fix(ci): move rtl-logical-classes test to ui/ so vitest:ui runner collects it

Three test files had net assertion removals after behavior-changing PRs:
- chatcore-translation-paths: emergency fallback moved to routing layer
  (#3699) — add body error assertion + model-name guard
- executor-vertex-extended: non-JSON is now Express API key (#3690) —
  add projects/-path guard to the express-key URL test
- stream-utils: empty streams now emit error (#3685) — add code/message/
  status/completePayload guards to both passthrough and translate variants

All new assertions are meaningful (code enum value, 5xx range, non-empty
message, onComplete must-not-fire contract).

.dockerignore

@@ -77,8 +77,6 @@ bun.lock
 # Agent config
 .agents
 .gemini
-.claude
-.source
 
 # Misc
 llm.txt
@@ -125,4 +123,3 @@ app.__qa_backup/
 .worktrees
 .next-playwright/
 cloud/
-electron/dist-electron

.editorconfig

@@ -1,12 +0,0 @@
-root = true
-
-[*]
-indent_style = space
-indent_size = 2
-end_of_line = lf
-charset = utf-8
-trim_trailing_whitespace = true
-insert_final_newline = true
-
-[*.sh]
-indent_size = 4

.env.homolog.example

@@ -1,9 +0,0 @@
-# Homologação E2E real — copie para .env.homolog (NUNCA commitar o real)
-HOMOLOG_BASE_URL=http://192.168.0.15:20128
-# Senha de management do dashboard da VPS (a mesma do /login)
-HOMOLOG_ADMIN_PASSWORD=
-# Deixe vazio: a suíte cria uma API key efêmera via admin e revoga no fim.
-# Só preencha para depurar uma camada isolada com uma key fixa.
-HOMOLOG_API_KEY=
-# Tier crítico (chat real, max_tokens=5). Demais providers: só validação de catálogo.
-HOMOLOG_CRITICAL_PROVIDERS=openai,anthropic,gemini,codex,grok,glm,deepseek,openrouter

.github/actions/npm-ci-retry/action.yml

@@ -1,29 +0,0 @@
-name: npm ci with retry
-description: Run npm ci with retries for transient registry/network failures.
-runs:
-  using: composite
-  steps:
-    - shell: bash
-      run: |
-        set -euo pipefail
-
-        max_attempts=3
-        delay_seconds=20
-
-        for attempt in $(seq 1 "$max_attempts"); do
-          if [ "$attempt" -gt 1 ]; then
-            echo "npm ci attempt $attempt/$max_attempts after transient failure"
-          fi
-
-          if npm ci; then
-            exit 0
-          fi
-
-          exit_code=$?
-          if [ "$attempt" -eq "$max_attempts" ]; then
-            exit "$exit_code"
-          fi
-
-          sleep "$delay_seconds"
-          delay_seconds=$((delay_seconds * 2))
-        done

.github/dependabot.yml

@@ -24,29 +24,6 @@ updates:
         update-types: ["version-update:semver-major"]
       - dependency-name: "eslint-config-next"
         update-types: ["version-update:semver-major"]
-      # typescript majors are peer-blocked by typescript-eslint, which pins a hard
-      # upper bound (8.64.0 → peerDependencies.typescript ">=4.8.4 <6.1.0"). A TS 7
-      # bump therefore violates the peer and takes down the whole toolchain at once —
-      # #7068 grouped it with 6 harmless bumps and turned Build + Lint + Quality Ratchet
-      # + Unit (6/8, 8/8) + Integration (1/2, 2/2) + dast-smoke red in one shot, blocking
-      # the innocuous updates riding along with it. Un-ignore once typescript-eslint
-      # widens the peer, and migrate TS majors intentionally (own PR, own CI run).
-      - dependency-name: "typescript"
-        update-types: ["version-update:semver-major"]
-      # jscpd v5 is a Rust rewrite (native binary, no Node.js programmatic API).
-      # scripts/check/check-duplication.mjs is deliberately pinned to jscpd@4 (it
-      # parses jscpd-report.json against a frozen baseline). A v5 major would break
-      # the duplication gate — migrate the gate intentionally, not via dependabot.
-      - dependency-name: "jscpd"
-        update-types: ["version-update:semver-major"]
-      # @huggingface/transformers is HARD-PINNED at 3.5.2 (exact, no caret) — FROZEN.
-      # It is load-bearing for the LLMLingua ONNX compression engine (open-sse/services/
-      # compression/engines/llmlingua/ — worker.ts pins @huggingface/transformers@3.5.2)
-      # and for local memory embeddings (src/lib/memory/embedding/transformersLocal.ts),
-      # and was VPS-validated at 3.5.2 (#4014). 4.x breaks both, and even 3.x minors must
-      # be re-validated on the VPS — so freeze ALL auto-bumps (no update-types = ignore
-      # every version). Migrate it intentionally, not via dependabot (#4050).
-      - dependency-name: "@huggingface/transformers"
 
   - package-ecosystem: "github-actions"
     directory: "/"

.github/workflows/build-fork.yml

@@ -7,10 +7,9 @@ on:
       - "v*"
   workflow_dispatch:
 
-# Least-privilege default: read-only at the top level; the build job that pushes to
-# GHCR grants packages: write itself (Scorecard TokenPermissions).
 permissions:
   contents: read
+  packages: write
 
 env:
   IMAGE_NAME: ghcr.io/kang-heewon/omniroute
@@ -20,14 +19,9 @@ jobs:
     name: Build and Push Fork Image
     if: github.repository == 'kang-heewon/OmniRoute'
     runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
-        with:
-          persist-credentials: false
+        uses: actions/checkout@v6
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v4

.github/workflows/claude.yml

@@ -10,10 +10,6 @@ on:
   pull_request_review:
     types: [submitted]
 
-# Least-privilege default: no token permissions at the top level; the `claude` job
-# grants exactly what it needs below (Scorecard TokenPermissions).
-permissions: {}
-
 jobs:
   claude:
     if: |
@@ -30,9 +26,8 @@ jobs:
       actions: read # Required for Claude to read CI results on PRs
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           fetch-depth: 1
 
       - name: Run Claude Code

.github/workflows/codeql.yml

@@ -1,31 +0,0 @@
-name: CodeQL
-# OWNER ACTION REQUIRED before enabling auto-triggers: advanced CodeQL conflicts with
-# GitHub "default setup" — the analyze step fails with "CodeQL analyses from advanced
-# configurations cannot be processed when the default setup is enabled". Switch repo
-# Settings → Code security → CodeQL from Default to Advanced, THEN restore the
-# push/pull_request/schedule triggers below. Until then this only runs on manual dispatch
-# so it never produces a red check on PRs. (The codeqlAlerts ratchet keeps working via the
-# default setup's alerts in the meantime.)
-on:
-  workflow_dispatch:
-permissions:
-  contents: read
-jobs:
-  analyze:
-    name: Analyze (javascript-typescript)
-    runs-on: ubuntu-latest
-    permissions:
-      security-events: write
-      actions: read
-      contents: read
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          persist-credentials: false
-      - uses: github/codeql-action/init@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
-        with:
-          languages: javascript-typescript
-          queries: security-extended
-      - uses: github/codeql-action/analyze@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4.37.0
-        with:
-          category: "/language:javascript-typescript"

.github/workflows/dast-smoke.yml

@@ -1,65 +0,0 @@
-name: DAST smoke (PR)
-on:
-  pull_request:
-    branches: ["main", "release/**"]
-permissions:
-  contents: read
-jobs:
-  dast-smoke:
-    runs-on: ubuntu-latest
-    # ADVISORY while this new gate matures (repo convention: advisory -> blocking).
-    # Flip to blocking (remove continue-on-error) once it's proven stable across a few PRs.
-    continue-on-error: true
-    # Build CLI bundle alone varies 6-11min on GitHub-hosted runners (3 consecutive
-    # timeouts observed on 2026-07-14 with the old 12min cap killing schemathesis
-    # mid-run) — 25min leaves real headroom for the actual DAST steps.
-    timeout-minutes: 25
-    env:
-      JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-api-key-secret-with-sufficient-length-aaaa
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - name: Build CLI bundle
-        run: npm run build:cli
-      - name: Start OmniRoute
-        env:
-          PORT: "20128"
-          INJECTION_GUARD_MODE: block
-        run: |
-          node dist/server.js > server.log 2>&1 &
-          echo $! > server.pid
-          for _ in $(seq 1 30); do
-            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
-            sleep 2
-          done
-      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
-        with:
-          python-version: "3.12"
-      - run: pip install schemathesis
-      - name: Schemathesis smoke (high-risk endpoints, blocking)
-        run: |
-          schemathesis run docs/openapi.yaml --url http://localhost:20128 \
-            --include-path-regex '^/v1/(chat/completions|models)$|^/api/(auth|keys)' \
-            --max-examples 8 --workers 4 --checks all --max-response-time 30 \
-            --request-timeout 20 --suppress-health-check all --no-color
-      - name: promptfoo injection-guard (blocking)
-        env:
-          OMNIROUTE_URL: http://localhost:20128
-          OMNIROUTE_API_KEY: not-needed-blocked-before-upstream
-        run: npx --yes promptfoo@latest eval -c promptfooconfig.yaml --no-cache
-      - name: Stop server
-        if: always()
-        run: kill "$(cat server.pid)" || true
-      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        if: always()
-        with:
-          name: dast-smoke-logs
-          path: server.log
-          retention-days: 7

.github/workflows/docker-publish.yml

@@ -25,10 +25,9 @@ on:
         type: boolean
         default: false
 
-# Least-privilege default: read-only at the top level; the build and merge jobs that
-# push to GHCR grant packages: write themselves (Scorecard TokenPermissions).
 permissions:
   contents: read
+  packages: write
 
 jobs:
   prepare:
@@ -42,9 +41,8 @@ jobs:
       IMAGE_NAME: diegosouzapw/omniroute
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}
           # Need full tag history for semver comparison when deciding :latest.
           fetch-depth: 0
@@ -98,13 +96,11 @@ jobs:
             PROMOTE="${PROMOTE_INPUT:-false}"
           else
             git fetch --tags --quiet || true
-            # Decide via the extracted helper, which folds VERSION into the
-            # candidate set so the result is independent of git-tag sync timing
-            # on `release` events (#5301). Without that, the freshly-created tag
-            # is often not yet visible here and :latest stays a release behind.
-            PROMOTE=$(git tag -l 'v[0-9]*' | bash scripts/ci/should-promote-latest.sh "$VERSION")
-            if [ "$PROMOTE" != "true" ]; then
-              echo "Version $VERSION is not the highest stable semver. Not promoting :latest."
+            HIGHEST=$(git tag -l 'v[0-9]*' | sed 's/^v//' | grep -vE -- '-(rc|alpha|beta|pre|next)' | sort -V | tail -1 || echo "")
+            if [ -n "$HIGHEST" ] && [ "$VERSION" = "$HIGHEST" ]; then
+              PROMOTE="true"
+            else
+              echo "Version $VERSION is not the highest semver tag (highest=${HIGHEST:-<none>}). Not promoting :latest."
             fi
           fi
           echo "promote_latest=$PROMOTE" >> "$GITHUB_OUTPUT"
@@ -127,9 +123,6 @@ jobs:
     needs: prepare
     if: needs.prepare.outputs.skip != 'true'
     runs-on: ${{ matrix.runner }}
-    permissions:
-      contents: read
-      packages: write
     strategy:
       fail-fast: false
       matrix:
@@ -145,9 +138,8 @@ jobs:
       GHCR_IMAGE_NAME: ghcr.io/diegosouzapw/omniroute
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}
           fetch-depth: 0
 
@@ -234,10 +226,6 @@ jobs:
       - build
     if: needs.prepare.outputs.skip != 'true'
     runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-      security-events: write
     env:
       IMAGE_NAME: diegosouzapw/omniroute
       GHCR_IMAGE_NAME: ghcr.io/diegosouzapw/omniroute
@@ -245,9 +233,8 @@ jobs:
       PROMOTE_LATEST: ${{ needs.prepare.outputs.promote_latest }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}
           fetch-depth: 0
 
@@ -334,67 +321,6 @@ jobs:
         run: |
           docker buildx imagetools inspect "${IMAGE_NAME}:${VERSION}"
 
-      - name: Generate CycloneDX SBOM (image, advisory)
-        if: needs.prepare.outputs.version != 'main'
-        continue-on-error: true
-        uses: anchore/sbom-action@v0
-        with:
-          image: ${{ env.GHCR_IMAGE_NAME }}:${{ env.VERSION }}
-          format: cyclonedx-json
-          output-file: sbom-image.cdx.json
-          artifact-name: sbom-image.cdx.json
-
-      # Visibility scan: reports HIGH + CRITICAL into the SARIF (Security tab) but
-      # never blocks (exit-code 0). The blocking gate below narrows to CRITICAL.
-      #
-      # ignore-unfixed mirrors the blocking gate: the Security tab must surface only
-      # ACTIONABLE vulnerabilities — ones with a published fix we can pull by rebuilding
-      # on a patched base or bumping the dep. Without it the advisory upload floods the
-      # tab with unfixable base-image OS CVEs (Debian trixie packages with no upstream
-      # patch yet, overwhelmingly local-only and not reachable from the proxy request
-      # surface), which is noise an operator cannot act on. trivyignores points at the
-      # repo-root .trivyignore so accepted-risk fixable CVEs have one auditable home.
-      # See docs/security/SUPPLY_CHAIN.md.
-      - name: Trivy image scan (SARIF, advisory)
-        if: needs.prepare.outputs.version != 'main'
-        continue-on-error: true
-        uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
-        with:
-          image-ref: ${{ env.GHCR_IMAGE_NAME }}:${{ env.VERSION }}
-          format: sarif
-          output: trivy-results.sarif
-          severity: HIGH,CRITICAL
-          ignore-unfixed: true
-          trivyignores: .trivyignore
-          exit-code: "0"
-
-      # BLOCKING gate (v3.8.27 cycle-end): fail the release on a CRITICAL CVE in the
-      # published image. Narrowed to severity CRITICAL (HIGH stays visible in the
-      # SARIF step above, not blocking). ignore-unfixed:true so an unfixable base-image
-      # CVE with no upstream patch does not red the release (reduces false-blocks);
-      # a fixable CRITICAL still blocks. Per docs/security/SUPPLY_CHAIN.md. NB: Trivy
-      # scans against a CVE DB that grows continuously — a newly-disclosed CRITICAL on
-      # an unchanged base image can red this gate; the fix is to rebuild on a patched
-      # base, bump the dep, or add a justified .trivyignore entry (see the CVE-variance
-      # note in docs/security/SUPPLY_CHAIN.md).
-      - name: Trivy CRITICAL gate (blocking)
-        if: needs.prepare.outputs.version != 'main'
-        uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
-        with:
-          image-ref: ${{ env.GHCR_IMAGE_NAME }}:${{ env.VERSION }}
-          format: table
-          severity: CRITICAL
-          ignore-unfixed: true
-          exit-code: "1"
-
-      - name: Upload Trivy SARIF to Security tab
-        if: needs.prepare.outputs.version != 'main'
-        continue-on-error: true
-        uses: github/codeql-action/upload-sarif@v4
-        with:
-          sarif_file: trivy-results.sarif
-          category: trivy-image
-
       - name: Update Docker Hub description
         # Only refresh README/description when we actually promote :latest
         # (avoids overwriting from main pushes or back-fill builds).

.github/workflows/electron-release.yml

@@ -11,56 +11,43 @@ on:
         required: true
         type: string
 
-# Least-privilege default: read-only at the top level; each job grants the writes it
-# needs (build/release upload assets, publish-npm forwards npm provenance / packages
-# to the reusable workflow) — Scorecard TokenPermissions.
 permissions:
-  contents: read
+  contents: write
+  id-token: write
+  packages: write
 
 jobs:
   validate:
     name: Validate version
     runs-on: ubuntu-latest
-    permissions:
-      contents: read
     outputs:
       version: ${{ steps.validate.outputs.version }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           fetch-depth: 0
 
       - name: Validate version format
         id: validate
-        env:
-          # Pass workflow context via env (never interpolate ${{ ... }} straight
-          # into the run: script body) so the shell receives variables, not
-          # inlined text — zizmor template-injection mitigation. INPUT_VERSION is
-          # the operator-supplied value and is regex-validated below before use.
-          EVENT_NAME: ${{ github.event_name }}
-          INPUT_VERSION: ${{ inputs.version }}
         run: |
-          if [[ "$EVENT_NAME" == "push" ]]; then
+          if [[ "${{ github.event_name }}" == "push" ]]; then
             VERSION="${GITHUB_REF#refs/tags/}"
           else
-            VERSION="$INPUT_VERSION"
+            VERSION="${{ inputs.version }}"
           fi
 
           if [[ ! "$VERSION" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
             echo "Error: Invalid version format. Expected: v1.6.8"
             exit 1
           fi
-          echo "version=$VERSION" >> "$GITHUB_OUTPUT"
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
           echo "✓ Valid version: $VERSION"
 
   build:
     name: Build Electron (${{ matrix.platform }})
     needs: validate
     runs-on: ${{ matrix.runner }}
-    permissions:
-      contents: write # electron-builder may publish artifacts with GH_TOKEN
     strategy:
       fail-fast: false
       matrix:
@@ -84,9 +71,7 @@ jobs:
             deb_ext: .deb
 
     steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
+      - uses: actions/checkout@v6
       - name: Setup Node
         uses: actions/setup-node@v6
         with:
@@ -94,7 +79,7 @@ jobs:
           cache: npm
 
       - name: Cache node_modules
-        uses: actions/cache@v6.1.0
+        uses: actions/cache@v5
         with:
           path: node_modules
           key: ${{ runner.os }}-node-${{ hashFiles('package-lock.json') }}
@@ -114,7 +99,7 @@ jobs:
           # that cause EPERM errors during Next.js standalone build glob scans.
           # Create a clean temp profile directory to avoid this.
           mkdir -p "$RUNNER_TEMP/home"
-          echo "USERPROFILE=$RUNNER_TEMP/home" >> "$GITHUB_ENV"
+          echo "USERPROFILE=$RUNNER_TEMP/home" >> $GITHUB_ENV
 
       - name: Build Next.js standalone
         env:
@@ -124,13 +109,8 @@ jobs:
 
       - name: Sync version in electron/package.json
         shell: bash
-        env:
-          # Pass the validated version via env (never interpolate ${{ ... }}
-          # straight into the run: script body) — zizmor template-injection
-          # mitigation. Already regex-validated (^v[0-9]+\.[0-9]+\.[0-9]+$) in
-          # the `validate` job, so it cannot carry shell metacharacters.
-          VERSION: ${{ needs.validate.outputs.version }}
         run: |
+          VERSION="${{ needs.validate.outputs.version }}"
           VERSION_NO_V="${VERSION#v}"
           node -e "
             const fs = require('fs');
@@ -201,12 +181,6 @@ jobs:
               [ -f "$file" ] && cp "$file" "../../release-assets/OmniRoute.exe" && break
             done
           fi
-          # electron-updater manifests (latest.yml / latest-mac.yml / latest-linux.yml)
-          # must be published alongside the installers, or autoUpdater fails with
-          # "Cannot find latest.yml in the latest release artifacts" (#6766).
-          for file in latest*.yml; do
-            [ -f "$file" ] && cp "$file" ../../release-assets/
-          done
 
       - name: Upload artifacts
         uses: actions/upload-artifact@v7
@@ -218,13 +192,10 @@ jobs:
     name: Create Release
     needs: [validate, build]
     runs-on: ubuntu-latest
-    permissions:
-      contents: write # softprops/action-gh-release creates the GitHub Release
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           fetch-depth: 0
 
       - name: Download all artifacts
@@ -234,20 +205,14 @@ jobs:
           merge-multiple: true
 
       - name: Create source archives
-        env:
-          # Pass the validated version via env (never interpolate ${{ ... }}
-          # straight into the run: script body) — zizmor template-injection
-          # mitigation. Already regex-validated (^v[0-9]+\.[0-9]+\.[0-9]+$) in
-          # the `validate` job, so it cannot carry shell metacharacters.
-          VERSION: ${{ needs.validate.outputs.version }}
         run: |
           # Create source code archives (excluding dev dependencies and build artifacts)
-          export TARBALL="OmniRoute-${VERSION}.source.tar.gz"
-          export ZIPBALL="OmniRoute-${VERSION}.source.zip"
+          export TARBALL="OmniRoute-${{ needs.validate.outputs.version }}.source.tar.gz"
+          export ZIPBALL="OmniRoute-${{ needs.validate.outputs.version }}.source.zip"
 
           # Use git archive for clean source export
-          git archive --format=tar.gz --prefix="OmniRoute-${VERSION}/" HEAD -o "release-assets/$TARBALL"
-          git archive --format=zip --prefix="OmniRoute-${VERSION}/" HEAD -o "release-assets/$ZIPBALL"
+          git archive --format=tar.gz --prefix=OmniRoute-${{ needs.validate.outputs.version }}/ HEAD -o "release-assets/$TARBALL"
+          git archive --format=zip --prefix=OmniRoute-${{ needs.validate.outputs.version }}/ HEAD -o "release-assets/$ZIPBALL"
 
           echo "✓ Created source archives:"
           ls -lh "release-assets/$TARBALL" "release-assets/$ZIPBALL"
@@ -269,7 +234,6 @@ jobs:
             release-assets/*.AppImage
             release-assets/*.deb
             release-assets/*.blockmap
-            release-assets/*.yml
             release-assets/*.source.tar.gz
             release-assets/*.source.zip
         env:
@@ -278,14 +242,6 @@ jobs:
   publish-npm:
     name: Publish to npm
     needs: [validate, release]
-    permissions:
-      # Must be `write`, not `read`: this job calls the reusable npm-publish.yml whose
-      # `publish` job needs `contents: write` (gh release upload — attach the SBOM, #3874).
-      # A reusable workflow's job cannot request more permission than the caller grants,
-      # so a `read` here makes GitHub reject the run at startup (startup_failure).
-      contents: write
-      id-token: write # npm provenance (forwarded to the reusable workflow)
-      packages: write # publish to npm.pkg.github.com
     uses: ./.github/workflows/npm-publish.yml
     with:
       version: ${{ needs.validate.outputs.version }}

.github/workflows/mutation-redundancy.yml

@@ -1,63 +0,0 @@
-name: Mutation Redundancy (disableBail, on-demand)
-# One-off measurement to UNBLOCK R1 (test-redundancy prune). The nightly mutation run
-# (nightly-mutation.yml) bails on the first kill, so `killedBy` lists only the FIRST
-# killer — 🟠 redundant is understated and 🟢 unique overstated (see the caveat in
-# scripts/quality/mutation-radiography.mjs). This workflow re-runs the SAME combo +
-# chatCore leaf batches with stryker.disablebail.json (disableBail:true, incremental:false)
-# so `killedBy` lists EVERY killer. Feed the uploaded reports to
-# `node scripts/quality/mutation-radiography.mjs --candidates mutation-nobail-*/mutation.json`
-# to get the accurate R1 prune-candidate list (🔴 empty ∪ 🟠 redundant) for human review.
-#
-# Batches mirror the nightly's leaf decomposition (d/e/f/g/h/i) rather than 2 mega-batches:
-# disableBail is MORE expensive than bail (it never stops early), and Stryker only writes
-# mutation.json on a SUCCESSFUL finish — a batch cancelled at the cap produces NO data — so
-# smaller batches each fit the 300min headroom and run in parallel. auth/accountFallback and
-# the security quartet are out of scope: R1 targets the combo/chatCore leaves.
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  stryker-nobail:
-    name: Stryker disableBail (batch ${{ matrix.batch.name }})
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        batch:
-          - name: d
-            mutate: "open-sse/services/combo/comboStructure.ts,open-sse/services/combo/autoStrategy.ts,open-sse/services/combo/validateQuality.ts"
-          - name: e
-            mutate: "open-sse/services/combo/shadowRouting.ts,open-sse/services/combo/targetSorters.ts,open-sse/services/combo/comboPredicates.ts,open-sse/services/combo/rrState.ts,open-sse/services/combo/comboData.ts"
-          - name: f
-            mutate: "open-sse/services/combo/quotaScoring.ts,open-sse/services/combo/quotaStrategies.ts"
-          - name: g
-            mutate: "open-sse/handlers/chatCore/comboContextCache.ts,open-sse/handlers/chatCore/idempotency.ts,open-sse/handlers/chatCore/passthroughHelpers.ts,open-sse/handlers/chatCore/responseHeaders.ts,open-sse/handlers/chatCore/sanitization.ts,open-sse/handlers/chatCore/upstreamTimeouts.ts"
-          - name: h
-            mutate: "open-sse/handlers/chatCore/headers.ts,open-sse/handlers/chatCore/logTruncation.ts,open-sse/handlers/chatCore/memoryExtraction.ts,open-sse/handlers/chatCore/nonStreamingSse.ts,open-sse/handlers/chatCore/passthroughToolNames.ts,open-sse/handlers/chatCore/executorHelpers.ts"
-          - name: i
-            mutate: "open-sse/handlers/chatCore/telemetryHelpers.ts,open-sse/handlers/chatCore/memorySkillsInjection.ts,open-sse/handlers/chatCore/semanticCache.ts"
-    timeout-minutes: 300
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - name: Run Stryker (disableBail)
-        env:
-          BATCH_MUTATE: ${{ matrix.batch.mutate }}
-        run: npx stryker run --config-file stryker.disablebail.json --mutate "$BATCH_MUTATE"
-      - name: Upload mutation report
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: mutation-nobail-${{ matrix.batch.name }}
-          path: reports/mutation/
-          if-no-files-found: warn
-          retention-days: 14

.github/workflows/nightly-compat.yml

@@ -1,126 +0,0 @@
-name: Nightly Node Compat
-
-# Plano mestre testes+CI (Eixo D2, aprovado 2026-07-04): as matrizes de compatibilidade
-# Node 24/26 custavam ~28% de CADA run do CI pesado (2 execuções completas da suíte por
-# sync da release-PR) para pegar uma classe de quebra que raramente nasce num PR típico.
-# Elas rodam aqui 1×/dia contra o tip da release ativa (mesmo alvo do nightly-release-green)
-# e continuam obrigatórias no gate de release via workflow_dispatch do ci.yml se preciso.
-# fail-fast desligado: numa quebra queremos saber TODAS as versões afetadas de uma vez.
-
-on:
-  schedule:
-    - cron: "47 6 * * *" # 06:47 UTC diário — slot distinto dos demais nightlies
-  workflow_dispatch:
-    inputs:
-      branch:
-        description: "Branch to validate (default: highest release/vX.Y.Z)"
-        required: false
-        type: string
-
-permissions:
-  contents: read
-  issues: write
-
-concurrency:
-  group: nightly-compat
-  cancel-in-progress: true
-
-jobs:
-  resolve-branch:
-    name: Resolve active release branch
-    runs-on: ubuntu-latest
-    outputs:
-      target: ${{ steps.branch.outputs.target }}
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-      - name: Resolve active release branch
-        id: branch
-        env:
-          INPUT_BRANCH: ${{ github.event.inputs.branch }}
-        run: |
-          set -euo pipefail
-          if [ -n "${INPUT_BRANCH:-}" ]; then
-            TARGET="$INPUT_BRANCH"
-          else
-            TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
-              | sed 's#origin/##' \
-              | sort -t/ -k2 -V \
-              | tail -1)
-          fi
-          case "$TARGET" in
-            release/v[0-9]*.[0-9]*.[0-9]*) ;;
-            *) echo "Refusing non-canonical branch name: $TARGET"; exit 1 ;;
-          esac
-          echo "target=$TARGET" >> "$GITHUB_OUTPUT"
-
-  compat-build-26:
-    name: Node 26 Compatibility Build
-    runs-on: ubuntu-latest
-    timeout-minutes: 25
-    needs: resolve-branch
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          ref: ${{ needs.resolve-branch.outputs.target }}
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "26"
-          cache: npm
-      - uses: ./.github/actions/npm-ci-retry
-      - run: npm run build
-
-  compat-tests:
-    name: Node ${{ matrix.node }} Compat Tests (${{ matrix.shard }}/4)
-    runs-on: ubuntu-latest
-    timeout-minutes: 25
-    needs: resolve-branch
-    strategy:
-      fail-fast: false
-      matrix:
-        node: [24, 26]
-        shard: [1, 2, 3, 4]
-    env:
-      JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-nightly-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-      TEST_SHARD: ${{ matrix.shard }}/4
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          ref: ${{ needs.resolve-branch.outputs.target }}
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ matrix.node }}
-          cache: npm
-      - uses: ./.github/actions/npm-ci-retry
-      - run: npm run check:node-runtime
-      - run: npm run test:unit:ci:shard
-
-  report:
-    name: Open / update tracking issue on failure
-    runs-on: ubuntu-latest
-    if: ${{ !cancelled() && (needs.compat-tests.result == 'failure' || needs.compat-build-26.result == 'failure') }}
-    needs: [resolve-branch, compat-build-26, compat-tests]
-    permissions:
-      issues: write
-    steps:
-      - name: Open or update issue
-        env:
-          GH_TOKEN: ${{ github.token }}
-          TARGET: ${{ needs.resolve-branch.outputs.target }}
-          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-        run: |
-          set -euo pipefail
-          TITLE="🌙 nightly-compat: Node 24/26 failures on $TARGET"
-          EXISTING=$(gh issue list --repo "$GITHUB_REPOSITORY" --state open --search "$TITLE in:title" --json number --jq '.[0].number')
-          BODY="Nightly Node-compat run failed on \`$TARGET\`: $RUN_URL — triage which Node version/shard broke (fail-fast off, all versions reported)."
-          if [ -n "$EXISTING" ]; then
-            gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body "$BODY"
-          else
-            gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --body "$BODY"
-          fi

.github/workflows/nightly-llm-security.yml

@@ -1,102 +0,0 @@
-name: Nightly LLM Security
-on:
-  schedule:
-    - cron: "53 5 * * *"
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  promptfoo-guard:
-    name: promptfoo — injection guard (block mode, no secret)
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with: { node-version: "24", cache: npm }
-      - run: npm ci
-      - name: Build CLI bundle
-        env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
-        run: npm run build:cli
-      - name: Start OmniRoute (block mode)
-        env:
-          JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
-          PORT: "20128"
-          INJECTION_GUARD_MODE: block
-        run: |
-          node dist/server.js > server.log 2>&1 &
-          echo $! > server.pid
-          for i in $(seq 1 30); do
-            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
-            sleep 2
-          done
-      - name: promptfoo guard-validation
-        run: npx --yes promptfoo@latest eval -c promptfooconfig.yaml --no-cache
-        env:
-          OMNIROUTE_URL: http://localhost:20128
-          OMNIROUTE_API_KEY: not-needed-blocked-before-upstream
-      - name: Stop server
-        if: always()
-        run: kill "$(cat server.pid)" || true
-
-  garak:
-    name: garak probes (skip without provider secret)
-    runs-on: ubuntu-latest
-    # NOTE: the `secrets` context is NOT available in a job-level `if:` — referencing
-    # it there makes GitHub reject the file on push (startup_failure on every push).
-    # Map the secret into a job-level env and gate each step on a presence check, so
-    # the job stays green and simply skips the probes when the secret is absent.
-    env:
-      PROMPTFOO_PROVIDER_KEY: ${{ secrets.PROMPTFOO_PROVIDER_KEY }}
-    steps:
-      - name: Gate on provider secret
-        id: gate
-        run: |
-          if [ -n "$PROMPTFOO_PROVIDER_KEY" ]; then
-            echo "run=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "run=false" >> "$GITHUB_OUTPUT"
-            echo "::notice::PROMPTFOO_PROVIDER_KEY not set — skipping garak probes (advisory)."
-          fi
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-        if: steps.gate.outputs.run == 'true'
-      - uses: actions/setup-node@v6
-        if: steps.gate.outputs.run == 'true'
-        with: { node-version: "24", cache: npm }
-      - run: npm ci
-        if: steps.gate.outputs.run == 'true'
-      - name: Build CLI bundle
-        if: steps.gate.outputs.run == 'true'
-        env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
-        run: npm run build:cli
-      - name: Start OmniRoute
-        if: steps.gate.outputs.run == 'true'
-        env:
-          JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
-          PORT: "20128"
-        run: |
-          node dist/server.js > server.log 2>&1 &
-          echo $! > server.pid
-          for i in $(seq 1 30); do
-            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
-            sleep 2
-          done
-      - uses: actions/setup-python@v6
-        if: steps.gate.outputs.run == 'true'
-        with: { python-version: "3.12" }
-      - run: pip install garak
-        if: steps.gate.outputs.run == 'true'
-      - name: garak limited probes
-        if: steps.gate.outputs.run == 'true'
-        env:
-          OPENAI_API_KEY: ${{ secrets.PROMPTFOO_PROVIDER_KEY }}
-          OPENAI_BASE_URL: http://localhost:20128/v1
-        run: garak --model_type openai --model_name gpt-4o-mini --probes promptinject,dan,leakreplay --report_prefix garak-omniroute || true
-      - name: Stop server
-        if: always() && steps.gate.outputs.run == 'true'
-        run: kill "$(cat server.pid)" || true

.github/workflows/nightly-mutation.yml

@@ -1,163 +0,0 @@
-name: Nightly Mutation
-on:
-  schedule:
-    - cron: "17 3 * * *"
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  stryker:
-    name: Stryker mutation (batch ${{ matrix.batch.name }} — advisory)
-    runs-on: ubuntu-latest
-    # Mutation testing is expensive. History of the budget:
-    #   - Full 8-module set TIMED OUT at the 180min cap (run 27705123780 = exactly 180min).
-    #     The two god-files chatCore.ts/combo.ts dominated ~2/3 of the mutants and were
-    #     removed from stryker.conf.json `mutate`.
-    #   - The remaining 6 modules in 3 batches: auth.ts and accountFallback.ts are large; the
-    #     a (auth+publicCreds) and b (accountFallback+error) batches still ran near the 180min
-    #     cap (the perTest dry-run over ~130 covering test files is itself costly), so the two
-    #     big modules are now ISOLATED into their own batches (a=auth, b=accountFallback).
-    #   - Onda 3 / Fase 9 T5 re-add: combo.ts was split into 11 leaves; the 8 well-covered
-    #     combo/* leaves are back in `mutate` (covered by the 24 combo-*.test.ts), grouped into
-    #     2 batches (d=heavy, e=light). After #4204 (D7b) merged, the reset-aware quota pair
-    #     quotaScoring/quotaStrategies was added as batch f. A covering-test audit then added the
-    #     6 chatCore/* leaves with direct unit coverage as batch g. A follow-up then wrote dedicated
-    #     unit tests for 6 more leaves and added them as batch h. A final follow-up added dedicated
-    #     tests (no mock.module — fetch-override + crafted inputs + temp-DATA_DIR) for telemetryHelpers
-    #     + memorySkillsInjection + semanticCache (its cache-HIT block now has a setCachedResponse
-    #     fixture) as batch i — ALL 15/15 chatCore leaves are now mutated. See
-    #     _mutate_godfiles_excluded_comment in stryker.conf.json.
-    # 9 PARALLEL batches, each overriding the mutate set via `--mutate` (Stryker 9 CLI:
-    # `-m, --mutate <comma-list>`; the conf's `mutate[]` remains the local-run default/union).
-    #   - Cold-seeding budget (per-batch `timeout-minutes: ${{ matrix.batch.timeout || 180 }}`):
-    #     a COLD run must COMPLETE once to write stryker-incremental.json (Stryker writes it only on
-    #     a successful finish); a job cancelled at the cap writes nothing, so the next run is cold
-    #     again — an infinite never-seeds loop. actions/cache is also branch-scoped, so each branch
-    #     (incl. release) must seed its OWN cache via a run with enough headroom. Measured cold runs
-    #     Measured cold totals (run 27801802713, extrapolated from the % at the 180/350 cancel point):
-    #     auth ~375min (2301 mutants — EXCEEDS the 360min job max even isolated), accountFallback
-    #     ~358min (1441), the c security quartet ~348min (1163), d ~197min (1316), g=142, h=132, e=66,
-    #     f=45, i=33. The widely-covered modules blow the budget because the tap-runner re-runs every
-    #     covering test file per mutant (a perTest fixed cost over ~138 test files, times thousands of
-    #     mutants). A flat timeout bump cannot rescue auth (>360min max) — so the three over-budget
-    #     batches are SPLIT so each half fits: auth->a1/a2 and accountFallback->b1/b2 by mutation range
-    #     (`file:startLine-endLine`), the c quartet->c1/c2 by module pair. Splitting also seeds each
-    #     sub-batch's own incremental cache, after which nightlies re-test only changed mutants.
-    # Full coverage every night in parallel; wall-clock = the slowest batch's cold run until seeded.
-    # Runs at stryker concurrency=4 with per-process DATA_DIR isolation
-    # (tests/_setup/isolateDataDir.ts) — see _concurrency_comment in stryker.conf.json.
-    strategy:
-      fail-fast: false
-      matrix:
-        batch:
-          # Per-batch `timeout` (minutes) tiers the cold-seeding budget by measured cost; batches
-          # without the key default to 180. Cold-run profiling (run 27801802713) showed the
-          # widely-covered modules need FAR more than the 180 cap because the tap-runner re-runs every
-          # covering test file per mutant: auth ~375min (2301 mutants, EXCEEDS the 360min GitHub job
-          # max even isolated), accountFallback ~358min, the c security quartet ~348min — none fit a
-          # single job. So auth/accountFallback are split by MUTATION RANGE (`file:startLine-endLine`,
-          # ~half the mutants each) into a1/a2, b1/b2; the c quartet is split by MODULE pair into
-          # c1/c2. d (3 combo modules, ~197min) stays whole. Split-heavy batches get 300min headroom
-          # for their cold seeding run; once each batch completes once and writes
-          # stryker-incremental.json, later runs re-test only changed mutants and finish far faster.
-          # g/h (142/132min cold) keep a 240 buffer; e/f/i (33-66min) keep the 180 default.
-          - name: a1
-            mutate: "src/sse/services/auth.ts:1-1109"
-            timeout: 300
-          - name: a2
-            mutate: "src/sse/services/auth.ts:1110-2218"
-            timeout: 300
-          - name: b1
-            mutate: "open-sse/services/accountFallback.ts:1-863"
-            timeout: 300
-          - name: b2
-            mutate: "open-sse/services/accountFallback.ts:864-1726"
-            timeout: 300
-          - name: c1
-            mutate: "src/server/authz/routeGuard.ts,src/shared/utils/circuitBreaker.ts"
-            timeout: 300
-          - name: c2
-            mutate: "open-sse/utils/error.ts,open-sse/utils/publicCreds.ts"
-            timeout: 300
-          - name: d
-            mutate: "open-sse/services/combo/comboStructure.ts,open-sse/services/combo/autoStrategy.ts,open-sse/services/combo/validateQuality.ts"
-            timeout: 300
-          - name: e
-            mutate: "open-sse/services/combo/shadowRouting.ts,open-sse/services/combo/targetSorters.ts,open-sse/services/combo/comboPredicates.ts,open-sse/services/combo/rrState.ts,open-sse/services/combo/comboData.ts"
-          - name: f
-            mutate: "open-sse/services/combo/quotaScoring.ts,open-sse/services/combo/quotaStrategies.ts"
-          - name: g
-            mutate: "open-sse/handlers/chatCore/comboContextCache.ts,open-sse/handlers/chatCore/idempotency.ts,open-sse/handlers/chatCore/passthroughHelpers.ts,open-sse/handlers/chatCore/responseHeaders.ts,open-sse/handlers/chatCore/sanitization.ts,open-sse/handlers/chatCore/upstreamTimeouts.ts"
-            timeout: 240
-          - name: h
-            mutate: "open-sse/handlers/chatCore/headers.ts,open-sse/handlers/chatCore/logTruncation.ts,open-sse/handlers/chatCore/memoryExtraction.ts,open-sse/handlers/chatCore/nonStreamingSse.ts,open-sse/handlers/chatCore/passthroughToolNames.ts,open-sse/handlers/chatCore/executorHelpers.ts"
-            timeout: 240
-          - name: i
-            mutate: "open-sse/handlers/chatCore/telemetryHelpers.ts,open-sse/handlers/chatCore/memorySkillsInjection.ts,open-sse/handlers/chatCore/semanticCache.ts"
-    # Per-batch budget: split-heavy batches (a1/a2/b1/b2/c1/c2/d) override to 300min, g/h to 240min;
-    # the rest default to 180min. `matrix.batch.timeout` is null for batches without the key -> `|| 180`.
-    # NOTE: a1+a2 both mutate auth.ts (disjoint line ranges) and b1+b2 both mutate accountFallback.ts;
-    # when merging the per-batch mutation.json for radiography/scores, same-file mutants from sibling
-    # ranges must be UNIONED (scripts/check/check-mutation-ratchet.mjs::measureMutationScores and
-    # scripts/quality/mutation-radiography.mjs both merge per file).
-    timeout-minutes: ${{ matrix.batch.timeout || 180 }}
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - name: Restore Stryker incremental cache
-        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-        with:
-          path: reports/mutation/stryker-incremental.json
-          key: stryker-incremental-${{ matrix.batch.name }}-${{ github.run_id }}
-          restore-keys: stryker-incremental-${{ matrix.batch.name }}-
-      - name: Run Stryker (advisory)
-        id: stryker
-        continue-on-error: true
-        env:
-          BATCH_MUTATE: ${{ matrix.batch.mutate }}
-        run: npx stryker run --mutate "$BATCH_MUTATE"
-      - name: Upload mutation report
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: mutation-report-${{ matrix.batch.name }}
-          path: reports/mutation/
-          if-no-files-found: warn
-          retention-days: 14
-
-  # Aggregation gate (T3): each split batch emits a PARTIAL view of a mutated file
-  # (auth.ts lives in a1+a2, accountFallback in b1+b2), so a PER-BATCH ratchet would
-  # only ever see half a file vs the whole-file baseline. This job runs AFTER every
-  # batch, downloads all reports, and ratchets the MERGED per-module scores
-  # (check-mutation-ratchet UNIONS same-file mutants across reports) against the
-  # dedicatedGate `mutationScore.*` floors in quality-baseline.json (seeded ~2pt below
-  # the first full measurement). Blocking: a module dropping below its floor fails the
-  # run. Missing reports (e.g. an artifact-upload flake) are skipped, never failed.
-  mutation-ratchet:
-    name: Mutation score ratchet (blocking)
-    needs: stryker
-    if: always()
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-      - name: Download all mutation reports
-        uses: actions/download-artifact@v8
-        with:
-          pattern: mutation-report-*
-          path: reports/all
-      - name: Ratchet merged per-module mutation scores
-        run: node scripts/check/check-mutation-ratchet.mjs reports/all/*/mutation.json --ratchet

.github/workflows/nightly-property.yml

@@ -1,35 +0,0 @@
-name: Nightly Property Discovery
-on:
-  schedule:
-    - cron: "0 6 * * *"
-  workflow_dispatch:
-permissions:
-  contents: read
-  issues: write
-jobs:
-  property-random-seed:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - name: fast-check random seed (high runs)
-        id: prop
-        run: FC_SEED=random FC_NUM_RUNS=2000 npm run test:property
-      - name: Open issue on failure
-        if: failure()
-        uses: actions/github-script@v9
-        with:
-          script: |
-            await github.rest.issues.create({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              title: "Nightly property-test failure (Fase 8 B)",
-              body: "fast-check found a counterexample with a random seed. Check the run logs for the reproducible seed + minimal case, then add it as a fixture.\n\nRun: " + context.serverUrl + "/" + context.repo.owner + "/" + context.repo.repo + "/actions/runs/" + context.runId,
-              labels: ["quality-gate-finding"],
-            });

.github/workflows/nightly-release-green.yml

@@ -1,303 +0,0 @@
-name: Release-Green (continuous)
-
-# Solution D — continuous, NON-BLOCKING drift signal for the active release branch.
-#
-# WHY: the full gate (ci.yml) only runs on the release PR (PR → main), so reds
-# accrue silently on release/** and explode — in layers — at release time. This
-# workflow reproduces the release-equivalent validation on the release branch and,
-# when there are HARD failures, opens/updates a single tracking issue.
-#
-# WS5.1 (v3.8.49 quality plan) — two modes:
-#   push to release/v* (code paths) → --quick (fast HARD gates, ~5-8min). Catches the
-#     captain's direct pushes (sync-back — the one ungated write path) AND the merged
-#     COMBINATION right after every PR merge, attributing the offending push range in
-#     the issue. Base-red MTTD drops from ≤24h to ≤~15min after the offending push.
-#   schedule (3×/day) → full --with-build --full-ci (the deep sweep incl. build+suites).
-#
-# It is NOT a required status check and never touches a contributor PR — it only
-# reports. Ratchet drift (eslint warnings / cognitive-complexity / file-size) is
-# expected mid-cycle and is reported but never raises the alarm on its own; only
-# real defects (typecheck / lint errors / unit / vitest / db-rules / public-creds /
-# package-artifact) flip the issue open.
-
-on:
-  push:
-    branches: ["release/v*", "main"]
-    paths:
-      - "src/**"
-      - "open-sse/**"
-      - "bin/**"
-      - "electron/**"
-      - "scripts/**"
-      - "tests/**"
-      - "config/**"
-      - "package.json"
-      - "package-lock.json"
-      - "tsconfig*.json"
-  schedule:
-    - cron: "23 5 * * *" # full sweep — off-peak, distinct from other nightlies
-    - cron: "23 12 * * *" # full sweep — midday (WS5.1: 3×/day instead of 1×)
-    - cron: "23 18 * * *" # full sweep — evening
-  workflow_dispatch:
-    inputs:
-      branch:
-        description: "Release branch to validate (default: highest release/vX.Y.Z)"
-        required: false
-        type: string
-
-permissions:
-  contents: read
-  issues: write
-
-concurrency:
-  # push storms during merge campaigns collapse to the newest commit per branch;
-  # scheduled full sweeps keep their own single lane.
-  group: release-green-${{ github.event_name }}-${{ github.ref }}
-  cancel-in-progress: true
-
-env:
-  OMNIROUTE_SKIP_SYSTEM_TRUST: "1"
-
-jobs:
-  release-green:
-    name: Validate active release branch
-    # On a push, only run for release/* pushes — a push to main is handled by the
-    # main-green job below. Schedule/dispatch always run (they validate the highest release).
-    if: ${{ github.event_name != 'push' || startsWith(github.ref_name, 'release/') }}
-    # Dynamic runner: with USE_VPS_RUNNER=true (release window / on-demand pre-flight)
-    # this runs on the dedicated VPS runner — clean env (no operator OMNIROUTE_API_KEY,
-    # no local noauth CLIs => zero machine-specific false positives) and no contention.
-    # Nightly cron normally finds the var false (VM off) and falls back to hosted.
-    runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
-    env:
-      JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-nightly-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-
-      - name: Resolve active release branch
-        id: branch
-        env:
-          INPUT_BRANCH: ${{ github.event.inputs.branch }}
-          EVENT_NAME: ${{ github.event_name }}
-          PUSHED_REF: ${{ github.ref_name }}
-        run: |
-          set -euo pipefail
-          if [ -n "${INPUT_BRANCH:-}" ]; then
-            TARGET="$INPUT_BRANCH"
-          elif [ "$EVENT_NAME" = "push" ]; then
-            # validate exactly what was pushed, not the highest branch
-            TARGET="$PUSHED_REF"
-          else
-            # highest release/vX.Y.Z by semver among remote branches
-            TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
-              | sed 's#origin/##' \
-              | sort -t/ -k2 -V \
-              | tail -1)
-          fi
-          if [ -z "$TARGET" ]; then echo "No release/v* branch found"; exit 1; fi
-          # Strict format guard — reject anything that isn't release/vX.Y.Z (blocks
-          # ref/command injection via the workflow_dispatch input).
-          if ! printf '%s' "$TARGET" | grep -qE '^release/v[0-9]+\.[0-9]+\.[0-9]+$'; then
-            echo "Refusing non-canonical branch name: $TARGET"; exit 1
-          fi
-          echo "target=$TARGET" >> "$GITHUB_OUTPUT"
-          echo "Active release branch: $TARGET"
-
-      - name: Checkout the release branch
-        env:
-          TARGET: ${{ steps.branch.outputs.target }}
-        run: |
-          set -euo pipefail
-          git checkout "$TARGET"
-          git log -1 --oneline
-
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-
-      - uses: ./.github/actions/npm-ci-retry
-
-      - name: Release-green validation (full)
-        id: validate
-        env:
-          EVENT_NAME: ${{ github.event_name }}
-        run: |
-          set +e
-          # --hermetic: scrub live-test trigger vars (self-hosted runner may carry
-          # operator env; hosted ignores the unknown flag before #6300 lands).
-          # push → --quick: fast HARD gates only (~5-8min), per-merge signal.
-          # schedule/dispatch → --with-build --full-ci: ALSO run every static gate from
-          # ci.yml's gate jobs (lint, quality-gate, quality-extended, docs-sync-strict,
-          # pr-test-policy) + build + full suites. PRs into release/** only get the
-          # fast-gates, so these accrue silently and explode in layers on the release PR
-          # (v3.8.46: 11 static base-reds leaked).
-          if [ "$EVENT_NAME" = "push" ]; then
-            MODE="--quick"
-          else
-            MODE="--with-build --full-ci"
-          fi
-          echo "[release-green] mode: $MODE (event: $EVENT_NAME)"
-          # shellcheck disable=SC2086 — MODE is an intentional flag list
-          node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
-            1> release-green.json 2> release-green.log
-          echo "exit=$?" >> "$GITHUB_OUTPUT"
-          echo "------- report -------"
-          cat release-green.log
-
-      - name: Open / update tracking issue on HARD failure
-        if: steps.validate.outputs.exit != '0'
-        env:
-          GH_TOKEN: ${{ github.token }}
-          TARGET: ${{ steps.branch.outputs.target }}
-          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-          EVENT_NAME: ${{ github.event_name }}
-          BEFORE_SHA: ${{ github.event.before }}
-          AFTER_SHA: ${{ github.event.after }}
-        run: |
-          set -euo pipefail
-          TITLE="🔴 Release branch not green: ${TARGET}"
-          {
-            echo "The **release-green** validation found HARD failures on \`${TARGET}\`."
-            echo "These are real defects that would block the release PR — fix them in the"
-            echo "originating PR branch (via co-authorship), not by demanding it from contributors."
-            echo ""
-            echo "**Run:** ${RUN_URL} (mode: ${EVENT_NAME})"
-            # WS5.1 attribution: on push events the offending change IS this push's range
-            # (one merge per push in the normal queue), so name it — no bisect needed.
-            if [ "$EVENT_NAME" = "push" ] && [ -n "${BEFORE_SHA:-}" ] && \
-               git cat-file -e "$BEFORE_SHA" 2>/dev/null; then
-              echo ""
-              echo "**Offending push range** (\`${BEFORE_SHA:0:9}..${AFTER_SHA:0:9}\`):"
-              echo '```'
-              git log --no-decorate --oneline "${BEFORE_SHA}..${AFTER_SHA}" | head -20
-              echo '```'
-            fi
-            echo ""
-            echo '```'
-            sed -n '/──────── verdict ────────/,$p' release-green.log || tail -40 release-green.log
-            echo '```'
-            echo ""
-            echo "_Ratchet drift (eslint warnings / cognitive-complexity / file-size) listed above is expected mid-cycle and is rebaselined at release — it is NOT a contributor concern and did not, on its own, open this issue._"
-          } > issue-body.md
-
-          EXISTING=$(gh issue list --repo "$GITHUB_REPOSITORY" --state open \
-            --search "in:title $TITLE" --json number --jq '.[0].number' 2>/dev/null || echo "")
-          if [ -n "$EXISTING" ]; then
-            gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file issue-body.md
-            echo "Updated existing issue #$EXISTING"
-          else
-            gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --body-file issue-body.md
-          fi
-
-      - name: Upload report artifact
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: release-green-report
-          path: |
-            release-green.json
-            release-green.log
-          if-no-files-found: ignore
-
-  # Companion arm for `main`. Under the parallel-cycle model, main only receives merged
-  # work at the release squash — so a gate/infra fix that lands only on release leaves
-  # main red the whole cycle, and repo-wide gates (CodeQL alert count, ratchet baselines)
-  # turn EVERY PR into main red on a check unrelated to its diff. This detects that and
-  # opens a "🔴 main not green" tracking issue. The PREVENTION is the companion-PR reflex
-  # (Hard Rule #21 area / _shared/merge-gates.md §8); this is the automated backstop.
-  main-green:
-    name: Validate main branch
-    # On a push, only run for a push to main — a push to release/* is handled by
-    # release-green above. Schedule/dispatch always run (they also sweep main).
-    if: ${{ github.event_name != 'push' || github.ref_name == 'main' }}
-    runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
-    env:
-      JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-nightly-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          ref: main # literal — no injection surface; scheduled runs default to the repo default branch (a release/v*), so pin main explicitly
-          fetch-depth: 0
-          persist-credentials: false
-
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-
-      - uses: ./.github/actions/npm-ci-retry
-
-      - name: Main-green validation
-        id: validate
-        env:
-          EVENT_NAME: ${{ github.event_name }}
-        run: |
-          set +e
-          # push (a merge into main) → --quick fast HARD gates; schedule/dispatch → full sweep.
-          if [ "$EVENT_NAME" = "push" ]; then
-            MODE="--quick"
-          else
-            MODE="--with-build --full-ci"
-          fi
-          echo "[main-green] mode: $MODE (event: $EVENT_NAME)"
-          # shellcheck disable=SC2086 — MODE is an intentional flag list
-          node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
-            1> main-green.json 2> main-green.log
-          echo "exit=$?" >> "$GITHUB_OUTPUT"
-          echo "------- report -------"
-          cat main-green.log
-
-      - name: Open / update tracking issue on HARD failure
-        if: steps.validate.outputs.exit != '0'
-        env:
-          GH_TOKEN: ${{ github.token }}
-          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-          EVENT_NAME: ${{ github.event_name }}
-        run: |
-          set -euo pipefail
-          TITLE="🔴 main branch not green"
-          {
-            echo "The **main-green** validation found HARD failures on \`main\`."
-            echo ""
-            echo "Because \`main\` only receives merged work at the release squash, a gate/infra"
-            echo "fix that landed only on the release branch leaves \`main\` broken for the whole"
-            echo "cycle — and repo-wide gates (CodeQL alert count, ratchet baselines) then turn"
-            echo "**every open PR into main** red on a check unrelated to its diff. The fix is a"
-            echo "companion PR \`--base main\` carrying the release-side fix (see"
-            echo "\`_shared/merge-gates.md\` §8), NOT chasing each contributor PR."
-            echo ""
-            echo "**Run:** ${RUN_URL} (mode: ${EVENT_NAME})"
-            echo ""
-            echo '```'
-            sed -n '/──────── verdict ────────/,$p' main-green.log || tail -40 main-green.log
-            echo '```'
-            echo ""
-            echo "_Ratchet drift (eslint warnings / cognitive-complexity / file-size) is expected mid-cycle and did NOT, on its own, open this issue._"
-          } > issue-body.md
-
-          EXISTING=$(gh issue list --repo "$GITHUB_REPOSITORY" --state open \
-            --search "in:title $TITLE" --json number --jq '.[0].number' 2>/dev/null || echo "")
-          if [ -n "$EXISTING" ]; then
-            gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file issue-body.md
-            echo "Updated existing issue #$EXISTING"
-          else
-            gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --body-file issue-body.md
-          fi
-
-      - name: Upload report artifact
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: main-green-report
-          path: |
-            main-green.json
-            main-green.log
-          if-no-files-found: ignore

.github/workflows/nightly-resilience.yml

@@ -1,110 +0,0 @@
-name: Nightly Resilience
-on:
-  schedule:
-    - cron: "41 4 * * *"
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  heap:
-    name: Heap-growth gate
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - run: npm run test:heap
-
-  chaos:
-    name: Resilience chaos (fault injection)
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - run: npm run test:chaos
-
-  k6-soak:
-    name: k6 load/soak
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - name: Build CLI bundle
-        env:
-          JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
-        run: npm run build:cli
-      - name: Start OmniRoute (background)
-        env:
-          JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
-          PORT: "20128"
-        run: |
-          node dist/server.js > server.log 2>&1 &
-          echo $! > server.pid
-          for i in $(seq 1 30); do
-            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo "server up"; break; fi
-            sleep 2
-          done
-      - name: Install k6
-        uses: grafana/setup-k6-action@v1
-      - name: Run k6 soak
-        run: k6 run tests/load/k6-soak.js
-        env:
-          BASE_URL: http://localhost:20128
-          SOAK_DURATION: "3m"
-          SOAK_VUS: "10"
-      - name: Stop server
-        if: always()
-        run: kill "$(cat server.pid)" || true
-
-  a11y:
-    name: A11y axe (nightly, freeze-and-alert)
-    runs-on: ubuntu-latest
-    # The Playwright webServer (`start` mode) builds Next via build-next-isolated.mjs and
-    # boots the standalone server itself (waits on /api/monitoring/health, 15min webServer
-    # timeout). Unlike the per-PR test-e2e job, this nightly job has no pre-built artifact,
-    # so it self-builds — hence the generous job timeout. REQUIRE_AXE=1 makes the suite run
-    # the real axe analysis (the 4 page tests are gated to nightly so per-PR e2e stays fast)
-    # and makes the meta-test fail loudly if @axe-core/playwright ever goes missing.
-    timeout-minutes: 30
-    env:
-      JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-test-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-      REQUIRE_AXE: "1"
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-          cache: npm
-      - run: npm ci
-      - name: Cache Playwright browsers
-        uses: actions/cache@v6.1.0
-        with:
-          path: ~/.cache/ms-playwright
-          key: playwright-chromium-${{ runner.os }}-${{ hashFiles('package-lock.json') }}
-          restore-keys: playwright-chromium-${{ runner.os }}-
-      - run: npx playwright install --with-deps chromium
-      - name: Run axe a11y suite (self-building webServer)
-        run: npx playwright test tests/e2e/a11y.spec.ts

.github/workflows/nightly-schemathesis.yml

@@ -1,72 +0,0 @@
-name: Nightly Schemathesis
-on:
-  schedule:
-    - cron: "23 4 * * *"
-  workflow_dispatch:
-
-permissions:
-  contents: read
-
-jobs:
-  schemathesis:
-    name: Schemathesis — OpenAPI contract fuzz (advisory)
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with: { node-version: "24", cache: npm }
-      - run: npm ci
-      - name: Build CLI bundle
-        env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
-        run: npm run build:cli
-      - name: Start OmniRoute (background)
-        env:
-          JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
-          PORT: "20128"
-        run: |
-          node dist/server.js > server.log 2>&1 &
-          echo $! > server.pid
-          for i in $(seq 1 30); do
-            if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo "server up"; break; fi
-            sleep 2
-          done
-      - uses: actions/setup-python@v6
-        with: { python-version: "3.12" }
-      - name: Install schemathesis
-        run: pip install schemathesis
-      - name: Schemathesis contract fuzz (advisory)
-        # Advisory gate: never fails the job. `continue-on-error` covers a crash of the
-        # step itself; `|| true` covers schemathesis exiting non-zero when it finds spec
-        # violations / upstream 500s — both are expected here (most /v1 endpoints proxy an
-        # upstream that has no provider configured in CI). The point of the nightly is to
-        # PROVE the contract is fuzzable and surface regressions, not to gate the build.
-        continue-on-error: true
-        run: |
-          schemathesis run docs/openapi.yaml \
-            --url http://localhost:20128 \
-            --max-examples 20 \
-            --workers 4 \
-            --checks all \
-            --max-response-time 30 \
-            --request-timeout 30 \
-            --suppress-health-check all \
-            --report junit \
-            --report-junit-path schemathesis-report/junit.xml \
-            --no-color \
-            || true
-      - name: Stop server
-        if: always()
-        run: kill "$(cat server.pid)" || true
-      - name: Upload schemathesis report
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: schemathesis-report
-          path: |
-            schemathesis-report/
-            server.log
-          if-no-files-found: warn
-          retention-days: 14

.github/workflows/npm-publish.yml

@@ -22,14 +22,6 @@ on:
           - latest
           - next
           - historic
-      publish_mode:
-        description: "staged = npm stage publish (owner approves with 2FA after the staged boot-verify); direct = legacy immediate publish (emergency fallback only)"
-        required: false
-        default: "staged"
-        type: choice
-        options:
-          - staged
-          - direct
   workflow_call:
     inputs:
       version:
@@ -45,11 +37,10 @@ on:
       NPM_TOKEN:
         required: true
 
-# Least-privilege default: read-only at the top level; each publish job grants the
-# id-token (npm provenance) / packages (GitHub Packages) writes it needs (Scorecard
-# TokenPermissions).
 permissions:
   contents: read
+  id-token: write
+  packages: write
 
 env:
   NPM_PUBLISH_NODE_VERSION: "24"
@@ -57,15 +48,10 @@ env:
 jobs:
   publish:
     runs-on: ubuntu-latest
-    permissions:
-      contents: write # gh release upload (attach SBOM to the GitHub Release)
-      id-token: write # npm provenance
-      packages: write # publish to npm.pkg.github.com
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
-          persist-credentials: false
           # Need full tag history to compare against highest semver when
           # deciding whether this release should claim dist-tag `latest`.
           fetch-depth: 0
@@ -155,53 +141,8 @@ jobs:
         if: steps.resolve.outputs.skip != 'true'
         run: npm run check:pack-artifact
 
-      - name: Generate CycloneDX SBOM (npm)
+      - name: Publish to npm
         if: steps.resolve.outputs.skip != 'true'
-        run: npx @cyclonedx/cyclonedx-npm --ignore-npm-errors --output-format JSON --output-file sbom-npm.cdx.json
-
-      - name: Upload SBOM (npm) as workflow artifact
-        if: steps.resolve.outputs.skip != 'true'
-        uses: actions/upload-artifact@v7
-        with:
-          name: sbom-npm
-          path: sbom-npm.cdx.json
-          if-no-files-found: error
-
-      - name: Attach SBOM to GitHub Release
-        if: steps.resolve.outputs.skip != 'true' && github.event_name == 'release'
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          TAG: ${{ github.ref_name }}
-        run: gh release upload "$TAG" sbom-npm.cdx.json --clobber
-
-      # WS1.2/WS1.3 (#7065 class): the artifact that is about to be published must
-      # BOOT. build:cli already assembled dist/ above; this packs+installs+boots the
-      # real tarball and fails the publish before anything reaches the registry.
-      - name: Boot-smoke the tarball before ANY publish
-        if: steps.resolve.outputs.skip != 'true'
-        run: npm run check:pack-boot
-
-      # WS1.3 (D2, v3.8.49 plan): STAGED publishing by default — `npm stage publish`
-      # parks the exact bytes on the registry WITHOUT making them installable; the
-      # owner then verifies and approves with 2FA (`npm stage approve`), moving the
-      # human gate to AFTER the proof instead of before it. Requires npm >= 11.15
-      # (staged publishing GA 2026-05-22). publish_mode=direct is the emergency
-      # fallback (legacy immediate publish) via workflow_dispatch.
-      - name: Ensure npm supports staged publishing
-        if: steps.resolve.outputs.skip != 'true' && (github.event_name != 'workflow_dispatch' || inputs.publish_mode != 'direct')
-        run: |
-          set -euo pipefail
-          CUR=$(npm --version)
-          if ! node -e "const [a,b]='$(npm --version)'.split('.').map(Number); process.exit(a>11||(a===11&&b>=15)?0:1)"; then
-            # Pinned exact version (supply-chain: never float @latest in the publish
-            # job); bump deliberately when a newer npm is required.
-            echo "npm $CUR < 11.15 — installing pinned npm 11.15.0 for staged publishing"
-            npm install -g --ignore-scripts npm@11.15.0
-          fi
-          npm --version
-
-      - name: Publish to npm (staged — owner approves with 2FA)
-        if: steps.resolve.outputs.skip != 'true' && (github.event_name != 'workflow_dispatch' || inputs.publish_mode != 'direct')
         env:
           VERSION: ${{ steps.resolve.outputs.version }}
           TAG: ${{ steps.resolve.outputs.tag }}
@@ -209,32 +150,10 @@ jobs:
         run: |
           set -euo pipefail
           # Always pass --tag explicitly. Defense in depth: even if VERSION is
-          # accidentally an older release, the historic tag will NOT claim `@latest`.
-          npm stage publish --provenance --access public --tag "$TAG"
-          {
-            echo "## 📦 omniroute@$VERSION STAGED (not yet installable)"
-            echo ""
-            echo "The exact bytes are parked on the registry. To release them:"
-            echo '```'
-            echo "npm stage list omniroute            # find the stage id"
-            echo "npm stage approve <id>              # owner 2FA — THE publish"
-            echo '```'
-            echo "To verify the staged bytes first: npm stage download <id> → run"
-            echo "scripts/check/check-pack-boot.mjs against them (see RELEASE_CHECKLIST)."
-            echo "To discard: npm stage reject <id>."
-          } >> "$GITHUB_STEP_SUMMARY"
-          echo "✅ Staged omniroute@$VERSION (dist-tag=$TAG) — awaiting owner 'npm stage approve'"
-
-      - name: Publish to npm (DIRECT — emergency fallback)
-        if: steps.resolve.outputs.skip != 'true' && github.event_name == 'workflow_dispatch' && inputs.publish_mode == 'direct'
-        env:
-          VERSION: ${{ steps.resolve.outputs.version }}
-          TAG: ${{ steps.resolve.outputs.tag }}
-          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
-        run: |
-          set -euo pipefail
-          npm publish --provenance --access public --tag "$TAG"
-          echo "✅ Published omniroute@$VERSION (dist-tag=$TAG) [DIRECT mode]"
+          # accidentally an older release, `npm publish --tag historic` will
+          # NOT promote it to `@latest`.
+          npm publish --access public --tag "$TAG"
+          echo "✅ Published omniroute@$VERSION (dist-tag=$TAG)"
 
