mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-17 20:52:15 +03:00
e3bca29bbcf57afb035733dcab347d7b725a7bcf
6935 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Rouzbeh†
|
e3bca29bbc |
fix(docker): real image tags (bifrost/cliproxyapi) + complete OMNIROUTE_BASE_PATH runtime patcher (#10482)
* fix(docker): real image tags + complete OMNIROUTE_BASE_PATH runtime patcher
Three docker issues fixed:
1. Images that do not exist:
- bifrost: ghcr.io/maximhq/bifrost:1.5.21 never existed (1.5.x tops at
v1.5.16, all tags carry the v prefix) -> ghcr.io/maximhq/bifrost:v1.6.11
- cliproxyapi: ghcr.io/router-for-me/* is not publicly pullable (403);
the official prebuilt image is docker.io/eceasy/cli-proxy-api, where
the pinned v6.9.7 exists -> docker.io/eceasy/cli-proxy-api:v6.9.7
- Verified still-current: redis:8.6.5-alpine (already on Redis 8 since
#9065; ioredis 5.10 is RESP2/3-compatible, no modules used) and
qdrant:v1.12.4 -- both exist, unchanged.
2. OMNIROUTE_BASE_PATH ignored on prebuilt images (root cause):
Next 16 (webpack and Turbopack) app-router renders SSR asset URLs from
assetPrefix ALONE; basePath only affects routing. The runtime patcher
(ensure-docker-base-path) rewrote basePath literals only, so a prebuilt
root-path image patched to /omniroute served the page but every
/_next/static shell reference stayed unprefixed (404 behind a subpath
proxy), the RSC flight-payload chunk refs came from client-reference
manifests baked with unprefixed paths, and the Turbopack client process
shim ships an empty env object so the client never learns the subpath.
Extended patch-standalone-base-path.mjs to also rewrite:
- assetPrefix literals (mirrors the subpath for SSR asset URLs)
- the NEXT_PUBLIC_OMNIROUTE_BASE_PATH env mirror in the inline config
- the client process.env shim (.env={}) with the two basePath keys
- every baked "/_next/static URL (manifests, media imports, .html pages)
next.config.mjs now mirrors basePath into assetPrefix so REBUILT images
bake prefixed assets too. E2E-verified on the published main-web image:
HTML under /omniroute now has 16/16 prefixed JS srcs and 82/82 prefixed
flight refs (was 13/9 + ~150 unprefixed), prefixed assets return 200.
* chore(changelog): fragment for #10482 (docker images + basepath patcher)
* chore(changelog): bullet-form fragment for #10482
* Merge branch 'release/v3.8.50' into fix/docker-compose-images-and-basepath
* test(fix): refresh expired alibaba quota sample validity and onnxruntime pin for v3.8.50 base
- alibaba-free-tier-quota-fetcher.test.ts: sample quotaValidityPeriod
(2026-08-16 16:00 UTC) is in the past, making every quota entry classify
as expired/not_capable; bump to 2028-01-01 UTC so the text/merge
classification tests exercise the intended path again.
- optional-transformers-dependency.test.ts: onnxruntime-node pin assertion
updated from ~1.24.3 to ~1.27.0 to match package.json (bumped by #10403);
the regular-not-optional intent is unchanged.
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
|
||
|
Rouzbeh†
|
6ff2e7b2c2 |
fix(antigravity): heal empty-projectId accounts via retryable auto-onboarding (#10424)
* fix(antigravity): heal empty-projectId accounts via retryable auto-onboarding Accounts with an empty Cloud Code projectId get a permanent 422 "Missing Google projectId" when loadCodeAssist returns no project. The 3.8.50 bootstrap attempts to CREATE the project via onboardUser, but a single failed attempt (transient network/upstream error) was memoized forever in onboardAttemptedCache: every later request in the process skipped onboarding and 422'd, even though a retry would succeed. Replace the permanent per-token Set with a failure-backoff map: failed onboard attempts are retried after a 5-minute backoff (bounded, self-healing), the in-flight lock still dedupes concurrent calls, and success clears the failure marker and memoizes the project as before. Accounts that CAN be onboarded now heal automatically on a later request or token refresh — no user action. Tests: the existing "does not retry" case is now framed as the backoff window; a new case proves the account heals (retries onboarding and recovers the project) once the backoff expires. * chore(changelog): fragment for #10424 antigravity project autocreate * feat(antigravity): BYOP fast-fail + manual GCP project-id override Port decolua/9router#2934 + VansRouter 802a859: - tryOnboardUser now returns a three-way status; a 200 onboardUser response WITHOUT cloudaicompanionProject means Google deprecated automatic project creation for standard-tier (personal) accounts (BYOP). Such accounts are cached permanently (no pointless ~18s re-onboard) and the executor fails fast with 403 GCP_PROJECT_REQUIRED + actionable 'enter your project id' message instead of the generic 422 or a delayed 429. - Transient onboard failures keep the existing 5-min backoff heal. - Manual project-id override: the EditConnectionModal now stamps providerSpecificData.isProjectIdManual when the operator enters a project id, and tokenRefresh skips auto-discovery for flagged accounts so the manual value is never overwritten. * chore(changelog): cover BYOP fast-fail + manual override in #10424 fragment * test(antigravity): expect fast 403 GCP_PROJECT_REQUIRED when loadCodeAssist finds no project (#10424) Google now marks accounts without an onboarded project as BYOP (automatic project creation deprecated for standard-tier accounts, #2934). The PR's BYOP fast-fail path returns 403 gcp_project_required instead of the old generic 422 missing_project_id; align the #2334 executor test with that contract so CI unit-test shard 2/4 passes. * fix(antigravity): persist isProjectIdManual, fix BYOP citation, dodge refresh-retry Review follow-up on #10424: 1. EditConnectionModal: isProjectIdManual was set on updates.providerSpecificData right after the project-id field, then the OAuth path (Antigravity is always OAuth) rebuilt providerSpecificData from connection.providerSpecificData before the request went out, discarding the flag — tokenRefresh.ts was guarding a field never actually persisted. The flag now lands in the single surviving antigravity merge, with a jsdom regression test (modeled on edit-connection-modal-openai-store-toggle). 2. The '#2934' citation for the Google BYOP claim pointed at an unrelated closed issue. Swapped for the real tracking issue #8491 (empty Google projectId -> 422 class) across bootstrap/executor/test comments. 