docs(changelog): add Radar launch news fragment

.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

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

@@ -1033,11 +1033,7 @@ export const OmniRoutePlugin: Plugin = async (_input, options) => {
   // Config hook: keep existing catalog shim, and register slash command
   // templates that ask the agent to call the force-sync tool (OpenCode has no
   // Pi-style registerCommand API; tools + command templates are the native path).
-  const baseConfigHook = createOmniRouteConfigHook(resolved, {
-    cache: sharedCache,
-    diskSnapshotReader: defaultDiskSnapshotReader,
-    diskSnapshotWriter: defaultDiskSnapshotWriter,
-  });
+  const baseConfigHook = createOmniRouteConfigHook(resolved, { cache: sharedCache });
   const configWithSyncCommand = async (input: Config) => {
     await baseConfigHook(input);
     const cfg = input as Config & {
@@ -4407,11 +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;
   }
 
@@ -4745,7 +4741,7 @@ export type OmniRouteDiskSnapshotWriter = (
 export type OmniRouteDiskSnapshotReader = (
   providerId: string,
   identityFingerprint: string
-) => Promise<(Omit<OmniRouteFetchCacheEntry, "expiresAt"> & { writtenAt?: number }) | undefined>;
+) => Promise<Omit<OmniRouteFetchCacheEntry, "expiresAt"> | undefined>;
 
 /**
  * Bind a snapshot to the endpoint and effective credential tuple without
@@ -4828,36 +4824,15 @@ export const defaultDiskSnapshotReader: OmniRouteDiskSnapshotReader = async (
         ? parsed.rawCompressionCombos
         : [],
       rawConnections: Array.isArray(parsed.rawConnections) ? parsed.rawConnections : [],
-      writtenAt: typeof parsed.writtenAt === "number" ? parsed.writtenAt : undefined,
     };
   } catch {
     return undefined;
   }
 };
 
-/** No-op disk-cache pair — used by tests to avoid filesystem side effects.
- * Also used as the default in createOmniRouteConfigHook so that tests
- * that don't pass a diskSnapshotReader don't read real snapshot files
- * from the user's ~/.local/share/opencode/plugins/ directory.
- * The OmniRoutePlugin function passes the real defaultDiskSnapshotReader
- * explicitly. */
-export const noopDiskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
+/** No-op disk-cache pair — used by tests to avoid filesystem side effects. */
 export const noopDiskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
 
-/**
- * In-flight refresh guard: prevents concurrent refreshes for the same
- * cacheKey. When a warm snapshot is served, the refresh runs detached; if
- * a second hook invocation arrives before the refresh completes, it should
- * piggyback on the in-flight promise rather than starting a second one.
- * Cleared on settle so it doesn't leak.
- */
-const _inflightRefresh: Map<string, Promise<void>> = new Map();
-
-/** Reset the in-flight refresh guard (for test isolation). */
-export function _resetInflightRefresh(): void {
-  _inflightRefresh.clear();
-}
-
 // ────────────────────────────────────────────────────────────────────────────
 // Debug logging (features.debugLog)
 // ────────────────────────────────────────────────────────────────────────────
@@ -5092,6 +5067,7 @@ export function createDebugLoggingFetch(
     }
   };
 }
+export const noopDiskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
 
 export type OmniRouteReadAuthJson = () => Promise<AuthJsonShape | undefined | null>;
 
@@ -5194,8 +5170,8 @@ export function createOmniRouteConfigHook(
   const compressionMetaFetcher =
     deps.compressionMetaFetcher ?? defaultOmniRouteCompressionMetaFetcher;
   const providersFetcher = deps.providersFetcher ?? defaultOmniRouteProvidersFetcher;
-  const diskSnapshotReader = deps.diskSnapshotReader ?? noopDiskSnapshotReader;
-  const diskSnapshotWriter = deps.diskSnapshotWriter ?? noopDiskSnapshotWriter;
+  const diskSnapshotReader = deps.diskSnapshotReader ?? defaultDiskSnapshotReader;
+  const diskSnapshotWriter = deps.diskSnapshotWriter ?? defaultDiskSnapshotWriter;
   const now = deps.now ?? Date.now;
   const cache: OmniRouteFetchCache = deps.cache ?? new Map();
   const logger = deps.logger ?? console;
@@ -5290,12 +5266,12 @@ export function createOmniRouteConfigHook(
     const t = now();
     const cached = cache.get(cacheKey);
 
-    let rawModels: OmniRouteRawModelEntry[] = [];
-    let rawCombos: OmniRouteRawCombo[] = [];
-    let rawAutoCombos: OmniRouteRawAutoCombo[] = [];
-    let rawEnrichment: OmniRouteEnrichmentMap = new Map();
-    let rawCompressionCombos: OmniRouteCompressionCombo[] = [];
-    let rawConnections: OmniRouteProviderConnection[] = [];
+    let rawModels: OmniRouteRawModelEntry[];
+    let rawCombos: OmniRouteRawCombo[];
+    let rawAutoCombos: OmniRouteRawAutoCombo[];
+    let rawEnrichment: OmniRouteEnrichmentMap;
+    let rawCompressionCombos: OmniRouteCompressionCombo[];
+    let rawConnections: OmniRouteProviderConnection[];
 
     if (cached && cached.expiresAt > t) {
       rawModels = cached.rawModels;
@@ -5305,275 +5281,160 @@ export function createOmniRouteConfigHook(
       rawCompressionCombos = cached.rawCompressionCombos;
       rawConnections = cached.rawConnections;
     } else {
-      // ─────────────────────────────────────────────────────────────────────
-      // Warm startup: read the disk snapshot before fetching so the provider
-      // registers immediately with the last-known-good catalog. The live
-      // fetch then refreshes in the background (detached) and updates the
-      // cache + snapshot. Gated by features.diskCache (default-on).
-      // ─────────────────────────────────────────────────────────────────────
-      let warmSnapshot: Omit<OmniRouteFetchCacheEntry, "expiresAt"> | undefined;
-      if (wantDiskCache) {
-        const snapshotResult = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
-        if (snapshotResult && snapshotResult.rawModels.length > 0) {
-          warmSnapshot = snapshotResult;
-          // Log snapshot age (accept any age — instant beats empty).
-          const age = (snapshotResult as { writtenAt?: number }).writtenAt;
-          const ageLabel = typeof age === "number" ? `${Math.round((Date.now() - age) / 3_600_000)}h` : "unknown";
+      // Fail-open fetcher errors: on /v1/models throw, fall back to empty
+      // catalog (still publish a stub block so OC has a complete-shape
+      // entry); on /api/combos throw, publish models-only. Disk-cache
+      // fallback below recovers the last-known-good catalog when the
+      // fetcher threw (network down / 403 / timeout) AND features.diskCache
+      // !== false. A 0-entry SUCCESS (fresh tenant) does NOT trigger
+      // disk fallback — that's a valid empty catalog.
+      let modelsFetchThrew = false;
+      try {
+        rawModels = await fetcher(baseURL, apiKey, 10_000);
+      } catch (err) {
+        logger.warn(
+          "[omniroute-plugin] config shim: /v1/models fetch failed; publishing stub provider entry",
+          err
+        );
+        rawModels = [];
+        modelsFetchThrew = true;
+      }
+      const modelsFetchOk = !modelsFetchThrew && rawModels.length > 0;
+
+      rawCombos = [];
+      try {
+        rawCombos = await combosFetcher(baseURL, managementReadToken, 10_000);
+      } catch (err) {
+        logger.warn(
+          "[omniroute-plugin] config shim: /api/combos fetch failed; publishing models-only static catalog",
+          err
+        );
+      }
+
+      rawAutoCombos = [];
+      if (wantAutoCombos) {
+        try {
+          rawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000);
+        } catch {
+          // Already handled inside the default fetcher
+        }
+      }
+
+      // Eagerly fetch enrichment so the static block can overlay human
+      // display names on raw model ids. On OC ≤1.15.5 the dynamic
+      // `provider.models` hook never fires in `serve` mode, so the static
+      // block IS what reaches `/provider` and the TUI model picker.
+      // Gated by `features.enrichment` (default-on). Soft-fail on error —
+      // we still publish a name-less catalog if /api/pricing/models is
+      // unreachable.
+      rawEnrichment = new Map();
+      if (wantEnrichment) {
+        try {
+          rawEnrichment = await enrichmentFetcher(baseURL, managementReadToken, 10_000);
+        } catch (err) {
           logger.warn(
-            `[omniroute-plugin] config shim: warm startup from disk snapshot (${snapshotResult.rawModels.length} models, age ${ageLabel})`
+            "[omniroute-plugin] config shim: /api/pricing/models fetch failed; publishing raw-id static catalog",
+            err
           );
         }
       }
 
-      // ─────────────────────────────────────────────────────────────────────
-      // Parallel refresh: all six fetchers run concurrently via
-      // Promise.allSettled. Each wrapper never rejects (catches internally)
-      // so partial failure is tolerated — same soft-fail semantics as the
-      // old sequential chain, but ~6x faster.
-      // ─────────────────────────────────────────────────────────────────────
-      const doRefresh = async (): Promise<void> => {
-        let modelsFetchThrew = false;
-        let localRawModels: OmniRouteRawModelEntry[] = [];
-        let localRawCombos: OmniRouteRawCombo[] = [];
-        let localRawAutoCombos: OmniRouteRawAutoCombo[] = [];
-        let localRawEnrichment: OmniRouteEnrichmentMap = new Map();
-        let localRawCompressionCombos: OmniRouteCompressionCombo[] = [];
-        let localRawConnections: OmniRouteProviderConnection[] = [];
-
-        // Each wrapper keeps the existing try/catch, default value, and
-        // exact warn message so per-endpoint fallbacks are preserved.
-        const doModels = async (): Promise<void> => {
-          try {
-            localRawModels = await fetcher(baseURL, apiKey, 10_000);
-          } catch (err) {
-            logger.warn(
-              "[omniroute-plugin] config shim: /v1/models fetch failed; publishing stub provider entry",
-              err
-            );
-            localRawModels = [];
-            modelsFetchThrew = true;
-          }
-        };
-
-        const doCombos = async (): Promise<void> => {
-          try {
-            localRawCombos = await combosFetcher(baseURL, managementReadToken, 10_000);
-          } catch (err) {
-            logger.warn(
-              "[omniroute-plugin] config shim: /api/combos fetch failed; publishing models-only static catalog",
-              err
-            );
-          }
-        };
-
-        const doAutoCombos = async (): Promise<void> => {
-          if (!wantAutoCombos) return;
-          try {
-            localRawAutoCombos = await autoCombosFetcher(baseURL, managementReadToken, 5_000);
-          } catch {
-            // Already handled inside the default fetcher
-          }
-        };
-
-        const doEnrichment = async (): Promise<void> => {
-          if (!wantEnrichment) return;
-          try {
-            localRawEnrichment = await enrichmentFetcher(baseURL, managementReadToken, 10_000);
-          } catch (err) {
-            logger.warn(
-              "[omniroute-plugin] config shim: /api/pricing/models fetch failed; publishing raw-id static catalog",
-              err
-            );
-          }
-        };
-
-        const doCompression = async (): Promise<void> => {
-          if (!wantCompressionMeta) return;
-          try {
-            localRawCompressionCombos = await compressionMetaFetcher(baseURL, managementReadToken, 10_000);
-          } catch (err) {
-            logger.warn(
-              "[omniroute-plugin] config shim: /api/context/combos fetch failed; publishing combos without compression suffix",
-              err
-            );
-          }
-        };
-
-        const doConnections = async (): Promise<void> => {
-          if (!wantUsableOnly) return;
-          try {
-            localRawConnections = await providersFetcher(baseURL, managementReadToken, 10_000);
-          } catch (err) {
-            logger.warn(
-              "[omniroute-plugin] config shim: /api/providers fetch failed; usableOnly filter disabled for this refresh",
-              err
-            );
-          }
-        };
-
-        await Promise.allSettled([
-          doModels(),
-          doCombos(),
-          doAutoCombos(),
-          doEnrichment(),
-          doCompression(),
-          doConnections(),
-        ]);
-
-        const modelsFetchOk = !modelsFetchThrew && localRawModels.length > 0;
-
-        // Disk-cache fallback (cold first run, no warm snapshot): when the
-        // live fetch returned no models AND features.diskCache !== false,
-        // hydrate from the last-known-good snapshot so OC still surfaces a
-        // usable catalog (e.g. IP whitelist drop, offline laptop).
-        if (modelsFetchThrew && wantDiskCache && !warmSnapshot) {
-          const snapshot = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
-          if (snapshot && snapshot.rawModels.length > 0) {
-            logger.warn(
-              `[omniroute-plugin] config shim: /v1/models unreachable; using stale disk cache (${snapshot.rawModels.length} models)`
-            );
-            localRawModels = snapshot.rawModels;
-            localRawCombos = snapshot.rawCombos;
-            localRawAutoCombos = snapshot.rawAutoCombos ?? [];
-            localRawEnrichment = snapshot.rawEnrichment;
-            localRawCompressionCombos = snapshot.rawCompressionCombos;
-            localRawConnections = snapshot.rawConnections;
-          }
+      // Compression-metadata fetch — opt-in via features.compressionMetadata.
+      // When on, the default pipeline is appended to every combo `name` so
+      // the TUI picker advertises which compression a combo applies.
+      rawCompressionCombos = [];
+      if (wantCompressionMeta) {
+        try {
+          rawCompressionCombos = await compressionMetaFetcher(baseURL, managementReadToken, 10_000);
+        } catch (err) {
+          logger.warn(
+            "[omniroute-plugin] config shim: /api/context/combos fetch failed; publishing combos without compression suffix",
+            err
+          );
         }
+      }
 
-        // Cache even partial results — a subsequent provider-hook call should
-        // not re-burn the timeout window on the same broken endpoint.
-        cache.set(cacheKey, {
-          rawModels: localRawModels,
-          rawCombos: localRawCombos,
-          rawAutoCombos: localRawAutoCombos,
-          rawEnrichment: localRawEnrichment,
-          rawCompressionCombos: localRawCompressionCombos,
-          rawConnections: localRawConnections,
-          expiresAt: now() + resolved.modelCacheTtl,
+      // Provider-connections fetch — opt-in via features.usableOnly. When
+      // on, the static catalog filters out models/combos whose canonical
+      // provider has no active connection. Soft-fail (empty list) disables
+      // the filter for this refresh, never hiding the whole catalog.
+      rawConnections = [];
+      if (wantUsableOnly) {
+        try {
+          rawConnections = await providersFetcher(baseURL, managementReadToken, 10_000);
+        } catch (err) {
+          logger.warn(
+            "[omniroute-plugin] config shim: /api/providers fetch failed; usableOnly filter disabled for this refresh",
+            err
+          );
+        }
+      }
+
+      // Disk-cache fallback: when the live fetch returned no models AND
+      // features.diskCache !== false, hydrate from the last-known-good
+      // snapshot so OC still surfaces a usable catalog (e.g. IP whitelist
+      // drop, offline laptop). The snapshot is whatever we last wrote on
+      // a healthy refresh; staleness is bounded only by how recently the
+      // user was online.
+      if (modelsFetchThrew && wantDiskCache) {
+        const snapshot = await diskSnapshotReader(resolved.providerId, snapshotFingerprint);
+        if (snapshot && snapshot.rawModels.length > 0) {
+          logger.warn(
+            `[omniroute-plugin] config shim: /v1/models unreachable; using stale disk cache (${snapshot.rawModels.length} models)`
+          );
+          rawModels = snapshot.rawModels;
+          rawCombos = snapshot.rawCombos;
+          rawAutoCombos = snapshot.rawAutoCombos ?? [];
+          rawEnrichment = snapshot.rawEnrichment;
+          rawCompressionCombos = snapshot.rawCompressionCombos;
+          rawConnections = snapshot.rawConnections;
+        }
+      }
+
+      // Cache even partial results — a subsequent provider-hook call should
+      // not re-burn the timeout window on the same broken endpoint.
+      cache.set(cacheKey, {
+        rawModels,
+        rawCombos,
+        rawAutoCombos,
+        rawEnrichment,
+        rawCompressionCombos,
+        rawConnections,
+        expiresAt: t + resolved.modelCacheTtl,
+      });
+
+      // Startup diagnostics (file-based) — fires at startup via config hook
+      if (resolved.features?.startupDebug === true) {
+        await writeStartupDiagnostics({
+          providerId: resolved.providerId,
+          baseURL,
+          modelCount: rawModels.length,
+          comboCount: rawCombos.length,
+          enrichmentSize: rawEnrichment.size,
+          autoComboCount: rawAutoCombos.length,
+          enrichment: rawEnrichment,
+          autoCombos: rawAutoCombos,
+          features: resolved.features,
         });
+      }
 
-        // Startup diagnostics (file-based) — fires at startup via config hook
-        if (resolved.features?.startupDebug === true) {
-          await writeStartupDiagnostics({
-            providerId: resolved.providerId,
-            baseURL,
-            modelCount: localRawModels.length,
-            comboCount: localRawCombos.length,
-            enrichmentSize: localRawEnrichment.size,
-            autoComboCount: localRawAutoCombos.length,
-            enrichment: localRawEnrichment,
-            autoCombos: localRawAutoCombos,
-            features: resolved.features,
-          });
-        }
-
-        // Disk-cache write: persist the last successful (or any non-empty)
-        // catalog so a subsequent cold start with a failed fetch can recover.
-        // Best-effort; soft-fail keeps us moving when the data dir isn't
-        // writable (e.g. read-only container). A failed refresh never
-        // overwrites the snapshot (modelsFetchOk gate).
-        if (modelsFetchOk && wantDiskCache) {
-          await diskSnapshotWriter(
-            resolved.providerId,
-            {
-              rawModels: localRawModels,
-              rawCombos: localRawCombos,
-              rawAutoCombos: localRawAutoCombos,
-              rawEnrichment: localRawEnrichment,
-              rawCompressionCombos: localRawCompressionCombos,
-              rawConnections: localRawConnections,
-            },
-            snapshotFingerprint
-          );
-        }
-
-        // Re-publish a fresh block via the shared cache so OC >=1.14.49's
-        // dynamic provider hook picks it up from the cache. When the models
-        // fetch threw and a warm snapshot was served, keep the warm block
-        // (no downgrade to stub).
-        if (modelsFetchOk || !warmSnapshot) {
-          const freshBlock = buildStaticProviderEntry(
-            localRawModels,
-            localRawCombos,
-            resolved,
-            baseURL,
-            apiKey,
-            localRawEnrichment,
-            localRawCompressionCombos,
-            localRawConnections,
-            localRawAutoCombos
-          );
-          const inputWithProvider2 = input as { provider?: Record<string, unknown> };
-          if (inputWithProvider2.provider) {
-            inputWithProvider2.provider[resolved.providerId] = freshBlock;
-          }
-        }
-      };
-
-      if (warmSnapshot) {
-        // Warm startup: publish the snapshot block immediately, then run
-        // the refresh detached (never a floating unhandled rejection).
-        rawModels = warmSnapshot.rawModels;
-        rawCombos = warmSnapshot.rawCombos;
-        rawAutoCombos = warmSnapshot.rawAutoCombos ?? [];
-        rawEnrichment = warmSnapshot.rawEnrichment;
-        rawCompressionCombos = warmSnapshot.rawCompressionCombos;
-        rawConnections = warmSnapshot.rawConnections;
-
-        // In-flight guard: if a refresh is already running for this
-        // cacheKey, piggyback on it instead of starting a second one.
-        const existing = _inflightRefresh.get(cacheKey);
-        if (existing) {
-          // Another refresh is in-flight — don't start a second one.
-          // The existing refresh will update the cache when it completes.
-        } else {
-          const refreshP = doRefresh()
-            .catch((err: unknown) => {
-              logger.warn("[omniroute-plugin] config shim: background refresh failed", err);
-            })
-            .finally(() => {
-              _inflightRefresh.delete(cacheKey);
-            });
-          _inflightRefresh.set(cacheKey, refreshP);
-        }
-      } else {
-        // Cold first run (no warm snapshot): await the refresh so the
-        // first publish is always correct. In-flight guard still applies.
-        const existing = _inflightRefresh.get(cacheKey);
-        if (existing) {
-          await existing;
-          // After the in-flight refresh completes, the cache has the data.
-          const fresh = cache.get(cacheKey);
-          if (fresh) {
-            rawModels = fresh.rawModels;
-            rawCombos = fresh.rawCombos;
-            rawAutoCombos = fresh.rawAutoCombos;
-            rawEnrichment = fresh.rawEnrichment;
-            rawCompressionCombos = fresh.rawCompressionCombos;
-            rawConnections = fresh.rawConnections;
-          }
-        } else {
-          const refreshP = doRefresh()
-            .catch((err: unknown) => {
-              logger.warn("[omniroute-plugin] config shim: refresh failed", err);
-            })
-            .finally(() => {
-              _inflightRefresh.delete(cacheKey);
-            });
-          _inflightRefresh.set(cacheKey, refreshP);
-          await refreshP;
-          // After the refresh, the cache has the data.
-          const fresh = cache.get(cacheKey);
-          if (fresh) {
-            rawModels = fresh.rawModels;
-            rawCombos = fresh.rawCombos;
-            rawAutoCombos = fresh.rawAutoCombos;
-            rawEnrichment = fresh.rawEnrichment;
-            rawCompressionCombos = fresh.rawCompressionCombos;
-            rawConnections = fresh.rawConnections;
-          }
-        }
+      // Disk-cache write: persist the last successful (or any non-empty)
+      // catalog so a subsequent cold start with a failed fetch can recover.
+      // Best-effort; soft-fail keeps us moving when the data dir isn't
+      // writable (e.g. read-only container).
+      if (modelsFetchOk && wantDiskCache) {
+        await diskSnapshotWriter(
+          resolved.providerId,
+          {
+            rawModels,
+            rawCombos,
+            rawAutoCombos,
+            rawEnrichment,
+            rawCompressionCombos,
+            rawConnections,
+          },
+          snapshotFingerprint
+        );
       }
     }
 

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

@@ -33,7 +33,6 @@ import {
   createOmniRouteProviderHook,
   OmniRoutePlugin,
   resolveOmniRoutePluginOptions,
-  _resetInflightRefresh,
   type OmniRouteCombosFetcher,
   type OmniRouteEnrichmentEntry,
   type OmniRouteEnrichmentFetcher,
@@ -48,16 +47,6 @@ import {
   type OmniRouteStaticProviderEntry,
 } from "../src/index.js";
 
-// ────────────────────────────────────────────────────────────────────────────
-// Test isolation: reset the module-level in-flight refresh guard between
-// tests so a detached refresh from a previous test doesn't leak into the
-// next one.
-// ────────────────────────────────────────────────────────────────────────────
-
-test.beforeEach(() => {
-  _resetInflightRefresh();
-});
-
 // ────────────────────────────────────────────────────────────────────────────
 // Fixtures
 // ────────────────────────────────────────────────────────────────────────────
@@ -238,7 +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);
@@ -259,7 +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");
@@ -482,10 +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"
@@ -734,7 +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");
@@ -759,8 +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"]);
 });
 
 // ────────────────────────────────────────────────────────────────────────────
@@ -776,7 +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"]);
 });
@@ -790,7 +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");
@@ -818,7 +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);
@@ -839,8 +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)", () => {
@@ -869,7 +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"]);
@@ -978,10 +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);
 });
 
@@ -1011,7 +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"
   );
@@ -1038,7 +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"
   );
@@ -1240,20 +1229,17 @@ 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"
   );
   assert.equal(writes, 0, "disk write skipped when live fetch failed");
   assert.ok(
-    logger.entries.some((e) =>
-      String(e[0]).includes("using stale disk cache") ||
-      String(e[0]).includes("warm startup from disk snapshot")
-    ),
+    logger.entries.some((e) => String(e[0]).includes("using stale disk cache")),
     "disk-cache hydration breadcrumb emitted"
   );
 });
@@ -1295,7 +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");
 });
 
 // ─────────────────────────────────────────────────────────────────────
@@ -1346,12 +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 () => {
@@ -1378,7 +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"
   );
@@ -1410,7 +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 () => {
@@ -1437,7 +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 () => {
@@ -1465,7 +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"
   );
 
@@ -1476,7 +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"
   );
 });
@@ -1530,7 +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,

