [data-role="assistant"]'))
-      .map(message => message.textContent?.trim() ?? '')
-      .filter(Boolean)
-  })
-}
-
-async function openFreshDraft(page: Page, priorSessionText: string): Promise<void> {
-  await page.locator('[data-slot="sidebar"] button[aria-label="New session"]').first().click()
-  await page.waitForFunction(
-    (priorText: string) => !(document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(priorText),
-    priorSessionText,
-    { timeout: 15_000 },
-  )
-}
-
-async function openSidebarSession(page: Page, sidebarText: string, expectedTranscriptText: string): Promise<void> {
-  const row = page.locator('[data-slot="sidebar"] button').filter({ hasText: sidebarText }).first()
-  await row.waitFor({ state: 'visible', timeout: 30_000 })
-  await row.click()
-  await waitForTranscriptText(page, expectedTranscriptText)
-}
-
-async function reopenOriginalSession(page: Page): Promise<void> {
-  // A still-running tool has not generated a final title yet, so the sidebar
-  // retains the source prompt as its provisional session title.
-  await openSidebarSession(page, ORIGINAL_PROMPT, ORIGINAL_PROMPT)
-}
-
-async function reopenInferenceSession(page: Page): Promise<void> {
-  const row = page.locator('[data-slot="sidebar"] button').filter({ hasText: INFERENCE_PROMPT }).first()
-  await row.waitFor({ state: 'visible', timeout: 30_000 })
-  await row.click()
-  await waitForTranscriptText(page, INFERENCE_PROMPT)
-}
-
-function relevantOrder(messages: string[]): string[] {
-  return messages.filter(message => message.includes(ORIGINAL_PROMPT) || message.includes(CORRECTION))
-}
-
-function steerTurnOrder(messages: string[]): string[] {
-  return messages.flatMap(message => {
-    if (message.includes(ORIGINAL_PROMPT)) return [ORIGINAL_PROMPT]
-    if (message.includes(CORRECTION)) return [CORRECTION]
-    if (message.includes(CORRECTED_REPLY)) return [CORRECTED_REPLY]
-
-    return []
-  })
-}
-
-test.describe('correction session switch', () => {
-  let fixture: MockBackendFixture | null = null
-
-  test.beforeEach(async () => {
-    fixture = await setupMockBackend({
-      mockServer: { holdFirstStreamForPrompt: INFERENCE_SWITCH_TRIGGER },
-    })
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterEach(async () => {
-    await fixture?.cleanup()
-    fixture = null
-  })
-
-  test('keeps a live correction in place and does not duplicate its original prompt after switching sessions', async ({}, testInfo: TestInfo) => {
-    const { page } = fixture!
-
-    // A blank draft does not exercise session hydration. Seed a real second
-    // session first, matching the observed switch between two saved chats.
-    await send(page, OTHER_SESSION_PROMPT)
-    await waitForTranscriptText(page, MOCK_REPLY)
-    await openFreshDraft(page, OTHER_SESSION_PROMPT)
-
-    await send(page, ORIGINAL_PROMPT)
-    await waitForTranscriptText(page, TOOL_STARTED)
-    await waitForTranscriptText(page, ORIGINAL_PROMPT)
-
-    // The historical session redirects while a foreground terminal task is
-    // running. Use the visible Steer action to cover the real composer path.
-    await steer(page, CORRECTION)
-    await waitForTranscriptText(page, CORRECTION)
-
-    const orderBeforeSwitch = relevantOrder(await transcriptTextOrder(page))
-    expect(orderBeforeSwitch).toEqual([ORIGINAL_PROMPT, CORRECTION])
-    expect(await textNodeOccurrences(page, ORIGINAL_PROMPT)).toBe(1)
-    expect(await textNodeOccurrences(page, CORRECTION)).toBe(1)
-    await page.screenshot({ path: testInfo.outputPath('correction-before-session-switch.png') })
-
-    // Reproduce the observed race: switch to another persisted session while
-    // the foreground tool is live, then return before its redirect settles.
-    await openSidebarSession(page, MOCK_REPLY, OTHER_SESSION_PROMPT)
-    await reopenOriginalSession(page)
-    await page.waitForTimeout(500)
-    await page.screenshot({ path: testInfo.outputPath('correction-after-warm-resume.png') })
-
-    expect(relevantOrder(await transcriptTextOrder(page))).toEqual(orderBeforeSwitch)
-    expect(await textNodeOccurrences(page, ORIGINAL_PROMPT)).toBe(1)
-    expect(await textNodeOccurrences(page, CORRECTION)).toBe(1)
-
-    await waitForTranscriptText(page, CORRECTED_REPLY)
-    expect(steerTurnOrder(await transcriptMessageOrder(page))).toEqual([ORIGINAL_PROMPT, CORRECTION, CORRECTED_REPLY])
-  })
-
-  test('keeps an inference-time correction visible through a warm session switch', async ({}, testInfo: TestInfo) => {
-    const { mock, page } = fixture!
-
-    await send(page, OTHER_SESSION_PROMPT)
-    await waitForTranscriptText(page, MOCK_REPLY)
-    await openFreshDraft(page, OTHER_SESSION_PROMPT)
-
-    await send(page, INFERENCE_PROMPT)
-    await mock.waitForHeldStream()
-    await waitForTranscriptText(page, INFERENCE_PROMPT)
-
-    await send(page, INFERENCE_CORRECTION)
-    await waitForTranscriptText(page, INFERENCE_CORRECTION)
-
-    await openSidebarSession(page, MOCK_REPLY, OTHER_SESSION_PROMPT)
-    await reopenInferenceSession(page)
-
-    expect(await textNodeOccurrences(page, INFERENCE_PROMPT)).toBe(1)
-    expect(await textNodeOccurrences(page, INFERENCE_CORRECTION)).toBe(1)
-    await page.screenshot({ path: testInfo.outputPath('inference-correction-after-warm-resume.png') })
-
-    mock.releaseHeldStream()
-    await waitForTranscriptText(page, MOCK_REPLY)
-  })
-})
@@ -27,8 +27,7 @@ import * as path from 'node:path'

 import { _electron, type ElectronApplication, type Page } from '@playwright/test'

-import { startMockServer, type MockServerOptions } from './mock-server'
-import { installErrorBannerGuard } from './test'
+import { startMockServer } from './mock-server'

 const DESKTOP_ROOT = path.resolve(import.meta.dirname, '..')
 const REPO_ROOT = path.resolve(DESKTOP_ROOT, '..', '..')
@@ -97,7 +96,7 @@ export interface Sandbox {
  cleanup: () => void
 }

-export function createSandbox(prefix: string): Sandbox {
+function createSandbox(prefix: string): Sandbox {
  const root = fs.mkdtempSync(path.join(os.tmpdir(), `hermes-e2e-${prefix}-${Math.random()}`))
  const hermesHome = path.join(root, 'hermes-home')
  const userDataDir = path.join(root, 'electron-user-data')
@@ -140,30 +139,15 @@ export function createSandbox(prefix: string): Sandbox {
 * Write a config.yaml that pre-configures a mock provider pointing at the
 * mock inference server. The provider is set as the active model provider so
 * the desktop app skips onboarding and boots straight to the chat UI.
- *
- * @param extraDisplayConfig optional YAML lines appended to the `display:`
- *   section, used by the interim-message e2e test.
- * @param extraConfig optional top-level YAML sections for a test scenario.
- * @param modelContextLength optional primary-model context limit.
 */
-export function writeMockProviderConfig(
-  hermesHome: string,
-  mockUrl: string,
-  extraDisplayConfig?: string,
-  extraConfig?: string,
-  modelContextLength?: number,
-): void {
+function writeMockProviderConfig(hermesHome: string, mockUrl: string): void {
  const configPath = path.join(hermesHome, 'config.yaml')

-  const displaySection = extraDisplayConfig
-    ? `\ndisplay:\n${extraDisplayConfig}\n`
-    : ''
-
  const config = `# Auto-generated by E2E test fixtures
 model:
  default: mock-model
  provider: mock
-${modelContextLength ? `  context_length: ${modelContextLength}\n` : ''}providers:
+providers:
  mock:
    api: ${mockUrl}/v1
    name: Mock
@@ -172,7 +156,7 @@ ${modelContextLength ? `  context_length: ${modelContextLength}\n` : ''}provider
    models:
      mock-model: {}
    context_length: 4096
-${displaySection}${extraConfig ? `\n${extraConfig.trim()}\n` : ''}`
+`

  fs.writeFileSync(configPath, config, 'utf8')
 }
@@ -181,7 +165,7 @@ ${displaySection}${extraConfig ? `\n${extraConfig.trim()}\n` : ''}`
 * Write a minimal .env with the mock API key. The key_env in config.yaml
 * references MOCK_API_KEY, so the backend resolves credentials from here.
 */
-export function writeEnvFile(hermesHome: string, apiKey = 'e2e-mock-key'): void {
+function writeEnvFile(hermesHome: string, apiKey = 'e2e-mock-key'): void {
  const envPath = path.join(hermesHome, '.env')
  fs.writeFileSync(envPath, `MOCK_API_KEY=${apiKey}\n`, 'utf8')
 }
@@ -209,7 +193,7 @@ function writeEmptyConfig(hermesHome: string): void {
 *  - HERMES_DESKTOP_APP_NAME → unique-ish per test (avoids single-instance lock)
 *  - XDG_RUNTIME_DIR → ensure Electron has a writable runtime dir on Linux
 */
-export function buildAppEnv(sandbox: Sandbox, extra: Record<string, string> = {}): Record<string, string> {
+function buildAppEnv(sandbox: Sandbox, extra: Record<string, string> = {}): Record<string, string> {
  const clean = stripCredentials(process.env)

  // XDG_RUNTIME_DIR is needed for Electron on Linux when running in a
@@ -268,7 +252,7 @@ function assertDistBuilt(): void {
 * Find the Electron binary. In the nix devshell, `electron` is on PATH.
 * As a fallback, use the node_modules/.bin/electron from the desktop package.
 */
-export function findElectron(): string {
+function findElectron(): string {
  // In dev mode, we use the `electron` binary directly (not the packaged app).
  // The dev:electron script in package.json does exactly this: `electron .`
  // after building. We replicate that here.
@@ -299,7 +283,7 @@ export function findElectron(): string {
 * @param env      - the process environment (already has HERMES_HOME etc.)
 * @returns the ElectronApplication + first Page
 */
-export async function launchDesktop(
+async function launchDesktop(
  env: Record<string, string>,
 ): Promise<{ app: ElectronApplication; page: Page }> {
  assertDistBuilt()
@@ -321,10 +305,6 @@ export async function launchDesktop(

  const page = await app.firstWindow()

-  // Install the error-banner guard so any [role="alert"] that appears
-  // during a test is collected and surfaced in afterEach.
-  installErrorBannerGuard(page)
-
  return { app, page }
 }

@@ -333,25 +313,11 @@ export async function launchDesktop(
 export interface MockBackendFixture {
  app: ElectronApplication
  page: Page
-  mock: Awaited<ReturnType<typeof startMockServer>>
  mockUrl: string
  sandbox: Sandbox
  cleanup: () => Promise<void>
 }

-export interface MockBackendOptions {
-  /**
-   * Optional YAML lines to inject under the `display:` section of the
-   * generated config.yaml. Used by the interim-message e2e test to toggle
-   * `display.interim_assistant_messages`.
-   */
-  extraDisplayConfig?: string
-  /** Additional top-level config.yaml sections for an E2E scenario. */
-  extraConfig?: string
-  /** Override the mock model's context window for compression scenarios. */
-  modelContextLength?: number
-}
-
 /**
 * Set up a full mock-backend E2E environment:
 *   1. Start the mock inference server
@@ -359,23 +325,13 @@ export interface MockBackendOptions {
 *   3. Launch the desktop app
 *   4. Return handles for test interaction
 */
-export interface MockBackendOptions {
-  mockServer?: MockServerOptions
-}
-
-export async function setupMockBackend(options: MockBackendOptions = {}): Promise<MockBackendFixture> {
+export async function setupMockBackend(): Promise<MockBackendFixture> {
  // 1. Start mock server
-  const mock = await startMockServer(options.mockServer)
+  const mock = await startMockServer()

  // 2. Create sandbox + write config
  const sandbox = createSandbox('mock')
-  writeMockProviderConfig(
-    sandbox.hermesHome,
-    mock.url,
-    options.extraDisplayConfig,
-    options.extraConfig,
-    options.modelContextLength,
-  )
+  writeMockProviderConfig(sandbox.hermesHome, mock.url)
  writeEnvFile(sandbox.hermesHome)

  // 3. Build env + launch
@@ -385,7 +341,6 @@ export async function setupMockBackend(options: MockBackendOptions = {}): Promis
  return {
    app,
    page,
-    mock,
    mockUrl: mock.url,
    sandbox,
    cleanup: async () => {
@@ -559,7 +514,6 @@ export async function setupPackagedApp(): Promise<PackagedAppFixture> {
  })

  const page = await app.firstWindow()
-  installErrorBannerGuard(page)