       - name: Publish to GitHub Packages
         if: steps.resolve.outputs.skip != 'true'
@@ -253,16 +172,9 @@ jobs:
 
   publish-opencode-plugin:
     runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      id-token: write # npm provenance
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-          # Full history needed for auto-bump: git diff against previous release tag
+        uses: actions/checkout@v6
 
       - name: Setup Node.js
         uses: actions/setup-node@v6
@@ -270,47 +182,6 @@ jobs:
           node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
           registry-url: https://registry.npmjs.org
 
-      - name: Auto-bump plugin version if plugin changed since last release
-        id: bump
-        working-directory: "@omniroute/opencode-plugin"
-        env:
-          CURRENT_TAG: ${{ github.ref_name }}
-        run: |
-          set -euo pipefail
-
-          PKG_VERSION=$(node -p "require('./package.json').version")
-          PKG_NAME=$(node -p "require('./package.json').name")
-
-          # 1) Skip if current version is not yet published (no bump needed)
-          PUBLISHED="$(npm view "${PKG_NAME}@${PKG_VERSION}" version 2>/dev/null || true)"
-          if [ "$PUBLISHED" != "$PKG_VERSION" ]; then
-            echo "✅ ${PKG_NAME}@${PKG_VERSION} is new — no bump needed."
-            echo "bumped=false" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # 2) Find the previous release tag (exclude the current one)
-          PREV_TAG=$(git tag -l 'v*' --sort=-version:refname \
-            | grep -v "^${CURRENT_TAG}$" | head -1 || echo "")
-          if [ -z "$PREV_TAG" ]; then
-            echo "No previous tag to compare — skipping bump."
-            echo "bumped=false" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # 3) Check if plugin dir actually changed since that tag
-          if git diff --quiet "$PREV_TAG" -- "@omniroute/opencode-plugin/"; then
-            echo "⏭️ No plugin changes since $PREV_TAG — nothing to publish."
-            echo "bumped=false" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # 4) Auto-bump patch version
-          npm version patch --no-git-tag-version --allow-same-version
-          NEW_VERSION=$(node -p "require('./package.json').version")
-          echo "bumped=true" >> "$GITHUB_OUTPUT"
-          echo "📦 Auto-bumped ${PKG_NAME} from ${PKG_VERSION} to ${NEW_VERSION}"
-
       - name: Install plugin dependencies
         working-directory: "@omniroute/opencode-plugin"
         run: npm install --no-audit --no-fund
@@ -337,5 +208,5 @@ jobs:
             echo "⚠️ ${PKG_NAME}@${PKG_VERSION} is already published on npm — skipping."
             exit 0
           fi
-          npm publish --provenance --access public --ignore-scripts
+          npm publish --access public --ignore-scripts
           echo "✅ Published ${PKG_NAME}@${PKG_VERSION}"

.github/workflows/opencode-plugin-ci.yml

@@ -32,9 +32,7 @@ jobs:
       matrix:
         node: ["22", "24"]
     steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
+      - uses: actions/checkout@v4
       - uses: actions/setup-node@v6
         with:
           node-version: ${{ matrix.node }}
@@ -49,9 +47,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: test
     steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
+      - uses: actions/checkout@v4
       - uses: actions/setup-node@v6
         with:
           node-version: "22"

.github/workflows/opencode-provider-ci.yml

@@ -32,9 +32,7 @@ jobs:
       matrix:
         node: ["20", "22", "24"]
     steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
+      - uses: actions/checkout@v4
       - uses: actions/setup-node@v6
         with:
           node-version: ${{ matrix.node }}
@@ -48,9 +46,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: test
     steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
+      - uses: actions/checkout@v4
       - uses: actions/setup-node@v6
         with:
           node-version: "20"

.github/workflows/quality.yml

@@ -1,354 +0,0 @@
-name: Quality Gates
-
-on:
-  pull_request:
-    branches: ["release/**"]
-    types: [opened, synchronize, reopened, ready_for_review]
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-permissions:
-  contents: read
-
-env:
-  # CI must never mutate the runner's OS trust store (2026-07-05: a cert-flow
-  # test installed a fake PEM on a persistent self-hosted runner and broke all
-  # system TLS). Belt-and-suspenders with tests/_setup/isolateDataDir.ts.
-  OMNIROUTE_SKIP_SYSTEM_TRUST: "1"
-  CI_NODE_VERSION: "24"
-
-jobs:
-  # Same classifier as ci.yml (scripts/quality/classify-pr-changes.mjs) so PR→release
-  # path filters share existence reasons: code / docs / i18n / workflow.
-  changes:
-    name: Change Classification
-    runs-on: ubuntu-latest
-    outputs:
-      code: ${{ steps.classify.outputs.code }}
-      docs: ${{ steps.classify.outputs.docs }}
-      i18n: ${{ steps.classify.outputs.i18n }}
-      workflow: ${{ steps.classify.outputs.workflow }}
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-      - id: classify
-        env:
-          EVENT_NAME: ${{ github.event_name }}
-          BASE_SHA: ${{ github.event.pull_request.base.sha }}
-          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
-        run: |
-          if [ "$EVENT_NAME" != "pull_request" ]; then
-            {
-              echo "code=true"
-              echo "docs=true"
-              echo "i18n=true"
-              echo "workflow=true"
-            } >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-          git diff --name-only "$BASE_SHA" "$HEAD_SHA" > changed-files.txt
-          node scripts/quality/classify-pr-changes.mjs changed-files.txt >> "$GITHUB_OUTPUT"
-
-  # Docs/OpenAPI contract gates only — existence reason is doc accuracy + route refs.
-  # Split out of fast-gates so pure-docs PRs skip typecheck/unit while still validating docs.
-  docs-gates:
-    name: Docs Gates (fast-path)
-    needs: changes
-    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && (needs.changes.outputs.docs == 'true' || needs.changes.outputs.code == 'true')) }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - run: npm ci
-      # One walk of src/app/api for openapi-routes + docs-symbols (both still fail independently).
-      - run: npm run check:api-docs-refs
-      - name: Docs accuracy (fabricated-docs + i18n mirrors, strict)
-        run: npm run check:docs-all
-
-  fast-gates:
-    name: Fast Quality Gates
-    needs: changes
-    # Code surface only — pure docs/i18n PRs skip this bag (docs-gates covers docs).
-    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
-    # Dynamic runner (same rule as ci.yml): use the self-hosted VPS pool only when the
-    # release captain has USE_VPS_RUNNER=true AND this is not a fork PR (own-origin
-    # branches only — a fork PR must never execute on the LAN runner). Var unset/false
-    # or a fork PR falls back to ubuntu-latest, so this is inert until the flag flips.
-    runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
-    # tsx gates (known-symbols, route-guard-membership) import modules that open
-    # SQLite on load; provide DB env so a fresh CI DB initializes cleanly.
-    env:
-      JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-lint-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - run: npm ci
-      - name: Restore ESLint file cache
-        uses: actions/cache@v6
-        with:
-          path: |
-            .eslintcache
-            .eslintcache-complexity
-          key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
-          restore-keys: |
-            eslint-${{ runner.os }}-
-      - run: npm run check:provider-consistency
-      - run: npm run check:fetch-targets
-      # docs-all / openapi-routes / docs-symbols live in docs-gates (path-filtered).
-      - run: npm run check:deps
-      - run: npm run check:file-size
-      - run: npm run check:error-helper
-      - run: npm run check:migration-numbering
-      - run: npm run check:public-creds
-      - run: npm run check:db-rules
-      - run: npm run check:known-symbols
-      - run: npm run check:route-guard-membership
-      - run: npm run check:test-discovery
-      - run: npm run check:test-runner-api
-      # Guards tap.testFiles drift: a covering unit test absent from stryker.conf.json
-      # tap.testFiles makes its module's mutants survive on a cold nightly-mutation run,
-      # false-failing the blocking mutationScore ratchet. See check-mutation-test-coverage.mjs.
-      - run: npm run check:mutation-test-coverage
-      - run: npm run check:any-budget:t11
-      # Build-scope guard: fails if worktrees/cruft leak into the tsconfig include
-      # scope (would OOM `next build`). Instant. See incident 2026-06-25 / #5031.
-      - run: npm run check:build-scope
-      # Pack-policy (unexpected-files allowlist) WITHOUT a build — catches a stray file
-      # leaking into the npm tarball (v3.8.36: 6 ops bin/*.sh) per-PR instead of only on
-      # the release PR's heavy Package Artifact job.
-      - run: npm run check:pack-policy
-      # Complexity + cognitive-complexity: ONE ESLint walk (both baselines still
-      # enforced separately by ruleId). Avoids two cold tree walks on fast-path.
-      - run: npm run check:complexity-ratchets
-      - name: Typecheck (core)
-        run: npm run typecheck:core
-      # #7033: dashboard-scoped typecheck gate — src/app/(dashboard) TSX is not
-      # covered by typecheck:core's curated allowlist. See check-dashboard-typecheck.mjs.
-      - name: Typecheck (dashboard)
-        run: npm run check:dashboard-typecheck
-      # WS4.2 (v3.8.49 plan): TypeScript 7 native-compiler SHADOW — advisory only.
-      # TS7 went GA 2026-07-08 with 8-12x type-check speedups; its Compiler API only
-      # arrives in 7.1, so typescript-eslint / type-coverage / Stryker stay on 6.x
-      # (the hybrid is the officially documented pattern). Isolated npx on purpose:
-      # installing an alias package could collide node_modules/.bin/tsc with 6.x.
-      # Promote to the blocking gate after ~1 week of parity with the step above.
-      - name: Typecheck (core) — TS7 native shadow (advisory)
-        continue-on-error: true
-        run: |
-          RC=0
-          START=$(date +%s)
-          npx -y -p typescript@7 tsc --pretty false -p tsconfig.typecheck-core.json || RC=$?
-          echo "[ts7-shadow] exit=$RC elapsed=$(( $(date +%s) - START ))s — the 6.x step above stays authoritative"
-          exit $RC
-      # TIA: build the impact map at runtime (gitignored, ~21MB) and run only the
-      # unit tests impacted by this PR's changed files. On hub/unmapped changes the
-      # selector returns __RUN_ALL__ — full-suite authority is the parallel
-      # `fast-unit` 4-shard job (test:unit:ci:shard; was 2-shard, #6781), NOT an
-      # unsharded re-run here. Stacking unsharded test:unit:ci on top of fast-unit
-      # doubled wall time (~16 min extra on ubuntu-latest) without extra coverage.
-      #
-      # BLOCKING for the *impacted subset* (flipped 2026-06-17). Fail-safe full
-      # coverage remains required via `Unit Tests fast-path` (fast-unit).
-      - name: Impacted unit tests (TIA subset; blocking)
-        env:
-          GITHUB_BASE_REF: ${{ github.base_ref }}
-        run: |
-          git fetch --no-tags origin "$GITHUB_BASE_REF" || true
-          node scripts/quality/build-test-impact-map.mjs
-          SEL="$(node scripts/quality/select-impacted-tests.mjs)"
-          if [ -z "$SEL" ]; then echo "No source/test changes — skipping unit tests"; exit 0; fi
-          # CI runners are 4-vCPU; run at --test-concurrency=4 (matching the ci.yml unit
-          # job) rather than test:unit's local-tuned concurrency=20. Oversubscribing the
-          # runner makes timing-sensitive tests (db-backup, upstream-timeout, ...) flake,
-          # which must not happen on a blocking gate. DATA_DIR isolation keeps the parallel
-          # run race-free regardless of concurrency.
-          if echo "$SEL" | grep -q "__RUN_ALL__"; then
-            echo "Fail-safe: __RUN_ALL__ — deferring FULL unit suite to fast-unit (4-shard)."
-            echo "Not re-running unsharded test:unit:ci here (duplicate of fast-unit coverage)."
-            exit 0
-          fi
-          echo "Running impacted tests:"; echo "$SEL"
-          mapfile -t FILES <<< "$SEL"
-          # Loader parity with test:unit:ci:shard (#6787): tests/unit/dashboard/** runs
-          # under `--import tsx` (CJS transform — required for ESM-only deep imports like
-          # @lobehub/icons/es/* reached via lobeProviderIcons.ts); everything else under
-          # `--import tsx/esm`. A single tsx/esm invocation false-reds every dashboard
-          # module-shape test the impact map selects ("Unexpected token 'export'").
-          DASH=(); REST=()
-          for f in "${FILES[@]}"; do
-            case "$f" in
-              tests/unit/dashboard/*) DASH+=("$f") ;;
-              *) REST+=("$f") ;;
-            esac
-          done
-          RC=0
-          if [ ${#REST[@]} -gt 0 ]; then
-            node --import tsx/esm --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${REST[@]}" || RC=$?
-          fi
-          if [ ${#DASH[@]} -gt 0 ]; then
-            node --import tsx --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${DASH[@]}" || RC=$?
-          fi
-          exit $RC
-
-  fast-vitest:
-    name: Vitest (fast-path)
-    needs: changes
-    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
-    # Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
-    runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
-    env:
-      JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-lint-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - run: npm ci
-      # WS5.2/5.3: JUnit feeds Trunk Flaky Tests — the fast-path runs on EVERY PR,
-      # which is where flaky-detection volume actually comes from (ci.yml's heavy
-      # jobs only run on the release PR). Advisory upload, own-origin only.
-      - run: npm run test:vitest -- --reporter=default --reporter=junit --outputFile.junit=trunk-junit/vitest-fastpath.xml
-      - name: Upload test results to Trunk (advisory)
-        if: ${{ always() && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository) }}
-        continue-on-error: true
-        uses: trunk-io/analytics-uploader@385f1ccdf345b4532dc4b6c665dd432b702b8e28 # v2.1.2
-        with:
-          junit-paths: trunk-junit/**/*.xml
-          org-slug: omniroute
-          token: ${{ secrets.TRUNK_TOKEN }}
-
-  fast-unit:
-    name: Unit Tests fast-path (${{ matrix.shard }}/4)
-    needs: changes
-    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
-    # Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
-    # This is the heaviest fast-path job; 4-way sharding (was 2, #6781) halves the
-    # critical path again (~8.5min → ~4.5min on ubuntu-latest; ~2min on the 8-slot
-    # runner box). Node's native --test-shard=N/total takes any denominator — only
-    # this matrix and the TEST_SHARD env below encode the shard count.
-    runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
-    strategy:
-      fail-fast: false
-      matrix:
-        shard: [1, 2, 3, 4]
-    env:
-      JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-lint-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - run: npm ci
-      # QW-d: fonte única — o mesmo npm script do CI pesado/local. Fecha dois drifts do
-      # comando inline antigo: os dirs `memory` e `usage` estavam FORA do glob (testes
-      # silenciosamente não rodavam no fast path) e o setupPolyfill não era importado.
-      - run: npm run test:unit:ci:shard
-        env:
-          TEST_SHARD: ${{ matrix.shard }}/4
-
-  # ── Pacote 4 (plano mestre testes+CI, aprovado 2026-07-04) ─────────────────────────
-  # No-new-warnings por PR via ESLint bulk suppressions nativo (>=9.24). O baseline
-  # config/quality/eslint-suppressions.json congela as violações EXISTENTES por
-  # arquivo+regra; qualquer warning NOVO aparece e o --max-warnings 0 falha o job — o
-  # drift de +41/+88 warnings por ciclo passa a morrer no PR que o introduz, em vez de
-  # ser rebaselinado às cegas na release. Aperto do baseline (na reconciliação da
-  # release): npx eslint . --prune-suppressions --suppressions-location config/quality/eslint-suppressions.json
-  #
-  # Princípio Zero: bloqueante SÓ para branches internas (as campanhas/sessões são a
-  # origem do drift). PR de FORK roda em modo report (continue-on-error → o job fica
-  # verde com anotação; a campanha /green-prs aplica o fix via co-autoria — o
-  # contribuidor NUNCA é bloqueado nem cobrado).
-  lint-guard:
-    name: No new ESLint warnings
-    needs: changes
-    if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
-    runs-on: ubuntu-latest
-    continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
-    steps:
-      - uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - run: npm ci
-      - name: Restore ESLint file cache
-        uses: actions/cache@v6
-        with:
-          path: |
-            .eslintcache
-            .eslintcache-complexity
-          key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
-          restore-keys: |
-            eslint-${{ runner.os }}-
-      - name: ESLint (baseline congelado — warning novo = vermelho)
-        # lint:json writes the report; --max-warnings 0 keeps no-new-warnings policy.
-        run: npm run lint:json -- --max-warnings 0
-
-  # Merge-integrity: pega no PR os dois vazamentos crônicos de merge que hoje só
-  # explodem na release-PR. (1) CHANGELOG-eat — o auto-resolve do merge come
-  # bullets vizinhos/seções inteiras (incidente #6193, 2026-07-05: 212 linhas /
-  # 130 bullets); o checkout de PR é refs/pull/N/merge, então comparar contra a
-  # base detecta o eat ANTES do merge. (2) SKILL.md gerado stale vs o catálogo de
-  # agent-skills (#6186 mergeou um id de catálogo sem rodar o gerador → 8 reds de
-  # integration invisíveis até a release).
-  #
-  # Princípio Zero: bloqueante SÓ para branches internas; PR de FORK roda em modo
-  # report (continue-on-error) — a campanha corrige via co-autoria, o contribuidor
-  # nunca é bloqueado.
-  merge-integrity:
-    name: Merge integrity (changelog + generated skills)
-    # Always on non-draft PRs — CHANGELOG/skills can break on docs-only merges too.
-    if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) }}
-    runs-on: ubuntu-latest
-    continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
-    env:
-      JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-lint-api-key-secret-long
-      DISABLE_SQLITE_AUTO_BACKUP: "true"
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
-        with:
-          fetch-depth: 0
-          persist-credentials: false
-      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
-        with:
-          node-version: ${{ env.CI_NODE_VERSION }}
-          cache: npm
-      - run: npm ci
-      - name: CHANGELOG integrity (nenhum bullet da base pode sumir no merge-result)
-        run: npm run check:changelog-integrity
-      - name: Agent-skills generator sync (SKILL.md gerado ≡ catálogo)
-        run: npm run check:agent-skills-sync

.github/workflows/scorecard.yml

@@ -1,40 +0,0 @@
-name: OpenSSF Scorecard
-on:
-  branch_protection_rule:
-  schedule:
-    - cron: "27 7 * * 1"
-  push:
-    branches: ["main"]
-
-permissions: read-all
-
-jobs:
-  analysis:
-    name: Scorecard analysis
-    runs-on: ubuntu-latest
-    permissions:
-      # security-events: write removed — Scorecard findings are advisory and no longer
-      # uploaded to the code-scanning Security tab (they are supply-chain/posture scores,
-      # not code vulnerabilities, and drowned out real CodeQL alerts). The run still
-      # produces the OpenSSF badge (publish_results) and a downloadable SARIF artifact.
-      id-token: write
-      contents: read
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v7
-        with:
-          persist-credentials: false
-
-      - name: Run analysis
-        uses: ossf/scorecard-action@v2.4.3
-        with:
-          results_file: results.sarif
-          results_format: sarif
-          publish_results: true
-
-      - name: Upload artifact
-        uses: actions/upload-artifact@v7
-        with:
-          name: SARIF file
-          path: results.sarif
-          retention-days: 5

.github/workflows/semgrep.yml

@@ -1,29 +0,0 @@
-name: semgrep
-on:
-  pull_request:
-    branches: ["main", "release/**"]
-  push:
-    branches: ["main"]
-permissions:
-  contents: read
-jobs:
-  semgrep:
-    runs-on: ubuntu-latest
-    container:
-      image: semgrep/semgrep
-    steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          persist-credentials: false
-      - name: Run semgrep (advisory)
-        continue-on-error: true
-        run: |
-          semgrep scan --config p/owasp-top-ten --config p/secrets \
-            --sarif --output semgrep.sarif --metrics off || true
-          python -c "import json; d=json.load(open('semgrep.sarif')); print('semgrepFindings=%d' % len(d['runs'][0]['results']))" || echo "semgrepFindings=SKIP"
-      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-        if: always()
-        with:
-          name: semgrep-sarif
-          path: semgrep.sarif
-          retention-days: 14

.github/workflows/wiki-sync.yml

@@ -1,69 +0,0 @@
-name: Wiki Sync
-
-# Keeps the GitHub wiki in sync with docs/ on every release that lands on main.
-# The wiki has no native generator and historically drifts (it sat at "212+ providers /
-# 14 strategies / 37 MCP tools" while code was at 226 / 15 / 87, and new docs like
-# SUPPLY_CHAIN never appeared). This runs scripts/docs/sync-wiki.mjs, which:
-#   - ADDS any docs/ page missing from the wiki (curated; internal reports excluded),
-#   - syncs the four cover-page counts on Home.md.
-# It does NOT overwrite existing wiki pages by default: several docs sources still carry
-# stale counts (e.g. ARCHITECTURE.md says "177 providers" while the wiki cover is 226),
-# so blind overwrite would regress the wiki. Full content parity (--update-existing) is
-# gated on regenerating those sources first.
-
-on:
-  push:
-    branches: [main]
-    paths:
-      - "docs/**"
-      - "README.md"
-      - "AGENTS.md"
-      - "src/shared/constants/routingStrategies.ts"
-      - "config/i18n.json"
-      - "open-sse/mcp-server/server.ts"
-      - "scripts/docs/sync-wiki.mjs"
-  workflow_dispatch:
-
-permissions:
-  contents: write
-
-concurrency:
-  group: wiki-sync
-  cancel-in-progress: false
-
-jobs:
-  sync-wiki:
-    name: Sync wiki with docs
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repo
-        uses: actions/checkout@v7
-
-      - name: Setup Node
-        uses: actions/setup-node@v6
-        with:
-          node-version: "24"
-
-      - name: Clone wiki
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          REPO: ${{ github.repository }}
-        run: |
-          git clone "https://x-access-token:${GH_TOKEN}@github.com/${REPO}.wiki.git" wiki
-
-      - name: Sync wiki (add missing pages + cover counts)
-        run: node scripts/docs/sync-wiki.mjs --wiki-dir wiki
-
-      - name: Commit & push if changed
-        run: |
-          cd wiki
-          if [ -n "$(git status --porcelain)" ]; then
-            git config user.name "github-actions[bot]"
-            git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-            git add -A
-            git commit -m "docs(wiki): auto-sync pages + cover counts with docs"
-            git push
-            echo "Wiki updated."
-          else
-            echo "Wiki already in sync — nothing to push."
-          fi

.gitignore

@@ -23,11 +23,6 @@ coverage/
 .build/**
 .out/**
 
-# Stryker mutation testing — ephemeral sandbox + generated reports (never commit)
-.stryker-tmp/
-reports/mutation/
-stryker-output-*.json
-
 
 # Memory Bank and Cursor rules (local-only AI agent context)
 memory-bank/
@@ -49,10 +44,6 @@ docs/new-features/
 
 # dependencies
 node_modules/
-# Also ignore a root node_modules SYMLINK (worktree setups symlink it from the main
-# checkout). The trailing-slash pattern above only matches a directory, so without this
-# a symlink named node_modules could be staged by `git add -A` and committed.
-/node_modules
 *.map
 .DS_Store
 
@@ -72,7 +63,6 @@ yarn-error.log*
 # env files (can opt-in for committing if needed)
 .env*
 !.env.example
-!.env.homolog.example
 # Provider API keys (never commit)
 *.api-key
 .nvidia-api-key
@@ -162,11 +152,6 @@ typescript
 
 # Superpowers plans/specs (internal tooling, not project code)
 docs/superpowers/
-# Superpowers visual-companion brainstorm mockups (ephemeral)
-.superpowers/
-
-# TIA test-impact map — generated at runtime in CI (build-test-impact-map.mjs), never committed (~21MB)
-config/quality/test-impact-map.json
 
 # GitNexus local index
 .gitnexus
@@ -218,11 +203,8 @@ pr_reviews*.json
 
 # internal setup prompts with personal credentials — never commit
 CODEX-SETUP-PROMPT.md
-# Quality ratchet — métricas efêmeras (baseline commitado em config/quality/; métricas não)
-config/quality/quality-metrics.json
-
-# Runtime logs (diretório local, nunca versionado)
-/logs/
+# Quality ratchet — métricas efêmeras (baseline é commitado, métricas não)
+quality-metrics.json
 -home-diegosouzapw-dev-automações-bots-yt-downloader-20260504 .txt
 -home-diegosouzapw-dev-automações-bots-yt-downloader-20260410 .txt
 docs/prompts/AGENT-OWNERSHIP-PROTOCOL.omniroute.md
@@ -230,22 +212,3 @@ docs/prompts/AGENT-OWNERSHIP-PROTOCOL.md
 docs/prompts/AGENT-OWNERSHIP-PROTOCOL.omniroute-mim.md
 docs/prompts/AGENT-OWNERSHIP-PROTOCOL.omniroute-mid.md
 omniroute.md
-
-# mise configuration
-mise.toml
-_artifacts/
-.claude-flow/
-
-# ESLint file cache (npm run lint --cache / complexity ratchets)
-.eslintcache
-.eslintcache-complexity
-
-
-# CI/local quality artifacts (eslint-results.json, etc.)
-.artifacts/
-
-# Homologation E2E suite (npm run homolog) — real-environment credentials + report output
-.env.homolog
-tests/homolog/.auth/
-tests/homolog/ui/.auth/
-homolog-report/

.gitleaks.toml

@@ -1,89 +0,0 @@
-# .gitleaks.toml — Configuração do gitleaks para OmniRoute
-# Task 7.18 — PLANO-QUALITY-GATES-FASE7.md
-#
-# Estende as regras padrão do gitleaks com allowlists específicas do projeto.
-#
-# INSTRUÇÕES para allowlists:
-#   Findings legítimos (fixtures de teste, creds OAuth públicas já cobertas pelo
-#   check-public-creds.mjs, valores de exemplo em docs) devem ser registrados abaixo
-#   em [[allowlist]] com um comentário explicativo obrigatório.
-#
-#   NÃO adicione uma entrada de allowlist sem justificativa. Cada entrada é revisada
-#   a cada release (stale-enforcement). Regra: se o finding é um valor real que o
-#   sistema usa em produção, é um verdadeiro positivo — não allowliste, corrija.
-#
-# Referência: docs/security/PUBLIC_CREDS.md (credenciais OAuth públicas conhecidas)
-#             CLAUDE.md Hard Rule #11 (resolvePublicCred obrigatório)
-
-# Herdar TODAS as regras padrão do gitleaks. ATENÇÃO: um config customizado
-# SEM [extend].useDefault = true (e sem [[rules]] próprias) resulta em ZERO
-# regras — o gitleaks SUBSTITUI o ruleset padrão pelo arquivo, não o estende
-# automaticamente. Sem esta seção, `gitleaks --config .gitleaks.toml` nunca
-# detecta nada (todo finding vira 0), tornando o gate inerte. Com useDefault,
-# a allowlist abaixo é aplicada POR CIMA das ~170 regras padrão.
-[extend]
-  useDefault = true
-
-# Para desabilitar uma regra específica, usar:
-# [[rules]]
-#   id = "rule-id"
-#   [rules.allowlist]
-#     description = "..."
-
-# ---------------------------------------------------------------------------
-# Allowlist global do projeto
-# Entradas aqui são ignoradas em TODAS as varreduras.
-# ---------------------------------------------------------------------------
-[allowlist]
-  description = "OmniRoute project-level allowlist — fixtures, test vectors, public OAuth creds"
-
-  # Paths a ignorar completamente (node_modules, builds, etc.)
-  paths = [
-    '''node_modules''',
-    '''\.next''',
-    '''dist''',
-    '''\.git''',
-    '''coverage''',
-    '''\.nyc_output''',
-  ]
-
-  # Commits específicos a ignorar (ex: commit que introduziu fixtures de teste)
-  # commits = []
-
-  # Regexes de stopwords — linhas que contêm estes padrões são ignoradas.
-  # Usar apenas para falsos positivos comprovados com justificativa abaixo.
-  # stopwords = []
-
-  # Regexes de targets (paths de arquivos) que podem ser allowlistados por regra.
-  # Ver [[allowlist]] por-regra abaixo para granularidade.
-
-# ---------------------------------------------------------------------------
-# Allowlist por-regra (adicionar conforme necessário durante o stale review)
-# ---------------------------------------------------------------------------
-#
-# Exemplo (REMOVER / SUBSTITUIR por entradas reais quando necessário):
-#
-# [[rules]]
-#   # Allowlistar fixtures de teste que contêm tokens OAuth de exemplo/inválidos
-#   # Adicionado: 2026-06-13 | Revisar em: v3.9.0 | Justificativa: valores não-reais de teste
-#   id = "github-fine-grained-pat"
-#   [rules.allowlist]
-#     description = "Test fixture PATs — valores sintéticos, não funcionais"
-#     paths = [
-#       '''tests/fixtures/''',
-#       '''tests/unit/''',
-#     ]
-#
-
-[[rules]]
-  # Falsos-positivos comprovados do generic-api-key — zerados em 2026-07-13 (WS6/D3,
-  # plano v3.8.49). Revisar em v3.9.0. Nenhum é credencial: dois são NOMES DE CAMPO
-  # de métricas de latência; o terceiro é o valor PÚBLICO de um beta header da API
-  # da Anthropic (documentado publicamente, não é segredo).
-  id = "generic-api-key"
-  [rules.allowlist]
-    description = "Field names + public Anthropic beta-header value (não são segredos)"
-    regexes = [
-      '''latencyP\d{2}Ms''',
-      '''interleaved-thinking-2025-05-14''',
-    ]

.husky/pre-commit

@@ -10,4 +10,3 @@ fi
 npx lint-staged
 node scripts/check/check-docs-sync.mjs
 npm run check:any-budget:t11
-node scripts/check/check-tracked-artifacts.mjs

.husky/pre-push

@@ -1,15 +1,8 @@
 #!/usr/bin/env sh
-# .husky/pre-push — intentionally light.
-# any-budget + tracked-artifacts already run on pre-commit; re-running them on
-# every push only doubles local wall time for the same existence reason (CI still
-# enforces both). Keep this hook as a PATH/npm sanity check + reminder.
-# Intentionally excludes test:unit / typecheck (slow; covered by CI).
+#if ! command -v npm >/dev/null 2>&1; then
+#  echo "⚠️  npm not found in PATH — skipping pre-push hooks"
+#  echo "   Run 'npm test' manually before pushing."
+#  exit 0
+#fi
 
-if ! command -v npm >/dev/null 2>&1; then
-  echo "⚠️  npm not found in PATH — skipping pre-push hooks"
-  echo "   Run 'npm run check:any-budget:t11 && npm run check:tracked-artifacts' manually before pushing."
-  exit 0
-fi
-
-# No-op success: real local gates live in pre-commit; CI owns the rest.
-exit 0
+#npm run test:unit

.markdownlint.json

@@ -1,14 +0,0 @@
-{
-  "_comment": "Advisory markdown lint for docs/ + root *.md. Rules that conflict with the existing doc style (heavy inline HTML, long lines, centered headings) are disabled so the gate stays signal-not-noise. Run: npm run lint:md",
-  "default": true,
-  "MD013": false,
-  "MD033": false,
-  "MD041": false,
-  "MD024": { "siblings_only": true },
-  "MD026": false,
-  "MD036": false,
-  "MD040": false,
-  "MD029": false,
-  "MD007": { "indent": 2 },
-  "MD046": false
-}

.mergify.yml

@@ -1,55 +0,0 @@
-# Mergify merge queue — WS3.4/D5 of the v3.8.49 quality/velocity master plan.
-#
-# WHY: ~85-100 active PR authors/month and 300+ PRs/week peaks, all merged by ONE
-# identity. The manual merge-train validated batches by hand; this queue automates
-# it with batching + automatic batch bisection (a red batch of N costs ~log2(N)
-# revalidations instead of N). Mergify Open Source plan: free, unlimited, public repo.
-#
-# GOVERNANCE (non-negotiable, mirrors CLAUDE.md Hard Rules #21/#22 + the owner's
-# pre-merge ⭐ gate):
-#   • A PR enters the queue ONLY via the `queue` label — applied by the owner (or a
-#     session acting for the owner) AFTER the pre-merge ⭐ report/decision. The label
-#     IS the merge approval; Mergify only executes it.
-#   • During a release-freeze (open issue labeled `release-freeze`), do NOT label PRs
-#     targeting the frozen branch — the freeze is a human-honored coordination signal
-#     the queue cannot see. Retarget to the active release/vX+1 first (Hard Rule #21).
-#   • Never label a PR another session is actively working (Hard Rule #22b).
-#   • Fallback path if Mergify misbehaves or the OSS plan changes: the manual
-#     merge-train runbook (docs/ops/MERGE_TRAIN.md) — remove labels, proceed by hand.
-
-queue_rules:
-  - name: release
-    # Any current or future release branch — the reason GitHub's native queue was
-    # rejected (no wildcard support on personal-account repos).
-    queue_conditions:
-      - base~=^release/v\d+\.\d+\.\d+$
-      - label=queue
-      - -draft
-      - -conflict
-    # "Everything that ran is green, nothing still running, AND the always-on
-    # anchor check succeeded" — robust to the path-filtered fast-gates (docs-only
-    # PRs skip code jobs; matrix shard names vary) while never fail-open: a PR with
-    # zero checks cannot vacuously merge, because `Merge integrity` runs on EVERY
-    # non-draft PR (quality.yml) and must be an affirmative success. Review approval
-    # is intentionally NOT a condition here: the owner-applied `queue` label IS the
-    # approval in this repo's single-maintainer model (see governance header).
-    merge_conditions:
-      - "#check-failure=0"
-      - "#check-pending=0"
-      - "#check-success>=1"
-      - check-success=Merge integrity (changelog + generated skills)
-    # Batching: validate up to 10 queued PRs together (the manual train's sweet spot);
-    # don't hold a lone PR hostage waiting for siblings.
-    batch_size: 10
-    batch_max_wait_time: 5 min
-    # Squash keeps the one-commit-per-PR history the CHANGELOG reconciliation expects.
-    merge_method: squash
-
-pull_request_rules:
-  - name: clean up the queue label after merge
-    conditions:
-      - merged
-    actions:
-      label:
-        remove:
-          - queue

.npmrc

@@ -2,13 +2,3 @@
 # Keeping peer auto-install disabled prevents npm from pulling @lobehub/ui/mermaid
 # back into the tree and reopening npm audit findings for unused packages.
 legacy-peer-deps=true
-
-# Network resilience: enlarge npm's fetch retry budget so a transient registry
-# socket reset (ECONNRESET) mid-download retries instead of failing the job.
-# npm defaults to only 2 retries with short timeouts; `npm ci` in
-# electron-release.yml hit ECONNRESET during v3.8.41 publish. Applies to every
-# CI workflow (electron / docker / unit) and local installs.
-fetch-retries=5
-fetch-retry-factor=4
-fetch-retry-mintimeout=20000
-fetch-retry-maxtimeout=120000

.prettierignore

@@ -1,5 +0,0 @@
-# Long reference tables are manually aligned; formatting the whole file causes noisy diffs.
-docs/reference/ENVIRONMENT.md
-
-# Dense auto-generated free-tier budget rows (one object per line) — prettier multi-line expand blows past file-size cap 800.
-open-sse/config/freeModelCatalog.data.ts

.size-limit.json

@@ -1,22 +0,0 @@
-[
-  {
-    "name": "CLI entry (omniroute.mjs)",
-    "path": "bin/omniroute.mjs",
-    "limit": "15 KB"
-  },
-  {
-    "name": "MCP server entry (mcp-server.mjs)",
-    "path": "bin/mcp-server.mjs",
-    "limit": "5 KB"
-  },
-  {
-    "name": "Node runtime support (nodeRuntimeSupport.mjs)",
-    "path": "bin/nodeRuntimeSupport.mjs",
-    "limit": "8 KB"
-  },
-  {
-    "name": "Reset password entry (reset-password.mjs)",
-    "path": "bin/reset-password.mjs",
-    "limit": "6 KB"
-  }
-]

.source/source.config.mjs

@@ -4,6 +4,7 @@ var docs = defineDocs({
   dir: "docs",
   docs: {
     files: [
+      "./getting-started/**/*.md",
       "./architecture/**/*.md",
       "./guides/**/*.md",
       "./reference/**/*.md",

.trivyignore

@@ -1,22 +0,0 @@
-# .trivyignore — accepted-risk suppressions for the container image scan
-#
-# Policy (see docs/security/SUPPLY_CHAIN.md):
-#   - The Trivy steps in .github/workflows/docker-publish.yml run with
-#     `ignore-unfixed: true`, so vulnerabilities WITHOUT a published fix are
-#     already excluded from both the blocking CRITICAL gate and the advisory
-#     Security-tab upload. You do NOT need an entry here for an unfixable
-#     base-image OS CVE — it will not be reported.
-#   - This file is the single auditable home for the rare case where a *fixable*
-#     CVE must be temporarily accepted (e.g. the upstream fix is not yet in the
-#     pinned base tag, or the affected package/binary is provably unreachable
-#     from the proxy request surface and rebuilding now is not justified).
-#
-# Format — one CVE id per line, each with a justification comment and, where
-# possible, an expiry, e.g.:
-#   # CVE-XXXX-YYYY — <why accepted>; revisit on next base-image bump (YYYY-MM-DD)
-#   CVE-XXXX-YYYY
-#
-# Keep this list SHORT and reviewed every release. Prefer fixing (rebuild on a
-# patched base / bump the dep) over suppressing. Stale entries are debt.
-#
-# (No accepted-risk suppressions at present — ignore-unfixed covers the noise.)

.vale.ini

@@ -1,15 +0,0 @@
-# Advisory prose lint for OmniRoute docs (Vale — https://vale.sh).
-# Warning-first: surfaces vague language, passive voice, and terminology drift without
-# blocking CI. The Microsoft style is pulled by the CI step (vale sync / vale-action).
-# Project terms live in the OmniRoute vocabulary so they never read as misspellings.
-StylesPath = .vale/styles
-MinAlertLevel = warning
-Packages = Microsoft
-Vocab = OmniRoute
-
-[*.md]
-BasedOnStyles = Vale, Microsoft
-
-# Code-heavy reference docs and auto-generated catalogs are noisy under prose rules.
-[docs/reference/PROVIDER_REFERENCE.md]
-BasedOnStyles = Vale

.vale/styles/Vocab/OmniRoute/accept.txt

@@ -1,50 +0,0 @@
-OmniRoute
-combo
-combos
-[Cc]ombo
-[Aa]uto-[Cc]ombo
-MCP
-A2A
-ACP
-RTK
-Caveman
-Troglodita
-Qdrant
-FTS5
-SQLite
-LowDB
-OAuth
-PKCE
-SSE
-JSON-RPC
-LKGP
-P2C
-Antigravity
-Codex
-Kiro
-Qoder
-Pollinations
-LongCat
-Cerebras
-DeepSeek
-Groq
-Cline
-OpenCode
-Termux
-Electron
-Fumadocs
-Notion
-Obsidian
-WebDAV
-IPv4
-IPv6
-SOCKS5
-loopback
-backoff
-changelog
-i18n
-locale
-locales
-roadmap
-[Ww]ildcard
-upstream

.vscode/settings.json

@@ -19,87 +19,30 @@
     }
   },
   "git.ignoreLimitWarning": true,
-
-  // ─── Git: não adicionar os ~44 repos aninhados (9 worktrees + _references/* +
-  // _mono_repo/* + _ideia/_tasks/.agents) ao Source Control. Era a causa do
-  // "validando muito": um git status + watcher por repo. Só o repo raiz fica. ───
-  "git.autoRepositoryDetection": false,
-  "git.repositoryScanMaxDepth": 0,
-  "git.detectSubmodules": false,
-  "git.autofetch": false,
-  "git.autorefresh": true,
-
-  // ─── Performance: não seguir o symlink de node_modules criado pelas worktrees ───
-  // As worktrees em .worktrees/ apontam node_modules para o checkout principal;
-  // sem isto a busca atravessa o symlink mesmo com node_modules excluído.
-  "search.followSymlinks": false,
-
-  // ─── TypeScript server (monorepo grande: ~6,6k arquivos rastreados, Next.js 16) ───
-  "typescript.tsserver.maxTsServerMemory": 4096,
-  "typescript.disableAutomaticTypeAcquisition": true,
-  "typescript.tsc.autoDetect": "off",
-  "npm.autoDetect": "off",
-  // O tsserver tem o próprio watcher (independente de files.watcherExclude).
-  // excludeDirectories evita que ele vigie as árvores pesadas.
-  "typescript.tsserver.watchOptions": {
-    "excludeDirectories": [
-      "**/node_modules",
-      "**/.next",
-      "**/.build",
-      "**/dist",
-      "**/coverage",
-      "**/.worktrees",
-      "**/.claude/worktrees",
-      "**/electron",
-      "**/_references",
-      "**/_mono_repo",
-      "**/_tasks"
-    ]
-  },
-
-  // Para esconder os diretórios gerados da árvore do Explorer, descomente:
-  // (MANTIDO comentado — o dono precisa ver _references/_mono_repo/_tasks na árvore.
-  //  A performance é resolvida por watcherExclude + search.exclude + tsserver, sem
-  //  precisar escondê-los do Explorer.)
   // "files.exclude": {
-  //   "**/.worktrees": true,
-  //   "**/coverage": true,
-  //   "**/dist": true,
-  //   "**/.build": true,
-  //   "**/.next": true,
   //   "**/_references": true,
   //   "**/_mono_repo": true,
-  //   "**/_tasks": true,
-  //   "**/omniroute-*.tgz": true
+  //   "**/electron": true,
+  //   "**/node_modules": true,
+  //   "**/.next": true,
+  //   "**/coverage": true,
+  //   "**/omniroute-*.tgz": true,
+  //   "**/_tasks": true
   // },
   "files.watcherExclude": {
-    "**/.git/objects/**": true,
-    "**/.git/subtree-cache/**": true,
+    "**/_references/**": true,
+    "**/_mono_repo/**": true,
+    "**/electron/**": true,
     "**/node_modules/**": true,
     "**/.next/**": true,
-    "**/.build/**": true,
+    "**/coverage/**": true,
+    "**/_tasks/**": true,
+    "**/.git/objects/**": true,
     "**/dist/**": true,
     "**/build/**": true,
     "**/out/**": true,
-    "**/coverage/**": true,
-    "**/.coverage/**": true,
-    "**/.nyc_output/**": true,
     "**/.cache/**": true,
     "**/.turbo/**": true,
-    "**/.swc/**": true,
-    "**/.stryker-tmp/**": true,
-    "**/stryker-output-*/**": true,
-    "**/playwright-report/**": true,
-    "**/test-results/**": true,
-    "**/.worktrees/**": true,
-    "**/.claude/worktrees/**": true,
-    "**/electron/**": true,
-    "**/_references/**": true,
-    "**/_mono_repo/**": true,
-    "**/_tasks/**": true,
-    "**/logs/**": true,
-    "**/*.tgz": true,
-    "**/*.tsbuildinfo": true,
     "**/OmniRoute-*/**": true,
     "**/*-merge-*/**": true,
     "**/*-worktree-*/**": true,
@@ -107,32 +50,16 @@
     "**/*-reorg*/**": true
   },
   "search.exclude": {
+    "**/_references": true,
+    "**/_mono_repo": true,
+    "**/electron": true,
     "**/node_modules": true,
     "**/.next": true,
-    "**/.build": true,
+    "**/coverage": true,
+    "**/_tasks": true,
     "**/dist": true,
     "**/build": true,
     "**/out": true,
-    "**/coverage": true,
-    "**/.coverage": true,
-    "**/.nyc_output": true,
-    "**/.cache": true,
-    "**/.turbo": true,
-    "**/.swc": true,
-    "**/.stryker-tmp": true,
-    "**/stryker-output-*": true,
-    "**/playwright-report": true,
-    "**/test-results": true,
-    "**/.worktrees": true,
-    "**/.claude/worktrees": true,
-    "**/electron": true,
-    "**/_references": true,
-    "**/_mono_repo": true,
-    "**/_tasks": true,
-    "**/logs": true,
-    "**/*.tgz": true,
-    "**/*.tsbuildinfo": true,
-    "**/package-lock.json": true,
     "**/OmniRoute-*": true,
     "**/*-merge-*": true,
     "**/*-worktree-*": true,

.zizmor.yml

@@ -1,104 +0,0 @@
-# .zizmor.yml — zizmor security audit configuration
-# https://github.com/woodruffw/zizmor
-#
-# zizmor audits GitHub Actions workflows for security anti-patterns:
-#   • Unpinned third-party actions (supply-chain risk)
-#   • Script injection via ${{ github.* }} in run: steps
-#   • pull_request_target misuse (allows untrusted code to reach secrets)
-#   • Excessive permissions / overly broad GITHUB_TOKEN scopes
-#   • Cache poisoning via actions/cache with unguarded keys
-#   • … 20+ additional audits
-#
-# MOTIVATION (2026-03 incident): the trivy-action/LiteLLM supply-chain attack
-# exploited exactly the kind of pull_request_target misconfiguration that zizmor
-# detects statically. OmniRoute's npm/Docker/Electron publish workflows are high-
-# value targets that warrant proactive audit.
-#
-# BASELINE STRATEGY: this file starts with an EMPTY ignores list. As zizmor is
-# first run against the existing workflows, findings will be reviewed:
-#   • True positives → fix the workflow (preferred)
-#   • Accepted risk  → add an entry below with a justification comment
-# This enforces the same stale-enforcement discipline as other allowlists in
-# this project: every ignore requires human sign-off and is subject to review
-# at each release cycle.
-#
-# RATCHET: zizmorFindings metric in quality-baseline.json (direction: down)
-# starts advisory; current baseline is frozen at first green run; new findings
-# must be remediated or explicitly ignored here.
-
-# ── Global settings ──────────────────────────────────────────────────────────
-# Uncomment to pin to a specific minimum severity level.
-# min-severity: low       # low | medium | high | critical (default: low = all)
-
-# ── Per-rule ignores ─────────────────────────────────────────────────────────
-# zizmor ≥1.0 replaced the old top-level `ignores:` list with a `rules:` map
-# keyed by audit id. Per-rule config lives under `rules.<audit-id>.ignore`,
-# where each entry is `filename` or `filename:line` (line optional, column
-# further-optional). See: https://docs.zizmor.sh/configuration/
-#
-# Format:
-#   rules:
-#     <zizmor-audit-id>:          # e.g. "unpinned-uses", "template-injection"
-#       ignore:
-#         - <workflow-filename>            # ignore this audit across the file
-#         - <workflow-filename>:<line>     # or scope to a specific line
-#
-# Example (do not uncomment without real justification):
-#
-#   rules:
-#     unpinned-uses:
-#       # actions/checkout@v6 is pinned at the major-version tag intentionally:
-#       # GitHub-managed first-party action; SHA pinning buys little against a
-#       # GitHub-side compromise and adds significant maintenance burden.
-#       ignore:
-#         - ci.yml
-
-# Every entry below is an explicit, justified ignore (same stale-review
-# discipline as the other allowlists in this project). New ignores require a
-# per-rule entry with a justification comment.
-rules:
-  dangerous-triggers:
-    # deploy-vps.yml uses `on: workflow_run` (after "Publish to Docker Hub").
-    # zizmor flags workflow_run as "almost always used insecurely", but this one
-    # is guarded and not exploitable:
-    #   • The deploy job is gated on `github.event.workflow_run.conclusion ==
-    #     'success'` (deploy-vps.yml job `if:`, L15), so it only runs after a
-    #     successful, trusted upstream run — never on a forked/PR-triggered
-    #     failure.
-    #   • It does NOT checkout or execute untrusted code: the deploy runs over SSH
-    #     using repository secrets; there is no `actions/checkout` of an attacker
-    #     ref in the privileged context.
-    # Accepted risk, re-review at the next release cycle (added 2026-06-15).
-    ignore:
-      - deploy-vps.yml
-
-  cache-poisoning:
-    # zizmor's cache-poisoning audit flags `actions/setup-node` (cache: npm) and
-    # `actions/cache` steps that populate a cache which a later artifact-publishing
-    # job could consume — the attack is: a fork PR seeds a poisoned cache that a
-    # trusted publish run then restores and ships. None of the four entries below
-    # are exploitable in that way:
-    #
-    #   • electron-release.yml / npm-publish.yml — PUBLISH workflows that trigger
-    #     ONLY on trusted events: `push: tags v*` + `workflow_dispatch` (electron)
-    #     and `release: [released]` + `workflow_dispatch` + `workflow_call`
-    #     (npm). They NEVER run on a `pull_request` from a fork, so an untrusted
-    #     ref can never populate the npm/node_modules cache they restore. The
-    #     cache key is `hashFiles('package-lock.json')` / `runner.os-node-…`, a
-    #     first-party, lockfile-pinned key on trusted events.
-    #
-    #   • opencode-plugin-ci.yml / opencode-provider-ci.yml — CI-only workflows
-    #     (lint/test of the two opencode packages). They DO run on `pull_request`,
-    #     but (a) they publish NO artifacts — there is no downstream publish job
-    #     that restores their cache, and (b) GitHub Actions cache is branch-scoped:
-    #     a fork-PR run writes to a PR-isolated cache that base-branch / release
-    #     runs cannot read. The `cache: npm` here only speeds up `npm ci` within
-    #     the same ephemeral CI run.
-    #
-    # Accepted risk (first-party caching on trusted/isolated events), re-review at
-    # the next release cycle (added 2026-06-16).
-    ignore:
-      - electron-release.yml
-      - npm-publish.yml
-      - opencode-plugin-ci.yml
-      - opencode-provider-ci.yml

@omniroute/opencode-plugin/README.md

@@ -196,7 +196,7 @@ Every field is optional. Defaults mirror v0.1.0 behaviour so existing `opencode.
 | `combos`              | `boolean` | `true`  | Discover `/api/combos` and surface them as pseudo-models with LCD capabilities. Combos are keyed under the `combo/<slug>` namespace and labelled `Combo: <name>` in the model picker so they're distinguishable from raw provider/model pairs.                                                                                                                                                                                                                                                                                                                               |
 | `enrichment`          | `boolean` | `true`  | Pull display names from `/api/pricing/models` AND per-million-token pricing (`input`, `output`, `cached` → `cacheRead`, `cache_creation` → `cacheWrite`) from `/api/pricing`, then overlay both onto the live catalog (so the UI shows `Claude 4.7 Opus` with `cost.input: 5`, `cost.output: 25` instead of raw IDs and zeroed cost).                                                                                                                                                                                                                                        |
 | `compressionMetadata` | `boolean` | `false` | Pull `/api/context/combos` so combo names get tagged with their compression pipeline, e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`. Intensity tokens render as traffic-light emoji (🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra) so the picker advertises "how compressed" each combo is at a glance.                                                                                                                                                                                                                                                  |
-| `providerTag`         | `boolean` | `true`  | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models` → `GHM`, `Gemini` → `GEMINI`). Idempotent. Combos intentionally skipped (the `Combo: ` prefix already conveys multi-upstream). |
+| `providerTag`         | `boolean` | `true`  | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models` → `GHM`, `Gemini-cli` → `GEMINI-CLI`). Idempotent. Combos intentionally skipped (the `Combo: ` prefix already conveys multi-upstream). |
 | `usableOnly`          | `boolean` | `false` | Read `/api/providers` and filter the catalog to providers that have at least one connection with `isActive: true` AND `testStatus: 'active'`. Subtract-filter semantics: providers unknown to BOTH the pricing-models catalog AND the connection table pass through (so synthetic prefixes like `agentrouter/*` survive). On fetch failure the filter is disabled for the refresh — never hides the whole catalog.                                                                                                                                                           |
 | `diskCache`           | `boolean` | `true`  | Persist the last successful `/v1/models` + `/api/combos` + enrichment + connections + compression snapshot to `${OPENCODE_DATA_DIR ?? ~/.local/share/opencode}/plugins/omniroute-<providerId>.json`. On a subsequent cold start where `/v1/models` throws (network down / IP whitelist drop / 5xx) the static block hydrates from the snapshot so OC's model picker survives offline. Soft-fail on read/write — never blocks publishing.                                                                                                                                     |
 | `geminiSanitization`  | `boolean` | `true`  | Strip `$schema`/`$ref`/`additionalProperties` from tool params when the model id matches `gemini`                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |

@omniroute/opencode-plugin/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@omniroute/opencode-plugin",
-  "version": "0.2.0",
+  "version": "0.1.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@omniroute/opencode-plugin",
-      "version": "0.2.0",
+      "version": "0.1.0",
       "license": "MIT",
       "dependencies": {
         "zod": "^4.4.3"
@@ -26,9 +26,9 @@
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.28.1.tgz",
-      "integrity": "sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.27.7.tgz",
+      "integrity": "sha512-EKX3Qwmhz1eMdEJokhALr0YiD0lhQNwDqkPYyPhiSwKrh7/4KRjQc04sZ8db+5DVVnZ1LmbNDI1uAMPEUBnQPg==",
       "cpu": [
         "ppc64"
       ],
@@ -43,9 +43,9 @@
       }
     },
     "node_modules/@esbuild/android-arm": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.28.1.tgz",
-      "integrity": "sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.27.7.tgz",
+      "integrity": "sha512-jbPXvB4Yj2yBV7HUfE2KHe4GJX51QplCN1pGbYjvsyCZbQmies29EoJbkEc+vYuU5o45AfQn37vZlyXy4YJ8RQ==",
       "cpu": [
         "arm"
       ],
@@ -60,9 +60,9 @@
       }
     },
     "node_modules/@esbuild/android-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.28.1.tgz",
-      "integrity": "sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.27.7.tgz",
+      "integrity": "sha512-62dPZHpIXzvChfvfLJow3q5dDtiNMkwiRzPylSCfriLvZeq0a1bWChrGx/BbUbPwOrsWKMn8idSllklzBy+dgQ==",
       "cpu": [
         "arm64"
       ],
@@ -77,9 +77,9 @@
       }
     },
     "node_modules/@esbuild/android-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.28.1.tgz",
-      "integrity": "sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.27.7.tgz",
+      "integrity": "sha512-x5VpMODneVDb70PYV2VQOmIUUiBtY3D3mPBG8NxVk5CogneYhkR7MmM3yR/uMdITLrC1ml/NV1rj4bMJuy9MCg==",
       "cpu": [
         "x64"
       ],
@@ -94,9 +94,9 @@
       }
     },
     "node_modules/@esbuild/darwin-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.28.1.tgz",
-      "integrity": "sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.27.7.tgz",
+      "integrity": "sha512-5lckdqeuBPlKUwvoCXIgI2D9/ABmPq3Rdp7IfL70393YgaASt7tbju3Ac+ePVi3KDH6N2RqePfHnXkaDtY9fkw==",
       "cpu": [
         "arm64"
       ],
@@ -111,9 +111,9 @@
       }
     },
     "node_modules/@esbuild/darwin-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.28.1.tgz",
-      "integrity": "sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.27.7.tgz",
+      "integrity": "sha512-rYnXrKcXuT7Z+WL5K980jVFdvVKhCHhUwid+dDYQpH+qu+TefcomiMAJpIiC2EM3Rjtq0sO3StMV/+3w3MyyqQ==",
       "cpu": [
         "x64"
       ],
@@ -128,9 +128,9 @@
       }
     },
     "node_modules/@esbuild/freebsd-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.28.1.tgz",
-      "integrity": "sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.27.7.tgz",
+      "integrity": "sha512-B48PqeCsEgOtzME2GbNM2roU29AMTuOIN91dsMO30t+Ydis3z/3Ngoj5hhnsOSSwNzS+6JppqWsuhTp6E82l2w==",
       "cpu": [
         "arm64"
       ],
@@ -145,9 +145,9 @@
       }
     },
     "node_modules/@esbuild/freebsd-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.28.1.tgz",
-      "integrity": "sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.27.7.tgz",
+      "integrity": "sha512-jOBDK5XEjA4m5IJK3bpAQF9/Lelu/Z9ZcdhTRLf4cajlB+8VEhFFRjWgfy3M1O4rO2GQ/b2dLwCUGpiF/eATNQ==",
       "cpu": [
         "x64"
       ],
@@ -162,9 +162,9 @@
       }
     },
     "node_modules/@esbuild/linux-arm": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.28.1.tgz",
-      "integrity": "sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.27.7.tgz",
+      "integrity": "sha512-RkT/YXYBTSULo3+af8Ib0ykH8u2MBh57o7q/DAs3lTJlyVQkgQvlrPTnjIzzRPQyavxtPtfg0EopvDyIt0j1rA==",
       "cpu": [
         "arm"
       ],
@@ -179,9 +179,9 @@
       }
     },
     "node_modules/@esbuild/linux-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.28.1.tgz",
-      "integrity": "sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.27.7.tgz",
+      "integrity": "sha512-RZPHBoxXuNnPQO9rvjh5jdkRmVizktkT7TCDkDmQ0W2SwHInKCAV95GRuvdSvA7w4VMwfCjUiPwDi0ZO6Nfe9A==",
       "cpu": [
         "arm64"
       ],
@@ -196,9 +196,9 @@
       }
     },
     "node_modules/@esbuild/linux-ia32": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.28.1.tgz",
-      "integrity": "sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.27.7.tgz",
+      "integrity": "sha512-GA48aKNkyQDbd3KtkplYWT102C5sn/EZTY4XROkxONgruHPU72l+gW+FfF8tf2cFjeHaRbWpOYa/uRBz/Xq1Pg==",
       "cpu": [
         "ia32"
       ],
@@ -213,9 +213,9 @@
       }
     },
     "node_modules/@esbuild/linux-loong64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.28.1.tgz",
-      "integrity": "sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.27.7.tgz",
+      "integrity": "sha512-a4POruNM2oWsD4WKvBSEKGIiWQF8fZOAsycHOt6JBpZ+JN2n2JH9WAv56SOyu9X5IqAjqSIPTaJkqN8F7XOQ5Q==",
       "cpu": [
         "loong64"
       ],
@@ -230,9 +230,9 @@
       }
     },
     "node_modules/@esbuild/linux-mips64el": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.28.1.tgz",
-      "integrity": "sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.27.7.tgz",
+      "integrity": "sha512-KabT5I6StirGfIz0FMgl1I+R1H73Gp0ofL9A3nG3i/cYFJzKHhouBV5VWK1CSgKvVaG4q1RNpCTR2LuTVB3fIw==",
       "cpu": [
         "mips64el"
       ],
@@ -247,9 +247,9 @@
       }
     },
     "node_modules/@esbuild/linux-ppc64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.28.1.tgz",
-      "integrity": "sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.27.7.tgz",
+      "integrity": "sha512-gRsL4x6wsGHGRqhtI+ifpN/vpOFTQtnbsupUF5R5YTAg+y/lKelYR1hXbnBdzDjGbMYjVJLJTd2OFmMewAgwlQ==",
       "cpu": [
         "ppc64"
       ],
@@ -264,9 +264,9 @@
       }
     },
     "node_modules/@esbuild/linux-riscv64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.28.1.tgz",
-      "integrity": "sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.27.7.tgz",
+      "integrity": "sha512-hL25LbxO1QOngGzu2U5xeXtxXcW+/GvMN3ejANqXkxZ/opySAZMrc+9LY/WyjAan41unrR3YrmtTsUpwT66InQ==",
       "cpu": [
         "riscv64"
       ],
@@ -281,9 +281,9 @@
       }
     },
     "node_modules/@esbuild/linux-s390x": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.28.1.tgz",
-      "integrity": "sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.27.7.tgz",
+      "integrity": "sha512-2k8go8Ycu1Kb46vEelhu1vqEP+UeRVj2zY1pSuPdgvbd5ykAw82Lrro28vXUrRmzEsUV0NzCf54yARIK8r0fdw==",
       "cpu": [
         "s390x"
       ],
@@ -298,9 +298,9 @@
       }
     },
     "node_modules/@esbuild/linux-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.28.1.tgz",
-      "integrity": "sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.27.7.tgz",
+      "integrity": "sha512-hzznmADPt+OmsYzw1EE33ccA+HPdIqiCRq7cQeL1Jlq2gb1+OyWBkMCrYGBJ+sxVzve2ZJEVeePbLM2iEIZSxA==",
       "cpu": [
         "x64"
       ],
@@ -315,9 +315,9 @@
       }
     },
     "node_modules/@esbuild/netbsd-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.28.1.tgz",
-      "integrity": "sha512-oks0DYbLwWMmaakTsCb+zL4E+aHRVLom9IJZOAthMQEPiQmydXHkziYEsGYRx0uNV/IjEKGAV941JzH02pflqw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.27.7.tgz",
+      "integrity": "sha512-b6pqtrQdigZBwZxAn1UpazEisvwaIDvdbMbmrly7cDTMFnw/+3lVxxCTGOrkPVnsYIosJJXAsILG9XcQS+Yu6w==",
       "cpu": [
         "arm64"
       ],
@@ -332,9 +332,9 @@
       }
     },
     "node_modules/@esbuild/netbsd-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.28.1.tgz",
-      "integrity": "sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.27.7.tgz",
+      "integrity": "sha512-OfatkLojr6U+WN5EDYuoQhtM+1xco+/6FSzJJnuWiUw5eVcicbyK3dq5EeV/QHT1uy6GoDhGbFpprUiHUYggrw==",
       "cpu": [
         "x64"
       ],
@@ -349,9 +349,9 @@
       }
     },
     "node_modules/@esbuild/openbsd-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.28.1.tgz",
-      "integrity": "sha512-MEFJe5C3R8pwXdZ5Y21oo6m7ePiS0d9pWucn99O/wvyJZChoIQKrQDxKrGeW8F5+T0okTHesAmDeiHDTIq0V/Q==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.27.7.tgz",
+      "integrity": "sha512-AFuojMQTxAz75Fo8idVcqoQWEHIXFRbOc1TrVcFSgCZtQfSdc1RXgB3tjOn/krRHENUB4j00bfGjyl2mJrU37A==",
       "cpu": [
         "arm64"
       ],
@@ -366,9 +366,9 @@
       }
     },
     "node_modules/@esbuild/openbsd-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.28.1.tgz",
-      "integrity": "sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.27.7.tgz",
+      "integrity": "sha512-+A1NJmfM8WNDv5CLVQYJ5PshuRm/4cI6WMZRg1by1GwPIQPCTs1GLEUHwiiQGT5zDdyLiRM/l1G0Pv54gvtKIg==",
       "cpu": [
         "x64"
       ],
@@ -383,9 +383,9 @@
       }
     },
     "node_modules/@esbuild/openharmony-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.28.1.tgz",
-      "integrity": "sha512-ge+Z7EXFNt2BO1oAMsVpiQ8EwndV9i1xXerAeTIK7AtPs3bKFXQM7nlRxDSIUIMeueR1CNXxqztLzdNeReKBJg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.27.7.tgz",
+      "integrity": "sha512-+KrvYb/C8zA9CU/g0sR6w2RBw7IGc5J2BPnc3dYc5VJxHCSF1yNMxTV5LQ7GuKteQXZtspjFbiuW5/dOj7H4Yw==",
       "cpu": [
         "arm64"
       ],
@@ -400,9 +400,9 @@
       }
     },
     "node_modules/@esbuild/sunos-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.28.1.tgz",
-      "integrity": "sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.27.7.tgz",
+      "integrity": "sha512-ikktIhFBzQNt/QDyOL580ti9+5mL/YZeUPKU2ivGtGjdTYoqz6jObj6nOMfhASpS4GU4Q/Clh1QtxWAvcYKamA==",
       "cpu": [
         "x64"
       ],
@@ -417,9 +417,9 @@
       }
     },
     "node_modules/@esbuild/win32-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.28.1.tgz",
-      "integrity": "sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.27.7.tgz",
+      "integrity": "sha512-7yRhbHvPqSpRUV7Q20VuDwbjW5kIMwTHpptuUzV+AA46kiPze5Z7qgt6CLCK3pWFrHeNfDd1VKgyP4O+ng17CA==",
       "cpu": [
         "arm64"
       ],
@@ -434,9 +434,9 @@
       }
     },
     "node_modules/@esbuild/win32-ia32": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.28.1.tgz",
-      "integrity": "sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.27.7.tgz",
+      "integrity": "sha512-SmwKXe6VHIyZYbBLJrhOoCJRB/Z1tckzmgTLfFYOfpMAx63BJEaL9ExI8x7v0oAO3Zh6D/Oi1gVxEYr5oUCFhw==",
       "cpu": [
         "ia32"
       ],
@@ -451,9 +451,9 @@
       }
     },
     "node_modules/@esbuild/win32-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.28.1.tgz",
-      "integrity": "sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.27.7.tgz",
+      "integrity": "sha512-56hiAJPhwQ1R4i+21FVF7V8kSD5zZTdHcVuRFMW0hn753vVfQN8xlx4uOPT4xoGH0Z/oVATuR82AiqSTDIpaHg==",
       "cpu": [
         "x64"
       ],
@@ -1165,9 +1165,9 @@
       }
     },
     "node_modules/esbuild": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.1.tgz",
-      "integrity": "sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.27.7.tgz",
+      "integrity": "sha512-IxpibTjyVnmrIQo5aqNpCgoACA/dTKLTlhMHihVHhdkxKyPO1uBBthumT0rdHmcsk9uMonIWS0m4FljWzILh3w==",
       "dev": true,
       "hasInstallScript": true,
       "license": "MIT",
@@ -1178,32 +1178,32 @@
         "node": ">=18"
       },
       "optionalDependencies": {
-        "@esbuild/aix-ppc64": "0.28.1",
-        "@esbuild/android-arm": "0.28.1",
-        "@esbuild/android-arm64": "0.28.1",
-        "@esbuild/android-x64": "0.28.1",
-        "@esbuild/darwin-arm64": "0.28.1",
-        "@esbuild/darwin-x64": "0.28.1",
-        "@esbuild/freebsd-arm64": "0.28.1",
-        "@esbuild/freebsd-x64": "0.28.1",
-        "@esbuild/linux-arm": "0.28.1",
-        "@esbuild/linux-arm64": "0.28.1",
-        "@esbuild/linux-ia32": "0.28.1",
-        "@esbuild/linux-loong64": "0.28.1",
-        "@esbuild/linux-mips64el": "0.28.1",
-        "@esbuild/linux-ppc64": "0.28.1",
-        "@esbuild/linux-riscv64": "0.28.1",
-        "@esbuild/linux-s390x": "0.28.1",
-        "@esbuild/linux-x64": "0.28.1",
-        "@esbuild/netbsd-arm64": "0.28.1",
-        "@esbuild/netbsd-x64": "0.28.1",
-        "@esbuild/openbsd-arm64": "0.28.1",
-        "@esbuild/openbsd-x64": "0.28.1",
-        "@esbuild/openharmony-arm64": "0.28.1",
-        "@esbuild/sunos-x64": "0.28.1",
-        "@esbuild/win32-arm64": "0.28.1",
-        "@esbuild/win32-ia32": "0.28.1",
-        "@esbuild/win32-x64": "0.28.1"
+        "@esbuild/aix-ppc64": "0.27.7",
+        "@esbuild/android-arm": "0.27.7",
+        "@esbuild/android-arm64": "0.27.7",
+        "@esbuild/android-x64": "0.27.7",
+        "@esbuild/darwin-arm64": "0.27.7",
+        "@esbuild/darwin-x64": "0.27.7",
+        "@esbuild/freebsd-arm64": "0.27.7",
+        "@esbuild/freebsd-x64": "0.27.7",
+        "@esbuild/linux-arm": "0.27.7",
+        "@esbuild/linux-arm64": "0.27.7",
+        "@esbuild/linux-ia32": "0.27.7",
+        "@esbuild/linux-loong64": "0.27.7",
+        "@esbuild/linux-mips64el": "0.27.7",
+        "@esbuild/linux-ppc64": "0.27.7",
+        "@esbuild/linux-riscv64": "0.27.7",
+        "@esbuild/linux-s390x": "0.27.7",
+        "@esbuild/linux-x64": "0.27.7",
+        "@esbuild/netbsd-arm64": "0.27.7",
+        "@esbuild/netbsd-x64": "0.27.7",
+        "@esbuild/openbsd-arm64": "0.27.7",
+        "@esbuild/openbsd-x64": "0.27.7",
+        "@esbuild/openharmony-arm64": "0.27.7",
+        "@esbuild/sunos-x64": "0.27.7",
+        "@esbuild/win32-arm64": "0.27.7",
+        "@esbuild/win32-ia32": "0.27.7",
+        "@esbuild/win32-x64": "0.27.7"
       }
     },
     "node_modules/fast-check": {
@@ -1843,6 +1843,490 @@
         "fsevents": "~2.3.3"
       }
     },
+    "node_modules/tsx/node_modules/@esbuild/aix-ppc64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.28.0.tgz",
+      "integrity": "sha512-lhRUCeuOyJQURhTxl4WkpFTjIsbDayJHih5kZC1giwE+MhIzAb7mEsQMqMf18rHLsrb5qI1tafG20mLxEWcWlA==",
+      "cpu": [
+        "ppc64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "aix"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/android-arm": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.28.0.tgz",
+      "integrity": "sha512-wqh0ByljabXLKHeWXYLqoJ5jKC4XBaw6Hk08OfMrCRd2nP2ZQ5eleDZC41XHyCNgktBGYMbqnrJKq/K/lzPMSQ==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/android-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.28.0.tgz",
+      "integrity": "sha512-+WzIXQOSaGs33tLEgYPYe/yQHf0WTU0X42Jca3y8NWMbUVhp7rUnw+vAsRC/QiDrdD31IszMrZy+qwPOPjd+rw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/android-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.28.0.tgz",
+      "integrity": "sha512-+VJggoaKhk2VNNqVL7f6S189UzShHC/mR9EE8rDdSkdpN0KflSwWY/gWjDrNxxisg8Fp1ZCD9jLMo4m0OUfeUA==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/darwin-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.28.0.tgz",
+      "integrity": "sha512-0T+A9WZm+bZ84nZBtk1ckYsOvyA3x7e2Acj1KdVfV4/2tdG4fzUp91YHx+GArWLtwqp77pBXVCPn2We7Letr0Q==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/darwin-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.28.0.tgz",
+      "integrity": "sha512-fyzLm/DLDl/84OCfp2f/XQ4flmORsjU7VKt8HLjvIXChJoFFOIL6pLJPH4Yhd1n1gGFF9mPwtlN5Wf82DZs+LQ==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/freebsd-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.28.0.tgz",
+      "integrity": "sha512-l9GeW5UZBT9k9brBYI+0WDffcRxgHQD8ShN2Ur4xWq/NFzUKm3k5lsH4PdaRgb2w7mI9u61nr2gI2mLI27Nh3Q==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "freebsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/freebsd-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.28.0.tgz",
+      "integrity": "sha512-BXoQai/A0wPO6Es3yFJ7APCiKGc1tdAEOgeTNy3SsB491S3aHn4S4r3e976eUnPdU+NbdtmBuLncYir2tMU9Nw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "freebsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-arm": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.28.0.tgz",
+      "integrity": "sha512-CjaaREJagqJp7iTaNQjjidaNbCKYcd4IDkzbwwxtSvjI7NZm79qiHc8HqciMddQ6CKvJT6aBd8lO9kN/ZudLlw==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.28.0.tgz",
+      "integrity": "sha512-RVyzfb3FWsGA55n6WY0MEIEPURL1FcbhFE6BffZEMEekfCzCIMtB5yyDcFnVbTnwk+CLAgTujmV/Lgvih56W+A==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-ia32": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.28.0.tgz",
+      "integrity": "sha512-KBnSTt1kxl9x70q+ydterVdl+Cn0H18ngRMRCEQfrbqdUuntQQ0LoMZv47uB97NljZFzY6HcfqEZ2SAyIUTQBQ==",
+      "cpu": [
+        "ia32"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-loong64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.28.0.tgz",
+      "integrity": "sha512-zpSlUce1mnxzgBADvxKXX5sl8aYQHo2ezvMNI8I0lbblJtp8V4odlm3Yzlj7gPyt3T8ReksE6bK+pT3WD+aJRg==",
+      "cpu": [
+        "loong64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-mips64el": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.28.0.tgz",
+      "integrity": "sha512-2jIfP6mmjkdmeTlsX/9vmdmhBmKADrWqN7zcdtHIeNSCH1SqIoNI63cYsjQR8J+wGa4Y5izRcSHSm8K3QWmk3w==",
+      "cpu": [
+        "mips64el"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-ppc64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.28.0.tgz",
+      "integrity": "sha512-bc0FE9wWeC0WBm49IQMPSPILRocGTQt3j5KPCA8os6VprfuJ7KD+5PzESSrJ6GmPIPJK965ZJHTUlSA6GNYEhg==",
+      "cpu": [
+        "ppc64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-riscv64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.28.0.tgz",
+      "integrity": "sha512-SQPZOwoTTT/HXFXQJG/vBX8sOFagGqvZyXcgLA3NhIqcBv1BJU1d46c0rGcrij2B56Z2rNiSLaZOYW5cUk7yLQ==",
+      "cpu": [
+        "riscv64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-s390x": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.28.0.tgz",
+      "integrity": "sha512-SCfR0HN8CEEjnYnySJTd2cw0k9OHB/YFzt5zgJEwa+wL/T/raGWYMBqwDNAC6dqFKmJYZoQBRfHjgwLHGSrn3Q==",
+      "cpu": [
+        "s390x"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.28.0.tgz",
+      "integrity": "sha512-us0dSb9iFxIi8srnpl931Nvs65it/Jd2a2K3qs7fz2WfGPHqzfzZTfec7oxZJRNPXPnNYZtanmRc4AL/JwVzHQ==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/netbsd-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.28.0.tgz",
+      "integrity": "sha512-CR/RYotgtCKwtftMwJlUU7xCVNg3lMYZ0RzTmAHSfLCXw3NtZtNpswLEj/Kkf6kEL3Gw+BpOekRX0BYCtklhUw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/netbsd-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.28.0.tgz",
+      "integrity": "sha512-nU1yhmYutL+fQ71Kxnhg8uEOdC0pwEW9entHykTgEbna2pw2dkbFSMeqjjyHZoCmt8SBkOSvV+yNmm94aUrrqw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/openbsd-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.28.0.tgz",
+      "integrity": "sha512-cXb5vApOsRsxsEl4mcZ1XY3D4DzcoMxR/nnc4IyqYs0rTI8ZKmW6kyyg+11Z8yvgMfAEldKzP7AdP64HnSC/6g==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/openbsd-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.28.0.tgz",
+      "integrity": "sha512-8wZM2qqtv9UP3mzy7HiGYNH/zjTA355mpeuA+859TyR+e+Tc08IHYpLJuMsfpDJwoLo1ikIJI8jC3GFjnRClzA==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/openharmony-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.28.0.tgz",
+      "integrity": "sha512-FLGfyizszcef5C3YtoyQDACyg95+dndv79i2EekILBofh5wpCa1KuBqOWKrEHZg3zrL3t5ouE5jgr94vA+Wb2w==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openharmony"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/sunos-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.28.0.tgz",
+      "integrity": "sha512-1ZgjUoEdHZZl/YlV76TSCz9Hqj9h9YmMGAgAPYd+q4SicWNX3G5GCyx9uhQWSLcbvPW8Ni7lj4gDa1T40akdlw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "sunos"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/win32-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.28.0.tgz",
+      "integrity": "sha512-Q9StnDmQ/enxnpxCCLSg0oo4+34B9TdXpuyPeTedN/6+iXBJ4J+zwfQI28u/Jl40nOYAxGoNi7mFP40RUtkmUA==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/win32-ia32": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.28.0.tgz",
+      "integrity": "sha512-zF3ag/gfiCe6U2iczcRzSYJKH1DCI+ByzSENHlM2FcDbEeo5Zd2C86Aq0tKUYAJJ1obRP84ymxIAksZUcdztHA==",
+      "cpu": [
+        "ia32"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/win32-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.28.0.tgz",
+      "integrity": "sha512-pEl1bO9mfAmIC+tW5btTmrKaujg3zGtUmWNdCw/xs70FBjwAL3o9OEKNHvNmnyylD6ubxUERiEhdsL0xBQ9efw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/esbuild": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.0.tgz",
+      "integrity": "sha512-sNR9MHpXSUV/XB4zmsFKN+QgVG82Cc7+/aaxJ8Adi8hyOac+EXptIp45QBPaVyX3N70664wRbTcLTOemCAnyqw==",
+      "dev": true,
+      "hasInstallScript": true,
+      "license": "MIT",
+      "bin": {
+        "esbuild": "bin/esbuild"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "optionalDependencies": {
+        "@esbuild/aix-ppc64": "0.28.0",
+        "@esbuild/android-arm": "0.28.0",
+        "@esbuild/android-arm64": "0.28.0",
+        "@esbuild/android-x64": "0.28.0",
+        "@esbuild/darwin-arm64": "0.28.0",
+        "@esbuild/darwin-x64": "0.28.0",
+        "@esbuild/freebsd-arm64": "0.28.0",
+        "@esbuild/freebsd-x64": "0.28.0",
+        "@esbuild/linux-arm": "0.28.0",
+        "@esbuild/linux-arm64": "0.28.0",
+        "@esbuild/linux-ia32": "0.28.0",
+        "@esbuild/linux-loong64": "0.28.0",
+        "@esbuild/linux-mips64el": "0.28.0",
+        "@esbuild/linux-ppc64": "0.28.0",
+        "@esbuild/linux-riscv64": "0.28.0",
+        "@esbuild/linux-s390x": "0.28.0",
+        "@esbuild/linux-x64": "0.28.0",
+        "@esbuild/netbsd-arm64": "0.28.0",
+        "@esbuild/netbsd-x64": "0.28.0",
+        "@esbuild/openbsd-arm64": "0.28.0",
+        "@esbuild/openbsd-x64": "0.28.0",
+        "@esbuild/openharmony-arm64": "0.28.0",
+        "@esbuild/sunos-x64": "0.28.0",
+        "@esbuild/win32-arm64": "0.28.0",
+        "@esbuild/win32-ia32": "0.28.0",
+        "@esbuild/win32-x64": "0.28.0"
+      }
+    },
     "node_modules/typescript": {
       "version": "5.9.3",
       "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",

@omniroute/opencode-plugin/package.json

@@ -1,18 +1,21 @@
 {
   "name": "@omniroute/opencode-plugin",
-  "version": "0.2.0",
+  "version": "0.1.0",
   "description": "OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @opencode-ai/plugin contract.",
   "type": "module",
-  "main": "./dist/index.js",
+  "main": "./dist/index.cjs",
+  "module": "./dist/index.js",
   "types": "./dist/index.d.ts",
   "exports": {
     ".": {
-      "types": "./dist/index.d.ts",
-      "import": "./dist/index.js"
-    },
-    "./runtime": {
-      "types": "./dist/index.d.ts",
-      "import": "./dist/index.js"
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
+      }
     }
   },
   "files": [
@@ -23,7 +26,7 @@
   "scripts": {
     "build": "tsup",
     "clean": "rm -rf dist",
-    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts",
+    "test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts",
     "prepublishOnly": "npm run clean && npm run build && npm test"
   },
   "keywords": [
@@ -66,8 +69,5 @@
     "tsup": "^8.5.1",
     "tsx": "^4.22.3",
     "typescript": "^5.9.3"
-  },
-  "overrides": {
-    "esbuild": "^0.28.1"
   }
 }

@omniroute/opencode-plugin/tests/auth.test.ts

@@ -13,12 +13,12 @@ import { createOmniRouteAuthHook } from "../src/index.js";
 
 test("createOmniRouteAuthHook: default providerId is 'omniroute'", () => {
   const hook = createOmniRouteAuthHook();
-  assert.equal(hook.provider, "opencode-omniroute");
+  assert.equal(hook.provider, "omniroute");
 });
 
 test("createOmniRouteAuthHook: custom providerId binds to hook.provider (multi-instance)", () => {
   const hook = createOmniRouteAuthHook({ providerId: "omniroute-preprod" });
-  assert.equal(hook.provider, "opencode-omniroute-preprod");
+  assert.equal(hook.provider, "omniroute-preprod");
 });
 
 test("createOmniRouteAuthHook: methods[0] is type 'api' with label including displayName", () => {
@@ -30,7 +30,7 @@ test("createOmniRouteAuthHook: methods[0] is type 'api' with label including dis
   assert.equal(m.label, "OmniRoute API Key");
 
   const custom = createOmniRouteAuthHook({ providerId: "omniroute-preprod" });
-  assert.equal(custom.methods[0].label, "OmniRoute (opencode-omniroute-preprod) API Key");
+  assert.equal(custom.methods[0].label, "OmniRoute (omniroute-preprod) API Key");
 });
 
 test("createOmniRouteAuthHook: prompts[0] uses key='apiKey' per @opencode-ai/plugin contract", () => {

@omniroute/opencode-plugin/tests/combos.test.ts

@@ -447,13 +447,13 @@ test("models() returns combo entries merged into the map", async () => {
 
   // 3 raw models + 1 combo = 4 entries
   assert.equal(Object.keys(out).length, 4);
-  assert.ok(out["omniroute/claude-primary"]);
-  assert.ok(out["omniroute/claude-secondary"]);
-  assert.ok(out["omniroute/gemini-3-flash"]);
-  assert.ok(out["omniroute/claude-tier"]);
+  assert.ok(out["claude-primary"]);
+  assert.ok(out["claude-secondary"]);
+  assert.ok(out["gemini-3-flash"]);
+  assert.ok(out["combo/claude-tier"]);
 
-  const combo = out["omniroute/claude-tier"];
-  assert.equal(combo.name, "Claude Tier");
+  const combo = out["combo/claude-tier"];
+  assert.equal(combo.name, "Combo: Claude Tier");
   assert.equal(combo.providerID, "omniroute");
   // LCD over claude-primary (200k, reasoning) + claude-secondary (100k, no reasoning)
   assert.equal(combo.limit.context, 100_000);
@@ -478,11 +478,11 @@ test("models(): combo with unknown member ids degrades to all-false LCD posture"
     { fetcher: modelsFetcher, combosFetcher }
   );
   const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
-  assert.ok(out["omniroute/phantom-combo"]);
+  assert.ok(out["combo/phantom-combo"]);
   // With zero resolvable members, LCD = all-false (defensive posture).
-  assert.equal(out["omniroute/phantom-combo"].capabilities.toolcall, false);
-  assert.equal(out["omniroute/phantom-combo"].capabilities.reasoning, false);
-  assert.equal(out["omniroute/phantom-combo"].limit.context, 0);
+  assert.equal(out["combo/phantom-combo"].capabilities.toolcall, false);
+  assert.equal(out["combo/phantom-combo"].capabilities.reasoning, false);
+  assert.equal(out["combo/phantom-combo"].limit.context, 0);
 });
 
 test("models(): hidden combos are excluded from the map", async () => {
@@ -505,11 +505,11 @@ test("models(): hidden combos are excluded from the map", async () => {
     { fetcher: modelsFetcher, combosFetcher }
   );
   const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
-  assert.ok(out["omniroute/visible"]);
-  assert.ok(!out["omniroute/hidden"], "hidden combo must be omitted");
+  assert.ok(out["combo/visible"]);
+  assert.ok(!out["combo/hidden"], "hidden combo must be omitted");
 });
 
-test("models(): combo name exactly matches raw model id → raw deleted, raw deleted, no warn", async () => {
+test("models(): combo name exactly matches raw model id → raw deleted, combo lives at combo/ key, no warn", async () => {
   // Combo.name === raw model id triggers the dedup deletion. This mirrors
   // the real OmniRoute payload where /v1/models pre-mirrors combos as
   // no-slash raw entries whose ids match /api/combos friendly names.
@@ -529,9 +529,10 @@ test("models(): combo name exactly matches raw model id → raw deleted, raw del
     return hook.models!({} as never, { auth: apiAuth("sk-z") as never });
   });
 
-  // Raw model replaced by combo of the same key; combo now lives at the bare slug.
-  assert.ok(out["omniroute/claude-primary"], "combo surfaces under prefixed key");
-  assert.equal(out["omniroute/claude-primary"].name, "claude-primary");
+  // Raw model deleted by combo-name dedup; combo surfaces under combo/<slug>.
+  assert.equal(out["claude-primary"], undefined, "raw deleted by combo-name dedup");
+  assert.ok(out["combo/claude-primary"], "combo surfaces under combo/ namespace");
+  assert.equal(out["combo/claude-primary"].name, "Combo: claude-primary");
 
   // No collision warning fires — dedup makes keys disjoint.
   const collisionWarns = warnings.filter((w) => {
@@ -542,7 +543,7 @@ test("models(): combo name exactly matches raw model id → raw deleted, raw del
 });
 
 test("models(): two combos with same slug → second gets disambiguator suffix", async () => {
-  // Both combos slug to `claude` — second must get `claude-<id-prefix>`.
+  // Both combos slug to `claude` — second must get `combo/claude-<id-prefix>`.
   const combos: OmniRouteRawCombo[] = [
     {
       id: "uuid-a",
@@ -565,8 +566,8 @@ test("models(): two combos with same slug → second gets disambiguator suffix",
 
   const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
   // First combo gets the bare slug; second gets disambiguated.
-  assert.ok(out["omniroute/claude"], "first combo at prefixed slug");
-  assert.ok(out["omniroute/claude-uuid"], "second combo disambiguated by id prefix");
+  assert.ok(out["combo/claude"], "first combo at bare slug");
+  assert.ok(out["combo/claude-uuid"], "second combo disambiguated by id prefix");
 });
 
 test("models(): combos fetch fails → falls back to models-only, warn emitted, no throw", async () => {
@@ -583,8 +584,8 @@ test("models(): combos fetch fails → falls back to models-only, warn emitted,
 
   // Catalog includes the models but NOT any combo entries.
   assert.equal(Object.keys(out).length, 2);
-  assert.ok(out["omniroute/claude-primary"]);
-  assert.ok(out["omniroute/claude-secondary"]);
+  assert.ok(out["claude-primary"]);
+  assert.ok(out["claude-secondary"]);
 
   // Soft-fail warning surfaced.
   const softFail = warnings.find((w) => {
@@ -609,7 +610,7 @@ test("models(): combos cached + reused within TTL (one combo fetch per TTL windo
   const second = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
   assert.equal(combosFetcher.callCount(), 1, "combos fetched only once within TTL");
   assert.equal(modelsFetcher.callCount(), 1, "models fetched only once within TTL");
-  assert.ok(second["omniroute/claude-tier"]);
+  assert.ok(second["combo/claude-tier"]);
 });
 
 test("models(): combos refetched after TTL expiry (same key as models)", async () => {
@@ -638,74 +639,3 @@ test("models(): combos fetcher receives the resolved baseURL + apiKey", async ()
   await hook.models!({} as never, { auth: apiAuth("sk-spy") as never });
   assert.deepEqual(combosFetcher.callsBy()[0], ["https://or.example.com/v1", "sk-spy"]);
 });
-
-test("models(): nested combo-ref context is the min of nested + raw members", async () => {
-  // Top-level combo MASTER-LIGHT has 1 raw model (claude-primary, 200k)
-  // and 2 combo-refs: OldLLM (8k member) and KIRO (32k member). The OLD
-  // plugin would advertise 200k (only the raw model); the fix should
-  // make it advertise 8k (the bottleneck across the member graph).
-  const modelsFetcher = stubModelsFetcher([
-    MODEL_PRIMARY,
-    {
-      id: "oldllm-member-1",
-      context_length: 8_000,
-      max_output_tokens: 4_000,
-      capabilities: {
-        tool_calling: false,
-        reasoning: false,
-        vision: false,
-        thinking: false,
-        temperature: true,
-      },
-      input_modalities: ["text"],
-      output_modalities: ["text"],
-    },
-    {
-      id: "kiro-member-1",
-      context_length: 32_000,
-      max_output_tokens: 8_000,
-      capabilities: {
-        tool_calling: true,
-        reasoning: false,
-        vision: false,
-        thinking: false,
-        temperature: true,
-      },
-      input_modalities: ["text"],
-      output_modalities: ["text"],
-    },
-  ]);
-  const combosFetcher = stubCombosFetcher([
-    {
-      id: "oldllm",
-      name: "OldLLM",
-      models: [{ id: "s1", kind: "model", model: "oldllm-member-1", weight: 100 }],
-    },
-    {
-      id: "kiro",
-      name: "KIRO",
-      models: [{ id: "s1", kind: "model", model: "kiro-member-1", weight: 100 }],
-    },
-    {
-      id: "master-light",
-      name: "MASTER-LIGHT",
-      models: [
-        { id: "r1", kind: "model", model: "claude-primary", weight: 50 },
-        { id: "r2", kind: "combo-ref", comboName: "OldLLM", weight: 25 },
-        { id: "r3", kind: "combo-ref", comboName: "KIRO", weight: 25 },
-      ],
-    },
-  ]);
-  const hook = createOmniRouteProviderHook(
-    { baseURL: "https://or.example.com/v1" },
-    { fetcher: modelsFetcher, combosFetcher }
-  );
-  const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
-  const masterLight = out["omniroute/master-light"];
-  assert.ok(masterLight, "MASTER-LIGHT entry must exist");
-  assert.equal(
-    masterLight.limit.context,
-    8_000,
-    `expected 8_000 (OldLLM bottleneck), got ${masterLight.limit.context}`
-  );
-});

@omniroute/opencode-plugin/tests/config-shim.test.ts

@@ -203,7 +203,7 @@ function makeInput(initialProvider: Record<string, unknown> = {}): Config {
 
 test("config: with valid auth.json + apiKey + baseURL → mutates input.provider[id] with stripped models block", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test-1", baseURL: "https://or.example.com/v1" },
+    omniroute: { type: "api", key: "sk-test-1", baseURL: "https://or.example.com/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
   const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
@@ -217,8 +217,8 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
   await hook(input);
 
   const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
-  const entry = provider["opencode-omniroute"];
-  assert.ok(entry, "input.provider['opencode-omniroute'] set");
+  const entry = provider.omniroute;
+  assert.ok(entry, "input.provider.omniroute set");
   assert.equal(entry.npm, "@ai-sdk/openai-compatible");
   assert.equal(entry.name, "OmniRoute");
   assert.equal(entry.options.baseURL, "https://or.example.com/v1");
@@ -227,7 +227,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
   // Stripped per-model shape: name + cap flags + modalities + (optional)
   // cost. OC's SDK static schema accepts only `limit.{context,output}` —
   // `limit.input` is NOT in the SDK shape and gets dropped silently.
-  const claude = entry.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = entry.models["claude-sonnet-4-6"];
   assert.ok(claude, "claude model surfaced");
   assert.equal(claude.name, "claude-sonnet-4-6");
   assert.equal(claude.attachment, true);
@@ -246,75 +246,16 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
   assert.deepEqual(claude.modalities?.input, ["text", "image"]);
   assert.deepEqual(claude.modalities?.output, ["text"]);
 
-  // Combo surfaces under bare key + LCD'd
+  // Combo surfaces under `combo/<friendly-name>` namespace + LCD'd
   // (gemini's reasoning=false → combo reasoning=false).
-  const combo = entry.models["opencode-omniroute/claude-tier"];
-  assert.ok(combo, "combo surfaced under bare key");
-  assert.equal(combo.name, "Claude Tier");
+  const combo = entry.models["combo/claude-tier"];
+  assert.ok(combo, "combo surfaced under combo/ namespace");
+  assert.equal(combo.name, "Combo: Claude Tier");
   assert.equal(combo.reasoning, false, "LCD: any member reasoning=false → combo reasoning=false");
   assert.equal(combo.tool_call, true);
   assert.equal(combo.limit?.context, 200_000, "LCD: min(200_000, 1_000_000)");
 });
 
-// ────────────────────────────────────────────────────────────────────────────
-// 1b. Dual-key fallback (#5027) — auth.json stored under the BARE providerId
-//     (pre-auto-prefix login) must still resolve when the active providerId is
-//     prefixed (`opencode-omniroute`). Without the fallback the lookup misses
-//     the stored key and the user is forced to re-auth.
-// ────────────────────────────────────────────────────────────────────────────
-
-test("config: auth.json under bare key (pre-prefix login) resolves via dual-key fallback", async () => {
-  // Stored under bare `omniroute` (the key OC wrote before the auto-prefix fix),
-  // but the resolved providerId is now `opencode-omniroute`.
-  const readAuthJson = stubReadAuthJson({
-    omniroute: { type: "api", key: "sk-bare-1", baseURL: "https://or.example.com/v1" },
-  });
-  const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
-  const combosFetcher = stubCombosFetcher([]);
-  const logger = captureWarn();
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" }, // resolves to opencode-omniroute internally
-    { readAuthJson, fetcher, combosFetcher, logger }
-  );
-  const input = makeInput();
-  await hook(input);
-
-  const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
-  const entry = provider["opencode-omniroute"];
-  assert.ok(entry, "provider entry published from bare-key apiKey");
-  assert.equal(entry.options.apiKey, "sk-bare-1", "apiKey resolved from the bare auth.json key");
-  assert.equal(entry.options.baseURL, "https://or.example.com/v1");
-});
-
-test("config: prefixed key wins over bare key when both present (dual-key precedence)", async () => {
-  const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-prefixed", baseURL: "https://pref.example/v1" },
-    omniroute: { type: "api", key: "sk-bare", baseURL: "https://bare.example/v1" },
-  });
-  const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
-  const combosFetcher = stubCombosFetcher([]);
-  const logger = captureWarn();
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    { readAuthJson, fetcher, combosFetcher, logger }
-  );
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry);
-  assert.equal(
-    entry.options.apiKey,
-    "sk-prefixed",
-    "prefixed key takes precedence (looked up first)"
-  );
-  assert.equal(entry.options.baseURL, "https://pref.example/v1");
-});
-
 // ────────────────────────────────────────────────────────────────────────────
 // 2. Missing auth.json → no-op, no throw, no mutation
 // ────────────────────────────────────────────────────────────────────────────
@@ -382,7 +323,7 @@ test("config: existing input.provider[id] → no overwrite (respect manual overr
     models: { "manual-model": { name: "manual-model" } },
   };
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -392,11 +333,11 @@ test("config: existing input.provider[id] → no overwrite (respect manual overr
     { providerId: "omniroute" },
     { readAuthJson, fetcher, combosFetcher, logger }
   );
-  const input = makeInput({ "opencode-omniroute": manual });
+  const input = makeInput({ omniroute: manual });
   await hook(input);
 
   const provider = (input as { provider: Record<string, unknown> }).provider;
-  assert.equal(provider["opencode-omniroute"], manual, "manual override preserved by reference");
+  assert.equal(provider.omniroute, manual, "manual override preserved by reference");
   assert.equal(fetcher.callCount(), 0, "no fetch — short-circuited before I/O");
   assert.equal(readAuthJson.callCount(), 0, "no auth.json read either");
   assert.ok(
@@ -411,7 +352,7 @@ test("config: existing input.provider[id] → no overwrite (respect manual overr
 
 test("config: fetchers throw → warn + emit stub entry with models: {}", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = throwingModelsFetcher();
   const combosFetcher = throwingCombosFetcher();
@@ -427,9 +368,8 @@ test("config: fetchers throw → warn + emit stub entry with models: {}", async
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry, "stub provider entry published even when fetchers fail");
   assert.equal(entry.npm, "@ai-sdk/openai-compatible");
   assert.deepEqual(entry.models, {}, "models stub is empty object");
@@ -452,7 +392,7 @@ test("config: fetchers throw → warn + emit stub entry with models: {}", async
 
 test("config: combos fetcher throws → emit models-only catalog (no combos in models block)", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
   const combosFetcher = throwingCombosFetcher();
@@ -465,16 +405,12 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry);
   const ids = Object.keys(entry.models).sort();
-  assert.deepEqual(ids, [
-    "opencode-omniroute/claude-sonnet-4-6",
-    "opencode-omniroute/gemini-3-flash",
-  ]);
-  assert.equal(entry.models["opencode-omniroute/claude-tier"], undefined, "no combo entry");
+  assert.deepEqual(ids, ["claude-sonnet-4-6", "gemini-3-flash"]);
+  assert.equal(entry.models["combo-claude-tier"], undefined, "no combo entry");
   assert.ok(
     logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
     "combos-fetch breadcrumb emitted"
@@ -487,7 +423,7 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
 
 test("config: baseURL from auth.json takes precedence when opts.baseURL absent", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://creds.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://creds.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -501,15 +437,14 @@ test("config: baseURL from auth.json takes precedence when opts.baseURL absent",
   await hook(input);
 
   assert.equal(fetcher.callsBy()[0][0], "https://creds.example/v1");
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.equal(entry.options.baseURL, "https://creds.example/v1");
 });
 
 test("config: opts.baseURL wins over auth.json's stored baseURL", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://creds.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://creds.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -523,15 +458,14 @@ test("config: opts.baseURL wins over auth.json's stored baseURL", async () => {
   await hook(input);
 
   assert.equal(fetcher.callsBy()[0][0], "https://opts.example/v1");
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.equal(entry.options.baseURL, "https://opts.example/v1");
 });
 
 test("config: no baseURL resolvable (no opts, no auth.json baseURL) → no-op", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test" }, // NO baseURL on the credential
+    omniroute: { type: "api", key: "sk-test" }, // NO baseURL on the credential
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -559,12 +493,12 @@ test("config: no baseURL resolvable (no opts, no auth.json baseURL) → no-op",
 
 test("config: multi-instance — two plugins with different providerIds publish to their own keys without collision", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute-prod": {
+    "omniroute-prod": {
       type: "api",
       key: "sk-prod",
       baseURL: "https://prod.example/v1",
     },
-    "opencode-omniroute-preprod": {
+    "omniroute-preprod": {
       type: "api",
       key: "sk-preprod",
       baseURL: "https://preprod.example/v1",
@@ -588,18 +522,15 @@ test("config: multi-instance — two plugins with different providerIds publish
   await hookB(input);
 
   const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
-  assert.ok(provider["opencode-omniroute-prod"], "prod block present");
-  assert.ok(provider["opencode-omniroute-preprod"], "preprod block present");
-  assert.equal(provider["opencode-omniroute-prod"].options.apiKey, "sk-prod");
-  assert.equal(provider["opencode-omniroute-preprod"].options.apiKey, "sk-preprod");
-  assert.equal(provider["opencode-omniroute-prod"].options.baseURL, "https://prod.example/v1");
-  assert.equal(
-    provider["opencode-omniroute-preprod"].options.baseURL,
-    "https://preprod.example/v1"
-  );
+  assert.ok(provider["omniroute-prod"], "prod block present");
+  assert.ok(provider["omniroute-preprod"], "preprod block present");
+  assert.equal(provider["omniroute-prod"].options.apiKey, "sk-prod");
+  assert.equal(provider["omniroute-preprod"].options.apiKey, "sk-preprod");
+  assert.equal(provider["omniroute-prod"].options.baseURL, "https://prod.example/v1");
+  assert.equal(provider["omniroute-preprod"].options.baseURL, "https://preprod.example/v1");
   assert.notEqual(
-    provider["opencode-omniroute-prod"],
-    provider["opencode-omniroute-preprod"],
+    provider["omniroute-prod"],
+    provider["omniroute-preprod"],
     "blocks are distinct references"
   );
 });
@@ -611,7 +542,7 @@ test("config: multi-instance — two plugins with different providerIds publish
 
 test("config + provider share cache: second call uses cached fetch result (single fetch per TTL)", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
@@ -643,7 +574,7 @@ test("config + provider share cache: second call uses cached fetch result (singl
 
 test("provider → config order also dedupes (cache populated by provider, consumed by config)", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-reverse", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-reverse", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -707,7 +638,6 @@ test("buildStaticProviderEntry: stripped per-model shape matches sibling @omniro
     "cost",
     "limit",
     "modalities",
-    "providerID",
   ]);
   for (const [id, entry] of Object.entries(block.models)) {
     for (const key of Object.keys(entry)) {
@@ -723,7 +653,7 @@ test("buildStaticProviderEntry: stripped per-model shape matches sibling @omniro
   }
 
   // Sanity: claude entry has all expected stripped fields.
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.equal(typeof claude.name, "string");
   assert.equal(typeof claude.attachment, "boolean");
   assert.equal(typeof claude.reasoning, "boolean");
@@ -748,8 +678,8 @@ test("buildStaticProviderEntry: hidden combos are excluded", () => {
     "https://or.example/v1",
     "sk-test"
   );
-  assert.equal(block.models["opencode-omniroute/claude-tier"], undefined);
-  assert.ok(block.models["opencode-omniroute/claude-sonnet-4-6"]);
+  assert.equal(block.models["combo-claude-tier"], undefined);
+  assert.ok(block.models["claude-sonnet-4-6"]);
 });
 
 // ────────────────────────────────────────────────────────────────────────────
@@ -765,7 +695,7 @@ test("buildStaticProviderEntry: emits modalities.input from raw.input_modalities
     "https://or.example/v1",
     "sk-test"
   );
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.deepEqual(claude.modalities?.input, ["text", "image"]);
   assert.deepEqual(claude.modalities?.output, ["text"]);
 });
@@ -779,7 +709,7 @@ test("buildStaticProviderEntry: never emits limit.input (OC SDK rejects it)", ()
     "https://or.example/v1",
     "sk-test"
   );
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.equal((claude.limit as Record<string, unknown>).input, undefined);
   assert.equal(typeof claude.limit?.context, "number");
   assert.equal(typeof claude.limit?.output, "number");
@@ -807,7 +737,7 @@ test("buildStaticProviderEntry: emits cost when enrichment carries pricing", ()
     "sk-test",
     enrichment
   );
-  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
+  const claude = block.models["claude-sonnet-4-6"];
   assert.equal(claude.cost?.input, 3);
   assert.equal(claude.cost?.output, 15);
   assert.equal(claude.cost?.cache_read, 0.3);
@@ -828,8 +758,8 @@ test("buildStaticProviderEntry: emits release_date when raw carries it; omits wh
     "https://or.example/v1",
     "sk-test"
   );
-  assert.equal(block.models["opencode-omniroute/claude-with-date"].release_date, "2026-02-19");
-  assert.equal(block.models["opencode-omniroute/gemini-3-flash"].release_date, undefined);
+  assert.equal(block.models["claude-with-date"].release_date, "2026-02-19");
+  assert.equal(block.models["gemini-3-flash"].release_date, undefined);
 });
 
 test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)", () => {
@@ -858,7 +788,7 @@ test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)
     "https://or.example/v1",
     "sk-test"
   );
-  const combo = block.models["opencode-omniroute/mixed-tier"];
+  const combo = block.models["combo/mixed-tier"];
   assert.ok(combo, "combo emitted under slug key");
   // claude has text+image, text-only has text → intersection drops image.
   assert.deepEqual(combo.modalities?.input, ["text"]);
@@ -882,7 +812,7 @@ test("OmniRoutePlugin factory exposes config hook alongside auth + provider", as
 
 test("config: auth.json entry of wrong type (oauth) → no-op", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "oauth", refresh: "r", access: "a", expires: 0 },
+    omniroute: { type: "oauth", refresh: "r", access: "a", expires: 0 },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -919,7 +849,7 @@ test("config: readAuthJson throws → treat as missing file (silent fallback)",
 
 test("config: initialises input.provider when undefined", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -934,7 +864,7 @@ test("config: initialises input.provider when undefined", async () => {
   await hook(input);
   const provider = (input as { provider?: Record<string, unknown> }).provider;
   assert.ok(provider, "provider bag initialised");
-  assert.ok(provider!["opencode-omniroute"]);
+  assert.ok(provider!.omniroute);
 });
 
 // ────────────────────────────────────────────────────────────────────────────
@@ -944,7 +874,7 @@ test("config: initialises input.provider when undefined", async () => {
 
 test("config: enrichment fetched + name overlaid on raw-model entries", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
   const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
@@ -963,20 +893,19 @@ test("config: enrichment fetched + name overlaid on raw-model entries", async ()
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry);
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
-  assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini 3 Flash");
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  assert.equal(entry.models["gemini-3-flash"].name, "Gemini 3 Flash");
   // Combo names still come from /api/combos — enrichment overlay does NOT touch combos.
-  assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
+  assert.equal(entry.models["combo/claude-tier"].name, "Combo: Claude Tier");
   assert.equal(enrichmentFetcher.callCount(), 1);
 });
 
 test("config: features.enrichment=false skips enrichment fetch + keeps raw-id names", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -994,21 +923,16 @@ test("config: features.enrichment=false skips enrichment fetch + keeps raw-id na
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry);
   assert.equal(enrichmentFetcher.callCount(), 0, "enrichment fetch suppressed by feature flag");
-  assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
-    "claude-sonnet-4-6",
-    "raw id retained"
-  );
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "claude-sonnet-4-6", "raw id retained");
 });
 
 test("config: enrichment fetcher throws → soft-fail (warn + raw-id static catalog)", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1022,15 +946,10 @@ test("config: enrichment fetcher throws → soft-fail (warn + raw-id static cata
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry, "static block still published on enrichment failure");
-  assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
-    "claude-sonnet-4-6",
-    "raw id retained"
-  );
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "claude-sonnet-4-6", "raw id retained");
   assert.equal(enrichmentFetcher.callCount(), 1);
   assert.ok(
     logger.entries.some((e) => String(e[0]).includes("/api/pricing/models fetch failed")),
@@ -1071,7 +990,7 @@ const MODEL_NV_LLAMA: OmniRouteRawModelEntry = {
 
 test("config: usableOnly=false → no filter (existing behavior)", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CC_OPUS, MODEL_NV_LLAMA]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1093,9 +1012,8 @@ test("config: usableOnly=false → no filter (existing behavior)", async () => {
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry.models["cc/claude-opus-4-7"], "claude kept");
   assert.ok(entry.models["nvidia/llama-3-70b"], "nvidia kept (filter off)");
   assert.equal(providersFetcher.callCount(), 0, "providers fetch not called when feature off");
@@ -1103,7 +1021,7 @@ test("config: usableOnly=false → no filter (existing behavior)", async () => {
 
 test("config: usableOnly=true → drops models for non-usable providers, keeps usable + unknown", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([
     MODEL_CC_OPUS,
@@ -1143,9 +1061,8 @@ test("config: usableOnly=true → drops models for non-usable providers, keeps u
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry.models["cc/claude-opus-4-7"], "claude kept (active)");
   assert.equal(entry.models["nvidia/llama-3-70b"], undefined, "nvidia dropped (error status)");
   assert.ok(entry.models["agentrouter/synthetic-1"], "unknown prefix kept (subtract-filter)");
@@ -1154,7 +1071,7 @@ test("config: usableOnly=true → drops models for non-usable providers, keeps u
 
 test("config: usableOnly=true + providers fetch fails → soft-fail keeps everything", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CC_OPUS, MODEL_NV_LLAMA]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1175,9 +1092,8 @@ test("config: usableOnly=true + providers fetch fails → soft-fail keeps everyt
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry.models["cc/claude-opus-4-7"]);
   assert.ok(entry.models["nvidia/llama-3-70b"], "soft-fail keeps both");
   assert.ok(
@@ -1188,7 +1104,7 @@ test("config: usableOnly=true + providers fetch fails → soft-fail keeps everyt
 
 test("config: diskCache hydrates stale snapshot when /v1/models throws", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = throwingModelsFetcher();
   const combosFetcher = stubCombosFetcher([]);
@@ -1225,15 +1141,11 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
-    "stale snapshot hydrated into static block"
-  );
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
+  assert.ok(entry.models["claude-sonnet-4-6"], "stale snapshot hydrated into static block");
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "Claude Sonnet 4.6 (cached)",
     "stale enrichment also reused"
   );
@@ -1246,7 +1158,7 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
 
 test("config: cached rawEnrichment from earlier provider hook is reused (no refetch)", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-shared", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1278,10 +1190,9 @@ test("config: cached rawEnrichment from earlier provider hook is reused (no refe
   await configHook(input);
   assert.equal(enrichmentFetcher.callCount(), 1, "config reused cached enrichment");
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
 });
 
 // ─────────────────────────────────────────────────────────────────────
@@ -1292,7 +1203,7 @@ test("config: cached rawEnrichment from earlier provider hook is reused (no refe
 
 test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-model names", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE, MODEL_GEMINI]);
   const combosFetcher = stubCombosFetcher([COMBO_CLAUDE_TIER]);
@@ -1311,9 +1222,9 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
         "gemini-3-flash",
         {
           name: "Gemini 3 Flash",
-          providerAlias: "gemini",
-          providerCanonical: "gemini",
-          providerDisplayName: "Gemini",
+          providerAlias: "gemini-cli",
+          providerCanonical: "gemini-cli",
+          providerDisplayName: "Gemini-cli",
         },
       ],
     ])
@@ -1327,22 +1238,18 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.ok(entry);
-  assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
-    "Claude - Claude Sonnet 4.6"
-  );
-  assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude - Claude Sonnet 4.6");
+  assert.equal(entry.models["gemini-3-flash"].name, "Gemini-cli - Gemini 3 Flash");
   // Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
-  assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
+  assert.equal(entry.models["combo/claude-tier"].name, "Combo: Claude Tier");
 });
 
 test("config: providerTag=false suppresses the suffix", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1360,11 +1267,10 @@ test("config: providerTag=false suppresses the suffix", async () => {
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
   assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
+    entry.models["claude-sonnet-4-6"].name,
     "Claude Sonnet 4.6",
     "enriched name kept, provider tag suppressed"
   );
@@ -1372,7 +1278,7 @@ test("config: providerTag=false suppresses the suffix", async () => {
 
 test("config: providerTag falls back to UPPER(alias) when providerDisplayName missing", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1393,15 +1299,14 @@ test("config: providerTag falls back to UPPER(alias) when providerDisplayName mi
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
 });
 
 test("config: providerTag skipped entirely when neither providerDisplayName nor providerAlias set", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1420,15 +1325,14 @@ test("config: providerTag skipped entirely when neither providerDisplayName nor
   const input = makeInput();
   await hook(input);
 
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
+  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
 });
 
 test("config: providerTag is idempotent — second hook call doesn't double-suffix", async () => {
   const readAuthJson = stubReadAuthJson({
-    "opencode-omniroute": { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
+    omniroute: { type: "api", key: "sk-test", baseURL: "https://or.example/v1" },
   });
   const fetcher = stubModelsFetcher([MODEL_CLAUDE]);
   const combosFetcher = stubCombosFetcher([]);
@@ -1447,76 +1351,14 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
 
   const inputA = makeInput();
   await hook(inputA);
-  const entryA = (inputA as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.equal(
-    entryA.models["opencode-omniroute/claude-sonnet-4-6"].name,
-    "Claude - Claude Sonnet 4.6"
-  );
+  const entryA = (inputA as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
+  assert.equal(entryA.models["claude-sonnet-4-6"].name, "Claude - Claude Sonnet 4.6");
 
   // Second invocation (cache hit) — name must still be single-suffixed.
   const inputB = makeInput();
   await hook(inputB);
-  const entryB = (inputB as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.equal(
-    entryB.models["opencode-omniroute/claude-sonnet-4-6"].name,
-    "Claude - Claude Sonnet 4.6"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// T-NN: nested combo-ref resolution in the static catalog
-// (mirrors the dynamic-catalog fix in combos.test.ts)
-// ────────────────────────────────────────────────────────────────────────────
-
-test("buildStaticProviderEntry: nested combo-ref context is the bottleneck across the graph", () => {
-  const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
-  const rawModels: OmniRouteRawModelEntry[] = [
-    {
-      id: "raw-big",
-      context_length: 200_000,
-      max_output_tokens: 64_000,
-      capabilities: { tool_calling: true, reasoning: true, vision: false, temperature: true },
-      input_modalities: ["text"],
-      output_modalities: ["text"],
-    },
-    {
-      id: "raw-tiny",
-      context_length: 8_000,
-      max_output_tokens: 4_000,
-      capabilities: { tool_calling: false, reasoning: false, vision: false, temperature: true },
-      input_modalities: ["text"],
-      output_modalities: ["text"],
-    },
-  ];
-  const rawCombos: OmniRouteRawCombo[] = [
-    {
-      id: "tiny-combo",
-      name: "TinyCombo",
-      models: [{ id: "m1", kind: "model", model: "raw-tiny", weight: 100 }],
-    },
-    {
-      id: "parent",
-      name: "Parent",
-      models: [
-        { id: "p1", kind: "model", model: "raw-big", weight: 50 },
-        { id: "p2", kind: "combo-ref", comboName: "TinyCombo", weight: 50 },
-      ],
-    },
-  ];
-  const block = buildStaticProviderEntry(
-    rawModels,
-    rawCombos,
-    resolved,
-    "https://or.example/v1",
-    "sk-test"
-  );
-  // Pre-fix: Parent would advertise 200_000 (only raw-big counted).
-  // Post-fix: Parent should advertise 8_000 (TinyCombo bottleneck).
-  const parent = block.models["opencode-omniroute/parent"];
-  assert.ok(parent, "Parent combo must be in the static catalog");
-  assert.equal(parent.limit?.context, 8_000);
+  const entryB = (inputB as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider
+    .omniroute;
+  assert.equal(entryB.models["claude-sonnet-4-6"].name, "Claude - Claude Sonnet 4.6");
 });

@omniroute/opencode-plugin/tests/features.test.ts

@@ -376,8 +376,7 @@ test("provider hook: enrichment fetcher called when features.enrichment !== fals
   );
   const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
   assert.equal(called, 1, "enrichment fetcher called once");
-  // #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId.
-  const m = out["omniroute/claude-sonnet-4-6"];
+  const m = out["claude-sonnet-4-6"];
   assert.equal(m.name, "Claude Sonnet 4.6", "enrichment name overlay applied");
   assert.equal(m.cost.input, 3, "enrichment pricing applied");
   assert.equal(m.cost.output, 15);
@@ -402,11 +401,7 @@ test("provider hook: enrichment fetcher NOT called when features.enrichment:fals
   );
   const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
   assert.equal(called, 0, "enrichment fetcher NOT called when gated off");
-  assert.equal(
-    out["omniroute/claude-sonnet-4-6"].name,
-    "claude-sonnet-4-6",
-    "raw id preserved"
-  );
+  assert.equal(out["claude-sonnet-4-6"].name, "claude-sonnet-4-6", "raw id preserved");
 });
 
 test("provider hook: compression metadata fetcher NOT called by default (opt-in)", async () => {
@@ -464,7 +459,7 @@ test("provider hook: compression metadata fetcher called when opted in", async (
   );
   const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
   assert.equal(called, 1, "compression metadata fetcher called");
-  const combo = out["omniroute/claude-primary"];
+  const combo = out["combo/claude-primary"];
   assert.ok(combo, "combo entry present");
   assert.match(
     combo.name,
@@ -478,7 +473,7 @@ test("provider hook: compression metadata fetcher called when opted in", async (
 // ─────────────────────────────────────────────────────────────────────────
 
 const stubAuthJson = (apiKey: string) => async () => ({
-  "opencode-omniroute": { type: "api" as const, key: apiKey },
+  omniroute: { type: "api" as const, key: apiKey },
 });
 
 test("config hook: MCP auto-emit OFF by default (no mcp entry)", async () => {
@@ -493,7 +488,7 @@ test("config hook: MCP auto-emit OFF by default (no mcp entry)", async () => {
   );
   const input: { provider?: Record<string, unknown>; mcp?: Record<string, unknown> } = {};
   await hook(input as never);
-  assert.ok(input.provider?.["opencode-omniroute"], "provider block written");
+  assert.ok(input.provider?.omniroute, "provider block written");
   assert.equal(input.mcp, undefined, "no mcp block written");
 });
 
@@ -513,7 +508,7 @@ test("config hook: features.mcpAutoEmit:true writes mcp entry with provider apiK
   );
   const input: { provider?: Record<string, unknown>; mcp?: Record<string, unknown> } = {};
   await hook(input as never);
-  const entry = input.mcp?.["opencode-omniroute"] as
+  const entry = input.mcp?.omniroute as
     | { type: string; url: string; enabled: boolean; headers: Record<string, string> }
     | undefined;
   assert.ok(entry, "mcp entry written");
@@ -543,7 +538,7 @@ test("config hook: features.mcpToken overrides provider apiKey in mcp Bearer", a
   );
   const input: { provider?: Record<string, unknown>; mcp?: Record<string, unknown> } = {};
   await hook(input as never);
-  const entry = input.mcp?.["opencode-omniroute"] as { headers: Record<string, string> };
+  const entry = input.mcp?.omniroute as { headers: Record<string, string> };
   assert.equal(
     entry.headers.Authorization,
     "Bearer sk-mcp-narrower",
@@ -566,11 +561,11 @@ test("config hook: existing operator mcp.<providerId> wins (no overwrite)", asyn
     }
   );
   const input: { provider?: Record<string, unknown>; mcp?: Record<string, unknown> } = {
-    mcp: { "opencode-omniroute": { type: "custom-user-entry", url: "https://manual.example/mcp" } },
+    mcp: { omniroute: { type: "custom-user-entry", url: "https://manual.example/mcp" } },
   };
   await hook(input as never);
   assert.deepEqual(
-    input.mcp?.["opencode-omniroute"],
+    input.mcp?.omniroute,
     { type: "custom-user-entry", url: "https://manual.example/mcp" },
     "operator override preserved"
   );
@@ -585,7 +580,7 @@ test("config hook: features.mcpAutoEmit:true with /v1 in baseURL → strips corr
     },
     {
       readAuthJson: async () => ({
-        "opencode-omniroute-preprod": { type: "api" as const, key: "sk-preprod" },
+        "omniroute-preprod": { type: "api" as const, key: "sk-preprod" },
       }),
       fetcher: async () => SAMPLE_RAW,
       combosFetcher: async () => [],
@@ -594,7 +589,7 @@ test("config hook: features.mcpAutoEmit:true with /v1 in baseURL → strips corr
   );
   const input: { provider?: Record<string, unknown>; mcp?: Record<string, unknown> } = {};
   await hook(input as never);
-  const entry = input.mcp?.["opencode-omniroute-preprod"] as { url: string };
+  const entry = input.mcp?.["omniroute-preprod"] as { url: string };
   assert.equal(
     entry.url,
     "https://or-preprod.example.com/api/mcp/stream",

@omniroute/opencode-plugin/tests/gemini-sanitize.test.ts

@@ -212,8 +212,8 @@ test("shouldSanitizeForGemini: google-vertex/gemini-1.5-flash → true", () => {
   assert.equal(shouldSanitizeForGemini({ model: "google-vertex/gemini-1.5-flash" }), true);
 });
 
-test("shouldSanitizeForGemini: gemini/gemini-2.5-pro → true", () => {
-  assert.equal(shouldSanitizeForGemini({ model: "gemini/gemini-2.5-pro" }), true);
+test("shouldSanitizeForGemini: gemini-cli/gemini-2.5-pro → true (real OmniRoute alias)", () => {
+  assert.equal(shouldSanitizeForGemini({ model: "gemini-cli/gemini-2.5-pro" }), true);
 });
 
 test("shouldSanitizeForGemini: claude-sonnet-4 → false", () => {

@omniroute/opencode-plugin/tests/multi-instance.test.ts

@@ -38,8 +38,8 @@ test("multi-instance: two plugin invocations bind to their own providerId", asyn
     baseURL: "https://b.example/v1",
   });
 
-  assert.equal(a.auth?.provider, "opencode-omniroute-prod");
-  assert.equal(b.auth?.provider, "opencode-omniroute-preprod");
+  assert.equal(a.auth?.provider, "omniroute-prod");
+  assert.equal(b.auth?.provider, "omniroute-preprod");
 });
 
 test("multi-instance: hook objects + nested arrays are independent references", async () => {
@@ -70,8 +70,8 @@ test("multi-instance: identical opts twice still yield independent objects", asy
   assert.notEqual(first.auth, second.auth);
   assert.notEqual(first.auth?.methods, second.auth?.methods);
   // Same provider id is fine — what matters is no shared mutable state.
-  assert.equal(first.auth?.provider, "opencode-twin");
-  assert.equal(second.auth?.provider, "opencode-twin");
+  assert.equal(first.auth?.provider, "twin");
+  assert.equal(second.auth?.provider, "twin");
 });
 
 test("multi-instance: mutating instance A's auth.methods does not affect instance B", async () => {
@@ -132,5 +132,5 @@ test("multi-instance: invalid opts on one instance does not poison the other", a
     providerId: "recovered",
     baseURL: "https://ok.example/v1",
   });
-  assert.equal(ok.auth?.provider, "opencode-recovered");
+  assert.equal(ok.auth?.provider, "recovered");
 });

@omniroute/opencode-plugin/tests/provider-id-routing.test.ts

@@ -1,99 +0,0 @@
-/**
- * Regression test for #6859.
- *
- * `resolveOmniRoutePluginOptions()` auto-prefixes `providerId` with
- * `"opencode-"` (commit 75b52e286) so OpenCode 1.17.8+'s native-adapter gate
- * accepts it as an OC-registered provider id. That prefixed value must stay
- * OC-internal (AuthHook.provider / provider registration keys) — it must
- * NEVER leak into the identifiers OmniRoute's own server parses to resolve
- * credentials (`mapRawModelToModelV2`'s `id`/`providerID`,
- * `mapComboToModelV2`'s `providerID`, and the dynamic-hook catalog keys).
- *
- * OmniRoute's server-side `parseModel()` (open-sse/services/model.ts) splits
- * a dispatched model string on `/` to recover the provider name and look up
- * credentials. If the plugin embeds the OC-gate-prefixed id in that string,
- * the server looks up credentials for a provider named "opencode-omniroute"
- * (which never exists in `src/shared/constants/providers.ts`) instead of
- * "omniroute" — producing the exact "No credentials for opencode-omniroute" /
- * "No active credentials for provider: opencode-omniroute" errors reported
- * in #6859.
- */
-
-import test from "node:test";
-import assert from "node:assert/strict";
-import {
-  createOmniRouteProviderHook,
-  mapRawModelToModelV2,
-  resolveOmniRoutePluginOptions,
-} from "../src/index.js";
-
-/**
- * Minimal stand-in for OmniRoute's own `parseModel()` (open-sse/services/
- * model.ts), which splits a dispatched `<providerID>/<modelID>` string on the
- * FIRST "/" to recover the provider name used for credential lookup. Kept
- * local (rather than cross-importing the real module) so this package's
- * self-contained test suite (`cd @omniroute/opencode-plugin && npm test`)
- * doesn't depend on the root repo's `@/*` path-alias resolution.
- */
-function splitProviderFromDispatchedModel(modelStr: string): string {
-  const idx = modelStr.indexOf("/");
-  return idx === -1 ? modelStr : modelStr.slice(0, idx);
-}
-
-const apiAuth = (key: string) => ({ type: "api" as const, key });
-
-test("#6859: server-facing model id/providerID must resolve to the unprefixed provider name", () => {
-  const resolved = resolveOmniRoutePluginOptions();
-
-  // The OC-gate-compatible id stays prefixed — it is legitimate for
-  // AuthHook.provider / provider registration.
-  assert.equal(resolved.providerId, "opencode-omniroute");
-
-  // A second, unprefixed id must be exposed for anything that reaches
-  // OmniRoute's own server (model id prefix, ModelV2.providerID, combo keys).
-  assert.equal(
-    resolved.omnirouteProviderId,
-    "omniroute",
-    "resolveOmniRoutePluginOptions() must expose an unprefixed omnirouteProviderId"
-  );
-
-  // A bare raw /v1/models entry (no existing "/" in its id — the common
-  // case for OmniRoute's catalog) mapped with the server-facing id.
-  const model = mapRawModelToModelV2(
-    { id: "claude-opus-4-7" },
-    { providerId: resolved.omnirouteProviderId, baseURL: "http://localhost:20128" }
-  );
-
-  assert.equal(model.providerID, "omniroute");
-  assert.equal(model.id, "omniroute/claude-opus-4-7");
-
-  // OpenCode dispatches back to OmniRoute using `providerID/modelKey`
-  // (matches the issue's own repro: `-m opencode-omniroute/oc/big-pickle`).
-  const dispatchedModelString = `${model.providerID}/claude-opus-4-7`;
-  const parsedProvider = splitProviderFromDispatchedModel(dispatchedModelString);
-
-  assert.equal(
-    parsedProvider,
-    "omniroute",
-    `server-side provider split resolved '${parsedProvider}', expected 'omniroute' — ` +
-      `credentials lookup would fail for an OC-gate-prefixed provider id`
-  );
-});
-
-test("#6859: createOmniRouteProviderHook end-to-end — catalog keys/providerID never carry the OC-gate prefix", async () => {
-  const hook = createOmniRouteProviderHook(
-    { baseURL: "https://or.example.com/v1" },
-    {
-      fetcher: async () => [{ id: "claude-opus-4-7" }],
-      combosFetcher: async () => [],
-    }
-  );
-  const out = await hook.models!({} as never, { auth: apiAuth("sk-test") as never });
-  const model = out["omniroute/claude-opus-4-7"];
-  assert.ok(model, "catalog keyed under the unprefixed provider name");
-  assert.equal(model.providerID, "omniroute");
-  assert.ok(
-    !model.providerID.startsWith("opencode-"),
-    "the OC-gate prefix must never leak into ModelV2.providerID"
-  );
-});

@omniroute/opencode-plugin/tests/provider.test.ts

@@ -75,7 +75,7 @@ const apiAuth = (key: string, baseURL?: string): unknown =>
 
 test("createOmniRouteProviderHook: default providerId is 'omniroute'", () => {
   const hook = createOmniRouteProviderHook(undefined, { combosFetcher: async () => [] });
-  assert.equal(hook.id, "opencode-omniroute");
+  assert.equal(hook.id, "omniroute");
 });
 
 test("createOmniRouteProviderHook: custom providerId binds to hook.id (multi-instance)", () => {
@@ -87,8 +87,8 @@ test("createOmniRouteProviderHook: custom providerId binds to hook.id (multi-ins
     { providerId: "omniroute-local" },
     { combosFetcher: async () => [] }
   );
-  assert.equal(a.id, "opencode-omniroute-preprod");
-  assert.equal(b.id, "opencode-omniroute-local");
+  assert.equal(a.id, "omniroute-preprod");
+  assert.equal(b.id, "omniroute-local");
 });
 
 test("models: extracts apiKey from ctx.auth (type=api) and calls fetcher with it", async () => {
@@ -101,10 +101,7 @@ test("models: extracts apiKey from ctx.auth (type=api) and calls fetcher with it
   assert.equal(fetcher.callCount(), 1);
   assert.deepEqual(fetcher.callsBy()[0], ["https://or.example.com/v1", "sk-abc"]);
   assert.equal(Object.keys(out).length, 3);
-  // #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId
-  // ("omniroute"), not the OC-gate-prefixed hook.id ("opencode-omniroute") —
-  // that prefix must never leak into anything OmniRoute's server parses.
-  assert.ok(out["omniroute/claude-primary"]);
+  assert.ok(out["claude-primary"]);
 });
 
 test("models: returns {} when ctx.auth is null/undefined/wrong-type/empty-key", async () => {
@@ -155,15 +152,9 @@ test("models: maps a sample /v1/models entry to ModelV2 (sanity)", async () => {
     { fetcher, combosFetcher: async () => [] }
   );
   const out = await hook.models!({} as never, { auth: apiAuth("sk-abc") as never });
-  // #6859: dynamic-hook catalog keys/ids/providerID use the unprefixed
-  // omnirouteProviderId ("omniroute") — the OC-gate prefix ("opencode-")
-  // must stay OC-internal (hook.id / AuthHook.provider) and never leak into
-  // anything OmniRoute's own server parses for credential lookup.
-  const claude = out["omniroute/claude-primary"];
+  const claude = out["claude-primary"];
   assert.ok(claude, "claude-primary present");
-  // `mapRawModelToModelV2` stamps the provider prefix on the id so OC's
-  // static-catalog reader resolves `(providerID, modelID)` from the key.
-  assert.equal(claude.id, "omniroute/claude-primary");
+  assert.equal(claude.id, "claude-primary");
   assert.equal(claude.name, "claude-primary");
   assert.equal(claude.providerID, "omniroute");
   assert.equal(claude.api.id, "openai-compatible");

@omniroute/opencode-plugin/tests/scaffold.test.ts

@@ -1,5 +1,6 @@
 import test from "node:test";
 import assert from "node:assert/strict";
+import { createRequire } from "node:module";
 import {
   OmniRoutePlugin,
   OMNIROUTE_PROVIDER_KEY,
@@ -26,7 +27,7 @@ test("scaffold: default export is v1 plugin shape { id, server: OmniRoutePlugin
 
 test("resolveOmniRoutePluginOptions: defaults", () => {
   const r = resolveOmniRoutePluginOptions();
-  assert.equal(r.providerId, "opencode-omniroute");
+  assert.equal(r.providerId, "omniroute");
   assert.equal(r.displayName, "OmniRoute");
   assert.equal(r.modelCacheTtl, 300_000);
   assert.equal(r.baseURL, undefined);
@@ -34,8 +35,8 @@ test("resolveOmniRoutePluginOptions: defaults", () => {
 
 test("resolveOmniRoutePluginOptions: custom providerId derives displayName", () => {
   const r = resolveOmniRoutePluginOptions({ providerId: "omniroute-preprod" });
-  assert.equal(r.providerId, "opencode-omniroute-preprod");
-  assert.equal(r.displayName, "OmniRoute (opencode-omniroute-preprod)");
+  assert.equal(r.providerId, "omniroute-preprod");
+  assert.equal(r.displayName, "OmniRoute (omniroute-preprod)");
 });
 
 test("resolveOmniRoutePluginOptions: explicit displayName wins", () => {
@@ -62,12 +63,11 @@ test("OmniRoutePlugin: returns an empty hooks object (scaffold)", async () => {
   assert.notEqual(hooks, null);
 });
 
