Merge remote-tracking branch 'origin/release/v3.8.50' into HEAD

Hoisting a mid-conversation `system`/`developer` message into the top-level
`system` field carried its `cache_control` marker along. Anthropic assembles the
cache prefix as tools -> system -> messages, so the marker ended the cached
prefix at the system block and left the accumulated conversation without a
breakpoint: that turn was billed as fresh input and the next one rebuilt the
cache.

`relocateHoistedCacheBoundary` moves the marker to the nearest preceding block
that can carry a breakpoint, skipping thinking blocks, empty text and anything
the upstream normalisation discards or empties out. If that block already
carries the client's own marker, both are kept - unless the hoisted one, now
ahead of the target in `system[]`, would put a 5m breakpoint before a 1h one,
which Anthropic rejects; it is dropped in that case. Either way the breakpoint
count never grows.

normalizeClaudeUpstreamMessages rewrites tool_result and inlined file/document
blocks into plain text after the hoist, which silently discarded any marker on
them - including a relocated one. The replacement block now inherits it.

Both hoisting implementations share the helper; a fix touching only
claudeSystemRole.ts would leave extractSystemMessagesToBody broken, and the
native Claude path reaches the former through normalizeClaudeUpstreamMessages.
Capability-gated hoisting for strict providers (#7293) is unaffected.

Fixes #9436

.env.example

@@ -1414,7 +1414,7 @@ APP_LOG_TO_FILE=true
 
 # Whether call log pipeline capture stores stream chunks when enabled in settings.
 # Only applies when call_log_pipeline_enabled=true.
-# Default: false (opt-in — saves disk: stream chunks are the biggest call-log artifact)
+# Default: true
 # CALL_LOG_PIPELINE_CAPTURE_STREAM_CHUNKS=true
 
 # Maximum call log artifact size for pipeline captures, in KB.
@@ -1426,7 +1426,7 @@ APP_LOG_TO_FILE=true
 # bodies is retained in the database.
 # Used by: open-sse/handlers/chatCore.ts — cloneBoundedChatLogPayload()
 # CHAT_LOG_TEXT_LIMIT=65536                  # Max string length before truncation (default: 64 KB)
-# CHAT_LOG_ARRAY_TAIL_ITEMS=128              # Number of array items retained from tail (default: 128)
+# CHAT_LOG_ARRAY_TAIL_ITEMS=24               # Number of array items retained from tail (default: 24)
 # CHAT_LOG_MAX_DEPTH=6                       # Max nesting depth before truncation (default: 6)
 # CHAT_LOG_MAX_OBJECT_KEYS=80                # Max object keys retained (default: 80, 0 = no limit)
 
@@ -1893,7 +1893,7 @@ APP_LOG_TO_FILE=true
 
 # Log request shape (content-type + content-length) for large chat payloads.
 # Used by: src/app/api/v1/chat/completions/route.ts. Set to "0" to silence.
-# Default: disabled (opt-in).
+# Default: enabled.
 # OMNIROUTE_LOG_REQUEST_SHAPE=1
 
 # Write raw (untruncated) request/response JSON in call log artifacts.
@@ -2514,46 +2514,3 @@ QUOTA_STORE_DRIVER=sqlite              # sqlite | redis
 # URL the dashboard's "Support the project" button opens (payment/plans
 # page). No pricing/value lives in this repo — only the link.
 # RADAR_SUPPORTER_PLANS_URL=https://radar.omniroute.online/planos
-
-# ═══════════════════════════════════════════════════════════════════════════════
-# 27. RELEASE v3.8.50 ADDITIONS
-# ═══════════════════════════════════════════════════════════════════════════════
-
-# Heavy chat admission queue wait before returning retryable 503. Set 0 for the
-# legacy immediate rejection. Used by: src/shared/middleware/chatBodyAdmission.ts.
-# Default: 5000 (5 seconds)
-# OMNIROUTE_CHAT_ADMISSION_QUEUE_MS=5000
-
-# Timeout for /api/jobs/:id/run-now while it waits for an in-flight run.
-# Used by: src/app/api/jobs/[id]/run-now/route.ts. Default: 30000 (30 seconds)
-# OMNIROUTE_RUNNOW_TIMEOUT_MS=30000
-
-# Maximum request/response body size before chat-log summarization, in KiB.
-# Used by: src/lib/chatLogTruncation.ts. Default: 1024
-# CHAT_LOG_MAX_BODY_KB=1024
-
-# Adobe Firefly browser renewal and durable session cache (enabled by default).
-# Used by: open-sse/services/adobeFireflySession.ts.
-# ADOBE_FIREFLY_BROWSER_REFRESH=1
-# ADOBE_FIREFLY_SESSION_DISK=1
-# Minimum spacing between submissions and the extra pause after every third success.
-# ADOBE_FIREFLY_MIN_SUBMIT_GAP_MS=12000
-# ADOBE_FIREFLY_BATCH_EXTRA_GAP_MS=15000
-# Chrome CDP runtime used by Adobe Firefly renewal. True headless is debug-only:
-# Adobe colligo normally rejects risk tokens minted without a headed browser.
-# ADOBE_FIREFLY_CHROME_CDP_PORT=9334
-# ADOBE_FIREFLY_CHROME_VISIBLE=0
-# ADOBE_FIREFLY_CHROME_HEADLESS=0
-# ADOBE_FIREFLY_CHROME_FORCE_RESTART=0
-# ADOBE_FIREFLY_CHROME_PING=auto
-# ADOBE_FIREFLY_LOGIN_WAIT_MS=0
-# ADOBE_FIREFLY_FORTER_WAIT_MS=45000
-# Optional absolute Chrome executable; auto-detected when unset.
-# CHROME_PATH=
-
-# Telegram Mini App bridge. The update endpoint remains disabled while the bot
-# token is unset. Used by: src/lib/telegram/* and src/app/api/telegram/update/route.ts.
-# TELEGRAM_BOT_TOKEN=
-# TELEGRAM_DEFAULT_MODEL=auto/chat
-# TELEGRAM_BOT_API_BASE=https://api.telegram.org
-# TELEGRAM_WEBHOOK_TIMEOUT_MS=60000

.github/workflows/ci.yml

@@ -811,12 +811,7 @@ jobs:
 
   test-bun-sqlite:
     name: Bun SQLite Compatibility
-    strategy:
-      matrix:
-        os: [ubuntu-latest, windows-latest]
-      fail-fast: false
-    runs-on: ${{ matrix.os }}
-    continue-on-error: ${{ matrix.os == 'windows-latest' }}
+    runs-on: ubuntu-latest
     timeout-minutes: 10
     needs: changes
     if: ${{ github.event_name != 'pull_request' || (needs.changes.outputs.code == 'true' && github.event.pull_request.draft == false) }}
@@ -829,15 +824,6 @@ jobs:
           node-version: ${{ env.CI_NODE_VERSION }}
           cache: npm
       - uses: ./.github/actions/npm-ci-retry
-      - name: Install Bun (Windows)
-        if: runner.os == 'Windows'
-        shell: pwsh
-        run: |
-          powershell -c "iwr bun.sh/install.ps1 -useb | iex"
-          echo "$env:USERPROFILE\.bun\bin" | Out-File -FilePath $env:GITHUB_PATH -Append
-      - name: Install Bun (non-Windows)
-        if: runner.os != 'Windows'
-        run: npm install -g bun
       - run: npm run test:bun:db
 
   test-vitest:

.github/workflows/quality.yml

@@ -151,6 +151,63 @@ jobs:
           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
+      # #8522: --base-ref mode for PR events — compare against max(frozen, base) so
+      # inherited drift (base already over frozen cap) doesn't red an innocent PR.
+      # workflow_dispatch (no PR base) falls back to absolute comparison.
+      - name: File-size ratchet (base-relative on PR)
+        env:
+          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          if [ -n "$PR_BASE_SHA" ]; then
+            npm run check:file-size -- --base-ref "$PR_BASE_SHA"
+          else
+            npm run check:file-size
+          fi
+      - 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
+      # ── G0 (trilho .50): gates do trilho A que faltavam no trilho B ──────────────
+      # The god-file refactor happens in PRs→release/**; without these, the release
+      # rail never sees a new import cycle, dead code, duplication or a security
+      # regression until the release PR to main. Deliberately NOT brought here:
+      # bundle-size (self-skips without a build — this rail's build job is advisory
+      # and uploads nothing, so it would be dead configuration) and the coverage
+      # run (fast-unit already runs the full suite; the coverage ratchet stays on
+      # the main rail via --allow-missing in lint-guard).
+      - run: npm run check:cycles
+      - run: npm run check:lockfile
+      - name: Duplication ratchet
+        run: npm run check:duplication
+      - name: Dead-code ratchet (knip)
+        run: npm run check:dead-code
+      - name: Type coverage ratchet
+        run: npm run check:type-coverage
+      - name: Compression budget ratchet
+        run: npm run check:compression-budget
       # Security scanners — same hardened install as ci.yml quality-extended
       # (gh release download = authenticated, 5000 req/hr; curl to api.github.com
       # is rate-limited to 60/hr and silently no-ops when throttled). The blocking
@@ -194,63 +251,30 @@ jobs:
           "$HOME/.local/bin/osv-scanner" --version || true
           "$HOME/.local/bin/oasdiff" --version || true
           zizmor --version || true
-      # Quality gates (all, non-fail-fast) — #8542: replaces 17 bare check:* steps,
-      # 6 G0 gates, 4 ratchet gates, and 3 typecheck steps with a single aggregation
-      # step. Each gate runs in a loop with ::group::; failures are collected and
-      # reported at the end. set -uo pipefail (NOT set -e) so one failing gate does
-      # not abort the job and mask every later gate. Release-added gates are folded
-      # in: open-sse typecheck (#8781) and file-size base-relative mode (#8522).
-      - name: Quality gates (all, non-fail-fast)
+      - name: Secret scan (gitleaks, ratchet, blocking)
+        run: npm run check:secrets -- --ratchet
+      - name: Vulnerability ratchet (osv-scanner, ratchet, blocking)
+        run: npm run check:vuln-ratchet -- --ratchet
+      - name: Workflow lint (actionlint+zizmor, ratchet, blocking)
+        run: npm run check:workflows -- --ratchet
+      # BASE_REF is read by the script from the env (never interpolated into a
+      # shell body) — workflow-injection-safe. actions/checkout fetches remote
+      # refs, not a local branch named github.base_ref, so prefix origin/ or this
+      # gate self-skips every PR with reason=base-unresolved.
+      - name: OpenAPI breaking-change (oasdiff, ratchet, blocking)
         env:
-          # #8522: base-relative file-size mode on PR events — inherited drift (base
-          # already over frozen cap) must not red an innocent PR. Unset on
-          # workflow_dispatch (no PR base) → absolute comparison.
-          PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
           BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
-        run: |
-          set -uo pipefail
-          gates=(
-            provider-consistency fetch-targets deps file-size error-helper
-            migration-numbering public-creds db-rules known-symbols
-            route-guard-membership test-discovery test-runner-api
-            mutation-test-coverage any-budget:t11 build-scope pack-policy
-            complexity-ratchets
-            cycles lockfile duplication dead-code type-coverage compression-budget
-            # #8781: open-sse workspace typecheck gate — the workspace imports @/ which
-            # escapes to src/ via undeclared path aliases. See check-open-sse-typecheck.mjs.
-            open-sse-typecheck
-          )
-          ratchet_gates=(
-            secrets vuln-ratchet workflows openapi-breaking
-          )
-          failed=()
-          for g in "${gates[@]}"; do
-            echo "::group::check:$g"
-            # #8522: file-size is base-relative on PR events (compare against
-            # max(frozen, base)) so inherited drift doesn't red an innocent PR;
-            # workflow_dispatch (no PR base) falls back to absolute comparison.
-            if [ "$g" = "file-size" ] && [ -n "${PR_BASE_SHA:-}" ]; then
-              npm run "check:$g" -- --base-ref "$PR_BASE_SHA" || failed+=("$g")
-            else
-              npm run "check:$g" || failed+=("$g")
-            fi
-            echo "::endgroup::"
-          done
-          for g in "${ratchet_gates[@]}"; do
-            echo "::group::check:$g (ratchet)"
-            npm run "check:$g" -- --ratchet || failed+=("$g")
-            echo "::endgroup::"
-          done
-          echo "::group::typecheck:core"
-          npm run typecheck:core || failed+=("typecheck:core")
-          echo "::endgroup::"
-          echo "::group::check:dashboard-typecheck"
-          npm run check:dashboard-typecheck || failed+=("check:dashboard-typecheck")
-          echo "::endgroup::"
-          if (( ${#failed[@]} )); then
-            printf '::error::%d gate(s) failed: %s\n' "${#failed[@]}" "${failed[*]}"
-            exit 1
-          fi
+        run: npm run check:openapi-breaking -- --ratchet
+      - 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
+      # #8781: open-sse workspace typecheck gate — the workspace imports @/ which
+      # escapes to src/ via undeclared path aliases. See check-open-sse-typecheck.mjs.
+      - name: Typecheck (open-sse)
+        run: npm run check:open-sse-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

.gitignore

@@ -72,6 +72,7 @@ yarn-error.log*
 # env files (can opt-in for committing if needed)
 .env*
 !.env.example
+!.env.devin-bridge.example
 !.env.homolog.example
 # Provider API keys (never commit)
 *.api-key
@@ -171,7 +172,6 @@ config/quality/test-impact-map.json
 # GitNexus local index
 .gitnexus
 .worktrees
-bin/omniroute.mjs
 
 # Consistent with .dockerignore / .npmignore
 .omc/
@@ -201,12 +201,17 @@ scripts/i18n/_pending-keys.json
 .codegraph/
 
 # Fumadocs generated source
-.source/
+/.source/
+
+# Temporary local worktrees used to build unpublished npm tarballs
+/.deploy-build-*/
 
 # AI agent local settings and configs
 .agents/
 .antigravitycli/
 .claude/
+!tests/fixtures/devin-bridge/e2e-workspace/.claude/
+!tests/fixtures/devin-bridge/e2e-workspace/.claude/**
 
 # PR Reviews and local feedback files
 pr_reviews*.json
@@ -221,26 +226,6 @@ CODEX-SETUP-PROMPT.md
 # Quality ratchet — métricas efêmeras (baseline commitado em config/quality/; métricas não)
 config/quality/quality-metrics.json
 
-# Electron desktop build output unpacked into the repo root.
-# `electron-builder` (squirrel-windows target) unpacks the packaged app — the
-# entire Chromium runtime, ~24k files — directly into the repository root.
-# Every rule below is ROOT-ANCHORED (leading `/`) on purpose: a bare `locales/`
-# or `resources/` would also swallow tracked sources such as the CLI
-# translations in `bin/cli/locales/*.json`.
-/OmniRoute.exe
-/Uninstall OmniRoute.exe
-/uninstallerIcon.ico
-/locales/
-/resources/
-/*.pak
-/*.dll
-/icudtl.dat
-/snapshot_blob.bin
-/v8_context_snapshot.bin
-/vk_swiftshader_icd.json
-/LICENSE.electron.txt
-/LICENSES.chromium.html
-
 # Runtime logs (diretório local, nunca versionado)
 /logs/
 -home-diegosouzapw-dev-automações-bots-yt-downloader-20260504 .txt
@@ -253,7 +238,10 @@ omniroute.md
 
 # mise configuration
 mise.toml
-_artifacts/          # release-green artifacts
+# release-green artifacts (.gitignore has no inline comments — a trailing
+# `# ...` becomes part of the pattern, so it must sit on its own line).
+# Already covered by /_*/ above; kept explicit for discoverability.
+_artifacts/
 .claude-flow/
 
 # ESLint file cache (npm run lint --cache / complexity ratchets)
@@ -263,6 +251,8 @@ _artifacts/          # release-green artifacts
 
 # CI/local quality artifacts (eslint-results.json, quality-ratchet.md, etc.)
 .artifacts/
+# Isolated Devin bridge workspaces, evidence, and test databases
+.sandbox/
 
 # Homologation E2E suite (npm run homolog) — real-environment credentials + report output
 .env.homolog
@@ -270,11 +260,8 @@ tests/homolog/.auth/
 tests/homolog/ui/.auth/
 homolog-report/
 docker-compose.yml.bak
-
-# _tasks e um repo git SEPARADO (ver AGENTS.md). A linha _tasks/ (com barra) NAO
-# ignora um SYMLINK chamado _tasks; /_tasks (ancorado) cobre arquivo/symlink/dir na raiz
-# e impede que um git add -A recapture o symlink (incidente 2026-08-08).
-/_tasks
-
-# CLI local cache/state
-.playwright-cli
+.playwright-cli/
+# Playwright screenshot/log output. Today every artifact happens to land inside
+# output/**/.playwright-cli/ (covered above), but anything written directly to
+# output/ would otherwise show up as untracked.
+/output/

@omniroute/opencode-plugin/src/index.ts

@@ -4403,11 +4403,11 @@ export function buildStaticProviderEntry(
       entry.release_date = raw.release_date;
     }
 
-    // #9175: OC's `getModel` looks the model up by BARE id — the part after
-    // the first `/` in the user's request — so a dict key with an embedded
-    // provider prefix (`<providerId>/<raw-id>`) is unreachable. Keys are the
-    // raw id verbatim; ids that already contain `/` (e.g. `cc/claude-opus-4-7`)
-    // keep it because the slash is part of the upstream model id itself.
+    // OC's static-catalog reader parses each key on `/` and rejects the
+    // entire provider block if ANY key resolves to a parsed providerID that
+    // has no corresponding provider block. So bare keys (no `/`) MUST be
+    // prefixed with the resolved providerId. Already-prefixed keys
+    // (e.g. `cc/claude-opus-4-7`) are left as-is to avoid double-prefixing.
     models[raw.id] = entry;
   }
 

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

@@ -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["claude-sonnet-4-6"];
+  const claude = entry.models["opencode-omniroute/claude-sonnet-4-6"];
   assert.ok(claude, "claude model surfaced");
   assert.equal(claude.name, "claude-sonnet-4-6");
   assert.equal(claude.attachment, true);
@@ -248,7 +248,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
 
   // Combo surfaces under bare key + LCD'd
   // (gemini's reasoning=false → combo reasoning=false).
-  const combo = entry.models["claude-tier"];
+  const combo = entry.models["omniroute/claude-tier"];
   assert.ok(combo, "combo surfaced under bare key");
   assert.equal(combo.name, "Claude Tier");
   assert.equal(combo.reasoning, false, "LCD: any member reasoning=false → combo reasoning=false");
@@ -471,10 +471,10 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
   assert.ok(entry);
   const ids = Object.keys(entry.models).sort();
   assert.deepEqual(ids, [
-    "claude-sonnet-4-6",
-    "gemini-3-flash",
+    "opencode-omniroute/claude-sonnet-4-6",
+    "opencode-omniroute/gemini-3-flash",
   ]);
-  assert.equal(entry.models["claude-tier"], undefined, "no combo entry");
+  assert.equal(entry.models["omniroute/claude-tier"], undefined, "no combo entry");
   assert.ok(
     logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
     "combos-fetch breadcrumb emitted"
@@ -723,7 +723,7 @@ test("buildStaticProviderEntry: stripped per-model shape matches sibling @omniro
   }
 
   // Sanity: claude entry has all expected stripped fields.
-  const claude = block.models["claude-sonnet-4-6"];
+  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
   assert.equal(typeof claude.name, "string");
   assert.equal(typeof claude.attachment, "boolean");
   assert.equal(typeof claude.reasoning, "boolean");
@@ -748,8 +748,8 @@ test("buildStaticProviderEntry: hidden combos are excluded", () => {
     "https://or.example/v1",
     "sk-test"
   );
-  assert.equal(block.models["claude-tier"], undefined);
-  assert.ok(block.models["claude-sonnet-4-6"]);
+  assert.equal(block.models["omniroute/claude-tier"], undefined);
+  assert.ok(block.models["opencode-omniroute/claude-sonnet-4-6"]);
 });
 
 // ────────────────────────────────────────────────────────────────────────────
@@ -765,7 +765,7 @@ test("buildStaticProviderEntry: emits modalities.input from raw.input_modalities
     "https://or.example/v1",
     "sk-test"
   );
-  const claude = block.models["claude-sonnet-4-6"];
+  const claude = block.models["opencode-omniroute/claude-sonnet-4-6"];
   assert.deepEqual(claude.modalities?.input, ["text", "image"]);
   assert.deepEqual(claude.modalities?.output, ["text"]);
 });
@@ -779,7 +779,7 @@ test("buildStaticProviderEntry: never emits limit.input (OC SDK rejects it)", ()
     "https://or.example/v1",
     "sk-test"
   );
-  const claude = block.models["claude-sonnet-4-6"];
+  const claude = block.models["opencode-omniroute/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 +807,7 @@ test("buildStaticProviderEntry: emits cost when enrichment carries pricing", ()
     "sk-test",
     enrichment
   );
-  const claude = block.models["claude-sonnet-4-6"];
+  const claude = block.models["opencode-omniroute/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 +828,8 @@ test("buildStaticProviderEntry: emits release_date when raw carries it; omits wh
     "https://or.example/v1",
     "sk-test"
   );
-  assert.equal(block.models["claude-with-date"].release_date, "2026-02-19");
-  assert.equal(block.models["gemini-3-flash"].release_date, undefined);
+  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);
 });
 
 test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)", () => {
@@ -858,7 +858,7 @@ test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)
     "https://or.example/v1",
     "sk-test"
   );
-  const combo = block.models["mixed-tier"];
+  const combo = block.models["omniroute/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"]);
@@ -967,10 +967,10 @@ test("config: enrichment fetched + name overlaid on raw-model entries", async ()
     "opencode-omniroute"
   ];
   assert.ok(entry);
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
-  assert.equal(entry.models["gemini-3-flash"].name, "Gemini 3 Flash");
+  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");
   // Combo names still come from /api/combos — enrichment overlay does NOT touch combos.
-  assert.equal(entry.models["claude-tier"].name, "Claude Tier");
+  assert.equal(entry.models["omniroute/claude-tier"].name, "Claude Tier");
   assert.equal(enrichmentFetcher.callCount(), 1);
 });
 
@@ -1000,7 +1000,7 @@ test("config: features.enrichment=false skips enrichment fetch + keeps raw-id na
   assert.ok(entry);
   assert.equal(enrichmentFetcher.callCount(), 0, "enrichment fetch suppressed by feature flag");
   assert.equal(
-    entry.models["claude-sonnet-4-6"].name,
+    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "claude-sonnet-4-6",
     "raw id retained"
   );
@@ -1027,7 +1027,7 @@ test("config: enrichment fetcher throws → soft-fail (warn + raw-id static cata
   ];
   assert.ok(entry, "static block still published on enrichment failure");
   assert.equal(
-    entry.models["claude-sonnet-4-6"].name,
+    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "claude-sonnet-4-6",
     "raw id retained"
   );
@@ -1229,11 +1229,11 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
     "opencode-omniroute"
   ];
   assert.ok(
-    entry.models["claude-sonnet-4-6"],
+    entry.models["opencode-omniroute/claude-sonnet-4-6"],
     "stale snapshot hydrated into static block"
   );
   assert.equal(
-    entry.models["claude-sonnet-4-6"].name,
+    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "Claude Sonnet 4.6 (cached)",
     "stale enrichment also reused"
   );
@@ -1281,7 +1281,7 @@ test("config: cached rawEnrichment from earlier provider hook is reused (no refe
   const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
     "opencode-omniroute"
   ];
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
 });
 
 // ─────────────────────────────────────────────────────────────────────
@@ -1332,12 +1332,12 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
   ];
   assert.ok(entry);
   assert.equal(
-    entry.models["claude-sonnet-4-6"].name,
+    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
-  assert.equal(entry.models["gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
+  assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
   // Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
-  assert.equal(entry.models["claude-tier"].name, "Claude Tier");
+  assert.equal(entry.models["omniroute/claude-tier"].name, "Claude Tier");
 });
 
 test("config: providerTag=false suppresses the suffix", async () => {
@@ -1364,7 +1364,7 @@ test("config: providerTag=false suppresses the suffix", async () => {
     "opencode-omniroute"
   ];
   assert.equal(
-    entry.models["claude-sonnet-4-6"].name,
+    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "Claude Sonnet 4.6",
     "enriched name kept, provider tag suppressed"
   );
@@ -1396,7 +1396,7 @@ test("config: providerTag falls back to UPPER(alias) when providerDisplayName mi
   const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
     "opencode-omniroute"
   ];
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
+  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "CC - Claude Sonnet 4.6");
 });
 
 test("config: providerTag skipped entirely when neither providerDisplayName nor providerAlias set", async () => {
@@ -1423,7 +1423,7 @@ test("config: providerTag skipped entirely when neither providerDisplayName nor
   const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
     "opencode-omniroute"
   ];
-  assert.equal(entry.models["claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
+  assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
 });
 
 test("config: providerTag is idempotent — second hook call doesn't double-suffix", async () => {
@@ -1451,7 +1451,7 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
     "opencode-omniroute"
   ];
   assert.equal(
-    entryA.models["claude-sonnet-4-6"].name,
+    entryA.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
 
@@ -1462,7 +1462,7 @@ test("config: providerTag is idempotent — second hook call doesn't double-suff
     "opencode-omniroute"
   ];
   assert.equal(
-    entryB.models["claude-sonnet-4-6"].name,
+    entryB.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
 });
@@ -1516,7 +1516,7 @@ test("buildStaticProviderEntry: nested combo-ref context is the bottleneck acros
   );
   // Pre-fix: Parent would advertise 200_000 (only raw-big counted).
   // Post-fix: Parent should advertise 8_000 (TinyCombo bottleneck).
-  const parent = block.models["parent"];
+  const parent = block.models["omniroute/parent"];
   assert.ok(parent, "Parent combo must be in the static catalog");
   assert.equal(parent.limit?.context, 8_000);
 });

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

@@ -111,9 +111,7 @@ test("#6859: createOmniRouteProviderHook end-to-end — catalog keys/providerID
 // `opencode-omniroute`. Confirmed against the issue's own curl repro
 // (`model: "opencode-omniroute/hermes-smart-stack"` → "No active
 // credentials for provider: opencode-omniroute").
-// #9175 tightened this further: OC's `getModel` looks models up by BARE id,
-// so combo dict keys now carry NO prefix at all (not even `omniroute/`).
-test("#7976/#9175: buildStaticProviderEntry keys combos by bare slug (no prefix at all — never the OC-gate providerId)", () => {
+test("#7976: buildStaticProviderEntry keys bare-slug combo ids with the unprefixed omnirouteProviderId (no double OC-gate prefix)", () => {
   const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
   assert.equal(resolved.providerId, "opencode-omniroute");
   assert.equal(resolved.omnirouteProviderId, "omniroute");
@@ -133,7 +131,7 @@ test("#7976/#9175: buildStaticProviderEntry keys combos by bare slug (no prefix
     "sk-test"
   );
 
-  assert.deepEqual(Object.keys(block.models), ["hermes-smart-stack"]);
+  assert.deepEqual(Object.keys(block.models), ["omniroute/hermes-smart-stack"]);
   assert.equal(
     block.models["opencode-omniroute/hermes-smart-stack"],
     undefined,

AGENTS.md

@@ -627,7 +627,7 @@ procedures are in [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALI
   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` has been blocking since PR #7127.
+  `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.

Dockerfile

@@ -93,15 +93,7 @@ RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
 # 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.
-#
-# Declared as ARG+ENV, not a bare ENV: a bare ENV shadows any same-named ARG for
-# the rest of the stage, so `--build-arg OMNIROUTE_USE_TURBOPACK=0` was silently
-# ignored and the escape hatch above only ever worked via `-e` at runtime, never
-# at build time. Turbopack compiles in native Rust memory that lives outside the
-# V8 heap, so OMNIROUTE_BUILD_MEMORY_MB cannot bound it and a memory-constrained
-# build host gets SIGKILLed by the cgroup OOM killer with no error message.
-ARG OMNIROUTE_USE_TURBOPACK=1
-ENV OMNIROUTE_USE_TURBOPACK="${OMNIROUTE_USE_TURBOPACK}"
+ENV OMNIROUTE_USE_TURBOPACK=1
 
 # Next.js basePath is fixed at build time; pass OMNIROUTE_BASE_PATH here when the
 # image should serve under a reverse-proxy subpath without a runtime patch.

Makefile

@@ -1,69 +0,0 @@
-.PHONY: help install dev start build build-release lint typecheck typecheck-strict \
-        test test-unit test-vitest test-coverage test-all test-integration test-e2e \
-        check check-cycles check-docs env-sync clean
-
-# OmniRoute — convenience wrapper around the npm scripts.
-# All targets delegate to the canonical package.json scripts (single source of truth).
-
-help: ## Show this help
-	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-18s\033[0m %s\n", $$1, $$2}'
-
-install: ## Install dependencies (auto-generates .env from .env.example)
-	npm install
-
-dev: ## Dev server at http://localhost:20128
-	npm run dev
-
-start: ## Production server (requires a prior build)
-	npm run start
-
-build: ## Production build (Next.js 16 standalone)
-	npm run build
-
-build-release: ## Release build
-	npm run build:release
-
-lint: ## ESLint (0 errors expected)
-	npm run lint
-
-typecheck: ## TypeScript check (core)
-	npm run typecheck:core
-
-typecheck-strict: ## Strict check (no implicit any)
-	npm run typecheck:noimplicit:core
-
-test: ## Unit tests (Node native runner)
-	npm run test:unit
-
-test-unit: ## Alias for `test`
-	npm run test:unit
-
-test-vitest: ## Vitest (MCP server, autoCombo, cache)
-	npm run test:vitest
-
-test-coverage: ## Unit tests + coverage gate (60/60/60/60)
-	npm run test:coverage
-
-test-all: ## All suites (unit + vitest + ecosystem + e2e)
-	npm run test:all
-
-test-integration: ## Integration tests
-	npm run test:integration
-
-test-e2e: ## E2E (Playwright)
-	npm run test:e2e
-
-check: ## lint + test combined
-	npm run check
-
-check-cycles: ## Detect circular dependencies
-	npm run check:cycles
-
-check-docs: ## Validate documentation (incl. fabricated-docs)
-	npm run check:docs-all
-
-env-sync: ## Sync .env from .env.example
-	npm run env:sync
-
-clean: ## Remove build artifacts
-	rm -rf .build dist coverage .eslintcache

_tasks

@@ -0,0 +1 @@
+/home/diegosouzapw/dev/proxys/OmniRoute/_tasks

bin/cli/runtime/processSupervisor.mjs

@@ -52,11 +52,8 @@ export class ServerSupervisor {
     // silently, so a boot that never becomes ready looked like a dead hang with zero
     // output even at APP_LOG_LEVEL=debug. Pipe stdout too and buffer it alongside
     // stderr so a readiness timeout can surface what the child actually printed.
-    // #9156: macOS launchd cannot resolve bare "node" because its PATH is
-    // minimal. Always use process.execPath (the absolute path to the running
-    // Node.js binary) so the supervisor never depends on PATH resolution.
     this.child = spawn(
-      process.execPath,
+      process.versions.bun ? process.execPath : "node",
       process.versions.bun
         ? [this.serverPath]
         : buildNodeRuntimeArgs(process.env, this.memoryLimit, this.serverPath),

changelog.d/features/5696-layer-a-capability-filter.md

@@ -1 +0,0 @@
-- **feat(core):** add Layer A capability filter at router (#5696)

changelog.d/features/8468-bun-windows-ci-coverage.md

@@ -1 +0,0 @@
-- feat(ci): add windows-latest leg to test-bun-sqlite job (#8468)

changelog.d/features/9000-encrypted-reasoning-replay.md

@@ -1,2 +0,0 @@
-- Add a default-off connection setting for Codex, OpenAI, and OpenAI-compatible Responses API providers that preserves client-supplied `reasoning.encrypted_content` items for replay, including per-target combo routing.
-- Omit opaque encrypted reasoning values from persisted call logs while retaining compact diagnostic markers.

changelog.d/features/9268-gemini-schema-recursive-type-empty-choices.md

@@ -1 +0,0 @@
-- **feat(gemini):** recursive type:object injection in schema normalizer + empty choices interceptor for streaming (#9268)

changelog.d/features/9322-nanogpt-endpoint-surface.md

@@ -1 +0,0 @@
-- **feat(providers):** expanded the NanoGPT (`nano-gpt.com`) upstream provider from chat-only to the full OpenAI-compatible endpoint surface: audio transcriptions (`/api/v1/audio/transcriptions`), audio speech (`/api/v1/audio/speech`), video generation (`/api/v1/video/generations`), embeddings (`/v1/embeddings`), and the Responses API (`responsesBaseUrl` → `/api/v1/responses`) ([#9322](https://github.com/diegosouzapw/OmniRoute/issues/9322))

changelog.d/features/9415-newapi-sub2api-aggregator-balance.md

@@ -1 +1 @@
-- **feat(sse):** New-API/One-API/Sub2API aggregator balance detection for compatible provider nodes — when the "Aggregator Gateway" toggle is enabled, OmniRoute queries the aggregator's `/api/user/self` endpoint to detect the account balance; the dashboard shows a balance badge and quota-preflight routing skips exhausted accounts. Gated by the `NEWAPI_AGGREGATOR_BALANCE` feature flag (default: off), with a custom `quotaPerUnit` override for aggregators that use a different rate than the default 500000 units/$1 ([#9415](https://github.com/diegosouzapw/OmniRoute/issues/9415))
+- **sse:** New-API / One-API / Sub2API aggregator balance detection for compatible nodes — with the "Aggregator Gateway" toggle on, OmniRoute queries the aggregator's `/api/user/self` to read the account balance, shows it as a dashboard badge and lets quota-preflight routing skip exhausted accounts. Gated by the `NEWAPI_AGGREGATOR_BALANCE` feature flag (default off), with a `quotaPerUnit` override for aggregators that do not use the default 500000 units/$1 rate ([#9415](https://github.com/diegosouzapw/OmniRoute/issues/9415))

changelog.d/features/9782-modality-bridge-settings.md

@@ -1 +0,0 @@
-- **feat(settings):** add a dedicated Modality Bridge settings page with Vision controls, runtime stats, and URL-addressable Audio and Video tabs ([#9782](https://github.com/diegosouzapw/OmniRoute/pull/9782))

changelog.d/fixes/7754-best-free-fallback.md

@@ -1 +0,0 @@
-- test(combo): guard auto/best-free never leaks the combo name as a model (#7754)

changelog.d/fixes/8542-fix.plan.md

@@ -1 +0,0 @@
-- fix(ci): aggregate all fast-gates into non-fail-fast loop so one red gate no longer masks later gates (#8542)

changelog.d/fixes/8847-bun-prebuilds.md

@@ -1 +0,0 @@
-- fix(build): include better-sqlite3 prebuilds in standalone bun bundle

changelog.d/fixes/8906-quota-pool-combo-cleanup.md

@@ -1 +0,0 @@
-- **fix(quota):** Deleting a quota pool now removes its scoped managed combos without racing in-flight pool mutations ([#8906](https://github.com/diegosouzapw/OmniRoute/pull/8906)) — thanks @xiaoyaner0201

changelog.d/fixes/8951-fix.plan.md

@@ -1 +0,0 @@
-- fix(github): add targetFormat to GPT-5.6 Sol/Terra/Luna models (#8951)

changelog.d/fixes/8997-gpt56-max-reasoning.plan.md

@@ -1 +0,0 @@
-- **fix(translator):** the Responses-to-Chat promotion path called `normalizeResponsesReasoningEffort` without the model argument, so GPT-5.6 Sol/Terra/Luna requests with `reasoning.effort: "max""` were downgraded to `"xhigh"`. The model is now threaded through, preserving `max` for GPT-5.6 while keeping the legacy downgrade for older models ([#8997](https://github.com/diegosouzapw/OmniRoute/pull/8997))

changelog.d/fixes/9034-fix.plan.md

@@ -1 +0,0 @@
-- fix(api): use configured prefix instead of raw node UUID for alias-backed model id in /v1/models (#9034)

changelog.d/fixes/9057-fix.plan.md

@@ -1 +0,0 @@
-- fix(api): auto/* routing aliases bypass API-key allowedConnections/disableNonPublicModels (#9057)

changelog.d/fixes/9096-fix-audio-speech-transcriptions-translations-provider-nodes.plan.md

@@ -1 +0,0 @@
-- fix(providers): admit audio-speech/audio-transcriptions apiType in audio route provider-node filters (#9096)

changelog.d/fixes/9134-fix.plan.md

@@ -1 +0,0 @@
-- fix(providers): resolve combo names in audio transcriptions route so /v1/models stays honest (#9134)

changelog.d/fixes/9140-fix.plan.md

@@ -1 +0,0 @@
-- fix(vscode): allow built-in auto-routing models in VS Code model filter (#9140)

changelog.d/fixes/9142-fix.plan.md

@@ -1 +0,0 @@
-- fix(background): detect Anthropic top-level system prompts for background task detection (#9142)

changelog.d/fixes/9156-macos-autostart-execpath.md

@@ -1 +0,0 @@
-- fix(cli): use process.execPath for macOS launchd autostart

changelog.d/fixes/9160-fix.plan.md

@@ -1 +0,0 @@
-- fix(model-discovery): ingest capabilities.effort_tiers for synced models (#9160)

changelog.d/fixes/9168-streamed-responses-tool-null.plan.md

@@ -1 +0,0 @@
-- fix(translator): buffer and normalize upstream tool-call argument deltas so optional null values are stripped before reaching the client (#9168)

changelog.d/fixes/9177-fix.plan.md

@@ -1 +0,0 @@
-- fix(translator): avoid double-normalizing tool names in Gemini-to-Claude response path (#9177)

changelog.d/fixes/9269-fix.plan.md

@@ -1 +0,0 @@
-- **fix(classify429):** add missing `have exhausted their quota` pattern so the synthetic 429 from auth.ts is recognized as quota exhaustion, preventing the combo loop from burning retries against the same provider instead of falling back to a healthy one ([#9269](https://github.com/diegosouzapw/OmniRoute/issues/9269))

changelog.d/fixes/9305-fix.plan.md

@@ -1 +0,0 @@
-- fix(sse): broaden OMNIROUTE_SSE_COMMENTS to accept 'false','0','no' and gate metadata comment emission (#9305)

changelog.d/fixes/9306-fix.plan.md

@@ -1 +0,0 @@
-- fix(lmarena): encode SSE stream chunks as Uint8Array to prevent TextDecoder TypeError (#9306)

changelog.d/fixes/9436-claude-system-role-cache-boundary.md

@@ -0,0 +1 @@
+- **fix(sse):** hoisting a mid-conversation `system`/`developer` message into the top-level `system` field no longer carries its `cache_control` marker along, which left the conversation history without a cache breakpoint and forced a full re-read plus a rebuild on the next turn. The boundary is moved to the nearest preceding block that can carry one, and now survives the rewrites that turn `tool_result` and inlined file/document blocks into plain text; if the target block is already marked, both markers are kept unless Anthropic's TTL ordering forbids it. Both hoisting paths are fixed — `extractSystemRoleMessages` and `extractSystemMessagesToBody`. Regression guard: `tests/unit/claude-system-role-cache-boundary.test.ts`. ([#9436](https://github.com/diegosouzapw/OmniRoute/issues/9436))

changelog.d/fixes/9486-claude-400-quota.md

@@ -1 +0,0 @@
-- fix(providers): classify 400 out of extra usage as quota_exhausted for Anthropic OAuth

changelog.d/fixes/9496-kimi-k3-responses-replay.md

@@ -1 +0,0 @@
-- fix(translator): preserve authentic K3 Responses reasoning by model across providers, keep it on the matching assistant turn, and make Kimi Coding prefer client reasoning then cached replay before its empty-marker fallback (#9496)

changelog.d/fixes/9615-docker-colocate-partial-trace.md

@@ -1 +0,0 @@
-- **fix(docker):** standalone co-location now completes packages Next's file tracing materialized partially (package.json without its `main` payload) — unblocks the Docker Hub publish that failed on every v3.8.50 push with `Cannot find module '@atjsh/llmlingua-2/dist/index.js'` ([#9615](https://github.com/diegosouzapw/OmniRoute/pull/9615))

changelog.d/fixes/9623-connection-test-recovery.md

@@ -1 +0,0 @@
-- fix(resilience): failed connection test now sets a short cooldown so connections recover after transient outages (#9623)

changelog.d/fixes/9624-telemetry-cleanup-wiring.md

@@ -1 +0,0 @@
-- fix(db): wire telemetry cleanup scheduler in Next.js startup path (#9624)

changelog.d/fixes/9625-domain-cost-ms.md

@@ -1 +0,0 @@
-- fix(db): align domain_cost_history cleanup cutoff with millisecond column (#9625)

changelog.d/fixes/9626-playground-errors.md

@@ -1 +0,0 @@
-- fix(playground): surface provider model loading errors and offer retry (#9626)

changelog.d/fixes/9633-npm-build-files.md

@@ -1 +0,0 @@
-- fix(build): add build-next-isolated.mjs sibling imports to package.json files array

changelog.d/fixes/9675-anonymous-fallback-disable-toggle.md

@@ -1 +0,0 @@
-- **fix(providers):** new per-provider `noAuthFallbackDisabledProviders` setting lets operators disable the synthetic anonymous (no-auth) credential fallback for API-key providers whose static definition declares `anonymousFallback: true` (e.g. `opencode-go`, `opencode-zen`) — upstream endpoints now reject anonymous requests with `401 Missing API key`, so the fallback added latency and caused UI health/reconnect churn. Real keyed connections keep working and recover automatically once quota state clears; true no-auth providers (`opencode`, `mimocode`, …) are unaffected, with `blockedProviders` remaining their disable mechanism. Default behavior is unchanged ([#9675](https://github.com/diegosouzapw/OmniRoute/pull/9675))

changelog.d/fixes/9695-docker-bundler-build-arg.md

@@ -1 +0,0 @@
-- **fix(docker):** `--build-arg OMNIROUTE_USE_TURBOPACK=0` now reaches the builder stage — a bare `ENV` was shadowing the `ARG`, so the documented webpack escape hatch was silently ignored and memory-constrained hosts were OOM-killed with no error output ([#9695](https://github.com/diegosouzapw/OmniRoute/pull/9695))

changelog.d/fixes/9719-combo-connection-pins.md

@@ -1 +0,0 @@
-- fix(db): clear stale combo connection pins when provider connections are deleted (#9719)

changelog.d/fixes/9730-persist-rtk-renderers.md

@@ -1 +0,0 @@
-- fix(compression): persist `enableRenderers` through `normalizeRtkConfig` so RTK renderer settings survive a DB round-trip ([#9730](https://github.com/diegosouzapw/OmniRoute/pull/9730))

changelog.d/fixes/9737-memory-id-route-backend.md

@@ -1 +0,0 @@
-- Fixed `GET`/`PUT`/`DELETE /api/memory/[id]` always failing with a 500 (`Primary backend "sqlite" not registered`) when the route was reached before any other memory endpoint in the same process.

