mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-17 12:22:34 +03:00
docs/dedup-hash-codeql-note
45 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Dizzle
|
a054ac408f |
feat(providers): allow per-connection maxWaitMs rate-limit override (#11251)
Validated on the combined 12-PR batch board: focused node:test suites green (incl. provider-rate-limit-overrides-schema + ratelimit-admission-control-6593 isolated 11/11 + the new EditConnectionModal vitest 3/3), typecheck:core clean, all static gates within baseline. Pushed one follow-up commit to your branch with the real Vietnamese translations for the two new keys (repo convention: vi never ships __MISSING__ placeholders). Per-connection maxWaitMs override lands, folding the zai-web exception into the general mechanism. Thank you @maxmad64bis! |
||
|
Paco Cartones
|
376b49d8a5 |
fix(ratelimit): keep operator minTime floor when relaxing on headroom (#9763) (#11086)
Validated on the combined batch board over tip
|
||
|
Bob.Hou
|
ff9a4c2fbd |
fix(combo): prevent unhandledRejection from per-model-timeout abort (#10846)
Merged — locally validated (11/11 focused tests across both new test files, typecheck:core clean after a 1-char fix pushed to this branch: ComboLogger.error is optional in combo/types.ts so the defensive race-catch needed log.error?.(...) — TS2722 otherwise). Solid production diagnosis (47 unhandledRejections traced to the orphaned race loser). Thanks! |
||
|
Diego Rodrigues de Sa e Souza
|
d259d9fcba |
fix(ci): clear base-reds on release/v3.8.50 (round 3) (#10213)
* 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> |
||
|
backryun
|
bd472200d5 |
[v3.8.50] Fix Z.ai web browser transport and model capabilities (#8451)
* fix: complete Z.ai web browser transport * refactor: address Z.ai review feedback * test(zai-web): reconcile the #8014 endpoint guard with the chats/new + signed flow Rebasing onto release/v3.8.49 pulled in #8503, which repointed CHAT_URL to /api/v2/chat/completions and added an endpoint probe. This branch already targets v2, so the executor conflict resolved to this branch's superset (NEW_CHAT_URL + signature constants alongside the same v2 CHAT_URL). The two tests needed adapting, because #8503's assertions assume the pre-rework flow: - executor-zai-web.test.ts: the completion URL now carries the request signature as a query string, so an exact-equality check on the endpoint can never match. Assert the v2 prefix instead. - zai-web-chat-endpoint-8014-probe.test.ts: the probe drove the executor with a bare cookie credential and no captcha proof, which now routes through the browser transport — fetch was never called and the probe captured nothing. Supplied a direct-path credential, and matched on pathname across all requests (the executor also probes the homepage for the frontend version and calls /api/v1/chats/new first). The guard's intent is unchanged and slightly strengthened: it now asserts no request reaches the stale unversioned path and that exactly one completions request is issued, against v2. 54/54 across the zai suites; typecheck:core and eslint clean. * fix(zai-web): surface upstream error frames instead of finishing empty Reported on this PR: HTTP 200, `out=0`, stream "complete", no content and no diagnosis. Cause. HTTP-level failures are already handled — fetchUpstream turns any !ok response into a makeErrorResult with the sanitized body. The gap is a 200 whose SSE body carries an error payload: parseZaiFrame returns null for it, drainSseDeltas drops it, and buildZaiStreamingBody then closes with an empty assistant message + stop + [DONE]. The caller reads that as a successful empty completion, so a rejected signature, an expired captcha and a stale token all look identical — which is why this had to be diagnosed by reading code rather than logs. Hard Rule #6. Fix. parseZaiFrame now classifies an affirmatively error-shaped frame (`error` at the top level or under `data`, string or {detail|message|msg}) as a terminal delta, checked before the delta paths so it cannot fall through to the "no usable delta" null. The stream emits it as `[Z.ai error] <message>`, matching the mid-stream convention the other web executors already use (zed-hosted's createErrorChunk) — the 200 is on the wire, so the status cannot change, but the caller must not be left reading a blank success. Content streamed before the failure is preserved. Message goes through sanitizeErrorMessage (Rule #12). Deliberately NOT changed: a contentless frame still parses to null. That is live-validated behaviour, not an oversight — z.ai emits phase frames with no delta_content, and executor-zai-web.test.ts pins it ("returns null for frames with no usable delta"). Treating "nothing parseable arrived" as a failure would invent policy on top of an observed protocol and risk false errors on the happy path, so this only adds recognition of explicit error frames. Tests (TDD, RED then GREEN): zai-web-silent-empty-repro.test.ts — 7 cases. Error frame classified and terminal; surfaced through the stream with the upstream's own text; surfaced after partial content without losing it; plus a REGRESSION GUARD that contentless/phase-only frames are still skipped, and two controls that the happy path and reasoning-only output are untouched. The guard and controls passed before the fix; the four error cases did not. 94/94 across the zai + stream suites; typecheck:core, eslint and check:file-size clean. * refactor(sse): extract the zai-web transports so the complexity ratchet holds The v3.8.49 merge-train rebaseline (#8686) set the ceiling to the tip's own measurement, leaving zero headroom, so this branch's +5 cyclomatic / +3 cognitive own-growth had nowhere to sit once rebased onto it. Eight violations, all in code this branch introduces, resolved by extraction — no behaviour change: - `execute` (152 lines, complexity 25, cognitive 20) now delegates to `resolveZaiRequest()` for the four client-error rejections and to a `fetchViaSignedApi()` method for the CAPTCHA/signature path, so it reads as "validate, pick a transport, shape the response". - `fetchThroughBrowser` (126 lines, cognitive 16) hands its image decoding to `resolveZaiBrowserAttachments()`, its Playwright options to `buildZaiBrowserChatOptions()`, and its call-log payload to `buildZaiBrowserAuditBody()`. - `configureZaiBrowserEffort` (cognitive 35 — the worst of the set) repeated a wrap-and-relabel try/catch four times inside an if/else. `runStage`, which already existed one function below, is now module-scoped and reused, and the toggle collapses to `checked !== config.enabled` (same four cases). - `validateWebCookieProvider` (complexity 19) moves its can-we-probe-this cascade into `resolveWebCookieProbe()`, which returns either a rejection or the URL + headers to use. - `acquireBrowserContext`'s creation closure (complexity 17) hands cookie and localStorage seeding to `seedContextSession()`. That last extraction also clears a violation that predates this branch — `acquireBrowserContext` was already over the 80-line ceiling — so cyclomatic lands at 2187 against a baseline of 2188. Verified: check:complexity-ratchets green both metrics; typecheck:core clean; ESLint clean on all four files; 85 tests across the zai-web, web-cookie validation, browser-pool and model-test-runner suites pass. * fix(zai-web): surface upstream errors on the non-streaming path collectZaiNonStreaming ignored delta.error — a 200 whose SSE body carries an error frame (rejected signature, expired captcha, stale token) came back as a successful empty completion. Now it throws on an error frame, matching the streaming path's [Z.ai error] convention; the caller's existing try/catch returns makeErrorResult(502) instead of an empty 200. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: backryun <busan011@ormbiz.co.kr> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Bob.Hou
|
fb83f43fca | fix(rate-limit): patch Bottleneck doExpire capacity leak (#9328) | ||
|
Arthur Bodera
|
8bdd29f835 |
fix(resilience): recover idle-capacity limiter wedges early (#9041)
* fix(resilience): recover idle-capacity limiter wedges early * docs(changelog): note limiter wedge recovery * fix(resilience): harden limiter wedge recovery * fix(resilience): close limiter recovery review gaps * test(resilience): preserve scoped exhaustion guards * docs(changelog): remove self-credit suffix * test: include limiter regressions in mutation coverage * chore(quality): reconcile v3.8.50 file-size baselines * fix(docs): add WAF MDX title frontmatter * fix(docs): complete WAF frontmatter metadata |
||
|
Diego Rodrigues de Sa e Souza
|
ece486dc38 |
fix(resilience): enforce RPM with rolling leases (#9604)
Validated in local merge-train (diegosouzapw batch) |
||
|
Diego Rodrigues de Sa e Souza
|
8180b49ce1 |
fix(quality): 2 production bugs + 24 unit base-reds + measured gate ceilings (#9529)
* fix(quality): resolve net-new lint errors and allowlist #9343 assert rewrite Two `no-explicit-any` errors landed with #9407 and #9320 after the suppressions inventory was generated. Project policy is to fix new violations rather than freeze them, so both are typed instead: - #9407: `executor as unknown as Record<string, unknown>` - #9320: `(k: { name?: string })` Also allowlists the net-assert reduction in web-tools-translation-2820 (39->35). #9343 inverted the contract — bare JSON must no longer be promoted to tool_calls without an explicit <tool> envelope — so the tests were rewritten to assert non-promotion, which costs fewer asserts than validating a promoted object. More restrictive, not weaker. * fix(quality): raise integration ceiling to 40min and unpin codex-cli version in test The integration gate's 20min ceiling killed a healthy run: measured 22m08s hermetic on an idle 16-core box (935 tests across 112 files, strictly serial at --test-concurrency=1 because ~16 of them bind a port or share a DB). The "~3-10min" estimate in the code was stale by ~3x. 40min keeps the ceiling's real purpose — turning a genuine hang into a visible failure — without failing a long-but-healthy suite. Also fixes a base-red in chat-pipeline: |
||
|
Jonathan Bailey
|
dd22d9c017 |
fix(resilience): recover idle wedged limiters (#8616)
* chore(resilience): log queue state on expiry * docs(changelog): document rate limiter instrumentation * fix(resilience): recover idle wedged limiters * chore(resilience): remove diagnostic queue logging |
||
|
Markus Hartung
|
cc17b304ab |
fix(sse): Gemini TPM/RPD quota classification + combo cooldown-wait resilience (#8213)
* fix(sse): Gemini TPM classification, combo-cooldown-wait for auto/quota-share, and target-timeout floor
Gemini TPM/RPM 429s were misclassified as QUOTA_EXHAUSTED because
sanitizeErrorMessage() truncates to the first line, hiding Google's
metric name and retry hint on lines 2-3. Added a rawMessage field
(internal-only, never reaches the client) and classifyGeminiQuotaMetricFromText()
to classify from the untruncated text, reordered ahead of the generic
credits/daily-quota checks.
Widened comboCooldownWaitEnabled (wait out a short transient cooldown
instead of crystallizing a 429/503) from quota-share-only to also cover
auto-strategy combos, and raised the wait ceiling to 65s/130s-budget/90s-cap
to match Gemini's ~60s TPM/RPM windows.
The per-target timeout (DEFAULT_COMBO_TARGET_TIMEOUT_MS, 120s) was shorter
than the new 130s cooldown-wait budget, so a target could get cut off
mid-wait with a synthetic 524 instead of completing the retry. Added
resolveComboTargetTimeoutMsForCombo()/isComboCooldownWaitEligible() in
comboConfig.ts to raise the per-target floor to budgetMs+buffer only for
wait-eligible strategies (auto/quota-share), verified live: a 12-request
concurrent burst against a TPM-exhausted combo went from 2/12 succeeding
(10 x 524) to 12/12 succeeding with zero 503/524.
Also: liveGeminiShared.ts's sendAndValidate now fails fast on a 503
instead of retrying past it, and the health dashboard + request logger
surface TPM stats alongside RPM/RPD.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo-exhausted rejection logs now capture request body + attempted models
recordRejectedRequestUsage() (the fast path for combo requests that never
reach handleChatCore, e.g. all targets locked by resilience cooldown)
hardcoded provider: "-" and never passed a request body to saveCallLog(),
so /dashboard/logs entries for these failures were nearly useless for
debugging: no way to see the client's request or which models were tried.
- recordRejectedRequestUsage() now accepts requestBody and persists it
through the existing saveCallLog() artifact mechanism (same path
handleChatCore's own logging uses).
- Added summarizeComboAttemptedModels(), which reads the combo's own model
list (always available, unlike the response's combo-diagnostics headers —
a model-level resilience-lockout skip never touches the
exhaustedProviders/exhaustedConnections sets those headers are built
from) to populate a real "provider" value instead of "-".
- Wired both into the call site in src/sse/handlers/chat.ts.
NOTE: unrelated to the Gemini TPM/combo-cooldown-wait fix on this branch —
landed here per operator request, to be split into its own branch/PR.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* feat(sse): synthetic streaming keep-alive event + 5-minute Gemini cooldown-wait ceiling
Many clients enforce a first-SSE-byte timeout, which made it unsafe to wait
out a longer upstream rate-limit cooldown on a streaming request — the
client would abandon the connection before any bytes arrived. This landed
in two parts:
1. Synthetic startup "thinking" event (OpenAI chat/completions format):
the already-existing withEarlyStreamKeepalive wrapper (open-sse/utils/
earlyStreamKeepalive.ts, wired into /v1/chat/completions, /v1/messages,
/v1/responses since #2544) opens the SSE stream immediately once a
request runs past its threshold, but only ever sent empty/no-op
keepalive frames. Added a `startupFrame` option (defaults to
`keepaliveFrame` — zero behavior change unless a route opts in) so the
very first frame can carry real content instead. Wired
OPENAI_STARTUP_THINKING_FRAME (a reasoning_content delta: "OmniRoute:
got request, sending to provider") into /v1/chat/completions only —
Claude Messages and Responses API formats both require a preceding
envelope event (message_start / response.created) that a synthetic
pre-dispatch frame can't safely fabricate without risking a duplicate
envelope once the real stream arrives, so those two routes keep their
existing (safe, proven) keepalive frames unchanged.
2. Raised the "wait out a known cooldown, then retry" ceiling to 5 minutes
for both retry mechanisms, now that a client-side first-byte timeout is
no longer a risk on the (opted-in) route:
- comboCooldownWait (auto/quota-share combos, open-sse/services/combo.ts):
maxWaitMs hard clamp raised 90s -> 300s (src/lib/resilience/settings/
normalize.ts); defaults raised to maxWaitMs:90s/maxAttempts:5/
budgetMs:300s. comboConfig.ts's resolveComboTargetTimeoutMsForCombo
already derives the per-target timeout floor from budgetMs, so it
tracks the new ceiling with no further changes.
- waitForCooldown (direct, non-combo model requests, src/sse/handlers/
chat.ts): this mechanism had NO cumulative cap before — only a
per-wait cap (maxRetryWaitMs) and a retry count (maxRetries), so
maxRetries x maxRetryWaitMs could exceed 5 minutes with no ceiling.
Added a budgetMs field (mirrors comboCooldownWait) to
WaitForCooldownSettings/CooldownAwareRetrySettings, threaded a
requestRetryBudgetLeftMs tracker through chat.ts's requestAttemptLoop
(mirrors combo.ts's comboCooldownBudgetLeftMs), and made
getCooldownAwareRetryDecision refuse to wait once the cumulative
budget is exhausted even if the single wait is under maxRetryWaitMs.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): extend the synthetic keep-alive thinking event to /v1/responses
Live incident (OpenClaw, log id 1784407081908-cbc24f): a /v1/responses
request to gemini/gemma-4-31b-it took 56s to produce a first byte and the
client disconnected (499 request_signal_aborted) — the same client-first-byte-
timeout problem the previous commit fixed for /v1/chat/completions, but
/v1/responses only had the generic bare-comment keepalive (no content), so it
wasn't covered.
Added RESPONSES_STARTUP_THINKING_FRAME: a self-contained synthetic reasoning
item (response.output_item.added -> reasoning_summary_part.added ->
reasoning_summary_text.delta -> reasoning_summary_part.done), opened AND
closed within this one frame rather than left dangling — it never carries a
response_id, so it can't collide with the real upstream response's own
independent response.created lifecycle that follows. Mirrors the abbreviated
delta+part.done close pattern open-sse/utils/stream.ts's own
emitSyntheticResponsesReasoningSummary already uses for real mid-stream
reasoning content.
Wired into src/app/api/v1/responses/route.ts via the startupFrame option
added in the previous commit.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait vars reset every setTry, crystallizing a bogus 503 instead of waiting
Live incident (log id 1784416706646-51): a request to the "default" combo
(strategy=auto, maxSetRetries=3) hit a real Gemini TPM 429 on both gemma-4
targets, correctly classified as a short 40s rate_limit lockout — then
crystallized a 503 "all upstream accounts are inactive" in 6.9s instead of
ever reaching the cooldown-aware wait.
Root cause: `lastError`/`earliestRetryAfter`/`lastStatus` were declared with
`let` INSIDE the `for (setTry...)` loop body, so they reset to null at the
start of every set-try. When both targets lock out on setTry 0, every
subsequent setTry (1..maxSetRetries) pre-skips both targets via the
isModelLocked check with no real dispatch — so on the FINAL setTry (the only
one whose values the post-loop decision reads, since it's gated behind
`if (setTry < maxSetRetries) continue`), lastStatus was null, hitting the
"!lastStatus" branch (ALL_ACCOUNTS_INACTIVE 503) and completely bypassing the
comboCooldownWaitEnabled / earliestRetryAfter wait logic — even though a
real 429 with a known ~40s retry-after WAS observed on setTry 0.
This bug predates today's Gemini TPM work (any combo with maxSetRetries > 0
whose targets all lock out on the first pass was affected) but was masked in
existing tests: the "auto strategy (2 models...)" regression test uses
maxSetRetries: 0, so it only ever runs ONE setTry iteration and never
exercises the reset-on-retry path. It also explains why the dedicated
12-concurrent-request burst test passed cleanly — with concurrent requests,
timing variance meant some request's FINAL setTry iteration still had a live
target to dispatch to, giving lastStatus/earliestRetryAfter fresh data. A
single isolated request has no such luck.
Fix: hoist lastError/earliestRetryAfter/lastStatus to just inside
dispatchWithCooldownRetry, before the setTry loop, so they persist across
set-tries (still reset fresh on each recursive dispatchWithCooldownRetry()
call after a wait, which is correct). recordedAttempts/fallbackCount/
exhaustedProviders etc. are intentionally left per-iteration (unrelated to
this bug).