  return {
    app,
@@ -1,147 +0,0 @@
-/**
- * E2E regression: desktop resume must hide agent-only transcript rows.
- *
- * Compaction handoffs are active user rows because the model needs them for
- * context continuity. They are not authored chat content, so the desktop
- * transcript must never display them after a real compressor-generated resume.
- */
-
-import * as fs from 'node:fs'
-import * as path from 'node:path'
-
-import { expect, test } from './test'
-
-import {
-  type MockBackendFixture,
-  buildAppEnv,
-  createSandbox,
-  launchDesktop,
-  waitForAppReady,
-  writeEnvFile,
-  writeMockProviderConfig,
-} from './fixtures'
-import {
-  MOCK_REPLY,
-  startMockServer,
-  VERIFICATION_STOP_TEXT,
-  VERIFICATION_STOP_TRIGGER,
-} from './mock-server'
-import { RealSessionBuilder } from './real-session-builder'
-
-const SESSION_TITLE = 'E2E Hidden History Messages'
-const VISIBLE_USER_TEXT = 'E2E_VISIBLE_USER_HISTORY'
-const VISIBLE_POST_COMPACTION_TEXT = 'E2E_VISIBLE_POST_COMPACTION_HISTORY'
-const COMPACTION_TRIGGER_PADDING = ' force real context compression'.repeat(600)
-
-async function setupSeededMockBackend(): Promise<MockBackendFixture> {
-  const mock = await startMockServer()
-  const sandbox = createSandbox('hidden-history')
-  writeMockProviderConfig(sandbox.hermesHome, mock.url)
-  fs.appendFileSync(
-    path.join(sandbox.hermesHome, 'config.yaml'),
-    '\ncompression:\n  threshold_tokens: 1\n',
-    'utf8',
-  )
-  writeEnvFile(sandbox.hermesHome)
-  const builder = await RealSessionBuilder.start(sandbox.hermesHome)
-  try {
-    await builder.createSession({
-      title: SESSION_TITLE,
-      turns: [
-        `${VISIBLE_USER_TEXT}${COMPACTION_TRIGGER_PADDING}`,
-        VISIBLE_POST_COMPACTION_TEXT,
-      ],
-    })
-  } finally {
-    await builder.close()
-  }
-
-  const { app, page } = await launchDesktop(buildAppEnv(sandbox))
-
-  return {
-    app,
-    page,
-    mock,
-    mockUrl: mock.url,
-    sandbox,
-    cleanup: async () => {
-      await app.close().catch(() => undefined)
-      await mock.close()
-      sandbox.cleanup()
-    },
-  }
-}
-
-test('resume hides real context-compaction handoffs', async ({}, testInfo) => {
-  const fixture = await setupSeededMockBackend()
-
-  try {
-    const { page } = fixture
-    await waitForAppReady(fixture, 120_000)
-
-    const sessionRow = page
-      .locator('[data-slot="sidebar"] button')
-      .filter({ hasText: SESSION_TITLE })
-      .first()
-    await sessionRow.click()
-
-    const transcript = page.locator('[data-slot="aui_thread-viewport"]')
-    await expect(transcript).toContainText(VISIBLE_USER_TEXT)
-    await expect(transcript).toContainText(VISIBLE_POST_COMPACTION_TEXT)
-    await expect(transcript).toContainText(MOCK_REPLY)
-    await expect(transcript).not.toContainText('[CONTEXT COMPACTION — REFERENCE ONLY]')
-    await page.screenshot({ path: testInfo.outputPath('hidden-history-resume.png') })
-  } finally {
-    await fixture.cleanup()
-  }
-})
-
-test('live verify-on-stop continuations stay out of the transcript', async ({}, testInfo) => {
-  const sandbox = createSandbox('live-verification-nudge')
-  const projectRoot = path.join(sandbox.root, 'project')
-  const changedFile = path.join(projectRoot, 'e2e-verification-target.py')
-  fs.mkdirSync(projectRoot)
-  fs.writeFileSync(
-    path.join(projectRoot, 'pyproject.toml'),
-    '[project]\nname = "e2e-verification-project"\nversion = "0.0.0"\n',
-    'utf8',
-  )
-
-  const mock = await startMockServer({ verificationWritePath: changedFile })
-  writeMockProviderConfig(sandbox.hermesHome, mock.url)
-  fs.appendFileSync(path.join(sandbox.hermesHome, 'config.yaml'), '\nagent:\n  verify_on_stop: true\n', 'utf8')
-  writeEnvFile(sandbox.hermesHome)
-  const { app, page } = await launchDesktop(buildAppEnv(sandbox))
-  const fixture: MockBackendFixture = {
-    app,
-    page,
-    mock,
-    mockUrl: mock.url,
-    sandbox,
-    cleanup: async () => {
-      await app.close().catch(() => undefined)
-      await mock.close()
-      sandbox.cleanup()
-    },
-  }
-
-  try {
-    await waitForAppReady(fixture, 120_000)
-    const composer = page.locator('[contenteditable="true"]').first()
-    await composer.click()
-    await composer.type(VERIFICATION_STOP_TRIGGER)
-    await page.keyboard.press('Enter')
-
-    const transcript = page.locator('[data-slot="aui_thread-viewport"]')
-    await expect(transcript).toContainText(VERIFICATION_STOP_TEXT, { timeout: 60_000 })
-    await expect.poll(
-      () => mock.receivedPrompts.some(prompt => prompt.includes('[System: You edited code in this turn')),
-      { timeout: 30_000 },
-    ).toBe(true)
-    expect(fs.existsSync(changedFile), 'The scripted write_file call should edit only the sandbox project').toBe(true)
-    await expect(transcript).not.toContainText('[System: You edited code in this turn')
-    await page.screenshot({ path: testInfo.outputPath('live-verification-nudge.png') })
-  } finally {
-    await fixture.cleanup()
-  }
-})
@@ -1,215 +0,0 @@
-/**
- * E2E test for the interim-assistant-message preservation fix (#65919).
- *
- * Reproduces the bug across all three layers (agent core → tui_gateway →
- * desktop renderer): when the agent emits assistant text alongside a tool
- * call, then completes the turn with a *different* final answer, the
- * interim text must survive in the transcript — not be wiped when
- * message.complete replaces the streaming bubble.
- *
- * The mock server walks through a multi-turn script when it sees the
- * trigger keyword:
- *
- *   Turn 1: "Let me start by planning the approach." + todo tool_call
- *   Turn 2: "Now checking the details before answering." + todo tool_call
- *   Turn 3: (no text) + todo tool_call          → NO interim (no visible text)
- *   Turn 4: "Found something interesting worth noting." + todo tool_call
- *   Turn 5: "All done! Here is the complete summary..." (final, stop)
- *
- * Two describe blocks exercise the config flag both ways:
- *
- *   display.interim_assistant_messages: true (default)
- *     → ALL interim texts AND the final text must be visible in the
- *       transcript.
- *
- *   display.interim_assistant_messages: false
- *     → only the final text is visible (no message.interim events emitted,
- *       so all streamed interim text is replaced at message.complete).
- *
- * Prerequisite: `npm run build` must have been run so dist/ exists.
- */
-
-import { expect, test, type Page } from '@playwright/test'
-
-import {
-  type MockBackendFixture,
-  setupMockBackend,
-  waitForAppReady,
-} from './fixtures'
-import { INTERIM_TEXTS, restartMockServer } from './mock-server'
-
-// ─── Helpers ──────────────────────────────────────────────────────────
-
-/** Unique trigger keyword the mock server detects to switch to the script. */
-const TRIGGER = 'E2E_INTERIM_TRIGGER'
-
-/**
- * Send a message and wait for BOTH the user's message and the agent's
- * final response to appear in the transcript. Returns when the final text
- * is visible, which means message.complete has fired and the transcript
- * has settled.
- */
-async function sendInterimMessage(page: Page): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.waitFor({ state: 'visible', timeout: 10_000 })
-  await composer.click()
-  await composer.type(TRIGGER, { delay: 20 })
-  await page.keyboard.press('Enter')
-
-  // Wait for the user's trigger message to appear.
-  await page.waitForFunction(
-    () => (document.body.textContent ?? '').includes('E2E_INTERIM_TRIGGER'),
-    undefined,
-    { timeout: 15_000 },
-  )
-
-  // Wait for the agent's FINAL response (last turn). This means
-  // message.complete has fired and the transcript is settled.
-  await page.waitForFunction(
-    (finalText) => (document.body.textContent ?? '').includes(finalText),
-    INTERIM_TEXTS.finalText,
-    { timeout: 90_000 },
-  )
-
-  // Give the renderer a moment to settle any final state updates
-  // (hydration, session refresh) before asserting.
-  await page.waitForTimeout(2000)
-}
-
-/**
- * Count how many times `text` appears as distinct text in the chat transcript
- * (excluding the session sidebar, whose session-preview label shows the
- * first streamed text as a title).
- *
- * The desktop app renders the transcript inside a
- * `[data-slot="aui_thread-viewport"]` container (from @assistant-ui/react).
- * The session sidebar's preview labels live outside that container, so
- * scoping the DOM walk to the viewport cleanly excludes them.
- */
-async function countTranscriptMessagesContaining(page: Page, text: string): Promise<number> {
-  return page.evaluate(
-    (search) => {
-      const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-      if (!viewport) {
-        return 0
-      }
-
-      let count = 0
-      const walker = document.createTreeWalker(
-        viewport,
-        NodeFilter.SHOW_ELEMENT,
-        {
-          acceptNode: (node) => {
-            const el = node as HTMLElement
-            const directText = el.textContent ?? ''
-            if (!directText.includes(search)) {
-              return NodeFilter.FILTER_SKIP
-            }
-            // Only count leaf-ish elements to avoid double-counting.
-            const hasChildWithText = Array.from(el.children).some(
-              (child) => (child.textContent ?? '').includes(search),
-            )
-            if (hasChildWithText) {
-              return NodeFilter.FILTER_SKIP
-            }
-            return NodeFilter.FILTER_ACCEPT
-          },
-        },
-      )
-      while (walker.nextNode()) {
-        count++
-      }
-      return count
-    },
-    text,
-  )
-}
-
-// ─── Flag ON: interim_assistant_messages = true (default) ─────────────
-
-test.describe('interim assistant messages — flag ON (default)', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('all interim texts survive alongside the final response', async () => {
-    const page = fixture.page
-    await sendInterimMessage(page)
-
-    // Every interim text (turns with visible text + tool calls) must be
-    // present in the transcript as its own sealed message — NOT wiped by
-    // message.complete.
-    for (const interimText of INTERIM_TEXTS.interims) {
-      await expect
-        .poll(
-          () => countTranscriptMessagesContaining(page, interimText),
-          { timeout: 15_000, message: `interim text "${interimText}" should be visible` },
-        )
-        .toBeGreaterThanOrEqual(1)
-    }
-
-    // The final text must also be visible.
-    await expect
-      .poll(
-        () => countTranscriptMessagesContaining(page, INTERIM_TEXTS.finalText),
-        { timeout: 15_000, message: 'final text should be visible' },
-      )
-      .toBeGreaterThanOrEqual(1)
-  })
-})
-
-// ─── Flag OFF: interim_assistant_messages = false ────────────────────
-
-test.describe('interim assistant messages — flag OFF', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend({
-      extraDisplayConfig: '  interim_assistant_messages: false',
-    })
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('only the final response is visible; all interim texts are wiped', async () => {
-    const page = fixture.page
-    await sendInterimMessage(page)
-
-    // The final text must be visible.
-    await expect
-      .poll(
-        () => countTranscriptMessagesContaining(page, INTERIM_TEXTS.finalText),
-        { timeout: 15_000, message: 'final text should be visible' },
-      )
-      .toBeGreaterThanOrEqual(1)
-
-    // NONE of the interim texts should be visible — with the flag off,
-    // the tui_gateway never installs interim_assistant_callback, so no
-    // message.interim events are emitted. All streamed interim text is
-    // accumulated into the streaming bubble and replaced by
-    // message.complete.
-    for (const interimText of INTERIM_TEXTS.interims) {
-      const count = await countTranscriptMessagesContaining(page, interimText)
-      expect(
-        count,
-        `interim text "${interimText}" should NOT be visible when flag is off`,
-      ).toBe(0)
-    }
-  })
-})
@@ -1,239 +0,0 @@
-import * as path from 'node:path'
-
-import { type TestInfo } from '@playwright/test'
-
-import { expect, test, type ElectronApplication, type Page } from './test'
-
-import {
-  buildAppEnv,
-  createSandbox,
-  launchDesktop,
-  type Sandbox,
-  waitForAppReady,
-  writeEnvFile,
-  writeMockProviderConfig,
-} from './fixtures'
-import { MOCK_REPLY, startMockServer, type MockServer, type MockServerOptions } from './mock-server'
-import { RealSessionBuilder } from './real-session-builder'
-
-const DESKTOP_ROOT = path.resolve(import.meta.dirname, '..')
-const SESSION_TITLE = 'E2E large persisted session'
-const EXPECTED_TEXT = 'E2E persisted user message 52'
-const BACKGROUND_PROMPT = 'E2E background inference must remain attached across resume'
-const HISTORY_TURNS = Array.from(
-  { length: 27 },
-  (_, index) => `E2E persisted user message ${index * 2}: audit the compatibility matrix`,
-)
-
-interface SeededFixture {
-  app: ElectronApplication
-  mock: MockServer
-  mockUrl: string
-  page: Page
-  sandbox: Sandbox
-  cleanup: () => Promise<void>
-}
-
-interface PaintState {
-  bursts: number
-  timeline: Array<{ mutations: number; time: number }>
-}
-
-async function setupSeededDesktop(mockServer?: MockServerOptions): Promise<SeededFixture> {
-  const mock = await startMockServer(mockServer)
-  const sandbox = createSandbox('large-session')
-  writeMockProviderConfig(sandbox.hermesHome, mock.url)
-  writeEnvFile(sandbox.hermesHome)
-
-  const builder = await RealSessionBuilder.start(sandbox.hermesHome)
-  try {
-    await builder.createSession({ title: SESSION_TITLE, turns: HISTORY_TURNS })
-  } finally {
-    await builder.close()
-  }
-
-  const { app, page } = await launchDesktop(buildAppEnv(sandbox))
-
-  return {
-    app,
-    mock,
-    mockUrl: mock.url,
-    page,
-    sandbox,
-    cleanup: async () => {
-      await app.close().catch(() => undefined)
-      await mock.close()
-      sandbox.cleanup()
-    },
-  }
-}
-
-function sessionRow(page: Page) {
-  return page.locator('[data-slot="sidebar"] button').filter({ hasText: SESSION_TITLE }).first()
-}
-
-async function openSeededSession(page: Page): Promise<void> {
-  const row = sessionRow(page)
-  await row.waitFor({ state: 'visible', timeout: 60_000 })
-  await row.click()
-  await page.waitForFunction(
-    expected => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-    EXPECTED_TEXT,
-    { timeout: 30_000 },
-  )
-}
-
-async function openNewSession(page: Page): Promise<void> {
-  const button = page.locator('[data-slot="sidebar"] button').filter({ hasText: 'New session' }).first()
-  await button.waitFor({ state: 'visible', timeout: 10_000 })
-  await button.click()
-  await page.waitForFunction(
-    expected => !(document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-    EXPECTED_TEXT,
-    { timeout: 15_000 },
-  )
-}
-
-async function submitPrompt(page: Page, prompt: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.waitFor({ state: 'visible', timeout: 15_000 })
-  await composer.click()
-  await composer.type(prompt, { delay: 2 })
-  await page.keyboard.press('Enter')
-  await page.waitForFunction(
-    expected => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-    prompt,
-    { timeout: 15_000 },
-  )
-}
-
-async function startPaintObserver(page: Page): Promise<void> {
-  await page.evaluate(() => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    const state = { bursts: 0, timeline: [] as Array<{ mutations: number; time: number }> }
-    ;(window as Window & { __largeSessionPaints?: typeof state }).__largeSessionPaints = state
-    if (!viewport) return
-
-    let additions = 0
-    let flushTimer: ReturnType<typeof setTimeout> | undefined
-    new MutationObserver(records => {
-      additions += records.reduce(
-        (count, record) => count + (record.type === 'childList' && record.addedNodes.length > 0 ? 1 : 0),
-        0,
-      )
-      if (additions === 0) return
-      if (flushTimer) clearTimeout(flushTimer)
-      flushTimer = setTimeout(() => {
-        state.bursts += 1
-        state.timeline.push({ mutations: additions, time: Date.now() })
-        additions = 0
-      }, 30)
-    }).observe(viewport, { childList: true, subtree: true })
-  })
-}
-
-async function paintState(page: Page): Promise<PaintState> {
-  const state = await page.evaluate(() => (window as Window & { __largeSessionPaints?: PaintState }).__largeSessionPaints)
-  expect(state, 'paint observer should attach to the thread viewport').toBeDefined()
-  return state!
-}
-
-async function textNodeOccurrences(page: Page, expected: string): Promise<number> {
-  return page.evaluate(text => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    if (!viewport) return 0
-
-    const walker = document.createTreeWalker(viewport, NodeFilter.SHOW_TEXT)
-    let count = 0
-    while (walker.nextNode()) {
-      if (walker.currentNode.textContent?.includes(text)) {
-        count += 1
-      }
-    }
-    return count
-  }, expected)
-}
-
-async function reloadIntoColdRenderer(fixture: SeededFixture): Promise<void> {
-  await fixture.page.reload()
-  await waitForAppReady(fixture, 120_000)
-  await openNewSession(fixture.page)
-}
-
-async function assertUnchangedResume(page: Page, testInfo: TestInfo): Promise<void> {
-  await openSeededSession(page)
-  await page.waitForTimeout(1_000)
-  await page.screenshot({ path: testInfo.outputPath('unchanged-session-resume.png'), fullPage: false })
-
-  const paints = await paintState(page)
-  expect(await textNodeOccurrences(page, EXPECTED_TEXT), 'the resumed user message should appear once').toBe(1)
-  // A warm session first restores its retained view, then reconciles it with the
-  // authoritative transcript. That is bounded at two builds; a third paint was
-  // the old eager-prefetch + runtime-rebuild regression. A cold restore has one.
-  expect(paints.bursts, `unexpected transcript paint count: ${JSON.stringify(paints.timeline)}`).toBeLessThanOrEqual(2)
-}
-
-test.describe('large session resume', () => {
-  let fixture: SeededFixture | null = null
-
-  test.afterEach(async () => {
-    await fixture?.cleanup()
-    fixture = null
-  })
-
-  test('cold resume of an unchanged session has one user row and bounded transcript paints', async ({}, testInfo) => {
-    fixture = await setupSeededDesktop()
-    await waitForAppReady(fixture, 120_000)
-
-    await startPaintObserver(fixture.page)
-    await assertUnchangedResume(fixture.page, testInfo)
-  })
-
-  test('fast resume of an unchanged session has one user row and bounded transcript paints', async ({}, testInfo) => {
-    // Known RED: a rapid warm resume rebuilds the transcript three times
-    // (28 → 53 → 53 DOM additions) instead of the two-paint budget. Keep the
-    // regression visible without making unrelated desktop work fail CI.
-    test.fixme(true, 'Fast warm resume has an unresolved third transcript rebuild')
-
-    fixture = await setupSeededDesktop()
-    await waitForAppReady(fixture, 120_000)
-
-    await openSeededSession(fixture.page)
-    await openNewSession(fixture.page)
-    await startPaintObserver(fixture.page)
-    await assertUnchangedResume(fixture.page, testInfo)
-  })
-
-  for (const resumeKind of ['fast', 'cold'] as const) {
-    test(`${resumeKind} resume keeps background inference attached without duplicate messages`, async ({}, testInfo) => {
-      fixture = await setupSeededDesktop({ holdFirstStreamForPrompt: BACKGROUND_PROMPT })
-      await waitForAppReady(fixture, 120_000)
-
-      await openSeededSession(fixture.page)
-      const initialMockReplyCount = await textNodeOccurrences(fixture.page, MOCK_REPLY)
-      await submitPrompt(fixture.page, BACKGROUND_PROMPT)
-      await fixture.mock.waitForHeldStream()
-      await openNewSession(fixture.page)
-
-      if (resumeKind === 'cold') {
-        await reloadIntoColdRenderer(fixture)
-      }
-
-      await openSeededSession(fixture.page)
-      fixture.mock.releaseHeldStream()
-      await fixture.page.waitForFunction(
-        expected => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-        MOCK_REPLY,
-        { timeout: 60_000 },
-      )
-      await fixture.page.waitForTimeout(300)
-      await fixture.page.screenshot({ path: testInfo.outputPath(`${resumeKind}-background-inference-resume.png`), fullPage: false })
-
-      expect(await textNodeOccurrences(fixture.page, BACKGROUND_PROMPT), 'the running user prompt should appear once').toBe(1)
-      expect(
-        await textNodeOccurrences(fixture.page, MOCK_REPLY),
-        'the completed assistant reply should add exactly one transcript row',
-      ).toBe(initialMockReplyCount + 1)
-    })
-  }
-})
@@ -1,4 +1,4 @@
-import { expect, test } from './test'
+import { expect, test } from '@playwright/test'

 import {
  PACKAGED_BINARY_PATH,
@@ -15,7 +15,7 @@
 * Prerequisite: `npm run build` must have been run so dist/ exists.
 */

-import { expect, test } from './test'
+import { expect, test } from '@playwright/test'

 import {
  type MockBackendFixture,
@@ -15,282 +15,17 @@
 */

 import http from 'node:http'
-import type { ServerResponse } from 'node:http'

