Merge remote-tracking branch 'origin/release/v3.8.50' into feat/9533-ratelimit-bound-queue-wait-bottleneck-exit

# Conflicts:
#	open-sse/services/combo.ts
#	tests/unit/repro-9630-combo-false-503.test.ts

@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 & {
@@ -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
 // ────────────────────────────────────────────────────────────────────────────
@@ -1250,10 +1239,7 @@ test("config: diskCache hydrates stale snapshot when /v1/models throws", async (
   );
   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"
   );
 });

@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)");
-});

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/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/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/9533-ratelimit-bound-queue-wait-bottleneck-exit.md

@@ -0,0 +1 @@
+- **fix(ratelimit):** added queue-wait timeout tests and updateFromResponseBody sequencing tests for the existing RATE_LIMIT_QUEUE_TIMEOUT feature in withRateLimit (#9533)

config/quality/file-size-baseline.json

@@ -408,8 +408,7 @@
     "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
+    "open-sse/translator/request/openai-to-kiro.ts": 1057
   },
   "_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.",
@@ -433,131 +432,5 @@
   "_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."
 }

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,

src/app/api/v1/vscode/[token]/usableChatModel.ts

@@ -13,9 +13,6 @@
 // happen once.
 
 export type UsableChatModelCandidate = {
-	id?: string;
-	root?: string;
-	name?: string;
 	owned_by?: string;
 	parent?: string | null;
 	type?: string;
@@ -47,19 +44,9 @@ function excludesTextOutputModality(model: UsableChatModelCandidate) {
 	);
 }
 
-function isBuiltinAutoModel(model: UsableChatModelCandidate): boolean {
-	const id = model.id || model.root || model.name || "";
-	const normalized = id.trim().toLowerCase();
-	return normalized === "auto" || normalized.startsWith("auto/");
-}
-
 export function isUsableChatModel(model: UsableChatModelCandidate) {
 	if (typeof model.owned_by === "string" && model.owned_by.trim().toLowerCase() === "combo") {
-		// Allow built-in auto-routing models (e.g. auto, auto/best-coding)
-		// while still excluding operator-created combos.
-		if (!isBuiltinAutoModel(model)) {
-			return false;
-		}
+		return false;
 	}
 	if (typeof model.parent === "string" && model.parent.length > 0) return false;
 	if (typeof model.type === "string" && model.type !== "chat") return false;

tests/unit/rateLimitManager-queue-timeout.test.ts

@@ -0,0 +1,38 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+
+const rlm = await import("../../open-sse/services/rateLimitManager.ts");
+const { enableRateLimitProtection, withRateLimit, __resetRateLimitManagerForTests } = rlm;
+
+test.beforeEach(async () => {
+  await __resetRateLimitManagerForTests();
+});
+
+test("withRateLimit works without abort signal (backward compat)", async () => {
+  enableRateLimitProtection("test-queue-1");
+  const result = await withRateLimit("openai", "test-queue-1", "gpt-4", async () => "ok");
+  assert.equal(result, "ok");
+});
+
+test("withRateLimit works with AbortSignal", async () => {
+  enableRateLimitProtection("test-queue-2");
+  const ac = new AbortController();
+  const result = await withRateLimit(
+    "openai",
+    "test-queue-2",
+    "gpt-4",
+    async () => "ok",
+    ac.signal
+  );
+  assert.equal(result, "ok");
+  ac.abort();
+});
+
+test("multiple sequential withRateLimit calls work", async () => {
+  enableRateLimitProtection("test-queue-3");
+  const results = await Promise.all([
+    withRateLimit("openai", "test-queue-3", "gpt-4", async () => "a"),
+    withRateLimit("openai", "test-queue-3", "gpt-4", async () => "b"),
+  ]);
+  assert.deepEqual(results.sort(), ["a", "b"]);
+});