-test("scaffold: built ESM default export resolves with the v1 plugin shape", async () => {
-  // The plugin is ESM-only now — the CJS bundle was dropped to fix the OpenCode
-  // loader (#3883), so there is no more ../dist/index.cjs. Validate that the built
-  // distributable's default export still carries the OpenCode v1 { id, server } shape.
-  const mod = await import("../dist/index.js");
-  assert.strictEqual(typeof mod.default, "object");
-  assert.strictEqual(mod.default.id, "@omniroute/opencode-plugin");
-  assert.strictEqual(typeof mod.default.server, "function");
+test("scaffold: CJS default export resolves via require() with v1 shape", () => {
+  const require_ = createRequire(import.meta.url);
+  const cjs = require_("../dist/index.cjs");
+  // after cjsInterop:true, default export is on cjs.default
+  assert.strictEqual(typeof cjs.default, "object");
+  assert.strictEqual(cjs.default.id, "@omniroute/opencode-plugin");
+  assert.strictEqual(typeof cjs.default.server, "function");
 });

@omniroute/opencode-plugin/tsup.config.ts

@@ -2,7 +2,7 @@ import { defineConfig } from "tsup";
 
 export default defineConfig({
   entry: ["src/index.ts"],
-  format: ["esm"],
+  format: ["esm", "cjs"],
   dts: true,
   clean: true,
   sourcemap: false,
@@ -11,7 +11,7 @@ export default defineConfig({
   target: "node22",
   outDir: "dist",
   minify: false,
-  cjsInterop: false,
+  cjsInterop: true,
   // Bundle runtime deps so the .tgz / npm install is self-contained.
   // `zod` is required at runtime by the options schema and would otherwise
   // need a peer install when the plugin is loaded directly from a file path

@omniroute/opencode-provider/package-lock.json

@@ -19,9 +19,9 @@
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.28.1.tgz",
-      "integrity": "sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.27.7.tgz",
+      "integrity": "sha512-EKX3Qwmhz1eMdEJokhALr0YiD0lhQNwDqkPYyPhiSwKrh7/4KRjQc04sZ8db+5DVVnZ1LmbNDI1uAMPEUBnQPg==",
       "cpu": [
         "ppc64"
       ],
@@ -36,9 +36,9 @@
       }
     },
     "node_modules/@esbuild/android-arm": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.28.1.tgz",
-      "integrity": "sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.27.7.tgz",
+      "integrity": "sha512-jbPXvB4Yj2yBV7HUfE2KHe4GJX51QplCN1pGbYjvsyCZbQmies29EoJbkEc+vYuU5o45AfQn37vZlyXy4YJ8RQ==",
       "cpu": [
         "arm"
       ],
@@ -53,9 +53,9 @@
       }
     },
     "node_modules/@esbuild/android-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.28.1.tgz",
-      "integrity": "sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.27.7.tgz",
+      "integrity": "sha512-62dPZHpIXzvChfvfLJow3q5dDtiNMkwiRzPylSCfriLvZeq0a1bWChrGx/BbUbPwOrsWKMn8idSllklzBy+dgQ==",
       "cpu": [
         "arm64"
       ],
@@ -70,9 +70,9 @@
       }
     },
     "node_modules/@esbuild/android-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.28.1.tgz",
-      "integrity": "sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.27.7.tgz",
+      "integrity": "sha512-x5VpMODneVDb70PYV2VQOmIUUiBtY3D3mPBG8NxVk5CogneYhkR7MmM3yR/uMdITLrC1ml/NV1rj4bMJuy9MCg==",
       "cpu": [
         "x64"
       ],
@@ -87,9 +87,9 @@
       }
     },
     "node_modules/@esbuild/darwin-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.28.1.tgz",
-      "integrity": "sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.27.7.tgz",
+      "integrity": "sha512-5lckdqeuBPlKUwvoCXIgI2D9/ABmPq3Rdp7IfL70393YgaASt7tbju3Ac+ePVi3KDH6N2RqePfHnXkaDtY9fkw==",
       "cpu": [
         "arm64"
       ],
@@ -104,9 +104,9 @@
       }
     },
     "node_modules/@esbuild/darwin-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.28.1.tgz",
-      "integrity": "sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.27.7.tgz",
+      "integrity": "sha512-rYnXrKcXuT7Z+WL5K980jVFdvVKhCHhUwid+dDYQpH+qu+TefcomiMAJpIiC2EM3Rjtq0sO3StMV/+3w3MyyqQ==",
       "cpu": [
         "x64"
       ],
@@ -121,9 +121,9 @@
       }
     },
     "node_modules/@esbuild/freebsd-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.28.1.tgz",
-      "integrity": "sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.27.7.tgz",
+      "integrity": "sha512-B48PqeCsEgOtzME2GbNM2roU29AMTuOIN91dsMO30t+Ydis3z/3Ngoj5hhnsOSSwNzS+6JppqWsuhTp6E82l2w==",
       "cpu": [
         "arm64"
       ],
@@ -138,9 +138,9 @@
       }
     },
     "node_modules/@esbuild/freebsd-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.28.1.tgz",
-      "integrity": "sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.27.7.tgz",
+      "integrity": "sha512-jOBDK5XEjA4m5IJK3bpAQF9/Lelu/Z9ZcdhTRLf4cajlB+8VEhFFRjWgfy3M1O4rO2GQ/b2dLwCUGpiF/eATNQ==",
       "cpu": [
         "x64"
       ],
@@ -155,9 +155,9 @@
       }
     },
     "node_modules/@esbuild/linux-arm": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.28.1.tgz",
-      "integrity": "sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.27.7.tgz",
+      "integrity": "sha512-RkT/YXYBTSULo3+af8Ib0ykH8u2MBh57o7q/DAs3lTJlyVQkgQvlrPTnjIzzRPQyavxtPtfg0EopvDyIt0j1rA==",
       "cpu": [
         "arm"
       ],
@@ -172,9 +172,9 @@
       }
     },
     "node_modules/@esbuild/linux-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.28.1.tgz",
-      "integrity": "sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.27.7.tgz",
+      "integrity": "sha512-RZPHBoxXuNnPQO9rvjh5jdkRmVizktkT7TCDkDmQ0W2SwHInKCAV95GRuvdSvA7w4VMwfCjUiPwDi0ZO6Nfe9A==",
       "cpu": [
         "arm64"
       ],
@@ -189,9 +189,9 @@
       }
     },
     "node_modules/@esbuild/linux-ia32": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.28.1.tgz",
-      "integrity": "sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.27.7.tgz",
+      "integrity": "sha512-GA48aKNkyQDbd3KtkplYWT102C5sn/EZTY4XROkxONgruHPU72l+gW+FfF8tf2cFjeHaRbWpOYa/uRBz/Xq1Pg==",
       "cpu": [
         "ia32"
       ],
@@ -206,9 +206,9 @@
       }
     },
     "node_modules/@esbuild/linux-loong64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.28.1.tgz",
-      "integrity": "sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.27.7.tgz",
+      "integrity": "sha512-a4POruNM2oWsD4WKvBSEKGIiWQF8fZOAsycHOt6JBpZ+JN2n2JH9WAv56SOyu9X5IqAjqSIPTaJkqN8F7XOQ5Q==",
       "cpu": [
         "loong64"
       ],
@@ -223,9 +223,9 @@
       }
     },
     "node_modules/@esbuild/linux-mips64el": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.28.1.tgz",
-      "integrity": "sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.27.7.tgz",
+      "integrity": "sha512-KabT5I6StirGfIz0FMgl1I+R1H73Gp0ofL9A3nG3i/cYFJzKHhouBV5VWK1CSgKvVaG4q1RNpCTR2LuTVB3fIw==",
       "cpu": [
         "mips64el"
       ],
@@ -240,9 +240,9 @@
       }
     },
     "node_modules/@esbuild/linux-ppc64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.28.1.tgz",
-      "integrity": "sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.27.7.tgz",
+      "integrity": "sha512-gRsL4x6wsGHGRqhtI+ifpN/vpOFTQtnbsupUF5R5YTAg+y/lKelYR1hXbnBdzDjGbMYjVJLJTd2OFmMewAgwlQ==",
       "cpu": [
         "ppc64"
       ],
@@ -257,9 +257,9 @@
       }
     },
     "node_modules/@esbuild/linux-riscv64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.28.1.tgz",
-      "integrity": "sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.27.7.tgz",
+      "integrity": "sha512-hL25LbxO1QOngGzu2U5xeXtxXcW+/GvMN3ejANqXkxZ/opySAZMrc+9LY/WyjAan41unrR3YrmtTsUpwT66InQ==",
       "cpu": [
         "riscv64"
       ],
@@ -274,9 +274,9 @@
       }
     },
     "node_modules/@esbuild/linux-s390x": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.28.1.tgz",
-      "integrity": "sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.27.7.tgz",
+      "integrity": "sha512-2k8go8Ycu1Kb46vEelhu1vqEP+UeRVj2zY1pSuPdgvbd5ykAw82Lrro28vXUrRmzEsUV0NzCf54yARIK8r0fdw==",
       "cpu": [
         "s390x"
       ],
@@ -291,9 +291,9 @@
       }
     },
     "node_modules/@esbuild/linux-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.28.1.tgz",
-      "integrity": "sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.27.7.tgz",
+      "integrity": "sha512-hzznmADPt+OmsYzw1EE33ccA+HPdIqiCRq7cQeL1Jlq2gb1+OyWBkMCrYGBJ+sxVzve2ZJEVeePbLM2iEIZSxA==",
       "cpu": [
         "x64"
       ],
@@ -308,9 +308,9 @@
       }
     },
     "node_modules/@esbuild/netbsd-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.28.1.tgz",
-      "integrity": "sha512-oks0DYbLwWMmaakTsCb+zL4E+aHRVLom9IJZOAthMQEPiQmydXHkziYEsGYRx0uNV/IjEKGAV941JzH02pflqw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.27.7.tgz",
+      "integrity": "sha512-b6pqtrQdigZBwZxAn1UpazEisvwaIDvdbMbmrly7cDTMFnw/+3lVxxCTGOrkPVnsYIosJJXAsILG9XcQS+Yu6w==",
       "cpu": [
         "arm64"
       ],
@@ -325,9 +325,9 @@
       }
     },
     "node_modules/@esbuild/netbsd-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.28.1.tgz",
-      "integrity": "sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.27.7.tgz",
+      "integrity": "sha512-OfatkLojr6U+WN5EDYuoQhtM+1xco+/6FSzJJnuWiUw5eVcicbyK3dq5EeV/QHT1uy6GoDhGbFpprUiHUYggrw==",
       "cpu": [
         "x64"
       ],
@@ -342,9 +342,9 @@
       }
     },
     "node_modules/@esbuild/openbsd-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.28.1.tgz",
-      "integrity": "sha512-MEFJe5C3R8pwXdZ5Y21oo6m7ePiS0d9pWucn99O/wvyJZChoIQKrQDxKrGeW8F5+T0okTHesAmDeiHDTIq0V/Q==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.27.7.tgz",
+      "integrity": "sha512-AFuojMQTxAz75Fo8idVcqoQWEHIXFRbOc1TrVcFSgCZtQfSdc1RXgB3tjOn/krRHENUB4j00bfGjyl2mJrU37A==",
       "cpu": [
         "arm64"
       ],
@@ -359,9 +359,9 @@
       }
     },
     "node_modules/@esbuild/openbsd-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.28.1.tgz",
-      "integrity": "sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.27.7.tgz",
+      "integrity": "sha512-+A1NJmfM8WNDv5CLVQYJ5PshuRm/4cI6WMZRg1by1GwPIQPCTs1GLEUHwiiQGT5zDdyLiRM/l1G0Pv54gvtKIg==",
       "cpu": [
         "x64"
       ],
@@ -376,9 +376,9 @@
       }
     },
     "node_modules/@esbuild/openharmony-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.28.1.tgz",
-      "integrity": "sha512-ge+Z7EXFNt2BO1oAMsVpiQ8EwndV9i1xXerAeTIK7AtPs3bKFXQM7nlRxDSIUIMeueR1CNXxqztLzdNeReKBJg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.27.7.tgz",
+      "integrity": "sha512-+KrvYb/C8zA9CU/g0sR6w2RBw7IGc5J2BPnc3dYc5VJxHCSF1yNMxTV5LQ7GuKteQXZtspjFbiuW5/dOj7H4Yw==",
       "cpu": [
         "arm64"
       ],
@@ -393,9 +393,9 @@
       }
     },
     "node_modules/@esbuild/sunos-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.28.1.tgz",
-      "integrity": "sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.27.7.tgz",
+      "integrity": "sha512-ikktIhFBzQNt/QDyOL580ti9+5mL/YZeUPKU2ivGtGjdTYoqz6jObj6nOMfhASpS4GU4Q/Clh1QtxWAvcYKamA==",
       "cpu": [
         "x64"
       ],
@@ -410,9 +410,9 @@
       }
     },
     "node_modules/@esbuild/win32-arm64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.28.1.tgz",
-      "integrity": "sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.27.7.tgz",
+      "integrity": "sha512-7yRhbHvPqSpRUV7Q20VuDwbjW5kIMwTHpptuUzV+AA46kiPze5Z7qgt6CLCK3pWFrHeNfDd1VKgyP4O+ng17CA==",
       "cpu": [
         "arm64"
       ],
@@ -427,9 +427,9 @@
       }
     },
     "node_modules/@esbuild/win32-ia32": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.28.1.tgz",
-      "integrity": "sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.27.7.tgz",
+      "integrity": "sha512-SmwKXe6VHIyZYbBLJrhOoCJRB/Z1tckzmgTLfFYOfpMAx63BJEaL9ExI8x7v0oAO3Zh6D/Oi1gVxEYr5oUCFhw==",
       "cpu": [
         "ia32"
       ],
@@ -444,9 +444,9 @@
       }
     },
     "node_modules/@esbuild/win32-x64": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.28.1.tgz",
-      "integrity": "sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.27.7.tgz",
+      "integrity": "sha512-56hiAJPhwQ1R4i+21FVF7V8kSD5zZTdHcVuRFMW0hn753vVfQN8xlx4uOPT4xoGH0Z/oVATuR82AiqSTDIpaHg==",
       "cpu": [
         "x64"
       ],
@@ -974,9 +974,9 @@
       }
     },
     "node_modules/esbuild": {
-      "version": "0.28.1",
-      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.1.tgz",
-      "integrity": "sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==",
+      "version": "0.27.7",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.27.7.tgz",
+      "integrity": "sha512-IxpibTjyVnmrIQo5aqNpCgoACA/dTKLTlhMHihVHhdkxKyPO1uBBthumT0rdHmcsk9uMonIWS0m4FljWzILh3w==",
       "dev": true,
       "hasInstallScript": true,
       "license": "MIT",
@@ -987,32 +987,32 @@
         "node": ">=18"
       },
       "optionalDependencies": {
-        "@esbuild/aix-ppc64": "0.28.1",
-        "@esbuild/android-arm": "0.28.1",
-        "@esbuild/android-arm64": "0.28.1",
-        "@esbuild/android-x64": "0.28.1",
-        "@esbuild/darwin-arm64": "0.28.1",
-        "@esbuild/darwin-x64": "0.28.1",
-        "@esbuild/freebsd-arm64": "0.28.1",
-        "@esbuild/freebsd-x64": "0.28.1",
-        "@esbuild/linux-arm": "0.28.1",
-        "@esbuild/linux-arm64": "0.28.1",
-        "@esbuild/linux-ia32": "0.28.1",
-        "@esbuild/linux-loong64": "0.28.1",
-        "@esbuild/linux-mips64el": "0.28.1",
-        "@esbuild/linux-ppc64": "0.28.1",
-        "@esbuild/linux-riscv64": "0.28.1",
-        "@esbuild/linux-s390x": "0.28.1",
-        "@esbuild/linux-x64": "0.28.1",
-        "@esbuild/netbsd-arm64": "0.28.1",
-        "@esbuild/netbsd-x64": "0.28.1",
-        "@esbuild/openbsd-arm64": "0.28.1",
-        "@esbuild/openbsd-x64": "0.28.1",
-        "@esbuild/openharmony-arm64": "0.28.1",
-        "@esbuild/sunos-x64": "0.28.1",
-        "@esbuild/win32-arm64": "0.28.1",
-        "@esbuild/win32-ia32": "0.28.1",
-        "@esbuild/win32-x64": "0.28.1"
+        "@esbuild/aix-ppc64": "0.27.7",
+        "@esbuild/android-arm": "0.27.7",
+        "@esbuild/android-arm64": "0.27.7",
+        "@esbuild/android-x64": "0.27.7",
+        "@esbuild/darwin-arm64": "0.27.7",
+        "@esbuild/darwin-x64": "0.27.7",
+        "@esbuild/freebsd-arm64": "0.27.7",
+        "@esbuild/freebsd-x64": "0.27.7",
+        "@esbuild/linux-arm": "0.27.7",
+        "@esbuild/linux-arm64": "0.27.7",
+        "@esbuild/linux-ia32": "0.27.7",
+        "@esbuild/linux-loong64": "0.27.7",
+        "@esbuild/linux-mips64el": "0.27.7",
+        "@esbuild/linux-ppc64": "0.27.7",
+        "@esbuild/linux-riscv64": "0.27.7",
+        "@esbuild/linux-s390x": "0.27.7",
+        "@esbuild/linux-x64": "0.27.7",
+        "@esbuild/netbsd-arm64": "0.27.7",
+        "@esbuild/netbsd-x64": "0.27.7",
+        "@esbuild/openbsd-arm64": "0.27.7",
+        "@esbuild/openbsd-x64": "0.27.7",
+        "@esbuild/openharmony-arm64": "0.27.7",
+        "@esbuild/sunos-x64": "0.27.7",
+        "@esbuild/win32-arm64": "0.27.7",
+        "@esbuild/win32-ia32": "0.27.7",
+        "@esbuild/win32-x64": "0.27.7"
       }
     },
     "node_modules/fdir": {
@@ -1482,6 +1482,490 @@
         "fsevents": "~2.3.3"
       }
     },
+    "node_modules/tsx/node_modules/@esbuild/aix-ppc64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.28.0.tgz",
+      "integrity": "sha512-lhRUCeuOyJQURhTxl4WkpFTjIsbDayJHih5kZC1giwE+MhIzAb7mEsQMqMf18rHLsrb5qI1tafG20mLxEWcWlA==",
+      "cpu": [
+        "ppc64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "aix"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/android-arm": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.28.0.tgz",
+      "integrity": "sha512-wqh0ByljabXLKHeWXYLqoJ5jKC4XBaw6Hk08OfMrCRd2nP2ZQ5eleDZC41XHyCNgktBGYMbqnrJKq/K/lzPMSQ==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/android-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.28.0.tgz",
+      "integrity": "sha512-+WzIXQOSaGs33tLEgYPYe/yQHf0WTU0X42Jca3y8NWMbUVhp7rUnw+vAsRC/QiDrdD31IszMrZy+qwPOPjd+rw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/android-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.28.0.tgz",
+      "integrity": "sha512-+VJggoaKhk2VNNqVL7f6S189UzShHC/mR9EE8rDdSkdpN0KflSwWY/gWjDrNxxisg8Fp1ZCD9jLMo4m0OUfeUA==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/darwin-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.28.0.tgz",
+      "integrity": "sha512-0T+A9WZm+bZ84nZBtk1ckYsOvyA3x7e2Acj1KdVfV4/2tdG4fzUp91YHx+GArWLtwqp77pBXVCPn2We7Letr0Q==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/darwin-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.28.0.tgz",
+      "integrity": "sha512-fyzLm/DLDl/84OCfp2f/XQ4flmORsjU7VKt8HLjvIXChJoFFOIL6pLJPH4Yhd1n1gGFF9mPwtlN5Wf82DZs+LQ==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/freebsd-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.28.0.tgz",
+      "integrity": "sha512-l9GeW5UZBT9k9brBYI+0WDffcRxgHQD8ShN2Ur4xWq/NFzUKm3k5lsH4PdaRgb2w7mI9u61nr2gI2mLI27Nh3Q==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "freebsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/freebsd-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.28.0.tgz",
+      "integrity": "sha512-BXoQai/A0wPO6Es3yFJ7APCiKGc1tdAEOgeTNy3SsB491S3aHn4S4r3e976eUnPdU+NbdtmBuLncYir2tMU9Nw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "freebsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-arm": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.28.0.tgz",
+      "integrity": "sha512-CjaaREJagqJp7iTaNQjjidaNbCKYcd4IDkzbwwxtSvjI7NZm79qiHc8HqciMddQ6CKvJT6aBd8lO9kN/ZudLlw==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.28.0.tgz",
+      "integrity": "sha512-RVyzfb3FWsGA55n6WY0MEIEPURL1FcbhFE6BffZEMEekfCzCIMtB5yyDcFnVbTnwk+CLAgTujmV/Lgvih56W+A==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-ia32": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.28.0.tgz",
+      "integrity": "sha512-KBnSTt1kxl9x70q+ydterVdl+Cn0H18ngRMRCEQfrbqdUuntQQ0LoMZv47uB97NljZFzY6HcfqEZ2SAyIUTQBQ==",
+      "cpu": [
+        "ia32"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-loong64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.28.0.tgz",
+      "integrity": "sha512-zpSlUce1mnxzgBADvxKXX5sl8aYQHo2ezvMNI8I0lbblJtp8V4odlm3Yzlj7gPyt3T8ReksE6bK+pT3WD+aJRg==",
+      "cpu": [
+        "loong64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-mips64el": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.28.0.tgz",
+      "integrity": "sha512-2jIfP6mmjkdmeTlsX/9vmdmhBmKADrWqN7zcdtHIeNSCH1SqIoNI63cYsjQR8J+wGa4Y5izRcSHSm8K3QWmk3w==",
+      "cpu": [
+        "mips64el"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-ppc64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.28.0.tgz",
+      "integrity": "sha512-bc0FE9wWeC0WBm49IQMPSPILRocGTQt3j5KPCA8os6VprfuJ7KD+5PzESSrJ6GmPIPJK965ZJHTUlSA6GNYEhg==",
+      "cpu": [
+        "ppc64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-riscv64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.28.0.tgz",
+      "integrity": "sha512-SQPZOwoTTT/HXFXQJG/vBX8sOFagGqvZyXcgLA3NhIqcBv1BJU1d46c0rGcrij2B56Z2rNiSLaZOYW5cUk7yLQ==",
+      "cpu": [
+        "riscv64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-s390x": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.28.0.tgz",
+      "integrity": "sha512-SCfR0HN8CEEjnYnySJTd2cw0k9OHB/YFzt5zgJEwa+wL/T/raGWYMBqwDNAC6dqFKmJYZoQBRfHjgwLHGSrn3Q==",
+      "cpu": [
+        "s390x"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/linux-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.28.0.tgz",
+      "integrity": "sha512-us0dSb9iFxIi8srnpl931Nvs65it/Jd2a2K3qs7fz2WfGPHqzfzZTfec7oxZJRNPXPnNYZtanmRc4AL/JwVzHQ==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/netbsd-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.28.0.tgz",
+      "integrity": "sha512-CR/RYotgtCKwtftMwJlUU7xCVNg3lMYZ0RzTmAHSfLCXw3NtZtNpswLEj/Kkf6kEL3Gw+BpOekRX0BYCtklhUw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/netbsd-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.28.0.tgz",
+      "integrity": "sha512-nU1yhmYutL+fQ71Kxnhg8uEOdC0pwEW9entHykTgEbna2pw2dkbFSMeqjjyHZoCmt8SBkOSvV+yNmm94aUrrqw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/openbsd-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.28.0.tgz",
+      "integrity": "sha512-cXb5vApOsRsxsEl4mcZ1XY3D4DzcoMxR/nnc4IyqYs0rTI8ZKmW6kyyg+11Z8yvgMfAEldKzP7AdP64HnSC/6g==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/openbsd-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.28.0.tgz",
+      "integrity": "sha512-8wZM2qqtv9UP3mzy7HiGYNH/zjTA355mpeuA+859TyR+e+Tc08IHYpLJuMsfpDJwoLo1ikIJI8jC3GFjnRClzA==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/openharmony-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.28.0.tgz",
+      "integrity": "sha512-FLGfyizszcef5C3YtoyQDACyg95+dndv79i2EekILBofh5wpCa1KuBqOWKrEHZg3zrL3t5ouE5jgr94vA+Wb2w==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openharmony"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/sunos-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.28.0.tgz",
+      "integrity": "sha512-1ZgjUoEdHZZl/YlV76TSCz9Hqj9h9YmMGAgAPYd+q4SicWNX3G5GCyx9uhQWSLcbvPW8Ni7lj4gDa1T40akdlw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "sunos"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/win32-arm64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.28.0.tgz",
+      "integrity": "sha512-Q9StnDmQ/enxnpxCCLSg0oo4+34B9TdXpuyPeTedN/6+iXBJ4J+zwfQI28u/Jl40nOYAxGoNi7mFP40RUtkmUA==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/win32-ia32": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.28.0.tgz",
+      "integrity": "sha512-zF3ag/gfiCe6U2iczcRzSYJKH1DCI+ByzSENHlM2FcDbEeo5Zd2C86Aq0tKUYAJJ1obRP84ymxIAksZUcdztHA==",
+      "cpu": [
+        "ia32"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/@esbuild/win32-x64": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.28.0.tgz",
+      "integrity": "sha512-pEl1bO9mfAmIC+tW5btTmrKaujg3zGtUmWNdCw/xs70FBjwAL3o9OEKNHvNmnyylD6ubxUERiEhdsL0xBQ9efw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/tsx/node_modules/esbuild": {
+      "version": "0.28.0",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.0.tgz",
+      "integrity": "sha512-sNR9MHpXSUV/XB4zmsFKN+QgVG82Cc7+/aaxJ8Adi8hyOac+EXptIp45QBPaVyX3N70664wRbTcLTOemCAnyqw==",
+      "dev": true,
+      "hasInstallScript": true,
+      "license": "MIT",
+      "bin": {
+        "esbuild": "bin/esbuild"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "optionalDependencies": {
+        "@esbuild/aix-ppc64": "0.28.0",
+        "@esbuild/android-arm": "0.28.0",
+        "@esbuild/android-arm64": "0.28.0",
+        "@esbuild/android-x64": "0.28.0",
+        "@esbuild/darwin-arm64": "0.28.0",
+        "@esbuild/darwin-x64": "0.28.0",
+        "@esbuild/freebsd-arm64": "0.28.0",
+        "@esbuild/freebsd-x64": "0.28.0",
+        "@esbuild/linux-arm": "0.28.0",
+        "@esbuild/linux-arm64": "0.28.0",
+        "@esbuild/linux-ia32": "0.28.0",
+        "@esbuild/linux-loong64": "0.28.0",
+        "@esbuild/linux-mips64el": "0.28.0",
+        "@esbuild/linux-ppc64": "0.28.0",
+        "@esbuild/linux-riscv64": "0.28.0",
+        "@esbuild/linux-s390x": "0.28.0",
+        "@esbuild/linux-x64": "0.28.0",
+        "@esbuild/netbsd-arm64": "0.28.0",
+        "@esbuild/netbsd-x64": "0.28.0",
+        "@esbuild/openbsd-arm64": "0.28.0",
+        "@esbuild/openbsd-x64": "0.28.0",
+        "@esbuild/openharmony-arm64": "0.28.0",
+        "@esbuild/sunos-x64": "0.28.0",
+        "@esbuild/win32-arm64": "0.28.0",
+        "@esbuild/win32-ia32": "0.28.0",
+        "@esbuild/win32-x64": "0.28.0"
+      }
+    },
     "node_modules/typescript": {
       "version": "5.9.3",
       "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",

@omniroute/opencode-provider/package.json

@@ -56,8 +56,5 @@
     "tsup": "^8.5.1",
     "tsx": "^4.22.3",
     "typescript": "^5.9.3"
-  },
-  "overrides": {
-    "esbuild": "^0.28.1"
   }
 }

AGENTS.md

@@ -3,14 +3,14 @@
 ## Project
 
 Unified AI proxy/router — route any LLM through one endpoint. Multi-provider support
-with **250 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
+with **229 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
 Cohere, NVIDIA, Cerebras, Pollinations, Puter, Cloudflare AI, HuggingFace, DeepInfra,
 SambaNova, Meta Llama API, Moonshot AI, AI21 Labs, Databricks, Snowflake, and many more)
-with **MCP Server** (94 tools), **A2A v0.3 Protocol**, and **Electron desktop app**.
+with **MCP Server** (69 tools), **A2A v0.3 Protocol**, and **Electron desktop app**.
 
-> **Live counts (v3.8.47)**: providers 250 · MCP tools 94 · MCP scopes 30 · A2A skills 6 ·
-> open-sse services 134 · routing strategies 17 · auto-combo scoring factors 12 ·
-> DB modules 95 · DB migrations 110 · base tables 17 · search providers 11 ·
+> **Live counts (v3.8.16)**: providers 229 · MCP tools 69 · MCP scopes 13 · A2A skills 6 ·
+> open-sse services 111 · routing strategies 15 · auto-combo scoring factors 12 ·
+> DB modules 76 · DB migrations 94 · base tables 17 · search providers 12 ·
 > i18n locales 42. **Refresh with `npm run check:docs-all`.**
 
 ## Doc Accuracy Discipline (read before writing any doc)
@@ -44,8 +44,8 @@ codebase. Run it locally before pushing docs; it runs in CI via `npm run check:d
 
 ## Stack
 
-- **Runtime**: Next.js 16 (App Router), Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
-- **Language**: TypeScript 6.0 (`src/`) + JavaScript (`open-sse/`, `electron/`)
+- **Runtime**: Next.js 16 (App Router), Node.js `>=20.20.2 <21`, `>=22.22.2 <23`, or `>=24.0.0 <25`, ES Modules (`"type": "module"`)
+- **Language**: TypeScript 5.9 (`src/`) + JavaScript (`open-sse/`, `electron/`)
 - **Database**: better-sqlite3 (SQLite) — `DATA_DIR` configurable, default `~/.omniroute/`
 - **Streaming**: SSE via `open-sse` internal workspace package
 - **Styling**: Tailwind CSS v4
@@ -178,7 +178,7 @@ Always run `prettier --write` on changed files.
 
 ### Data Layer (`src/lib/db/`)
 
-All persistence uses SQLite through **95 domain-specific modules** in `src/lib/db/`. Top modules:
+All persistence uses SQLite through **76 domain-specific modules** in `src/lib/db/`. Top modules:
 
 - Core: `core.ts`, `migrationRunner.ts`, `encryption.ts`, `stateReset.ts`
 - Providers / catalog: `providers.ts`, `models.ts`, `providerLimits.ts`, `compressionAnalytics.ts`
@@ -188,8 +188,8 @@ All persistence uses SQLite through **95 domain-specific modules** in `src/lib/d
 - Storage: `backup.ts`, `cleanup.ts`, `jsonMigration.ts`, `healthCheck.ts`, `databaseSettings.ts`
 - Extension modules: `evals.ts`, `webhooks.ts`, `reasoningCache.ts`, `readCache.ts`, `tierConfig.ts`, `compressionCombos.ts`, `compressionScheduler.ts`, `batches.ts`, `files.ts`, `syncTokens.ts`, `proxies.ts`, `oneproxy.ts`, `upstreamProxy.ts`, `versionManager.ts`, `cliToolState.ts`, `prompts.ts`, `detailedLogs.ts`, `contextHandoffs.ts`, `compression.ts`, `stats.ts`
 
-Live count: `ls src/lib/db/*.ts | wc -l` (currently 95). Drift detection: `npm run check:docs-counts`.
-Schema migrations live in `db/migrations/` (**110 files** as of v3.8.43) and run via `migrationRunner.ts`.
+Live count: `ls src/lib/db/*.ts | wc -l` (currently 76). Drift detection: `npm run check:docs-counts`.
+Schema migrations live in `db/migrations/` (**94 files** as of v3.8.16) and run via `migrationRunner.ts`.
 `src/lib/localDb.ts` is a **re-export layer only** — never add logic there.
 
 #### DB Internals
@@ -198,7 +198,7 @@ Schema migrations live in `db/migrations/` (**110 files** as of v3.8.43) and run
   journaling. `SCHEMA_SQL` defines **17 base tables** (verify with `grep -c "CREATE TABLE" src/lib/db/core.ts` minus 1 for the bookkeeping `_omniroute_migrations` table). Helpers: `rowToCamel`, `encryptConnectionFields`.
 - **`migrationRunner.ts`**: Applies versioned SQL files from `db/migrations/` inside transactions.
   Tracks applied migrations in `_omniroute_migrations` table.
-- **Migrations**: 110 files (`001_initial_schema.sql` → `110_*.sql`).
+- **Migrations**: 94 files (`001_initial_schema.sql` → `094_*.sql`).
   Each migration is idempotent and runs in a transaction. Live count: `ls src/lib/db/migrations/*.sql | wc -l`.
 - **Domain modules** import `getDbInstance()` from `core.ts` for all CRUD operations.
   Each module owns a specific table/set of tables (e.g., `providers.ts` → `provider_connections`,
@@ -267,7 +267,7 @@ Zod schemas, and unit tests aligned when editing.
 
 ### Provider Categories
 
-- **Free** (3): Qoder AI, Qwen Code, Kiro AI
+- **Free** (4): Qoder AI, Qwen Code, Gemini CLI (deprecated), Kiro AI
 - **OAuth** (14): Claude Code, Antigravity, Codex, GitHub Copilot, Cursor, Kimi Coding, Kilo Code, Cline, Qwen (⚠️ free tier discontinued 2026-04-15), Kiro, Qoder, Gemini, Windsurf (v3.8), GitLab Duo (v3.8)
 - **API Key** (120+): OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Perplexity,
   Together, Fireworks, Cerebras, Cohere, NVIDIA, Nebius, SiliconFlow, Hyperbolic,
@@ -291,7 +291,7 @@ Providers are registered in `src/shared/constants/providers.ts` with Zod validat
 ### Executors (`open-sse/executors/`)
 
 Provider-specific request executors: `base.ts`, `default.ts`, `cursor.ts`, `codex.ts`,
-`antigravity.ts`, `github.ts`, `kiro.ts`, `qoder.ts`, `vertex.ts`,
+`antigravity.ts`, `github.ts`, `gemini-cli.ts`, `kiro.ts`, `qoder.ts`, `vertex.ts`,
 `cloudflare-ai.ts`, `opencode.ts`, `pollinations.ts`, `puter.ts`.
 
 #### Executor Internals
@@ -336,7 +336,7 @@ Includes request/response translators with helpers for image handling.
 
 ### Services (`open-sse/services/`)
 
-134 service modules in `open-sse/services/` (top-level only; more including sub-dirs like `autoCombo/` and `compression/`). Refresh: `ls open-sse/services/*.ts | wc -l`. Key modules:
+111 service modules in `open-sse/services/` (top-level only; 171 including sub-dirs like `autoCombo/` and `compression/`). Refresh: `ls open-sse/services/*.ts | wc -l`. Key modules:
 `combo.ts` (routing engine), `usage.ts`, `tokenRefresh.ts`,
 `rateLimitManager.ts`, `accountFallback.ts`, `sessionManager.ts`, `wildcardRouter.ts`,
 `autoCombo/`, `intentClassifier.ts`, `taskAwareRouter.ts`, `thinkingBudget.ts`,
@@ -378,8 +378,8 @@ Modular prompt compression that runs proactively before the existing reactive co
   and iterates through targets in order until one succeeds or all fail.
 - **`resolveComboTargets()`**: Expands a combo configuration into an ordered array of
   `ResolvedComboTarget[]`, each specifying provider + model + account + credentials.
-- **Strategies** (17): priority, weighted, fill-first, round-robin, P2C, random, least-used, reset-aware (v3.8),
-  reset-window, cost-optimized, strict-random, auto, lkgp, context-optimized, context-relay, headroom, fusion. Source: `ROUTING_STRATEGY_VALUES` in `src/shared/constants/routingStrategies.ts`.
+- **Strategies** (15): priority, weighted, fill-first, round-robin, P2C, random, least-used, reset-aware (v3.8),
+  reset-window, cost-optimized, strict-random, auto, lkgp, context-optimized, context-relay. Source: `ROUTING_STRATEGY_VALUES` in `src/shared/constants/routingStrategies.ts`.
 - Each target calls **`handleSingleModel()`** which wraps `handleChatCore()` with
   per-target error handling and circuit breaker checks.
 
@@ -391,7 +391,7 @@ Policy engine modules: `policyEngine.ts`, `comboResolver.ts`, `costRules.ts`,
 
 ### MCP Server (`open-sse/mcp-server/`)
 
-**94 tools** total (`TOTAL_MCP_TOOL_COUNT`, `open-sse/mcp-server/server.ts`): a 34-entry base registry (`MCP_TOOLS` in `schemas/tools.ts`, bundling the core / cache / compression / 1proxy / advanced tools) **plus** standalone module sets — memory (3), skill (4), agentSkill (3), pool (6), gamification (8), plugin (8), notion (6), obsidian (22). 3 transports (stdio / SSE / Streamable HTTP). Scoped auth (30 scopes — see `OMNIROUTE_MCP_SCOPES`), Zod schemas. See [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md).
+69 tools across 10 tool files (advancedTools: 5, agentSkillTools: 3, compressionTools: 5, gamificationTools: 8, memoryTools: 3, notionTools: 6, obsidianTools: 22, pluginTools: 8, poolTools: 5, skillTools: 4), 3 transports (stdio / SSE / Streamable HTTP). Scoped auth (13 scopes — see `OMNIROUTE_MCP_SCOPES` in `open-sse/mcp-server/README.md:51`), Zod schemas. See [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md).
 
 **Core tools** (20): get_health, list_combos, get_combo_metrics, switch_combo, check_quota,
 route_request, cost_report, list_models_catalog, web_search, simulate_route, set_budget_guard,
@@ -409,14 +409,6 @@ list_compression_combos, compression_combo_stats.
 
 **Skill tools** (4): skills_list, skills_enable, skills_execute, skills_executions.
 
-**Agent-skill tools** (3): A2A skill discovery / invocation bridges.
-
-**Gamification tools** (8): levels, badges, leaderboard, and community-federation queries.
-
-**Plugin tools** (8): plugin marketplace listing, install/enable/disable, and runtime inspection.
-
-**Notion tools** (6) + **Obsidian tools** (22): knowledge-base read/write integrations (the largest tool family — vault search, note CRUD, WebDAV-backed file ops).
-
 #### MCP Internals
 
 - **Tool registration**: Each tool is an object with `{ name, description, inputSchema: ZodSchema,
@@ -425,7 +417,7 @@ handler: async (args) => {...} }`. Zod validates inputs before the handler fires
   `createMcpServer()` wires all tool sets; `startMcpStdio()` launches the stdio transport.
 - **Transports**: stdio (CLI `omniroute --mcp`), SSE (`/api/mcp/sse`), Streamable HTTP
   (`/api/mcp/stream`). All share the same tool/scope engine.
-- **Scopes** (30): Control which tool categories an API key can access. Enforcement happens
+- **Scopes** (13): Control which tool categories an API key can access. Enforcement happens
   before handler dispatch.
 - **Audit**: Every tool invocation is logged to SQLite (`mcp_audit` table) with tool name,
   args, success/failure, API key attribution, and timestamp.
@@ -489,7 +481,7 @@ Request middleware including `promptInjectionGuard.ts`.
 
 ### Guardrails (`src/lib/guardrails/`)
 
-Hot-reloadable guardrails framework (3 built-in: pii-masker, prompt-injection, vision-bridge). Fail-open. The `pii-masker` guardrail is registered and runs on every request, but its data-mutating logic is **opt-in** and OFF by default — it only redacts when `PII_REDACTION_ENABLED` (request) / `PII_RESPONSE_SANITIZATION` (response + streaming) are enabled (both `defaultValue: "false"`); with them off, payloads pass through untouched. A request can additionally opt OUT of any guardrail via header (`x-omniroute-disabled-guardrails`). Never make PII default-on (Hard Rule #20). See [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md).
+Hot-reloadable guardrails framework (3 built-in: pii-masker, prompt-injection, vision-bridge). Fail-open; per-request opt-out via header. See [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md).
 
 ### Cloud Agents (`src/lib/cloudAgent/`)
 
@@ -527,6 +519,7 @@ Cloudflare Quick/Named, ngrok, Tailscale Funnel. See [`docs/ops/TUNNELS_GUIDE.md
 
 ## Subdirectory AGENTS.md Files
 
+- **[`open-sse/AGENTS.md`](open-sse/AGENTS.md)** — Streaming engine, request pipeline, handlers, and executors
 - **[`src/lib/db/AGENTS.md`](src/lib/db/AGENTS.md)** — SQLite persistence, domain modules, migrations
 - **[`open-sse/services/AGENTS.md`](open-sse/services/AGENTS.md)** — Routing engine, combo resolution, strategy selection
 
@@ -534,33 +527,31 @@ Cloudflare Quick/Named, ngrok, Tailscale Funnel. See [`docs/ops/TUNNELS_GUIDE.md
 
 For any non-trivial change, read the matching deep-dive first:
 
-| Area                                       | Doc                                                                                                             |
-| ------------------------------------------ | --------------------------------------------------------------------------------------------------------------- |
-| Repo navigation                            | [`docs/architecture/REPOSITORY_MAP.md`](docs/architecture/REPOSITORY_MAP.md)                                    |
-| Architecture                               | [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md)                                        |
-| Engineering reference                      | [`docs/architecture/CODEBASE_DOCUMENTATION.md`](docs/architecture/CODEBASE_DOCUMENTATION.md)                    |
-| Auto-Combo (12-factor, 18 strategies)      | [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md)                                                      |
-| Resilience (3 layers)                      | [`docs/architecture/RESILIENCE_GUIDE.md`](docs/architecture/RESILIENCE_GUIDE.md)                                |
-| Skills                                     | [`docs/frameworks/SKILLS.md`](docs/frameworks/SKILLS.md)                                                        |
-| Memory                                     | [`docs/frameworks/MEMORY.md`](docs/frameworks/MEMORY.md)                                                        |
-| Cloud agents                               | [`docs/frameworks/CLOUD_AGENT.md`](docs/frameworks/CLOUD_AGENT.md)                                              |
-| Guardrails                                 | [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md)                                                    |
-| Evals                                      | [`docs/frameworks/EVALS.md`](docs/frameworks/EVALS.md)                                                          |
-| Compliance                                 | [`docs/security/COMPLIANCE.md`](docs/security/COMPLIANCE.md)                                                    |
-| Webhooks                                   | [`docs/frameworks/WEBHOOKS.md`](docs/frameworks/WEBHOOKS.md)                                                    |
-| Authz                                      | [`docs/architecture/AUTHZ_GUIDE.md`](docs/architecture/AUTHZ_GUIDE.md)                                          |
-| Stealth                                    | [`docs/security/STEALTH_GUIDE.md`](docs/security/STEALTH_GUIDE.md)                                              |
-| Reasoning replay                           | [`docs/routing/REASONING_REPLAY.md`](docs/routing/REASONING_REPLAY.md)                                          |
-| Agent protocols (A2A / ACP / Cloud)        | [`docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`](docs/frameworks/AGENT_PROTOCOLS_GUIDE.md)                          |
-| MCP server                                 | [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md)                                                |
-| A2A server                                 | [`docs/frameworks/A2A-SERVER.md`](docs/frameworks/A2A-SERVER.md)                                                |
-| API reference                              | [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md) + [`docs/openapi.yaml`](docs/openapi.yaml) |
-| Provider catalog (auto-generated)          | [`docs/reference/PROVIDER_REFERENCE.md`](docs/reference/PROVIDER_REFERENCE.md)                                  |
-| Tunnels                                    | [`docs/ops/TUNNELS_GUIDE.md`](docs/ops/TUNNELS_GUIDE.md)                                                        |
-| Electron desktop                           | [`docs/guides/ELECTRON_GUIDE.md`](docs/guides/ELECTRON_GUIDE.md)                                                |
-| Release flow                               | [`docs/ops/RELEASE_CHECKLIST.md`](docs/ops/RELEASE_CHECKLIST.md)                                                |
-| Quality gates (35 gates, allowlist policy) | [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALITY_GATES.md)                                      |
-| Cluster opt-in profiles (memory, bifrost)  | [`docs/architecture/cluster-decisions.md`](docs/architecture/cluster-decisions.md)                              |
+| Area                                  | Doc                                                                                                                                 |
+| ------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- |
+| Repo navigation                       | [`docs/architecture/REPOSITORY_MAP.md`](docs/architecture/REPOSITORY_MAP.md)                                                        |
+| Architecture                          | [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md)                                                            |
+| Engineering reference                 | [`docs/architecture/CODEBASE_DOCUMENTATION.md`](docs/architecture/CODEBASE_DOCUMENTATION.md)                                        |
+| Auto-Combo (12-factor, 15 strategies) | [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md)                                                                          |
+| Resilience (3 layers)                 | [`docs/architecture/RESILIENCE_GUIDE.md`](docs/architecture/RESILIENCE_GUIDE.md)                                                    |
+| Skills                                | [`docs/frameworks/SKILLS.md`](docs/frameworks/SKILLS.md)                                                                            |
+| Memory                                | [`docs/frameworks/MEMORY.md`](docs/frameworks/MEMORY.md)                                                                            |
+| Cloud agents                          | [`docs/frameworks/CLOUD_AGENT.md`](docs/frameworks/CLOUD_AGENT.md)                                                                  |
+| Guardrails                            | [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md)                                                                        |
+| Evals                                 | [`docs/frameworks/EVALS.md`](docs/frameworks/EVALS.md)                                                                              |
+| Compliance                            | [`docs/security/COMPLIANCE.md`](docs/security/COMPLIANCE.md)                                                                        |
+| Webhooks                              | [`docs/frameworks/WEBHOOKS.md`](docs/frameworks/WEBHOOKS.md)                                                                        |
+| Authz                                 | [`docs/architecture/AUTHZ_GUIDE.md`](docs/architecture/AUTHZ_GUIDE.md)                                                              |
+| Stealth                               | [`docs/security/STEALTH_GUIDE.md`](docs/security/STEALTH_GUIDE.md)                                                                  |
+| Reasoning replay                      | [`docs/routing/REASONING_REPLAY.md`](docs/routing/REASONING_REPLAY.md)                                                              |
+| Agent protocols (A2A / ACP / Cloud)   | [`docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`](docs/frameworks/AGENT_PROTOCOLS_GUIDE.md)                                              |
+| MCP server                            | [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md)                                                                    |
+| A2A server                            | [`docs/frameworks/A2A-SERVER.md`](docs/frameworks/A2A-SERVER.md)                                                                    |
+| API reference                         | [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md) + [`docs/reference/openapi.yaml`](docs/reference/openapi.yaml) |
+| Provider catalog (auto-generated)     | [`docs/reference/PROVIDER_REFERENCE.md`](docs/reference/PROVIDER_REFERENCE.md)                                                      |
+| Tunnels                               | [`docs/ops/TUNNELS_GUIDE.md`](docs/ops/TUNNELS_GUIDE.md)                                                                            |
+| Electron desktop                      | [`docs/guides/ELECTRON_GUIDE.md`](docs/guides/ELECTRON_GUIDE.md)                                                                    |
+| Release flow                          | [`docs/ops/RELEASE_CHECKLIST.md`](docs/ops/RELEASE_CHECKLIST.md)                                                                    |
 
 ---
 

CLAUDE.md

@@ -35,22 +35,22 @@ For full test matrix, see `CONTRIBUTING.md` → "Running Tests". For deep archit
 
 ## Project at a Glance
 
-**OmniRoute** — unified AI proxy/router. One endpoint, 250 LLM providers, auto-fallback.
+**OmniRoute** — unified AI proxy/router. One endpoint, 160+ LLM providers, auto-fallback.
 
-| Layer         | Location                | Purpose                                                                                                                                                |
-| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| API Routes    | `src/app/api/v1/`       | Next.js App Router — entry points                                                                                                                      |
-| Handlers      | `open-sse/handlers/`    | Request processing (chat, embeddings, etc)                                                                                                             |
-| Executors     | `open-sse/executors/`   | Provider-specific HTTP dispatch                                                                                                                        |
-| Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                               |
-| Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                       |
-| Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                               |
-| Database      | `src/lib/db/`           | SQLite domain modules (95 files, 110 migrations)                                                                                                       |
-| Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                              |
-| MCP Server    | `open-sse/mcp-server/`  | 94 tools (34 base + memory/skill/agentSkill/pool/notion/obsidian/gamification/plugin modules), 3 transports (stdio / SSE / Streamable HTTP), 30 scopes |
-| A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                            |
-| Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                             |
-| Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                       |
+| Layer         | Location                | Purpose                                                            |
+| ------------- | ----------------------- | ------------------------------------------------------------------ |
+| API Routes    | `src/app/api/v1/`       | Next.js App Router — entry points                                  |
+| Handlers      | `open-sse/handlers/`    | Request processing (chat, embeddings, etc)                         |
+| Executors     | `open-sse/executors/`   | Provider-specific HTTP dispatch                                    |
+| Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                           |
+| Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                   |
+| Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                           |
+| Database      | `src/lib/db/`           | SQLite domain modules (45+ files, 55 migrations)                   |
+| Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                          |
+| MCP Server    | `open-sse/mcp-server/`  | 43 tools (30 base + 3 memory + 4 skills + 6 notion), 3 transports, ~13 scopes |
+| A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                        |
+| Skills        | `src/lib/skills/`       | Extensible skill framework                                         |
+| Memory        | `src/lib/memory/`       | Persistent conversational memory                                   |
 
 Monorepo: `src/` (Next.js 16 app), `open-sse/` (streaming engine workspace), `electron/` (desktop app), `tests/`, `bin/` (CLI entry point).
 
@@ -72,7 +72,7 @@ Client → /v1/chat/completions (Next.js route)
 
 API routes follow a consistent pattern: `Route → CORS preflight → Zod body validation → Optional auth (extractApiKey/isValidApiKey) → API key policy enforcement → Handler delegation (open-sse)`. No global Next.js middleware — interception is route-specific.
 
-**Combo routing** (`open-sse/services/combo.ts`): 18 strategies (priority, weighted, fill-first, round-robin, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline). Each target calls `handleSingleModel()` which wraps `handleChatCore()` with per-target error handling and circuit breaker checks. The `fusion` strategy is the exception: it fans out to a panel of models in parallel, then a judge model synthesizes one final answer (`open-sse/services/fusion.ts`). See `docs/routing/AUTO-COMBO.md` for the 12-factor Auto-Combo scoring + the full strategy table and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
+**Combo routing** (`open-sse/services/combo.ts`): 14 strategies (priority, weighted, fill-first, round-robin, P2C, random, least-used, cost-optimized, reset-aware, strict-random, auto, lkgp, context-optimized, context-relay). Each target calls `handleSingleModel()` which wraps `handleChatCore()` with per-target error handling and circuit breaker checks. See `docs/routing/AUTO-COMBO.md` for the 9-factor Auto-Combo scoring and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
 
 ---
 
@@ -221,7 +221,7 @@ connection continue serving other models.
 - **2 spaces**, semicolons, double quotes, 100 char width, es5 trailing commas (enforced by lint-staged via Prettier)
 - **Imports**: external → internal (`@/`, `@omniroute/open-sse`) → relative
 - **Naming**: files=camelCase/kebab, components=PascalCase, constants=UPPER_SNAKE
-- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = error everywhere; `no-explicit-any` = **error** in `open-sse/` and `tests/` (since #6218 — pre-existing violations are frozen in `config/quality/eslint-suppressions.json`, new ones must be fixed; `npm run lint` applies the suppressions and is what CI runs)
+- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = error everywhere; `no-explicit-any` = warn in `open-sse/` and `tests/`
 - **TypeScript**: `strict: false`, target ES2022, module esnext, resolution bundler. Prefer explicit types.
 
 ### Database
@@ -311,7 +311,7 @@ connection continue serving other models.
 4. Create 7 API endpoints under `src/app/api/services/{name}/` (`_lib.ts`, `install`, `start`, `stop`, `restart`, `update`, `status`, `auto-start`). All delegate errors through `createErrorResponse()`. The shared `logs` endpoint is already wired via `[name]/logs/route.ts`.
 5. Verify `/api/services/` is in `LOCAL_ONLY_API_PREFIXES` in `src/server/authz/routeGuard.ts`; add a test asserting `isLocalOnlyPath()` returns `true` for the new prefix if you add one (hard rule #17).
 6. Add a UI tab in `src/app/(dashboard)/dashboard/providers/services/tabs/` reusing `ServiceStatusCard`, `ServiceLifecycleButtons`, `ServiceLogsPanel`.
-7. Document in `docs/frameworks/EMBEDDED-SERVICES.md` (update §1 service table + §4 API reference) and `docs/openapi.yaml`.
+7. Document in `docs/frameworks/EMBEDDED-SERVICES.md` (update §1 service table + §4 API reference) and `docs/reference/openapi.yaml`.
 8. Write tests: unit (`tests/unit/services/`), integration (`tests/integration/services/`, gated by `RUN_SERVICES_INT=1`), and update `docs/ops/RELEASE_CHECKLIST.md` smoke section.
 
 ### Adding a New Guardrail / Eval / Skill / Webhook event
@@ -327,33 +327,32 @@ connection continue serving other models.
 
 For any non-trivial change, read the matching deep-dive first:
 
-| Area                                          | Doc                                                     |
-| --------------------------------------------- | ------------------------------------------------------- |
-| Repo navigation                               | `docs/architecture/REPOSITORY_MAP.md`                   |
-| Architecture                                  | `docs/architecture/ARCHITECTURE.md`                     |
-| Engineering reference                         | `docs/architecture/CODEBASE_DOCUMENTATION.md`           |
-| Auto-Combo (12-factor scoring, 18 strategies) | `docs/routing/AUTO-COMBO.md`                            |
-| Resilience (3 mechanisms)                     | `docs/architecture/RESILIENCE_GUIDE.md`                 |
-| Reasoning replay                              | `docs/routing/REASONING_REPLAY.md`                      |
-| Skills framework                              | `docs/frameworks/SKILLS.md`                             |
-| Memory system (FTS5 + Qdrant)                 | `docs/frameworks/MEMORY.md`                             |
-| Cloud agents                                  | `docs/frameworks/CLOUD_AGENT.md`                        |
-| Guardrails (PII / injection / vision)         | `docs/security/GUARDRAILS.md`                           |
-| Public upstream credentials (Gemini/etc.)     | `docs/security/PUBLIC_CREDS.md`                         |
-| Error message sanitization                    | `docs/security/ERROR_SANITIZATION.md`                   |
-| Evals                                         | `docs/frameworks/EVALS.md`                              |
-| Compliance / audit                            | `docs/security/COMPLIANCE.md`                           |
-| Webhooks                                      | `docs/frameworks/WEBHOOKS.md`                           |
-| Authorization pipeline                        | `docs/architecture/AUTHZ_GUIDE.md`                      |
-| Stealth (TLS / fingerprint)                   | `docs/security/STEALTH_GUIDE.md`                        |
-| Agent protocols (A2A / ACP / Cloud)           | `docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`              |
-| MCP server                                    | `docs/frameworks/MCP-SERVER.md`                         |
-| A2A server                                    | `docs/frameworks/A2A-SERVER.md`                         |
-| API reference + OpenAPI                       | `docs/reference/API_REFERENCE.md` + `docs/openapi.yaml` |
-| Provider catalog (auto-generated)             | `docs/reference/PROVIDER_REFERENCE.md`                  |
-| Release flow                                  | `docs/ops/RELEASE_CHECKLIST.md`                         |
-| Embedded services                             | `docs/frameworks/EMBEDDED-SERVICES.md`                  |
-| Quality gates (~48 scripts, allowlist policy) | `docs/architecture/QUALITY_GATES.md`                    |
+| Area                                         | Doc                                                               |
+| -------------------------------------------- | ----------------------------------------------------------------- |
+| Repo navigation                              | `docs/architecture/REPOSITORY_MAP.md`                             |
+| Architecture                                 | `docs/architecture/ARCHITECTURE.md`                               |
+| Engineering reference                        | `docs/architecture/CODEBASE_DOCUMENTATION.md`                     |
+| Auto-Combo (9-factor scoring, 14 strategies) | `docs/routing/AUTO-COMBO.md`                                      |
+| Resilience (3 mechanisms)                    | `docs/architecture/RESILIENCE_GUIDE.md`                           |
+| Reasoning replay                             | `docs/routing/REASONING_REPLAY.md`                                |
+| Skills framework                             | `docs/frameworks/SKILLS.md`                                       |
+| Memory system (FTS5 + Qdrant)                | `docs/frameworks/MEMORY.md`                                       |
+| Cloud agents                                 | `docs/frameworks/CLOUD_AGENT.md`                                  |
+| Guardrails (PII / injection / vision)        | `docs/security/GUARDRAILS.md`                                     |
+| Public upstream credentials (Gemini/etc.)    | `docs/security/PUBLIC_CREDS.md`                                   |
+| Error message sanitization                   | `docs/security/ERROR_SANITIZATION.md`                             |
+| Evals                                        | `docs/frameworks/EVALS.md`                                        |
+| Compliance / audit                           | `docs/security/COMPLIANCE.md`                                     |
+| Webhooks                                     | `docs/frameworks/WEBHOOKS.md`                                     |
+| Authorization pipeline                       | `docs/architecture/AUTHZ_GUIDE.md`                                |
+| Stealth (TLS / fingerprint)                  | `docs/security/STEALTH_GUIDE.md`                                  |
+| Agent protocols (A2A / ACP / Cloud)          | `docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`                        |
+| MCP server                                   | `docs/frameworks/MCP-SERVER.md`                                   |
+| A2A server                                   | `docs/frameworks/A2A-SERVER.md`                                   |
+| API reference + OpenAPI                      | `docs/reference/API_REFERENCE.md` + `docs/reference/openapi.yaml` |
+| Provider catalog (auto-generated)            | `docs/reference/PROVIDER_REFERENCE.md`                            |
+| Release flow                                 | `docs/ops/RELEASE_CHECKLIST.md`                                   |
+| Embedded services                            | `docs/frameworks/EMBEDDED-SERVICES.md`                            |
 
 ---
 
@@ -374,10 +373,9 @@ For any non-trivial change, read the matching deep-dive first:
 
 **Test layer preference**: unit first → integration (multi-module or DB state) → e2e (UI/workflow only). Encode bug reproductions as automated tests before or alongside the fix.
 
-**Both test runners must pass**: `npm run test:unit` (Node native — most tests) AND `npm run test:vitest` (MCP server, autoCombo, cache) cover **non-overlapping files**. Both are wired in CI (jobs `test-unit` and `test-vitest`) and must be green before merging. A PR where only one suite passes may silently ship broken MCP tools or routing regressions.
+**Both test runners must pass**: `npm run test:unit` (Node native — most tests) AND `npm run test:vitest` (MCP server, autoCombo, cache) cover **non-overlapping files**. Both must be green before merging. A PR where only one suite passes may silently ship broken MCP tools or routing regressions.
 