changelog.d/fixes/9737-route-body-validation.md

@@ -1 +0,0 @@
-- Replaced hand-rolled body type checks with Zod validation in the plugins marketplace install route and the three Dario admin routes, restoring the `t06:route-validation` gate (Hard Rule #7).

changelog.d/fixes/9737-vietnamese-locale-parity.md

@@ -1 +0,0 @@
-- Restore Vietnamese locale parity after the entity-normalization sync dropped Radar, provider, and mini-playground messages.

changelog.d/fixes/9788-model-catalog-gateway-permissions.md

@@ -1 +0,0 @@
-- **fix(api):** Model catalogs no longer expose functional gateway mirrors unless the API key permits the mirror's final public model ID ([#9788](https://github.com/diegosouzapw/OmniRoute/pull/9788)) — thanks @xz-dev

changelog.d/fixes/9826-command-code-responses-usage.md

@@ -1 +0,0 @@
-- **fix(executors):** preserve Command Code usage in `/v1/responses` streams so Codex clients receive real input, output, cache, and reasoning token counts ([#9826](https://github.com/diegosouzapw/OmniRoute/pull/9826)) — thanks @MrShitFox

changelog.d/fixes/9828-codex-redundant-oneof-enum.md

@@ -1 +0,0 @@
-- **fix(executors):** prevent intermittent Codex `upstream_empty_response` errors for tool schemas that combine `oneOf` const branches with a matching sibling `enum` by removing only the semantically redundant `oneOf`; bare, narrowing, non-matching, and type-discriminated `oneOf` schemas remain unchanged. ([#9828](https://github.com/diegosouzapw/OmniRoute/pull/9828))

changelog.d/fixes/9834-cursor-selected-image-blobid.md

@@ -1 +0,0 @@
-- **fix(cursor):** SelectedImage uses `blobIdWithData` + session blobStore, with JPEG soft-cap prep via sharp ([#9834](https://github.com/diegosouzapw/OmniRoute/pull/9834)) — thanks @yansigit

changelog.d/fixes/i18n-cc-alias-unclosed-tags.md

@@ -1 +0,0 @@
-- fix(i18n): re-escape CC discovery-alias `claude/<provider>/<model>` to HTML entities so next-intl stops logging INVALID_MESSAGE: UNCLOSED_TAG on provider detail pages (#8747 regression)

changelog.d/fixes/release-v3850-base-drifted-test-expectations.md

@@ -1 +0,0 @@
-- **fix(test):** reconcile test expectations that drifted from the code they guard on `release/v3.8.50` — auth/vision/provider schema snapshots, and three context-aware combo compatibility assertions that contradicted the same file's own stated contract (catalog-too-small targets stay available as runtime fallback rather than being dropped). The combo assertions were masked by an unresolved import that stopped `combo.ts` from loading at all, so they only become reachable once that import is repaired.

changelog.d/fixes/release-v3850-post-sweep-locale-lint.md

@@ -1 +0,0 @@
-- Repair release-sweep regressions in locale and environment contracts, package metadata, scripts, dependency, size and dead-code ratchets, OpenAPI coverage, Telegram error sanitization, Openference public-credential handling, DB-module classification, resilience UI test assertions, strict CodeBuddy CN tests, Lite compression typing, and the job-registry migration number.

changelog.d/fixes/release-v3850-validator-test-masking-timeout.md

@@ -1 +0,0 @@
-- Let the release-green validator finish the test-masking gate on loaded runners while preserving the existing timeout for every other full-CI gate, and report Node.js `ETIMEDOUT` errors as explicit timeout failures.

changelog.d/maintenance/9614-opencode-plugin-bare-key-suite.md

@@ -1 +0,0 @@
-- **test(cli):** OpenCode plugin suite realigned to the bare-key static-catalog contract from #9178/#9175 (21 tests were red on every opencode-plugin CI run; 287/287 after) ([#9614](https://github.com/diegosouzapw/OmniRoute/pull/9614))

changelog.d/maintenance/9738-deadcode-radar-referrals.md

@@ -1 +0,0 @@
-- Removed the unused `RadarReferrals` type export left by the radar referral-links feature (#9697), returning the dead-code ratchet to its 227 baseline.

changelog.d/maintenance/9839-v3850-quality-ratchets.md

@@ -1 +0,0 @@
-- Reconcile the final v3.8.50 bundle-size and file-size ratchets against the measured release tip, preserving exact direction-down ceilings and their source attribution.

config/quality/dependency-allowlist.json

@@ -44,7 +44,6 @@
     "commander",
     "concurrently",
     "cross-env",
-    "cron-parser",
     "csv-stringify",
     "ctrf",
     "dompurify",
@@ -97,7 +96,6 @@
     "node-machine-id",
     "omniglyph",
     "open",
-    "opencode-ai",
     "ora",
     "parse5",
     "pino",
@@ -115,7 +113,6 @@
     "recharts",
     "safe-regex",
     "selfsigned",
-    "sharp",
     "size-limit",
     "smol-toml",
     "socks",

config/quality/eslint-suppressions.json

@@ -81,7 +81,7 @@
   },
   "open-sse/handlers/search.ts": {
     "@typescript-eslint/no-explicit-any": {
-      "count": 33
+      "count": 34
     }
   },
   "open-sse/handlers/sseParser.ts": {
@@ -1673,7 +1673,7 @@
   },
   "tests/unit/base-executor-sanitize-effort.test.ts": {
     "@typescript-eslint/no-explicit-any": {
-      "count": 6
+      "count": 48
     }
   },
   "tests/unit/batch-deletion.test.ts": {
@@ -2036,6 +2036,11 @@
       "count": 3
     }
   },
+  "tests/unit/codebuddy-cn-provider.test.ts": {
+    "@typescript-eslint/no-explicit-any": {
+      "count": 3
+    }
+  },
   "tests/unit/codex-banked-reset-credits-5199.test.ts": {
     "@typescript-eslint/no-explicit-any": {
       "count": 7
@@ -3334,4 +3339,4 @@
       "count": 5
     }
   }
-}
+}