3. BYOP fast-fail now returns 422 instead of 403: chatCore's generic 401/403 -> refresh-and-retry path was hitting Google's OAuth token endpoint on every request from an affected account (pointless — refreshing cannot create a GCP project), and 422 matches the sibling missing_project_id error the client already maps to an action-needed prompt. Also: eslint-disable-next-line for the pre-existing react-hooks/set-state-in-effect baseline noise in the modal (repo convention, same pattern as 11 other dashboard files). * chore(ci): drop unused eslint-disable in EditConnectionModal form hydration The react-hooks/set-state-in-effect disable added in the previous commit is unused under the repo's pinned eslint-plugin-react-hooks (7.0.1) — the rule does not fire on this line at that version, so the unused directive tripped the whole-repo 'No new ESLint warnings' gate (max-warnings 0). Verified with the lockfile-pinned plugin: lint:json is clean (0 errors, 0 warnings). * fix(build): bound and retry the opencode-plugin npm install in prepublish The plugin's node_modules is gitignored, so every fresh CI checkout runs a full npm install inside @omniroute/opencode-plugin during build:cli. npm's unbounded fetch retries turn a stalled registry CDN connection (the recurring onnxruntime-class ETIMEDOUT flake) into a 20-30 minute hang — the DAST 'Build CLI bundle' step has been cancelled at the 30m cap repeatedly. - Bound npm fetch: --fetch-timeout 60s, 2 retries with capped backoff — a stalled connection now fails fast instead of hanging the job. - Retry the install up to 3 times with a 10s pause between attempts, so transient CDN failures recover in-build. Net effect: the step either completes (network OK) or fails quickly with a clear error (network down) — it can no longer eat the whole job budget. * ci(quality): use the npm-ci-retry action on every install step Fast Quality Gates failed on the recurring onnxruntime-node postinstall ETIMEDOUT (Microsoft CDN 150.171.x.x) - the same transient flake that has hit Vitest and dast-smoke today. Only the Build job used the retry action; the other five jobs (Docs, Fast Quality Gates, Vitest, Unit Tests, changelog) still ran a bare install and die on any CDN hiccup. Use the existing retry action (3 attempts, exponential backoff) on every install step for consistency. * Merge branch 'release/v3.8.50' into fix/antigravity-project-autocreate * test(fix): refresh expired alibaba quota sample validity and onnxruntime pin for v3.8.50 base - alibaba-free-tier-quota-fetcher.test.ts: sample quotaValidityPeriod (2026-08-16 16:00 UTC) is in the past, making every quota entry classify as expired/not_capable; bump to 2028-01-01 UTC so the text/merge classification tests exercise the intended path again. - optional-transformers-dependency.test.ts: onnxruntime-node pin assertion updated from ~1.24.3 to ~1.27.0 to match package.json (bumped by #10403); the regular-not-optional intent is unchanged. * test(fix): widen modelsDevSync lastSync wait from 200ms default to 2000ms The truthy-spellings loop asserted each enabled case completes its first fetch within waitFor's 200ms default timeout, which trips under CI runner load (observed on PR 10424 shard 2/4). Match the file's other lastSync waits (2000ms) so the sync-completion assertion is load-tolerant. --------- Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com> |
||
|
blarovse
|
24ef1dc3d4 |
Sanitize test fixtures, add developer .env guidance, and add gitleaks… (#10411)
* Sanitize test fixtures, add developer .env guidance, and add gitleaks workflow - Replace realistic-looking AWS keys and PEM fixtures in unit tests with synthetic placeholders to avoid false positives from secret scanners. - Add docs/DEVELOPER-ENVIRONMENT.md describing postinstall .env behavior and remediation guidance. - Add .github/workflows/gitleaks.yml to run gitleaks on pull requests. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add gitleaks baseline and CI baseline support; update ignore and PR body\n\n- Copy gitleaks-local.json -> gitleaks-baseline.json\n- Add --baseline-path to workflow\n- Allowlist baseline in .gitleaks.toml\n- Ignore gitleaks-local.json\n- Add PR_BODY.md with scan summary\n\nCo-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * chore(security): fix gitleaks config, drop redundant baseline/CI, clean doc artifacts - Fix the malformed .gitleaks.toml [[rules]] block: an inline [rules.allowlist] with only paths (no regex/path at rule level) made gitleaks refuse to load the config (`FTL Failed to load config ... both |regex| and |path| are empty`), turning the project's blocking check-secrets ratchet into a hard failure. Verified: check-secrets config now loads and exits 0. - Reconcile with the existing gitleaks gate: remove the redundant .github/workflows/gitleaks.yml and root gitleaks-baseline.json (a second, differently-scoped scanning mechanism + an unreviewed 430-finding blanket baseline) — the project already runs scripts/check/check-secrets.mjs as a blocking ratchet in ci.yml/quality.yml and its .gitleaks.toml policy is to fix real findings, not blanket-allowlist them. - Remove the stray PR_BODY.md automation artifact from the repo root. - Fix the duplicated <div align="center"> tag in README.md. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: OmniRoute Bot <noreply@omniroute.local> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: blarovse <312250233+blarovse@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Ravi Tharuma
|
722748f7c1 |
fix(sse): keep Codex quota headers under the forwarding budget (#10306)
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190) Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13 (with monaco-editor scoped override). Closes Dependabot #189, #190. Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge — awaiting Dependabot re-scan. npm audit → 0 vulnerabilities. * fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks) _tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential _tasks symlink can slip in via git add -A and, once pulled, checkout materializes it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks ignores the symlink too, preventing re-capture. * Hide health-check excluded models from /v1/models catalog (#10026) Mirror the request-time exclusion rule (provider_specific_data.excludedModels) in the unified catalog builder: a model is hidden when its provider has connections but none of them is eligible for it. Applied across the PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops so ghost models no longer appear as available. Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> * fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055) * fix(models): memoize getModelsDevPricing for /v1/models catalog resolveCatalogPricing called getModelsDevPricing once per model while building GET /v1/models. Each call re-scanned models_dev_pricing and JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging the event loop so even /healthz timed out (#9685, #10052). Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing and add a unit test for invalidation. Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> * fix(db): invalidate modelsDevPricing cache on DB reset (#10055) Copilot review fixes: 1. Register invalidateModelsDevPricingCache() with DB state reset system so resetDbInstance() clears the process-local memo, preventing stale pricing data from surviving across DB reset/restore operations. 2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055). The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing() results until saveModelsDevPricing()/clearModelsDevPricing() to avoid re-scanning all pricing rows on every /v1/models request. Without this hook, backup restore and test DB resets would serve stale cached data from the previous connection. Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> * fix(sse): keep Codex quota headers under the forwarding budget The 768-byte cap plus priority-3 for any name that does not contain "ratelimit" dropped x-codex-*-used-percent / reset / credits on every stream. x-codex-turn-state (314 bytes) ate the budget. Raise the cap, treat Codex quota headers as rate-limit priority, and do not forward turn-state. --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca> Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> |
||
|
Markus Hartung
|
0f402a84a4 |
feat(responses): virtualize previous_response_id continuation regardless of upstream support (#10262)
* feat(responses): virtualize previous_response_id continuation regardless of upstream support OmniRoute now exposes OpenAI-compatible previous_response_id/store continuation to clients unconditionally, even when the selected upstream provider has no native Responses-API state support. Reconstruction happens server-side in handleChatImplementation, before any downstream validation or provider translation: OmniRoute resolves the response id back to the full input/output it previously produced, prepends it to the client's delta, and forwards the full reconstructed history upstream exactly as it does today. Client<->OmniRoute traffic shrinks to the new delta only; OmniRoute<->provider traffic is unchanged. Storage reuses the existing call-log pipeline artifact (already gated by call_log_pipeline_enabled, already retained/cleaned up by the existing call-log lifecycle) instead of duplicating conversation content into a second store -- only a lightweight call_logs.response_id index is new. Every lookup is scoped by api_key_id so one client can never resolve another client's stored conversation, and any unresolvable/missing/ size-limit-omitted state fails closed with OpenAI's own previous_response_not_found contract. Stacked on feat/openai-responses-store-toggle (#10121). * fix(db): re-export responsesContinuationStore from the localDb barrel check-db-rules requires every db/ module to be re-exported (or explicitly allowlisted as intentionally-internal) for discoverability. Missed this when the module was first added. * fix(db): renumber previous_response_id index migration to 154 The migration was numbered 153, but release/v3.8.50 already carries 153_radar_local_model_state.sql. The emngrating runner's collision guard throws on two live .sql files sharing a numeric prefix, so the refreshed merge would fail DB startup. Renumber to the next free slot (154). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * docs(db): sync migration count to 149 across llm.txt mirrors The responses-continuation store adds one migration, so the docs' migration count is now 149 (was 148). Update README/AGENTS/llm.txt and regenerate the i18n llm.txt mirrors to keep check:docs-all green. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(responses-continuation): respect preserve mode, drop dead export - Un-export ResponsesContinuationState: it's never imported outside responsesContinuationStore.ts, its own defining file. Fixes the check:dead-code regression (410 > baseline 409). - Scope the previous_response_id virtualization interception in chat.ts to skip entirely when responsesPreviousResponseIdMode=preserve. The interception ran unconditionally before target/connection selection, ahead of applyResponsesPreviousResponseIdPolicy (chatCore.ts) -- the existing per-target enforcement point for this setting -- so "preserve" (the explicit, connection-independent contract for "let the upstream resolve previous_response_id natively") was silently unreachable: the field was already deleted and replaced with locally-reconstructed input by the time that policy ran. This also broke Codex's own executor, which relies on an untouched previous_response_id to delegate history resolution upstream (see stripOrphanedCodexFunctionCallOutputs in codex.ts). "auto" and "strip" modes are unaffected -- virtualization is a strict improvement over their old "drop the field, hope the client resent everything" behavior. - Add a regression test exercising the actual chat.ts handler (not just the policy helper in isolation): confirms mode=preserve now proceeds to normal routing instead of the virtualization's previous_response_not_found rejection, and that default/auto mode's existing virtualization behavior is unchanged. Verified the test fails for the right reason against pre-fix chat.ts. Addresses PR review feedback. --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: hartmark <hartmark@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Benson K B
|
14afdcb923 |
fix(routing): fallback to default model alias seeds when unmapped in database (#10124)
* fix(routing): fallback to default model alias seeds when unmapped in database * fix(routing): rename seed-fallback resolver; hermetic 401 regression test Maintainer review (PR #10124): 1. Rename resolveModelAlias -> resolveModelAliasWithSeedFallback (and resolveModelAliasOnBody -> resolveModelAliasWithSeedFallbackOnBody) to avoid the export collision with the sync resolveModelAlias in open-sse/services/modelDeprecation.ts and src/shared/constants/modelSpecs.ts. 2. Regression test now reproduces the 401: alias unmapped in the (empty, DATA_DIR-isolated) modelAliases namespace but present in the static seed resolves to the seed target instead of passing through unmapped. 3. Test isolates DATA_DIR (temp dir + resetDbInstance) instead of reading the operator's live DB. * fix(models): add outputTokenLimit to CustomModelEntry Fixes the open-sse typecheck gate regression: catalog.ts reads model.outputTokenLimit (for max_output_tokens in custom model metadata) but CustomModelEntry only declared inputTokenLimit — TS2551. The field exists in the runtime model data and is already consumed; the interface just never declared it. |