 **Bug fix / issue triage protocol (Hard Rule #18)**: Every fix for a reported issue must be validated by one of the following — no exceptions:
-
 1. **TDD (preferred)** — write a failing test reproducing the bug → fix it → confirm the test passes. The test becomes the permanent regression guard. Touch only the files the test proves need changing; nothing more.
 2. **Real-environment test (when TDD is not possible)** — deploy to the production VPS (`root@192.168.0.15`) and run a documented live test. Record the exact command + result in the PR description. Applies to: OAuth upstream flows, Cloudflare/WS upstream behavior, UI-only regressions, hardware-dependent behavior.
 3. "It worked locally without a test" does not count. A fix without a test or a VPS validation record is not a fix — it is a guess.
@@ -388,31 +386,6 @@ Why this matters: fixing bug A while opening bug B is worse than not fixing at a
 
 ---
 
-## Planning & Research Artifacts (superpowers, deep-research)
-
-`_tasks/` is a **separate, isolated git repository** that is gitignored by the main
-repo (`.gitignore` → `_tasks/`). It is the canonical home for working artifacts —
-plans, specs/designs, research, hand-offs — so they stay **versioned in their own
-repo** instead of polluting the main OmniRoute tree.
-
-**Hard rule — never write superpowers / planning / research output under `docs/` or
-the repo root.** The superpowers skills ship with defaults that point at `docs/…`
-(`writing-plans` → `docs/superpowers/plans/`, `brainstorming` → `docs/superpowers/specs/`).
-Those defaults are **overridden here**. Whenever you invoke superpowers (or any
-plan/spec/research generator) in this project, save to `_tasks/` instead, using the
-same filename convention:
-
-| Artifact (skill)                   | Default (do NOT use)      | Save here instead                                             |
-| ---------------------------------- | ------------------------- | ------------------------------------------------------------- |
-| Plans (`writing-plans`)            | `docs/superpowers/plans/` | `_tasks/superpowers/plans/YYYY-MM-DD-<feature>.md`            |
-| Specs / design (`brainstorming`)   | `docs/superpowers/specs/` | `_tasks/superpowers/specs/YYYY-MM-DD-<topic>-design.md`       |
-| Research (`deep-research`, ad-hoc) | `docs/research/`          | `_tasks/research/…`                                           |
-| Hand-offs (`/handoff`)             | —                         | `_tasks/hands-off/<YYYY-MM-DD>_<branch>_v<versão>_sess-<id>/` |
-
-When a superpowers skill announces a path like "saved to `docs/superpowers/plans/…`",
-rewrite it to the `_tasks/…` equivalent before writing. Commit those artifacts inside
-the `_tasks/` repo (`git -C _tasks …`), never in the main repo.
-
 ## Git Workflow
 
 ```bash
@@ -428,63 +401,15 @@ git push -u origin feat/your-feature
 
 **Husky hooks**:
 
-- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11` + `check:tracked-artifacts`
-- **pre-push**: intentionally light (PATH/npm sanity only). `any-budget` + `tracked-artifacts`
-  already run on pre-commit; re-running them on every push was pure double-pay. CI still
-  enforces both. (Was Fase 6A.12 full pre-push gate; folded into pre-commit in #6716.)
-
-### Worktree isolation (MANDATORY for every development task)
-
-Multiple sessions/agents work this repo in parallel. The main checkout is **shared**, so a
-`git checkout`/branch switch in it silently discards another session's uncommitted work and
-yanks the branch out from under whatever else is running (incidents: 2026-06-05, 2026-06-13).
-
-**Rule: never develop on the shared main checkout. Every task gets its own git worktree on its
-own dedicated branch, and you MUST confirm the base branch with the operator before creating it.**
-
-1. **Ask first — which base branch?** Before creating anything, ask the operator (via
-   `AskUserQuestion`, unless they already told you) from which branch the new worktree/branch
-   should be cut. Do NOT assume `main` or "whatever I'm on" — the answer is usually the active
-   `release/vX.Y.Z`, but it can be another feature/release branch. Get the base explicitly.
-2. **Create an isolated worktree + branch off that base** (never reuse the main checkout).
-   **🔴 MANDATORY PATH: every worktree lives under `.claude/worktrees/` — and nowhere else.**
-   This is the single canonical location (the same dir the native `EnterWorktree` tool uses). It
-   is gitignored AND in the `tsconfig.json` / `.dockerignore` excludes, so worktrees never leak
-   into the build scope. **Never** use `.worktrees/`, repo-root, or any other path — a worktree
-   outside `.claude/worktrees/` (a) escapes the build-scope excludes and poisons `next build` (the
-   `tsconfig` `include: **/*` globs ~70× the codebase → OOM; incident 2026-06-25) and (b) scatters
-   worktrees across two dirs.
-
-   ```bash
-   BASE_BRANCH="release/vX.Y.Z"          # ← the branch the operator confirmed in step 1
-   TASK="feat/your-feature"               # feat/ fix/ refactor/ docs/ test/ chore/
-   git fetch origin "$BASE_BRANCH"
-   git worktree add ".claude/worktrees/${TASK##*/}" -b "$TASK" "origin/$BASE_BRANCH"
-   cd ".claude/worktrees/${TASK##*/}"
-   # symlink node_modules from the main checkout to skip a per-worktree npm install:
-   ln -s "$(git -C <main_checkout> rev-parse --show-toplevel)/node_modules" node_modules
-   ```
-
-   In Claude Code prefer the native `EnterWorktree` tool (it already creates worktrees under
-   `.claude/worktrees/`): create the worktree with the command above, then call `EnterWorktree`
-   with its `path`.
-
-3. **Work, commit, push, open the PR — all from inside the worktree.** Never `git checkout` a
-   different branch inside a worktree another session might share.
-4. **Tear down only your own** worktree + branch when done, from the main checkout:
-   `git worktree remove .claude/worktrees/<dir>` then `git branch -D <task>`. Never blanket-delete
-   `fix/*`/`feat/*` — other sessions keep their own; delete only the branches you created, by name.
-5. **Never touch another session's worktree, branch, or uncommitted changes.** If `git worktree
-list` shows worktrees you didn't create, leave them alone. End every session with the main
-   checkout back on the branch it started on (the active `release/vX.Y.Z`, never `main`).
+- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11`
+- **pre-push**: `npm run test:unit`
 
 ---
 
 ## Environment
 
-- **Runtime**: Node.js ≥22.0.0 <23 || ≥24.0.0 <27, ES Modules. This is the **only** runtime for the published `omniroute` CLI, the server, and the test suites (`node:test` + vitest) — `engines.node` is authoritative and end users never need Bun.
-- **Bun (build/dev script runner only)**: Bun `1.3.10` is pinned as an **exact devDependency** (provisioned through the existing `npm ci` via the lockfile's `@oven/bun-*` platform binaries — no `setup-bun`/ad-hoc install). It is used **only** to execute a small, allow-listed set of TypeScript **gate/generator scripts** (replacing `node --import tsx` for startup speed): the CI checks `check:provider-consistency`, `check:compression-budget`, `check:known-symbols`, and the non-CI `gen:provider-reference`, `bench:compression`. **Do NOT** widen Bun to `npm install`, the build (`build:cli*`), `check:pack-artifact`, the published runtime, or the test runners — those stay on Node. Any new Bun-invoking script must be validated byte-identical against its `node --import tsx` output first. After pulling the lockfile change, run `npm install` so `bun` resolves locally (a stale `node_modules` will fail those 5 scripts with `bun: not found`).
-- **TypeScript**: 6.0+, target ES2022, module esnext, resolution bundler
+- **Runtime**: Node.js ≥20.20.2 <21 || ≥22.22.2 <23 || ≥24 <25, ES Modules
+- **TypeScript**: 5.9+, target ES2022, module esnext, resolution bundler
 - **Path aliases**: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
 - **Default port**: 20128 (API + dashboard on same port)
 - **Data directory**: `DATA_DIR` env var, defaults to `~/.omniroute/`
@@ -493,33 +418,6 @@ list` shows worktrees you didn't create, leave them alone. End every session wit
 
 ---
 
-## Quality Gates & Ratchets
-
-OmniRoute has **~48 quality-gate scripts** (`scripts/check/` + `scripts/quality/`) wired
-across **9 gate-running jobs** in `.github/workflows/ci.yml` (`lint`, `quality-gate`,
-`quality-extended`, `docs-sync-strict`, `i18n-ui-coverage`, `i18n`, `pr-test-policy`,
-`test-vitest`, `sonarqube`), plus the `quality.yml` fast-gates job (PR→`release/**`) and
-3 nightly workflows (`nightly-property`, `nightly-resilience`, `nightly-llm-security`;
-`nightly-mutation` once merged). Full inventory, per-job breakdown, and operational
-procedures are in [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALITY_GATES.md).
-
-**Quick reference:**
-
-- Gates in jobs `lint` + `docs-sync-strict`: pass/fail policy gates —
-  fix the violation or add an allowlist entry with a justification comment + tracking issue.
-- Gates in job `quality-gate`: ratchet — metrics (ESLint warnings, code coverage, duplication,
-  complexity) must not regress vs `quality-baseline.json`. Update via
-  `npm run quality:ratchet -- --update` when a metric genuinely improves.
-- Job `test-vitest` runs `npm run test:vitest` (MCP tools, autoCombo, cache) — blocking.
-  `test:vitest:ui` is advisory until UI component tests are triaged.
-
-**Allowlist policy (short form):** Fix the cause; use the allowlist only for pre-existing
-violations you cannot fix in the same PR. Add a comment with justification + issue number.
-Stale allowlist entries (suppressing a violation that no longer exists) will be caught by
-the stale-enforcement added in Fase 6A.3.
-
----
-
 ## Hard Rules
 
 1. Never commit secrets or credentials
@@ -530,35 +428,26 @@ the stale-enforcement added in Fase 6A.3.
 6. Never silently swallow errors in SSE streams
 7. Always validate inputs with Zod schemas
 8. Always include tests when changing production code
-9. Coverage must not regress below the baseline frozen in `quality-baseline.json` (ratchet); absolute floor is 60% (statements/lines/functions/branches). Update the baseline via `npm run quality:ratchet -- --update` only when coverage genuinely improves. See `docs/architecture/QUALITY_GATES.md`.
+9. Coverage must stay ≥60% (statements, lines, functions, branches).
 10. Never bypass Husky hooks (`--no-verify`, `--no-gpg-sign`) without explicit operator approval.
 11. Never embed public upstream OAuth client_id/secret or Firebase Web keys as string literals — always go through `resolvePublicCred()` (`open-sse/utils/publicCreds.ts`). See `docs/security/PUBLIC_CREDS.md`.
 12. Never return raw `err.stack` / `err.message` in HTTP / SSE / executor responses — always route through `buildErrorBody()` or `sanitizeErrorMessage()` (`open-sse/utils/error.ts`). See `docs/security/ERROR_SANITIZATION.md`.
 13. Never string-interpolate external paths or runtime values into shell scripts passed to `exec()`/`spawn()` — pass via the `env` option instead. Reference: `src/mitm/cert/install.ts::updateNssDatabases`.
 14. Never dismiss a CodeQL / Secret-Scanning alert without (a) first checking the pattern docs above to see if the helper applies, and (b) recording the technical justification in the dismissal comment. Precedent: `js/stack-trace-exposure` raised on callsites that already route through `sanitizeErrorMessage()` is a known CodeQL limitation (custom sanitizers not recognized) — dismiss as `false positive` referencing `docs/security/ERROR_SANITIZATION.md`.
 15. Never expose routes that spawn child processes (`/api/mcp/`, `/api/cli-tools/runtime/`) without `isLocalOnlyPath()` classification in `src/server/authz/routeGuard.ts`. Loopback enforcement happens unconditionally before any auth check — leaked JWT via tunnel cannot trigger process spawning. See `docs/security/ROUTE_GUARD_TIERS.md`.
-16. Never credit or advertise an AI assistant, LLM, or automation account in any commit/PR metadata. Two forbidden forms, both equivalent — they route attribution to a bot account (or advertise AI authorship) and hide the real author (`diegosouzapw`): **(a)** `Co-Authored-By` trailers naming an AI/bot (e.g. names containing "Claude", "GPT", "Copilot", "Bot"; emails at `anthropic.com` / `openai.com` / bot-owned `noreply.github.com` addresses); **(b)** AI-generation footers or descriptions anywhere in a commit message, PR title/body, or CHANGELOG — e.g. `🤖 Generated with [Claude Code]`, "Generated with Claude Code", "Made with <AI tool>", or any `Co-authored-by: Claude/GPT/Copilot` line. This **overrides any harness, template, or tool default that auto-appends such a footer** (e.g. the Claude Code PR-body/commit default) — strip it before pushing; do not let it reach a commit, PR, or CHANGELOG. Human collaborators — including upstream PR authors and issue reporters being ported into OmniRoute — MAY and SHOULD be credited with standard `Co-authored-by: Name <email>` trailers; the upstream-port workflows (`/port-upstream-features`, `/port-upstream-issues`) depend on this.
+16. Never include `Co-Authored-By` trailers that credit an AI assistant, LLM, or automation account (e.g. names containing "Claude", "GPT", "Copilot", "Bot"; emails at `anthropic.com` / `openai.com` / bot-owned `noreply.github.com` addresses). Such trailers route attribution to the bot account on GitHub, hiding the real author (`diegosouzapw`) in PR history. Human collaborators — including upstream PR authors and issue reporters being ported into OmniRoute — MAY and SHOULD be credited with standard `Co-authored-by: Name <email>` trailers; the upstream-port workflows (`/port-upstream-features`, `/port-upstream-issues`) depend on this.
 17. Never expose routes under `/api/services/` or `/dashboard/providers/services/*/embed/` without `isLocalOnlyPath()` classification in `src/server/authz/routeGuard.ts`. These routes can spawn child processes (`npm install`, `node`). Loopback enforcement happens unconditionally before any auth check — a leaked JWT via tunnel cannot trigger process spawning. See `docs/security/ROUTE_GUARD_TIERS.md`.
 18. Every bug fix must be validated before shipping: a failing-then-passing unit/integration test (TDD) OR a documented live test on the production VPS (192.168.0.15). A fix without either is not merged. See Testing → "Bug fix / issue triage protocol" for the full decision tree.
-19. Never develop on the shared main checkout. Every development task runs in its own git worktree on its own dedicated branch, and you MUST confirm the base branch with the operator (e.g. via `AskUserQuestion`) before creating the worktree/branch — never assume `main` or the currently checked-out branch. A `git checkout` in the shared checkout silently destroys other sessions' uncommitted work. Tear down only the worktrees/branches you created (by name, never `fix/*`/`feat/*` wildcards), leave other sessions' worktrees untouched, and end on the branch you started on (the active `release/vX.Y.Z`, never `main`). See Git Workflow → "Worktree isolation".
-20. PII redaction/sanitization is **opt-in — never on by default**. OmniRoute proxies for self-hosted/local LLMs where the operator owns the data, so mutating request/response payloads by default would silently corrupt legitimate traffic. The two data-mutating PII feature flags **MUST** keep `defaultValue: "false"` in `src/shared/constants/featureFlagDefinitions.ts`: `PII_REDACTION_ENABLED` (request-side) and `PII_RESPONSE_SANITIZATION` (response + streaming). All three application points — `src/lib/guardrails/piiMasker.ts` (request guardrail), `src/lib/piiSanitizer.ts` (response), `src/lib/streamingPiiTransform.ts` (SSE) — are gated on these flags; with both off the `pii-masker` guardrail still runs but never mutates payloads (data passes through untouched). Flipping either default to `"true"` requires explicit operator approval. The regression guard is `tests/unit/pii-opt-in-default.test.ts` (asserts both definition defaults + behavioral pass-through). Opt-in is per-operator via env or the settings/DB override (`src/lib/db/featureFlags.ts`), never a silent default. See `docs/security/GUARDRAILS.md`.
-21. **Release-freeze — the FROZEN release branch belongs to the release captain; development does NOT stop (parallel-cycle model, 2026-07-04).** `/generate-release` opens a marker issue labeled `release-freeze` at the start of reconciliation (Phase 0a), **immediately cuts the next cycle's branch `release/vX+1` from the frozen tip (Phase 0a.0b — bump + living release PR + re-home of open PRs)**, and closes the freeze once the release PR squash-merges to `main`. Before merging **any** PR, every campaign workflow (`/review-prs`, `/review-group-prs`, `/merge-prs`, `/triage-fix-bugs`, `/implement-fix-bugs`, `/triage-features`, `/implement-features`, `/green-prs`, `/port-upstream-*`) **MUST** check `gh issue list --repo diegosouzapw/OmniRoute --label release-freeze --state open` — if a freeze is active: **NEVER merge into the frozen `release/vX.Y.Z` named in the freeze title**; instead resolve the ACTIVE development branch (the **highest** `release/v*` by semver — normally `release/vX+1`, announced in a freeze-issue comment) and **retarget the PR there** (`gh pr edit <N> --base release/vX+1`, then VERIFY with `gh pr view <N> --json baseRefName` — the edit fails silently) and merge normally. **HOLD only when the highest release/v\* branch IS the frozen one** (the short window before 0a.0b completes, or a pre-parallel-cycle release) — in that case leave the PR ready and open, tell the operator, and resume when the next branch appears or the freeze lifts. The just-shipped fixes reach `release/vX+1` via the Phase 5 sync-back (`scripts/release/sync-next-cycle.mjs`); do not try to sync mid-release. This is a **coordination signal, not a permission lock**: the release captain and the campaign sessions share the `diegosouzapw` identity, so a GitHub branch-protection lock cannot distinguish them — only this honored marker prevents the mid-release commit races that forced full CHANGELOG re-reconciliation in v3.8.40/v3.8.41 (a parallel campaign advanced `release/vX.Y.Z` by 34 commits mid-run). The release captain's own reconciliation/cycle-open pushes are exempt — they _are_ the release. Fixes that must land during a freeze (a homologation finding) follow the post-merge read-only rule: land on `main` first via `fix/release-vX.Y.Z-*`. **⛔ ONLY `/generate-release` may raise a release-freeze, and ONLY at its Phase 0a (start of generating a new version) — lifted at Phase 12c after the squash-merge to `main`.** No campaign, session, or agent may open a `release-freeze` marker at any other time — a freeze is **never** a mid-development coordination tool. If a session ever believes a freeze is genuinely, unavoidably necessary outside the `/generate-release` flow, it **MUST first ask the operator (`diegosouzapw`) in chat, explicitly alert "estou criando um freeze" and get an explicit yes** — never open, extend, or re-open a `release-freeze` autonomously. Conversely, do **not** close/lift an active `/generate-release` freeze to unblock campaign merges: it protects the captain's single clean CI run and auto-lifts at Phase 12c — closing it early re-triggers the exact commit race it prevents. Verify a freeze is legitimate before acting on it: an open `release-freeze` whose title/body references an **OPEN** release PR (`gh pr view <N> --json state`) is the authorized captain freeze — hold, don't touch.
-22. **Cross-session safety — this repo is worked by MANY parallel sessions/agents at once; never step on another's in-flight work.** Two absolute bans, both recurring incidents (this rule exists because they keep happening):
-    - **(a) Never `git stash` / `git stash pop` — ANYWHERE in this repo, including inside an isolated worktree, and including inside any subagent you dispatch.** `git stash` operates on the **shared repository object store**, not the per-worktree working tree — so a stash pushed or popped in one session can silently clobber or resurrect another parallel session's uncommitted changes. This is not hypothetical: 2026-07-02 a `#5923` quotaCache change leaked into the unrelated `#2296` worktree via a global `stash pop`, and the same class reincided through a **subagent**. To compare working changes against a base ref **without** stashing, use `git show <ref>:<path>` or `git diff <ref> -- <path>`; to confirm a typecheck/lint error is pre-existing on the base, inspect the base ref directly (`git show origin/release/vX.Y.Z:<path>`) — never stash your tree away to "get it clean". **Put this ban verbatim in the prompt of every subagent that touches git** (agents don't inherit this file's context — the recurrence was a subagent).
-    - **(b) Never merge, push, rebase, or force-push a PR / branch / worktree that another session is actively working.** An open PR whose head is a live fix worktree in `.claude/worktrees/` you did **not** create (e.g. `fix-5852`/`fix-5923` carrying fresh commits, even when they share your `diegosouzapw` identity), or any branch another session owns, is **off-limits — HOLD**, and let the owning session merge it. **Before** merging or pushing to any PR you did not create _this_ session, run `git worktree list` to check for a matching in-flight worktree and re-check `gh pr view <N> --json state,headRefOid`. Only the owning session merges its own in-flight PR; mid-flight merges race the owner and re-trigger the exact commit/CHANGELOG races Rule #19 and Rule #21 guard against. (Reinforces Rule #19.)
 
 ---
 
 ## PII & Stream Sanitization Learnings
 
 ### 1. Regex Security (ReDoS)
-
 All regex patterns matching variable-length strings (e.g. IPv6 address, credit cards) must use strictly bounded, non-overlapping sequences (e.g., limit occurrences with bounded ranges `{1,7}`) to prevent catastrophic backtracking when processing untrusted inputs.
 
 ### 2. SSE Snapshot Handling
-
 When parsing streaming LLM responses (e.g. Responses API), check if a chunk represents a final snapshot (`done` or `completed` events). Snapshot text must be sanitized directly as a standalone string (bypassing rolling delta buffers) to prevent text duplication at the end of the stream.
 
 ### 3. Database Handles in Tests
-
 Ensure that any unit tests that trigger database migrations or establish SQLite connections call `resetDbInstance()` and properly clean up/close all DB handles in a `test.after(...)` hook. Failure to release database connection handles will cause Node's native test runner to hang indefinitely.

CONTRIBUTING.md

@@ -71,11 +71,11 @@ PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
 
 ### Build Output Layout
 
-| Directory | Contents                                                                  | Tracked |
-| --------- | ------------------------------------------------------------------------- | ------- |
-| `src/`    | Application source (TypeScript / TSX)                                     | Yes     |
-| `.build/` | Intermediates — `next build` output (gitignored, `distDir = .build/next`) | No      |
-| `dist/`   | Shippable bundle — assembled by `assembleStandalone` (gitignored)         | No      |
+| Directory  | Contents                                    | Tracked |
+| ---------- | ------------------------------------------- | ------- |
+| `src/`     | Application source (TypeScript / TSX)       | Yes     |
+| `.build/`  | Intermediates — `next build` output (gitignored, `distDir = .build/next`) | No |
+| `dist/`    | Shippable bundle — assembled by `assembleStandalone` (gitignored) | No |
 
 The build pipeline is a single pass:
 
@@ -160,31 +160,19 @@ npm run test:protocols:e2e
 # Ecosystem compatibility tests
 npm run test:ecosystem
 
-# Coverage gate: 60% statements/lines/functions/branches
+# Coverage gate: 75% statements/lines/functions, 70% branches
 npm run test:coverage
 npm run coverage:report
 
 # Lint + format check
 npm run lint
 npm run check
-
-# Gated real-upstream combo smoke (requires VPS access + real provider credits)
-# Hits REAL providers — costs a little. NEVER runs in CI. Skips cleanly without the gate.
-# Needs: ssh root@192.168.0.15 access (sources a read-only DB snapshot from the VPS).
-RUN_COMBO_LIVE=1 npm run test:combo:live
-
-# Phase-3 VPS live smoke — plain Node ESM scripts, hit the live .15 server directly.
-# Requires: ssh root@192.168.0.15 access (combos created/torn down via SSH sqlite).
-# Hits REAL providers (small cost). Creates/deletes only __live_test__* combos. NEVER runs in CI.
-# REQUIRE_API_KEY=false on .15 so no API key needed, but honors COMBO_LIVE_BASE_URL / COMBO_LIVE_API_KEY if set.
-npm run test:combo:live:vps              # 7 HTTP scenarios (priority/round-robin/weighted/cost/fusion/auto + health)
-npm run test:combo:live:vps:failover     # adds a real cross-provider failover scenario (8 total)
 ```
 
 Coverage notes:
 
 - `npm run test:coverage` measures source coverage for the main unit test suite, excludes `tests/**`, and includes `open-sse/**`
-- Pull requests must keep the coverage gate at **60%+** statements/lines/functions/branches
+- Pull requests must keep the coverage gate at **75%+** statements/lines/functions and **70%+** branches
 - If a PR changes production code in `src/`, `open-sse/`, `electron/`, or `bin/`, it must add or update automated tests in the same PR
 - `npm run coverage:report` prints the detailed file-by-file report from the latest coverage run
 - `npm run test:coverage:legacy` preserves the older metric for historical comparison
@@ -196,7 +184,7 @@ Before opening or merging a PR:
 
 - Run `npm run test:unit`
 - Run `npm run test:coverage`
-- Ensure the coverage gate stays at **60%+** statements/lines/functions/branches
+- Ensure the coverage gate stays at **75%+** statements/lines/functions, **70%+** branches
 - Include the changed or added test files in the PR description when production code changed
 - Check the SonarQube result on the PR when the project secrets are configured in CI
 
@@ -264,7 +252,7 @@ open-sse/                   # @omniroute/open-sse workspace
 electron/                   # Electron desktop app (cross-platform)
 
 tests/
-├── unit/                   # Node.js test runner (1,574 test files)
+├── unit/                   # Node.js test runner (122 test files)
 ├── integration/            # Integration tests
 ├── e2e/                    # Playwright tests
 ├── security/               # Security tests
@@ -341,7 +329,7 @@ Write unit tests in `tests/unit/` covering at minimum:
 - [ ] Error responses route through `buildErrorBody()` / `sanitizeErrorMessage()` — no raw stack traces in response bodies (see [`docs/security/ERROR_SANITIZATION.md`](./docs/security/ERROR_SANITIZATION.md))
 - [ ] Shell commands (`exec` / `spawn`) pass runtime values via `env`, not via string interpolation
 - [ ] All inputs validated with Zod schemas
-- [ ] Changelog **fragment** added under `changelog.d/{features|fixes|maintenance}/<PR>-<slug>.md` for user-facing changes (see [`changelog.d/README.md`](./changelog.d/README.md)) — do **not** edit `CHANGELOG.md` directly; fragments are aggregated at release time and never conflict between PRs
+- [ ] CHANGELOG updated (if user-facing change)
 - [ ] Documentation updated (if applicable)
 - [ ] No new CodeQL / Secret-Scanning alerts opened, or each one dismissed with technical justification referencing the relevant `docs/security/` doc
 - [ ] Routes that spawn child processes (`/api/mcp/`, `/api/cli-tools/runtime/`) classified as `isLocalOnlyPath()` in `src/server/authz/routeGuard.ts` — see [Hard Rule #15](docs/security/ROUTE_GUARD_TIERS.md)

Dockerfile

@@ -2,46 +2,24 @@
 FROM node:24-trixie-slim AS base
 WORKDIR /app
 
-# `apt-get upgrade` pulls the security-patched versions of the Debian (trixie)
-# base-image packages at build time — clears the subset of container-scan CVEs
-# (perl / util-linux / systemd / ncurses / zlib / tar / sqlite / shadow / pam …)
-# that already have a fix published in trixie. CVEs without an upstream fix yet
-# (local-only TOCTOU, etc.) remain until the distro patches them and the image
-# is rebuilt; none are reachable from the proxy's request surface at runtime.
-RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=shared \
-  --mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=shared \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=shared \
+  --mount=type=cache,target=/var/lib/apt/lists,sharing=shared \
   apt-get update \
-  && apt-get upgrade -y \
   && apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
   && rm -rf /var/lib/apt/lists/*
 
-# Refresh the globally-installed npm so its *bundled* node_modules (undici, tar)
-# ship the patched versions. These are npm's own internals — not application
-# dependencies (our app already resolves undici@8.5.0 / tar@7.5.16, both fixed) —
-# but the container scanner flags the stale copies under
-# /usr/local/lib/node_modules/npm/node_modules. npm is not invoked at runtime in
-# the runner stages, so this is hygiene, not an exploitable runtime path.
-RUN npm install -g npm@latest \
-  && npm cache clean --force
-
 # ── Builder ────────────────────────────────────────────────────────────────
 FROM base AS builder
 
 # Build tools for native module compilation
 # apt-get update needed here because base's rm -rf clears the shared cache
-RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=shared \
-  --mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=shared \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=shared \
+  --mount=type=cache,target=/var/lib/apt/lists,sharing=shared \
   apt-get update \
   && apt-get install -y --no-install-recommends python3 make g++ \
   && rm -rf /var/lib/apt/lists/*
 
 COPY package*.json ./
-# Workspace package manifests MUST be present before `npm ci` so npm materializes
-# the workspace and installs its *workspace-only* deps (e.g. safe-regex,
-# @toon-format/toon — declared in open-sse/package.json, not hoisted to root).
-# Without this, `npm ci` skips them and the application build fails with "Module not
-# found" (root cause of the v3.8.39 Docker build break). workspaces = ["open-sse"].
-COPY open-sse/package.json ./open-sse/package.json
 COPY scripts/build/postinstall.mjs ./scripts/build/postinstall.mjs
 COPY scripts/build/postinstallSupport.mjs ./scripts/build/postinstallSupport.mjs
 COPY scripts/build/native-binary-compat.mjs ./scripts/build/native-binary-compat.mjs
@@ -55,51 +33,16 @@ ENV NPM_CONFIG_LEGACY_PEER_DEPS=true
 # are reproducible.
 RUN test -f package-lock.json \
   || (echo "package-lock.json is required for reproducible Docker builds" >&2 && exit 1)
-# `npm rebuild <pkg>` re-runs the package's own install script, so under npm 11 +
-# `--ignore-scripts` on the parent `npm ci` it depends on npm's script-allowlist
-# machinery correctly re-enabling that one package's script. Some self-hosted build
-# environments (e.g. Dokploy) hit a broken/incomplete better-sqlite3 native binding
-# from that indirection. Invoking `node-gyp rebuild` directly inside the package
-# directory bypasses npm's script-running layer entirely and is deterministic
-# regardless of npm version or ignore-scripts allowlist behavior.
-# node-gyp comes from npm's own bundled copy (deterministic, already in the image)
-# instead of `npx --yes`, which would install an arbitrary registry version
-# on-demand and run its lifecycle scripts (Sonar docker:S6505).
-RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
+RUN --mount=type=cache,target=/root/.npm \
   npm ci --no-audit --no-fund --legacy-peer-deps --ignore-scripts \
-  && (cd node_modules/better-sqlite3 \
-      && node /usr/local/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js rebuild) \
+  && npm rebuild better-sqlite3 \
   && node -e "require('better-sqlite3')(':memory:').close()"
 
-# Build with Turbopack (stable in Next 16, the repo default). The v3.8.27-era
-# TurbopackInternalError panic ("entered unreachable code: there must be a path to a
-# root" in ImportTracer::get_traces) no longer reproduces on Next 16.2.9 — validated
-# 2026-07-05 with clean amd64 (12min14s, image smoke-tested: /api/monitoring/health
-# 200) and arm64 (qemu, exit 0, zero panic strings) builds. Turbopack cut the bare
-# build from 17min to 9min on the same 32-core box. Webpack stays available as the
-# escape hatch: `--build-arg`/-e OMNIROUTE_USE_TURBOPACK=0.
-# See docs/ops/QUALITY_GATE_PLAYBOOK.md Parte 6.
+# Use Turbopack for significant build speedup
 ENV OMNIROUTE_USE_TURBOPACK=1
 
-# Docker containers cannot run the MITM/Agent-Bridge stack (no host DNS/cert
-# access), so keep @/mitm/manager on the graceful stub (#3390). This flag is
-# Docker-only: npm/Electron/VPS builds must bundle the REAL manager (#6344).
-ENV OMNIROUTE_MITM_STUB=1
-
-# Raise the V8 heap ceiling for the build. The webpack production optimization
-# pass needs more than V8's default ceiling (~2 GB) for a codebase this size; a
-# memory-constrained Docker build otherwise dies with "FATAL ERROR: ... JavaScript
-# heap out of memory" during the builder stage (#4076). Turbopack's compile is
-# native (Rust) and less V8-heap-bound, but the prerender/export phase still runs
-# on V8, so keep the ceiling. NODE_OPTIONS propagates to the spawned `next build`
-# child (build-next-isolated.mjs → resolveNextBuildEnv spreads process.env).
-# Build-only; the runtime heap is set separately on the runner stage
-# (OMNIROUTE_MEMORY_MB). Override: `--build-arg OMNIROUTE_BUILD_MEMORY_MB=6144`.
-ARG OMNIROUTE_BUILD_MEMORY_MB=4096
-ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_BUILD_MEMORY_MB}"
-
 COPY . ./
-RUN --mount=type=cache,id=next-cache,target=/app/.build/next/cache \
+RUN --mount=type=cache,target=/app/.build/next/cache \
   mkdir -p /app/data && npm run build
 
 # ── Runner base ────────────────────────────────────────────────────────────
@@ -114,12 +57,6 @@ LABEL org.opencontainers.image.title="omniroute" \
 ENV NODE_ENV=production
 ENV PORT=20128
 ENV HOSTNAME=0.0.0.0
-# Runtime heap ceiling. 1024MB is enough for normal traffic but can be tight
-# for large fusion-combo panels (many models fanned out in parallel, each
-# response buffered in full — see open-sse/services/fusion.ts::FUSION_DEFAULTS
-# .maxPanel, issue #1905). Override at `docker run` time with
-# `-e OMNIROUTE_MEMORY_MB=2048` (or higher) if you raise fusionTuning.maxPanel
-# above the default cap.
 ENV OMNIROUTE_MEMORY_MB=1024
 ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_MEMORY_MB}"
 
@@ -201,8 +138,8 @@ COPY --from=builder /app/node_modules/playwright ./node_modules/playwright
 # browsers land under /home/node which persists across image layers and is
 # accessible to the non-root runtime user.
 ENV PLAYWRIGHT_BROWSERS_PATH=/home/node/.cache/ms-playwright
-RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
-  --mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
   apt-get update \
   && node node_modules/playwright/cli.js install chromium --with-deps \
   && chown -R node:node /home/node/.cache \
@@ -218,15 +155,15 @@ FROM runner-base AS runner-cli
 USER root
 
 # Install system dependencies required by openclaw (git+ssh references).
-RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
-  --mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+  --mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
   apt-get update \
   && apt-get install -y --no-install-recommends git ca-certificates docker.io docker-compose \
   && rm -rf /var/lib/apt/lists/* \
   && git config --system url."https://github.com/".insteadOf "ssh://git@github.com/"
 
 # Install CLI tools globally. Separate layer from apt for better cache reuse.
-RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
+RUN --mount=type=cache,target=/root/.npm \
   npm install -g --no-audit --no-fund @openai/codex @anthropic-ai/claude-code droid openclaw@latest
 
 USER node

PLANO-QUALITY-GATES-FASE6A.md

@@ -0,0 +1,209 @@
+# Fase 6A — Auditoria Crítica das Fases 0–6: o que deixamos passar
+
+> **Para workers agênticos:** SUB-SKILL OBRIGATÓRIA: `superpowers:subagent-driven-development` (recomendado) ou `superpowers:executing-plans`, tarefa-a-tarefa. Tarefas P0/P1 maiores devem ser **expandidas em sub-plano bite-sized próprio** (`writing-plans`) no momento da execução. Hard Rule #18 (TDD/VPS) em tudo. Auditar subagentes (trust-but-verify) após cada task.
+
+> # ⏳ PORTÃO DE ATIVAÇÃO — NÃO INICIAR ANTES DE **2026-06-16**
+> Mesma janela da Fase 7 (decisão do owner 2026-06-09: 1 semana de uso em produção das Fases 0–6 antes de evoluir). **Ordem na ativação: Fase 6A ANTES da Fase 7** — primeiro consertamos/endurecemos o que já existe, depois adicionamos ferramentas novas.
+> **Exceção possível (decisão do owner):** as tasks **6A.1 e 6A.2 são bugs pré-existentes descobertos pela auditoria** (testes que nunca rodam + suíte vitest fora do CI), não "gates novos" — podem ser antecipados como fix avulso se o owner preferir não esperar a janela.
+
+**Goal:** Fechar os furos que a auditoria crítica pós-implementação (2026-06-09, análise inline dos 18 gates + motor + CI + baselines) encontrou nas Fases 0–6 — antes de adicionar qualquer ferramenta nova na Fase 7.
+
+**Architecture:** Zero ferramenta nova (tudo homegrown, padrão `check-*.mjs` + motor existente). Três frentes: (1) **bugs sistêmicos de runner** descobertos (testes órfãos, vitest fora do CI); (2) **endurecimento do padrão de catraca** (stale-allowlist enforcement + require-tighten, validados pela prática da Notion); (3) **expansão de escopo** dos gates existentes (diretórios/superfícies que ficaram de fora).
+
+**Tech Stack:** Node ≥20 ESM, ESLint 9 flat, c8, jscpd@4 (a pinar), GitHub Actions, Node native test runner, vitest. Nada novo em `dependency-allowlist.json` exceto a promoção do jscpd a devDependency (Task 6A.12).
+
+---
+
+## Origem: o que a auditoria encontrou (resumo dos achados)
+
+Método: releitura inline de todos os `scripts/check/*.{mjs,ts}` criados nas Fases 0–6, `scripts/quality/*`, baselines, `ci.yml`, `package.json`, hooks Husky e docs — sem subagentes — mais validação por pesquisa (sistema de ratcheting da Notion; práticas de suppression-hygiene de linters).
+
+| # | Achado | Gravidade | Task |
+|---|--------|-----------|------|
+| A1 | **≈135 arquivos `*.test.ts` em subdiretórios de `tests/unit/` não são coletados por NENHUM runner** — `test:unit`, `test:coverage` e os shards do CI usam o glob não-recursivo `tests/unit/*.test.ts`; o vitest só inclui `autoCombo/**` (+ `.tsx`). Inclui `authz/routeGuard.test.ts` (Hard Rules #15/#17), 50 testes de `compression/`, 12 de `services/`, 10 de `gamification/`, 6 de `guardrails/`, 5 de `security/`. **Amostra rodada na auditoria: 2 asserts de `routeGuard.test.ts` FALHAM hoje** ("management policy allows /api/services/ (e /api/copilot/chat) from localhost with valid CLI token") — o arquivo apodreceu sem ninguém ver, provavelmente desde o redesign do peer-stamp (2026-05-31) | **P0 — falso verde sistêmico** | 6A.1 |
+| A2 | **Nenhum workflow roda `test:vitest`** (`grep -rln vitest .github/workflows/` = vazio). O CLAUDE.md afirma "Both test runners must pass… before merging", mas a suíte vitest (MCP server 43 tools, autoCombo, cache, componentes) está 100% fora da esteira | **P0** | 6A.2 |
+| B1 | **Nenhum gate falha quando uma entrada de allowlist deixa de ser necessária.** Os 18 gates congelam ~90 violações em `KNOWN_*`; quando alguém corrige a violação (ex.: criar `/api/gamification/level` da issue #3484, remover `krutrim` da #3483), a entrada vira um furo aberto — a regressão pode VOLTAR sem revisão. Só `check-error-helper` tem detecção parcial (WARN de arquivo inexistente, que ninguém lê). Prática validada: linters maduros "yell when an exclusion exists that doesn't break the rule" | **P0 — corrói a catraca com o tempo** | 6A.3 |
+| B2 | **Melhoria não-capturada vira folga permanente no motor**: sem `--update` manual, uma métrica que melhorou pode regredir de volta até o baseline antigo sem ninguém ver. A Notion auto-decrementa budgets no pre-commit; nosso motor não exige aperto | P1 | 6A.5 |
+| B3 | EPS único (0.01) para todas as métricas; o plano da Fase 4 pedia epsilon maior para `coverage.branches` (não-determinismo do v8) e não foi implementado | P1 | 6A.5 |
+| B4 | Métrica coletada sem entrada no baseline é ignorada em silêncio (coletor novo esquecido do baseline = falso conforto) | P2 | 6A.5 |
+| C1 | `check-fetch-targets` só varre `src/app/(dashboard)` — **20+ arquivos com `fetch("/api/…")` fora do escopo**: `src/shared/components/` (Sidebar, CommandPalette, modais…), `src/app/connect/`, `src/app/status/`, `src/lib/evals/` | P1 | 6A.7 |
+| C2 | `check-fetch-targets` ignora 100% dos template literals (`` fetch(`/api/x/${id}`) ``) — nem o prefixo estático é validado | P1 | 6A.7 |
+| C3 | `check-fetch-targets` não valida o método HTTP (fetch `POST` → rota só com `GET` = 405 em runtime, gate verde) | P2 | 6A.7 |
+| C4 | `check-deps` cobre só `package.json` raiz + `electron/` — **`@omniroute/opencode-plugin` (dep `zod` + 5 devDeps, pacote PUBLICADO no npm), `@omniroute/opencode-provider` e `open-sse/` ficam fora** | P1 | 6A.8 |
+| C5 | `check-public-creds` escaneia só 2 arquivos hardcoded — credencial literal em arquivo NOVO (executor, oauth provider) passa batida | P1 | 6A.8 |
+| C6 | `check-error-helper` cobre `open-sse/executors` + `handlers` — a Hard Rule #12 também fala de **MCP handlers** (`open-sse/mcp-server/`) e rotas HTTP (`src/app/api/`), fora do escopo | P1 | 6A.8 |
+| C7 | `check-file-size` e `check-complexity` varrem `src` + `open-sse` — `electron/` e `bin/` fora (god-file pode nascer lá) | P2 | 6A.11 |
+| C8 | `check-known-symbols` cobre executors/strategies/translators — **faltam as 3 superfícies de despacho por-string restantes: MCP tools (43), A2A skills (5, `A2A_SKILL_HANDLERS`), cloud agents (3, registry)** | P1 | 6A.9 |
+| C10 | `check-route-guard-membership` depende da lista manual `SPAWN_CAPABLE_ROUTE_ROOTS` (3 raízes) — rota nova que spawna processo FORA dessas raízes é invisível ao gate | P1 | 6A.8 |
+| C11 | `check-openapi-coverage` (THRESHOLD=36%) e `check-ui-keys-coverage` (65%) são pisos fixos manuais — não ratcheteiam; rotas/strings novas sem doc/i18n passam enquanto o % não cai do piso | P2 | 6A.11 |
+| C12 | `check-test-masking`: (a) `--diff-filter=M` não vê teste **DELETADO** (o masking mais brutal); (b) não vê `.skip`/`.todo`/`.only` adicionados (mantêm os asserts no texto, mas nunca rodam); (c) tautologia só cobre `assert.ok(true)` | P1 | 6A.10 |
+| D1 | **`ci.yml` roda gates apenas em `pull_request → main`** — todo o ciclo de PRs feature→`release/vX` passa SEM gate; as violações acumulam por semanas e estouram juntas no merge release→main (observado no gate da v3.8.18: 4 fixes de typecheck + ReDoS de última hora) | P1 — decisão do owner | 6A.6 |
+| D2 | `.husky/pre-push` está 100% comentado, mas o CLAUDE.md afirma "pre-push: npm run test:unit" (drift doc↔real) | P2 | 6A.12 |
+| D3 | **CLAUDE.md não menciona nenhum dos 18 gates** — um agente futuro não sabe que existem, qual a política de allowlist ("corrija, não congele"), nem como apertar baselines. Hard Rule #9 ainda diz "≥60%" (a catraca real é 80/80/82/73) | **P0 — anti-alucinação para os próprios agentes** | 6A.4 |
+| D4 | `check-duplication` roda `npx --yes jscpd@4` — pacote **não pinado por lockfile**, baixado do registry a cada run do CI (supply-chain + flakiness + latência); contraria o espírito do próprio `check-deps` | P2 | 6A.12 |
+| D5 | A skill `/quality-scan` roda ~20 comandos um a um — falta um runner agregador paralelo | P2 | 6A.12 |
+| D6 | Baselines de coverage com folga de ~2,5pt (80/80/82/73 vs real ~82,6/82,6/84,2/75,2) — a nota "_aperte após o 1º run verde_" existe no JSON mas não é tarefa de ninguém | P1 | 6A.5 |
+| E4 | Sem guarda contra artefato trackeado por engano — `node_modules` symlink já foi commitado 2× neste repo (`git add -A` em worktree) | P2 | 6A.12 |
+
+**Decisões conscientes de NÃO fazer (avaliadas e descartadas, com motivo):**
+- **Gate de idempotência de migrations via regex** — SQLite não tem `ADD COLUMN IF NOT EXISTS`; idempotência vive em try/catch do runner; regex seria frágil (FP/FN). O `check-migration-numbering` + revisão humana bastam.
+- **Endurecer `check-docs-counts-sync` para fail** — contagens em prosa são heurísticas; soft-fail é o design correto. A cobertura de MCP tools entra pela 6A.9 (símbolos, não prosa).
+- **Sentido inverso do provider-consistency (providers.ts → REGISTRY)** — muitos providers canônicos legitimamente não têm entrada no REGISTRY (web/OAuth-only); a allowlist nasceria com dezenas de entradas e baixa razão sinal/ruído. Reavaliar quando o refactor #3501 tocar o split de providers.
+- **Complexidade por-função/por-arquivo (formato any-budget)** — upgrade real, mas o count global + `max-lines-per-function` já bloqueiam o grosso; o formato per-file entra junto com `sonarjs/cognitive-complexity` na Fase 7 Task 5 para não pagar duas migrações de baseline.
+
+---
+
+# Tasks
+
+## P0 — bugs sistêmicos + documentação
+
+### Task 6A.1 — `check-test-discovery` + religamento triado dos ~135 testes órfãos ⭐
+
+**O achado nº1 da auditoria.** Testes que não rodam são o falso verde definitivo — todo o investimento anti test-masking da Fase 4 protege asserts de testes que **nem executam**.
+
+**Files:**
+- Create: `scripts/check/check-test-discovery.mjs` + `tests/unit/check-test-discovery.test.ts`
+- Modify: `package.json` (globs de `test:unit`, `test:coverage`), `.github/workflows/ci.yml` (globs dos shards 8×/node24/node26), `vitest.mcp.config.ts` ou `vitest.config.ts` (se algum subdir for re-homed para vitest)
+- Create: `test-discovery-baseline.json` (órfãos ainda-não-religados, catraca `down` até zerar)
+
+**Approach (expandir em sub-plano na execução):**
+1. **Gate primeiro (TDD):** `check-test-discovery.mjs` enumera todo `**/*.{test,spec}.{ts,tsx}` do repo (fora de `node_modules`/`.next`) e verifica que cada arquivo é coletado por ≥1 runner: (a) globs do node test runner extraídos de `package.json`/`ci.yml`; (b) `include` dos dois `vitest.*config.ts`; (c) projetos Playwright. Órfão fora do baseline → exit 1. O baseline congela os órfãos atuais (catraca: não pode SUBIR; religamentos a fazem cair até `{}`).
+2. **Inventário verde/vermelho:** rodar cada subdir órfão isoladamente (`node --import tsx --test tests/unit/<dir>/*.test.ts`), registrar passa/falha. *Não* ligar tudo de uma vez — a amostra já provou que há vermelhos (`authz/routeGuard.test.ts`: 2 asserts).
+3. **Religar os verdes:** trocar o glob principal para recursivo — `"tests/unit/**/*.test.ts"` ENTRE ASPAS (expandido pelo test runner do Node, não pelo shell; **Step 0: validar o suporte a glob do runner na menor versão de Node suportada pelo repo** — fallback: listar os subdirs explicitamente) — em `test:unit`, `test:coverage` e nos 3 lugares do `ci.yml` (shards 8×, node24, node26). Remover religados do baseline.
+4. **Triar os vermelhos (Hard Rule #18 em cada um):** teste desatualizado → atualizar para o comportamento real (e provar que o comportamento real é o desejado); bug real revelado → fix TDD; teste de feature morta → deletar com justificativa no commit. Os 2 asserts do `routeGuard.test.ts` ("allows … with valid CLI token") são o primeiro caso: provável drift do peer-stamp de 2026-05-31 — MAS, por ser superfície de segurança (#15/#17), confirmar com cuidado que é o teste que está errado, não o guard.
+5. **Recalibrar cobertura:** religar ≈135 arquivos muda o denominador/numerador da cobertura — re-medir e apertar `quality-baseline.json` via `--update` no mesmo PR (resolve também o D6).
+
+**Acceptance:** `check-test-discovery` no CI (job lint); zero órfãos fora do baseline; baseline decrescente documentado; suíte verde com os religados; cobertura recalibrada.
+
+### Task 6A.2 — vitest no CI
+
+**Files:** `.github/workflows/ci.yml` (job novo `test-vitest`, paralelo aos shards; NÃO tocar nos triggers — apenas adicionar job).
+
+**Approach:** job com `npm ci` + `npm run test:vitest` (+ `test:vitest:ui` se o tempo couber; senão segundo step). Rodar localmente primeiro para garantir verde (a suíte passa hoje fora da esteira — confirmar). Se houver vermelho pré-existente, triagem antes do wire (mesmo protocolo da 6A.1 passo 4).
+
+**Acceptance:** PR→main roda as DUAS suítes; o claim do CLAUDE.md ("both must be green") vira verdade mecânica.
+
+### Task 6A.3 — Stale-allowlist enforcement em todos os gates (suppression hygiene)
+
+**O endurecimento sistêmico nº1.** Padrão validado (ESLint `--report-unused-disable-directives`; Notion): exclusão que não exclui nada vivo é dívida fantasma e furo de regressão.
+
+**Files:** todos os gates com allowlist + seus testes:
+`check-fetch-targets` (KNOWN_MISSING, 7) · `check-provider-consistency` (KNOWN_REGISTRY_ONLY, 1) · `check-openapi-routes` (KNOWN_STALE_SPEC, 1) · `check-public-creds` (KNOWN_LITERAL_CREDS, 5) · `check-db-rules` (KNOWN_UNEXPORTED 25 + KNOWN_RAW_SQL 15) · `check-docs-symbols` (KNOWN_STALE_DOC_REFS, 30) · `check-migration-numbering` (KNOWN_GAPS/DUPLICATES) · `check-error-helper` (KNOWN_MISSING_ERROR_HELPER, 7 — promover o WARN existente a FAIL e cobrir também "arquivo existe mas não viola mais") · `check-deps` (dependency-allowlist: entrada sem dep correspondente em manifest algum = stale) · `check-file-size` (entrada `frozen` cujo arquivo foi deletado/renomeado) · `check-route-guard-membership` (KNOWN_UNCLASSIFIED — vazio hoje; implementar o check para quando deixar de ser).
+
+**Approach (mecânica única, TDD por gate):** após a detecção normal, re-avaliar cada entrada da allowlist: *"se esta entrada não existisse, o gate flagaria algo?"* — para allowlists de path/valor isso é `violationsDetectadas.has(entry)`; para arquivos, existência + violação presente. Entrada que não suprime nada → **exit 1** com mensagem `entrada obsoleta — a violação foi corrigida; REMOVA a entrada para travar a correção`. Extrair helper comum `reportStaleEntries(allowlist, liveViolations, gateName)` em `scripts/check/lib/allowlist.mjs` para não duplicar 11×.
+
+**Acceptance:** corrigir qualquer violação congelada (ex.: as issues #3483–#3501) passa a EXIGIR a remoção da entrada no mesmo PR; teste sintético prova fail-on-stale em cada gate.
+
+### Task 6A.4 — Documentar os gates no CLAUDE.md (+ corrigir drifts de doc)
+
+**Files:** `CLAUDE.md`, `AGENTS.md` (se houver seção espelho), `docs/architecture/` (página `QUALITY_GATES.md` referenciada pela tabela de docs).
+
+**Approach:** (1) seção nova "Quality Gates & Ratchets" no CLAUDE.md: tabela dos gates (nome → o que trava → allowlist/baseline), a política **"corrija a causa; allowlist só com justificativa + issue"**, como apertar (`npm run quality:ratchet -- --update`, `check:<gate> -- --update`), e o que fazer quando um gate falha num PR. (2) Corrigir: Hard Rule #9 (60% → "catraca de cobertura: nunca abaixo do baseline congelado em `quality-baseline.json`; piso absoluto 60"), claim do pre-push (refletir o real pós-6A.12), claim "both runners" (verdade pós-6A.2). (3) Página `docs/architecture/QUALITY_GATES.md` com o detalhe operacional (o CLAUDE.md fica curto, linka). Rodar `check:docs-all` após editar (o próprio docs-sync valida).
+
+**Acceptance:** agente novo lendo o CLAUDE.md descobre os gates e a política sem ler scripts; `check:docs-all` verde.
+
+## P1 — endurecimento do motor + escopos
+
+### Task 6A.5 — Motor v2: `--require-tighten`, eps por métrica, métricas órfãs
+
+**Files:** `scripts/quality/check-quality-ratchet.mjs`, `quality-baseline.json` (schema), `tests/unit/quality-ratchet.test.ts`, `.github/workflows/ci.yml` (flag no job quality-gate).
+
+**Approach (TDD):**
+1. Schema por métrica ganha campos opcionais: `eps` (default 0.01) e `tightenSlack` (default: igual a `eps`).
+2. Novo modo `--require-tighten` (ligado no CI): se `atual` melhor que `baseline` além de `tightenSlack`, **exit 1** com `melhorou de X para Y — rode 'npm run quality:ratchet -- --update' e commite o baseline apertado neste PR`. Métricas determinísticas (`eslintWarnings`) usam slack 0; cobertura usa slack 1.5 (flutuação v8). É o "auto-decrement" da Notion adaptado a CI sem bot de commit.
+3. Warning para métricas presentes em `quality-metrics.json` sem entrada no baseline (coletor órfão).
+4. Calibrar os 4 `coverage.*` para o real medido (fecha D6 — coordenar com a 6A.1 passo 5, que muda a base).
+
+**Acceptance:** melhoria sem aperto de baseline falha no CI; flutuação de coverage dentro do slack não falha; testes cobrem os 3 comportamentos novos.
+
+### Task 6A.6 — `quality.yml`: gates rápidos em PRs → `release/**` ⚠️ DECISÃO DO OWNER
+
+**Contexto sensível:** o owner já reverteu mudança de trigger no `ci.yml` ("não mexe na CI"). Esta task **não toca o `ci.yml`** — cria um workflow NOVO e enxuto. Ainda assim, **passo 0 = confirmação explícita do owner**.
+
+**Files:** Create: `.github/workflows/quality.yml`.
+
+**Approach:** `on: pull_request: branches: ["release/**"]`; um job único (~1–2 min) só com os gates determinísticos filesystem-only: provider-consistency, fetch-targets, openapi-routes, docs-symbols, deps, file-size, error-helper, migration-numbering, public-creds, db-rules, known-symbols, route-guard-membership, test-discovery (pós-6A.1) + `check:any-budget:t11`. SEM lint/test/build (continuam só no PR→main). Ganho: a violação aparece no PR que a introduz, não semanas depois no gate do release (padrão observado: 4 fixes de última hora no release da v3.8.18).
+
+**Acceptance:** PR de teste contra a release branch com uma rota inventada falha em <2 min; PRs limpos não ganham mais que ~2 min de CI.
+
+### Task 6A.7 — `check-fetch-targets` v2: escopo completo + prefixo de template + método HTTP
+
+**Files:** `scripts/check/check-fetch-targets.mjs`, `tests/unit/check-fetch-targets.test.ts`.
+
+**Approach (TDD):**
+1. **Escopo:** varrer todo `src/**/*.{ts,tsx}` client-side (excluindo `src/app/api/**`, testes, `src/lib/db`), não só `(dashboard)` — congela os misses pré-existentes que aparecerem em `KNOWN_MISSING` (com triagem/issue por cluster, igual Fase 2).
+2. **Template literals:** extrair o prefixo estático de `` fetch(`/api/x/y/${id}…`) `` e validar por **prefix-match** contra as rotas reais (existe alguma rota cujo path começa com `/api/x/y/`?). Pega diretório inteiro alucinado; não tenta resolver o sufixo dinâmico.
+3. **Método HTTP (heurístico, mesma chamada):** quando o 2º argumento literal contém `method: "POST"` (etc.), verificar que o `route.ts` resolvido exporta a função correspondente (`grep` por `export (async )?function POST` / `export const POST`). Sem method literal → assume GET-ok (rota existe basta). Casos dinâmicos → skip silencioso.
+
+**Acceptance:** fixture com fetch em `src/shared/components` + template com prefixo falso + `method: "DELETE"` para rota só-GET — 3 detecções; repo real verde com os novos congelados documentados.
+
+### Task 6A.8 — Escopo dos gates de segurança: error-helper, public-creds, route-guard, deps
+
+**Files:** `check-error-helper.mjs`, `check-public-creds.mjs`, `check-route-guard-membership.ts`, `check-deps.mjs` + testes.
+
+**Approach (TDD, um sub-commit por gate):**
+1. **error-helper** (+Rule #12 completa): incluir `open-sse/mcp-server/**` e `src/app/api/**/route.ts` no SCAN_DIRS; rodar; congelar os achados novos em KNOWN com comentário-justificativa cada (e issue por cluster).
+2. **public-creds**: além dos 2 arquivos âncora, varrer `open-sse/**` e `src/lib/oauth/**` com a mesma `CRED_KEY_RE` (linha a linha, barato); congelar achados. Limitação documentada: `const CLIENT_ID = "…"` (variável solta) continua fora — o gitleaks da Fase 7 cobre essa classe.
+3. **route-guard**: novo sub-check — todo `route.ts` (qualquer raiz) cujo fonte OU imports de 1º nível relativos contenham `child_process`/`spawn(`/`execFile(`/`worker_threads` deve ser classificado local-only por `isLocalOnlyPath()`. Mata a dependência da lista manual de 3 raízes.
+4. **deps**: `MANIFESTS` → descoberta automática de todo `package.json` do repo (fora `node_modules`/`.next`): hoje raiz, `electron/`, `open-sse/`, `@omniroute/opencode-plugin/` (dep `zod` entra na allowlist), `@omniroute/opencode-provider/`. Workspace novo amanhã entra sozinho.
+
+**Acceptance:** fixtures sintéticas por gate; repo real verde com achados congelados + issues; dep nova em QUALQUER manifest do repo dispara o gate.
+
+### Task 6A.9 — `check-known-symbols` v2: MCP tools, A2A skills, cloud agents
+
+**Files:** `scripts/check/check-known-symbols.ts`, `tests/unit/check-known-symbols.test.ts`.
+
+**Approach (TDD, mesmo padrão das 3 superfícies existentes — Step 0 de verificação dos exports reais antes de codar):**
+1. **MCP tools:** enumerar os tools registrados (via `createMcpServer()` ou parse determinístico do tool-set em `open-sse/mcp-server/tools/`) e congelar o snapshot de nomes (catraca: tool sumir = fail; tool novo = report). Cruzar com os scopes (~13) — tool sem scope atribuído = fail.
+2. **A2A skills:** chaves de `A2A_SKILL_HANDLERS` (`src/lib/a2a/taskExecution.ts`) ↔ skills expostas no Agent Card (`src/app/.well-known/agent.json/route.ts`) — divergência = fail.
+3. **Cloud agents:** entradas do `src/lib/cloudAgent/registry.ts` ↔ classes em `agents/` — incompleto/órfão = fail.
+
+**Acceptance:** remover um tool/skill/agent do registro quebra o gate; adicionar reporta (e `check-docs-counts-sync` continua cuidando da prosa).
+
+## P2 — refinamentos
+
+### Task 6A.10 — `check-test-masking` v2: deleções, skips, tautologias
+
+**Files:** `scripts/check/check-test-masking.mjs`, `tests/unit/check-test-masking.test.ts`.
+
+**Approach (TDD):** (a) `--diff-filter=M` → `MDR` (com `-M` para rename-detection): arquivo de teste **deletado** = flag automático ("N asserts removidos — arquivo deletado"); renamed = comparar contra o path antigo. (b) Contar `\.(skip|todo|only)\s*\(` + `\{\s*skip:\s*true` base vs HEAD — **aumento líquido de skips = flag** (skip novo esconde asserts sem removê-los); `.only` novo = flag sempre (filtra o resto da suíte). (c) Tautologias extras: `expect(true).toBe(true)`, `assert.equal(1, 1)`, `expect(x).toBeDefined()` como ÚNICO assert do teste.
+
+**Acceptance:** fixtures para os 3 bypasses (delete, skip, only) — todos flagados; suíte real verde.
+
+### Task 6A.11 — Pisos manuais → catraca do motor + escopo electron/bin
+
+**Files:** `scripts/quality/collect-metrics.mjs`, `quality-baseline.json`, `check-openapi-coverage.mjs`, `scripts/i18n/check-ui-keys-coverage.mjs` (só leitura do valor), `check-file-size.mjs`, `eslint.complexity.config.mjs` + baselines.
+
+**Approach:** (1) coletor emite `openapiCoverage.pct` e `i18nUiCoverage.pct` → baseline `{direction: up}` com o valor real atual (36→real, 65→real); os THRESHOLDs fixos viram redundância de segurança (mantidos). Rotas/strings novas sem doc/i18n agora REGRIDEM o % e falham. (2) `check-file-size` e `check-complexity`: adicionar `electron/` e `bin/` ao scan (congelar os >cap que existirem).
+
+**Acceptance:** rota nova não-documentada derruba `openapiCoverage.pct` → gate falha; god-file novo em `electron/` falha.
+
+### Task 6A.12 — Higiene operacional (4 itens pequenos)
+
+**Files:** `package.json`, `dependency-allowlist.json`, `.husky/pre-push`, Create: `scripts/check/check-tracked-artifacts.mjs`, `scripts/quality/run-all-gates.mjs`; Modify: `.agents/skills/quality-scan/SKILL.md`.
+
+**Approach:**
+1. **jscpd pinado:** `jscpd@^4` como devDependency (entra no lockfile + allowlist); `check-duplication` chama o binário local em vez de `npx --yes jscpd@4` (remove download de registry no CI + supply-chain risk + flakiness).
+2. **pre-push barato:** reativar com APENAS os gates determinísticos rápidos (<10s: fetch-targets, openapi-routes, db-rules, public-creds, migration-numbering, file-size, deps, error-helper) — NÃO `test:unit` (lento; CI cobre). Atualizar o claim do CLAUDE.md (coordenar com 6A.4).
+3. **check-tracked-artifacts:** falhar se `git ls-files` contém `node_modules/`, `.next/`, `coverage/`, `quality-metrics.json` ou symlink para fora do repo (o incidente do symlink trackeado já aconteceu 2×). Wire no lint job + pre-commit (é instantâneo).
+4. **Runner agregador:** `scripts/quality/run-all-gates.mjs` roda os gates em paralelo (pool ~4), agrega `{gate, exitCode, lastLine, durationMs}` e imprime a tabela consolidada; `npm run quality:scan`. A skill `/quality-scan` passa a chamá-lo (atualizar SKILL.md).
+
+**Acceptance:** `npm run quality:scan` < 3 min com tabela única; pre-push roda <10s; `git add node_modules && commit` falha no pre-commit.
+
+---
+
+## Ordem de execução recomendada (na ativação, 2026-06-16+)
+
+1. **6A.1 + 6A.2** (bugs de runner — destravam números reais de cobertura para o resto)
+2. **6A.3 + 6A.4** (stale-enforcement + docs — endurecem o que já roda)
+3. **6A.5** (motor v2) → **6A.6** (quality.yml, após OK do owner)
+4. **6A.7 → 6A.9** (escopos)
+5. **6A.10 → 6A.12** (refinamentos)
+6. Só então **Fase 7** (ferramentas novas sobre uma fundação consertada)
+
+## Self-Review
+- **Cobertura dos achados:** todos os achados A*/B*/C*/D*/E* da tabela têm task (coluna Task); os descartados estão em "Decisões conscientes de NÃO fazer" com motivo. ✓
+- **Zero dependência nova** exceto a promoção do jscpd (que já roda hoje via npx, não-pinado — a task REDUZ risco). ✓
+- **Sem flag-day:** toda expansão de escopo congela os achados pré-existentes (allowlist + issue), igual Fases 0–6; o stale-enforcement só exige remoção quando a correção JÁ aconteceu. ✓
+- **Consistência com o motor:** novas métricas (`openapiCoverage.pct`, `i18nUiCoverage.pct`) usam o formato `{value, direction}`; `eps`/`tightenSlack` são opcionais e retrocompatíveis. ✓
+- **Não-duplicação com a Fase 7:** cognitive-complexity per-file, gitleaks (creds não-públicas), knip, osv — tudo continua na Fase 7; a 6A só conserta/endurece o existente. ✓