config/quality/file-size-baseline.json

@@ -1,8 +1,4 @@
 {
-  "_rebaseline_2026_08_09_9296_adobe_media_capabilities": "PR #9296 (artickc, fix/adobe-firefly-model-capabilities) own growth: src/app/api/v1/models/catalog.ts 1590->1597 (+7). The image and video catalog serializers now expose the already-normalized Adobe Firefly discovery capability data (media_capabilities, plus the existing video modality/size fields) at their only response-emission chokepoints. The discovery parser and capability normalization remain in open-sse/services/adobeFireflyModels.ts; extracting these seven serialization fields would obscure the catalog contract. Covered by tests/unit/adobe-firefly.test.ts and tests/unit/image-upscale.test.ts.",
-  "_rebaseline_2026_08_08_v3850_base_drift_batch_9757": "Base drift on release/v3.8.50, not own growth: the 08-06..08-08 merge batches grew 12 already-frozen (or newly-landed) files without carrying their rebaselines — the dedicated rebaseline PR #9616 was closed as 'superseded' but its file-size entries never actually reached the base, and later merges (#8894 combos page, #9539 EditConnectionModal, #8895 models route, #9294/#9293 catalog, #9541 db/core, #8970 tokenHealthCheck, #8925 mcp schemas+server, #8890 accountFallback, #9467 chat.ts, #8931 openai-to-kiro, ProxyRegistryManager) kept growing them. All 12 values re-measured on THIS branch's tree (= pure tip + this PR's 1-line chat.ts fix, which adds zero lines). This PR's own source changes (chat.ts identifier restore, stream.ts format carve-out) do not grow any frozen file past these values.",
-  "_rebaseline_2026_08_08_migration_135_collision": "fix(db): resolve migration version 135 numbering collision — #9449's 135_connection_runtime_state.sql and #8908's 135_migrate_model_capability_max_token.sql both claimed version 135 (#9449 branched before #8908 merged and never got renumbered before landing on release/v3.8.50), which threw 'Migration version collision detected' the moment ANY code touched the database — a fresh install/deploy from this tip cannot even boot. Renumbered the later-landing file to 140 (next free slot) and added the matching isSchemaAlreadyApplied('140') retroactive guard, matching the established pattern already used for the prior 135/136 -> 137/138 renumber in the same file. Own growth: src/lib/db/migrationRunner.ts 1084->1094 (+10, the new case block) — irreducible, matches the existing per-case guard pattern exactly. Covered by tests/unit/migration-135-numbering-collision.test.ts (2/2), confirmed failing (reproducing the exact live crash) against the pre-fix colliding filenames, passing after.",
-  "_rebaseline_2026_08_08_9183_reasoning_cache_index_sync": "Extracted fix(responses-api): sync reasoning-cache write index with the fixed read side (from the originally-authored #9183) — chatCore.ts's write side cached every response under a hardcoded messageIndex:0, and translator/index.ts's plain-turn (non-tool-call) cache-key lookup ALSO still hardcoded messageIndex 0 at its call site (a second, previously-undiscovered instance of the same hardcoding bug, found while re-verifying this fix against the current upstream tip — the two never agreed once a conversation went past its first assistant turn, so DeepSeek/Xiaomi-mimo plain-turn reasoning replay silently missed the cache). Own growth: open-sse/handlers/chatCore.ts 5034->5042 (+8, computing messageIndex from the incoming request's message count at both the streaming and non-streaming cache-write call sites) — irreducible call-site wiring. Covered by tests/unit/reasoning-cache.test.ts (new end-to-end write/read regression test, rebaselined below) and tests/unit/translator-helper-branches.test.ts fixture updates. Other #9183 sub-fixes (output_index collision prevention, reasoning-content-alias generalization) were originally assumed already superseded by upstream's own independent fix — a live incident 2026-08-08 disproved that for the message-vs-tool-call collision case specifically (fixed separately in #9822); not re-extracted here since this PR's own scope is the narrower messageIndex sync only.",
   "_rebaseline_2026_08_02_9259_rolling_rpm": "PR #9259 (issue #8733) own growth: open-sse/services/rateLimitManager.ts baseline 1060->1167 (+107; final source 1153). The existing withRateLimit chokepoint now composes process-local rolling RPM leases with Bottleneck admission, releases pre-dispatch leases on queue timeout/abort/connection disable, preserves caller abort reasons, and wires 429/header state into the extracted rollingRpmGate.ts. The remaining growth is irreducible lifecycle wiring at the dispatch boundary plus the real watchdog test hooks needed to verify queued-wedge recovery; moving it further would obscure lease ownership and Bottleneck cleanup. Covered by the focused rate-limit manager/sliding-window suite (33/33); distributed multi-instance coordination remains explicitly out of scope.",
   "_rebaseline_2026_07_24_8470_hyperagent_sticky_thread": "PR #8470 (artickc, fix/hyperagent-tool-loop-thread-sticky) own growth: open-sse/executors/hyperagent.ts 936->1025 (wc -l; check-file-size.mjs counts via split(\"\\n\").length so the gate sees 937->1026, +89, crosses the 1000 cap). Fixes a real bug where a reverse-conversion proxy (text-Intent/JSON to Claude Code native tool_calls) rewrites assistant messages between agentic tool-loop turns, breaking HyperAgent’s conversation-prefix fingerprint and cold-starting the thread mid tool-loop. Adds Anthropic tool_use/tool_result flattening to extractMessageText() plus a new rootUserFingerprint()/root-key lookup tier in resolveHyperAgentThreadBinding()/storeHyperAgentThreadAfterTurn() so the thread stays sticky across the tool loop. Cohesive additions inside the existing single-file executor; not extractable without splitting the executor mid-request-flow. Covered by tests/unit/executor-hyperagent.test.ts (19/19, +5 new cases for tool_result/tool_use flattening + root-key stickiness). Pre-merge review flagged a cross-conversation root-key collision risk (tracked in the PR’s own mandatory pre-merge checklist, not yet addressed) — unrelated to this file-size ratchet, tracked separately by /fix-prs.",
   "_rebaseline_2026_07_25_8494_capability_filter_fail_closed": "PR #8494 (fix/capability-filters-fail-closed, #8488) own growth: open-sse/services/combo.ts 3640->3693 (+53) adds a fail-closed guard after filterTargetsByRequestCompatibility() — when every eligible target is excluded by request-capability filtering (vision/tools/etc) instead of quota/health, the combo now returns an explicit `capability_mismatch` 400 (describeCapabilityFilterExhaustion, imported from combo/comboStructure.ts) rather than silently falling through to a generic no-targets error, plus a `compatFilterFailOpen` escape hatch (combo config OR settings) mirrored at both the main/auto and round-robin call sites for symmetry. combo/comboStructure.ts (previously under cap, un-frozen) grows 794->918 (+124) — new home for describeCapabilityFilterExhaustion + providerSupportsEmulatedToolCalling (#5240 emulated tool-calling exemption so fail-closed does not regress prompt-emulation-only combos like all-chatgpt-web). Irreducible orchestration wiring at the existing filter chokepoint (same precedent as #7301's universal-cooldown-retry generalization). Companion test tests/unit/combo-routing-engine.test.ts 3409->3449 (+40, fail-closed/fail-open coverage across both call sites) also rebaselined. Covered by tests/unit/8488-capability-filter-fail-closed.test.ts (new) + 95/95 passing across both files. Structural shrink of combo.ts tracked in #3501.",
@@ -18,6 +14,7 @@
   "_rebaseline_2026_07_19_7546_ghe_copilot_route": "PR #7546 (GHE Copilot OAuth provider) own growth: oauth/[provider]/[action]/route.ts 960->963 (gate units, +3 = ghe-copilot device-code wiring at the existing multi-provider device-code branch — reading + HTTPS-validating the gheUrl search param (isValidGheUrl guards at both raw entry points, security-review hardening, 963->970), adding ghe-copilot to the no-PKCE provider set, and building the provider config override / threading gheUrl through poll->postExchange extraData). Mirrors the existing kiro/amazon-q startUrl override pattern right above it in the same branch; cohesive with the existing device-code dispatch chokepoint, not separately extractable without splitting a single provider-switch mid-branch. Frozen so can only shrink; structural shrink tracked in #3501.",
   "_rebaseline_2026_07_19_6846_nvidia_concurrency_gate": "Issue #6846 Phase 1 (nvidia NIM local RPM budget + per-model lockout + per-connection concurrency cap) own growth: open-sse/executors/default.ts 877->890 (+13 = the irreducible call-site wiring at DefaultExecutor.execute(), the only place nvidia requests dispatch through — the existing session-pool body was extracted verbatim into a new private executeWithSessionPool() so the outer execute() can wrap it in the nvidia concurrency-gate acquire/finally-release). All actual gating logic (semaphore key + cap resolution) lives in the new leaf open-sse/executors/default/nvidiaConcurrencyGate.ts (not frozen, well under cap). Covered by tests/unit/nvidia-quota-phase1.test.ts.",
   "_rebaseline_2026_07_18_v3849_provider_detail_wiring": "Merge campaign R2/R3 (2026-07-18): three authorized PRs each add irreducible call-site wiring to ProviderDetailPageClient.tsx — #7360 +5 (ProviderQuotaVisibilityToggle render, component extracted), #7419 +4 (NoAuthProviderControls wiring), #7062 +3 (Dahl provider hook) = 786->798. All three follow the extracted-component pattern (AgentrouterConsoleFields precedent); the frozen file only takes the wiring. Structural shrink tracked in #3501.",
+  "_rebaseline_2026_07_25_dario_upstream_proxy_selector": "PR #8523 (Dario embedded service): upstream-proxy mode selector replaces the binary CLIProxyAPI toggle with Native/CLIProxyAPI/Dario/Fallback + a fallback-backend picker. ProviderDetailPageClient.tsx 798->804 (+6, new hook fields threaded through to ConnectionsListPanel), ConnectionRow.tsx 942->958 (+16, the mode <select> + conditional fallback-backend <select> replacing a single pill button), useProviderConnections.ts 954->986 (+32, upstreamProxyMode/upstreamProxyFallbackBackend state + handleSetUpstreamProxyMode, handleToggleCliproxyapiMode kept as a thin backward-compat wrapper for the existing hook-shape test). All additive UI/state for the new modes — no unrelated refactor.",
   "_rebaseline_2026_07_18_pr7653_chat_tracker_import": "PR #7653 merge-interaction growth: release moved chat.ts to its 1796 cap while this PR adds the single side-effect import 'quotaTrackersBatch.ts' (line 130) — chat.ts IS the canonical quota-fetcher registration point (codex/bailian/deepseek/openrouter/opencode/generic all import+register there), so the +1 is irreducible call-site wiring. 1796->1797. Covered by tests/unit/{agentrouter,v0,freemodel}-quota-fetcher.test.ts.",
   "_rebaseline_2026_07_17_pr7653_agentrouter_console_fields": "PR #7653 own growth (missing acceptance criterion: the AgentRouter quota tracker (#6850) read providerSpecificData.consoleApiKey/newApiUserId but neither field had dashboard UI for provider agentrouter — consoleApiKey was gated to bailian-coding-plan only and newApiUserId had zero UI). AddApiKeyModal.tsx 961->967 (+6) and EditConnectionModal.tsx 1278->1286 (+8) = import + a single <AgentrouterConsoleFields .../> render call plus the newApiUserId formData init field. The actual Input rendering (both consoleApiKey reuse + the new newApiUserId field) was EXTRACTED into a new leaf src/app/(dashboard)/dashboard/providers/[id]/components/modals/AgentrouterConsoleFields.tsx (48 LOC, <cap), mirroring the QuotaScrapingFields.tsx / GlmTeamQuotaFields.tsx precedent (#6351) so the frozen modals only carry the irreducible call-site wiring. Persist logic lives in connectionProviderSpecificData.ts (not frozen). Covered by tests/unit/agentrouter-connection-modal-fields.test.ts.",
   "_rebaseline_2026_07_17_v3849_6842_free_window_wiring": "PR #7651 (openrouter :free-window quota tracking) follow-up: the counter shipped built but never wired into the request pipeline, so combos kept spending guaranteed-429 requests on exhausted free-tier targets. Own growth: src/sse/services/auth.ts 2461->2462 (+1, irreducible at the existing model-aware preflight chokepoint — the `provider === \"codex\"` check that forwards requestedModel into the connection arg is extended to also cover `openrouter`, one added boolean + a doc comment, offset to a single net line by dropping the now-redundant inline condition). Enforcement itself lives in open-sse/services/openrouterQuotaFetcher.ts (not frozen) and the dispatch-time record/correct hooks live in open-sse/executors/base.ts (not frozen). Covered by tests/unit/openrouter-free-window-wiring-6842.test.ts.",
@@ -162,13 +159,135 @@
   "_rebaseline_2026_06_20_1409_1294_models": "Re-baseline src/lib/db/models.ts 1184->1221: combined growth of sibling fixes #1409 (cascade-delete orphaned model aliases when a provider is removed) + #1294 (persist max_input_tokens/max_output_tokens on custom models), both adding CRUD at the existing models domain module. Cohesive db module; not extractable.",
   "_rebaseline_2026_06_20_4389_thinking_toolchoice": "Re-baseline base.ts 1387->1399 (#4389): tool_choice-forced thinking guard at the existing Claude wire-image injection chokepoint (effThinking gate avoids the Anthropic 400 when tool_choice forces a tool). Cohesive guard; structural shrink tracked in #3501.",
   "_rebaseline_2026_07_18_6979_codex_test": "PR #6979 own growth: executor-codex.test.ts 1340->1347 (+7 = generalized ensureThinkingBudget assertion added to the existing codex thinking-budget cases). antigravity-test bump 942->977 REVERTED here: #7408's test split dropped that file to 888, so this PR's +35 fits under the original 942 frozen cap.",
-  "_rebaseline_2026_07_24_8354_logs_timeline_sidebar": "PR #8354 (hartmark, feature/scrolling-log) own growth: src/shared/constants/sidebarVisibility/sections.ts 812->820 (+8, the single new logs-timeline SidebarItemDefinition entry added to LOGS_GROUP.items for the new /dashboard/logs/timeline scrolling request-timeline page). Irreducible data-literal wiring at the existing sidebar-sections chokepoint, same shape as every other item in the file; not extractable without an ad-hoc single-item exception to the file's otherwise-uniform multi-line item style.",
-  "_rebaseline_2026_08_09_v3850_post_sweep_tip": "Release-captain reconciliation of absolute file-size drift on pure tip 382449d593 after the authorized cherry-pick wave. The affected production growth already belongs to merged, tested commits: Adobe Firefly CDP/session recovery (#9881), model capability serialization (#9296), Modality Bridge request wiring (#9759), disconnect-grace/reasoning-cache chatCore wiring (#9653/#9183), stacked Lite precedence, and Responses tool-call index/argument handling (#9843 plus the release translator fixes). This repair adds only the compact migration-146 retroactive guard, covered by db-job-registry-migration-renumber-139.test.ts. Values are the exact check:file-size split-newline measurements and remain shrink-only; structural decomposition remains tracked by the existing #3501 notes.",
   "cap": 1000,
+  "frozen": {
+    "_rebaseline_2026_06_22_4644_deepseek_web_tools": "PR #4644 (BugsBag/robust deepseek-web tool-call parsing): open-sse/executors/deepseek-web.ts 1117->1125 (+8). The new agentic tool-call path emits surrounding text + reasoning before tool_calls and swaps to the dedicated deepseekWebTools.ts parser; the +8 lines are cohesive wiring at the existing transformSSE chokepoint (the parser itself lives in the new deepseekWebTools.ts file, already under cap). The PR's own fast-gate (PR->release) does not run check:file-size, so this surfaced only at release reconcile. Covered by tests/unit/deepseek-web-tools-variants.test.ts + deepseek-web-tools-execute.test.ts.",
+    "_rebaseline_2026_06_23_4712_deepseek_web_tool_results": "PR for #4712 (deepseek-web drops role:tool): open-sse/executors/deepseek-web.ts 1125->1148 (+23). messagesToPrompt() now folds role:\"tool\" results into the single-prompt transcript (recovering the tool name from the preceding assistant tool_calls by tool_call_id) instead of silently dropping them; the lines are cohesive wiring inside the existing function. Covered by tests/unit/deepseek-web-tool-result-prompt-4712.test.ts.",
+    "_rebaseline_2026_06_24_headroom_strategy": "Headroom-aware connection selection (dario technique): combo.ts 3168->3180 (+12 = a new `else if (strategy === \"headroom\")` dispatch branch in handleComboChat that delegates to orderTargetsByHeadroom + its log line, plus the import). The actual logic lives OUT of the god-file: the pure ranker rankByHeadroom/computeHeadroom is the new leaf open-sse/services/combo/headroomRanking.ts (91 LOC, <cap) and the async orderer orderTargetsByHeadroom is appended to the existing open-sse/services/combo/quotaStrategies.ts (<cap) next to its sibling reset-aware/reset-window orderers (reuses their connection-expansion machinery). headroom = 1 - max(util_5h, util_7d) from getSaturation (src/lib/quota/saturationSignals.ts), prefers the connection with the most free capacity. Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. fill-first stays default; all existing strategies untouched. Covered by tests/unit/combo-headroom-ranking.test.ts (pure helper) + tests/unit/combo-headroom-strategy.test.ts (orderer, saturation injected). Structural shrink of combo.ts tracked in #3501.",
+    "_rebaseline_2026_06_24_quota_share_strategy": "Dedicated quota-share strategy (Phase 3 #9): combo.ts 3180->3190 (+10 = one new `else if (strategy === \"quota-share\")` dispatch branch in handleComboChat that delegates 100% to selectQuotaShareTarget + its log line, plus the import). All the new logic lives OUT of the god-file in two new leaves under open-sse/services/combo/: quotaShareInflight.ts (in-flight counter with TTL/lease, ~150 LOC <cap) and quotaShareStrategy.ts (per-model bucket gating via isBucketSaturated + DRR proportional to weight + P2C over in-flight, ~240 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the headroom/reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. ZERO existing strategy cases were modified — only this branch was added, and the qtSd/ combos switched from fill-first to quota-share in src/lib/quota/quotaCombos.ts. Covered by tests/unit/quota-share-strategy.test.ts (gating, DRR fairness, P2C in-flight, fail-open, activation). Structural shrink of combo.ts tracked in #3501.",
+    "_rebaseline_2026_06_24_task_aware_routing": "Task-aware routing strategy (port PR #2045, OmniRoute #4945): combo.ts 3190->3225 (+35) = one new `else if (strategy === \"task-aware\")` dispatch branch delegating 100% to selectTaskAwareTarget + its imports/log lines. All scoring/classification logic lives OUT of the god-file in the new leaf open-sse/services/taskAwareRouting.ts (553 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors quota-share/headroom/reset-aware branches). ZERO existing strategy cases modified. Covered by tests/unit/combo-task-aware.test.ts (35 tests). Structural shrink of combo.ts tracked in #3501.",
+    "_rebaseline_2026_06_26_fidelity_gate_extraction": "Milestone-B fidelity-gate wiring residual: bodyToText+gateAdvance extracted to fidelityGateStep.ts (889->854, -35), but the StackOptions.fidelityGate field, the `const fidelityGate` reads at the two stacked-loop dispatch chokepoints, and the import of FidelityGateConfig are irreducible wiring that cannot leave strategySelector without an architectural refactor of the pre-existing stacked pipeline. Net: 889->854 (+6 vs the pre-Milestone-B frozen 848). Covered by tests/unit/compression/*.test.ts (940 pass).",
+    "_rebaseline_2026_06_27_5193_5203_antigravity_oauthmodal": "Antigravity remote-login own growth: OAuthModal.tsx 960->969 (gate units). #5193 (+~4: remote paste instruction shown for all remote incl. Google + its rationale comment) and #5203 (+~5: handleManualSubmit credential-blob branch + button guard; submit logic extracted to oauthBlobSubmit.ts to minimize). Frozen set to the SUM so either merge order passes. Cohesive at the existing manual-submit chokepoint.",
+    "_rebaseline_2026_06_27_5193_antigravity_basered": "Base-red (pre-existing release drift, fast-gate PR->release skips check:file-size): accountFallback.ts 1773->1777 and src/app/api/providers/[id]/test/route.ts 924->940 were already over their frozen caps on release/v3.8.39 independent of any antigravity change. Owner chose to rebaseline (keep the documented issue-reference comments #1846/#1449/#347 etc.) rather than accept the contributor comment-stripping in #5200/#5198. Reverted #5200 to restore the comments; bumped these two frozen caps to the actual base sizes. No logic change.",
+    "_rebaseline_2026_06_28_5237_impersonation_ua_refresh": "PR #5237 (refresh impersonation UAs): grok-web.ts 1871->1873 (+2), muse-spark-web.ts 1284->1302 (+18), perplexity-web.ts 1013->1032 (+19). Net semantic change in each file is a single User-Agent constant (Chrome 147->149 for grok/muse; perplexity kept at Firefox 148 to stay matched with the firefox_148 TLS profile — the contributor's 152 bump was reverted to avoid a UA-vs-JA3 mismatch, #2459). The growth is Prettier reflow that lint-staged unavoidably applies to these grandfathered long-line files the moment they are touched; not extractable. src/sse/services/auth.ts 2336->2401 in the same reconcile is #5222's antigravity-LRU-retry growth that merged via --admin without a baseline bump.",
+    "_rebaseline_2026_06_28_5243_risk_gate_prepass": "PR #5243 (compression risk-gate pre-pass) own growth: open-sse/services/compression/strategySelector.ts 854->899 (+45). The three exported entry points (applyCompression/applyStackedCompression/applyStackedCompressionAsync) become thin wrappers over pure-extracted private bodies (runCompression/runStackedCompression/runStackedCompressionAsync) so the risk-gate mask->run->restore wrapper sits strictly OUTSIDE the per-step loop — a single universal integration point. The wrapper logic itself (resolveRiskGate/withRiskGate) lives in the new riskGate/strategyWrap.ts (<cap); the residual growth is the duplicated thin-wrapper signatures + the extracted bodies' dispatch boundary, guarded by a byte-identical parity test (riskGateIntegration). Default off (DEFAULT_COMPRESSION_CONFIG unchanged). Not extractable without hiding the dispatch boundary, mirroring prior compression rebaselines. Structural shrink tracked in #3501.",
+    "_rebaseline_2026_06_28_5275_correlation_id_extract": "Extraction of the safe CorrelationId subset of #5275 (hartmark) — request correlation id stored in call_logs (migration 109) and returned via the X-Correlation-Id response header, WITHOUT the combo/resilience or build/lazy-loading changes (those stay in #5275). Own growth: callLogs.ts 975->985 (correlation_id column on CallLogSummaryRow + read/map), usageHistory.ts 983->988 (correlationId metadata normalize), chat.ts 1575->1632 (withCorrelationId response wiring + combo-failure log carrying correlationId), chatHelpers.ts new 811 (withCorrelationId helper + reqId threading; was 791<cap pre-feature). Cohesive request/logging chokepoint wiring; structural shrink of chat.ts tracked in #3501.",
+    "_rebaseline_2026_06_29_4038_cas_guard": "PR (#4038) own growth: tokenRefresh.ts 2103->2181 (+78 = the compare-and-swap guard on the refresh persist — runWithCasGuard/getActiveCasGuard AsyncLocalStorage pair mirroring runWithOnPersist, casGuardShouldSkipPersist that rereads the row right before persisting and skips the write when a concurrent writer already rotated the refresh_token past the one presented, plus getCasGuardStats counters). Fixes the sibling-rotation-revert → token-family-revocation storm. Gated behind an active guard (opt-in; no guard => byte-identical). Wiring lives at the two persist chokepoints inside getAccessToken; the comparison reuses wasRefreshTokenRotated from refreshSerializer. Not extractable without splitting the refresh hot path.",
+    "_rebaseline_2026_06_29_5286_memoization": "PR #5286 own growth: strategySelector.ts 899->960 (+61 = the opt-in result-memoization branches in applyCompression/applyCompressionAsync — principal+determinism gate, makeMemoKey lookup/store with model+supportsVision folded into the key, recompute-with-memo-off). Default off (memoizeCompressionResults), so zero behavior change. The memo helpers live in the leaf resultMemo.ts (<cap); the chokepoint wiring here is not extractable. Structural shrink of this hot-path file tracked in #3501.",
+    "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
+    "_rebaseline_2026_07_02_5816_qoder": "PR #5816 (@AgentKiller45, qoder PAT via qodercli): qoderCli.ts 666->989, new-above-cap frozen (owner-approved baseline freeze). The growth is the legitimate PAT job-token exchange + quota parsing CLI transport (the pure-JS Cosy path 500'd on every PAT request); extracting the spawn/parse helpers now would just add indirection to a contributor PR mid-merge. Test frozen also raised for this PR's coverage growth: providers-page-utils.test.ts 1052->1092. Additionally clears an inherited base-red from the already-merged #5933 (codex json_schema->text.format): translator-openai-responses-req.test.ts 1097->1172 (+75 regression tests, no offending branch left). All remain frozen (cannot grow further); release captain's rebaseline-at-release supersedes.",
+    "_rebaseline_2026_07_09_6126_clinepass_dual_auth": "PR #6126 (@hajilok, dual-auth ClinePass) own growth: tokenRefresh.ts 2181->2182 (+1 = a single `case \"clinepass\":` fallthrough label added to the existing `case \"cline\":` in _getAccessTokenInternal's provider switch, so clinepass token refresh dispatches to the already-shared refreshClineToken() instead of silently falling through to the generic OAuth refresh). Irreducible 1-line switch-case wiring at the existing chokepoint; the header-building logic for the same feature was extracted to a new leaf src/shared/utils/clineAuth.ts::buildClinepassHeaders() (well under cap) to avoid growing open-sse/executors/default.ts. Covered by tests/unit/clinepass-provider.test.ts.",
+    "_rebaseline_2026_07_09_6363_kiro_external_idp": "PR #6363 (@artickc, Kiro external IdP) own growth: tokenRefresh.ts 2182->2249 (+67 = the external_idp refresh branch inside refreshKiroToken — standard public-client OAuth2 refresh_token grant against the org IdP tokenEndpoint via buildExternalIdpRefreshParams/isExternalIdpAuthMethod from the new leaf open-sse/services/kiroExternalIdp.ts, with invalid_grant/invalid_client -> unrecoverable_refresh_error mapping). Cohesive addition at the existing refreshKiroToken chokepoint. Covered by tests/unit/kiro-external-idp.test.ts.",
+    "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
+    "_rebaseline_2026_07_09_6678_routing_strategy_9router": "#6678 (SeaXen) — 9router-parity Routing Strategy settings card + per-provider/combo sticky-round-robin override. Own growth: ProviderDetailPageClient.tsx 784->786 (single ProviderAccountRoutingCard mount + import), auth.ts 2448->2458 (providerStrategies override resolution: fallbackStrategy/stickyRoundRobinLimit per-provider cascade in getProviderCredentials). Both additive, zero unrelated refactor; new UI/logic lives in new files (ProviderAccountRoutingCard.tsx, RoutingStrategyCard.tsx, rrState.ts::resolveComboStickyRoundRobinLimit). chat.ts value below reflects the current release tip (grown by other concurrent PRs, e.g. #6640), not this PR own change.",
+    "_rebaseline_2026_07_10_6318_omp_letta": "PR #6318 (@hamsa0x7, omp+letta CLI integrations) own growth: cliTools.ts (+53 = 2 registry entries incl. omp docsUrl) and cliRuntime.ts (+18 = runtime-detection wiring for the 2 new tools). Cohesive registry/wiring growth at the existing chokepoints; scope reduced from the original 5 tools (pi/codewhale/jcode shipped separately).",
+    "_rebaseline_2026_07_10_gcf_v3_2_decode": "PR #6838 own growth: new vendored file open-sse/services/compression/engines/headroom/gcf/decode_generic.ts frozen at 880 (> 800 cap). It is the vendored GCF generic-profile decoder (spec v3.2 nested flattening plus the prototype-pollution / hasOwnProperty hardening added in this PR's Gemini review). Kept as one file faithful to upstream gcf-typescript so re-vendoring stays a clean copy rather than a re-split each cycle (sibling generic.ts/scalar.ts stay < cap; extraction would also fragment the file's frozen eslint no-explicit-any suppressions). Round-trip + prototype-pollution regression coverage in tests/unit/compression/headroom-smartcrusher.test.ts. Frozen: only shrinks from here.",
+    "_rebaseline_2026_07_12_v3847_mergeprs_tail": "v3.8.47 /merge-prs tail (owner-approved): src/lib/localDb.ts NEW>800 (799->805, +6 re-exports countFreeProxies + recordFreeProxySyncErrors/clearFreeProxySyncErrors/getFreeProxySyncErrors + FreeProxySyncErrors type for #6909 free-pool relay-repair; re-export-only per Hard Rule #2, not extractable).",
+    "_rebaseline_2026_07_15_7070_combos_memo": "PR #7070 (perf/p1-memo) own growth: src/app/(dashboard)/dashboard/combos/page.tsx 4655->4656 (+1 = React.memo wrapping of ComboCard). Covered by tests/unit/ui/combos-page-smoke.test.tsx.",
+    "_rebaseline_2026_07_18_7399_xai_oauth_modal": "PR #7399 (xAI OAuth PKCE) own growth: OAuthModal.tsx 993->998 (+5 = provider entry + PKCE flow branch wiring at the existing provider-switch chokepoint; the provider logic itself lives in src/lib/oauth/providers/xai-oauth.ts, new leaf). Third irreducible wiring bump on this modal (969->989->993->998); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_19_6636_codex_session_json": "#6636 own growth: OAuthModal.tsx 998->1030 (gate units, split(\"\\n\").length incl. trailing newline; +32 = session-JSON paste branch for handleManualSubmit plus a shared submitCodexAccessToken() helper extracted from the pre-existing bare-JWT branch, mirroring the #5203 oauthBlobSubmit.ts extraction precedent; the normalizer logic itself lives in the new src/lib/oauth/utils/codexSessionImport.ts leaf module, not here). Fourth irreducible wiring bump on this modal (969->989->993->998->1030); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_19_7546_ghe_copilot_modal": "PR #7546 (GHE Copilot OAuth provider) own growth: OAuthModal.tsx 1030->1056 (gate units). Adds a gheUrl input state, routes ghe-copilot through the existing device-code branch, and threads gheUrl into the device-code request/poll extraData at the existing provider-switch chokepoints (+~24 lines, cohesive with the same pattern as #7399/#6636). The standalone GHE enterprise-URL config step JSX (originally +31 lines inline) was extracted to the new src/shared/components/oauthModal/GheConfigStep.tsx leaf component to minimize the bump; what remains is the irreducible provider-branch wiring. Fifth bump on this modal (969->989->993->998->1030->1056); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
+    "_rebaseline_2026_07_20_7779_routingcombo_thread": "PR #7779 own growth: chatHelpers.ts 876->877 (+1, thread routingComboId into executeChatWithBreaker for compression-combo assignment). Frozen so it can only shrink.",
+    "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \"./db/autoCandidateOverrides\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
+    "_rebaseline_2026_07_21_8027_grok_cli_auth_json_paste": "PR #8027 (RaviTharuma, fix(grok-cli) #7610) own growth: OAuthModal.tsx 1080->1100 (gate units). Requires the full ~/.grok/auth.json (with refresh_token) on the paste-import path instead of a bare JWT, at the existing paste-token chokepoint (renamed tab label, updated instructions/placeholder, textarea for the auth.json blob, inline error surface). The validation logic itself (parseGrokCliPasteToken, previously an inline ~75-line function) was extracted to the new src/lib/oauth/utils/grokCliAuthJson.ts leaf module — mirroring the #6636/#7546 extraction precedent — so only the irreducible UI wiring remains here. Sixth bump on this modal (969->989->993->998->1030->1056->1100); structural shrink tracked in #3501.",
+    "_rebaseline_2026_07_21_8034_compression_exclusions_sidebar": "#8034 (compression exclusions dashboard tab) own growth: sections.ts 796->806 (+10, one new COMPRESSION_CONTEXT_GROUP sidebar item linking /dashboard/compression/exclusions). The file was already 796/800 before this PR (organic growth from prior sidebar entries), so a single new nav item pushed it 6 lines over cap. Freezing at 806 (cannot grow further); the sidebar item array is data, not extractable logic.",
+    "_rebaseline_2026_07_22_7936_namespace_roundtrip": "#7936 (@RCrushMe, Responses-Chat namespace round-trip identity seam) own growth: open-sse/translator/response/openai-responses.ts 1092->1125 (+33) and open-sse/utils/stream.ts 2814->2869 (+55) — threading the namespace-identity seam through the Responses↔Chat translation + stream paths so tool-call namespaces survive the round-trip. Cohesive translation/stream wiring at existing chokepoints, frozen at new size.",
+    "_rebaseline_2026_07_22_8010_codex_responses_engine": "PR #8010 (@JxnLexn) own growth: open-sse/mcp-server/schemas/tools.ts 1497->1505 (+8 = threading the new \"codex-responses\" literal into the compressionConfigureInput strategy/autoTriggerMode Zod enums and setCompressionEngineInput engine enum, mirroring the existing rtk/omniglyph enum entries; no new tool). open-sse/services/compression/strategySelector.ts 1043->1054 (+11 = one new `if (mode === \"codex-responses\")` dispatch branch in runCompression that delegates 100% to the new codexResponsesEngine.apply, mirroring the existing rtk single-mode dispatch, plus threading config.codexResponsesConfig.preserveToolNames into the shared adaptBodyForCompression call at the 3 existing call sites). src/lib/db/compression.ts (untracked, new-file cap 800) 794->845 (+51 = normalizeCodexResponsesConfig, mirroring the existing normalizeRtkConfig normalizer, plus registering \"codex-responses\" in the COMPRESSION_MODES/STACKED_PIPELINE_ENGINE_IDS/SINGLE_MODE_ENGINE sets and the getCompressionSettings load/save switch) — added to the baseline at its current size. All three are cohesive dispatch/normalizer wiring at existing chokepoints (mirroring the prior compression-mode rebaselines #6534/#6556), not extractable without hiding the mode-dispatch boundary. Covered by tests/unit/compression/codex-responses.test.ts (6) + omniglyph-registries.test.ts/types.test.ts (22, updated for the new mode).",
+    "_rebaseline_2026_07_22_8034_compression_exclusions_persistence": "#8034 (compression exclusions) own growth: src/lib/db/compression.ts 845->850 (+5 = threading the new compressionExclusions field through the existing getCompressionSettings/saveCompressionSettings load/save switch over the shared key_value compression namespace — no new table, no raw SQL). Mirrors the prior compression-field rebaselines (#8010 codex-responses normalizer at the same chokepoint); the load/save switch is a single dispatch boundary, not extractable without hiding it. Covered by the PR's 8 node:test + 3 vitest cases.",
+    "_rebaseline_2026_07_22_8050_model_lockout_exact_family": "#8050 (@AndrianBalanescu) own growth: accountFallback.ts 1864->1892 (+28) — exact-vs-family model-lockout scoping (getModelLockKey/isModelLocked/clearModelLock/getModelLockoutInfo) so an Antigravity 404 for one bare model no longer hijacks the whole family cooldown. Cohesive lockout logic; frozen at new size.",
+    "_rebaseline_2026_07_22_8056_headroom_minrows": "#8056 (@RaviTharuma, persist Headroom minRows) own growth: src/lib/db/compression.ts 850->866 (+16 HeadroomConfig+DEFAULT_HEADROOM_CONFIG+normalize/store in get/updateCompressionSettings) and open-sse/services/compression/strategySelector.ts 1054->1060 (+6 merge settings.headroom into stacked stepConfig). Cohesive settings-persistence + stacked-merge wiring at existing chokepoints, frozen at new size.",
+    "_rebaseline_2026_07_22_8081_reasoning_placeholder_guard": "#8081 (@Dingding-leo) own growth: openai-responses.ts 1125->1137 (+12) restructuring the reasoning-placeholder guard so it skips only the empty content block and still emits finish_reason/tool_calls in the same chunk. Cohesive translator wiring; frozen at new size.",
+    "_rebaseline_2026_07_22_8210_openrouter_midstream_error": "PR #8210 (hartmark, fix/openrouter-midstream-error-surfacing) own growth: open-sse/translator/response/openai-responses.ts 1137->1163 (+26) measured on the merged tip (release 1137 + this PR own growth). Adds a single new branch inside openaiToOpenAIResponsesResponse() that detects an OpenRouter-style mid-stream aggregator error (HTTP 200 SSE chunk with empty choices + a top-level error object) and surfaces it as state.upstreamError instead of silently falling through to the no-op/awaitingTrailingUsage path, which previously masked the failure as a false empty-success completion and skipped combo fallback. Irreducible call-site addition at the existing chunk-dispatch chokepoint (mirrors the Gemini-to-OpenAI translator's #4177 precedent for the same class of upstream error surfacing). Note: this baseline entry does NOT cover the separate pre-existing +11 drift already on the release tip from #8081/#8162 (1125->1136, unrelated reasoning-placeholder-stripping fix merged after this PR branched) — that drift belongs to the maintainer's rebaseline, not this PR.",
+    "_rebaseline_2026_07_22_8211_gemini_malformed_tool_choice": "PR #8211 (hartmark, fix/gemini-malformed-function-call-tool-choice) own growth: open-sse/translator/response/gemini-to-openai.ts 771->821 (+50, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds MALFORMED_FUNCTION_CALL/UNEXPECTED_TOOL_CALL handling inside geminiToOpenAIResponse(): synthesizes a `malformed_tool_call` tool_calls entry so finish_reason normalizes to the standard \"tool_calls\" instead of an unrecognized raw enum value that OpenAI-compatible clients (e.g. OpenClaw) silently ignore, and always synthesizes (rather than skipping when a real tool call already exists) so a malformed attempt alongside a real one in the same turn is not silently discarded. Irreducible cohesive addition at the existing candidate/finishReason translation chokepoint (mirrors the 9router#2462 raw-finish-reason precedent immediately below it in the same function). Covered by the PR's own tests/unit test additions for both the malformed-only and malformed-plus-real-call cases.",
+    "_rebaseline_2026_07_22_8213_chat_abandoned_target_abort": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/sse/handlers/chat.ts 1794->1860 (+66, measured against the PR's own merge-base — the release tip separately carries an unrelated -5 net shrink from #8013's antigravity callable-catalog alignment, which this PR's branch does not include and this entry does not cover). Adds resolveDispatchClientRawRequest(): merges a per-target modelAbortSignal into clientRawRequest.signal (via mergeAbortSignals) so a combo target abandoned by comboTargetTimeoutMs actually observes its own abort and reaches its cleanup path, instead of hanging forever inside withRateLimit/acquireAccountSemaphore and leaking a permanent 'pending' dashboard entry (live incident, log id 1784418258231-14961a). Also wires combo-exhausted rejection logging to capture request body + attempted models via the new rejectedRequestUsage helper. Irreducible additions at the existing chat dispatch chokepoint. Covered by the PR's own combo-config + integration test additions.",
+    "_rebaseline_2026_07_22_8213_combo_cooldown_wait_recording": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/combo.ts 3548->3604 (+56, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Fixes combo cooldown-wait state recording so a bogus 503 is no longer crystallized when the cooldown-wait vars reset every setTry, adds an OpenAI-format SSE error frame path for combo-exhausted rejections (capturing request body + attempted models), and gives an abandoned per-target dispatch its own timeout instead of leaking a permanent 'pending' dashboard entry. Irreducible additions at the existing handleComboChat dispatch/retry chokepoint (mirrors the prior quota-share/headroom/task-aware strategy-branch precedents already frozen in this file). Covered by the PR's own combo-config + Gemini TPM-ceiling benchmark test additions.",
+    "_rebaseline_2026_07_22_8213_gemini_tpm_quota_cooldown_wait": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/accountFallback.ts 1857->1932 on the merged tip (release 1892 incl #8050 +35, plus this PR own growth +40); measured against the PR own merge-base was 1857->1898 (+41 — the release tip separately carries an unrelated +34 from #8050's antigravity 404 model-not-found lockout scoping, which this PR's branch does not include and this entry does not cover). Own growth is the Gemini TPM-ceiling classification + cooldown-wait wiring feeding into the combo cooldown-wait state machine (rate-limit wedge recovery) introduced by this PR's commit series. Irreducible additions at the existing account-fallback/model-lockout chokepoint. Covered by the PR's own gemini-rate-limit-tracker and TPM-ceiling benchmark test additions.",
+    "_rebaseline_2026_07_22_8213_health_unblock_model_cooldowns": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/app/(dashboard)/dashboard/health/page.tsx 1094->1165 (+71, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds handleUnblockAll/handleUnblockOne dashboard actions (DELETE /api/resilience/model-cooldowns) so an operator can manually clear a Gemini TPM-wedge model lockout surfaced by this PR's cooldown-wait fixes, instead of waiting out the ceiling. Irreducible UI wiring at the existing health-page action chokepoint. Covered by the PR's own dashboard/resilience test additions.",
+    "_rebaseline_2026_07_22_8213_requestloggerdetail_unblock_ui": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/shared/components/RequestLoggerDetail.tsx 799->941 (+142, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip; crosses the general 800-line new-file cap so is frozen here for the first time). Adds a collapsible section header (open/expand-less toggle) plus per-log-entry unblock (`unblocking`/`cleared` state, isCombo503 detection) so the request-logger detail panel surfaces the same Gemini TPM cooldown-wait / model-lockout unblock action introduced by this PR at the individual-request level (mirrors the health-page bulk unblock action added in the same PR). Covered by the PR's own dashboard/resilience test additions.",
+    "_rebaseline_2026_07_22_fusion_8013_8098_antigravity": "Fusion of #8013 (backryun, catalog/IDE-CLI-split rewrite) + #8098 (nguyenha935, protocol-fidelity/fail-closed/credits/tool-cloaking): open-sse/services/usage/antigravity.ts NEW 802 (>cap 800, +2 — #8098 credits/tier usage service on #8013's profile-aware headers). Test growth (models-catalog-route 1605->1608, provider-models-route 1752->1757 from #8013 Gemini 3.6 catalog) tracked in testFrozen.",
+    "_rebaseline_2026_07_23_8127_grok_weekly_quota": "#8127 (@apoapostolov) own growth: src/sse/handlers/chat.ts 1861->1865 (+4) — weekly quota tracking for grok-web wires a quota-fetch hook at the existing dispatch chokepoint. Thin wiring mirroring adjacent provider-quota branches; not extractable. Covered by tests/unit/grok-quota-fetcher.test.ts.",
+    "_rebaseline_2026_07_23_8143_empty_catch_logging": "#8143 (@chirag127) own growth: open-sse/utils/stream.ts 2869->2887 (+18) — replacing empty catch blocks in the SSE stream subsystem with console.debug logging (Rule #6 silent-swallow fix, issues #8138-#8142). Cohesive logging additions at the existing catch chokepoints, not extractable; frozen at new size. Covered by tests/unit/stream-handler-catch-logging-8143.test.ts.",
+    "_rebaseline_2026_07_23_8219_cache_ttl_settings_sidebar": "#8219 (@oyi77) own growth: sections.ts 806->813 (+7) — configurable model-catalog cache-TTL settings adds a new sidebar nav entry + its visibility wiring. Sidebar item array is data, not extractable logic; frozen at new size.",
+    "_rebaseline_2026_07_23_8247_8248_model_unhealthy": "#8247+#8248 own growth: accountFallback.ts 1940->1941 (+1, irreducible import statement only — the substantive #8248 DEGRADED-pattern classifier was extracted into open-sse/config/errorConfig.ts, which has ample headroom, instead of growing this frozen file; #8247's fix is a single existing-line condition change, net zero lines). Scoping the credits-exhausted 403/429 branch to isCompatibleProvider() (per-model-quota openai/anthropic-compatible-* nicknames) so it stays model-scoped instead of terminalling the whole connection, and classifying NVIDIA NIM 'Function ... DEGRADED' 400 bodies as model-access-denied instead of a raw passthrough 400. Covered by tests/unit/8247-accountfallback-model-unhealthy.test.ts and tests/unit/8248-accountfallback-nvidia-degraded.test.ts.",
+    "_rebaseline_2026_07_23_8252_combo_400_advance": "#8252 (@RaviTharuma) own growth: accountFallback.ts 1932->1940 (+8) + combo.ts 3604->3630 (+26) — advance combo on model-scoped 400s wrapped as invalid/Bad-Request. Irreducible wiring at existing account-fallback + combo dispatch chokepoints. Covered by combo-model-scoped-400-advance.test.ts.",
+    "_rebaseline_2026_07_23_8266_alibaba_media": "#8266 (@backryun) own growth: imageRegistry.ts 821->979 (+158) — Alibaba-family media models (Qwen image/video, Bailian, Wan) added to the image/video registry. Registry model data, not extractable logic; frozen at new size.",
+    "_rebaseline_2026_07_24_8388_compression_detail_persist": "#8388 (compression engine DETAIL settings — Headroom/session-dedup/CCR — dropped on save) own growth: src/lib/db/compression.ts 866->872 (+6 = irreducible call-site wiring at the existing getCompressionSettings/updateCompressionSettings chokepoint: one import line, one `...buildDetailConfigDefaults()` spread in the seed config, and one `case \"sessionDedup\": case \"ccr\": applyDetailConfigUpdate(config, key, parsed); break;` load-switch case, mirroring the existing headroom/#8056 case immediately above it). The actual normalizer logic (normalizeSessionDedupConfig/normalizeCcrConfig, matching SESSION_DEDUP_SCHEMA/CCR_SCHEMA bounds) was EXTRACTED into a new leaf src/lib/db/compressionDetailNormalizers.ts (well under cap) so this frozen file only carries the minimal dispatch wiring. Covered by tests/unit/8388-compression-detail-persist.test.ts (schema-accept + full DB save->reload round-trip for both new sub-objects, plus a no-regression assertion on the existing headroom round-trip).",
+    "_rebaseline_2026_07_24_responses_toolcalls_log_summary": "hartmark, fix/responses-tool-calls-log-summary own growth: open-sse/translator/response/openai-responses.ts 1163->1174 (+11). closeToolCall() now also writes the completed tool call into the shared state.toolCalls Map (already populated by the openai-to-claude / claude-to-openai / gemini-to-openai response translators) so stream.ts's completion-log summary builder (which reads state.toolCalls, not this translator's own funcCallIds/funcNames/funcArgsBuf bookkeeping) reports finish_reason \"tool_calls\" and message.tool_calls for openai->openai-responses translated streams instead of always logging \"stop\" with no tool_calls — the actual client-facing SSE events were already correct; only the persisted call-log summary was wrong. Irreducible call-site addition at the existing tool-call-close chokepoint. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts.",
+    "_rebaseline_2026_07_25_8476_combo_input_bound_homogeneous_scope": "PR #8476 (herjarsa, fix/8375-8459-combo-image-fixes, #8375) own growth: open-sse/services/combo.ts 3642->3679 (+37 net: +29 the PR's own isInputBoundFailure short-circuit for deterministic context_length_exceeded/context_window_exceeded failures, +8 a /green-prs pre-merge fix scoping that short-circuit to homogeneous remainders only — the shipped code fired unconditionally on ANY target, regressing the intentional heterogeneous-combo fallback #6637/isContextOverflow400 protects, exactly as flagged by this PR's own review evidence but never actually implemented in the branch). The fix compares orderedTargets[i+1..] modelStr against the failing target's modelStr at the existing executeTarget dispatch chokepoint (mirrors the sameProviderNext precedent a few lines below) — irreducible call-site wiring, not extractable without hiding the dispatch boundary. Covered by tests/unit/combo-input-bound-failure-8375.test.ts (homogeneous pool still short-circuits) and the new tests/unit/combo-input-bound-heterogeneous-8375.test.ts (heterogeneous combo now correctly falls through to the larger-context target).",
+    "_rebaseline_2026_07_25_adobe_firefly_reference_images": "Follow-up to #8006: storage upload + referenceBlobs for image/video and /v1/images/edits dispatch. adobeFireflyClient.ts 1958->2317 (+upload helpers, extract sources, resolve blob ids). Note: 2317 not 2316 — check-file-size.mjs counts LOC via split(\"\\n\").length (counts the trailing-newline empty element), which is 1 higher than `wc -l` on a file ending in \\n; the PR's original entry (2316) was measured with wc -l and undercounted by 1 against the actual gate.",
+    "_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
+    "_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
+    "open-sse/executors/antigravity.ts": 1528,
+    "open-sse/executors/base.ts": 1640,
+    "open-sse/executors/chatgpt-web.ts": 3241,
+    "open-sse/executors/codex.ts": 1562,
+    "open-sse/executors/cursor.ts": 1563,
+    "open-sse/executors/deepseek-web.ts": 1148,
+    "open-sse/executors/grok-web.ts": 1044,
+    "open-sse/executors/muse-spark-web.ts": 1405,
+    "open-sse/handlers/chatCore.ts": 5034,
+    "open-sse/handlers/imageGeneration.ts": 3101,
+    "open-sse/handlers/responseSanitizer.ts": 1128,
+    "open-sse/handlers/search.ts": 1536,
+    "open-sse/handlers/videoGeneration.ts": 1063,
+    "open-sse/mcp-server/schemas/tools.ts": 1505,
+    "open-sse/mcp-server/server.ts": 1411,
+    "open-sse/mcp-server/tools/advancedTools.ts": 1120,
+    "open-sse/services/accountFallback.ts": 1972,
+    "open-sse/services/adobeFireflyClient.ts": 2385,
+    "open-sse/services/claudeCodeCompatible.ts": 1202,
+    "open-sse/services/combo.ts": 3648,
+    "open-sse/services/compression/strategySelector.ts": 1060,
+    "open-sse/services/rateLimitManager.ts": 1167,
+    "open-sse/translator/response/openai-responses.ts": 1204,
+    "open-sse/utils/cursorAgentProtobuf.ts": 1505,
+    "open-sse/utils/stream.ts": 2889,
+    "src/app/(dashboard)/dashboard/HomePageClient.tsx": 1388,
+    "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": 1031,
+    "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": 3117,
+    "src/app/(dashboard)/dashboard/cache/media/MediaPageClient.tsx": 1067,
+    "src/app/(dashboard)/dashboard/combos/page.tsx": 4647,
+    "src/app/(dashboard)/dashboard/costs/CostOverviewTab.tsx": 1283,
+    "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": 1022,
+    "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": 2615,
+    "src/app/(dashboard)/dashboard/health/page.tsx": 1165,
+    "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": 1316,
+    "src/app/(dashboard)/dashboard/providers/page.tsx": 1944,
+    "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": 1201,
+    "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": 1019,
+    "src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx": 1464,
+    "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": 1123,
+    "src/app/(dashboard)/dashboard/settings/components/RoutingTab.tsx": 1629,
+    "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": 1573,
+    "src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx": 1028,
+    "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": 2148,
+    "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": 1119,
+    "src/app/api/providers/[id]/models/route.ts": 2250,
+    "src/app/api/v1/models/catalog.ts": 1549,
+    "src/lib/tokenHealthCheck.ts": 1021,
+    "src/lib/db/apiKeys.ts": 1529,
+    "src/lib/db/core.ts": 1637,
+    "src/lib/db/migrationRunner.ts": 1084,
+    "src/lib/db/models.ts": 1097,
+    "src/lib/db/providers.ts": 1034,
+    "src/lib/memory/retrieval.ts": 1073,
+    "src/lib/tailscaleTunnel.ts": 1202,
+    "src/lib/usage/providerLimits.ts": 1013,
+    "src/shared/components/OAuthModal.tsx": 1134,
+    "src/shared/components/RequestLoggerV2.tsx": 1629,
+    "src/shared/components/analytics/charts.tsx": 1035,
+    "src/shared/services/cliRuntime.ts": 1122,
+    "src/sse/handlers/chat.ts": 1877,
+    "src/sse/services/auth.ts": 2508,
+    "tests/unit/account-fallback-service.test.ts": 1572,
+    "tests/unit/provider-validation-specialty.test.ts": 2985,
+    "open-sse/executors/hyperagent.ts": 1026,