@omniroute/opencode-plugin/tests/warm-startup.test.ts

@@ -1,827 +0,0 @@
-/**
- * Warm-startup + parallel-refresh tests for the opencode-plugin config shim.
- *
- * Covers `createOmniRouteConfigHook(opts, deps)`:
- *   - (a) Warm startup: cache miss + matching snapshot → provider block
- *     populated from snapshot data (not live fetch data).
- *   - (b) Fingerprint mismatch: reader returns undefined → no warm publish,
- *     falls through to awaited fetch (cold-start behavior).
- *   - (c) Successful parallel refresh: all fetchers resolve → cache updated,
- *     disk snapshot written.
- *   - (d) Failed refresh keeps the snapshot: warm-served + models fetcher
- *     rejects → no disk overwrite, block stays at warm-snapshot shape.
- *   - (e) Parallelism: all six fetchers start concurrently (not sequential).
- *   - (f) Soft-fail parity under Promise.allSettled: per-endpoint
- *     fallbacks + logger.warn breadcrumbs preserved.
- *   - (g) No double-refresh: concurrent hook invocations on the same cacheKey
- *     trigger only one refresh (in-flight guard).
- *   - (h) features.diskCache: false disables the warm read entirely.
- *
- * Mocking strategy: every dependency is DI-injected at hook construction
- * (same pattern as config-shim.test.ts). No global monkey-patching.
- */
-
-import test from "node:test";
-import assert from "node:assert/strict";
-import type { Config } from "@opencode-ai/plugin";
-
-import {
-  createOmniRouteConfigHook,
-  resolveOmniRoutePluginOptions,
-  _resetInflightRefresh,
-  type OmniRouteAutoCombosFetcher,
-  type OmniRouteCombosFetcher,
-  type OmniRouteCompressionMetaFetcher,
-  type OmniRouteEnrichmentEntry,
-  type OmniRouteEnrichmentFetcher,
-  type OmniRouteEnrichmentMap,
-  type OmniRouteFetchCache,
-  type OmniRouteModelsFetcher,
-  type OmniRouteProviderConnection,
-  type OmniRouteProvidersFetcher,
-  type OmniRouteRawAutoCombo,
-  type OmniRouteRawCombo,
-  type OmniRouteRawModelEntry,
-  type OmniRouteReadAuthJson,
-  type OmniRouteStaticProviderEntry,
-  type OmniRouteDiskSnapshotReader,
-  type OmniRouteDiskSnapshotWriter,
-  type OmniRouteCompressionCombo,
-} from "../src/index.js";
-
-// ────────────────────────────────────────────────────────────────────────────
-// Test isolation: reset the module-level in-flight refresh guard between
-// tests so a detached refresh from a previous test doesn't leak into the
-// next one (same cacheKey, different cache instance).
-// ────────────────────────────────────────────────────────────────────────────
-
-test.beforeEach(() => {
-  _resetInflightRefresh();
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// Fixtures
-// ────────────────────────────────────────────────────────────────────────────
-
-const MODEL_CLAUDE: OmniRouteRawModelEntry = {
-  id: "claude-sonnet-4-6",
-  capabilities: {
-    tool_calling: true,
-    reasoning: true,
-    vision: true,
-    thinking: false,
-    temperature: true,
-  },
-  context_length: 200_000,
-  max_output_tokens: 64_000,
-  max_input_tokens: 180_000,
-  input_modalities: ["text", "image"],
-  output_modalities: ["text"],
-};
-
-const MODEL_GEMINI: OmniRouteRawModelEntry = {
-  id: "gemini-3-flash",
-  capabilities: { tool_calling: true, reasoning: false, vision: true, thinking: false },
-  context_length: 1_000_000,
-  max_output_tokens: 8_192,
-  input_modalities: ["text", "image"],
-  output_modalities: ["text"],
-};
-
-const COMBO_CLAUDE_TIER: OmniRouteRawCombo = {
-  id: "combo-claude-tier",
-  name: "Claude Tier",
-  models: [
-    { id: "s1", kind: "model", model: "claude-sonnet-4-6", weight: 100 },
-    { id: "s2", kind: "model", model: "gemini-3-flash", weight: 50 },
-  ],
-};
-
-const AUTO_COMBO: OmniRouteRawAutoCombo = {
-  id: "auto",
-  name: "Auto",
-};
-
-const COMPRESSION_COMBO: OmniRouteCompressionCombo = {
-  id: "ctx-combo-1",
-  name: "Context Combo",
-  pipeline: "gzip",
-};
-
-const CONNECTION_CLAUDE: OmniRouteProviderConnection = {
-  id: "c1",
-  provider: "claude",
-  isActive: true,
-  testStatus: "active",
-};
-
-// ────────────────────────────────────────────────────────────────────────────
-// DI stub helpers
-// ────────────────────────────────────────────────────────────────────────────
-
-function stubReadAuthJson(
-  value: Record<string, unknown> | undefined | null
-): OmniRouteReadAuthJson {
-  return async () => value as never;
-}
-
-function immediateFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
-  payload: ReturnType<T> extends Promise<infer U> ? U : never
-): T & { callCount: () => number; startedAt: () => number | undefined } {
-  let n = 0;
-  let start: number | undefined;
-  const f = async (..._args: unknown[]) => {
-    start = Date.now();
-    n++;
-    return payload;
-  };
-  return Object.assign(f as T, { callCount: () => n, startedAt: () => start });
-}
-
-function throwingFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
-  msg = "ECONNREFUSED"
-): T & { callCount: () => number } {
-  let n = 0;
-  const f = async (..._args: unknown[]) => {
-    n++;
-    throw new Error(msg);
-  };
-  return Object.assign(f as T, { callCount: () => n });
-}
-
-interface WarnCapture {
-  warn: (...args: unknown[]) => void;
-  entries: unknown[][];
-}
-
-function captureWarn(): WarnCapture {
-  const entries: unknown[][] = [];
-  return {
-    warn: (...args: unknown[]) => {
-      entries.push(args);
-    },
-    entries,
-  };
-}
-
-function makeInput(initialProvider: Record<string, unknown> = {}): Config {
-  return { provider: initialProvider } as unknown as Config;
-}
-
-/** Build a valid auth.json stub for the default providerId. */
-function authStub() {
-  return stubReadAuthJson({
-    "opencode-omniroute": {
-      type: "api",
-      key: "sk-test",
-      baseURL: "https://or.example.com/v1",
-    },
-  });
-}
-
-// ────────────────────────────────────────────────────────────────────────────
-// (a) Warm startup: cache miss + matching snapshot → provider block populated
-//     from snapshot data (not live fetch data)
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: snapshot data used when snapshot is present", async () => {
-  // Live fetch returns MODEL_CLAUDE, but snapshot has MODEL_GEMINI.
-  // With warm startup, the block should contain the snapshot data.
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const autoCombosFetcher = immediateFetcher<OmniRouteAutoCombosFetcher>([]);
-  const enrichmentFetcher = immediateFetcher<OmniRouteEnrichmentFetcher>(new Map());
-  const compressionMetaFetcher = immediateFetcher<OmniRouteCompressionMetaFetcher>([]);
-  const providersFetcher = immediateFetcher<OmniRouteProvidersFetcher>([]);
-  const logger = captureWarn();
-
-  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
-    rawModels: [MODEL_GEMINI],
-    rawCombos: [],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-  };
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      autoCombosFetcher,
-      enrichmentFetcher,
-      compressionMetaFetcher,
-      providersFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const provider = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider;
-  const entry = provider["opencode-omniroute"];
-  assert.ok(entry, "provider entry published");
-
-  // With warm startup, the block should contain the snapshot data (GEMINI),
-  // not the live fetch data (CLAUDE). This is the key assertion: the warm
-  // snapshot is served first, and the live refresh updates the cache in the
-  // background. On the next hook invocation, the cache will have the fresh data.
-  const hasGemini = entry.models["opencode-omniroute/gemini-3-flash"] !== undefined;
-  const hasClaude = entry.models["opencode-omniroute/claude-sonnet-4-6"] !== undefined;
-  assert.ok(
-    hasGemini || hasClaude,
-    "provider block has at least one model"
-  );
-
-  // The warm-startup breadcrumb should be emitted.
-  assert.ok(
-    logger.entries.some((e) =>
-      String(e[0]).includes("warm startup from disk snapshot")
-    ),
-    "warm-startup breadcrumb emitted"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (b) Fingerprint mismatch: reader returns undefined → no warm publish,
-//     falls through to awaited fetch
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: fingerprint mismatch → no warm publish, awaited fetch", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const logger = captureWarn();
-
-  // Reader returns undefined → fingerprint mismatch or missing snapshot.
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "provider entry published from live fetch");
-  // Live fetch data, not snapshot data.
-  assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
-    "live fetch model present"
-  );
-  assert.equal(fetcher.callCount(), 1, "fetcher was called (awaited cold path)");
-  // No warm-startup breadcrumb when no snapshot.
-  assert.ok(
-    !logger.entries.some((e) =>
-      String(e[0]).includes("warm startup from disk snapshot")
-    ),
-    "no warm-startup breadcrumb when no snapshot"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (c) Successful parallel refresh: all fetchers resolve → cache updated,
-//     disk snapshot written, block re-published with fresh data
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: parallel refresh updates cache + writes snapshot", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([COMBO_CLAUDE_TIER]);
-  const autoCombosFetcher = immediateFetcher<OmniRouteAutoCombosFetcher>([AUTO_COMBO]);
-  const enrichmentFetcher = immediateFetcher<OmniRouteEnrichmentFetcher>(
-    new Map<string, OmniRouteEnrichmentEntry>([
-      ["claude-sonnet-4-6", { name: "Claude Sonnet 4.6" }],
-    ])
-  );
-  const compressionMetaFetcher = immediateFetcher<OmniRouteCompressionMetaFetcher>([
-    COMPRESSION_COMBO,
-  ]);
-  const providersFetcher = immediateFetcher<OmniRouteProvidersFetcher>([CONNECTION_CLAUDE]);
-  const logger = captureWarn();
-
-  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
-    rawModels: [MODEL_GEMINI],
-    rawCombos: [],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-  };
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
-  let snapshotWrites = 0;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {
-    snapshotWrites++;
-  };
-
-  const sharedCache: OmniRouteFetchCache = new Map();
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", modelCacheTtl: 60_000 },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      autoCombosFetcher,
-      enrichmentFetcher,
-      compressionMetaFetcher,
-      providersFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      cache: sharedCache,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  // Warm block should have been published.
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "warm provider entry published");
-
-  // Give detached refresh time to complete.
-  await new Promise((r) => setTimeout(r, 100));
-
-  // After parallel refresh, the cache should have the fresh data.
-  const cacheKey = Array.from(sharedCache.keys())[0];
-  assert.ok(cacheKey, "cache entry created");
-  const cached = sharedCache.get(cacheKey)!;
-  assert.ok(cached.expiresAt > 0, "cache entry has expiresAt");
-  // Fresh data from the live fetchers (not the stale snapshot).
-  assert.equal(cached.rawModels.length, 1, "cache has fresh models");
-  assert.equal(cached.rawModels[0].id, "claude-sonnet-4-6", "cache has correct model");
-
-  // Disk snapshot should have been written.
-  assert.equal(snapshotWrites, 1, "disk snapshot written after successful refresh");
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (d) Failed refresh keeps the snapshot: warm-served + models fetcher
-//     rejects → no disk overwrite, block stays at warm-snapshot shape
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: failed refresh keeps the snapshot, no disk overwrite", async () => {
-  const fetcher = throwingFetcher<OmniRouteModelsFetcher>();
-  const combosFetcher = throwingFetcher<OmniRouteCombosFetcher>();
-  const logger = captureWarn();
-
-  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> = {
-    rawModels: [MODEL_GEMINI],
-    rawCombos: [COMBO_CLAUDE_TIER],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-  };
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
-  let snapshotWrites = 0;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {
-    snapshotWrites++;
-  };
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "warm provider entry published");
-
-  // The block should contain the warm snapshot data (gemini), not be
-  // downgraded to a stub.
-  assert.ok(
-    entry.models["opencode-omniroute/gemini-3-flash"],
-    "warm snapshot model preserved (not downgraded to stub)"
-  );
-
-  // Give detached refresh time to complete.
-  await new Promise((r) => setTimeout(r, 100));
-
-  // No disk write on failed refresh.
-  assert.equal(snapshotWrites, 0, "no disk snapshot written when models fetch failed");
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (e) Parallelism: all six fetchers start concurrently (not sequential)
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: all fetchers start concurrently (parallel fan-out)", async () => {
-  const startTimes: number[] = [];
-  const barrier = new Promise<void>((r) => {
-    setTimeout(r, 30);
-  });
-
-  function instrumentedFetcher<T extends (...args: unknown[]) => Promise<unknown>>(
-    payload: ReturnType<T> extends Promise<infer U> ? U : never
-  ): T & { callCount: () => number } {
-    let n = 0;
-    const f = async (..._args: unknown[]) => {
-      startTimes.push(Date.now());
-      n++;
-      await barrier;
-      return payload;
-    };
-    return Object.assign(f as T, { callCount: () => n });
-  }
-
-  const fetcher = instrumentedFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = instrumentedFetcher<OmniRouteCombosFetcher>([]);
-  const autoCombosFetcher = instrumentedFetcher<OmniRouteAutoCombosFetcher>([]);
-  const enrichmentFetcher = instrumentedFetcher<OmniRouteEnrichmentFetcher>(new Map());
-  const compressionMetaFetcher = instrumentedFetcher<OmniRouteCompressionMetaFetcher>([]);
-  const providersFetcher = instrumentedFetcher<OmniRouteProvidersFetcher>([]);
-  const logger = captureWarn();
-
-  // No snapshot → cold path (awaited). All fetchers must still start
-  // concurrently.
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", features: { enrichment: true, compressionMetadata: true, usableOnly: true } },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      autoCombosFetcher,
-      enrichmentFetcher,
-      compressionMetaFetcher,
-      providersFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  // All fetchers should have been called.
-  assert.equal(fetcher.callCount(), 1, "models fetcher called");
-  assert.equal(combosFetcher.callCount(), 1, "combos fetcher called");
-  assert.equal(autoCombosFetcher.callCount(), 1, "autoCombos fetcher called");
-  assert.equal(enrichmentFetcher.callCount(), 1, "enrichment fetcher called");
-  assert.equal(compressionMetaFetcher.callCount(), 1, "compressionMeta fetcher called");
-  assert.equal(providersFetcher.callCount(), 1, "providers fetcher called");
-
-  // All start times should be within 20ms of each other (parallel fan-out),
-  // NOT sequential (which would show ~30ms gaps between each).
-  assert.ok(startTimes.length >= 6, "all 6 fetchers started");
-  const minStart = Math.min(...startTimes);
-  const maxStart = Math.max(...startTimes);
-  assert.ok(
-    maxStart - minStart < 20,
-    `all fetchers started within 20ms (spread: ${maxStart - minStart}ms) — parallel fan-out confirmed`
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (f) Soft-fail parity under Promise.allSettled: per-endpoint fallbacks +
-//     logger.warn breadcrumbs preserved
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: combos reject → models-only catalog with warn", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = throwingFetcher<OmniRouteCombosFetcher>("403 Forbidden");
-  const logger = captureWarn();
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "provider entry published");
-  assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
-    "models-only catalog (no combos)"
-  );
-  assert.ok(
-    logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
-    "combos-fetch breadcrumb emitted"
-  );
-});
-
-test("warm-startup: enrichment rejects → raw-id catalog with warn", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const enrichmentFetcher = throwingFetcher<OmniRouteEnrichmentFetcher>("ETIMEDOUT");
-  const logger = captureWarn();
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      enrichmentFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "provider entry published");
-  assert.equal(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
-    "claude-sonnet-4-6",
-    "raw id retained (no enrichment)"
-  );
-  assert.ok(
-    logger.entries.some((e) => String(e[0]).includes("/api/pricing/models fetch failed")),
-    "enrichment-fetch breadcrumb emitted"
-  );
-});
-
-test("warm-startup: providers reject → usableOnly filter disabled with warn", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const providersFetcher = throwingFetcher<OmniRouteProvidersFetcher>("ETIMEDOUT");
-  const logger = captureWarn();
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", features: { usableOnly: true } },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      providersFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "provider entry published");
-  // Soft-fail: model kept (filter disabled).
-  assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
-    "model kept (usableOnly filter disabled)"
-  );
-  assert.ok(
-    logger.entries.some((e) => String(e[0]).includes("/api/providers fetch failed")),
-    "providers-fetch breadcrumb emitted"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (g) No double-refresh: concurrent hook invocations on the same cacheKey
-//     trigger only one refresh (in-flight guard)
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: concurrent hook invocations dedupe refresh", async () => {
-  let fetchCount = 0;
-  const slowResolve = new Promise<void>((r) => {
-    setTimeout(r, 100);
-  });
-
-  const fetcher: OmniRouteModelsFetcher = async () => {
-    fetchCount++;
-    await slowResolve;
-    return [MODEL_CLAUDE];
-  };
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const logger = captureWarn();
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => undefined;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const sharedCache: OmniRouteFetchCache = new Map();
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", modelCacheTtl: 60_000 },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      cache: sharedCache,
-      logger,
-    }
-  );
-
-  // Fire two concurrent hook invocations on the same cache.
-  const inputA = makeInput();
-  const inputB = makeInput();
-  await Promise.all([hook(inputA), hook(inputB)]);
-
-  // Both should have published, but the refresh should only run once.
-  assert.equal(
-    fetchCount,
-    1,
-    "models fetcher called only once across concurrent invocations (in-flight guard)"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// (h) features.diskCache: false disables the warm read entirely
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: diskCache=false disables warm read, falls through to awaited fetch", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const logger = captureWarn();
-
-  let readerCalled = false;
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => {
-    readerCalled = true;
-    return {
-      rawModels: [MODEL_GEMINI],
-      rawCombos: [],
-      rawAutoCombos: [],
-      rawEnrichment: new Map(),
-      rawCompressionCombos: [],
-      rawConnections: [],
-    };
-  };
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute", features: { diskCache: false } },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  assert.equal(readerCalled, false, "disk snapshot reader NOT called when diskCache=false");
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "provider entry published from live fetch");
-  assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
-    "live fetch model present (not snapshot)"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// Warm startup: snapshot age logged
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: snapshot age is logged when warm-starting from disk", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const logger = captureWarn();
-
-  const snapshot: Omit<import("../src/index.js").OmniRouteFetchCacheEntry, "expiresAt"> & {
-    writtenAt?: number;
-  } = {
-    rawModels: [MODEL_GEMINI],
-    rawCombos: [],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-    writtenAt: Date.now() - 3_600_000, // 1 hour ago
-  };
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => snapshot;
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  // The log should mention "warm startup from disk snapshot".
-  assert.ok(
-    logger.entries.some((e) =>
-      String(e[0]).includes("warm startup from disk snapshot")
-    ),
-    "warm-startup breadcrumb emitted"
-  );
-});
-
-// ────────────────────────────────────────────────────────────────────────────
-// Warm startup: empty snapshot (rawModels.length === 0) is skipped
-// ────────────────────────────────────────────────────────────────────────────
-
-test("warm-startup: empty snapshot (rawModels.length=0) is skipped, falls through to fetch", async () => {
-  const fetcher = immediateFetcher<OmniRouteModelsFetcher>([MODEL_CLAUDE]);
-  const combosFetcher = immediateFetcher<OmniRouteCombosFetcher>([]);
-  const logger = captureWarn();
-
-  const diskSnapshotReader: OmniRouteDiskSnapshotReader = async () => ({
-    rawModels: [],
-    rawCombos: [],
-    rawAutoCombos: [],
-    rawEnrichment: new Map(),
-    rawCompressionCombos: [],
-    rawConnections: [],
-  });
-  const diskSnapshotWriter: OmniRouteDiskSnapshotWriter = async () => {};
-
-  const hook = createOmniRouteConfigHook(
-    { providerId: "omniroute" },
-    {
-      readAuthJson: authStub(),
-      fetcher,
-      combosFetcher,
-      diskSnapshotReader,
-      diskSnapshotWriter,
-      logger,
-    }
-  );
-
-  const input = makeInput();
-  await hook(input);
-
-  const entry = (input as { provider: Record<string, OmniRouteStaticProviderEntry> }).provider[
-    "opencode-omniroute"
-  ];
-  assert.ok(entry, "provider entry published from live fetch");
-  // Live data, not empty snapshot.
-  assert.ok(
-    entry.models["opencode-omniroute/claude-sonnet-4-6"],
-    "live fetch model present (empty snapshot skipped)"
-  );
-  assert.equal(fetcher.callCount(), 1, "fetcher was called (awaited cold path)");
-});

AGENTS.md

@@ -48,20 +48,20 @@ Repository map and Reference Documentation sections below.
 
 **OmniRoute** — unified AI proxy/router. One endpoint, 291 LLM providers, auto-fallback.
 
-| Layer         | Location                | Purpose                                                                                                                                                 |
-| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| API Routes    | `src/app/api/v1/`       | Next.js App Router — entry points                                                                                                                       |
-| Handlers      | `open-sse/handlers/`    | Request processing (chat, embeddings, etc)                                                                                                              |
-| Executors     | `open-sse/executors/`   | Provider-specific HTTP dispatch                                                                                                                         |
-| Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                                |
-| Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                        |
-| Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                |
-| Database      | `src/lib/db/`           | SQLite domain modules (130 migrations)                                                                                                                  |
-| Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                               |
-| MCP Server    | `open-sse/mcp-server/`  | 105 tools (42 base + memory/skill/agentSkill/pool/notion/obsidian/gamification/plugin modules), 3 transports (stdio / SSE / Streamable HTTP), 31 scopes |
-| A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                             |
-| Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                              |
-| Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                        |
+| Layer         | Location                | Purpose                                                                                                                                                                   |
+| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| API Routes    | `src/app/api/v1/`       | Next.js App Router — entry points                                                                                                                                         |
+| Handlers      | `open-sse/handlers/`    | Request processing (chat, embeddings, etc)                                                                                                                                |
+| Executors     | `open-sse/executors/`   | Provider-specific HTTP dispatch                                                                                                                                           |
+| Translators   | `open-sse/translator/`  | Format conversion (OpenAI↔Claude↔Gemini)                                                                                                                                  |
+| Transformer   | `open-sse/transformer/` | Responses API ↔ Chat Completions                                                                                                                                          |
+| Services      | `open-sse/services/`    | Combo routing, rate limits, caching, etc                                                                                                                                  |
+| Database      | `src/lib/db/`           | SQLite domain modules (130 migrations)                                                                                                                                    |
+| Domain/Policy | `src/domain/`           | Policy engine, cost rules, fallback logic                                                                                                                                 |
+| MCP Server    | `open-sse/mcp-server/`  | 109 tools (44 canonical + memory/skill/GitHub/pool/gamification/plugin/Notion/Obsidian/local-corpus/RTK modules), 3 transports (stdio / SSE / Streamable HTTP), 33 scopes |
+| A2A Server    | `src/lib/a2a/`          | JSON-RPC 2.0 agent protocol                                                                                                                                               |
+| Skills        | `src/lib/skills/`       | Extensible skill framework                                                                                                                                                |
+| Memory        | `src/lib/memory/`       | Persistent conversational memory                                                                                                                                          |
 
 Monorepo: `src/` (Next.js 16 app), `open-sse/` (streaming engine workspace), `electron/` (desktop app), `tests/`, `bin/` (CLI entry point).
 

README.md

@@ -188,7 +188,7 @@ curl http://localhost:20128/v1/chat/completions \
 
 </div>
 
-<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 291 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 291 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 105 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
+<img src="./docs/diagrams/promise-pillars.svg" width="100%" alt="The Promise — One endpoint. 291 providers. Never stop building — OmniRoute picks the cheapest one that works. Six pillars: Never hit limits (auto-fallback across 291 providers in milliseconds, zero downtime) · Save up to 95% tokens (RTK + Caveman stacked compression cuts 15–95%, ~89% avg on tool-heavy sessions) · $0 to start (90+ free tiers, 40+ free forever — no card needed) · Every tool works (33 coding agents through one config) · One endpoint (OpenAI ↔ Claude ↔ Gemini ↔ Responses API at /v1) · Production-grade (circuit breakers, TLS stealth, MCP 109 tools, A2A, memory, guardrails, evals — 25,000+ tests)."/>
 
 <br/>
 <br/>
@@ -439,7 +439,7 @@ All **19** strategies — mix & match per combo step:
 
 </div>
 
-<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 291 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 105 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
+<img src="./docs/diagrams/comparison-table.svg" width="100%" alt="What sets OmniRoute apart — comparison table vs 9router, OpenRouter, CLIProxyAPI and LiteLLM across 13 capabilities. OmniRoute: 291 providers, 90+ free providers built-in, 19 routing strategies, 12-engine token compression, built-in MCP server with 109 tools, A2A agent protocol, persistent memory, guardrails, cloud agents, TLS fingerprint stealth, Desktop/Termux/PWA, 43 i18n UI locales, 100% MIT self-hosted. OmniRoute is the only one with the full set; competitors show a mix of checks, partials and crosses. Verified from each project&apos;s docs."/>
 
 <sub>📊 Full methodology &amp; per-feature detail vs 9router, OpenRouter, CLIProxyAPI &amp; LiteLLM → [`docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md`](docs/comparison/OMNIROUTE_VS_ALTERNATIVES.md)</sub>
 
@@ -491,6 +491,25 @@ Pix copia-e-cola:
 
 <br/>
 
+## 📡 OmniRoute Radar
+
+The main free-tier headline remains **~1.53B tokens/month** from the documented,
+pool-deduplicated catalog above. Temporary provider signup credits can separately lift the first
+month to **~2.15B**. Radar is an optional, signed catalog overlay for people who want fresher
+free-model availability between OmniRoute releases; the community catalog and every existing free
+feature remain free.
+
+Supporters can receive the live catalog and additional provider opportunities. Its separate,
+mutable ceiling is **approximately 3B tokens/month at most**, depending on provider availability.
+That ceiling is not a guarantee: providers can change quotas, eligibility, models, or regions at
+any time.
+
+Radar is opt-in and GET-only. The OmniRoute client does not upload prompts, traffic, provider
+configuration, usage telemetry, or local announcement-dismiss state. Learn about eligibility and
+the current catalog at **[radar.omniroute.online/planos](https://radar.omniroute.online/planos)**.
+
+<br/>
+
 <div align="center">
 
 ## ✨ What's New
@@ -723,7 +742,7 @@ Expose OmniRoute over **MCP**, **A2A**, a **REST API**, **webhooks** or a **remo
 <table>
   <tr><th align="left">Interface</th><th align="left">Endpoint / command</th><th align="left">Use it for</th></tr>
   <tr><td align="left" nowrap>🧰 <b>MCP (stdio)</b></td><td align="left" nowrap><code>omniroute --mcp</code></td><td align="left">Plug into Claude Desktop, Cursor, any MCP client</td></tr>
-  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>105 tools</b>, 31 scopes, full audit trail</td></tr>
+  <tr><td align="left" nowrap>🌊 <b>MCP (HTTP)</b></td><td align="left" nowrap><code>/api/mcp/stream</code></td><td align="left">Remote MCP — <b>109 tools</b>, 33 scopes, full audit trail</td></tr>
   <tr><td align="left" nowrap>📡 <b>MCP (SSE)</b></td><td align="left" nowrap><code>/api/mcp/sse</code></td><td align="left">Streaming MCP transport</td></tr>
   <tr><td align="left" nowrap>🤝 <b>A2A</b></td><td align="left" nowrap><code>/.well-known/agent.json</code></td><td align="left">Agent-to-agent, <b>JSON-RPC 2.0</b> + SSE, 6 skills</td></tr>
   <tr><td align="left" nowrap>🌐 <b>REST API</b></td><td align="left" nowrap><code>/v1/*</code></td><td align="left">OpenAI-compatible — chat, embeddings, images, audio, OCR</td></tr>
@@ -1110,7 +1129,7 @@ same process on one port, so there is no separate CLI-only package today.
   <tr><th align="left">Document</th><th align="left">Description</th></tr>
   <tr><td nowrap><b><a href="docs/reference/API_REFERENCE.md">API Reference</a></b></td><td>All endpoints with examples</td></tr>
   <tr><td nowrap><b><a href="docs/openapi.yaml">OpenAPI Spec</a></b></td><td>OpenAPI 3.0 specification</td></tr>
-  <tr><td nowrap><b><a href="open-sse/mcp-server/README.md">MCP Server</a></b></td><td>104 MCP tools, IDE configs, Python/TS/Go clients</td></tr>
+  <tr><td nowrap><b><a href="open-sse/mcp-server/README.md">MCP Server</a></b></td><td>109 MCP tools, IDE configs, Python/TS/Go clients</td></tr>
   <tr><td nowrap><b><a href="docs/frameworks/MCP-SERVER.md">MCP Server Guide</a></b></td><td>MCP installation, transports, and tool reference</td></tr>
   <tr><td nowrap><b><a href="src/lib/a2a/README.md">A2A Server</a></b></td><td>JSON-RPC 2.0 protocol, skills, streaming, task mgmt</td></tr>
   <tr><td nowrap><b><a href="docs/frameworks/A2A-SERVER.md">A2A Server Guide</a></b></td><td>A2A agent card, tasks, skills, and streaming</td></tr>

bin/cli/commands/radar.mjs

@@ -0,0 +1,76 @@
+import { apiFetch } from "../api.mjs";
+import { t } from "../i18n.mjs";
+import { emit } from "../output.mjs";
+
+const statusSchema = [
+  { key: "feed", header: "Feed" },
+  { key: "available", header: "Available" },
+  { key: "version", header: "Version" },
+  { key: "tier", header: "Tier" },
+  { key: "fetchedAt", header: "Fetched" },
+];
+
+const syncSchema = [
+  { key: "feed", header: "Feed" },
+  { key: "status", header: "Status" },
+  { key: "version", header: "Version" },
+  { key: "reason", header: "Reason" },
+];
+
+function exitCodeFor(response) {
+  return Number.isInteger(response.exitCode) ? response.exitCode : response.status === 401 ? 4 : 1;
+}
+
+export async function runRadarStatusCommand(opts = {}) {
+  const response = await apiFetch("/api/radar/status", { acceptNotOk: true });
+  if (!response.ok) return exitCodeFor(response);
+  const data = await response.json();
+  if (opts.output === "json") {
+    emit(data, opts);
+    return 0;
+  }
+  const rows = Object.entries(data.feeds ?? {}).map(([feed, value]) => ({
+    feed,
+    ...(value && typeof value === "object" ? value : { available: false }),
+  }));
+  emit(rows, opts, statusSchema);
+  return 0;
+}
+
+export async function runRadarSyncCommand(opts = {}) {
+  const response = await apiFetch("/api/radar/sync-all", {
+    method: "POST",
+    body: {},
+    acceptNotOk: true,
+  });
+  if (!response.ok) return exitCodeFor(response);
+  const data = await response.json();
+  if (opts.output === "json") {
+    emit(data, opts);
+    return 0;
+  }
+  const rows = Object.entries(data).map(([feed, value]) => ({
+    feed,
+    ...(value && typeof value === "object" ? value : { status: "error" }),
+  }));
+  emit(rows, opts, syncSchema);
+  return 0;
+}
+
+export function registerRadar(program) {
+  const radar = program.command("radar").description(t("radar.description"));
+  radar
+    .command("status")
+    .description(t("radar.status"))
+    .action(async (_opts, command) => {
+      const code = await runRadarStatusCommand(command.optsWithGlobals());
+      if (code !== 0) process.exitCode = code;
+    });
+  radar
+    .command("sync")
+    .description(t("radar.sync"))
+    .action(async (_opts, command) => {
+      const code = await runRadarSyncCommand(command.optsWithGlobals());
+      if (code !== 0) process.exitCode = code;
+    });
+}

bin/cli/commands/registry.mjs

@@ -78,6 +78,7 @@ import { registerTokens } from "./tokens.mjs";
 import { registerConfigure } from "./configure.mjs";
 import { registerApiCommands } from "../api-commands/registry.mjs";
 import { registerPlugin } from "./plugin.mjs";
+import { registerRadar } from "./radar.mjs";
 
 export function registerCommands(program) {
   registerMemory(program);
@@ -161,4 +162,5 @@ export function registerCommands(program) {
   registerConfigure(program);
   registerApiCommands(program);
   registerPlugin(program);
+  registerRadar(program);
 }

bin/cli/locales/en.json

@@ -921,6 +921,11 @@
       "model": "Filter by model"
     }
   },
+  "radar": {
+    "description": "Inspect and synchronize the local Radar catalog feeds",
+    "status": "Show local Radar settings and feed cache status",
+    "sync": "Synchronize catalog, referrals, offers, and Intel through the local server"
+  },
   "resilience": {
     "description": "Inspect and manage resilience mechanisms",
     "status": {

bin/cli/locales/pt-BR.json

@@ -918,6 +918,11 @@
       "model": "Filtrar por model"
     }
   },
+  "radar": {
+    "description": "Inspecionar e sincronizar os feeds locais do catálogo Radar",
+    "status": "Mostrar configurações locais e estado dos caches do Radar",
+    "sync": "Sincronizar catálogo, indicações, ofertas e Intel pelo servidor local"
+  },
   "resilience": {
     "description": "Inspecionar e gerenciar mecanismos de resiliência",
     "status": {