New regression test in tests/unit/combo-quota-share-cooldown-wait.test.ts
reproduces the exact live scenario (2 targets, both lock out on setTry 0,
maxSetRetries: 3) — confirmed red (503) against the pre-fix code, green
(200, waits and retries) against the fix.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* test(sse): extend live Gemini workload to Responses API + add large-context TPM test
Two additions to the live Gemini test suite, both live-verified against the
dev instance:
1. sendAndValidate() (tests/integration/liveGeminiShared.ts) now accepts an
apiFormat: "chat" | "responses" parameter, building the Responses-API
request shape (input array, max_output_tokens) and parsing its SSE events
(response.output_text.delta / response.reasoning_summary_text.delta /
response.completed) via the new readResponsesSSEStream(). Wired into two
new tests in live-gemini-workload.test.ts ([30]/[31]), mirroring the
existing Chat Completions streaming coverage. Verified live: 24/25 + 5/5
payloads succeeded end-to-end through the new code path (the one failure
was a ~300s test-client fetch timeout unrelated to the Responses API code
itself — a separate, not-yet-addressed test-harness limitation).
2. genHugeContextMessage() builds a single message large enough (~4
chars/token estimate) to approach or exceed Gemini's free-tier TPM ceiling
(16000 input tokens/min for gemma-4) by itself. Every other prompt
generator in this file tops out around 1-2k tokens — nowhere near that
ceiling — so none of the existing workload tests ever exercised a REAL TPM
429, only RPM-style rate limiting. tests/integration/gemini-large-context-tpm.test.ts
sends two ~12-13k-token requests back-to-back (comfortably exceeding
16000/min together) to exercise the full path against production Gemini:
TPM classification, the comboCooldownWait retry, and the synthetic
keep-alive frame on a genuinely slow request.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): abandoned combo target dispatch now observes its own per-target timeout, fixing a permanent "pending" dashboard leak
Live incident (dashboard log id 1784418258231-14961a, reported as "an ongoing
request even though there's already a 200"): a combo target dispatch
abandoned by comboTargetTimeoutMs (open-sse/services/combo/targetTimeoutRunner.ts)
left a permanent phantom "pending" entry in the dashboard, even after the
overall combo request had already succeeded via a different retry.
Root cause: chatCore.ts's createStreamController — and everything downstream
that depends on it (withRateLimit's Promise.race against Bottleneck,
acquireAccountSemaphore) — only ever watches clientRawRequest.signal, which
is the ORIGINAL client's request signal (set once via buildClientRawRequest
and reused unchanged across every target dispatch in a combo). It has no
connection to targetTimeoutRunner.ts's OWN AbortController
(target.modelAbortSignal), which is what actually fires when
comboTargetTimeoutMs (300s) elapses. src/sse/handlers/chat.ts's
handleSingleModel bridge between combo.ts and handleSingleModelChat received
`target.modelAbortSignal` but silently dropped it — never forwarded it
anywhere. So when a target got abandoned (e.g. stuck inside a wedged
Bottleneck rate-limiter queue, see the WEDGED force-reset log line from the
same incident), its per-target timeout fired and let the COMBO move on and
retry successfully elsewhere — but the abandoned dispatch's own promise
chain never learned it had been superseded, so it hung forever waiting on a
signal that was never going to fire, and trackPendingRequest(false) (the
finalize call) never ran.
Fix: thread target.modelAbortSignal through as a new modelAbortSignal
runtimeOption, and merge it into clientRawRequest.signal (via the existing
mergeAbortSignals helper from open-sse/executors/base.ts) right before
dispatch, so an abandoned target's own promise chain now observes its abort
and can reach its cleanup path — new resolveDispatchClientRawRequest() makes
this mechanically testable in isolation.
Co-authored-by: Markus Hartung <markus.hartung@gmail.com>
* fix(sse): combo cooldown-wait state recording, rate-limit wedge recovery, OpenAI-format SSE error frames
Five related fixes surfaced by live incidents (dashboard log ids 1784457764961-73,
1784465227489-a2cbc0, 1784504040241-6f8b9a) while validating the Gemini TPM/cooldown-wait
work on this branch against real OpenClaw traffic:
- combo.ts: the model-lockout bail-out branches in dispatchWithCooldownRetry never
recorded lastStatus, so once every target in a set hit an existing lockout the final
check crystallized a bogus ALL_ACCOUNTS_INACTIVE 503 instead of reaching the
cooldown-wait decision, even with a real 429 + short retry-after observed.
- combo.ts/combo/types.ts: the "all credentials cooling down" pre-dispatch rejection
(buildModelCooldownBody) nests its retry hint as error.retry_after/reset_seconds, not
the top-level retryAfter every other 429 shape uses — combo's extraction only read the
latter, so earliestRetryAfter stayed null for this shape even after lastStatus was fixed.
- rateLimitManager.ts: the wedge-recovery watchdog used disconnect(), which releases the
heartbeat timer but never rejects jobs already QUEUED on that instance — orphaned
dispatches hung until the outer ~300s per-target timeout, well past real clients'
patience. Switched to stop({ dropWaitingJobs: true }), safe because the wedge condition
already requires RUNNING===0 && EXECUTING===0.
- earlyStreamKeepalive.ts: the in-band error frame emitted after committing to a 200 SSE
stream was hardcoded to Anthropic's `event: error` convention for every route, including
the OpenAI-format ones (/v1/chat/completions, /v1/responses) where that framing is
either invisible or malformed to a plain data-line parser. Added per-route
OPENAI_CHAT_ERROR_FRAME / OPENAI_RESPONSES_ERROR_FRAME and wired them in.
- chatCore.ts: persisted a synthetic clientResponse error body even when the client had
already disconnected (AbortError) before that body was ever computed — misleading the
dashboard into showing "what the client received" for a response that was never sent.
Also: RequestLoggerDetail.tsx — Provider/Client Event Stream panes lost their collapse
toggle when StreamSection replaced the collapsible PayloadSection (
|
||
|
backryun
|
ed8755a6d0 | feat(github-models): refresh catalog and compatibility (#8225) | ||
|
backryun
|
34aefcf4e2 | fix(ci): repair release regressions exposed by clean runs (#7812) | ||
|
Paijo
|
9a6a846ae6 |
perf(memory): mitigate event-loop starvation under 3000+ provider connections (#7719)
* chore(ci): add .mergify.yml to main — Mergify only reads config from the default branch (#7168) * fix(ci): add the auto-enqueue pull_request_rule to the Mergify config (queue_conditions alone are eligibility-only) (#7179) * fix(ci): migrate Mergify auto-enqueue to merge_protections_settings.auto_merge_conditions (rules-based path is EOL 2026-07-16) (#7216) * fix(ci): drop Mergify batch settings (batching is a paid-tier feature; free plan queue is serial) (#7220) * fix(ci): merge queue tolerates the advisory dast-smoke failure (its GH-hosted build hang dequeued every attempt) (#7225) * test(ci): make the #6634 selfref guard hermetic — main's copy hard-fails every PR (#7341) main's copy of this test still does git I/O inside a unit test: const baseSrc = git(['show', 'origin/main:' + FILE]); Runners check out a shallow single ref, so origin/main does not resolve and the test dies with 'fatal: invalid object name origin/main'. Every PR into main fails Unit Tests (7/8) on it — today that is #7313, #7315, #7316, #7334, #7336 and #7337, six PRs red on a defect none of them introduced. #7313 has no other red at all. release/v3.8.49 already carries a fix ( |
||
|
Ry
|
ad5e67dc49 |
fix(quota): fix antigravity/agy multi-model quota skipping in combos (#7695)
* fix(quota): fix antigravity/agy multi-model quota skipping in combos * fix(quota): preserve exact-model scoping for unknown models in 'other' family * refactor(quota): extract helper to keep isQuotaExhaustedForRequest under the cognitive-complexity cap Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: irvandikky <irvandikky@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
0ecc380928 |
feat(sse): add nvidia NIM local RPM budget + concurrency cap (#6846) (#7726)
Phase 1 of client-side quota tracking for NVIDIA NIM (no rate-limit headers, no usage API): - Register nvidia in PROVIDER_DEFAULT_RATE_LIMITS (40 RPM sliding window, matching the documented free-tier note), operator-overridable via a new ResilienceSettings.providerQuotaOverrides map. - Per-connection concurrency cap (default 6) via a new nvidiaConcurrencyGate leaf module wrapping rateLimitSemaphore, wired into DefaultExecutor.execute(). - Per-model 429 lockout: confirmed already satisfied by #6773's passthroughModels flag on the nvidia registry entry (no new code needed) — added as a regression-guard test instead. Phase 2 (AIMD adaptive ceiling learning) and Phase 3 (dashboard quota card + combo-routing headroom preference) are explicitly deferred to follow-up issues, per the plan's own scope note. |
||
|
Jan Leon
|
ea650253af |
Stream model health probes for slow providers (#7377)
* fix(model-test): stream slow chat probes * fix(model-test): handle JSON responses for streaming probes * fix(model-test): preserve transient errors from streaming probes * fix(model-test): keep transient probe failures visible * chore(ci): rerun pull request checks * docs(model-test): clarify transient failure handling * chore(ci): rerun pull request checks * test(model-test): cover slow timeout response path * chore(quality): register base-branch mutation tests * fix(sse): stop real-network leak and DOMException crash in model-test-runner timeout path Two new tests added by this PR fail against the current release tip: - tests/unit/model-test-runner.test.ts's slow-timeout regression test races the cold-start cost of the chat-completions pipeline (SSE translators, compression settings, etc. all lazily init on the first real request in a process). With a 1s AbortController timeout, the abort can fire before chatCore ever reaches the executor's fetch() call; the mocked fetch is then invoked after the test's own `finally` block has already restored the real fetch, so the assertion on the mock never fires and the request leaks onto the real network. Warm up the pipeline with one fast, resolving mock call before timing the 1s scenario. - Once the warm-up unblocks that race, a second, real bug surfaces: withRateLimit's abort handling (open-sse/services/rateLimitManager.ts) mutates `reason.name = "AbortError"` in place. When `AbortController.abort()` is called with no explicit reason (as modelTestRunner's timeout path does), the default reason is a native DOMException, whose `name` is a read-only getter — the mutation throws `TypeError: Cannot set property name of [object DOMException] which has only a getter` instead of rejecting cleanly. Build a fresh Error instead of mutating the caller-supplied reason, preserving the original as `.cause`. Adds a focused regression test in tests/unit/rate-limit-manager.test.ts that reproduces the DOMException crash directly against withRateLimit. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@gmail.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
13e57b2b35 |
feat: rate-limit queue admission control (maxQueueDepth + 15s default) (#6593) (#7649)
Validated in merge-train 2026-07-18 @ 9084b408b: 12198/12201 pass; single red = earlyStreamKeepalive timer test, confirmed load-flake (6/6 green isolated on release tip AND the merged tree; no boarded PR touches keepalive) |
||
|
Diego Rodrigues de Sa e Souza
|
b729a8f273 |
Release v3.8.43 (#5609)
* chore(release): open v3.8.43 development cycle * docs(relay): clarify backend routing contract (#5621) Integrated into release/v3.8.43 (drift-shed: cherry-picked the real change onto the release tip; stale-base drift dropped). * fix(security): avoid rendering error stacks (#5624) Integrated into release/v3.8.43 (drift-shed: cherry-picked the real change onto the release tip; stale-base drift dropped). * fix(chatgpt-web): restore dot-form Pro model ids (#5549) Integrated into release/v3.8.43 (drift-shed: cherry-picked the real change onto the release tip; stale-base drift dropped). * feat(commandCode): add multimodal image support for CC vision models (#5557) Integrated into release/v3.8.43 (drift-shed: cherry-picked the real change onto the release tip; stale-base drift dropped). * fix(providers): validate M365 Copilot web credentials (#5432) Integrated into release/v3.8.43 (drift-shed: cherry-picked the real change onto the release tip; stale-base drift dropped). * fix(sse): bound chat hot-path heap — pressure-aware admission + response cap + clone reductions (#5152) (#5425) Integrated into release/v3.8.43 (drift-shed: cherry-picked the real change onto the release tip; stale-base drift dropped). * fix: model lockout not recording for 429 rate_limit_exceeded from Antigravity ## Problem When Antigravity returns HTTP 429 with `rate_limit_exceeded` error code, the model lockout system never records the failure, so the model is not cooled down despite being rate-limited. ### Root Cause Antigravity's 429 error text is: `"Resource has been exhausted (e.g. check quota)."` The QUOTA_PATTERNS in `classify429.ts` contained overly broad regexes: - `/resource.*exhaust/i` — matches "Resource has been exhausted" - `/check.*quota/i` — matches "check quota" This caused `classifyErrorText()` to return `QUOTA_EXHAUSTED` (wrong), which set `providerExhausted = true` in the combo target exhaustion logic. With `providerExhausted`, the retry path was skipped entirely, and while the "done retrying" path should still record lockout, the misclassification cascaded into incorrect provider-level exhaustion state. Additionally, `targetExhaustion.ts` used the raw error text string instead of the structured error code (`rate_limit_exceeded`) that was already parsed from the response body. ## Fix 1. **classify429.ts** — Removed overly broad `/resource.*exhaust/i` and `/check.*quota/i` from QUOTA_PATTERNS. Antigravity's rate-limit wording is not a true quota exhaustion signal. 2. **targetExhaustion.ts** — Added optional `structuredError` to `ApplyComboTargetExhaustionOptions`. When available, the structured error code (e.g. `rate_limit_exceeded`) takes precedence over raw error text for exhaustion classification. 3. **combo.ts** — Passes `structuredError` to both `applyComboTargetExhaustion` call sites (dispatch path + retry-or-rotate path). ## Effect `structuredError.code = "rate_limit_exceeded"` → classified as rate-limit (not quota) → `providerExhausted = false` → retry proceeds → `recordModelLockoutFailure` called → model enters lockout with proper cooldown (120s base, exponential backoff). ## Tests Added 2 new tests for `structuredError.code` precedence in exhaustion classification. All 28 related tests pass. * fix(checks): normalize route paths on windows (#5613) Integrated into release/v3.8.43. Windows path-normalization fix for the route-guard membership gate + regression test (Rule #18). Co-authored test added by maintainer. * fix: truncate tool list when provider limit exceeds MAX_TOOLS_LIMIT (grok-cli 200) - Add proactive PROVIDER_TOOL_LIMITS map with grok-cli: 200 - Fix regex to capture 'maximum is 200' (not '427 tools provided') - Remove broken truncation gate that skipped limits >= MAX_TOOLS_LIMIT (128) - Add tests for Grok regex, proactive limits, and limits above threshold Refs #5563 * test(chatcore): cover grok-cli tool-list truncation via prepareUpstreamBody (#5563) Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(security): v3.8.15 hardening follow-ups (Seg2/Seg3/Seg4/Bug3) (#5512) Security v3.8.15 hardening follow-ups: Seg2 (CHANGEME boot warn), Seg3 (auth_token cookie maxAge 30d), Seg4 (VS Code path-token once-per-process warning), Bug3 (real global install path resolution), Bug1 (segment-match node_modules in auto-update detection). All 5 carry TDD regression guards. * Fix HuggingChat web session routing (#5592) (#5592) Integrated into release/v3.8.43. HuggingChat web session-routing fix (root parent-message fetch + cookie propagation + encrypted-credential guard) + 24-model catalog refresh. Maintainer adjustments (co-authored): reverted the freeModelCatalog.data.ts whole-file reformat down to the surgical 24-record huggingchat change (preserving the auto-generated compact format), and added a 502 regression test for the null parent-message-id path (Rule #18). * fix: preserve system role for GLM 5.1/5.2 (#5610) (#5663) * fix: restore Codex Responses WS TLS profile + apply proxy (#5591, #5611) (#5668) * fix: allow saving providers without a live validator (#5565, #5567) (#5669) * fix: static model catalog for jules/linkup/ollama/searchapi search providers (#5569, #5571, #5573, #5575) (#5672) * fix: live AI/ML API catalog + deprecate dead CablyAI (#5570, #5568) (#5673) * fix: correct 404 provider setup links for ollama/searchapi/you.com (#5572, #5574, #5576) (#5674) * fix: page call_logs cleanup queries to avoid startup OOM on large DBs (#5618) (#5675) * fix: use PowerShell Expand-Archive on Windows for embedded-service install (#5590) (#5678) * fix: treat array content blocks as valid output in detectMalformedNonStream (#5559) (#5680) * fix: render memory engine status detail strings in English (#5596) (#5685) * fix: free proxy pool silent sync failure — iplocate txt + per-source isolation + surface errors (#5595) (#5686) * chore(quality): close QG v2 tail — drop orphan semcheck.yaml + Fase 9 maturity re-eval (#5681) - Remove semcheck.yaml: orphan config (zero workflow/script wiring) with stale rule counts; deterministic doc-accuracy coverage already exists (check:fabricated-docs --strict + docs-counts-sync + docs-symbols). Drop the REPOSITORY_MAP row referencing it. - Add docs/ops/MATURITY_REEVAL.md (Fase 9): re-measures maturity post-Ondas 0-3. The two biggest structural weaknesses from QUALITY_GATE_PLAYBOOK (2026-06-16) are now closed: fast-gates hole (quality.yml runs typecheck:core + impacted TIA unit tests + vitest + shards) and mutation-score-as-ratchet (check-mutation-ratchet.mjs + seeded baseline + nightly blocking job). Residual gap is owner/infra-gated (branch-protection main, SLSA L3, CodeQL advanced). - Record agent-lsp as deferred/opt-in (doc-only scaffold, no wiring). * fix(ci): stabilize nightly-mutation — guard tap.testFiles drift + anti-flake eps (#5682) Root cause (NOT a timeout): the nightly-mutation run fails on cold-cache nights because the blocking mutation-ratchet job measures modules below baseline, while warm-cache nights pass — the verdict tracked GitHub Actions cache state, not code quality. Proven via a local Stryker probe on headers.ts: covering unit tests (no-memory-header, strip-reasoning) had drifted OUT of stryker.conf.json tap.testFiles, so their mutants went covered-but-unkilled = Survived on a cold full run (COVERED score 61.73 vs 94.29 baseline); adding them restores the kills. - Add scripts/check/check-mutation-test-coverage.mjs: guards that every UNIT test importing a Stryker-mutated module is listed in tap.testFiles. Advisory by default, --strict in CI (wired in quality.yml fast-gates). Prevents recurrence. - Add the 38 drifted covering unit tests to stryker.conf.json tap.testFiles (138 -> 176). Monotonically safe: more covering tests only raise/hold the score. - Add MUTATION_RATCHET_EPS (1.0pt) anti-flake tolerance to check-mutation-ratchet so sub-point tap-runner jitter no longer false-fails the gate. Lowers no baseline. - Tests: check-mutation-test-coverage (3) + eps cases in check-mutation-ratchet. Residual: a clean post-merge nightly confirms scores return to/above baseline; any marginal residual gets a baseline re-seed (operator). * refactor(dashboard): split sidebarVisibility god-file into types + sections leaves (#5683) Behavior-preserving decomposition: src/shared/constants/sidebarVisibility.ts 1197 -> 291 LOC by extracting two leaves under sidebarVisibility/: - types.ts (160): HIDEABLE_SIDEBAR_ITEM_IDS + all sidebar types (self-contained). - sections.ts (762): section building-block consts + SIDEBAR_SECTIONS (imports types only — cycle-safe). COMPRESSION_CONTEXT_GROUP + SIDEBAR_SECTIONS stay exported; host re-exports both + 'export *' of types, so every consumer import path is unchanged. Byte-identical data verified via JSON.stringify of HIDEABLE_SIDEBAR_ITEM_IDS / SIDEBAR_ICON_ACCENTS / COMPRESSION_CONTEXT_GROUP / SIDEBAR_SECTIONS / SIDEBAR_PRESETS + getSectionItems output (identical before/after). typecheck:core, check:cycles (no cycles), check:file-size (3 files <800), and the 3 sidebar suites (20/20) pass. No logic changed. Note: file-size frozen baseline for sidebarVisibility.ts (1198) can ratchet to 291 to lock the shrink (left for the release ratchet / operator). * fix: surface fusion-specific config on the Global Routing tab (#5598) (#5688) * fix(executor): route OpenAI-compatible MCP Responses requests to /responses (#5483) Closes #5483. OpenAI-compatible providers receiving a Responses-shaped request carrying MCP / tool_search tools now route to the upstream /responses endpoint instead of downgrading to /chat/completions, preserving Codex deferred tool discovery. Detection helpers extracted to open-sse/executors/forceResponsesUpstream.ts. Thanks to @KooshaPari. * fix(ci): make release-green pre-flight gates visible + bounded so unit reds are not missed (#5644) Integrated into release/v3.8.43. * fix(body-size): raise LLM API payload limit for responses routes (#5652) Integrated into release/v3.8.43. Thanks @JxnLexn! * fix(test): use lightweight health probe for batch e2e (#5651) Integrated into release/v3.8.43. Thanks @KooshaPari! * feat(compression): T05/C5 — preserveSystemPrompt mode enum + legacy back-compat (#5653) Integrated into release/v3.8.43. Includes the legacy-boolean back-compat derivation so existing preserveSystemPrompt=false installs keep whenNoCache behavior. * routing: optimize latency strategy with perf metrics (#5629) Integrated into release/v3.8.43. Thanks @KooshaPari! * feat(db): models/5004 — self-correcting model context-window overrides (#5667) Integrated into release/v3.8.43. * feat(providers): complete SenseNova free Token Plan — chat + Text-to-Image (port from 9router#2233) (#5679) Integrated into release/v3.8.43. * feat(api): routing/4985 — configurable response-body validation + failover (#5684) Integrated into release/v3.8.43. * fix(chatcore): default Claude tool type to "custom" when missing (#5662) Integrated into release/v3.8.43. Port from 9router#2196. Co-authored-by: warelik <warelik@users.noreply.github.com> * fix(translator): merge consecutive same-role contents for Gemini (port from 9router#2191) (#5661) Integrated into release/v3.8.43. Port from 9router#2191. * chore(bun): add locked bun runtime dependency (#5615) Integrated into release/v3.8.43. Bun 1.3.10 pinned via npm lockfile (adopt-partial decision). Thanks @KooshaPari! * chore(bun): run validated ts scripts with bun (#5612) Integrated into release/v3.8.43. Thanks @KooshaPari! * chore(bun): run CI script checks with bun (#5617) Integrated into release/v3.8.43. Validated bun==node output for all 3 gates (provider-consistency, compression-budget, known-symbols). Thanks @KooshaPari! * fix(build): make pack validator bun safe (#5643) Integrated into release/v3.8.43. Forward-compat guard; node/npm path unchanged. Thanks @KooshaPari! * docs: document Bun as the allow-listed build/dev script runner (Node stays the published runtime) (#5703) Integrated into release/v3.8.43. * feat(analytics): show $0 cost for flat-rate subscription/cookie providers (#5552) (#5704) * refactor(api): extract unified-catalog helpers into cohesive leaf modules (#5699) BLOCO E2 of the god-files campaign. The module-level pure/standalone helpers in src/app/api/v1/models/catalog.ts (1611 LOC) were lifted out verbatim into five cohesive leaf modules so the catalog host shrinks toward the 800-LOC file-size cap without any behavior change (host now 1345 LOC; the heavy getUnifiedModelsResponse orchestrator is untouched — its in-function closures stay put): - catalogHelpers.ts — pure numeric/array/shape helpers + shared catalog types - catalogOpenrouter.ts — OpenRouter id/modality/free-model/display-name helpers - catalogVision.ts — vision-capability field derivation (+ isVisionModelId re-export) - catalogProviderMaps.ts — alias<->providerId resolution maps (buildAliasMaps) - catalogRequest.ts — /v1/models API-key auth gating + Codex CLI client detection The host re-exports getCustomVisionCapabilityFields and isVisionModelId so the public API consumed by other tests (llm-selector-custom-vision-models, vision-detection- consistency) is unchanged; all 9 catalog/vision suites stay green. Adds tests/unit/catalog-helpers-extraction.test.ts: characterization tests for every extracted helper + a guard asserting the host preserves its public exports. Validated: typecheck:core, 50 catalog characterization tests, 12 new leaf tests, integration-wiring, check:cycles, check:file-size (no new violations), ESLint, Prettier. * feat(mcp): T07 — expose RTK learn/discover as MCP tools (#5691) Adds two read-only MCP tools wrapping the existing RTK discovery primitives: omniroute_rtk_discover (discoverRepeatedNoise/suggestFilter over recently captured raw tool output → candidate noise patterns + suggested filter) and omniroute_rtk_learn (listRtkCommandSamples + commandToId). Scope read:compression, MCP audit-logged, no new engine logic. Regression guard: tests/unit/compression/rtk-mcp-tools.test.ts. gaps v3.8.42 — T07. * feat(compression): T05/C3 — opt-in LLM-tier compression engine (#5702) Adds an opt-in, default-off LLM-tier compression engine ('llm') that condenses non-system message prose via a pluggable chat-completion backend, mirroring the llmlingua contract. Safe by construction: no-op default backend (pass-through out of the box), not in the default stacked pipeline, enabled defaults false, fenced code blocks + system messages never sent to the model, fail-open everywhere, minTokens floor. Real production backend is a VPS-validated follow-up (Hard Rule #18). Regression guard: tests/unit/compression/llm-compressor-engine.test.ts (8). gaps v3.8.42 — T05/C3. * refactor(db): extract compat/aliases/mitm helpers from db/models.ts into leaf modules (#5705) BLOCO E3 of the god-files campaign. db/models.ts (1250 LOC) mixed six concerns; the three cleanly-separable ones plus the shared key_value helpers were lifted out verbatim into a new src/lib/db/models/ subdirectory, leaving the tightly-coupled custom/synced/ flags trio in the host (host now 936 LOC). The host re-exports every moved public symbol so the module's public API (consumed by ~29 test files + localDb) is unchanged. - models/shared.ts — asRecord / toNonEmptyString / getKeyValue + JsonRecord (19 LOC) - models/compat.ts — model-compat overrides + sanitizeUpstreamHeadersMap (249 LOC) - models/aliases.ts — model-alias CRUD + cascade delete (61 LOC) - models/mitmAlias.ts — MITM alias get/set (32 LOC) The custom/synced/flags trio stays in the host because it is genuinely coupled (flags->getCustomModelRow, flags->readCompatList, custom->removeModelCompatOverride, synced->getModelIsDeleted, setModelIsHidden->updateCustomModel) — splitting it cleanly is a follow-up. Dependency DAG is acyclic (verified by check:cycles). Adds tests/unit/db-models-split.test.ts: characterization of the pure extracted helpers + a guard asserting the host preserves its full public export surface. Validated: typecheck:core, check:cycles (no cycles), 77 existing db/models consumer tests (db-models-crud/extended/aliases-cascade + 7 more) green, 7 new tests, ESLint, Prettier, check:file-size (host 936 < frozen 1259; no new violations). * refactor(db): extract pricing/lkgp/cache-metrics from db/settings.ts into leaf modules (#5709) BLOCO E3 of the god-files campaign. db/settings.ts (1154 LOC) mixed five concerns; the three cleanly-separable ones plus the shared toRecord/JsonRecord helper were lifted out verbatim into a new src/lib/db/settings/ subdirectory, leaving the Settings-core + Proxy config concerns in the host (host now 646 LOC). The host re-exports every moved public symbol so the module's public API (consumed by ~93 test files + localDb) is unchanged. - settings/shared.ts — toRecord + JsonRecord (9 LOC) - settings/pricing.ts — pricing layers/sources/per-model + update/reset (254 LOC) - settings/lkgp.ts — Last-Known-Good-Provider get/set/clear (49 LOC) - settings/cacheMetrics.ts — cache metrics + trend (235 LOC) Settings-core + the Proxy-config concern stay in the host: proxy is the most tangled (245-line resolveProxyForConnection, resolution cache, imports from ./proxies) and getSettings is the most central function — leaving them is the correct coupled-core stop. Pricing/LKGP/Cache have NO dependency on Settings/Proxy helpers (verified); the dependency DAG is acyclic (check:cycles). Adds tests/unit/db-settings-split.test.ts: characterization of the shared toRecord helper + a guard asserting the host preserves its full public export surface. Validated: typecheck:core, check:cycles (no cycles), 149 existing+new db/settings consumer tests green (db-settings-crud/extended, 8 pricing suites, cache-metrics, 2 proxy-resolution suites + 29 new), ESLint, Prettier, check:file-size (host 646 < frozen 1155). * fix(translator): re-apply lost defensive hardening for Gemini merge + Claude tool defaults (#5706) Re-applies two dropped gemini-code-assist hardening fixes (defaultClaudeToolType non-object passthrough; mergeConsecutiveSameRoleContents shallow-copy) with regression tests. Follow-up to #5661/#5662. Integrated into release/v3.8.43. * feat(codex): generate fallback profiles for compatible models (#5701) setup-codex now generates Codex profiles for compatible text models from the live /v1/models catalog when the model id doesn't match a hand-tuned pattern, skipping media/embedding models. Integrated into release/v3.8.43. * docs(changelog): credit @Chewji9875 for #5563 + #5579 Add CHANGELOG credit bullets for grok-cli tool-limit (#5563) and Antigravity 429 lockout (#5579). Documentation-only. * test(dashboard): repoint sidebar quota-share placement scan to sections.ts (#5711) The D1 god-file split (#5683) moved the nav-item id definitions out of src/shared/constants/sidebarVisibility.ts into the extracted leaf src/shared/constants/sidebarVisibility/sections.ts. This source-scan test still read the old monolith path, so it found 0 occurrences of id: "costs-quota-share" and failed (base-red on release/v3.8.43). Repoint SIDEBAR_PATH to sections.ts where the ids now live. All four placement assertions (quota-share after quota, same array, far from costs-budget, exactly one occurrence) hold against the new source. * refactor(db): extract columns/nodes/rate-limit leaves from db/providers.ts (#5714) db/providers.ts was a 1106-line god-file mixing four concerns. Extract the three acyclic, cohesive slices into sibling leaf modules under src/lib/db/providers/, leaving the tightly-coupled connection-CRUD core in the host: - providers/columns.ts (116) 10 pure column-normalizer helpers (DB-free) - providers/nodes.ts (163) 6 provider-node CRUD functions - providers/rateLimit.ts (177) 6 rate-limit/quota runtime helpers + formatResetCountdown Host providers.ts: 1106 -> 719 lines. The connection-CRUD core does not call any node or rate-limit function (verified), so the host re-exports the 12 moved public symbols via `export { ... } from './providers/<leaf>'` — the module's public API stays IDENTICAL (23 symbols). Bodies moved verbatim (byte-identical); the only edit to a moved line is the added `export` on the 10 previously-private normalizers. Behavior-preserving: 122 existing provider/quota/rate-limit consumer tests stay green; new tests/unit/db-providers-split.test.ts guards the re-export barrel + characterizes the pure column helpers (38 assertions). Refs #3501 (god-file structural shrink). * refactor(db): extract types + pure mappers from db/proxies.ts (#5717) db/proxies.ts was a 1059-line god-file. Extract the two acyclic, DB-free slices into sibling leaf modules under src/lib/db/proxies/, leaving the tightly-coupled CRUD + assignment + resolution core in the host: - proxies/types.ts (65) 10 proxy type/interface declarations - proxies/mappers.ts (180) pure row mappers / scope normalizers / payload coercers (toRecord, mapProxyRow, mapAssignmentRow, isRelayProxyType, extractRelayAuth, toRegistryProxyResolution, normalizeScope, normalizeAssignmentScopeId, toLegacyProxyLevel, coerceProxyPayload, redactProxySecrets) Host proxies.ts: 1059 -> 847 lines. The resolution functions call createProxy/assignProxyToScope, so the CRUD+resolution core CANNOT be extracted without an import cycle and stays in the host. The host re-exports the 2 moved public functions (extractRelayAuth, redactProxySecrets) via `export { ... } from './proxies/mappers'` — the public API stays IDENTICAL (20 functions; no types were ever publicly exported). Bodies moved verbatim; the only host edits are the new leaf imports, the re-export, dropping the now unused `import { decrypt }`, and two prettier line-wrap reflows of retained ternary/union lines (token-identical). Behavior-preserving: 69 existing proxy/registry/relay/family consumer tests stay green; new tests/unit/db-proxies-split.test.ts guards the re-export barrel + characterizes the pure mappers (35 assertions). Refs #3501. * refactor(db): extract static migration data tables from migrationRunner.ts (#5721) migrationRunner.ts (1124 lines, frozen-baselined) is the startup migration orchestrator. As a conservative, zero-behaviour-risk first slice, extract the six static migration-compatibility DATA tables (verbatim) into a pure-data leaf, leaving the entire orchestrator + all SQL-running helpers in the host: - migrationRunner/constants.ts (118) RENAMED_MIGRATION_COMPATIBILITY, LEGACY_VERSION_SLOT_MIGRATIONS, SUPERSEDED_DUPLICATE_MIGRATIONS, PHYSICAL_SCHEMA_SENTINELS, INITIAL_SCHEMA_SENTINELS, OPTIONAL_FTS5_MIGRATION_VERSIONS Host migrationRunner.ts: 1124 -> 1023. The runtime fts5SupportCache (a WeakMap, mutable state) stays in the host. No public API change (these consts were module-internal). Data moved byte-identical (sed-extracted, verbatim verified); the only host edits are the leaf import + one prettier collapse of a pre-existing 2-line union type annotation to 1 line (token-identical, typecheck-confirmed). Characterize-first (operator-chosen): the existing db-migration-runner.test.ts (26 tests) + no-migration-collisions/weak-rng-fixes/check-db-rules (11) prove the reconciliation/dedup/already-applied BEHAVIOUR is unchanged; the new tests/unit/db-migrationrunner-constants-split.test.ts (7 tests) PINS THE DATA (counts + shape + spot-checks of every table) so a dropped/transposed row is caught immediately. Refs #3501. * refactor(db): extract pure SQL-source builders from usageAnalytics.ts (#5722) usageAnalytics.ts (924 lines, frozen-baselined) mixes two pure SQL-source builders with ~20 getXxxRows() query functions. Extract the contiguous, DB-free builder block verbatim into a leaf, leaving every query function in the host: - usageAnalytics/sources.ts (208) AnalyticsParams, BuildUnifiedSourceOptions, UnifiedSourceResult + buildUnifiedSource + buildPresetUnifiedSource (pure string builders; no DB, no imports) Host usageAnalytics.ts: 924 -> 723. The query functions do not call the builders (callers build the unified source then pass the string in), so the host re-exports the 5 moved public symbols (2 fns + 3 types) and imports AnalyticsParams as a type for its query signatures — the public API stays IDENTICAL (39 symbols). Builder bodies moved byte-identical; the two orphaned section-header banners that described the moved block were removed with it; the retained query-function suffix is byte-identical to the original. Behavior-preserving: 37 existing analytics consumer tests stay green (usage-analytics 12, usage-endpoint-dimension 3, db-usage-analytics-3500 22); new tests/unit/db-usageanalytics-split.test.ts (25 assertions) characterizes buildUnifiedSource's needsAggregated branching (raw-only vs raw+daily_usage_summary) + guards the 39-symbol re-export barrel. Refs #3501. * docs(readme): refresh metrics, list 17 strategies, add Quota-Share + real provider logos - Unify provider count to 236; MCP tools 87->94; cloud agents 3->4 (+Cursor); compression 9->10 engines (+relevance) - Tests -> 21,000+ across 2,586 files; footer -> v3.8.43 - Raise lower bounds to real values: 90+ free, 80+ commands, 24+ CLIs - Language flag grid 33->43 (15/14/14, all locales) - List all 17 routing strategies; new Quota-Share section before Resilience - Real provider logos (lobe-icons + local agentrouter) in providers grid and Free Forever - Top Contributors: refreshed stats + add herjarsa; 280+ title; half-size avatars; contrib.rocks 100->200 - Acknowledgments: refreshed star counts; fix headroom repo rename * docs(readme): update provider counts and add new badges * feat(memory): T10/TV6 — opt-in typed memory decay (#5723) Opt-in typed memory decay so the conversational memory store self-prunes stale episodic noise. access_count + last_accessed_at telemetry (migration 111) is always-on/non-destructive; the sweep is opt-in (MEMORY_TYPED_DECAY_ENABLED, default false). Only episodic decays by default (30d); factual/procedural/semantic immune; access_count>=3 earns immunity; deletions reuse deleteMemory (SQLite+vec+Qdrant in sync), fail-open. Regression