||
|
Nick Sullivan
|
b6d2b4a41c |
Compression telemetry retention has never deleted a row (same unit bug as #9625) (#10559)
* fix(db): align compression_run_telemetry cleanup cutoff with millisecond column cleanupCompressionRunTelemetry() computed its cutoff in epoch seconds while insertCompressionRunTelemetryRow() stamps the timestamp column with Date.now() (epoch milliseconds). A millisecond timestamp is ~1000x larger than a seconds cutoff, so DELETE WHERE timestamp < cutoff never matched an old row and the retention sweep added by #6848 to bound storage.sqlite growth was inert. This is the same defect as domain_cost_history (#9625), whose fix corrected cleanupDomainCostHistory() ~90 lines earlier in this file and missed this sibling call site. The stale docstring asserting a unix-epoch column is corrected too. The repro test seeds through the real writer to establish the stored unit, so it also fails if the producer format diverges from the consumer again. * docs(changelog): add fragment for the telemetry retention unit fix |
||
|
Nick Sullivan
|
a87c9236ff |
Database settings page returns HTTP 500 when SQLite lacks the optional dbstat table (#10558)
* fix(db): tolerate a SQLite build without the dbstat virtual table
getDatabaseStats() queried `dbstat` once per table with no guard. `dbstat` is
compile-time optional (ENABLE_DBSTAT_VTAB) and is absent from sql.js/WASM
builds, so on those runtimes the query throws and the error propagates out of
getDatabaseStats().
Every caller dies with it. Most visibly, GET and PATCH /api/settings/database
return HTTP 500, which makes the entire database settings page unusable — users
cannot read or change page size, cache size, or vacuum settings.
The function already anticipated missing virtual-table modules: the COUNT(*)
lookup a few lines above swallows "no such module:" errors. The dbstat query
simply sat outside that guard.
Probe dbstat once per call and skip the per-table size lookups when it is
unavailable, reporting size 0. Database-level figures (total size, page count,
cache size) come from pragmas and stay accurate; only per-table byte sizes are
lost, which is the correct trade against a hard 500.
Unrelated failures (I/O errors, corruption) still propagate.
Both spellings are handled: sql.js reports "no such module: dbstat" while
better-sqlite3 can surface "no such table: dbstat".
* test(db): cover prefixed driver errors and dbstat edge cases
Review follow-up on the previous commit.
The guard is deliberately unanchored because real drivers stringify errors
with their class name attached ("SqliteError: no such table: dbstat",
"RuntimeError: ..."). Nothing pinned that, so anchoring the regex would have
passed the suite while silently breaking every real driver. Add a case for the
prefixed form; it fails if a caret is introduced.
Also cover three shapes the fake previously could not express:
- a database with no user tables, which is what a fresh install hits first
- SUM(pgsize) returning NULL for a table occupying no pages
- dbstat answering the probe but failing on a later table, which documents
that a mid-iteration fault still propagates rather than being mistaken for
an absent module
Correct the source comment: the two error spellings track the SQLite build,
not the driver package, so the earlier attribution to better-sqlite3 was
wrong.
* docs(changelog): add fragment for the dbstat availability guard
Registers the new test with Stryker alongside the sibling db suites and adds
the changelog fragment for this fix.
---------
Co-authored-by: Nick Sullivan <nick@technick.ai>
|
||
|
Yahoo
|
2098ba3848 |
fix(cli): ignore non-Windows HOSTNAME when binding server (#10557)
* fix(cli): ignore non-Windows HOSTNAME when binding server * chore(changelog): assign PR number |
||
|
Rizx
|
b8b78f7a69 |
fix(providers): remove invalid CodeBuddy CN glm-4.7 and add hy3 (0.0x… (#10356)
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190) Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13 (with monaco-editor scoped override). Closes Dependabot #189, #190. Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge — awaiting Dependabot re-scan. npm audit → 0 vulnerabilities. * fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks) _tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential _tasks symlink can slip in via git add -A and, once pulled, checkout materializes it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks ignores the symlink too, preventing re-capture. * Hide health-check excluded models from /v1/models catalog (#10026) Mirror the request-time exclusion rule (provider_specific_data.excludedModels) in the unified catalog builder: a model is hidden when its provider has connections but none of them is eligible for it. Applied across the PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops so ghost models no longer appear as available. Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> * fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055) * fix(models): memoize getModelsDevPricing for /v1/models catalog resolveCatalogPricing called getModelsDevPricing once per model while building GET /v1/models. Each call re-scanned models_dev_pricing and JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging the event loop so even /healthz timed out (#9685, #10052). Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing and add a unit test for invalidation. Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> * fix(db): invalidate modelsDevPricing cache on DB reset (#10055) Copilot review fixes: 1. Register invalidateModelsDevPricingCache() with DB state reset system so resetDbInstance() clears the process-local memo, preventing stale pricing data from surviving across DB reset/restore operations. 2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055). The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing() results until saveModelsDevPricing()/clearModelsDevPricing() to avoid re-scanning all pricing rows on every /v1/models request. Without this hook, backup restore and test DB resets would serve stale cached data from the previous connection. Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> * fix(providers): remove invalid CodeBuddy CN glm-4.7 and add hy3 (0.0x credit) Swap the GLM-4.7 model for the Hunyuan hy3 model in the codebuddy-cn registry, keep the catalog at 15 models, and update the matching provider test expectations. Regenerated the auto-generated provider reference doc. --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca> Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> Co-authored-by: Ravi Tharuma <25951435+RaviTharuma@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Ravi Tharuma