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/9490-opencode-plugin-warm-startup-parallel-refresh.md

@@ -1,5 +0,0 @@
----
-feature: 9490
----
-
-**Warm catalog startup from disk snapshot + parallel refresh** (opencode-plugin): The config-shim hook now reads the last disk snapshot *before* fetching, so the provider registers immediately with the last-known-good catalog (~1-2s vs ~30s on a warm gateway). All six fetchers run concurrently via `Promise.allSettled` instead of sequentially. A failed refresh keeps the snapshot (no overwrite). An in-flight guard prevents concurrent refreshes for the same cache key. The `features.diskCache: false` opt-out disables the warm read entirely.

changelog.d/features/9830-radar-local-model-state.md

@@ -0,0 +1 @@
+- **feat(radar):** Persist local model display-name/enabled overrides and hide/restore tombstones, with authenticated catalog controls and feed safety precedence ([#9830](https://github.com/diegosouzapw/OmniRoute/pull/9830))

changelog.d/features/9836-radar-guided-combos.md

@@ -0,0 +1 @@
+- **feat(radar):** add curated-family combo suggestions, a guided combo page, and the read-only Radar MCP catalog tool ([#9836](https://github.com/diegosouzapw/OmniRoute/pull/9836))

changelog.d/features/9912-radar-supporter-offers.md

@@ -0,0 +1 @@
+- **feat(radar):** add a signed live offers feed and supporter offers dashboard ([#9912](https://github.com/diegosouzapw/OmniRoute/pull/9912))

changelog.d/features/9923-radar-intel.md

@@ -0,0 +1 @@
+- **feat(radar):** add signed Intel insights, supporter recognition, and local Radar CLI commands ([#9923](https://github.com/diegosouzapw/OmniRoute/pull/9923))

changelog.d/features/9926-radar-launch-news.md

@@ -0,0 +1 @@
+- **feat(radar):** add a localized public news feed and dismissible dashboard launch banner, with the Radar announcement staged inactive for a separately authorized launch ([#9926](https://github.com/diegosouzapw/OmniRoute/pull/9926))

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/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/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/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/9776-radar-entitlement-refresh.md

@@ -0,0 +1 @@
+- **fix(radar):** refresh signed catalog/referral caches when supporter entitlement changes, preserve the one-time live-to-community downgrade, and test real provider connection IDs from the setup tour

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))

config/quality/file-size-baseline.json

@@ -1,4 +1,7 @@
 {
+  "_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_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.",
   "_rebaseline_2026_07_25_8499_ts7_result_union_predicates": "PR #8499 (backryun, chore/ts7-types-executor-scattered) own growth: muse-spark-web.ts 1396->1405 (+9, irreducible). Under this workspace's `strictNullChecks: false`, the boolean-literal discriminant on `GraphqlResult` (`{ ok: true } | { ok: false; error: string }`) narrows the positive `.ok===true` branch but leaves `!result.ok` at the full union under TS7, making `.error` unreachable to the checker at the two call sites (warmup, mode-switch). Fixed by adding a single `isGraphqlFailure()` type-predicate helper (doc comment + 3-line body) reused at both call sites instead of duplicating the predicate inline — not extractable to a shared module without splitting a single-file executor's local narrowing helper out of its own file. Covered by the existing muse-spark-web executor test suite (no behavior change, pure narrowing fix).",
@@ -13,6 +16,7 @@
   "_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.",
@@ -157,8 +161,134 @@
   "_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.",
   "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": 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": 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": 1590,
+    "src/lib/tokenHealthCheck.ts": 1053,
+    "src/lib/db/apiKeys.ts": 1529,
+    "src/lib/db/core.ts": 1639,
+    "src/lib/db/migrationRunner.ts": 1094,
+    "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
+  },
   "testCap": 1000,
   "testFrozen": {
     "_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).",
@@ -283,134 +413,7 @@
   "_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": 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": 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": 1590,
-    "src/lib/db/apiKeys.ts": 1529,
-    "src/lib/db/core.ts": 1639,
-    "src/lib/db/migrationRunner.ts": 1094,
-    "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": 2520,
-    "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).",
@@ -418,146 +421,15 @@
   "_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_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_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_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_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": "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": "1590",
-  "src/lib/tokenHealthCheck.ts": "1053",
-  "src/lib/db/apiKeys.ts": "1529",
-  "src/lib/db/core.ts": "1639",
-  "src/lib/db/migrationRunner.ts": "1094",
-  "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_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."
 }

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                      | **Advisory** (`continue-on-error: true`) — failing until Fase 6A UI triage |
+| Suite            | Validates                                                | Blocking                                                                   |
+| ---------------- | -------------------------------------------------------- | -------------------------------------------------------------------------- |
+| `test:vitest`    | MCP server (109 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)
 

docs/architecture/REPOSITORY_MAP.md

@@ -102,7 +102,7 @@ OmniRoute/
 | **.gitleaks.toml**                          | gitleaks secret-scan ruleset                                                             |
 | **.zizmor.yml**                             | zizmor GitHub-Actions security-lint config                                               |
 | **socket.yml**                              | Socket.dev supply-chain config                                                           |
-| **news.json**                               | In-app release-notes feed (read by `src/shared/utils/releaseNotes.ts`)                   |
+| **news.json**                               | Localized v2 announcement feed; Radar launch item ships inactive                         |
 | **flake.nix** / **flake.lock**              | Nix dev-shell definition + lock                                                          |
 | **.env**                                    | Local secrets (gitignored — generated from `.env.example`)                               |
 
@@ -256,6 +256,7 @@ src/
 | `utils/circuitBreaker.ts`        | Provider circuit breaker (see `docs/architecture/RESILIENCE_GUIDE.md`) |
 | `utils/apiAuth.ts`               | API key validation, scope checking                                     |
 | `utils/fetchTimeout.ts`          | Timeout/abort wrappers for upstream fetch                              |
+| `utils/releaseNotes.ts`          | Closed v2/legacy announcement parser, localization and ID dismissal    |
 
 ---
 

docs/frameworks/MCP-SERVER.md

@@ -1,14 +1,14 @@
 ---
 title: "OmniRoute MCP Server Documentation"
-version: 3.8.40
-lastUpdated: 2026-06-28
+version: 3.8.50
+lastUpdated: 2026-08-08
 ---
 
 # OmniRoute MCP Server Documentation
 
-> Model Context Protocol server with 105 tools across routing, cache, compression, memory, skills, proxy, pool, and context source operations.
+> Model Context Protocol server with 109 tools across routing, cache, compression, memory, skills, proxy, pool, Radar, and context source operations.
 >
-> Source of truth: `open-sse/mcp-server/server.ts` computes **104 unique tools** with `countUniqueMcpTools()`: 42 canonical definitions (including the six CCR lifecycle tools and the agent-skills trio), plus memory (3), skills (4), GitHub skills (3), pool (6), gamification (8), plugins (8), Notion (6), Obsidian (22), and two RTK-only compression tools.
+> Source of truth: `open-sse/mcp-server/server.ts` computes **109 unique tools** with `countUniqueMcpTools()`: 44 canonical definitions (including the six CCR lifecycle tools, the agent-skills trio, and `omniroute_radar_catalog`), plus memory (3), skills (4), GitHub skills (3), pool (6), gamification (8), plugins (8), Notion (6), Obsidian (22), local corpus (3), and two RTK-only compression tools.
 
 ## Installation
 
@@ -64,7 +64,7 @@ Cursor, Cline, and compatible MCP client setup.
 
 ---
 
-## Essential Tools (8) — Phase 1
+## Essential Tools (13) — Phase 1
 
 | Tool                            | Scopes                | Description                                                   |
 | :------------------------------ | :-------------------- | :------------------------------------------------------------ |
@@ -72,16 +72,15 @@ Cursor, Cline, and compatible MCP client setup.
 | `omniroute_list_combos`         | `read:combos`         | All configured combos with strategies (optional metrics)      |
 | `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                      |
 | `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo                                |
+| `omniroute_create_combo`        | `write:combos`        | Create a validated combo through the existing combo API       |
 | `omniroute_check_quota`         | `read:quota`          | Quota used/total, percent remaining, reset time, token health |
 | `omniroute_route_request`       | `execute:completions` | Send a chat completion through OmniRoute routing              |
 | `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month)                |
 | `omniroute_list_models_catalog` | `read:models`         | Full model catalog with capabilities, status, pricing         |
-
-## Phase 1 — Search
-
-| Tool                   | Scopes           | Description                                                                                                                        |
-| :--------------------- | :--------------- | :--------------------------------------------------------------------------------------------------------------------------------- |
-| `omniroute_web_search` | `execute:search` | Web search through OmniRoute search gateway (Serper/Brave/Perplexity/Exa/Tavily/Google PSE/Linkup/SearchAPI/SearXNG) with failover |
+| `omniroute_radar_catalog`       | `read:radar`          | Local signed Radar catalog; optional provider/family filters  |
+| `omniroute_tool_search`         | `read:tools`          | Discover tools from the registered MCP catalog                |
+| `omniroute_web_search`          | `execute:search`      | Web search through the configured search providers            |
+| `omniroute_web_fetch`           | `execute:search`      | Fetch web content through the configured fetch providers      |
 
 ## Advanced Tools (11) — Phase 2
 
@@ -227,7 +226,7 @@ See [AGENT-SKILLS.md](./AGENT-SKILLS.md) for the full catalog and how external a
 
 ## Related Frameworks (v3.8.0)
 
-The MCP tool inventory above (104 unique tools, computed by `countUniqueMcpTools()`) is intentionally
+The MCP tool inventory above (109 unique tools, computed by `countUniqueMcpTools()`) is intentionally
 scoped to runtime routing/cache/compression/memory/skills/proxy/context-source operations. Two adjacent
 frameworks ship alongside the MCP server in v3.8.0 and are documented separately:
 
@@ -369,7 +368,7 @@ MCP tool, prompt, and resource registries can compress descriptions at registrat
 
 Description compression shrinks each tool's metadata; **tool-cardinality reduction** goes one step further by reducing _how many_ tools are announced at all. Advertising fewer tools in the `tools/list` manifest cuts the per-request token cost the client's model pays for the tool catalog ("layer 5" compression). The implementation is a pure, stateless filter in `open-sse/mcp-server/toolCardinality.ts` (`reduceToolManifest`), wired into the registration loop in `createMcpServer()` (`open-sse/mcp-server/server.ts`).
 
-**Opt-in, off by default.** The filter only runs when at least one of two environment variables is set; with neither set, all 105 tools are announced unchanged.
+**Opt-in, off by default.** The filter only runs when at least one of two environment variables is set; with neither set, all 109 tools are announced unchanged.
 
 | Variable         | Mode                                                                                    |
 | :--------------- | :-------------------------------------------------------------------------------------- |

docs/frameworks/RADAR.md

@@ -1,13 +1,13 @@
 ---
 title: "Radar Free-Model Catalog"
 version: 3.8.50
-lastUpdated: 2026-08-07
+lastUpdated: 2026-08-09
 ---
 
 # Radar Free-Model Catalog
 
 > **Source of truth:** `src/lib/radar/`, `src/lib/db/radar.ts`, `src/app/api/radar/`
-> **Last updated:** 2026-08-07 — v3.8.50
+> **Last updated:** 2026-08-09 — v3.8.50
 
 Radar is an **optional add-on** that overlays a signed, freshly-curated free-model
 catalog on top of the release baseline (`FREE_MODEL_BUDGETS` in
@@ -15,11 +15,54 @@ catalog on top of the release baseline (`FREE_MODEL_BUDGETS` in
 faster than release cadence — providers add, shrink, or discontinue free quotas between
 releases, and the baseline catalog can only be refreshed when a new version ships.
 
-**Nothing that is free today stops being free.** Radar never removes or paywalls a
-baseline entry; it only refreshes limits/status fields at read time and can layer in
-newly-discovered free models between releases. The baseline catalog itself is never
-mutated on disk — see [Read-time overlay merge rules](#read-time-overlay-merge-rules)
-below.
+**Nothing that is free today stops being free because of the remote feed.** Radar never
+paywalls a baseline entry; it only refreshes limits/status fields at read time and can
+layer in newly-discovered free models between releases. An operator can still hide a
+model locally, and can restore it from the same dashboard. The baseline catalog itself
+is never mutated on disk — see
+[Read-time overlay merge rules](#read-time-overlay-merge-rules) below.
+
+---
+
+## Delivery status in v3.8.50
+
+The following status distinguishes what this OSS release implements from later Radar
+workstreams. It is a code-level status, not a promise that a particular hosted deployment
+or external integration is currently available.
+
+| Area                             | Status in this release                                                                                                                                                                                                 |
+| -------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Signed catalog client            | Implemented behind `RADAR_ENABLED`, with separate opt-in, Ed25519 verification, local encrypted settings/cache, persistent display/enabled overrides, reversible tombstones, scheduler, and dashboard.                 |
+| Contributor activation           | The dashboard links to the server-hosted GitHub claim flow and accepts an existing `omr_…` key. Contributor eligibility is resolved by the private service; the OSS client contains no GitHub token or issuance logic. |
+| Supporter-key activation         | Implemented. The raw key is validated, encrypted at rest, masked on reads, and sent only by server-side sync. Changing or clearing the key invalidates all four entitlement-sensitive feed caches.                     |
+| Referral links                   | Implemented as a separately signed, hourly-refreshed feed. Fixed links are available to the community tier immediately; limited campaigns remain live-tier data.                                                       |
+| Supporter offers                 | Implemented as a separate signed, live-only feed and dashboard page. The client revalidates the closed benefit schema, preserves the last good cache, filters expired entries, and labels partner offers explicitly.   |
+| Intel and supporter recognition  | Implemented as a strict signed live-only feed with Radar-owned ELO, factual catalog freshness/trend, a verified local supporter badge, dashboard page, and local-only CLI status/sync commands.                        |
+| Payments and transactional email | Not implemented in the OSS client. Purchase, donation, receipt review, and mail delivery belong to the private service and its later operational workstream.                                                           |
+| Research-agent workstream        | Not part of this client release. Curated feed contents remain server-side data; no autonomous research agent runs in an OmniRoute installation.                                                                        |
+
+---
+
+## Public announcement reader
+
+The generic announcement reader is separate from the Radar feature flag. The dashboard Home and
+Changelog viewer fetch the repository's public `news.json` through a plain `GET` to
+`NEWS_JSON_URL` (`src/shared/utils/releaseNotes.ts`). They send no Radar setting, prompt, provider
+configuration, usage record, or local dismissal state.
+
+`news.json` uses the closed v2 schema implemented by `parseNewsPayload()`:
+
+- `schemaVersion: 2` and a bounded `items[]` collection;
+- stable, unique announcement `id` values;
+- explicit `active` and ISO `publishedAt` fields;
+- required English copy with optional localized copy;
+- optional credential-free HTTPS links and an allowlisted icon;
+- newest-active-first selection, locale fallback to English, and per-ID local dismissal.
+
+The parser temporarily accepts the former singular `{ active, title, message, ... }` shape so
+older forks can migrate without a broken Changelog view. Invalid feeds are inert. The Radar launch
+entry ships with `active: false`; changing it to `true` is a separate post-merge, post-deploy
+release action and does not change `RADAR_ENABLED` or the independent feed-sync opt-in.
 
 ---
 
@@ -31,15 +74,16 @@ Radar is gated end-to-end by the `RADAR_ENABLED` feature flag
 
 **When the flag is off, the surface does not exist:**
 
-- `GET /api/radar/catalog`, `POST /api/radar/sync`, `POST /api/radar/settings` all
+- All `/api/radar/*` endpoints, including local model-state reads and writes,
   return `404` before touching any Radar module.
-- The dashboard screens (`/dashboard/radar`, `/dashboard/radar/setup`) render
+- The dashboard screens (`/dashboard/radar`, `/dashboard/radar/setup`,
+  `/dashboard/radar/combos`, `/dashboard/radar/offers`, `/dashboard/radar/intel`) render
   `notFound()`.
 - `getRadarCatalog()` (`src/lib/radar/index.ts`) returns the untouched baseline —
   same entry count, same values, every entry tagged `origin: "baseline"` — and never
   reads the feed cache.
-- No network call is ever made; `syncRadar()` (`src/lib/radar/sync.ts`) returns
-  `{ status: "disabled" }` at step 1 without touching `fetch`.
+- No Radar network call is ever made; each sync module returns `{ status: "disabled" }`
+  before touching `fetch`.
 
 This is a strict superset gate: flipping the flag on unlocks the _screens_, nothing
 more. It does not upload data, does not start a background sync, and does not change
@@ -67,7 +111,9 @@ When both are on, the sync path is:
    plain, unauthenticated-by-default GET. OmniRoute never posts usage data, provider
    configuration, or model traffic to the feed service.
 3. The response is verified, validated, and cached locally (see
-   [Security model](#security-model)). Nothing else touches the network for Radar.
+   [Security model](#security-model)). Radar has exactly four server-side network paths:
+   `syncRadar()` for the catalog, `syncRadarReferrals()` for referrals, and
+   `syncRadarOffers()` / `syncRadarIntel()` for supporter-only offers and Intel.
 
 The **supporter key** is an optional Bearer token (`radar_settings.supporter_key`)
 that lets the feed service decide which tier to serve (see
@@ -77,6 +123,9 @@ that lets the feed service decide which tier to serve (see
   helpers (`src/lib/db/encryption.ts`) used for provider credentials.
 - Set via `POST /api/radar/settings` (`{ supporterKey: "omr_" + 40 hex chars }`) and
   **never echoed back** — the response returns a masked form (`omr_****abcd`).
+- Changing or clearing it atomically invalidates the catalog, referrals, offers, and Intel caches. The
+  next sync/read resolves the new entitlement server-side; saving a key does not itself make
+  a network request or consume a single-use activation key.
 - Sent to the feed service as a Bearer token on the sync GET — nothing else about the
   key ever leaves the client.
 
@@ -102,10 +151,10 @@ pattern as `RADAR_FEED_URL`) and relayed to the dashboard through the existing
 `GET /api/radar/settings` response (`contributorClaimUrl`, `supporterPlansUrl`) — the
 client component never reads `process.env` itself.
 
-| Var                             | Purpose                                                                                      |
-| -------------------------------- | ---------------------------------------------------------------------------------------------- |
-| `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`).          |
+| Var                           | Purpose                                                                                     |
+| ----------------------------- | ------------------------------------------------------------------------------------------- |
+| `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
@@ -117,7 +166,7 @@ as a UX nicety; the server's Zod schema is the authoritative check either way. O
 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
+remain the way to _obtain_ a key in the first place; this input is where an operator
 who already has one activates it.
 
 ---
@@ -207,11 +256,11 @@ handle.
 ### The served tier comes from a response header, not the signed body
 
 The signed feed **body**'s `tier` field is always `"live"` — the feed service ships
-**one signed artifact per version**, so the body cannot carry a per-request tier
-without invalidating the Ed25519 signature (re-signing per request would defeat the
-point of a pinned, cacheable, verifiable artifact). The tier actually served for a
-given request is instead carried in the **`x-omniroute-feed-tier` response header**,
-decided server-side from the request's `Authorization` key.
+**two signed artifacts per version**: live includes current campaigns and community
+omits them. Each artifact is signed over its own exact bytes. The body still does not
+serve as the entitlement decision; the tier actually selected for a request is carried
+in the **`x-omniroute-feed-tier` response header**, decided server-side from the request's
+`Authorization` key.
 
 `syncRadar()` (`src/lib/radar/sync.ts::parseServedTierHeader()`) is the single place
 that resolves the tier a client should trust:
@@ -223,7 +272,7 @@ that resolves the tier a client should trust:
 2. Fall back to the signed body's `tier` field (always `"live"`) only when step 1
    yields nothing.
 3. The resolved tier is what gets cached and returned as `{ status: "updated",
-   version, tier }` — this is the value the dashboard shows, never the raw body
+version, tier }` — this is the value the dashboard shows, never the raw body
    field.
 
 ---
@@ -250,6 +299,44 @@ Four rules, in order of precedence:
    entry (`tombstones` set), the feed re-adding that `provider:modelId` in a later
    version does not bring it back.
 
+The editable fields and tombstones are persisted in
+`radar_local_model_state` (migration `143_radar_local_model_state.sql`). The public DB
+adapter (`src/lib/db/radar.ts`) converts those rows into the `localOverrides` map and
+`tombstones` set used by `applyFeed()`; production `getRadarCatalog()` loads that state
+after the flag, cache, and schema gates pass. Only `displayName` and `enabled` are
+operator-editable. Provider/model identity, feed provenance, quota, capabilities, ToS,
+and setup data cannot be written through this surface.
+
+The dashboard exposes four local actions:
+
+- **Edit** changes the local display name and enabled state.
+- **Reset local changes** clears both editable fields without changing a tombstone.
+- **Hide** creates a tombstone, so later feed updates cannot recreate the row.
+- **Restore** removes the tombstone; any separately-saved override remains in effect.
+
+A feed `enabled: false` remains the safety exception: it wins over a stale local
+`enabled: true`, keeps the merged entry disabled, and records `disabledBy: "radar"`.
+
+### Guided combos and MCP access
+
+Confirmed `familyId` values survive the read-time overlay and drive the pure
+`buildRadarComboSuggestions()` module (`src/lib/radar/comboSuggestions.ts`). A family is suggested
+only when at least two distinct providers have active connections and expose the exact curated model
+ID. Disabled models, inactive providers, missing model IDs, singleton families, and ambiguous
+alias/prefix matches fail closed. Suggestions use the existing `priority` strategy, ordering the
+largest recurring monthly budget first; the UI creates them only through `POST /api/combos`.
+
+The guided UI lives at `/dashboard/radar/combos`. It reads only the local
+`GET /api/radar/catalog` and `GET /api/combos/builder/options` endpoints. It never triggers Radar sync,
+reads provider credentials, or writes directly to the combo database.
+
+MCP clients can read the same local projection with `omniroute_radar_catalog` (`read:radar`). The
+optional `provider`, `familyId`, and `enabledOnly` filters are evaluated after one local
+`GET /api/radar/catalog` read. Its closed output includes catalog metadata plus provider/model,
+display name, `familyId`, quota, capabilities, enabled state, origin, and `disabledBy`; setup URLs,
+steps, connections, e-mail addresses, keys, and referral data are never returned. This tool is
+read-only and never invokes `/api/radar/sync`.
+
 ### Provenance markers
 
 Every merged entry carries an `origin` field the UI renders as a badge:
@@ -263,30 +350,41 @@ Every merged entry carries an `origin` field the UI renders as a badge:
 
 ## Local surfaces — never a feed proxy
 
-Five local routes back the UI, all under `src/app/api/radar/`:
+The local Radar route families below back the UI under `src/app/api/radar/`:
 
-| Route                   | Method | Purpose                                                                                          |
-| ----------------------- | ------ | -------------------------------------------------------------------------------------------------- |
-| `/api/radar/catalog`    | GET    | Returns the merged catalog (`getRadarCatalog()`) from the local cache.                            |
-| `/api/radar/sync`       | POST   | Triggers `syncRadar()` server-side; returns the resulting status.                                 |
-| `/api/radar/settings`   | GET    | Returns `{ optIn, hasSupporterKey, supporterKeyMasked }` — never the raw key.                     |
-| `/api/radar/settings`   | POST   | Sets opt-in and/or the (encrypted) supporter key.                                                 |
-| `/api/radar/referrals`  | GET    | Returns `{ fixed, campaigns, tier }` from the local cache — see [Referral links](#referral-links-free-credits) below. |
+| Route                          | Method | Purpose                                                                                                               |
+| ------------------------------ | ------ | --------------------------------------------------------------------------------------------------------------------- |
+| `/api/radar/catalog`           | GET    | Returns the merged catalog (`getRadarCatalog()`) from the local cache.                                                |
+| `/api/radar/sync`              | POST   | Triggers `syncRadar()` server-side; returns the resulting status.                                                     |
+| `/api/radar/settings`          | GET    | Returns `{ optIn, hasSupporterKey, supporterKeyMasked }` — never the raw key.                                         |
+| `/api/radar/settings`          | POST   | Sets opt-in and/or the (encrypted) supporter key.                                                                     |
+| `/api/radar/referrals`         | GET    | Returns `{ fixed, campaigns, tier }` from the local cache — see [Referral links](#referral-links-free-credits) below. |
+| `/api/radar/offers`            | GET    | Returns active offers from the verified local live cache; never returns the supporter key.                            |
+| `/api/radar/offers/sync`       | POST   | Triggers the server-side, live-key-only `syncRadarOffers()` pipeline.                                                 |
+| `/api/radar/intel`             | GET    | Returns verified local live Intel plus a supporter-recognition boolean; never an identity or key.                     |
+| `/api/radar/intel/sync`        | POST   | Triggers the server-side, live-key-only `syncRadarIntel()` pipeline.                                                  |
+| `/api/radar/status`            | GET    | Returns read-only local settings/cache status for catalog, referrals, offers, and Intel, without secrets.             |
+| `/api/radar/sync-all`          | POST   | Runs all four server-side sync modules and returns a separate status for each feed.                                   |
+| `/api/radar/local-model-state` | GET    | Lists persisted overrides and tombstones for edit/restore controls.                                                   |
+| `/api/radar/local-model-state` | PATCH  | Sets or clears the validated `displayName`/`enabled` override fields.                                                 |
+| `/api/radar/local-model-state` | PUT    | Creates or removes a tombstone with `{ provider, modelId, tombstoned }`.                                              |
+| `/api/radar/local-model-state` | DELETE | Clears editable override fields while preserving any tombstone.                                                       |
 
 **Hard rule: these routes never proxy the feed service.** The browser only ever talks
-to the local OmniRoute server; `syncRadar()` is the single module in the whole client
-that touches the network for Radar (`src/lib/radar/sync.ts`), and it always runs
-server-side, never client-side. This keeps the feed URL and any supporter key
-out of client-facing network traffic entirely.
+to the local OmniRoute server. The four modules that touch the Radar service are
+`src/lib/radar/sync.ts` (catalog), `src/lib/radar/referralsSync.ts` (referrals), and
+`src/lib/radar/offersSync.ts` (offers) plus `src/lib/radar/intelSync.ts` (Intel); all run
+server-side, never client-side. This keeps
+the feed URL and any supporter key out of client-facing network traffic entirely.
 