 /** A canned assistant reply used for every chat completion request. */
-export const MOCK_REPLY = 'Hello from the mock inference server! The full boot chain is working.'
-
-export interface MockServerOptions {
-  /** Pause the matching stream after its first token for session-switch E2E coverage. */
-  holdFirstStreamForPrompt?: string
-/** Pause the first completion whose request JSON contains this text. */
-holdFirstCompletionContaining?: string
-/** Absolute sandbox path written by the verify-on-stop scripted tool call. */
-verificationWritePath?: string
-}
-
-export interface MockServer {
-  port: number
-  url: string
-  receivedPrompts: string[]
-  waitForHeldStream: () => Promise<void>
-  waitForHeldCompletion: () => Promise<void>
-  releaseHeldStream: () => void
-  heldCompletionCount: () => number
-  close: () => Promise<void>
-}
-
-// ─── Multi-turn interim script ─────────────────────────────────────────
-//
-// When the user's message contains the trigger keyword, the mock server
-// walks through a scripted sequence of responses that exercise the
-// interim-assistant-message fix (#65919) across several patterns:
-//
-//   1. text + single tool_call  → should produce an interim message
-//   2. text + single tool_call  → another interim message
-//   3. no text + tool_call       → NO interim (no visible text alongside tools)
-//   4. text + single tool_call  → another interim message
-//   5. final answer (stop)      → message.complete, different from all interims
-//
-// Each "turn" is one API call. The agent executes the tool after each
-// tool_calls response, then re-calls the API, advancing to the next turn.
-
-export interface ScriptedTurn {
-  /** Assistant text content to stream. Empty string = no visible text. */
-  text: string
-  /** Tool calls to emit. Empty array = final turn (finish_reason: stop). */
-  toolCalls?: Array<{
-    name: string
-    args: Record<string, unknown>
-  }>
-}
-
-const INTERIM_SCRIPT: ScriptedTurn[] = [
-  {
-    text: 'Let me start by planning the approach.',
-    toolCalls: [{ name: 'todo', args: { todos: [{ id: '1', content: 'Plan', status: 'in_progress' }] } }],
-  },
-  {
-    text: 'Now checking the details before answering.',
-    toolCalls: [{ name: 'todo', args: { todos: [{ id: '2', content: 'Check details', status: 'in_progress' }] } }],
-  },
-  {
-    // No visible text alongside this tool call — should NOT produce an
-    // interim message. The agent fires _emit_interim_assistant_message
-    // but _interim_assistant_visible_text returns "" so it's a no-op.
-    text: '',
-    toolCalls: [{ name: 'todo', args: { todos: [{ id: '3', content: 'Silent step', status: 'completed' }] } }],
-  },
-  {
-    text: 'Found something interesting worth noting.',
-    toolCalls: [{ name: 'todo', args: { todos: [{ id: '4', content: 'Note finding', status: 'completed' }] } }],
-  },
-  {
-    // Final answer — different from all interim texts.
-    text: 'All done! Here is the complete summary of what I found.',
-  },
-]
-
-/** Per-server request counter so we can walk through the script turns. */
-let _scriptIndex = 0
-
-/** Per-server counter for the sidebar-states script (independent from _scriptIndex). */
-let _sidebarScriptIndex = 0
-
-/** Per-server counter for the cross-session sidebar script. */
-let _sidebarCrossIndex = 0
-
-/** Per-server counter for the queue-stop script. */
-let _queueStopIndex = 0
-
-/** Per-server counter for the correction/session-switch script. */
-let _correctionSwitchIndex = 0
-
-/** Per-server counter for the verify-on-stop script. */
-let _verificationStopIndex = 0
-
-/** User messages received by the mock, for E2E assertions on real submits. */
-const _receivedUserTexts: string[] = []
-
-/** Reset the script indices (called between tests via restartMockServer). */
-function resetScriptIndex(): void {
-  _scriptIndex = 0
-  _sidebarScriptIndex = 0
-  _sidebarCrossIndex = 0
-  _queueStopIndex = 0
-  _correctionSwitchIndex = 0
-  _verificationStopIndex = 0
-  _receivedUserTexts.length = 0
-}
-
-/** Return the user prompts the real backend submitted to this mock server. */
-export function receivedUserTexts(): readonly string[] {
-  return _receivedUserTexts
-}
-
-// ─── Sidebar-states script ─────────────────────────────────────────────
-//
-// A separate trigger (E2E_SIDEBAR_TRIGGER) exercises the desktop sidebar's
-// background-process and subagent states. The mock returns tool_calls that
-// the agent executes for real — `terminal(background=true)` spawns a real
-// (but trivial) background process, and `delegate_task` spawns a real
-// subagent that calls the mock server and gets the canned reply.
-//
-// Turn 1: text + terminal(bg=true) + delegate_task → tools execute
-// Turn 2: final answer → message.complete, dot transitions
-
-const SIDEBAR_SCRIPT: ScriptedTurn[] = [
-  {
-    text: 'Let me run a background task and delegate some work.',
-    toolCalls: [
-      {
-        name: 'terminal',
-        args: {
-          command: 'echo "background process output" && sleep 1 && echo "done"',
-          background: true,
-          notify_on_complete: true,
-        },
-      },
-      {
-        name: 'delegate_task',
-        args: {
-          goal: 'Summarize the test results',
-          context: 'This is a test subagent for the sidebar states E2E test.',
-        },
-      },
-    ],
-  },
-  {
-    text: 'All tasks complete. The background process finished and the subagent returned its summary.',
-  },
-]
-
-// ─── Sidebar cross-session script ──────────────────────────────────────
-//
-// E2E_SIDEBAR_CROSS trigger uses a longer background process (sleep 5) so
-// the "background running" dot is visible long enough for the test to:
-//   1. See the background dot while the subagent runs.
-//   2. Open a different session and see session A's dot transition to
-//      "finished unread" when the background process completes.
-
-const SIDEBAR_CROSS_SCRIPT: ScriptedTurn[] = [
-  {
-    text: 'Starting a long background task and delegating work.',
-    toolCalls: [
-      {
-        name: 'terminal',
-        args: {
-          command: 'echo "long bg output" && sleep 5 && echo "finished"',
-          background: true,
-          notify_on_complete: true,
-        },
-      },
-      {
-        name: 'delegate_task',
-        args: {
-          goal: 'Analyze cross-session state',
-          context: 'Testing that the background dot updates across sessions.',
-        },
-      },
-    ],
-  },
-  {
-    text: 'Both tasks are running in the background now.',
-  },
-]
-
-const QUEUE_STOP_SCRIPT: ScriptedTurn[] = [
-  {
-    text: 'Starting a task that will keep this turn active.',
-    toolCalls: [{ name: 'clarify', args: { question: 'Keep working?', choices: ['Yes', 'No'] } }],
-  },
-  { text: 'The paused task completed.' },
-]
-
-// The reported correction arrived while a foreground tool was still running.
-// Keep that boundary open long enough for the renderer to redirect the turn,
-// then let the next model request complete normally.
-const CORRECTION_SWITCH_SCRIPT: ScriptedTurn[] = [
-  {
-    text: 'Checking the long-running task before I continue.',
-    toolCalls: [{ name: 'terminal', args: { command: 'sleep 5' } }],
-  },
-  { text: 'The corrected task finished.' },
-]
-
-export const CORRECTION_SWITCH_TRIGGER = 'E2E_CORRECTION_SWITCH_TRIGGER'
-
-/**
- * Drives a real code edit followed by two finish attempts. Hermes should add
- * its synthetic verify-on-stop continuation after each finish attempt until
- * the bounded verifier gives up. The mock's request capture proves the nudge
- * reached the model; desktop must never render it as chat content.
- */
-function verificationStopScript(writePath: string): ScriptedTurn[] {
-  return [
-  {
-    text: 'I will make the requested code change.',
-    toolCalls: [{
-      name: 'write_file',
-      args: {
-        path: writePath,
-        content: 'def changed_by_e2e():\n    return "changed"\n',
-      },
-    }],
-  },
-  { text: 'The code edit is complete.' },
-  { text: 'I cannot provide fresh verification evidence for that edit.' },
-  ]
-}
-
-export const VERIFICATION_STOP_TRIGGER = 'E2E_VERIFY_ON_STOP_TRIGGER'
-export const VERIFICATION_STOP_TEXT = 'I cannot provide fresh verification evidence for that edit.'
-
-/**
- * A marker that makes the mock emit a real blocking clarify tool call. Tests
- * use it to hold a turn open while exercising busy-composer interactions.
- */
-export const BLOCKING_CLARIFY_TRIGGER = 'E2E_BLOCKING_CLARIFY_TRIGGER'
-export const BLOCKING_CLARIFY_QUESTION = 'Keep this test turn running?'
-
-const BLOCKING_CLARIFY_TURN: ScriptedTurn = {
-  text: '',
-  toolCalls: [{ name: 'clarify', args: { question: BLOCKING_CLARIFY_QUESTION, choices: ['Yes', 'No'] } }],
-}
-
-function includesBlockingClarifyTrigger(value: unknown): boolean {
-  if (typeof value === 'string') {
-    return value.includes(BLOCKING_CLARIFY_TRIGGER)
-  }
-
-  if (Array.isArray(value)) {
-    return value.some(includesBlockingClarifyTrigger)
-  }
-
-  if (value && typeof value === 'object') {
-    return Object.values(value).some(includesBlockingClarifyTrigger)
-  }
-
-  return false
-}
+const CANNED_REPLY = 'Hello from the mock inference server! The full boot chain is working.'

 /**
 * Start the mock server on an ephemeral port.
 *
- * @returns a handle with `port`, `url`, received user prompts, and `close()`.
+ * @returns a handle with `port`, `url`, and `close()`.
 */
-export function startMockServer(options: MockServerOptions = {}): Promise<MockServer> {
+export function startMockServer(): Promise<{ port: number; url: string; close: () => Promise<void> }> {
  return new Promise((resolve, reject) => {
-    const receivedPrompts: string[] = []
-    let resolveHeldStreamStarted: (() => void) | null = null
-    let releaseHeldStream: (() => void) | null = null
-    let heldCompletionCount = 0
-    const heldStreamStarted = new Promise<void>(resolveHeld => {
-      resolveHeldStreamStarted = resolveHeld
-    })
-    const heldStreamReleased = new Promise<void>(resolveRelease => {
-      releaseHeldStream = resolveRelease
-    })
    const server = http.createServer((req, res) => {
      // CORS headers — the Electron renderer doesn't need them, but they
      // don't hurt and make the server usable from a browser context too.
@@ -340,143 +75,88 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
            // malformed JSON — treat as non-streaming with defaults
          }

-          const lastUserMessage = [...(parsed.messages ?? [])]
-            .reverse()
-            .find((message: { role?: unknown }) => message?.role === 'user')
-
-          if (typeof lastUserMessage?.content === 'string') {
-            receivedPrompts.push(lastUserMessage.content)
-          }
-
          const stream = parsed.stream === true
          const model = parsed.model || 'mock-model'
-          const holdThisCompletion = Boolean(
-            options.holdFirstCompletionContaining &&
-            heldCompletionCount === 0 &&
-            JSON.stringify(parsed).includes(options.holdFirstCompletionContaining),
-          )
-
-          // Detect the interim-message test trigger: the user's message
-          // contains a specific keyword. The mock walks through the
-          // INTERIM_SCRIPT turns in sequence.
-          //
-          // The trigger keyword is chosen so normal chat tests (which send
-          // "Hello, can you hear me?" etc.) never hit this path.
-          const messages: any[] = Array.isArray(parsed.messages) ? parsed.messages : []
-          const lastUserMsg = [...messages].reverse().find(m => m?.role === 'user')
-          const userText = typeof lastUserMsg?.content === 'string' ? lastUserMsg.content : ''
-          if (userText) {
-            _receivedUserTexts.push(userText)
-          }
-          const isInterimTrigger = userText.includes('E2E_INTERIM_TRIGGER')
-          const isSidebarTrigger = userText.includes('E2E_SIDEBAR_TRIGGER')
-          const isSidebarCrossTrigger = userText.includes('E2E_SIDEBAR_CROSS')
-          const isQueueStopTrigger = userText.includes('E2E_QUEUE_STOP_TRIGGER')
-          const isVerificationStopTrigger = messages.some(
-            message => typeof message?.content === 'string' && message.content.includes(VERIFICATION_STOP_TRIGGER),
-          )
-          const isCorrectionSwitchTrigger = messages.some(
-            message => typeof message?.content === 'string' && message.content.includes(CORRECTION_SWITCH_TRIGGER),
-          )
-
-          if (includesBlockingClarifyTrigger(parsed.messages)) {
-            if (stream) {
-              streamScriptedTurn(res, model, BLOCKING_CLARIFY_TURN)
-            } else {
-              nonStreamingScriptedTurn(res, model, BLOCKING_CLARIFY_TURN)
-            }
-            return
-          }
-
-          if (isQueueStopTrigger) {
-            const turn = QUEUE_STOP_SCRIPT[_queueStopIndex] ?? QUEUE_STOP_SCRIPT[QUEUE_STOP_SCRIPT.length - 1]
-            _queueStopIndex++
-            if (stream) {
-              streamScriptedTurn(res, model, turn)
-            } else {
-              nonStreamingScriptedTurn(res, model, turn)
-            }
-            return
-          }
-
-          if (isVerificationStopTrigger) {
-            const script = verificationStopScript(options.verificationWritePath ?? 'e2e-verification-target.py')
-            const turn = script[_verificationStopIndex] ?? script[script.length - 1]
-            _verificationStopIndex++
-            if (stream) {
-              streamScriptedTurn(res, model, turn)
-            } else {
-              nonStreamingScriptedTurn(res, model, turn)
-            }
-            return
-          }
-
-          if (isCorrectionSwitchTrigger) {
-            const turn = CORRECTION_SWITCH_SCRIPT[_correctionSwitchIndex] ?? CORRECTION_SWITCH_SCRIPT[CORRECTION_SWITCH_SCRIPT.length - 1]
-            _correctionSwitchIndex++
-            if (stream) {
-              streamScriptedTurn(res, model, turn)
-            } else {
-              nonStreamingScriptedTurn(res, model, turn)
-            }
-            return
-          }
-
-          if (isSidebarCrossTrigger) {
-            const turn = SIDEBAR_CROSS_SCRIPT[_sidebarCrossIndex] ?? SIDEBAR_CROSS_SCRIPT[SIDEBAR_CROSS_SCRIPT.length - 1]
-            _sidebarCrossIndex++
-
-            if (stream) {
-              streamScriptedTurn(res, model, turn)
-            } else {
-              nonStreamingScriptedTurn(res, model, turn)
-            }
-            return
-          }
-
-          if (isSidebarTrigger) {
-            const turn = SIDEBAR_SCRIPT[_sidebarScriptIndex] ?? SIDEBAR_SCRIPT[SIDEBAR_SCRIPT.length - 1]
-            _sidebarScriptIndex++
-
-            if (stream) {
-              streamScriptedTurn(res, model, turn)
-            } else {
-              nonStreamingScriptedTurn(res, model, turn)
-            }
-            return
-          }
-
-          if (isInterimTrigger) {
-            const turn = INTERIM_SCRIPT[_scriptIndex] ?? INTERIM_SCRIPT[INTERIM_SCRIPT.length - 1]
-            _scriptIndex++
-            if (stream) {
-              streamScriptedTurn(res, model, turn)
-            } else {
-              nonStreamingScriptedTurn(res, model, turn)
-            }
-            return
-          }

          if (stream) {
-            const holdThisStream = Boolean(
-              options.holdFirstStreamForPrompt && typeof lastUserMessage?.content === 'string' &&
-                lastUserMessage.content.includes(options.holdFirstStreamForPrompt),
-            )
-            streamTextResponse(res, model, MOCK_REPLY, holdThisStream || holdThisCompletion ? () => {
-              if (holdThisCompletion) {
-                heldCompletionCount++
+            res.writeHead(200, {
+              'Content-Type': 'text/event-stream',
+              'Cache-Control': 'no-cache',
+              Connection: 'keep-alive',
+            })
+
+            // Send the content in a few chunks to simulate streaming.
+            const words = CANNED_REPLY.split(' ')
+            let i = 0
+
+            const sendChunk = () => {
+              if (i >= words.length) {
+                // Final chunk with finish_reason
+                res.write(
+                  `data: ${JSON.stringify({
+                    id: 'mock-completion',
+                    object: 'chat.completion.chunk',
+                    created: 0,
+                    model,
+                    choices: [
+                      {
+                        index: 0,
+                        delta: {},
+                        finish_reason: 'stop',
+                      },
+                    ],
+                  })}\n\n`,
+                )
+                res.write('data: [DONE]\n\n')
+                res.end()
+                return
              }
-              resolveHeldStreamStarted?.()
-              return heldStreamReleased
-            } : undefined)
-          } else {
-            if (holdThisCompletion) {
-              heldCompletionCount++
-              resolveHeldStreamStarted?.()
-              void heldStreamReleased.then(() => nonStreamingTextResponse(res, model, MOCK_REPLY))
-            } else {
-              nonStreamingTextResponse(res, model, MOCK_REPLY)
+
+              const word = i === 0 ? words[i] : ' ' + words[i]
+              res.write(
+                `data: ${JSON.stringify({
+                  id: 'mock-completion',
+                  object: 'chat.completion.chunk',
+                  created: 0,
+                  model,
+                  choices: [
+                    {
+                      index: 0,
+                      delta: { content: word },
+                      finish_reason: null,
+                    },
+                  ],
+                })}\n\n`,
+              )
+              i++
+              // Small delay between chunks to simulate real streaming.
+              setTimeout(sendChunk, 20)
            }
+
+            sendChunk()
+          } else {
+            // Non-streaming response
+            res.writeHead(200, { 'Content-Type': 'application/json' })
+            res.end(
+              JSON.stringify({
+                id: 'mock-completion',
+                object: 'chat.completion',
+                created: 0,
+                model,
+                choices: [
+                  {
+                    index: 0,
+                    message: { role: 'assistant', content: CANNED_REPLY },
+                    finish_reason: 'stop',
+                  },
+                ],
+                usage: {
+                  prompt_tokens: 10,
+                  completion_tokens: 20,
+                  total_tokens: 30,
+                },
+              }),
+            )
          }
        })