|
fbc67f1338 |
fix(models): honor MODELS_DEV_SYNC_ENABLED=0 over dashboard settings (#10299)
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190) Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13 (with monaco-editor scoped override). Closes Dependabot #189, #190. Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge — awaiting Dependabot re-scan. npm audit → 0 vulnerabilities. * fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks) _tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential _tasks symlink can slip in via git add -A and, once pulled, checkout materializes it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks ignores the symlink too, preventing re-capture. * Hide health-check excluded models from /v1/models catalog (#10026) Mirror the request-time exclusion rule (provider_specific_data.excludedModels) in the unified catalog builder: a model is hidden when its provider has connections but none of them is eligible for it. Applied across the PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops so ghost models no longer appear as available. Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> * fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055) * fix(models): memoize getModelsDevPricing for /v1/models catalog resolveCatalogPricing called getModelsDevPricing once per model while building GET /v1/models. Each call re-scanned models_dev_pricing and JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging the event loop so even /healthz timed out (#9685, #10052). Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing and add a unit test for invalidation. Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> * fix(db): invalidate modelsDevPricing cache on DB reset (#10055) Copilot review fixes: 1. Register invalidateModelsDevPricingCache() with DB state reset system so resetDbInstance() clears the process-local memo, preventing stale pricing data from surviving across DB reset/restore operations. 2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055). The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing() results until saveModelsDevPricing()/clearModelsDevPricing() to avoid re-scanning all pricing rows on every /v1/models request. Without this hook, backup restore and test DB resets would serve stale cached data from the previous connection. Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> * fix(models): honor MODELS_DEV_SYNC_ENABLED=0 over dashboard settings The file header already advertised this env var but nothing read it. When catalog/compression pin the event loop, the dashboard (same process) cannot turn models.dev sync off. Let 0/false/off win over sqlite so an operator can recover with env + restart. Skip getModelsDevPricing SQL scans while the kill switch is set. * fix(models): restore prettier formatting after base merge Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * test(models): cover env kill switch during live settings updates Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca> Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Gi99lin
|
b1a2ff6887 |
feat(proxy): non-destructive auto-disable mode for the proxy health scheduler (#10342)
* feat(proxy): add non-destructive auto-disable mode for the proxy health scheduler PROXY_AUTO_REMOVE was the only opt-in action the background proxy health scheduler could take on a consistently failing proxy, and it deletes the row. For a manually-maintained proxy chain (multi-proxy pool/rotation, #6365) that is too destructive just to exclude a temporarily-dead member. Add PROXY_AUTO_DISABLE as a sibling flag: at the same consecutive-failure threshold it soft-disables the proxy (status "dead") instead of removing it. "dead" is already one of the statuses the pool/rotation alive-filter excludes, so a disabled proxy drops out of the active chain immediately with no other code changes. The scheduler keeps probing dead proxies on its normal interval, and the existing recovery branch (previously autoRemove-only) re-activates it automatically once it starts answering again. decision.ts's decideProxyHealthAction() gets an optional `autoDisable` input (defaults to false, so existing callers are unaffected) and a "dead" status value; scheduler.ts wires the new PROXY_AUTO_DISABLE env flag through. If both flags are set, auto-remove wins. getProxyHealthStats() now also surfaces the registry `status` so operators can see when a proxy was auto-disabled, and ProxyStatusBadge now treats the full "not alive" status set (not just the literal string "inactive") as inactive in the dashboard. * test(proxy): assert registry status in getProxyHealthStats output The non-destructive auto-disable change added the live registry status to the stats object returned by getProxyHealthStats. Align the pre-existing db-proxies-crud assertion with the intended output shape. Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> * fix(proxy): preserve auto-disabled status in dashboard edits Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: Gi99lin <Gi99lin@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
stanley
|
4540d303d7 |
fix(oauth): send required CLI headers in claude-auth import bootstrap call (#10144)