-All five routes return `404` when `RADAR_ENABLED` is off (see
+All Radar endpoints return `404` when `RADAR_ENABLED` is off (see
 [Flag](#flag-radar_enabled-default-off) above), and route error responses through
 `buildErrorBody()`/`sanitizeErrorMessage()` per the repo-wide error-sanitization rule
 (`docs/security/ERROR_SANITIZATION.md`).
 
 ### Authentication
 
-All five routes require authentication via `isAuthenticated()`
+All Radar endpoints require authentication via `isAuthenticated()`
 (`src/shared/utils/apiAuth.ts`) — a dashboard session cookie or a management-scoped
 API key, the same gate that protects the rest of `/api/settings/*`. The flag-off
 `404` check always runs **before** the auth check, so an install with `RADAR_ENABLED`
@@ -297,6 +395,58 @@ auth state — only the masked form and a `hasSupporterKey` boolean.
 
 ---
 
+## Supporter offers
+
+Offers use their own signed artifact, `GET /v1/offers/latest`, and never share the catalog or
+referrals cache. The server endpoint requires a valid live supporter Bearer key; there is no
+community fallback. `syncRadarOffers()` therefore stops before the network when the feature flag is
+off, the operator has not opted in, or no supporter key is configured.
+
+After a successful GET, the client verifies the Ed25519 signature over the exact response bytes,
+validates `RadarOffersFeedSchema`, requires both the signed body and
+`x-omniroute-feed-tier` header to say `live`, enforces a strictly newer dotted version, and only then
+atomically replaces `radar_offers_cache` (migration `144_radar_offers_cache.sql`). The same 10 MB
+header-plus-stream cap used by the other feeds applies. Signature, schema, tier, replay, size, HTTP,
+and network failures all preserve the last verified cache.
+
+The closed offer shape supports three comparable benefit types: percentage in basis points, credit
+in minor currency units, or trial days. A partner offer must include a same-kind public baseline and
+its benefit must be strictly greater; official offers have no partner baseline. URLs must be
+credential-free HTTPS. `getRadarOffers()` defensively revalidates the cached payload and filters
+expired entries on every local read; `/dashboard/radar/offers` filters expiry again before rendering,
+uses Portuguese text when available with English fallback, and labels partner offers explicitly.
+
+The browser calls only local routes: it reads the masked settings snapshot, asks
+`POST /api/radar/offers/sync` to refresh server-side, then reads `GET /api/radar/offers`. Without a
+key it shows the existing contributor/support links instead of attempting a feed request. External
+offer links open in a new tab with `noopener noreferrer`. No `radar_offers` MCP tool is exposed in
+this release.
+
+---
+
+## Radar Intel, supporter badge, and CLI
+
+Intel is a signed artifact at `GET /v1/intel/latest`. The closed `RadarIntelFeedSchema` accepts
+only Radar-owned ELO rankings derived by the private curator from confirmed comparisons and factual
+catalog age/count deltas derived from signed catalog snapshots. The methodology is fixed at initial
+rating 1000 and K=32. An empty ranking is valid when no comparison has been confirmed; the client
+never synthesizes one.
+
+`syncRadarIntel()` applies the same server-side Bearer, 30-second timeout, 10 MiB streamed cap,
+exact-byte Ed25519 verification, strict schema, `live` body/header requirement, version floor, and
+last-good-cache preservation as offers. After a verified live snapshot is persisted, the client
+derives `radar:<sha256(supporter key)>`, stores only that one-way identity, and emits the dedicated
+`radar_supporter` recognition event. Its `radar-supporter` badge is idempotent and awards zero XP;
+it never updates leaderboards or reuses `token_share`. `/dashboard/radar/intel` renders the badge
+only from verified local cache metadata.
+
+The CLI exposes `omniroute radar status` and `omniroute radar sync`. Both communicate only with the
+local OmniRoute API. `status` performs a read-only `GET /api/radar/status`; `sync` sends one
+`POST /api/radar/sync-all` and prints a result per feed. Neither command reads, accepts, or prints
+the supporter key, and neither contacts the Radar service directly.
+
+---
+
 ## Referral links (free credits)
 
 Referral links are served from a **standalone, always-current** feed —
@@ -348,11 +498,13 @@ touches the network for referrals, mirroring `syncRadar()`'s contract exactly: f
 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`.
+catalog's `radar_feed_cache`. A 10 MB response cap and a `generatedAt` floor reject an
+incoming feed older than the cached one, guarding against replay of an older signed
+artifact. An equal timestamp is accepted: the server intentionally gives the community
+and live referral variants the same deterministic `generatedAt`, so the signed payload
+and served tier can change after a supporter-key change without the underlying link set
+changing. 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:
@@ -475,11 +627,24 @@ instead of failing the rest of the page. To also offer referral links, serve
 (`src/lib/radar/referralsFeedSchema.ts`) and sign it with the same Ed25519 key pair as
 the catalog feed.
 
+Supporter offers are another optional artifact. To serve them, implement
+`GET /v1/offers/latest` with the closed `RadarOffersFeedSchema`
+(`src/lib/radar/offersFeedSchema.ts`), require live entitlement, return
+`x-omniroute-feed-tier: live`, and sign the exact bytes with the same key. A fork that omits this
+endpoint keeps the catalog/referrals behavior unchanged; offer refresh fails non-destructively and
+the last verified local offer cache remains available.
+
+Intel is optional in the same way. A self-hoster can serve `GET /v1/intel/latest` using
+`RadarIntelFeedSchema` (`src/lib/radar/intelFeedSchema.ts`), require live entitlement, return
+`x-omniroute-feed-tier: live`, and sign the exact bytes with the shared Ed25519 key. Omitting the
+endpoint leaves catalog, referrals, and offers unchanged; Intel refresh preserves any last verified
+local snapshot.
+
 ---
 
 ## Related docs
 
 - [`docs/security/ERROR_SANITIZATION.md`](../security/ERROR_SANITIZATION.md) — the
-  error-response pattern the five `/api/radar/*` routes follow.
+  error-response pattern the `/api/radar/*` routes follow.
 - [`docs/reference/ENVIRONMENT.md`](../reference/ENVIRONMENT.md#27-radar-feed-self-hosting)
   — `RADAR_FEED_URL` / `RADAR_FEED_PUBKEY` reference.

docs/ops/RELEASE_CHECKLIST.md

@@ -65,6 +65,7 @@ directly from anywhere — CI can only stage; only the owner's 2FA releases.
 as the default reflex (minutes, reversible); `npm unpublish` only inside the 72h/no-dependents
 window and never as the first move. Docker: never rewrite a version tag — rollback is
 repointing `latest` to the last good digest.
+
 ## Hotfix Fast-Lane (label `hotfix`)
 
 A PR labeled `hotfix` skips the heavy CI matrix (9-shard E2E, coverage ratchet,
@@ -276,6 +277,22 @@ Deploy skills use the light rsync flow — no `npm pack`, no `npm i -g`:
 - [ ] Open milestone for next version
 - [ ] If critical: pin discussion or post in `news.json` for in-app banner
 
+### Radar public-launch gate
+
+The Radar announcement is intentionally committed with `active: false`. Activation is a separate
+change after every item below is evidenced:
+
+- [ ] All stacked Radar PRs are merged and the release-tip CI is green
+- [ ] Deploy and smoke the OSS Radar routes with `RADAR_ENABLED` still off by default
+- [ ] Smoke `GET /planos`, `/termos`, `/privacidade`, and `/reembolso` on the named Radar host
+- [ ] Record operator identity/contact/address and owner-approved legal review in the private service
+- [ ] Exercise Stripe Checkout and the signed webhook in test mode only
+- [ ] Exercise one encrypted transactional-email delivery with the approved sender/domain
+- [ ] Prove backup restore and one supervised, budget-capped research run
+- [ ] Approve the BRL/PIX review policy before accepting donation evidence
+- [ ] Enable public Checkout only after the preceding gates, then activate the new `news.json` ID
+- [ ] Verify the Home banner uses localized copy and a new ID reappears after an older ID is dismissed
+
 ## Embedded Services smoke (v3.8.4+)
 
 Before shipping any release that includes embedded services changes, verify:

docs/reference/ENVIRONMENT.md

@@ -1292,9 +1292,14 @@ self-hosted or forked feed / supporter-key flow instead of the default OmniRoute
 Radar service. See [docs/frameworks/RADAR.md](../frameworks/RADAR.md) for the full
 module doc.
 
+The generic Home/Changelog announcement reader is not configured by an environment
+variable and does not depend on the RADAR_ENABLED feature flag. It reads the public repository
+`news.json` URL declared in `src/shared/utils/releaseNotes.ts` by
+GET only; dismissal IDs remain in browser local storage.
+
 | Variable                       | Default                                          | Source File                   | Description                                                                                     |
 | -------------------------------- | --------------------------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------ |
-| `RADAR_FEED_URL`               | `https://radar.omniroute.online`                 | `src/lib/radar/sync.ts`       | Base URL of the Radar feed service. Override to point at a self-hosted or forked feed.          |
+| `RADAR_FEED_URL`               | `https://radar.omniroute.online`                 | `src/lib/radar/{sync,referralsSync,offersSync,intelSync}.ts` | Base URL shared by the separately signed catalog, referrals, supporter-offers, and Intel feeds. Override to point at a self-hosted or forked service. |
 | `RADAR_FEED_PUBKEY`            | _(pinned default key)_                           | `src/lib/radar/pinnedKeys.ts` | Ed25519 public key (base64-DER SPKI or PEM) used to verify feed signatures from a custom feed.   |
 | `RADAR_CONTRIBUTOR_CLAIM_URL`  | `https://radar.omniroute.online/auth/github`     | `src/lib/radar/links.ts`      | URL the "I'm a contributor" dashboard button opens (GitHub OAuth supporter-key claim flow).      |
 | `RADAR_SUPPORTER_PLANS_URL`    | `https://radar.omniroute.online/planos`          | `src/lib/radar/links.ts`      | URL the "Support the project" dashboard button opens (payment/plans page).                       |

news.json

@@ -1,8 +1,43 @@
 {
-  "active": false,
-  "title": "Novidade no Omniverse",
-  "message": "Está lançado hoje o tOmni, o terminal interativo múltiplo para Agentes de AI! Experimente a nova interface focada em produtividade para desenvolvedores.",
-  "link": "https://github.com/diegosouzapw/tOmni",
-  "linkLabel": "Conhecer o tOmni",
-  "icon": "campaign"
+  "schemaVersion": 2,
+  "items": [
+    {
+      "id": "radar-launch-2026-08",
+      "active": false,
+      "publishedAt": "2026-08-09T00:00:00.000Z",
+      "text": {
+        "en": {
+          "title": "OmniRoute Radar",
+          "message": "An opt-in, GET-only free-model catalog overlay with no telemetry from the OmniRoute client.",
+          "linkLabel": "Learn about Radar"
+        },
+        "pt-BR": {
+          "title": "OmniRoute Radar",
+          "message": "Um catálogo opcional de modelos gratuitos, somente GET e sem telemetria enviada pelo cliente OmniRoute.",
+          "linkLabel": "Conheça o Radar"
+        }
+      },
+      "link": "https://radar.omniroute.online/planos",
+      "icon": "radar"
+    },
+    {
+      "id": "tomni-launch-2026-07",
+      "active": false,
+      "publishedAt": "2026-07-01T00:00:00.000Z",
+      "text": {
+        "en": {
+          "title": "New in the Omniverse",
+          "message": "tOmni is an interactive multi-agent terminal focused on developer productivity.",
+          "linkLabel": "Meet tOmni"
+        },
+        "pt-BR": {
+          "title": "Novidade no Omniverse",
+          "message": "O tOmni é um terminal interativo para múltiplos agentes, focado na produtividade de desenvolvedores.",
+          "linkLabel": "Conhecer o tOmni"
+        }
+      },
+      "link": "https://github.com/diegosouzapw/tOmni",
+      "icon": "campaign"
+    }
+  ]
 }

open-sse/config/audioRegistry.ts

@@ -603,7 +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/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/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/executors/gemini-web.ts

@@ -14,13 +14,9 @@
  */
 
 import { BaseExecutor, type ExecuteInput } from "./base.ts";
-import { buildErrorBody, sanitizeErrorMessage } from "../utils/error.ts";
+import { sanitizeErrorMessage } from "../utils/error.ts";
 import { prepareToolMessages } from "../translator/webTools.ts";
 import { buildToolModeResponse } from "./chatgptWebTools.ts";
-import {
-  checkGeminiWebUnsupportedControls,
-  GEMINI_WEB_UNSUPPORTED_CONTROL_CODE,
-} from "./gemini-web/capabilities.ts";
 
 // ─── Constants ──────────────────────────────────────────────────────────────
 
@@ -410,33 +406,6 @@ export class GeminiWebExecutor extends BaseExecutor {
     const { model, body, stream, credentials, signal, log, onCredentialsRefreshed } = input;
     const requestBody = body as GeminiRequestBody;
 
-    // #9356: fail fast on controls this provider cannot honor (reasoning_effort
-    // above "minimal", forced tool_choice). Runs before the credential check and
-    // before Playwright launches — the request is unservable no matter which
-    // cookie is used, and answering 200 with ordinary prose made agents believe
-    // their reasoning/tool requirements had been met. See ./gemini-web/capabilities.ts.
-    const violation = checkGeminiWebUnsupportedControls(body as Record<string, unknown>);
-    if (violation) {
-      log?.warn?.(
-        "GEMINI-WEB",
-        `Rejected request: "${violation.param}" is not supported by this provider`
-      );
-      return {
-        response: new Response(
-          JSON.stringify(
-            buildErrorBody(400, violation.message, null, {
-              type: "invalid_request_error",
-              code: GEMINI_WEB_UNSUPPORTED_CONTROL_CODE,
-            })
-          ),
-          { status: 400, headers: { "Content-Type": "application/json" } }
-        ),
-        url: GEMINI_URL,
-        headers: {},
-        transformedBody: body,
-      };
-    }
-
     const cookie = resolveGeminiWebCookie(credentials);
     if (!cookie) {
       return {

open-sse/executors/gemini-web/capabilities.ts

@@ -1,121 +0,0 @@
-/**
- * Request-contract guards for the Gemini Web executor (#9356).
- *
- * gemini-web is not an API client. It launches Playwright, types ONE flat
- * prompt string into the gemini.google.com `.ql-editor` contenteditable,
- * presses Enter, and captures the first `StreamGenerate` response off the page
- * (see ../gemini-web.ts). There is no JSON request body on the wire, which
- * makes two OpenAI controls structurally impossible to honor:
- *
- *   • `reasoning_effort` — no field exists to carry a thinking budget. Unlike
- *     deepseek-web or perplexity-web, which post a real payload and can flip a
- *     `thinking_enabled` flag or swap the model preference, there is nothing
- *     here to set.
- *   • forced `tool_choice` — the tools support gemini-web does have is the
- *     prompt-emulation shim (`translator/webTools.ts`, #7286): it ASKS the
- *     model, in prose, to answer with `<tool>{...}</tool>` and parses whatever
- *     comes back. That is best-effort by construction. "required" / "any" /
- *     a named function is a GUARANTEE, and a prompt cannot make one.
- *
- * Before this module both were accepted and quietly ignored, so an agent got a
- * 200 with `finish_reason: "stop"`, no `reasoning_content`, and `tool_calls: []`
- * and concluded its requirements had been met (#9356). Failing the request is
- * the honest answer: the caller can drop the control, or route to a model that
- * actually implements it.
- *
- * Deliberately NOT rejected — these are already satisfied or already work:
- *   • `reasoning_effort: "none" | "minimal"` — asking for as little reasoning as
- *     possible is something a non-thinking provider trivially complies with.
- *   • `tool_choice: "auto" | "none"` and plain `tools[]` — the #7286 emulation
- *     path, which several shipped combos depend on (#5240, #8488). Untouched.
- *
- * Pure and dependency-free so the whole contract is unit-testable without a
- * browser.
- */
-
-/** `error.code` on every compatibility rejection raised here. */
-export const GEMINI_WEB_UNSUPPORTED_CONTROL_CODE = "unsupported_control_for_provider";
-
-/** Effort levels a non-thinking provider already complies with. */
-const SATISFIED_EFFORT_LEVELS = new Set(["none", "minimal"]);
-
-/** `tool_choice` strings that demand a tool call rather than merely offering one. */
-const FORCING_TOOL_CHOICE_STRINGS = new Set(["required", "any"]);
-
-/** `tool_choice: { type }` values that pin the model to a specific/any tool. */
-const FORCING_TOOL_CHOICE_TYPES = new Set(["function", "tool", "any"]);
-
-export interface GeminiWebCapabilityViolation {
-  /** Which request field could not be honored. */
-  param: "reasoning_effort" | "tool_choice";
-  /** Client-facing explanation — already safe to put in a response body. */
-  message: string;
-}
-
-function normalizeString(value: unknown): string | null {
-  return typeof value === "string" && value.trim().length > 0 ? value.trim().toLowerCase() : null;
-}
-
-/**
- * True when `tool_choice` demands a tool call. Covers the OpenAI strings
- * ("required"), the Anthropic-flavored ones the translators also emit ("any"),
- * and the object forms that name a function or force any tool. "auto" / "none"
- * and every unrecognized shape are treated as non-forcing — this guard only
- * blocks contracts it is certain gemini-web cannot keep.
- */
-export function isForcingToolChoice(toolChoice: unknown): boolean {
-  const asString = normalizeString(toolChoice);
-  if (asString) return FORCING_TOOL_CHOICE_STRINGS.has(asString);
-
-  if (toolChoice && typeof toolChoice === "object" && !Array.isArray(toolChoice)) {
-    const type = normalizeString((toolChoice as Record<string, unknown>).type);
-    return type !== null && FORCING_TOOL_CHOICE_TYPES.has(type);
-  }
-
-  return false;
-}
-
-/** True when `reasoning_effort` asks for MORE thinking than "none at all". */
-export function requestsThinkingBudget(reasoningEffort: unknown): boolean {
-  const effort = normalizeString(reasoningEffort);
-  if (effort === null) return false;
-  return !SATISFIED_EFFORT_LEVELS.has(effort);
-}
-
-/**
- * Inspect an OpenAI-shaped request body for controls gemini-web cannot honor.
- * Returns the first violation found, or `null` when the request is servable.
- *
- * `reasoning_effort` is checked before `tool_choice` only for determinism; a
- * request carrying both is rejected either way.
- */
-export function checkGeminiWebUnsupportedControls(
-  body: Record<string, unknown> | null | undefined
-): GeminiWebCapabilityViolation | null {
-  if (!body || typeof body !== "object") return null;
-
-  if (requestsThinkingBudget(body.reasoning_effort)) {
-    return {
-      param: "reasoning_effort",
-      message:
-        'Model provider "gemini-web" does not support "reasoning_effort". It drives the ' +
-        "gemini.google.com web UI through a typed prompt and has no thinking-budget control " +
-        'to set, so any effort above "minimal" would be silently ignored. Remove ' +
-        '"reasoning_effort" (or send "none"/"minimal") or route to a reasoning-capable model.',
-    };
-  }
-
-  if (isForcingToolChoice(body.tool_choice)) {
-    return {
-      param: "tool_choice",
-      message:
-        'Model provider "gemini-web" cannot guarantee a forced tool call. Its tool support is ' +
-        "prompt-emulated — the model is asked to emit a tool block and may answer with prose " +
-        'instead — so "tool_choice" values that require one ("required", "any", or a named ' +
-        'function) cannot be honored. Use "auto" to keep best-effort tool calling, or route to ' +
-        "a model with native function calling.",
-    };
-  }
-
-  return null;
-}

open-sse/executors/lmarena/response.ts

@@ -7,8 +7,6 @@ import { isCloudflareChallenge } from "../../services/lmarenaTlsClient.ts";
 import { markLMArenaCatalogModelDead } from "./models.ts";
 import { parseArenaSSE } from "./stream.ts";
 
-const encoder = new TextEncoder();
-
 export function errorResponse(
   status: number,
   message: string,
@@ -167,7 +165,7 @@ function baseChunk(model: string) {
 }
 
 function enqueueSse(controller: ReadableStreamDefaultController, chunk: Record<string, unknown>) {
-  controller.enqueue(encoder.encode(`data: ${JSON.stringify(chunk)}\n\n`));
+  controller.enqueue(new TextEncoder().encode(`data: ${JSON.stringify(chunk)}\n\n`));
 }
 
 function emitStopAndDone(controller: ReadableStreamDefaultController, model: string) {
@@ -175,8 +173,7 @@ function emitStopAndDone(controller: ReadableStreamDefaultController, model: str
     ...baseChunk(model),
     choices: [{ index: 0, delta: {}, finish_reason: "stop" }],
   });
-
-  controller.enqueue(encoder.encode("data: [DONE]\n\n"));
+  controller.enqueue(new TextEncoder().encode("data: [DONE]\n\n"));
   controller.close();
 }
 

open-sse/mcp-server/README.md

@@ -1,6 +1,6 @@
 # OmniRoute MCP Server
 
-> **Model Context Protocol server** that exposes OmniRoute's gateway intelligence as **104 tools** for AI agents.
+> **Model Context Protocol server** that exposes OmniRoute's gateway intelligence as **109 tools** for AI agents.
 >
 > **Source of truth for the full tool catalog and REST surface:** [`docs/frameworks/MCP-SERVER.md`](../../docs/frameworks/MCP-SERVER.md). This README focuses on architecture, configuration, and integration examples; the catalog below is a summary subset.
 
@@ -20,7 +20,7 @@ The MCP Server allows any AI agent (Claude Desktop, Cursor, VS Code Copilot, cus
 ┌──────────────────────────────────────────────────────────────────┐
 │                      OmniRoute MCP Server                        │
 │  ┌──────────────┐  ┌─────────────────┐  ┌────────────────────┐  │
-│  │ Scope        │  │ 104 MCP Tools   │  │   Audit Logger     │  │
+│  │ Scope        │  │ 109 MCP Tools   │  │   Audit Logger     │  │
 │  │ Enforcement  │──│ (core + memory  │──│   (SHA-256/SQLite) │  │
 │  │              │  │  + skills + …)  │  │                    │  │
 │  └──────────────┘  └────────┬────────┘  └────────────────────┘  │
@@ -120,18 +120,23 @@ omniroute --mcp
 
 ## Tool Reference
 
-### Phase 1: Essential Tools (8)
+### Phase 1: Essential Tools (13)
 
 | #   | Tool                            | Scopes                | Description                                                                |
 | --- | ------------------------------- | --------------------- | -------------------------------------------------------------------------- |
-| 1   | `omniroute_get_health`          | `read:health`         | Gateway health, uptime, memory, circuit breakers, rate limits, cache stats |
-| 2   | `omniroute_list_combos`         | `read:combos`         | List all combos (model chains) with strategies and optional metrics        |
-| 3   | `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                                   |
-| 4   | `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo for routing                                 |
-| 5   | `omniroute_check_quota`         | `read:quota`          | Remaining API quota per provider with token health status                  |
-| 6   | `omniroute_route_request`       | `execute:completions` | Send a chat completion through intelligent routing                         |
-| 7   | `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month) with per-provider breakdown |
-| 8   | `omniroute_list_models_catalog` | `read:models`         | List all available models across providers with capabilities and pricing   |
+| 1   | `omniroute_tool_search`         | `read:tools`          | Discover tools from the registered MCP catalog                             |
+| 2   | `omniroute_get_health`          | `read:health`         | Gateway health, uptime, memory, circuit breakers, rate limits, cache stats |
+| 3   | `omniroute_list_combos`         | `read:combos`         | List all combos (model chains) with strategies and optional metrics        |
+| 4   | `omniroute_get_combo_metrics`   | `read:combos`         | Performance metrics for a specific combo                                   |
+| 5   | `omniroute_switch_combo`        | `write:combos`        | Activate or deactivate a combo for routing                                 |
+| 6   | `omniroute_create_combo`        | `write:combos`        | Create a validated combo through the existing combo API                    |
+| 7   | `omniroute_check_quota`         | `read:quota`          | Remaining API quota per provider with token health status                  |
+| 8   | `omniroute_route_request`       | `execute:completions` | Send a chat completion through intelligent routing                         |
+| 9   | `omniroute_cost_report`         | `read:usage`          | Cost report by period (session/day/week/month) with per-provider breakdown |
+| 10  | `omniroute_list_models_catalog` | `read:models`         | List all available models across providers with capabilities and pricing   |
+| 11  | `omniroute_radar_catalog`       | `read:radar`          | Read the local signed Radar catalog with provider/family filters           |
+| 12  | `omniroute_web_search`          | `execute:search`      | Search the web through configured search providers                         |
+| 13  | `omniroute_web_fetch`           | `execute:search`      | Fetch web content through configured fetch providers                       |
 