tests/unit/rateLimitManager-update-sequencing.test.ts

@@ -0,0 +1,43 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+
+const rlm = await import("../../open-sse/services/rateLimitManager.ts");
+const {
+  enableRateLimitProtection,
+  withRateLimit,
+  updateFromHeaders,
+  updateFromResponseBody,
+  __resetRateLimitManagerForTests,
+} = rlm;
+
+test.beforeEach(async () => {
+  await __resetRateLimitManagerForTests();
+});
+
+test("updateFromResponseBody overwrites updateFromHeaders retry-after", async () => {
+  enableRateLimitProtection("test-seq-1");
+  await withRateLimit("openai", "test-seq-1", "gpt-4", async () => "ok");
+  const headers = new Headers({ "retry-after": "5" });
+  updateFromHeaders("openai", "test-seq-1", headers, 429, "gpt-4");
+  updateFromResponseBody("openai", "test-seq-1", JSON.stringify({ retry_after: 10 }), 429, "gpt-4");
+});
+
+test("no retry-after in either source leaves limiter state unchanged", async () => {
+  enableRateLimitProtection("test-seq-2");
+  await withRateLimit("openai", "test-seq-2", "gpt-4", async () => "ok");
+  const headers = new Headers({});
+  updateFromHeaders("openai", "test-seq-2", headers, 200, "gpt-4");
+  updateFromResponseBody("openai", "test-seq-2", "{}", 200, "gpt-4");
+});
+
+test("response body retry-after is parsed correctly", async () => {
+  enableRateLimitProtection("test-seq-3");
+  await withRateLimit("openai", "test-seq-3", "gpt-4", async () => "ok");
+  updateFromResponseBody(
+    "openai",
+    "test-seq-3",
+    JSON.stringify({ data: { retry_after: 30 } }),
+    429,
+    "gpt-4"
+  );
+});

tests/unit/sseHeartbeat.test.ts

@@ -23,17 +23,11 @@ test("sseCommentsEnabled defaults to true when the env var is unset", () => {
   withEnv(undefined, () => assert.equal(sseCommentsEnabled(), true));
 });
 
-test("sseCommentsEnabled is false for 'off', 'false', '0', 'no' (case-insensitive)", () => {
+test("sseCommentsEnabled is false only when set to 'off' (case-insensitive)", () => {
   withEnv("off", () => assert.equal(sseCommentsEnabled(), false));
   withEnv("OFF", () => assert.equal(sseCommentsEnabled(), false));
-  withEnv("false", () => assert.equal(sseCommentsEnabled(), false));
-  withEnv("FALSE", () => assert.equal(sseCommentsEnabled(), false));
-  withEnv("0", () => assert.equal(sseCommentsEnabled(), false));
-  withEnv("no", () => assert.equal(sseCommentsEnabled(), false));
-  withEnv("NO", () => assert.equal(sseCommentsEnabled(), false));
   withEnv("on", () => assert.equal(sseCommentsEnabled(), true));
-  withEnv("yes", () => assert.equal(sseCommentsEnabled(), true));
-  withEnv("1", () => assert.equal(sseCommentsEnabled(), true));
+  withEnv("false", () => assert.equal(sseCommentsEnabled(), true));
 });
 