PLANO-QUALITY-GATES-FASE7.md

@@ -0,0 +1,182 @@
+# Fase 7 — Quality Gates: Segurança, Dead-Code, Mutação & Ferramental Community
+
+> **Para workers agênticos:** SUB-SKILL OBRIGATÓRIA: `superpowers:subagent-driven-development` (recomendado) ou `superpowers:executing-plans`, tarefa-a-tarefa. Cada tarefa aqui é um subsistema independente → **expandir em sub-plano bite-sized próprio** no momento da execução. Hard Rule #18 (TDD/VPS) em tudo.
+
+> # ⏳ PORTÃO DE ATIVAÇÃO — NÃO INICIAR ANTES DE **2026-06-16**
+> **Este plano está GUARDADO, não ativo.** Decisão do owner (2026-06-09): finalizar 100% as Fases 0–6 (PR #3471), **usar em produção por 1 semana** para validar na prática, e só então evoluir. **Data cravada de início da Fase 7: 2026-06-16.** Não ativar antes — o objetivo da semana é coletar sinal real (falsos-positivos dos gates, custo de CI, atrito) antes de adicionar mais.
+> **Pré-condições para ativar:** (1) PR #3471 (Fases 0–6) mergeada e rodada ≥1 semana; (2) re-home do PR para `release/v3.8.18` resolvido; (3) as issues #3483–#3501 com decisões aplicadas ou conscientemente adiadas; (4) **Fase 6A executada (ou conscientemente re-priorizada)** — a auditoria crítica de 2026-06-09 ([`PLANO-QUALITY-GATES-FASE6A.md`](./PLANO-QUALITY-GATES-FASE6A.md)) encontrou bugs sistêmicos de runner (≈135 testes órfãos, vitest fora do CI) e furos de escopo nos gates existentes que devem ser consertados ANTES de adicionar ferramentas novas por cima.
+
+**Goal:** Maximizar a cobertura de quality gates do OmniRoute adicionando catracas de **segurança** (Sonar/osv/CodeQL → zero na timeline), **dead-code**, **complexidade cognitiva**, **type-coverage**, **mutação**, **bundle-size**, **a11y** e completando o anti-slopsquatting — usando **somente ferramentas Community/OSS** (projeto é open-source, zero SaaS pago, dados na box).
+
+**Architecture:** Reusa o motor existente — toda métrica numérica entra como `{value, direction}` em `quality-baseline.json` (catraca só-regressão) ou vira um `scripts/check/check-*.mjs` dedicado (padrão `check-t11-any-budget.mjs`). Gates pesados vão no job paralelo `quality-gate`; gates rápidos no `lint`; mutação/visual em job nightly separado. Tudo só-regressão (sem flag-day).
+
+**Tech Stack (tudo OSS/Community):** SonarQube **Community Build** (self-hosted) · osv-scanner (Google) · CodeQL (GitHub, grátis p/ público) · knip · eslint-plugin-sonarjs · type-coverage · lockfile-lint · dpdm · Stryker (`@stryker-mutator/*`) · size-limit · `@axe-core/playwright` · semcheck · agent-lsp (MCP) · Qlty CLI (OSS, opcional) · **gitleaks** (secret scanning, MIT; avaliar o sucessor drop-in Betterleaks, 2026-03) · **actionlint + zizmor** (lint + auditoria de segurança dos workflows) · **license-compliance** (allowlist SPDX de licenças). ESLint 9 flat · c8 · Node native test runner · GitHub Actions.
+
+---
+
+## Princípio (igual às Fases 0–6)
+
+Toda catraca é **só-regressão**: congela o baseline atual, bloqueia QUALQUER piora, decai a zero/melhor com o tempo via `--update`. Nenhum gate exige limpeza imediata (flag-day). Cada ferramenta nova que vira dependência **deve ser adicionada a `dependency-allowlist.json`** (o gate `check-deps` da Fase 2 vai exigir — é o ponto de revisão humana).
+
+## Mapa de arquivos (criar/modificar)
+
+| Arquivo | Responsabilidade |
+|---|---|
+| `quality-baseline.json` (modificar) | + `vulnCount`, `codeqlAlerts`, `sonarIssues`, `cognitiveComplexity`, `typeCoveragePct`, `deadExports` |
+| `scripts/quality/collect-metrics.mjs` (modificar) | + coletores: osv-scanner, CodeQL count, Sonar API, knip, type-coverage, sonarjs |
+| `scripts/check/check-vuln-ratchet.mjs` (criar) | osv-scanner → vulnCount (catraca) |
+| `scripts/check/check-dead-code.mjs` (criar) | knip → exports/files/deps mortos (catraca) |
+| `scripts/check/check-cognitive-complexity.mjs` + `eslint.sonarjs.config.mjs` (criar) | sonarjs/cognitive-complexity em config isolado (não polui o count principal) |
+| `scripts/check/check-type-coverage.mjs` (criar) | type-coverage % (catraca up) |
+| `scripts/check/check-lockfile.mjs` (criar) | lockfile-lint (host/https/integrity) |
+| `scripts/check/check-pr-evidence.mjs` (criar) | exige output de comando no corpo do PR (Rule #18 mecânica) |
+| `scripts/check/check-bundle-size.mjs` + `.size-limit.json` (criar) | size-limit → orçamento de bundle |
+| `tests/e2e/a11y.spec.ts` (criar) | `@axe-core/playwright` nas páginas-chave |
+| `stryker.conf.json` (criar) | mutação nos ~8 módulos críticos (nightly) |
+| `sonar-project.properties` (modificar) | remover `coverage`/`cpd` exclusions; ativar new-code gate |
+| `.github/workflows/ci.yml` (modificar) | wirar novos gates (lint / quality-gate / nightly) + `qualitygate.wait` no Sonar |
+| `semcheck.yaml` (criar) | semcheck: docs↔código (camada fuzzy LLM, opcional) |
+| `.mcp.json` / config de agentes (modificar) | registrar agent-lsp (LSP-in-the-loop) |
+| `.gitleaks.toml` + `scripts/check/check-secrets.mjs` (criar) | gitleaks → catraca de findings de secret (Task 18) |
+| `.github/workflows/quality.yml` ou job lint (modificar) | actionlint + zizmor sobre `.github/workflows/**` (Task 19) |
+| `scripts/check/check-licenses.mjs` + `.license-allowlist.json` (criar) | allowlist SPDX das licenças das deps (Task 20) |
+| `dependency-allowlist.json` (modificar) | + osv-scanner, knip, sonarjs, type-coverage, lockfile-lint, stryker, size-limit, axe-core, dpdm, license-compliance |
+
+---
+
+## Tarefas (cada uma = 1 sub-plano bite-sized na execução)
+
+### Task 1 — Ativar SonarQube Community + "Clean as You Code" (gate de segurança nativo)
+- **Tool:** SonarQube Community Build (self-hosted, grátis).
+- **Files:** `sonar-project.properties`, `.github/workflows/ci.yml` (job `sonarqube`).
+- **Approach:** setar secrets `SONAR_TOKEN`/`SONAR_HOST_URL`; **remover** `sonar.coverage.exclusions=**/*` e `sonar.cpd.exclusions=**/*` (hoje neutralizam o Sonar); ativar o quality gate **new-code / "Clean as You Code"** (código novo não pode adicionar issue/bug/vuln/hotspot; legado grandfathered) + adicionar `-Dsonar.qualitygate.wait=true` para **bloquear** o PR (hoje o job é inerte: secrets-gated, sem wait).
+- **Acceptance:** PR que introduz um code-smell/bug/vuln em código novo falha o gate; legado não bloqueia. Documentar suppressions legítimas (já há h1–h6 no properties).
+
+### Task 2 — Catraca de vulnerabilidades (osv-scanner)
+- **Tool:** osv-scanner (Google/OSV, OSS) — `--format json`, on-box.
+- **Files:** `scripts/check/check-vuln-ratchet.mjs`, `quality-baseline.json` (+`vulnCount`), `collect-metrics.mjs`, `ci.yml` (job `quality-gate`), `dependency-allowlist.json`.
+- **Approach:** rodar `osv-scanner --format json` sobre os lockfiles → contar vulns → métrica `vulnCount {direction: down}`. Catraca: não pode subir, decai a zero. Mantém o `npm audit` escalonado da Fase 0 como bloqueio de crítico imediato; osv é o ratchet de timeline.
+- **Acceptance:** nova dep com vuln conhecida sobe o count → falha; remediar/remover baixa → `--update`.
+
+### Task 3 — Catraca de alertas CodeQL
+- **Tool:** GitHub CodeQL (já roda; grátis p/ repo público).
+- **Files:** `scripts/check/check-codeql-ratchet.mjs`, `quality-baseline.json` (+`codeqlAlerts`), `ci.yml`.
+- **Approach:** puxar a contagem de alertas abertos via `gh api /repos/{owner}/{repo}/code-scanning/alerts?state=open` → métrica `codeqlAlerts {down}`. (Respeitar Hard Rule #14 — dismiss só com justificativa; alertas dismissed não contam.)
+- **Acceptance:** novo alerta CodeQL sobe o count → sinaliza; resolver baixa.
+
+### Task 4 — Dead-code / unused-exports / unused-deps (knip)
+- **Tool:** knip (OSS, v6+) — `--reporter json`.
+- **Files:** `scripts/check/check-dead-code.mjs`, `quality-baseline.json` (+`deadExports`/`unusedDeps`), `knip.json` (config), `collect-metrics.mjs`, `ci.yml`, `dependency-allowlist.json`.
+- **Approach:** `knip --reporter json` sobre os workspaces `src/`+`open-sse/` → contar unused files/exports/deps → catraca `down`. Config knip ciente do monorepo + Next 16.
+- **Acceptance:** novo export/dep morto sobe → falha; remoção baixa.
+
+### Task 5 — Complexidade cognitiva (eslint-plugin-sonarjs, config isolado)
+- **Tool:** eslint-plugin-sonarjs (OSS) — `sonarjs/cognitive-complexity`.
+- **Files:** `eslint.sonarjs.config.mjs` (config standalone, NÃO o principal — não polui o `eslintWarnings=3482`), `scripts/check/check-cognitive-complexity.mjs`, `quality-baseline.json` (+`cognitiveComplexity`), `ci.yml` (job `quality-gate`), `dependency-allowlist.json`.
+- **Approach:** mesmo molde do `check-complexity` (Fase 6) mas com `sonarjs/cognitive-complexity` num config isolado; contar violações → catraca `down`. (Complementa a complexidade ciclomática core já existente.)
+- **Acceptance:** função acima do limite cognitivo sobe o count → falha.
+
+### Task 6 — Type-coverage ratchet
+- **Tool:** type-coverage (OSS).
+- **Files:** `scripts/check/check-type-coverage.mjs`, `quality-baseline.json` (+`typeCoveragePct {up}`), `dependency-allowlist.json`.
+- **Approach:** `type-coverage --detail --json` → % de símbolos tipados → catraca `up`. Complementa o `check:any-budget` (count de `any` por arquivo) com a visão %-global.
+- **Acceptance:** queda do % tipado → falha.
+
+### Task 7 — Lockfile policy (lockfile-lint)
+- **Tool:** lockfile-lint (OSS, v5).
+- **Files:** `scripts/check/check-lockfile.mjs`, `ci.yml` (lint), `dependency-allowlist.json`.
+- **Approach:** `lockfile-lint --path package-lock.json --type npm --validate-https --validate-integrity --allowed-hosts npm` → gate pass/fail (não é ratchet; é política anti-poisoning). Complementa o `check-deps` (Fase 2).
+- **Acceptance:** lockfile com host não-https/sem integrity → falha.
+
+### Task 8 — Completar anti-slopsquatting (registry-existence + age-cooldown)
+- **Tool:** npm registry API (`npm view <pkg> time.created`).
+- **Files:** `scripts/check/check-deps.mjs` (estender), test.
+- **Approach:** além do allowlist-diff atual, para uma dep NOVA: verificar que existe no registry E que foi publicada há ≥72h (age-cooldown contra "registra o nome alucinado em horas"). Base: CSA 2026 (19,7% de nomes alucinados; 43% reaparecem).
+- **Acceptance:** dep nova inexistente no registry ou publicada há <72h → falha (a menos que allowlistada com justificativa).
+
+### Task 9 — Pisos de cobertura por módulo crítico (peça adiada da Fase 4)
+- **Files:** `scripts/quality/collect-metrics.mjs` (estender), `quality-baseline.json`.
+- **Approach:** emitir `coverage.<modulo>.lines` (lido do `coverage-summary.json` por-arquivo) para ~8 módulos de alto risco: `open-sse/handlers/chatCore.ts`, `open-sse/services/combo.ts`, `open-sse/services/accountFallback.ts`, `src/sse/services/auth.ts`, `src/server/authz/routeGuard.ts`, `open-sse/utils/error.ts`, `open-sse/utils/publicCreds.ts`, `src/shared/utils/circuitBreaker.ts`. Cada um vira métrica `up`. **Calibrar a partir do coverage mergeado real do 1º run verde na main.**
+- **Acceptance:** queda de cobertura num módulo crítico → falha, mesmo que o global não caia.
+
+### Task 10 — Evidence-in-PR-body (peça adiada da Fase 5)
+- **Files:** `scripts/check/check-pr-evidence.mjs`, `ci.yml` (job `pr-test-policy`).
+- **Approach:** se o corpo do PR afirma "tests pass"/"added endpoint X"/"fixed Y" sem um bloco de **output de comando** anexado (typecheck/test/grep), falha (torna a Rule #18 mecânica — "evidence before assertions"). Heurístico, no contexto de PR.
+- **Acceptance:** PR alegando sucesso sem output anexado → falha.
+
+### Task 11 — Mutation testing nos módulos críticos (Stryker, nightly)
+- **Tool:** Stryker (`@stryker-mutator/core` + runner; OSS).
+- **Files:** `stryker.conf.json`, `ci.yml` (job NIGHTLY separado — não no PR), `dependency-allowlist.json`.
+- **Approach:** escopar Stryker aos ~8 módulos críticos da Task 9 (não repo-wide — é caro + c8 já OOM-prone). Mutantes sobreviventes = **testes tautológicos** (passam sem provar nada) → complementa o `check-test-masking` da Fase 4. Rodar nightly/weekly, não por-PR.
+- **Acceptance:** mutation score por módulo crítico vira métrica (catraca `up`, nightly).
+
+### Task 12 — Bundle-size / perf budget (size-limit)
+- **Tool:** size-limit (OSS).
+- **Files:** `.size-limit.json`, `scripts/check/check-bundle-size.mjs`, `ci.yml`, `dependency-allowlist.json`.
+- **Approach:** definir orçamento por bundle Next 16; size-limit emite tamanhos → catraca `down` (bundle não pode inchar).
+- **Acceptance:** PR que estoura o orçamento de bundle → falha.
+
+### Task 13 — a11y gate (axe-core + Playwright)
+- **Tool:** `@axe-core/playwright` (OSS; Playwright já existe).
+- **Files:** `tests/e2e/a11y.spec.ts`, `ci.yml` (job `test-e2e`), `dependency-allowlist.json`.
+- **Approach:** rodar axe nas páginas-chave do dashboard; congelar violações atuais (catraca `down`). Atende o item a11y/visual do plano t15.
+- **Acceptance:** nova violação a11y → falha; correção baixa.
+
+### Task 14 — semcheck (camada fuzzy docs↔código, opcional/LLM)
+- **Tool:** semcheck (OSS, MIT) — `fail-on-issues`.
+- **Files:** `semcheck.yaml`, `ci.yml` (advisory).
+- **Approach:** regras ligando `docs/**` ao módulo de código que documentam; pega docs que descrevem o que o código NÃO faz (camada fuzzy sobre o determinístico `check-docs-symbols` da Fase 6). É LLM → rodar advisory/non-blocking ou em label, por custo.
+- **Acceptance:** doc que descreve comportamento inexistente → flag (advisory).
+
+### Task 15 — agent-lsp (LSP-in-the-loop para os agentes)
+- **Tool:** agent-lsp (MCP server, OSS).
+- **Files:** config MCP dos agentes (`.mcp.json`/equivalente).
+- **Approach:** expor `tsserver`/agent-lsp aos agentes para `blast_radius`/diagnostics/`preview_edit` ANTES de escrever — vira "símbolo inventado" de catch-de-review para impossibilidade-no-edit. Pareia com `typecheck:core` como gate pré-PR (compile-before-claim).
+- **Acceptance:** agentes resolvem símbolo/import via LSP; menos alucinação de símbolo na origem.
+
+### Task 16 — dpdm circular-deps JSON cross-check (opcional)
+- **Tool:** dpdm (OSS, v4) — `--circular --output`.
+- **Approach:** cross-check JSON de ciclos complementando o `check-cycles.mjs` existente (AST-TS mais preciso). Catraca de contagem de ciclos. Baixa prioridade (já temos check-cycles).
+
+### Task 17 — Avaliar Qlty CLI como consolidador (opcional, spike)
+- **Tool:** Qlty CLI (OSS, grátis).
+- **Approach:** spike: avaliar se Qlty (Baseline analysis + 70 analyzers) substitui N scripts caseiros sem perder o controle/determinismo. Decisão build-vs-buy. Não obrigatório.
+
+### Task 18 — Secret scanning local (gitleaks) ➕ *adicionada pela auditoria 6A (2026-06-09)*
+- **Tool:** gitleaks (OSS, MIT — binário Go, on-box). Nota 2026: o criador original (Zach Rice) lançou o **Betterleaks** (2026-03) como drop-in replacement (flags/config compatíveis) — avaliar os dois no Step 0 e escolher 1.
+- **Files:** `.gitleaks.toml`, `scripts/check/check-secrets.mjs`, `quality-baseline.json` (+`secretFindings {down}`), `ci.yml` (job quality-gate), pre-commit (modo `--staged`, é rápido).
+- **Approach:** complementa o `check-public-creds` da Fase 6 (que cobre apenas credenciais PÚBLICAS por chave de objeto em 2 arquivos): gitleaks pega a classe geral — `const API_KEY = "sk-…"`, tokens em config/teste/docs, secrets em histórico. Rodar `gitleaks dir --report-format json` → contar findings → catraca `down`. Findings legítimos (creds públicas já congeladas no check-public-creds, fixtures de teste) vão para `.gitleaks.toml` `[allowlist]` com comentário — sujeitos ao stale-enforcement da 6A.3 (conceitual: revisar allowlist a cada release).
+- **Acceptance:** secret real plantado em fixture é detectado; baseline congela os findings atuais; novo finding falha o gate.
+
+### Task 19 — Lint + auditoria de segurança dos workflows (actionlint + zizmor) ➕ *adicionada pela auditoria 6A*
+- **Tools:** actionlint (OSS — correção/sintaxe/shellcheck dos YAML) + zizmor (OSS, zizmorcore — 24+ audits de segurança: unpinned actions, script injection, `pull_request_target` perigoso, cache poisoning). Complementares por design; o repo tem 10 workflows sem NENHUMA validação hoje.
+- **Motivação 2026:** o incidente trivy-action/LiteLLM (2026-03) explorou exatamente uma misconfiguração de `pull_request_target` que o zizmor detecta estaticamente. Os release-workflows do OmniRoute (npm/Docker/Electron publish) são alvo de alto valor.
+- **Files:** `ci.yml` ou `quality.yml` (steps actionlint + zizmor), `zizmor.yml` (config/ignores justificados), `quality-baseline.json` (+`zizmorFindings {down}` — começar advisory, congelar baseline, depois bloquear).
+- **Approach:** actionlint = pass/fail imediato (sintaxe não tem "legado aceitável"); zizmor = catraca `down` no padrão do motor (os findings atuais — provavelmente actions não-pinadas por SHA — são dívida congelada que decai).
+- **Acceptance:** workflow novo com `pull_request_target` + checkout de código do PR falha; action não-pinada NOVA sobe o count e falha.
+
+### Task 20 — License compliance (allowlist SPDX) ➕ *adicionada pela auditoria 6A*
+- **Tool:** license-compliance ou @onebeyond/license-checker (ambos OSS, npm). Projeto é **MIT** — deps com copyleft forte (GPL/AGPL) em produção são risco de compliance para os usuários do proxy.
+- **Files:** `scripts/check/check-licenses.mjs`, `.license-allowlist.json` (SPDX permitidas: MIT, Apache-2.0, BSD-2/3, ISC, 0BSD, …), `ci.yml` (lint job), `dependency-allowlist.json`.
+- **Approach:** rodar sobre as `dependencies` de produção (devDependencies = relatório advisory); licença fora da allowlist → fail com o caminho da dep. Exceções pontuais (dual-license, LGPL avaliada) entram na allowlist por **pacote** com justificativa — pareia com o `check-deps` da Fase 2 (lá controla O QUE entra; aqui, SOB QUAL licença).
+- **Acceptance:** dep GPL-3.0 sintética em fixture falha; árvore atual passa com a allowlist calibrada.
+
+---
+
+## Wiring & CI (resumo)
+- **lint job:** check-lockfile, check-cognitive-complexity (rápido?), check-type-coverage, **check-licenses (Task 20)**, **actionlint (Task 19)**.
+- **quality-gate job (paralelo):** check-vuln-ratchet, check-dead-code, check-codeql-ratchet, check-cognitive-complexity (se lento), check-bundle-size, **check-secrets (Task 18)**, **zizmor (Task 19)**.
+- **pr-test-policy job:** check-pr-evidence.
+- **sonarqube job:** Clean-as-You-Code + `qualitygate.wait`.
+- **NIGHTLY job (novo):** Stryker (mutação), semcheck (advisory), a11y full.
+- Todas as métricas numéricas → `quality-baseline.json` (motor da Fase 1, com `eps`/`tightenSlack` da 6A.5). Toda dep nova → `dependency-allowlist.json`. Toda allowlist nova nasce com o stale-enforcement da 6A.3.
+
+## Self-Review
+- **Cobertura do spec:** 7 gates sugeridos = Task 1-3 (segurança), 4 (knip), 9 (coverage por módulo), 10 (evidence), 11 (mutação), 12 (bundle), 13 (a11y). "Todas as ferramentas discutidas" = Tasks 1-8, 11-17 (Sonar/osv/CodeQL/knip/sonarjs/type-coverage/lockfile/dpdm/stryker/size-limit/axe/semcheck/agent-lsp/Qlty). Auditoria 6A (2026-06-09) acrescentou Tasks 18-20 (gitleaks, actionlint+zizmor, license compliance). ✓
+- **Community/OSS only:** confirmado — Sonar Community Build, todos os demais OSS (gitleaks MIT, zizmor/actionlint OSS, license-compliance npm), zero SaaS pago. ✓
+- **Sem flag-day:** toda catraca é só-regressão, calibrada do estado atual (zizmor/gitleaks começam advisory→baseline→bloqueio). ✓
+- **Consistência:** todas as métricas usam o formato `{value, direction}` do motor da Fase 1; deps novas passam pelo `check-deps`+`dependency-allowlist.json`. ✓
+- **Não-sobreposição com a 6A:** a 6A conserta/endurece o EXISTENTE (runners, stale-allowlists, escopos); a Fase 7 só adiciona ferramenta nova. gitleaks (Task 18) complementa — não substitui — o check-public-creds expandido pela 6A.8. ✓
+
+## Handoff (na ativação, 2026-06-16+)
+**Ordem: Fase 6A primeiro** ([`PLANO-QUALITY-GATES-FASE6A.md`](./PLANO-QUALITY-GATES-FASE6A.md)) — consertar os runners (testes órfãos + vitest no CI) e endurecer as catracas existentes muda os baselines (cobertura recalibrada) sobre os quais várias tasks daqui (1, 9, 11) calibram. Depois: começar pela **Task 1-3 (catraca de segurança)**, **Task 4 (knip)** e **Task 19 (zizmor — protege os release-workflows)** — maior retorno. Cada Task vira um sub-plano `writing-plans` bite-sized próprio. Recomendado: Subagent-Driven, 1 subagente por Task, com auditoria (trust-but-verify) e o ratchet `eslintWarnings`/`check-deps` validando que cada adição não regride o que já temos.

PLANO-QUALITY-GATES.md

@@ -0,0 +1,688 @@
+# Plano de Implementação — Quality Gates & Catraca Anti-Alucinação
+
+> **Para workers agênticos:** SUB-SKILL OBRIGATÓRIA: use `superpowers:subagent-driven-development` (recomendado) ou `superpowers:executing-plans` para executar este plano tarefa-a-tarefa. Os passos usam checkbox (`- [ ]`) para rastreio. **Cada fix de bug obedece à Hard Rule #18** (teste falha→passa OU validação ao vivo no VPS). Não burle Husky (`--no-verify`) sem aprovação. Veja o diagnóstico completo em [`RELATORIO-QUALITY-GATES.md`](./RELATORIO-QUALITY-GATES.md).
+
+**Goal:** Generalizar a catraca de qualidade do OmniRoute (hoje só para `any`) para todas as métricas relevantes — cobertura, duplicação, tamanho de arquivo, complexidade — e adicionar gates determinísticos anti-alucinação, tudo no padrão `check-*.mjs` já existente, sem SaaS novo.
+
+**Architecture:** Camadas incrementais. (0) reativa/reconcilia o que já existe; (1) constrói o **motor de catraca** (`quality-baseline.json` commitado + coletor + comparador genérico que clona o `check-t11-any-budget.mjs`); (2) adiciona gates determinísticos que matam os ímãs de alucinação (provider-consistency, fetch-targets, openapi-routes); (3) catraca de duplicação+tamanho; (4) catraca de cobertura + anti test-masking; (5) skill `/babysit` + evidência. Toda catraca é **só-regressão** (baseline congelado) — nunca um piso absoluto que exija limpeza flag-day.
+
+**Tech Stack:** Node ≥20 ESM (`.mjs`/`.ts` via `tsx`), ESLint 9 flat config, c8, jscpd v5, eslint-plugin-sonarjs v4, GitHub Actions, Node native test runner (`node --import tsx --test`), `gh` CLI + GraphQL.
+
+**Escopo / sub-planos (scope-check):** Fases 0, 1 e 2 estão totalmente bite-sized aqui. Fases 3, 4 e 5 são subsistemas independentes — cada uma deve ser **expandida no próprio sub-plano** (via `writing-plans`) no momento da execução, a partir das specs/critérios de aceitação definidos aqui. Cada fase entrega software funcional e testável por si só.
+
+---
+
+## Mapa de arquivos (o que será criado/modificado)
+
+| Arquivo | Responsabilidade |
+|---------|------------------|
+| `quality-baseline.json` (criar, **commitar**) | Baseline congelado: por métrica `{value, direction}` (`down`=menor-é-melhor, `up`=maior-é-melhor) |
+| `scripts/quality/collect-metrics.mjs` (criar) | Roda os coletores → emite `quality-metrics.json` |
+| `scripts/quality/check-quality-ratchet.mjs` (criar) | Comparador genérico: falha em qualquer regressão; com `--update` ratcheta o baseline |
+| `scripts/check/check-fetch-targets.mjs` (criar) | Todo `fetch("/api/...")` do dashboard resolve para um `route.ts` real |
+| `scripts/check/check-provider-consistency.ts` (criar) | ids de provider batem entre `providers.ts` ↔ `providerRegistry.ts` ↔ `validation.ts` |
+| `scripts/check/check-openapi-routes.mjs` (criar) | Toda `path` do `openapi.yaml` ↔ `route.ts` real (bidirecional) |
+| `scripts/check/check-deps.mjs` (criar) | Anti-slopsquatting: allowlist + existência no registry + age-cooldown |
+| `.github/workflows/ci.yml` (modificar) | Novo job `quality-gate`; reconciliar gate de cobertura; escalonar audit; plugar scripts órfãos |
+| `.husky/pre-commit` (modificar) | Reativar a parte barata |
+| `package.json` (modificar) | Novos scripts `check:*` / `quality:*` |
+| `eslint.config.mjs` (modificar, Fase 3) | `max-lines`, `max-lines-per-function`, `complexity`, `sonarjs/cognitive-complexity` (warn) |
+| `.claude/skills/babysit/SKILL.md` (criar, Fase 5) | Skill `/babysit` |
+| `tests/unit/quality-ratchet.test.ts` etc. (criar) | Testes TDD de cada gate |
+
+---
+
+# FASE 0 — Reativar & Reconciliar (quick wins, sem tooling novo)
+
+### Task 0.1: Reconciliar o gate de cobertura do CI (40 → baseline real)
+
+**Contexto:** `ci.yml:377` gata em `40/40/40/40`; local gata `60`; comentário renderiza `60`; baseline real ≈ 79–82%. O 40 torna o gate quase banguela.
+
+**Files:**
+- Modify: `.github/workflows/ci.yml:376-377`
+
+- [ ] **Step 1: Confirmar o baseline real de cobertura**
+
+Run:
+```bash
+npm run test:coverage 2>&1 | tail -20
+node -e "const c=require('./coverage/coverage-summary.json').total; console.log(c.statements.pct,c.lines.pct,c.functions.pct,c.branches.pct)"
+```
+Expected: 4 números (ex.: `79.8 79.8 82.2 75.2`). Anote-os.
+
+- [ ] **Step 2: Subir o gate do CI para `baseline_real - 2` (headroom anti-flake)**
+
+Em `.github/workflows/ci.yml`, troque a linha `--statements 40 --lines 40 --functions 40 --branches 40` pelos valores `(real-2)` de cada métrica (ex.: `--statements 77 --lines 77 --functions 80 --branches 73`). Mantenha como **piso**; a catraca da Fase 4 cuidará do "não-cair".
+
+- [ ] **Step 3: Alinhar o script local e o display do comentário** para os mesmos números (procure `60` em `package.json` `test:coverage` e em `scripts/check/test-report-summary.mjs`).
+
+- [ ] **Step 4: Verificar que o CI não quebra** — abrir um PR de teste (ou rodar `act`/push numa branch) e confirmar que o job `test-coverage` fica verde com o novo piso.
+
+- [ ] **Step 5: Commit**
+```bash
+git add .github/workflows/ci.yml package.json scripts/check/test-report-summary.mjs
+git commit -m "fix(ci): reconcile coverage gate to real baseline (40->~78) across CI/local/report"
+```
+
+### Task 0.2: Escalonar `npm audit` (critical=bloqueia / high=avisa)
+
+**Files:** Modify: `package.json:112`
+
+- [ ] **Step 1: Trocar o script `audit:deps`** de `npm audit --audit-level=moderate && npm run audit:electron` para:
+```json
+"audit:deps": "npm audit --audit-level=critical && (npm audit --audit-level=high || echo '::warning::high-severity advisories present (non-blocking)') && npm run audit:electron",
+```
+
+- [ ] **Step 2: Rodar e observar o comportamento**
+```bash
+npm run audit:deps; echo "exit=$?"
+```
+Expected: `exit=0` se não houver critical; mensagem de warning se houver high.
+
+- [ ] **Step 3: Commit**
+```bash
+git add package.json && git commit -m "chore(ci): tier npm audit (critical blocks, high warns)"
+```
+
+### Task 0.3: Plugar os 3 scripts órfãos no CI
+
+**Contexto:** `check:cli-i18n`, `check:openapi-coverage`, `check:openapi-security-tiers` existem, dão `exit 1`, mas não rodam em lugar nenhum (Hard Rules #15/#17).
+
+**Files:** Modify: `.github/workflows/ci.yml` (job `docs-sync-strict` ou `lint`)
+
+- [ ] **Step 1: Rodar os 3 localmente para confirmar verde no estado atual**
+```bash
+npm run check:cli-i18n && npm run check:openapi-coverage && npm run check:openapi-security-tiers; echo "exit=$?"
+```
+Expected: `exit=0` (se algum falhar, corrija a deriva antes de plugar).
+
+- [ ] **Step 2: Adicionar os 3 como steps** no job `docs-sync-strict` do `ci.yml`, após `check:docs-all`.
+
+- [ ] **Step 3: Commit**
+```bash
+git add .github/workflows/ci.yml && git commit -m "ci: wire orphaned gates (cli-i18n, openapi-coverage, openapi-security-tiers)"
+```
+
+### Task 0.4: Reativar a parte barata do pre-commit do Husky
+
+**Files:** Modify: `.husky/pre-commit`
+
+- [ ] **Step 1: Descomentar SÓ as 3 linhas baratas e determinísticas:**
+```sh
+npx lint-staged
+node scripts/check/check-docs-sync.mjs
+npm run check:any-budget:t11
+```
+(Deixe i18n/openapi comentados por enquanto — eles são mais lentos; rodam no CI.)
+
+- [ ] **Step 2: Testar o hook** com um commit trivial e medir o tempo:
+```bash
+time git commit --allow-empty -m "chore: test pre-commit hook"
+git reset --soft HEAD~1
+```
+Expected: hook roda lint-staged + 2 checks em poucos segundos.
+
+- [ ] **Step 3: Commit**
+```bash
+git add .husky/pre-commit && git commit -m "chore(husky): re-enable cheap pre-commit gates (lint-staged, docs-sync, any-budget)"
+```
+
+---
+
+# FASE 1 — Motor de Catraca (o coração) ⭐
+
+> Generaliza o `check-t11-any-budget.mjs` (catraca de `any` por arquivo) para um motor de catraca genérico, multi-métrica, que lê um baseline commitado e falha em qualquer regressão. Começa com 2 métricas (warnings de ESLint + cobertura) e é estendido nas fases seguintes.
+
+### Task 1.1: Comparador genérico de catraca (TDD)
+
+**Files:**
+- Create: `scripts/quality/check-quality-ratchet.mjs`
+- Test: `tests/unit/quality-ratchet.test.ts`
+
+- [ ] **Step 1: Escrever o teste que falha**
+```ts
+// tests/unit/quality-ratchet.test.ts
+import { test } from "node:test";
+import assert from "node:assert";
+import { execFileSync } from "node:child_process";
+import fs from "node:fs";
+import os from "node:os";
+import path from "node:path";
+
+const SCRIPT = path.resolve("scripts/quality/check-quality-ratchet.mjs");
+
+function run(baseline, metrics, extraArgs = []) {
+  const dir = fs.mkdtempSync(path.join(os.tmpdir(), "ratchet-"));
+  const bPath = path.join(dir, "baseline.json");
+  const mPath = path.join(dir, "metrics.json");
+  fs.writeFileSync(bPath, JSON.stringify(baseline));
+  fs.writeFileSync(mPath, JSON.stringify(metrics));
+  try {
+    const out = execFileSync("node", [SCRIPT, "--baseline", bPath, "--metrics", mPath, ...extraArgs], { encoding: "utf8" });
+    return { code: 0, out, dir, bPath };
+  } catch (e) {
+    return { code: e.status, out: (e.stdout || "") + (e.stderr || ""), dir, bPath };
+  }
+}
+
+test("passes when metrics equal baseline", () => {
+  const b = { metrics: { eslintWarnings: { value: 100, direction: "down" }, "coverage.lines": { value: 80, direction: "up" } } };
+  assert.equal(run(b, { eslintWarnings: 100, "coverage.lines": 80 }).code, 0);
+});
+
+test("fails when a 'down' metric regresses (more warnings)", () => {
+  const b = { metrics: { eslintWarnings: { value: 100, direction: "down" } } };
+  const r = run(b, { eslintWarnings: 101 });
+  assert.equal(r.code, 1);
+  assert.match(r.out, /eslintWarnings/);
+});
+
+test("fails when an 'up' metric regresses (coverage drops)", () => {
+  const b = { metrics: { "coverage.lines": { value: 80, direction: "up" } } };
+  assert.equal(run(b, { "coverage.lines": 79 }).code, 1);
+});
+
+test("passes on improvement; --update ratchets the baseline", () => {
+  const b = { metrics: { eslintWarnings: { value: 100, direction: "down" } } };
+  const r = run(b, { eslintWarnings: 90 }, ["--update"]);
+  assert.equal(r.code, 0);
+  const updated = JSON.parse(fs.readFileSync(r.bPath, "utf8"));
+  assert.equal(updated.metrics.eslintWarnings.value, 90);
+});
+
+test("fails (code 2) when a baseline metric is missing from collected metrics", () => {
+  const b = { metrics: { eslintWarnings: { value: 100, direction: "down" } } };
+  assert.equal(run(b, {}).code, 1);
+});
+```
+
+- [ ] **Step 2: Rodar o teste e ver falhar**
+```bash
+node --import tsx --test tests/unit/quality-ratchet.test.ts
+```
+Expected: FAIL (script não existe ainda).
+
+- [ ] **Step 3: Implementar o comparador**
+```js
+#!/usr/bin/env node
+// scripts/quality/check-quality-ratchet.mjs
+// Catraca genérica multi-métrica. Clona o espírito de check-t11-any-budget.mjs:
+// um baseline congelado por métrica; falha em qualquer regressão; só anda num sentido.
+import fs from "node:fs";
+import path from "node:path";
+
+const cwd = process.cwd();
+function getArg(name, fallback) {
+  const i = process.argv.indexOf(name);
+  return i >= 0 && process.argv[i + 1] ? process.argv[i + 1] : fallback;
+}
+const BASELINE = path.resolve(getArg("--baseline", path.join(cwd, "quality-baseline.json")));
+const METRICS = path.resolve(getArg("--metrics", path.join(cwd, "quality-metrics.json")));
+const SUMMARY = getArg("--summary", null);
+const UPDATE = process.argv.includes("--update");
+const EPS = 0.01;
+
+function load(p) {
+  if (!fs.existsSync(p)) { console.error(`[quality-ratchet] arquivo ausente: ${p}`); process.exit(2); }
+  return JSON.parse(fs.readFileSync(p, "utf8"));
+}
+
+const baseline = load(BASELINE);
+const metrics = load(METRICS);
+const failures = [];
+const improvements = [];
+const rows = [];
+
+for (const [key, spec] of Object.entries(baseline.metrics)) {
+  const current = metrics[key];
+  const base = spec.value;
+  const dir = spec.direction; // "down" = menor-é-melhor | "up" = maior-é-melhor
+  if (current === undefined) { failures.push(`métrica "${key}" ausente em ${path.basename(METRICS)}`); rows.push([key, base, "—", "MISSING"]); continue; }
+  let status = "ok";
+  if (dir === "down") {
+    if (current > base + EPS) { failures.push(`${key}: ${current} > baseline ${base} (não pode aumentar)`); status = "REGRESSÃO"; }
+    else if (current < base - EPS) { improvements.push([key, current]); status = "↑ melhorou"; }
+  } else {
+    if (current < base - EPS) { failures.push(`${key}: ${current} < baseline ${base} (não pode cair)`); status = "REGRESSÃO"; }
+    else if (current > base + EPS) { improvements.push([key, current]); status = "↑ melhorou"; }
+  }
+  rows.push([key, base, current, status]);
+}
+
+if (SUMMARY) {
+  const md = ["# Quality Ratchet", "", "| Métrica | Baseline | Atual | Status |", "|---|---|---|---|",
+    ...rows.map(([k, b, c, s]) => `| ${k} | ${b} | ${c} | ${s} |`), "",
+    failures.length ? `**${failures.length} regressão(ões) — gate BLOQUEADO.**` : "**Sem regressões — gate OK.**"].join("\n");
+  fs.mkdirSync(path.dirname(SUMMARY), { recursive: true });
+  fs.writeFileSync(SUMMARY, md + "\n");
+}
+
+if (UPDATE && failures.length === 0 && improvements.length) {
+  for (const [key, val] of improvements) baseline.metrics[key].value = val;
+  fs.writeFileSync(BASELINE, JSON.stringify(baseline, null, 2) + "\n");
+  console.log(`[quality-ratchet] baseline ratcheado: ${improvements.length} métrica(s) melhoraram`);
+}
+
+if (failures.length) { console.error("[quality-ratchet] FALHOU:\n" + failures.map((f) => "  ✗ " + f).join("\n")); process.exit(1); }
+console.log(`[quality-ratchet] OK (${rows.length} métricas, ${improvements.length} melhoraram)`);
+```
+
+- [ ] **Step 4: Rodar o teste e ver passar**
+```bash
+node --import tsx --test tests/unit/quality-ratchet.test.ts
+```
+Expected: PASS (5/5).
+
+- [ ] **Step 5: Commit**
+```bash
+git add scripts/quality/check-quality-ratchet.mjs tests/unit/quality-ratchet.test.ts
+git commit -m "feat(quality): generic ratchet comparator (multi-metric, regression-only)"
+```
+
+### Task 1.2: Coletor de métricas (ESLint warnings + cobertura)
+
+**Files:** Create: `scripts/quality/collect-metrics.mjs`
+
+- [ ] **Step 1: Implementar o coletor**
+```js
+#!/usr/bin/env node
+// scripts/quality/collect-metrics.mjs — emite quality-metrics.json
+import fs from "node:fs";
+import path from "node:path";
+import { execFileSync } from "node:child_process";
+
+const cwd = process.cwd();
+const out = {};
+
+// 1) ESLint: contagem de warnings (errors devem ser 0; o lint já gata isso)
+function eslintCounts() {
+  let stdout;
+  try {
+    stdout = execFileSync("npx", ["eslint", ".", "--format", "json"], { encoding: "utf8", maxBuffer: 256 * 1024 * 1024 });
+  } catch (e) { stdout = e.stdout?.toString() || "[]"; } // eslint sai !=0 quando há errors
+  const results = JSON.parse(stdout);
+  out.eslintWarnings = results.reduce((n, r) => n + (r.warningCount || 0), 0);
+  out.eslintErrors = results.reduce((n, r) => n + (r.errorCount || 0), 0);
+}
+
+// 2) Cobertura: lê coverage/coverage-summary.json se existir
+function coverage() {
+  const p = path.join(cwd, "coverage", "coverage-summary.json");
+  if (!fs.existsSync(p)) return;
+  const t = JSON.parse(fs.readFileSync(p, "utf8")).total;
+  out["coverage.statements"] = t.statements.pct;
+  out["coverage.lines"] = t.lines.pct;
+  out["coverage.functions"] = t.functions.pct;
+  out["coverage.branches"] = t.branches.pct;
+}
+
+eslintCounts();
+coverage();
+fs.writeFileSync(path.join(cwd, "quality-metrics.json"), JSON.stringify(out, null, 2) + "\n");
+console.log("[collect-metrics]", JSON.stringify(out));
+```
+
+- [ ] **Step 2: Rodar e inspecionar a saída**
+```bash
+node scripts/quality/collect-metrics.mjs && cat quality-metrics.json
+```
+Expected: JSON com `eslintWarnings`, `eslintErrors` e (se houver coverage) os 4 `coverage.*`. **Anote `eslintWarnings`.**
+
+- [ ] **Step 3: Commit**
+```bash
+git add scripts/quality/collect-metrics.mjs && echo "quality-metrics.json" >> .gitignore
+git add .gitignore && git commit -m "feat(quality): metrics collector (eslint warnings + coverage)"
+```
+
+### Task 1.3: Congelar o baseline inicial
+
+**Files:** Create: `quality-baseline.json` (**commitado**)
+
+- [ ] **Step 1: Gerar o baseline a partir das métricas reais** (use os números anotados):
+```json
+{
+  "_comment": "Catraca: 'down' nao pode aumentar, 'up' nao pode cair. Atualize via 'npm run quality:ratchet -- --update' (so em melhora).",
+  "metrics": {
+    "eslintWarnings": { "value": <N_REAL>, "direction": "down" },
+    "coverage.statements": { "value": <S>, "direction": "up" },
+    "coverage.lines": { "value": <L>, "direction": "up" },
+    "coverage.functions": { "value": <F>, "direction": "up" },
+    "coverage.branches": { "value": <B>, "direction": "up" }
+  }
+}
+```
+
+- [ ] **Step 2: Validar a catraca contra si mesma**
+```bash
+node scripts/quality/collect-metrics.mjs
+node scripts/quality/check-quality-ratchet.mjs; echo "exit=$?"
+```
+Expected: `[quality-ratchet] OK` e `exit=0`.
+
+- [ ] **Step 3: Provar que pega regressão** (teste manual): edite `quality-metrics.json` somando 1 a `eslintWarnings`, rode o comparador, confirme `exit=1`, depois descarte a edição.
+
+- [ ] **Step 4: Adicionar scripts npm**
+```json
+"quality:collect": "node scripts/quality/collect-metrics.mjs",
+"quality:ratchet": "node scripts/quality/check-quality-ratchet.mjs",
+"quality:gate": "npm run quality:collect && npm run quality:ratchet"
+```
+
+- [ ] **Step 5: Commit**
+```bash
+git add quality-baseline.json package.json
+git commit -m "feat(quality): freeze initial quality baseline (eslint warnings + coverage)"
+```
+
+### Task 1.4: Wire no CI (job + artefato + comentário no PR)
+
+**Files:** Modify: `.github/workflows/ci.yml`
+
+- [ ] **Step 1: Adicionar job `quality-gate`** (depois de `test-coverage`, para reusar `coverage/coverage-summary.json`):
+```yaml
+  quality-gate:
+    name: Quality Ratchet
+    runs-on: ubuntu-latest
+    needs: test-coverage
+    if: ${{ always() && needs.test-coverage.result == 'success' }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with: { node-version: '24', cache: 'npm' }
+      - run: npm ci
+      - uses: actions/download-artifact@v4
+        with: { name: coverage-report, path: coverage/ }
+      - run: npm run quality:collect
+      - run: node scripts/quality/check-quality-ratchet.mjs --summary .artifacts/quality-ratchet.md
+      - if: always()
+        run: cat .artifacts/quality-ratchet.md >> "$GITHUB_STEP_SUMMARY"
+      - if: always()
+        uses: actions/upload-artifact@v4
+        with: { name: quality-ratchet, path: .artifacts/quality-ratchet.md }
+```
+
+- [ ] **Step 2: Adicionar comentário no PR** clonando o job `coverage-pr-comment` (marcador `<!-- omniroute-quality-ratchet -->`, lê `.artifacts/quality-ratchet.md`). Reuse o mesmo `github-script` de upsert de comentário.
+
+- [ ] **Step 3: Validar num PR de teste** — confirmar que o job aparece, o step summary mostra a tabela, e o comentário é postado.
+
+- [ ] **Step 4: Commit**
+```bash
+git add .github/workflows/ci.yml
+git commit -m "ci(quality): add quality-ratchet job with PR comment + artifact"
+```
+
+---
+
+# FASE 2 — Gates Determinísticos Anti-Alucinação
+
+> Cada gate ataca um ímã de alucinação específico (ver §2.4 do relatório). Todos no padrão `check-*.mjs`. **`check-fetch-targets` vem com código completo** (parsing determinístico de arquivos, sem risco de inventar nomes de export). **`check-provider-consistency` e `check-openapi-routes` começam com um Step 0 de verificação dos nomes reais** — propositalmente, porque fabricar a forma do import/spec seria o exato anti-padrão que este plano combate.
+
+### Task 2.1: `check-fetch-targets.mjs` — toda rota chamada pelo dashboard existe (TDD)
+
+**Ataca:** ímã nº2 (300 paths `fetch("/api/...")` sem ligação com as rotas).
+
+**Files:**
+- Create: `scripts/check/check-fetch-targets.mjs`
+- Test: `tests/unit/check-fetch-targets.test.ts`
+
+- [ ] **Step 1: Escrever o teste que falha**
+```ts
+// tests/unit/check-fetch-targets.test.ts
+import { test } from "node:test";
+import assert from "node:assert";
+import { resolveApiPathToRoute } from "../../scripts/check/check-fetch-targets.mjs";
+
+test("matches a static route file", () => {
+  const files = new Set(["src/app/api/usage/route.ts"]);
+  assert.equal(resolveApiPathToRoute("/api/usage", files), true);
+});
+
+test("matches a dynamic [param] segment", () => {
+  const files = new Set(["src/app/api/providers/[id]/models/route.ts"]);
+  assert.equal(resolveApiPathToRoute("/api/providers/abc-123/models", files), true);
+});
+
+test("rejects a hallucinated route", () => {
+  const files = new Set(["src/app/api/usage/route.ts"]);
+  assert.equal(resolveApiPathToRoute("/api/providers/refresh", files), false);
+});
+```
+
+- [ ] **Step 2: Rodar e ver falhar**
+```bash
+node --import tsx --test tests/unit/check-fetch-targets.test.ts
+```
+Expected: FAIL (módulo não existe).
+
+- [ ] **Step 3: Implementar o gate**
+```js
+#!/usr/bin/env node
+// scripts/check/check-fetch-targets.mjs
+// Todo fetch("/api/...") em src/app/(dashboard) deve resolver para um route.ts real.
+import fs from "node:fs";
+import path from "node:path";
+
+const cwd = process.cwd();
+const DASH = path.join(cwd, "src/app/(dashboard)");
+const API = path.join(cwd, "src/app/api");
+
+// allowlist de paths dinâmicos/externos que o checker não consegue resolver estaticamente
+const IGNORE = [/^\/api\/v1\//, /\$\{/, /` \+/]; // /v1 é a superfície OpenAI-compat; templates
+
+function walk(dir, acc = []) {
+  if (!fs.existsSync(dir)) return acc;
+  for (const e of fs.readdirSync(dir, { withFileTypes: true })) {
+    const p = path.join(dir, e.name);
+    if (e.isDirectory()) walk(p, acc);
+    else if (/\.(ts|tsx)$/.test(e.name)) acc.push(p);
+  }
+  return acc;
+}
+
+function collectRouteFiles() {
+  return new Set(walk(API).filter((p) => /route\.tsx?$/.test(p)).map((p) => path.relative(cwd, p).replace(/\\/g, "/")));
+}
+
+export function resolveApiPathToRoute(apiPath, routeFiles) {
+  // apiPath ex.: /api/providers/abc/models  →  src/app/api/providers/[id]/models/route.ts
+  const segs = apiPath.replace(/^\//, "").replace(/[?#].*$/, "").split("/"); // ["api","providers","abc","models"]
+  for (const rf of routeFiles) {
+    const rsegs = rf.replace(/^src\/app\//, "").replace(/\/route\.tsx?$/, "").split("/"); // ["api","providers","[id]","models"]
+    if (rsegs.length !== segs.length) continue;
+    const ok = rsegs.every((rs, i) => rs === segs[i] || /^\[.*\]$/.test(rs));
+    if (ok) return true;
+  }
+  return false;
+}
+
+function extractFetchPaths(file) {
+  const src = fs.readFileSync(file, "utf8");
+  const re = /(?:fetch|fetchJson|apiFetch)\(\s*["'`](\/api\/[^"'`?]+)/g;
+  const out = [];
+  let m;
+  while ((m = re.exec(src))) out.push(m[1]);
+  return out;
+}
+
+function main() {
+  const routeFiles = collectRouteFiles();
+  const misses = [];
+  for (const f of walk(DASH)) {
+    for (const apiPath of extractFetchPaths(f)) {
+      if (IGNORE.some((rx) => rx.test(apiPath))) continue;
+      if (!resolveApiPathToRoute(apiPath, routeFiles)) misses.push(`${path.relative(cwd, f)} → ${apiPath}`);
+    }
+  }
+  if (misses.length) {
+    console.error(`[check-fetch-targets] ${misses.length} fetch(es) para rota inexistente:\n` + misses.map((m) => "  ✗ " + m).join("\n"));
+    process.exit(1);
+  }
+  console.log(`[check-fetch-targets] OK (${routeFiles.size} rotas conhecidas)`);
+}
+
+if (import.meta.url === `file://${process.argv[1]}`) main();
+```
+
+- [ ] **Step 4: Rodar o teste unitário e ver passar**
+```bash
+node --import tsx --test tests/unit/check-fetch-targets.test.ts
+```
+Expected: PASS (3/3).
+
+- [ ] **Step 5: Rodar o gate no repo real** (modo descoberta — pode encontrar misses legítimos)
+```bash
+node scripts/check/check-fetch-targets.mjs; echo "exit=$?"
+```
+Se encontrar misses reais: triagem — ou são rotas faltantes (bug), ou paths dinâmicos a adicionar ao `IGNORE`. **Não** mascare; documente cada exceção no `IGNORE` com comentário.
+
+- [ ] **Step 6: Adicionar script + commit**
+```json
+"check:fetch-targets": "node scripts/check/check-fetch-targets.mjs"
+```
+```bash
+git add scripts/check/check-fetch-targets.mjs tests/unit/check-fetch-targets.test.ts package.json
+git commit -m "feat(check): gate that every dashboard fetch() targets a real API route"
+```
+
+### Task 2.2: `check-provider-consistency.ts` — ids batem entre os 3 arquivos
+
+**Ataca:** ímã nº1 (split de provider; 229 vs 155 vs N já divergem).
+
+**Files:** Create: `scripts/check/check-provider-consistency.ts` (rodado via `tsx`); Test: `tests/unit/check-provider-consistency.test.ts`
+
+- [ ] **Step 0 (VERIFICAÇÃO — obrigatório antes de codar):** descobrir os nomes reais de export, para **não inventar**:
+```bash
+grep -nE "export (const|function) " src/shared/constants/providers.ts | grep -iE "provider|section" | head
+grep -nE "getOrCreateAiProviders|_PROVIDER_SECTIONS|AI_PROVIDERS" src/shared/constants/providers.ts | head
+grep -nE "baseUrl|^\s*['\"][a-z0-9-]+['\"]\s*:" open-sse/config/providerRegistry.ts | head
+grep -nE "case ['\"]|=== ['\"]|SPECIALTY_VALIDATORS" src/lib/providers/validation.ts | head
+```
+Anote: como enumerar os ids canônicos em runtime, a forma das chaves do `providerRegistry.ts`, e onde `validation.ts` lista os providers cobertos.
+
+- [ ] **Step 1: Escrever o teste** com fixtures sintéticas (3 conjuntos de ids), afirmando que o diff detecta um id presente em um e ausente em outro. (Implemente a lógica como função pura `diffProviderSets(canonical, registry, validators)` que retorna `{missingInRegistry, missingInValidators, orphanInRegistry}`.)
+
+- [ ] **Step 2: Rodar e ver falhar.**
+
+- [ ] **Step 3: Implementar** importando os ids reais (descobertos no Step 0) e cruzando-os. Reusar o padrão de `scripts/check/check-docs-counts-sync.mjs` (que **já conta** executors/oauth/strategies vs docs — é o template direto). Para ids que legitimamente vivem só num lugar, manter um `KNOWN_EXCEPTIONS` allowlist com comentário por entrada.
+
+- [ ] **Step 4: Rodar no repo real**, triar as divergências reais (as contagens já divergem — algumas serão bugs de registro pela metade, outras exceções legítimas).
+
+- [ ] **Step 5: Commit** (`feat(check): provider-id consistency gate across providers.ts/registry/validation`).
+
+**Critério de aceitação:** o gate falha quando um id existe em `providers.ts` mas não no `providerRegistry.ts` (ou vice-versa), e quando um model no registry referencia um provider id desconhecido.
+
+### Task 2.3: `check-openapi-routes.mjs` — spec ↔ rotas (bidirecional)
+
+**Ataca:** docs-hallucination (endpoint inventado no `openapi.yaml`).
+
+**Files:** Create: `scripts/check/check-openapi-routes.mjs`; Test correspondente.
+
+- [ ] **Step 0 (VERIFICAÇÃO):** confirmar o caminho e a forma do spec:
+```bash
+ls docs/reference/openapi.yaml && grep -nE "^\s{2,4}/[a-z]" docs/reference/openapi.yaml | head
+```
+Confirmar como `check-openapi-coverage.mjs` já parseia o YAML (reusar o parser dele).
+
+- [ ] **Step 1–5 (TDD):** teste com spec sintética → implementar: toda `path` do spec resolve para um `route.ts` (reusando `resolveApiPathToRoute` da Task 2.1) e toda rota não-interna aparece no spec (com allowlist para rotas LOCAL_ONLY/internas). Commit.
+
+### Task 2.4: `check-deps.mjs` — anti-slopsquatting
+
+**Ataca:** pacotes alucinados (CSA: 19,7% das amostras IA).
+
+**Files:** Create: `scripts/check/check-deps.mjs`; Test.
+
+- [ ] **Step 0 (VERIFICAÇÃO):** decidir política — allowlist = todas as deps atuais do `package.json`/lockfile como baseline; novas deps exigem (a) existir no registry, (b) idade ≥ 72h, (c) entrada explícita.
+- [ ] **Step 1–5 (TDD):** teste com `package.json` sintético adicionando uma dep nova → gate falha se a dep não está no baseline E (não existe no registry OU foi publicada há <72h). Usar `npm view <pkg> time.created` para idade. Reusar o padrão diff-base...HEAD de `check-pr-test-policy.mjs`. Commit.
+
+### Task 2.5 (opcional): lints Rule #11/#12 via `no-restricted-syntax`
+
+- [ ] Estender o `eslint.config.mjs` (bloco `no-restricted-syntax` já usado p/ a regra de busca turca) para sinalizar `NextResponse.json({ error: "<string>" })` cru (exigir `buildErrorBody()`) e literais de `clientIdDefault`/`clientSecretDefault` no `providerRegistry.ts` (exigir `resolvePublicCred()`). Ratchet via contagem (adoção 11% → sobe). TDD com fixtures de ESLint.
+
+**Plugar tudo da Fase 2 no CI:** adicionar `check:fetch-targets`, `check:provider-consistency`, `check:openapi-routes`, `check:deps` ao job `lint` (ou `docs-sync-strict`) do `ci.yml`, e ao pre-commit barato quando rápidos o suficiente.
+
+---
+
+# FASE 3 — Catraca de Duplicação + Tamanho (mata-slop) — *expandir em sub-plano*
+
+**Justificativa:** GitClear mostra duplicação 4–8× na era IA; é a assinatura nº1 de slop. Nenhum gate hoje (Sonar CPD excluído).
+
+**Specs (criar sub-plano `writing-plans` a partir daqui):**
+
+1. **Adicionar `jscpd` v5** como devDependency. Rodar `jscpd --reporters json src open-sse` → `quality-metrics.json` ganha `duplication.pct`. **[verificar no install]** o schema JSON do v5 antes de parsear (ver ressalva no relatório §4.2).
+2. **Estender `collect-metrics.mjs`** com um coletor de duplicação (lê o JSON do jscpd) e um coletor de **tamanho de arquivo** (conta LOC de cada arquivo em `src`+`open-sse`, emite `fileSize.<path>` para os arquivos já acima de um teto, ex. >700 LOC — congelando os 64 atuais).
+3. **Adicionar regras ESLint** em `eslint.config.mjs` como `warn`: `max-lines` (700), `max-lines-per-function` (80), `complexity` (15), `sonarjs/cognitive-complexity` (15). Coletor adiciona `eslintWarnings` por categoria (a contagem já está na catraca da Fase 1; opcionalmente segregar `complexityWarnings`).
+4. **Estender `quality-baseline.json`** com `duplication.pct` (`down`) e os `fileSize.*` dos arquivos grandes (`down` — só podem encolher; arquivos novos têm teto absoluto).
+5. **Teto absoluto para arquivos novos:** o gate falha se um arquivo **não** presente no baseline nasce acima do teto (ex. 700 LOC) — impede o próximo god-component.
+
+**Critérios de aceitação:** PR que aumenta a duplicação % falha; PR que cresce qualquer um dos 64 arquivos grandes falha; PR que cria arquivo novo >700 LOC falha; refator que encolhe um arquivo grande ratcheta o baseline para baixo (via `--update`).
+
+---
+
+# FASE 4 — Catraca de Cobertura + Anti Test-Masking — *expandir em sub-plano*
+
+**Specs:**
+
+1. **`check-coverage-ratchet`** já é coberto pelo motor da Fase 1 (as 4 métricas `coverage.*` com `direction: "up"`). Confirmar que o job `quality-gate` roda **após** o merge dos 8 shards de cobertura no CI (não localmente, onde a cobertura é parcial). Adicionar **epsilon** maior (ex. 0.5) para `coverage.branches` por causa do não-determinismo do v8.
+2. **Pisos por módulo crítico:** estender `collect-metrics.mjs` para emitir `coverage.<modulo>.lines` para uma lista curta de módulos de alto risco (lendo o `coverage-summary.json` por arquivo): `open-sse/handlers/chatCore.ts`, `open-sse/services/combo.ts`, `open-sse/services/accountFallback.ts`, `src/sse/services/auth.ts`, `src/server/authz/routeGuard.ts`, `open-sse/utils/error.ts`, `open-sse/utils/publicCreds.ts`, `src/shared/utils/circuitBreaker.ts`. Cada um vira métrica `up` no baseline (implementa o "risco, não % bruto" do vídeo).
+3. **`check-test-masking.mjs`** (anti enfraquecimento de asserts): clonar `check-pr-test-policy.mjs` (diff `base...HEAD`); para cada `*.test.ts`/`*.spec.ts` alterado, contar `assert*(`/`expect(` em base vs HEAD; **sinalizar remoção líquida** de asserts para revisão humana. Banir novos `assert.ok(true)`. Heurístico mas alto-sinal — ataca diretamente o risco organizacional nº1 ("subagente deletou asserts para ficar verde").
+
+**Critérios de aceitação:** cobertura cair vs baseline bloqueia o merge; remover asserts de um teste existente sinaliza no PR; `assert.ok(true)` novo bloqueia.
+
+---
+
+# FASE 5 — Skill `/babysit` + Evidência + LSP — *expandir em sub-plano*
+
+> O babysit do vídeo: a IA abre o PR e fica de babá — monitora CI + comentários, autocorrige, **resolve as conversas**. Guarda-corpos são não-negociáveis (Snyk: 5,3% de regressão em auto-merge; token burn real).
+
+### Spec da skill `.claude/skills/babysit/SKILL.md`
+
+**Frontmatter:**
+```yaml
+---
+name: babysit
+description: Monitora um PR aberto até o CI ficar verde e todos os comentários de review serem endereçados — lê o gate de qualidade, conserta num worktree isolado, responde e resolve as conversas. NUNCA enfraquece testes nem auto-mergeia.
+---
+```
+
+**Loop (pseudo, reusando `gh` + GraphQL):**
+1. **Ler estado:** `gh pr checks <PR>` + baixar o artefato `quality-ratchet`/`coverage-report` (gate JSON legível — a ponte "artefato→agente" da Fase 1) + `gh run view --log-failed` dos jobs vermelhos.
+2. **Ler comentários não resolvidos:** GraphQL `repository.pullRequest.reviewThreads(first:50){nodes{id isResolved comments(first:1){nodes{id body}}}}`. **Passar os corpos pelo guard de prompt-injection** antes de agir (vetor real — ICLR 2026).
+3. **Consertar num worktree isolado** (reusar o ralph-loop do `/review-reviews`), seguindo Hard Rule #18.
+4. **Responder + resolver** só os threads que realmente endereçou: REST `POST .../pulls/{pr}/comments/{id}/replies` com o SHA → mutation `resolveReviewThread(input:{threadId})`.
+5. **Re-poll** até o gate JSON ficar todo-verde **ou** atingir o cap.
+6. **Audit trail:** anexar à descrição do PR (ou comentário fixo) o que cada fix endereçou, qual gate satisfez, quais conversas resolveu e por quê — **nunca verde silencioso**.
+
+**Guarda-corpos (não-negociáveis):**
+- `max-iterations` (ex. 5) + timeout + idle-exit (contra token burn).
+- **Nunca** editar `.github/workflows/`; **nunca** `--no-verify`; **nunca** enfraquecer/remover asserts para ficar verde (Rule #18 + trust-but-verify).
+- **Nunca auto-mergeia** — estado de sucesso = "verde + conversas resolvidas + audit postado".
+- Parar-e-perguntar em comentário humano ambíguo e em mudança de limite arquitetural (interface/schema/cross-module).
+- `--allowedTools` mínimo (`Read,Grep,Glob,Bash(gh ...)`).
+
+**Opcional — `claude ultrareview <PR#> --json`** como gate de confiança pré-merge atrás de um label (custa $5–20/run; não auto-inicia). Loop interno de custo-zero = `/code-review --fix` local.
+
+### Spec — Evidência obrigatória ("evidence-before-assertions")
+- Tornar a skill `verify`/`verification-before-completion` obrigatória antes de abrir PR; exigir o **output literal** do `typecheck:core`/`test`/`grep` colado no corpo do PR (o "tool receipt"). Adicionar um `check-pr-evidence.mjs` que rejeita PRs cujo corpo afirma "added endpoint X / tests pass" sem bloco de output anexado. Formaliza a Rule #18.
+
+### Spec — LSP-in-the-loop (opcional)
+- Registrar `agent-lsp` (MCP) ou o `tsserver` para os agentes terem `blast_radius`/diagnostics e `preview_edit` antes de escrever — vira "símbolo inventado" de catch-de-review para impossibilidade-no-edit. Pareia com `typecheck:core` como gate pré-PR (compile-before-claim).
+
+**Critérios de aceitação:** a skill `/babysit <PR#>` leva um PR de vermelho a verde sem auto-merge, resolve só as conversas que endereçou, respeita o cap de iterações, e deixa rastro auditável; nenhum assert é enfraquecido.
+
+---
+
+## Self-Review (checklist do autor)
+
+- **Cobertura do spec:** Fases 0–2 mapeiam 1:1 com as recomendações do relatório §5; Fases 3–5 cobrem duplicação/tamanho, cobertura/masking e babysit/evidência. ✓
+- **Sem placeholders nos passos bite-sized:** Fases 0/1/2.1 têm comandos e código reais. As Fases 2.2–2.4 usam um Step-0 de verificação **deliberado** (não placeholder) para não fabricar nomes de export — coerente com o objetivo anti-alucinação. ✓
+- **Consistência de tipos:** `resolveApiPathToRoute` (Task 2.1) é reusada na Task 2.3; o comparador usa o mesmo formato `{value, direction}` em todas as fases; `quality-metrics.json` é a interface única coletor↔comparador. ✓
+- **Ordem de dependência:** Fase 1 (motor) precede 3/4 (que só adicionam métricas ao baseline); Fase 0 destrava o resto. ✓
+
+## Handoff de Execução
+
+**Plano salvo em `PLANO-QUALITY-GATES.md`.** Duas opções:
+
+1. **Subagent-Driven (recomendado)** — um subagente fresco por task, review entre tasks. SUB-SKILL: `superpowers:subagent-driven-development`.
+2. **Inline** — executar nesta sessão com checkpoints. SUB-SKILL: `superpowers:executing-plans`.
+
+**Recomendação:** começar pela **Fase 0** (quick wins, baixo risco) e **Fase 1** (motor de catraca) numa branch `feat/quality-ratchet`, validar num PR de teste, e só então abrir as fases anti-alucinação. Fases 3–5 viram sub-planos próprios.

README.md

@@ -6,7 +6,7 @@
 
 # 🚀 OmniRoute — The Free AI Gateway
 
-### Never stop coding. Connect every AI tool to **250 providers** — **90+ free** — through one endpoint.
+### Never stop coding. Connect every AI tool to **177 providers** — **50+ free** — through one endpoint.
 