guard: tests/unit/memory/typed-decay.test.ts (15). gaps v3.8.42 — T10/TV6. * feat(dashboard): T06/T03 — drag-reorder compression pipeline editor + studio e2e (#5727) T06: named-combos editor gains a @dnd-kit/sortable drag-to-reorder stacked pipeline backed by a pure model (compressionPipelineModel.ts: add/remove/move/update, engine->intensity invariant, never-empty). CompressionPipelineEditor.tsx replaces the inline fixed list in CompressionCombosPageClient; order persists via the existing combos endpoint (no API change). T03: adds tests/e2e/compression-studio.spec.ts (Tela A render + Play/Compare tab switch), the dedicated compression-studio e2e combo-live-studio.spec.ts did not cover. TDD: compression-pipeline-model.test.ts (11) + compression-pipeline-editor.test.tsx (4). gaps v3.8.42 — T06 + T03. * fix(thinking): wire Thinking-Budget boot hydration into live instrumentation path (#5312) (#5729) hydrateThinkingBudgetConfig was only called from the unused src/server-init.ts, which never runs in production, so the dashboard Thinking-Budget mode silently reverted to passthrough on every restart. Wire it into the real boot path (src/instrumentation-node.ts), next to the Global System Prompt restore. Surfaced by live Anthropic-OAuth validation on the VPS (fix A of #5312 was non-functional even though its direct unit test passed). New guard tests/unit/thinking-budget-boot-wiring-5312.test.ts asserts the production boot module calls the hydration, closing the test gap that let this ship. * refactor(usage): extract pure formatting helpers from callLogs.ts (#5725) callLogs.ts (996 lines, frozen-baselined) mixes pure log-formatting / sanitization helpers with DB CRUD, disk-artifact, and rotation logic. Extract the ten pure, DB-free helpers verbatim into a leaf, leaving all stateful code in the host: - callLogs/format.ts (129) asRecord, toNumber, toStringOrNull, truncateText, parseInlineError, normalizeDetailState, sanitizeErrorForLog, toStoredErrorSummary, protectPipelinePayloads, buildRequestSummary Host callLogs.ts: 996 -> 885. The stateful generateLogId (mutates logIdCounter) stays in the host. These helpers were all module-internal, so the public API is unchanged (10 exported functions). Bodies moved byte-identical; the host's now unused 'sanitizePII' import (only referenced inside the moved bodies) moved to the leaf; prettier wrapped buildRequestSummary's signature across lines once the 'export' prefix pushed it past 100 cols (token-identical). Behavior-preserving: 46 existing call-log consumer tests stay green (call-log-cap 14, pagination 4, file-rotation 5, log-retention 5, startup 1, oom 2, trim-sql 2, db-settings-maintenance 13); new tests/unit/calllogs-format-split.test.ts (26 assertions) characterizes the pure helpers + guards the 10-function public API. Refs #3501. * refactor(usage): extract pure stat/coercer helpers from usageHistory.ts (#5728) usageHistory.ts (987 lines, frozen-baselined) mixes pure DB-free helpers with an in-memory pending-request state machine and DB CRUD. Extract the contiguous pure block verbatim into a leaf, leaving all stateful code in the host: - usageHistory/helpers.ts (85) asRecord, toStringOrNull, normalizeServiceTier, toNumber, percentile, stdDev, truncatePendingPreview (+ its MAX_PREVIEW_* bounds, co-located) Host usageHistory.ts: 987 -> 916. The pending-request state machine (module Maps + track/update/finalize/sweep) and DB CRUD stay in the host. These helpers were all module-internal, so the public API is unchanged (21 direct exports + the pre-existing getCompletedDetails re-export = 22). Bodies moved byte-identical (leaf 0 non-verbatim lines); the host's local 'type JsonRecord' moved with the bodies that used it (host no longer references it — typecheck-confirmed). Behavior-preserving: 38 existing usage-history consumer tests stay green (usage-history-db 5, api-key-usage-limits 6, log-retention 5, usage-endpoint-dimension 3, provider-request-failure-pipeline 6, database-settings-maintenance 13); new tests/unit/usagehistory-helpers-split.test.ts (30 assertions) pins the percentile/stdDev formulas + normalizeServiceTier + guards the public API. Refs #3501. * refactor(usage): extract pure quota-normalize helpers from providerLimits.ts (#5730) providerLimits.ts (954 lines, frozen-baselined) is the heavily DB/network-coupled provider quota sync module. Extract a small, fully SELF-CONTAINED leaf of pure quota-key/quota-value normalization helpers (+ the isRecord type guard they share), leaving all sync/DB/network code in the host: - providerLimits/quotaNormalize.ts (72) isRecord, isUsageQuotaKeyAllowed, normalizeUsageQuotaKey, normalizeUsageQuotasForProvider, sanitizeUsageQuotasForProvider Host providerLimits.ts: 954 -> 890. The leaf imports only the external antigravity/agy model-alias helpers the moved bodies reference (moved from the host's import block) — it does NOT import the host, so check:cycles stays clean (no cycle). isRecord (used ~9x in the host) is co-extracted and imported back. These five were all module-internal, so the public API is unchanged (13 exported functions). Bodies moved byte-identical. Behavior-preserving: 18 existing provider-limits consumer tests stay green (sanitize-scope 3, db-provider-limits 3, proxy-fail-closed 3, rotating-expired-guard 7, codex-quota-sync 2); new tests/unit/providerlimits-quotanormalize-split.test.ts (19 assertions) pins isRecord + isUsageQuotaKeyAllowed + guards the 13-function public API. Refs #3501. * refactor(memory): extract pure scoring/conversion helpers from retrieval.ts (#5733) retrieval.ts (1192 lines — ABOVE its 1171 frozen baseline) is the memory retrieval engine (DB + vector + rerank network). Extract the pure, DB-free scoring/conversion helpers (+ the MemoryRow row shape they share) verbatim into a self-contained leaf, leaving all DB/vector/network code in the host: - retrieval/scoring.ts (104) interface MemoryRow + estimateTokens, parseMetadata, rowToMemory, getRelevanceScore Host retrieval.ts: 1192 -> 1072 — back UNDER the 1171 frozen baseline (the split also repairs the pre-existing file-size drift). The leaf imports only ../types, never the host, so check:cycles stays clean (no cycle). MemoryRow moved to the leaf and imported back as a type by the host's DB row functions. The public estimateTokens is re-exported from the leaf; the host also imports it for its internal token-budget loops. The other three helpers were module-internal, so the public API is unchanged (7 exports). Bodies moved byte-identical. Behavior-preserving: 38 existing memory-retrieval consumer tests stay green (rerank 5, hybrid 6, semantic 6, engine-status 9, stats-api 12); new tests/unit/retrieval-scoring-split.test.ts (11 assertions) pins estimateTokens (ceil(len/4)) + parseMetadata + rowToMemory mapping + getRelevanceScore (+20 phrase / +3 token) and guards the public API. Refs #3501. * refactor(sse): extract reasoning-tag detection/extraction from responseSanitizer.ts (#5734) responseSanitizer.ts (1133 lines, frozen-baselined) mixes reasoning-tag detection/extraction with response/usage/streaming sanitization. Extract the cohesive, ZERO-IMPORT reasoning block verbatim into a self-contained leaf: - responseSanitizer/reasoning.ts (143) the reasoning regex consts + collapseExcessiveNewlines, cleanReasoningFragment, splitClosingOnlyReasoningPrefix, movePrefixBeforeContentTagToThinking, extractThinkingFromContent, normalizeReasoningRouteId, isAntigravityReasoningRoute, isTextualReasoningTagNativeRoute, shouldParseTextualReasoningTags Host responseSanitizer.ts: 1133 -> 1003. The block's helpers only call each other, so the leaf has ZERO imports — it cannot import the host (check:cycles clean). The host imports back collapseExcessiveNewlines (6 call sites) + extractThinkingFromContent, and re-exports the two public symbols (extractThinkingFromContent, shouldParseTextualReasoningTags) — the public API stays IDENTICAL (7 exports). Bodies moved byte-identical; two long declarations (REASONING_TAG_FRAGMENT_REGEX, movePrefixBeforeContentTagToThinking signature) were line-wrapped by prettier once the 'export' prefix pushed them past 100 cols (token-identical). Behavior-preserving: 47 existing consumer tests stay green (response-sanitizer 36, strip-reasoning-header 8, textual-toolcall-false-positive 3); new tests/unit/responsesanitizer-reasoning-split.test.ts (11 assertions) characterizes extractThinkingFromContent + shouldParseTextualReasoningTags and guards the public API. Refs #3501. * refactor(sse): extract rate-limit header parsing from rateLimitManager.ts (#5736) rateLimitManager.ts (1034 lines, frozen-baselined) is the stateful rate-limiter (Bottleneck limiters, watchdog timers, learned-limits Map). Extract the pure, ZERO-IMPORT header-parsing block verbatim into a self-contained leaf, leaving all stateful machinery in the host: - rateLimitManager/headers.ts (94) STANDARD_HEADERS, ANTHROPIC_HEADERS, parseResetTime, toPlainHeaders Host rateLimitManager.ts: 1034 -> 945. The four items are pure (no limiter state, no external deps), so the leaf has ZERO imports — it cannot import the host (check:cycles clean). The host imports all four back (used by updateFromHeaders). They were module-internal, so the public API is unchanged (17 exports). Bodies moved byte-identical. Behavior-preserving: 21 existing rate-limit consumer tests stay green (rate-limit-manager 7, limiter-lifecycle 4, queue-timeout-msg 2, idle-eviction 6, body-lock 2); new tests/unit/ratelimitmanager-headers-split.test.ts (7 assertions) pins parseResetTime (durations / bare-number / nullish) + toPlainHeaders + guards the 17-function public API (with a watchdog-timer teardown hook so the runner exits cleanly). Refs #3501. * fix(config): back boot-hydrated proxy config singletons with globalThis (#5312) (#5742) Next.js compiles instrumentation.ts as a separate webpack module graph from the app-route/open-sse executors, so a module-local `let _config` is duplicated: the boot-time hydration (applyRuntimeSettings / restore hooks) lands on the instrumentation graph's copy, but the request path (base.ts) reads a different, un-hydrated copy. Live VPS validation proved the Thinking-Budget hydrate ran to completion at boot yet base.ts still read the passthrough default — why #5312 fix A stayed broken after the boot-wiring fix. Back the singletons with globalThis (the pattern systemPrompt.ts already uses for #2470) so all graph copies share one instance: - thinkingBudget.ts — dashboard Thinking-Budget mode reaches the executor - backgroundTaskDetector.ts — opt-in background degradation actually fires - systemTransforms.ts — operator pipeline overrides reach the request path payloadRules.ts was already safe (lazy per-request DB self-load, #2986). Guards: thinking-budget-globalthis-5312 + runtime-config-globalthis-5312 (assert globalThis sharing; a module-local let fails them, RED->GREEN). * refactor(evals): extract built-in golden-set suites from evalRunner.ts (#5740) Move the 7 static built-in eval suites (golden-set, coding-proficiency, reasoning-logic, multilingual, safety-guardrails, instruction-following, codex-comparison) plus the builtInSuites aggregate into the pure-data leaf src/lib/evals/evalRunner/builtinSuites.ts (zero imports, no side effects). evalRunner.ts keeps all logic (register/get/list/evaluate/run/scorecard/reset) and registers the leaf suites at module load, mirroring the original inline calls. Public API is unchanged (7 exported functions; the suite consts were already module-private). Host 960->301 LOC; leaf 676 LOC (< 800 cap); host was frozen-satisfied (961), so this is debt reduction. Suite data moved verbatim (652 data lines byte-identical). New split-guard test characterizes the suite ids/case counts/key cases and proves the host registers every leaf suite at load. * refactor(models): extract pure transform layer from modelsDevSync.ts (#5743) Move the models.dev data-model types, the provider-id mapping table (MODELS_DEV_PROVIDER_MAP + mapProviderId), and the raw->OmniRoute transforms (transformModelsDevToPricing, transformModelsDevToCapabilities) into the pure leaf src/lib/modelsDevSync/transform.ts (zero imports, no DB, no module state). modelsDevSync.ts keeps all sync orchestration, DB access, caches and the periodic-sync timer; it imports the transforms for internal use and re-exports mapProviderId/transformModelsDevToPricing/transformModelsDevToCapabilities plus the ModelCapabilityEntry/CapabilitiesByProvider types, so the public API is unchanged. Host 924->677 LOC; leaf 279 LOC (< 800 cap); host was frozen-satisfied (934), so this is debt reduction. 238 moved lines are byte-identical. New split-guard test characterizes the provider map + both transforms and proves the host re-exports them. * refactor(resilience): split settings.ts into types + normalize leaves (#5745) Decompose the (fully pure) resilience settings module into two sibling leaves: - src/lib/resilience/settings/types.ts: the settings shape (11 public interfaces + JsonRecord/AuthCategory), zero imports. - src/lib/resilience/settings/normalize.ts: the coercers (asRecord/toInteger/ toBoolean/feature-flag resolvers) + the 11 per-section normalize* functions. settings.ts keeps DEFAULT_RESILIENCE_SETTINGS, DEFAULT_REQUEST_QUEUE_MAX_WAIT_MS, buildLegacyFallback, and the public orchestrators (resolveResilienceSettings, mergeResilienceSettings, buildLegacyResilienceCompat); it imports the coercers/normalizers for internal use and re-exports the 11 settings interfaces, so the public API is unchanged. Host 840->363 LOC; leaves 182 + 359 LOC (< 800 cap); host was frozen-satisfied (841), so this is debt reduction. 472 moved lines are byte-identical; no cycles (leaves never import the host). New split-guard test characterizes the coercers/normalizers and the host resolve/merge/compat orchestration. * docs(readme): document faster/leaner install — skip native build, sql.js fallback (#5713) Documents the optional better-sqlite3 + pure-JS fallback chain and OMNIROUTE_SKIP_POSTINSTALL/CI skip flags. Docs-only, claims verified. (#5550) * feat(compression): T02 opt-in per-engine pipeline circuit-breaker (#5735) Opt-in, default-off per-engine circuit-breaker for the stacked compression pipeline. Byte-identical to legacy when off. 9 regression tests. * docs: sync MCP tool count to 95 + routing-strategy count (#5732) Sync CLAUDE.md/README.md to canonical MCP tool count (95, 35 base) and routing strategies (17). Numbers fact-checked against getAllToolDefinitions()/ROUTING_STRATEGY_VALUES. * feat(api): add first-class Ollama local provider card (#5712) First-class ollama-local provider card (localhost:11434/v1, keyless, passthrough models) in LOCAL_PROVIDERS + SELF_HOSTED + default.ts executor case. Docs count 236→237, Local 11→12 (full README sweep). 4 tests. (#5578) * feat(api): add opt-in API-key provider quota-policy bypass scope (#5731) Adds an opt-in per-API-key scope (policy:bypass-provider-quota) that lets a key skip provider/account-side quota cutoffs during routing. Operator USD budgets/usage limits still enforced unconditionally (fail-closed, before the bypass). Default-off; UI toggle + badge in API Manager. Integrated into release/v3.8.43. * feat(codex): opt-in auto-sync of Codex profiles after model discovery (#5737) Auto-sync ~/.codex/*.config.toml profiles after a provider model sync, reusing the setup-codex generator. Opt-in, default OFF (OMNIROUTE_AUTO_SYNC_CODEX_PROFILES=true; also honors CLI_ALLOW_CONFIG_WRITES). Never touches the active Codex config. Gating test added. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * feat(providers): opt-in CLI profile auto-sync toggles + Claude Code auto-sync (#5755) Providers-dashboard 'CLI profile auto-sync' card (Codex + Claude Code toggles), feature-flag backed (default off), + Claude Code auto-sync mirroring the Codex path. Follow-up to #5737. * feat(compression): T08/H8 (2.3) — graduated CCR retrieval-feedback ramp (#5739) Turns CCR retrieval feedback from a binary cliff into a graduated ramp: each prior retrieval raises a block's effective minChars linearly (effectiveMinChars); >= 3 retrievals still excluded (Infinity). retrievalRampFactor default 2 (config/env COMPRESSION_CCR_RETRIEVAL_RAMP_FACTOR); 1 = legacy binary. Regression guard: tests/unit/compression/ccr-retrieval-ramp.test.ts (12); 51 existing CCR tests green. gaps v3.8.42 — T08/H8 (2.3). * feat(compression): T08/H5 (2.4) — usage-observed prefix freeze (opt-in) (#5744) Evolves the cache-aware guard to also learn which system prompts recur: observed >= threshold → treated as a stable cacheable prefix and preserved even for providers the static check misses. Content-addressed by a hash of the system prompt (OpenAI/Claude/Gemini), in-memory, freeze=preserve (never mutates). Opt-in/default-off (COMPRESSION_PREFIX_FREEZE_ENABLED); respects the never preserve-mode. New prefixFreeze.ts wired into resolveCacheAwareConfig. Regression guard: prefix-freeze.test.ts (10); 44 cache-aware tests green. gaps v3.8.42 — T08/H5 (2.4). * feat(compression): T08/H7 (2.5) — read-lifecycle engine (collapse superseded reads) (#5754) New opt-in, default-off read-lifecycle engine: collapses stale/superseded file-Read tool results (same path re-read OR modified later) to a stub, keeping the current Read intact. Anthropic + OpenAI tool shapes; conservative (known tool names, exact path, strictly-later); fail-open. Lossy → opt-in. Regression guard: read-lifecycle.test.ts (10); 41 registry/pipeline suites green. gaps v3.8.42 — T08/H7 (2.5). Completes Onda 2. * fix(sse): anti-thundering-herd guard tolerates numeric-epoch cooldowns (#5747) markAccountUnavailable's dedupe guard used a raw `new Date()` on rateLimitedUntil, which can hold a numeric-epoch string (e.g. the Antigravity full-quota path via setConnectionRateLimitUntil). That produced Invalid Date/NaN, so the guard never detected an already cooling connection — a second concurrent failure on the same connection overwrote a long quota-exhaustion cooldown with a much shorter fresh backoff cooldown, making the account selectable again far sooner than intended. Reuses the existing cooldownUntilMs normalizer (#3954) instead of a raw Date parse. * fix(chat): harden non-streaming SSE aggregation (#5746) * fix: repoint DashScope/Alibaba setup links to consoles (#5665) (#5762) * fix: point Quick Start step 1 to API Keys page, not Endpoint (#5695) (#5763) * fix: onboarding wizard saves providers with unsupported validation (#5692) (#5764) * docs(security): document full LOCAL_ONLY route set + GHSA-fhh6-4qxv-rpqj + audit path (#5599) (#5748) Expand ROUTE_GUARD_TIERS.md Tier 1 (LOCAL_ONLY): - link the GHSA advisory and explain the attack class (RCE via a subprocess spawn reachable from non-loopback traffic) - replace the 3-example prefix table with the full LOCAL_ONLY set, mirroring