mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-15 11:43:10 +03:00
* fix(ci): clear base-reds on release/v3.8.50 (round 3) - CHANGELOG.md: restore the top [Unreleased] section dropped by the #10189 reconcile (docs-sync gate: first section must be Unreleased) - env-doc-sync: document CONDUCTOR_ORCHESTRATOR_TOKEN + CONDUCTOR_SPOKESPERSON_URL in .env.example/ENVIRONMENT.md; allowlist the CI-only GITHUB_STEP_SUMMARY and TS7_BASE_REF (ts7 ratchet signals); drop a stray merge artifact line - providers: restore the audited chatanywhere metadata entry that base-reds round 2 dropped together with its duplicate — the provider was half-wired (registry+endpoint without APIKEY metadata), which is what the wave3 test catches; re-pin providers-constants-split at the measured 228 - docs counts: 338 -> 339 (today's +2 void-ai/helixmind, -1 Puter) via gen:provider-reference + README/AGENTS/llm.txt/package.json/diagrams/i18n mirrors - file-size ratchet: annotated rebaseline for the two pre-existing drifts (ModelSelectModal 1138, gateways 1250) following the 2026-08-11 precedent Refs #9985 * fix(ci): base-reds round 3b — stale sibling tests + mode-pack weight contract - check-docs-counts-sync.test.ts: drop the imports/subtests of the four helpers #10196 removed from the gate script (readMcpFactsFromSource, listLocalizedDocs, makeRequiredCountsValidator, checkFreeTierInventory) — the new-API tests that #10196 added stay; the file now loads again under the node runner - quota-connection-recovery.test.ts: convert from vitest APIs to node:test — the file lives in tests/unit/*.test.ts (node-runner glob) and the vitest runtime crashes when imported outside vitest, killing the whole shard entry - modePacks.ts: re-normalize all six mode packs to sum 1.0 — #8940 added sessionAvailability: 0.05 to every pack without rebalancing (1.05 total); ratios preserved exactly (÷1.05), so post-normalizeScoringWeights behavior is unchanged; restores the declared sum-to-1.0 contract the 4235 test pins Refs #9985 * fix(ci): base-reds round 3c — vitest siblings, weights default, secrets FP, mutation tap - DistributeProxiesButton.test.tsx: wrap renders in NextIntlClientProvider — #9245 localized the component (useTranslations) and left the test without the intl context, failing all 14 cases - scoring.ts: re-normalize DEFAULT_WEIGHTS to sum 1.0 (same #8940 class as the mode packs — sessionAvailability added without rebalancing; ratios preserved) - .gitleaks.toml: generalize the kimi sponsor-banner localStorage-key allowlist to -v\d+ — #10200 bumped v1→v2 and the stale regex regressed the secrets ratchet with a false positive - stryker.conf.json: register 6 covering unit tests in tap.testFiles (4 modules) so their mutant kills count — unblocks check:mutation-test-coverage --strict Refs #9985 * fix(ci): base-reds round 3d — inspector factor gap, stale registry/gap tests, i18n key sync - comboScoringInspector: add cacheAffinity/sessionAvailability/connectionDensity to FACTOR_KEYS + the factor-key type — calculateScore() weighs them but the breakdown omitted them, so the explained contributions never summed to the reported score (inspector bug, red on the pure tip) - combo-scoring-inspector.test: make the explicit-weights override sum-neutral (±0.05 shift) so it stays valid for any DEFAULT_WEIGHTS values — the hardcoded override only summed to 1.0 against the pre-#8940 defaults, which is also why explicit weights silently fell back to 'default' on the tip - unorouter-registry.test: align to the canonical .com host (api.unorouter.ai 301-redirects there, verified live) and to wave4's live model discovery (passthrough, no static seed) — the .ai/auto-model expectations were stale - check-migration-numbering.test: 147 left KNOWN_GAPS when 147_api_keys_model_access_mode.sql landed — assert absent (same as 143) - i18n: sync-ui pass — 35,914 missing UI keys stamped as __MISSING__ placeholders across 42 locales (mechanical; greens the