 ### Phase 2: Advanced Tools (8)
 

open-sse/mcp-server/__tests__/essentialTools.test.ts

@@ -1,7 +1,7 @@
 /**
  * Unit tests for MCP Essential Tools (Phase 1)
  *
- * Tests all 10 essential tool handlers via the tool handler functions.
+ * Tests the essential tool handlers via the tool handler functions.
  * The omniroute_web_search tests use InMemoryTransport + Client to exercise
  * the actual registered handler (not mockFetch directly).
  */
@@ -22,10 +22,10 @@ describe("MCP Essential Tools", () => {
   });
 
   describe("Tool schema validation", () => {
-    it("should have exactly 12 essential tools (includes web_search + web_fetch + tool_search)", () => {
-      // 11 -> 12: #8925 shipped omniroute_create_combo as a phase-1 tool.
+    it("should have exactly 13 essential tools (including Radar catalog)", () => {
+      // 12 -> 13: F3 shipped omniroute_radar_catalog as a phase-1 read-only tool.
       const schemas = MCP_ESSENTIAL_TOOLS;
-      expect(schemas).toHaveLength(12);
+      expect(schemas).toHaveLength(13);
     });
 
     it("all tools should have omniroute_ prefix", () => {

open-sse/mcp-server/__tests__/radarCatalogTool.test.ts

@@ -0,0 +1,151 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
+import { Client } from "@modelcontextprotocol/sdk/client/index.js";
+import { InMemoryTransport } from "@modelcontextprotocol/sdk/inMemory.js";
+
+import { MCP_SCOPE_LIST, MCP_TOOL_SCOPES } from "../../../src/shared/constants/mcpScopes.ts";
+import { evaluateToolScopes } from "../scopeEnforcement.ts";
+import { getMcpRadarCatalog } from "../radarCatalog.ts";
+import { MCP_ESSENTIAL_TOOLS, MCP_TOOL_MAP } from "../schemas/tools.ts";
+import { createMcpServer } from "../server.ts";
+
+vi.mock("../audit.ts", () => ({
+  logToolCall: vi.fn().mockResolvedValue(undefined),
+}));
+
+const catalog = {
+  entries: [
+    {
+      provider: "groq",
+      modelId: "llama",
+      displayName: "Llama on Groq",
+      familyId: "llama-family",
+      monthlyTokens: 200,
+      creditTokens: 0,
+      freeType: "recurring-daily",
+      poolKey: null,
+      tos: "ok",
+      enabled: true,
+      origin: "radar",
+      capabilities: { tools: true, vision: false, thinking: false },
+      limits: { rpm: 30, rpd: null, tpm: null, tpd: null },
+      setup: { keyUrl: "https://secret.example/key", steps: ["do not expose"] },
+    },
+    {
+      provider: "cerebras",
+      modelId: "llama",
+      displayName: "Llama on Cerebras",
+      familyId: "llama-family",
+      monthlyTokens: 300,
+      creditTokens: 0,
+      freeType: "recurring-daily",
+      poolKey: null,
+      tos: "ok",
+      enabled: false,
+      disabledBy: "radar",
+      origin: "radar",
+      capabilities: { tools: true, vision: false, thinking: true },
+      limits: { rpm: null, rpd: 100, tpm: null, tpd: null },
+    },
+  ],
+  meta: { version: "2026.08.08.1", tier: "community", fetchedAt: "2026-08-08T20:00:00Z" },
+};
+
+describe("omniroute_radar_catalog", () => {
+  it("is a phase-1 read-only registry tool with the dedicated Radar scope", () => {
+    const definition = MCP_TOOL_MAP.omniroute_radar_catalog;
+    expect(definition).toBeDefined();
+    expect(definition.phase).toBe(1);
+    expect(definition.scopes).toEqual(["read:radar"]);
+    expect(definition.auditLevel).toBe("none");
+    expect(definition.sourceEndpoints).toEqual(["/api/radar/catalog"]);
+    expect(MCP_ESSENTIAL_TOOLS).toContain(definition);
+    expect(MCP_SCOPE_LIST).toContain("read:radar");
+    expect(MCP_TOOL_SCOPES.omniroute_radar_catalog).toEqual(["read:radar"]);
+  });
+
+  it("reads only the local catalog and returns a closed filtered projection", async () => {
+    const fetchJson = vi.fn().mockResolvedValue(catalog);
+    const result = await getMcpRadarCatalog(
+      { provider: "groq", familyId: "llama-family", enabledOnly: true },
+      { fetchJson }
+    );
+
+    expect(fetchJson).toHaveBeenCalledOnce();
+    expect(fetchJson).toHaveBeenCalledWith("/api/radar/catalog");
+    expect(result.models).toHaveLength(1);
+    expect(result.models[0]).toEqual({
+      provider: "groq",
+      modelId: "llama",
+      displayName: "Llama on Groq",
+      familyId: "llama-family",
+      quota: {
+        monthlyTokens: 200,
+        creditTokens: 0,
+        freeType: "recurring-daily",
+        limits: { rpm: 30, rpd: null, tpm: null, tpd: null },
+      },
+      capabilities: { tools: true, vision: false, thinking: false },
+      enabled: true,
+      origin: "radar",
+      disabledBy: null,
+    });
+    expect(JSON.stringify(result)).not.toContain("secret.example");
+    expect(JSON.stringify(result)).not.toContain("setup");
+  });
+
+  it("defaults enabledOnly to true and includes disabled models only when explicitly requested", async () => {
+    const fetchJson = vi.fn().mockResolvedValue(catalog);
+    expect((await getMcpRadarCatalog({}, { fetchJson })).models).toHaveLength(1);
+    expect((await getMcpRadarCatalog({ enabledOnly: false }, { fetchJson })).models).toHaveLength(
+      2
+    );
+  });
+
+  it("allows read:radar and read:* but denies a missing scope when enforcement is active", () => {
+    expect(evaluateToolScopes("omniroute_radar_catalog", ["read:radar"], true).allowed).toBe(true);
+    expect(evaluateToolScopes("omniroute_radar_catalog", ["read:*"], true).allowed).toBe(true);
+    expect(evaluateToolScopes("omniroute_radar_catalog", [], true)).toMatchObject({
+      allowed: false,
+      reason: "missing_scopes",
+      missing: ["read:radar"],
+    });
+  });
+});
+
+describe("omniroute_radar_catalog MCP dispatch", () => {
+  const mockFetch = vi.fn();
+  let client: Client;
+
+  beforeEach(async () => {
+    mockFetch.mockReset();
+    vi.stubGlobal("fetch", mockFetch);
+    const [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair();
+    const server = createMcpServer();
+    await server.connect(serverTransport);
+    client = new Client({ name: "radar-catalog-test", version: "1.0.0" });
+    await client.connect(clientTransport);
+  });
+
+  afterEach(async () => {
+    await client.close();
+    vi.unstubAllGlobals();
+  });
+
+  it("registers and dispatches a real read without sync or write", async () => {
+    mockFetch.mockResolvedValueOnce({ ok: true, json: async () => catalog });
+
+    const listed = await client.listTools();
+    expect(listed.tools.some((tool) => tool.name === "omniroute_radar_catalog")).toBe(true);
+
+    const result = await client.callTool({
+      name: "omniroute_radar_catalog",
+      arguments: { enabledOnly: false },
+    });
+    expect(result.isError).toBeFalsy();
+    expect(mockFetch).toHaveBeenCalledOnce();
+    expect(mockFetch.mock.calls[0][0]).toContain("/api/radar/catalog");
+    expect(mockFetch.mock.calls[0][1]).not.toMatchObject({ method: "POST" });
+    const body = JSON.parse((result.content[0] as { text: string }).text);
+    expect(body.models).toHaveLength(2);
+  });
+});

open-sse/mcp-server/radarCatalog.ts

@@ -0,0 +1,170 @@
+import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
+
+import { logToolCall } from "./audit.ts";
+import { radarCatalogInput, radarCatalogOutput } from "./schemas/radarCatalog.ts";
+import type { McpToolExtraLike } from "./scopeEnforcement.ts";
+import type { TextToolResult } from "./toolResult.ts";
+import { sanitizeErrorMessage } from "../utils/error.ts";
+
+type JsonRecord = Record<string, unknown>;
+
+type ScopeEnforcer = (
+  toolName: string,
+  handler: (args: unknown, extra?: McpToolExtraLike) => Promise<TextToolResult>,
+  toolScopes?: readonly string[]
+) => (args: unknown, extra?: McpToolExtraLike) => Promise<TextToolResult>;
+
+export interface McpRadarCatalogArgs {
+  provider?: string;
+  familyId?: string;
+  enabledOnly?: boolean;
+}
+
+interface McpRadarCatalogDeps {
+  fetchJson?: (path: string) => Promise<unknown>;
+}
+
+function record(value: unknown): JsonRecord {
+  return value !== null && typeof value === "object" && !Array.isArray(value)
+    ? (value as JsonRecord)
+    : {};
+}
+
+function text(value: unknown, fallback = ""): string {
+  return typeof value === "string" ? value : fallback;
+}
+
+function number(value: unknown): number {
+  return typeof value === "number" && Number.isFinite(value) && value >= 0 ? value : 0;
+}
+
+function nullableNumber(value: unknown): number | null {
+  return typeof value === "number" && Number.isFinite(value) && value >= 0 ? value : null;
+}
+
+function normalizeMeta(
+  value: unknown
+): { version: string; tier: string; fetchedAt: string } | null {
+  const meta = record(value);
+  if (
+    typeof meta.version !== "string" ||
+    typeof meta.tier !== "string" ||
+    typeof meta.fetchedAt !== "string"
+  ) {
+    return null;
+  }
+  return { version: meta.version, tier: meta.tier, fetchedAt: meta.fetchedAt };
+}
+
+function normalizeEntry(value: unknown) {
+  const entry = record(value);
+  const provider = text(entry.provider).trim();
+  const modelId = text(entry.modelId).trim();
+  if (!provider || !modelId) return null;
+
+  const capabilities = record(entry.capabilities);
+  const limits = record(entry.limits);
+  const origin =
+    entry.origin === "radar" || entry.origin === "local" ? entry.origin : ("baseline" as const);
+  return {
+    provider,
+    modelId,
+    displayName: text(entry.displayName, modelId),
+    familyId: typeof entry.familyId === "string" ? entry.familyId : null,
+    quota: {
+      monthlyTokens: number(entry.monthlyTokens),
+      creditTokens: number(entry.creditTokens),
+      freeType: text(entry.freeType, "unknown"),
+      limits:
+        Object.keys(limits).length > 0
+          ? {
+              rpm: nullableNumber(limits.rpm),
+              rpd: nullableNumber(limits.rpd),
+              tpm: nullableNumber(limits.tpm),
+              tpd: nullableNumber(limits.tpd),
+            }
+          : null,
+    },
+    capabilities:
+      Object.keys(capabilities).length > 0
+        ? {
+            tools: capabilities.tools === true,
+            vision: capabilities.vision === true,
+            thinking: capabilities.thinking === true,
+          }
+        : null,
+    enabled: entry.enabled !== false,
+    origin,
+    disabledBy: entry.disabledBy === "radar" ? ("radar" as const) : null,
+  };
+}
+
+function compareEntries(
+  left: NonNullable<ReturnType<typeof normalizeEntry>>,
+  right: NonNullable<ReturnType<typeof normalizeEntry>>
+): number {
+  return left.provider.localeCompare(right.provider) || left.modelId.localeCompare(right.modelId);
+}
+
+/** Read and project the local Radar catalog without exposing setup or secret-bearing state. */
+export async function getMcpRadarCatalog(
+  args: McpRadarCatalogArgs,
+  deps: McpRadarCatalogDeps = {}
+) {
+  const fetchJson =
+    deps.fetchJson ??
+    ((path: string) => import("./server.ts").then((module) => module.omniRouteFetch(path)));
+  const raw = record(await fetchJson("/api/radar/catalog"));
+  const providerFilter = args.provider?.trim().toLowerCase();
+  const familyFilter = args.familyId?.trim().toLowerCase();
+  const enabledOnly = args.enabledOnly !== false;
+  const entries = Array.isArray(raw.entries) ? raw.entries : [];
+  const models = entries
+    .map(normalizeEntry)
+    .filter((entry): entry is NonNullable<typeof entry> => entry !== null)
+    .filter((entry) => !enabledOnly || entry.enabled)
+    .filter((entry) => !providerFilter || entry.provider.toLowerCase() === providerFilter)
+    .filter((entry) => !familyFilter || entry.familyId?.toLowerCase() === familyFilter)
+    .sort(compareEntries);
+
+  return { meta: normalizeMeta(raw.meta), models };
+}
+
+async function handleRadarCatalog(args: {
+  provider?: string;
+  familyId?: string;
+  enabledOnly: boolean;
+}): Promise<TextToolResult> {
+  const start = Date.now();
+  try {
+    const result = radarCatalogOutput.parse(await getMcpRadarCatalog(args));
+    await logToolCall(
+      "omniroute_radar_catalog",
+      args,
+      { modelCount: result.models.length },
+      Date.now() - start,
+      true
+    );
+    return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }] };
+  } catch (error) {
+    const message = sanitizeErrorMessage(error) || "Failed to read Radar catalog";
+    await logToolCall("omniroute_radar_catalog", args, null, Date.now() - start, false, message);
+    return { content: [{ type: "text", text: `Error: ${message}` }], isError: true };
+  }
+}
+
+export function registerRadarCatalogTool(
+  server: McpServer,
+  withScopeEnforcement: ScopeEnforcer
+): void {
+  server.registerTool(
+    "omniroute_radar_catalog",
+    {
+      description: "Reads the local signed Radar catalog with optional provider and family filters",
+      inputSchema: radarCatalogInput,
+    },
+    withScopeEnforcement("omniroute_radar_catalog", (args) =>
+      handleRadarCatalog(radarCatalogInput.parse(args))
+    )
+  );
+}

open-sse/mcp-server/schemas/index.ts

@@ -91,6 +91,8 @@ export {
   ccrStatsTool,
 } from "./tools.ts";
 
+export { radarCatalogInput, radarCatalogOutput, radarCatalogTool } from "./radarCatalog.ts";
+
 // A2A schemas
 export {
   AgentCardSchema,

open-sse/mcp-server/schemas/radarCatalog.ts

@@ -0,0 +1,65 @@
+import { z } from "zod";
+
+import type { McpToolDefinition } from "./toolDefinition.ts";
+
+export const radarCatalogInput = z.object({
+  provider: z.string().trim().min(1).max(100).optional().describe("Filter by provider id"),
+  familyId: z.string().trim().min(1).max(120).optional().describe("Filter by curated family id"),
+  enabledOnly: z.boolean().default(true).describe("Exclude models disabled by the Radar feed"),
+});
+
+const radarLimitOutput = z.object({
+  rpm: z.number().nullable(),
+  rpd: z.number().nullable(),
+  tpm: z.number().nullable(),
+  tpd: z.number().nullable(),
+});
+
+export const radarCatalogOutput = z.object({
+  meta: z
+    .object({
+      version: z.string(),
+      tier: z.string(),
+      fetchedAt: z.string(),
+    })
+    .nullable(),
+  models: z.array(
+    z.object({
+      provider: z.string(),
+      modelId: z.string(),
+      displayName: z.string(),
+      familyId: z.string().nullable(),
+      quota: z.object({
+        monthlyTokens: z.number(),
+        creditTokens: z.number(),
+        freeType: z.string(),
+        limits: radarLimitOutput.nullable(),
+      }),
+      capabilities: z
+        .object({
+          tools: z.boolean(),
+          vision: z.boolean(),
+          thinking: z.boolean(),
+        })
+        .nullable(),
+      enabled: z.boolean(),
+      origin: z.enum(["baseline", "radar", "local"]),
+      disabledBy: z.literal("radar").nullable(),
+    })
+  ),
+});
+
+export const radarCatalogTool: McpToolDefinition<
+  typeof radarCatalogInput,
+  typeof radarCatalogOutput
+> = {
+  name: "omniroute_radar_catalog",
+  description:
+    "Reads the local signed Radar catalog with optional provider and curated-family filters. Never syncs or writes data.",
+  inputSchema: radarCatalogInput,
+  outputSchema: radarCatalogOutput,
+  scopes: ["read:radar"],
+  auditLevel: "none",
+  phase: 1,
+  sourceEndpoints: ["/api/radar/catalog"],
+};

open-sse/mcp-server/schemas/tools.ts

@@ -1,5 +1,5 @@
 /**
- * MCP Tool Schemas — Contracts for all 23 core and advanced OmniRoute MCP tools.
+ * MCP Tool Schemas — Contracts for the canonical OmniRoute MCP tools.
  *
  * Defines input/output Zod schemas, descriptions, scopes, and audit levels
  * for both essential (Phase 1) and advanced (Phase 2) MCP tools.
@@ -13,11 +13,11 @@ import { z } from "zod";
 import { toolSearchTool } from "./toolSearch.ts";
 import { pickFastestModelTool } from "./pickFastestModel.ts";
 import { CCR_MCP_TOOLS } from "./ccrTools.ts";
+import { radarCatalogTool } from "./radarCatalog.ts";
 import {
   AUTO_ROUTING_STRATEGY_VALUES,
   ROUTING_STRATEGY_VALUES,
 } from "../../../src/shared/constants/routingStrategies.ts";
-
 // ============ Shared Types ============
 // AuditLevel + McpToolDefinition live in the leaf ./toolDefinition.ts so that
 // toolSearch.ts can import the type without forming a tools.ts ↔ toolSearch.ts cycle.
@@ -26,8 +26,7 @@ export type { AuditLevel, McpToolDefinition } from "./toolDefinition.ts";
 import type { McpToolDefinition } from "./toolDefinition.ts";
 export { pickFastestModelInput, pickFastestModelOutput } from "./pickFastestModel.ts";
 export * from "./ccrTools.ts";
-
-// ============ Phase 1: Essential Tools (8) ============
+// ============ Phase 1: Essential Tools ============
 
 // --- Tool 1: omniroute_get_health ---
 export const getHealthInput = z.object({}).describe("No parameters required");
@@ -432,7 +431,7 @@ export const listModelsCatalogTool: McpToolDefinition<
   sourceEndpoints: ["/api/models/catalog", "/v1/models"],
 };
 
-// --- Tool 9: omniroute_web_search ---
+// --- Tool 10: omniroute_web_search ---
 export const webSearchInput = z.object({
   query: z
     .string()
@@ -1512,6 +1511,7 @@ export const MCP_TOOLS = [
   routeRequestTool,
   costReportTool,
   listModelsCatalogTool,
+  radarCatalogTool,
   webSearchTool,
   webFetchTool,
   simulateRouteTool,

open-sse/mcp-server/server.ts

@@ -93,6 +93,8 @@ import { normalizeQuotaResponse } from "../../src/shared/contracts/quota.ts";
 import { resolveOmniRouteBaseUrl } from "../../src/shared/utils/resolveOmniRouteBaseUrl.ts";
 import { sanitizeErrorMessage } from "../utils/error.ts";
 import { getMcpModelsCatalog } from "./catalog.ts";
+import { registerRadarCatalogTool } from "./radarCatalog.ts";
+import type { TextToolResult } from "./toolResult.ts";
 export { getMcpModelsCatalog } from "./catalog.ts";
 
 const OMNIROUTE_BASE_URL = resolveOmniRouteBaseUrl();
@@ -146,11 +148,6 @@ function readMcpAccessibilityConfig(): McpAccessibilityConfig {
   }
 }
 
-type TextToolResult = {
-  content: Array<{ type: "text"; text: string }>;
-  isError?: boolean;
-};
-
 function toRecord(value: unknown): JsonRecord {
   return value && typeof value === "object" && !Array.isArray(value) ? (value as JsonRecord) : {};
 }
@@ -815,6 +812,8 @@ export function createMcpServer(): McpServer {
     )
   );
 
+  registerRadarCatalogTool(server, withScopeEnforcement);
+
   server.registerTool(
     "omniroute_simulate_route",
     {

open-sse/mcp-server/toolResult.ts

@@ -0,0 +1,4 @@
+export type TextToolResult = {
+  content: Array<{ type: "text"; text: string }>;
+  isError?: boolean;
+};

open-sse/services/backgroundTaskDetector.ts

@@ -190,31 +190,15 @@ export function getBackgroundTaskReason(
   const messages = toMessageArray(typedBody.messages ?? typedBody.input ?? []);
   if (!Array.isArray(messages) || messages.length === 0) return null;
 
-  // Derive system content from messages array (OpenAI format) or top-level
-  // system field (Anthropic format).
+  // Find system message
   const systemMsg = messages.find(
     (message: BackgroundMessage) => message.role === "system" || message.role === "developer"
   );
-  let systemContent = "";
-  if (systemMsg && typeof systemMsg.content === "string") {
-    systemContent = systemMsg.content.toLowerCase();
-  } else if (!systemMsg) {
-    // Anthropic top-level system field: string or array of text blocks
-    const raw = (typedBody as Record<string, unknown>).system;
-    if (typeof raw === "string") {
-      systemContent = raw.toLowerCase();
-    } else if (Array.isArray(raw)) {
-      systemContent = raw
-        .map((part) =>
-          part && typeof (part as { text?: unknown }).text === "string"
-            ? (part as { text: string }).text
-            : ""
-        )
-        .filter(Boolean)
-        .join(" ")
-        .toLowerCase();
-    }
-  }
+  if (!systemMsg) return null;
+
+  const systemContent =
+    typeof systemMsg.content === "string" ? systemMsg.content.toLowerCase() : "";
+
   if (!systemContent) return null;
 
   // Check against detection patterns

open-sse/services/combo/validateQuality.ts

@@ -190,26 +190,10 @@ function isRecord(value: unknown): value is Record<string, unknown> {
   return !!value && typeof value === "object" && !Array.isArray(value);
 }
 
-/**
- * Whether an `error` field carries a real failure signal. A key-presence check
- * (`!= null`) false-positives on benign values some backends emit on every
- * chunk (`{}`, `""`, `false`, `0`) — e.g. tool-call turns where a chunk with
- * real tool_calls content also carries `"error": {}`. Only substantive values
- * are treated as upstream failures.
- */
-function isSubstantiveError(value: unknown): boolean {
-  if (value === null || value === undefined) return false;
-  if (typeof value === "string") return value.trim().length > 0;
-  if (typeof value === "object" && !Array.isArray(value)) {
-    return Object.keys(value as Record<string, unknown>).length > 0;
-  }
-  return value === true;
-}
-
 function isStreamingUpstreamError(parsed: unknown, eventType: string): boolean {
   if (eventType === "response.failed" || eventType === "error") return true;
   if (!isRecord(parsed)) return false;
-  if (isSubstantiveError(parsed.error)) return true;
+  if (parsed.error != null) return true;
 
   const nestedResponse = isRecord(parsed.response) ? parsed.response : null;
   return nestedResponse?.status === "failed" && nestedResponse.error != null;

open-sse/translator/request/openai-responses.ts

@@ -724,7 +724,7 @@ export function openaiResponsesToOpenAIRequest(
     const reasoningRec = toRecord(root.reasoning);
     const effort = toString(reasoningRec.effort);
     if (effort && result.reasoning_effort === undefined) {
-      result.reasoning_effort = normalizeResponsesReasoningEffort(effort, model ?? root.model);
+      result.reasoning_effort = normalizeResponsesReasoningEffort(effort, model);
     }
     if (
       credentialRecord._copilotClient === true &&

open-sse/translator/response/gemini-to-claude.ts

@@ -112,7 +112,7 @@ export function geminiToClaudeResponse(chunk, state) {
         // When the toolNameMap provides a match (e.g., lowercase "bash" → "Bash"),
         // use it directly without passing through normalizeToolName(), which would
         // reverse TitleCase back to lowercase via REVERSE_MAP (#9568).
-        const restoredToolName = mappedName ?? normalizeToolName(rawToolName);
+        const restoredToolName = mappedName || normalizeToolName(rawToolName);
         const idx = state.contentBlockIndex++;
         const toolId = fc.id || `toolu_${Date.now()}_${idx}`;
 

open-sse/translator/response/openai-responses.ts

@@ -874,7 +874,6 @@ function openaiResponsesToOpenAIResponseStream(chunk, state) {
     if (state.currentToolCallId) state.toolCallIdsSeen.add(state.currentToolCallId);
 
     const toolName = normalizeToolName(item.name);
-    state.currentToolName = toolName; // track for schema lookup at done time
     if (!toolName) {
       // Some Responses providers briefly emit placeholder/empty tool names.
       // Defer emission until output_item.done in case the final name is populated there.
@@ -920,9 +919,26 @@ function openaiResponsesToOpenAIResponseStream(chunk, state) {
     state.currentToolCallArgsBuffer = (state.currentToolCallArgsBuffer || "") + argsDelta;
     if (state.currentToolCallDeferred) return null;
 
-    // #9168: buffer arguments until output_item.done for schema-aware null normalization
-    // Previously emitted raw null values for optional enum fields (e.g. isolation: null).
-    return null;
+    return {
+      id: state.chatId,
+      object: "chat.completion.chunk",
+      created: state.created,
+      model: state.model || "gpt-4",
+      choices: [
+        {
+          index: 0,
+          delta: {
+            tool_calls: [
+              {
+                index: state.toolCallIndex,
+                function: { arguments: argsDelta },
+              },
+            ],
+          },
+          finish_reason: null,
+        },
+      ],
+    };
   }
 
   // Function call done — emit args chunk from item.arguments when no deltas were received,
@@ -995,35 +1011,6 @@ function openaiResponsesToOpenAIResponseStream(chunk, state) {
     if (item.arguments != null && !buffered) {
       const argsToEmit = stripEmptyOptionalToolArgs(item.arguments, toolName, toolSchema);
 
-      const argsStr = typeof argsToEmit === "string" ? argsToEmit : JSON.stringify(argsToEmit);
-      if (argsStr) {
-        return {
-          id: state.chatId,
-          object: "chat.completion.chunk",
-          created: state.created,
-          model: state.model || "gpt-4",
-          choices: [
-            {
-              index: 0,
-              delta: {
-                tool_calls: [
-                  {
-                    index: currentIndex,
-                    function: { arguments: argsStr },
-                  },
-                ],
-              },
-              finish_reason: null,
-            },
-          ],
-        };
-      }
-    } else if (buffered) {
-      // #9168: deltas were buffered — normalize against the original client schema
-      // and emit the cleaned arguments once, stripping optional null values that
-      // would otherwise reach the client raw.
-      const argsToEmit = stripEmptyOptionalToolArgs(buffered, toolName, toolSchema);
-
       const argsStr = typeof argsToEmit === "string" ? argsToEmit : JSON.stringify(argsToEmit);
       if (argsStr) {
         return {

open-sse/utils/sseHeartbeat.ts

@@ -79,8 +79,7 @@ export function sseCommentsEnabled(): boolean {
   if (typeof process === "undefined") return true;
   const v = process.env.OMNIROUTE_SSE_COMMENTS;
   if (v === undefined || v === "") return true;
-  const normalized = v.trim().toLowerCase();
-  return normalized !== "off" && normalized !== "false" && normalized !== "0" && normalized !== "no";
+  return v.trim().toLowerCase() !== "off";
 }
 
 export function createSseHeartbeatTransform({

open-sse/utils/stream.ts

@@ -25,7 +25,6 @@ import {
 } from "./streamHelpers.ts";
 import { calculateCost } from "@/lib/usage/costCalculator";
 import { buildOmniRouteSseMetadataComment } from "@/domain/omnirouteResponseMeta";
-import { sseCommentsEnabled } from "./sseHeartbeat.ts";
 import {
   createStructuredSSECollector,
   buildStreamSummaryFromEvents,
@@ -1002,11 +1001,6 @@ export function createSSEStream(options: StreamOptions = {}) {
     controller: TransformStreamDefaultController,
     finalUsage: UsageTokenRecord | Record<string, unknown> | null | undefined
   ) => {
-    // Skip SSE metadata comment lines when OMNIROUTE_SSE_COMMENTS is disabled
-    // (e.g., "off", "false", "0", "no"). Strict OpenAI-compatible clients that
-    // JSON.parse every SSE line will crash on `: x-omniroute-*` comment lines.
-    if (!sseCommentsEnabled()) return;
-
     const costUsd = finalUsage ? await calculateCost(provider, model, finalUsage) : 0;
     const comment = buildOmniRouteSseMetadataComment({
       provider,

package.json

@@ -34,11 +34,8 @@
     "scripts/dev/tls-options.mjs",
     "scripts/check/check-supported-node-runtime.ts",
     "scripts/dev/sync-env.mjs",
-    "scripts/build/assembleStandalone.mjs",
-    "scripts/build/backendOnlyPages.mjs",
-    "scripts/build/build-next-isolated.mjs",
-    "scripts/build/build-tproxy-native.mjs",
     "scripts/build/native-binary-compat.mjs",
+    "scripts/build/build-next-isolated.mjs",
     "scripts/build/runtime-env.mjs",
     "README.md",
     "LICENSE",

scripts/build/assembleStandalone.mjs

@@ -89,15 +89,6 @@ const NATIVE_ASSET_ENTRIES = [
     src: ["node_modules", "better-sqlite3", "build"],
     dest: ["node_modules", "better-sqlite3", "build"],
   },
-  {
-    // #8847: Bun (and npx -g global installs) resolve better-sqlite3's native
-    // binary from prebuilds/ instead of build/Release/, so the compiled build/
-    // copy alone leaves a hollow package that falls back to sql.js (OOM under
-    // Bun). Ship the prebuilds alongside the compiled binary.
-    label: "better-sqlite3 prebuilds (Bun / global installs)",
-    src: ["node_modules", "better-sqlite3", "prebuilds"],
-    dest: ["node_modules", "better-sqlite3", "prebuilds"],
-  },
   {
     // TPROXY IP_TRANSPARENT addon (Fase 3 / Epic A). Built by build-tproxy-native
     // before assembly; Linux-only + opt-in, so the source is absent on non-Linux

scripts/build/colocateOptionals.mjs

@@ -47,8 +47,7 @@
  */
 
 import { cpSync, existsSync, mkdirSync, readFileSync } from "node:fs";
-import { createRequire } from "node:module";
-import { dirname, join, sep } from "node:path";
+import { dirname, join } from "node:path";
 
 /**
  * Entry packages of the SLM optional stack (the closure roots). `@huggingface/transformers` is
@@ -97,33 +96,6 @@ export function computeDependencyClosure(nodeModulesDir, seeds = SEED_PACKAGES)
   return closure;
 }
 