@@ -507,11 +187,6 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
      resolve({
        port,
        url,
-        receivedPrompts,
-        waitForHeldStream: () => heldStreamStarted,
-        waitForHeldCompletion: () => heldStreamStarted,
-        releaseHeldStream: () => releaseHeldStream?.(),
-        heldCompletionCount: () => heldCompletionCount,
        close: () =>
          new Promise((resolveClose, rejectClose) => {
            server.close((err) => {
@@ -526,238 +201,3 @@ export function startMockServer(options: MockServerOptions = {}): Promise<MockSe
    })
  })
 }
-
-// ─── Response helpers ──────────────────────────────────────────────────
-
-/** SSE chunk shape for a streaming chat completion. */
-function sseChunk(model: string, delta: Record<string, unknown>, finishReason: string | null = null): string {
-  return `data: ${JSON.stringify({
-    id: 'mock-completion',
-    object: 'chat.completion.chunk',
-    created: 0,
-    model,
-    choices: [{ index: 0, delta, finish_reason: finishReason }],
-  })}\n\n`
-}
-
-/**
- * Stream a plain text response (no tool calls) as SSE, finishing with
- * `finish_reason: "stop"`. This is the default canned-reply path.
- */
-function streamTextResponse(
-  res: ServerResponse,
-  model: string,
-  text: string,
-  waitForRelease?: () => Promise<void>,
-): void {
-  res.writeHead(200, {
-    'Content-Type': 'text/event-stream',
-    'Cache-Control': 'no-cache',
-    Connection: 'keep-alive',
-  })
-
-  const words = text.split(' ')
-  let i = 0
-
-  const sendChunk = (): void => {
-    if (i >= words.length) {
-      res.write(sseChunk(model, {}, 'stop'))
-      res.write('data: [DONE]\n\n')
-      res.end()
-      return
-    }
-
-    const word = i === 0 ? words[i] : ' ' + words[i]
-    res.write(sseChunk(model, { content: word }))
-    i++
-    if (waitForRelease && i === 1) {
-      waitForRelease().then(() => setTimeout(sendChunk, 20))
-      return
-    }
-    setTimeout(sendChunk, 20)
-  }
-
-  sendChunk()
-}
-
-/** Non-streaming plain text response. */
-function nonStreamingTextResponse(res: ServerResponse, model: string, text: string): void {
-  res.writeHead(200, { 'Content-Type': 'application/json' })
-  res.end(
-    JSON.stringify({
-      id: 'mock-completion',
-      object: 'chat.completion',
-      created: 0,
-      model,
-      choices: [
-        {
-          index: 0,
-          message: { role: 'assistant', content: text },
-          finish_reason: 'stop',
-        },
-      ],
-      usage: { prompt_tokens: 10, completion_tokens: 20, total_tokens: 30 },
-    }),
-  )
-}
-
-/**
- * Stream a single scripted turn: first the text content (word by word),
- * then a chunk carrying the tool_calls (if any), with the appropriate
- * finish_reason.
- *
- * If the turn has no text and no tool calls, it's an empty final response.
- * If it has text but no tool calls, it's a final answer (finish_reason: stop).
- * If it has tool calls (with or without text), finish_reason is "tool_calls".
- */
-function streamScriptedTurn(
-  res: ServerResponse,
-  model: string,
-  turn: ScriptedTurn,
-): void {
-  res.writeHead(200, {
-    'Content-Type': 'text/event-stream',
-    'Cache-Control': 'no-cache',
-    Connection: 'keep-alive',
-  })
-
-  const hasToolCalls = turn.toolCalls && turn.toolCalls.length > 0
-  const finishReason = hasToolCalls ? 'tool_calls' : 'stop'
-
-  // If there's no text to stream, go straight to the tool_calls / finish.
-  if (!turn.text) {
-    if (hasToolCalls) {
-      res.write(
-        sseChunk(model, {
-          tool_calls: turn.toolCalls!.map((tc, idx) => ({
-            index: idx,
-            id: `call_e2e_${_scriptIndex}_${idx}`,
-            type: 'function',
-            function: { name: tc.name, arguments: JSON.stringify(tc.args) },
-          })),
-        }, finishReason),
-      )
-    } else {
-      res.write(sseChunk(model, {}, finishReason))
-    }
-    res.write('data: [DONE]\n\n')
-    res.end()
-    return
-  }
-
-  // Stream the text word by word, then emit tool_calls if present.
-  const words = turn.text.split(' ')
-  let i = 0
-
-  const sendChunk = (): void => {
-    if (i >= words.length) {
-      // All text streamed — emit tool_calls if present, then finish.
-      if (hasToolCalls) {
-        res.write(
-          sseChunk(model, {
-            tool_calls: turn.toolCalls!.map((tc, idx) => ({
-              index: idx,
-              id: `call_e2e_${_scriptIndex}_${idx}`,
-              type: 'function',
-              function: { name: tc.name, arguments: JSON.stringify(tc.args) },
-            })),
-          }, finishReason),
-        )
-      } else {
-        res.write(sseChunk(model, {}, finishReason))
-      }
-      res.write('data: [DONE]\n\n')
-      res.end()
-      return
-    }
-
-    const word = i === 0 ? words[i] : ' ' + words[i]
-    res.write(sseChunk(model, { content: word }))
-    i++
-    setTimeout(sendChunk, 20)
-  }
-
-  sendChunk()
-}
-
-/** Non-streaming version of a scripted turn. */
-function nonStreamingScriptedTurn(
-  res: ServerResponse,
-  model: string,
-  turn: ScriptedTurn,
-): void {
-  const hasToolCalls = turn.toolCalls && turn.toolCalls.length > 0
-  const finishReason = hasToolCalls ? 'tool_calls' : 'stop'
-
-  const message: Record<string, unknown> = { role: 'assistant' }
-  if (turn.text) {
-    message.content = turn.text
-  }
-  if (hasToolCalls) {
-    message.tool_calls = turn.toolCalls!.map((tc, idx) => ({
-      id: `call_e2e_${_scriptIndex}_${idx}`,
-      type: 'function',
-      function: { name: tc.name, arguments: JSON.stringify(tc.args) },
-    }))
-  }
-
-  res.writeHead(200, { 'Content-Type': 'application/json' })
-  res.end(
-    JSON.stringify({
-      id: 'mock-completion',
-      object: 'chat.completion',
-      created: 0,
-      model,
-      choices: [{ index: 0, message, finish_reason: finishReason }],
-      usage: { prompt_tokens: 10, completion_tokens: 20, total_tokens: 30 },
-    }),
-  )
-}
-
-/**
- * Restart the mock server's script index so each test starts from turn 0.
- * Call this between tests that use the interim trigger.
- */
-export function restartMockServer(): void {
-  resetScriptIndex()
-}
-
-/**
- * The interim script's text constants, exported for test assertions.
- * Each entry is the visible text of one turn. Turns with empty text
- * produce no interim message and are excluded from this list.
- */
-export const INTERIM_TEXTS = {
-  /** All interim texts that should appear as sealed messages when the flag is ON. */
-  interims: INTERIM_SCRIPT
-    .filter((t) => t.text && t.toolCalls)
-    .map((t) => t.text),
-  /** The final answer text. */
-  finalText: INTERIM_SCRIPT[INTERIM_SCRIPT.length - 1].text,
-  /** Text that should NOT produce an interim (empty-text tool turn). */
-  silentTurnIndex: INTERIM_SCRIPT.findIndex((t) => !t.text && t.toolCalls),
-} as const
-
-/** The sidebar-states script's text constants, exported for test assertions. */
-export const SIDEBAR_TEXTS = {
-  /** The interim text from turn 1 (alongside tool calls). */
-  interimText: SIDEBAR_SCRIPT[0].text,
-  /** The final answer text. */
-  finalText: SIDEBAR_SCRIPT[SIDEBAR_SCRIPT.length - 1].text,
-  /** The background process command (for asserting process.list entries). */
-  bgCommand: 'echo "background process output" && sleep 1 && echo "done"',
-  /** The subagent's goal (for asserting subagent panel state). */
-  subagentGoal: 'Summarize the test results',
-} as const
-
-/** The cross-session sidebar script's text constants. */
-export const SIDEBAR_CROSS_TEXTS = {
-  /** The interim text from turn 1. */
-  interimText: SIDEBAR_CROSS_SCRIPT[0].text,
-  /** The final answer text. */
-  finalText: SIDEBAR_CROSS_SCRIPT[SIDEBAR_CROSS_SCRIPT.length - 1].text,
-  /** The longer background process command (sleep 5). */
-  bgCommand: 'echo "long bg output" && sleep 5 && echo "finished"',
-  /** The subagent's goal. */
-  subagentGoal: 'Analyze cross-session state',
-} as const
@@ -9,7 +9,7 @@
 * Prerequisite: `npm run build` must have been run so dist/ exists.
 */

-import { expect, test } from './test'
+import { expect, test } from '@playwright/test'