+    "open-sse/executors/default.ts": 1042,
+    "open-sse/executors/kiro.ts": 1069
+  },
   "testCap": 1000,
   "testFrozen": {
-    "tests/unit/adobe-firefly.test.ts": 1136,
-    "tests/unit/reasoning-cache.test.ts": 1035,
     "_rebaseline_2026_06_27_5193_antigravity_test": "#5193 own test growth: oauth-providers-config.test.ts 870->873 (+3: antigravity projectId assertion + 50ms tick for the now fire-and-forget onboarding, matching the no-PKCE/no-openid flow).",
     "_rebaseline_2026_07_02_5928_base_red": "web-cookie-providers-new.test.ts 845->850: #5928 (test(security) Kimi Web URL host parse, CodeQL #689) grew the file +5 lines and merged into release/v3.8.44 WITHOUT rebaselining, leaving a fast-gates base-red that blocked every subsequent PR->release. Test growth is legitimate (a security regression test); maintainer absorbs the drift here. Frozen at 850.",
     "_rebaseline_2026_07_09_6126_clinepass_dualauth": "#6126 (ClinePass dual-auth) own test growth: oauth-providers-config.test.ts 842->845 (+3: clinepass key/config/required-fields entries reusing the Cline WorkOS flow config, needed after registering clinepass in the oauth.ts PROVIDERS enum).",
@@ -291,137 +410,7 @@
   "_rebaseline_2026_07_27_3850_relax_filesize_cap_v2_20pct": "OWNER-APPROVED TEMPORARY relax for v3.8.50-3.8.54 PREPARE phase (docs/ROADMAP.md). v1 was cap 800->900 / testCap 800->900 on 2026-07-27; v2 = v1 +20% buffer = cap 900->1000 (+100), testCap 900->1000 (+100). Justification: same as complexity v2 — the v3.8.50 release cut coincides with high-merge activity; owner accepted enlarging the headroom to cover the entire PREPARE phase (5 minor cycles .50-.54) without per-PR rebaseline noise. Targets: decompose-existing-frozen unchanged (frozen still only-shrink — see frozen[] entries and the 105 files >900 that still need structural decomposition regardless of cap); this only relaxes the cap for NEW files in the decompose/extract-while-PREPARE phase (.51='executor registry in-place' and .52='combo.ts decomposition' create new leaf modules above 800). RE-TIGHTENING MANDATORY in v3.8.51: cap target 850 = 850 once decomposition wave stabilizes (gives 150 units of post-tighten headroom vs the new 1000 ceiling). Tracked via same roadmap issue as complexity v2. Window: v3.8.50 (release cut) → v3.8.54 close (RE-TIGHTEN at v3.8.51 prep merge per ROADMAP.md). Last entry unless measured regression. v1 entry retained below for audit trail.",
   "_rebaseline_2026_07_27_3850_relax_filesize_cap": "OWNER-APPROVED TEMPORARY relax for v3.8.50-3.8.54 PREPARE phase (docs/ROADMAP.md). cap 800->900 (+100), testCap 800->900 (+100). Targets: decompose-existing-frozen unchanged (frozen still only-shrink); this only relaxes the cap for NEW files in the decompose/extract-while-PREPARE phase (.51='executor registry in-place' and .52='combo.ts decomposition' create new leaf modules above 800). RE-TIGHTENING MANDATORY in v3.8.51: cap target 850 = 850 once decomposition wave stabilizes. SUPERSEDED by _rebaseline_2026_07_27_3850_relax_filesize_cap_v2_20pct (v1 +20% buffer) — retained for audit. Tracked via same roadmap issue.",
   "_rebaseline_2026_07_27_v3849_train1h": "Merge-train 1H (31 PRs) — owner-approved 2026-07-27. Two distinct causes, kept separate on purpose: (1) GENUINE irreducible growth at existing chokepoints — providerLimits/auth (#8632 Kimi quota-reset recovery), rateLimitManager (#8616 idle wedged limiters), models-catalog-route.test (#8610 OpenCode Go effort aliases); (2) COLLISION with #8585, which banked shrinks measured on the pre-train release tip while 30 sibling PRs in the SAME train grew those files again — chat/accountFallback (#8628), chatCore (#8613), videoGeneration (#8581), imageGeneration. The zero-headroom frozen entries cannot absorb either. Ceilings re-pinned to the post-merge tip; #8612 (also in this train) automates shrink-banking so this self-inflicted drift stops recurring. Detail: src/lib/usage/providerLimits.ts 1006->1013 (#8632); src/sse/services/auth.ts 2492->2508 (#8632); open-sse/services/rateLimitManager.ts 1014->1060 (#8616); src/sse/handlers/chat.ts 1842->1845 (#8628); open-sse/handlers/chatCore.ts 4939->4955 (#8613); open-sse/handlers/imageGeneration.ts 3100->3101 ((sem PR — teto do #8585)); open-sse/handlers/videoGeneration.ts 1038->1063 (#8581); open-sse/services/accountFallback.ts 1965->1966 (#8628); tests/unit/models-catalog-route.test.ts 1608->1636 (#8610)",
-  "frozen": {
-    "_rebaseline_2026_06_22_4644_deepseek_web_tools": "PR #4644 (BugsBag/robust deepseek-web tool-call parsing): open-sse/executors/deepseek-web.ts 1117->1125 (+8). The new agentic tool-call path emits surrounding text + reasoning before tool_calls and swaps to the dedicated deepseekWebTools.ts parser; the +8 lines are cohesive wiring at the existing transformSSE chokepoint (the parser itself lives in the new deepseekWebTools.ts file, already under cap). The PR's own fast-gate (PR->release) does not run check:file-size, so this surfaced only at release reconcile. Covered by tests/unit/deepseek-web-tools-variants.test.ts + deepseek-web-tools-execute.test.ts.",
-    "_rebaseline_2026_06_23_4712_deepseek_web_tool_results": "PR for #4712 (deepseek-web drops role:tool): open-sse/executors/deepseek-web.ts 1125->1148 (+23). messagesToPrompt() now folds role:\"tool\" results into the single-prompt transcript (recovering the tool name from the preceding assistant tool_calls by tool_call_id) instead of silently dropping them; the lines are cohesive wiring inside the existing function. Covered by tests/unit/deepseek-web-tool-result-prompt-4712.test.ts.",
-    "_rebaseline_2026_06_24_headroom_strategy": "Headroom-aware connection selection (dario technique): combo.ts 3168->3180 (+12 = a new `else if (strategy === \"headroom\")` dispatch branch in handleComboChat that delegates to orderTargetsByHeadroom + its log line, plus the import). The actual logic lives OUT of the god-file: the pure ranker rankByHeadroom/computeHeadroom is the new leaf open-sse/services/combo/headroomRanking.ts (91 LOC, <cap) and the async orderer orderTargetsByHeadroom is appended to the existing open-sse/services/combo/quotaStrategies.ts (<cap) next to its sibling reset-aware/reset-window orderers (reuses their connection-expansion machinery). headroom = 1 - max(util_5h, util_7d) from getSaturation (src/lib/quota/saturationSignals.ts), prefers the connection with the most free capacity. Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. fill-first stays default; all existing strategies untouched. Covered by tests/unit/combo-headroom-ranking.test.ts (pure helper) + tests/unit/combo-headroom-strategy.test.ts (orderer, saturation injected). Structural shrink of combo.ts tracked in #3501.",
-    "_rebaseline_2026_06_24_quota_share_strategy": "Dedicated quota-share strategy (Phase 3 #9): combo.ts 3180->3190 (+10 = one new `else if (strategy === \"quota-share\")` dispatch branch in handleComboChat that delegates 100% to selectQuotaShareTarget + its log line, plus the import). All the new logic lives OUT of the god-file in two new leaves under open-sse/services/combo/: quotaShareInflight.ts (in-flight counter with TTL/lease, ~150 LOC <cap) and quotaShareStrategy.ts (per-model bucket gating via isBucketSaturated + DRR proportional to weight + P2C over in-flight, ~240 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the headroom/reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. ZERO existing strategy cases were modified — only this branch was added, and the qtSd/ combos switched from fill-first to quota-share in src/lib/quota/quotaCombos.ts. Covered by tests/unit/quota-share-strategy.test.ts (gating, DRR fairness, P2C in-flight, fail-open, activation). Structural shrink of combo.ts tracked in #3501.",
-    "_rebaseline_2026_06_24_task_aware_routing": "Task-aware routing strategy (port PR #2045, OmniRoute #4945): combo.ts 3190->3225 (+35) = one new `else if (strategy === \"task-aware\")` dispatch branch delegating 100% to selectTaskAwareTarget + its imports/log lines. All scoring/classification logic lives OUT of the god-file in the new leaf open-sse/services/taskAwareRouting.ts (553 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors quota-share/headroom/reset-aware branches). ZERO existing strategy cases modified. Covered by tests/unit/combo-task-aware.test.ts (35 tests). Structural shrink of combo.ts tracked in #3501.",
-    "_rebaseline_2026_06_26_fidelity_gate_extraction": "Milestone-B fidelity-gate wiring residual: bodyToText+gateAdvance extracted to fidelityGateStep.ts (889->854, -35), but the StackOptions.fidelityGate field, the `const fidelityGate` reads at the two stacked-loop dispatch chokepoints, and the import of FidelityGateConfig are irreducible wiring that cannot leave strategySelector without an architectural refactor of the pre-existing stacked pipeline. Net: 889->854 (+6 vs the pre-Milestone-B frozen 848). Covered by tests/unit/compression/*.test.ts (940 pass).",
-    "_rebaseline_2026_06_27_5193_5203_antigravity_oauthmodal": "Antigravity remote-login own growth: OAuthModal.tsx 960->969 (gate units). #5193 (+~4: remote paste instruction shown for all remote incl. Google + its rationale comment) and #5203 (+~5: handleManualSubmit credential-blob branch + button guard; submit logic extracted to oauthBlobSubmit.ts to minimize). Frozen set to the SUM so either merge order passes. Cohesive at the existing manual-submit chokepoint.",
-    "_rebaseline_2026_06_27_5193_antigravity_basered": "Base-red (pre-existing release drift, fast-gate PR->release skips check:file-size): accountFallback.ts 1773->1777 and src/app/api/providers/[id]/test/route.ts 924->940 were already over their frozen caps on release/v3.8.39 independent of any antigravity change. Owner chose to rebaseline (keep the documented issue-reference comments #1846/#1449/#347 etc.) rather than accept the contributor comment-stripping in #5200/#5198. Reverted #5200 to restore the comments; bumped these two frozen caps to the actual base sizes. No logic change.",
-    "_rebaseline_2026_06_28_5237_impersonation_ua_refresh": "PR #5237 (refresh impersonation UAs): grok-web.ts 1871->1873 (+2), muse-spark-web.ts 1284->1302 (+18), perplexity-web.ts 1013->1032 (+19). Net semantic change in each file is a single User-Agent constant (Chrome 147->149 for grok/muse; perplexity kept at Firefox 148 to stay matched with the firefox_148 TLS profile — the contributor's 152 bump was reverted to avoid a UA-vs-JA3 mismatch, #2459). The growth is Prettier reflow that lint-staged unavoidably applies to these grandfathered long-line files the moment they are touched; not extractable. src/sse/services/auth.ts 2336->2401 in the same reconcile is #5222's antigravity-LRU-retry growth that merged via --admin without a baseline bump.",
-    "_rebaseline_2026_06_28_5243_risk_gate_prepass": "PR #5243 (compression risk-gate pre-pass) own growth: open-sse/services/compression/strategySelector.ts 854->899 (+45). The three exported entry points (applyCompression/applyStackedCompression/applyStackedCompressionAsync) become thin wrappers over pure-extracted private bodies (runCompression/runStackedCompression/runStackedCompressionAsync) so the risk-gate mask->run->restore wrapper sits strictly OUTSIDE the per-step loop — a single universal integration point. The wrapper logic itself (resolveRiskGate/withRiskGate) lives in the new riskGate/strategyWrap.ts (<cap); the residual growth is the duplicated thin-wrapper signatures + the extracted bodies' dispatch boundary, guarded by a byte-identical parity test (riskGateIntegration). Default off (DEFAULT_COMPRESSION_CONFIG unchanged). Not extractable without hiding the dispatch boundary, mirroring prior compression rebaselines. Structural shrink tracked in #3501.",
-    "_rebaseline_2026_06_28_5275_correlation_id_extract": "Extraction of the safe CorrelationId subset of #5275 (hartmark) — request correlation id stored in call_logs (migration 109) and returned via the X-Correlation-Id response header, WITHOUT the combo/resilience or build/lazy-loading changes (those stay in #5275). Own growth: callLogs.ts 975->985 (correlation_id column on CallLogSummaryRow + read/map), usageHistory.ts 983->988 (correlationId metadata normalize), chat.ts 1575->1632 (withCorrelationId response wiring + combo-failure log carrying correlationId), chatHelpers.ts new 811 (withCorrelationId helper + reqId threading; was 791<cap pre-feature). Cohesive request/logging chokepoint wiring; structural shrink of chat.ts tracked in #3501.",
-    "_rebaseline_2026_06_29_4038_cas_guard": "PR (#4038) own growth: tokenRefresh.ts 2103->2181 (+78 = the compare-and-swap guard on the refresh persist — runWithCasGuard/getActiveCasGuard AsyncLocalStorage pair mirroring runWithOnPersist, casGuardShouldSkipPersist that rereads the row right before persisting and skips the write when a concurrent writer already rotated the refresh_token past the one presented, plus getCasGuardStats counters). Fixes the sibling-rotation-revert → token-family-revocation storm. Gated behind an active guard (opt-in; no guard => byte-identical). Wiring lives at the two persist chokepoints inside getAccessToken; the comparison reuses wasRefreshTokenRotated from refreshSerializer. Not extractable without splitting the refresh hot path.",
-    "_rebaseline_2026_06_29_5286_memoization": "PR #5286 own growth: strategySelector.ts 899->960 (+61 = the opt-in result-memoization branches in applyCompression/applyCompressionAsync — principal+determinism gate, makeMemoKey lookup/store with model+supportsVision folded into the key, recompute-with-memo-off). Default off (memoizeCompressionResults), so zero behavior change. The memo helpers live in the leaf resultMemo.ts (<cap); the chokepoint wiring here is not extractable. Structural shrink of this hot-path file tracked in #3501.",
-    "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
-    "_rebaseline_2026_07_02_5816_qoder": "PR #5816 (@AgentKiller45, qoder PAT via qodercli): qoderCli.ts 666->989, new-above-cap frozen (owner-approved baseline freeze). The growth is the legitimate PAT job-token exchange + quota parsing CLI transport (the pure-JS Cosy path 500'd on every PAT request); extracting the spawn/parse helpers now would just add indirection to a contributor PR mid-merge. Test frozen also raised for this PR's coverage growth: providers-page-utils.test.ts 1052->1092. Additionally clears an inherited base-red from the already-merged #5933 (codex json_schema->text.format): translator-openai-responses-req.test.ts 1097->1172 (+75 regression tests, no offending branch left). All remain frozen (cannot grow further); release captain's rebaseline-at-release supersedes.",
-    "_rebaseline_2026_07_09_6126_clinepass_dual_auth": "PR #6126 (@hajilok, dual-auth ClinePass) own growth: tokenRefresh.ts 2181->2182 (+1 = a single `case \"clinepass\":` fallthrough label added to the existing `case \"cline\":` in _getAccessTokenInternal's provider switch, so clinepass token refresh dispatches to the already-shared refreshClineToken() instead of silently falling through to the generic OAuth refresh). Irreducible 1-line switch-case wiring at the existing chokepoint; the header-building logic for the same feature was extracted to a new leaf src/shared/utils/clineAuth.ts::buildClinepassHeaders() (well under cap) to avoid growing open-sse/executors/default.ts. Covered by tests/unit/clinepass-provider.test.ts.",
-    "_rebaseline_2026_07_09_6363_kiro_external_idp": "PR #6363 (@artickc, Kiro external IdP) own growth: tokenRefresh.ts 2182->2249 (+67 = the external_idp refresh branch inside refreshKiroToken — standard public-client OAuth2 refresh_token grant against the org IdP tokenEndpoint via buildExternalIdpRefreshParams/isExternalIdpAuthMethod from the new leaf open-sse/services/kiroExternalIdp.ts, with invalid_grant/invalid_client -> unrecoverable_refresh_error mapping). Cohesive addition at the existing refreshKiroToken chokepoint. Covered by tests/unit/kiro-external-idp.test.ts.",
-    "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
-    "_rebaseline_2026_07_09_6678_routing_strategy_9router": "#6678 (SeaXen) — 9router-parity Routing Strategy settings card + per-provider/combo sticky-round-robin override. Own growth: ProviderDetailPageClient.tsx 784->786 (single ProviderAccountRoutingCard mount + import), auth.ts 2448->2458 (providerStrategies override resolution: fallbackStrategy/stickyRoundRobinLimit per-provider cascade in getProviderCredentials). Both additive, zero unrelated refactor; new UI/logic lives in new files (ProviderAccountRoutingCard.tsx, RoutingStrategyCard.tsx, rrState.ts::resolveComboStickyRoundRobinLimit). chat.ts value below reflects the current release tip (grown by other concurrent PRs, e.g. #6640), not this PR own change.",
-    "_rebaseline_2026_07_10_6318_omp_letta": "PR #6318 (@hamsa0x7, omp+letta CLI integrations) own growth: cliTools.ts (+53 = 2 registry entries incl. omp docsUrl) and cliRuntime.ts (+18 = runtime-detection wiring for the 2 new tools). Cohesive registry/wiring growth at the existing chokepoints; scope reduced from the original 5 tools (pi/codewhale/jcode shipped separately).",
-    "_rebaseline_2026_07_10_gcf_v3_2_decode": "PR #6838 own growth: new vendored file open-sse/services/compression/engines/headroom/gcf/decode_generic.ts frozen at 880 (> 800 cap). It is the vendored GCF generic-profile decoder (spec v3.2 nested flattening plus the prototype-pollution / hasOwnProperty hardening added in this PR's Gemini review). Kept as one file faithful to upstream gcf-typescript so re-vendoring stays a clean copy rather than a re-split each cycle (sibling generic.ts/scalar.ts stay < cap; extraction would also fragment the file's frozen eslint no-explicit-any suppressions). Round-trip + prototype-pollution regression coverage in tests/unit/compression/headroom-smartcrusher.test.ts. Frozen: only shrinks from here.",
-    "_rebaseline_2026_07_12_v3847_mergeprs_tail": "v3.8.47 /merge-prs tail (owner-approved): src/lib/localDb.ts NEW>800 (799->805, +6 re-exports countFreeProxies + recordFreeProxySyncErrors/clearFreeProxySyncErrors/getFreeProxySyncErrors + FreeProxySyncErrors type for #6909 free-pool relay-repair; re-export-only per Hard Rule #2, not extractable).",
-    "_rebaseline_2026_07_15_7070_combos_memo": "PR #7070 (perf/p1-memo) own growth: src/app/(dashboard)/dashboard/combos/page.tsx 4655->4656 (+1 = React.memo wrapping of ComboCard). Covered by tests/unit/ui/combos-page-smoke.test.tsx.",
-    "_rebaseline_2026_07_18_7399_xai_oauth_modal": "PR #7399 (xAI OAuth PKCE) own growth: OAuthModal.tsx 993->998 (+5 = provider entry + PKCE flow branch wiring at the existing provider-switch chokepoint; the provider logic itself lives in src/lib/oauth/providers/xai-oauth.ts, new leaf). Third irreducible wiring bump on this modal (969->989->993->998); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_19_6636_codex_session_json": "#6636 own growth: OAuthModal.tsx 998->1030 (gate units, split(\"\\n\").length incl. trailing newline; +32 = session-JSON paste branch for handleManualSubmit plus a shared submitCodexAccessToken() helper extracted from the pre-existing bare-JWT branch, mirroring the #5203 oauthBlobSubmit.ts extraction precedent; the normalizer logic itself lives in the new src/lib/oauth/utils/codexSessionImport.ts leaf module, not here). Fourth irreducible wiring bump on this modal (969->989->993->998->1030); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_19_7546_ghe_copilot_modal": "PR #7546 (GHE Copilot OAuth provider) own growth: OAuthModal.tsx 1030->1056 (gate units). Adds a gheUrl input state, routes ghe-copilot through the existing device-code branch, and threads gheUrl into the device-code request/poll extraData at the existing provider-switch chokepoints (+~24 lines, cohesive with the same pattern as #7399/#6636). The standalone GHE enterprise-URL config step JSX (originally +31 lines inline) was extracted to the new src/shared/components/oauthModal/GheConfigStep.tsx leaf component to minimize the bump; what remains is the irreducible provider-branch wiring. Fifth bump on this modal (969->989->993->998->1030->1056); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
-    "_rebaseline_2026_07_20_7779_routingcombo_thread": "PR #7779 own growth: chatHelpers.ts 876->877 (+1, thread routingComboId into executeChatWithBreaker for compression-combo assignment). Frozen so it can only shrink.",
-    "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \"./db/autoCandidateOverrides\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
-    "_rebaseline_2026_07_21_8027_grok_cli_auth_json_paste": "PR #8027 (RaviTharuma, fix(grok-cli) #7610) own growth: OAuthModal.tsx 1080->1100 (gate units). Requires the full ~/.grok/auth.json (with refresh_token) on the paste-import path instead of a bare JWT, at the existing paste-token chokepoint (renamed tab label, updated instructions/placeholder, textarea for the auth.json blob, inline error surface). The validation logic itself (parseGrokCliPasteToken, previously an inline ~75-line function) was extracted to the new src/lib/oauth/utils/grokCliAuthJson.ts leaf module — mirroring the #6636/#7546 extraction precedent — so only the irreducible UI wiring remains here. Sixth bump on this modal (969->989->993->998->1030->1056->1100); structural shrink tracked in #3501.",
-    "_rebaseline_2026_07_21_8034_compression_exclusions_sidebar": "#8034 (compression exclusions dashboard tab) own growth: sections.ts 796->806 (+10, one new COMPRESSION_CONTEXT_GROUP sidebar item linking /dashboard/compression/exclusions). The file was already 796/800 before this PR (organic growth from prior sidebar entries), so a single new nav item pushed it 6 lines over cap. Freezing at 806 (cannot grow further); the sidebar item array is data, not extractable logic.",
-    "_rebaseline_2026_07_22_7936_namespace_roundtrip": "#7936 (@RCrushMe, Responses-Chat namespace round-trip identity seam) own growth: open-sse/translator/response/openai-responses.ts 1092->1125 (+33) and open-sse/utils/stream.ts 2814->2869 (+55) — threading the namespace-identity seam through the Responses↔Chat translation + stream paths so tool-call namespaces survive the round-trip. Cohesive translation/stream wiring at existing chokepoints, frozen at new size.",
-    "_rebaseline_2026_07_22_8010_codex_responses_engine": "PR #8010 (@JxnLexn) own growth: open-sse/mcp-server/schemas/tools.ts 1497->1505 (+8 = threading the new \"codex-responses\" literal into the compressionConfigureInput strategy/autoTriggerMode Zod enums and setCompressionEngineInput engine enum, mirroring the existing rtk/omniglyph enum entries; no new tool). open-sse/services/compression/strategySelector.ts 1043->1054 (+11 = one new `if (mode === \"codex-responses\")` dispatch branch in runCompression that delegates 100% to the new codexResponsesEngine.apply, mirroring the existing rtk single-mode dispatch, plus threading config.codexResponsesConfig.preserveToolNames into the shared adaptBodyForCompression call at the 3 existing call sites). src/lib/db/compression.ts (untracked, new-file cap 800) 794->845 (+51 = normalizeCodexResponsesConfig, mirroring the existing normalizeRtkConfig normalizer, plus registering \"codex-responses\" in the COMPRESSION_MODES/STACKED_PIPELINE_ENGINE_IDS/SINGLE_MODE_ENGINE sets and the getCompressionSettings load/save switch) — added to the baseline at its current size. All three are cohesive dispatch/normalizer wiring at existing chokepoints (mirroring the prior compression-mode rebaselines #6534/#6556), not extractable without hiding the mode-dispatch boundary. Covered by tests/unit/compression/codex-responses.test.ts (6) + omniglyph-registries.test.ts/types.test.ts (22, updated for the new mode).",
-    "_rebaseline_2026_07_22_8034_compression_exclusions_persistence": "#8034 (compression exclusions) own growth: src/lib/db/compression.ts 845->850 (+5 = threading the new compressionExclusions field through the existing getCompressionSettings/saveCompressionSettings load/save switch over the shared key_value compression namespace — no new table, no raw SQL). Mirrors the prior compression-field rebaselines (#8010 codex-responses normalizer at the same chokepoint); the load/save switch is a single dispatch boundary, not extractable without hiding it. Covered by the PR's 8 node:test + 3 vitest cases.",
-    "_rebaseline_2026_07_22_8050_model_lockout_exact_family": "#8050 (@AndrianBalanescu) own growth: accountFallback.ts 1864->1892 (+28) — exact-vs-family model-lockout scoping (getModelLockKey/isModelLocked/clearModelLock/getModelLockoutInfo) so an Antigravity 404 for one bare model no longer hijacks the whole family cooldown. Cohesive lockout logic; frozen at new size.",
-    "_rebaseline_2026_07_22_8056_headroom_minrows": "#8056 (@RaviTharuma, persist Headroom minRows) own growth: src/lib/db/compression.ts 850->866 (+16 HeadroomConfig+DEFAULT_HEADROOM_CONFIG+normalize/store in get/updateCompressionSettings) and open-sse/services/compression/strategySelector.ts 1054->1060 (+6 merge settings.headroom into stacked stepConfig). Cohesive settings-persistence + stacked-merge wiring at existing chokepoints, frozen at new size.",
-    "_rebaseline_2026_07_22_8081_reasoning_placeholder_guard": "#8081 (@Dingding-leo) own growth: openai-responses.ts 1125->1137 (+12) restructuring the reasoning-placeholder guard so it skips only the empty content block and still emits finish_reason/tool_calls in the same chunk. Cohesive translator wiring; frozen at new size.",
-    "_rebaseline_2026_07_22_8210_openrouter_midstream_error": "PR #8210 (hartmark, fix/openrouter-midstream-error-surfacing) own growth: open-sse/translator/response/openai-responses.ts 1137->1163 (+26) measured on the merged tip (release 1137 + this PR own growth). Adds a single new branch inside openaiToOpenAIResponsesResponse() that detects an OpenRouter-style mid-stream aggregator error (HTTP 200 SSE chunk with empty choices + a top-level error object) and surfaces it as state.upstreamError instead of silently falling through to the no-op/awaitingTrailingUsage path, which previously masked the failure as a false empty-success completion and skipped combo fallback. Irreducible call-site addition at the existing chunk-dispatch chokepoint (mirrors the Gemini-to-OpenAI translator's #4177 precedent for the same class of upstream error surfacing). Note: this baseline entry does NOT cover the separate pre-existing +11 drift already on the release tip from #8081/#8162 (1125->1136, unrelated reasoning-placeholder-stripping fix merged after this PR branched) — that drift belongs to the maintainer's rebaseline, not this PR.",
-    "_rebaseline_2026_07_22_8211_gemini_malformed_tool_choice": "PR #8211 (hartmark, fix/gemini-malformed-function-call-tool-choice) own growth: open-sse/translator/response/gemini-to-openai.ts 771->821 (+50, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds MALFORMED_FUNCTION_CALL/UNEXPECTED_TOOL_CALL handling inside geminiToOpenAIResponse(): synthesizes a `malformed_tool_call` tool_calls entry so finish_reason normalizes to the standard \"tool_calls\" instead of an unrecognized raw enum value that OpenAI-compatible clients (e.g. OpenClaw) silently ignore, and always synthesizes (rather than skipping when a real tool call already exists) so a malformed attempt alongside a real one in the same turn is not silently discarded. Irreducible cohesive addition at the existing candidate/finishReason translation chokepoint (mirrors the 9router#2462 raw-finish-reason precedent immediately below it in the same function). Covered by the PR's own tests/unit test additions for both the malformed-only and malformed-plus-real-call cases.",
-    "_rebaseline_2026_07_22_8213_chat_abandoned_target_abort": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/sse/handlers/chat.ts 1794->1860 (+66, measured against the PR's own merge-base — the release tip separately carries an unrelated -5 net shrink from #8013's antigravity callable-catalog alignment, which this PR's branch does not include and this entry does not cover). Adds resolveDispatchClientRawRequest(): merges a per-target modelAbortSignal into clientRawRequest.signal (via mergeAbortSignals) so a combo target abandoned by comboTargetTimeoutMs actually observes its own abort and reaches its cleanup path, instead of hanging forever inside withRateLimit/acquireAccountSemaphore and leaking a permanent 'pending' dashboard entry (live incident, log id 1784418258231-14961a). Also wires combo-exhausted rejection logging to capture request body + attempted models via the new rejectedRequestUsage helper. Irreducible additions at the existing chat dispatch chokepoint. Covered by the PR's own combo-config + integration test additions.",
-    "_rebaseline_2026_07_22_8213_combo_cooldown_wait_recording": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/combo.ts 3548->3604 (+56, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Fixes combo cooldown-wait state recording so a bogus 503 is no longer crystallized when the cooldown-wait vars reset every setTry, adds an OpenAI-format SSE error frame path for combo-exhausted rejections (capturing request body + attempted models), and gives an abandoned per-target dispatch its own timeout instead of leaking a permanent 'pending' dashboard entry. Irreducible additions at the existing handleComboChat dispatch/retry chokepoint (mirrors the prior quota-share/headroom/task-aware strategy-branch precedents already frozen in this file). Covered by the PR's own combo-config + Gemini TPM-ceiling benchmark test additions.",
-    "_rebaseline_2026_07_22_8213_gemini_tpm_quota_cooldown_wait": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/accountFallback.ts 1857->1932 on the merged tip (release 1892 incl #8050 +35, plus this PR own growth +40); measured against the PR own merge-base was 1857->1898 (+41 — the release tip separately carries an unrelated +34 from #8050's antigravity 404 model-not-found lockout scoping, which this PR's branch does not include and this entry does not cover). Own growth is the Gemini TPM-ceiling classification + cooldown-wait wiring feeding into the combo cooldown-wait state machine (rate-limit wedge recovery) introduced by this PR's commit series. Irreducible additions at the existing account-fallback/model-lockout chokepoint. Covered by the PR's own gemini-rate-limit-tracker and TPM-ceiling benchmark test additions.",
-    "_rebaseline_2026_07_22_8213_health_unblock_model_cooldowns": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/app/(dashboard)/dashboard/health/page.tsx 1094->1165 (+71, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds handleUnblockAll/handleUnblockOne dashboard actions (DELETE /api/resilience/model-cooldowns) so an operator can manually clear a Gemini TPM-wedge model lockout surfaced by this PR's cooldown-wait fixes, instead of waiting out the ceiling. Irreducible UI wiring at the existing health-page action chokepoint. Covered by the PR's own dashboard/resilience test additions.",
-    "_rebaseline_2026_07_22_8213_requestloggerdetail_unblock_ui": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/shared/components/RequestLoggerDetail.tsx 799->941 (+142, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip; crosses the general 800-line new-file cap so is frozen here for the first time). Adds a collapsible section header (open/expand-less toggle) plus per-log-entry unblock (`unblocking`/`cleared` state, isCombo503 detection) so the request-logger detail panel surfaces the same Gemini TPM cooldown-wait / model-lockout unblock action introduced by this PR at the individual-request level (mirrors the health-page bulk unblock action added in the same PR). Covered by the PR's own dashboard/resilience test additions.",
-    "_rebaseline_2026_07_22_fusion_8013_8098_antigravity": "Fusion of #8013 (backryun, catalog/IDE-CLI-split rewrite) + #8098 (nguyenha935, protocol-fidelity/fail-closed/credits/tool-cloaking): open-sse/services/usage/antigravity.ts NEW 802 (>cap 800, +2 — #8098 credits/tier usage service on #8013's profile-aware headers). Test growth (models-catalog-route 1605->1608, provider-models-route 1752->1757 from #8013 Gemini 3.6 catalog) tracked in testFrozen.",
-    "_rebaseline_2026_07_23_8127_grok_weekly_quota": "#8127 (@apoapostolov) own growth: src/sse/handlers/chat.ts 1861->1865 (+4) — weekly quota tracking for grok-web wires a quota-fetch hook at the existing dispatch chokepoint. Thin wiring mirroring adjacent provider-quota branches; not extractable. Covered by tests/unit/grok-quota-fetcher.test.ts.",
-    "_rebaseline_2026_07_23_8143_empty_catch_logging": "#8143 (@chirag127) own growth: open-sse/utils/stream.ts 2869->2887 (+18) — replacing empty catch blocks in the SSE stream subsystem with console.debug logging (Rule #6 silent-swallow fix, issues #8138-#8142). Cohesive logging additions at the existing catch chokepoints, not extractable; frozen at new size. Covered by tests/unit/stream-handler-catch-logging-8143.test.ts.",
-    "_rebaseline_2026_07_23_8219_cache_ttl_settings_sidebar": "#8219 (@oyi77) own growth: sections.ts 806->813 (+7) — configurable model-catalog cache-TTL settings adds a new sidebar nav entry + its visibility wiring. Sidebar item array is data, not extractable logic; frozen at new size.",
-    "_rebaseline_2026_07_23_8247_8248_model_unhealthy": "#8247+#8248 own growth: accountFallback.ts 1940->1941 (+1, irreducible import statement only — the substantive #8248 DEGRADED-pattern classifier was extracted into open-sse/config/errorConfig.ts, which has ample headroom, instead of growing this frozen file; #8247's fix is a single existing-line condition change, net zero lines). Scoping the credits-exhausted 403/429 branch to isCompatibleProvider() (per-model-quota openai/anthropic-compatible-* nicknames) so it stays model-scoped instead of terminalling the whole connection, and classifying NVIDIA NIM 'Function ... DEGRADED' 400 bodies as model-access-denied instead of a raw passthrough 400. Covered by tests/unit/8247-accountfallback-model-unhealthy.test.ts and tests/unit/8248-accountfallback-nvidia-degraded.test.ts.",
-    "_rebaseline_2026_07_23_8252_combo_400_advance": "#8252 (@RaviTharuma) own growth: accountFallback.ts 1932->1940 (+8) + combo.ts 3604->3630 (+26) — advance combo on model-scoped 400s wrapped as invalid/Bad-Request. Irreducible wiring at existing account-fallback + combo dispatch chokepoints. Covered by combo-model-scoped-400-advance.test.ts.",
-    "_rebaseline_2026_07_23_8266_alibaba_media": "#8266 (@backryun) own growth: imageRegistry.ts 821->979 (+158) — Alibaba-family media models (Qwen image/video, Bailian, Wan) added to the image/video registry. Registry model data, not extractable logic; frozen at new size.",
-    "_rebaseline_2026_07_24_8388_compression_detail_persist": "#8388 (compression engine DETAIL settings — Headroom/session-dedup/CCR — dropped on save) own growth: src/lib/db/compression.ts 866->872 (+6 = irreducible call-site wiring at the existing getCompressionSettings/updateCompressionSettings chokepoint: one import line, one `...buildDetailConfigDefaults()` spread in the seed config, and one `case \"sessionDedup\": case \"ccr\": applyDetailConfigUpdate(config, key, parsed); break;` load-switch case, mirroring the existing headroom/#8056 case immediately above it). The actual normalizer logic (normalizeSessionDedupConfig/normalizeCcrConfig, matching SESSION_DEDUP_SCHEMA/CCR_SCHEMA bounds) was EXTRACTED into a new leaf src/lib/db/compressionDetailNormalizers.ts (well under cap) so this frozen file only carries the minimal dispatch wiring. Covered by tests/unit/8388-compression-detail-persist.test.ts (schema-accept + full DB save->reload round-trip for both new sub-objects, plus a no-regression assertion on the existing headroom round-trip).",
-    "_rebaseline_2026_07_24_responses_toolcalls_log_summary": "hartmark, fix/responses-tool-calls-log-summary own growth: open-sse/translator/response/openai-responses.ts 1163->1174 (+11). closeToolCall() now also writes the completed tool call into the shared state.toolCalls Map (already populated by the openai-to-claude / claude-to-openai / gemini-to-openai response translators) so stream.ts's completion-log summary builder (which reads state.toolCalls, not this translator's own funcCallIds/funcNames/funcArgsBuf bookkeeping) reports finish_reason \"tool_calls\" and message.tool_calls for openai->openai-responses translated streams instead of always logging \"stop\" with no tool_calls — the actual client-facing SSE events were already correct; only the persisted call-log summary was wrong. Irreducible call-site addition at the existing tool-call-close chokepoint. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts.",
-    "_rebaseline_2026_07_25_8476_combo_input_bound_homogeneous_scope": "PR #8476 (herjarsa, fix/8375-8459-combo-image-fixes, #8375) own growth: open-sse/services/combo.ts 3642->3679 (+37 net: +29 the PR's own isInputBoundFailure short-circuit for deterministic context_length_exceeded/context_window_exceeded failures, +8 a /green-prs pre-merge fix scoping that short-circuit to homogeneous remainders only — the shipped code fired unconditionally on ANY target, regressing the intentional heterogeneous-combo fallback #6637/isContextOverflow400 protects, exactly as flagged by this PR's own review evidence but never actually implemented in the branch). The fix compares orderedTargets[i+1..] modelStr against the failing target's modelStr at the existing executeTarget dispatch chokepoint (mirrors the sameProviderNext precedent a few lines below) — irreducible call-site wiring, not extractable without hiding the dispatch boundary. Covered by tests/unit/combo-input-bound-failure-8375.test.ts (homogeneous pool still short-circuits) and the new tests/unit/combo-input-bound-heterogeneous-8375.test.ts (heterogeneous combo now correctly falls through to the larger-context target).",
-    "_rebaseline_2026_07_25_adobe_firefly_reference_images": "Follow-up to #8006: storage upload + referenceBlobs for image/video and /v1/images/edits dispatch. adobeFireflyClient.ts 1958->2317 (+upload helpers, extract sources, resolve blob ids). Note: 2317 not 2316 — check-file-size.mjs counts LOC via split(\"\\n\").length (counts the trailing-newline empty element), which is 1 higher than `wc -l` on a file ending in \\n; the PR's original entry (2316) was measured with wc -l and undercounted by 1 against the actual gate.",
-    "_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
-    "_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
-    "open-sse/executors/antigravity.ts": 1528,
-    "open-sse/executors/base.ts": 1640,
-    "open-sse/executors/chatgpt-web.ts": 3241,
-    "open-sse/executors/codex.ts": 1562,
-    "open-sse/executors/cursor.ts": 1563,
-    "open-sse/executors/deepseek-web.ts": 1148,
-    "open-sse/executors/grok-web.ts": 1044,
-    "open-sse/executors/muse-spark-web.ts": 1405,
-    "open-sse/handlers/chatCore.ts": 5061,
-    "open-sse/handlers/imageGeneration.ts": 3101,
-    "open-sse/handlers/responseSanitizer.ts": 1128,
-    "open-sse/handlers/search.ts": 1536,
-    "open-sse/handlers/videoGeneration.ts": 1063,
-    "open-sse/mcp-server/schemas/tools.ts": 1553,
-    "open-sse/mcp-server/server.ts": 1448,
-    "open-sse/mcp-server/tools/advancedTools.ts": 1120,
-    "open-sse/services/accountFallback.ts": 1978,
-    "open-sse/services/adobeFireflyBrowserLogin.ts": 1362,
-    "open-sse/services/adobeFireflyChromeRuntime.ts": 1201,
-    "open-sse/services/adobeFireflyClient.ts": 2999,
-    "open-sse/services/adobeFireflySession.ts": 1003,
-    "open-sse/services/claudeCodeCompatible.ts": 1202,
-    "open-sse/services/combo.ts": 3648,
-    "open-sse/services/compression/strategySelector.ts": 1061,
-    "open-sse/services/rateLimitManager.ts": 1167,
-    "open-sse/translator/response/openai-responses.ts": 1271,
-    "open-sse/utils/cursorAgentProtobuf.ts": 1505,
-    "open-sse/utils/stream.ts": 2889,
-    "src/app/(dashboard)/dashboard/HomePageClient.tsx": 1388,
-    "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": 1031,
-    "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": 3117,
-    "src/app/(dashboard)/dashboard/cache/media/MediaPageClient.tsx": 1067,
-    "src/app/(dashboard)/dashboard/combos/page.tsx": 4703,
-    "src/app/(dashboard)/dashboard/costs/CostOverviewTab.tsx": 1283,
-    "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": 1022,
-    "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": 2615,
-    "src/app/(dashboard)/dashboard/health/page.tsx": 1165,
-    "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": 1324,
-    "src/app/(dashboard)/dashboard/providers/page.tsx": 1944,
-    "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": 1201,
-    "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": 1019,
-    "src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx": 1470,
-    "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": 1123,
-    "src/app/(dashboard)/dashboard/settings/components/RoutingTab.tsx": 1629,
-    "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": 1573,
-    "src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx": 1028,
-    "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": 2148,
-    "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": 1119,
-    "src/app/api/providers/[id]/models/route.ts": 2361,
-    "src/app/api/v1/models/catalog.ts": 1597,
-    "src/lib/db/apiKeys.ts": 1529,
-    "src/lib/db/core.ts": 1639,
-    "src/lib/db/migrationRunner.ts": 1101,
-    "src/lib/db/models.ts": 1097,
-    "src/lib/db/providers.ts": 1034,
-    "src/lib/memory/retrieval.ts": 1073,
-    "src/lib/tailscaleTunnel.ts": 1202,
-    "src/lib/usage/providerLimits.ts": 1013,
-    "src/shared/components/OAuthModal.tsx": 1134,
-    "src/shared/components/RequestLoggerV2.tsx": 1629,
-    "src/shared/components/analytics/charts.tsx": 1035,
-    "src/shared/services/cliRuntime.ts": 1122,
-    "src/sse/handlers/chat.ts": 1918,
-    "src/sse/services/auth.ts": 2508,
-    "tests/unit/account-fallback-service.test.ts": 1572,
-    "tests/unit/provider-validation-specialty.test.ts": 2985,
-    "open-sse/executors/hyperagent.ts": 1026,
-    "src/lib/tokenHealthCheck.ts": 1053,
-    "open-sse/executors/default.ts": 1042,
-    "open-sse/executors/kiro.ts": 1069,
-    "open-sse/translator/request/openai-to-kiro.ts": 1057,
-    "open-sse/utils/sseHeartbeat.ts": 149
-  },
+  "_rebaseline_2026_08_02_9242_token_health_transient": "PR #9242 (fix/refresh-circuit-transient): src/lib/tokenHealthCheck.ts 1021 (new file, above cap 1000). The file consolidates token-refresh health checking logic that was previously scattered across auth.ts and tokenRefresh.ts. Cohesive single-responsibility module for refresh circuit state management; not extractable without splitting the refresh state machine. Covered by tests/unit/tokenHealthCheck-transient.test.ts.",
   "_rebaseline_2026_07_27_v3849_train2": "Merge-train 2 (7 PRs) — owner-approved 2026-07-27. Single entry: chatCore.ts 4955->5006 (#8595, Responses multi-turn image compaction before the context hard-reject). Genuine irreducible growth at the existing compaction chokepoint in handleChatCore — the PR adds a last-resort retry against the concrete budget plus the estimateFinalInputTokens helper, both wired at the pre-existing call site rather than a new branch. Covered by tests/unit/8560-responses-image-compaction.test.ts (4 tests).",
   "_rebaseline_2026_07_27_v3849_train3": "Merge-train 3 (13 PRs) — owner-approved 2026-07-27. Both entries are genuine irreducible growth at existing chokepoints, not new branches: src/lib/db/apiKeys.ts 1518->1529 (#8805 cx/* ≡ codex/* API-key model permissions); open-sse/handlers/chatCore.ts 5006->5020 (#8806 real response payload into plugin onResponse hooks). Covered by tests/unit/db-apiKeys-crud.test.ts (4 new cases) and the two plugin-hook test files updated in #8806 respectively.",
   "_rebaseline_2026_07_28_8842_antigravity_projectid_refresh": "PR #8842 (fix/antigravity-projectid-refresh) own growth: open-sse/executors/antigravity.ts 1493->1528 (+35 = projectId discovery in refreshCredentials: import ensureAntigravityProjectAssigned + trim projectId + call ensureAntigravityProjectAssigned with 8s timeout + persistDiscoveredAntigravityProjectId + log success/failure). Irreducible wiring at the existing credential-refresh chokepoint. Covered by tests/unit/executor-antigravity.test.ts (4 new test cases).",
@@ -429,150 +418,15 @@
   "_rebaseline_2026_07_28_8860_tokenrefresh_projectid": "PR #8860 (fix/antigravity-projectid-centralized) own test growth: tests/unit/token-refresh-service.test.ts 1311->1378 (+67 = 4 cases covering projectId discovery on the tokenRefresh.ts path — the Dashboard/health-check refresh route, which #8842 did not reach since that fixed the executor path). Covered by the same file.",
   "_rebaseline_2026_07_28_8861_xiaomi_token_plan": "PR #8861 (feat/xiaomi-token-plan-protocol-selector) own growth: EditConnectionModal.tsx 1283->1316 (+33 = the per-connection API-protocol selector field) and open-sse/executors/base.ts 1540->1562 (+22 = alternate-format resolution at the existing buildUrl/headers chokepoint). Both are irreducible wiring at existing call sites.",
   "_rebaseline_2026_07_28_8863_firefly_detail_level": "PR #8863 (fix/adobe-firefly-gpt-detail-level-max) own growth: adobeFireflyClient.ts 2317->2322 (+5 = gpt-image detailLevel defaulting to maximal at the existing payload-build site). Covered by tests/unit/adobe-firefly.test.ts.",
-  "_rebaseline_2026_07_29_8281_home_quickstart_prefetch": "Release v3.8.49 base-red fix (no PR — captain sweep): src/app/(dashboard)/dashboard/HomePageClient.tsx 1377->1381 (+4). #8292 added prefetch={false} to the sidebar but left /home's five quick-start Links prefetching, so first paint still fired 12 speculative RSC requests — caught by navigation.spec.ts only after the e2e helper bug (APP_ROUTE_PATTERN missing /home) was repaired in the same cycle. Growth is the five prefetch attributes; it was offset first by extracting the repeated className literals (INLINE_LINK x4, DOCS_LINK x1), which collapsed five wrapped <Link> blocks back to one line each — a naive fix measured 1391. Guard: tests/unit/sidebar-prefetch-policy-8281.test.ts.",
-  "_rebaseline_2026_08_02_v3850_agentrouter_responses": "Release v3.8.50 AgentRouter/Codex compatibility reconciliation. open-sse/executors/base.ts 1562->1578: #9190 wires AgentRouter's selected Claude/OpenAI/Responses protocol through the existing executor URL, auth, identity-header and fingerprint chokepoints; the reusable alternate resolver remains outside base.ts. open-sse/utils/stream.ts 2887->2889: #9213 evaluates Responses ID and usage normalization independently so response.completed always receives finite usage.total_tokens instead of short-circuiting after an ID rewrite. tests/unit/chatcore-translation-paths.test.ts 2769->2776: #9191 updates the existing Claude-Code bridge assertions for the dynamic AgentRouter wire image. PR #9224 offsets its own chatCore growth by extracting the AgentRouter protocol decisions into chatCore/agentRouterProtocol.ts, leaving chatCore below its frozen ceiling. Covered by agentrouter executor/chatCore protocol tests, chatcore translation-path tests, and responses-commentary-passthrough tests.",
-  "_rebaseline_2026_07_25_dario_upstream_proxy_selector": "PR #8523 (Dario embedded service): upstream-proxy mode selector replaces the binary CLIProxyAPI toggle with Native/CLIProxyAPI/Dario/Fallback + a fallback-backend picker. ProviderDetailPageClient.tsx 798->804 (+6, new hook fields threaded through to ConnectionsListPanel), ConnectionRow.tsx 942->958 (+16, the mode <select> + conditional fallback-backend <select> replacing a single pill button), useProviderConnections.ts 954->986 (+32, upstreamProxyMode/upstreamProxyFallbackBackend state + handleSetUpstreamProxyMode, handleToggleCliproxyapiMode kept as a thin backward-compat wrapper for the existing hook-shape test). All additive UI/state for the new modes — no unrelated refactor.",
-  "_rebaseline_2026_08_02_9242_token_health_transient": "PR #9242 (fix/refresh-circuit-transient): src/lib/tokenHealthCheck.ts 1021 (new file, above cap 1000). The file consolidates token-refresh health checking logic that was previously scattered across auth.ts and tokenRefresh.ts. Cohesive single-responsibility module for refresh circuit state management; not extractable without splitting the refresh state machine. Covered by tests/unit/tokenHealthCheck-transient.test.ts.",
   "_rebaseline_2026_07_28_8870_firefly_ref_cap_timeout": "PR #8870 (fix/adobe-firefly-gpt-ref-cap-timeout) own growth: adobeFireflyClient.ts 2322->2385 (+63 = gpt-image subject-ref hard cap at 2 + adaptive poll timeout budget (base 300s + 60s/ref, max 600s) + defensive .slice on referenceBlobs for gpt/nano/generic families). Fixes live 504s on multi-screenshot listing jobs (Featured Promo / Box Art) where 3–4+ subject refs stall colligo until the old 180s poll budget expires. Helpers adobeFireflyMaxImageRefs/adobeFireflyImageTimeoutMs live next to the existing payload/poll chokepoint (not extractable without splitting the wire recipe mid-PR). Covered by tests/unit/adobe-firefly.test.ts (ref-cap + timeout cases). Structural shrink tracked in #3501.",
+  "_rebaseline_2026_07_29_8281_home_quickstart_prefetch": "Release v3.8.49 base-red fix (no PR — captain sweep): src/app/(dashboard)/dashboard/HomePageClient.tsx 1377->1381 (+4). #8292 added prefetch={false} to the sidebar but left /home's five quick-start Links prefetching, so first paint still fired 12 speculative RSC requests — caught by navigation.spec.ts only after the e2e helper bug (APP_ROUTE_PATTERN missing /home) was repaired in the same cycle. Growth is the five prefetch attributes; it was offset first by extracting the repeated className literals (INLINE_LINK x4, DOCS_LINK x1), which collapsed five wrapped <Link> blocks back to one line each — a naive fix measured 1391. Guard: tests/unit/sidebar-prefetch-policy-8281.test.ts.",
   "_rebaseline_2026_08_01_8964_xai_agent_tools": "PR #8964 own growth: chatCore.ts 5020->5034 at the existing native-passthrough chokepoint. Adds xAI Agent Tools passthrough for /v1/responses (xai/xai-oauth/xao): resolve nativeXaiResponsesPassthrough, force openai-responses targetFormat, stamp body marker, and OR into the existing nativeCodexPassthrough sites (web-search bypass + requestEndpointPath). Leaf logic in passthroughHelpers, responsesEndpoint, targetFormat, xai executor, responseSanitizer, usageTracking. Cohesive wiring at the Codex passthrough boundary.",
   "_rebaseline_2026_08_01_8964_response_sanitizer": "PR #8964 own growth: responseSanitizer.ts 1115->1128. Keep cost_in_usd_ticks / server_side_tool_usage(_details) through sanitizeResponsesApiResponse allowlists so native xAI tool responses retain usage.",
+  "_rebaseline_2026_08_02_v3850_agentrouter_responses": "Release v3.8.50 AgentRouter/Codex compatibility reconciliation. open-sse/executors/base.ts 1562->1578: #9190 wires AgentRouter's selected Claude/OpenAI/Responses protocol through the existing executor URL, auth, identity-header and fingerprint chokepoints; the reusable alternate resolver remains outside base.ts. open-sse/utils/stream.ts 2887->2889: #9213 evaluates Responses ID and usage normalization independently so response.completed always receives finite usage.total_tokens instead of short-circuiting after an ID rewrite. tests/unit/chatcore-translation-paths.test.ts 2769->2776: #9191 updates the existing Claude-Code bridge assertions for the dynamic AgentRouter wire image. PR #9224 offsets its own chatCore growth by extracting the AgentRouter protocol decisions into chatCore/agentRouterProtocol.ts, leaving chatCore below its frozen ceiling. Covered by agentrouter executor/chatCore protocol tests, chatcore translation-path tests, and responses-commentary-passthrough tests.",
   "_rebaseline_2026_08_05_9323_agentrouter_waf_retry": "PR #9323 (fix(agentrouter): retry on 400 content-blocked + burst guard) own growth: open-sse/executors/base.ts 1578->1623 (check-file-size.mjs conta via split(\"\\n\").length; wc -l ve 1622). As +45 linhas sao o WAF_RETRY_CONFIG + o burst guard via gateOutboundRequest() para o WAF do agentrouter.org, com comentarios explicando o porque de cada mitigacao e cobertos por tests/unit/base-executor-waf-retry.test.ts e tests/unit/wafRateLimit.test.ts. Crescimento funcional legitimo, nao inchaco.",