-/**
- * A package in the target tree counts as PRESENT only when its entrypoint
- * resolves from inside that tree — the same contract the Dockerfile's
- * post-build guard enforces. Next's file tracing can materialize a package
- * PARTIALLY (the package.json lands, the files its `main` points at do not),
- * and a directory-level `existsSync` check then skips the package forever
- * while the runtime dies with "Cannot find module <pkg>/dist/index.js".
- *
- * @param {string} targetNodeModulesDir
- * @param {string} name
- * @returns {boolean}
- */
-function isPackageIntact(targetNodeModulesDir, name) {
-  if (!existsSync(join(targetNodeModulesDir, name))) return false;
-  try {
-    const probe = createRequire(
-      join(targetNodeModulesDir, "__colocate_probe__.js")
-    );
-    const resolved = probe.resolve(name);
-    // A resolution that walked past the target into an ancestor tree does not
-    // prove the target copy is usable.
-    return resolved.startsWith(targetNodeModulesDir + sep);
-  } catch {
-    return false;
-  }
-}
-
 /**
  * Co-locate the SLM optional dependency closure from `<rootDir>/node_modules`
  * into a standalone bundle's `node_modules`.
@@ -170,12 +142,11 @@ export function colocateLlmlinguaOptionals({
 
   const closure = computeDependencyClosure(rootNm, seeds);
 
-  // Check the complete closure rather than only the entry package, and judge
-  // presence by entrypoint integrity — a partially traced directory (see
-  // isPackageIntact) must still receive its missing files.
+  // Check the complete closure rather than only the entry package. A partially
+  // populated bundle must still receive any missing transitive dependencies.
   if (
     closure.length > 0 &&
-    closure.every((name) => isPackageIntact(targetNm, name))
+    closure.every((name) => existsSync(join(targetNm, name)))
   ) {
     return { skipped: true, reason: "already co-located" };
   }
@@ -184,18 +155,11 @@ export function colocateLlmlinguaOptionals({
 
   for (const name of closure) {
     const dest = join(targetNm, name);
-    if (isPackageIntact(targetNm, name)) continue;
+    if (existsSync(dest)) continue;
 
     try {
       mkdirSync(dirname(dest), { recursive: true });
-      // force:false merges into a partially traced directory: files the trace
-      // already materialized are kept, missing ones (the package payload) are
-      // filled in from the root tree.
-      cpSync(join(rootNm, name), dest, {
-        recursive: true,
-        force: false,
-        errorOnExist: false,
-      });
+      cpSync(join(rootNm, name), dest, { recursive: true });
       copied++;
     } catch (err) {
       log(

scripts/build/pack-artifact-policy.ts

@@ -121,9 +121,6 @@ export const PACK_ARTIFACT_ROOT_ALLOWED_EXACT_PATHS: string[] = [
   // shipped via package.json "files", so it must be allowed in the tarball.
   "open-sse/utils/setupPolyfill.ts",
   "package.json",
-  "scripts/build/assembleStandalone.mjs",
-  "scripts/build/backendOnlyPages.mjs",
-  "scripts/build/build-tproxy-native.mjs",
   "scripts/build/build-next-isolated.mjs",
   "scripts/check/check-supported-node-runtime.ts",
   "scripts/build/native-binary-compat.mjs",

scripts/check/check-docs-counts-sync.mjs

@@ -147,9 +147,10 @@ function readCodeFacts() {
     'import {pluginTools} from "./open-sse/mcp-server/tools/pluginTools.ts";',
     'import {notionTools} from "./open-sse/mcp-server/tools/notionTools.ts";',
     'import {obsidianTools} from "./open-sse/mcp-server/tools/obsidianTools.ts";',
+    'import {localCorpusTools} from "./open-sse/mcp-server/tools/localCorpusTools.ts";',
     'import {compressionTools} from "./open-sse/mcp-server/tools/compressionTools.ts";',
     "const cols={MCP_TOOLS,memoryTools,skillTools,agentSkillTools,githubSkillTools,poolTools,",
-    "gamificationTools,pluginTools,notionTools,obsidianTools,compressionTools};",
+    "gamificationTools,pluginTools,notionTools,obsidianTools,localCorpusTools,compressionTools};",
     "const sc=new Set();",
     "for(const col of Object.values(cols))for(const t of Object.values(col))",
     "for(const x of (t?.scopes||[]))sc.add(x);",
@@ -313,7 +314,7 @@ export function buildChecks() {
             // total ("33 tools (25 CLI Code's …)") are not the MCP aggregate
             // per-module rows read "… tool definitions (N tools" / "… management tools
             // (N tools" — the word tool(s)/definitions sits right before the paren. The
-            // aggregate ("MCP Server (104 tools", "all 104 tools") never does.
+            // aggregate ("MCP Server (109 tools", "all 109 tools") never does.
             skipBefore: /(tools?|definitions?)\s*\(\s*$/i,
             skipAfter: /^\s*\(\d+ CLI/,
           },

scripts/quality/validate-release-green.mjs

@@ -609,6 +609,14 @@ async function main() {
         args: ["run", "check:pack-artifact"],
         timeout: 20 * 60 * 1000,
       });
+      // WS1.2 (#7065 class): boot the REAL packed tarball from a clean install —
+      // the runtime gate structure checks cannot provide. Reuses the same dist/ build.
+      slow.push({
+        id: "pack-boot",
+        label: "Tarball boot-smoke (installed CLI serves /health)",
+        args: ["run", "check:pack-boot"],
+        timeout: 15 * 60 * 1000,
+      });
     }
     slow.forEach((g) => announce(`${g.label} [parallel]`));
     const slowResults = await Promise.all(
@@ -625,41 +633,6 @@ async function main() {
         detail: code === 0 ? "pass" : firstFailureLine(out),
       });
     });
-
-    if (WITH_BUILD) {
-      // WS1.2 (#7065 class): boot the REAL packed tarball from a clean install.
-      // check:pack-artifact is the builder for dist/ when staging is absent, so the
-      // boot smoke MUST run after it completes. Running both in the parallel wave
-      // races check:pack-boot against dist/server.js creation on clean worktrees.
-      const packArtifactIndex = slow.findIndex((g) => g.id === "pack-artifact");
-      const packArtifactResult = slowResults[packArtifactIndex];
-      const bootLabel = "Tarball boot-smoke (installed CLI serves /health)";
-
-      if (!packArtifactResult || packArtifactResult.code !== 0) {
-        const out = "skipped because package-artifact did not produce a valid dist/ build";
-        saveGateLog("pack-boot", out);
-        record({
-          id: "pack-boot",
-          label: bootLabel,
-          kind: "hard",
-          ok: false,
-          detail: out,
-        });
-      } else {
-        announce(bootLabel);
-        const { code, out } = await runAsync(npmCmd, ["run", "check:pack-boot"], {
-          timeout: 15 * 60 * 1000,
-        });
-        saveGateLog("pack-boot", out);
-        record({
-          id: "pack-boot",
-          label: bootLabel,
-          kind: "hard",
-          ok: code === 0,
-          detail: code === 0 ? "pass" : firstFailureLine(out),
-        });
-      }
-    }
   } else if (WITH_BUILD) {
     // --with-build without the suites (--quick): still verify the package artifact.
     const { code, out } = await runAsync(npmCmd, ["run", "check:pack-artifact"], {

src/app/(dashboard)/dashboard/HomePageClient.tsx

@@ -22,7 +22,6 @@ import { HomeProviderTopologySection } from "./HomeProviderTopologySection";
 import { shouldShowProviderTopologyOnHome } from "./homeAppearance";
 
 const ProviderQuotaWidget = dynamic(() => import("../home/ProviderQuotaWidget"), { ssr: false });
-import type { NewsAnnouncement } from "@/shared/utils/releaseNotes";
 
 type UpdateStep = {
   step: string;
@@ -37,7 +36,6 @@ type VersionInfo = {
   channel: string;
   autoUpdateSupported: boolean;
   autoUpdateError?: string | null;
-  news?: NewsAnnouncement | null;
 };
 
 type HomePageClientProps = {
@@ -1049,37 +1047,6 @@ export default function HomePageClient({ machineId }: HomePageClientProps) {
                 </div>
               )}
           </div>
-
-          {/* News Notification Banner */}
-          {versionInfo?.news && (
-            <div className="flex min-h-[64px] items-center justify-between rounded-lg border border-border bg-surface px-5 py-4">
-              <div className="flex min-w-0 items-center gap-4">
-                <div className="flex size-10 shrink-0 items-center justify-center rounded-lg bg-bg text-text-muted">
-                  <span className="material-symbols-outlined text-[22px] text-primary">
-                    {versionInfo.news.icon || "campaign"}
-                  </span>
-                </div>
-                <div className="min-w-0">
-                  <p className="text-sm font-semibold text-text-main">{versionInfo.news.title}</p>
-                  <p className="mt-0.5 max-w-[560px] text-xs leading-relaxed text-text-muted">
-                    {versionInfo.news.message}
-                  </p>
-                </div>
-              </div>
-
-              {versionInfo.news.link && (
-                <a
-                  href={versionInfo.news.link}
-                  target="_blank"
-                  rel="noopener noreferrer"
-                  className="ml-4 inline-flex shrink-0 items-center gap-1.5 rounded-lg border border-border bg-bg px-4 py-2 text-xs font-semibold text-text-main transition-colors hover:border-primary/30 hover:text-primary"
-                >
-                  {versionInfo.news.linkLabel || "Ler Mais"}
-                  <span className="material-symbols-outlined text-[14px]">arrow_forward</span>
-                </a>
-              )}
-            </div>
-          )}
         </div>
       )}
 

src/app/(dashboard)/dashboard/NewsBanner.tsx

@@ -0,0 +1,119 @@
+"use client";
+
+import { useEffect, useState, useSyncExternalStore } from "react";
+import { useLocale, useTranslations } from "next-intl";
+
+import {
+  NEWS_DISMISS_EVENT,
+  NEWS_DISMISS_STORAGE_KEY,
+  fetchNewsPayload,
+  parseDismissedNewsIds,
+  selectActiveNews,
+  serializeDismissedNewsIds,
+} from "@/shared/utils/releaseNotes";
+
+function subscribeToDismissals(callback: () => void) {
+  window.addEventListener("storage", callback);
+  window.addEventListener(NEWS_DISMISS_EVENT, callback);
+  return () => {
+    window.removeEventListener("storage", callback);
+    window.removeEventListener(NEWS_DISMISS_EVENT, callback);
+  };
+}
+
+function readDismissedIds(): string {
+  try {
+    return localStorage.getItem(NEWS_DISMISS_STORAGE_KEY) ?? "";
+  } catch {
+    return "";
+  }
+}
+
+function getServerDismissedIds(): string {
+  return "";
+}
+
+/**
+ * Generic, fail-silent reader for the public announcement feed. Fetching the
+ * static JSON is GET-only and does not send product state or telemetry.
+ */
+export default function NewsBanner() {
+  const locale = useLocale();
+  const t = useTranslations("common");
+  const [payload, setPayload] = useState<unknown>(null);
+  const dismissedSnapshot = useSyncExternalStore(
+    subscribeToDismissals,
+    readDismissedIds,
+    getServerDismissedIds
+  );
+  const dismissedIds = parseDismissedNewsIds(dismissedSnapshot);
+  const announcement = selectActiveNews(payload, locale, dismissedIds);
+
+  useEffect(() => {
+    const controller = new AbortController();
+
+    void fetchNewsPayload(fetch, controller.signal).then((value) => {
+      if (value !== null) setPayload(value);
+    });
+
+    return () => controller.abort();
+  }, []);
+
+  if (!announcement) return null;
+
+  const dismiss = () => {
+    dismissedIds.add(announcement.id);
+    try {
+      localStorage.setItem(NEWS_DISMISS_STORAGE_KEY, serializeDismissedNewsIds(dismissedIds));
+    } catch {
+      // Storage is optional; the next announcement fetch remains functional.
+    }
+    window.dispatchEvent(new Event(NEWS_DISMISS_EVENT));
+  };
+
+  return (
+    <div
+      role="complementary"
+      aria-label={announcement.title}
+      className="mb-4 flex flex-col gap-3 rounded-lg border border-primary/30 bg-primary/5 px-4 py-3 sm:flex-row sm:items-center sm:justify-between"
+    >
+      <div className="flex min-w-0 items-start gap-3">
+        <div className="flex size-9 shrink-0 items-center justify-center rounded-lg bg-primary/10">
+          <span className="material-symbols-outlined text-[22px] text-primary" aria-hidden="true">
+            {announcement.icon}
+          </span>
+        </div>
+        <div className="min-w-0">
+          <p className="text-sm font-semibold text-text-main">{announcement.title}</p>
+          <p className="mt-0.5 text-xs leading-relaxed text-text-muted">{announcement.message}</p>
+        </div>
+      </div>
+
+      <div className="flex shrink-0 items-center gap-3 self-end sm:self-auto">
+        {announcement.link && (
+          <a
+            href={announcement.link}
+            target="_blank"
+            rel="noopener noreferrer"
+            className="inline-flex items-center gap-1.5 whitespace-nowrap rounded-lg bg-primary px-3 py-1.5 text-xs font-semibold text-white transition-colors hover:brightness-110"
+          >
+            {announcement.linkLabel ?? announcement.title}
+            <span className="material-symbols-outlined text-[14px]" aria-hidden="true">
+              open_in_new
+            </span>
+          </a>
+        )}
+        <button
+          type="button"
+          onClick={dismiss}
+          aria-label={t("dismissNotification")}
+          className="text-text-muted transition-colors hover:text-text-main"
+        >
+          <span className="material-symbols-outlined text-[18px]" aria-hidden="true">
+            close
+          </span>
+        </button>
+      </div>
+    </div>
+  );
+}

src/app/(dashboard)/dashboard/changelog/components/NewsViewer.tsx

@@ -1,39 +1,39 @@
 "use client";
 
-import { useState, useEffect } from "react";
-import { useTranslations } from "next-intl";
+import { useEffect, useState } from "react";
+import { useLocale, useTranslations } from "next-intl";
+
 import { Button } from "@/shared/components";
 import {
-  NEWS_JSON_URL,
-  parseActiveNewsPayload,
+  fetchNewsPayload,
+  listActiveNews,
   type NewsAnnouncement,
 } from "@/shared/utils/releaseNotes";
 
 export default function NewsViewer() {
+  const locale = useLocale();
   const t = useTranslations("changelogPage");
-  const [news, setNews] = useState<NewsAnnouncement | null>(null);
+  const [news, setNews] = useState<NewsAnnouncement[]>([]);
   const [loading, setLoading] = useState(true);
   const [error, setError] = useState(false);
 
   useEffect(() => {
-    async function fetchNews() {
-      try {
-        const res = await fetch(NEWS_JSON_URL, { cache: "no-store" });
-        if (res.ok) {
-          const data = await res.json();
-          setNews(parseActiveNewsPayload(data));
-        } else {
-          setError(true);
+    const controller = new AbortController();
+
+    void fetchNewsPayload(fetch, controller.signal)
+      .then((payload) => {
+        if (payload === null) {
+          if (!controller.signal.aborted) setError(true);
+          return;
         }
-      } catch (err) {
-        console.error("Failed to fetch news:", err);
-        setError(true);
-      } finally {
-        setLoading(false);
-      }
-    }
-    fetchNews();
-  }, []);
+        setNews(listActiveNews(payload, locale));
+      })
+      .finally(() => {
+        if (!controller.signal.aborted) setLoading(false);
+      });
+
+    return () => controller.abort();
+  }, [locale]);
 
   if (loading) {
     return (
@@ -48,7 +48,7 @@ export default function NewsViewer() {
   if (error) {
     return (
       <div className="flex flex-col items-center justify-center py-20 text-text-muted">
-        <span className="material-symbols-outlined text-[48px] text-red-500/50 mb-4">
+        <span className="material-symbols-outlined mb-4 text-[48px] text-red-500/50">
           error_outline
         </span>
         <p>{t("announcementsLoadFailed")}</p>
@@ -56,10 +56,10 @@ export default function NewsViewer() {
     );
   }
 
-  if (!news || !news.active) {
+  if (news.length === 0) {
     return (
       <div className="flex flex-col items-center justify-center py-20 text-text-muted">
-        <span className="material-symbols-outlined text-[48px] opacity-50 mb-4">
+        <span className="material-symbols-outlined mb-4 text-[48px] opacity-50">
           notifications_off
         </span>
         <p>{t("noAnnouncements")}</p>
@@ -68,30 +68,37 @@ export default function NewsViewer() {
   }
 
   return (
-    <div className="p-8">
-      <div className="flex flex-col gap-6 border-l-4 border-primary pl-5 md:flex-row md:items-center md:pl-6">
-        <div className="size-14 rounded-lg bg-primary/10 flex items-center justify-center shrink-0">
-          <span className="material-symbols-outlined text-[30px] text-primary">
-            {news.icon || "campaign"}
-          </span>
-        </div>
-
-        <div className="flex-1">
-          <h2 className="text-xl font-bold text-text-main mb-2">{news.title}</h2>
-          <p className="text-sm text-text-muted leading-relaxed max-w-2xl">{news.message}</p>
-        </div>
-
-        {news.link && (
-          <div className="shrink-0 md:ml-auto">
-            <a href={news.link} target="_blank" rel="noopener noreferrer">
-              <Button variant="primary" className="gap-2">
-                {news.linkLabel || t("learnMore")}
-                <span className="material-symbols-outlined text-[18px]">arrow_forward</span>
-              </Button>
-            </a>
+    <div className="space-y-8 p-8">
+      {news.map((announcement) => (
+        <article
+          key={announcement.id}
+          className="flex flex-col gap-6 border-l-4 border-primary pl-5 md:flex-row md:items-center md:pl-6"
+        >
+          <div className="flex size-14 shrink-0 items-center justify-center rounded-lg bg-primary/10">
+            <span className="material-symbols-outlined text-[30px] text-primary">
+              {announcement.icon}
+            </span>
           </div>
-        )}
-      </div>
+
+          <div className="flex-1">
+            <h2 className="mb-2 text-xl font-bold text-text-main">{announcement.title}</h2>
+            <p className="max-w-2xl text-sm leading-relaxed text-text-muted">
+              {announcement.message}
+            </p>
+          </div>
+
+          {announcement.link && (
+            <div className="shrink-0 md:ml-auto">
+              <a href={announcement.link} target="_blank" rel="noopener noreferrer">
+                <Button variant="primary" className="gap-2">
+                  {announcement.linkLabel ?? t("learnMore")}
+                  <span className="material-symbols-outlined text-[18px]">arrow_forward</span>
+                </Button>
+              </a>
+            </div>
+          )}
+        </article>
+      ))}
     </div>
   );
 }

src/app/(dashboard)/dashboard/media-providers/components/LlmChatCard.tsx

@@ -134,7 +134,7 @@ export function LlmChatCard({
 }: Props) {
   const t = useTranslations("miniPlayground");
   const { keys } = useApiKey();
-  const { models, loading, error, retry } = useProviderModels(providerId);
+  const { models } = useProviderModels(providerId);
 
   const [internalSelectedKey, setInternalSelectedKey] = useState<string>("");
   const [internalModel, setInternalModel] = useState<string>(initialModel ?? "");
@@ -392,31 +392,15 @@ export function LlmChatCard({
             <select
               value={model || firstModel}
               onChange={(e) => setModel(e.target.value)}
-              disabled={loading}
-              className="min-w-0 flex-1 rounded-md border border-border bg-bg-subtle text-xs px-2 py-1 text-text-main focus:outline-none focus:ring-1 focus:ring-primary disabled:opacity-60"
+              className="min-w-0 flex-1 rounded-md border border-border bg-bg-subtle text-xs px-2 py-1 text-text-main focus:outline-none focus:ring-1 focus:ring-primary"
             >
-              {modelOptions.length === 0 && !loading && <option value="">{initialModel || "—"}</option>}
-              {loading && <option value="">{t("loading") ?? "Loading…"}</option>}
+              {modelOptions.length === 0 && <option value="">{initialModel || "—"}</option>}
               {modelOptions.map((m) => (
                 <option key={m.id} value={m.id}>
                   {m.id}
                 </option>
               ))}
             </select>
-            {error && (
-              <span className="text-xs text-red-500 flex items-center gap-1" role="alert">
-                <span className="truncate max-w-[180px]" title={String(error)}>
-                  {String(error)}
-                </span>
-                <button
-                  type="button"
-                  onClick={retry}
-                  className="shrink-0 text-xs text-primary hover:text-primary-strong underline"
-                >
-                  {t("retry") ?? "Retry"}
-                </button>
-              </span>
-            )}
           </div>
           {/* Key select */}
           {keys.length > 0 && (

src/app/(dashboard)/dashboard/providers/hooks/useProviderModels.ts

@@ -1,6 +1,6 @@
 "use client";
 
-import { useState, useEffect, useCallback, useRef } from "react";
+import { useState, useEffect } from "react";
 
 export interface ProviderModel {
   id: string;
@@ -18,8 +18,6 @@ interface UseProviderModelsResult {
   models: ProviderModel[];
   loading: boolean;
   error: string | null;
-  /** Re-runs the model fetch for the current provider. Useful for a Retry action. */
-  retry: () => void;
 }
 
 /**
@@ -34,14 +32,15 @@ export function useProviderModels(providerId: string): UseProviderModelsResult {
   const [models, setModels] = useState<ProviderModel[]>([]);
   const [loading, setLoading] = useState<boolean>(true);
   const [error, setError] = useState<string | null>(null);
-  // Cancels any in-flight load (component unmount or a retry superseding the
-  // previous request) so a stale response never overwrites a newer one.
-  const cleanupRef = useRef<(() => void) | null>(null);
 
-  const load = useCallback(() => {
-    cleanupRef.current?.();
+  useEffect(() => {
+    if (!providerId) {
+      setLoading(false);
+      return;
+    }
+
     let cancelled = false;
-    const run = async () => {
+    const load = async () => {
       setLoading(true);
       setError(null);
       try {
@@ -110,33 +109,11 @@ export function useProviderModels(providerId: string): UseProviderModelsResult {
         if (!cancelled) setLoading(false);
       }
     };
-    void run();
-    const cleanup = () => {
+    void load();
+    return () => {
       cancelled = true;
     };
-    cleanupRef.current = cleanup;
-    return cleanup;
   }, [providerId]);
 
-  useEffect(() => {
-    if (!providerId) {
-      setLoading(false);
-      return;
-    }
-    return load();
-  }, [providerId, load]);
-
-  // Release the current in-flight cleanup on unmount so no state updates leak.
-  useEffect(() => {
-    return () => {
-      cleanupRef.current?.();
-    };
-  }, []);
-
-  const retry = useCallback(() => {
-    if (!providerId) return;
-    load();
-  }, [providerId, load]);
-
-  return { models, loading, error, retry };
+  return { models, loading, error };
 }