 import {
  type NoProviderFixture,
@@ -1,119 +0,0 @@
-/**
- * A queued prompt must remain local until the current inference turn settles.
- *
- * Hold the first streamed reply open after its first token. This gives the
- * composer a live, busy turn while the user queues a follow-up, then lets us
- * assert against the mock provider's real request log before and after the
- * held turn completes.
- */
-
-import { expect, test, type Page } from './test'
-
-import { type MockBackendFixture, setupMockBackend, waitForAppReady } from './fixtures'
-import { MOCK_REPLY } from './mock-server'
-
-const ACTIVE_PROMPT = 'E2E_QUEUE_TURN_BOUNDARY_ACTIVE'
-const QUEUED_PROMPT = 'E2E_QUEUE_TURN_BOUNDARY_QUEUED'
-const STEER_PROMPT = 'E2E_STEER_TURN_BOUNDARY_CORRECTION'
-
-async function send(page: Page, text: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.waitFor({ state: 'visible', timeout: 15_000 })
-  await composer.click()
-  await composer.type(text, { delay: 5 })
-  await page.keyboard.press('Enter')
-}
-
-async function steer(page: Page, text: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-
-  await composer.click()
-  await composer.type(text, { delay: 5 })
-  await page.keyboard.press('Enter')
-}
-
-async function queue(page: Page, text: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-
-  await composer.click()
-  await composer.type(text, { delay: 5 })
-  await page.keyboard.press('Control+Enter')
-}
-
-async function transcriptMessageOrder(page: Page): Promise<string[]> {
-  return page.evaluate(() => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    if (!viewport) return []
-
-    return Array.from(viewport.querySelectorAll<HTMLElement>('[data-role="user"], [data-role="assistant"]'))
-      .map(message => message.textContent?.trim() ?? '')
-      .filter(Boolean)
-  })
-}
-
-function steerTurnOrder(messages: string[]): string[] {
-  return messages.flatMap(message => {
-    if (message.includes(ACTIVE_PROMPT)) return [ACTIVE_PROMPT]
-    if (message.includes(STEER_PROMPT)) return [STEER_PROMPT]
-    if (message.includes(MOCK_REPLY)) return [MOCK_REPLY]
-
-    return []
-  })
-}
-
-test.describe('queued prompt turn boundary', () => {
-  let fixture: MockBackendFixture | null = null
-
-  test.beforeEach(async () => {
-    fixture = await setupMockBackend({
-      mockServer: { holdFirstStreamForPrompt: ACTIVE_PROMPT }
-    })
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterEach(async () => {
-    await fixture?.cleanup()
-    fixture = null
-  })
-
-  test('submits a queued prompt only after the active turn completes', async () => {
-    const { mock, page } = fixture!
-
-    await send(page, ACTIVE_PROMPT)
-    await mock.waitForHeldStream()
-    await queue(page, QUEUED_PROMPT)
-    await expect(page.getByText('1 Queued')).toBeVisible()
-
-    // The mock keeps the active SSE stream open, so a queued prompt has no
-    // completed-turn boundary that could legitimately drain it. Wait past the
-    // queue retry interval and assert the provider saw only the active turn.
-    await page.waitForTimeout(1_000)
-    expect(mock.receivedPrompts.filter(prompt => prompt === QUEUED_PROMPT)).toHaveLength(0)
-    await expect(page.locator('[data-slot="aui_thread-viewport"]')).not.toContainText(QUEUED_PROMPT)
-
-    mock.releaseHeldStream()
-    await page.waitForFunction(
-      expected => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-      MOCK_REPLY,
-      { timeout: 60_000 }
-    )
-    await expect.poll(() => mock.receivedPrompts.filter(prompt => prompt === QUEUED_PROMPT)).toHaveLength(1)
-  })
-
-  test('places a steer prompt before the reply it redirects', async () => {
-    const { mock, page } = fixture!
-
-    await send(page, ACTIVE_PROMPT)
-    await mock.waitForHeldStream()
-    await steer(page, STEER_PROMPT)
-    mock.releaseHeldStream()
-
-    await page.waitForFunction(
-      expected => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(expected),
-      MOCK_REPLY,
-      { timeout: 60_000 }
-    )
-
-    expect(steerTurnOrder(await transcriptMessageOrder(page))).toEqual([ACTIVE_PROMPT, STEER_PROMPT, MOCK_REPLY])
-  })
-})
@@ -1,226 +0,0 @@
-import { type ChildProcessWithoutNullStreams, spawn } from 'node:child_process'
-import * as path from 'node:path'
-import { createInterface } from 'node:readline'
-
-const DESKTOP_ROOT = path.resolve(import.meta.dirname, '..')
-const REPO_ROOT = path.resolve(DESKTOP_ROOT, '..', '..')
-const DEFAULT_TIMEOUT_MS = 60_000
-
-interface JsonRpcError {
-  code?: number
-  message?: string
-}
-
-interface JsonRpcFrame {
-  error?: JsonRpcError
-  id?: number
-  method?: string
-  params?: {
-    payload?: unknown
-    session_id?: string
-    type?: string
-  }
-  result?: unknown
-}
-
-interface CreatedSession {
-  session_id: string
-  stored_session_id: string
-}
-
-export interface RealSessionSpec {
-  /** Human-visible sidebar title, persisted by the first completed turn. */
-  title: string
-  /** Each item becomes one real user prompt followed by the mock provider's reply. */
-  turns: readonly string[]
-}
-
-export interface RealSession {
-  /** Runtime-only TUI session id, valid only while the builder process is alive. */
-  runtimeId: string
-  /** Durable SessionDB id that desktop resumes after the builder exits. */
-  sessionId: string
-}
-
-/**
- * Creates durable desktop session history through the real TUI gateway and
- * AIAgent loop, using the E2E mock provider configured in `hermesHome`.
- *
- * This intentionally uses the shipped stdio JSON-RPC transport instead of
- * importing SessionDB or launching Electron. The desktop's WebSocket backend
- * dispatches the same `tui_gateway.server` methods.
- */
-export class RealSessionBuilder {
-  private readonly child: ChildProcessWithoutNullStreams
-  private nextRequestId = 0
-  private readonly pending = new Map<number, { reject: (reason: Error) => void; resolve: (value: unknown) => void }>()
-  private readonly events: JsonRpcFrame[] = []
-  private readonly eventWaiters: Array<{
-    predicate: (frame: JsonRpcFrame) => boolean
-    reject: (reason: Error) => void
-    resolve: (frame: JsonRpcFrame) => void
-  }> = []
-  private readonly stderr: string[] = []
-  private closed = false
-
-  private constructor(hermesHome: string) {
-    this.child = spawn('uv', ['run', '--active', '--no-sync', 'python', '-m', 'tui_gateway.entry'], {
-      cwd: REPO_ROOT,
-      env: {
-        ...process.env,
-        HERMES_HOME: hermesHome,
-        PYTHONPATH: REPO_ROOT,
-      },
-      stdio: 'pipe',
-    })
-
-    createInterface({ input: this.child.stdout }).on('line', line => this.handleLine(line))
-    createInterface({ input: this.child.stderr }).on('line', line => {
-      this.stderr.push(line)
-      if (this.stderr.length > 80) this.stderr.shift()
-    })
-    this.child.once('error', error => this.failAll(new Error(`real-session gateway failed to start: ${error.message}`)))
-    this.child.once('exit', (code, signal) => {
-      if (!this.closed) {
-        this.failAll(new Error(`real-session gateway exited unexpectedly (${signal ?? code ?? 'unknown'}):\n${this.stderr.join('\n')}`))
-      }
-    })
-  }
-
-  static async start(hermesHome: string): Promise<RealSessionBuilder> {
-    const builder = new RealSessionBuilder(hermesHome)
-    await builder.waitForEvent(frame => frame.params?.type === 'gateway.ready')
-    return builder
-  }
-
-  async createSession(spec: RealSessionSpec): Promise<RealSession> {
-    if (spec.turns.length === 0) {
-      throw new Error('RealSessionBuilder requires at least one turn so the real agent creates a durable session row')
-    }
-
-    const created = await this.request<CreatedSession>('session.create', {
-      cols: 120,
-      cwd: REPO_ROOT,
-      source: 'desktop',
-      title: spec.title,
-    })
-    const runtimeId = requireString(created, 'session_id')
-    const sessionId = requireString(created, 'stored_session_id')
-
-    for (const text of spec.turns) {
-      const completion = this.waitForEvent(
-        frame => frame.params?.type === 'message.complete' && frame.params.session_id === runtimeId,
-      )
-      await this.request('prompt.submit', { session_id: runtimeId, text })
-      const frame = await completion
-      const status = readString(frame.params?.payload, 'status')
-      if (status !== 'complete') {
-        throw new Error(`real session turn failed with status ${status ?? 'unknown'}: ${JSON.stringify(frame.params?.payload)}`)
-      }
-    }
-
-    await this.request('session.close', { session_id: runtimeId })
-    return { runtimeId, sessionId }
-  }
-
-  async close(): Promise<void> {
-    if (this.closed) return
-    this.closed = true
-    this.child.stdin.end()
-    await new Promise<void>(resolve => {
-      const timeout = setTimeout(() => {
-        this.child.kill('SIGTERM')
-        resolve()
-      }, 5_000)
-      this.child.once('exit', () => {
-        clearTimeout(timeout)
-        resolve()
-      })
-    })
-  }
-
-  private request<T = unknown>(method: string, params: Record<string, unknown>): Promise<T> {
-    const id = ++this.nextRequestId
-    return this.withTimeout(new Promise<T>((resolve, reject) => {
-      this.pending.set(id, { resolve: value => resolve(value as T), reject })
-      this.child.stdin.write(`${JSON.stringify({ jsonrpc: '2.0', id, method, params })}\n`, error => {
-        if (error) {
-          this.pending.delete(id)
-          reject(error)
-        }
-      })
-    }), `request ${method}`)
-  }
-
-  private waitForEvent(predicate: (frame: JsonRpcFrame) => boolean): Promise<JsonRpcFrame> {
-    const index = this.events.findIndex(predicate)
-    if (index >= 0) {
-      return Promise.resolve(this.events.splice(index, 1)[0])
-    }
-    return this.withTimeout(new Promise<JsonRpcFrame>((resolve, reject) => {
-      this.eventWaiters.push({ predicate, resolve, reject })
-    }), 'gateway event')
-  }
-
-  private handleLine(line: string): void {
-    let frame: JsonRpcFrame
-    try {
-      frame = JSON.parse(line) as JsonRpcFrame
-    } catch {
-      return
-    }
-
-    if (typeof frame.id === 'number') {
-      const pending = this.pending.get(frame.id)
-      if (!pending) return
-      this.pending.delete(frame.id)
-      if (frame.error) {
-        pending.reject(new Error(`JSON-RPC error ${frame.error.code ?? 'unknown'}: ${frame.error.message ?? 'unknown error'}`))
-      } else {
-        pending.resolve(frame.result)
-      }
-      return
-    }
-
-    if (frame.method !== 'event') return
-    const waiter = this.eventWaiters.find(candidate => candidate.predicate(frame))
-    if (!waiter) {
-      this.events.push(frame)
-      return
-    }
-    this.eventWaiters.splice(this.eventWaiters.indexOf(waiter), 1)
-    waiter.resolve(frame)
-  }
-
-  private withTimeout<T>(promise: Promise<T>, operation: string): Promise<T> {
-    return new Promise<T>((resolve, reject) => {
-      const timer = setTimeout(() => reject(new Error(`Timed out after ${DEFAULT_TIMEOUT_MS / 1000}s waiting for ${operation}:\n${this.stderr.join('\n')}`)), DEFAULT_TIMEOUT_MS)
-      promise.then(value => {
-        clearTimeout(timer)
-        resolve(value)
-      }, error => {
-        clearTimeout(timer)
-        reject(error)
-      })
-    })
-  }
-
-  private failAll(error: Error): void {
-    for (const pending of this.pending.values()) pending.reject(error)
-    this.pending.clear()
-    for (const waiter of this.eventWaiters) waiter.reject(error)
-    this.eventWaiters.length = 0
-  }
-}
-
-function readString(value: unknown, key: string): string | undefined {
-  if (!value || typeof value !== 'object') return undefined
-  const candidate = (value as Record<string, unknown>)[key]
-  return typeof candidate === 'string' ? candidate : undefined
-}
-
-function requireString(value: unknown, key: string): string {
-  const candidate = readString(value, key)
-  if (!candidate) throw new Error(`Gateway response omitted required ${key}: ${JSON.stringify(value)}`)
-  return candidate
-}
@@ -1,151 +0,0 @@
-/**
- * E2E coverage for session compression, which rotates a live backend session.
- */
-
-import { expect, test, type Page } from '@playwright/test'
-
-import {
-  type MockBackendFixture,
-  setupMockBackend,
-  waitForAppReady,
-} from './fixtures'
-import { MOCK_REPLY, receivedUserTexts, restartMockServer } from './mock-server'
-
-async function send(page: Page, text: string, delay = 15): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.click()
-  await composer.type(text, { delay })
-  await page.keyboard.press('Enter')
-}
-
-async function pasteAndSend(page: Page, text: string): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.click()
-  await page.keyboard.insertText(text)
-  await page.keyboard.press('Enter')
-}
-
-
-async function waitForTranscript(page: Page, text: string, timeout = 90_000): Promise<void> {
-  await page.waitForFunction(
-    expected => document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(expected) ?? false,
-    text,
-    { timeout },
-  )
-}
-
-test.describe('session compression', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('compresses an existing session and accepts a follow-up turn on its continuation', async () => {
-    const { page } = fixture
-    const reply = 'Hello from the mock inference server! The full boot chain is working.'
-
-    // Three completed exchanges leave a compressible middle after the
-    // compressor's protected head/tail boundaries.
-    await send(page, 'E2E_COMPRESSION_FIRST')
-    await waitForTranscript(page, reply)
-    await send(page, 'E2E_COMPRESSION_SECOND')
-    await expect.poll(() => receivedUserTexts().filter(text => text === 'E2E_COMPRESSION_SECOND').length).toBe(1)
-    await send(page, 'E2E_COMPRESSION_THIRD')
-    await expect.poll(() => receivedUserTexts().filter(text => text === 'E2E_COMPRESSION_THIRD').length).toBe(1)
-
-    // Commit the command before typing its argument. This waits for the async
-    // completion request on cold CI workers, then uses the composer's own
-    // keyboard accept path to replace the `/compress` trigger with a command
-    // chip. Clicking a later completion after typing the argument can insert a
-    // second command token (for example `//compress ...`) as plain text.
-    const composer = page.locator('[contenteditable="true"]').first()
-    await composer.click()
-    await composer.type('/compress', { delay: 15 })
-    await page.getByText('/compress').first().waitFor({ state: 'visible' })
-    await page.keyboard.press('Enter')
-    await composer.type(' preserve the three test turns', { delay: 15 })
-    await page.keyboard.press('Enter')
-    await expect
-      .poll(
-        () => page.locator('[data-slot="aui_thread-viewport"]').textContent(),
-        { timeout: 90_000 },
-      )
-      .toMatch(/Compressed|No changes from compression/)
-
-    // Compression rotates the agent's live session id. A post-compression
-    // ordinary turn proves the desktop's runtime binding followed that child.
-    await send(page, 'E2E_COMPRESSION_FOLLOW_UP')
-    await expect.poll(() => receivedUserTexts().filter(text => text === 'E2E_COMPRESSION_FOLLOW_UP').length).toBe(1)
-    await waitForTranscript(page, reply)
-    await page.screenshot({ path: 'test-results/session-compression-continuation.png' })
-  })
-})
-
-test.describe('session compression in progress', () => {
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    fixture = await setupMockBackend({
-      modelContextLength: 64_000,
-      extraConfig: `compression:
-  threshold_tokens: 22000
-  protect_first_n: 0
-  protect_last_n: 1
-auxiliary:
-  compression:
-    provider: custom
-    model: mock-model`,
-      mockServer: {
-        holdFirstCompletionContaining: 'You are a summarization agent creating a context checkpoint.',
-      }
-    })
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('queues an Enter-submitted draft instead of steering while compaction is active', async ({}, testInfo) => {
-    const { page } = fixture
-    const queued = 'E2E_QUEUED_DURING_COMPACTION'
-
-    // A normal message crosses the tiny configured context budget. The mock
-    // blocks only the resulting summary request, so these assertions run
-    // during automatic compaction rather than a slash-command path.
-    // The payload must cross threshold_tokens (22k) on its OWN weight
-    // (~12k tokens) on top of the system prompt. Do not shrink it: at
-    // repeat(500) the trigger only worked because the ambient system prompt
-    // (skills index + tool schemas) happened to carry it over the line, and
-    // a 160-token skills-index cleanup on main broke the test for a day.
-    await pasteAndSend(page, 'E2E_COMPACTION_HISTORY_ONE '.repeat(5))
-    await waitForTranscript(page, MOCK_REPLY)
-    await pasteAndSend(page, 'E2E_COMPACTION_HISTORY_TWO '.repeat(5))
-    await waitForTranscript(page, MOCK_REPLY)
-    await pasteAndSend(page, 'E2E_TRIGGER_AUTOMATIC_COMPACTION '.repeat(1500))
-    await fixture.mock.waitForHeldCompletion()
-    await expect(page.getByRole('status', { name: 'Summarizing thread' }).last()).toBeVisible()
-
-    const primary = page.locator('[data-slot="composer-root"] button[type="submit"]')
-    await expect(primary).toHaveAttribute('aria-label', 'Queue message')
-
-    await send(page, queued)
-    await expect(page.getByText('1 Queued')).toBeVisible()
-    expect(fixture.mock.heldCompletionCount()).toBe(1)
-    expect(receivedUserTexts()).not.toContain(queued)
-    await page.screenshot({ path: testInfo.outputPath('queued-during-compaction.png') })
-
-    fixture.mock.releaseHeldStream()
-    await expect.poll(() => receivedUserTexts().filter(text => text === queued).length).toBe(1)
-    expect(fixture.mock.heldCompletionCount()).toBe(1)
-  })
-})
@@ -1,252 +0,0 @@
-/**
- * E2E tests for desktop sidebar states — background processes, subagents,
- * and session dot transitions.
- *
- * The mock server returns scripted tool_calls that the agent executes for
- * real (trivial commands + real subagent delegations). The tests assert the
- * sidebar states driven by real gateway events.
- *
- * Prerequisite: `npm run build` must have been run so dist/ exists.
- */
-
-import { expect, test, type Page } from '@playwright/test'
-
-import {
-  type MockBackendFixture,
-  setupMockBackend,
-  waitForAppReady,
-} from './fixtures'
-import { SIDEBAR_CROSS_TEXTS, SIDEBAR_TEXTS, restartMockServer } from './mock-server'
-
-/** Background-running dot aria-label (from i18n en.ts). */
-const BG_DOT_LABEL = 'Background task running'
-/** Finished-unread dot aria-label. */
-const UNREAD_DOT_LABEL = 'Finished — unread'
-
-/** Send a message and wait for the final response to appear. */
-async function sendMessageAndWait(
-  page: Page,
-  trigger: string,
-  finalText: string,
-  timeout = 90_000,
-): Promise<void> {
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.waitFor({ state: 'visible', timeout: 10_000 })
-  await composer.click()
-  await composer.type(trigger, { delay: 20 })
-  await page.keyboard.press('Enter')
-
-  await page.waitForFunction(
-    () => (document.body.textContent ?? '').includes('E2E_'),
-    undefined,
-    { timeout: 15_000 },
-  )
-
-  await page.waitForFunction(
-    (text) => (document.body.textContent ?? '').includes(text),
-    finalText,
-    { timeout },
-  )
-}
-
-// ────────────────────────────────────────────────────────────────────────
-// Test 1: background process + subagent appear in sidebar during turn
-// ────────────────────────────────────────────────────────────────────────
-
-test.describe('sidebar states — background process and subagent', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('background process dot appears and disappears, subagent runs, final answer visible', async () => {
-    const page = fixture.page
-
-    await sendMessageAndWait(page, 'E2E_SIDEBAR_TRIGGER', SIDEBAR_TEXTS.finalText)
-
-    // The background process (sleep 1) should have shown a "Background task
-    // running" dot at some point during the turn. We try to catch it; if
-    // the process was too fast, that's OK — the real assertion is that the
-    // final answer appeared and the dot is gone afterward.
-    try {
-      await expect
-        .poll(
-          () => page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count(),
-          { timeout: 15_000, message: 'background dot should appear' },
-        )
-        .toBeGreaterThan(0)
-    } catch {
-      // sleep 1 may have finished before we polled — not a failure.
-    }
-
-    // After the turn completes and auto-dismiss fires, the background dot
-    // should be gone.
-    await page.waitForTimeout(8000)