 **Plug Claude Code, Codex, Cursor, Cline, Copilot & Antigravity into FREE Claude / GPT / Gemini. Auto-fallback.**
 <br/>
@@ -15,109 +15,97 @@
 
 <br/>
 
-**~1.6B documented free tokens/month** — up to **~2.1B in your first month** with signup credits — aggregated across the free tiers, plus a long tail of permanently-free, no-cap providers, and the compression above stretches every one further. ([how we count →](docs/reference/FREE_TIERS.md#tldr--how-much-free-inference-does-omniroute-actually-aggregate))
+**~1.9B+ documented free tokens/month** — up to **~2.5B in your first month** with signup credits — aggregated across the free tiers, and the compression above stretches every one further. ([how we count →](docs/reference/FREE_TIERS.md#tldr--how-much-free-inference-does-omniroute-actually-aggregate))
 
 <br/>
 
-<h3>
-
-⭐ Star the repo if OMNIROUTE helped you save money and make your work easier.
-
-</h3>
-
-[![Stars](https://img.shields.io/github/stars/diegosouzapw/OmniRoute?style=social)](https://github.com/diegosouzapw/OmniRoute)
-<a href="https://trendshift.io/repositories/23589" target="_blank"><img src="https://trendshift.io/api/badge/repositories/23589" alt="diegosouzapw%2FOmniRoute | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-[![Star History Rank](https://api.star-history.com/badge?repo=diegosouzapw/OmniRoute&theme=dark)](https://www.star-history.com/diegosouzapw/omniroute)
-
-</br>
-
-[![250 AI Providers](https://img.shields.io/badge/250-AI_Providers-6C5CE7?style=for-the-badge)](#-250-ai-providers--90-free)
-[![90+ Free](https://img.shields.io/badge/90%2B-Free_Tiers-00B894?style=for-the-badge)](#-250-ai-providers--90-free)
-[![1.6B Free Tokens/mo](https://img.shields.io/badge/1.6B-Free_Tokens%2Fmo-00B894?style=for-the-badge)](docs/reference/FREE_TIERS.md)
+[![177 AI Providers](https://img.shields.io/badge/177-AI_Providers-6C5CE7?style=for-the-badge)](#-177-ai-providers--50-free)
+[![50+ Free](https://img.shields.io/badge/50%2B-Free_Tiers-00B894?style=for-the-badge)](#-177-ai-providers--50-free)
+[![1.9B+ Free Tokens/mo](https://img.shields.io/badge/1.9B%2B-Free_Tokens%2Fmo-00B894?style=for-the-badge)](docs/reference/FREE_TIERS.md)
 [![Token Savings](https://img.shields.io/badge/up_to_95%25-Token_Savings-E17055?style=for-the-badge)](#%EF%B8%8F-save-1595-tokens--automatically)
-[![18 Strategies](https://img.shields.io/badge/18-Routing_Strategies-0984E3?style=for-the-badge)](#-combos--the-flagship)
+[![14 Strategies](https://img.shields.io/badge/14-Routing_Strategies-0984E3?style=for-the-badge)](#-combos--the-flagship)
 [![$0 to start](https://img.shields.io/badge/%240-To_Start-FDCB6E?style=for-the-badge&logoColor=black)](#-quick-start)
 
 <br/>
 
 ### 💬 Join the community
 
-[![Discord](https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/EkzRkpzKYt)
+[![Discord](https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/hmexnhgE)
 [![Telegram](https://img.shields.io/badge/Telegram-26A5E4?style=for-the-badge&logo=telegram&logoColor=white)](https://t.me/omnirouteOficial)
 [![WhatsApp Global](https://img.shields.io/badge/WhatsApp_Global-25D366?style=for-the-badge&logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
 [![WhatsApp Brasil](https://img.shields.io/badge/WhatsApp_Brasil-25D366?style=for-the-badge&logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/BTGJXIyjeNIIgExvTMGGhI)
-[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
 
-**Questions, provider tips, roadmap & support → [Discord](https://discord.gg/EkzRkpzKYt) · [Telegram](https://t.me/omnirouteOficial) · WhatsApp [🌍 Global](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) / [🇧🇷 Brasil](https://chat.whatsapp.com/BTGJXIyjeNIIgExvTMGGhI)**
+**Questions, provider tips, roadmap & support → [Discord](https://discord.gg/hmexnhgE) · [Telegram](https://t.me/omnirouteOficial) · WhatsApp [🌍 Global](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) / [🇧🇷 Brasil](https://chat.whatsapp.com/BTGJXIyjeNIIgExvTMGGhI)**
 
 <br/>
 
-### 🧩 Available
+<a href="https://trendshift.io/repositories/23589" target="_blank"><img src="https://trendshift.io/api/badge/repositories/23589" alt="diegosouzapw%2FOmniRoute | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
+[![npm](https://img.shields.io/npm/v/omniroute?logo=npm&style=flat-square)](https://www.npmjs.com/package/omniroute)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](LICENSE)
+[![Node](https://img.shields.io/badge/node-%E2%89%A522.22.2-brightgreen?style=flat-square)](package.json)
+[![Stars](https://img.shields.io/github/stars/diegosouzapw/OmniRoute?style=social)](https://github.com/diegosouzapw/OmniRoute)
+
+<div align="center">
 
 [![npm version](https://img.shields.io/npm/v/omniroute?color=cb3837&logo=npm)](https://www.npmjs.com/package/omniroute)
 ![NPM Monthly](https://img.shields.io/npm/dm/omniroute?label=npm/month&color=cb3837&logo=npm)
 [![Docker Hub](https://img.shields.io/docker/v/diegosouzapw/omniroute?label=Docker%20Hub&logo=docker&color=2496ED)](https://hub.docker.com/r/diegosouzapw/omniroute)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](LICENSE)
 ![Docker Pulls](https://img.shields.io/docker/pulls/diegosouzapw/omniroute?label=docker%20pulls&logo=docker&color=2496ED)
 ![Electron Downloads](https://img.shields.io/github/downloads/diegosouzapw/omniroute/total?style=flat&label=electron%20downloads&logo=electron&color=47848F)
+[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
 
-[**🚀 Quick Start**](#-quick-start) • [**🎯 Combos**](#-combos--the-flagship) • [**🌐 Providers**](#-250-ai-providers--90-free) • [**🔌 CLI & MCP**](#-full-cli--a2a--mcp) • [**🗜️ Compression**](#%EF%B8%8F-save-1595-tokens--automatically) • [**🌍 Website**](https://omniroute.online)
+</div>
+
+<br/>
+
+[**🚀 Quick Start**](#-quick-start) • [**🎯 Combos**](#-combos--the-flagship) • [**🌐 Providers**](#-177-ai-providers--50-free) • [**🔌 CLI & MCP**](#-full-cli--a2a--mcp) • [**🗜️ Compression**](#%EF%B8%8F-save-1595-tokens--automatically) • [**🌍 Website**](https://omniroute.online)
 
 [💥 The Promise](#-the-promise) • [🤔 Why](#-why-omniroute) • [🏆 What Sets Apart](#-what-sets-omniroute-apart) • [🤖 Compatible CLIs](#-compatible-clis--coding-agents) • [🖥️ Where It Runs](#%EF%B8%8F-where-omniroute-runs--anywhere) • [🔒 Private](#-private--local-first) • [🎬 In Action](#-omniroute-in-action) • [📚 Explore More](#-explore-more) • [📧 Support](#-support--community)
 
 </div>
 
 <div align="center">
- <b>🌐 In 42+ languages</b>
- <table>
+<b>🌐 Available in 40+ languages</b>
+<table>
   <tr>
-    <td align="center"><a href="README.md"><img src="docs/assets/flags/us.svg" width="26" alt="English (en)"></a></td>
-    <td align="center"><a href="docs/i18n/pt-BR/README.md"><img src="docs/assets/flags/br.svg" width="26" alt="Português — Brasil (pt-BR)"></a></td>
-    <td align="center"><a href="docs/i18n/pt/README.md"><img src="docs/assets/flags/pt.svg" width="26" alt="Português (pt)"></a></td>
-    <td align="center"><a href="docs/i18n/es/README.md"><img src="docs/assets/flags/es.svg" width="26" alt="Español (es)"></a></td>
-    <td align="center"><a href="docs/i18n/fr/README.md"><img src="docs/assets/flags/fr.svg" width="26" alt="Français (fr)"></a></td>
-    <td align="center"><a href="docs/i18n/it/README.md"><img src="docs/assets/flags/it.svg" width="26" alt="Italiano (it)"></a></td>
-    <td align="center"><a href="docs/i18n/de/README.md"><img src="docs/assets/flags/de.svg" width="26" alt="Deutsch (de)"></a></td>
-    <td align="center"><a href="docs/i18n/nl/README.md"><img src="docs/assets/flags/nl.svg" width="26" alt="Nederlands (nl)"></a></td>
-    <td align="center"><a href="docs/i18n/ru/README.md"><img src="docs/assets/flags/ru.svg" width="26" alt="Русский (ru)"></a></td>
-    <td align="center"><a href="docs/i18n/uk-UA/README.md"><img src="docs/assets/flags/ua.svg" width="26" alt="Українська (uk-UA)"></a></td>
-    <td align="center"><a href="docs/i18n/pl/README.md"><img src="docs/assets/flags/pl.svg" width="26" alt="Polski (pl)"></a></td>
-    <td align="center"><a href="docs/i18n/cs/README.md"><img src="docs/assets/flags/cz.svg" width="26" alt="Čeština (cs)"></a></td>
-    <td align="center"><a href="docs/i18n/sk/README.md"><img src="docs/assets/flags/sk.svg" width="26" alt="Slovenčina (sk)"></a></td>
-    <td align="center"><a href="docs/i18n/ro/README.md"><img src="docs/assets/flags/ro.svg" width="26" alt="Română (ro)"></a></td>
-    <td align="center"><a href="docs/i18n/hu/README.md"><img src="docs/assets/flags/hu.svg" width="26" alt="Magyar (hu)"></a></td>
+    <td align="center"><a href="README.md">🇺🇸</a></td>
+    <td align="center"><a href="docs/i18n/pt-BR/README.md">🇧🇷</a></td>
+    <td align="center"><a href="docs/i18n/es/README.md">🇪🇸</a></td>
+    <td align="center"><a href="docs/i18n/fr/README.md">🇫🇷</a></td>
+    <td align="center"><a href="docs/i18n/it/README.md">🇮🇹</a></td>
+    <td align="center"><a href="docs/i18n/ru/README.md">🇷🇺</a></td>
+    <td align="center"><a href="docs/i18n/zh-CN/README.md">🇨🇳</a></td>
+    <td align="center"><a href="docs/i18n/de/README.md">🇩🇪</a></td>
+    <td align="center"><a href="docs/i18n/ja/README.md">🇯🇵</a></td>
+    <td align="center"><a href="docs/i18n/ko/README.md">🇰🇷</a></td>
+    <td align="center"><a href="docs/i18n/in/README.md">🇮🇳</a></td>
   </tr>
   <tr>
-    <td align="center"><a href="docs/i18n/bg/README.md"><img src="docs/assets/flags/bg.svg" width="26" alt="Български (bg)"></a></td>
-    <td align="center"><a href="docs/i18n/da/README.md"><img src="docs/assets/flags/dk.svg" width="26" alt="Dansk (da)"></a></td>
-    <td align="center"><a href="docs/i18n/fi/README.md"><img src="docs/assets/flags/fi.svg" width="26" alt="Suomi (fi)"></a></td>
-    <td align="center"><a href="docs/i18n/no/README.md"><img src="docs/assets/flags/no.svg" width="26" alt="Norsk (no)"></a></td>
-    <td align="center"><a href="docs/i18n/sv/README.md"><img src="docs/assets/flags/se.svg" width="26" alt="Svenska (sv)"></a></td>
-    <td align="center"><a href="docs/i18n/zh-CN/README.md"><img src="docs/assets/flags/cn.svg" width="26" alt="中文 — 简体 (zh-CN)"></a></td>
-    <td align="center"><a href="docs/i18n/zh-TW/README.md"><img src="docs/assets/flags/tw.svg" width="26" alt="中文 — 繁體 (zh-TW)"></a></td>
-    <td align="center"><a href="docs/i18n/ja/README.md"><img src="docs/assets/flags/jp.svg" width="26" alt="日本語 (ja)"></a></td>
-    <td align="center"><a href="docs/i18n/ko/README.md"><img src="docs/assets/flags/kr.svg" width="26" alt="한국어 (ko)"></a></td>
-    <td align="center"><a href="docs/i18n/th/README.md"><img src="docs/assets/flags/th.svg" width="26" alt="ไทย (th)"></a></td>
-    <td align="center"><a href="docs/i18n/vi/README.md"><img src="docs/assets/flags/vn.svg" width="26" alt="Tiếng Việt (vi)"></a></td>
-    <td align="center"><a href="docs/i18n/id/README.md"><img src="docs/assets/flags/id.svg" width="26" alt="Bahasa Indonesia (id)"></a></td>
-    <td align="center"><a href="docs/i18n/ms/README.md"><img src="docs/assets/flags/my.svg" width="26" alt="Bahasa Melayu (ms)"></a></td>
-    <td align="center"><a href="docs/i18n/phi/README.md"><img src="docs/assets/flags/ph.svg" width="26" alt="Filipino (phi)"></a></td>
+    <td align="center"><a href="docs/i18n/th/README.md">🇹🇭</a></td>
+    <td align="center"><a href="docs/i18n/vi/README.md">🇻🇳</a></td>
+    <td align="center"><a href="docs/i18n/id/README.md">🇮🇩</a></td>
+    <td align="center"><a href="docs/i18n/ms/README.md">🇲🇾</a></td>
+    <td align="center"><a href="docs/i18n/phi/README.md">🇵🇭</a></td>
+    <td align="center"><a href="docs/i18n/ar/README.md">🇸🇦</a></td>
+    <td align="center"><a href="docs/i18n/he/README.md">🇮🇱</a></td>
+    <td align="center"><a href="docs/i18n/az/README.md">🇦🇿</a></td>
+    <td align="center"><a href="docs/i18n/uk-UA/README.md">🇺🇦</a></td>
+    <td align="center"><a href="docs/i18n/pl/README.md">🇵🇱</a></td>
+    <td align="center"><a href="docs/i18n/cs/README.md">🇨🇿</a></td>
   </tr>
   <tr>
-    <td align="center"><a href="docs/i18n/in/README.md"><img src="docs/assets/flags/in.svg" width="26" alt="हिन्दी (in)"></a></td>
-    <td align="center"><a href="docs/i18n/hi/README.md"><img src="docs/assets/flags/in.svg" width="26" alt="हिन्दी (hi)"></a></td>
-    <td align="center"><a href="docs/i18n/gu/README.md"><img src="docs/assets/flags/in.svg" width="26" alt="ગુજરાતી (gu)"></a></td>
-    <td align="center"><a href="docs/i18n/mr/README.md"><img src="docs/assets/flags/in.svg" width="26" alt="मराठी (mr)"></a></td>
-    <td align="center"><a href="docs/i18n/ta/README.md"><img src="docs/assets/flags/in.svg" width="26" alt="தமிழ் (ta)"></a></td>
-    <td align="center"><a href="docs/i18n/te/README.md"><img src="docs/assets/flags/in.svg" width="26" alt="తెలుగు (te)"></a></td>
-    <td align="center"><a href="docs/i18n/bn/README.md"><img src="docs/assets/flags/bd.svg" width="26" alt="বাংলা (bn)"></a></td>
-    <td align="center"><a href="docs/i18n/ur/README.md"><img src="docs/assets/flags/pk.svg" width="26" alt="اردو (ur)"></a></td>
-    <td align="center"><a href="docs/i18n/fa/README.md"><img src="docs/assets/flags/ir.svg" width="26" alt="فارسی (fa)"></a></td>
-    <td align="center"><a href="docs/i18n/ar/README.md"><img src="docs/assets/flags/sa.svg" width="26" alt="العربية (ar)"></a></td>
-    <td align="center"><a href="docs/i18n/he/README.md"><img src="docs/assets/flags/il.svg" width="26" alt="עברית (he)"></a></td>
-    <td align="center"><a href="docs/i18n/tr/README.md"><img src="docs/assets/flags/tr.svg" width="26" alt="Türkçe (tr)"></a></td>
-    <td align="center"><a href="docs/i18n/az/README.md"><img src="docs/assets/flags/az.svg" width="26" alt="Azərbaycan (az)"></a></td>
-    <td align="center"><a href="docs/i18n/sw/README.md"><img src="docs/assets/flags/tz.svg" width="26" alt="Kiswahili (sw)"></a></td>
+    <td align="center"><a href="docs/i18n/nl/README.md">🇳🇱</a></td>
+    <td align="center"><a href="docs/i18n/bg/README.md">🇧🇬</a></td>
+    <td align="center"><a href="docs/i18n/da/README.md">🇩🇰</a></td>
+    <td align="center"><a href="docs/i18n/fi/README.md">🇫🇮</a></td>
+    <td align="center"><a href="docs/i18n/no/README.md">🇳🇴</a></td>
+    <td align="center"><a href="docs/i18n/sv/README.md">🇸🇪</a></td>
+    <td align="center"><a href="docs/i18n/hu/README.md">🇭🇺</a></td>
+    <td align="center"><a href="docs/i18n/ro/README.md">🇷🇴</a></td>
+    <td align="center"><a href="docs/i18n/sk/README.md">🇸🇰</a></td>
+    <td align="center"><a href="docs/i18n/pt/README.md">🇵🇹</a></td>
+    <td align="center"></td>
   </tr>
 </table>
 </div>
@@ -126,15 +114,14 @@
 
 <div align="center">
 
-# 💰 ~1.6B Free Tokens / Month
+# 💰 ~1.9B Free Tokens / Month
 
 </div>
 
-> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute aggregates the **documented** free tiers of **40+ provider pools / 500+ models** into one honest number and shows it live on the dashboard (`/dashboard/free-tiers`).
+> Stacking free tiers by hand is painful — dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute aggregates the **documented** free tiers of **50+ provider pools / 530 models** into one honest number and shows it live on the dashboard (`/dashboard/free-tiers`).
 
-- **~1.6B free tokens / month** (steady) — and **up to ~2.1B in your first month** with signup credits.
-- **Pool-deduped, honest** — we count each shared free pool **once**, so the headline isn't inflated by rate-limit ceilings the way multi-billion competitor claims are. (Counting every rate limit 24/7 would read ~10B; we don't publish that.)
-- **Plus the un-countable** — permanently-free, no-token-cap providers (SiliconFlow, Z.AI GLM-Flash, Kilo, OpenCode Zen…) and a **$10 OpenRouter top-up** that unlocks **+24M/mo**, both surfaced separately so they never inflate the headline.
+- **~1.9B free tokens / month** (steady) — and **up to ~2.5B in your first month** with signup credits.
+- **Pool-deduped, honest** — we count each shared free pool **once**, so the headline isn't inflated by rate-limit ceilings the way multi-billion competitor claims are. (The naïve per-model sum would read ~8B; we don't publish that.)
 - **Per-model breakdown**, **live used / remaining** for the current month, and a transparent **terms flag** per provider.
 
 ![Free-Tier Budget card (preview mockup)](docs/screenshots/free-tier-budget-card.svg)
@@ -149,18 +136,18 @@
 
 </div>
 
-> One endpoint. **250 providers.** Never stop building — and let OmniRoute pick the cheapest one that works.
+> One endpoint. **177 providers.** Never stop building — and let OmniRoute pick the cheapest one that works.
 
 <table>
   <tr>
-    <td width="33%" valign="top"><b>🚫 Never hit limits</b><br/><sub>Auto-fallback across 250 providers in milliseconds. Quota out? Next provider takes over — zero downtime.</sub></td>
+    <td width="33%" valign="top"><b>🚫 Never hit limits</b><br/><sub>Auto-fallback across 177 providers in milliseconds. Quota out? Next provider takes over — zero downtime.</sub></td>
     <td width="33%" valign="top"><b>💸 Save up to 95% tokens</b><br/><sub>RTK + Caveman stacked compression cuts 15–95% of eligible tokens (~89% avg on tool-heavy sessions).</sub></td>
-    <td width="33%" valign="top"><b>🆓 $0 to start</b><br/><sub>90+ providers with a free tier, 11 free <i>forever</i> (Kiro, Qoder, Pollinations, LongCat…). No card needed.</sub></td>
+    <td width="33%" valign="top"><b>🆓 $0 to start</b><br/><sub>50+ providers with a free tier, 11 free <i>forever</i> (Kiro, Qoder, Pollinations, LongCat…). No card needed.</sub></td>
   </tr>
   <tr>
-    <td width="33%" valign="top"><b>🔌 Every tool works</b><br/><sub>24+ coding agents — Claude Code, Codex, Cursor, Cline, Copilot, Antigravity — through one config.</sub></td>
+    <td width="33%" valign="top"><b>🔌 Every tool works</b><br/><sub>16+ coding agents — Claude Code, Codex, Cursor, Cline, Copilot, Antigravity — through one config.</sub></td>
     <td width="33%" valign="top"><b>🧩 One endpoint</b><br/><sub>OpenAI ↔ Claude ↔ Gemini ↔ Responses API translation. Point any tool at <code>/v1</code> and it just works.</sub></td>
-    <td width="33%" valign="top"><b>🛡️ Production-grade</b><br/><sub>Circuit breakers, TLS stealth, MCP (94 tools), A2A, memory, guardrails, evals. 21,000+ tests.</sub></td>
+    <td width="33%" valign="top"><b>🛡️ Production-grade</b><br/><sub>Circuit breakers, TLS stealth, MCP (37 tools), A2A, memory, guardrails, evals. 4,690+ tests.</sub></td>
   </tr>
 </table>
 
@@ -194,7 +181,7 @@
                           ▼
 ┌──────────────────────────────────────────────────────────┐
 │                  OmniRoute — Smart Router                  │
-│  RTK + Caveman compression · 18 routing strategies         │
+│  RTK + Caveman compression · 14 routing strategies         │
 │  Circuit breakers · TLS stealth · MCP · A2A · Guardrails   │
 └─────────────────────────┬──────────────────────────────────┘
         ┌─────────────┬────┴────────┬─────────────┐
@@ -232,56 +219,18 @@ No combo to create. Set your model to `auto` (or a variant) and OmniRoute builds
 
 ##
 
-### 🔀 Or build your own — 18 routing strategies
+### 🔀 Or build your own — 14 routing strategies
 
-All **18** strategies — mix & match per combo step:
+| Goal                                    | Strategy / combo                                   |
+| --------------------------------------- | -------------------------------------------------- |
+| 🥇 Drain my subscription before paying  | `priority` / `fill-first`                          |
+| ⚖️ Spread load across accounts          | `round-robin` · `weighted` · `p2c` · `least-used`  |
+| 💸 Always cheapest viable model         | `cost-optimized` · `auto/cheap`                    |
+| 🧠 Hand off long context between models | `context-relay` · `context-optimized`              |
+| 🎲 Randomized / privacy routing         | `random` · `strict-random`                         |
+| 🤖 Just make it smart                   | `auto` (9-factor scoring) · `lkgp` · `reset-aware` |
 
-| #   | Strategy            | What it does                                                     |
-| --- | ------------------- | ---------------------------------------------------------------- |
-| 1   | `priority`          | First-target ordered list — drain each before the next 🥇        |
-| 2   | `fill-first`        | Fill each target's quota fully before moving on                  |
-| 3   | `weighted`          | Weighted random by per-target weight                             |
-| 4   | `round-robin`       | Cycle through targets in order                                   |
-| 5   | `p2c`               | Power-of-two-choices random load balancing                       |
-| 6   | `least-used`        | Pick the target with the lowest current load                     |
-| 7   | `random`            | Uniform random pick (deduplicated)                               |
-| 8   | `strict-random`     | Random without de-duplicating repeats 🎲                         |
-| 9   | `cost-optimized`    | Minimize $ per request from live catalog pricing 💸              |
-| 10  | `headroom`          | Pick the target with the most remaining quota                    |
-| 11  | `reset-window`      | Prefer the target whose quota window resets soonest              |
-| 12  | `reset-aware`       | Rank by quota reset time — short windows first 📊                |
-| 13  | `context-relay`     | Hand off context across targets for long conversations 🧠        |
-| 14  | `context-optimized` | Pick the best fit for the current context size                   |
-| 15  | `lkgp`              | Last-Known-Good Path — sticky to the last successful target      |
-| 16  | `auto`              | 12-factor live scoring across every connection 🤖                |
-| 17  | `fusion`            | Fan out to a panel of models + a judge synthesizes one answer 🧬 |
-| 18  | `pipeline`          | Chain steps — each target's output feeds the next one 🔗         |
-
-<sub>The Auto-Combo engine scores every candidate on **12 factors** (health, quota, cost, latency, success rate, freshness…) — see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md).</sub>
-
-##
-
-### ⚖️ Quota-Share — split one subscription across a team ✨ NEW
-
-> Running several keys against the **same upstream account** (one Codex Pro plan, one Kimi key, one GLM Coding seat)? A burst on one key can burn the whole 5-hour / hourly quota and lock everyone else out. **Quota-Share** distributes a provider's time-based quota **fairly** across the keys in a pool — and it's _work-conserving_, so an idle member's slice is lent out instead of wasted.
-
-| Knob                     | What it controls                                                                |
-| ------------------------ | ------------------------------------------------------------------------------- |
-| ⚖️ **Allocation weight** | each key's slice of the pool — e.g. `50 / 30 / 20`                              |
-| 📐 **Dimensions**        | track `%` · requests · tokens · `$`, per **5h / 7d / per-model** window         |
-| 🚦 **Policy**            | `hard` (block over share) · `soft` (deprioritize) · `burst` (use idle headroom) |
-| 🧱 **Cap**               | absolute ceiling per key, independent of mode                                   |
-
-```
-Pool "team-codex"   ·   1 Codex Pro account   ·   3 keys   ·   5-hour window
-  ├─ alice    weight 50  ██████████░░░░░░░░░░   ≤ 50% of the shared 5h quota
-  ├─ bob      weight 30  ██████░░░░░░░░░░░░░░   ≤ 30%
-  └─ ci-bot   weight 20  ████░░░░░░░░░░░░░░░░   ≤ 20%
-Generous mode (<50% pool used) → idle shares are lent out
-Strict mode  (≥50% pool used)  → each key held to its fair share
-```
-
-<sub>Enforced in the hot path **before** the request leaves OmniRoute, with per-(key, model) caps + session stickiness for prompt-cache integrity (now with a per-combo / global disable toggle). 📖 [Quota Sharing Engine](docs/routing/QUOTA_SHARE.md)</sub>
+<sub>The Auto-Combo engine scores every candidate on **9 factors** (health, quota, cost, latency, success rate, freshness…) — see [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md).</sub>
 
 ##
 
@@ -312,20 +261,20 @@ Result: 4 layers of fallback = zero downtime
 
 </div>
 
-| Feature                                | OmniRoute                                                           | Other routers |
-| -------------------------------------- | ------------------------------------------------------------------- | ------------- |
-| 🌐 Providers                           | **250**                                                             | 20–100        |
-| 🆓 Free providers                      | **90+ (11 free forever)**                                           | 1–5           |
-| 🔀 Routing strategies                  | **18** (priority, weighted, cost-optimized, context-relay, fusion…) | 1–3           |
-| 🗜️ Token compression                   | **RTK + Caveman stacked (15–95%)**                                  | None / 20–40% |
-| 🧰 Built-in MCP server                 | **94 tools, 3 transports, 30 scopes**                               | Rare          |
-| 🤝 A2A agent protocol                  | **6 skills, JSON-RPC 2.0**                                          | None          |
-| 🧠 Memory (FTS5 + vector)              | **Yes**                                                             | Rare          |
-| 🛡️ Guardrails (PII, injection, vision) | **Yes**                                                             | Rare          |
-| ☁️ Cloud agents                        | **Codex, Cursor, Devin, Jules**                                     | None          |
-| 🥷 TLS fingerprint stealth             | **JA3/JA4 via wreq-js**                                             | None          |
-| 🖥️ Multi-platform                      | **Web · Desktop · Termux · PWA**                                    | Web only      |
-| 🌍 i18n                                | **42 locales**                                                      | 0–4           |
+| Feature                                | OmniRoute                                                   | Other routers |
+| -------------------------------------- | ----------------------------------------------------------- | ------------- |
+| 🌐 Providers                           | **177**                                                     | 20–100        |
+| 🆓 Free providers                      | **50+ (11 free forever)**                                   | 1–5           |
+| 🔀 Routing strategies                  | **14** (priority, weighted, cost-optimized, context-relay…) | 1–3           |
+| 🗜️ Token compression                   | **RTK + Caveman stacked (15–95%)**                          | None / 20–40% |
+| 🧰 Built-in MCP server                 | **37 tools, 3 transports, 13 scopes**                       | Rare          |
+| 🤝 A2A agent protocol                  | **5 skills, JSON-RPC 2.0**                                  | None          |
+| 🧠 Memory (FTS5 + vector)              | **Yes**                                                     | Rare          |
+| 🛡️ Guardrails (PII, injection, vision) | **Yes**                                                     | Rare          |
+| ☁️ Cloud agents                        | **Codex, Devin, Jules**                                     | None          |
+| 🥷 TLS fingerprint stealth             | **JA3/JA4 via wreq-js**                                     | None          |
+| 🖥️ Multi-platform                      | **Web · Desktop · Termux · PWA**                            | Web only      |
+| 🌍 i18n                                | **40+ locales**                                             | 0–4           |
 
 <sub>📊 Detailed comparison vs LiteLLM, OpenRouter & Portkey → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -333,32 +282,6 @@ Result: 4 layers of fallback = zero downtime
 
 <div align="center">
 
-# ✨ What's New
-
-</div>
-
-> Recent highlights from **v3.8.20 → v3.8.47**. Full history in [`CHANGELOG.md`](CHANGELOG.md).
-
-- **🗜️ Compression hardening** — a default-on **inflation guard** (discard the stacked result and send the verbatim original whenever compression would _grow_ the prompt), completed **Caveman rule packs** for German / French / Japanese (dedup + ultra) plus a new **Chinese (文言 / wényán) input pack** with zh-vs-ja auto-detection, and **RTK filters for Gradle & .NET (`dotnet`)** build output. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
-- **💸 Honest flat-rate cost** — subscription / coding-plan providers (ChatGPT Web, grok-web, the Minimax / Kimi / GLM / Alibaba Coding plans, Xiaomi MiMo…) now read **$0** in cost analytics instead of an inflated per-token estimate, while budget / quota / routing keep estimating unchanged. → [API Reference](docs/reference/API_REFERENCE.md)
-- **⚖️ Quota-Share routing** — a dedicated combo strategy that spreads load across accounts by _available quota_: Deficit-Round-Robin scheduling, per-connection `max_concurrent` with cooldown-wait queueing, multi-window usage buckets (5h / 7d / per-model), per-(key, model) caps, session stickiness for prompt-cache integrity (now with a per-combo / global disable toggle), and proactive saturation from upstream token-usage headers. → [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)
-- **🤖 One-command CLI/agent setup** — a dedicated `setup-*` command configures each coding tool to route through OmniRoute (Claude Code, Codex, Cline, Continue, Cursor, Roo Code, Kilo Code, Crush, Goose, Qwen Code, Aider, OpenCode); `omniroute launch` / `omniroute launch-codex` are zero-config launchers. → [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
-- **🛰️ Remote mode** — drive a remote OmniRoute from any machine with scoped access tokens (`omniroute connect` / `omniroute contexts` / `omniroute tokens`), plus an `omniroute login antigravity` helper that runs Google "native/desktop" OAuth on your own machine and pastes a credential blob into a remote/VPS install (where the loopback redirect is unreachable). → [Remote Mode](docs/guides/REMOTE-MODE.md)
-- **🧭 Smarter auto-routing** — OpenRouter-style `auto/<category>:<tier>` combos (e.g. `auto/coding:fast`, `auto/reasoning:pro`), a **Fusion** strategy (fan out to a panel of models in parallel, then synthesize via a judge), **task-aware routing** (best-fit connection per task type), per-request `X-Route-Model` override, live Arena-ELO + models.dev model intelligence, per-step account allowlists, provider-wildcard combo steps, nested combo-ref execution, sticky weighted selection, `web_search`-aware routing (now with **per-model web-search/web-fetch interception rules**), native **xAI Grok `/v1/responses`** routing, and **per-request Auto-Combo controls** (`X-OmniRoute-Mode` mode-preset override + `X-OmniRoute-Budget` hard USD cost ceiling, scoped to a single request). Embeddings-only and rerank-only models (JinaAI, OpenRouter custom, reranker models…) no longer disappear from the combo builder's model picker. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
-- **🗜️ Pluggable compression** — an async pipeline of **10 composable engines** with Compression Studios, an LLMLingua-2 ONNX engine and a heuristic/SLM two-tier **Ultra**, RTK, delegated Anthropic Context Editing, **Output Styles** (output-axis steering: terse-prose / less-code / terse-CJK), an **adaptive context-budget dial** (escalate only as far as needed to fit the context window), per-request `x-omniroute-compression` control, an opt-in offline eval harness, one-click **Headroom** proxy lifecycle management from the dashboard (Docker sidecar supported), a synthetic **compression playground** (Play lanes + A/B Compare with USD-capped fidelity verdicts), an opt-in **per-step fidelity gate** that rejects a lossy engine before it degrades the prompt, a **best-of-N candidate encoder** (GCF vs TOON — keep whichever is shorter, with an A/B bytes/token table in the studio), the vendored **GCF codec updated to spec v3.2** (nested flattening — deeply-nested payloads go from ~3% to ~32% compression vs JSON), a new **omniglyph** engine (context-as-image, ~10× fewer tokens on the converted block), **CCR ranged/grep/stats retrieval** (pull an exact byte/line slice or summary of a stored block instead of re-expanding it), a unified panel with named profiles + an active-profile selector, an opt-in **per-engine pipeline circuit-breaker**, an opt-in **LLM-tier engine** (a model pass for higher-ratio semantic compression), a **read-lifecycle engine** that collapses superseded file reads, **usage-observed prefix freeze**, a graduated **CCR retrieval-feedback ramp**, a `preserveSystemPrompt` mode enum, and a **drag-reorder pipeline editor** in the studio. → [Compression](docs/compression/COMPRESSION_ENGINES.md)
-- **🕵️ Transparent MITM decrypt (TPROXY)** — capture & translate traffic from CLIs that ignore proxy env vars, with a per-SNI certificate authority and a trust-store installer. → [MITM/TPROXY](docs/security/MITM-TPROXY-DECRYPT.md)
-- **💸 Cost telemetry everywhere** — `X-OmniRoute-*` cost/usage headers on every endpoint (including media), a non-token cost engine, a cache-HIT `X-OmniRoute-Cost-Saved` header, and per-key USD spend quotas. → [API Reference](docs/reference/API_REFERENCE.md)
-- **🧠 Memory you control** — opt-in int8 vector quantization (Qdrant + sqlite-vec), opt-in **typed memory decay** (aged low-value memories fade on a per-type schedule), memory off by default, and a per-request `x-omniroute-no-memory` header. → [Memory](docs/frameworks/MEMORY.md)
-- **🛡️ Security** — a prompt-injection guard across every LLM route (backed by a red-team suite), plus a free DuckDuckGo last-resort web search. → [Guardrails](docs/security/GUARDRAILS.md)
-- **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style audio translation) round out the media API surface. → [API Reference](docs/reference/API_REFERENCE.md)
-- **🌍 Deployment & ops** — reverse-proxy `basePath` deployment (`OMNIROUTE_BASE_PATH`, e.g. serving OmniRoute under `/omniroute/`), browser-language auto-detect on first visit, per-API-key device/connection tracking (IP+UA fingerprint, masked, in-memory only), root-less MITM cert trust for user-namespaced containers (`OMNIROUTE_NO_SUDO`), server-side configured-only / available-only filters on the Free Provider Rankings page, and **Traditional Chinese (zh-TW)** localization for the frontend + CLI. → [Environment](docs/reference/ENVIRONMENT.md)
-- **🤝 More providers & agents** — Cursor Cloud Agent (a 4th cloud agent), CodeBuddy CN (`copilot.tencent.com`), a Google Flow video-generation provider, new gateways **DGrid** and **Pioneer AI** (Fastino Labs), inbound **xAI Grok** translators plus **Grok Build (xAI)** with an OAuth import-token flow, GPT-4 / GPT-4o-mini on the GitHub Copilot provider, multi-model **Factory Droid**, **ZenMux Free** (session-cookie free tier), **Alibaba DashScope** text-to-video (`wan2.7-t2v`), a refreshed 250-provider catalog (OrcaRouter, Wafer AI, OpenAdapter, dit.ai, TokenRouter, …), Vertex AI media generation (speech/transcription/music/video), a first-class **Ollama** local-provider card, the **SenseNova** free Token Plan (chat + text-to-image), one-click account import from CLIProxyAPI (`~/.cli-proxy-api/`), **Claude Sonnet 5** wired end-to-end, a new provider wave (**Kenari**, **SumoPod**, **X5Lab**, **Charm Hyper**, **Nube.sh**, **b.ai**, **Qiniu**, **ModelScope**, **Augment/Auggie CLI**, **ClinePass**, NVIDIA NIM image generation), Codex account import from a raw ChatGPT access token, the **Requesty** gateway (BYOK, ~200 free req/day), **Yuanbao (web)** as a cookie-session provider (DeepSeek V3/R1 + Hunyuan), the **Zed** hosted LLM aggregator (OAuth), **Claude 5 Sonnet** on the Claude Web provider, Kiro **adaptive-thinking reasoning** surfaced as `reasoning_content`, **bulk API-key add for Cloudflare Workers AI**, and **OpenVecta** (AI inference gateway). → [Providers](docs/reference/PROVIDER_REFERENCE.md)
-- **⚡ Local performance & infra** — a one-click local Redis launcher (`omniroute redis up`, plus a dashboard Redis panel), one-click **Cloudflare Workers** and **Deno Deploy** relay deployers wired into the proxy pool, a relay-backend selector (`OMNIROUTE_RELAY_BACKEND=ts|bifrost|auto`) so `/v1/relay` stays the stable surface while choosing the fastest backend internally, **Bifrost** (Go AI-gateway) and **Mux** (agent-orchestration daemon) promoted to first-class embedded/supervised services alongside 9Router/CLIProxyAPI, **Webshare** added as a paid fourth source in the free-proxy provider framework, and **shorthand proxy formats + protocol header mode** for bulk proxy import. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
-
-<br/>
-
-<div align="center">
-
 # 🤖 Compatible CLIs & Coding Agents
 
 > One config — `http://localhost:20128/v1` — and **every** AI IDE or CLI runs on free & low-cost models.
@@ -368,6 +291,7 @@ Result: 4 layers of fallback = zero downtime
   <tr>
     <td align="center" width="120"><a href="https://github.com/anthropics/claude-code"><img src="./public/providers/claude.svg" width="52" alt="Claude Code"/><br/><b>Claude Code</b></a></td>
     <td align="center" width="120"><a href="https://github.com/openai/codex"><img src="./public/providers/codex.svg" width="52" alt="Codex CLI"/><br/><b>Codex CLI</b></a></td>
+    <td align="center" width="120"><a href="https://github.com/google-gemini/gemini-cli"><img src="./public/providers/gemini-cli.svg" width="52" alt="Gemini CLI"/><br/><b>Gemini CLI</b></a></td>
     <td align="center" width="120"><img src="./public/providers/cursor.png" width="52" alt="Cursor"/><br/><b>Cursor</b></td>
     <td align="center" width="120"><img src="./public/providers/copilot.png" width="52" alt="Copilot"/><br/><b>Copilot</b></td>
     <td align="center" width="120"><img src="./public/providers/continue.png" width="52" alt="Continue"/><br/><b>Continue</b></td>
@@ -387,7 +311,7 @@ Result: 4 layers of fallback = zero downtime
 <b>＋ also works with</b> · Cline · Antigravity · Windsurf · AMP · Hermes · Qwen CLI · Roo · Continue · <b>any OpenAI-compatible tool</b>
 </div>
 
-<sub>📖 Per-tool setup for all 24+ tools → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
+<sub>📖 Per-tool setup for all 16+ tools → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
 
 </div>
 
@@ -395,60 +319,28 @@ Result: 4 layers of fallback = zero downtime
 
 <div align="center">
 
-# 🌐 250 AI Providers — 90+ Free
+# 🌐 177 AI Providers — 50+ Free
 
 </div>
 
-> The most complete catalog of any open-source router: **250 providers**, **90+ with a free tier**, **11 free forever**.
+> The most complete catalog of any open-source router: **177 providers**, **50+ with a free tier**, **11 free forever**.
 
 <div align="center">
 
-### 🏢 Every major lab — through one endpoint
-
-<table>
-  <tr>
-    <td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/openai.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/openai.svg" width="40" alt="OpenAI"/></picture><br/><sub>OpenAI</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/claude-color.svg" width="40" alt="Anthropic"/><br/><sub>Anthropic</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/gemini-color.svg" width="40" alt="Gemini"/><br/><sub>Gemini</sub></td>
-    <td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/grok.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/grok.svg" width="40" alt="xAI Grok"/></picture><br/><sub>xAI Grok</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/deepseek-color.svg" width="40" alt="DeepSeek"/><br/><sub>DeepSeek</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/mistral-color.svg" width="40" alt="Mistral"/><br/><sub>Mistral</sub></td>
-  </tr>
-  <tr>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/qwen-color.svg" width="40" alt="Qwen"/><br/><sub>Qwen</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/meta-color.svg" width="40" alt="Meta Llama"/><br/><sub>Meta Llama</sub></td>
-    <td align="center" width="92"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/groq.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/groq.svg" width="40" alt="Groq"/></picture><br/><sub>Groq</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nvidia-color.svg" width="40" alt="NVIDIA"/><br/><sub>NVIDIA</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/minimax-color.svg" width="40" alt="MiniMax"/><br/><sub>MiniMax</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cohere-color.svg" width="40" alt="Cohere"/><br/><sub>Cohere</sub></td>
-  </tr>
-  <tr>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/perplexity-color.svg" width="40" alt="Perplexity"/><br/><sub>Perplexity</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/huggingface-color.svg" width="40" alt="Hugging Face"/><br/><sub>HuggingFace</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/together-color.svg" width="40" alt="Together"/><br/><sub>Together</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/fireworks-color.svg" width="40" alt="Fireworks"/><br/><sub>Fireworks</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cloudflare-color.svg" width="40" alt="Cloudflare"/><br/><sub>Cloudflare</sub></td>
-    <td align="center" width="92"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/baidu-color.svg" width="40" alt="Baidu"/><br/><sub>Baidu</sub></td>
-  </tr>
-</table>
-
-<sub>…and 220+ more — every icon resolves live from the dashboard's provider catalog. 📖 [Provider Reference](docs/reference/PROVIDER_REFERENCE.md)</sub>
-
-<br/>
-
 ### 🆓 Free Forever — $0, no card
 
 <table>
   <tr>
-    <td align="center" width="150"><img src="./public/providers/agentrouter.png" width="44" alt="AgentRouter"/><br/><b>AgentRouter</b><br/><sub>GPT-5, Claude, Gemini<br/>$100 free credits</sub></td>
-    <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/qoder-color.svg" width="44" alt="Qoder AI"/><br/><b>Qoder AI</b><br/><sub>Kimi-K2, DeepSeek-R1<br/>Unlimited FREE</sub></td>
-    <td align="center" width="150"><picture><source media="(prefers-color-scheme:dark)" srcset="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-png@1.91.0/dark/pollinations.png"/><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/pollinations.svg" width="44" alt="Pollinations"/></picture><br/><b>Pollinations</b><br/><sub>GPT-5, Claude, Llama 4<br/>No key needed</sub></td>
-    <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/longcat-color.svg" width="44" alt="LongCat"/><br/><b>LongCat</b><br/><sub>LongCat-2.0<br/>10M tokens one-time (KYC) 🔑</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/AgentRouter-FF6600?style=flat-square" alt="AgentRouter"/><br/><sub>GPT-5, Claude, Gemini<br/>$100 free credits</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/Qoder_AI-6366F1?style=flat-square" alt="Qoder AI"/><br/><sub>Kimi-K2, DeepSeek-R1<br/>Unlimited FREE</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/Pollinations-10B981?style=flat-square" alt="Pollinations"/><br/><sub>GPT-5, Claude, Llama 4<br/>No key needed</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/LongCat-FF7A00?style=flat-square" alt="LongCat"/><br/><sub>Flash-Lite<br/>50M tokens/day 🔥</sub></td>
   </tr>
   <tr>
-    <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cloudflare-color.svg" width="44" alt="Cloudflare AI"/><br/><b>Cloudflare AI</b><br/><sub>50+ models<br/>10K neurons/day</sub></td>
-    <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/nvidia-color.svg" width="44" alt="NVIDIA NIM"/><br/><b>NVIDIA NIM</b><br/><sub>129 models<br/>~40 RPM free</sub></td>
-    <td align="center" width="150"><img src="https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.91.0/icons/cerebras-color.svg" width="44" alt="Cerebras"/><br/><b>Cerebras</b><br/><sub>Qwen3 235B<br/>1M tokens/day</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/Cloudflare_AI-F38020?style=flat-square&logo=cloudflare&logoColor=white" alt="Cloudflare AI"/><br/><sub>50+ models<br/>10K neurons/day</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/Gemini_CLI-8E75B2?style=flat-square&logo=googlegemini&logoColor=white" alt="Gemini CLI"/><br/><sub>gemini-3-flash<br/>180K/mo free</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/NVIDIA_NIM-76B900?style=flat-square&logo=nvidia&logoColor=white" alt="NVIDIA NIM"/><br/><sub>129 models<br/>~40 RPM free</sub></td>
+    <td align="center" width="150"><img src="https://img.shields.io/badge/Cerebras-F15A29?style=flat-square" alt="Cerebras"/><br/><sub>Qwen3 235B<br/>1M tokens/day</sub></td>
   </tr>
 </table>
 
@@ -465,16 +357,16 @@ Result: 4 layers of fallback = zero downtime
 
 > Same app, your machine, your rules. From a global npm install to **your phone** via Termux.
 
-| Platform                  | Install                                  | Highlights                                                |
-| ------------------------- | ---------------------------------------- | --------------------------------------------------------- |
-| 📦 **npm (global)**       | `npm install -g omniroute`               | One command, any OS                                       |
-| 🐳 **Docker**             | `docker run … diegosouzapw/omniroute`    | Multi-arch **AMD64 + ARM64**                              |
-| 🖥️ **Desktop (Electron)** | `npm run electron:build`                 | Native window + system tray — **Windows / macOS / Linux** |
-| 💪 **ARM**                | native `arm64`                           | Raspberry Pi, ARM servers, Apple Silicon                  |
-| 📱 **Android (Termux)**   | `pkg install nodejs && npx -y omniroute` | Runs **on your phone**, 24/7, no root                     |
-| 📲 **PWA**                | "Add to Home Screen"                     | Fullscreen, offline, installable from browser             |
-| 🧩 **OpenCode plugin**    | `@omniroute/opencode-provider`           | Native OpenCode integration                               |
-| 🛠️ **From source**        | `npm install && npm run dev`             | Hack on it, contribute                                    |
+| Platform                  | Install                                      | Highlights                                                |
+| ------------------------- | -------------------------------------------- | --------------------------------------------------------- |
+| 📦 **npm (global)**       | `npm install -g omniroute`                   | One command, any OS                                       |
+| 🐳 **Docker**             | `docker run … diegosouzapw/omniroute`        | Multi-arch **AMD64 + ARM64**                              |
+| 🖥️ **Desktop (Electron)** | `npm run electron:build`                     | Native window + system tray — **Windows / macOS / Linux** |
+| 💪 **ARM**                | native `arm64`                               | Raspberry Pi, ARM servers, Apple Silicon                  |
+| 📱 **Android (Termux)**   | `pkg install nodejs-lts && npx -y omniroute` | Runs **on your phone**, 24/7, no root                     |
+| 📲 **PWA**                | "Add to Home Screen"                         | Fullscreen, offline, installable from browser             |
+| 🧩 **OpenCode plugin**    | `@omniroute/opencode-provider`               | Native OpenCode integration                               |
+| 🛠️ **From source**        | `npm install && npm run dev`                 | Hack on it, contribute                                    |
 
 <sub>📖 [Docker Guide](docs/guides/DOCKER_GUIDE.md) · [Desktop](electron/README.md) · [Termux](docs/guides/TERMUX_GUIDE.md) · [PWA](docs/guides/PWA_GUIDE.md) · [OpenCode](docs/frameworks/OPENCODE.md)</sub>
 
@@ -504,7 +396,7 @@ Result: 4 layers of fallback = zero downtime
 
 </div>
 
-> OmniRoute isn't just a server — it's a **full command-line cockpit** with **80+ commands**, plus open agent protocols so an AI agent can drive OmniRoute **by itself**.
+> OmniRoute isn't just a server — it's a **full command-line cockpit** with **60+ commands**, plus open agent protocols so an AI agent can drive OmniRoute **by itself**.
 
 ### ⌨️ A real CLI (not just `start`)
 
@@ -515,22 +407,6 @@ omniroute setup         # guided first-run wizard
 omniroute doctor        # diagnose providers, ports, native deps
 ```
 
-### 🛰️ Remote mode — run the CLI here, OmniRoute on a VPS
-
-OmniRoute on a server? Drive it from your laptop with the **same CLI**. Log in once
-with a scoped access token; every command then targets the remote.
-
-```bash
-omniroute connect 192.168.0.15            # password → scoped token, saved as a context
-omniroute models list                     # ← runs against the REMOTE server
-omniroute configure codex                 # ← picks a remote model, writes a local Codex profile
-omniroute tokens create --name ci --scope read   # mint narrower tokens for other machines
-omniroute contexts use default            # ← switch back to the local server
-```
-
-Tokens are scoped `read` / `write` / `admin`; process-spawning routes stay loopback-only.
-<sub>📖 [Remote Mode](docs/guides/REMOTE-MODE.md)</sub>
-
 <div align="center">
 
 `providers` · `oauth` · `keys` · `combo` · `nodes` · `models` · `cache` · `compression` · `cost` · `usage` · `quota` · `health` · `resilience` · `telemetry` · `logs` · `audit` · `mcp` · `a2a` · `cloud` · `memory` · `skills` · `eval` · `tunnel` · `backup` · `sync` · `webhooks` · `policy` · `pricing` · `translator` · `simulate` …
@@ -544,9 +420,9 @@ Expose OmniRoute over **MCP** or **A2A** and any capable agent gets the keys to
 | Protocol           | Endpoint                                        | Use it for                                             |
 | ------------------ | ----------------------------------------------- | ------------------------------------------------------ |
 | 🧰 **MCP (stdio)** | `omniroute --mcp`                               | Plug into Claude Desktop, Cursor, any MCP client       |
-| 🌊 **MCP (HTTP)**  | `http://localhost:20128/api/mcp/stream`         | Remote MCP — **94 tools**, 30 scopes, full audit trail |
+| 🌊 **MCP (HTTP)**  | `http://localhost:20128/api/mcp/stream`         | Remote MCP — **37 tools**, 13 scopes, full audit trail |
 | 📡 **MCP (SSE)**   | `http://localhost:20128/api/mcp/sse`            | Streaming MCP transport                                |
-| 🤝 **A2A**         | `http://localhost:20128/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 6 skills       |
+| 🤝 **A2A**         | `http://localhost:20128/.well-known/agent.json` | Agent-to-agent, **JSON-RPC 2.0** + SSE, 5 skills       |
 
 ```bash
 # Give Claude Code the full OmniRoute toolset over MCP:
@@ -563,26 +439,7 @@ claude mcp add-server omniroute --type http --url http://localhost:20128/api/mcp
 
 </div>
 
-> **Why use many tokens when few tokens do the trick?** Every request passes through OmniRoute's compression pipeline **transparently** — no client changes. It's now a **stack of 10 composable engines** that run in order and mix & match per routing combo — building on ideas from [RTK](https://github.com/rtk-ai/rtk), [Caveman](https://github.com/JuliusBrussee/caveman) (⭐ 78K+), [LLMLingua-2](https://github.com/microsoft/LLMLingua), and [Troglodita](https://github.com/leninejunior/troglodita) (PT-BR).
-
-### 🧱 The 10-engine stack
-
-Engines run in pipeline order; each is independently toggleable and configurable per combo:
-
-| #   | Engine            | What it does                                                        |
-| --- | ----------------- | ------------------------------------------------------------------- |
-| 1   | **Session-Dedup** | Drops content repeated across turns (content-addressed, cross-turn) |
-| 2   | **CCR**           | Archives large blocks behind retrieve markers, fetched on demand    |
-| 3   | **RTK**           | Smart tool-result filtering, dedup & truncation (command-aware)     |
-| 4   | **Headroom**      | Lossless tabular compaction of homogeneous JSON arrays, flat or nested (~30%), via a vendored **GCF** codec (spec v3.2) |
-| 5   | **Relevance**     | Extractive sentence scoring against the last user query             |
-| 6   | **Caveman**       | Rule-based prose compression (~65–75% on output)                    |
-| 7   | **LLMLingua-2**   | ML semantic pruning via MobileBERT ONNX — code-safe, async          |
-| 8   | **Lite**          | Whitespace + image-URL trimming (latency-light baseline)            |
-| 9   | **Aggressive**    | Summarization + progressive aging of old turns                      |
-| 10  | **Ultra**         | Heuristic token pruning with an optional small-model (SLM) tier     |
-
-Code blocks, URLs and structured data are **always preserved** byte-perfect. **One-click presets** combine the engines:
+> **Why use many token when few token do trick?** Every request passes through OmniRoute's compression pipeline **transparently** — no client changes. It stacks ideas from [RTK](https://github.com/rtk-ai/rtk), [Caveman](https://github.com/JuliusBrussee/caveman) (⭐ 51K+), and [Troglodita](https://github.com/leninejunior/troglodita) (PT-BR).
 
 | Mode                           | Savings    | Best for                    |
 | ------------------------------ | ---------- | --------------------------- |
@@ -611,10 +468,10 @@ Code blocks, URLs and structured data are **always preserved** byte-perfect. **O
 
 <br/>
 
-### 📖 How it works — pipeline, architecture & savings math
+### 📖 How it works — pipeline, architecture & savings math</b></summary>
 
 ```
-Client (10,000 tok) ──▶ OmniRoute Compression (10 engines) ──▶ Provider (~1,080 tok, up to 95% saved)
+Client (10,000 tok) ──▶ OmniRoute Compression (7 options) ──▶ Provider (~1,080 tok, up to 95% saved)
 ```
 
 Default stacked combo runs `RTK → Caveman`. When both act on the same tool/context payload, savings compound:
@@ -625,20 +482,7 @@ average  = 1 − (1 − 0.80) × (1 − 0.46) = 89.2%
 range    = 78.4 – 94.6%
 ```
 
-Code blocks, URLs, JSON and structured data are **always protected** by the preservation engine.
-
-### 🎚️ Beyond the engines — output styles, the adaptive dial & per-request control
-
-The 10 engines above shrink what goes **in**. Three more layers shape **how**, **when**, and what comes **out**:
-
-- **🪄 Output Styles** _(output-axis steering)_ — inject deterministic, cache-safe response-shaping instructions; combinable, each at `lite` / `full` / `ultra` intensity. Adding a style is a one-line registry entry:
-  - **Terse prose** — drop filler / articles / hedging; keep technical substance exact.
-  - **Less code** — "lazy senior dev" YAGNI: smallest working change, no unrequested scaffolding.
-  - **Terse CJK (文言)** — classical-Chinese ultra-terse style (locale-gated to `zh`).
-- **🎯 Adaptive context-budget** _(the dial)_ — instead of one on/off token threshold, escalate the cheapest, most-lossless engines only as far as needed to **fit the model's context window**. Policy: `reserve-output` (default, model-aware) · `percentage` · `absolute`. Mode: `floor` (guarantee fit) · `replace-autotrigger` (your explicit choice wins) · `off` (legacy threshold).
-- **🎛️ Where compression is decided** _(precedence, high → low)_ — per-request `x-omniroute-compression` header › routing-combo override › active named profile › adaptive / auto-trigger › panel default › off. The applied plan echoes back in the `X-OmniRoute-Compression: <mode>; source=<source>` response header.
-
-Auto-trigger by token threshold, flip on the adaptive dial, pin a named profile, set a one-off per request, or assign a pipeline per routing combo — whichever fits the workload. An opt-in offline **eval harness** (`npm run eval:compression`) scores fidelity vs. savings on a pinned corpus before you promote a change.
+Code blocks, URLs, JSON and structured data are **always protected** by the preservation engine. Auto-trigger compression by token threshold, or assign a compression pipeline per routing combo.
 
 📖 [`COMPRESSION_GUIDE.md`](docs/compression/COMPRESSION_GUIDE.md) · [`RTK_COMPRESSION.md`](docs/compression/RTK_COMPRESSION.md) · [`COMPRESSION_ENGINES.md`](docs/compression/COMPRESSION_ENGINES.md)
 
@@ -661,7 +505,7 @@ Dashboard at `http://localhost:20128` · API at `http://localhost:20128/v1`.
 
 **2) Connect a FREE provider (no signup)**
 
-Dashboard → **Providers** → connect **Kiro AI** (free Claude, ~50 credits/month per account) or **OpenCode Free** (no auth) → done.
+Dashboard → **Providers** → connect **Kiro AI** (free Claude unlimited) or **OpenCode Free** (no auth) → done.
 
 **3) Point your coding tool**
 
@@ -694,7 +538,7 @@ Use these only for clients that cannot attach `Authorization: Bearer ...`. Heade
 
 <br/>
 
-## 📦 More install methods — Docker, source, pnpm, Arch
+## 📦 More install methods — Docker, source, pnpm, Arch</b></summary>
 
 **🐳 Docker**
 
@@ -713,7 +557,7 @@ PORT=20128 npm run dev
 **📦 pnpm**
 
 ```bash
-pnpm add -g omniroute@latest --allow-build=better-sqlite3 --allow-build=@swc/core && omniroute
+pnpm install -g omniroute && pnpm approve-builds -g && omniroute
 ```
 
 **🐧 Arch Linux (AUR)**
@@ -751,23 +595,7 @@ podman compose --profile base up -d
 
 📖 [Podman Guide](contrib/podman/README.md) — Quadlet setup, podman-compose, Quadlet.
 
-**⚡ Faster / leaner install (skip the native build)**
-
-The native SQLite engine (`better-sqlite3`) is an **optional** dependency, so a global
-install never blocks on compiling from source: it uses a prebuilt binary when one matches
-your platform/Node, and otherwise falls back transparently to a pure-JS engine
-(`node:sqlite` on Node 22+, else the bundled `sql.js` WASM) — no build tools required.
-
-To skip the post-install native warm-up entirely (CI, headless, or slow machines):
-
-```bash
-OMNIROUTE_SKIP_POSTINSTALL=1 npm install -g omniroute   # CI=1 also skips it
-```
-
-For the fastest installs prefer **pnpm** (content-addressed store + hard links — see above).
-For a dashboard-free, headless runtime use the Docker `base` profile (above) or the
-[Termux guide](docs/guides/TERMUX_GUIDE.md). The CLI and the web dashboard are served by the
-same process on one port, so there is no separate CLI-only package today.
+</details>
 
 <br/>
 
@@ -823,16 +651,16 @@ same process on one port, so there is no separate CLI-only package today.
 
 **The $0 Free Stack — combine into one unbreakable combo:**
 
-| Provider          | Prefix      | Free models                                     | Quota              |
-| ----------------- | ----------- | ----------------------------------------------- | ------------------ |
-| **Kiro**          | `kr/`       | Claude Sonnet 4.5, Haiku 4.5, Opus 4.6          | 50 credits/mo      |
-| **Qoder**         | `if/`       | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 | ♾️ Unlimited       |
-| **Qwen**          | `qw/`       | qwen3-coder-plus/flash/next                     | ♾️ Unlimited       |
-| **Pollinations**  | `pol/`      | GPT-5, Claude, Gemini, DeepSeek, Llama 4        | No key needed      |
-| **LongCat**       | `lc/`       | LongCat-2.0                                     | 10M one-time (KYC) |
-| **Cloudflare AI** | `cf/`       | 50+ models                                      | 10K neurons/day    |
-| **NVIDIA NIM**    | `nvidia/`   | 129 models                                      | ~40 RPM            |
-| **Cerebras**      | `cerebras/` | Qwen3 235B, GPT-OSS 120B                        | 1M tok/day         |
+| Provider          | Prefix      | Free models                                     | Quota             |
+| ----------------- | ----------- | ----------------------------------------------- | ----------------- |
+| **Kiro**          | `kr/`       | Claude Sonnet 4.5, Haiku 4.5, Opus 4.6          | 50 credits/mo     |
+| **Qoder**         | `if/`       | kimi-k2-thinking, qwen3-coder-plus, deepseek-r1 | ♾️ Unlimited      |
+| **Qwen**          | `qw/`       | qwen3-coder-plus/flash/next                     | ♾️ Unlimited      |
+| **Pollinations**  | `pol/`      | GPT-5, Claude, Gemini, DeepSeek, Llama 4        | No key needed     |
+| **LongCat**       | `lc/`       | LongCat-Flash-Lite                              | 50M tokens/day 🔥 |
+| **Cloudflare AI** | `cf/`       | 50+ models                                      | 10K neurons/day   |
+| **NVIDIA NIM**    | `nvidia/`   | 129 models                                      | ~40 RPM           |
+| **Cerebras**      | `cerebras/` | Qwen3 235B, GPT-OSS 120B                        | 1M tok/day        |
 
 > 💡 The dashboard "cost" is a **savings tracker**, not a bill — OmniRoute never charges you. A "$290 total cost" using free models means **$290 saved**.
 
@@ -848,10 +676,10 @@ same process on one port, so there is no separate CLI-only package today.
 **$0 forever:**
 
 ```
-1. kr/claude-sonnet-4.5   (Kiro — ~50 credits/mo per acct)
+1. kr/claude-sonnet-4.5   (Kiro — unlimited)
 2. if/kimi-k2-thinking    (Qoder — unlimited)
 3. pol/gpt-5              (Pollinations — no key)
-4. lc/LongCat-2.0         (10M one-time backup, KYC)
+4. lc/longcat-flash-lite  (50M tok/day backup)
 Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 ```
 
@@ -881,13 +709,11 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 
 <br/>
 
-**Routing:** 18 strategies · task-aware smart routing · thinking budget controls · wildcard routing · system prompt injection.
+**Routing:** 14 strategies · task-aware smart routing · thinking budget controls · wildcard routing · system prompt injection.
 **Compatibility:** OpenAI ↔ Claude ↔ Gemini ↔ Responses API · auto OAuth refresh (PKCE, 8 providers) · multi-account round-robin · Batch + Files API · live OpenAPI 3.0.
-**Protocols:** MCP (94 tools, 3 transports, 30 scopes) · A2A (JSON-RPC 2.0, SSE, 6 skills) · ACP · cloud agents (Codex, Cursor, Devin, Jules).
-**Plugins:** custom plugin marketplace (system-configured registry URL with SSRF-guarded fetch) · install / enable / disable · Notion + Obsidian knowledge-base integrations (WebDAV file server, vault search, note CRUD).
-**Embedded services:** one-click install & lifecycle management of local sidecar services (CLIProxy, NineRouter).
+**Protocols:** MCP (37 tools, 3 transports, 13 scopes) · A2A (JSON-RPC 2.0, SSE, skills) · ACP · cloud agents (Codex, Devin, Jules).
 **Quality & Ops:** built-in **Evals** (golden-set: exact/contains/regex/custom) · guardrails (PII, injection, vision) · health dashboard · p50/p95/p99 telemetry · webhooks · compliance audit.
-**AI Agent Skills:** drop-in markdown manifests — point any agent at a `skills/*/SKILL.md` manifest. 43 skills available.
+**AI Agent Skills:** drop-in markdown manifests — point any agent at `skills/omniroute/SKILL.md`. 10 skills available.
 
 📖 [MCP Server](open-sse/mcp-server/README.md) · [A2A Server](src/lib/a2a/README.md) · [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) · [Features Gallery](docs/guides/FEATURES.md)
 
@@ -905,9 +731,9 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 | `DATA_DIR`        | `~/.omniroute` | Database & config storage        |
 
 **Will I be charged by OmniRoute?** No — it's free, open-source software on your machine. You only pay paid providers directly. OmniRoute has no billing system.
-**Are FREE providers really unlimited?** Mostly — Qoder, Pollinations, LongCat, and Cloudflare are free with no per-account credit cap. Kiro is free too but capped at ~50 credits/month per account. Stack multiple free providers in a combo and auto-fallback keeps you serving for $0.
+**Are FREE providers really unlimited?** Yes — Kiro, Qoder, Pollinations, LongCat, Cloudflare. No catch.
 **Will compression hurt quality?** No — it only compresses the **input**; code, URLs, JSON are always protected.
-**Does it work where AI is blocked?** Yes — 3-level proxy + 1proxy marketplace reach all 250 providers.
+**Does it work where AI is blocked?** Yes — 3-level proxy + 1proxy marketplace reach all 177 providers.
 