 test("shapeForClientFormat maps known client formats", () => {

tests/unit/triage-bugs-2026-08-02.test.ts

@@ -1,3 +1,124 @@
+/**
+ * #8853 — authenticated HTTP proxy health checks drop credentials
+ *
+ * Root cause: both the auto-test route and the scheduler build proxy URLs
+ * manually as `${proxy.type}://${proxy.host}:${proxy.port}`, dropping
+ * username/password. The `proxyConfigToUrl()` function in proxyDispatcher.ts
+ * already handles URL-encoded credentials correctly.
+ *
+ * We prove the bug by showing that the proxy URL produced by the current
+ * manual construction lacks credentials, and that `proxyConfigToUrl()` with
+ * the same config object includes them — therefore the fix is to reuse it.
+ */
+import test from "node:test";
+import assert from "node:assert/strict";
+
+// The function that fixes the bug — we import it here to verify it works
+import { proxyConfigToUrl } from "@omniroute/open-sse/utils/proxyDispatcher";
+
+// ── proxyConfigToUrl credential tests ──────────────────────────────────────
+
+test("#8853 proxyConfigToUrl encodes username and password into proxy URL", () => {
+  const url = proxyConfigToUrl({
+    type: "http",
+    host: "127.0.0.1",
+    port: 3128,
+    username: "alice",
+    password: "s3cret",
+  });
+  assert.ok(url, "proxyConfigToUrl must return a URL");
+  assert.match(url!, /:\/\/alice:s3cret@/, "URL must contain credentials");
+});
+
+test("#8853 proxyConfigToUrl encodes special characters in credentials", () => {
+  const url = proxyConfigToUrl({
+    type: "http",
+    host: "proxy.example.com",
+    port: 8080,
+    username: "user@domain",
+    password: "p@ss:w0rd",
+  });
+  assert.ok(url, "proxyConfigToUrl must return a URL");
+  assert.match(url!, /:\/\/user%40domain:p%40ss%3Aw0rd@/, "URL must URL-encode special chars");
+});
+
+test("#8853 proxyConfigToUrl omits auth when no username", () => {
+  const url = proxyConfigToUrl({
+    type: "http",
+    host: "127.0.0.1",
+    port: 3128,
+  });
+  assert.ok(url, "proxyConfigToUrl must return a URL");
+  assert.doesNotMatch(url!, /@/, "URL must not contain @ (no auth)");
+});
+
+test("#8853 proxyConfigToUrl handles IPv6 host with family", () => {
+  const url = proxyConfigToUrl({
+    type: "http",
+    host: "[::1]",
+    port: 3128,
+    family: "ipv6",
+  });
+  assert.ok(url, "proxyConfigToUrl must return a URL");
+  assert.match(url!, /\[::1\]/, "IPv6 host must be bracketed");
+});
+
+// ── Simulate the buggy construction ─────────────────────────────────────────
+
+function buggyManualUrl(proxy: { type: string; host: string; port: number }) {
+  return `${proxy.type}://${proxy.host}:${proxy.port}`;
+}
+
+test("#8853 manual URL construction (current bug) drops credentials", () => {
+  const proxy = {
+    type: "http",
+    host: "127.0.0.1",
+    port: 3128,
+    username: "alice",
+    password: "s3cret",
+  };
+  const manualUrl = buggyManualUrl(proxy);
+  assert.doesNotMatch(manualUrl, /alice/, "Buggy URL must NOT contain username");
+  assert.doesNotMatch(manualUrl, /s3cret/, "Buggy URL must NOT contain password");
+
+  // Compare with proxyConfigToUrl which includes credentials
+  const fixedUrl = proxyConfigToUrl(proxy);
+  assert.ok(fixedUrl);
+  assert.match(fixedUrl!, /alice/, "Fixed URL must contain username");
+  assert.match(fixedUrl!, /s3cret/, "Fixed URL must contain password");
+});
+
+// ── Verify the scheduler and auto-test would use proxyConfigToUrl ──────────
+
+test("#8853 proxyConfigToUrl accepts ProxyRegistryRecord-shaped object", () => {
+  // Simulating the shape of a proxy record returned by listProxies({ includeSecrets: true })
+  const proxyRecord = {
+    id: "p1",
+    name: "test",
+    type: "http",
+    host: "10.0.0.1",
+    port: 8888,
+    username: "bob",
+    password: "p4ss",
+    family: "auto",
+    region: null,
+    notes: null,
+    status: "active",
+    source: "manual",
+    subscriptionId: null,
+    createdAt: "2026-01-01",
+    updatedAt: "2026-01-01",
+  };
+  const url = proxyConfigToUrl(proxyRecord);
+  assert.ok(url, "proxyConfigToUrl must accept ProxyRegistryRecord-shaped objects");
+  assert.match(url!, /bob:p4ss/, "URL must include credentials from the record");
+});
+
+test("#8853 proxyConfigToUrl returns null for partial config (no host)", () => {
+  const url = proxyConfigToUrl({ type: "http", port: 8080 } as Record<string, unknown>);
+  assert.equal(url, null, "proxyConfigToUrl must return null for partial config without host");
+});
+
 import test from "node:test";
 import assert from "node:assert/strict";
 import { openaiResponsesToOpenAIRequest } from "../../open-sse/translator/request/openai-responses.ts";
@@ -42,20 +163,4 @@ test("non-GPT-5.6 models still get max downgraded to xhigh", () => {
     )
   );
   assert.equal(translated.reasoning_effort, "xhigh");
-
-// #9140 — VS Code routes filter out built-in auto models
-const { isUsableChatModel } = await import(
-  "../../src/app/api/v1/vscode/[token]/usableChatModel.ts"
-);
-
-test("#9140 VS Code listing must accept built-in auto routing entries", () => {
-  assert.equal(
-    isUsableChatModel({ id: "auto/best-coding", owned_by: "combo" }),
-    true,
-    "built-in auto/* model should be accepted"
-  );
-  assert.equal(
-    isUsableChatModel({ id: "operator-combo", owned_by: "combo" }),
-    false,
-    "operator-created combo should still be rejected"
-  );
+});