-    const bgCount = await page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count()
-    expect(bgCount, 'background dot should be gone after auto-dismiss').toBe(0)
-
-    // Evidence: capture the final state — no background dot, final answer visible.
-    await page.screenshot({ path: 'test-results/bg-dot-gone-after-dismiss.png' })
-
-    // The final answer text must be in the transcript.
-    const viewportText = await page
-      .locator('[data-slot="aui_thread-viewport"]')
-      .textContent()
-    expect(viewportText).toContain(SIDEBAR_TEXTS.finalText)
-  })
-})
-
-// ────────────────────────────────────────────────────────────────────────
-// Test 2: subagent running shows background dot too (longer bg process)
-// ────────────────────────────────────────────────────────────────────────
-
-test.describe('sidebar states — subagent and background dot coexist', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('background dot visible while subagent runs', async () => {
-    const page = fixture.page
-
-    // Start the turn but DON'T wait for the final answer yet — we want
-    // to assert the background dot is visible WHILE the subagent runs.
-    const composer = page.locator('[contenteditable="true"]').first()
-    await composer.waitFor({ state: 'visible', timeout: 10_000 })
-    await composer.click()
-    await composer.type('E2E_SIDEBAR_CROSS', { delay: 20 })
-    await page.keyboard.press('Enter')
-
-    // Wait for the user's message to appear.
-    await page.waitForFunction(
-      () => (document.body.textContent ?? '').includes('E2E_SIDEBAR_CROSS'),
-      undefined,
-      { timeout: 15_000 },
-    )
-
-    // The background process (sleep 5) should show a "Background task
-    // running" dot while the subagent is also running.
-    await expect
-      .poll(
-        () => page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count(),
-        { timeout: 30_000, message: 'background dot should appear while subagent runs' },
-      )
-      .toBeGreaterThan(0)
-
-    // Evidence: the background dot is visible while the subagent runs.
-    await page.screenshot({ path: 'test-results/bg-dot-while-subagent-runs.png' })
-
-    // Now wait for the final answer to appear.
-    await page.waitForFunction(
-      (text) => (document.body.textContent ?? '').includes(text),
-      SIDEBAR_CROSS_TEXTS.finalText,
-      { timeout: 90_000 },
-    )
-
-    // After the turn + auto-dismiss, the background dot should be gone.
-    await page.waitForTimeout(8000)
-    const bgCount = await page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count()
-    expect(bgCount, 'background dot should be gone after process exits').toBe(0)
-  })
-})
-
-// ────────────────────────────────────────────────────────────────────────
-// Test 3: cross-session — dot updates when viewing a different session
-// ────────────────────────────────────────────────────────────────────────
-
-test.describe('sidebar states — cross-session dot transition', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('background dot transitions to finished when viewing another session', async () => {
-    const page = fixture.page
-
-    // Start a turn with a long background process (sleep 5).
-    const composer = page.locator('[contenteditable="true"]').first()
-    await composer.waitFor({ state: 'visible', timeout: 10_000 })
-    await composer.click()
-    await composer.type('E2E_SIDEBAR_CROSS', { delay: 20 })
-    await page.keyboard.press('Enter')
-
-    // Wait for the background dot to appear.
-    await expect
-      .poll(
-        () => page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count(),
-        { timeout: 30_000, message: 'background dot should appear' },
-      )
-      .toBeGreaterThan(0)
-
-    // Wait for the final answer (turn completes, but bg process still running).
-    await page.waitForFunction(
-      (text) => (document.body.textContent ?? '').includes(text),
-      SIDEBAR_CROSS_TEXTS.finalText,
-      { timeout: 90_000 },
-    )
-
-    // The background dot should still be visible (sleep 5 hasn't finished yet,
-    // or auto-dismiss hasn't fired).
-    const bgDuringTurn = await page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count()
-    expect(bgDuringTurn, 'background dot should still be visible after turn completes').toBeGreaterThan(0)
-
-    // Evidence: bg dot visible on session A while its turn is done but the
-    // background process hasn't exited yet.
-    await page.screenshot({ path: 'test-results/cross-session-bg-dot-before-switch.png' })
-
-    // Create a new session (click "New session" button).
-    await page.locator('button:has-text("New session")').first().click()
-    await page.waitForTimeout(2000)
-
-    // Now wait for the background process to finish (sleep 5 + auto-dismiss).
-    // The session A dot should transition away from "background running".
-    await expect
-      .poll(
-        () => page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count(),
-        { timeout: 30_000, message: 'background dot should disappear after process finishes' },
-      )
-      .toBe(0)
-
-    // The original session should show a "finished unread" indicator (green dot)
-    // since its turn completed while we were in a different session. This is an
-    // event-driven transition, so wait for it instead of sampling the DOM right
-    // after the running dot disappears.
-    await expect
-      .poll(
-        () => page.locator(`[aria-label="${UNREAD_DOT_LABEL}"]`).count(),
-        { timeout: 30_000, message: 'original session should show finished-unread dot' },
-      )
-      .toBeGreaterThan(0)
-
-    // Evidence: the green "finished unread" dot on the original session after
-    // switching to a new session — the cross-session dot transition.
-    await page.screenshot({ path: 'test-results/cross-session-unread-dot-after-switch.png' })
-  })
-})
@@ -1,75 +0,0 @@
-/**
- * Regression coverage for #69578: harmless route-token churn during a send
- * must not make the desktop silently drop the prompt before prompt.submit.
- */
-
-import { test, expect } from './test'
-
-import {
-  type MockBackendFixture,
-  setupMockBackend,
-  waitForAppReady,
-} from './fixtures'
-
-const PROMPT = 'E2E route token drift must still submit this prompt.'
-
-let fixture: MockBackendFixture | null = null
-
-test.beforeAll(async () => {
-  fixture = await setupMockBackend()
-  await waitForAppReady(fixture!, 120_000)
-})
-
-test.afterAll(async () => {
-  await fixture?.cleanup()
-  fixture = null
-})
-
-test('submits while same-chat search tokens churn during new-session creation', async ({}, testInfo) => {
-  const { page, mock } = fixture!
-  const composer = page.locator('[contenteditable="true"]').first()
-
-  await composer.click()
-  await composer.type(PROMPT, { delay: 10 })
-
-  // The submit pipeline snapshots the route synchronously, then awaits session
-  // creation. Keep changing only the query string of whichever chat route is
-  // current. Before #69578, comparing the raw route token treated this as a
-  // user chat switch and aborted before prompt.submit.
-  await page.evaluate(() => {
-    let revision = 0
-    const interval = window.setInterval(() => {
-      const pathname = window.location.hash.slice(1).split(/[?#]/, 1)[0] || '/new'
-      window.location.hash = `${pathname}?e2e-route-churn=${revision++}`
-    }, 1)
-
-    ;(window as typeof window & { __e2eStopRouteChurn?: () => void }).__e2eStopRouteChurn = () => {
-      window.clearInterval(interval)
-    }
-  })
-
-  try {
-    await page.keyboard.press('Enter')
-
-    await expect
-      .poll(() => mock.receivedPrompts.includes(PROMPT), { timeout: 60_000 })
-      .toBe(true)
-
-    await page.waitForFunction(
-      prompt => document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(prompt) ?? false,
-      PROMPT,
-      { timeout: 15_000 },
-    )
-    await page.waitForFunction(
-      () => document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes('mock inference server') ?? false,
-      undefined,
-      { timeout: 60_000 },
-    )
-  } finally {
-    await page.evaluate(() => {
-      ;(window as typeof window & { __e2eStopRouteChurn?: () => void }).__e2eStopRouteChurn?.()
-    })
-  }
-
-  await page.screenshot({ path: testInfo.outputPath('same-chat-route-churn-submitted.png') })
-})
@@ -1,166 +0,0 @@
-/**
- * Extended Playwright test fixture that auto-fails any test if an error
- * banner (notification toast with role="alert") appears in the DOM.
- *
- * The desktop app surfaces errors as `[data-slot="alert"][role="alert"]`
- * elements (see components/notifications.tsx). When one appears during a
- * test, it means something went wrong (resume failed, boot error, etc.)
- * — the test should fail with the error message, not silently pass while
- * an error toast is visible on screen.
- *
- * Usage: import { test, expect } from './test' instead of
- * '@playwright/test'. The guard is auto-installed on every page — no
- * per-spec setup needed.
- */
-
-import { test as base, expect, type Page, type ElectronApplication, _electron } from '@playwright/test'
-
-// Track error messages per test so afterEach can assert + report.
-const seenErrors: string[] = []
-let activePage: Page | null = null
-// When true, the afterEach guard skips the error-banner check.
-// Set by tests that deliberately trigger error states (e.g. boot-failure).
-let errorBannersAllowed = false
-
-/**
- * Opt out of the error-banner guard for the current test. Call in
- * test.beforeEach or at the top of a test body when error banners are
- * expected (e.g. boot-failure tests that deliberately trigger errors).
- */
-export function allowErrorBanners(): void {
-  errorBannersAllowed = true
-}
-
-/**
- * Install the error-banner guard on a page. Watches for `[role="alert"]`
- * elements appearing in the DOM. When one is found, records its text
- * content for the afterEach assertion.
- *
- * Exported so e2e fixture functions (which create pages via _electron.launch)
- * can install the guard on their custom pages — the default Playwright `page`
- * fixture override only catches pages created by Playwright itself, not
- * pages created by the test's own Electron launch.
- */
-export function installErrorBannerGuard(page: Page): void {
-  activePage = page
-
-  // Clear any errors from a previous test when a new page is created.
-  seenErrors.length = 0
-
-  // Use a MutationObserver to catch error banners as they appear.
-  // We inject this via addInitScript so it runs before any app code.
-  page.addInitScript(() => {
-    const seen: string[] = []
-    ;(window as unknown as { __ERROR_BANNER_GUARD__?: string[] }).__ERROR_BANNER_GUARD__ = seen
-
-    const observer = new MutationObserver(() => {
-      const alerts = document.querySelectorAll('[role="alert"]')
-
-      for (const alert of alerts) {
-        const text = (alert.textContent ?? '').trim()
-
-        if (text && !seen.includes(text)) {
-          seen.push(text)
-        }
-      }
-    })
-
-    // Start observing once the DOM is ready.
-    if (document.body) {
-      observer.observe(document.body, { childList: true, subtree: true })
-    } else {
-      document.addEventListener('DOMContentLoaded', () => {
-        observer.observe(document.body, { childList: true, subtree: true })
-      })
-    }
-  })
-
-  // Also poll via evaluate — MutationObserver via addInitScript can miss
-  // elements that appear during the Electron renderer's initial mount
-  // (before the observer is installed). A periodic poll catches those.
-  page.on('console', () => {
-    // Console messages are not errors — but we keep the listener to
-    // ensure the page context is active for our evaluate calls.
-  })
-}
-
-/**
- * Check for error banners that appeared during the test. Called in
- * afterEach via the custom fixture below. Also exported so specs that
- * manage their own page lifecycle can call it directly.
- */
-export async function collectErrorBanners(page: Page | null): Promise<string[]> {
-  if (!page) {
-    return []
-  }
-
-  try {
-    // Read errors collected by the MutationObserver in the page context.
-    const pageErrors = await page.evaluate(() => {
-      const w = window as unknown as { __ERROR_BANNER_GUARD__?: string[] }
-
-      return [...(w.__ERROR_BANNER_GUARD__ ?? [])]
-    })
-
-    // Also do a final DOM scan for any alert elements still visible.
-    const domAlerts = await page
-      .locator('[role="alert"]')
-      .allTextContents()
-      .catch(() => [] as string[])
-
-    const all = [...new Set([...pageErrors, ...domAlerts.map(t => t.trim()).filter(Boolean)])]
-    seenErrors.push(...all)
-
-    return [...new Set(seenErrors)]
-  } catch {
-    // Page might be closed — return whatever we have.
-    return [...new Set(seenErrors)]
-  }
-}
-
-// Extended test fixture: wraps the default page with the error guard.
-export const test = base.extend({
-  // Override the page fixture to auto-install the guard.
-  page: async ({ page }, use) => {
-    installErrorBannerGuard(page)
-    await use(page)
-  },
-})
-
-// afterEach: fail the test if any error banners appeared.
-// Always fires — even if the test already failed for another reason.
-// An error banner often IS the root cause (e.g. "resume failed" from a
-// backend bug), and suppressing it when the test also fails on an
-// assertion hides the real problem.
-//
-// Uses `activePage` (set by installErrorBannerGuard) instead of the
-// default `page` fixture — Electron tests create their own page via
-// app.firstWindow(), so the default `page` fixture is undefined.
-base.afterEach(async ({}, testInfo) => {
-  const wasAllowed = errorBannersAllowed
-  // Reset for the next test.
-  errorBannersAllowed = false
-
-  if (wasAllowed) {
-    // Test opted out — clear any collected errors without asserting.
-    seenErrors.length = 0
-    return
-  }
-
-  const errors = await collectErrorBanners(activePage)
-
-  if (errors.length > 0) {
-    throw new Error(
-      `Error banner(s) appeared during test "${testInfo.title}":\n` +
-        errors.map(e => `  • ${e}`).join('\n'),
-    )
-  }
-})
-
-// Reset for the next test file.
-base.afterAll(async () => {
-  seenErrors.length = 0
-  activePage = null
-})
-
-export { expect, type Page, type ElectronApplication, _electron }
@@ -1,210 +0,0 @@
-/**
- * E2E tests for the tile-unread bug — two scenarios:
- *
- * 1. TAB (stacked, not visible) — a session opened as a tab via ⌃-click is
- *    NOT visible on screen. When it finishes, the green "unread" dot IS
- *    correct — the user isn't looking at it. This test PASSES.
- *
- * 2. SPLIT (side-by-side, visible) — a session dragged to the edge of the
- *    workspace zone opens as a split tile, visible on screen at the same time
- *    as the main session. When it finishes, it should NOT get the green
- *    "unread" dot — the user is looking right at it. This test FAILS until
- *    the fix in session-states.ts:174 lands (the unread check only compares
- *    against $selectedStoredSessionId and ignores $sessionTiles).
- *
- * Prerequisite: `npm run build` must have been run so dist/ exists.
- */
-
-import { expect, test } from '@playwright/test'
-
-import {
-  type MockBackendFixture,
-  setupMockBackend,
-  waitForAppReady,
-} from './fixtures'
-import { SIDEBAR_CROSS_TEXTS, restartMockServer } from './mock-server'
-
-/** Finished-unread dot aria-label. */
-const UNREAD_DOT_LABEL = 'Finished — unread'
-/** Background-running dot aria-label. */
-const BG_DOT_LABEL = 'Background task running'
-
-/** Locate a session's sidebar row by its preview text. */
-function sessionRow(page: import('@playwright/test').Page, text: string) {
-  return page.locator('[data-slot="sidebar"] button').filter({ hasText: text }).first()
-}
-
-/** Common setup: start a turn with a sleep 5 bg process + subagent, wait for
- *  the turn to complete, then switch to a new session so the first session is
- *  no longer $selectedStoredSessionId (required before opening a tile). */
-async function startTurnAndSwitchAway(page: import('@playwright/test').Page) {
-  // Send E2E_SIDEBAR_CROSS — starts a turn with sleep 5 + subagent.
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.waitFor({ state: 'visible', timeout: 10_000 })
-  await composer.click()
-  await composer.type('E2E_SIDEBAR_CROSS', { delay: 20 })
-  await page.keyboard.press('Enter')
-
-  // Wait for the user's message to appear.
-  await page.waitForFunction(
-    () => (document.body.textContent ?? '').includes('E2E_SIDEBAR_CROSS'),
-    undefined,
-    { timeout: 15_000 },
-  )
-
-  // Wait for the background dot — confirms the turn is running.
-  await expect
-    .poll(
-      () => page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count(),
-      { timeout: 30_000, message: 'background dot should appear' },
-    )
-    .toBeGreaterThan(0)
-
-  // Wait for the turn to complete (final answer visible).
-  await page.waitForFunction(
-    (text) => (document.body.textContent ?? '').includes(text),
-    SIDEBAR_CROSS_TEXTS.finalText,
-    { timeout: 90_000 },
-  )
-
-  // The background dot should still be visible (sleep 5 hasn't finished).
-  const bgDuringTurn = await page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count()
-  expect(bgDuringTurn, 'background dot should still be visible after turn completes').toBeGreaterThan(0)
-
-  // Switch to a new session — session A is no longer $selectedStoredSessionId.
-  // This is required: openSessionTile bails if the session is already selected.
-  await page.locator('button:has-text("New session")').first().click()
-  await page.waitForTimeout(2000)
-}
-
-/** Wait for the background process to finish (sleep 5 + auto-dismiss). */
-async function waitForBgProcessToFinish(page: import('@playwright/test').Page) {
-  await expect
-    .poll(
-      () => page.locator(`[aria-label="${BG_DOT_LABEL}"]`).count(),
-      { timeout: 30_000, message: 'background dot should disappear after process finishes' },
-    )
-    .toBe(0)
-}
-
-// ────────────────────────────────────────────────────────────────────────
-// Test 1: TAB (not visible) — unread dot IS correct (PASSES)
-// ────────────────────────────────────────────────────────────────────────
-
-test.describe('sidebar states — tab (hidden) unread is correct', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('session opened as a tab (not visible) correctly gets unread dot', async () => {
-    const page = fixture.page
-
-    await startTurnAndSwitchAway(page)
-
-    // Evidence: session A is in the background (bg dot in sidebar).
-    await page.screenshot({ path: 'test-results/tile-bug-tab-switched-away.png' })
-
-    // ⌃-click opens the session as a TAB (center dock = stacked, not visible
-    // unless it's the active tab). The session is NOT on screen.
-    const row = sessionRow(page, SIDEBAR_CROSS_TEXTS.finalText)
-    await row.click({ modifiers: ['Control'] })
-    await page.waitForTimeout(2000)
-
-    // Evidence: the tab is open but the session is not visible on screen.
-    await page.screenshot({ path: 'test-results/tile-bug-tab-opened.png' })
-
-    await waitForBgProcessToFinish(page)
-
-    // A tab that's not the active tab IS hidden — the unread dot is correct.
-    // The user is NOT looking at it, so marking it "unread" is right.
-    const unreadCount = await page.locator(`[aria-label="${UNREAD_DOT_LABEL}"]`).count()
-    expect(unreadCount, 'hidden tab should be marked unread').toBeGreaterThan(0)
-
-    await page.screenshot({ path: 'test-results/tile-bug-tab-unread-correct.png' })
-  })
-})
-
-// ────────────────────────────────────────────────────────────────────────
-// Test 2: SPLIT (visible) — unread dot is WRONG (FAILS until fix)
-// ────────────────────────────────────────────────────────────────────────
-
-test.describe.skip('sidebar states — split (visible) unread bug (RED)', () => {
-  test.describe.configure({ mode: 'serial' })
-
-  let fixture: MockBackendFixture
-
-  test.beforeAll(async () => {
-    restartMockServer()
-    fixture = await setupMockBackend()
-    await waitForAppReady(fixture, 120_000)
-  })
-
-  test.afterAll(async () => {
-    await fixture?.cleanup()
-  })
-
-  test('session visible in a split tile does NOT get unread dot when it finishes', async () => {
-    const page = fixture.page
-
-    await startTurnAndSwitchAway(page)
-
-    // Evidence: session A is in the background (bg dot in sidebar).
-    await page.screenshot({ path: 'test-results/tile-bug-split-switched-away.png' })
-
-    // Drag the session row from the sidebar to the right edge of the workspace
-    // zone to create a SPLIT (side-by-side) tile. This triggers the real