LOCAL_ONLY_API_PREFIXES / LOCAL_ONLY_API_PATTERNS in routeGuard.ts (the authoritative source; check-route-guard-membership enforces the code side) - add an "Operator guidance & auditing" section for users behind nginx/Cloudflare/Tailscale: don't forge X-Forwarded-For loopback, keep the manage-scope bypass minimal, and how to audit non-loopback access Docs-only; SECURITY.md already links here. Closes #5599 * docs(security): document banned-keyword / account-ban detection (#5600) (#5756) * docs(security): add BAN_DETECTION.md — banned-keyword / account-ban detection (#5600) New docs/security/BAN_DETECTION.md documenting the previously-undocumented system: - the 8 built-in ACCOUNT_DEACTIVATED_SIGNALS + custom keywords are additive - detection flow (body substring match -> terminal `banned` state, skipped in account selection; `deactivated` on 401/403; autoDisableBannedAccounts) - scope: global (all providers); the signal strings target OAuth/subscription scrapers - custom keywords: add path, 200-char cap, hot-reload, and the false-positive warning (raw substring match -> prefer full ban sentences, not "quota"/"limit") - recovery: terminal states never auto-recover -> re-test / re-auth / re-enable Registered in security meta.json; cross-linked from RESILIENCE_GUIDE (terminal states). Docs-only. Closes #5600 * docs(security): clarify deactivated vs expired terminal-status split (#5600) The same ACCOUNT_DEACTIVATED signal surfaces as two different terminal statuses depending on the code path: chatCore.ts inline writes 'deactivated' (401/403 via classifyProviderError), while markAccountUnavailable() -> resolveTerminalConnectionStatus() writes 'expired'. Document both. * fix: surface relay proxy-test errors instead of silent failure (#5716) (#5765) * refactor(api): extract pure discovery leaves from provider-models route (#5758) Split src/app/api/providers/[id]/models/route.ts (2511 -> 1818 LOC) by moving the cohesive, DB-free discovery building blocks into four leaves under discovery/: - helpers.ts record/string coercion, Azure + base-url helpers, bearer/named-openai header builders - normalizers.ts Antigravity / DataRobot / OpenAI-like / SAP models response normalizers - providerModelsConfig.ts PROVIDER_MODELS_CONFIG + ProviderModelsConfigEntry - providerSets.ts NAMED_OPENAI_STYLE_PROVIDERS + isNamedOpenAIStyleProvider The host keeps all request orchestration and imports the leaves back. The moved symbols were module-private, so the route's public export set (GET) is unchanged and no external importer needs updating. Bodies are byte-identical: the code-line multiset of host + leaves equals the original route verbatim. Tests: - repoint the qwen-web source-guard in catalog-updates-v3829-kimi-qwen to the new config leaf (assertions unchanged) - add provider-models-discovery-split as the split regression guard (leaf public surface + host wiring + the #5570 cablyai->aimlapi entry swap) * fix(memory): enabling Qdrant activates it as the engine + inline guidance (#5597) (#5741) * fix(memory): enabling Qdrant now activates it as the engine + inline guidance (#5597) Enabling Qdrant in the Engine tab was inert: retrieval only routes to Qdrant when memoryVectorStore === "qdrant" (the default "auto" never selects it), and the card only wrote qdrantEnabled — nothing set the engine selector, and there is no UI for it. So users configured Qdrant, saw "enabled", but it was never actually used. - PUT /api/settings/qdrant now sets memoryVectorStore alongside the toggle: enable -> "qdrant", disable -> "auto". Editing other fields leaves it untouched. - Add inline guidance to QdrantConfigCard: a Tier-1-vs-Tier-2 banner + per-field help (host, collection, embedding model). Note there is no "vector dimension" or "distance metric" field: dimension is auto-detected from the embedder, distance is always Cosine. - Document the real behavior in MEMORY.md: engine gate, no back-fill of existing memories, dimension auto-detect, Cosine-only, API-key-only auth. Tests: tests/integration/qdrant-routes.test.ts — enable->qdrant, disable->auto, and field-edit-without-enabled leaves the engine untouched (TDD: red -> green). Closes #5597 * fix(memory): invalidate memory-settings cache on Qdrant toggle (#5597) The PUT handler wrote memoryVectorStore to the DB but retrieval reads through getMemorySettings(), a module-level cache. Without busting it, the engine switch did not take effect until a process restart (the DB said qdrant, retrieval kept routing to sqlite-vec). Now calls invalidateMemorySettingsCache() after the write, mirroring src/app/api/settings/memory/route.ts. Regression test warms the cache, toggles via the route, and asserts getMemorySettings().vectorStore flips to qdrant (fails without the invalidate call). * fix(compression): record Context Editing telemetry on the streaming path (#5761) Streaming SSE responses now preserve context_management from the final message_delta snapshot and fire the telemetry hook in onStreamComplete, so context-clear savings surface in compression analytics for streaming (not just non-streaming). Additive telemetry, Claude-only, opt-in-neutral. gaps v3.8.42 — T01 (5.1). Test: context-editing-streaming-telemetry.test.ts (3, failing->passing). * Persist batch item checkpoints during recovery (#5753) * fix(sse): checkpoint batch item recovery * fix(db): renumber batch checkpoints migration 110→112 (collision with #5667) 110 was taken by 110_model_context_overrides.sql (#5667), which landed on the release branch after this PR branched. migrationRunner throws a hard version- collision error on startup when two files share a numeric prefix. 112 is the next free slot (110/111 taken on the release tip). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> --------- Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix: resolve CCR MCP retrieve principal from api-key auth context (#5649) (#5768) * feat(cli): show version in startup banner (integrates #5752) (#5769) * feat(cli): show version in startup banner Print dim 'v<version>' line below ASCII art logo in omniroute serve. Uses readFileSync (same pattern as program.mjs) to read package.json. Closes #5749. * test(cli): guard startup-banner version line (#5752) Source-inspection test (same pattern as cli-serve-port.test.ts) asserting serve.mjs parses the version from package.json and prints v${_pkg.version} in the startup banner — satisfies Hard Rule #8 for the bin/ change. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * docs(changelog): credit #5752 startup-banner version line (thanks @chirag127) --------- Co-authored-by: Chirag Singhal <76880977+chirag127@users.noreply.github.com> * fix(proxyfetch): skip fallback for non-replayable bodies (#5770) * chore(release): open v3.8.42 cycle Bump version to 3.8.42, add CHANGELOG placeholder, sync openapi/electron/open-sse + 42 i18n CHANGELOG mirrors. * chore: remove unused qdrant schema aliases (#5404) Integrated into release/v3.8.42 * chore: remove unused memory schema aliases (#5403) Integrated into release/v3.8.42 * chore: remove unused quota schema types (#5402) Integrated into release/v3.8.42 * chore: remove unused playground row type (#5401) Integrated into release/v3.8.42 * chore: remove unused codegraph exports (#5400) Integrated into release/v3.8.42 * chore: remove unused notion client type (#5399) Integrated into release/v3.8.42 * chore: remove unused settings types (#5398) Integrated into release/v3.8.42 * chore: remove unused combo types (#5396) Integrated into release/v3.8.42 * chore: remove unused provider types (#5393) Integrated into release/v3.8.42 * chore: remove unused skillssh skill type (#5392) Integrated into release/v3.8.42 * chore: remove unused status hex key type (#5391) Integrated into release/v3.8.42 * chore: remove unused batch provider type (#5390) Integrated into release/v3.8.42 * chore: remove unused skills schema types (#5389) Integrated into release/v3.8.42 * chore: remove unused codex auth input type (#5388) Integrated into release/v3.8.42 * chore: remove unused memory schema types (#5387) Integrated into release/v3.8.42 * chore: remove unused playground row type (#5386) Integrated into release/v3.8.42 * chore: remove unused qdrant schema types (#5385) Integrated into release/v3.8.42 * chore: remove unused kiro social schema (#5384) Integrated into release/v3.8.42 * chore: remove unused memory schema types (#5383) Integrated into release/v3.8.42 * chore: remove unused audit action type (#5382) Integrated into release/v3.8.42 * chore: remove unused agent skills schema types (#5381) Integrated into release/v3.8.42 * chore: remove unused shared logger default export (#5380) Integrated into release/v3.8.42 * chore: remove unused sse logger helpers (#5378) Integrated into release/v3.8.42 * chore: remove unused sse model legacy helpers (#5377) Integrated into release/v3.8.42 * chore: remove unused v1 search response schema (#5376) Integrated into release/v3.8.42 * chore: remove unused cloud agent result schemas (#5375) Integrated into release/v3.8.42 * chore: remove unused a2a routing logger readers (#5374) Integrated into release/v3.8.42 * chore: remove unused webhook delivery detail export (#5372) Integrated into release/v3.8.42 * chore: remove unused api key type (#5395) Integrated into release/v3.8.42 * chore: remove unused usage types (#5397) Integrated into release/v3.8.42 * chore: remove unused cloud agent input types (#5373) Integrated into release/v3.8.42 * deps: bump electron from 42.4.1 to 42.5.1 in /electron (#5413) Integrated into release/v3.8.42 * deps: bump the production group with 11 updates (#5414) Integrated into release/v3.8.42 * fix: frame non-streaming JSON responses (#5416) Integrated into release/v3.8.42 * fix(services): runNpm shell on win32 + prefix via env for Node 24 EINVAL (#5379) (#5474) Node 24 refuses execFile of npm.cmd without a shell (nodejs/node#52554), so embedded-service install (9Router/CLIProxy) failed with spawn EINVAL on Windows. runNpm now enables shell on win32 only; to stay Hard-Rule-#13 safe under a shell, the install --prefix is passed via npm_config_prefix (env) instead of an argv path (survives spaces), and the user-supplied version is constrained by SERVICE_VERSION_PATTERN at the route boundary. * fix(cli): restore dist/tls-options.mjs to npm tarball (#5452) (#5503) Closes #5452 * fix(dashboard): render onboarding wizard on /providers/new (#5427) (#5505) Closes #5427 * fix(db): EBUSY-safe database import on Windows (#5406) (#5507) Closes #5406 * chore: remove unused gamification streak exports (#5463) * chore: remove unused headroom log tail export (#5464) * chore(dead-code): remove unused prompt cache control helper (#5466) * chore(duplication): share vscode metadata helpers (#5471) * chore(duplication): share auth zip extractors (#5475) * chore(duplication): share vscode tokenized request helper (#5479) * chore(duplication): share quota strategy ranking helpers (#5482) * chore(duplication): share recharts donut card (#5484) * chore(duplication): share provider specific validation (#5485) * chore(duplication): share batch response formatter (#5488) * chore(duplication): share redis runtime helpers (#5490) * chore(duplication): share version manager request parsing (#5492) * chore(duplication): share media generation route helpers (#5493) * chore(duplication): share settings transform schemas (#5496) * chore(duplication): share relay stream finalizer (#5497) * chore(duplication): share machine id fallback (#5498) * chore(duplication): share node sqlite adapter (#5500) * fix: treat terminal stream cancels as complete (#5491) * fix post-merge ci regressions (#5467) * fix: gate claude adaptive thinking defaults (#5480) Co-authored-by: KooshaPari <koosha@example.com> * fix(fallback): normalize provider error rule headers (#5473) Co-authored-by: KooshaPari <koosha@example.com> * fix(rate-limit): normalize queue refresh settings (#5499) Co-authored-by: KooshaPari <koosha@example.com> * chore(ci): add npm fetch-retry + release-freeze protocol (Hard Rule #21) (#5506) - .npmrc: bump fetch-retries 2->5 with backoff so transient registry ECONNRESET during npm ci (electron-release, v3.8.41) retries instead of failing the job; applies repo-wide. - CLAUDE.md Hard Rule #21: release-freeze coordination marker (label release-freeze) that campaign workflows honor before merging into the active release branch, preventing the mid-release commit races that forced CHANGELOG re-reconciliation in v3.8.40/v3.8.41. * chore(duplication): share service install helpers (#5495) Share service install helpers; re-add SERVICE_VERSION_PATTERN regex to the shared schema (dropped in extraction, #5474) + tests rejecting malformed versions. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * chore(duplication): share proxy route handlers (#5472) Share proxy route handlers; add resolveProxyLookupResponse regression test (3 branches + custom whereUsed param name). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * chore(duplication): share combo builder model options (#5477) Share combo builder model options; add regression test locking custom-model source classification (manual->custom, api-sync->imported). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * chore(dead-code): ratchet dead code baseline (#5468) Ratchet dead-code baseline to the true measured value (310 -> 225) after the v3.8.42 dead-code + duplication wave. Measured by check-dead-code.mjs on the tip. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(dashboard): provider-add UX — i18n labels, surface import warning, default key name (#5511) * fix(dashboard): provider-add UX — real i18n labels, surface import warning, default key name (#5421 #5428 #5429 #5431 #5435) Three rough edges in the Add-API-Key / model-import flow, all from the provider-catalog audit: 1. Validation Model + Account ID form fields shipped untranslated i18n stub copy ('Validation Model Id Label', etc.) that rendered verbatim. Replaced with real copy in en.json. 2. Model import silently fell back to the cached/local catalog — the route returns a 'warning' field the import hook never read. New pure helper extractImportWarning surfaces it as a log line. 3. Required connection-name field defaulted to '' (let browser autofill inject garbage like 'wiw'); now defaults to 'main'. Regression guard: tests/unit/provider-add-ux-i18n-import-warning.test.ts. * fix(dashboard): compress AddApiKeyModal comment to keep file under frozen size cap * fix(providers): align Muse Spark (Meta AI) cookie copy to ecto_1_sess (#5449) (#5513) * fix(providers): align Muse Spark (Meta AI) cookie copy to ecto_1_sess (#5449) The default Meta AI session cookie migrated from the retired abra_sess to ecto_1_sess (META_AI_DEFAULT_COOKIE), but the provider form hint and one 401 auth-failure message still named abra_sess, telling users to paste a cookie that no longer exists. Both strings now name ecto_1_sess. Regression guard: tests/unit/muse-spark-cookie-copy-5449.test.ts. * chore: reconcile CHANGELOG with release (keep #5449 + #5511 bullets) * fix(providers): correct FriendliAI (serverless) + Novita (/openai/v1) endpoints (#5430 #5455) (#5515) * fix(providers): correct FriendliAI (serverless) and Novita (/openai/v1) endpoints (#5430 #5455) Both rejected valid keys, verified live with real provider keys: - FriendliAI baseUrl was /dedicated/v1/... which 403s a serverless flp_* token; switched to /serverless/v1/... + serverless modelsUrl. - Novita baseUrl was the legacy /v3/... with a typo'd model id ai-ai/... (both 404); switched to OpenAI-compat /openai/v1/... + meta-llama/llama-3.1-8b-instruct. Regression guard: tests/unit/provider-endpoints-friendliai-novita.test.ts. * chore: reconcile CHANGELOG with release (keep #5430/#5455 + prior bullets) * fix(providers): gate import for tool-only providers + sanitize Coze validation error (#5420 #5426) (#5522) #5420: the 'Import Models' button now hides for tool-only providers (web search / web fetch) via a capability check over resolved serviceKinds, not just the -search suffix — firecrawl/jina-reader (webFetch) no longer show an Import button that 400s. No LLM/media provider is affected. #5426: Coze key validation no longer leaks the raw upstream envelope ({code,msg,logId,from}) into the UI; the Coze error becomes a friendly message, scoped to provider === 'coze' so no other provider is affected. Regression guards: tests/unit/model-listing-capability-5420.test.ts, tests/unit/coze-validation-error-5426.test.ts. * fix(providers): correct LongCat free tier — GA LongCat-2.0, one-time 10M (KYC) (#5508) LongCat's preview ended and the Flash-* line was retired (2026-05-29); the API now exposes only the GA LongCat-2.0 (1M context, 128K output). The free tier is a ONE-TIME 10M-token grant unlocked after account signup + KYC verification — NOT a recurring daily/monthly allowance. The catalog still described the retired preview/Flash models and a recurring 150M / 5M-per-day budget; this corrects every reference. Config / code: - registry/longcat: model LongCat-2.0-Preview -> LongCat-2.0, name + comment reflect one-time 10M (KYC) and pay-as-you-go beyond it. - freeModelCatalog: longcat-2.0-preview (150M, recurring-daily) -> LongCat-2.0 (10M, freeType one-time-initial via creditTokens). - freeTierCatalog: drop longcat from the recurring-monthly budget map (one-time credits are excluded by that catalog's own rule). - regional.ts freeNote: one-time 10M after signup + KYC, not recurring. - providerCostData: longcat-flash-lite -> longcat-2.0 (pay-as-you-go 0.75/2.95 per 1M, 10M free quota). - validation probe model longcat -> LongCat-2.0. Tests: - free-tier-catalog: longcat now absent from FREE_TIER_BUDGETS; providerCount 22->21 (clean 21->20); documented total ~1.39B. - tierResolver: sample model flash-lite -> LongCat-2.0. Docs: - README, PROVIDERS-GUIDE, FREE-TIERS-GUIDE, FREE_TIERS: 50M/day Flash-Lite -> one-time 10M LongCat-2.0 (KYC); 'No auth' -> API key + KYC. - Regenerated PROVIDER_REFERENCE.md (picks up the new freeNote). typecheck:core clean; changed-file lint 0 errors; docs-sync PASS. * fix(providers): Bytez OpenAI-compat base URL + auth-only key validation (#5422) (#5528) Bytez IS OpenAI-compatible at .../models/v2/openai/v1, but the registry stored the bare .../models/v2 base, so validation's chat-probe hit .../models/v2/chat/completions -> 404 -> 'endpoint not supported'. Part A: registry baseUrl -> full OpenAI-compat chat path. Part B: a Bytez account only serves catalog-provisioned models, so chat-probe validation 404s even for valid keys. validateBytezProvider instead probes the auth-only GET .../models/v2/list/tasks (200=valid, 401/403=invalid). Verified live with a real key: list/tasks -> 200 (valid) / 401 (invalid). Regression guard: tests/unit/bytez-validation-5422.test.ts. * fix(providers): remove dead Phind provider + dedupe HuggingChat catalog listing (#5530) Integrated into release/v3.8.42 (round 3). Dead Phind removal + HuggingChat dedupe, verified complete. * fix: protect dynamic dashboard tests with CSRF (#5405) Integrated into release/v3.8.42 (round 3). Reworked CSRF (HMAC-signed synchronized token). * docs: clarify bifrost relay backend envs (#5520) Integrated into release/v3.8.42 (round 3). Doc-only: bifrost relay envs. * test(quota): guard Claude-Code identity version lockstep (Phase 2) (#5514) Integrated into release/v3.8.42 (round 3). Claude-Code identity version lockstep guard. * feat(compression): T02 — honest default-on pipeline inflation guard (H1) (#5527) Integrated into release/v3.8.42 (round 3). T02 pipeline inflation guard * feat(compression): T05/C2 — caveman dedup + ultra packs for de, fr, ja (#5529) Integrated into release/v3.8.42 (round 3). T05/C2 caveman packs de/fr/ja * feat(compression): T05/C6 — Chinese (zh / wenyan) caveman pack + detection (#5532) Integrated into release/v3.8.42 (round 3). T05/C6 zh/wenyan pack + detection * feat(compression): T07/R9 — gradle + dotnet RTK catalog filters (#5537) Integrated into release/v3.8.42 (round 3). T07/R9 RTK gradle+dotnet filters * refactor(dashboard): T11 — drop duplicate caveman on/off toggle from the compression settings tab (#5524) Integrated into release/v3.8.42 (round 3). T11 consolidate duplicate caveman controls; i18n'd the panel hint string (source key). * test relay routing fallback headers (#5526) Integrated into release/v3.8.42 (round 3). Relay fallback header extraction + tests (drift-shed: dependabot #5415 commit dropped). * fix(opencode-plugin): bump to 0.2.0 + auto-publish on release (#5363) - Bump @omniroute/opencode-plugin from 0.1.0 to 0.2.0 so CI publishes the accumulated fixes (auto combos, schema fields, debug logging) that were merged after the initial 0.1.0 publish on May 24. - Add auto-bump step in npm-publish.yml: detects if the plugin dir changed since the last release tag and auto-increments patch version, so the plugin never falls behind again on future releases. Co-authored-by: herjarsa <herjarsa@users.noreply.github.com> * [codex] add bifrost auto fallback cooldown (#5519) Integrated into release/v3.8.42 (round 3). Bifrost auto fallback cooldown; header reconciled with #5526 helper + env-doc. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix onboarding schema client import (#5525) Integrated into release/v3.8.42 (round 3). Browser-safe onboarding schema import (drift-shed: dependabot #5415 dropped). * docs: add relay backend strategy guide (#5547) Port #5533 relay strategy guide to release/v3.8.42 (doc-only). * fix(chatgpt-web): support GPT-5.5 Pro handoff (#5536) Integrated into release/v3.8.42 (round 3). GPT-5.5 Pro async stream_handoff support (drift-shed: dependabot #5415 dropped). * fix(providers): persist Configured filter across page reloads (#5510) Integrated into release/v3.8.42 (round 3). Persist Configured filter across reloads; extracted shouldSyncProviderDisplayMode race guard + TDD test (Closes #4059). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(mimocode): route per-account traffic through SOCKS5 proxy dispatchers (#5521) Integrated into release/v3.8.42 (round 3). Per-account SOCKS5 dispatcher routing — completes #3837's stored proxy config with the actual undici dispatcher layer. Rebased onto .42 (dropped the CI-workflow-deletion commits; merged proxyUrlMap dispatch with #3837's acct.proxy storage). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(chatgpt-web): portable SHA3-512 for sentinel PoW under Electron/BoringSSL (#5531) (#5540) * fix(build): keep ioredis out of the client/CLI bundle via SPAWN_CAPABLE_PREFIXES leaf (#5546) Fix the dast-smoke ioredis client-bundle regression (proven: dast-smoke green). Remaining reds are pre-existing base-reds/flakes (base.ts file-size, GOLDEN provider drift, shard-1 compression flakes) inherited by all PRs — not from this change. * chore(release): finalize v3.8.42 CHANGELOG + cycle-close reconciliation - Reconcile CHANGELOG.md for v3.8.42: 40 bullets covering all 89 commits since v3.8.41 (4 features, 26 fixes, 10 maintenance incl. 2 rollups for the 35-PR dead-code sweep + 17-PR DRY consolidation), dedup the merge- artifact duplicate New Features headers, set release date 2026-06-30. - Sync 42 docs/i18n/*/CHANGELOG.md mirrors. - Document 3 new chatgpt-web/TLS env vars in .env.example + ENVIRONMENT.md (OMNIROUTE_CGPT_WEB_PRO_TIMEOUT_MS, _PRO_POLL_INTERVAL_MS, OMNIROUTE_CHATGPT_STREAM_FIRST_BYTE_TIMEOUT_MS). - Cycle-close ratchet rebaselines: eslintWarnings 4116->4121, file-size base.ts/chatgpt-web.ts/strategySelector.ts/chatgpt-web.test.ts (all inherited drift, justified inline). - Regenerate provider translate-path golden snapshot for the merged bytez/friendliai/novita endpoint fixes. * chore(changelog): cover #5415 dev-deps bump merged from main The release/v3.8.42 ↔ main merge ( |
||
|
Diego Rodrigues de Sa e Souza
|
0adae00c7b |
Release v3.8.42 (#5459)
Release v3.8.42 — full CHANGELOG in CHANGELOG.md. CI: 103 checks green incl. CodeQL (all languages), Semgrep, all 8 unit shards, coverage, Node 24 compat, and integration tests. Full unit suite validated locally: 19437 pass / 0 fail. The 3 red checks are advisory and do not gate main (no required status checks): SonarCloud/SonarQube new-code coverage gate, and PR Test Policy (test-masking detector flagging the legitimate dead-Phind provider removal in #5530 — reviewed, correct). Includes cycle-close reconciliation + repair of inherited base-red tests from #5480/#5527/#5427/#5521 that the PR->release fast-path did not exercise. |
||
|
Diego Rodrigues de Sa e Souza
|
3c9883bb73 |
Release v3.8.29 (#4126)
OmniRoute v3.8.29 — 115 commits since v3.8.28. Full CHANGELOG + 41 i18n mirrors. All content quality gates green (build, unit 8/8, vitest 188/188, PR test policy, quality gates extended, docs sync, quality ratchet). Remaining red CI checks are pre-existing release flakes (coverage-shard/integration/node-compat teardown), a new transitive undici advisory in electron devDeps, and a workflow-level CodeQL fail (0 open alerts). VPS-validated by the operator. |
||
|
Diego Rodrigues de Sa e Souza
|
a25d5f1ef6 |
Release v3.8.13 (#3327)
* chore(release): open v3.8.13 development cycle Bump 3.8.12 → 3.8.13 across package.json, lockfile, electron/, open-sse/, and docs/reference/openapi.yaml; add the [3.8.13] cycle placeholder to the root CHANGELOG and the 41 i18n mirrors. Integration branch for the v3.8.13 cycle — fixes/features land here via per-issue PRs and it merges to main at release time. * fix(ci): skip auto-deploy when VPS host is unreachable from the runner (#3299) Integrated into release/v3.8.13 * fix(dev): auto-rebuild better-sqlite3 on Node ABI mismatch at dev startup (#3301) Integrated into release/v3.8.13 * feat(api): accept path-scoped API keys on client API routes (#3300) Integrated into release/v3.8.13 * fix(sse): harden against empty responses causing Copilot Chat failures (#3297) Integrated into release/v3.8.13 * fix(api): remove Completions.me rickroll provider (discussion #3293) (#3302) Integrated into release/v3.8.13 * fix(opencode-provider): extract contextLength from live model catalog (#3298) Integrated into release/v3.8.13 * feat(web-cookie): self-service login infrastructure + auto-refresh daemon (#3292) Integrated into release/v3.8.13 * docs(changelog): record the v3.8.13 PRs merged this round (#3292/#3300/#3297/#3298/#3301/#3302/#3299) * fix(auth): harden URL token extraction — drop query-string fallback, gate to client routes (security follow-up to #3300) (#3309) Security follow-up to #3300 — integrated into release/v3.8.13 * docs: rename resolve-issues → review-issues skill references * fix(dashboard): keep no-auth providers visible under 'Show configured only' (#3290) (#3312) no-auth providers (opencode, duckduckgo-web, theoldllm, veoaifree-web) never create a DB connection row so stats.total stays 0, which the configured-only filter treated as 'unconfigured' and hid them — even though they are always usable and appear unconditionally in /v1/models. filterConfiguredProviderEntries now treats displayAuthType === 'no-auth' as configured. Co-authored-by: uniQta <uniQta@users.noreply.github.com> * fix(cli): resolve update paths relative to script + recursive backup (#3295) (#3313) omniroute update always failed on a global install: - getCurrentVersion() read package.json from process.cwd(), which on a global npm/brew install is the user's working dir, not the package root → null → 'Could not determine current version'. - createBackup() resolved bin/ from cwd too, and passed the 'cli' directory to copyFileSync → EISDIR, swallowed by the catch → 'Failed to create backup'. Both now resolve package.json/bin relative to the script via import.meta.url, and the backup uses cpSync({recursive:true}) so the cli/ directory is copied. Co-authored-by: uniQta <uniQta@users.noreply.github.com> * fix(theoldllm): read upstream body once to avoid [502] body-already-read (#3296) (#3314) On the cached-token path the executor never enters the refresh branch, so the same upstream Response was read with .text() twice (token-rejection check + final body). A Response body is single-use, so the second read threw 'Body is unusable: Body has already been read', caught and surfaced as [502]. Read the body once into finalBody and only re-read after a token-rejection refetch. Co-authored-by: onizukashonan14-png <onizukashonan14-png@users.noreply.github.com> * fix(sse): strip leaked internal tool envelopes from streaming output (#3311) Integrated into release/v3.8.13 * fix(sse): expose Claude + Gemini budget tiers in the antigravity catalog (#3184) (#3303) Integrated into release/v3.8.13 (#3184) * fix(catalog): compute combo context_length from known targets only (#3304) Integrated into release/v3.8.13 — live contextLength + known-targets combo context (#3298 follow-up) * chore(i18n): add message keys for proxy UI + vscode/ollama endpoint (#3307) Integrated into release/v3.8.13 — i18n message keys for proxy UI + vscode/ollama * feat(dashboard): i18n the proxy settings UI (#3310) Integrated into release/v3.8.13 — i18n the proxy settings UI * feat(api): model catalog enrichment + MCP model-catalog tools (#3306) Integrated into release/v3.8.13 — model catalog enrichment + MCP model-catalog tools, reconciled with #3309 URL-token hardening * test(catalog): align Antigravity preview-alias test with #3303 budget tiers #3303 added the Gemini `-high`/`-low` budget tiers to ANTIGRAVITY_PUBLIC_MODELS (user-callable on the Antigravity OAuth backend, verified via #3184), but did not update the catalog-route test that asserted `antigravity/gemini-3.1-pro-high` must NOT be exposed. The assertion now reflects the intended behavior — the client-visible budget alias IS surfaced — while keeping the legacy `gemini-claude-*` alias keys unexposed. Caught running the full catalog suite on the merged release HEAD (the #3303 round only ran the antigravity-aliases and usage-hardening files). * docs(changelog): record the 6 PRs merged this review round into v3.8.13 #3306/#3307/#3310 (New Features — VS Code split: catalog+MCP, i18n keys, proxy UI i18n), #3311/#3303/#3304 (Bug Fixes — SSE envelope sanitizer, antigravity budget tiers, combo known-targets context_length). * chore(release): finalize v3.8.13 changelog and cleanup Finalize the v3.8.13 changelog with release date, maintenance notes, and contributor credits. Update MCP docs to reference the correct tool inventory diagram, exclude nested .claude worktrees from ESLint scans, and tighten a response sanitizer type guard. * fix(dashboard): refresh connections after provider auth import (#3320) Integrated into release/v3.8.13 — refresh connections after provider auth import * fix(codex): strip client-only params on native /responses passthrough (#3317) (#3325) A /v1/responses request against the built-in codex/ provider does an openai-responses -> openai-responses passthrough (CodexExecutor.transformRequest returns the body early for _nativeCodexPassthrough). It forwarded client-only fields verbatim and the Codex upstream rejected them with 400 Unsupported parameter: prompt_cache_retention / safety_identifier / user — breaking Factory Droid (which injects all three). The chat-completions path already strips these (base.ts #1884, openai-responses translator #2770) but the passthrough skips translation. Strip the three fields in the shared block before the passthrough return; user is removed unconditionally since Codex /responses always rejects it. Co-authored-by: tycronk20 <tycronk20@users.noreply.github.com> * fix(dashboard): normalize agent-bridge /state response to stop page crash (#3318) (#3326) The Agent Bridge page seeded a well-shaped initialData default then replaced it wholesale with the raw /api/tools/agent-bridge/state response. The route returns { server, agents } but the UI reads { serverState, agentStates, bypassPatterns, mappings }, so serverState became undefined and AgentBridgeServerCard crashed on serverState.running — surfaced as the full-page 'Internal Server Error' boundary (client render error, not a real 5xx). Add a shared normalizeAgentBridgeState() that maps the route shape into the page contract (server.running/certExists -> serverState) and always returns safe defaults (never undefined serverState). Wired into both the SSR loader (page.tsx) and the polling hook. The legacy 'agents' entry shape differs from AgentStateEntry so it is not coerced; full route<->page contract reconciliation (port, upstreamCa, bypassPatterns, mappings, agentStates) is a follow-up. Co-authored-by: tycronk20 <tycronk20@users.noreply.github.com> * docs: VS Code/Ollama endpoints + env & i18n tooling (#3319) Integrated into release/v3.8.13 — VS Code/Ollama docs + env & i18n tooling * feat(provider): test-all endpoint, rate-limit overrides, visibility f… (#3267) Integrated into release/v3.8.13 — provider test-all endpoint, rate-limit overrides, model visibility * feat: auto-combo optimization, playground model dropdown, only-configured toggle (#3322) Integrated into release/v3.8.13 — auto-combo candidate expansion + playground dropdown + only-configured toggle * feat(api): VS Code Copilot Ollama-compatible BYOK endpoint (#3316) Integrated into release/v3.8.13 — VS Code Copilot Ollama-compatible BYOK endpoint (reconciled with #3306/#3309 auth hardening) * chore(release): document #3320 in the v3.8.13 changelog + contributor credits --------- Co-authored-by: Felipe Almeman <4226997+zhiru@users.noreply.github.com> Co-authored-by: Wilson <pedbookmed@gmail.com> Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: uniQta <uniQta@users.noreply.github.com> Co-authored-by: onizukashonan14-png <onizukashonan14-png@users.noreply.github.com> Co-authored-by: tycronk20 <tycronk20@users.noreply.github.com> Co-authored-by: Vinayrnani <vinayrnani@gmail.com> |
||
|
mi
|
847799092e |
fix: CPU leak from Bottleneck limiter accumulation + per-request optimizations (#2951)
Integrated into release/v3.8.8 |
||
|
mi
|
94682d2a76 |
perf(ram): reduce server memory footprint (#2903)
Integrated into release/v3.8.7 |
||
|
Diego Rodrigues de Sa e Souza
|
b91ffa7f72 |
Release v3.8.4 (#2678)
* chore: bump version to 3.8.4 * feat(providers): enhance Google Gemini, CLI, and Antigravity resilience and features (#2676) Integrated into release/v3.8.4 * docs: add PR #2676 to changelog * fix(vision-bridge): process images when vision-capable model has combo mapping When a model-combo mapping routes a vision-capable model through a combo where some targets may NOT support vision, the vision bridge must process images so combo targets can describe them. Before: if body.model supports vision, the vision bridge skipped image processing entirely. Non-vision combo targets would receive raw images they can't handle. After: before skipping, check if the model has a model-combo mapping. If it does, process images through the vision bridge regardless of body.model's native vision support. - Add checkModelHasComboMapping() helper (dynamic import, failsafe) - Add checkModelHasComboMapping dep to VisionBridgeDependencies (testable) - Guardrail preCall: check combo mapping before early-return on vision support - Add VB-S11 / VB-S11b tests * fix(vision-bridge): only process images when some combo targets lack native vision Optimization per code review: instead of always processing images when a combo mapping exists, resolve the combo targets and check each target model's native vision support. Only invoke the vision bridge when at least one target model does not support vision. - Replace checkModelHasComboMapping() with shouldProcessImagesForComboModel() - When combo has ComboRefStep targets, conservatively process images - When all targets are model steps with native vision, skip processing - On errors, process images (conservative fail-safe) * fix(combos): repair context handoff ordering and add per-model timeout Root cause: recordSessionModelUsage was called BEFORE getLastSessionModel, so prevModel always matched the current modelStr — handoff summaries were never generated when auto-routing switched models. Fix: call getLastSessionModel first (captures actual previous model), generate handoff on mismatch, then record the new model for next time. Also: - ORDER BY id DESC in session_model_history query (deterministic vs used_at which has second-precision ties) - 30s per-model timeout for combo routing (default FETCH_TIMEOUT_MS is 600s, too long for combo fallback scenarios) * Revert "fix(combos): repair context handoff ordering and add per-model timeout" This reverts commit |
||
|
Anton
|
44a04df4f6 |
fix(rateLimit): never .stop() during runtime reset, evict cache instead (#2218)
Integrated into release/v3.8.0 |
||
|
payne
|
6c172df547 |
fix(rate-limit): watchdog, env override, and stage tracing to prevent silent wedges (#1828)
Integrated into release/v3.7.7 |
||
|
Diego Rodrigues de Sa e Souza
|
24ffdde03d |
Release v3.7.5 (#1753)