pt-BR key-presence integrity test; coverage pct unchanged by design — translation is a separate workstream) Refs #9985 * fix(ci): base-reds round 3e — 2 real defects + 14 stale sibling tests (waves A-E) Real defects fixed: - src/lib/db/apiKeys.ts: #9313's empty-allowlist early return bypassed the group permission check, silently disabling group deny rules (#8817) for every key without a per-key allowlist; fall-through restored, restricted+[] deny-all kept - open-sse/utils/proxyFetch.ts: #10032 re-appended the raw transport error to the propagated message, reintroducing the proxy user:password leak #9837 closed; new redactProxyDetailsInMessage() keeps the reason, redacts URL/credentials - .github/workflows/quality.yml: #10134 added the TS7 ratchet as a separate blocking step AFTER the aggregated gates — the exact #8542 masking mechanism; folded into the non-fail-fast loop (still blocking, still PR-only) ⚠️ CI edit, gate-strengthening — explicit owner sign-off requested on the PR - src/i18n/messages/ko.json: 3 machine-mistranslation regressions caught by the #8244 glossary checker (장애인→비활성화됨, 양말5://→socks5://, 비클로드→Claude가 아닌) Stale sibling tests aligned to deliberately-moved contracts (each cites its mover): request-log-detail-layout + -stream (#9245 intl provider), repro-8542 pin update, quality-rail-gate-membership (#10134 shape), agentSkills-routes 45→46 (#9058), cloudflare-ai-catalog-8717 (#8804 supersedes #8808), executor-xai (#9994), vision-bridge-claude-wire (#9463 minimax→openai), sse-auth forced-pin (#8893), tls-proxy-context (strengthened leak guards), rate-limit-local-error-classification (#9164/#9342), minimax-thinking-signature (#9463), codebuddy-cn (#9723 +1 test), github-copilot-custom-model (#9050), providers-g4f-batch3 (#9584), synced-capability-warmup (#9199, stricter), sidebar-tools-group (#8221), oauth-modal-grok-cli-paste (#9245); agentSkills/catalog.ts comment 45→46; file-size rebaseline for proxyFetch (+19, annotated) Refs #9985 * fix(ci): base-reds round 3f — waves F-J: 9 more real defects + stale sibling sweep Real production defects fixed (all red on the pure tip, each with its origin): - routeGuard.ts: #8949 accidentally DELETED the /api/providers/[id]/login local-only pattern — the route spawns a browser, so the loopback gate for a process-spawning route was gone (Hard Rules #15/#17); restored (314 guard tests green) - agentSkills generator: #9058's category dispatch gave the config category an empty body, wiping skills/config-codex-cli/SKILL.md at the #10131 sync; fixed + SKILL.md regenerated via the official generator - imageRegistry: #9982 broke same-provider bare aliasing (antigravity preview id sent upstream unresolved); new resolveSameProviderBareAlias() keeps the fal cross-provider fix intact - imageRegistry: #9982's prefix strip handed the bare nano-banana ids to fal-ai, violating the pinned 2026-07-31 operator decision (adobe-firefly owns them); fal entries made prefix-only (dispatch already re-prefixes) - mediaGeneration/fal.ts: the missing-credential 401 guard was lost when #10198 deleted the superseded falHandler — tests were hitting the live network - bottleneckPatch/rateLimitManager: #9041's merge clobbered #9604, resurrecting the Bottleneck v2.19.5 heartbeat bug (reservoir never refills); patched the library defect at the root and re-aligned chat-rate-limit-body-lock to the working reservoir contract - processSupervisor.mjs: #9761 regressed the Node spawn to bare "node" (the #9156 launchd bug) and dropped #9209's ipv4first args; both restored - openai-responses/pureHelpers: #9423's Agent null-sentinel was unreachable on the schemaless JSON-string path; gate extended - i18n en.json: #8222's regen reverted the #9976 unclosed-tag fix and #8559's combo-cooldown copy; #9038 shipped 40 t() calls with no messages (runtime MISSING_MESSAGE); all restored/added + official sync-ui stamps, and vi's zero-marker policy re-established via the sanctioned