-    // startSessionDrag → onCommit → openSessionTile(id, 'right', anchor) path.
-    const row = sessionRow(page, SIDEBAR_CROSS_TEXTS.finalText)
-    const rowBox = await row.boundingBox()
-    expect(rowBox, 'session row must be visible').not.toBeNull()
-
-    // Find the workspace zone — the main chat area. We drop on its right edge.
-    const workspace = page.locator('[data-session-anchor="workspace"]')
-    const wsBox = await workspace.boundingBox()
-    expect(wsBox, 'workspace zone must be visible').not.toBeNull()
-
-    // Drag from the session row to the right edge of the workspace.
-    // The drag-session's subZonePosition resolves a right-edge drop as 'right'
-    // (a split dock), not 'center' (which would be a composer link).
-    await page.mouse.move(rowBox!.x + rowBox!.width / 2, rowBox!.y + rowBox!.height / 2)
-    await page.mouse.down()
-    // Move in steps so the drag-session's pointermove handler tracks the
-    // position and resolves the drop zone (a single jump can miss the
-    // threshold/engage logic).
-    const targetX = wsBox!.x + wsBox!.width - 20
-    const targetY = wsBox!.y + wsBox!.height / 2
-    const steps = 10
-    for (let i = 1; i <= steps; i++) {
-      const x = rowBox!.x + rowBox!.width / 2 + (targetX - (rowBox!.x + rowBox!.width / 2)) * (i / steps)
-      const y = rowBox!.y + rowBox!.height / 2 + (targetY - (rowBox!.y + rowBox!.height / 2)) * (i / steps)
-      await page.mouse.move(x, y)
-      await page.waitForTimeout(30)
-    }
-    await page.mouse.up()
-    await page.waitForTimeout(2000)
-
-    // Evidence: the split tile is now open side-by-side — both sessions visible.
-    await page.screenshot({ path: 'test-results/tile-bug-split-opened.png' })
-
-    await waitForBgProcessToFinish(page)
-
-    // THE BUG: the session visible in the split tile should NOT have the green
-    // "finished unread" dot — the user is looking right at it. This assertion
-    // FAILS until the fix in session-states.ts:174 lands.
-    const unreadCount = await page.locator(`[aria-label="${UNREAD_DOT_LABEL}"]`).count()
-    expect(unreadCount, 'session visible in a split tile should NOT be marked unread').toBe(0)
-
-    // Evidence: the green dot should NOT be here — this screenshot shows the bug.
-    await page.screenshot({ path: 'test-results/tile-bug-split-unread-should-not-exist.png' })
-  })
-})
@@ -1,434 +0,0 @@
-/**
- * E2E regression: warm-route resume must not re-render the transcript more
- * than once.
- *
- * When a session is already in the runtime-id cache (the "warm" path in
- * `resumeSession()`), clicking its sidebar row should paint the transcript
- * exactly once. Before the fix, the warm cache painted via
- * `syncSessionStateToView`, then the `session.activate` RPC returned a
- * reconciled message list with different message object references, causing
- * `syncSessionStateToView` to fire a second `setMessages` — a visual
- * flicker as the transcript DOM was updated.
- *
- * This test pre-seeds a 32-message session into state.db, boots the app,
- * clicks the session (cold resume — populates the warm cache), navigates
- * away to a new chat, then clicks back (warm resume). Two detectors run:
- *
- * 1. A MutationObserver counts additive DOM mutation bursts (childList
- *    additions). More than 1 burst = the transcript was repainted.
- *
- * 2. A 2ms innerHTML-length poll counts "reconciles" — DOM content changes
- *    that happen AFTER the initial paint, while messages are already on
- *    screen. This catches the case where React reconciles by key without
- *    adding/removing nodes (same keys → in-place prop update → no
- *    MutationObserver burst), but `$messages` was still set twice.
- *
- * The test passes when bursts === 1 AND reconciles === 0.
- *
- * Prerequisite: `npm run build` must have been run so dist/ exists.
- */
-
-import { expect, test } from './test'
-
-import {
-  type MockBackendFixture,
-  waitForAppReady,
-  createSandbox,
-  writeMockProviderConfig,
-  writeEnvFile,
-  buildAppEnv,
-  launchDesktop,
-} from './fixtures'
-import { startMockServer } from './mock-server'
-import { RealSessionBuilder } from './real-session-builder'
-
-const SESSION_TITLE = 'E2E Warm Resume Jitter Test'
-/** 32 messages (16 user/assistant pairs) — enough DOM churn for detection. */
-const MESSAGE_COUNT = 32
-/** Seeded PRNG so the generated content is deterministic across runs. */
-const RNG_SEED = 42
-
-/** Mulberry32 — tiny deterministic PRNG. */
-function mulberry32(seed: number): () => number {
-  let a = seed
-  return () => {
-    a |= 0
-    a = (a + 0x6d2b79f5) | 0
-    let t = Math.imul(a ^ (a >>> 15), 1 | a)
-    t = (t + Math.imul(t ^ (t >>> 7), 61 | t)) ^ t
-    return ((t ^ (t >>> 14)) >>> 0) / 4294967296
-  }
-}
-
-/** Generate ~40 chars of gibberish from a seeded PRNG. */
-function gibberish(rng: () => number): string {
-  const len = 30 + Math.floor(rng() * 20)
-  let s = ''
-  for (let i = 0; i < len; i++) {
-    s += String.fromCharCode(97 + Math.floor(rng() * 26))
-  }
-  return s
-}
-
-/** First user message — used as a wait target in the test. */
-const FIRST_USER_MSG = gibberish(mulberry32(RNG_SEED))
-
-/**
- * Generate the user turns for a real session. The mock provider produces the
- * assistant side of each pair through the normal AIAgent persistence path.
- */
-function generateSessionTurns(): string[] {
-  const rng = mulberry32(RNG_SEED)
-  const turns: string[] = []
-
-  for (let i = 0; i < MESSAGE_COUNT / 2; i++) {
-    turns.push(gibberish(rng))
-    gibberish(rng)
-  }
-
-  return turns
-}
-
-/**
- * Set up a mock-backend sandbox with a real persisted session in state.db.
- *
- * Unlike the shared `setupMockBackend()`, this variant creates the session
- * through the real stdio gateway before launching desktop so the session is
- * visible in the sidebar on first load.
- */
-async function setupSeededMockBackend(): Promise<MockBackendFixture> {
-  // 1. Start mock server
-  const mock = await startMockServer()
-
-  // 2. Create sandbox + write config
-  const sandbox = createSandbox('warm-seed')
-  writeMockProviderConfig(sandbox.hermesHome, mock.url)
-  writeEnvFile(sandbox.hermesHome)
-
-  // 3. Produce all 16 user/assistant pairs through the real TUI gateway,
-  // AIAgent, mock provider, and SessionDB persistence path before desktop starts.
-  const builder = await RealSessionBuilder.start(sandbox.hermesHome)
-  try {
-    await builder.createSession({ title: SESSION_TITLE, turns: generateSessionTurns() })
-  } finally {
-    await builder.close()
-  }
-
-  // 4. Build env + launch
-  const env = buildAppEnv(sandbox)
-  const { app, page } = await launchDesktop(env)
-
-  return {
-    app,
-    page,
-    mock,
-    mockUrl: mock.url,
-    sandbox,
-    cleanup: async () => {
-      await app.close().catch(() => undefined)
-      await mock.close()
-      sandbox.cleanup()
-    },
-  }
-}
-
-let fixture: MockBackendFixture | null = null
-
-test.beforeAll(async () => {
-  fixture = await setupSeededMockBackend()
-  await waitForAppReady(fixture!, 120_000)
-})
-
-test.afterAll(async () => {
-  await fixture?.cleanup()
-  fixture = null
-})
-
-/**
- * Install a MutationObserver + text-content poll on the thread viewport
- * to detect re-renders after the initial paint. Returns nothing — call
- * `readRenderCount` to stop and collect results.
- *
- * - MutationObserver: counts additive childList bursts (5ms coalescing).
- * - Text-content poll: counts "reconciles" — first-message text changes
- *   after the initial paint, catching key-based reconciles that don't
- *   add/remove nodes.
- */
-async function installRenderCounter(page: import('@playwright/test').Page): Promise<void> {
-  await page.evaluate(() => {
-    const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-    if (!viewport) {
-      throw new Error('Thread viewport not found before warm resume')
-    }
-
-    const state = { bursts: 0, mutations: 0, timeline: [] as number[], stopped: false, reconciles: 0 }
-    ;(window as unknown as { __RENDER_COUNT__: typeof state }).__RENDER_COUNT__ = state
-
-    let currentBatch = 0
-    let flushTimer: ReturnType<typeof setTimeout> | null = null
-
-    const flush = () => {
-      flushTimer = null
-      if (currentBatch > 0 && !state.stopped) {
-        state.bursts += 1
-        state.timeline.push(currentBatch)
-        currentBatch = 0
-      }
-    }
-
-    const observer = new MutationObserver(records => {
-      if (state.stopped) return
-      let batchAdded = 0
-      for (const record of records) {
-        state.mutations += 1
-        if (record.type === 'childList' && record.addedNodes.length > 0) {
-          batchAdded += 1
-        }
-      }
-      if (batchAdded > 0) {
-        currentBatch += batchAdded
-        if (flushTimer) clearTimeout(flushTimer)
-        flushTimer = setTimeout(flush, 5)
-      }
-    })
-
-    observer.observe(viewport, {
-      childList: true,
-      subtree: true,
-      attributes: false,
-      characterData: false,
-    })
-
-    // Poll the first message's text content every 2ms. The MutationObserver
-    // only catches childList additions; React may reconcile by key without
-    // adding/removing nodes (same keys → in-place prop update → no childList
-    // mutation). The poll catches this by detecting text content changes in
-    // the first message after the initial paint. Metadata-only changes (model
-    // name, busy indicator) don't affect message text, so they don't produce
-    // false positives.
-    const contentEl = viewport.querySelector('[data-slot="aui_thread-content"]') ?? viewport
-    let lastFirstMsgText = ''
-    let hasMessages = false
-    const pollInterval = setInterval(() => {
-      if (state.stopped) {
-        clearInterval(pollInterval)
-        return
-      }
-      const firstMsg = contentEl.querySelector('[data-role="message"], [data-message-id]')
-      const firstMsgText = firstMsg?.textContent ?? ''
-      if (firstMsgText && firstMsgText !== lastFirstMsgText) {
-        if (hasMessages) {
-          state.reconciles = (state.reconciles ?? 0) + 1
-        }
-        lastFirstMsgText = firstMsgText
-        hasMessages = true
-      }
-    }, 2)
-  })
-}
-
-/** Stop the render counter and return the recorded burst/reconcile counts. */
-async function readRenderCount(page: import('@playwright/test').Page): Promise<{
-  bursts: number
-  mutations: number
-  timeline: number[]
-  reconciles: number
-} | null> {
-  return page.evaluate(() => {
-    type RenderCount = { bursts: number; mutations: number; timeline: number[]; stopped: boolean; reconciles: number }
-    const w = window as unknown as { __RENDER_COUNT__?: RenderCount }
-    const rc = w.__RENDER_COUNT__
-    if (rc) {
-      rc.stopped = true
-    }
-    return rc ? { bursts: rc.bursts, mutations: rc.mutations, timeline: rc.timeline, reconciles: rc.reconciles } : null
-  })
-}
-
-/** Assert the render counter shows exactly one paint with no re-renders. */
-function assertNoJitter(result: { bursts: number; mutations: number; timeline: number[]; reconciles: number } | null): void {
-  expect(result, 'MutationObserver should have recorded render data').toBeTruthy()
-  expect(
-    result!.bursts,
-    `Expected 1 additive render burst (single paint), but got ${result!.bursts} bursts. ` +
-      `Mutation timeline: ${JSON.stringify(result!.timeline)}.`,
-  ).toBe(1)
-  expect(
-    result!.reconciles,
-    `Expected 0 reconciles (no re-render after initial paint), but got ${result!.reconciles}. ` +
-      `This means the warm-route resume re-rendered the transcript after the initial paint ` +
-      `— the "warm resume jitter" bug is present.`,
-  ).toBe(0)
-}
-
-test('warm-route resume paints transcript exactly once (no jitter)', async ({}, testInfo) => {
-  const page = fixture!.page
-
-  // Wait for the sidebar to populate with our seeded session.
-  const sessionRow = page
-    .locator('[data-slot="sidebar"] button')
-    .filter({ hasText: SESSION_TITLE })
-    .first()
-  await sessionRow.waitFor({ state: 'visible', timeout: 60_000 })
-
-  // Step 1: Cold resume — click the session row to load it.
-  // This populates the warm cache (runtimeIdByStoredSessionId + sessionStateByRuntimeId).
-  await sessionRow.click()
-
-  // Wait for the transcript to appear — the first user message text confirms
-  // the cold-path prefetch painted.
-  await page.waitForFunction(
-    (text: string) =>
-      document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(text) ??
-      false,
-    FIRST_USER_MSG,
-    { timeout: 30_000 },
-  )
-
-  // Wait for the session to fully settle (cold-path RPC + reconciliation).
-  await page.waitForTimeout(2_000)
-
-  // Step 2: Navigate away to a new chat — this does NOT evict the warm cache.
-  const newSessionButton = page
-    .locator('[data-slot="sidebar"] button[aria-label="New session"]')
-    .first()
-  await newSessionButton.click()
-
-  // Wait for the new-chat empty state.
-  await page.waitForFunction(
-    (firstMsg: string) => {
-      const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-      if (!viewport) return false
-      const text = viewport.textContent ?? ''
-      return !text.includes(firstMsg)
-    },
-    FIRST_USER_MSG,
-    { timeout: 15_000 },
-  )
-
-  await page.waitForTimeout(500)
-
-  // Step 3: Install render counter, click back (warm resume), wait, assert.
-  await installRenderCounter(page)
-  await sessionRow.click()
-
-  await page.waitForFunction(
-    (text: string) =>
-      document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(text) ??
-      false,
-    FIRST_USER_MSG,
-    { timeout: 30_000 },
-  )
-
-  // Wait for at least 1 burst, then settle.
-  await page.waitForFunction(
-    () => {
-      const w = window as unknown as { __RENDER_COUNT__?: { bursts: number } }
-      return Boolean(w.__RENDER_COUNT__ && w.__RENDER_COUNT__.bursts > 0)
-    },
-    undefined,
-    { timeout: 10_000 },
-  )
-  await page.waitForTimeout(2_000)
-
-  const result = await readRenderCount(page)
-  await page.screenshot({ path: testInfo.outputPath('warm-resume-idle.png') })
-  assertNoJitter(result)
-})
-
-test('warm-route resume after background inference completes (no jitter)', async ({}, testInfo) => {
-  test.fixme(
-    true,
-    'Warm resume repaints after inference: expected one additive burst, got two ([18,1]).',
-  )
-
-  const page = fixture!.page
-  const { mock } = fixture!
-
-  // Wait for the sidebar to populate with our seeded session.
-  const sessionRow = page
-    .locator('[data-slot="sidebar"] button')
-    .filter({ hasText: SESSION_TITLE })
-    .first()
-  await sessionRow.waitFor({ state: 'visible', timeout: 60_000 })
-
-  // Step 1: Cold resume — populate the warm cache.
-  await sessionRow.click()
-  await page.waitForFunction(
-    (text: string) =>
-      document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(text) ??
-      false,
-    FIRST_USER_MSG,
-    { timeout: 30_000 },
-  )
-  await page.waitForTimeout(2_000)
-
-  // Step 2: Send a message — triggers inference via the mock server.
-  const PROMPT = 'E2E post-inference warm resume test prompt'
-  const composer = page.locator('[contenteditable="true"]').first()
-  await composer.click()
-  await composer.type(PROMPT, { delay: 10 })
-  await page.keyboard.press('Enter')
-
-  // Wait for the mock response to appear in the transcript, confirming
-  // the turn completed and message.complete fired (which updates the warm
-  // cache via updateSessionState).
-  await page.waitForFunction(
-    () => {
-      const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-      return viewport?.textContent?.includes('mock inference server') ?? false
-    },
-    undefined,
-    { timeout: 60_000 },
-  )
-  // Extra settle for message.complete → updateSessionState → cache write.
-  await page.waitForTimeout(2_000)
-
-  // Verify the prompt was received by the mock server.
-  expect(mock.receivedPrompts).toContain(PROMPT)
-
-  // Step 3: Navigate away — the warm cache retains the updated messages.
-  const newSessionButton = page
-    .locator('[data-slot="sidebar"] button[aria-label="New session"]')
-    .first()
-  await newSessionButton.click()
-  await page.waitForFunction(
-    (prompt: string) => {
-      const viewport = document.querySelector('[data-slot="aui_thread-viewport"]')
-      if (!viewport) return false
-      return !(viewport.textContent ?? '').includes(prompt)
-    },
-    PROMPT,
-    { timeout: 15_000 },
-  )
-  await page.waitForTimeout(500)
-
-  // Step 4: Install render counter, click back (warm resume), wait, assert.
-  await installRenderCounter(page)
-  await sessionRow.click()
-
-  // Wait for the transcript to reappear — the warm cache should already
-  // have the completed turn (updated by message.complete events).
-  await page.waitForFunction(
-    (text: string) =>
-      document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent?.includes(text) ??
-      false,
-    FIRST_USER_MSG,
-    { timeout: 30_000 },
-  )
-
-  // Wait for at least 1 burst, then settle.
-  await page.waitForFunction(
-    () => {
-      const w = window as unknown as { __RENDER_COUNT__?: { bursts: number } }
-      return Boolean(w.__RENDER_COUNT__ && w.__RENDER_COUNT__.bursts > 0)
-    },
-    undefined,
-    { timeout: 10_000 },
-  )
-  await page.waitForTimeout(2_000)
-
-  const result = await readRenderCount(page)
-  await page.screenshot({ path: testInfo.outputPath('warm-resume-post-inference.png') })
-  assertNoJitter(result)
-})
@@ -1,94 +0,0 @@
-import { execFileSync } from 'node:child_process'
-import * as fs from 'node:fs'
-import * as path from 'node:path'
-
-import { test, expect } from './test'
-
-import {
-  buildAppEnv,
-  createSandbox,
-  launchDesktop,
-  writeEnvFile,
-  writeMockProviderConfig,
-  type MockBackendFixture,
-  waitForAppReady,
-} from './fixtures'
-import { startMockServer } from './mock-server'
-
-const BRANCH_NAME = 'e2e-composer-branch'
-
-function createGitRepo(root: string): string {
-  const repo = path.join(root, 'repo')
-
-  fs.mkdirSync(repo, { recursive: true })
-  execFileSync('git', ['init', '--initial-branch=main'], { cwd: repo })
-  execFileSync('git', ['config', 'user.email', 'e2e@example.com'], { cwd: repo })
-  execFileSync('git', ['config', 'user.name', 'Hermes E2E'], { cwd: repo })
-  fs.writeFileSync(path.join(repo, 'README.md'), '# E2E repo\n', 'utf8')
-  execFileSync('git', ['add', 'README.md'], { cwd: repo })
-  execFileSync('git', ['commit', '-m', 'initial'], { cwd: repo })
-
-  return repo
-}
-
-function configureRepoCwd(hermesHome: string, mockUrl: string, repo: string): void {
-  writeMockProviderConfig(hermesHome, mockUrl)
-  fs.appendFileSync(path.join(hermesHome, 'config.yaml'), `\nterminal:\n  cwd: ${repo}\n`, 'utf8')
-  writeEnvFile(hermesHome)
-}
-
-let fixture: MockBackendFixture | null = null
-
-test.beforeAll(async () => {
-  const sandbox = createSandbox('worktree-branch-status')
-  const repo = createGitRepo(sandbox.root)
-  const mock = await startMockServer()
-
-  configureRepoCwd(sandbox.hermesHome, mock.url, repo)
-
-  const { app, page } = await launchDesktop(buildAppEnv(sandbox))
-  fixture = {
-    app,
-    page,
-    mock,
-    mockUrl: mock.url,
-    sandbox,
-    cleanup: async () => {
-      await app.close().catch(() => undefined)
-      await mock.close()
-      sandbox.cleanup()
-    },
-  }
-
-  await waitForAppReady(fixture, 120_000)
-})
-
-test.afterAll(async () => {
-  await fixture?.cleanup()
-  fixture = null
-})
-
-test('creating a branch with ctrl-shift-b updates the composer git-status branch', async ({}, testInfo) => {
-  const page = fixture!.page
-  const codingRow = page.locator('.coding-status-bar')
-  const composer = page.locator('[contenteditable="true"]').first()
-
-  await composer.click()
-  await composer.type('create a repo-backed e2e session', { delay: 2 })
-  await page.keyboard.press('Enter')
-  await page.waitForFunction(
-    prompt => (document.querySelector('[data-slot="aui_thread-viewport"]')?.textContent ?? '').includes(prompt),
-    'create a repo-backed e2e session',
-    { timeout: 15_000 },
-  )
-  await expect(codingRow).toContainText('main')
-  await page.keyboard.press('Control+Shift+B')
-
-  const branchInput = page.locator('input[placeholder="e.g. my-feature"]').first()
-  await expect(branchInput).toBeVisible()
-  await branchInput.fill(BRANCH_NAME)
-  await page.getByRole('button', { name: 'New worktree' }).click()
-
-  await expect(codingRow).toContainText(BRANCH_NAME, { timeout: 15_000 })
-  await page.screenshot({ path: testInfo.outputPath('composer-branch-after-create.png') })
-})
@@ -12,12 +12,7 @@ import path from 'node:path'