* docs(changelog): record PR #1748 for next release * fix(models): apply blocked providers filter to non-chat catalog models (#1752) * chore(release): v3.7.5 — integrate ngrok tunnel and fix models filter (#1753, #1752) * chore(release): update changelog format for v3.7.5 * Speed up endpoint initial render * Address endpoint review feedback * Add endpoint loading model translations * fix: resolve build issues and implement memory UPSERT logic (#1763) * fix: resolve build issues for v3.7.5 and apply memory/translation fixes 1. antigravityHeaders.ts: restore ANTIGRAVITY_LOAD_CODE_ASSIST_* exports for oauth.ts compatibility 2. next.config.mjs: add @ngrok/ngrok to serverExternalPackages and webpack externals to handle native .node modules 3. Memory system: UPSERT logic to prevent duplicate entries with same apiKeyId + key 4. Chinese translations: complete CLI tools and memory dashboard localizations 5. Test fixes: unique keys for pagination tests to comply with unique constraint Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: address Gemini Code Assist review feedback 1. store.ts: add expires_at to UPDATE statement in UPSERT logic - Previously, expires_at was not being persisted to database on update - This caused state mismatch between returned Memory object and actual DB row 2. package-lock.json: revert react-markdown registry to official npmjs.org - Mirror-specific registry URL (npmmirror.com) should not be in lockfile Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> * fix(antigravity): normalize Gemini bridge payloads (#1769) * fix(antigravity): normalize Gemini bridge payloads Clamp Claude bridge output tokens, use Gemini-valid system roles and tool names, and serialize antigravity requests from a cloned body so Cloud Code payload shaping stays valid. * fix(cli): stop fallback after unsafe known paths Preserve known-path security checks by stopping command discovery when a configured CLI path is suspicious or non-executable, instead of falling through to PATH discovery. * test(memory): make query result assertion deterministic Avoid relying on database result ordering when checking filtered memory keys so the unit suite remains stable across runs. * fix(review): preserve safe cloning and CLI reasons Handle non-cloneable antigravity request bodies without throwing and preserve specific CLI known-path failure reasons instead of masking them as not_found. * fix(sse): propagate AbortSignal to pre-fetch semaphore and rate-limit awaits (#1771) When a combo target takes too long, the request-level deadline fires and calls abortController.abort() on the stream controller, but the abort signal never reaches pending awaits in acquireAccountSemaphore() or withRateLimit(). These awaits sit between stream controller creation and executor.execute(), causing requests to hang indefinitely past the 600s deadline. Pass streamController.signal to both functions so they can respond to abort events and terminate early when the request deadline expires. Signed-off-by: wucm667 <stevenwucongmin@gmail.com> * Fix model sync import handling (#1755) * Fix model sync import handling * Align model import storage semantics * Address model review feedback * fix(codex): stabilize copilot responses reasoning and tool replay (#1750) * chore(xiaomi): Update Xiaomi provider model list (#1759) * Move DB health to management API (#1757) * Move DB health to management API * Address DB health review feedback * fix(kiro): support organization IDC OAuth with regional endpoints and refresh (#1754) * fix(kiro): support organization IDC OAuth with regional endpoints and refresh * fix(kiro): refresh IDC tokens with stored region --------- Co-authored-by: ngocdb <ngocdb@ngocdb.local> * chore(workflows): add strict PR contributor credit policy - Add ABSOLUTE PROHIBITION section to review-prs.md - Add PR PROHIBITION rule to resolve-issues.md - Add contributor credit rule to AGENTS.md Review Focus - Based on audit finding: 37 PRs had code absorbed without merge credit * chore(release): acknowledge 29 community contributors with retroactive credit This commit formally recognizes 29 contributors whose code was manually integrated across releases v3.4.0 through v3.7.4 without proper GitHub merge credit. Their PRs were resolved locally due to merge conflicts but closed instead of merged, preventing them from appearing in the Contributors graph. We have updated our workflows to ensure this never happens again. Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Benson K B <4044180+benzntech@users.noreply.github.com> Co-authored-by: clousky2020 <33016567+clousky2020@users.noreply.github.com> Co-authored-by: Raxxoor <7317522+dhaern@users.noreply.github.com> Co-authored-by: Jason Landbridge <15127381+JasonLandbridge@users.noreply.github.com> Co-authored-by: slewis3600 <35925982+slewis3600@users.noreply.github.com> Co-authored-by: Markus Hartung <12826053+hartmark@users.noreply.github.com> Co-authored-by: Hernan Javier Ardila Sanchez <204746071+herjarsa@users.noreply.github.com> Co-authored-by: 3_1_3_u <5846351+andruwa13@users.noreply.github.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: i1hwan <35260883+i1hwan@users.noreply.github.com> Co-authored-by: xandr0s <1709302+xandr0s@users.noreply.github.com> Co-authored-by: backryun <24198422+backryun@users.noreply.github.com> Co-authored-by: Owen <36758131+kang-heewon@users.noreply.github.com> Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com> Co-authored-by: Chris <3751981+christopher-s@users.noreply.github.com> Co-authored-by: Wellington Fonseca <5421548+wlfonseca@users.noreply.github.com> Co-authored-by: Ethan Hunt <136065060+only4copilot@users.noreply.github.com> Co-authored-by: tombii <6607822+tombii@users.noreply.github.com> Co-authored-by: AndrewDragonIV <7906124+AndrewDragonIV@users.noreply.github.com> Co-authored-by: Danh Thanh <50534210+dt418@users.noreply.github.com> Co-authored-by: Will F <30637450+willbnu@users.noreply.github.com> Co-authored-by: defhouse <232128212+defhouse@users.noreply.github.com> Co-authored-by: Skydwest <186351198+mercs2910@users.noreply.github.com> Co-authored-by: zenobit <6384793+zen0bit@users.noreply.github.com> Co-authored-by: Ivan <16905671+razllivan@users.noreply.github.com> Co-authored-by: foxy1402 <45601526+foxy1402@users.noreply.github.com> Co-authored-by: Luan Dias <65574834+luandiasrj@users.noreply.github.com> Co-authored-by: Sergei Korolev <891832+knopki@users.noreply.github.com> Co-authored-by: dail45 <69967573+dail45@users.noreply.github.com> * fix(combo): include 429 in provider circuit breaker to stop infinite retry on exhausted quotas (#1767) Previously, PROVIDER_FAILURE_ERROR_CODES only included {408, 500, 502, 503, 504}, meaning 429 responses never counted toward the circuit breaker threshold. This caused exhausted accounts to be retried every 3-5 seconds indefinitely instead of being blocked by the provider breaker. Adding 429 ensures persistent rate limiting triggers the circuit breaker after the configured failure threshold, giving the provider time to recover. * fix(claude): respect client thinking/effort params to prevent forced quota drain (#1761) Previously, OmniRoute unconditionally injected thinking: {type: 'adaptive'} and output_config: {effort: 'high'} for Claude Opus 4.7 in Claude Code client requests. This caused Claude Max 5h quota to drain in ~15 minutes. Now checks the original client body: if thinking or output_config are explicitly set (even to null or a different value), the injection is skipped. Users can opt-out by sending thinking: null or output_config: {effort: 'low'}. * Add MseeP.ai badge to README.md (#1727) Integrated into release/v3.7.5 * chore(docs): update CHANGELOG for PR #1727 * fix(tests): update stream-utils assertion for responses api compliance * feat: Fix support for claude-cli using Gemini provider (#1779) Integrated into release/v3.7.5 * fix(codex): align client identity metadata (#1778) Integrated into release/v3.7.5 * fix(blackbox-web): correct cookie name and populate session/subscription fields (#1776) Integrated into release/v3.7.5 * Fix Codex /responses/compact passthrough (#1777) Integrated into release/v3.7.5 * test(reasoning-cache): isolate DB state using mkdtempSync to prevent 401 middleware errors * chore(release): v3.7.5 — integrate remaining PRs and finalize stability * chore(config): remove local patch artifacts and trim workspace config Delete temporary patch scripts and local OMC session files that should not ship with the repository. Also remove the Next.js config file and expand editor and TypeScript exclusions to ignore large local workspace directories and reduce unnecessary indexing. * fix(antigravity): cap Claude bridge output tokens (#1785) Integrated into release/v3.7.5 * fix(codex): stabilize Copilot responses replay state (#1791) Integrated into release/v3.7.5 * fix(chatgpt-web): restore validator + expand model catalog to ChatGPT Plus tier (#1792) Integrated into release/v3.7.5 * fix(antigravity): scrub internal OmniRoute headers (#1794) Integrated into release/v3.7.5 * fix(grok-web): fix Grok validator and cookie parsing (#1793) Integrated into release/v3.7.5 * chore(release): v3.7.5 — finalize changelog for LTS patch * feat(api-keys): add rename support in permissions modal Add an editable key name field at the top of the permissions modal, allowing users to rename API keys alongside existing permission settings. The backend already supported name updates via PATCH /api/keys/:id — this wires the UI to send the name field and refreshes the key list on success. Changes: - Add keyName state and text input to PermissionsModal - Update handleUpdatePermissions to validate and send name in PATCH body - Add integration test for rename via PATCH (valid, empty, too-long names) - Update E2E mock to handle PATCH requests * chore(release): finalize v3.7.5 LTS release with schema and db initialization fixes * test: fix json escaping in stream-utilities test * fix(build): restore next.config.mjs that was accidentally deleted * fix(sse): decrement pending requests on passthrough mode failure (#1798) Integrated into release/v3.7.5 * fix(grok-web): repair validator probe + accept full cookie blobs (#1793) Integrated into release/v3.7.5 * docs(i18n): sync documentation updates to 40 languages --------- Signed-off-by: wucm667 <stevenwucongmin@gmail.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: R.D. <rogerproself@gmail.com> Co-authored-by: clousky2020 <33016567+clousky2020@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: cloudy <37777261+uwuclxdy@users.noreply.github.com> Co-authored-by: wucm667 <109257021+wucm667@users.noreply.github.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: ivan-mezentsev <ivan@mezentsev.me> Co-authored-by: backryun <bakryun0718@proton.me> Co-authored-by: Dao Bao Ngoc <42265865+daongoc315@users.noreply.github.com> Co-authored-by: ngocdb <ngocdb@ngocdb.local> Co-authored-by: Benson K B <4044180+benzntech@users.noreply.github.com> Co-authored-by: Raxxoor <7317522+dhaern@users.noreply.github.com> Co-authored-by: Jason Landbridge <15127381+JasonLandbridge@users.noreply.github.com> Co-authored-by: slewis3600 <35925982+slewis3600@users.noreply.github.com> Co-authored-by: Markus Hartung <12826053+hartmark@users.noreply.github.com> Co-authored-by: Hernan Javier Ardila Sanchez <204746071+herjarsa@users.noreply.github.com> Co-authored-by: 3_1_3_u <5846351+andruwa13@users.noreply.github.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: i1hwan <35260883+i1hwan@users.noreply.github.com> Co-authored-by: xandr0s <1709302+xandr0s@users.noreply.github.com> Co-authored-by: backryun <24198422+backryun@users.noreply.github.com> Co-authored-by: Owen <36758131+kang-heewon@users.noreply.github.com> Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com> Co-authored-by: Chris <3751981+christopher-s@users.noreply.github.com> Co-authored-by: Wellington Fonseca <5421548+wlfonseca@users.noreply.github.com> Co-authored-by: Ethan Hunt <136065060+only4copilot@users.noreply.github.com> Co-authored-by: tombii <6607822+tombii@users.noreply.github.com> Co-authored-by: AndrewDragonIV <7906124+AndrewDragonIV@users.noreply.github.com> Co-authored-by: Danh Thanh <50534210+dt418@users.noreply.github.com> Co-authored-by: Will F <30637450+willbnu@users.noreply.github.com> Co-authored-by: defhouse <232128212+defhouse@users.noreply.github.com> Co-authored-by: Skydwest <186351198+mercs2910@users.noreply.github.com> Co-authored-by: zenobit <6384793+zen0bit@users.noreply.github.com> Co-authored-by: Ivan <16905671+razllivan@users.noreply.github.com> Co-authored-by: foxy1402 <45601526+foxy1402@users.noreply.github.com> Co-authored-by: Luan Dias <65574834+luandiasrj@users.noreply.github.com> Co-authored-by: Sergei Korolev <891832+knopki@users.noreply.github.com> Co-authored-by: dail45 <69967573+dail45@users.noreply.github.com> Co-authored-by: MseeP.ai <mseep@skydeck.ai> Co-authored-by: Markus Hartung <mail@hartmark.se> Co-authored-by: Raxxoor <manker_lol@hotmail.com> Co-authored-by: Jack <5443152+hijak@users.noreply.github.com> Co-authored-by: Sergey Morozov <tr0st@bk.ru> Co-authored-by: payne <baboialex95@gmail.com> Co-authored-by: Antigravity Assistant <bot@antigravity.local> Co-authored-by: Andrew Munsell <andrew@wizardapps.net> |
||
|
backryun
|
a16e47c593 |
fix(providers): refresh web client user agents (#1699)
Integrated release/v3.7.2 changes — refreshed web client user agents, env docs, Gemini OAuth fix |
||
|
diegosouzapw
|
accb58f5b2 |
fix: per-model rate limiting for GitHub Copilot provider (#1624)
- Add 'github' to hasPerModelQuota() so 429 on one model doesn't lock the entire connection — same pattern already used for Gemini - Add 'github' to getLimiterKey() for model-scoped Bottleneck rate limiter keys (github:connectionId:model) - Add unit tests for hasPerModelQuota, shouldMarkAccountExhaustedFrom429, lockModelIfPerModelQuota (account-fallback-service.test.ts) - Add integration test for model-scoped limiter keys (rate-limit-manager.test.ts) Co-authored-by: slewis3600 <slewis3600@users.noreply.github.com> |
||
|
Cong Vu Chi
|
15b4a54454 |
fix(claude): preserve tool_result adjacency (#1555)
* fix(claude): preserve tool_result adjacency in native and CC-compatible paths * feat(providers): add Petals and Nous Research provider support Register Nous Research as an OpenAI-compatible gateway with remote model discovery and validation against chat completions. Add Petals provider metadata, default config, validation, and a specialized executor that maps OpenAI-style requests to the public generate endpoint. Also allow optional API keys and configurable base URLs for Petals in the dashboard and provider schemas. Expand provider model and catalog tests to cover both integrations. * fix(resilience): sync queue updates and clear stale discovery caches Await runtime request queue updates so limiter settings and auto-enabled API key protections are recomputed when resilience settings change. Preserve cancelled batch state for in-flight work by marking input files processed without generating output artifacts, and replace cached synced models with an empty set when remote discovery returns no models so the providers route falls back to the local catalog instead of stale cache. --------- Co-authored-by: congvc <congvc-dev@gmail.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> |
||
|
Randi
|
b38e57d452 |
refactor: unify resilience controls (#1449)
Integrated into release/v3.7.0 |
||
|
Diego Rodrigues de Sa e Souza
|
9e45baae58 |
chore(release): v3.6.6 — Stabilization (#1241)
* fix(streaming): #1211 greedy strip omniModel tags to prevent literal \n\n artifacts - Changed regex quantifier from ? to * in combo.ts, comboAgentMiddleware.ts, and contextHandoff.ts to greedily strip all JSON-escaped newline sequences surrounding <omniModel> tags in SSE streaming chunks - Added \r to the character class for cross-platform robustness - Fixed Playwright strict-mode violation in combo-unification.spec.ts - Bumped OpenAPI version and CHANGELOG to 3.6.6 * fix: 3 bugs found during issue triage (#1175, #1187/#1218, #1202) - fix(gemini): strip VS Code JSON Schema extensions from tool schemas (#1175) Add enumDescriptions, markdownDescription, markdownEnumDescriptions, enumItemLabels and tags to UNSUPPORTED_SCHEMA_CONSTRAINTS so the Gemini sanitizer removes them before forwarding. GitHub Copilot injects these non-standard fields into tool definitions, causing Gemini to reject with 'Unknown name enumDescriptions at functionDeclarations[n].parameters'. - fix(health-check): unwrap proxy config object before passing to getAccessToken (#1187 #1218) resolveProxyForConnection() returns { proxy, level, levelId } but the health check loop was passing the full wrapper to getAccessToken(), which expects the inner config object (.host, .port etc). The proxy dispatcher validated .host on the wrapper (undefined) and threw 'Context proxy host is required', silently marking every connection as unhealthy every sweep. Fix mirrors the pattern already used in chatHelpers.ts: proxyResult?.proxy || null. - fix(ui): debounce models.dev sync interval slider to save only on release (#1202) The slider's onChange fired updateInterval() on every drag tick, sending a PATCH per pixel of movement. Rapid API responses overwrote UI state mid-drag. Introduce draftIntervalHours for smooth visual feedback; the PATCH fires on onMouseUp / onBlur once the user releases the control. * fix(providers): update Xiaomi MiMo token-plan endpoints (#1238) Integrated into release/v3.6.6 * fix(cc-compatible): trim beta flags and preserve cache passthrough (#1230) Integrated into release/v3.6.6 * feat(memory+skills): full-featured memory & skills systems with tests (#1228) Integrated into release/v3.6.6 * fix: forward client x-initiator header to GitHub Copilot upstream (#1227) Integrated into release/v3.6.6 * feat(bailian-quota): add Alibaba Coding Plan quota monitoring (#1235) * fix: resolve v3.6.6 backlog bugs (#1206, #1211, #1220, #1231) - fix(core): #1206 inject startup guard against app/ and src/app/ conflict - fix(health): #1220 add HEALTHCHECK_STAGGER_MS to prevent token refresh bursting - fix(proxy): #1231 prioritize HTTP 429 over quota body heuristics - fix(sse): #1211 strip leading double-newlines in responses API stream * fix(tests): resolve memory migration and skills route pagination bugs from PR overlaps * docs: Update CHANGELOG.md with v3.6.6 features (#1182, #1165, #1177) * chore(release): bump version to 3.6.6 Update package versions for the electron app and open-sse package. Sync llm.txt metadata and feature headings with the 3.6.6 release. * feat(core): harden outbound provider calls and add cooldown retries Add guarded outbound fetch helpers with private/local URL blocking, controlled retries, timeout normalization, and route-level status propagation for provider validation and model discovery. Introduce cooldown-aware chat retries with configurable requestRetry and maxRetryIntervalSec settings, model-scoped cooldown responses, and improved rate-limit learning from headers and error bodies so short upstream lockouts can recover automatically. Also align Antigravity and Codex header handling, require API keys for Pollinations, validate web runtime env at startup, restore sanitized Gemini tool names in translated responses, and inject a synthetic Claude text block when upstream SSE completes empty. * feat(models): add glmt preset and hybrid token counting Introduce GLM Thinking as a first-class provider preset with shared GLM model metadata, pricing, usage sync, dashboard support, and provider request defaults for higher token