translation backend Stale sibling tests aligned (movers cited inline): chat-helpers (#9447), executor-antigravity (#9351), video-fal-grok (#9982), visionBridge (#9759), web-session-credentials (#8974), production-build-module-integrity (positive anchor added), agentSkills-generator/skillManifestsLint/skills-injection/ agentSkillTools-mcp/listCapabilities-a2a (#9058), memory-settings (#10010), model-catalog-policy-invalidation (#8906), model-alias-seed (#9485), reactive-context-compaction (#8949), combo-provider-wildcard (broken upsert helper), oauth-google-loopback (43-locale resurrected-key removal) Validation: 501/501 across the 47 touched test files; typecheck:core, lint, file-size, docs-sync all green. Refs #9985 * fix(ci): base-reds round 3g — wave K/L: 4 more real defects + stale alignments Real defects: - base/reasoningEffort.ts: the stale duplicate cherry-pick #9612 re-added the codex minimal→low rewrite that #9883 had deliberately removed (OMP minimal passthrough); block removed again - cursorImages.ts: #9840 wired prepareCursorImageForWire (sharp re-encode, fail-closed) into the SHARED resolveCursorImages, breaking zai-web and conol-web image uploads (HTTP 400 'undecodable'); new prepareForWire opt-out, Cursor default path unchanged (8 cursor suites green) - modelCapabilities/snapshot: catalog prepare still issued 323 per-model reads of model_context_overrides + max_input_tokens overrides, violating #9199's bulk-load contract; both now resolve from the snapshot single pass - v1-models-discovery-conformance: re-pinned to the bounded 30s SWR window (#9199/#10198) — the old 'stale-first regardless of age' contract is gone Stale tests aligned (movers cited inline): codex-tools-strict-default (#9828 redundant-oneOf strip), devin-providers (#9245 i18n), db-migrationrunner- constants-split (147→151 renumber #8228), gitlab-duo-oauth-setup (#9245), chatcore-extracted-modules (#9161 outbound-protocol keying) compression-api CI failures were cascade artifacts of codex-tools-strict-default failing in the same force-exit shard process — no own defect (171/171 local). Refs #9985 * fix(test): compression-api — register both describes before the runner starts The DATA_DIR setup + route/db top-level awaits sat BETWEEN the two describes; under --test-force-exit (the CI unit-runner flag) the process exits once the already-registered tests finish, so on slow CI machines the whole second describe died as 'Promise resolution is still pending' — the recurring CI-only shard-2 failure that never reproduced locally without the flag. Moved to the top of the file; 10/10 under --test-force-exit locally. Refs #9985 * fix(quality): freeze modelCapabilities.ts at 1006 (annotated) — snapshot routing growth Refs #9985 * fix(quality): move the modelCapabilities freeze into the frozen map (nested schema) Refs #9985 * fix(i18n): translate all 39,718 pending UI keys across 42 locales (owner-approved) Mass-translated every __MISSING__ placeholder via the official i18n:sync-ui --translate-markers pipeline (operator backend), restoring i18nUiCoverage to the 100 baseline (was 89.9 after the merge-storm UI landings + the 42 keys #9038 never shipped). Post-pass repairs, all caught by the existing gates: - glossary: retired renderings the machine reintroduced normalized again (提供商→提供者 zh-CN/zh-TW, 鏈接→連結, 文檔→文件, 調用→呼叫, 供應商→提供者, 響應→回應, 不活躍→未啟用 zh-TW; 클로드→Claude, 옴니루트→OmniRoute ko); DATA_DIR forbidden rendering avoided via 数据文件夹 rephrase - ICU integrity: 120 values with renamed/dropped {params} repaired (39 positional renames, 81 reset to the en source — functional over fluent) Validation: glossary/pt-BR/vi/deno-relay/settings-keys/value-drift/google- loopback suites 76/76; placeholder diff en×42 locales = 0; worst-locale coverage = 100.0%. Refs #9985 --------- Co-authored-by: backryun <bakryun0718@proton.me>
152 lines
6.5 KiB
TypeScript
152 lines
6.5 KiB
TypeScript
/**
|
|
* Monkey-patch for Bottleneck v2.19.5 doExpire bug.