 import { test } from 'vitest'

-import {
-  canImportHermesCli,
-  hermesRuntimeImportProbe,
-  shouldTrustHermesOverride,
-  verifyHermesCli
-} from './backend-probes'
+import { canImportHermesCli, hermesRuntimeImportProbe, verifyHermesCli } from './backend-probes'

 // Resolve the host's own Node binary -- guaranteed to be on disk and
 // runnable. We use it as both a stand-in for "a python that doesn't
@@ -56,15 +51,6 @@ test('hermes runtime import probe checks config dependencies', () => {
  assert.match(probe, /\bimport hermes_cli\.config\b/)
 })

-test('explicit Hermes override is authoritative', () => {
-  assert.equal(shouldTrustHermesOverride('/nix/store/abc/bin/hermes'), true)
-})
-
-test('empty Hermes override is not authoritative', () => {
-  assert.equal(shouldTrustHermesOverride(''), false)
-  assert.equal(shouldTrustHermesOverride(undefined), false)
-})
-
 test('verifyHermesCli returns false when command is falsy', () => {
  assert.equal(verifyHermesCli(''), false)
  assert.equal(verifyHermesCli(null), false)
@@ -104,16 +104,6 @@ function canImportHermesCli(pythonPath: string, opts: { env?: Record<string, str
 *   in resolveHermesBackend.
 * @returns {boolean}
 */
-/**
- * An explicit desktop backend command is a deployment contract, not a PATH
- * discovery candidate. In particular, the Nix desktop wrapper points this at
- * its immutable, matching Hermes package; it must never fall through to the
- * mutable install-script bootstrap path if a best-effort probe is slow.
- */
-function shouldTrustHermesOverride(hermesOverride?: string) {
-  return typeof hermesOverride === 'string' && hermesOverride.trim().length > 0
-}
-
 function verifyHermesCli(hermesCommand: string, opts?: { shell?: boolean }) {
  if (!hermesCommand) {
    return false
@@ -133,4 +123,4 @@ function verifyHermesCli(hermesCommand: string, opts?: { shell?: boolean }) {
  }
 }

-export { canImportHermesCli, hermesRuntimeImportProbe, PROBE_TIMEOUT_MS, shouldTrustHermesOverride, verifyHermesCli }
+export { canImportHermesCli, hermesRuntimeImportProbe, PROBE_TIMEOUT_MS, verifyHermesCli }
@@ -1,100 +0,0 @@
-import { describe, expect, it, vi } from 'vitest'
-
-import { applyConnectionChange, commitConnectionFailure, resolveTerminalConnection } from './connection-apply'
-
-function deferred() {
-  let resolve!: () => void
-
-  const promise = new Promise<void>(done => {
-    resolve = done
-  })
-
-  return { promise, resolve }
-}
-
-describe('applyConnectionChange', () => {
-  it.each([['SSH A to SSH B'], ['SSH to Cloud'], ['Cloud to SSH']])(
-    'serializes %s behind bootstrap rollback before teardown and apply',
-    async () => {
-      const gate = deferred()
-      const events: string[] = []
-
-      const run = applyConnectionChange({
-        cancelAndWait: async () => {
-          events.push('cancel')
-          await gate.promise
-          events.push('drained')
-        },
-        isPrimary: true,
-        scope: '',
-        sendApplied: () => events.push('applied'),
-        stopPool: vi.fn(),
-        teardownPrimary: async () => {
-          events.push('primary')
-        },
-        teardownSsh: async () => {
-          events.push('ssh')
-        }
-      })
-
-      await Promise.resolve()
-      expect(events).toEqual(['cancel'])
-      gate.resolve()
-      await run
-      expect(events).toEqual(['cancel', 'drained', 'ssh', 'primary', 'applied'])
-    }
-  )
-
-  it('tears down only a non-primary scope without applying the primary connection', async () => {
-    const events: string[] = []
-    await applyConnectionChange({
-      cancelAndWait: async scope => {
-        events.push(`cancel:${scope}`)
-      },
-      isPrimary: false,
-      scope: 'worker',
-      sendApplied: () => events.push('applied'),
-      stopPool: scope => events.push(`pool:${scope}`),
-      teardownPrimary: async () => {
-        events.push('primary')
-      },
-      teardownSsh: async scope => {
-        events.push(`ssh:${scope}`)
-      }
-    })
-    expect(events).toEqual(['cancel:worker', 'ssh:worker', 'pool:worker'])
-  })
-})
-
-describe('resolveTerminalConnection', () => {
-  it('joins an in-flight backend before resolving the SSH terminal target', async () => {
-    const target = { ssh: {}, scope: '' }
-    const getTarget = vi.fn().mockReturnValueOnce('pending').mockReturnValueOnce(target)
-    const ensureBackend = vi.fn(async () => undefined)
-
-    await expect(resolveTerminalConnection(getTarget, ensureBackend)).resolves.toBe(target)
-    expect(ensureBackend).toHaveBeenCalledOnce()
-  })
-
-  it('does not start a local terminal while configured SSH remains unavailable', async () => {
-    await expect(
-      resolveTerminalConnection(
-        () => 'pending',
-        async () => undefined
-      )
-    ).rejects.toThrow('not ready')
-  })
-})
-
-describe('commitConnectionFailure', () => {
-  it('prevents a stale bootstrap from publishing failure state', () => {
-    const stale = Promise.resolve('stale')
-    const current = Promise.resolve('current')
-    const commit = vi.fn()
-
-    expect(commitConnectionFailure(current, stale, commit)).toBe(false)
-    expect(commit).not.toHaveBeenCalled()
-    expect(commitConnectionFailure(current, current, commit)).toBe(true)
-    expect(commit).toHaveBeenCalledOnce()
-  })
-})
@@ -1,50 +0,0 @@
-async function applyConnectionChange({
-  cancelAndWait,
-  isPrimary,
-  scope,
-  sendApplied,
-  stopPool,
-  teardownPrimary,
-  teardownSsh
-}) {
-  await cancelAndWait(scope)
-  await teardownSsh(scope)
-
-  if (!isPrimary) {
-    stopPool(scope)
-
-    return
-  }
-
-  await teardownPrimary()
-  sendApplied()
-}
-
-function commitConnectionFailure(current, starting, commit) {
-  if (current !== starting) {
-    return false
-  }
-
-  commit()
-
-  return true
-}
-
-async function resolveTerminalConnection(getTarget, ensureBackend) {
-  let target = getTarget()
-
-  if (target !== 'pending') {
-    return target
-  }
-
-  await ensureBackend()
-  target = getTarget()
-
-  if (target === 'pending') {
-    throw new Error('Remote connection is not ready yet. Try again in a moment.')
-  }
-
-  return target
-}
-
-export { applyConnectionChange, commitConnectionFailure, resolveTerminalConnection }
@@ -26,19 +26,14 @@ import {
  gatewayTicketFailure,
  gatewayWsUrlIpcResult,
  isGatewayAuthRejection,
-  localProfileEntry,
  modeIsRemoteLike,
  normalizeRemoteBaseUrl,
-  normalizeSshConfig,
  normAuthMode,
  pathWithGlobalRemoteProfile,
-  profileHasRemoteConnection,
  profileRemoteOverride,
-  profileSshOverride,
  resolveAuthMode,
  resolveTestWsUrl,
  RT_COOKIE_VARIANTS,
-  savedProfileSsh,
  tokenPreview
 } from './connection-config'

@@ -132,61 +127,6 @@ test('profileRemoteOverride tolerates a missing/!object profiles map', () => {
  assert.equal(profileRemoteOverride(null, 'coder'), null)
 })

-test('SSH remains separate from URL-shaped remote modes', () => {
-  assert.equal(modeIsRemoteLike('ssh'), false)
-  const config = { profiles: { coder: { mode: 'ssh', host: 'alice@box:2222', keyPath: '/key' } } }
-  assert.equal(profileRemoteOverride(config, 'coder'), null)
-  assert.deepEqual(profileSshOverride(config, 'coder'), {
-    mode: 'ssh',
-    host: 'box',
-    user: 'alice',
-    port: 2222,
-    keyPath: '/key'
-  })
-})
-
-test('normalizeSshConfig handles IPv6 and strict port bounds', () => {
-  assert.deepEqual(normalizeSshConfig({ mode: 'ssh', host: '::1', port: 22 }), {
-    mode: 'ssh',
-    host: '::1'
-  })
-  assert.deepEqual(normalizeSshConfig({ mode: 'ssh', host: '[::1]:2222' }), {
-    mode: 'ssh',
-    host: '::1',
-    port: 2222
-  })
-  assert.deepEqual(normalizeSshConfig({ mode: 'ssh', host: 'box', port: '2222junk' }), {
-    mode: 'ssh',
-    host: 'box'
-  })
-  assert.deepEqual(normalizeSshConfig({ mode: 'ssh', host: 'box', port: 65536 }), {
-    mode: 'ssh',
-    host: 'box'
-  })
-})
-
-test('localProfileEntry preserves inactive SSH drafts but drops Cloud state', () => {
-  const ssh = { mode: 'ssh', host: 'box', user: 'alice', remoteHermesPath: '/hermes' }
-  assert.deepEqual(localProfileEntry(ssh), { mode: 'local', savedSsh: ssh })
-  assert.deepEqual(localProfileEntry({ mode: 'local', savedSsh: ssh }), {
-    mode: 'local',
-    savedSsh: ssh
-  })
-  assert.equal(localProfileEntry({ mode: 'cloud', url: 'https://agent' }), null)
-})
-
-test('saved SSH drafts are inactive and explicit overrides take precedence', () => {
-  const saved = { mode: 'ssh', host: 'saved' }
-  const config: any = { profiles: { coder: { mode: 'local', savedSsh: saved } } }
-  assert.deepEqual(savedProfileSsh(config, 'coder'), saved)
-  assert.equal(profileSshOverride(config, 'coder'), null)
-  assert.equal(profileHasRemoteConnection(config, 'coder'), false)
-
-  config.profiles.coder = { mode: 'ssh', host: 'active' }
-  assert.deepEqual(profileSshOverride(config, 'coder'), { mode: 'ssh', host: 'active' })
-  assert.equal(profileHasRemoteConnection(config, 'coder'), true)
-})
-
 // --- pathWithGlobalRemoteProfile ---

 test('pathWithGlobalRemoteProfile appends profile in global remote mode', () => {
@@ -203,127 +203,6 @@ function modeIsRemoteLike(mode) {
  return mode === 'remote' || mode === 'cloud'
 }

-function normalizeSshConfig(entry) {
-  if (!entry || typeof entry !== 'object' || entry.mode !== 'ssh') {
-    return null
-  }
-
-  let host = String(entry.host || '').trim()
-
-  if (!host) {
-    return null
-  }
-
-  let parsedUser
-  let parsedPort
-  const at = host.indexOf('@')
-
-  if (at > 0) {
-    parsedUser = host.slice(0, at)
-    host = host.slice(at + 1)
-  }
-
-  const bracketed = /^\[([^\]]+)](?::(\d+))?$/.exec(host)
-
-  if (bracketed) {
-    host = bracketed[1]
-
-    if (bracketed[2]) {
-      parsedPort = Number(bracketed[2])
-    }
-  } else if ((host.match(/:/g) || []).length === 1) {
-    const [name, rawPort] = host.split(':')
-
-    if (/^\d+$/.test(rawPort)) {
-      host = name
-      parsedPort = Number(rawPort)
-    }
-  }
-
-  if (!host) {
-    return null
-  }
-
-  const out: any = { mode: 'ssh', host }
-  const user = String(entry.user || '').trim() || parsedUser || ''
-
-  if (user) {
-    out.user = user
-  }
-
-  const rawExplicitPort = String(entry.port ?? '').trim()
-  const explicitPort = /^\d+$/.test(rawExplicitPort) ? Number(rawExplicitPort) : null
-  const port = explicitPort ?? parsedPort
-
-  if (Number.isInteger(port) && port > 0 && port <= 65535 && port !== 22) {
-    out.port = port
-  }
-
-  const keyPath = String(entry.keyPath || '').trim()
-
-  if (keyPath) {
-    out.keyPath = keyPath
-  }
-
-  const remoteHermesPath = String(entry.remoteHermesPath || '').trim()
-
-  if (remoteHermesPath) {
-    out.remoteHermesPath = remoteHermesPath
-  }
-
-  return out
-}
-
-function profileSshOverride(config, profile) {
-  const key = connectionScopeKey(profile)
-  const entry = key ? config?.profiles?.[key] : null
-
-  return normalizeSshConfig(entry)
-}
-
-function savedProfileSsh(config, profile) {
-  const key = connectionScopeKey(profile)
-  const entry = key ? config?.profiles?.[key] : null
-
-  if (!entry || entry.mode !== 'local') {
-    return null
-  }
-
-  return normalizeSshConfig(entry.savedSsh)
-}
-
-function profileHasRemoteConnection(config, profile) {
-  return Boolean(profileRemoteOverride(config, profile) || profileSshOverride(config, profile))
-}
-
-function localProfileEntry(existing) {
-  const ssh = normalizeSshConfig(existing) || normalizeSshConfig(existing?.savedSsh)
-
-  return ssh ? { mode: 'local', savedSsh: ssh } : null
-}
-
-function hostLabelFromBaseUrl(baseUrl) {
-  const raw = String(baseUrl || '').trim()
-
-  if (!raw) {
-    return null
-  }
-
-  try {
-    const parsed = new URL(raw)
-
-    if (!parsed.hostname) {
-      return null
-    }
-
-    return parsed.port && parsed.port !== '80' && parsed.port !== '443'
-      ? `${parsed.hostname}:${parsed.port}`
-      : parsed.hostname
-  } catch {
-    return null
-  }
-}
-
 /**
 * Select a profile's explicit remote override from a connection config, or null
 * when it has none (so the caller falls back to env → global remote → local).
@@ -493,21 +372,15 @@ export {
  cookiesHaveSession,
  gatewayTicketFailure,
  gatewayWsUrlIpcResult,
-  hostLabelFromBaseUrl,
  isGatewayAuthRejection,
-  localProfileEntry,
  modeIsRemoteLike,
  normalizeRemoteBaseUrl,
-  normalizeSshConfig,
  normAuthMode,
  pathWithGlobalRemoteProfile,
  PRIVY_SESSION_COOKIE_VARIANTS,
-  profileHasRemoteConnection,
  profileRemoteOverride,
-  profileSshOverride,
  resolveAuthMode,
  resolveTestWsUrl,
  RT_COOKIE_VARIANTS,
-  savedProfileSsh,
  tokenPreview
 }
@@ -1,105 +0,0 @@
-import assert from 'node:assert/strict'
-import fs from 'node:fs'
-import os from 'node:os'
-import path from 'node:path'
-
-import { test } from 'vitest'
-
-import { loadOrCreateInstallationId, parseInstallationId, sshOwnershipId } from './desktop-installation'
-
-const ID_A = '11111111-1111-4111-8111-111111111111'
-const ID_B = '22222222-2222-4222-8222-222222222222'
-
-function withTempDir(run) {
-  const directory = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-installation-'))
-
-  try {
-    return run(directory)
-  } finally {
-    fs.rmSync(directory, { recursive: true, force: true })
-  }
-}
-
-test('parseInstallationId accepts only a version-4 UUID record', () => {
-  assert.equal(parseInstallationId(JSON.stringify({ installationId: ID_A.toUpperCase() })), ID_A)
-  assert.equal(parseInstallationId(JSON.stringify({ installationId: 'not-an-id' })), '')
-  assert.equal(parseInstallationId('{}'), '')
-  assert.equal(parseInstallationId('{'), '')
-})
-
-test('loadOrCreateInstallationId persists and reuses one installation ID', () =>
-  withTempDir(directory => {
-    const filePath = path.join(directory, 'desktop-installation.json')
-    assert.equal(
-      loadOrCreateInstallationId(filePath, () => ID_A),
-      ID_A
-    )
-    assert.equal(
-      loadOrCreateInstallationId(filePath, () => ID_B),
-      ID_A
-    )
-    assert.equal(fs.statSync(filePath).mode & 0o777, 0o600)
-  }))
-
-test('loadOrCreateInstallationId tightens an existing identity file', () =>
-  withTempDir(directory => {
-    const filePath = path.join(directory, 'desktop-installation.json')
-    fs.writeFileSync(filePath, JSON.stringify({ installationId: ID_A }), { mode: 0o644 })
-    assert.equal(
-      loadOrCreateInstallationId(filePath, () => ID_B),
-      ID_A
-    )
-
-    if (process.platform !== 'win32') {
-      assert.equal(fs.statSync(filePath).mode & 0o777, 0o600)
-    }
-  }))
-
-test('loadOrCreateInstallationId replaces a malformed existing record', () =>
-  withTempDir(directory => {
-    const filePath = path.join(directory, 'desktop-installation.json')
-    fs.writeFileSync(filePath, '{', { mode: 0o600 })
-    assert.equal(
-      loadOrCreateInstallationId(filePath, () => ID_A),
-      ID_A
-    )
-    assert.equal(JSON.parse(fs.readFileSync(filePath, 'utf8')).installationId, ID_A)
-  }))
-
-test('loadOrCreateInstallationId replaces an existing symlink', () =>
-  withTempDir(directory => {
-    if (process.platform === 'win32') {
-      return
-    }
-
-    const target = path.join(directory, 'target.json')
-    const filePath = path.join(directory, 'desktop-installation.json')
-    fs.writeFileSync(target, JSON.stringify({ installationId: ID_B }), { mode: 0o600 })
-    fs.symlinkSync(target, filePath)
-    assert.equal(
-      loadOrCreateInstallationId(filePath, () => ID_A),
-      ID_A
-    )
-    assert.equal(fs.lstatSync(filePath).isSymbolicLink(), false)
-    assert.equal(JSON.parse(fs.readFileSync(target, 'utf8')).installationId, ID_B)
-  }))
-
-test('loadOrCreateInstallationId replaces a malformed destination without a repair lock', () =>
-  withTempDir(directory => {
-    const filePath = path.join(directory, 'desktop-installation.json')
-    fs.writeFileSync(filePath, '{', { mode: 0o600 })
-    assert.equal(
-      loadOrCreateInstallationId(filePath, () => ID_A),
-      ID_A
-    )
-    assert.equal(fs.existsSync(`${filePath}.lock`), false)
-  }))
-
-test('sshOwnershipId is stable, scoped, and does not disclose the UUID', () => {
-  const global = sshOwnershipId(ID_A, '')
-  assert.match(global, /^[0-9a-f]{32}$/)
-  assert.equal(global, sshOwnershipId(ID_A, ''))
-  assert.notEqual(global, sshOwnershipId(ID_A, 'worker'))
-  assert.ok(!global.includes(ID_A.slice(0, 8)))
-  assert.throws(() => sshOwnershipId('bad', ''))
-})
--- a/Show More
+++ b/Show More