budgets and longer timeouts. Use provider-side /messages/count_tokens when a Claude-compatible upstream supports it, while preserving estimated fallback behavior for missing models, missing credentials, and upstream failures. Also add startup seeding for default model aliases and normalize common cross-proxy model dialects so canonical slashful model ids do not get misrouted during resolution. * feat(api): add sync tokens and v1 websocket bridge Add dedicated sync token storage, issuance, revocation, and bundle download routes backed by stable config bundle versioning and ETag support. Expose the v1 websocket handshake route and custom Next server bridge so OpenAI-compatible websocket traffic can be upgraded and proxied through the dashboard and API bridge. Expand compliance auditing with structured metadata, pagination, request context, auth and provider credential events, and SSRF-blocked validation logging. * docs: Update all documentation for v3.6.6 - CHANGELOG: Add WebSocket bridge, GLM Thinking preset, safe outbound fetch/SSRF guard, cooldown-aware retries, compliance audit v2, model alias seeding, and all Internal Improvements for the 3 new commits - README: Expand v3.6.x highlights table with 10 new features; add SafeOutboundFetch, CooldownAwareRetry, SSRF guard, TPS metric, sync tokens, WebSocket bridge to Resilience/Observability/Deployment tables - ARCHITECTURE: Bump date; add new modules to executive summary, API routes, SSE core services, Auth/Security section; add SSRF/Outbound guard failure mode (section 6); expand module mapping - ENVIRONMENT: Add OMNIROUTE_CRYPT_KEY/OMNIROUTE_API_KEY_BASE64 legacy aliases, OUTBOUND_SSRF_GUARD_ENABLED, CODEX_CLIENT_VERSION, and REQUEST_RETRY/MAX_RETRY_INTERVAL_SEC cooldown retry settings - FEATURES: Add 6 new feature sections — V1 WebSocket Bridge, Sync Tokens & Config Bundle, GLM Thinking Preset, Safe Outbound Fetch & SSRF Guard, Cooldown-Aware Retries, Compliance Audit v2 * fix: use api64 for proxy test (#1255) Integrated into release/v3.6.6 — IPv6 proxy test fix * fix(page): update custom models section to include all providers #1200 (#1256) Integrated into release/v3.6.6 — Gemini custom model picker fix * fix: provide default client_id fallbacks to prevent broken OAuth requests (#1246) Integrated into release/v3.6.6 — OAuth client_id default fallbacks * fix: translate max_tokens/max_completion_tokens → max_output_tokens in Chat→Responses translator (#1245) Integrated into release/v3.6.6 — max_tokens → max_output_tokens Responses API translation + unit tests * feat(oauth): support cursor-agent CLI as Cursor credential source (#1258) Integrated into release/v3.6.6 — cursor-agent CLI credential source support * fix(cc-compatible): restore upstream SSE and correct stream/combo timeout behavior (#1257) Integrated into release/v3.6.6 — CC-compatible upstream SSE restore + stream timeout fix + README table repair * fix(cli-tools): resolve API key resolution and model mapping bugs in CLI tools (#1263) Integrated into release/v3.6.6 * feat(cli-tools): add Qwen Code CLI integration (#1266) Integrated into release/v3.6.6 * fix(i18n): add missing zh-CN translations and fix logger imports (#1269) Integrated into release/v3.6.6 * fix(i18n): add Chinese i18n support to dashboard components (#1274) Integrated into release/v3.6.6 * feat: update Pollinations to require API key, remove free tier flag (#1177) * feat: friendly error messages for crypto/encryption failures (#1165) * feat: add TPS (tokens per second) metric column to request logs (#1182) * feat: merge custom/imported models into filter list for all providers (#1191) * feat(fallback): Fix provider-profile-driven lockouts (#1267) This integrates rdself's unify-provider-profile-locks PR manually to handle structural conflicts. * fix(claude): proper Anthropic SDK integration (#1271) * fix(healthcheck): use correct proxy wrapper format for getAccessToken (#1272) * chore(release): v3.6.6 — skills registry stability fix + final integration * fix(auth): harden bootstrap auth and memory dashboard behavior Restrict unauthenticated writes to /api/settings/require-login to the initial bootstrap window while keeping read-only checks public. This prevents post-setup config changes without blocking first-run login setup, and the onboarding flow now logs in immediately after setting the password. Restore memory API filtering and pagination behavior by supporting q searches, honoring offset-based requests, and avoiding unrelated fallback results when FTS misses. Update dashboard stats fallback to use the response totals consistently. Package the MCP server with explicit file entries and add regression tests for bootstrap auth and memory route behavior * fix(codex): remove max_output_tokens from body for compatibility * chore(release): v3.6.6 — include PR 1274 fixes in changelog * chore: exclude additional build artifacts and internal directories from npm package distribution * fix: update Gemini OAuth test to match registry defaults + codex UI improvements * fix: restore .mjs refs for scripts/ in test imports after ts migration * fix: restore next.config.mjs ref in dev-origins test * fix: implement db migration safety checks and codex config format * fix: disable mass-migration abort during unit tests based on auto-backup flag * fix: update script regex in auto-update tests to use .mjs * feat: Add Perplexity Web (Session) provider (#1289) Integrated into release/v3.6.6 * fix(cli): resolve codex routing config parsing, standardize select model button positioning, and clarify oauth documentation * docs(changelog): record recent cli, provider, and test updates Document the latest fixes for Codex routing configuration parsing and Lobehub provider icon fallback behavior. Add the note that the remaining JavaScript test files were migrated to TypeScript ES modules to reflect the completed test stack transition. * chore(release): merge #1286 minor improvements manually to avoid testing conflict * chore(test): rename perplexity-web.test.mjs to .ts to maintain 100% TS codebase * chore(docs): update CHANGELOG.md for perplexity-web provider * fix(security): resolve CodeQL incomplete URL substring sanitization via URL parsing in test mocks * fix: integrate compressContext() into chatCore.ts request pipeline Proactively compress oversized contexts before sending to upstream providers, preventing context_length_exceeded errors. Compression triggers at 85% of model's context limit using the existing 3-layer compressContext() function. - Import compressContext, estimateTokens, getTokenLimit from contextManager - Add compression check after translation, before executor dispatch - Estimate tokens and compare against 85% threshold of model's context limit - Apply 3-layer compression (trim tools, compress thinking, purify history) - Log compression events with before/after token counts and layers applied - Audit compression events for observability - Add unit tests verifying integration behavior Closes #1290 * fix(tests): align reasoning expectations with GLM thinking structure * fix: prevent orphaned tool_result messages in purifyHistory() When purifyHistory() drops oldest messages to fit context window, it can split tool_use/tool_result pairs — keeping the tool_result but dropping the tool_use that initiated it. This causes upstream providers to reject the request with format errors. Add fixToolPairs() that runs after each purification pass to remove: - OpenAI format: orphaned role='tool' messages without matching tool_calls ID - Claude format: orphaned tool_result content blocks without matching tool_use ID Closes #1291 * fix(tests): supply tool_use in mock so it is not dropped * chore: convert remaining test to TypeScript * fix(tests): restore compatibility with compressContext threshold test after tsx migration * docs: finalize v3.6.6 release documentation * fix(core): finalize provider removal, type issues, and codex API key config * fix(dashboard): render Web/Cookie, Search, Audio provider sections and fix TypeScript errors * fix: increase MCP web_search timeout to 60s (#1278) * fix: route combo testing properly for embedding models (#1260) * fix: accumulate excluded accounts in combo fallback loop (#1233) * fix: strip leading whitespace and newlines from first streaming chunk (#1211) * docs: clarify VPS and Docker settings for OAuth credentials (#1204) * fix: return real retry-after for pipeline gates (#1301) Integrated into release/v3.6.6 — returns real Retry-After values from pipeline gates * feat: streaming semantic cache, Cursor auto-version detection, and call-log enhancements (#1296) Integrated into release/v3.6.6 — streaming semantic cache, Cursor auto-version detection, call-log cache_source tracking * feat(api): support more OpenAI types (image, embeddings, audio-transcriptions, audio-speech) (#1297) Integrated into release/v3.6.6 — adds embeddings, audio-transcriptions, audio-speech, and images-generations support for custom OpenAI-compatible providers, plus Pollinations image registry * deps: bump hono from 4.12.12 to 4.12.14 (#1302) Integrated into release/v3.6.6 * deps: bump hono from 4.12.12 to 4.12.14 (#1306) Integrated into release/v3.6.6 * chore: stabilization fixes for v3.6.6 (#1298, #1254, #59, CI) * fix(providers): match correct endpoint for Xiaomi MiMo, strip routing prefix for custom openai endpoints (#1303, #1261) * feat(storage): add database backup cleanup controls * chore(release): v3.6.6 — Final Stabilization Push * Backport call log storage refactor to release/v3.6.6 (#1307) Integrated into release/v3.6.6 * deps: update dompurify to 3.4.0 to resolve CVE-XYZ (#60) * test: disable sqlite auto backup in CI to resolve E2E timeout (#24481475058) * chore(docs): sync CHANGELOG for v3.6.6 with missing features and fixes * chore(release): prep v3.6.6 infrastructure and type safety fixes - Migrated legacy .mjs scripts to .ts (bin, prepublish, policies) - Resolved pre-commit strict lint (t11 budget) errors in combo.ts - Explicitly typed all TS bindings in pack-artifact policies - Updated package.json commands to run Node via tsx/esm internally - Hardened CI/CD with explicit node version 22.22.2 checks - Completed stage validations for v3.6.6 final release * chore: fix TS build errors and e2e timeouts in CI - Migrate nodeRuntimeSupport to TS interfaces avoiding implicit any - Increase visibility timeouts in skills-marketplace E2E test to 15s to bypass CI flakiness - Complete migration of .mjs scripts to .ts ensuring type safety * chore(release): sync package version 3.6.6 across workspaces * test(e2e): universally increase UI component visibility timeouts from 5s to 15s to bypass CI starvation * chore(build): inject baseUrl, paths, and types:node into MITM tsconfig within prepublish hook to fix missing types in CI check --------- Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: Jack <5443152+hijak@users.noreply.github.com> Co-authored-by: Randi <55005611+rdself@users.noreply.github.com> Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com> Co-authored-by: Samuel Cedric <ceds.sam@gmail.com> Co-authored-by: Max Garmash <max@37bytes.com> Co-authored-by: Markus Hartung <mail@hartmark.se> Co-authored-by: Gi99lin <74502520+Gi99lin@users.noreply.github.com> Co-authored-by: Payne <baboialex95@gmail.com> Co-authored-by: Benson K B <bensonkbmca@gmail.com> Co-authored-by: clousky2020 <33016567+clousky2020@users.noreply.github.com> Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com> Co-authored-by: oyi77 <oyi77@users.noreply.github.com> Co-authored-by: Hdsje <vovan877@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: xiaoge1688 <moyekongling@gmail.com> |
||
|
diegosouzapw
|
7b75476c4a |
fix(core): preserve primary failures across chat fallbacks
Keep the original combo and budget exhaustion errors when global or emergency fallbacks also fail so callers see the real upstream cause. Also preserve translated responses for memory extraction before output post-processing, track pending rate-limit async work for deterministic test resets, and expose usage helpers needed for deeper branch coverage. Expand unit coverage across moderation, media generation, streaming, response logging, usage helpers, and fallback proxy error handling. |
||
|
diegosouzapw
|
b7bd41942d |
fix(chat): extract pipeline helpers and harden edge cases
Move chat pipeline validation, circuit breaker execution, proxy resolution, logging, and session header handling into dedicated helpers to keep the SSE handler smaller and easier to verify. Also fix shared API option precedence, rebuild skill version caches after deletions, ignore api.trycloudflare.com false positives, and add rate-limit manager test flush/reset hooks for deterministic coverage. Expand integration and unit coverage across chat routing, auth, cloud sync, skills, executors, streaming, DB helpers, proxy handling, and provider/model utilities. |
||
|
Chris Staley
|
f8d045c275 |
fix(gemini): per-model quota isolation — 429 on one model keeps others active
Gemini AI Studio enforces per-model quotas. Previously a 429 on gemini-2.5-pro would mark the entire connection as credits_exhausted, blocking all models on that API key. Three-layer fix: - chatCore: lock model only (not connection) for RATE_LIMITED and QUOTA_EXHAUSTED errors from Gemini - auth: early-return with model-only lockout before terminal status check, so credits_exhausted is never set on the connection - rateLimitManager: use model-scoped limiter keys for Gemini so the Bottleneck queue pauses only the affected model, not the connection - chat: skip markAccountExhaustedFrom429 for Gemini (per-model quotas) |
||
|
diegosouzapw
|
0546d06c0a |
fix(types): cast extracted usage to Record<string,number> in stream.ts to resolve TS property errors
Also fix syntax error in openai-to-claude-strip-empty.test.mjs (tool/assistant messages were incorrectly nested) |
||
|
Oleg Saprykin
|
c009c40606 |
refactor: use .finally() to always delete limiter from Map
Address bot review feedback: use .finally() instead of .then()/.catch() so limiters.delete() runs regardless of whether stop() succeeds or throws (e.g. already stopped by concurrent 429). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Oleg Saprykin
|
b29456c8e5 |
fix: catch stop() already called on concurrent 429s
Multiple concurrent requests can receive 429 simultaneously, causing stop() to be called on an already-stopped limiter. Add .catch() to prevent unhandled rejection. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Oleg Saprykin
|
64f040bddd |
fix: drop Bottleneck queue on 429 instead of waiting for reservoir refresh
When a provider returns 429 (rate limit exceeded), the rate limit manager
was setting reservoir=0 and waiting for reservoirRefreshInterval before
releasing queued requests. For providers with long rate limit windows
(e.g. Codex with hours-long resets), this caused all queued requests to
hang indefinitely — they never timed out or returned an error.
This prevented upstream callers (e.g. LiteLLM) from triggering fallback
to alternative providers, effectively making the entire model unavailable
until the rate limit window expired.
Fix: on 429, call limiter.stop({ dropWaitingJobs: true }) to immediately
fail all queued requests, then delete the limiter from the Map so
getLimiter() creates a fresh instance for subsequent requests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|
diegosouzapw
|
a4276444b5 |
fix(rate-limit): add maxWait to Bottleneck to prevent endless queuing (#297)
When all provider quotas are exhausted (reservoir=0 after repeated 429s), Bottleneck's schedule() would queue requests indefinitely since no maxWait was configured. Clients (Cursor, Claude Code, VS Code) would hang forever. Fix: add maxWait=120000 (2min, configurable via RATE_LIMIT_MAX_WAIT_MS env) to DEFAULT_SETTINGS and all three Bottleneck constructors. When a job waits longer than maxWait, Bottleneck rejects with a BottleneckError which propagates as a 502/503 error to the client — a clean fail-fast instead of infinite hang. |
||
|
diegosouzapw
|
5a53c17e81 |
feat: configurable tool name prefix (#199) and custom rpm/tpm rate limits (#198)
- Issue #199: proxy_ prefix on tool names is now automatically disabled when routing to non-Claude backends (Gemini, Compatible, etc.). Prevents tool name mismatches in OpenCode, Cursor, and other clients. - Issue #198: Added customRpm/customTpm support per provider connection. Users can configure custom rate limits via connection settings, overriding the default auto-learned limits from response headers. |
||
|
diegosouzapw
|
33dfbf0177 |
refactor: harden open-sse services, eliminate any casts, add dashboard pages
- Replace all `as any` casts in MCP advancedTools with typed helpers (toRecord, toString, toNumber) - Harden open-sse services: rateLimitManager, sessionManager, usage, roleNormalizer, signatureCache, comboMetrics - Improve responseSanitizer and responseTranslator type safety - Remove deprecated openai-responses request translator - Add dashboard pages: /a2a, /mcp, /auto-combo with live data - Improve error/loading/not-found pages with consistent design - Add root loading.tsx and typecheck tsconfig variants - Add check-t11-any-budget.mjs audit script |
||
|
diegosouzapw
|
4a1acb1446 |
feat(release): v1.7.3 — model deprecation, background degradation, rate limit persistence, thinking improvements, circuit breaker
Features: - Model Deprecation Auto-Forward (10+ built-in aliases + custom via UI) - Background Task Smart Degradation (19 patterns, degradation map) - Rate Limit Persistence (SQLite, 60s debounce, 24h staleness) - thinkingLevel string → budget conversion (high/medium/low/none) - Claude -thinking model auto-injection - Gemini 3.0/3.1 model registry distinction - Token Refresh Circuit Breaker (5 failures → 30min cooldown) Tests: 561 total (40+ new), 0 failures |
||
|
diegosouzapw
|
71d14209a4 |
feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy
OmniRoute is an intelligent API gateway that unifies 20+ AI providers behind a single OpenAI-compatible endpoint. Features include intelligent routing with 6 strategies, multi-format translation (OpenAI/Claude/Gemini/Responses API), circuit breakers, semantic caching, combo fallback chains, real-time health monitoring, and a full dashboard with provider management, analytics, and CLI tool integration. Key highlights: - 20+ providers (Claude Code, Codex, Gemini CLI, GitHub Copilot, iFlow, Qwen, Kiro, etc.) - 6 routing strategies (Fill First, Round Robin, P2C, Random, Least Used, Cost Optimized) - Export/Import database backup with full archive support - Translator Playground with 4 modes (Playground, Chat Tester, Test Bench, Live Monitor) - 100% TypeScript across src/ and open-sse/ - Docker support with multi-stage builds - Comprehensive documentation and 9 dashboard screenshots |