   "_rebaseline_2026_08_05_9529_own_growth": "PR #9529 own growth (base release/v3.8.50 medida EXATAMENTE nos frozen antigos, entao o modo base-relative #8522 nao cobre): open-sse/services/rateLimitManager.ts 1060->1105 (+45: helper applyLimiterSettings() que re-arma o heartbeat do reservoir apos updateSettings — fix do bug Bottleneck 2.19.5 que congelava a fila weighted; TDD em tests/unit/ratelimit-reservoir-refresh.test.ts); tests/integration/chat-pipeline.test.ts 1592->1598 (+6: User-Agent do codex derivado de getCodexClientVersion() em vez de literal pinado — teste-irmao alinhado ao contrato); tests/unit/provider-validation-specialty.test.ts 2980->2985 (+5: cobertura NOVA claude-web 429 -> valid:false, alinhamento #9406); open-sse/translator/response/openai-responses.ts 1174->1204 (+30: buildResponsesReasoningSummaryDelta MOVIDA do leaf pureHelpers.ts para o host — a funcao do #9500 muta stream state e violava o contrato do leaf puro; o LOC total do par host+leaf nao cresceu, o pureHelpers encolheu o mesmo tanto). Crescimento por fix de producao + cobertura adicional + realocacao arquitetural, nao inchaco.",
   "_rebaseline_2026_08_06_v3850_inherited_drift_reconcile": "Reconciliacao 2026-08-06 do drift ACUMULADO da release/v3.8.50 apos o lote de merges de 08-05/06: 13 arquivos acima do frozen no tip puro 8180b49ce1 (medidos pelo proprio gate). O modo PR base-relative (#8522) deixa PRs inocentes passarem, e os rebaselines individuais dos PRs se perderam nas resolucoes sucessivas de conflito deste hot-file — o drift so aparece no modo absoluto (nightly/local). Crescimentos funcionais dos PRs mergeados: #9024 topology click-nav src/app/(dashboard)/dashboard/HomePageClient.tsx; #9324 OpenRouter enrich src/app/(dashboard)/dashboard/providers/page.tsx; #9329 quota card ordering src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx; #9193 context-window suffixes src/sse/handlers/chat.ts; #9332 nested Claude server tool ids open-sse/executors/base.ts; #9228 strip orphaned tool outputs open-sse/executors/codex.ts; #9236 nvidia tool-name normalize open-sse/executors/default.ts; #9314 nested tool_call validation open-sse/executors/kiro.ts; #9260 caller identity REST hops open-sse/mcp-server/server.ts; #8934 cache breakpoints tests tests/unit/chatcore-translation-paths.test.ts; #9193 suffix tests tests/unit/combo-routing-engine.test.ts; #9196 reasoning-on-tool-finish tests tests/unit/sse-auth.test.ts; #9163 GPT-5.6 Max reasoning tests tests/unit/translator-openai-to-kiro.test.ts. default.ts e kiro.ts entram no frozen (estavam sem entrada, acima do cap 1000). Atualizacao pos-medicao (a base avancou durante o ciclo do PR): src/sse/handlers/chat.ts 1857->1877 (#9184 affinity EOF evict) e open-sse/executors/default.ts 1027->1042 (#9005 Kimi K3 tool-name backfill).",
   "_rebaseline_2026_08_06b_v3850_sweepreds_drift": "Segunda reconciliacao de 2026-08-06 (/sweep-reds sobre o tip puro 2ddbbc61a6): 3 arquivos voltaram a passar do frozen apos os merges do mesmo dia, com atribuicao 1:1 por commit. (1) src/app/(dashboard)/dashboard/providers/page.tsx 1928->1944 e (2) open-sse/executors/base.ts 1635->1640, ambos do #9515 (feat(radar): flag-gated signed free-model catalog overlay, commit e7f6b1d130) — o overlay do Radar entra por wiring nos chokepoints ja existentes (a resolucao/verificacao do catalogo assinado mora fora destes dois arquivos); +16 e +5 linhas liquidas nao sao extraiveis sem inventar um leaf por callsite. (3) open-sse/services/accountFallback.ts 1966->1972 do #8704 (commit c4527f97bd), +6 linhas de dados em CREDITS_EXHAUSTED_SIGNALS ('has been exhausted', fixes #8631). src/sse/handlers/chat.ts 1880>1877 tambem estava violando e NAO entra aqui de proposito: e drenado por encolhimento na PR #9598, sem rebaseline. Crescimento proprio DESTA PR: src/lib/db/migrationRunner.ts 1077->1084 (+7) — o guard retroativo em isSchemaAlreadyApplied para os arquivos renumerados 137/138, exigido pela propria mensagem de erro de colisao do runner (ambas as migracoes sao ALTER TABLE ADD COLUMN puro, nao idempotente). Dois `case` + dois `return hasColumn(...)` + 3 linhas de comentario dentro do switch existente; nao extraivel.",
   "_rebaseline_2026_08_06c_v3850_sweepreds_pr2": "Segunda PR do /sweep-reds (fix/release-v3.8.50-basereds-0806b): tests/unit/provider-models-route.test.ts 1784->1787 (medido pelo gate, que conta split(\"\\n\").length) (+2 apos compressao de comentarios) — alinhamento de contrato forcado por dois merges do dia: #9106 tornou gemini-3.1-pro-high user-callable (a entry do alias entra na lista esperada do teste de discovery-retry, +1 linha de dado + 1 de comentario) e ff012ff420 adicionou onboardUser como bootstrap hop (exclusao no mock, ja comprimida a 1 linha). Nao ha o que encolher sem apagar o comentario que explica o porque.",
-  "_rebaseline_2026_08_07_v3850_sweepreds_pr2_toolnamemap": "tests/unit/translator-openai-to-gemini.test.ts 1616->1619 (+3). O frozen estava EXATAMENTE no tamanho da base, entao qualquer linha nova viola. #9568 (c9a3361e5a) fez buildChangedToolNameMap emitir entradas IDENTIDADE (o Gemini minusculiza nomes de tool nas respostas, entao o tradutor de resposta precisa da chave para mapear de volta), o que passou a incluir `_toolNameMap` no envelope Antigravity de qualquer request com tools. As 3 linhas sao: a chave nova na lista esperada de Object.keys, 1 comentario explicando POR QUE ela aparece (sem ele o proximo leitor tenta remove-la de novo) e 1 assert do CONTEUDO do map — presenca de chave sozinha nao provaria a entrada identidade, que e justamente o comportamento novo. Nao ha o que extrair: e alinhamento de contrato dentro de um teste existente.",
-  "_rebaseline_2026_08_08_9634_migration_139_guard": "PR #9634 (fix/release-v3850-basereds) own growth, re-measured on e0ce95c59 after rebase: src/lib/db/migrationRunner.ts 1094->1096 (+2, the isSchemaAlreadyApplied case-139 retroactive guard for the renumbered ccr migration). Irreducible, matches the per-case guard pattern exactly. Covered by tests/unit/migration-135-numbering-collision.test.ts.",
-  "_rebaseline_2026_06_22_4644_deepseek_web_tools": "PR #4644 (BugsBag/robust deepseek-web tool-call parsing): open-sse/executors/deepseek-web.ts 1117->1125 (+8). The new agentic tool-call path emits surrounding text + reasoning before tool_calls and swaps to the dedicated deepseekWebTools.ts parser; the +8 lines are cohesive wiring at the existing transformSSE chokepoint (the parser itself lives in the new deepseekWebTools.ts file, already under cap). The PR's own fast-gate (PR->release) does not run check:file-size, so this surfaced only at release reconcile. Covered by tests/unit/deepseek-web-tools-variants.test.ts + deepseek-web-tools-execute.test.ts.",
-  "_rebaseline_2026_06_23_4712_deepseek_web_tool_results": "PR for #4712 (deepseek-web drops role:tool): open-sse/executors/deepseek-web.ts 1125->1148 (+23). messagesToPrompt() now folds role:\\\"tool\\\" results into the single-prompt transcript (recovering the tool name from the preceding assistant tool_calls by tool_call_id) instead of silently dropping them; the lines are cohesive wiring inside the existing function. Covered by tests/unit/deepseek-web-tool-result-prompt-4712.test.ts.",
-  "_rebaseline_2026_06_24_headroom_strategy": "Headroom-aware connection selection (dario technique): combo.ts 3168->3180 (+12 = a new `else if (strategy === \\\"headroom\\\")` dispatch branch in handleComboChat that delegates to orderTargetsByHeadroom + its log line, plus the import). The actual logic lives OUT of the god-file: the pure ranker rankByHeadroom/computeHeadroom is the new leaf open-sse/services/combo/headroomRanking.ts (91 LOC, <cap) and the async orderer orderTargetsByHeadroom is appended to the existing open-sse/services/combo/quotaStrategies.ts (<cap) next to its sibling reset-aware/reset-window orderers (reuses their connection-expansion machinery). headroom = 1 - max(util_5h, util_7d) from getSaturation (src/lib/quota/saturationSignals.ts), prefers the connection with the most free capacity. Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. fill-first stays default; all existing strategies untouched. Covered by tests/unit/combo-headroom-ranking.test.ts (pure helper) + tests/unit/combo-headroom-strategy.test.ts (orderer, saturation injected). Structural shrink of combo.ts tracked in #3501.",
-  "_rebaseline_2026_06_24_quota_share_strategy": "Dedicated quota-share strategy (Phase 3 #9): combo.ts 3180->3190 (+10 = one new `else if (strategy === \\\"quota-share\\\")` dispatch branch in handleComboChat that delegates 100% to selectQuotaShareTarget + its log line, plus the import). All the new logic lives OUT of the god-file in two new leaves under open-sse/services/combo/: quotaShareInflight.ts (in-flight counter with TTL/lease, ~150 LOC <cap) and quotaShareStrategy.ts (per-model bucket gating via isBucketSaturated + DRR proportional to weight + P2C over in-flight, ~240 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors the headroom/reset-aware/reset-window/context-optimized branches); not extractable without hiding the call site. ZERO existing strategy cases were modified — only this branch was added, and the qtSd/ combos switched from fill-first to quota-share in src/lib/quota/quotaCombos.ts. Covered by tests/unit/quota-share-strategy.test.ts (gating, DRR fairness, P2C in-flight, fail-open, activation). Structural shrink of combo.ts tracked in #3501.",
-  "_rebaseline_2026_06_24_task_aware_routing": "Task-aware routing strategy (port PR #2045, OmniRoute #4945): combo.ts 3190->3225 (+35) = one new `else if (strategy === \\\"task-aware\\\")` dispatch branch delegating 100% to selectTaskAwareTarget + its imports/log lines. All scoring/classification logic lives OUT of the god-file in the new leaf open-sse/services/taskAwareRouting.ts (553 LOC <cap). Only the dispatch wiring is irreducible at the existing combo strategy chokepoint (mirrors quota-share/headroom/reset-aware branches). ZERO existing strategy cases modified. Covered by tests/unit/combo-task-aware.test.ts (35 tests). Structural shrink of combo.ts tracked in #3501.",
-  "_rebaseline_2026_06_26_fidelity_gate_extraction": "Milestone-B fidelity-gate wiring residual: bodyToText+gateAdvance extracted to fidelityGateStep.ts (889->854, -35), but the StackOptions.fidelityGate field, the `const fidelityGate` reads at the two stacked-loop dispatch chokepoints, and the import of FidelityGateConfig are irreducible wiring that cannot leave strategySelector without an architectural refactor of the pre-existing stacked pipeline. Net: 889->854 (+6 vs the pre-Milestone-B frozen 848). Covered by tests/unit/compression/*.test.ts (940 pass).",
-  "_rebaseline_2026_06_27_5193_5203_antigravity_oauthmodal": "Antigravity remote-login own growth: OAuthModal.tsx 960->969 (gate units). #5193 (+~4: remote paste instruction shown for all remote incl. Google + its rationale comment) and #5203 (+~5: handleManualSubmit credential-blob branch + button guard; submit logic extracted to oauthBlobSubmit.ts to minimize). Frozen set to the SUM so either merge order passes. Cohesive at the existing manual-submit chokepoint.",
-  "_rebaseline_2026_06_27_5193_antigravity_basered": "Base-red (pre-existing release drift, fast-gate PR->release skips check:file-size): accountFallback.ts 1773->1777 and src/app/api/providers/[id]/test/route.ts 924->940 were already over their frozen caps on release/v3.8.39 independent of any antigravity change. Owner chose to rebaseline (keep the documented issue-reference comments #1846/#1449/#347 etc.) rather than accept the contributor comment-stripping in #5200/#5198. Reverted #5200 to restore the comments; bumped these two frozen caps to the actual base sizes. No logic change.",
-  "_rebaseline_2026_06_28_5237_impersonation_ua_refresh": "PR #5237 (refresh impersonation UAs): grok-web.ts 1871->1873 (+2), muse-spark-web.ts 1284->1302 (+18), perplexity-web.ts 1013->1032 (+19). Net semantic change in each file is a single User-Agent constant (Chrome 147->149 for grok/muse; perplexity kept at Firefox 148 to stay matched with the firefox_148 TLS profile — the contributor's 152 bump was reverted to avoid a UA-vs-JA3 mismatch, #2459). The growth is Prettier reflow that lint-staged unavoidably applies to these grandfathered long-line files the moment they are touched; not extractable. src/sse/services/auth.ts 2336->2401 in the same reconcile is #5222's antigravity-LRU-retry growth that merged via --admin without a baseline bump.",
-  "_rebaseline_2026_06_28_5243_risk_gate_prepass": "PR #5243 (compression risk-gate pre-pass) own growth: open-sse/services/compression/strategySelector.ts 854->899 (+45). The three exported entry points (applyCompression/applyStackedCompression/applyStackedCompressionAsync) become thin wrappers over pure-extracted private bodies (runCompression/runStackedCompression/runStackedCompressionAsync) so the risk-gate mask->run->restore wrapper sits strictly OUTSIDE the per-step loop — a single universal integration point. The wrapper logic itself (resolveRiskGate/withRiskGate) lives in the new riskGate/strategyWrap.ts (<cap); the residual growth is the duplicated thin-wrapper signatures + the extracted bodies' dispatch boundary, guarded by a byte-identical parity test (riskGateIntegration). Default off (DEFAULT_COMPRESSION_CONFIG unchanged). Not extractable without hiding the dispatch boundary, mirroring prior compression rebaselines. Structural shrink tracked in #3501.",
-  "_rebaseline_2026_06_28_5275_correlation_id_extract": "Extraction of the safe CorrelationId subset of #5275 (hartmark) — request correlation id stored in call_logs (migration 109) and returned via the X-Correlation-Id response header, WITHOUT the combo/resilience or build/lazy-loading changes (those stay in #5275). Own growth: callLogs.ts 975->985 (correlation_id column on CallLogSummaryRow + read/map), usageHistory.ts 983->988 (correlationId metadata normalize), chat.ts 1575->1632 (withCorrelationId response wiring + combo-failure log carrying correlationId), chatHelpers.ts new 811 (withCorrelationId helper + reqId threading; was 791<cap pre-feature). Cohesive request/logging chokepoint wiring; structural shrink of chat.ts tracked in #3501.",
-  "_rebaseline_2026_06_29_4038_cas_guard": "PR (#4038) own growth: tokenRefresh.ts 2103->2181 (+78 = the compare-and-swap guard on the refresh persist — runWithCasGuard/getActiveCasGuard AsyncLocalStorage pair mirroring runWithOnPersist, casGuardShouldSkipPersist that rereads the row right before persisting and skips the write when a concurrent writer already rotated the refresh_token past the one presented, plus getCasGuardStats counters). Fixes the sibling-rotation-revert → token-family-revocation storm. Gated behind an active guard (opt-in; no guard => byte-identical). Wiring lives at the two persist chokepoints inside getAccessToken; the comparison reuses wasRefreshTokenRotated from refreshSerializer. Not extractable without splitting the refresh hot path.",
-  "_rebaseline_2026_06_29_5286_memoization": "PR #5286 own growth: strategySelector.ts 899->960 (+61 = the opt-in result-memoization branches in applyCompression/applyCompressionAsync — principal+determinism gate, makeMemoKey lookup/store with model+supportsVision folded into the key, recompute-with-memo-off). Default off (memoizeCompressionResults), so zero behavior change. The memo helpers live in the leaf resultMemo.ts (<cap); the chokepoint wiring here is not extractable. Structural shrink of this hot-path file tracked in #3501.",
-  "_rebaseline_2026_07_01_v3843_release_5609": "Rebaseline v3.8.43 (PR #5609 release reconciliation). DRIFT dos 109 commits do ciclo: 8 god-files existentes cresceram (ApiManagerPageClient 2983->3017, combos/page 4594->4608, AddApiKeyModal 868->869, providerPageHelpers 974->996, chat.ts 1635->1647, auth.ts 2401->2403, batchProcessor 828->915, combo.ts 3368->3387) + 2 novos acima do cap (huggingchat.ts 813, tests web-cookie-providers-new 827) + 4 test files cresceram. Modularizacao deferida (blast-radius mid-release); congelado no estado atual p/ o proximo ciclo ratchetar daqui.",
-  "_rebaseline_2026_07_02_5816_qoder": "PR #5816 (@AgentKiller45, qoder PAT via qodercli): qoderCli.ts 666->989, new-above-cap frozen (owner-approved baseline freeze). The growth is the legitimate PAT job-token exchange + quota parsing CLI transport (the pure-JS Cosy path 500'd on every PAT request); extracting the spawn/parse helpers now would just add indirection to a contributor PR mid-merge. Test frozen also raised for this PR's coverage growth: providers-page-utils.test.ts 1052->1092. Additionally clears an inherited base-red from the already-merged #5933 (codex json_schema->text.format): translator-openai-responses-req.test.ts 1097->1172 (+75 regression tests, no offending branch left). All remain frozen (cannot grow further); release captain's rebaseline-at-release supersedes.",
-  "_rebaseline_2026_07_09_6126_clinepass_dual_auth": "PR #6126 (@hajilok, dual-auth ClinePass) own growth: tokenRefresh.ts 2181->2182 (+1 = a single `case \\\"clinepass\\\":` fallthrough label added to the existing `case \\\"cline\\\":` in _getAccessTokenInternal's provider switch, so clinepass token refresh dispatches to the already-shared refreshClineToken() instead of silently falling through to the generic OAuth refresh). Irreducible 1-line switch-case wiring at the existing chokepoint; the header-building logic for the same feature was extracted to a new leaf src/shared/utils/clineAuth.ts::buildClinepassHeaders() (well under cap) to avoid growing open-sse/executors/default.ts. Covered by tests/unit/clinepass-provider.test.ts.",
-  "_rebaseline_2026_07_09_6363_kiro_external_idp": "PR #6363 (@artickc, Kiro external IdP) own growth: tokenRefresh.ts 2182->2249 (+67 = the external_idp refresh branch inside refreshKiroToken — standard public-client OAuth2 refresh_token grant against the org IdP tokenEndpoint via buildExternalIdpRefreshParams/isExternalIdpAuthMethod from the new leaf open-sse/services/kiroExternalIdp.ts, with invalid_grant/invalid_client -> unrecoverable_refresh_error mapping). Cohesive addition at the existing refreshKiroToken chokepoint. Covered by tests/unit/kiro-external-idp.test.ts.",
-  "_rebaseline_2026_07_09_6587_kiro_api_key_auth": "PR #6587 (@strangersp) own growth for Kiro long-lived API-key auth, merged onto v3.8.47 tip: openai-to-kiro.ts 890->912 (+22, auth-header selection for API-key-vs-OAuth-token connections), providerLimits.ts 998->1000 (+2, API-key auth-type branch), translator-openai-to-kiro.test.ts 1234->1257 (+23), providers-page-utils.test.ts 1109->1107 (net -2 after merging with parallel release drift; connectionMatchesProviderCard api_key coverage added), provider-validation-specialty.test.ts 2856->2980 (+124 net after merge with parallel release drift; this PR also removed the file's `@typescript-eslint/no-explicit-any` eslint-suppression entry by fixing all `any` usages, adding typed replacements). Cohesive additive feature growth, well tested; not extractable without splitting the existing chokepoints mid-merge.",
-  "_rebaseline_2026_07_09_6678_routing_strategy_9router": "#6678 (SeaXen) — 9router-parity Routing Strategy settings card + per-provider/combo sticky-round-robin override. Own growth: ProviderDetailPageClient.tsx 784->786 (single ProviderAccountRoutingCard mount + import), auth.ts 2448->2458 (providerStrategies override resolution: fallbackStrategy/stickyRoundRobinLimit per-provider cascade in getProviderCredentials). Both additive, zero unrelated refactor; new UI/logic lives in new files (ProviderAccountRoutingCard.tsx, RoutingStrategyCard.tsx, rrState.ts::resolveComboStickyRoundRobinLimit). chat.ts value below reflects the current release tip (grown by other concurrent PRs, e.g. #6640), not this PR own change.",
-  "_rebaseline_2026_07_10_6318_omp_letta": "PR #6318 (@hamsa0x7, omp+letta CLI integrations) own growth: cliTools.ts (+53 = 2 registry entries incl. omp docsUrl) and cliRuntime.ts (+18 = runtime-detection wiring for the 2 new tools). Cohesive registry/wiring growth at the existing chokepoints; scope reduced from the original 5 tools (pi/codewhale/jcode shipped separately).",
-  "_rebaseline_2026_07_10_gcf_v3_2_decode": "PR #6838 own growth: new vendored file open-sse/services/compression/engines/headroom/gcf/decode_generic.ts frozen at 880 (> 800 cap). It is the vendored GCF generic-profile decoder (spec v3.2 nested flattening plus the prototype-pollution / hasOwnProperty hardening added in this PR's Gemini review). Kept as one file faithful to upstream gcf-typescript so re-vendoring stays a clean copy rather than a re-split each cycle (sibling generic.ts/scalar.ts stay < cap; extraction would also fragment the file's frozen eslint no-explicit-any suppressions). Round-trip + prototype-pollution regression coverage in tests/unit/compression/headroom-smartcrusher.test.ts. Frozen: only shrinks from here.",
-  "_rebaseline_2026_07_12_v3847_mergeprs_tail": "v3.8.47 /merge-prs tail (owner-approved): src/lib/localDb.ts NEW>800 (799->805, +6 re-exports countFreeProxies + recordFreeProxySyncErrors/clearFreeProxySyncErrors/getFreeProxySyncErrors + FreeProxySyncErrors type for #6909 free-pool relay-repair; re-export-only per Hard Rule #2, not extractable).",
-  "_rebaseline_2026_07_15_7070_combos_memo": "PR #7070 (perf/p1-memo) own growth: src/app/(dashboard)/dashboard/combos/page.tsx 4655->4656 (+1 = React.memo wrapping of ComboCard). Covered by tests/unit/ui/combos-page-smoke.test.tsx.",
-  "_rebaseline_2026_07_18_7399_xai_oauth_modal": "PR #7399 (xAI OAuth PKCE) own growth: OAuthModal.tsx 993->998 (+5 = provider entry + PKCE flow branch wiring at the existing provider-switch chokepoint; the provider logic itself lives in src/lib/oauth/providers/xai-oauth.ts, new leaf). Third irreducible wiring bump on this modal (969->989->993->998); structural shrink tracked in #3501.",
-  "_rebaseline_2026_07_19_6636_codex_session_json": "#6636 own growth: OAuthModal.tsx 998->1030 (gate units, split(\\\"\\\\n\\\").length incl. trailing newline; +32 = session-JSON paste branch for handleManualSubmit plus a shared submitCodexAccessToken() helper extracted from the pre-existing bare-JWT branch, mirroring the #5203 oauthBlobSubmit.ts extraction precedent; the normalizer logic itself lives in the new src/lib/oauth/utils/codexSessionImport.ts leaf module, not here). Fourth irreducible wiring bump on this modal (969->989->993->998->1030); structural shrink tracked in #3501.",
-  "_rebaseline_2026_07_19_7546_ghe_copilot_modal": "PR #7546 (GHE Copilot OAuth provider) own growth: OAuthModal.tsx 1030->1056 (gate units). Adds a gheUrl input state, routes ghe-copilot through the existing device-code branch, and threads gheUrl into the device-code request/poll extraData at the existing provider-switch chokepoints (+~24 lines, cohesive with the same pattern as #7399/#6636). The standalone GHE enterprise-URL config step JSX (originally +31 lines inline) was extracted to the new src/shared/components/oauthModal/GheConfigStep.tsx leaf component to minimize the bump; what remains is the irreducible provider-branch wiring. Fifth bump on this modal (969->989->993->998->1030->1056); structural shrink tracked in #3501.",
-  "_rebaseline_2026_07_19_7787_ic2_localdb_reexports": "PR #7787 (IC2 raw connections cache + lazy-decrypt) own growth: localDb.ts 805->807 (gate units, +2). localDb.ts is the re-export-only layer (hard rule #2 — no logic); the PR adds 4 new db/readCache re-exports (touchConnectionLastUsed, getCachedRawProviderConnections, getCachedProviderConnectionById, getCachedProviderNodes) required by existing barrel importers. Irreducible for a re-export list; frozen so it can only shrink.",
-  "_rebaseline_2026_07_20_7779_routingcombo_thread": "PR #7779 own growth: chatHelpers.ts 876->877 (+1, thread routingComboId into executeChatWithBreaker for compression-combo assignment). Frozen so it can only shrink.",
-  "_rebaseline_2026_07_20_7819_autocandidateoverrides_reexport": "PR for #7819 (Level 1+2: read-only auto/* candidate transparency + per-API-key exclusions) own growth: localDb.ts 807->808 (+1). Adds a single `export * from \\\"./db/autoCandidateOverrides\\\"` barrel re-export (hard rule #2 — no logic) for the new DB module backing per-apiKey candidate exclusions. Irreducible for a re-export list; frozen so it can only shrink.",
-  "_rebaseline_2026_07_21_8027_grok_cli_auth_json_paste": "PR #8027 (RaviTharuma, fix(grok-cli) #7610) own growth: OAuthModal.tsx 1080->1100 (gate units). Requires the full ~/.grok/auth.json (with refresh_token) on the paste-import path instead of a bare JWT, at the existing paste-token chokepoint (renamed tab label, updated instructions/placeholder, textarea for the auth.json blob, inline error surface). The validation logic itself (parseGrokCliPasteToken, previously an inline ~75-line function) was extracted to the new src/lib/oauth/utils/grokCliAuthJson.ts leaf module — mirroring the #6636/#7546 extraction precedent — so only the irreducible UI wiring remains here. Sixth bump on this modal (969->989->993->998->1030->1056->1100); structural shrink tracked in #3501.",
-  "_rebaseline_2026_07_21_8034_compression_exclusions_sidebar": "#8034 (compression exclusions dashboard tab) own growth: sections.ts 796->806 (+10, one new COMPRESSION_CONTEXT_GROUP sidebar item linking /dashboard/compression/exclusions). The file was already 796/800 before this PR (organic growth from prior sidebar entries), so a single new nav item pushed it 6 lines over cap. Freezing at 806 (cannot grow further); the sidebar item array is data, not extractable logic.",
-  "_rebaseline_2026_07_22_7936_namespace_roundtrip": "#7936 (@RCrushMe, Responses-Chat namespace round-trip identity seam) own growth: open-sse/translator/response/openai-responses.ts 1092->1125 (+33) and open-sse/utils/stream.ts 2814->2869 (+55) — threading the namespace-identity seam through the Responses↔Chat translation + stream paths so tool-call namespaces survive the round-trip. Cohesive translation/stream wiring at existing chokepoints, frozen at new size.",
-  "_rebaseline_2026_07_22_8010_codex_responses_engine": "PR #8010 (@JxnLexn) own growth: open-sse/mcp-server/schemas/tools.ts 1497->1505 (+8 = threading the new \\\"codex-responses\\\" literal into the compressionConfigureInput strategy/autoTriggerMode Zod enums and setCompressionEngineInput engine enum, mirroring the existing rtk/omniglyph enum entries; no new tool). open-sse/services/compression/strategySelector.ts 1043->1054 (+11 = one new `if (mode === \\\"codex-responses\\\")` dispatch branch in runCompression that delegates 100% to the new codexResponsesEngine.apply, mirroring the existing rtk single-mode dispatch, plus threading config.codexResponsesConfig.preserveToolNames into the shared adaptBodyForCompression call at the 3 existing call sites). src/lib/db/compression.ts (untracked, new-file cap 800) 794->845 (+51 = normalizeCodexResponsesConfig, mirroring the existing normalizeRtkConfig normalizer, plus registering \\\"codex-responses\\\" in the COMPRESSION_MODES/STACKED_PIPELINE_ENGINE_IDS/SINGLE_MODE_ENGINE sets and the getCompressionSettings load/save switch) — added to the baseline at its current size. All three are cohesive dispatch/normalizer wiring at existing chokepoints (mirroring the prior compression-mode rebaselines #6534/#6556), not extractable without hiding the mode-dispatch boundary. Covered by tests/unit/compression/codex-responses.test.ts (6) + omniglyph-registries.test.ts/types.test.ts (22, updated for the new mode).",
-  "_rebaseline_2026_07_22_8034_compression_exclusions_persistence": "#8034 (compression exclusions) own growth: src/lib/db/compression.ts 845->850 (+5 = threading the new compressionExclusions field through the existing getCompressionSettings/saveCompressionSettings load/save switch over the shared key_value compression namespace — no new table, no raw SQL). Mirrors the prior compression-field rebaselines (#8010 codex-responses normalizer at the same chokepoint); the load/save switch is a single dispatch boundary, not extractable without hiding it. Covered by the PR's 8 node:test + 3 vitest cases.",
-  "_rebaseline_2026_07_22_8050_model_lockout_exact_family": "#8050 (@AndrianBalanescu) own growth: accountFallback.ts 1864->1892 (+28) — exact-vs-family model-lockout scoping (getModelLockKey/isModelLocked/clearModelLock/getModelLockoutInfo) so an Antigravity 404 for one bare model no longer hijacks the whole family cooldown. Cohesive lockout logic; frozen at new size.",
-  "_rebaseline_2026_07_22_8081_reasoning_placeholder_guard": "#8081 (@Dingding-leo) own growth: openai-responses.ts 1125->1137 (+12) restructuring the reasoning-placeholder guard so it skips only the empty content block and still emits finish_reason/tool_calls in the same chunk. Cohesive translator wiring; frozen at new size.",
-  "_rebaseline_2026_07_22_8210_openrouter_midstream_error": "PR #8210 (hartmark, fix/openrouter-midstream-error-surfacing) own growth: open-sse/translator/response/openai-responses.ts 1137->1163 (+26) measured on the merged tip (release 1137 + this PR own growth). Adds a single new branch inside openaiToOpenAIResponsesResponse() that detects an OpenRouter-style mid-stream aggregator error (HTTP 200 SSE chunk with empty choices + a top-level error object) and surfaces it as state.upstreamError instead of silently falling through to the no-op/awaitingTrailingUsage path, which previously masked the failure as a false empty-success completion and skipped combo fallback. Irreducible call-site addition at the existing chunk-dispatch chokepoint (mirrors the Gemini-to-OpenAI translator's #4177 precedent for the same class of upstream error surfacing). Note: this baseline entry does NOT cover the separate pre-existing +11 drift already on the release tip from #8081/#8162 (1125->1136, unrelated reasoning-placeholder-stripping fix merged after this PR branched) — that drift belongs to the maintainer's rebaseline, not this PR.",
-  "_rebaseline_2026_07_22_8211_gemini_malformed_tool_choice": "PR #8211 (hartmark, fix/gemini-malformed-function-call-tool-choice) own growth: open-sse/translator/response/gemini-to-openai.ts 771->821 (+50, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds MALFORMED_FUNCTION_CALL/UNEXPECTED_TOOL_CALL handling inside geminiToOpenAIResponse(): synthesizes a `malformed_tool_call` tool_calls entry so finish_reason normalizes to the standard \\\"tool_calls\\\" instead of an unrecognized raw enum value that OpenAI-compatible clients (e.g. OpenClaw) silently ignore, and always synthesizes (rather than skipping when a real tool call already exists) so a malformed attempt alongside a real one in the same turn is not silently discarded. Irreducible cohesive addition at the existing candidate/finishReason translation chokepoint (mirrors the 9router#2462 raw-finish-reason precedent immediately below it in the same function). Covered by the PR's own tests/unit test additions for both the malformed-only and malformed-plus-real-call cases.",
-  "_rebaseline_2026_07_22_8213_chat_abandoned_target_abort": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/sse/handlers/chat.ts 1794->1860 (+66, measured against the PR's own merge-base — the release tip separately carries an unrelated -5 net shrink from #8013's antigravity callable-catalog alignment, which this PR's branch does not include and this entry does not cover). Adds resolveDispatchClientRawRequest(): merges a per-target modelAbortSignal into clientRawRequest.signal (via mergeAbortSignals) so a combo target abandoned by comboTargetTimeoutMs actually observes its own abort and reaches its cleanup path, instead of hanging forever inside withRateLimit/acquireAccountSemaphore and leaking a permanent 'pending' dashboard entry (live incident, log id 1784418258231-14961a). Also wires combo-exhausted rejection logging to capture request body + attempted models via the new rejectedRequestUsage helper. Irreducible additions at the existing chat dispatch chokepoint. Covered by the PR's own combo-config + integration test additions.",
-  "_rebaseline_2026_07_22_8213_combo_cooldown_wait_recording": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/combo.ts 3548->3604 (+56, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Fixes combo cooldown-wait state recording so a bogus 503 is no longer crystallized when the cooldown-wait vars reset every setTry, adds an OpenAI-format SSE error frame path for combo-exhausted rejections (capturing request body + attempted models), and gives an abandoned per-target dispatch its own timeout instead of leaking a permanent 'pending' dashboard entry. Irreducible additions at the existing handleComboChat dispatch/retry chokepoint (mirrors the prior quota-share/headroom/task-aware strategy-branch precedents already frozen in this file). Covered by the PR's own combo-config + Gemini TPM-ceiling benchmark test additions.",
-  "_rebaseline_2026_07_22_8213_gemini_tpm_quota_cooldown_wait": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: open-sse/services/accountFallback.ts 1857->1932 on the merged tip (release 1892 incl #8050 +35, plus this PR own growth +40); measured against the PR own merge-base was 1857->1898 (+41 — the release tip separately carries an unrelated +34 from #8050's antigravity 404 model-not-found lockout scoping, which this PR's branch does not include and this entry does not cover). Own growth is the Gemini TPM-ceiling classification + cooldown-wait wiring feeding into the combo cooldown-wait state machine (rate-limit wedge recovery) introduced by this PR's commit series. Irreducible additions at the existing account-fallback/model-lockout chokepoint. Covered by the PR's own gemini-rate-limit-tracker and TPM-ceiling benchmark test additions.",
-  "_rebaseline_2026_07_22_8213_health_unblock_model_cooldowns": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/app/(dashboard)/dashboard/health/page.tsx 1094->1165 (+71, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip). Adds handleUnblockAll/handleUnblockOne dashboard actions (DELETE /api/resilience/model-cooldowns) so an operator can manually clear a Gemini TPM-wedge model lockout surfaced by this PR's cooldown-wait fixes, instead of waiting out the ceiling. Irreducible UI wiring at the existing health-page action chokepoint. Covered by the PR's own dashboard/resilience test additions.",
-  "_rebaseline_2026_07_22_8213_requestloggerdetail_unblock_ui": "PR #8213 (hartmark, fix/gemini-tpm-quota-cooldown-wait) own growth: src/shared/components/RequestLoggerDetail.tsx 799->941 (+142, entirely this PR's diff — no other commit touched this file between the PR's merge-base and the release tip; crosses the general 800-line new-file cap so is frozen here for the first time). Adds a collapsible section header (open/expand-less toggle) plus per-log-entry unblock (`unblocking`/`cleared` state, isCombo503 detection) so the request-logger detail panel surfaces the same Gemini TPM cooldown-wait / model-lockout unblock action introduced by this PR at the individual-request level (mirrors the health-page bulk unblock action added in the same PR). Covered by the PR's own dashboard/resilience test additions.",
-  "_rebaseline_2026_07_22_fusion_8013_8098_antigravity": "Fusion of #8013 (backryun, catalog/IDE-CLI-split rewrite) + #8098 (nguyenha935, protocol-fidelity/fail-closed/credits/tool-cloaking): open-sse/services/usage/antigravity.ts NEW 802 (>cap 800, +2 — #8098 credits/tier usage service on #8013's profile-aware headers). Test growth (models-catalog-route 1605->1608, provider-models-route 1752->1757 from #8013 Gemini 3.6 catalog) tracked in testFrozen.",
-  "_rebaseline_2026_07_23_8127_grok_weekly_quota": "#8127 (@apoapostolov) own growth: src/sse/handlers/chat.ts 1861->1865 (+4) — weekly quota tracking for grok-web wires a quota-fetch hook at the existing dispatch chokepoint. Thin wiring mirroring adjacent provider-quota branches; not extractable. Covered by tests/unit/grok-quota-fetcher.test.ts.",
-  "_rebaseline_2026_07_23_8143_empty_catch_logging": "#8143 (@chirag127) own growth: open-sse/utils/stream.ts 2869->2887 (+18) — replacing empty catch blocks in the SSE stream subsystem with console.debug logging (Rule #6 silent-swallow fix, issues #8138-#8142). Cohesive logging additions at the existing catch chokepoints, not extractable; frozen at new size. Covered by tests/unit/stream-handler-catch-logging-8143.test.ts.",
-  "_rebaseline_2026_07_23_8219_cache_ttl_settings_sidebar": "#8219 (@oyi77) own growth: sections.ts 806->813 (+7) — configurable model-catalog cache-TTL settings adds a new sidebar nav entry + its visibility wiring. Sidebar item array is data, not extractable logic; frozen at new size.",
-  "_rebaseline_2026_07_23_8247_8248_model_unhealthy": "#8247+#8248 own growth: accountFallback.ts 1940->1941 (+1, irreducible import statement only — the substantive #8248 DEGRADED-pattern classifier was extracted into open-sse/config/errorConfig.ts, which has ample headroom, instead of growing this frozen file; #8247's fix is a single existing-line condition change, net zero lines). Scoping the credits-exhausted 403/429 branch to isCompatibleProvider() (per-model-quota openai/anthropic-compatible-* nicknames) so it stays model-scoped instead of terminalling the whole connection, and classifying NVIDIA NIM 'Function ... DEGRADED' 400 bodies as model-access-denied instead of a raw passthrough 400. Covered by tests/unit/8247-accountfallback-model-unhealthy.test.ts and tests/unit/8248-accountfallback-nvidia-degraded.test.ts.",
-  "_rebaseline_2026_07_23_8252_combo_400_advance": "#8252 (@RaviTharuma) own growth: accountFallback.ts 1932->1940 (+8) + combo.ts 3604->3630 (+26) — advance combo on model-scoped 400s wrapped as invalid/Bad-Request. Irreducible wiring at existing account-fallback + combo dispatch chokepoints. Covered by combo-model-scoped-400-advance.test.ts.",
-  "_rebaseline_2026_07_23_8266_alibaba_media": "#8266 (@backryun) own growth: imageRegistry.ts 821->979 (+158) — Alibaba-family media models (Qwen image/video, Bailian, Wan) added to the image/video registry. Registry model data, not extractable logic; frozen at new size.",
-  "_rebaseline_2026_07_24_8388_compression_detail_persist": "#8388 (compression engine DETAIL settings — Headroom/session-dedup/CCR — dropped on save) own growth: src/lib/db/compression.ts 866->872 (+6 = irreducible call-site wiring at the existing getCompressionSettings/updateCompressionSettings chokepoint: one import line, one `...buildDetailConfigDefaults()` spread in the seed config, and one `case \\\"sessionDedup\\\": case \\\"ccr\\\": applyDetailConfigUpdate(config, key, parsed); break;` load-switch case, mirroring the existing headroom/#8056 case immediately above it). The actual normalizer logic (normalizeSessionDedupConfig/normalizeCcrConfig, matching SESSION_DEDUP_SCHEMA/CCR_SCHEMA bounds) was EXTRACTED into a new leaf src/lib/db/compressionDetailNormalizers.ts (well under cap) so this frozen file only carries the minimal dispatch wiring. Covered by tests/unit/8388-compression-detail-persist.test.ts (schema-accept + full DB save->reload round-trip for both new sub-objects, plus a no-regression assertion on the existing headroom round-trip).",
-  "_rebaseline_2026_07_24_responses_toolcalls_log_summary": "hartmark, fix/responses-tool-calls-log-summary own growth: open-sse/translator/response/openai-responses.ts 1163->1174 (+11). closeToolCall() now also writes the completed tool call into the shared state.toolCalls Map (already populated by the openai-to-claude / claude-to-openai / gemini-to-openai response translators) so stream.ts's completion-log summary builder (which reads state.toolCalls, not this translator's own funcCallIds/funcNames/funcArgsBuf bookkeeping) reports finish_reason \\\"tool_calls\\\" and message.tool_calls for openai->openai-responses translated streams instead of always logging \\\"stop\\\" with no tool_calls — the actual client-facing SSE events were already correct; only the persisted call-log summary was wrong. Irreducible call-site addition at the existing tool-call-close chokepoint. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts.",
-  "_rebaseline_2026_07_25_8476_combo_input_bound_homogeneous_scope": "PR #8476 (herjarsa, fix/8375-8459-combo-image-fixes, #8375) own growth: open-sse/services/combo.ts 3642->3679 (+37 net: +29 the PR's own isInputBoundFailure short-circuit for deterministic context_length_exceeded/context_window_exceeded failures, +8 a /green-prs pre-merge fix scoping that short-circuit to homogeneous remainders only — the shipped code fired unconditionally on ANY target, regressing the intentional heterogeneous-combo fallback #6637/isContextOverflow400 protects, exactly as flagged by this PR's own review evidence but never actually implemented in the branch). The fix compares orderedTargets[i+1..] modelStr against the failing target's modelStr at the existing executeTarget dispatch chokepoint (mirrors the sameProviderNext precedent a few lines below) — irreducible call-site wiring, not extractable without hiding the dispatch boundary. Covered by tests/unit/combo-input-bound-failure-8375.test.ts (homogeneous pool still short-circuits) and the new tests/unit/combo-input-bound-heterogeneous-8375.test.ts (heterogeneous combo now correctly falls through to the larger-context target).",
-  "_rebaseline_2026_07_25_adobe_firefly_reference_images": "Follow-up to #8006: storage upload + referenceBlobs for image/video and /v1/images/edits dispatch. adobeFireflyClient.ts 1958->2317 (+upload helpers, extract sources, resolve blob ids). Note: 2317 not 2316 — check-file-size.mjs counts LOC via split(\\\"\\\\n\\\").length (counts the trailing-newline empty element), which is 1 higher than `wc -l` on a file ending in \\\\n; the PR's original entry (2316) was measured with wc -l and undercounted by 1 against the actual gate.",
-  "_rebaseline_pr1043_minimax_tts": "Upstream port decolua/9router#1043 (toanalien) own growth: audioSpeech.ts 965->1061 (+96). Adds MiniMax T2A v2 TTS dispatch (handleMinimaxSpeech + hexToBytes helper) — provider entry was already in audioRegistry (format: minimax-tts) but no handler existed, falling through to the OpenAI-compatible default that fails (T2A has custom shape + hex-encoded audio + base_resp envelope). New branch sits next to the other inline provider branches (xiaomi-mimo, coqui, tortoise, aws-polly) — extracting would just create indirection. Covered by tests/unit/minimax-tts-1043.test.ts (3 tests, GREEN: success, base_resp error, invalid-hex).",
-  "_rebaseline_pr4592_exclude_exhausted_auto": "Reconcile #4592 already-merged growth: combo.ts 2991->3036 (+45, terminal-status quota-cutoff exclusion in buildAutoCandidates + opt-in gate). Fast-gate PR->release does not run check:file-size.",
-  "open-sse/executors/antigravity.ts": "1528",
-  "open-sse/executors/base.ts": "1640",
-  "open-sse/executors/chatgpt-web.ts": "3241",
-  "open-sse/executors/codex.ts": "1562",
-  "open-sse/executors/cursor.ts": "1563",
-  "open-sse/executors/deepseek-web.ts": "1148",
-  "open-sse/executors/grok-web.ts": "1044",
-  "open-sse/executors/muse-spark-web.ts": "1405",
-  "open-sse/handlers/chatCore.ts": "5034",
-  "open-sse/handlers/imageGeneration.ts": "3101",
-  "open-sse/handlers/responseSanitizer.ts": "1128",
-  "open-sse/handlers/search.ts": "1536",
-  "open-sse/handlers/videoGeneration.ts": "1063",
-  "open-sse/mcp-server/schemas/tools.ts": "1553",
-  "open-sse/mcp-server/server.ts": "1448",
-  "open-sse/mcp-server/tools/advancedTools.ts": "1120",
-  "open-sse/services/accountFallback.ts": "1978",
-  "open-sse/services/adobeFireflyClient.ts": "2385",
-  "open-sse/services/claudeCodeCompatible.ts": "1202",
-  "open-sse/services/combo.ts": "3648",
-  "open-sse/services/compression/strategySelector.ts": "1060",
-  "open-sse/services/rateLimitManager.ts": "1167",
-  "open-sse/translator/response/openai-responses.ts": "1204",
-  "open-sse/utils/cursorAgentProtobuf.ts": "1505",
-  "open-sse/utils/stream.ts": 2915,
-  "src/app/(dashboard)/dashboard/HomePageClient.tsx": "1388",
-  "src/app/(dashboard)/dashboard/analytics/ComboHealthTab.tsx": "1031",
-  "src/app/(dashboard)/dashboard/api-manager/ApiManagerPageClient.tsx": "3117",
-  "src/app/(dashboard)/dashboard/cache/media/MediaPageClient.tsx": "1067",
-  "src/app/(dashboard)/dashboard/combos/page.tsx": "4703",
-  "src/app/(dashboard)/dashboard/costs/CostOverviewTab.tsx": "1283",
-  "src/app/(dashboard)/dashboard/costs/quota-share/components/PoolWizard.tsx": "1022",
-  "src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx": "2615",
-  "src/app/(dashboard)/dashboard/health/page.tsx": "1165",
-  "src/app/(dashboard)/dashboard/providers/[id]/components/modals/EditConnectionModal.tsx": "1324",
-  "src/app/(dashboard)/dashboard/providers/page.tsx": "1944",
-  "src/app/(dashboard)/dashboard/runtime/RuntimePageClient.tsx": "1201",
-  "src/app/(dashboard)/dashboard/settings/components/PricingTab.tsx": "1019",
-  "src/app/(dashboard)/dashboard/settings/components/ProxyRegistryManager.tsx": "1470",
-  "src/app/(dashboard)/dashboard/settings/components/ResilienceTab.tsx": "1123",
-  "src/app/(dashboard)/dashboard/settings/components/RoutingTab.tsx": "1629",
-  "src/app/(dashboard)/dashboard/settings/components/SystemStorageTab.tsx": "1573",
-  "src/app/(dashboard)/dashboard/usage/components/BudgetTab.tsx": "1028",
-  "src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx": "2148",
-  "src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx": "1119",
-  "src/app/api/providers/[id]/models/route.ts": "2361",
-  "src/app/api/v1/models/catalog.ts": "1597",
-  "src/lib/tokenHealthCheck.ts": "1053",
-  "src/lib/db/apiKeys.ts": "1529",
-  "src/lib/db/core.ts": "1639",
-  "src/lib/db/migrationRunner.ts": "1096",
-  "src/lib/db/models.ts": "1097",
-  "src/lib/db/providers.ts": "1034",
-  "src/lib/memory/retrieval.ts": "1073",
-  "src/lib/tailscaleTunnel.ts": "1202",
-  "src/lib/usage/providerLimits.ts": "1013",
-  "src/shared/components/OAuthModal.tsx": "1134",
-  "src/shared/components/RequestLoggerV2.tsx": "1629",
-  "src/shared/components/analytics/charts.tsx": "1035",
-  "src/shared/services/cliRuntime.ts": "1122",
-  "src/sse/handlers/chat.ts": "1904",
-  "src/sse/services/auth.ts": "2508",
-  "tests/unit/account-fallback-service.test.ts": "1572",
-  "tests/unit/provider-validation-specialty.test.ts": "2985",
-  "open-sse/executors/hyperagent.ts": "1026",
-  "open-sse/executors/default.ts": "1042",
-  "open-sse/executors/kiro.ts": "1069",
-  "open-sse/translator/request/openai-to-kiro.ts": "1057",
-  "open-sse/utils/sseHeartbeat.ts": "142",
-  "_rebaseline_2026_08_04_9305_sse_comments": "#9305 fix: broadened sseCommentsEnabled()",
-  "_rebaseline_2026_08_09_v3850_release_close": "Release v3.8.50 close reconciliation on e0ce95c592: src/sse/handlers/chat.ts 1904->1918 is the irreducible request-pipeline wiring from #9759 that invokes the Modality Bridge guardrail without moving its implementation into the handler; covered by the 17 Vision Bridge canaries plus the PR-1 focused suite. open-sse/translator/response/openai-responses.ts 1204->1215 is #9168's Responses tool-call argument delta buffering/normalization at the existing translator state-machine chokepoint; covered by its dedicated translator regression tests. Both values are measured by check:file-size (split-newline semantics), and the gate remains frozen at the new exact sizes.",
-  "_rebaseline_2026_08_08_toolcall_message_index_collision": "fix(responses-api): tool call after a text message collided on the same output_index. own growth: open-sse/translator/response/openai-responses.ts 1204->1224 (+20, extracted toolCallOutputIndexBase() shared helper so emitToolCall/closeToolCall can no longer compute a tool call's output_index independently and collide with a text message emitted in the same turn). Live incident (2026-08-08, OpenClaw agent): a client that tracks response items by output_index saw the tool call's added/delta/done events land on an index it had already marked complete (the just-closed text message), and silently dropped them — the agent spoke its preamble and never executed the tool call, even though OmniRoute's own recorded responseBody had a complete, valid tool_calls entry. Covered by the new regression test in tests/unit/translator-resp-openai-responses.test.ts reproducing the exact live scenario.",
-  "_rebaseline_2026_08_03_9255_adobe_firefly_durable_sessions": "PR #9255 own cohesive growth: open-sse/services/adobeFireflyClient.ts 2322->2894 adds authenticated-vs-guest IMS classification, browser-risk ARP validation/rebuild, bounded 408 retry/recovery, sticky accepted-session handling, and matching image/video submit recovery at the existing Adobe upstream client chokepoints. This client was already explicitly frozen as a single self-contained upstream integration by #8006/#8510; splitting only the retry/auth helpers now would scatter one request state machine while structural shrink remains tracked in #3501. tests/unit/adobe-firefly.test.ts 871->1136 adds direct regression coverage for guest-token rejection, cookie/ARP rebuilding, 408 retries, sticky accepted ARP reuse, forced auth recovery, and cookie-to-IMS exchange. The obsolete 1179-line managed-Chrome fallback module was deleted rather than rebaselined after the packaged-safe pure-CDP path became authoritative. Focused Adobe suite: 61/61.",
-  "_rebaseline_2026_08_07_9653_disconnect_grace_period": "Extracted fix(sse): grace period before finalizing a client disconnect as 499 (#9653) — a client that closes its connection right after reading a fully-completed SSE stream can race OmniRoute's own completion bookkeeping, getting persisted as a false 499/0-tokens even though it delivered the full response (live-confirmed: a real disconnect at 18236ms was corrected to 200/82814+1292 tokens). Own growth: open-sse/handlers/chatCore.ts 5030->5039 (+9, wiring createClientDisconnectGraceHandler at the existing onClientDisconnectFinalize call site) — irreducible call-site wiring, the actual grace-period logic lives in the new leaf createClientDisconnectGraceHandler (open-sse/utils/streamFailureFinalization.ts, not frozen). Re-measured to 5042 after rebasing onto a newer release/v3.8.50 tip: the file carries an unrelated +3 base drift from already-merged upstream commits between this PR's original branch point and the rebase target, not covered by this entry. Covered by tests/unit/stream-disconnect-grace-period-9653.test.ts (4/4, fake-timer driven). Other file-size gate violations present on this base tip are pre-existing/unrelated to this change (base-red #9679, re-verify current issue number at merge time).",
-  "_rebaseline_2026_08_04_9268_gemini_schema_empty_choices": "Feature #9268 own growth: open-sse/utils/stream.ts 2889->2915 (+26 = irreducible call-site wiring for the empty-choices interceptor). The translate-mode flush now rejects a stream that completed without forwarding any valuable chunk (all-empty `choices: []`, no content/tool_calls/finish_reason) as a retryable 502 \"empty content\" instead of a clean empty 200 — the missing streaming counterpart of chatCore.ts's non-streaming isEmptyContentResponse. All rejection logic lives in the NEW leaf module open-sse/utils/streamEmptyChoices.ts (<cap, not frozen, unit-tested via tests/unit/stream-empty-choices-interceptor.test.ts); stream.ts only carries the `forwardedValuableChunk` boolean (declared at createSSEStream scope, set in emitTranslatedClientItem where the sole hasValuableContent check passes) plus the one flush-time rejectEmptyChoicesStream() call — the wait/orchestration at the chokepoint, not a movable block (mirrors the comboCooldownRetry.ts precedent). Schema-side twin fix: recursive type:\"object\" injection in open-sse/translator/helpers/geminiHelper.ts (not frozen, +33) for nested schemas with properties but no type (Gemini 400).",
-  "_rebaseline_2026_08_09_5696_capability_filter": "PR #9424 own growth: open-sse/handlers/chatCore.ts 5050->5061 (+11). The Layer A capability gate is irreducible wiring at the existing pre-dispatch chokepoint: feature-flag check, capability derivation, compatibility decision, sanitized 400 response, pending-request cleanup, and warning telemetry. All matching and message logic lives outside the god-file in src/shared/constants/capabilities/capabilityFilter.ts; only orchestration remains here. Covered by tests/unit/capability-filter.test.ts (20 cases, including flag-off and sanitized error behavior). Structural shrink remains tracked separately."
+  "_rebaseline_2026_08_07_v3850_sweepreds_pr2_toolnamemap": "tests/unit/translator-openai-to-gemini.test.ts 1616->1619 (+3). O frozen estava EXATAMENTE no tamanho da base, entao qualquer linha nova viola. #9568 (c9a3361e5a) fez buildChangedToolNameMap emitir entradas IDENTIDADE (o Gemini minusculiza nomes de tool nas respostas, entao o tradutor de resposta precisa da chave para mapear de volta), o que passou a incluir `_toolNameMap` no envelope Antigravity de qualquer request com tools. As 3 linhas sao: a chave nova na lista esperada de Object.keys, 1 comentario explicando POR QUE ela aparece (sem ele o proximo leitor tenta remove-la de novo) e 1 assert do CONTEUDO do map — presenca de chave sozinha nao provaria a entrada identidade, que e justamente o comportamento novo. Nao ha o que extrair: e alinhamento de contrato dentro de um teste existente."
 }