|
|
*
|
|
* Bug (Job.js:162):
|
|
* `this._states.jobStatus(this.options.id === "RUNNING")`
|
|
* compares job ID to "RUNNING" (always false) instead of checking status.
|
|
* Should be: `this._states.jobStatus(this.options.id) === "RUNNING"`
|
|
*
|
|
* Impact: when a job's execution time exceeds `expiration`, doExpire fires but
|
|
* fails to advance the job from RUNNING to EXECUTING. The _assertStatus throws
|
|
* in a setTimeout (uncaught), and the job is permanently stuck in RUNNING state.
|
|
* Bottleneck's internal _running counter never decrements -> capacity leak.
|
|
*
|
|
* This patch intercepts Bottleneck's _run method to fix job.doExpire before
|
|
* the expiration timeout fires.
|
|
*/
|
|
|
|
import Bottleneck from "bottleneck";
|
|
|
|
/** Bottleneck LocalDatastore instance (internal, not exported). */
|
|
interface BottleneckLocalDatastore {
|
|
heartbeat: ReturnType<typeof setInterval> | null | undefined;
|
|
storeOptions: {
|
|
reservoirRefreshInterval?: number | null;
|
|
reservoirRefreshAmount?: number | null;
|
|
reservoirIncreaseInterval?: number | null;
|
|
reservoirIncreaseAmount?: number | null;
|
|
};
|
|
_startHeartbeat: () => unknown;
|
|
}
|
|
|
|
let heartbeatPatched = false;
|
|
|
|
/**
|
|
* Monkey-patch for Bottleneck v2.19.5 LocalDatastore#_startHeartbeat bug.
|
|
*
|
|
* Bug (LocalDatastore.js:26-58): the guard `if (this.heartbeat == null && <config>)`
|
|
* only creates the reservoir-refresh setInterval the FIRST time. Every later call —
|
|
* including the one `updateSettings()` triggers via `__updateSettings__` — takes the
|
|
* `else` branch and does `clearInterval(this.heartbeat)` WITHOUT resetting
|
|
* `this.heartbeat` to null. The stale reference makes all future calls keep taking
|
|
* the dead `else` branch: the periodic reservoir refresh is gone forever after the
|
|
* first manual `updateSettings()` on a limiter that already had a heartbeat.
|
|
*
|
|
* Production symptom (#9529 / weighted.test.ts E2E): after a header-learned
|
|
* updateSettings(), the reservoir zeroes and never refills — the request queue wedges
|
|
* until the watchdog fires a synthetic 502.
|
|
*
|
|
* Fixed semantics:
|
|
* - refresh config present, no live interval → create (delegate to the original).
|
|
* - refresh config present, interval alive → keep it (interval reads storeOptions
|
|
* live, so updated amounts are picked up) — upstream wrongly killed it here.
|
|
* - refresh config absent, interval alive → clearInterval AND null the handle.
|
|
*/
|
|
export function applyBottleneckHeartbeatPatch(): void {
|
|
if (heartbeatPatched) return;
|
|
heartbeatPatched = true;
|
|
|
|
// LocalDatastore is not exported; reach its prototype through a throwaway instance.