* fix(oauth): send required CLI headers in claude-auth import bootstrap call enrichWithBootstrap() in claudeAuthImport.ts was missing the User-Agent and anthropic-beta headers that the two other callers of the same /api/claude_cli/bootstrap endpoint (claudeIdentity.ts and src/lib/oauth/providers/claude.ts) always send. Without them, Anthropic doesn't recognize the request as coming from a CLI client and the bootstrap call fails, silently returning a null identity (accountUUID/organizationUUID/organizationType all null). createConnectionFromAuthFile()'s identity-verification refusal then gets bypassed via overwriteExisting: true (the only way imports currently succeed, since first attempts fail with identity_unverified because of this same bug), so every imported Claude connection ends up with unverified identity. Downstream, resolveAccountUUID() in claudeIdentity.ts falls back to a hash-derived fake UUID when providerSpecificData.accountUUID is null. That fake UUID is shape-valid but was never associated with the real account by Anthropic, so requests carrying it get classified as unrecognized third-party traffic and routed to the separate extra-usage pool instead of the account's plan limits -- producing an intermittent (~50% observed) 400: "Third-party apps now draw from your extra usage, not your plan limits." on an otherwise perfectly valid, imported subscription token. Fixes the header mismatch so bootstrap succeeds and imported connections get a real, Anthropic-recognized account identity from the start, same as connections created via the native OAuth flow. Fixes #10143 * fix(oauth): persist cliUserID device identity on claude-auth import createConnectionFromAuthFile() in claudeAuthImport.ts never set providerSpecificData.cliUserID, unlike the native OAuth setup flow in src/lib/oauth/providers/claude.ts which always mints one. cliUserID is read by resolveCliUserID() (open-sse/executors/claudeIdentity.ts) as the request's device_id; when absent it falls back to a lazy-random device id regenerated fresh every process restart (in-memory Map, process-lifetime only), so every restart of an imported connection presents as a brand-new device to Anthropic for the same account -- a second, independent contributor (alongside Part 1's bootstrap header fix in this same PR) to the intermittent third-party-usage 400 on valid imported subscription tokens. - "create new connection" branch: always mint a fresh cliUserID. - "update existing connection" branch: preserve any already-persisted cliUserID from existing.providerSpecificData (don't rotate a working device identity on re-import); only mint a fresh one if absent. Adds changelog.d/fixes/10144-claude-import-cli-user-id.md per CONTRIBUTING.md. Fixes #10143 * test(oauth): cover claude-auth import bootstrap headers + cliUserID persistence Adds tests/unit/claudeAuthImport-bootstrap-headers-10144.test.ts (Rule #18 regression guard for #10143): 1. enrichWithBootstrap() sends the required CLI headers on the /api/claude_cli/bootstrap call — a claude-cli User-Agent (now sourced from CLAUDE_CODE_CLIENT_VERSION, matching the two working call-sites) and anthropic-beta: oauth-2025-04-20 — and still falls back to null identity fields on non-OK upstream responses. 2. createConnectionFromAuthFile() mints a 64-hex cliUserID device identity on create, preserves an already-persisted cliUserID on overwrite re-import (no rotation), and mints a fresh one when the existing connection has none. Also aligns the hardcoded claude-cli/1.0.0 User-Agent in the import bootstrap with the version constant the two working call-sites (claudeIdentity.ts, oauth/providers/claude.ts) already use. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> * refactor(oauth): source claude-auth import UA from canonical constant (#10144 review nit) Addresses the hardcoded-version nit from review: the bootstrap User-Agent was re-typed as `claude-cli/${CLAUDE_CODE_CLIENT_VERSION}` instead of importing getClaudeCodeUserAgent() — the single source of truth the two working call-sites (claudeIdentity.ts, oauth/providers/claude.ts) use. - claudeAuthImport.ts: use getClaudeCodeUserAgent("cli") for the bootstrap call - test: import the same canonical helper instead of a local copy of the pinned version, and assert the outbound UA byte-for-byte against it, so a future version bump can't silently desync the wire identity. Verified: node --import tsx/esm --test on the new test file -> 5/5 pass; sibling claudeAuthImport.test.ts -> pass; eslint on both changed files -> no new findings (only the pre-existing @/lib/localDb barrel-import restriction on an untouched import line). * test(oauth): exercise claude auth import implementation Replace copied helper tests with real implementation coverage for bootstrap headers and persistent cliUserID behavior. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> Co-authored-by: stanleytejakusuma <stanleytejakusuma@users.noreply.github.com> |
||
|
Dave Cox
|
dcfbc24625 |
fix(deps): pin onnxruntime-node to the exact version @huggingface/transformers requires (#10543)
`@huggingface/transformers` 4.2.0 hard-pins `onnxruntime-node` to "1.24.3". The production-group bump in #10403 raised the root range from "~1.24.3" to "~1.27.0", so npm stopped deduping and nested a second copy under `node_modules/@huggingface/transformers/node_modules/onnxruntime-node`. Both copies ship a native `libonnxruntime.so.1` under the SAME SONAME, so glibc binds whichever is dlopen()ed first and the other addon dies. The Dockerfile post-build verification imports `@huggingface/transformers` and `onnxruntime-node` in one process, so `docker build` has failed on every commit since #10403: Error: .../transformers/node_modules/onnxruntime-node/bin/napi-v6/linux/x64/libonnxruntime.so.1: version `VERS_1.27.0' not found (required by .../onnxruntime-node/bin/napi-v6/linux/x64/onnxruntime_binding.node) Restore the root range to "~1.24.3" so a single hoisted copy is resolved again. Copying the nested native binaries into the standalone bundle is NOT a workaround: it makes both `.so` files present, which is precisely what triggers the SONAME clash above (verified against a real image build). Regression guard: tests/unit/onnxruntime-single-copy.test.ts asserts the lockfile resolves exactly one onnxruntime-node and that it matches the version transformers pins. Confirmed failing on the pre-fix lockfile (two copies, 1.27.0 vs 1.24.3) and passing after. Validated with a full `docker build --target runner-base`: the post-build verification step now passes (#19 DONE 156.9s) and the image boots healthy (/api/monitoring/health 200, migrations 134-148 applied). |
||
|
Diego Rodrigues de Sa e Souza
|
8dec2ad472 |
fix(resilience): mark embed connection terminal on hard upstream failure so dead accounts are not re-hit (#10347) (#10506)
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
31b02ff85f |
fix(responses): keep stream-aware TextDecoder across SSE transform chunks (#10223) (#10495)
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Ravi Tharuma
|
48e5cf7fe4 |
fix(sse): do not ZWJ-obfuscate the substring hermes in user text (#10488)
Keep the #8350 Hermes system-prompt drops, but remove hermes from the factory obfuscate_words list so hostnames and CLI mentions stay intact. Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> |
||
|
Chewji
|
8bd0b840f6 |
fix(antigravity): unblock Gemini and Claude reasoning capabilities (#10376)