config/quality/quality-baseline.json

@@ -92,19 +92,17 @@
       "_rebaseline_2026_07_13_v3847_release": "39.3 -> 38.0 (-1.3, beyond the 0.5 eps). v3.8.47 cycle drift: the cycle merged ~45 PRs adding API routes (relay repair/free-pool #6909, backpressure #6590, combo context requirements #6907, services/usage endpoints) faster than openapi.yaml documentation; same class as the v3.8.34/v3.8.39 rebaselines. Documented follow-up: raise coverage next cycle via docs/openapi.yaml additions."
     },
     "i18nUiCoverage.pct": {
-      "value": 100,
+      "value": 99,
       "direction": "up",
       "eps": 0.5,
-      "_tighten_2026_08_08_modality_bridge": "99 -> 100. Tighten required by the PR quality gate after the Modality Bridge UI keys were translated across all 42 non-English locales. CI collect-metrics on PR #9782 measured i18nUiCoverage.pct=100 with 0 ESLint warnings and 0 ESLint errors; locale dry-sync and UI coverage also report 100% with no missing keys or placeholders.",
       "_rebaseline_2026_07_04_v3844_release": "77.5 -> 76.8 (-0.7, beyond the 0.5 eps). v3.8.44 cycle drift surfaced only on the release PR (i18n-ui-coverage does NOT run on PR->release fast-gates). The cycle added ~1352 new UI keys to the en.json denominator (Discovery dashboard tab #5939, Bifrost/Mux embedded-service tabs #5817/#6034, proxy batch-ops #5918, fusion defaults #5598, tool-source toggle #5978, quota-row collapse #5977, CodeWhale/Crush CLI cards #5996/#5970, etc.) that the async i18n translation workflow has not yet back-filled (worst locales measure 76.8; __MISSING__ placeholders count as uncovered by design). Same shape and remedy as _rebaseline_2026_06_28_v3839_release. Recover via the i18n workflow next cycle; tighten with --require-tighten once translations land.",
       "_rebaseline_2026_06_28_v3839_release": "78.4 -> 77.5 (-0.9, beyond the 0.5 eps). v3.8.39 cycle drift surfaced ONLY on the release PR (i18n-ui-coverage does NOT run on PR->release fast-gates). The cycle added new UI strings (compression studio TOON A/B table, antigravity remote-login dashboard field, amber warning icon) to the en denominator faster than the 37 non-en locales were translated; those locales need `npm run i18n:run` with OMNIROUTE_TRANSLATION_API_KEY (unavailable locally) — same precedent as _rebaseline_2026_06_18_v3828_cycle_close + _quality_rebaseline_2026_06_20_ci_ratchet. Measured by CI collect-metrics (run 28317145160) = 77.5. My release-finalize tree changes no src/i18n/messages/*.json. Tightening is tracked as follow-up (run i18n:run with creds).",
       "_rebaseline_2026_07_13_v3847_release": "76.8 -> 75.5 (-1.3, beyond the 0.5 eps). v3.8.47 cycle drift: merged UI features added EN strings (relay repair UI #6909, combo builder #6907/#6991, capability override UI #6727) ahead of the 42-locale mirrors; same class as the v3.8.39/v3.8.44 rebaselines.",
       "_rebaseline_2026_07_28_v3849_release": "75.5 -> 99 (+23.5). Aperto EXIGIDO pelo modo --require-tighten do ratchet: a métrica melhorou de verdade no ciclo v3.8.49. A causa é o workflow assíncrono de tradução, que finalmente alcançou o denominador em EN — as rebaselines anteriores (v3.8.39/.44/.47) foram todas afrouxamentos registrando o atraso das traduções, e agora ele foi pago. O coletor SUBTRAI os placeholders (present - placeholder em scripts/quality/collect-metrics.mjs), então os 317 marcadores __MISSING__ que esta release introduziu para o drift de valor já estão descontados dos 99 — o número é honesto, não inflado por placeholder. Medido pelo collect-metrics do CI no run 30404226939."
     },
     "deadExports": {
-      "value": 230,
+      "value": 227,
       "direction": "down",
-      "_rebaseline_2026_08_09_v3850_post_sweep": "227 -> 230. Measured by npm run check:dead-code on the unmodified release/v3.8.50 tip 382449d593 during the mandatory --full-ci pre-flight. The +3 is inherited cycle drift from the authorized merge sweep; this repair adds no production exports. Rebaseline records the actual tip so ci.yml quality-gate can run, while structural cleanup remains separate debt.",
       "_rebaseline_2026_07_01_v3843_release": "225->227 (+2). v3.8.43 cycle drift, surfaced in the Quality Ratchet job after eslintWarnings was rebaselined (check:dead-code runs there). 227 = measured by check:dead-code (knip) on the release tip 4635076eb. The 5 CI fixes add 0 dead exports: safeHttpHref in linkify.ts is module-local AND used (called by linkifyText); no new exports; test files are not scanned. Tighten via --update next cycle.",
       "dedicatedGate": true,
       "_rebaseline_2026_06_30_v3842_deadcode_wave": "310 -> 225. Measured by `node scripts/check/check-dead-code.mjs` on the v3.8.42 tip after the JxnLexn dead-code (#5463/#5464/#5466) + duplication (#5471..#5500) wave landed: DEAD_EXPORTS=133 + DEAD_FILES=92 = 225. The stale 310 was the v3.8.38 release snapshot never ratcheted on PR->release fast-gates (check:dead-code runs only on ci.yml PR->main, not quality.yml). Tightening to the true measured value; release-time captain rebaselines up if parallel cycle merges add dead exports.",
@@ -179,13 +177,12 @@
       "dedicatedGate": true
     },
     "bundleSize": {
-      "value": 8045,
+      "value": 7666,
       "direction": "down",
       "dedicatedGate": true,
       "_rebaseline_2026_07_07_v3846_release_close": "5601->6534 (+933). v3.8.46 release close: gzip of the 4 bin/*.mjs entrypoints (size-limit + @size-limit/file) grew from this cycle's feature/fix merges pulled transitively into the CLI entrypoints (new providers, combo pipeline strategy #6396, effort/thinking standardization #6241, catalog cache-invalidation #6408). Measured 6534 locally via `check:bundle-size --ratchet` (deterministic gzip, matches CI). Legitimate cycle growth; shrink is separate debt.",
       "_rebaseline_2026_07_19_7808_codeql_alias_resolver_hook": "6534->6762 (+228). PR #7808 (CodeQL js/incomplete-url-substring-sanitization fix): the ESM loader hook source moved out of the inline `HOOK_SOURCE` template literal in bin/aliasResolver.mjs into a real file bin/aliasResolverHook.mjs, loaded via pathToFileURL() instead of a dynamically-built `data:text/javascript,...` URL. The new file is now counted by size-limit as a 5th bin/*.mjs entrypoint. Net +228 = the hook's gzip size (previously hidden inside aliasResolver.mjs because the template literal was compressed away). Security-driven; no shrink opportunity.",
-      "_rebaseline_2026_07_28_v3849_release_preflight": "6762 -> 7666 (+904). Fechamento do ciclo v3.8.49: gzip dos entrypoints bin/*.mjs (size-limit + @size-limit/file) cresceu com o que os merges do ciclo puxam transitivamente para o CLI (novos provedores — 271->290, seletor de protocolo por conexão #8861, catálogos de busca #8814, resiliência). Crescimento legítimo de ciclo, medido localmente com `npm run check:bundle-size` = 7666 (gzip determinístico, bate com o CI). Encolher é dívida separada.",
-      "_rebaseline_2026_08_09_v3850_release_close": "7666 -> 8045 (+379 gzip bytes, +4.9%). Release v3.8.50 close reconciliation measured twice with the real size-limit + @size-limit/file path on tip e0ce95c592. Per-entry measurements remain below their absolute budgets: omniroute.mjs 4380/15000, mcp-server.mjs 1195/5000, nodeRuntimeSupport.mjs 887/8000, reset-password.mjs 1583/6000. The growth accumulated through legitimate CLI/runtime work in this cycle, including global-install ESM alias resolution, Termux cache preparation, and MCP stdio startup hardening; no entrypoint is near its absolute ceiling. The direction:down ratchet stays blocking from this exact measured tip."
+      "_rebaseline_2026_07_28_v3849_release_preflight": "6762 -> 7666 (+904). Fechamento do ciclo v3.8.49: gzip dos entrypoints bin/*.mjs (size-limit + @size-limit/file) cresceu com o que os merges do ciclo puxam transitivamente para o CLI (novos provedores — 271->290, seletor de protocolo por conexão #8861, catálogos de busca #8814, resiliência). Crescimento legítimo de ciclo, medido localmente com `npm run check:bundle-size` = 7666 (gzip determinístico, bate com o CI). Encolher é dívida separada."
     },
     "openapiBreaking": {
       "value": 0,