|
|
const probe = new Bottleneck({});
|
|
const store = (probe as unknown as { _store: BottleneckLocalDatastore })._store;
|
|
const proto = Object.getPrototypeOf(store) as BottleneckLocalDatastore;
|
|
void probe.disconnect();
|
|
|
|
const originalStartHeartbeat = proto._startHeartbeat;
|
|
if (typeof originalStartHeartbeat !== "function") {
|
|
console.warn("[bottleneck-patch] _startHeartbeat not found on LocalDatastore, patch skipped");
|
|
return;
|
|
}
|
|
|
|
proto._startHeartbeat = function patchedStartHeartbeat(this: BottleneckLocalDatastore) {
|
|
const opts = this.storeOptions ?? {};
|
|
const wantsHeartbeat =
|
|
(opts.reservoirRefreshInterval != null && opts.reservoirRefreshAmount != null) ||
|
|
(opts.reservoirIncreaseInterval != null && opts.reservoirIncreaseAmount != null);
|
|
|
|
if (this.heartbeat != null) {
|
|
if (wantsHeartbeat) return; // alive and still wanted — upstream wrongly cleared it here
|
|
clearInterval(this.heartbeat);
|
|
this.heartbeat = null; // upstream forgot this null-out — the core of the bug
|
|
return;
|
|
}
|
|
return originalStartHeartbeat.call(this);
|
|
};
|
|
|
|
console.log("[bottleneck-patch] Applied _startHeartbeat fix for Bottleneck v2.19.5");
|
|
}
|
|
|
|
/** Bottleneck Job instance (internal, not exported). */
|
|
interface BottleneckJob {
|
|
options: { id?: string; expiration?: number };
|
|
doExpire: (clearGlobalState: () => void, run: () => void, free: () => void) => void;
|
|
_states: { jobStatus: (id: string) => string | null; next: (id: string) => void };
|
|
}
|
|
|
|
let patched = false;
|
|
|
|
export function applyBottleneckDoExpirePatch(): void {
|
|
if (patched) return;
|
|
patched = true;
|
|
|
|
const proto = Bottleneck.prototype as unknown as Record<string, unknown>;
|
|
const originalRun = proto._run as
|
|
((index: string, job: BottleneckJob, wait: number) => unknown) | undefined;
|
|
if (typeof originalRun !== "function") {
|
|
console.warn("[bottleneck-patch] _run not found on prototype, patch skipped");
|
|
return;
|
|
}
|
|
|
|
proto._run = function patchedRun(this: unknown, index: string, job: BottleneckJob, wait: number) {
|
|
// Patch job.doExpire BEFORE calling originalRun.
|
|
// originalRun passes job.doExpire to setTimeout by reference -- once captured,
|
|
// reassigning the property later has no effect on the queued timer callback.
|
|
//
|
|
// Guard: _run is called twice for jobs with wait > 0 (first with the delay,
|
|
// then with wait=0 when the timer fires). Without the flag, fixedDoExpire
|
|
// would wrap itself recursively on the second call.
|
|
if (typeof job?.doExpire === "function" && !(job as unknown as Record<string, unknown>)._doExpirePatched) {
|
|
(job as unknown as Record<string, unknown>)._doExpirePatched = true;
|
|
const originalDoExpire = job.doExpire.bind(job);
|
|
// Bottleneck registers the job in _states under options.id (Job.js
|
|
// states.start(this.options.id)); a bare `job.id` does not exist and
|
|
// reading it makes the RUNNING check below always miss. options.id is
|
|
// stable on the job and is the key the state machine uses.
|
|
const jobId = job.options.id;
|
|
|
|
job.doExpire = function fixedDoExpire(
|
|
clearGlobalState: () => void,
|
|
run: () => void,
|
|
free: () => void
|
|
) {
|
|
// Fix: check job status, not compare ID to string "RUNNING"
|
|
const states = job._states;
|
|
const currentStatus = states?.jobStatus?.(jobId);
|
|
if (currentStatus === "RUNNING") {
|
|
states?.next?.(jobId);
|
|
console.warn(
|
|
`[bottleneck-patch] doExpire bug triggered: job ${jobId} stuck in RUNNING, ` +
|
|
`advanced to EXECUTING before expiry. This is the Bottleneck v2.19.5 capacity leak.`
|
|
);
|
|
}
|
|
return originalDoExpire(clearGlobalState, run, free);
|
|
};
|
|
}
|
|
|
|
// Now call original _run which captures the (now-patched) job.doExpire.
|
|
return originalRun.call(this, index, job, wait);
|
|
};
|
|
|
|
console.log("[bottleneck-patch] Applied doExpire fix for Bottleneck v2.19.5");
|
|
}
|