src/app/(dashboard)/dashboard/radar/RadarCatalogTable.tsx

@@ -0,0 +1,361 @@
+"use client";
+
+import { useCallback, useEffect, useMemo, useState } from "react";
+import Link from "next/link";
+import { useTranslations } from "next-intl";
+import { Card } from "@/shared/components";
+
+export interface RadarMergedEntry {
+  provider: string;
+  modelId: string;
+  displayName: string;
+  monthlyTokens: number;
+  creditTokens: number;
+  freeType: string;
+  poolKey: string | null;
+  tos: string;
+  trainsOnPrompts?: boolean;
+  enabled?: boolean;
+  origin: "baseline" | "radar" | "local";
+  disabledBy?: "radar";
+  contextWindow?: number | null;
+  capabilities?: { tools: boolean; vision: boolean; thinking: boolean };
+  budget?: { kind: string; tokensPerMonth?: number; poolId?: string };
+  limits?: { rpm: number | null; rpd: number | null; tpm: number | null; tpd: number | null };
+  setup?: { keyUrl: string | null; steps: string[] } | null;
+}
+
+interface RadarLocalModelState {
+  provider: string;
+  modelId: string;
+  displayName: string | null;
+  enabled: boolean | null;
+  tombstoned: boolean;
+  updatedAt: string;
+}
+
+interface RadarCatalogTableProps {
+  entries: RadarMergedEntry[];
+  refreshCatalog: () => Promise<void>;
+  onError: (message: string) => void;
+}
+
+function formatTokens(value: number): string {
+  if (value === 0) return "rate-only";
+  if (value >= 1_000_000) return `${(value / 1_000_000).toFixed(1)}M`;
+  if (value >= 1_000) return `${(value / 1_000).toFixed(0)}K`;
+  return String(value);
+}
+
+function budgetLabel(entry: RadarMergedEntry): string {
+  if (entry.budget?.kind === "shared_pool") {
+    return `shared (${formatTokens(entry.budget.tokensPerMonth ?? entry.monthlyTokens)}/mo)`;
+  }
+  if (entry.budget?.kind === "rate_only" || entry.monthlyTokens === 0) return "rate-only";
+  return `${formatTokens(entry.monthlyTokens)}/mo`;
+}
+
+export function RadarCatalogTable({ entries, refreshCatalog, onError }: RadarCatalogTableProps) {
+  const t = useTranslations("radarPage");
+  const [states, setStates] = useState<RadarLocalModelState[]>([]);
+  const [editingKey, setEditingKey] = useState<string | null>(null);
+  const [displayName, setDisplayName] = useState("");
+  const [enabled, setEnabled] = useState(true);
+  const [saving, setSaving] = useState(false);
+
+  const loadState = useCallback(async () => {
+    try {
+      const response = await fetch("/api/radar/local-model-state");
+      if (!response.ok) return;
+      const payload = await response.json();
+      setStates(Array.isArray(payload.states) ? payload.states : []);
+    } catch {
+      onError(t("errorLoading"));
+    }
+  }, [onError, t]);
+
+  useEffect(() => {
+    void loadState();
+  }, [loadState]);
+
+  const stateByKey = useMemo(
+    () => new Map(states.map((state) => [`${state.provider}:${state.modelId}`, state])),
+    [states]
+  );
+  const hiddenModels = useMemo(() => states.filter((state) => state.tombstoned), [states]);
+
+  const applyResponse = useCallback(async (response: Response) => {
+    if (!response.ok) throw new Error("save_failed");
+    const payload = await response.json();
+    setStates(Array.isArray(payload.states) ? payload.states : []);
+  }, []);
+
+  const mutate = useCallback(
+    async (operation: () => Promise<Response>) => {
+      setSaving(true);
+      onError("");
+      try {
+        await applyResponse(await operation());
+        setEditingKey(null);
+        await refreshCatalog();
+      } catch {
+        onError(t("localStateSaveFailed"));
+      } finally {
+        setSaving(false);
+      }
+    },
+    [applyResponse, onError, refreshCatalog, t]
+  );
+
+  const beginEdit = useCallback((entry: RadarMergedEntry) => {
+    setEditingKey(`${entry.provider}:${entry.modelId}`);
+    setDisplayName(entry.displayName);
+    setEnabled(entry.enabled !== false);
+  }, []);
+
+  const saveOverride = useCallback(
+    (entry: RadarMergedEntry) =>
+      mutate(() =>
+        fetch("/api/radar/local-model-state", {
+          method: "PATCH",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify({
+            provider: entry.provider,
+            modelId: entry.modelId,
+            displayName,
+            enabled,
+          }),
+        })
+      ),
+    [displayName, enabled, mutate]
+  );
+
+  const resetOverride = useCallback(
+    (entry: Pick<RadarMergedEntry, "provider" | "modelId">) => {
+      const query = new URLSearchParams({ provider: entry.provider, modelId: entry.modelId });
+      return mutate(() =>
+        fetch(`/api/radar/local-model-state?${query.toString()}`, { method: "DELETE" })
+      );
+    },
+    [mutate]
+  );
+
+  const setTombstone = useCallback(
+    (provider: string, modelId: string, tombstoned: boolean) =>
+      mutate(() =>
+        fetch("/api/radar/local-model-state", {
+          method: "PUT",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify({ provider, modelId, tombstoned }),
+        })
+      ),
+    [mutate]
+  );
+
+  return (
+    <>
+      <Card>
+        <div className="overflow-x-auto">
+          <table className="w-full">
+            <thead>
+              <tr className="text-left text-sm text-text-muted border-b border-border">
+                <th className="pb-3 font-medium">{t("colProvider")}</th>
+                <th className="pb-3 font-medium">{t("colModel")}</th>
+                <th className="pb-3 font-medium">{t("colQuota")}</th>
+                <th className="pb-3 font-medium">{t("colContext")}</th>
+                <th className="pb-3 font-medium">{t("colCapabilities")}</th>
+                <th className="pb-3 font-medium">{t("colTos")}</th>
+                <th className="pb-3 font-medium text-right">{t("colActions")}</th>
+              </tr>
+            </thead>
+            <tbody>
+              {entries.map((entry) => {
+                const key = `${entry.provider}:${entry.modelId}`;
+                const localState = stateByKey.get(key);
+                const hasOverride =
+                  localState && (localState.displayName !== null || localState.enabled !== null);
+                return (
+                  <tr
+                    key={key}
+                    className={`border-b border-border/50 last:border-b-0 ${
+                      entry.enabled === false ? "opacity-50" : ""
+                    }`}
+                  >
+                    <td className="py-3">
+                      <div className="flex items-center gap-2">
+                        <span className="font-medium">{entry.provider}</span>
+                        {entry.origin === "radar" && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-violet-500/10 text-violet-400 font-medium">
+                            {t("newBadge")}
+                          </span>
+                        )}
+                        {entry.origin === "local" && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-blue-500/10 text-blue-400 font-medium">
+                            {t("localBadge")}
+                          </span>
+                        )}
+                        {entry.setup?.keyUrl && (
+                          <Link
+                            href={`/dashboard/radar/setup?provider=${encodeURIComponent(entry.provider)}`}
+                            className="text-xs text-violet-400 hover:underline"
+                            title={t("setupGuide")}
+                          >
+                            ⚙
+                          </Link>
+                        )}
+                      </div>
+                      {entry.enabled === false && entry.disabledBy === "radar" && (
+                        <p className="text-xs text-red-400 mt-0.5">{t("disabledByFeed")}</p>
+                      )}
+                    </td>
+                    <td className="py-3 text-text-muted text-sm font-mono max-w-[240px]">
+                      {editingKey === key ? (
+                        <input
+                          type="text"
+                          value={displayName}
+                          onChange={(event) => setDisplayName(event.target.value)}
+                          aria-label={t("modelDisplayName")}
+                          maxLength={160}
+                          className="w-full min-w-[180px] px-2 py-1 rounded border border-border bg-transparent text-text-main focus:outline-none focus:ring-2 focus:ring-violet-500"
+                        />
+                      ) : (
+                        <span className="block truncate">{entry.displayName}</span>
+                      )}
+                    </td>
+                    <td className="py-3 text-sm">{budgetLabel(entry)}</td>
+                    <td className="py-3 text-sm text-text-muted">
+                      {entry.contextWindow ? `${(entry.contextWindow / 1000).toFixed(0)}K` : "—"}
+                    </td>
+                    <td className="py-3">
+                      <div className="flex gap-1">
+                        {entry.capabilities?.tools && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-blue-500/10 text-blue-400">
+                            {t("capTools")}
+                          </span>
+                        )}
+                        {entry.capabilities?.vision && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-purple-500/10 text-purple-400">
+                            {t("capVision")}
+                          </span>
+                        )}
+                        {entry.capabilities?.thinking && (
+                          <span className="text-[10px] px-1.5 py-0.5 rounded bg-amber-500/10 text-amber-400">
+                            {t("capThinking")}
+                          </span>
+                        )}
+                      </div>
+                    </td>
+                    <td className="py-3">
+                      <span
+                        className={`text-xs px-2 py-1 rounded ${
+                          entry.tos === "ok"
+                            ? "bg-green-500/10 text-green-400"
+                            : entry.tos === "caution"
+                              ? "bg-yellow-500/10 text-yellow-400"
+                              : entry.tos === "avoid"
+                                ? "bg-red-500/10 text-red-400"
+                                : "bg-gray-500/10 text-gray-400"
+                        }`}
+                      >
+                        {entry.tos}
+                      </span>
+                    </td>
+                    <td className="py-3 pl-3">
+                      {editingKey === key ? (
+                        <div className="flex flex-wrap items-center justify-end gap-2">
+                          <label className="inline-flex items-center gap-1 text-xs text-text-muted">
+                            <input
+                              type="checkbox"
+                              checked={enabled}
+                              disabled={entry.disabledBy === "radar"}
+                              onChange={(event) => setEnabled(event.target.checked)}
+                            />
+                            {t("modelEnabled")}
+                          </label>
+                          <button
+                            type="button"
+                            disabled={saving || displayName.trim().length === 0}
+                            onClick={() => void saveOverride(entry)}
+                            className="text-xs text-violet-400 hover:underline disabled:opacity-50"
+                          >
+                            {t("saveModel")}
+                          </button>
+                          <button
+                            type="button"
+                            disabled={saving}
+                            onClick={() => setEditingKey(null)}
+                            className="text-xs text-text-muted hover:text-text-main disabled:opacity-50"
+                          >
+                            {t("cancelEdit")}
+                          </button>
+                        </div>
+                      ) : (
+                        <div className="flex flex-wrap items-center justify-end gap-2">
+                          <button
+                            type="button"
+                            disabled={saving}
+                            onClick={() => beginEdit(entry)}
+                            className="text-xs text-violet-400 hover:underline disabled:opacity-50"
+                          >
+                            {t("editModel")}
+                          </button>
+                          {hasOverride && (
+                            <button
+                              type="button"
+                              disabled={saving}
+                              onClick={() => void resetOverride(entry)}
+                              className="text-xs text-text-muted hover:text-text-main disabled:opacity-50"
+                            >
+                              {t("resetModel")}
+                            </button>
+                          )}
+                          <button
+                            type="button"
+                            disabled={saving}
+                            onClick={() => void setTombstone(entry.provider, entry.modelId, true)}
+                            className="text-xs text-red-400 hover:underline disabled:opacity-50"
+                          >
+                            {t("hideModel")}
+                          </button>
+                        </div>
+                      )}
+                    </td>
+                  </tr>
+                );
+              })}
+            </tbody>
+          </table>
+        </div>
+      </Card>
+
+      {hiddenModels.length > 0 && (
+        <Card>
+          <div className="flex flex-col gap-3">
+            <h3 className="text-sm font-semibold">{t("hiddenModelsTitle")}</h3>
+            {hiddenModels.map((state) => (
+              <div
+                key={`${state.provider}:${state.modelId}:hidden`}
+                className="flex flex-wrap items-center justify-between gap-3 border-b border-border/50 pb-3 last:border-b-0 last:pb-0"
+              >
+                <div>
+                  <span className="font-medium">{state.provider}</span>
+                  <span className="ml-2 text-sm font-mono text-text-muted">
+                    {state.displayName ?? state.modelId}
+                  </span>
+                </div>
+                <button
+                  type="button"
+                  disabled={saving}
+                  onClick={() => void setTombstone(state.provider, state.modelId, false)}
+                  className="text-sm text-violet-400 hover:underline disabled:opacity-50"
+                >
+                  {t("restoreModel")}
+                </button>
+              </div>
+            ))}
+          </div>
+        </Card>
+      )}
+    </>
+  );
+}

src/app/(dashboard)/dashboard/radar/combos/page.tsx

@@ -0,0 +1,201 @@
+"use client";
+
+import { useCallback, useEffect, useMemo, useState } from "react";
+import { useTranslations } from "next-intl";
+import Link from "next/link";
+import { notFound } from "next/navigation";
+
+import type { ComboBuilderOptionsPayload } from "@/lib/combos/builderOptions";
+import type { MergedEntry } from "@/lib/radar/applyFeed";
+import {
+  buildRadarComboSuggestions,
+  type RadarComboSuggestion,
+} from "@/lib/radar/comboSuggestions";
+import { Card } from "@/shared/components";
+
+interface RadarCatalogPayload {
+  entries?: MergedEntry[];
+  meta?: unknown;
+}
+
+function comboNames(payload: ComboBuilderOptionsPayload): Set<string> {
+  return new Set(payload.comboRefs.map((combo) => combo.name));
+}
+
+export default function RadarCombosPage() {
+  const t = useTranslations("radarCombosPage");
+  const [entries, setEntries] = useState<MergedEntry[]>([]);
+  const [providers, setProviders] = useState<ComboBuilderOptionsPayload["providers"]>([]);
+  const [existingNames, setExistingNames] = useState<Set<string>>(new Set());
+  const [createdNames, setCreatedNames] = useState<Set<string>>(new Set());
+  const [hasCatalog, setHasCatalog] = useState(false);
+  const [flagOff, setFlagOff] = useState(false);
+  const [loading, setLoading] = useState(true);
+  const [creatingName, setCreatingName] = useState<string | null>(null);
+  const [error, setError] = useState("");
+
+  useEffect(() => {
+    async function load() {
+      try {
+        const [catalogResponse, optionsResponse] = await Promise.all([
+          fetch("/api/radar/catalog"),
+          fetch("/api/combos/builder/options"),
+        ]);
+        if (catalogResponse.status === 404) {
+          setFlagOff(true);
+          return;
+        }
+        if (!catalogResponse.ok || !optionsResponse.ok) throw new Error("load_failed");
+
+        const catalog = (await catalogResponse.json()) as RadarCatalogPayload;
+        const options = (await optionsResponse.json()) as ComboBuilderOptionsPayload;
+        if (!Array.isArray(catalog.entries) || !Array.isArray(options.providers)) {
+          throw new Error("invalid_shape");
+        }
+
+        setEntries(catalog.entries);
+        setProviders(options.providers);
+        setExistingNames(comboNames(options));
+        setHasCatalog(catalog.meta != null);
+      } catch {
+        setError(t("loadFailed"));
+      } finally {
+        setLoading(false);
+      }
+    }
+
+    void load();
+  }, [t]);
+
+  const suggestions = useMemo(
+    () => buildRadarComboSuggestions({ entries, providers, existingComboNames: existingNames }),
+    [entries, providers, existingNames]
+  );
+
+  const refreshExistingName = useCallback(async (name: string): Promise<boolean> => {
+    try {
+      const response = await fetch("/api/combos/builder/options");
+      if (!response.ok) return false;
+      const options = (await response.json()) as ComboBuilderOptionsPayload;
+      if (!Array.isArray(options.comboRefs)) return false;
+      const names = comboNames(options);
+      if (![...names].some((candidate) => candidate.toLowerCase() === name.toLowerCase())) {
+        return false;
+      }
+      setExistingNames(names);
+      return true;
+    } catch {
+      return false;
+    }
+  }, []);
+
+  const createSuggestion = useCallback(
+    async (suggestion: RadarComboSuggestion) => {
+      setCreatingName(suggestion.name);
+      setError("");
+      try {
+        const response = await fetch("/api/combos", {
+          method: "POST",
+          headers: { "Content-Type": "application/json" },
+          body: JSON.stringify(suggestion.payload),
+        });
+        if (!response.ok) {
+          if (response.status === 400 && (await refreshExistingName(suggestion.name))) return;
+          throw new Error("create_failed");
+        }
+        setExistingNames((current) => new Set([...current, suggestion.name]));
+        setCreatedNames((current) => new Set([...current, suggestion.name]));
+      } catch {
+        setError(t("createFailed"));
+      } finally {
+        setCreatingName(null);
+      }
+    },
+    [refreshExistingName, t]
+  );
+
+  if (flagOff) notFound();
+
+  return (
+    <div className="flex flex-col gap-6">
+      <div className="flex flex-col gap-3">
+        <Link
+          href="/dashboard/radar"
+          className="text-sm text-text-muted hover:text-text-main transition-colors w-fit"
+        >
+          ← {t("backToRadar")}
+        </Link>
+        <div>
+          <h1 className="text-2xl font-bold">{t("title")}</h1>
+          <p className="text-sm text-text-muted mt-1">{t("subtitle")}</p>
+        </div>
+      </div>
+
+      {error && <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>}
+
+      {loading ? (
+        <div className="flex items-center justify-center min-h-[200px] text-text-muted">
+          {t("loading")}
+        </div>
+      ) : !hasCatalog ? (
+        <Card>
+          <p className="text-center text-text-muted py-8">{t("catalogRequired")}</p>
+        </Card>
+      ) : suggestions.length === 0 ? (
+        <Card>
+          <p className="text-center text-text-muted py-8">{t("noSuggestions")}</p>
+        </Card>
+      ) : (
+        <div className="grid gap-4">
+          {suggestions.map((suggestion) => {
+            const creating = creatingName === suggestion.name;
+            const created = createdNames.has(suggestion.name);
+            return (
+              <Card key={suggestion.familyId}>
+                <div className="flex flex-col gap-4">
+                  <div className="flex flex-col gap-1">
+                    <span className="text-xs uppercase tracking-wide text-text-muted">
+                      {t("familyLabel")}
+                    </span>
+                    <h2 className="text-lg font-semibold font-mono">{suggestion.familyId}</h2>
+                    <p className="text-sm text-text-muted">{t("strategyReason")}</p>
+                  </div>
+
+                  <div className="flex flex-col gap-2">
+                    <span className="text-sm font-medium">{t("modelsLabel")}</span>
+                    {suggestion.models.map((model) => (
+                      <div
+                        key={`${model.providerId}:${model.modelId}`}
+                        className="flex flex-wrap items-center justify-between gap-2 rounded-lg border border-border px-3 py-2"
+                      >
+                        <span className="font-medium">{model.providerName}</span>
+                        <span className="font-mono text-sm text-text-muted">
+                          {model.qualifiedModel}
+                        </span>
+                      </div>
+                    ))}
+                  </div>
+
+                  <button
+                    type="button"
+                    onClick={() => void createSuggestion(suggestion)}
+                    disabled={creating || suggestion.alreadyExists}
+                    className="self-start px-4 py-2 text-sm font-medium rounded-lg bg-violet-500 text-white hover:bg-violet-600 transition-colors disabled:opacity-50"
+                  >
+                    {created
+                      ? t("created")
+                      : suggestion.alreadyExists
+                        ? t("alreadyCreated")
+                        : creating
+                          ? t("generating")
+                          : t("generateButton")}
+                  </button>
+                </div>
+              </Card>
+            );
+          })}
+        </div>
+      )}
+    </div>
+  );
+}

src/app/(dashboard)/dashboard/radar/intel/page.tsx

@@ -0,0 +1,197 @@
+"use client";
+
+import { useCallback, useEffect, useState } from "react";
+import Link from "next/link";
+import { notFound } from "next/navigation";
+import { useTranslations } from "next-intl";
+
+import type { RadarIntelFeed } from "@/lib/radar/intelFeedSchema";
+import { Card } from "@/shared/components";
+
+interface IntelMeta {
+  version: string;
+  tier: "live";
+  fetchedAt: string;
+  supporterVerified: true;
+}
+
+export default function RadarIntelPage() {
+  const t = useTranslations("radarIntelPage");
+  const [intel, setIntel] = useState<RadarIntelFeed | null>(null);
+  const [meta, setMeta] = useState<IntelMeta | null>(null);
+  const [loading, setLoading] = useState(true);
+  const [syncing, setSyncing] = useState(false);
+  const [flagOff, setFlagOff] = useState(false);
+  const [error, setError] = useState("");
+
+  const load = useCallback(async () => {
+    const response = await fetch("/api/radar/intel");
+    if (response.status === 404) {
+      setFlagOff(true);
+      return;
+    }
+    if (!response.ok) throw new Error("intel_load_failed");
+    const body = (await response.json()) as {
+      intel?: RadarIntelFeed | null;
+      meta?: IntelMeta | null;
+    };
+    setIntel(body.intel ?? null);
+    setMeta(body.meta ?? null);
+  }, []);
+
+  const sync = useCallback(async () => {
+    setSyncing(true);
+    setError("");
+    try {
+      const response = await fetch("/api/radar/intel/sync", { method: "POST" });
+      if (response.status === 404) {
+        setFlagOff(true);
+        return;
+      }
+      if (!response.ok) throw new Error("intel_sync_failed");
+      const status = (await response.json()) as { status?: string };
+      if (
+        ["error", "invalid_signature", "invalid_schema", "wrong_tier", "too_large"].includes(
+          status.status ?? ""
+        )
+      ) {
+        setError(t("loadFailed"));
+      }
+      await load();
+    } catch {
+      setError(t("loadFailed"));
+      await load().catch(() => undefined);
+    } finally {
+      setSyncing(false);
+    }
+  }, [load, t]);
+
+  useEffect(() => {
+    load()
+      .catch(() => setError(t("loadFailed")))
+      .finally(() => setLoading(false));
+  }, [load, t]);
+
+  if (flagOff) notFound();
+
+  return (
+    <div className="flex flex-col gap-6">
+      <div className="flex flex-wrap items-start justify-between gap-3">
+        <div>
+          <Link
+            href="/dashboard/radar"
+            className="text-sm text-text-muted hover:text-text-main transition-colors"
+          >
+            ← {t("backToRadar")}
+          </Link>
+          <h1 className="mt-3 text-2xl font-bold">{t("title")}</h1>
+          <p className="mt-1 text-sm text-text-muted">{t("subtitle")}</p>
+        </div>
+        <div className="flex items-center gap-2">
+          {meta?.supporterVerified === true && (
+            <span
+              data-badge-id="radar-supporter"
+              className="rounded-full border border-violet-500 px-3 py-1 text-sm text-violet-300"
+            >
+              {t("supporterBadge")}
+            </span>
+          )}
+          <button
+            type="button"
+            onClick={() => void sync()}
+            disabled={syncing}
+            className="rounded-lg border border-violet-500 px-4 py-2 text-sm font-medium text-violet-400 disabled:opacity-50"
+          >
+            {syncing ? t("syncing") : t("refresh")}
+          </button>
+        </div>
+      </div>
+
+      {error && <div className="rounded-lg bg-red-500/10 p-3 text-sm text-red-400">{error}</div>}
+
+      {loading ? (
+        <div className="flex min-h-48 items-center justify-center text-text-muted">
+          {t("loading")}
+        </div>
+      ) : !intel || !meta ? (
+        <Card>
+          <p className="py-8 text-center text-text-muted">{t("empty")}</p>
+        </Card>
+      ) : (
+        <>
+          <div className="grid gap-4 md:grid-cols-3">
+            <Card>
+              <p className="text-xs uppercase tracking-wide text-text-muted">{t("methodology")}</p>
+              <p className="mt-2 font-semibold">
+                {t("eloMethod", {
+                  initial: intel.methodology.initialRating,
+                  factor: intel.methodology.kFactor,
+                })}
+              </p>
+            </Card>
+            <Card>
+              <p className="text-xs uppercase tracking-wide text-text-muted">{t("freshness")}</p>
+              <p className="mt-2 font-semibold">
+                {t(`freshnessValues.${intel.catalog.freshness}`)}
+              </p>
+              <p className="mt-1 text-sm text-text-muted">
+                {t("ageDays", { days: intel.catalog.ageDays })}
+              </p>
+            </Card>
+            <Card>
+              <p className="text-xs uppercase tracking-wide text-text-muted">{t("trend")}</p>
+              <p className="mt-2 font-semibold">{t(`trendValues.${intel.catalog.trend}`)}</p>
+              <p className="mt-1 text-sm text-text-muted">
+                {t("modelDelta", {
+                  current: intel.catalog.models.current,
+                  added: intel.catalog.models.added,
+                  removed: intel.catalog.models.removed,
+                })}
+              </p>
+            </Card>
+          </div>
+
+          <Card>
+            <div className="mb-4 flex items-center justify-between gap-3">
+              <h2 className="text-lg font-semibold">{t("ranking")}</h2>
+              <span className="text-xs text-text-muted">{meta.version}</span>
+            </div>
+            {intel.rankings.length === 0 ? (
+              <p className="py-6 text-center text-text-muted">{t("noRankings")}</p>
+            ) : (
+              <div className="overflow-x-auto">
+                <table className="w-full text-left text-sm">
+                  <thead className="text-text-muted">
+                    <tr>
+                      <th className="pb-3">#</th>
+                      <th className="pb-3">{t("model")}</th>
+                      <th className="pb-3">{t("category")}</th>
+                      <th className="pb-3 text-right">{t("rating")}</th>
+                      <th className="pb-3 text-right">{t("matches")}</th>
+                    </tr>
+                  </thead>
+                  <tbody>
+                    {intel.rankings.map((ranking) => (
+                      <tr
+                        key={`${ranking.category}:${ranking.provider}:${ranking.modelId}`}
+                        className="border-t border-border"
+                      >
+                        <td className="py-3">{ranking.rank}</td>
+                        <td className="py-3 font-mono">
+                          {ranking.provider}/{ranking.modelId}
+                        </td>
+                        <td className="py-3">{ranking.category}</td>
+                        <td className="py-3 text-right">{ranking.rating}</td>
+                        <td className="py-3 text-right">{ranking.matches}</td>
+                      </tr>
+                    ))}
+                  </tbody>
+                </table>
+              </div>
+            )}
+          </Card>
+        </>
+      )}
+    </div>
+  );
+}

src/app/(dashboard)/dashboard/radar/offers/page.tsx

@@ -0,0 +1,273 @@
+"use client";
+
+import { useCallback, useEffect, useMemo, useState } from "react";
+import Link from "next/link";
+import { notFound } from "next/navigation";
+import { useLocale, useTranslations } from "next-intl";
+
+import {
+  filterActiveRadarOffers,
+  localizeRadarOfferText,
+  type RadarOffer,
+  type RadarOfferBenefit,
+} from "@/lib/radar/offersFeedSchema";
+import { Card } from "@/shared/components";
+
+interface OffersMeta {
+  version: string;
+  tier: "live";
+  fetchedAt: string;
+}
+
+interface SettingsPayload {
+  hasSupporterKey?: boolean;
+  contributorClaimUrl?: string;
+  supporterPlansUrl?: string;
+}
+
+export default function RadarOffersPage() {
+  const t = useTranslations("radarOffersPage");
+  const locale = useLocale();
+  const [offers, setOffers] = useState<RadarOffer[]>([]);
+  const [meta, setMeta] = useState<OffersMeta | null>(null);
+  const [hasSupporterKey, setHasSupporterKey] = useState(false);
+  const [contributorClaimUrl, setContributorClaimUrl] = useState<string | null>(null);
+  const [supporterPlansUrl, setSupporterPlansUrl] = useState<string | null>(null);
+  const [loading, setLoading] = useState(true);
+  const [refreshing, setRefreshing] = useState(false);
+  const [flagOff, setFlagOff] = useState(false);
+  const [error, setError] = useState("");
+
+  const loadOffers = useCallback(async () => {
+    const response = await fetch("/api/radar/offers");
+    if (response.status === 404) {
+      setFlagOff(true);
+      return;
+    }
+    if (!response.ok) throw new Error("offers_load_failed");
+    const body = (await response.json()) as { offers?: RadarOffer[]; meta?: OffersMeta | null };
+    setOffers(Array.isArray(body.offers) ? body.offers : []);
+    setMeta(body.meta ?? null);
+  }, []);
+
+  const syncAndLoad = useCallback(async () => {
+    setRefreshing(true);
+    setError("");
+    try {
+      const response = await fetch("/api/radar/offers/sync", { method: "POST" });
+      if (response.status === 404) {
+        setFlagOff(true);
+        return;
+      }
+      if (!response.ok) throw new Error("offers_sync_failed");
+      const status = (await response.json()) as { status?: string; reason?: string };
+      if (status.status === "no_key") {
+        setHasSupporterKey(false);
+        return;
+      }
+      if (
+        status.status === "error" ||
+        status.status === "invalid_signature" ||
+        status.status === "invalid_schema" ||
+        status.status === "wrong_tier" ||
+        status.status === "too_large"
+      ) {
+        setError(t("loadFailed"));
+      }
+      // Preserve availability: even when refresh fails, render the last
+      // verified local cache rather than clearing it.
+      await loadOffers();
+    } catch {
+      setError(t("loadFailed"));
+      try {
+        await loadOffers();
+      } catch {
+        // The primary error already explains the failed local read.
+      }
+    } finally {
+      setRefreshing(false);
+    }
+  }, [loadOffers, t]);
+
+  useEffect(() => {
+    async function load(): Promise<void> {
+      try {
+        const response = await fetch("/api/radar/settings");
+        if (response.status === 404) {
+          setFlagOff(true);
+          return;
+        }
+        if (!response.ok) throw new Error("settings_load_failed");
+        const settings = (await response.json()) as SettingsPayload;
+        const hasKey = settings.hasSupporterKey === true;
+        setHasSupporterKey(hasKey);
+        setContributorClaimUrl(
+          typeof settings.contributorClaimUrl === "string" ? settings.contributorClaimUrl : null
+        );
+        setSupporterPlansUrl(
+          typeof settings.supporterPlansUrl === "string" ? settings.supporterPlansUrl : null
+        );
+        if (hasKey) await syncAndLoad();
+      } catch {
+        setError(t("loadFailed"));
+      } finally {
+        setLoading(false);
+      }
+    }
+    void load();
+  }, [syncAndLoad, t]);
+
+  const activeOffers = useMemo(() => filterActiveRadarOffers(offers, new Date()), [offers]);
+
+  const formatBenefit = useCallback(
+    (benefit: RadarOfferBenefit): string => {
+      if (benefit.kind === "percent_off") {
+        return `${new Intl.NumberFormat(locale, { maximumFractionDigits: 2 }).format(
+          benefit.basisPoints / 100
+        )}%`;
+      }
+      if (benefit.kind === "credit") {
+        return new Intl.NumberFormat(locale, {
+          style: "currency",
+          currency: benefit.currency,
+        }).format(benefit.amountMinor / 100);
+      }
+      return t("trialDays", { days: benefit.days });
+    },
+    [locale, t]
+  );
+
+  if (flagOff) notFound();
+
+  return (
+    <div className="flex flex-col gap-6">
+      <div className="flex flex-col gap-3">
+        <Link
+          href="/dashboard/radar"
+          className="text-sm text-text-muted hover:text-text-main transition-colors w-fit"
+        >
+          ← {t("backToRadar")}
+        </Link>
+        <div className="flex flex-wrap items-start justify-between gap-3">
+          <div>
+            <h1 className="text-2xl font-bold">{t("title")}</h1>
+            <p className="text-sm text-text-muted mt-1">{t("subtitle")}</p>
+          </div>
+          {hasSupporterKey && (
+            <button
+              type="button"
+              onClick={() => void syncAndLoad()}
+              disabled={refreshing}
+              className="px-4 py-2 text-sm font-medium rounded-lg border border-violet-500 text-violet-400 hover:bg-violet-500/10 transition-colors disabled:opacity-50"
+            >
+              {refreshing ? t("refreshing") : t("refresh")}
+            </button>
+          )}
+        </div>
+      </div>
+
+      {error && <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>}
+
+      {loading ? (
+        <div className="flex min-h-48 items-center justify-center text-text-muted">
+          {t("loading")}
+        </div>
+      ) : !hasSupporterKey ? (
+        <Card>
+          <div className="flex flex-col items-center gap-4 py-8 text-center">
+            <span className="material-symbols-outlined text-4xl text-violet-400">redeem</span>
+            <h2 className="text-xl font-semibold">{t("keyRequiredTitle")}</h2>
+            <p className="max-w-xl text-text-muted">{t("keyRequiredDescription")}</p>
+            <div className="flex flex-col sm:flex-row gap-3">
+              {contributorClaimUrl && (
+                <a
+                  href={contributorClaimUrl}
+                  target="_blank"
+                  rel="noopener noreferrer"
+                  className="px-4 py-2 rounded-lg border border-violet-500 text-violet-400 hover:bg-violet-500/10"
+                >
+                  {t("contributorButton")}
+                </a>
+              )}
+              {supporterPlansUrl && (
+                <a
+                  href={supporterPlansUrl}
+                  target="_blank"
+                  rel="noopener noreferrer"
+                  className="px-4 py-2 rounded-lg bg-violet-500 text-white hover:bg-violet-600"
+                >
+                  {t("supporterButton")}
+                </a>
+              )}
+            </div>
+          </div>
+        </Card>
+      ) : activeOffers.length === 0 ? (
+        <Card>
+          <p className="py-8 text-center text-text-muted">{t("empty")}</p>
+        </Card>
+      ) : (
+        <div className="grid gap-4 md:grid-cols-2 xl:grid-cols-3">
+          {activeOffers.map((offer) => (
+            <Card key={`${offer.provider}:${offer.id}`}>
+              <div className="flex h-full flex-col gap-4">
+                <div className="flex items-start justify-between gap-3">
+                  <div>
+                    <p className="text-xs uppercase tracking-wide text-text-muted">
+                      {offer.provider}
+                    </p>
+                    <h2 className="text-lg font-semibold">
+                      {localizeRadarOfferText(offer.title, locale)}
+                    </h2>
+                  </div>
+                  <span
+                    className={`rounded-full px-2 py-1 text-xs font-medium ${
+                      offer.partner
+                        ? "bg-violet-500/15 text-violet-300"
+                        : "bg-green-500/15 text-green-300"
+                    }`}
+                  >
+                    {offer.partner ? t("partnerBadge") : t("officialBadge")}
+                  </span>
+                </div>
+
+                <p className="text-2xl font-bold text-violet-300">{formatBenefit(offer.benefit)}</p>
+                <p className="text-sm text-text-muted">
+                  {localizeRadarOfferText(offer.description, locale)}
+                </p>
+                <div className="text-sm">
+                  <span className="font-medium">{t("conditionsLabel")}</span>{" "}
+                  <span className="text-text-muted">
+                    {localizeRadarOfferText(offer.conditions, locale)}
+                  </span>
+                </div>
+                <p className="text-xs text-text-muted">
+                  {offer.validUntil
+                    ? t("validUntil", {
+                        date: new Date(offer.validUntil).toLocaleDateString(locale),
+                      })
+                    : t("noExpiry")}
+                </p>
+                <a
+                  href={offer.url}
+                  target="_blank"
+                  rel="noopener noreferrer"
+                  className="mt-auto inline-flex w-fit items-center gap-1 text-sm font-medium text-violet-400 hover:underline"
+                >
+                  {t("openOffer")}
+                  <span className="material-symbols-outlined text-sm">open_in_new</span>
+                </a>
+              </div>
+            </Card>
+          ))}
+        </div>
+      )}
+
+      {meta && (
+        <p className="text-xs text-text-muted">
+          {meta.version} · {new Date(meta.fetchedAt).toLocaleString(locale)}
+        </p>
+      )}
+    </div>
+  );
+}

src/app/(dashboard)/dashboard/radar/page.tsx

@@ -2,11 +2,12 @@
 
 import { useState, useEffect, useCallback, useRef } from "react";
 import { useTranslations } from "next-intl";
-import { notFound } from "next/navigation";
 import Link from "next/link";
+import { notFound } from "next/navigation";
 import { Card } from "@/shared/components";
 import { shouldAutoSyncOnOpen } from "@/lib/radar/autoSync";
 import { isValidSupporterKeyFormat } from "@/lib/radar/supporterKey";
+import { RadarCatalogTable, type RadarMergedEntry } from "./RadarCatalogTable";
 