config/quality/test-discovery-baseline.json

@@ -1,10 +1,24 @@
 {
   "_comment": "Catraca de test-discovery (check-test-discovery.mjs). Cada entrada e um arquivo de teste que NENHUM runner coleta (ele nunca roda) — divida congelada na auditoria 6A.1 (2026-06-09; 195 originais, 135 religados no node runner em 6A.1c). So pode DIMINUIR: religue o teste (ajustando o glob do runner ou movendo o arquivo) e remova a entrada via --update. NAO adicione novos orfaos — corrija o runner.",
-  "_remaining_13": "13 orfaos restantes: 2 testes de API em settings + 1 snapshot de quota do DB; 4 golden-set + 1 benchmark + 1 teste live + 1 stress (deliberadamente manuais — decidir runner/gating); 3 integration/services (gated RUN_SERVICES_INT=1, sem runner CI).",
+  "_remaining_60": "Categorias: 33 .test.tsx de tests/unit (religaveis via vitest.config root, MAS o experimento 2026-06-09 mostrou 24 arquivos vermelhos — triagem de drift de UI na janela 2026-06-16, junto com os 14 fails do proprio test:vitest:ui atual); 9 open-sse __tests__ + 8 src __tests__ (includes de vitest.config que NENHUM script executa sem filtro); 4 golden-set + 1 benchmarks + 1 live + 1 stress (deliberadamente manuais — decidir runner/gating); 3 integration/services (gated RUN_SERVICES_INT=1, sem runner CI).",
   "orphans": [
+    "open-sse/services/__tests__/chatgptTlsClient.test.ts",
+    "open-sse/services/__tests__/claudeTlsClient.test.ts",
+    "open-sse/services/__tests__/grokTlsClient.test.ts",
+    "open-sse/services/__tests__/manifestAdapter.test.ts",
+    "open-sse/services/__tests__/specificityDetector.test.ts",
+    "open-sse/services/__tests__/tierResolver.test.ts",
+    "open-sse/services/__tests__/volumeDetector.test.ts",
+    "open-sse/translator/helpers/__tests__/maxTokensHelper.test.ts",
+    "open-sse/translator/helpers/__tests__/schemaCoercion.test.ts",
     "src/app/api/settings/__tests__/memory.test.ts",
     "src/app/api/settings/__tests__/settings.test.ts",
     "src/lib/db/__tests__/quotaSnapshots.test.ts",
+    "src/lib/memory/__tests__/injection.test.ts",
+    "src/lib/memory/__tests__/qdrant-wiring.test.ts",
+    "src/lib/memory/__tests__/retrieval.test.ts",
+    "src/lib/memory/__tests__/schemas.test.ts",
+    "src/lib/skills/__tests__/integration.test.ts",
     "tests/benchmarks/pipeline-accuracy.test.ts",
     "tests/golden-set/compression-caveman-v2.test.ts",
     "tests/golden-set/compression-quality.test.ts",
@@ -14,6 +28,36 @@
     "tests/integration/services/full-lifecycle.int.test.ts",
     "tests/integration/services/route-guard-services.int.test.ts",
     "tests/live/deepseek-web-live.test.ts",
-    "tests/theoldllm-stress.test.ts"
+    "tests/theoldllm-stress.test.ts",
+    "tests/unit/AutoComboCatalog.test.tsx",
+    "tests/unit/SkillsConceptCard.test.tsx",
+    "tests/unit/agent-skills-page.test.tsx",
+    "tests/unit/dashboard/batch/components/BatchDetailModal.test.tsx",
+    "tests/unit/dashboard/batch/components/ExpirationBadge.test.tsx",
+    "tests/unit/dashboard/batch/components/NewBatchWizard.test.tsx",
+    "tests/unit/dashboard/batch/components/ProgressBarBicolor.test.tsx",
+    "tests/unit/dashboard/batch/components/UploadFileModal.test.tsx",
+    "tests/unit/dashboard/batch/components/useBatchActions.test.tsx",
+    "tests/unit/dashboard/batch/concept-cards.test.tsx",
+    "tests/unit/dashboard/batch/list-regression.test.tsx",
+    "tests/unit/dashboard/batch/sanitization.test.tsx",
+    "tests/unit/omni-skills-page.test.tsx",
+    "tests/unit/shared-clipboard.test.tsx",
+    "tests/unit/shared/components/AutoRoutingBanner.test.tsx",
+    "tests/unit/shared/components/KiroAuthModal.test.tsx",
+    "tests/unit/shared/components/ProxyConfigModal.test.tsx",
+    "tests/unit/translator-friendly-advanced-section.test.tsx",
+    "tests/unit/translator-friendly-compression.test.tsx",
+    "tests/unit/translator-friendly-concept-card.test.tsx",
+    "tests/unit/translator-friendly-integration.test.tsx",
+    "tests/unit/translator-friendly-monitor-tab.test.tsx",
+    "tests/unit/translator-friendly-page-client.test.tsx",
+    "tests/unit/translator-friendly-pipeline-view.test.tsx",
+    "tests/unit/translator-friendly-raw-json-panel.test.tsx",
+    "tests/unit/translator-friendly-result-narrated.test.tsx",
+    "tests/unit/translator-friendly-simple-controls.test.tsx",
+    "tests/unit/translator-friendly-stream-transformer.test.tsx",
+    "tests/unit/translator-friendly-test-bench.test.tsx",
+    "tests/unit/translator-friendly-translate-tab.test.tsx"
   ]
 }

docs/architecture/QUALITY_GATES.md

@@ -186,10 +186,10 @@ Runs on pull requests only.
 
 Runs after `build`. Blocks merge on failure.
 
-| Suite            | Validates                                               | Blocking                                                                                                      |
-| ---------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------- |
-| `test:vitest`    | MCP server (94 tools), autoCombo, cache — vitest runner | Yes                                                                                                           |
-| `test:vitest:ui` | UI component tests — vitest runner                      | **Blocking** — pre-existing failures are explicitly excluded in `vitest.config.ts`; new failures fail the job |
+| Suite            | Validates                                               | Blocking                                                                   |
+| ---------------- | ------------------------------------------------------- | -------------------------------------------------------------------------- |
+| `test:vitest`    | MCP server (94 tools), autoCombo, cache — vitest runner | Yes                                                                        |
+| `test:vitest:ui` | UI component tests — vitest runner                      | **Advisory** (`continue-on-error: true`) — failing until Fase 6A UI triage |
 
 ### Nightly workflows (scheduled, advisory)
 
@@ -401,7 +401,7 @@ several "obvious" merges turned out to hide debt and are **not** clean drop-ins.
 
 - `check:openapi-security-tiers` (advisory) — ❌ **NOT cleanly flippable.** It exits 0 but warns that several `traffic-inspector` routes under `LOCAL_ONLY_API_PREFIXES` lack the `x-loopback-only: true` annotation. Enforcing it requires adding those annotations to `openapi.yaml` first.
 - `typecheck:noimplicit:core` (advisory) — largely subsumed by the blocking `check:type-coverage` ratchet. Flip to a ratchet or drop the redundant second `tsc` pass.
-- `test:vitest:ui` (now **blocking**) — pre-existing failures are explicitly excluded in `vitest.config.ts` with `// #8618` tracking comments; new failures fail the job.
+- `test:vitest:ui` (advisory, 14 parked fails) — fix-and-block or delete; don't leave rotting.
 - `check:secrets` (gitleaks, blocking ratchet frozen at 3 documented false-positives) — allowlist the 3 to reach 0, or demote to advisory. Overlaps GitHub native secret-scanning + `check:public-creds`.
 - `check:pr-evidence` (blocking, greps PR-body prose) — high false-positive risk; weakens Hard Rule #18 enforcement if dropped, so this is a genuine policy call.
 - `semgrep` (advisory standalone) — overlaps CodeQL for the OWASP families; wire its baseline to a ratchet or drop.

docs/compression/COMPRESSION_GUIDE.md

@@ -158,7 +158,7 @@ error lines produced **95.93% token savings / 96.26% character savings** — squ
 range. But the same pipeline run against normal, non-redundant tool output (a clean `grep` match list,
 a short file read, ordinary conversational text) correctly produces **near-zero savings**, because
 there is nothing repetitive to remove and `validateCompression()` (`validation.ts`) refuses to ship a
-rewrite that would drop or alter code blocks, URLs, headings, versions, or ALL-CAPS constant identifiers.
+rewrite that would drop or alter code blocks, URLs, headings, versions, or `CONST_CASE` identifiers.
 
 This is expected, safe behavior, not a bug: a coding session that mostly reads/greps clean files will
 see modest total savings even with compression fully enabled, while a session that hits a failing

docs/frameworks/RADAR.md

@@ -107,18 +107,15 @@ client component never reads `process.env` itself.
 | `RADAR_CONTRIBUTOR_CLAIM_URL`   | Overrides the contributor-claim URL (default `https://radar.omniroute.online/auth/github`).   |
 | `RADAR_SUPPORTER_PLANS_URL`     | Overrides the supporter-plans URL (default `https://radar.omniroute.online/planos`).          |
 
-Once a visitor has a key (`omr_` + 40 hex chars), the activation screen
-(`src/app/(dashboard)/dashboard/radar/page.tsx`) has a paste-key input as the primary
-path: pasting a key and submitting sends `POST /api/radar/settings`
-(`{ optIn: true, supporterKey }`) in one call — pasting a key both sets it and opts in,
-unlocking the screen. The format (`omr_` + 40 hex chars) is checked client-side first
-with the shared `isValidSupporterKeyFormat()` helper (`src/lib/radar/supporterKey.ts`)
-as a UX nicety; the server's Zod schema is the authoritative check either way. Once a
-key is set, the activation screen shows the masked form (`supporterKeyMasked` from
-`GET /api/radar/settings`) instead of an empty input, with a "change key" control to
-paste a new one — the raw key is never redisplayed. The two claim/plans buttons above
-remain the way to *obtain* a key in the first place; this input is where an operator
-who already has one activates it.
+Once a visitor has a key (`omr_` + 40 hex chars), it is set with `POST
+/api/radar/settings` (`{ supporterKey }`) — the same endpoint documented under
+[Data sync](#data-sync-is-a-separate-opt-in--the-privacy-promise) above.
+
+**Known gap:** the dashboard activation screen does not yet have a dedicated
+key-paste input — pasting a key today requires calling `POST /api/radar/settings`
+directly (curl, a script, or a future UI). This release only adds the two claim/plans
+buttons; the API already accepts and masks the key, but no `<input>` for it exists in
+`src/app/(dashboard)/dashboard/radar/page.tsx` yet.
 
 ---
 
@@ -299,84 +296,36 @@ auth state — only the masked form and a `hasSupporterKey` boolean.
 
 ## Referral links (free credits)
 
-Referral links are served from a **standalone, always-current** feed —
-`GET /v1/referrals/latest` — separate from the catalog feed. This is deliberate: the
-catalog feed on the community tier is a snapshot that can be up to 30 days old, so a
-referral link extracted from it used to lag the server's real link list by the same
-amount (a newly-added referral wouldn't reach a free/community user for up to a month).
-The referrals feed removes that delay by syncing on its own, much shorter cadence.
+The server-published feed carries a `referrals` section (server-side D28 work, already
+in production — this section documents the **client** consumption only):
 
 ```ts
-// GET /v1/referrals/latest response body (Ed25519-signed, same pinned key as
-// the catalog feed):
-{
-  feed: "omniroute-radar-referrals",
-  schemaVersion: 1,
-  generatedAt: string,           // ISO — deterministic: max(updatedAt) across referral
-                                  // links, so two identical requests produce the exact
-                                  // same signed bytes/signature
-  referrals: {
-    fixed: RadarReferral[],      // present in EVERY tier, including no-auth/community
-    campaigns: RadarReferral[],  // only populated for a valid live (supporter) Bearer
-                                  // key; no-auth/expired-key requests get []
-  },
+referrals: {
+  fixed: RadarReferral[],      // present in EVERY tier, including community
+  campaigns: RadarReferral[],  // only populated on the live (supporter) tier;
+                                // the community artifact always publishes []
 }
 // RadarReferral = { provider, url, kind: "fixo" | "campanha", validUntil,
 //                    requiredAction, isDefault }
 ```
 
-Unlike the catalog feed, this body carries no `tier` field at all — the server decides
-what to include per-request based on the `Authorization` key, so the
-`x-omniroute-feed-tier` response header is the ONLY source for the served tier
-(`referralsSync.ts::syncRadarReferrals`); an absent/unrecognized header degrades to
-`"community"`, the least-privileged assumption. `RadarReferralsFeedSchema`
-(`src/lib/radar/referralsFeedSchema.ts`) validates the whole body, reusing the same
-per-referral `RadarReferralSchema` exported from `feedSchema.ts` so both feeds validate
-individual referrals identically. Every `RadarReferral.url` must be `https://` — a
-`http://` url fails schema validation.
-
-The OLD catalog-embedded `referrals` field on `RadarFeedSchema` (`feedSchema.ts`) is
-kept for backward-compat with already-cached catalog feeds, but `getRadarReferrals()`
-no longer reads it — see [Accessor](#accessor) below.
-
-### Sync
-
-`syncRadarReferrals()` (`src/lib/radar/referralsSync.ts`) is the ONLY module that
-touches the network for referrals, mirroring `syncRadar()`'s contract exactly: flag off
-→ `disabled`; opt-in false → `opt_out`; downloads `${RADAR_FEED_URL}/v1/referrals/latest`
-(same `RADAR_FEED_URL`/`RADAR_FEED_PUBKEY` fork overrides as the catalog), verifies the
-Ed25519 signature over the exact response bytes (`verifyFeedBytes`), validates against
-`RadarReferralsFeedSchema`, and caches into the `radar_referrals_cache` table
-(migration `142_radar_referrals_cache.sql`) — a table entirely separate from the
-catalog's `radar_feed_cache`. A 10 MB response cap and a `generatedAt` floor (an
-incoming feed with a `generatedAt` no newer than the cached one is treated as `stale`
-and never overwrites the cache — guards against a replay of an older signed artifact)
-mirror the catalog sync's own `MAX_FEED_BYTES`/version-floor guards. Never throws —
-always returns a status object; errors never carry a stack trace in `reason`.
-
-Two triggers keep the referrals cache warm, both independent of the catalog's own
-24h cadence:
-
-- **Sync-on-read** — `GET /api/radar/referrals` itself calls `syncRadarReferrals()`
-  inline whenever the cache is missing or older than `REFERRALS_STALE_MS` (1h,
-  `shouldSyncReferralsOnRead()`), before serving the response. This is what makes fixed
-  links "always current" for the very next dashboard load, without waiting on any
-  background timer.
-- **Scheduler side-sync** — `radarSchedulerTick()` (`scheduler.ts`) independently
-  evaluates referrals staleness on the same hourly tick used for the catalog, calling
-  `syncRadarReferrals()` when due. This runs regardless of whether the catalog itself
-  was due that tick, and never affects `RadarTickResult`'s shape (best-effort side
-  effect only, swallowed on error).
+The client never decides which tier it received or which referrals belong in which
+tier — the server already publishes two artifacts (`live`/`community`) with
+`campaigns` gated server-side, same principle as the [tiers](#tiers-community-and-live)
+section above. `RadarFeedSchema` (`src/lib/radar/feedSchema.ts`) validates `referrals`
+as a whole-object `.default({fixed:[],campaigns:[]})`, and `campaigns` defaults
+independently inside it — so a feed cached before this section existed on the server
+still parses cleanly, and `campaigns` alone can also be absent without failing
+validation. Every `RadarReferral.url` must be `https://` — a `http://` url fails
+schema validation.
 
 ### Accessor
 
 `src/lib/radar/index.ts` exports two read-only accessors, both never throwing (same
-defensive contract as `getRadarCatalog()` — flag off, no cache, or a corrupt cached
+defensive contract as `getRadarCatalog()` — flag off, no cache, or a corrupt/old cached
 payload all resolve to the empty shape instead of an error):
 
-- `getRadarReferrals()` → `{ fixed: RadarReferral[], campaigns: RadarReferral[] }`,
-  reading from `radar_referrals_cache` (via `getRadarReferralsCache()`) and validating
-  through `RadarReferralsFeedSchema` — **not** the catalog cache.
+- `getRadarReferrals()` → `{ fixed: RadarReferral[], campaigns: RadarReferral[] }`.
 - `getDefaultReferralFor(provider)` → the `fixed` referral with `isDefault: true` for
   that provider, or `null`. Only looks at `fixed` — a campaign is never used as a
   provider's "default" link.
@@ -391,13 +340,11 @@ server-only; the providers dashboard imports `referrals.ts` directly instead of
 ### `GET /api/radar/referrals`
 
 Follows the exact same gate order as every other Radar route: `RADAR_ENABLED` off →
-`404` (checked first, byte-identical inertia); unauthenticated → `401`; otherwise
-triggers a sync-on-read (see above) when stale, then `200` with
-`{ fixed, campaigns, tier }` — `tier` comes straight from the (possibly just-refreshed)
-cache row and is purely informative (drives the UI's soft upsell copy below). Never
-proxies the feed server directly — the route's own source contains no `fetch(` call;
-the network only ever happens inside `syncRadarReferrals()`, same local-cache-only
-principle as `/api/radar/catalog`.
+`404` (checked first, byte-identical inertia); unauthenticated → `401`; otherwise `200`
+with `{ fixed, campaigns, tier }` — `tier` comes straight from the cache row and is
+purely informative (drives the UI's soft upsell copy below), the route does no
+gating of its own. Never proxies the feed server — same local-cache-only contract as
+`/api/radar/catalog`.
 
 ### Dashboard UI — "Free credits" tab on `/dashboard/radar`
 
@@ -465,16 +412,6 @@ automatically (`getFeedPublicKeys()` in `src/lib/radar/pinnedKeys.ts`), and vers
 comparison, schema validation, and the merge rules apply identically to a self-hosted
 feed.
 
-Referral links (see [Referral links (free credits)](#referral-links-free-credits)
-above) are a separate, optional artifact: a fork that only serves `/v1/catalog/latest`
-still works fully — `syncRadarReferrals()` degrades to `{ status: "error" }` on a `404`
-from `/v1/referrals/latest` and the cache simply stays empty, so
-`GET /api/radar/referrals` keeps returning `{ fixed: [], campaigns: [], tier: null }`
-instead of failing the rest of the page. To also offer referral links, serve
-`GET /v1/referrals/latest` satisfying `RadarReferralsFeedSchema`
-(`src/lib/radar/referralsFeedSchema.ts`) and sign it with the same Ed25519 key pair as
-the catalog feed.
-
 ---
 
 ## Related docs

docs/getting-started/WEB-COOKIE-GUIDE.md

@@ -18,7 +18,7 @@ Unlike API-key providers, Web Cookie providers authenticate using the credential
 
 Many authentication issues are caused by copying cookies from the wrong place.
 
-## Do NOT copy from Cookie Storage
+##  Do NOT copy from Cookie Storage
 
 Most browsers expose stored cookies through:
 
@@ -36,7 +36,7 @@ Although these cookies look correct, they may be:
 
 Using these values may cause authentication failures even if they appear valid.
 
-## Copy from a Live Request
+##  Copy from a Live Request
 
 Instead, use the cookies from a successful request:
 
@@ -80,14 +80,14 @@ The exact credentials required depend on the provider.
 
 Different websites store authentication differently. Some require only cookies, while others may require additional headers or tokens.
 
-| Provider    | Credential Format                                              | Provider Guide                  |
-| ----------- | -------------------------------------------------------------- | ------------------------------- |
-| Claude Web  | Full Cookie request header                                     | `docs/providers/CLAUDE_WEB.md`  |
-| ChatGPT Web | Full Cookie header or `__Secure-next-auth.session-token` value | `docs/providers/CHATGPT_WEB.md` |
-| Gemini Web  | _(verify)_                                                     |                                 |
-| Copilot Web | _(verify)_                                                     |                                 |
-| Grok Web    | _(verify)_                                                     |                                 |
-| ...         | ...                                                            | ...                             |
+| Provider | Credential Format | Provider Guide |
+|----------|-------------------|----------------|
+| Claude Web | Full Cookie request header | `docs/providers/CLAUDE_WEB.md` |
+| ChatGPT Web | _(verify)_ | |
+| Gemini Web | _(verify)_ | |
+| Copilot Web | _(verify)_ | |
+| Grok Web | _(verify)_ | |
+| ... | ... | ... |
 
 > Update this table as new Web Cookie providers are added or existing providers change their authentication requirements.
 

docs/guides/DOCKER_GUIDE.md

@@ -147,11 +147,11 @@ The prod stack runs in parallel with the dev compose (different container names,
 
 The repository ships a multi-stage Dockerfile (`Dockerfile`). Three stages are exposed; pick the right `target` for your use case.
 
-| Stage         | Base image            | Purpose                                                                                                                                                            |
-| ------------- | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `builder`     | `node:26-trixie-slim` | Installs deps (`npm ci --legacy-peer-deps`) and runs `npm run build` (Turbopack by default — see Build-time resources below)                                       |
-| `runner-base` | `node:26-trixie-slim` | Production runtime with the Next.js standalone output. **No provider CLIs bundled.**                                                                               |
-| `runner-cli`  | `runner-base`         | Adds `git`, `docker.io`, `docker-compose` and global CLIs: `@openai/codex`, `@anthropic-ai/claude-code`, `droid`, `openclaw`. **Pick this for agentic workflows.** |
+| Stage         | Base image                 | Purpose                                                                                                                                                            |
+| ------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `builder`     | `node:24.15.0-trixie-slim` | Installs deps (`npm ci --legacy-peer-deps`) and runs `npm run build -- --webpack`                                                                                  |
+| `runner-base` | `node:24.15.0-trixie-slim` | Production runtime with the Next.js standalone output. **No provider CLIs bundled.**                                                                               |
+| `runner-cli`  | `runner-base`              | Adds `git`, `docker.io`, `docker-compose` and global CLIs: `@openai/codex`, `@anthropic-ai/claude-code`, `droid`, `openclaw`. **Pick this for agentic workflows.** |
 
 Build a specific target manually:
 