* fix(antigravity): unblock Gemini and Claude reasoning capabilities * fix(antigravity): align two unit tests with unblocked Gemini/Claude reasoning The PR unblocks Antigravity Gemini/Claude reasoning (removed from REASONING_UNSUPPORTED_PATTERNS, mirroring model-capabilities-registry.test.ts). models-catalog-combo-metadata and services-branch-hardening still asserted the pre-PR deny contract; align them to the new verified behavior. No production code changed. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: Chewji9875 <Chewji9875@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Benson K B
|
3e8a8f71cc |
fix(providers): add PATCH handler to provider connection route (CLI rotate 405) (#10366)
* fix(providers): add PATCH handler to provider connection route The OpenAPI spec and the CLI (omniroute providers rotate, generated api-commands) both use PATCH /api/providers/[id], but the route only implemented PUT — PATCH requests returned 405 and key rotation via the CLI silently failed while reporting success (the DB-write fallback only catches thrown exceptions, not non-OK HTTP responses). Add a PATCH handler delegating to the PUT handler: both apply the same partial-update schema, so the semantics are identical. Regression test proves the PATCH export exists and delegates into the shared auth path; verified to fail without the fix. * docs(changelog): note PATCH provider route fix (PR #10366) * fix(providers): make PATCH delegation test environment-robust The 'PATCH delegates to PUT' assertion hardcoded a 401, which only holds when management auth is enforced (dev). In the CI unit-test env auth is not required, so the flow falls through to 'Connection not found' (404) for an unknown id — the test failed on the status code while the PATCH->PUT delegation itself is correct. Assert on delegation equivalence instead: PATCH must never 405 (the regression) and must return the same status as PUT for the same input. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * test(providers): use fresh Request per handler in PATCH delegation test The same Request was passed to both PATCH and PUT — PUT consumes the body via request.json(), so the second call got an empty body (400 validation) vs the first (404 not-found): a false status mismatch on bases where management auth is bypassed in the test env (release v3.8.50). Fresh Request per invocation makes identical inputs produce identical statuses. --------- Co-authored-by: benzntech <benzntech@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Sahil Singh
|
8ff3a1dda3 |
fix(mcp): dynamically generate web search provider enum from registry (#10209)
* fix(mcp): dynamically generate web search provider enum from registry * test(mcp): add contract test for dynamic web search provider enum Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> * fix(mcp): restore search.ts eslint suppression, type builder maps, fix firecrawl searchType arg The enum-dynamic refactor dropped search.ts's no-explicit-any suppression while a new Record<string,any> map re-introduced anys, and the response normalizer map swapped the firecrawl searchType argument with query. Type both maps explicitly, restore the base suppression (33 pre-existing anys), and pass searchType (not query) to normalizeFirecrawlSearchResponse. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: sadSanta-07 <sadSanta-07@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Xiangzhe
|
faeca3bbac |
fix(providers): scope model target formats to providers (#10072)
Co-authored-by: xz-dev <xz-dev@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Xiangzhe
|
b082d0735b |
fix(api-manager): allow empty combo restrictions (#10066)
* fix(api-manager): allow empty combo restrictions Represent unrestricted Combo access explicitly as combo/* so an empty Allowed Combos list can deny every Combo without affecting direct model routes. Preserve existing keys through migration 149 and cover Dashboard, policy, routing-target, and migration behavior. * docs: sync migration count to 149 after api-key combo-access migration Merging release/v3.8.50 forward landed 149_api_key_combo_access.sql, bumping the real migration count from 148 to 149. Updates README.md, AGENTS.md, llm.txt (root + all 42 i18n mirrors, exact-copy requirement) so the strict docs-counts-sync gate matches the live count again. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: xz-dev <xz-dev@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Aman
|
2723698fe2 | fix(providers): update token-backed web sessions (#10518) | ||
|
Diego Rodrigues de Sa e Souza
|
bdc30ca4dd |
fix(providers): strip uniqueItems from Gemini tool schemas to avoid upstream 400 (#9617) (#10511)
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
9bfdc15cbc |
fix(providers): emit Cursor kv_after_text before tool calls instead of truncating them (#10215) (#10502)
Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Bob.Hou
|
33e0fea8b0 |
fix(sse): flag OpenAI streams that close with content but no terminal marker (#10475)
Issue #10443: when the upstream kills an SSE stream mid-generation (antigravity/Gemini does this under its own rate enforcement), OmniRoute closed the stream silently for OpenAI-format clients - HTTP 200, a few content chunks, no finish_reason. The client sees a truncated turn. resolveSilentCloseReason() only flagged that shape for Claude clients (#7699). Extend it to OpenAI chat completions guarded on sawContent(), and teach hasClientTerminalSseMarker() that a non-null finish_reason chunk is a terminal marker (some providers omit data: [DONE]). Every known OpenAI-producing path ends with one of the two, so content forwarded without either is an upstream drop and now surfaces the in-band 502 error chunk + [DONE] instead of a silent close. TDD: tests/unit/silent-sse-close-openai-10443.test.ts - core case RED before / GREEN after, plus guard cases for finish_reason-only close, [DONE] close, empty-content (#8649 verdict preserved), and literal finish_reason text inside model content (JSON escaping keeps the raw bytes from matching the unescaped-field regex). Signed-off-by: Minxi Hou <houminxi@gmail.com> |
||
|
Diego Rodrigues de Sa e Souza
|
b17dfa4a14 |
fix(sse): mark gemini-3.5-flash as thinking-capable (#10450)
The base gemini-3.5-flash entry spread the shared GEMINI_35_FLASH_MODEL_SPEC constant, which has supportsThinking:false because it is also spread into several Antigravity flash-tier aliases that reject client-supplied thinking params. That made the reasoning-routing policy resolve reasoning_effort as "unsupported" for the base Google AI Studio model, producing a spurious pre-provider HTTP 400 even though the model supports reasoning (it has an effort-tier alias gemini-3.5-flash-high). Set supportsThinking:true as an explicit override on the base gemini-3.5-flash entry only, leaving the shared spec and the Antigravity tier aliases unchanged. Closes #10286 Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Diego Rodrigues de Sa e Souza