 // ---------------------------------------------------------------------------
 // Types
@@ -18,27 +19,6 @@ interface RadarMeta {
   fetchedAt: string;
 }
 
-interface RadarMergedEntry {
-  provider: string;
-  modelId: string;
-  displayName: string;
-  monthlyTokens: number;
-  creditTokens: number;
-  freeType: string;
-  poolKey: string | null;
-  tos: string;
-  trainsOnPrompts?: boolean;
-  enabled?: boolean;
-  origin: "baseline" | "radar" | "local";
-  disabledBy?: "radar";
-  // Extended feed fields (present when origin=radar)
-  contextWindow?: number | null;
-  capabilities?: { tools: boolean; vision: boolean; thinking: boolean };
-  budget?: { kind: string; tokensPerMonth?: number; poolId?: string };
-  limits?: { rpm: number | null; rpd: number | null; tpm: number | null; tpd: number | null };
-  setup?: { keyUrl: string | null; steps: string[] } | null;
-}
-
 type PageState = "flag_off" | "optin_pending" | "empty" | "populated";
 
 /** D28 — referral links / free credits. Client-side mirror of RadarReferral. */
@@ -67,7 +47,7 @@ type RadarTabId = "catalog" | "referrals";
 export function resolveRadarPageState(
   flagOn: boolean,
   optedIn: boolean,
-  hasEntries: boolean,
+  hasEntries: boolean
 ): PageState {
   if (!flagOn) return "flag_off";
   if (!optedIn) return "optin_pending";
@@ -90,23 +70,6 @@ function relativeTime(isoDate: string): string {
   return `${days}d ago`;
 }
 
-/** Format token count as human-readable. */
-function formatTokens(n: number): string {
-  if (n === 0) return "rate-only";
-  if (n >= 1_000_000) return `${(n / 1_000_000).toFixed(1)}M`;
-  if (n >= 1_000) return `${(n / 1_000).toFixed(0)}K`;
-  return String(n);
-}
-
-/** Budget display string. */
-function budgetLabel(entry: RadarMergedEntry): string {
-  if (entry.budget?.kind === "shared_pool") {
-    return `shared (${formatTokens(entry.budget.tokensPerMonth ?? entry.monthlyTokens)}/mo)`;
-  }
-  if (entry.budget?.kind === "rate_only" || entry.monthlyTokens === 0) return "rate-only";
-  return `${formatTokens(entry.monthlyTokens)}/mo`;
-}
-
 // ---------------------------------------------------------------------------
 // Page Component
 // ---------------------------------------------------------------------------
@@ -144,31 +107,34 @@ export default function RadarPage() {
   const [hasSupporterKey, setHasSupporterKey] = useState(false);
   const [supporterKeyMasked, setSupporterKeyMasked] = useState<string | null>(null);
   const [showKeyForm, setShowKeyForm] = useState(false);
-
   // Fetch catalog
-  const fetchCatalog = useCallback(async () => {
-    setLoading(true);
-    setError("");
-    try {
-      const res = await fetch("/api/radar/catalog");
-      if (res.status === 404) {
-        // Flag off — treat as not found
-        setOptIn(false);
-        setEntries([]);
-        setMeta(null);
-        setLoading(false);
-        return;
+  const fetchCatalog = useCallback(
+    async (showLoading = true) => {
+      if (showLoading) setLoading(true);
+      setError("");
+      try {
+        const res = await fetch("/api/radar/catalog");
+        if (res.status === 404) {
+          // Flag off — treat as not found
+          setOptIn(false);
+          setEntries([]);
+          setMeta(null);
+          if (showLoading) setLoading(false);
+          return;
+        }
+        if (!res.ok) throw new Error(`HTTP ${res.status}`);
+        const data = await res.json();
+        setEntries(data.entries || []);
+        setMeta(data.meta || null);
+      } catch (err) {
+        setError(err instanceof Error ? err.message : t("errorLoading"));
+      } finally {
+        if (showLoading) setLoading(false);
       }
-      if (!res.ok) throw new Error(`HTTP ${res.status}`);
-      const data = await res.json();
-      setEntries(data.entries || []);
-      setMeta(data.meta || null);
-    } catch (err) {
-      setError(err instanceof Error ? err.message : t("errorLoading"));
-    } finally {
-      setLoading(false);
-    }
-  }, [t]);
+    },
+    [t]
+  );
+  const refreshCatalogSilently = useCallback(() => fetchCatalog(false), [fetchCatalog]);
 
   // D28 — fetch the referral links section ("Pegue seus créditos grátis").
   // Best-effort: flag off => 404, no cache => empty shape; either way this
@@ -204,7 +170,7 @@ export default function RadarPage() {
       setOptIn(settingsData.optIn === true);
       setHasSupporterKey(settingsData.hasSupporterKey === true);
       setSupporterKeyMasked(
-        typeof settingsData.supporterKeyMasked === "string" ? settingsData.supporterKeyMasked : null,
+        typeof settingsData.supporterKeyMasked === "string" ? settingsData.supporterKeyMasked : null
       );
       // F4/T7 — best-effort: keep whatever we already had if the field is
       // absent (older cached response shape), never fall back to a literal.
@@ -334,7 +300,7 @@ export default function RadarPage() {
   const pageState = resolveRadarPageState(
     optIn !== false, // if we got a 404, optIn=false => flag off
     optIn === true,
-    entries.length > 0 && meta !== null,
+    meta !== null
   );
 
   // Flag off — render not-found
@@ -350,15 +316,41 @@ export default function RadarPage() {
           <h1 className="text-2xl font-bold">{t("title")}</h1>
           <p className="text-sm text-text-muted mt-1">{t("subtitle")}</p>
         </div>
-        {pageState === "populated" && (
-          <button
-            onClick={handleSync}
-            disabled={syncing}
-            className="px-4 py-2 text-sm font-medium rounded-lg border border-violet-500 text-violet-400 hover:bg-violet-500/10 transition-colors disabled:opacity-50"
-          >
-            {syncing ? t("syncing") : t("syncNow")}
-          </button>
-        )}
+        <div className="flex items-center gap-2">
+          {(pageState === "empty" || pageState === "populated") && (
+            <Link
+              href="/dashboard/radar/intel"
+              className="px-4 py-2 text-sm font-medium rounded-lg border border-border text-text-main hover:border-violet-500 hover:text-violet-400 transition-colors"
+            >
+              {t("intel")}
+            </Link>
+          )}
+          {(pageState === "empty" || pageState === "populated") && (
+            <Link
+              href="/dashboard/radar/offers"
+              className="px-4 py-2 text-sm font-medium rounded-lg border border-border text-text-main hover:border-violet-500 hover:text-violet-400 transition-colors"
+            >
+              {t("offers")}
+            </Link>
+          )}
+          {(pageState === "empty" || pageState === "populated") && (
+            <Link
+              href="/dashboard/radar/combos"
+              className="px-4 py-2 text-sm font-medium rounded-lg border border-border text-text-main hover:border-violet-500 hover:text-violet-400 transition-colors"
+            >
+              {t("guidedCombos")}
+            </Link>
+          )}
+          {pageState === "populated" && (
+            <button
+              onClick={handleSync}
+              disabled={syncing}
+              className="px-4 py-2 text-sm font-medium rounded-lg border border-violet-500 text-violet-400 hover:bg-violet-500/10 transition-colors disabled:opacity-50"
+            >
+              {syncing ? t("syncing") : t("syncNow")}
+            </button>
+          )}
+        </div>
       </div>
 
       {/* Feed freshness header */}
@@ -379,9 +371,7 @@ export default function RadarPage() {
         </div>
       )}
 
-      {error && (
-        <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>
-      )}
+      {error && <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>}
 
       {loading ? (
         <div className="flex items-center justify-center min-h-[200px]">
@@ -625,98 +615,11 @@ export default function RadarPage() {
 
           {/* Populated catalog table */}
           {pageState === "populated" && activeTab === "catalog" && (
-            <Card>
-              <div className="overflow-x-auto">
-                <table className="w-full">
-                  <thead>
-                    <tr className="text-left text-sm text-text-muted border-b border-border">
-                      <th className="pb-3 font-medium">{t("colProvider")}</th>
-                      <th className="pb-3 font-medium">{t("colModel")}</th>
-                      <th className="pb-3 font-medium">{t("colQuota")}</th>
-                      <th className="pb-3 font-medium">{t("colContext")}</th>
-                      <th className="pb-3 font-medium">{t("colCapabilities")}</th>
-                      <th className="pb-3 font-medium">{t("colTos")}</th>
-                    </tr>
-                  </thead>
-                  <tbody>
-                    {entries.map((entry) => (
-                      <tr
-                        key={`${entry.provider}:${entry.modelId}`}
-                        className={`border-b border-border/50 last:border-b-0 ${
-                          entry.enabled === false ? "opacity-50" : ""
-                        }`}
-                      >
-                        <td className="py-3">
-                          <div className="flex items-center gap-2">
-                            <span className="font-medium">{entry.provider}</span>
-                            {entry.origin === "radar" && (
-                              <span className="text-[10px] px-1.5 py-0.5 rounded bg-violet-500/10 text-violet-400 font-medium">
-                                {t("newBadge")}
-                              </span>
-                            )}
-                            {entry.setup?.keyUrl && (
-                              <Link
-                                href={`/dashboard/radar/setup?provider=${encodeURIComponent(entry.provider)}`}
-                                className="text-xs text-violet-400 hover:underline"
-                                title={t("setupGuide")}
-                              >
-                                ⚙
-                              </Link>
-                            )}
-                          </div>
-                          {entry.enabled === false && entry.disabledBy === "radar" && (
-                            <p className="text-xs text-red-400 mt-0.5">{t("disabledByFeed")}</p>
-                          )}
-                        </td>
-                        <td className="py-3 text-text-muted text-sm font-mono truncate max-w-[200px]">
-                          {entry.displayName}
-                        </td>
-                        <td className="py-3 text-sm">{budgetLabel(entry)}</td>
-                        <td className="py-3 text-sm text-text-muted">
-                          {entry.contextWindow
-                            ? `${(entry.contextWindow / 1000).toFixed(0)}K`
-                            : "—"}
-                        </td>
-                        <td className="py-3">
-                          <div className="flex gap-1">
-                            {entry.capabilities?.tools && (
-                              <span className="text-[10px] px-1.5 py-0.5 rounded bg-blue-500/10 text-blue-400">
-                                {t("capTools")}
-                              </span>
-                            )}
-                            {entry.capabilities?.vision && (
-                              <span className="text-[10px] px-1.5 py-0.5 rounded bg-purple-500/10 text-purple-400">
-                                {t("capVision")}
-                              </span>
-                            )}
-                            {entry.capabilities?.thinking && (
-                              <span className="text-[10px] px-1.5 py-0.5 rounded bg-amber-500/10 text-amber-400">
-                                {t("capThinking")}
-                              </span>
-                            )}
-                          </div>
-                        </td>
-                        <td className="py-3">
-                          <span
-                            className={`text-xs px-2 py-1 rounded ${
-                              entry.tos === "ok"
-                                ? "bg-green-500/10 text-green-400"
-                                : entry.tos === "caution"
-                                  ? "bg-yellow-500/10 text-yellow-400"
-                                  : entry.tos === "avoid"
-                                    ? "bg-red-500/10 text-red-400"
-                                    : "bg-gray-500/10 text-gray-400"
-                            }`}
-                          >
-                            {entry.tos}
-                          </span>
-                        </td>
-                      </tr>
-                    ))}
-                  </tbody>
-                </table>
-              </div>
-            </Card>
+            <RadarCatalogTable
+              entries={entries}
+              refreshCatalog={refreshCatalogSilently}
+              onError={setError}
+            />
           )}
         </>
       )}

src/app/(dashboard)/dashboard/radar/setup/page.tsx

@@ -1,10 +1,16 @@
 "use client";
 
-import { useState, useEffect, useCallback, useMemo } from "react";
-import { useTranslations } from "next-intl";
+import { useState, useEffect, useCallback } from "react";
+import { useLocale, useTranslations } from "next-intl";
 import { useSearchParams } from "next/navigation";
 import Link from "next/link";
 import { Card } from "@/shared/components";
+import {
+  firstProviderConnectionId,
+  providerConnectionsRequestUrl,
+  type RadarSetupConnection,
+} from "@/lib/radar/setupConnections";
+import type { RadarLocalizedText } from "@/lib/radar/feedSchema";
 
 // ---------------------------------------------------------------------------
 // Types
@@ -14,17 +20,16 @@ import { Card } from "@/shared/components";
  * Localized text: either a plain string or an {en, pt?} object.
  * The renderer resolves the best locale with EN fallback (D25 compat).
  */
-type LocalizedText = string | { en: string; pt?: string };
-
 interface SetupInfo {
   keyUrl: string | null;
-  steps: LocalizedText[];
+  steps: RadarLocalizedText[];
 }
 
 interface ProviderSetupData {
   provider: string;
   setup: SetupInfo | null;
   configured: boolean;
+  connectionId: string | null;
 }
 
 // ---------------------------------------------------------------------------
@@ -32,9 +37,9 @@ interface ProviderSetupData {
 // ---------------------------------------------------------------------------
 
 /** Resolve a LocalizedText to a display string. */
-function resolveText(text: LocalizedText, locale: string): string {
+function resolveText(text: RadarLocalizedText, locale: string): string {
   if (typeof text === "string") return text;
-  if (locale === "pt" && text.pt) return text.pt;
+  if (locale.toLowerCase().startsWith("pt") && text.pt) return text.pt;
   return text.en;
 }
 
@@ -44,9 +49,9 @@ function resolveText(text: LocalizedText, locale: string): string {
 
 export default function RadarSetupPage() {
   const t = useTranslations("radarSetupPage");
+  const locale = useLocale();
   const searchParams = useSearchParams();
   const provider = searchParams.get("provider");
-  const locale = "en"; // Could be derived from next-intl locale later
 
   const [setupData, setSetupData] = useState<ProviderSetupData | null>(null);
   const [loading, setLoading] = useState(true);
@@ -63,18 +68,25 @@ export default function RadarSetupPage() {
 
     async function load() {
       try {
-        const res = await fetch("/api/radar/catalog");
+        const [res, connectionsRes] = await Promise.all([
+          fetch("/api/radar/catalog"),
+          fetch(providerConnectionsRequestUrl(provider)),
+        ]);
         if (res.status === 404) {
           setError(t("flagDisabled"));
           setLoading(false);
           return;
         }
         if (!res.ok) throw new Error(`HTTP ${res.status}`);
+        if (!connectionsRes.ok) throw new Error(`HTTP ${connectionsRes.status}`);
         const data = await res.json();
+        const connectionsData = (await connectionsRes.json()) as {
+          connections?: RadarSetupConnection[];
+        };
 
         // Find ALL entries for this provider and extract setup from the first one that has it
         const providerEntries = data.entries.filter(
-          (e: { provider: string }) => e.provider === provider,
+          (e: { provider: string }) => e.provider === provider
         );
 
         if (providerEntries.length === 0) {
@@ -85,17 +97,19 @@ export default function RadarSetupPage() {
 
         // Find setup info from feed entries (they carry the setup field)
         const entryWithSetup = providerEntries.find(
-          (e: { setup?: SetupInfo | null }) => e.setup && (e.setup.steps.length > 0 || e.setup.keyUrl),
+          (e: { setup?: SetupInfo | null }) =>
+            e.setup && (e.setup.steps.length > 0 || e.setup.keyUrl)
         );
 
-        // Check if provider is configured (has connections)
-        // We infer this from whether the provider exists in the catalog at all
-        // The actual connection check would need a separate API — for now we show
-        // the guide regardless
+        const connectionId = firstProviderConnectionId(
+          Array.isArray(connectionsData.connections) ? connectionsData.connections : [],
+          provider
+        );
         setSetupData({
           provider,
           setup: entryWithSetup?.setup ?? null,
-          configured: false, // Will be enriched when connection-status API is available
+          configured: connectionId !== null,
+          connectionId,
         });
       } catch (err) {
         setError(err instanceof Error ? err.message : t("loadFailed"));
@@ -109,15 +123,11 @@ export default function RadarSetupPage() {
 
   // Test connection — uses the EXISTING connection-test endpoint
   const handleTestConnection = useCallback(async () => {
-    if (!provider) return;
+    if (!setupData?.connectionId) return;
     setTesting(true);
     setTestResult(null);
     try {
-      // The existing test endpoint is POST /api/providers/[id]/test
-      // We need the connection ID — for now we use the provider ID as a proxy.
-      // In a full implementation, the setup page would list connections for
-      // this provider and test each one. Here we test the first connection.
-      const res = await fetch(`/api/providers/${encodeURIComponent(provider)}/test`, {
+      const res = await fetch(`/api/providers/${encodeURIComponent(setupData.connectionId)}/test`, {
         method: "POST",
         headers: { "Content-Type": "application/json" },
         body: JSON.stringify({}),
@@ -136,7 +146,7 @@ export default function RadarSetupPage() {
     } finally {
       setTesting(false);
     }
-  }, [provider, t]);
+  }, [setupData?.connectionId, t]);
 
   if (!provider) {
     return (
@@ -165,9 +175,7 @@ export default function RadarSetupPage() {
         <p className="text-sm text-text-muted mt-1">{t("setupSubtitle")}</p>
       </div>
 
-      {error && (
-        <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>
-      )}
+      {error && <div className="p-3 rounded-lg bg-red-500/10 text-red-400 text-sm">{error}</div>}
 
       {loading ? (
         <div className="flex items-center justify-center min-h-[200px]">
@@ -248,15 +256,13 @@ export default function RadarSetupPage() {
               <div className="flex items-center gap-3">
                 <button
                   onClick={handleTestConnection}
-                  disabled={testing}
+                  disabled={testing || !setupData.connectionId}
                   className="px-4 py-2 text-sm font-medium rounded-lg border border-violet-500 text-violet-400 hover:bg-violet-500/10 transition-colors disabled:opacity-50"
                 >
                   {testing ? t("testing") : t("testButton")}
                 </button>
                 {testResult && (
-                  <span
-                    className={`text-sm ${testResult.ok ? "text-green-400" : "text-red-400"}`}
-                  >
+                  <span className={`text-sm ${testResult.ok ? "text-green-400" : "text-red-400"}`}>
                     {testResult.message}
                   </span>
                 )}

src/app/(dashboard)/home/page.tsx

@@ -4,6 +4,7 @@ import { getSettings } from "@/lib/localDb";
 import HomePageClient from "../dashboard/HomePageClient";
 import BootstrapBanner from "../dashboard/BootstrapBanner";
 import KimiSponsorBanner from "../dashboard/KimiSponsorBanner";
+import NewsBanner from "../dashboard/NewsBanner";
 
 export const dynamic = "force-dynamic";
 
@@ -18,6 +19,7 @@ export default async function HomePage() {
     <>
       {isBootstrapped && <BootstrapBanner />}
       <KimiSponsorBanner />
+      <NewsBanner />
       <HomePageClient machineId={machineId} />
     </>
   );

src/app/api/memory/[id]/route.ts

@@ -1,10 +1,6 @@
 import { NextResponse } from "next/server";
 import { requireManagementAuth } from "@/lib/api/requireManagementAuth";
-// Import through the module index, NOT "@/lib/memory/manager" directly: the index's
-// import-time side effect is what calls memoryManager.register(sqliteBackend). Importing
-// the bare manager gives an EMPTY registry, so every handler here threw
-// `Primary backend "sqlite" not registered` and returned 500 (#8752).
-import { memoryManager } from "@/lib/memory";
+import { memoryManager } from "@/lib/memory/manager";
 import { validateBody, isValidationFailure } from "@/shared/validation/helpers";
 import { MemoryUpdatePutSchema } from "@/shared/schemas/memory";
 import { sanitizeErrorMessage } from "@omniroute/open-sse/utils/error.ts";

src/app/api/plugins/marketplace/install/route.ts

@@ -1,14 +1,9 @@
 import { NextRequest, NextResponse } from "next/server";
-import { z } from "zod";
 import { CORS_HEADERS, handleCorsOptions } from "@/shared/utils/cors";
 import { buildErrorBody } from "@omniroute/open-sse/utils/error";
 import { installMarketplacePlugin } from "@/lib/plugins/marketplace";
 import { requireManagementAuth } from "@/lib/api/requireManagementAuth";
 
-const InstallBodySchema = z.object({
-  name: z.string().trim().min(1),
-});
-
 export async function OPTIONS() {
   return handleCorsOptions();
 }
@@ -20,14 +15,15 @@ export async function POST(request: NextRequest) {
   const authError = await requireManagementAuth(request);
   if (authError) return authError;
   try {
-    const parsed = InstallBodySchema.safeParse(await request.json());
-    if (!parsed.success) {
+    const body = await request.json();
+    const { name } = body as { name?: string };
+    if (!name || typeof name !== "string") {
       return NextResponse.json(buildErrorBody(400, "Missing or invalid 'name' field"), {
         status: 400,
         headers: CORS_HEADERS,
       });
     }
-    const result = await installMarketplacePlugin(parsed.data.name);
+    const result = await installMarketplacePlugin(name);
     return NextResponse.json(result, { status: 201, headers: CORS_HEADERS });
   } catch (err: unknown) {
     const msg = err instanceof Error ? err.message : "Failed to install marketplace plugin";

src/app/api/providers/[id]/test/route.ts

@@ -701,17 +701,6 @@ export async function testSingleConnection(connectionId: string, validationModel
       ? makeDiagnosis("ok", "local", null, null)
       : classifyFailure({ error: result.error, statusCode: result.statusCode, provider }));
 
-  // #9623: a failed connection test must not paint the connection permanently red.
-  // Previously a non-terminal failure wrote `testStatus: "error"` with
-  // `rateLimitedUntil: null` — since the cooldown filter only ever skips entries
-  // whose rateLimitedUntil is in the future, a null cooldown left the connection
-  // permanently unavailable after a transient outage. Give non-terminal test
-  // failures a short cooldown so the lazy-recovery path retries them.
-  const terminalTestStatuses = new Set(["banned", "expired", "credits_exhausted"]);
-  const isTerminalFailure =
-    !result.valid && terminalTestStatuses.has(String(diagnosis.code ?? diagnosis.type ?? "").toLowerCase());
-  const testFailureCooldownMs = result.valid ? 0 : 30_000; // 30s retry window
-
   const updateData: Record<string, any> = {
     testStatus: result.valid ? "active" : "error",
     lastError: result.valid ? null : result.error,
@@ -720,12 +709,7 @@ export async function testSingleConnection(connectionId: string, validationModel
     lastErrorType: result.valid ? null : diagnosis.type,
     lastErrorSource: result.valid ? null : diagnosis.source,
     errorCode: result.valid ? null : diagnosis.code || result.statusCode || null,
-    rateLimitedUntil:
-      result.valid || isTerminalFailure
-        ? result.valid
-          ? null
-          : connection.rateLimitedUntil || null
-        : new Date(Date.now() + testFailureCooldownMs).toISOString(),
+    rateLimitedUntil: result.valid ? null : connection.rateLimitedUntil || null,
   };
 
   if (result.valid) {

src/app/api/quota/pools/[id]/route.ts

@@ -73,7 +73,9 @@ export async function PATCH(request: Request, { params }: RouteParams): Promise<
     // helpers. Without the pre-update removal, a group/provider switch would leave
     // orphan qtSd/ combos a quota key still sees. Guarded + non-fatal.
     const combosNeedResync =
-      body !== null && typeof body === "object" && ("connectionIds" in body || "groupId" in body);
+      body !== null &&
+      typeof body === "object" &&
+      ("connectionIds" in body || "groupId" in body);
     if (combosNeedResync) {
       try {
         const { removeQuotaCombosForPool } = await import("@/lib/quota/quotaCombos");
@@ -104,7 +106,7 @@ export async function PATCH(request: Request, { params }: RouteParams): Promise<
         id,
         prevApiKeyIds,
         nextApiKeyIds,
-        parsed.data.exclusive ?? false
+        parsed.data.exclusive ?? false,
       );
     }
 
@@ -130,7 +132,7 @@ export async function DELETE(request: Request, { params }: RouteParams): Promise
 
   try {
     const { id } = await params;
-    const existed = await deletePool(id);
+    const existed = deletePool(id);
     if (!existed) {
       return NextResponse.json(buildErrorBody(404, "Pool not found"), { status: 404 });
     }