@@ -160,50 +160,14 @@ docker build --target runner-base -t omniroute:base .
 docker build --target runner-cli  -t omniroute:cli  .
 ```
 
-### Build-time resources
-
-Two build args control what the `builder` stage costs. They are build-time only —
-`OMNIROUTE_MEMORY_MB` (below) is a separate, runtime knob.
-
-| Build arg                   | Default | Effect                                                                 |
-| --------------------------- | ------- | ---------------------------------------------------------------------- |
-| `OMNIROUTE_USE_TURBOPACK`   | `1`     | `0` builds with webpack instead. Lower peak memory, slower.            |
-| `OMNIROUTE_BUILD_MEMORY_MB` | `4096`  | V8 heap ceiling (`--max-old-space-size`) for the spawned `next build`. |
-
-Turbopack compiles in native Rust memory that lives **outside** the V8 heap, so
-`OMNIROUTE_BUILD_MEMORY_MB` does not bound it. On a host with a memory ceiling the
-build is then SIGKILLed by the OOM killer with no error text at all — it simply
-stops mid-`Creating an optimized production build`, which reads like a hang rather
-than an out-of-memory. If the build host is constrained, switch bundlers:
-
-```bash
-docker build --target runner-base \
-  --build-arg OMNIROUTE_USE_TURBOPACK=0 \
-  -t omniroute:base .
-```
-
-`webpackBuildWorker` is enabled, so `next build` runs a parent **and** a worker
-process and each honours `OMNIROUTE_BUILD_MEMORY_MB` separately. Size the container
-ceiling above roughly twice that value, not once.
-
-Measured on this tree (`--target runner-base`, `OMNIROUTE_BUILD_MEMORY_MB=6144`):
-
-| Bundler   | Container ceiling | Result                        |
-| --------- | ----------------- | ----------------------------- |
-| Turbopack | 8 GiB / 16 GiB    | OOM-killed at both, silently  |
-| webpack   | 8 GiB             | build worker SIGKILLed        |
-| webpack   | 12 GiB            | succeeded, peaked at 11.1 GiB |
-
-### Runtime defaults
-
-Defaults exported by `runner-base`: `PORT=20128`, `HOSTNAME=0.0.0.0`, `OMNIROUTE_MEMORY_MB=1024`, `NODE_OPTIONS=--max-old-space-size=1024`, `DATA_DIR=/app/data`, `OMNIROUTE_MIGRATIONS_DIR=/app/migrations`.
+Defaults exported by `runner-base`: `PORT=20128`, `HOSTNAME=0.0.0.0`, `NODE_OPTIONS=--max-old-space-size=512`, `DATA_DIR=/app/data`, `OMNIROUTE_MIGRATIONS_DIR=/app/migrations`.
 
 Memory behavior in Docker:
 
-- The image sets `OMNIROUTE_MEMORY_MB=1024` and derives `NODE_OPTIONS=--max-old-space-size=1024` from it.
+- `NODE_OPTIONS=--max-old-space-size=512` is baked into the image as a fallback.
 - The actual server process is started by the standalone launcher, which reads `OMNIROUTE_MEMORY_MB` and appends `--max-old-space-size=<OMNIROUTE_MEMORY_MB>`.
 - Node uses the last repeated `--max-old-space-size` value, so setting `OMNIROUTE_MEMORY_MB` controls the effective Docker heap limit.
-- Because the image always sets it, the launcher's own RAM-calibrated fallback never applies under Docker. Raise it explicitly (`-e OMNIROUTE_MEMORY_MB=2048`) on a host with headroom.
+- If `OMNIROUTE_MEMORY_MB` is unset, the launcher uses `512`.
 
 ## Critical Environment Variables
 
@@ -216,7 +180,7 @@ Beyond the defaults documented in [ENVIRONMENT.md](../reference/ENVIRONMENT.md),
 | `REDIS_PORT`                  | Host-side port for the bundled Redis container                                                      | `6379`                   |
 | `REDIS_BIND_HOST`             | Host interface the bundled Redis port is published on (loopback unless you add AUTH)                | `127.0.0.1`              |
 | `AUTO_UPDATE_HOST_REPO_DIR`   | Host path mounted into `cli` profile at `/workspace/omniroute` for self-update workflows            | `.` (current directory)  |
-| `OMNIROUTE_MEMORY_MB`         | Runtime Node heap ceiling for the Docker standalone server; overrides the image default above       | `1024`                   |
+| `OMNIROUTE_MEMORY_MB`         | Runtime Node heap ceiling for the Docker standalone server; overrides the image fallback above      | `512`                    |
 | `DASHBOARD_PORT` / `API_PORT` | Override exposed ports for dashboard (20128) and API (20129)                                        | `20128` / `20129`        |
 | `OMNIROUTE_BASE_PATH`         | URL subpath when the app is published behind a reverse proxy (e.g. `/omniroute`)                    | _(empty = root)_         |
 | `NEXT_PUBLIC_BASE_URL`        | Public browser origin including the subpath (e.g. `https://host/omniroute`)                         | unset                    |

docs/guides/TROUBLESHOOTING.md

@@ -523,12 +523,6 @@ exhausts its bounds of `10,000` visited nodes or depth `12`.
 Each process uses a process-local guard to reserve limited heavyweight capacity before retaining
 and parsing a large request body. A heavyweight lease remains held for the lifetime of an SSE
 response.
-
-When capacity is busy, a heavyweight request first waits up to
-`OMNIROUTE_CHAT_ADMISSION_QUEUE_MS` (default `5000`, `0` disables the wait) for a slot to free up
-before answering the retryable `503`. The bounded wait exists so agent-style clients
-(OpenCode, Claude Code, Cursor) that fan out heavy sub-requests concurrently serialize the burst
-instead of burning their whole retry budget on immediate rejections and dying mid-task.
 Current heavyweight lease occupancy is not surfaced in the dashboard.
 Settings → Resilience → Request Queue → Concurrent Requests does not control this; that setting
 governs a separate provider request-queue mechanism.
@@ -536,18 +530,13 @@ governs a separate provider request-queue mechanism.
 **Fix:**
 
 1. Retry first. Clients should honor `Retry-After` and use backoff rather than immediately
-   repeating the request. Note that with the default `OMNIROUTE_CHAT_ADMISSION_QUEUE_MS=5000`
-   a heavy request already waited up to 5 seconds before the `503`, so a client retry loop should
-   back off beyond that instead of hammering.
+   repeating the request.
 2. If normal deployment traffic repeatedly exhausts the guard, you can cautiously raise
    `OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT` from its default of `1`. Increase it one step at a time,
    restart OmniRoute after each change, and observe memory headroom under representative load.
    Every additional heavyweight request can increase concurrent V8 heap use and container or
    host OOM risk. No value is safe for every deployment; validate the setting against your own
    traffic and memory limits rather than assuming that `2` is universally safe.
-3. Prefer widening the wait (`OMNIROUTE_CHAT_ADMISSION_QUEUE_MS`) over raising the in-flight
-   limit when bursts are short: waiting costs latency, while an extra concurrent heavyweight
-   request costs heap residency for the whole request lifetime.
 
 See the [environment-variable reference](../reference/ENVIRONMENT.md#4-security--authentication)
 for the authoritative admission settings. Loosening the heavyweight classification thresholds

docs/openapi.yaml

@@ -5225,102 +5225,6 @@ paths:
         "200":
           description: Sync initialized
 
-  # ─── Background Jobs (local-only administration) ───────────────
-
-  /api/jobs:
-    get:
-      tags: [System]
-      summary: List registered background jobs
-      description: Local-only runtime administration. Returns each registered job and its latest run.
-      x-internal: true
-      responses:
-        "200":
-          description: Registered jobs
-        "500":
-          description: Failed to list jobs
-
-  /api/jobs/{id}/enable:
-    post:
-      tags: [System]
-      summary: Enable a background job
-      description: Local-only runtime administration. Enables the job and restarts its timer.
-      x-internal: true
-      parameters:
-        - name: id
-          in: path
-          required: true
-          schema:
-            type: string
-      responses:
-        "200":
-          description: Job enabled
-        "404":
-          description: Job not found
-        "500":
-          description: Failed to enable job
-
-  /api/jobs/{id}/disable:
-    post:
-      tags: [System]
-      summary: Disable a background job
-      description: Local-only runtime administration. Disables the job and stops its timer.
-      x-internal: true
-      parameters:
-        - name: id
-          in: path
-          required: true
-          schema:
-            type: string
-      responses:
-        "200":
-          description: Job disabled
-        "404":
-          description: Job not found
-        "500":
-          description: Failed to disable job
-
-  /api/jobs/{id}/run-now:
-    post:
-      tags: [System]
-      summary: Trigger a background job
-      description: >-
-        Local-only runtime administration. Starts the job, or waits for an in-flight
-        run before queueing the next one, subject to OMNIROUTE_RUNNOW_TIMEOUT_MS.
-      x-internal: true
-      parameters:
-        - name: id
-          in: path
-          required: true
-          schema:
-            type: string
-      responses:
-        "200":
-          description: Job trigger accepted
-        "404":
-          description: Job not found
-        "500":
-          description: Failed to trigger job
-
-  /api/jobs/{id}/runs:
-    get:
-      tags: [System]
-      summary: Read background-job run history
-      description: Local-only runtime administration. Returns newest-first run history for one job.
-      x-internal: true
-      parameters:
-        - name: id
-          in: path
-          required: true
-          schema:
-            type: string
-      responses:
-        "200":
-          description: Job run history
-        "404":
-          description: Job not found
-        "500":
-          description: Failed to load job runs
-
   # ─── Resilience & Monitoring ────────────────────────────────────
 
   /api/resilience:
@@ -5343,70 +5247,6 @@ paths:
         "200":
           description: Updated resilience configuration
 
-  /api/resilience/connections:
-    get:
-      tags: [System]
-      summary: Inspect connection resilience state
-      description: >-
-        Local-only operational view of per-connection cooldowns, provider circuit
-        breakers, model lockouts, and recent breaker transitions. Credential columns
-        are excluded by an explicit database whitelist.
-      x-internal: true
-      parameters:
-        - name: windowMs
-          in: query
-          schema:
-            type: integer
-            minimum: 0
-            maximum: 86400000
-            default: 3600000
-        - name: provider
-          in: query
-          schema:
-            type: string
-            minLength: 1
-            maxLength: 64
-      responses:
-        "200":
-          description: Connection, breaker, lockout, window, and degradation metadata
-        "400":
-          description: Invalid query parameters
-        "500":
-          description: Failed to collect resilience state
-
-  /api/telegram/update:
-    post:
-      tags: [System]
-      summary: Receive Telegram updates or Mini App messages
-      description: >-
-        Public Telegram integration endpoint. Bot updates are acknowledged after
-        reply dispatch is queued. Mini App requests must include Telegram-signed
-        initData, which is verified with TELEGRAM_BOT_TOKEN before chat proxying.
-      security: []
-      requestBody:
-        required: true
-        content:
-          application/json:
-            schema:
-              type: object
-              additionalProperties: true
-              properties:
-                initData:
-                  type: string
-                message:
-                  type: string
-                update_id:
-                  type: integer
-      responses:
-        "200":
-          description: Update acknowledged or Mini App reply returned
-        "400":
-          description: Invalid JSON, request shape, or missing Mini App message
-        "401":
-          description: Invalid Mini App initData signature
-        "503":
-          description: Telegram integration is not configured
-
   /api/resilience/reset:
     post:
       tags: [System]
@@ -5454,19 +5294,6 @@ paths:
         "200":
           description: Caches cleared
 
-  /api/modality-bridge/stats:
-    get:
-      tags: [System]
-      summary: Get Modality Bridge telemetry
-      description: In-memory per-modality bridge counters (bridged, cacheHits, failures, lastUsedAt). Counters reset on process restart.
-      security:
-        - ManagementSessionAuth: []
-      responses:
-        "200":
-          description: Per-modality bridge stats (vision, audio)
-        "401":
-          description: Unauthorized
-
   /api/cache/stats:
     get:
       tags: [System]

docs/proposals/TELEGRAM-MINIAPP.md

@@ -1,143 +0,0 @@
----
-title: "Feasibility — Telegram Mini App Integration"
-version: 3.8.49
-lastUpdated: 2026-08-08
----
-
-# Telegram Mini App Integration — Feasibility Analysis
-
-**Status: FEASIBLE with moderate effort (estimated 2–4 dev-days for a working slice)**
-
-## 1. What "Telegram Mini App" means here
-
-A Telegram Mini App is an iframe-hosted web app opened inside Telegram (via
-inline buttons / bot menu buttons) that talks to a bot backend through the
-[Telegram WebApp SDK](https://core.telegram.org/bots/webapps). For OmniRoute
-the natural shape is:
-
-- **Bot backend** (new): receives Telegram updates (webhook), validates the
-  Mini App's `initData` signature, and proxies chat requests to OmniRoute's
-  existing OpenAI-compatible `/v1/chat/completions` surface.
-- **Mini App frontend** (new): a small chat UI served by OmniRoute (Next.js
-  route or `public/` static bundle), using the Telegram WebApp JS SDK.
-
-## 2. Current state of the codebase (verified against `main` @ 918fba5e3)
-
-### Already present — outbound notifications only
-
-| Piece                        | Location                                    | What it does                                                                                    |
-| ---------------------------- | ------------------------------------------- | ----------------------------------------------------------------------------------------------- |
-| Telegram webhook integration | `src/lib/webhooks/integrations/telegram.ts` | Builds `sendMessage` payloads for **outbound** gateway events (model, provider, latency, error) |
-| Webhook dispatcher           | `src/lib/webhookDispatcher.ts`              | Routes by kind; decrypts `botToken` from DB metadata for telegram                               |
-| Webhook kinds                | `src/lib/db/webhooks.ts`                    | `slack \| telegram \| discord \| custom`                                                        |
-| Webhook CRUD + test          | `src/app/api/webhooks/*`                    | Create/update/test; telegram kind skips `url` (uses bot token + chat_id)                        |
-| Bot token validation         | `telegram.ts:18`                            | `BOT_TOKEN_RE = /^\d+:[A-Za-z0-9_-]{35,}$/`                                                     |
-| Encryption requirement       | `webhooks/route.ts:77`                      | Telegram webhooks require DB encryption enabled (bot tokens stored at rest)                     |
-
-### Missing — what a Mini App needs that does not exist yet
-
-| Gap                              | Detail                                                                                                                                                                                      |
-| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Inbound Bot API listener**     | No `setWebhook` registration, no `/bot<token>/getUpdates` polling, no update handling anywhere. Only the `sendMessage` direction exists.                                                    |
-| **WebApp `initData` validation** | No HMAC-SHA256 check of `initData` against the bot token (`WebAppData` hash validation from the Bot API docs).                                                                              |
-| **Telegram bot library**         | `package.json` has no `telegraf`/`grammy`/`telegram-bot-api` dependency. Would need to add one or hand-roll the (small) HMAC + fetch logic.                                                 |
-| **Mini App hosting surface**     | `public/` exists (static assets) and Next.js routes exist; no `/miniapp` route or static bundle yet.                                                                                        |
-| **Session → API key mapping**    | Mini App users need to authenticate to `/v1/chat/completions`. Two options: per-user generated OmniRoute API keys (via `src/lib/db/apiKeys`) or a bot-side proxy that injects a shared key. |
-
-## 3. Constraints
-
-### 3.1 Architectural
-
-- **No existing inbound-bot layer.** The webhook system is strictly
-  event→outbound. A Mini App needs a _new_ Bot API webhook endpoint
-  (`POST /api/telegram/webhook/<botToken-prefix>` or a dedicated route) plus
-  update dispatch. This is additive — no conflicts with the existing
-  `webhooks/` subsystem, but the two must not share the `botToken` storage
-  semantics blindly (webhooks store bot tokens for _outbound_; the Mini App
-  needs the same token for _inbound_ signature checks — same token, new use).
-- **Public HTTPS required.** Telegram only delivers updates to an HTTPS
-  endpoint with a valid cert. Self-hosted OmniRoute behind Tailscale/ngrok
-  needs a public tunnel or Cloudflare Tunnel for the webhook path
-  (a future webhook-URL setting). The dashboard can render the current
-  public origin (`OMNIROUTE_PUBLIC_BASE_URL`) but no webhook registration
-  helper exists.
-- **Encryption gate.** `webhooks/route.ts:77` already refuses telegram
-  kinds without DB encryption. The Mini App bot token has the same
-  sensitivity (it _is_ the HMAC secret for initData validation) — same gate
-  applies, which is a _good_ constraint (no plaintext tokens).
-
-### 3.2 Telegram platform
-
-- **initData is the only trust anchor.** Mini App auth = verify
-  `hash` field of `initData` using HMAC-SHA256(key = SHA256(bot_token),
-  data = sorted `key=value` pairs minus `hash`). Must be implemented
-  server-side; never trust the client.
-- **No inbound push to arbitrary users.** Telegram bots cannot initiate
-  conversations. The Mini App works for users who _already_ have the bot —
-  or you add a `/start` command handler + deep-link (`t.me/bot?startapp=`).
-- **Rate limits.** Bot API ~30 msg/s per bot, 20 msg/min per chat group.
-  Chat responses via `sendMessage`/`answerWebAppQuery` are fine at gateway
-  scale, but streaming must be emulated (send progressive edits or chunked
-  messages) — no native SSE into Telegram.
-- **WebApp SDK quirks.** `Telegram.WebApp.ready()` must be called; theme
-  params come from the SDK; the mini app is sandboxed iframe (no
-  `window.open` to external, clipboard limited). For a chat UI this is fine.
-
-### 3.3 Security / policy
-
-- **Per-user key issuance is the clean model.** Rather than exposing the
-  admin's own API keys, mint a scoped OmniRoute API key per Telegram user
-  (`apiKeys` table + `isModelAllowedForKey` policy), or proxy with a single
-  gateway key and map `user_id` → account. Recommendation: per-user keys so
-  existing rate-limit / model-allowlist / policy code applies unchanged.
-- **initData expiry.** `auth_date` in initData must be checked (Telegram
-  recommends < 24h; short TTLs for chat flows).
-- **Secret handling.** Bot token must stay in the encrypted DB / env —
-  mirror the existing `isEncryptionEnabled()` gate.
-
-## 4. Required next steps (implementation plan)
-
-### Phase 0 — Spike (½–1 dev-day)
-
-1. Add `grammy` or `telegraf` (or ~60 lines of hand-rolled HMAC + fetch).
-2. Implement `src/lib/telegram/initData.ts` — `verifyInitData(initData, botToken)`.
-3. Stand up a throwaway `POST /api/telegram/miniapp/webhook` route behind
-   a dedicated webhook secret; register via `setWebhook` once, locally.
-
-### Phase 1 — Minimal chat slice (1–2 dev-days)
-
-1. **Webhook endpoint** `POST /api/telegram/bot/update` (or
-   `/api/telegram/miniapp/update`): parse Update, verify initData, dispatch.
-2. **Command handler**: `/start` → reply with deep link
-   `https://t.me/<bot>?startapp=<userKey>`; `startapp` param carries a
-   one-time token that maps to a generated OmniRoute API key.
-3. **Chat proxy**: map `initData.user.id` → API key → call
-   `handleChat` (same path as `/v1/chat/completions`) → reply via
-   `sendMessage` (non-stream) or chunked edits (fake streaming).
-4. **Mini App page**: `src/app/(dashboard)/miniapp/page.tsx` (or static
-   bundle in `public/miniapp/`) — Telegram WebApp SDK init + minimal chat
-   UI posting to the bot webhook.
-5. **Config**: `TELEGRAM_BOT_TOKEN` env (or reuse webhook metadata),
-   `OMNIROUTE_PUBLIC_BASE_URL` for webhook URL display; doc in
-   `.env.example` + `ENVIRONMENT.md` (env-doc-sync check).
-
-### Phase 2 — Production hardening (1 dev-day)
-
-- Streaming emulation (message edits), error/backpressure mapping to Bot API
-  limits, per-user key revocation (`/logout` command → revoke API key),
-  usage/rate-limit surfacing (reuse `enforceApiKeyPolicy`), webhook
-  registration helper in dashboard settings, i18n for the mini app UI.
-
-## 5. Verdict
-
-**Feasible.** The gateway already exposes the exact API a Mini App chat
-needs (`/v1/chat/completions` with per-key policy), and the outbound
-Telegram webhook shows the team already handles bot tokens safely
-(encryption gate + token format validation). The genuinely new surface is
-small: an inbound update webhook + initData HMAC verification + a thin
-chat proxy + a static Mini App page. No changes to the core SSE/relay
-pipeline are required.
-
-**Primary risks:** (1) public HTTPS requirement for the webhook (tunnel
-needed on self-hosted installs), (2) no native streaming to Telegram
-(UX tradeoff), (3) initData trust must be strictly server-side.

docs/providers/CHATGPT_WEB.md

@@ -1,125 +0,0 @@
----
-title: "Providers — ChatGPT Web (session credentials via Cookie Editor)"
-version: 3.8.50
-lastUpdated: 2026-08-08
----
-
-# Providers — ChatGPT Web (Plus/Pro session credentials)
-
-`chatgpt-web` (alias `cgpt-web`, display name **ChatGPT Web (Plus/Pro)**) sends OpenAI-format chat requests through an authenticated `chatgpt.com` browser session. It authenticates with the `__Secure-next-auth.session-token` cookie — **no API key required**.
-
-> **New to Web Cookie providers?**
->
-> Read **`docs/getting-started/WEB-COOKIE-GUIDE.md`** for the general setup process, limitations, and troubleshooting before following this provider-specific guide.
-
----
-
-## 1. What credential does OmniRoute need?
-
-Defined in `src/shared/constants/providers/web-cookie.ts` + `src/shared/providers/webSessionCredentials.ts`:
-
-| Field                      | Value                                                                         |
-| -------------------------- | ----------------------------------------------------------------------------- |
-| Provider id                | `chatgpt-web`                                                                 |
-| Credential name            | `__Secure-next-auth.session-token`                                            |
-| Accepts full Cookie header | ✅ yes                                                                        |
-| Accepted storage keys      | `cookie`, `sessionToken`, `session-token`, `__Secure-next-auth.session-token` |
-
-Two paste formats both work:
-
-- **Bare value** — just the token contents: `eyJhbGciOi...`
-- **Full Cookie header** — `__Secure-next-auth.session-token=eyJhbGciOi...; cf_clearance=...` (preferred — carries rotation/anti-bot cookies the executor needs)
-
----
-
-## 2. Copy the cookie header with Cookie Editor
-
-Cookie Editor can copy the cookies for the active `chatgpt.com` tab as an HTTP header string.
-Always compare the exported value with a live authenticated request as described in section 3.
-
-### 2.1 Install and pin
-
-1. Install **[Cookie-Editor](https://chromewebstore.google.com/detail/cookie-editor/hlkenndednhfkekhgcdicdfddnkalmdm)** (Moustachauve) in Chrome/Edge, or the Firefox equivalent.
-2. Pin it to the toolbar if you use it regularly.
-
-### 2.2 Copy the credential
-
-1. Go to **https://chatgpt.com** and make sure you're **signed in with the Plus/Pro account** you want OmniRoute to use.
-2. Open a conversation and send at least one message (forces the session token to be live/refreshed).
-3. Click the **Cookie Editor** icon to open its side panel for the active tab.
-4. Find `__Secure-next-auth.session-token`. If it's split into chunks (`__Secure-next-auth.session-token.0`, `.1`, …), select **all** of them — OmniRoute's `nextAuthCookie.ts` merges rotated chunk families.
-5. Click **Copy**, choose **Header string**, and copy the resulting `name=value; name=value` text.
-
-> **If the token is missing:** confirm that you are signed in, send a message to refresh the session, and inspect the live request in section 3.
-
----
-
-## 3. Verify the required data (before pasting)
-
-The repo's `WEB-COOKIE-GUIDE.md` mandates a live-request check. Do it once per session:
-
-1. With chatgpt.com open, press **F12** → **Network** tab.
-2. Refresh the page, then send a chat message.
-3. Click the conversation request (e.g. `/backend-api/conversation` or the SSE stream) → **Headers** → **Request Headers** → **Cookie**.
-4. Confirm it contains `__Secure-next-auth.session-token=...` — **not** just `cf_clearance` or `__cf_bm`.
-
-The value you copied in step 2.3 must match what the live request sends. If they differ, re-copy from Cookie Editor.
-
----
-
-## 4. Add / update the credential in OmniRoute
-
-### Dashboard (typical user path)
-
-1. Open the OmniRoute dashboard → **Providers** → **Add Provider**.
-2. Search **ChatGPT Web (Plus/Pro)** (id `chatgpt-web`).
-3. Paste the copied cookie header into the credential field.
-4. Click **Test Connection**.
-5. Save.
-
-If requests later return 401 or 403, re-copy the header from a fresh live session. The executor merges `Set-Cookie` rotations while the connection is active, but it cannot recover a credential that is no longer accepted upstream.
-
-### Bulk / session pools (many accounts)
-
-For multiple ChatGPT sessions, use the bulk web-session import or session-pool endpoints:
-
-- `POST /api/providers/bulk-web-session` — import many cookie credentials at once
-- `GET /api/session-pools` + `/api/session-pools/[provider]` — pool rotation across accounts
-
-Each credential blob must carry the `__Secure-next-auth.session-token` value under one of the accepted storage keys (`cookie`, `sessionToken`, `session-token`, or the cookie's exact name).
-
-### Renewing when the session expires
-
-Web sessions can stop working after sign-out or server-side rotation. Re-run steps 2.2 through 4 whenever requests start failing with 401/403.
-
----
-
-## 5. Contributing updates
-
-If you changed the credential contract (new storage key, new cookie name, changed hint) or are filling the docs gap, contribute it:
-
-1. Update `src/shared/providers/webSessionCredentials.ts` (credential name / placeholder / storage keys) or `src/shared/constants/providers/web-cookie.ts` (`authHint`).
-2. Update this guide (`docs/providers/CHATGPT_WEB.md`) and the provider table in `docs/getting-started/WEB-COOKIE-GUIDE.md`.
-3. Update `.env.example` + `docs/reference/ENVIRONMENT.md` if you touched env vars, then run:
-   ```bash
-   node scripts/check/check-env-doc-sync.mjs   # must pass
-   ```
-4. Run the provider/unit tests:
-   ```bash
-   npm run test:unit
-   # targeted: tests/unit/chatgpt-web.test.ts (stealth path)
-   ```
-5. Follow `CONTRIBUTING.md`, branch from the current active release tip, use a Conventional Commit message, and open the PR against that active release branch.
-
-> ⚠️ **Never commit a real cookie value.** All examples above are placeholders. If a test fixture needs a token, use a fake `eyJhbGciOi...` string.
-
----
-
-## Troubleshooting
-
-| Symptom                          | Likely cause                                 | Fix                                                       |
-| -------------------------------- | -------------------------------------------- | --------------------------------------------------------- |
-| Cookie not in Cookie Editor      | Signed out / not HttpOnly-visible            | Sign in; enable HttpOnly display in options               |
-| Token missing from live request  | Request is not authenticated                  | Sign in and send a chat message first                     |
-| 401 after Test Connection passed | Expired or rotated session                    | Re-copy from a fresh live request                         |
-| Chunked token fails              | Only one chunk pasted                        | Select all `__Secure-next-auth.session-token.*` chunks    |

docs/reference/API_REFERENCE.md

@@ -573,7 +573,6 @@ Response example:
 | `/api/rate-limits`       | GET        | Per-account rate limits                                                                              |
 | `/api/monitoring/health` | GET        | Health check + provider summary (`catalogCount`, `configuredCount`, `activeCount`, `monitoredCount`) |
 | `/api/cache/stats`       | GET/DELETE | Cache stats / clear                                                                                  |
-| `/api/modality-bridge/stats` | GET    | In-memory Modality Bridge telemetry — per-modality `bridged`/`cacheHits`/`failures`/`lastUsedAt` counters (reset on restart; management auth) |
 
 ### Backup & Export/Import
 

docs/reference/ENVIRONMENT.md

@@ -736,12 +736,12 @@ The logging system writes to both stdout and rotated log files. All configuratio
 | `CALL_LOGS_TABLE_MAX_ROWS`                | `100000`                   | Max rows in the `call_logs` SQLite table before pruning.                          |
 | `ENABLE_REQUEST_LOGS`                     | _(unset)_                  | Force detailed request logging on or off, overriding the dashboard setting.       |
 | `MAX_PENDING_REQUEST_AGE_MS`              | `3600000` (1 hour)         | Max age for orphaned active request log entries before in-memory cleanup.         |
-| `CALL_LOG_PIPELINE_CAPTURE_STREAM_CHUNKS` | `false`                    | Store stream chunks in pipeline artifacts when `call_log_pipeline_enabled=true`. Opt-in (`true`) — off by default to save disk. |
+| `CALL_LOG_PIPELINE_CAPTURE_STREAM_CHUNKS` | `true`                     | Store stream chunks in pipeline artifacts when `call_log_pipeline_enabled=true`.  |
 | `CALL_LOG_PIPELINE_MAX_SIZE_KB`           | `512`                      | Max pipeline call log artifact size in KB when `call_log_pipeline_enabled=true`.  |
 | `PROXY_LOGS_TABLE_MAX_ROWS`               | `100000`                   | Max rows in the `proxy_logs` SQLite table before pruning.                         |
 | `APP_LOG_ROTATION_CHECK_INTERVAL_MS`      | `60000` (1 min)            | How often `src/lib/logRotation.ts` re-checks the active log file size.            |
 | `CHAT_LOG_TEXT_LIMIT`                     | `65536`                    | Max string length retained in chat log artifacts (default 64 KB).                 |
-| `CHAT_LOG_ARRAY_TAIL_ITEMS`               | `128`                      | Number of array items retained from the tail when truncating chat log payloads.   |
+| `CHAT_LOG_ARRAY_TAIL_ITEMS`               | `24`                       | Number of array items retained from the tail when truncating chat log payloads.   |
 | `CHAT_LOG_MAX_DEPTH`                      | `6`                        | Max nesting depth before chat log payloads are truncated.                         |
 | `CHAT_LOG_MAX_OBJECT_KEYS`                | `80`                       | Max object keys retained in chat log payloads (0 = unlimited).                    |
 | `CHAT_DEBUG_FILE`                         | `false`                    | When true, `serializeArtifactForStorage` skips size-based truncation. Debug only. |
@@ -976,7 +976,7 @@ changing them requires a code edit, not an env var:
 | `CURSOR_AGENT_CLI_VERSION`       | _(detect / pin)_    | `open-sse/utils/cursorAgentCliVersion.ts`  | Agent CLI build id (`YYYY.MM.DD-<hash>`) for `x-cursor-client-version: cli-…` on Agent Run.   |
 | `CURSOR_DATA_DIR`                | _(probed)_          | `open-sse/utils/cursorAgentCliVersion.ts`  | Override Cursor Agent CLI data dir (`…/versions/<id>`); same var the official agent uses.    |
 | `CURSOR_TOKEN`                   | _(unset)_           | `scripts/ad-hoc/cursor-tap.cjs`            | Direct Cursor bearer token used by developer tooling.                                        |
-| `OMNIROUTE_LOG_REQUEST_SHAPE`    | disabled (opt-in via `"1"`) | `src/app/api/v1/chat/completions/route.ts` | Log content-type/length markers for large chat payloads when `"1"` is set. Off by default to reduce log noise. |
+| `OMNIROUTE_LOG_REQUEST_SHAPE`    | enabled (`!== "0"`) | `src/app/api/v1/chat/completions/route.ts` | Log content-type/length markers for large chat payloads. Set `"0"` to silence.               |
 | `DEBUG_RESPONSES_SSE_TO_JSON`    | _(unset)_           | `open-sse/handlers/responseTranslator.ts`  | Set `true` to log Responses API SSE→JSON translation details.                                |
 | `NEXT_PUBLIC_OMNIROUTE_E2E_MODE` | _(unset)_           | E2E test harness                           | Set `true` to enable E2E test mode (relaxed auth, test hooks).                               |
 
@@ -1389,31 +1389,3 @@ Used by `src/lib/vncSession/manifest.ts` to configure Docker-based headless Chro
 | `REDIS_BIND_HOST` | `127.0.0.1` | Bind address for the embedded Redis service. |
 | `REDIS_PORT` | `6379` | Port for the embedded Redis service. |
 | `OMNIROUTE_REDIS_BIND_HOST` | – | OmniRoute-scoped override for the embedded Redis bind address. |
-
----
-
-## 24. Release v3.8.50 additions
-
-These settings were introduced after the previous environment-contract snapshot.
-
-| Variable | Default | Source File | Description |
-| --- | --- | --- | --- |
-| `OMNIROUTE_CHAT_ADMISSION_QUEUE_MS` | `5000` | `src/shared/middleware/chatBodyAdmission.ts` | Maximum wait for a heavyweight chat admission slot before a retryable `503`; `0` restores immediate rejection. |
-| `OMNIROUTE_RUNNOW_TIMEOUT_MS` | `30000` | `src/app/api/jobs/[id]/run-now/route.ts` | Bounds how long a run-now call waits for an in-flight job before starting the queued run. |
-| `CHAT_LOG_MAX_BODY_KB` | `1024` | `src/lib/logEnv.ts` | Maximum request or response body size before log summarization, in KiB. |
-| `ADOBE_FIREFLY_BROWSER_REFRESH` | enabled | `open-sse/services/adobeFireflySession.ts` | Keeps IMS and browser-risk state fresh through account-scoped Chrome CDP sessions; set `0` to disable. |
-| `ADOBE_FIREFLY_SESSION_DISK` | enabled | `open-sse/services/adobeFireflySession.ts` | Persists repaired Adobe sessions under `DATA_DIR`; set `0` for memory-only state. |
-| `ADOBE_FIREFLY_MIN_SUBMIT_GAP_MS` | `12000` | `open-sse/services/adobeFireflySession.ts` | Minimum spacing between Adobe Firefly generate submissions. |
-| `ADOBE_FIREFLY_BATCH_EXTRA_GAP_MS` | `15000` | `open-sse/services/adobeFireflySession.ts` | Extra quiet period after every third successful Adobe submission. |
-| `ADOBE_FIREFLY_CHROME_CDP_PORT` | `9334` | `open-sse/services/adobeFireflyChromeRuntime.ts` | CDP port for the account-scoped Chrome runtime. |
-| `ADOBE_FIREFLY_CHROME_VISIBLE` | `0` | `open-sse/services/adobeFireflyChromeRuntime.ts` | Set `1` to keep the Adobe renewal browser visible; the default parks a headed window off-screen. |
-| `ADOBE_FIREFLY_CHROME_HEADLESS` | `0` | `open-sse/services/adobeFireflyChromeRuntime.ts` | Debug-only true-headless mode; Adobe colligo normally rejects the resulting risk session. |
-| `ADOBE_FIREFLY_CHROME_FORCE_RESTART` | `0` | `open-sse/services/adobeFireflyChromeRuntime.ts` | Set `1` to restart the account-scoped Chrome runtime before renewal. |
-| `ADOBE_FIREFLY_CHROME_PING` | automatic | `open-sse/services/adobeFireflyChromeRuntime.ts` | `1` forces, and `0` disables, the in-page generate probe used to prove the renewed ARP session. |
-| `ADOBE_FIREFLY_LOGIN_WAIT_MS` | context-dependent | `open-sse/services/adobeFireflyChromeRuntime.ts` | Interactive-login wait budget: `0` on background renewal and `300000` on the explicit login flow unless overridden. |
-| `ADOBE_FIREFLY_FORTER_WAIT_MS` | `45000` | `open-sse/services/adobeFireflyChromeRuntime.ts` | Maximum wait for a fresh Forter token during session renewal. |
-| `CHROME_PATH` | auto-detect | `open-sse/services/adobeFireflyChromeRuntime.ts` | Optional absolute Chrome executable used when platform auto-detection is insufficient. |
-| `TELEGRAM_BOT_TOKEN` | _(unset)_ | `src/lib/telegram/config.ts` | BotFather token that enables the inbound webhook and signs Mini App `initData`. |
-| `TELEGRAM_DEFAULT_MODEL` | `auto/chat` | `src/lib/telegram/chatProxy.ts` | Model used for Telegram chat replies. |
-| `TELEGRAM_BOT_API_BASE` | `https://api.telegram.org` | `src/lib/telegram/config.ts` | Bot API base URL override for proxies or self-hosted Bot API servers. |
-| `TELEGRAM_WEBHOOK_TIMEOUT_MS` | `60000` | `src/lib/telegram/config.ts` | Timeout in milliseconds for outbound Bot API calls. |

docs/security/GUARDRAILS.md

@@ -1,13 +1,13 @@
 ---
 title: "Guardrails"
-version: 3.8.50
-lastUpdated: 2026-08-08
+version: 3.8.40
+lastUpdated: 2026-06-28
 ---
 
 # Guardrails
 
 > **Source of truth:** `src/lib/guardrails/`
-> **Last updated:** 2026-08-08 — v3.8.50 (Modality Bridge PR-2: dashboard settings page, live stats, test action, and media-provider shortcuts)
+> **Last updated:** 2026-06-28 — v3.8.40 (injection-guard coverage + 16 KB scan bound + red-team)
 
 Guardrails enforce safety, policy, and content transformations at the boundary
 between OmniRoute and upstream providers. Each guardrail can inspect (and
@@ -32,123 +32,31 @@ The registry auto-loads four guardrails in priority order on import
 
 Lower priority numbers run **first**.
 
-### Vision Bridge (`visionBridge.ts`) — Modality Bridge PR-1
+### Vision Bridge (`visionBridge.ts`)
 
-Intercepts image-bearing requests aimed at **non-vision models** and either
-reroutes the whole request to a vision-capable model or replaces the image
-parts with text descriptions produced by a configurable vision model before
-the upstream call. This lets text-only providers transparently handle
+Intercepts image-bearing requests aimed at **non-vision models** and replaces
+the image parts with text descriptions produced by a configurable vision model
+before the upstream call. This lets text-only providers transparently handle
 multimodal payloads.
 
 Flow:
 
 1. Skip if the target model already supports vision (unless it appears in the
    forced-bridge list `isVisionBridgeForcedModel`).
-2. Extract image parts via `extractImageParts(messages)`
-   (`visionBridgeHelpers.ts`), which delegates to the **unified media
-   detector** `detectMediaParts()` in `open-sse/utils/mediaParts.ts` — the
-   single source of truth shared with the combo compatibility filter.
-   Extraction is allowlisted to top-level parts of the shapes
-   `replaceImageParts` can splice back (the extract↔replace contract): OpenAI
-   `image_url`, Anthropic base64 `source.type:"base64"`, Anthropic URL
-   `source.type:"url"`, and Responses API `input_image`. Nested hits and
-   indicator-only shapes are combo-filter material and are never extracted.
-   Skip if none found.
-3. Resolve runtime config via `resolveVisionBridgeRuntimeSettings()`
-   (`src/shared/constants/modalityBridgeDefaults.ts`): new `modalityBridge*`
-   settings keys win; legacy `visionBridge*` keys remain a **one-cycle
-   fallback** (rollback window). Skip before any media traversal when the
-   bridge is disabled.
-4. Mode selector (`modalityBridgeVisionMode`, see table below) decides
-   reroute vs describe. Reroute returns `modifiedPayload` with only `model`
-   swapped, plus meta `{ rerouted, fromModel, toModel, imagesKept }`.
-5. Describe path: cap images at `maxImages`, compose the task-aware prompt,
-   consult the describe cache, call the vision model **in parallel**
-   (`Promise.allSettled`), and inject `[Image N]: <description>` text parts in
-   their place. A failed describe yields `null` and the original image part is
-   **preserved** (#4012) — except on the combo describe path when every
-   describe failed, where a confirmed non-vision upstream gets an
-   `(unavailable — no vision-capable provider connected)` stub instead (#8430).
-6. Return `modifiedPayload` + meta (`imagesProcessed`, `descriptions`,
-   `processingTimeMs`, `visionModel`).
-
-#### Mode selector (`modalityBridgeVisionMode`)
-
-| Mode       | Default | Behavior                                                                                                                                                                                                                                                |
-| ---------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `auto`     | ✔       | Legacy heuristic, untouched (#6640/#7204): non-combo/`auto/` models reroute to the best vision model unless the original model already has usable credentials (then describe); combo targets always describe.                                           |
-| `describe` |         | Always describe — the reroute block is skipped entirely; the user's chosen model always answers.                                                                                                                                                        |
-| `reroute`  |         | Force reroute: the keep-credentialed-model guard is bypassed. The reroute-**target** credential guard still applies — when no usable vision target exists, the request falls through to describe so raw images never reach a text-only backend (#8430). |
-
-Forced modes short-circuit **before** the auto heuristic runs; `auto` behavior
-is byte-identical to the pre-PR-1 guardrail.
-
-#### Task-aware describe prompt (`modalityBridgeVisionTaskAware`)
-
-Default **true**. `composeVisionPrompt()` (`visionBridgeHelpers.ts`) appends
-the text of the **last user message** (truncated to 500 chars) to the base
-describe prompt, steering the description toward what the user actually asked
-(codex-vision-proxy pattern) and asking the vision model to transcribe visible
-text. With the flag off — or no user text — the base prompt is used unchanged.
-
-#### Describe cache (`modalityBridge/bridgeCache.ts`)
-
-In-memory LRU + TTL cache for describe outputs, shared process-wide.
-Key = `sha256(imageRef + composedPrompt + configuredBridgeModel)` with
-length-prefix framing (no field-boundary collisions). The model component is
-the **configured** bridge model, not the model that actually answered —
-`callVisionModel` may fall back internally, and keying per attempt would
-fragment the cache. Failed describes are never cached. Settings:
-
-| Key                             | Default | Range   |
-| ------------------------------- | ------- | ------- |
-| `modalityBridgeCacheEnabled`    | `true`  | —       |
-| `modalityBridgeCacheTtlMinutes` | `60`    | 1–1440  |
-| `modalityBridgeCacheMaxEntries` | `200`   | 10–5000 |
-
-#### Settings schema + migration
-
-The new `modalityBridge*` keys are Zod-validated in `updateSettingsSchema`
-(`src/shared/validation/settingsSchemas.ts`): `modalityBridgeVisionEnabled`,
-`modalityBridgeVisionMode`, `modalityBridgeVisionModel`,
-`modalityBridgeVisionTaskAware`, `modalityBridgeVisionPrompt`,
-`modalityBridgeVisionTimeout`, `modalityBridgeVisionMaxImages`, the
-`modalityBridgeCache*` trio, and the PR-3-reserved `modalityBridgeAudio*`
-group. Migration `141_modality_bridge_settings.sql` copies existing legacy
-`visionBridge*` values to the matching new keys (idempotent, never overwrites
-an operator-set `modalityBridge*` value); the legacy keys stay accepted as a
-read fallback for one release cycle.
-
-#### Transparency header + stats
-
-Describe-transformed responses carry
-`x-omniroute-modality-bridge: image->text;model=<visionModel>;parts=<n>`
-(built by `buildModalityBridgeHeader()` in `modalityBridge/bridgeStats.ts`,
-stamped by `withModalityBridgeHeader()` in `src/sse/handlers/chatHelpers.ts`).
-Rerouted requests get **no** header — the payload was untouched and the model
-swap is already visible in the response body's `model` field.
-
-`GET /api/modality-bridge/stats` (management auth, same tier as
-`GET /api/settings`) returns the in-memory per-modality counters
-`{ bridged, cacheHits, failures, lastUsedAt }` for `vision` (and the
-PR-3-reserved `audio`). Counters reset on process restart by design
-(telemetry, not accounting).
-
-#### Dashboard configuration
-
-The dedicated dashboard page is
-`/dashboard/settings/modality-bridge`. Its URL-addressable `Vision`, `Audio`,
-and `Video` tabs preserve query parameters while switching the `tab` value.
-The Vision tab is live: it exposes enablement, mode, model selection (including
-the automatic default), task-aware prompting, advanced timeout/image/cache
-limits, runtime counters, and a guarded sample request. Audio and Video are
-explicit placeholders: Audio is reserved for PR-3, while Video remains tracked
-in issue `#9760`.
-
-The former Vision Bridge card under AI settings is a compatibility link to the
-new page; it no longer owns a second copy of the form. Media Providers also
-links Image-to-Text and Speech-to-Text workflows to the corresponding Modality
-Bridge tabs without removing the existing Speech-to-Text playground.
+2. Extract image parts via `extractImageParts(messages)`. Skip if none.
+   `extractImageParts` recognizes all three image shapes: OpenAI `image_url`,
+   Anthropic base64 `source.type:"base64"`, and Anthropic URL
+   `source.type:"url"` — so Claude-Code-compatible clients (e.g. Zoo Code)
+   sending `{ type: "image", source: { type: "url", url } }` are described
+   instead of silently dropped.
+3. Load runtime config from `getSettings()` (`visionBridgeEnabled`,
+   `visionBridgeModel`, `visionBridgePrompt`, `visionBridgeTimeout`,
+   `visionBridgeMaxImages`).
+4. Cap images at `maxImages`, call the vision model **in parallel**
+   (`Promise.allSettled`), and inject `[Image N]: <description>` text parts
+   in their place — failed images become `[Image N]: (unavailable)`.
+5. Return `modifiedPayload` + meta (`imagesProcessed`, `processingTimeMs`,
+   `visionModel`).
 
 **Self-loop admission bypass:** when the describe call routes through OmniRoute's
 own `/v1` self-loop (non-standard provider model), the sub-request sends
@@ -159,10 +67,8 @@ operator-configured `OMNIROUTE_API_KEY` / `ROUTER_API_KEY` env key (#1350) so
 is only honored for those exact credentials, so external clients cannot use the
 header to skip admission.
 
-Legacy defaults live in `src/shared/constants/visionBridgeDefaults.ts`; the
-new mode/task-aware/cache defaults and the settings resolver live in
-`src/shared/constants/modalityBridgeDefaults.ts`. The guardrail exposes a
-`deps` constructor option so tests can inject fake `getSettings` and
+Defaults live in `src/shared/constants/visionBridgeDefaults.ts`. The guardrail
+exposes a `deps` constructor option so tests can inject fake `getSettings` and
 `callVisionModel` implementations.
 
 ### PII Masker (`piiMasker.ts`)
@@ -371,16 +277,9 @@ Environment variables read by the built-in guardrails:
 | `PII_RESPONSE_SANITIZATION` / `_MODE` | `pii-masker` (downstream) | Controls response-side masker behavior.                                                             |
 
 The Vision Bridge reads runtime config from the DB-backed settings store
-(`getSettings()`), not env vars. The primary keys are
-`modalityBridgeVisionEnabled`, `modalityBridgeVisionMode`,
-`modalityBridgeVisionModel`, `modalityBridgeVisionTaskAware`,
-`modalityBridgeVisionPrompt`, `modalityBridgeVisionTimeout`,
-`modalityBridgeVisionMaxImages`, `modalityBridgeCacheEnabled`,
-`modalityBridgeCacheTtlMinutes`, and `modalityBridgeCacheMaxEntries`. The legacy
-`visionBridge*` keys are accepted only as the documented one-cycle read
-fallback; dashboard writes use the primary keys. Defaults and the fallback
-resolver live in `src/shared/constants/modalityBridgeDefaults.ts`, with legacy
-constants retained in `src/shared/constants/visionBridgeDefaults.ts`.
+(`getSettings()`), not env vars: `visionBridgeEnabled`, `visionBridgeModel`,
+`visionBridgePrompt`, `visionBridgeTimeout`, `visionBridgeMaxImages`. Defaults
+live in `src/shared/constants/visionBridgeDefaults.ts`.
 
 ## Custom Guardrails
 

docs/video-preset-generation.md

@@ -1,113 +0,0 @@
-# Video Generation Through Preset Jobs
-
-Custom provider nodes whose `/videos` surface is an **async submit → poll → fetch-result API** (instead of a synchronous generation endpoint) can be wired into the `/api/v1/videos/generations` route without any new provider code. The model row carries a `generationConfig.preset`, and the dispatcher routes the request through a single job executor that is configured entirely by declarative preset data.
-
-## How dispatch works
-
-1. The route parses `model` as `provider/model` and resolves the provider node's credentials (`POST /api/v1/videos/generations`).
-2. `handleVideoGeneration` (in `open-sse/handlers/videoGeneration.ts`) checks whether the provider is a **custom provider node** (no entry in the static video registry).
-3. For custom nodes it reads the custom model row via `getCustomModelVideoPreset(provider, model)`:
-   - The model row has `generationConfig.preset` set (e.g. `"agnes-video-job"`) → dispatch through the **job executor** (`open-sse/handlers/videoGeneration/job.ts`).
-   - The preset name does not match any known preset → **502** `Unknown video job preset: <preset>` (server-side misconfiguration).
-   - No preset configured → fall back to the generic OpenAI-compatible sync handler, mirroring the images route.
-4. The job executor runs the preset pipeline: **submit** the job, **poll** for terminal status, **read** the finished video URL, and return the standard OpenAI-compatible response shape.
-
-The executor is one handler family; every provider-specific detail (paths, auth, body shape, status/result fields, poll cadence) is data in the preset definition.
-
-## Response contract
-
-Both the sync and job paths return the same shape:
-
-```json
-{
-  "created": 1234567890,
-  "data": [{ "url": "https://…", "format": "mp4" }]
-}
-```
-
-This is the shape the media-generation consumer reads (`data.data[0].url`), so preset-job providers are drop-in replacements for sync providers.
-
-## Presets
-
-Presets live in `open-sse/handlers/videoGeneration/job.ts` (`VIDEO_JOB_PRESETS`). Each preset declares:
-
-| Field                                        | Meaning                                                                                                                                                                                                |
-| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `authHeaderName` / `authScheme`              | `x-api-key` with `raw` value (Agnes, muapi) or `Authorization` with `Bearer` prefix (Sora). Missing credentials → request goes out without an auth header.                                             |
-| `baseUrlFallback`                            | Default base URL. Overridden by the provider connection's `providerSpecificData.baseUrl` (or top-level `baseUrl`), which wins when set.                                                                |
-| `submit.path` / `submit.buildBody`           | Where and how the job is submitted. `{model}` in the path is substituted with the encoded model id; the body is built from `model`/`prompt`/`duration` plus pass-through of every other request field. |
-| `taskIdPath`                                 | Dot path into the submit response identifying the job (e.g. `task_id`, `request_id`, `id`). Missing job id → **502**.                                                                                  |
-| `poll.pathTemplate`                          | Poll URL template; `{taskId}` is substituted.                                                                                                                                                          |
-| `statusPath` / `statusDone` / `statusFailed` | Where the job status lives and which values are terminal.                                                                                                                                              |
-| `resultPath`                                 | Dot path into the poll response holding the finished video URL: a string, a string array, or an array of `{ url }` objects are all accepted. Completed job with no readable URL → **502**.             |
-| `maxPolls` / `pollIntervalMs`                | Poll budget (default 60 polls × 2000 ms). Exhausted → **504** `Video job timed out`.                                                                                                                   |
-
-### `agnes-video-job` — Agnes Video V2.0
-
-- Auth: `x-api-key: <key>` (raw).
-- Base URL fallback: `https://apihub.agnes-ai.com`.
-- Submit: `POST /v1/videos` with `{ model, prompt, ...extras }` — image, mode, `num_frames`, `frame_rate` and other provider knobs pass through untouched.
-- Job id: `task_id` from the submit response.
-- Poll: `GET /v1/videos/{taskId}`; status at `status` (`completed` / `failed`).
-- Result: `metadata.url` — the completed video URL is returned as JSON metadata, not a binary body.
-
-### `muapi-video-job` — muapi.ai
-
-- Auth: `x-api-key: <key>` (raw).
-- Base URL fallback: `https://api.muapi.ai`.
-- Submit: `POST /api/v1/{model}` with `{ prompt, duration?, ...extras }`.
-- Job id: `request_id` from the submit response.
-- Poll: `GET /api/v1/predictions/{taskId}/result`; status at `status` (`completed` / `failed`).
-- Result: `outputs` — an array of video URLs.
-
-### `sora-job` — OpenAI Sora
-
-- Auth: `Authorization: Bearer <key>`.
-- Base URL fallback: `https://api.openai.com`.
-- Submit: `POST /v1/videos` with `{ model, prompt, seconds?, ...extras }`. `seconds` is a **string** enum (`"4" | "8" | "12"`) in the Sora API, so a numeric `duration` is stringified; size mapping is intentionally not forced.
-- Job id: `id` from the submit response.
-- Poll: `GET /v1/videos/{taskId}`; status at `status` (`completed` / `failed`).
-- Result: `data` — an array whose entries are either a URL string or `{ url: "…" }`.
-
-## Setup
-
-1. **Register the provider node** as an OpenAI-compatible custom provider (`providerSpecificData.baseUrl` optional — the preset's `baseUrlFallback` is used when absent).
-2. **Register a custom model** tagged with the `videos` endpoint and a `generationConfig`:
-
-   ```json
-   {
-     "id": "super-video-v1",
-     "name": "Super Video v1",
-     "source": "manual",
-     "apiFormat": "chat-completions",
-     "supportedEndpoints": ["videos"],
-     "generationConfig": { "preset": "agnes-video-job" }
-   }
-   ```
-
-   `addCustomModel` (in `src/lib/db/models.ts`) accepts `generationConfig?: { preset: string }` as its final parameter and persists it on the model row; `updateCustomModel` forwards it the same way. The provider-models API accepts `generationConfig` on create and update.
-
-3. **Call the route** as usual:
-
-   ```bash
-   curl -X POST http://localhost:8787/api/v1/videos/generations \
-     -H "Content-Type: application/json" \
-     -H "Authorization: Bearer $API_KEY" \
-     -d '{
-       "model": "my-custom-provider/super-video-v1",
-       "prompt": "a cat playing piano",
-       "duration": 5
-     }'
-   ```
-
-## Troubleshooting
-
-| Symptom                                                                        | Cause                                                                                            |
-| ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
-| `400 Unknown video provider: …`                                                | Non-custom provider not in the static registry; preset jobs only apply to custom provider nodes. |
-| `502 Unknown video job preset: …`                                              | `generationConfig.preset` does not match any preset in `VIDEO_JOB_PRESETS`. Fix the model row.   |
-| `502 Video provider did not return a job id (…)`                               | Submit succeeded but the response had no readable value at `taskIdPath`.                         |
-| `502 Video job failed (…)` / `Video job completed but no result URL found (…)` | Poll reached a terminal `statusFailed` state, or `resultPath` held no readable URL.              |
-| `504 Video job timed out after 60 polls (…)`                                   | Job never reached a terminal status within the poll budget.                                      |
-| Upstream 4xx/5xx passthrough                                                   | `fetchJson` returns the upstream status when the submit/poll request itself is not OK.           |
-| Requests go out without auth                                                   | No `apiKey`/`accessToken` on the provider connection; the executor sends `Content-Type` only.    |

electron/package-lock.json

@@ -55,9 +55,9 @@
       "license": "MIT"
     },
     "node_modules/@electron/asar/node_modules/brace-expansion": {
-      "version": "1.1.18",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
-      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
+      "version": "1.1.16",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.16.tgz",
+      "integrity": "sha512-IDw48K2/2kRkg9LdJxurvq3lV3aBgq0REY89duEqFRthjlPdXHKMj7EnQOXVckxzgisinf3nHfrcE2FufFLXMw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -257,9 +257,9 @@
       "license": "MIT"
     },
     "node_modules/@electron/universal/node_modules/brace-expansion": {
-      "version": "2.1.4",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.4.tgz",
-      "integrity": "sha512-hGfVzPxthbf3+2yjg/RBs60cB0FhqBS/zvdV/4wn4/BmN0bNMMHPc4V/BbFieqf1TKAGGAHnY4eSjajCl0f2Xg==",
+      "version": "2.1.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.2.tgz",
+      "integrity": "sha512-w5JZcKgdhDOgOwm8H+KgbosopHMuGcl6qbulwjtz3SM7I7P3yW1eAjzMPLrIE+NQ9vjgANKHWeMHnrT0OXW1oA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -297,45 +297,6 @@
         "url": "https://github.com/sponsors/isaacs"
       }
     },
-    "node_modules/@electron/windows-sign": {
-      "version": "1.2.2",
-      "resolved": "https://registry.npmjs.org/@electron/windows-sign/-/windows-sign-1.2.2.tgz",
-      "integrity": "sha512-dfZeox66AvdPtb2lD8OsIIQh12Tp0GNCRUDfBHIKGpbmopZto2/A8nSpYYLoedPIHpqkeblZ/k8OV0Gy7PYuyQ==",
-      "dev": true,
-      "license": "BSD-2-Clause",
-      "optional": true,
-      "peer": true,
-      "dependencies": {
-        "cross-dirname": "^0.1.0",
-        "debug": "^4.3.4",
-        "fs-extra": "^11.1.1",
-        "minimist": "^1.2.8",
-        "postject": "^1.0.0-alpha.6"
-      },
-      "bin": {
-        "electron-windows-sign": "bin/electron-windows-sign.js"
-      },
-      "engines": {
-        "node": ">=14.14"
-      }
-    },
-    "node_modules/@electron/windows-sign/node_modules/fs-extra": {
-      "version": "11.4.0",
-      "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-11.4.0.tgz",
-      "integrity": "sha512-EQsFzMUJkCKGr1ePqlYADkIUmHW1s3ZXr5Yqy6wbGrfUCphpl2maM/kyOIRA2HpP3AaFQTZXD4ldjek+nccddA==",
-      "dev": true,
-      "license": "MIT",
-      "optional": true,
-      "peer": true,
-      "dependencies": {
-        "graceful-fs": "^4.2.0",
-        "jsonfile": "^6.0.1",
-        "universalify": "^2.0.0"
-      },
-      "engines": {
-        "node": ">=14.14"
-      }
-    },
     "node_modules/@isaacs/fs-minipass": {
       "version": "4.0.1",
       "resolved": "https://registry.npmjs.org/@isaacs/fs-minipass/-/fs-minipass-4.0.1.tgz",
@@ -874,16 +835,16 @@
       "optional": true
     },
     "node_modules/brace-expansion": {
-      "version": "5.0.9",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz",
-      "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==",
+      "version": "5.0.7",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.7.tgz",
+      "integrity": "sha512-7oFy703dxfY3/NLxC1fh2SUCQ0H9rmAY+5EpDVfXjUTTs+HEwR2nYaqLv+GWcTsumwxPfiz6CzCNkwXwBUwqCA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
         "balanced-match": "^4.0.2"
       },
       "engines": {
-        "node": "20 || >=22"
+        "node": "18 || 20 || >=22"
       }
     },
     "node_modules/buffer-from": {
@@ -1130,15 +1091,6 @@
       "dev": true,
       "license": "MIT"
     },
-    "node_modules/cross-dirname": {
-      "version": "0.1.0",
-      "resolved": "https://registry.npmjs.org/cross-dirname/-/cross-dirname-0.1.0.tgz",
-      "integrity": "sha512-+R08/oI0nl3vfPcqftZRpytksBXDzOUveBq/NBVx0sUp1axwzPQrKinNx5yd5sxPu8j1wIy8AfnVQ+5eFdha6Q==",
-      "dev": true,
-      "license": "MIT",
-      "optional": true,
-      "peer": true
-    },
     "node_modules/cross-spawn": {
       "version": "7.0.6",
       "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
@@ -1308,9 +1260,9 @@
       "license": "MIT"
     },
     "node_modules/dir-compare/node_modules/brace-expansion": {
-      "version": "1.1.18",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
-      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
+      "version": "1.1.16",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.16.tgz",
+      "integrity": "sha512-IDw48K2/2kRkg9LdJxurvq3lV3aBgq0REY89duEqFRthjlPdXHKMj7EnQOXVckxzgisinf3nHfrcE2FufFLXMw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -1459,19 +1411,6 @@
         "node": ">=14.0.0"
       }
     },
-    "node_modules/electron-builder-squirrel-windows": {
-      "version": "26.15.3",
-      "resolved": "https://registry.npmjs.org/electron-builder-squirrel-windows/-/electron-builder-squirrel-windows-26.15.3.tgz",
-      "integrity": "sha512-Jc19XPV9y9+2bAdZPkXuVNGNIEFBq9poHC61l8Kv6FdK7DRG3+Ic0rerC0DXOaeHNz8yW0fg/JnF8GQROOF5MA==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true,
-      "dependencies": {
-        "app-builder-lib": "26.15.3",
-        "builder-util": "26.15.3",
-        "electron-winstaller": "5.4.0"
-      }
-    },
     "node_modules/electron-publish": {
       "version": "26.15.3",
       "resolved": "https://registry.npmjs.org/electron-publish/-/electron-publish-26.15.3.tgz",
@@ -1506,66 +1445,6 @@
         "tiny-typed-emitter": "^2.1.0"
       }
     },
-    "node_modules/electron-winstaller": {
-      "version": "5.4.0",
-      "resolved": "https://registry.npmjs.org/electron-winstaller/-/electron-winstaller-5.4.0.tgz",
-      "integrity": "sha512-bO3y10YikuUwUuDUQRM4KfwNkKhnpVO7IPdbsrejwN9/AABJzzTQ4GeHwyzNSrVO+tEH3/Np255a3sVZpZDjvg==",
-      "dev": true,
-      "hasInstallScript": true,
-      "license": "MIT",
-      "peer": true,
-      "dependencies": {
-        "@electron/asar": "^3.2.1",
-        "debug": "^4.1.1",
-        "fs-extra": "^7.0.1",
-        "lodash": "^4.17.21",
-        "temp": "^0.9.0"
-      },
-      "engines": {
-        "node": ">=8.0.0"
-      },
-      "optionalDependencies": {
-        "@electron/windows-sign": "^1.1.2"
-      }
-    },
-    "node_modules/electron-winstaller/node_modules/fs-extra": {
-      "version": "7.0.1",
-      "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-7.0.1.tgz",
-      "integrity": "sha512-YJDaCJZEnBmcbw13fvdAM9AwNOJwOzrE4pqMqBq5nFiEqXUqHwlK4B+3pUw6JNvfSPtX05xFHtYy/1ni01eGCw==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true,
-      "dependencies": {
-        "graceful-fs": "^4.1.2",
-        "jsonfile": "^4.0.0",
-        "universalify": "^0.1.0"
-      },
-      "engines": {
-        "node": ">=6 <7 || >=8"
-      }
-    },
-    "node_modules/electron-winstaller/node_modules/jsonfile": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/jsonfile/-/jsonfile-4.0.0.tgz",
-      "integrity": "sha512-m6F1R3z8jjlf2imQHS2Qez5sjKWQzbuuhuJ/FKYFRZvPE3PuHcSMVZzfsLhGVOkfd20obL5SWEBew5ShlquNxg==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true,
-      "optionalDependencies": {
-        "graceful-fs": "^4.1.6"
-      }
-    },
-    "node_modules/electron-winstaller/node_modules/universalify": {
-      "version": "0.1.2",
-      "resolved": "https://registry.npmjs.org/universalify/-/universalify-0.1.2.tgz",
-      "integrity": "sha512-rBJeI5CXAlmy1pV+617WB9J63U6XcazHHF2f2dbJix4XzpUF0RS3Zbj0FGIOCAva5P/d/GBOYaACQ1w+0azUkg==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true,
-      "engines": {
-        "node": ">= 4.0.0"
-      }
-    },
     "node_modules/emoji-regex": {
       "version": "8.0.0",
       "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
@@ -1748,9 +1627,9 @@
       "license": "MIT"
     },
     "node_modules/filelist/node_modules/brace-expansion": {
-      "version": "2.1.4",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.4.tgz",
-      "integrity": "sha512-hGfVzPxthbf3+2yjg/RBs60cB0FhqBS/zvdV/4wn4/BmN0bNMMHPc4V/BbFieqf1TKAGGAHnY4eSjajCl0f2Xg==",
+      "version": "2.1.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.2.tgz",
+      "integrity": "sha512-w5JZcKgdhDOgOwm8H+KgbosopHMuGcl6qbulwjtz3SM7I7P3yW1eAjzMPLrIE+NQ9vjgANKHWeMHnrT0OXW1oA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -1913,9 +1792,9 @@
       "license": "MIT"
     },
     "node_modules/glob/node_modules/brace-expansion": {
-      "version": "1.1.18",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz",
-      "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==",
+      "version": "1.1.16",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.16.tgz",
+      "integrity": "sha512-IDw48K2/2kRkg9LdJxurvq3lV3aBgq0REY89duEqFRthjlPdXHKMj7EnQOXVckxzgisinf3nHfrcE2FufFLXMw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -2234,9 +2113,9 @@
       }
     },
     "node_modules/js-yaml": {
-      "version": "4.3.1",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.3.1.tgz",
-      "integrity": "sha512-CY6crGq313MX8GkwvB7tzgp99vjQxY1++5y10/BKN/GUfHqWaOGQMNZkBvqSzsZKWk/ijwHlWzzkLulsGHhjWQ==",
+      "version": "4.3.0",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.3.0.tgz",
+      "integrity": "sha512-1td788aAnnZ5qs7V2QIRl1owjtYpbKt749Y3xauqQgwIIGF/xXWz1wMTEBx5O3LK3lXLVuqXPdPxj2BoFHaW9Q==",
       "funding": [
         {
           "type": "github",
@@ -2480,20 +2359,6 @@
         "node": ">= 18"
       }
     },
-    "node_modules/mkdirp": {
-      "version": "0.5.6",
-      "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-0.5.6.tgz",
-      "integrity": "sha512-FP+p8RB8OWpF3YZBCrP5gtADmtXApB5AMLn+vdyA+PyxCjrCs00mjyUozssO33cwDeT3wNGdLxJ5M//YqtHAJw==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true,
-      "dependencies": {
-        "minimist": "^1.2.6"
-      },
-      "bin": {
-        "mkdirp": "bin/cmd.js"
-      }
-    },
     "node_modules/ms": {
       "version": "2.1.3",
       "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
@@ -2757,36 +2622,6 @@
         "node": ">=18"
       }
     },
-    "node_modules/postject": {
-      "version": "1.0.0-alpha.6",
-      "resolved": "https://registry.npmjs.org/postject/-/postject-1.0.0-alpha.6.tgz",
-      "integrity": "sha512-b9Eb8h2eVqNE8edvKdwqkrY6O7kAwmI8kcnBv1NScolYJbo59XUF0noFq+lxbC1yN20bmC0WBEbDC5H/7ASb0A==",
-      "dev": true,
-      "license": "MIT",
-      "optional": true,
-      "peer": true,
-      "dependencies": {
-        "commander": "^9.4.0"
-      },
-      "bin": {
-        "postject": "dist/cli.js"
-      },
-      "engines": {
-        "node": ">=14.0.0"
-      }
-    },
-    "node_modules/postject/node_modules/commander": {
-      "version": "9.5.0",
-      "resolved": "https://registry.npmjs.org/commander/-/commander-9.5.0.tgz",
-      "integrity": "sha512-KRs7WVDKg86PWiuAqhDrAQnTXZKraVcCc6vFdL14qrZ/DcWwuRo7VoiYXalXO7S5GKpqYiVEwCbgFDfxNHKJBQ==",
-      "dev": true,
-      "license": "MIT",
-      "optional": true,
-      "peer": true,
-      "engines": {
-        "node": "^12.20.0 || >=14"
-      }
-    },
     "node_modules/proc-log": {
       "version": "6.1.0",
       "resolved": "https://registry.npmjs.org/proc-log/-/proc-log-6.1.0.tgz",
@@ -2981,21 +2816,6 @@
         "node": ">= 4"
       }
     },
-    "node_modules/rimraf": {
-      "version": "2.6.3",
-      "resolved": "https://registry.npmjs.org/rimraf/-/rimraf-2.6.3.tgz",
-      "integrity": "sha512-mwqeW5XsA2qAejG46gYdENaxXjx9onRNCfn7L0duuP4hCuTIi/QO7PDK07KJfp1d+izWPrzEJDcSqBa0OZQriA==",
-      "deprecated": "Rimraf versions prior to v4 are no longer supported",
-      "dev": true,
-      "license": "ISC",
-      "peer": true,
-      "dependencies": {
-        "glob": "^7.1.3"
-      },
-      "bin": {
-        "rimraf": "bin.js"
-      }
-    },
     "node_modules/roarr": {
       "version": "2.15.4",
       "resolved": "https://registry.npmjs.org/roarr/-/roarr-2.15.4.tgz",
@@ -3225,9 +3045,9 @@
       }
     },
     "node_modules/tar": {
-      "version": "7.5.22",
-      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.22.tgz",
-      "integrity": "sha512-MFO/QzvtAOmJbkhOaCTvbGcFN9L9b+JunIsDwaKljSOdcLMea3NJ1k9Usz/rjdfSXTq4dfzfeS7W4p4YOAAHeA==",
+      "version": "7.5.20",
+      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.20.tgz",
+      "integrity": "sha512-9FcyK4PA6+WbzlTM9WhQm6vB5W7cP7dUiPsv1g7YDwEQnQ1CGpK3MGlKk/ITVWMk05kHZuBhmVhiv8LZoy/PFQ==",
       "dev": true,
       "license": "BlueOak-1.0.0",
       "dependencies": {
@@ -3251,21 +3071,6 @@
         "node": ">=18"
       }
     },
-    "node_modules/temp": {
-      "version": "0.9.4",
-      "resolved": "https://registry.npmjs.org/temp/-/temp-0.9.4.tgz",
-      "integrity": "sha512-yYrrsWnrXMcdsnu/7YMYAofM1ktpL5By7vZhf15CrXijWWrEYZks5AXBudalfSWJLlnen/QUJUB5aoB0kqZUGA==",
-      "dev": true,
-      "license": "MIT",
-      "peer": true,
-      "dependencies": {
-        "mkdirp": "^0.5.1",
-        "rimraf": "~2.6.2"
-      },
-      "engines": {
-        "node": ">=6.0.0"
-      }
-    },
     "node_modules/temp-file": {
       "version": "3.4.0",
       "resolved": "https://registry.npmjs.org/temp-file/-/temp-file-3.4.0.tgz",

open-sse/config/audioRegistry.ts

@@ -247,17 +247,6 @@ export const AUDIO_TRANSCRIPTION_PROVIDERS: Record<string, AudioProvider> = {
     format: "speechmatics",
     models: [{ id: "enhanced", name: "Enhanced" }],
   },
-
-  nanogpt: {
-    id: "nanogpt",
-    baseUrl: "https://nano-gpt.com/api/v1/audio/transcriptions",
-    authType: "apikey",
-    authHeader: "bearer",
-    models: [
-      { id: "whisper-1", name: "Whisper 1" },
-      { id: "gpt-4o-transcription", name: "GPT-4o Transcription" },
-    ],
-  },
 };
 
 /**
@@ -581,17 +570,6 @@ export const AUDIO_SPEECH_PROVIDERS: Record<string, AudioProvider> = {
       { id: "mimo-v2.5-tts-voiceclone", name: "MiMo V2.5 Voice Clone" },
     ],
   },
-
-  nanogpt: {
-    id: "nanogpt",
-    baseUrl: "https://nano-gpt.com/api/v1/audio/speech",
-    authType: "apikey",
-    authHeader: "bearer",
-    models: [
-      { id: "tts-1-hd", name: "TTS 1 HD" },
-      { id: "tts-1", name: "TTS 1" },
-    ],
-  },
 };
 
 /**
@@ -625,7 +603,7 @@ export interface ProviderNodeRow {
 }
 
 /** Hosts reachable only from the operator's machine/Docker network. */
-export function isLoopbackNodeHost(baseUrl: string): boolean {
+function isLoopbackNodeHost(baseUrl: string): boolean {
   try {
     const hostname = new URL(baseUrl).hostname;
     return (

open-sse/config/constants.ts

@@ -1,5 +1,4 @@
 import { getUpstreamTimeoutConfig } from "@/shared/utils/runtimeTimeouts";
-import { resolvePublicCred } from "../utils/publicCreds.ts";
 import type { LegacyProvider } from "./providerRegistry.ts";
 import { loadProviderCredentials } from "./credentialLoader.ts";
 import { generateLegacyProviders } from "./providerRegistry.ts";
@@ -19,15 +18,6 @@ export const FETCH_TIMEOUT_MS = upstreamTimeouts.fetchTimeoutMs;
 // idle for this duration. Override with STREAM_IDLE_TIMEOUT_MS env var.
 export const STREAM_IDLE_TIMEOUT_MS = upstreamTimeouts.streamIdleTimeoutMs;
 
-// Grace period (ms) a client-disconnect finalization waits for the stream's own
-// completion bookkeeping to land before persisting a 499. See #9653 — a client
-// that closes right after reading a fully-completed SSE stream can otherwise
-// race OmniRoute's own completion callback, resulting in a false 499 with zero
-// token usage for a request that actually delivered its full response. Set
-// STREAM_DISCONNECT_GRACE_PERIOD_MS=0 to disable and restore the old
-// immediate-fail behavior.
-export const STREAM_DISCONNECT_GRACE_PERIOD_MS = upstreamTimeouts.streamDisconnectGracePeriodMs;
-
 // Timeout for the first non-ping SSE event. Inherits REQUEST_TIMEOUT_MS when
 // set, unless STREAM_READINESS_TIMEOUT_MS is specified directly. This must stay
 // conservative for large prompts and slow first-byte reasoning providers.
@@ -75,27 +65,27 @@ export const PROVIDERS: Record<string, LegacyProvider> = new Proxy(
   {} as Record<string, LegacyProvider>,
   {
     get(_, prop) {
-      if (typeof prop === "symbol") return undefined;
+      if (typeof prop === 'symbol') return undefined;
       return Reflect.get(initProviders(), prop, _providers);
     },
     has(_, prop) {
-      if (typeof prop === "symbol") return false;
+      if (typeof prop === 'symbol') return false;
       return Reflect.has(initProviders(), prop);
     },
     ownKeys() {
       return Reflect.ownKeys(initProviders());
     },
     getOwnPropertyDescriptor(_, prop) {
-      if (typeof prop === "symbol") return undefined;
+      if (typeof prop === 'symbol') return undefined;
       return Object.getOwnPropertyDescriptor(initProviders(), prop);
     },
     set(_, prop, value) {
-      if (typeof prop === "symbol") return false;
+      if (typeof prop === 'symbol') return false;
       (initProviders() as Record<string, LegacyProvider>)[prop] = value;
       return true;
     },
     deleteProperty(_, prop) {
-      if (typeof prop === "symbol") return false;
+      if (typeof prop === 'symbol') return false;
       return Reflect.deleteProperty(initProviders(), prop);
     },
   }
@@ -134,11 +124,6 @@ export const OAUTH_ENDPOINTS = {
     auth: "https://github.com/login/oauth/authorize",
     deviceCode: "https://github.com/login/device/code",
   },
-  openference: {
-    token: "https://openference.com/oauth/token",
-    auth: "https://openference.com/app/oauth/authorize",
-    clientId: resolvePublicCred("openference_id"),
-  },
 };
 
 // Cache TTLs (seconds)

open-sse/config/embeddingRegistry.ts

@@ -409,25 +409,6 @@ export const EMBEDDING_PROVIDERS: Record<string, EmbeddingProvider> = {
       },
     ],
   },
-
-  nanogpt: {
-    id: "nanogpt",
-    baseUrl: "https://nano-gpt.com/v1/embeddings",
-    authType: "apikey",
-    authHeader: "bearer",
-    models: [
-      {
-        id: "text-embedding-3-small",
-        name: "Text Embedding 3 Small",
-        dimensions: 1536,
-      },
-      {
-        id: "text-embedding-3-large",
-        name: "Text Embedding 3 Large",
-        dimensions: 3072,
-      },
-    ],
-  },
 };
 
 const EMBEDDING_PROVIDER_ALIASES: Record<string, string> = {

open-sse/config/errorConfig.ts

@@ -149,18 +149,6 @@ export const ERROR_RULES: ErrorRule[] = [
     backoff: true,
     reason: "quota_exhausted",
   },
-  {
-    id: "out_of_extra_usage",
-    text: "out of extra usage",
-    backoff: true,
-    reason: "quota_exhausted",
-  },
-  {
-    id: "extra_usage_required",
-    text: "extra usage required",
-    backoff: true,
-    reason: "quota_exhausted",
-  },
   { id: "capacity", text: "capacity", backoff: true, reason: "model_capacity" },
   { id: "overloaded", text: "overloaded", backoff: true, reason: "model_capacity" },
   { id: "high_demand", text: "high demand", backoff: true, reason: "model_capacity" },

open-sse/config/freeModelCatalog.data.ts

@@ -311,6 +311,7 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "nscale", modelId: "openai/gpt-oss-20b", displayName: "openai/gpt-oss-20b", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
   { provider: "nscale", modelId: "meta-llama/Llama-4-Scout-17B-16E-Instruct", displayName: "meta-llama/Llama-4-Scout-17B-16E-Instruct", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
   { provider: "nscale", modelId: "meta-llama/Llama-3.3-70B-Instruct", displayName: "meta-llama/Llama-3.3-70B-Instruct", monthlyTokens: 0, creditTokens: 5000000, freeType: "one-time-initial", poolKey: "nscale", tos: "caution" },
+  { provider: "nvidia", modelId: "z-ai/glm-5.1", displayName: "GLM 5.1", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "z-ai/glm-5.2", displayName: "GLM 5.2", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "minimaxai/minimax-m2.7", displayName: "MiniMax M2.7", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "google/gemma-4-31b-it", displayName: "Gemma 4 31B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
@@ -320,6 +321,7 @@ export const FREE_MODEL_BUDGETS: FreeModelBudget[] = [
   { provider: "nvidia", modelId: "qwen/qwen3.5-397b-a17b", displayName: "Qwen3.5-397B-A17B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "qwen/qwen3.5-122b-a10b", displayName: "Qwen3.5-122B-A10B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "stepfun-ai/step-3.5-flash", displayName: "Step 3.5 Flash", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
+  { provider: "nvidia", modelId: "deepseek-ai/deepseek-v4-pro", displayName: "DeepSeek V4 Pro", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "openai/gpt-oss-120b", displayName: "GPT OSS 120B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "openai/gpt-oss-20b", displayName: "GPT OSS 20B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },
   { provider: "nvidia", modelId: "nvidia/nemotron-3-super-120b-a12b", displayName: "Nemotron 3 Super 120B A12B", monthlyTokens: 0, creditTokens: 0, freeType: "one-time-initial", poolKey: "nvidia", tos: "caution" },

open-sse/config/imageRegistry.ts

@@ -12,10 +12,6 @@ import { FREEPIK_IMAGE_PROVIDER } from "./providers/registry/freepik/index.ts";
 import { STABILITY_AI_IMAGE_MODELS } from "./providers/registry/stability-ai/imageModels.ts";
 import { GEMINI_IMAGEN_PROVIDER } from "./providers/registry/gemini/imageModels.ts";
 import { CHEAPERINFERENCE_IMAGE_PROVIDER } from "./providers/registry/cheaperinference/imageModels.ts";
-import {
-  ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
-  toRegistryImageModels,
-} from "../services/adobeFireflyModels.ts";
 
 interface ImageModelEntry {
   id: string;
@@ -26,8 +22,6 @@ interface ImageModelEntry {
   imageRequired?: boolean;
   description?: string;
   isMarket?: boolean;
-  supportedSizes?: string[];
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface ImageProviderConfig {
@@ -41,7 +35,6 @@ interface ImageProviderConfig {
   authHeader: string;
   format: string;
   models: ImageModelEntry[];
-  routingAliases?: readonly string[];
   supportedSizes: string[];
 }
 
@@ -53,7 +46,6 @@ interface ImageModelAliasEntry {
   inputModalities?: string[];
   imageRequired?: boolean;
   description?: string;
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface ImageCatalogModelEntry {
@@ -63,7 +55,6 @@ interface ImageCatalogModelEntry {
   supportedSizes: string[];
   inputModalities: string[];
   description?: string;
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 const IMAGE_MODEL_ALIASES: Record<string, ImageModelAliasEntry> = {
@@ -687,9 +678,55 @@ export const IMAGE_PROVIDERS: Record<string, ImageProviderConfig> = {
     authType: "apikey",
     authHeader: "bearer",
     format: "adobe-firefly-image",
-    models: toRegistryImageModels(),
-    routingAliases: ADOBE_FIREFLY_IMAGE_ROUTING_ALIASES,
-    supportedSizes: [],
+    models: [
+      {
+        id: "nano-banana-pro",
+        name: "Firefly Gemini 3.0 (Nano Banana Pro)",
+        inputModalities: ["text", "image"],
+      },
+      {
+        id: "nano-banana",
+        name: "Firefly Gemini 2.5 (Nano Banana)",
+        inputModalities: ["text", "image"],
+      },
+      {
+        id: "nano-banana-2",
+        name: "Firefly Gemini 3.1 (Nano Banana 2)",
+        inputModalities: ["text", "image"],
+      },
+      { id: "gpt-image-2", name: "Firefly GPT Image 2", inputModalities: ["text", "image"] },
+      { id: "gpt-image", name: "Firefly GPT Image 2", inputModalities: ["text", "image"] },
+      { id: "gpt-image-1.5", name: "Firefly GPT Image 1.5", inputModalities: ["text", "image"] },
+      { id: "flux-2", name: "Firefly Flux 2", inputModalities: ["text", "image"] },
+      { id: "flux-pro", name: "Firefly Flux 1.1 Pro", inputModalities: ["text", "image"] },
+      { id: "flux-ultra", name: "Firefly Flux 1.1 Ultra", inputModalities: ["text", "image"] },
+      { id: "seedream-4", name: "Firefly Seedream 4.0", inputModalities: ["text", "image"] },
+      {
+        id: "seedream-5-lite",
+        name: "Firefly Seedream 5.0 Lite",
+        inputModalities: ["text", "image"],
+      },
+      {
+        id: "runway-gen4-image",
+        name: "Firefly Runway Gen-4 Image",
+        inputModalities: ["text", "image"],
+      },
+      // Topaz Labs upscalers (inputMediaUseCase: ["upscaling"]).
+      // Served by firefly-3p /v2/3p-images/upsample — see config/upscaleRegistry.ts.
+      {
+        id: "topaz-standard",
+        name: "Firefly Topaz Upscale (Standard)",
+        inputModalities: ["image"],
+        imageRequired: true,
+      },
+      {
+        id: "topaz-bloom",
+        name: "Firefly Topaz Bloom (Creative Upscale)",
+        inputModalities: ["image"],
+        imageRequired: true,
+      },
+    ],
+    supportedSizes: ["1:1", "16:9", "9:16", "4:3", "3:4", "1024x1024", "1792x1024", "1024x1792"],
   },
 
   // Cheaper Inference (OSS-sponsor gateway). Declared AFTER adobe-firefly on
@@ -850,7 +887,7 @@ export function parseImageModel(modelStr) {
 
   // No provider prefix — try to find the model in every provider
   for (const [providerId, config] of Object.entries(IMAGE_PROVIDERS)) {
-    if (config.routingAliases?.includes(modelStr) || config.models.some((m) => m.id === modelStr)) {
+    if (config.models.some((m) => m.id === modelStr)) {
       return { provider: providerId, model: modelStr };
     }
   }
@@ -869,10 +906,9 @@ function imageProviderCatalogEntries(
     id: `${providerId}/${model.id}`,
     name: model.name,
     provider: providerId,
-    supportedSizes: model.supportedSizes || config.supportedSizes,
+    supportedSizes: config.supportedSizes,
     inputModalities: model.inputModalities || ["text"],
     description: model.description || undefined,
-    mediaCapabilities: model.mediaCapabilities,
   }));
 }
 

open-sse/config/nvidiaHostedModels.snapshot.json

@@ -1,4 +1,5 @@
 [
+  "deepseek-ai/deepseek-v4-pro",
   "google/gemma-4-31b-it",
   "minimaxai/minimax-m2.7",
   "mistralai/devstral-2-123b-instruct-2512",
@@ -12,5 +13,6 @@
   "qwen/qwen3.5-397b-a17b",
   "stepfun-ai/step-3.5-flash",
   "thinkingmachines/inkling",
+  "z-ai/glm-5.1",
   "z-ai/glm-5.2"
 ]

open-sse/config/providerModels.ts

@@ -90,65 +90,10 @@ export function getDefaultModel(aliasOrId: string): string | null {
   return models?.[0]?.id || null;
 }
 
-/** Score a registry entry by how many capability flags it defines. */
-function modelRichness(m: RegistryModel): number {
-  let score = 0;
-  if (m.supportsXHighEffort !== undefined) score += 10; // critical for effort routing
-  if (m.supportsReasoning !== undefined) score += 5;
-  if (m.contextLength !== undefined) score += 3;
-  if (m.maxOutputTokens !== undefined) score += 2;
-  if (m.supportsVision !== undefined) score += 2;
-  if (m.toolCalling !== undefined) score += 2;
-  if (m.interleavedField !== undefined) score += 1;
-  if (m.unsupportedParams !== undefined) score += 1;
-  return score;
-}
-
-function getGlobalModel(modelId: string): RegistryModel | undefined {
-  // 1. Exact match — collect all, pick the richest
-  let candidates: RegistryModel[] = [];
-  for (const models of Object.values(PROVIDER_MODELS)) {
-    const found = models.find((m) => m.id === modelId);
-    if (found) candidates.push(found);
-  }
-  if (candidates.length > 0) {
-    return candidates.sort((a, b) => modelRichness(b) - modelRichness(a))[0];
-  }
-
-  // 2. Strip provider prefix (e.g. moonshotai/kimi-k3-free -> kimi-k3-free)
-  const basename = modelId.split("/").pop() || modelId;
-  candidates = [];
-  for (const models of Object.values(PROVIDER_MODELS)) {
-    const found = models.find((m) => m.id === basename);
-    if (found) candidates.push(found);
-  }
-  if (candidates.length > 0) {
-    return candidates.sort((a, b) => modelRichness(b) - modelRichness(a))[0];
-  }
-
-  // 3. Substring match for base model name (e.g. kimi-k3-free -> kimi-k3)
-  // Finds the longest matching base model ID; on ties, prefers the richer entry.
-  let bestMatch: RegistryModel | undefined;
-  for (const models of Object.values(PROVIDER_MODELS)) {
-    for (const m of models) {
-      if (basename.startsWith(m.id)) {
-        if (
-          !bestMatch ||
-          m.id.length > bestMatch.id.length ||
-          (m.id.length === bestMatch.id.length && modelRichness(m) > modelRichness(bestMatch))
-        ) {
-          bestMatch = m;
-        }
-      }
-    }
-  }
-  return bestMatch;
-}
-
 export function getProviderModel(aliasOrId: string, modelId: string): RegistryModel | undefined {
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return getGlobalModel(modelId);
-  return models.find((model) => model.id === modelId) || getGlobalModel(modelId);
+  if (!models) return undefined;
+  return models.find((model) => model.id === modelId);
 }
 
 export function isValidModel(
@@ -158,20 +103,26 @@ export function isValidModel(
 ): boolean {
   if (passthroughProviders.has(aliasOrId)) return true;
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return !!getGlobalModel(modelId);
-  return models.some((m) => m.id === modelId) || !!getGlobalModel(modelId);
+  if (!models) return false;
+  return models.some((m) => m.id === modelId);
 }
 
 export function findModelName(aliasOrId: string, modelId: string): string {
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return getGlobalModel(modelId)?.name || modelId;
-  const found = models.find((m) => m.id === modelId) || getGlobalModel(modelId);
+  if (!models) return modelId;
+  const found = models.find((m) => m.id === modelId);
   return found?.name || modelId;
 }
 
 export function getModelTargetFormat(aliasOrId: string, modelId: string): string | null {
   const models = PROVIDER_MODELS[aliasOrId];
-  const found = models?.find((m) => m.id === modelId) || getGlobalModel(modelId);
+  // Strip provider prefix if present: "openai/gpt-5.6-luna" → "gpt-5.6-luna"
+  const prefix = aliasOrId + "/";
+  const bareModelId =
+    typeof modelId === "string" && modelId.startsWith(prefix)
+      ? modelId.slice(prefix.length)
+      : modelId;
+  const found = models?.find((m) => m.id === bareModelId);
   if (found?.targetFormat) return found.targetFormat;
   // #5842: OpenAI "*-pro" reasoning models (o1-pro, gpt-5.x-pro) are only served by
   // the native /v1/responses endpoint — /v1/chat/completions 404s ("only supported
@@ -179,17 +130,14 @@ export function getModelTargetFormat(aliasOrId: string, modelId: string): string
   // covers dynamically-synced ids that post-date the catalog (same spirit as the gh
   // executor's /codex/i routing, 9router#102). Scoped to the openai alias so other
   // providers shipping *-pro ids keep their own endpoint semantics.
-  if (aliasOrId === "openai" && /-pro$/i.test(modelId)) return "openai-responses";
+  if (aliasOrId === "openai" && /-pro$/i.test(bareModelId)) return "openai-responses";
   return null;
 }
 
 export function getModelStripTypes(aliasOrId: string, modelId: string): string[] {
   const models = PROVIDER_MODELS[aliasOrId];
-  if (!models)
-    return Array.isArray(getGlobalModel(modelId)?.strip)
-      ? [...getGlobalModel(modelId)!.strip!]
-      : [];
-  const found = models.find((m) => m.id === modelId) || getGlobalModel(modelId);
+  if (!models) return [];
+  const found = models.find((m) => m.id === modelId);
   return Array.isArray(found?.strip) ? [...found.strip] : [];
 }
 
@@ -314,7 +262,7 @@ function resolveProviderModelList(aliasOrId: string): {
 
 export function supportsXHighEffort(aliasOrId: string, modelId: string): boolean {
   const { models: providerModels } = resolveProviderModelList(aliasOrId);
-  const model = providerModels?.find((entry) => entry.id === modelId) || getGlobalModel(modelId);
+  const model = providerModels?.find((entry) => entry.id === modelId);
   if (model?.supportsXHighEffort !== undefined) {
     return model.supportsXHighEffort !== false;
   }

open-sse/config/providers/index.ts

@@ -121,8 +121,6 @@ import { chatgpt_webProvider } from "./registry/chatgpt-web/index.ts";
 import { openrouterProvider } from "./registry/openrouter/index.ts";
 import { cheaperinferenceProvider } from "./registry/cheaperinference/index.ts";
 import { openvectaProvider } from "./registry/openvecta/index.ts";
-import { openferenceProvider } from "./registry/openference/index.ts";
-import { openference_apiProvider } from "./registry/openference-api/index.ts";
 import { orcarouterProvider } from "./registry/orcarouter/index.ts";
 import { copilot_webProvider } from "./registry/copilot-web/index.ts";
 import { copilot_m365_webProvider } from "./registry/copilot-m365-web/index.ts";
@@ -347,8 +345,6 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   openrouter: openrouterProvider,
   cheaperinference: cheaperinferenceProvider,
   openvecta: openvectaProvider,
-  openference: openferenceProvider,
-  "openference-api": openference_apiProvider,
   orcarouter: orcarouterProvider,
   "copilot-web": copilot_webProvider,
   "copilot-m365-web": copilot_m365_webProvider,

open-sse/config/providers/registry/gemini/web/index.ts

@@ -8,32 +8,9 @@ export const gemini_webProvider: RegistryEntry = {
   baseUrl: "https://gemini.google.com/app",
   authType: "apikey",
   authHeader: "cookie",
-  // #9356: `supportsReasoning: false` is a live-behavior statement, not a guess
-  // about the underlying Gemini model. The executor drives the gemini.google.com
-  // web UI by typing a prompt, so it has no thinking-budget control to set and
-  // never surfaces `reasoning_content` — agent routers reading /v1/models must
-  // not select these for reasoning work. `toolCalling: false` is the matching
-  // statement for native function calling; the prompt-emulation shim (#7286)
-  // stays available and is advertised separately as `toolCalling: "emulated"`
-  // on the provider constant (src/shared/constants/providers/web-cookie.ts).
   models: [
-    {
-      id: "gemini-3.1-pro",
-      name: "Gemini 3.1 Pro",
-      toolCalling: false,
-      supportsReasoning: false,
-    },
-    {
-      id: "gemini-3.5-flash",
-      name: "Gemini 3.5 Flash",
-      toolCalling: false,
-      supportsReasoning: false,
-    },
-    {
-      id: "gemini-3.1-flash-lite",
-      name: "Gemini 3.1 Flash-Lite",
-      toolCalling: false,
-      supportsReasoning: false,
-    },
+    { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro", toolCalling: false },
+    { id: "gemini-3.5-flash", name: "Gemini 3.5 Flash", toolCalling: false },
+    { id: "gemini-3.1-flash-lite", name: "Gemini 3.1 Flash-Lite", toolCalling: false },
   ],
 };

open-sse/config/providers/registry/nanogpt/index.ts

@@ -8,7 +8,6 @@ export const nanogptProvider: RegistryEntry = {
   executor: "default",
   baseUrl: "https://nano-gpt.com/api/v1/chat/completions",
   modelsUrl: "https://nano-gpt.com/api/v1/models",
-  responsesBaseUrl: "https://nano-gpt.com/api/v1/responses",
   authType: "apikey",
   authHeader: "bearer",
   models: CHAT_OPENAI_COMPAT_MODELS.nanogpt,

open-sse/config/providers/registry/nvidia/index.ts

@@ -32,6 +32,8 @@ export const nvidiaProvider: RegistryEntry = {
     { id: "qwen/qwen3.5-122b-a10b", name: "Qwen3.5-122B-A10B" },
     { id: "stepfun-ai/step-3.5-flash", name: "Step 3.5 Flash" },
     { id: "stepfun-ai/step-3.7-flash", name: "Step 3.7 Flash" },
+    { id: "deepseek-ai/deepseek-v4-pro", name: "DeepSeek V4 Pro", supportsReasoning: true },
+    { id: "deepseek-ai/deepseek-v4-flash", name: "DeepSeek V4 Flash", supportsReasoning: true },
     // Sweep 2026-06-19: verified present in the live NVIDIA NIM /v1/models catalog.
     { id: "moonshotai/kimi-k2.6", name: "Kimi K2.6" },
     { id: "openai/gpt-oss-120b", name: "GPT OSS 120B", toolCalling: false },

open-sse/config/providers/registry/openference-api/index.ts

@@ -1,18 +0,0 @@
-import type { RegistryEntry } from "../../shared.ts";
-import { buildOpenAiCompatibleRegistryEntry } from "../../shared.ts";
-
-/**
- * Openference API key — OpenAI-compatible gateway (https://openference.com/).
- *
- * Bearer API keys (`sk-…`) hit the same api.openference.com/v1/* surface as OAuth
- * JWTs. Live model discovery uses NAMED_OPENAI_STYLE_PROVIDERS; the seed below is
- * the offline fallback when the live fetch fails.
- */
-export const openference_apiProvider: RegistryEntry = buildOpenAiCompatibleRegistryEntry({
-  id: "openference-api",
-  alias: "ofa",
-  baseUrl: "https://api.openference.com/v1/chat/completions",
-  responsesBaseUrl: "https://api.openference.com/v1/responses",
-  passthroughModels: true,
-  models: [{ id: "GLM-5.2", name: "GLM 5.2", contextLength: 850000 }],
-});

open-sse/config/providers/registry/openference/index.ts

@@ -1,25 +0,0 @@
-import { resolvePublicCred, type RegistryEntry } from "../../shared.ts";
-
-/**
- * Openference — OpenAI-compatible AI inference gateway (https://openference.com/).
- *
- * OAuth access tokens are ES256 JWTs accepted as Bearer credentials on
- * api.openference.com/v1/*. Live model discovery uses NAMED_OPENAI_STYLE_PROVIDERS;
- * seed models below are the offline fallback when the live fetch fails.
- */
-export const openferenceProvider: RegistryEntry = {
-  id: "openference",
-  alias: "of",
-  format: "openai",
-  executor: "default",
-  baseUrl: "https://api.openference.com/v1/chat/completions",
-  responsesBaseUrl: "https://api.openference.com/v1/responses",
-  authType: "oauth",
-  authHeader: "bearer",
-  passthroughModels: true,
-  oauth: {
-    clientIdDefault: resolvePublicCred("openference_id"),
-    tokenUrl: "https://openference.com/oauth/token",
-  },
-  models: [{ id: "GLM-5.2", name: "GLM 5.2", contextLength: 850000 }],
-};

open-sse/config/videoRegistry.ts

@@ -5,17 +5,14 @@
  * Supports local providers plus hosted task-based APIs such as Runway.
  */
 
-import { parseModelFromRegistry } from "./registryUtils.ts";
+import { parseModelFromRegistry, getAllModelsFromRegistry } from "./registryUtils.ts";
 import { RUNWAYML_SUPPORTED_VIDEO_MODELS } from "./runway.ts";
 import { SEGMIND_VIDEO_MODELS } from "./providers/registry/segmind/videoModels.ts";
-import { toRegistryVideoModels } from "../services/adobeFireflyModels.ts";
 
 interface VideoModel {
   id: string;
   name: string;
   isMarket?: boolean;
-  supportedSizes?: string[];
-  mediaCapabilities?: Record<string, unknown>;
 }
 
 interface VideoProvider {
@@ -329,7 +326,8 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
   },
 
   // Adobe Firefly (unofficial) — same IMS/cookie credential as the image entry.
-  // Exact async video models and capabilities from the verified discovery snapshot.
+  // Async 3P video generate + poll (Sora 2, Veo 3.1, Kling …). Fallback list
+  // from models/discovery capture (adobe/get_models.txt).
   "adobe-firefly": {
     id: "adobe-firefly",
     alias: "firefly",
@@ -337,16 +335,18 @@ export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
     authType: "apikey",
     authHeader: "bearer",
     format: "adobe-firefly-video",
-    models: toRegistryVideoModels(),
-  },
-
-  nanogpt: {
-    id: "nanogpt",
-    baseUrl: "https://nano-gpt.com/api/v1/video/generations",
-    authType: "apikey",
-    authHeader: "bearer",
-    format: "openai",
-    models: [{ id: "default", name: "NanoGPT Video" }],
+    models: [
+      { id: "sora-2", name: "Firefly Sora 2" },
+      { id: "sora-2-pro", name: "Firefly Sora 2 Pro" },
+      { id: "veo-3.1", name: "Firefly Veo 3.1" },
+      { id: "veo-3.1-fast", name: "Firefly Veo 3.1 Fast" },
+      { id: "veo-3.1-ref", name: "Firefly Veo 3.1 Reference" },
+      { id: "kling-3", name: "Firefly Kling v3 Standard I2V" },
+      { id: "kling-v3-t2v", name: "Firefly Kling v3 Standard T2V" },
+      { id: "kling-v3-pro-i2v", name: "Firefly Kling v3 Pro I2V" },
+      { id: "luma-ray3", name: "Firefly Ray3" },
+      { id: "runway-gen4-turbo", name: "Firefly Runway Gen-4 Video" },
+    ],
   },
 };
 
@@ -368,17 +368,5 @@ export function parseVideoModel(modelStr: string | null) {
  * Get all video models as a flat list
  */
 export function getAllVideoModels() {
-  return Object.entries(VIDEO_PROVIDERS).flatMap(([providerId, config]) =>
-    [providerId, config.alias]
-      .filter((prefix): prefix is string => Boolean(prefix))
-      .flatMap((prefix) =>
-        config.models.map((model) => ({
-          id: `${prefix}/${model.id}`,
-          name: model.name,
-          provider: providerId,
-          supportedSizes: model.supportedSizes || [],
-          mediaCapabilities: model.mediaCapabilities,
-        }))
-      )
-  );
+  return getAllModelsFromRegistry(VIDEO_PROVIDERS);
 }

open-sse/executors/azure-ai.ts

@@ -1,35 +0,0 @@
-import { DefaultExecutor } from "./default.ts";
-import type { ProviderCredentials } from "./base.ts";
-import { applyAzureParamRules } from "./azureParamRules.ts";
-
-/**
- * Azure AI Foundry (`azure-ai`).
- *
- * URL building, auth headers and the `responses` vs `chat` apiType switch all
- * live in `DefaultExecutor`, keyed on the `azure-ai` provider id — this subclass
- * inherits them unchanged and adds only the Azure request-param rules.
- *
- * Before this existed, `azure-ai` fell through to the bare `DefaultExecutor`
- * while `azure-openai` had the rules inline, so the same Azure deployment
- * behaved differently depending on which connection served it: `azure-openai`
- * succeeded and `azure-ai` returned HTTP 400 for `max_tokens` /
- * `reasoning_effort`.
- */
-export class AzureAiExecutor extends DefaultExecutor {
-  constructor() {
-    super("azure-ai");
-  }
-
-  override transformRequest(
-    model: string,
-    body: unknown,
-    stream: boolean,
-    credentials: ProviderCredentials
-  ): unknown {
-    return applyAzureParamRules(
-      model,
-      body,
-      super.transformRequest(model, body, stream, credentials)
-    );
-  }
-}