 📖 [User Guide](docs/guides/USER_GUIDE.md) · [API Reference](docs/reference/API_REFERENCE.md) · [Environment Config](docs/reference/ENVIRONMENT.md)
 
@@ -925,7 +751,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 | OAuth token expired                       | Auto-refreshed; if stuck, delete + re-auth in Providers       |
 | `unsupported_country_region_territory`    | Configure proxy in Settings → Proxy                           |
 | Docker SQLite locks                       | Use `--stop-timeout 40` for clean WAL checkpoint              |
-| Node runtime errors                       | Use Node `>=22.0.0 <23` or `>=24.0.0 <27`                     |
+| Node runtime errors                       | Use Node `>=20.20.2 <21`, `>=22.22.2 <23`, or `>=24 <25`      |
 
 🐛 **Reporting a bug?** Run `npm run system-info` and attach `system-info.txt`. 📖 [`docs/guides/TROUBLESHOOTING.md`](docs/guides/TROUBLESHOOTING.md)
 
@@ -969,15 +795,15 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 
 </div>
 
-- **Runtime**: Node.js 22.x or 24.x LTS (24 LTS recommended) — `>=22.0.0 <23 || >=24.0.0 <27`
-- **Language**: TypeScript 6.0 — **100% TypeScript** across `src/` and `open-sse/` (zero `any` in core modules since v2.0)
+- **Runtime**: Node.js 20.20.2+, 22.22.2+, or 24.x LTS (24 LTS recommended)
+- **Language**: TypeScript 5.9 — **100% TypeScript** across `src/` and `open-sse/` (zero `any` in core modules since v2.0)
 - **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
 - **Database**: better-sqlite3 (SQLite) + LowDB (JSON legacy) — domain state, proxy logs, MCP audit, routing decisions, memory, skills
 - **Schemas**: Zod (MCP tool I/O validation, API contracts)
 - **Protocols**: MCP (stdio/HTTP) + A2A v0.3 (JSON-RPC 2.0 + SSE)
 - **Streaming**: Server-Sent Events (SSE) + WebSocket bridge (`/v1/ws`)
 - **Auth**: OAuth 2.0 (PKCE) + JWT + API Keys + MCP Scoped Authorization
-- **Testing**: Node.js test runner + Vitest (**21,000+ test cases** across 2,586 files — unit, integration, E2E, security, ecosystem)
+- **Testing**: Node.js test runner + Vitest (**4,690+ test cases** across 517 files — unit, integration, E2E, security, ecosystem)
 - **Platforms**: Desktop (Electron), Android (Termux), PWA (any browser)
 - **CI/CD**: GitHub Actions (auto npm publish + Docker Hub on release)
 - **Website**: [omniroute.online](https://omniroute.online)
@@ -995,56 +821,63 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 
 ### 📘 Getting Started
 
-- **[User Guide](docs/guides/USER_GUIDE.md)** — Providers, combos, CLI integration, deployment
-- **[Setup Guide](docs/guides/SETUP_GUIDE.md)** — Full install methods, CLI tool configs, protocol setup, timeout tuning
-- **[CLI Tools Guide](docs/reference/CLI-TOOLS.md)** — Per-tool setup for Claude Code, Codex, Cursor, Cline, OpenClaw, Kilo, Copilot
-- **[Remote Mode](docs/guides/REMOTE-MODE.md)** — Drive a remote OmniRoute (VPS) from your laptop CLI via scoped access tokens
-- **[Claude Code Config](docs/guides/CLAUDE-CODE-CONFIGURATION.md)** — Point Claude Code at OmniRoute (local/remote) with `launch` + per-model profiles
-- **[Quick Start](README.md#-quick-start)** — 3-step install → connect → configure
+| Document                              | Description                                                                   |
+| ------------------------------------- | ----------------------------------------------------------------------------- |
+| [User Guide](docs/guides/USER_GUIDE.md)      | Providers, combos, CLI integration, deployment                                |
+| [Setup Guide](docs/guides/SETUP_GUIDE.md)    | Full install methods, CLI tool configs, protocol setup, timeout tuning        |
+| [CLI Tools Guide](docs/reference/CLI-TOOLS.md) | Per-tool setup for Claude Code, Codex, Cursor, Cline, OpenClaw, Kilo, Copilot |
+| [Quick Start](README.md#-quick-start) | 3-step install → connect → configure                                          |
 
 ### 🔧 Operations & Deployment
 
-- **[Docker Guide](docs/guides/DOCKER_GUIDE.md)** — Docker run, Compose profiles, Caddy HTTPS, tunnels, image tags
-- **[Podman Guide](contrib/podman/README.md)** — Quadlet systemd integration, podman-compose, SELinux
-- **[VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md)** — Complete guide: VM + nginx + Cloudflare setup
-- **[Fly.io Deployment](docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md)** — Deploy to Fly.io with persistent storage
-- **[Termux Guide](docs/guides/TERMUX_GUIDE.md)** — Run OmniRoute on Android via Termux
-- **[PWA Guide](docs/guides/PWA_GUIDE.md)** — Progressive Web App install, caching, architecture
-- **[Uninstall Guide](docs/guides/UNINSTALL.md)** — Clean removal for all install methods
-- **[Environment Config](docs/reference/ENVIRONMENT.md)** — Complete `.env` variables and references
+| Document                                             | Description                                                    |
+| ---------------------------------------------------- | -------------------------------------------------------------- |
+| [Docker Guide](docs/guides/DOCKER_GUIDE.md)                 | Docker run, Compose profiles, Caddy HTTPS, tunnels, image tags |
+| [Podman Guide](contrib/podman/README.md)                   | Quadlet systemd integration, podman-compose, SELinux           |
+| [VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md)         | Complete guide: VM + nginx + Cloudflare setup                  |
+| [Fly.io Deployment](docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md) | Deploy to Fly.io with persistent storage                       |
+| [Termux Guide](docs/guides/TERMUX_GUIDE.md)                 | Run OmniRoute on Android via Termux                            |
+| [PWA Guide](docs/guides/PWA_GUIDE.md)                       | Progressive Web App install, caching, architecture             |
+| [Uninstall Guide](docs/guides/UNINSTALL.md)                 | Clean removal for all install methods                          |
+| [Environment Config](docs/reference/ENVIRONMENT.md)            | Complete `.env` variables and references                       |
 
 ### 🧠 Features & Architecture
 
-- **[Architecture](docs/architecture/ARCHITECTURE.md)** — System architecture, data flow, and internals
-- **[Compression Guide](docs/compression/COMPRESSION_GUIDE.md)** — 7-option pipeline: off / lite / standard / aggressive / ultra / RTK / stacked
-- **[RTK Compression](docs/compression/RTK_COMPRESSION.md)** — Command-output compression, filters, trust, verify, raw-output recovery
-- **[Compression Engines](docs/compression/COMPRESSION_ENGINES.md)** — Caveman, RTK, stacked pipelines, dashboard/API/MCP surfaces
-- **[Compression Rules Format](docs/compression/COMPRESSION_RULES_FORMAT.md)** — JSON rule-pack schemas for Caveman and RTK filters
-- **[Compression Language Packs](docs/compression/COMPRESSION_LANGUAGE_PACKS.md)** — Language detection and Caveman rule-pack authoring
-- **[Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)** — Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing
-- **[Auto-Combo Engine](docs/routing/AUTO-COMBO.md)** — 12-factor scoring, mode packs, self-healing
-- **[Proxy Guide](docs/ops/PROXY_GUIDE.md)** — 3-level proxy system, 1proxy marketplace, registry CRUD
-- **[Free Tiers](docs/reference/FREE_TIERS.md)** — 25+ free API providers consolidated directory
-- **[Features Gallery](docs/guides/FEATURES.md)** — Visual dashboard tour with screenshots
-- **[Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md)** — Beginner-friendly codebase walkthrough
+| Document                                                         | Description                                                                   |
+| ---------------------------------------------------------------- | ----------------------------------------------------------------------------- |
+| [Architecture](docs/architecture/ARCHITECTURE.md)                          | System architecture, data flow, and internals                                 |
+| [Compression Guide](docs/compression/COMPRESSION_GUIDE.md)                | 7-option pipeline: off / lite / standard / aggressive / ultra / RTK / stacked |
+| [RTK Compression](docs/compression/RTK_COMPRESSION.md)                    | Command-output compression, filters, trust, verify, raw-output recovery       |
+| [Compression Engines](docs/compression/COMPRESSION_ENGINES.md)            | Caveman, RTK, stacked pipelines, dashboard/API/MCP surfaces                   |
+| [Compression Rules Format](docs/compression/COMPRESSION_RULES_FORMAT.md)  | JSON rule-pack schemas for Caveman and RTK filters                            |
+| [Compression Language Packs](docs/compression/COMPRESSION_LANGUAGE_PACKS.md) | Language detection and Caveman rule-pack authoring                         |
+| [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md)                 | Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing        |
+| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md)                           | 6-factor scoring, mode packs, self-healing                                    |
+| [Proxy Guide](docs/ops/PROXY_GUIDE.md)                                    | 3-level proxy system, 1proxy marketplace, registry CRUD                       |
+| [Free Tiers](docs/reference/FREE_TIERS.md)                                | 25+ free API providers consolidated directory                                 |
+| [Features Gallery](docs/guides/FEATURES.md)                               | Visual dashboard tour with screenshots                                        |
+| [Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md)      | Beginner-friendly codebase walkthrough                                        |
 
 ### 🤖 Protocols & APIs
 
-- **[API Reference](docs/reference/API_REFERENCE.md)** — All endpoints with examples
-- **[OpenAPI Spec](docs/openapi.yaml)** — OpenAPI 3.0 specification
-- **[MCP Server](open-sse/mcp-server/README.md)** — 95 MCP tools, IDE configs, Python/TS/Go clients
-- **[MCP Server Guide](docs/frameworks/MCP-SERVER.md)** — MCP installation, transports, and tool reference
-- **[A2A Server](src/lib/a2a/README.md)** — JSON-RPC 2.0 protocol, skills, streaming, task mgmt
-- **[A2A Server Guide](docs/frameworks/A2A-SERVER.md)** — A2A agent card, tasks, skills, and streaming
+| Document                                    | Description                                         |
+| ------------------------------------------- | --------------------------------------------------- |
+| [API Reference](docs/reference/API_REFERENCE.md)         | All endpoints with examples                         |
+| [OpenAPI Spec](docs/reference/openapi.yaml)               | OpenAPI 3.0 specification                           |
+| [MCP Server](open-sse/mcp-server/README.md) | 29 MCP tools, IDE configs, Python/TS/Go clients     |
+| [MCP Server Guide](docs/frameworks/MCP-SERVER.md)         | MCP installation, transports, and tool reference    |
+| [A2A Server](src/lib/a2a/README.md)         | JSON-RPC 2.0 protocol, skills, streaming, task mgmt |
+| [A2A Server Guide](docs/frameworks/A2A-SERVER.md)         | A2A agent card, tasks, skills, and streaming        |
 
 ### 📋 Project & Quality
 
-- **[Contributing](CONTRIBUTING.md)** — Development setup and guidelines
-- **[Changelog](CHANGELOG.md)** — Full per-version release history
-- **[Security Policy](SECURITY.md)** — Vulnerability reporting and security practices
-- **[i18n Guide](docs/guides/I18N.md)** — 40+ language support, translation workflow, RTL
-- **[Release Checklist](docs/ops/RELEASE_CHECKLIST.md)** — Pre-release validation steps
-- **[Coverage Plan](docs/ops/COVERAGE_PLAN.md)** — Test coverage strategy and 21,000+ test suite
+| Document                                       | Description                                     |
+| ---------------------------------------------- | ----------------------------------------------- |
+| [Contributing](CONTRIBUTING.md)                | Development setup and guidelines                |
+| [Security Policy](SECURITY.md)                 | Vulnerability reporting and security practices  |
+| [i18n Guide](docs/guides/I18N.md)                     | 40+ language support, translation workflow, RTL |
+| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps                    |
+| [Coverage Plan](docs/ops/COVERAGE_PLAN.md)         | Test coverage strategy and 4,690+ test suite    |
 
 <br/>
 
@@ -1058,23 +891,23 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
   <tr>
     <td align="center" width="160">
       <a href="https://github.com/oyi77">
-        <img src="https://github.com/oyi77.png" width="40" style="border-radius:50%" alt="oyi77"/><br/>
+        <img src="https://github.com/oyi77.png" width="80" style="border-radius:50%" alt="oyi77"/><br/>
         <b>oyi77</b>
       </a><br/>
-      <sub>🥇 189 commits • +155K lines</sub><br/>
+      <sub>🥇 190 commits • +72K lines</sub><br/>
       <sub>Analytics engine, SQL aggregations,<br/>proxy marketplace, test coverage</sub>
     </td>
     <td align="center" width="160">
       <a href="https://github.com/christopher-s">
-        <img src="https://github.com/christopher-s.png" width="40" style="border-radius:50%" alt="Chris Staley"/><br/>
+        <img src="https://github.com/christopher-s.png" width="80" style="border-radius:50%" alt="Chris Staley"/><br/>
         <b>Chris Staley</b>
       </a><br/>
-      <sub>🥈 70 commits • +5.7K lines</sub><br/>
+      <sub>🥈 72 commits • +5.7K lines</sub><br/>
       <sub>SSE stream hardening, Responses API,<br/>Gemini pagination, test regression fixes</sub>
     </td>
     <td align="center" width="160">
       <a href="https://github.com/zenobit">
-        <img src="https://github.com/zenobit.png" width="40" style="border-radius:50%" alt="zenobit"/><br/>
+        <img src="https://github.com/zenobit.png" width="80" style="border-radius:50%" alt="zenobit"/><br/>
         <b>zenobit</b>
       </a><br/>
       <sub>🥉 62 commits • +24K lines</sub><br/>
@@ -1082,28 +915,20 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
     </td>
     <td align="center" width="160">
       <a href="https://github.com/rdself">
-        <img src="https://github.com/rdself.png" width="40" style="border-radius:50%" alt="R.D. & Randi"/><br/>
+        <img src="https://github.com/rdself.png" width="80" style="border-radius:50%" alt="R.D. & Randi"/><br/>
         <b>R.D. & Randi</b>
       </a><br/>
-      <sub>🏅 108 commits • +30K lines</sub><br/>
+      <sub>🏅 107 commits • +28K lines</sub><br/>
       <sub>Endpoints page, tunnel integrations,<br/>Docker workflows, A2A status, compression UI</sub>
     </td>
     <td align="center" width="160">
       <a href="https://github.com/benzntech">
-        <img src="https://github.com/benzntech.png" width="40" style="border-radius:50%" alt="benzntech"/><br/>
+        <img src="https://github.com/benzntech.png" width="80" style="border-radius:50%" alt="benzntech"/><br/>
         <b>benzntech</b>
       </a><br/>
-      <sub>🏅 22 commits • +7.5K lines</sub><br/>
+      <sub>🏅 20 commits • +7.5K lines</sub><br/>
       <sub>Electron desktop app, auto-updater,<br/>release build workflows, cross-platform CI</sub>
     </td>
-    <td align="center" width="160">
-      <a href="https://github.com/herjarsa">
-        <img src="https://github.com/herjarsa.png" width="40" style="border-radius:50%" alt="herjarsa"/><br/>
-        <b>herjarsa</b>
-      </a><br/>
-      <sub>🏅 21 commits • +6K lines</sub><br/>
-      <sub>Zero-latency combos, vision-bridge auto-routing,<br/>catalog context-length, resilience 429 hints</sub>
-    </td>
   </tr>
 </table>
 
@@ -1117,11 +942,11 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
 
 <div align="center">
 
-## 👥 280+ Contributors
+## 👥 Contributors
 
 </div>
 
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=200&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
+[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=100&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
 
 ### How to Contribute
 
@@ -1146,13 +971,14 @@ gh release create v3.8.2 --title "v3.8.2" --generate-notes
 
 ## 📊 Stars
 
-<a href="https://www.star-history.com/?repos=diegosouzapw%2FOmniRoute&type=date&legend=top-left">
+<a href="https://www.star-history.com/?repos=diegosouzapw%2Fomniroute&type=date&legend=top-left">
  <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=diegosouzapw/OmniRoute&type=date&theme=dark&legend=top-left&sealed_token=XP_ycEjv7s31p1edvhsMOXry51OWYsUjDRWjflSG7jQKRpO9hPGg7i_EHvwhI6QtrARTMH-YGjJhi8sumRYflEJD0DPlH_MMHjizhBYCX8fbHFrHEiNvVA" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=diegosouzapw/OmniRoute&type=date&legend=top-left&sealed_token=XP_ycEjv7s31p1edvhsMOXry51OWYsUjDRWjflSG7jQKRpO9hPGg7i_EHvwhI6QtrARTMH-YGjJhi8sumRYflEJD0DPlH_MMHjizhBYCX8fbHFrHEiNvVA" />
-   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=diegosouzapw/OmniRoute&type=date&legend=top-left&sealed_token=XP_ycEjv7s31p1edvhsMOXry51OWYsUjDRWjflSG7jQKRpO9hPGg7i_EHvwhI6QtrARTMH-YGjJhi8sumRYflEJD0DPlH_MMHjizhBYCX8fbHFrHEiNvVA" />
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=diegosouzapw/omniroute&type=date&theme=dark&legend=top-left" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=diegosouzapw/omniroute&type=date&legend=top-left" />
+   <img alt="Star History Chart" src="https://api.star-history.com/chart?repos=diegosouzapw/omniroute&type=date&legend=top-left" />
  </picture>
 </a>
+</div>
 
 <br/>
 
@@ -1177,84 +1003,15 @@ gh release create v3.8.2 --title "v3.8.2" --generate-notes
 
 </div>
 
-OmniRoute stands on the shoulders of giants. It started as a fork of **[9router](https://github.com/decolua/9router)** and a TypeScript port of the Go project **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — and from there, every subsystem below was inspired by an open-source project that got there first. Each one shaped a concrete piece of OmniRoute. This is our thank-you to all of them. 🙏
+Special thanks to **[9router](https://github.com/decolua/9router)** by **[decolua](https://github.com/decolua)** — the original project that inspired this fork. OmniRoute builds upon that incredible foundation with additional features, multi-modal APIs, and a full TypeScript rewrite.
 
-> ⭐ star counts as of June 2026 — go give these projects a star.
+Special thanks to **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** by **[router-for-me](https://github.com/router-for-me)** — the original Go implementation that inspired this JavaScript port.
 
-### 🧬 Lineage & gateway
+Special thanks to **[Caveman](https://github.com/JuliusBrussee/caveman)** by **[JuliusBrussee](https://github.com/JuliusBrussee)** (⭐ 51K+) — the viral "why use many token when few token do trick" project whose caveman-speak compression philosophy inspired OmniRoute's standard compression mode and 30+ filler/condensation regex rules.
 
-| Project                                                                         |    ⭐ | How it inspired OmniRoute                                                                                                             |
-| ------------------------------------------------------------------------------- | ----: | ------------------------------------------------------------------------------------------------------------------------------------- |
-| **[9router](https://github.com/decolua/9router)** · decolua                     | 19.0k | The original project this fork is built on — extended here with multi-modal APIs and a full TypeScript rewrite.                       |
-| **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** · router-for-me | 38.8k | The Go implementation that inspired this JavaScript / TypeScript port.                                                                |
-| **[LiteLLM](https://github.com/BerriAI/litellm)** · BerriAI                     | 52.1k | The AI gateway whose public pricing dataset feeds our cost-tracking sync and whose provider-normalization model informed our routing. |
+Special thanks to **[RTK - Rust Token Killer](https://github.com/rtk-ai/rtk)** by **[RTK AI](https://github.com/rtk-ai)** — the high-performance command-output compression project whose terminal, build, test, git, and tool-output filtering model inspired OmniRoute's RTK engine, JSON filter DSL, raw-output recovery, and stacked RTK → Caveman compression pipeline.
 
-### 🗜️ Context & token compression — engines
-
-| Project                                                                       |    ⭐ | How it inspired OmniRoute                                                                                                                                                                                |
-| ----------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **[Caveman](https://github.com/JuliusBrussee/caveman)** · JuliusBrussee       | 78.2k | The viral "why use many token when few token do trick" project — its caveman-speak philosophy powers our standard compression mode and 30+ filler/condensation rules.                                    |
-| **[RTK – Rust Token Killer](https://github.com/rtk-ai/rtk)** · rtk-ai         | 67.3k | High-performance command-output compression — inspired our RTK engine, JSON filter DSL, raw-output recovery and the stacked RTK → Caveman pipeline.                                                      |
-| **[headroom](https://github.com/headroomlabs-ai/headroom)** · headroomlabs-ai | 54.5k | Reversible context-compression (SmartCrusher) — inspired our `headroom` engine and the `ccr` retrieve-marker pattern.                                                                                    |
-| **[LLMLingua](https://github.com/microsoft/LLMLingua)** · Microsoft           |  6.4k | Prompt-compression research (LLMLingua / LLMLingua-2) — inspired our async, code-safe, fail-open `llmlingua` engine.                                                                                     |
-| **[llmlingua-2-js](https://github.com/atjsh/llmlingua-2-js)** · atjsh         |    28 | The JS/ONNX port (MobileBERT / XLM-RoBERTa) used as the worker-thread backend for our LLMLingua engine.                                                                                                  |
-| **[Troglodita](https://github.com/leninejunior/troglodita)** · Lenine Júnior  |    16 | PT-BR token compression — powers our pt-BR language pack: pleonasm reduction and filler removal tuned for Brazilian-Portuguese grammar.                                                                  |
-| **[ponytail](https://github.com/DietrichGebert/ponytail)** · DietrichGebert   | 68.8k | The viral "lazy senior dev" YAGNI-coder skill — inspired our **less-code** Output Style: smallest-working-change steering that cuts _generated_ code (the output-axis sibling to Caveman's terse prose). |
-
-### 🧩 Compact formats, token research & code-aware tooling
-
-| Project                                                                                        |    ⭐ | How it inspired OmniRoute                                                                                                                                                                                      |
-| ---------------------------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **[TOON](https://github.com/toon-format/toon)** · toon-format                                  | 24.7k | Token-Oriented Object Notation — its columnar, header-plus-rows model shaped our tabular compaction stage.                                                                                                     |
-| **[GCF – Graph Compact Format](https://github.com/blackwell-systems/gcf)** · Blackwell Systems |    14 | First inspired our tabular compaction stage; now its zero-dependency, lossless generic-profile encoder is **vendored directly** as the Headroom codec (MIT, SPDX-marked), current with GCF spec v3.2. |
-| **[token-optimizer-mcp](https://github.com/ooples/token-optimizer-mcp)** · ooples              |   421 | Brotli/SQLite cache + per-session context-delta — inspired our `session-dedup` engine.                                                                                                                         |
-| **[token-savior](https://github.com/Mibayy/token-savior)** · Mibayy                            |  1.0k | Bash-output compaction + MCP profiles — inspired our compression bail-out discipline and MCP tool-manifest reduction.                                                                                          |
-| **[token-saver](https://github.com/ppgranger/token-saver)** · ppgranger                        |   110 | Content-aware, per-file-type output compression with failure-aware bail-out — validated our per-type dispatch and minimum-gain skip.                                                                           |
-| **[token-optimizer](https://github.com/alexgreensh/token-optimizer)** · alexgreensh            |  1.5k | "Find the ghost tokens" — its offload + recoverable-handle pattern informed our CCR offload thinking.                                                                                                          |
-| **[TokenMizer](https://github.com/Shweta-Mishra-ai/tokenmizer)** · Shweta-Mishra-ai            |     2 | A session-graph + cross-turn line-dedup blueprint that informed our session-dedup design.                                                                                                                      |
-| **[OmniCompress](https://github.com/jessefreitas/OmniCompress)** · jessefreitas                |     2 | Rust columnar-JSON + content-addressed retrieve + cross-message dedup — validated our `headroom`/`ccr`/`session-dedup` engine design and the cache-stable "compressed form is position-independent" invariant. |
-| **[mcp-compressor](https://github.com/atlassian-labs/mcp-compressor)** · Atlassian Labs        |    89 | MCP tool-schema/description compression — informed our MCP tool-manifest cardinality reduction.                                                                                                                |
-| **[RepoMapper](https://github.com/pdavis68/RepoMapper)** · pdavis68                            |   181 | Aider-style repo-map ranking — informed our repo-map / retrieval-ranking exploration.                                                                                                                          |
-| **[quiet-shell-mcp](https://github.com/mrsimpson/quiet-shell-mcp)** · mrsimpson                |     4 | Declarative shell-output reduction over MCP — validated our declarative bash-output compaction.                                                                                                                |
-| **[ts-morph](https://github.com/dsherret/ts-morph)** · David Sherret                           |  6.1k | TypeScript Compiler API toolkit — inspired our parser-based comment removal that preserves string, template and regex literals.                                                                                |
-
-### 🧠 Memory & RAG
-
-| Project                                                            |    ⭐ | How it inspired OmniRoute                                                                                           |
-| ------------------------------------------------------------------ | ----: | ------------------------------------------------------------------------------------------------------------------- |
-| **[Mem0](https://github.com/mem0ai/mem0)** · mem0ai                | 59.8k | Universal memory layer — its proxy-as-write/read-boundary model shaped our memory architecture.                     |
-| **[Letta (MemGPT)](https://github.com/letta-ai/letta)** · letta-ai | 23.6k | Stateful agents with tiered memory — inspired our Context Control & Recovery (CCR) tiered model.                    |
-| **[WFGY](https://github.com/onestardao/WFGY)** · onestardao        |  1.8k | The ProblemMap taxonomy of 16 recurring RAG/LLM failure modes — the shared vocabulary in our troubleshooting guide. |
-
-### 🛰️ Traffic inspection, MITM & transparent proxy
-
-| Project                                                                           |   ⭐ | How it inspired OmniRoute                                                                                                                                                        |
-| --------------------------------------------------------------------------------- | ---: | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **[llm-interceptor](https://github.com/chouzz/llm-interceptor)** · chouzz         |   48 | MITM interception/analysis of coding-assistant ↔ LLM traffic — our Traffic Inspector ports its SSE merge, conversation normalization, host passthrough and secret masking (MIT). |
-| **[ProxyBridge](https://github.com/InterceptSuite/ProxyBridge)** · InterceptSuite | 5.3k | Transparent per-process proxy routing — inspired our crash-safe MITM teardown, socket idle-timeouts, `/proc` process attribution and TPROXY capture.                             |
-
-### 📚 Model data, observability & UI
-
-| Project                                                                    |    ⭐ | How it inspired OmniRoute                                                                                                  |
-| -------------------------------------------------------------------------- | ----: | -------------------------------------------------------------------------------------------------------------------------- |
-| **[models.dev](https://github.com/anomalyco/models.dev)** · SST / OpenCode |  5.6k | Open database of AI model specs, pricing and capabilities — synced natively into our model catalog.                        |
-| **[React Flow / xyflow](https://github.com/xyflow/xyflow)** · xyflow       | 37.4k | The node-based graph library powering our real-time Compression Studio and Combo/Routing Studio.                           |
-| **[LangGraph](https://github.com/langchain-ai/langgraph)** · LangChain     | 36.1k | LangGraph Studio's live workflow-graph visualization inspired our Studios' real-time cascade view.                         |
-| **[Langfuse](https://github.com/langfuse/langfuse)** · Langfuse            | 30.1k | Its trace → span → generation observability model shaped our Compression Studio waterfall.                                 |
-| **[Kiali](https://github.com/kiali/kiali)** · Kiali                        |  3.6k | Istio service-mesh observability — inspired our circuit-breaker badges and error-edge visuals in the Routing/Combo Studio. |
-| **[lobe-icons](https://github.com/lobehub/lobe-icons)** · LobeHub          |  2.2k | AI/LLM brand logos that render the provider icons across our dashboard.                                                    |
-
-### 🛡️ Security
-
-| Project                                                                                     |  ⭐ | How it inspired OmniRoute                                                                                                                        |
-| ------------------------------------------------------------------------------------------- | --: | ------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **[awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults)** · tldrsec | 708 | A curated list of secure-by-default libraries that guides our security choices (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink). |
-
-### 🧭 Complementary tools
-
-| Project                                                                       | How it composes with OmniRoute                                                                                                                                                                             |
-| ----------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **[CodeWebChat](https://github.com/robertpiosik/CodeWebChat)** · robertpiosik | Editor-side companion — VS Code + browser extension that autofills 15+ chatbot web UIs with editor context. Owns the free-web-UI rail alongside OmniRoute's API rail; can point its API mode at OmniRoute. |
+Special thanks to **[Troglodita](https://github.com/leninejunior/troglodita)** by **[Lenine Júnior](https://github.com/leninejunior)** — the PT-BR token compression project ("por que gastar muitos tokens quando poucos resolve?") whose Portuguese-native rules power OmniRoute's pt-BR language pack: pleonasm reduction, filler removal tuned for Brazilian Portuguese grammar, and technical abbreviations for the dev BR community.
 
 ## ❤️ Support
 
@@ -1274,7 +1031,7 @@ MIT License - see [LICENSE](LICENSE) for details.
 
 **[⬆ Back to top](#-omniroute)** · Built with ❤️ for the open-source AI community.
 
-<sub>OmniRoute v3.8.43 · Node ≥22.0.0 · MIT License · <a href="https://omniroute.online">omniroute.online</a></sub>
+<sub>OmniRoute v3.8.6 · Node ≥22.22.2 · MIT License · <a href="https://omniroute.online">omniroute.online</a></sub>
 
 </div>
 <!-- GitHub Discussions enabled for community Q&A -->

RELATORIO-QUALITY-GATES.md

@@ -0,0 +1,219 @@
+# Relatório — Quality Gates, Catraca & Anti-Alucinação no OmniRoute
+
+> **Data:** 2026-06-09
+> **Origem:** Auditoria do projeto (5 subagentes Opus em paralelo mapeando todas as pastas exceto `node_modules`/`_references`/`dist`) + análise da transcrição do vídeo *"Qualidade de código"* (Stupid Button Club, 2026-05-04) + pesquisa web 2026 (4 frentes, últimos ~3 meses).
+> **Companheiro:** Veja [`PLANO-QUALITY-GATES.md`](./PLANO-QUALITY-GATES.md) para o plano de implementação bite-sized (TDD).
+
+---
+
+## 0. TL;DR
+
+1. **O OmniRoute já é muito mais maduro** que o projeto "Strawberry" do vídeo: tem CI com 20 jobs, gate de cobertura, ESLint 9 flat, SonarQube, 14 scripts `check-*.mjs` e **uma catraca real já funcionando** (`check-t11-any-budget.mjs` — orçamento de `any` por arquivo que só pode encolher). O vídeo descreve onde queremos chegar; nós já estamos a meio caminho.
+2. **Mas faltam exatamente as catracas que o vídeo prega.** Não há baseline congelado de métricas, nem gate de **duplicação**, nem de **tamanho de arquivo**, e o gate de cobertura é um **piso fixo** — não uma catraca "nunca piorar".
+3. **Há derivas (drifts) reais que pegamos na auditoria:** o gate de cobertura **no CI é `40/40/40/40`** (ci.yml:377), não os `60/60/60/60` que o CLAUDE.md anuncia (esse é só o script local). O Husky está **100% comentado** (zero gate local). O SonarQube tem `coverage` e `cpd` **excluídos** (`sonar-project.properties:9-10`) — as duas métricas mais úteis contra "slop" estão desligadas. E 3 scripts `check-*` existem mas **não rodam em lugar nenhum**.
+4. **Os maiores ímãs de alucinação são estruturais:** o split de provider em 3 arquivos gigantes em 2 workspaces (`providers.ts` ↔ `providerRegistry.ts` ↔ `validation.ts`, com contagens que já divergem: 229 ids vs 155 blocos vs N validadores), os 300 paths `fetch("/api/...")` hardcoded sem ligação de compilação com as rotas, e o arquivo de **12.760 linhas** (`providers/[id]/page.tsx`) que nenhum agente consegue segurar em contexto.
+5. **2026 confirma a tese do vídeo com dados:** GitClear (211M linhas) mostra duplicação crescendo 4–8× na era da IA; o paper SlopCodeBench prova que *instrução de prompt sozinha não impede a degradação* — só gates determinísticos seguram. O ecossistema 2026 tem ferramentas maduras para cada métrica (jscpd v5, knip v6, eslint-plugin-sonarjs v4, osv-scanner, Qlty, Sonar "Clean as You Code"/"AI Code Assurance").
+6. **A jogada é em camadas:** (a) reativar/reconciliar o que já existe; (b) construir o **motor de catraca** (baseline.json + coletor + comparador, clonando o `any-budget`); (c) adicionar **gates determinísticos anti-alucinação** (provider-consistency, fetch-target, openapi-routes); (d) catraca de **duplicação + tamanho**; (e) catraca de **cobertura** + detecção de test-masking; (f) skill **`/babysit`** com guarda-corpos. Detalhe no plano.
+
+---
+
+## 1. O que o vídeo ensina (insights destilados)
+
+O vídeo é uma fala sem roteiro sobre *qualidade de código no mundo em que a IA escreve ~100% do código*. Pontos centrais:
+
+| # | Insight | Citação/essência |
+|---|---------|------------------|
+| 1 | **O humano virou o gargalo.** | "Eu acabei virando o gargalo da IA. Fazer o babysit das coisas do request básicas é o gargalo. Não consigo entregar 4 tarefas ao mesmo tempo se preciso ler 10.000 linhas/dia." |
+| 2 | **Quality Gate = portão que a IA tem que passar.** | Todo PR passa por um portão; a IA fica em loop se autocorrigindo até ficar verde, em vez de o humano revisar e pedir refação. |
+| 3 | **Baseline + Catraca (ratchet).** | "Tu congela o baseline e o repositório só pode melhorar a partir dali ou empatar." A catraca anda num sentido só. |
+| 4 | **Regra de ouro.** | "Cada PR pode adicionar código, mas não pode aumentar nenhuma das métricas — nem por uma violação, nem por uma linha, nem por 0,1 ponto percentual." |
+| 5 | **Métricas do baseline.** | Violações de ESLint (483 em 120 arquivos), duplicação de código (2,2% via JSCPD), cobertura (%), arquivos acima do limite de tamanho (19 arquivos; o maior com 4.600 linhas). |
+| 6 | **Pipeline de CI.** | `npm ci` → `npm audit` (critical=bloqueia / high=avisa) → `npm run lint` → `test:coverage` → **script node de quality gate** que compara métricas atuais vs `baseline.json` e falha em qualquer regressão → comentário no PR + **upload de artefatos** que o agente lê para se autocorrigir. |
+| 7 | **Artefatos legíveis pelo agente.** | "Não adianta cuspir isso no PR. O agente precisa ter acesso ao que está dando errado." |
+| 8 | **Babysit skill.** | "Recomendo criar uma skill de babysit": a IA monitora o CI + comentários dos revisores, endereça os comentários e **resolve as conversas** para dar rastreabilidade no GitHub. |
+| 9 | **Comentários perto do código (legibilidade p/ agente).** | Mudou de ideia: antes era contra comentários ("o código é a documentação"); agora, no mundo de agentes, comentário explicando *o quê* e *por quê* perto do código vale mais que um MD gigante, porque o harness faz `grep` no arquivo e lê o comentário junto. |
+| 10 | **É "só" colar ferramentas.** | "Não é nada excepcional. Eu só estou colando um monte de ferramentas e chamando de quality gate." Pode-se usar SonarQube ou GitHub Code Quality no lugar do script caseiro. |
+| 11 | **Por que a IA não faz certo de primeira.** | Modelos top já sabem (foram treinados com os livros), mas são "preguiçosos" porque output imperfeito = mais tokens vendidos. A catraca força o nível. |
+
+**Tradução para o nosso contexto:** o vídeo descreve um sistema que **já temos em embrião** (o `any-budget` é exatamente a catraca da regra de ouro, só que para uma métrica). O salto é (1) generalizar a catraca para todas as métricas, (2) reconciliar os drifts, e (3) fechar os buracos anti-alucinação que são específicos do nosso tamanho.
+
+---
+
+## 2. Onde o OmniRoute está hoje (panorama auditado)
+
+### 2.1 O que já temos (e o vídeo nem sonha)
+
+- **CI robusto** (`.github/workflows/ci.yml`, ~25 KB, 20 jobs): lint + audit + cycles + route-validation + any-budget + docs-sync + typecheck (core e noimplicit) + build + package-artifact + electron-smoke + unit (8 shards) + Node 24/26 compat + coverage (8 shards + merge) + SonarQube + e2e (9 shards) + integration + security.
+- **Catraca real já existente:** `scripts/check/check-t11-any-budget.mjs` — array `{file, maxAny}` (a maioria `0`), strip de comentários, anotações de falso-positivo, `exit 1` em regressão. **É o template exato da catraca do vídeo.**
+- **14 scripts `check-*.mjs`** (cycles, route-validation, any-budget, docs-sync, docs-counts, env-doc-sync, deprecated-versions, doc-links, cli-i18n, openapi-coverage, openapi-security-tiers, pr-test-policy, node-runtime, test-report-summary) — vários já são *gates de consistência fonte-vs-derivado*, o mesmo padrão que precisamos para anti-alucinação.
+- **PR test policy:** `check-pr-test-policy.mjs` já força "mudou código de produção ⇒ mudou teste" (diff base...HEAD).
+- **Cobertura sumarizada + comentada no PR:** `test-report-summary.mjs` + `coverage/coverage-summary.json` + job `coverage-pr-comment` (comentário com marcador `<!-- omniroute-coverage-report -->`). **Isto é exatamente o "artefato legível pelo agente" do vídeo** — já construído.
+- **Disciplina TDD institucionalizada** (Hard Rule #18: todo fix precisa de teste falha→passa ou validação ao vivo no VPS).
+- **SonarQube** configurado (job no CI + `sonar-project.properties`).
+- **Skills agênticas de review** já existem: `/review-prs`, `/review-reviews` (bateria de 8 reviewers + ralph-loop), `/code-review`, `/generate-release` (a única com babysit real de CI, mas de workflows de *release*, não do `ci.yml` do PR).
+
+### 2.2 O que está DESLIGADO ou inerte ⚠️ (achados da auditoria)
+
+| Item | Estado | Evidência | Impacto |
+|------|--------|-----------|---------|
+| **Husky** | 100% comentado (pre-commit **e** pre-push) | `.husky/pre-commit`, `.husky/pre-push` (todas as linhas com `#`) | Zero enforcement local — lint-staged, docs-sync, any-budget, env-doc-sync, openapi checks e o `test:unit` de pre-push dependem 100% do CI. |
+| **Gate de cobertura no CI** | **40/40/40/40** (não 60) | `ci.yml:377` `--statements 40 --lines 40 --functions 40 --branches 40` | O comentário do PR renderiza contra 60, o script local gata 60, o RELEASE_CHECKLIST diz 75/70, e o baseline real é ~79–82%. **O único número que bloqueia merge é 40** → gate de cobertura quase banguela. |
+| **Sonar coverage** | Excluído | `sonar-project.properties:9` `sonar.coverage.exclusions=**/*` | Sonar ignora cobertura de todo arquivo. |
+| **Sonar CPD (duplicação)** | Excluído | `sonar-project.properties:10` `sonar.cpd.exclusions=**/*` | Sonar não detecta copy-paste — a assinatura nº1 de slop de IA. |
+| **SonarQube job** | Inerte | `ci.yml` roda scan só se `PR && SONAR_TOKEN != '' && SONAR_HOST_URL != ''`; sem `qualitygate.wait` | Em runs sem secret, escreve "skipped"; mesmo quando roda, nunca falha o build. |
+| **`npm audit`** | Plano (`moderate`), não escalonado | `package.json:112` `--audit-level=moderate` | O vídeo prega critical=bloqueia / high=avisa. O nosso é um nível único. |
+| **3 scripts órfãos** | Sem CI nem husky | `check:cli-i18n`, `check:openapi-coverage`, `check:openapi-security-tiers` | Existem, dão `exit 1`, mas não rodam em lugar nenhum (Hard Rules #15/#17 guardadas só por um deles). |
+| **`typecheck:noimplicit:core`** | `continue-on-error: true` | `ci.yml:45-46` | Warn-only "forward-looking". |
+
+### 2.3 Hotspots de tamanho (sem gate hoje)
+
+`64 arquivos > 1000 LOC`, `194 > 500 LOC` (src + open-sse, sem testes). Top:
+
+| LOC | Arquivo | Risco para edição por IA |
+|-----|---------|--------------------------|
+| **12.760** | `src/app/(dashboard)/dashboard/providers/[id]/page.tsx` | God-component: **192 `useState`**, 21 `useEffect`, 87 `fetch()` inline, 34 tipos inline. Nenhuma IA segura em contexto; qualquer edição arrisca apagar estado não relacionado. |
+| 5.977 | `open-sse/handlers/chatCore.ts` | God-handler: 58 funções, invariantes demais, blast radius alto. |
+| 4.590 | `open-sse/config/providerRegistry.ts` | Array gigante providers+models+OAuth; mistura `resolvePublicCred()` e literais crus. |
+| 4.456 | `open-sse/services/combo.ts` | 14 estratégias num `if/else if` sem enum/exhaustiveness — estratégia desconhecida vira no-op silencioso. |
+| 4.349 | `src/app/(dashboard)/dashboard/combos/page.tsx` | 51 `useState`, mesmo padrão god-component. |
+| 4.205 | `src/lib/providers/validation.ts` | Mega-função com closures e `SPECIALTY_VALIDATORS` definidos *dentro* da função. |
+| 3.776 | `open-sse/handlers/imageGeneration.ts` | Branching multi-provider num handler. |
+| 3.076 | `src/shared/constants/providers.ts` | 229 ids em 27 consts agrupados via `Proxy` — sem lista plana. |
+| 2.869 | `open-sse/executors/chatgpt-web.ts` | Sessão web reversa; classe só começa na linha 2443. |
+| 2.278 | `src/app/api/providers/[id]/models/route.ts` | God-route: importa ~30 módulos provider-específicos e ramifica por provider num GET. |
+
+### 2.4 Ímãs de alucinação (ranqueados, da auditoria)
+
+1. **Split de provider em 3 arquivos / 2 workspaces (nº1).** Não há lista plana de providers — 229 ids escondidos atrás de 27 consts + merge via `Proxy` (`AI_PROVIDERS`). Uma IA não consegue enumerar "quais providers existem" barato → **inventa ids plausíveis** (variantes `*-web`/`*-cli` inexistentes) ou registra no grupo errado. As três contagens (`providers.ts` 229 ids ↔ `providerRegistry.ts` 155 blocos ↔ `validation.ts` N validadores) **já divergem**, então não há cross-check autoritativo. *(Esse é o tema recorrente das nossas memórias de alucinação — ex.: ids inventados, modelos inexistentes.)*
+2. **300 paths `fetch("/api/...")` hardcoded** no dashboard (659 call sites), sem client tipado. Refatore uma rota e os call sites apodrecem silenciosamente; uma IA editando a UI inventa rota (`/api/providers/[id]/refresh`) ou assume `res.error.message` numa rota que devolve `{error:"..."}`. Sem ligação de símbolo entre os 659 call sites e os 488 `route.ts`.
+3. **Dual chat stack (armadilha documentada).** Seleção/fallback de conta vive em `src/sse/` (não `open-sse/`). Uma IA pedida para "consertar fallback de conta" edita `open-sse/handlers/chatCore.ts` (errado) em vez de `src/sse/services/auth.ts`. Nada no código cruza os dois stacks. *(Já erramos um diagnóstico público por isso.)*
+4. **Estratégias de combo inventadas.** 14 nomes reais soterrados num `if/else` de strings (sem enum exportado) → IA inventa nomes plausíveis-mas-falsos (`"latency-optimized"`, `"failover"`) que passam no typecheck como string e viram no-op.
+5. **Métodos de executor inventados.** O padrão real é "sobrescreve `execute()` inteiro" (48/50 executors), sem hooks documentados → IA inventa `buildRequest`/`parseChunk`/`mapError` que não existem em `BaseExecutor`.
+6. **Helpers de erro inventados** + queda para `err.message` cru (viola Rule #12) quando o helper inventado "falha"; 5 web executors hoje **não importam helper nenhum**.
+7. **AGENTS.md de DB defasado:** documenta 21 migrations / 22 módulos quando o real é **94 / 75** — uma IA lendo isso acredita em conjuntos de tabelas/módulos que não existem mais.
+8. **Route-guard omitido:** rotas novas spawn-capazes (`/api/services/`, `/api/mcp/`) devem entrar em `LOCAL_ONLY_API_PREFIXES`; a convenção está só no CLAUDE.md, não num teste que a IA veja (parcialmente coberta por 1 script órfão).
+
+---
+
+## 3. Gap analysis — modelo do vídeo vs OmniRoute
+
+| Métrica/peça do vídeo | OmniRoute hoje | Gap |
+|-----------------------|----------------|-----|
+| `npm ci` determinístico | ✅ em todos os 14 jobs | — |
+| `npm audit` critical=bloqueia / high=avisa | ⚠️ `--audit-level=moderate` (nível único) | **Escalonar** em dois invokes |
+| `lint` | ✅ bloqueante | — |
+| `test` + cobertura | ✅ mas piso **40** no CI (drift) | **Reconciliar** p/ baseline real + catraca |
+| **Contagem de ESLint congelada** | ❌ (lint é 0-erros, mas warnings livres) | **Construir** (ratchet de violações) |
+| **Duplicação % (JSCPD)** | ❌ (Sonar CPD excluído, sem jscpd) | **Construir** (jscpd + catraca) |
+| **Limite de tamanho de arquivo** | ❌ (sem `max-lines`, sem script) | **Construir** (ESLint max-lines + catraca, freeze dos 64) |
+| **`baseline.json` congelado** | ❌ (nenhum baseline de métricas no repo) | **Construir** (o coração da catraca) |
+| **Script comparador (regra de ouro)** | 🟡 existe **para `any`** (`any-budget`) | **Generalizar** p/ todas as métricas |
+| **Sumário markdown + artefatos p/ o agente** | ✅ (coverage summary + PR comment + artifact) | **Reusar** wholesale |
+| **Babysit skill (monitora CI + resolve conversas)** | 🟡 `review-prs`/`review-reviews`/`generate-release` parciais; nenhuma resolve threads do PR nem loopa no `ci.yml` | **Construir** `/babysit` |
+| **Comentários perto do código p/ legibilidade de agente** | 🟡 `routeGuard.ts` é exemplar; resto irregular | **Padrão cultural** (Karpathy/guidelines) |
+
+---
+
+## 4. O que o mundo faz em 2026 (pesquisa, últimos ~3 meses)
+
+> Todas as fontes abaixo vêm com URL + data nas seções de origem (ver §7). Onde a pesquisa **não conseguiu confirmar** algo de fonte primária, está marcado **[não-verificado]** — honestidade de engenharia.
+
+### 4.1 Catraca / baseline-freeze (a "catraca" do vídeo)
+
+- **betterer** — o tool canônico de ratchet (snapshot de métrica → `.betterer.results`; CI falha se piora, auto-atualiza se melhora). **[caveat]** Baixa velocidade: último commit no `master` em **ago/2025**, releases vazias no GitHub. Viável, mas **não** apostar como peça load-bearing de longo prazo.
+- **eslint-formatter-ratchet** — formatter que congela contagem de violações de ESLint. **Ativamente mantido** (commit 2026-03-17). Mais estreito (só ESLint) mas é a trajetória oposta ao betterer.
+- **SonarQube "Clean as You Code" (new-code conditions)** — o padrão baseline-freeze mais maduro: o quality gate aplica condições **só ao código novo** (branch de referência), grandfathering do legado. Atual.
+- **SonarQube "AI Code Assurance" (2026.1.0)** — gate específico para código gerado por IA (tag o projeto → workflow de assurance + "Sonar way for AI Code" mais estrito). **[não-verificado]** se *bloqueia* o PR (docs canônicas deram 404; descrito como "enforced quality gate" mas mecânica de bloqueio não confirmada em fonte única).
+- **Qlty CLI (qlty.sh)** — o produto 2026 mais aderente: CLI Rust **OSS e grátis** (v0.630.0, 2026-05-08) que agrega 70+ analisadores; tem **Baseline analysis** (= a catraca), **Quality Gates** com veredito go/no-go e coverage gates. **[caveat]** `qlty metrics` (a tabela LOC/complexidade) **não tem flag JSON** — só `qlty check --sarif`/`qlty smells --sarif`; o ratchet de tamanho/complexidade por arquivo ainda precisa do JSON do ESLint.
+- **Code Climate Quality → Qlty** — a marca clássica de ratchet virou empresa separada (Qlty, nov/2024). Write-ups antigos de "Code Climate" = Qlty hoje.
+
+### 4.2 Ferramentas de métrica por tipo (todas com JSON p/ alimentar a catraca)
+
+| Métrica | Tool 2026 | Comando JSON | Status |
+|---------|-----------|--------------|--------|
+| Duplicação | **jscpd v5** (reescrita Rust) | `jscpd --reporters json` (ou `sarif`) | Muito ativo (v5.0.4, 2026-06-08). **[caveat]** schema JSON v4→v5 não confirmado — verificar no install. |
+| Tamanho/fn-length/ciclomática | **ESLint core** (`max-lines`, `max-lines-per-function`, `complexity`) | `eslint --format json` | Built-in ESLint 9 |
+| Complexidade cognitiva | **eslint-plugin-sonarjs** (`sonarjs/cognitive-complexity`) | `eslint --format json` | Mantido (v4.0.3, 2026-04-16; agora no monorepo SonarJS — o repo standalone foi arquivado, mas o pacote está vivo). **[caveat]** README das rules deu 404; presença de S3776 em v4 é alta-confiança mas confirmar no install. |
+| Dead code / unused exports / unused deps | **knip** (vence ts-prune **arquivado** + depcheck **arquivado**) | `knip --reporter json` | Muito ativo (v6.16.1, 2026-06-06) |
+| Ciclos | **check-cycles.mjs** (já temos) + **dpdm** opcional | `dpdm --circular --output deps.json` | dpdm ativo (v4.2.0, 2026-05-09); madge estagnado |
+| Vulnerabilidades | **osv-scanner** (Google/OSV) | `osv-scanner --format json` | Muito ativo (push 2026-06-08) |
+| Política de lockfile (gate, não métrica) | **lockfile-lint** | `lockfile-lint --validate-https --validate-integrity` | Mantido (v5.0.0, 2026-01-25) |
+
+> **Realidade do ratchet:** não existe tool único 2026 que emita *todas* as métricas como um JSON limpo. O padrão robusto é **N tools que emitem JSON + um reducer Node** que monta `metrics-summary.json` + o comparador que falha só em regressão (exatamente o que o `any-budget` já faz para uma métrica).
+
+### 4.3 Anti-alucinação (2026)
+
+- **LSP-in-the-loop / `agent-lsp` (MCP)** — servidor MCP que dá ao agente fatos verificáveis do language server (definições, referências, tipos, diagnostics, `blast_radius`) e `preview_edit` antes de escrever. Funciona com Claude Code. **Fit alto:** vira "símbolo inventado" de catch-de-review para *impossibilidade-no-edit*. (v0.13.0, 2026-06-04 — pequeno mas ativo.)
+- **Slopsquatting / pacotes alucinados** — **CSA Research Note (2026-04-19):** **19,7%** de 2,23M amostras de código IA continham nomes de pacote alucinados; 205k nomes fabricados únicos; **43%** reaparecem em re-runs (registráveis por atacantes). Defesas: **allowlist** de deps para agentes, **registry existence check** antes de instalar, **age-cooldown** (24–72h), lockfile-exact, scripts de install desabilitados. **Fit alto:** novo `check-deps.mjs`.
+- **Semcheck** (v1.2.1, fev/2026) — CLI que usa LLM para verificar que a implementação bate com o spec/doc, via `semcheck.yaml` ligando doc↔código; roda em pre-commit e Actions com `fail-on-issues`. Feito para pegar **"docs que descrevem features não implementadas"**. **Fit muito alto** para nossos incidentes recorrentes de docs alucinadas — porém é fuzzy (LLM); pareie com checks determinísticos.
+- **OpenAPI drift determinístico** — check que toda `path` do `openapi.yaml` resolve para um `route.ts` real (e vice-versa). Rápido, sem LLM, pega "endpoint inventado". **Fit alto** para `docs/reference/openapi.yaml`.
+- **Skill `verify` / `verification-before-completion`** (já no nosso ambiente) — "evidence before assertions": o veredito PASS/FAIL repousa **só** no que o app rodando demonstrou; rejeita "rodei os testes" como prova. **Fit altíssimo:** é a formalização da nossa Hard Rule #18 — exigir o *output literal* do comando colado no PR ("tool receipt").
+- **Adversarial review (críticos de sessão fresca)** — agentes Skeptic/Architect/Minimalist leem o diff *contra o spec* ("o autor está comprometido — vai racionalizar"); símbolos/APIs inventados viram violação de spec. Mapeia no nosso `/review-reviews`.
+- **SlopCodeBench (arXiv 2603.24755, ~mai/2026)** — sem mitigação, erosão estrutural aumentou em **77%** das trajetórias; o código de agente acumula verbosidade ~7× e erosão ~5× mais rápido que repos humanos. **Mitigações só-de-prompt ("anti-slop", "plan-first") melhoram o início mas NÃO param a degradação iterativa.** → **justificativa empírica** de que precisamos de gates determinísticos, não instrução.
+- **GPT-5.5 System Card (2026-04-23)** — figuras oficiais são modestas (23% mais provável de acerto factual; 3% menos erros num set propenso). O headline de **"queda de 60% em alucinação / 88,7% SWE-bench" é imprensa secundária [não-verificado]**, não a seção de factualidade do system card. Upgrade de modelo ajuda na margem, não substitui gate.
+
+### 4.4 Babysit loops (2026)
+
+- **Claude Code "auto-fix in the cloud"** (Anthropic, lançado 2026-03-27): "observa seus PRs na nuvem, resolvendo falhas de CI e comentários de review automaticamente; empurra fixes quando claro, pergunta quando ambíguo." Não auto-mergeia.
+- **Devin Autofix** (2026-02-10): auto-conserta comentários de review + lint/CI; endereça comentários de bots, mas deixa julgamento humano nas conversas humanas.
+- **CodeRabbit Autofix** (early access abr/2026): coleta o bloco **"Prompt for AI Agents"** de cada comentário, aplica fix, roda build-verification; **nada mergeia automaticamente**.
+- **Greptile `greploop` + skill `check-pr`** (MIT) — "dispara review → conserta comentários → re-review até 5/5 de confiança e zero comentários". **Template quase-exato** para a nossa `/babysit`.
+- **Claude `claude ultrareview <PR#> --json`** (subcomando não-interativo, research preview): bloqueia até terminar, `exit 0/1`, payload de bugs verificados parseável. **Não auto-inicia** e custa $5–20/run → usar atrás de label, não em todo push. (O `/code-review ultra` local com `--fix` é o loop interno de custo-zero.)
+- **Resolver threads de review:** não há comando `gh` nativo (cli/cli#12419). Padrão de 2 passos GraphQL: `reviewThreads(first:50){nodes{id isResolved...}}` → `mutation { resolveReviewThread(input:{threadId}) }`, respondendo antes com o SHA do commit via REST.
+- **Guarda-corpos (críticos):**
+  - **Snyk Agent Fix field test (2026): ~5,3% de regressão** ("1 em 19 fixes auto-mergeados introduz problema novo") → **forte argumento contra auto-merge**.
+  - **Token burn:** loops ingênuos realimentam a conversa crescente → prompt incha → alucina do próprio histórico. Uber capou gasto em **$1.500/mês/dev/tool** (abr/2026). Mitigação: **max-iterations**, time limit, idle-exit.
+  - **Test-masking:** o babysit **NÃO** pode enfraquecer/remover asserts para ficar verde (= nossa Rule #18 + memória "trust but verify"). Revisão humana fica nos limites arquiteturais (interface/schema/cross-service).
+  - **Audit trail:** deixar rastro humano-legível (qual fix endereçou o quê, qual gate satisfez, quais conversas resolveu) — nunca um verde silencioso. Reforça o guard de prompt-injection sobre os *corpos de comentário* que o agente ingere (21% dos reviews do ICLR 2026 eram IA; injeção embutida em código é vetor real).
+
+---
+
+## 5. Recomendações (ranqueadas) → ver o PLANO
+
+> Build-vs-buy: **construir in-repo** os gates determinísticos (zero SaaS, dados não saem da box, reusa o harness `check-*.mjs`). **Avaliar Qlty CLI** depois, se quisermos consolidar N scripts num tool. **Não** depender de CodeRabbit/Greptile/Diamond como *o* gate de "não-piorar-métrica" — são opiniões de LLM, não contadores determinísticos.
+
+**Fase 0 — Reativar & reconciliar (quick wins, sem tooling novo):**
+1. Reativar pre-commit barato do Husky (lint-staged + docs-sync + any-budget).
+2. Reconciliar o gate de cobertura: subir o CI de 40 → baseline real (com headroom) e alinhar os 4 lugares que divergem.
+3. Escalonar `npm audit` (critical=bloqueia / high=avisa).
+4. Plugar os 3 scripts órfãos (`cli-i18n`, `openapi-coverage`, `openapi-security-tiers`) no CI.
+
+**Fase 1 — Motor de catraca (o coração):**
+5. `quality-baseline.json` commitado + `collect-metrics.mjs` (coletor) + `check-quality-ratchet.mjs` (comparador, clone do `any-budget`) + job de CI + artefato + comentário no PR (clone do `coverage-pr-comment`).
+
+**Fase 2 — Gates determinísticos anti-alucinação:**
+6. `check-provider-consistency.mjs` (o ímã nº1), `check-fetch-targets.mjs`, `check-openapi-routes.mjs`, allow-list de estratégias/translators/executors, lint Rule #11/#12, `check-deps.mjs` (slopsquatting).
+
+**Fase 3 — Catraca de duplicação + tamanho (mata-slop):**
+7. jscpd + ESLint `max-lines`/`max-lines-per-function`/`complexity` + `sonarjs/cognitive-complexity`, congelando os 64 arquivos grandes (catraca só-pode-encolher).
+
+**Fase 4 — Catraca de cobertura + anti test-masking:**
+8. `check-coverage-ratchet.mjs` (cobertura não cai vs baseline) + pisos por módulo crítico + `check-test-masking.mjs` (delta de contagem de asserts em testes alterados).
+
+**Fase 5 — Skill `/babysit` + evidência + LSP:**
+9. Skill `/babysit` (gh pr checks + reviewThreads + worktree de fix + resolveReviewThread + loop-até-verde, com guarda-corpos), "evidence-before-assertions" obrigatório no corpo do PR, e (opcional) `agent-lsp` MCP.
+
+---
+
+## 6. Riscos & ressalvas (honestidade de engenharia)
+
+- **Flag-day risk:** ligar qualquer gate num projeto que nunca o teve deixa tudo vermelho. **Toda** catraca aqui é *só-regressão* (baseline congelado), nunca um piso absoluto que exige limpeza imediata — exatamente o ponto do vídeo.
+- **Custo de IA:** o babysit pode queimar tokens. Guarda-corpos (max-iterations, sem auto-merge, sem editar `.github/workflows/`) são não-negociáveis.
+- **Ressalvas de pesquisa não-verificadas:** betterer baixa-velocidade; Sonar "AI Code Assurance" bloqueio-de-PR não confirmado; "GPT-5.5 −60% alucinação" é imprensa, não system card; schema JSON do jscpd v5 e S3776 do sonarjs v4 a confirmar no install; `qlty metrics` sem JSON. Nenhuma decisão do plano depende criticamente de um item não-verificado.
+- **Trust-but-verify:** estes números internos (CI=40, husky off, sonar exclusions, 12.760 LOC, any-budget como catraca) foram **conferidos manualmente** contra os arquivos, não só relatados pelos subagentes.
+
+---
+
+## 7. Fontes (consolidadas)
+
+**Catraca / ratchet:** betterer `github.com/phenomnomnominal/betterer` (último master ago/2025); eslint-formatter-ratchet `github.com/Jmsa/eslint-formatter-ratchet` (commit 2026-03-17); SonarQube Clean as You Code `docs.sonarsource.com/.../clean-as-you-code/about-new-code/`; Sonar AI Code Assurance `sonarsource.com/solutions/ai/ai-code-assurance/` + community thread 2026.1.0; Qlty `github.com/qltysh/qlty` (v0.630.0, 2026-05-08), `docs.qlty.sh`; Code Climate→Qlty `codeclimate.com/legacy/...` (2024-11-11).
+
+**Métricas:** jscpd `github.com/kucherenko/jscpd` (v5.0.4, 2026-06-08); ESLint v10 `eslint.org/blog/2026/02/eslint-v10.0.0-released/` (2026-02-06); eslint-plugin-sonarjs `npm` (v4.0.3, 2026-04-16) + `github.com/SonarSource/SonarJS`; knip `knip.dev` (v6.16.1, 2026-06-06); dpdm `github.com/acrazing/dpdm` (v4.2.0, 2026-05-09); osv-scanner `google.github.io/osv-scanner` (push 2026-06-08); lockfile-lint `github.com/lirantal/lockfile-lint` (v5.0.0, 2026-01-25); GitClear `gitclear.com/ai_assistant_code_quality_2025_research`.
+
+**Anti-alucinação:** agent-lsp `github.com/blackwell-systems/agent-lsp` (v0.13.0, 2026-06-04); CSA Slopsquatting `labs.cloudsecurityalliance.org/research/...slopsquatting...20260419...` (2026-04-19); Nesbitt package defenses `nesbitt.io/2026/04/09/...` (2026-04-09); Semcheck `github.com/rejot-dev/semcheck` (v1.2.1, fev/2026); verify skill `github.com/Piebald-AI/claude-code-system-prompts/.../skill-verify-skill.md`; Claude best practices `code.claude.com/docs/en/best-practices`; SlopCodeBench `arxiv.org/pdf/2603.24755`; GPT-5.5 system card `deploymentsafety.openai.com/gpt-5-5` (2026-04-23); adversarial review `asdlc.io/patterns/adversarial-code-review/`; OpenAPI drift `speakeasy.com/blog/openapi-spec-drift-detection`.
+
+**Babysit:** Claude auto-fix cloud `producthunt.com/products/claude-code-auto-fix-in-the-cloud` (2026-03-27); Devin Autofix `cognition.ai/blog/closing-the-agent-loop-...` (2026-02-10); CodeRabbit Autofix `coderabbit.ai/blog/fix-all-issues-with-ai-agents` (2026-02-19); Greptile skills `github.com/greptileai/skills`; Claude GitHub Actions/Code Review/ultrareview `code.claude.com/docs/en/{github-actions,code-review,ultrareview}`; Nx self-healing `nx.dev/blog/autonomous-ai-workflows-with-nx` (2026-02-03); Snyk Agent Fix 5,3% `safeguard.sh/resources/blog/snyk-agent-fix-autofix-field-test-2026`; resolveReviewThread `nakamasato.medium.com/...` + `github.com/cli/cli/issues/12419`; ICLR 2026 AI review `blog.pebblous.ai/report/iclr-2026-ai-peer-review-crisis`.
+
+---
+
+*Relatório gerado a partir de auditoria paralela do código + transcrição do vídeo + pesquisa web 2026. Próximo passo: aprovar o [`PLANO-QUALITY-GATES.md`](./PLANO-QUALITY-GATES.md) e escolher por onde começar (recomendação: Fase 0 → Fase 1).*

SECURITY.md

@@ -113,14 +113,14 @@ PII_REDACTION_ENABLED=true
 
 ### 🌐 Network Security
 
-| Feature                  | Description                                                                    |
-| ------------------------ | ------------------------------------------------------------------------------ |
-| **CORS**                 | Explicit cross-origin allowlist (`CORS_ALLOWED_ORIGINS`; legacy `CORS_ORIGIN`) |
-| **IP Filtering**         | Allowlist/blocklist IP ranges in dashboard                                     |
-| **Rate Limiting**        | Per-provider rate limits with automatic backoff                                |
-| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s                         |
-| **TLS Fingerprint**      | Browser-like TLS fingerprint spoofing to reduce bot detection                  |
-| **CLI Fingerprint**      | Per-provider header/body ordering to match native CLI signatures               |
+| Feature                  | Description                                                      |
+| ------------------------ | ---------------------------------------------------------------- |
+| **CORS**                 | Configurable origin control (`CORS_ORIGIN` env var, default `*`) |
+| **IP Filtering**         | Allowlist/blocklist IP ranges in dashboard                       |
+| **Rate Limiting**        | Per-provider rate limits with automatic backoff                  |
+| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s           |
+| **TLS Fingerprint**      | Browser-like TLS fingerprint spoofing to reduce bot detection    |
+| **CLI Fingerprint**      | Per-provider header/body ordering to match native CLI signatures |
 
 ### 🔌 Resilience & Availability
 

bin/_ops-common.sh

@@ -1,70 +0,0 @@
-# bin/_ops-common.sh — shared helpers for the OmniRoute ops runbook scripts.
-#
-# Sourced (not executed) by rollback.sh / snapshot-data.sh / restore-data.sh /
-# restore-policies.sh / cold-start-bench.sh — the self-hoster incident-recovery
-# and cold-start ops tooling. Each script documents its own contract via --help.
-#
-# Path resolution mirrors the app (src/lib/db/core.ts): the SQLite store is
-# $DATA_DIR/storage.sqlite and managed backups go to $DATA_DIR/db_backups
-# (overridable via DB_BACKUPS_DIR), so snapshots created here are interchangeable
-# with the ones the server writes on migrations.
-
-# Recompute the data-dir-derived paths. Called once on source, and again by
-# scripts that accept a --data-dir override.
-ops_set_data_dir() {
-  OMNIROUTE_DATA_DIR="$1"
-  OMNIROUTE_SQLITE="${OMNIROUTE_DATA_DIR}/storage.sqlite"
-  OMNIROUTE_BACKUPS_DIR="${DB_BACKUPS_DIR:-${OMNIROUTE_DATA_DIR}/db_backups}"
-}
-ops_set_data_dir "${DATA_DIR:-$HOME/.omniroute}"
-
-ops_log() { printf '[%s] %s\n' "${SCRIPT_NAME:-ops}" "$*" >&2; }
-ops_die() {
-  printf '[%s] ERROR: %s\n' "${SCRIPT_NAME:-ops}" "$*" >&2
-  exit 1
-}
-
-ops_require_cmd() {
-  command -v "$1" >/dev/null 2>&1 || ops_die "required command not found: $1"
-}
-
-# ops_confirm "<prompt>" — return 0 to proceed. Honors ASSUME_YES=1 (set by the
-# --yes flag) and REFUSES a destructive action on a non-interactive stdin unless
-# ASSUME_YES is set, so an unattended/CI invocation can never silently destroy data.
-ops_confirm() {
-  local prompt="$1" reply
-  if [ "${ASSUME_YES:-0}" = "1" ]; then return 0; fi
-  if [ ! -t 0 ]; then
-    ops_die "refusing a destructive action without a TTY; pass --yes to proceed non-interactively"
-  fi
-  read -r -p "$prompt [y/N] " reply
-  case "$reply" in
-    [yY] | [yY][eE][sS]) return 0 ;;
-    *) return 1 ;;
-  esac
-}
-
-# ops_find_snapshot <id> — resolve a snapshot identifier (a snapshot dir name,
-# a bare timestamp/sha, or an explicit path) to a directory containing
-# storage.sqlite. Echoes the resolved dir or dies.
-ops_find_snapshot() {
-  local id="$1" cand
-  [ -n "$id" ] || ops_die "snapshot id required (a timestamp/sha, dir name, or path)"
-  for cand in \
-    "$id" \
-    "$id/" \
-    "$OMNIROUTE_BACKUPS_DIR/$id" \
-    "$OMNIROUTE_BACKUPS_DIR/snapshot_$id"; do
-    if [ -f "${cand%/}/storage.sqlite" ]; then
-      printf '%s\n' "${cand%/}"
-      return 0
-    fi
-  done
-  # Fall back to a prefix match against snapshot_* dirs (e.g. a short sha/date).
-  if [ -d "$OMNIROUTE_BACKUPS_DIR" ]; then
-    for cand in "$OMNIROUTE_BACKUPS_DIR"/snapshot_*"$id"*; do
-      [ -f "$cand/storage.sqlite" ] && { printf '%s\n' "$cand"; return 0; }
-    done
-  fi
-  ops_die "no snapshot matching '$id' under $OMNIROUTE_BACKUPS_DIR (run bin/snapshot-data.sh first)"
-}

bin/cli/api-commands/agent-skills.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/agentbridge.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/api-keys.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/audio.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/chat.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/cli-tools.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/cloud.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/combos.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/compression.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/embedded-services.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/embeddings.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/fallback.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/images.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/memory.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/messages.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/models.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/moderations.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/oauth.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/playground.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/pricing.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/provider-nodes.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/providers.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/quota.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/rerank.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/responses.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/settings.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/system.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/telemetry.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";

bin/cli/api-commands/traffic-inspector.mjs

@@ -1,4 +1,4 @@
-// AUTO-GENERATED from docs/openapi.yaml. Do not edit.
+// AUTO-GENERATED from docs/reference/openapi.yaml. Do not edit.
 import { apiFetch } from "../api.mjs";
 import { emit } from "../output.mjs";
 import { readFileSync } from "node:fs";