|
5ca747f6a5 |
fix(sse): exclude search providers from credential-health scheduler sweep (#10435)
* fix(sse): exclude search providers from credential-health scheduler sweep The credential-health scheduler's sweep() tested every active connection every 5 minutes with no exclusion for search providers. For providers in SEARCH_VALIDATOR_CONFIGS (tavily-search, exa-search, serper-search, brave-search, google-pse-search, linkup-search, searchapi-search, youcom-search), "validation" fires a real billed upstream query (e.g. POST api.tavily.com/search), so the periodic sweep silently burned quota with no user-initiated search. Exclude connections whose provider id is registered in SEARCH_VALIDATOR_CONFIGS from the sweep's connection-selection filter. Non-search API-key/OAuth connections remain monitored (#9180, #9289 regressions verified green). Closes #9970 * fix(docs): drop backticks around SEARCH_VALIDATOR_CONFIGS in ENVIRONMENT.md The env/docs sync gate (check-env-doc-sync.mjs) treats any backtick-wrapped SHOUTY_NAME as an env var reference. SEARCH_VALIDATOR_CONFIGS is a code export, not an env var, so wrapping it in backticks made the #9970 doc note trip the env/docs contract check (docMissingEnv). Drop the backticks so the gate stops classifying it as an undocumented env var. --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
adevwithpurpose
|
be364d2c70 |
fix(release): align agent skills catalog tests
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
adevwithpurpose
|
810c6b9843 | fix(release): clear v3.8.50 base quality reds | ||
|
Diego Rodrigues de Sa e Souza
|
e646fe84c7 |
feat(dashboard): VS Code Copilot Chat home banner, remove Provider Quota home card (#10520)
* feat(dashboard): add VS Code Copilot Chat home banner, remove Provider Quota home card Announce the OmniCopilot extension right below the Kimi sponsor banner on the dashboard home page (same size/shape, dismissible, no version gate). Also removes the "pin Provider Quota to home" card and its now-dead settings toggle — the widget itself, its auto-refresh setting (shared with the standalone /dashboard/quota page), and its component tests are untouched. * fix(dashboard): remove now-dead homeWidgets.ts (dead-code gate) Deleting the AppearanceTab pin-to-home toggle left this file's sole export, PIN_PROVIDER_QUOTA_TO_HOME_KEY, with zero remaining consumers, which regressed the dead-code ratchet from 415 to 416. Removing the file restores the exact baseline count (415). --------- Co-authored-by: Xiangzhe <bakryun0718@proton.me> |
||
|
backryun
|
c6c134300b |
perf(electron): ship optional ML/browser deps as installable packs (#10382)
Stage 7 of issue #10321 moves the optional ML and browser automation dependency closures out of the desktop bundle into checksummed, versioned packs installed on demand through the omniroute packs command. - scripts/build/optionalPackStaging.mjs stages pack members under .build/optional-packs, creates release tarballs, and emits optional-packs.index.json with per-member SHA-256 checksums. - scripts/packs provides manifest, install, remove, and verification helpers plus the packs CLI commands. - Runtime lookup includes installed pack node_modules directories, while LLMLingua and browser executors continue to degrade gracefully when packs are absent. The measured darwin-arm64 staging closure was about 534 MB of the 929 MB standalone node_modules tree (57%). |
||
|
backryun
|
2162289f0a |
perf(electron): verify better-sqlite3 v13 Node-API prebuilds instead of source rebuild (#10367)
better-sqlite3 v13 ships Node-API prebuilds for every packaged platform (darwin/linux/linuxmusl/win32 x x64/arm64) inside the npm tarball, so the Electron-ABI node-gyp source rebuild in prepare-electron-standalone.mjs is obsolete. Replace it with a fail-fast prebuild verification that mirrors better-sqlite3 lib/binding.js selection, and strip build/deps/src so the packaged loader can only resolve the prebuild. Verified locally on darwin-arm64: the same darwin-arm64.node prebuild loads under both Node 24 (NODE_MODULE_VERSION 137) and Electron 43.3.0 under ELECTRON_RUN_AS_NODE (148); DB create/migrate/read/write/close/reopen pass in both runtimes and cross-runtime on each other's database files. Issue #10321 Stage 6. |
||
|
Brandon Bennett
|
6d9336088c |
fix(chat-body-admission): process-wide budget (#10110) (#10322)
* fix(chat-body-admission): process-wide budget (#10110) Remove per-session admission lanes that multiplied the documented "in one process" heavy/bytes bound by up to 64. All requests now admit against ONE process-global ChatAdmissionController so the bound holds against fake-credential sharding. Per-request session identity survives only as a fairness scheduling key: waiters are grouped per key and served round-robin (#9654) against the shared budget — one connection's burst cannot starve others. - src/shared/middleware/chatBodyAdmission.ts: delete lane map + LRU/TTL eviction; ChatAdmissionController is now the global budget with per-key FIFO queues + round-robin dispatchFair(). PerConnectionAdmissionController returns the same shared controller for every session. resolveSessionId stays as a scheduling key with honest re-scoping docs. snapshot() emits process-wide aggregates. - tests/unit/chat-body-admission-aggregate-10110.test.ts: new U6 suite — 6 deterministic tests (LRU-no-mint, TTL-no-mint, shared byte budget, 16 MiB config, same-session recreation, round-robin fairness). RED on release/v3.8.50, GREEN post-fix. - tests/unit/per-connection-admission-9654.test.ts: rewrite the tests that encoded the defect (per-session isolation) to assert the global-budget contract. - docs/reference/ENVIRONMENT.md: OMNIROUTE_CHAT_ADMISSION_MAX_QUEUED_BYTES documented as process-wide; VIRTUAL_TTL_MS/VIRTUAL_MAX_SESSIONS deprecated. * docs(changelog): add #10322 fragment for process-wide admission budget * ci: retrigger checks after transient npm ci network failure in shard 3/4 (ETIMEDOUT) --------- Co-authored-by: Brandon Bennett <brandonbennett@macbookair.myfiosgateway.com> |
||
|
Jan Leon
|
e5e1358693 |
fix(antigravity): discover live chat models dynamically (#10422)
* fix(antigravity): discover Gemini 3.7 Flash models * fix(antigravity): discover live chat models dynamically * fix(antigravity): keep provider limits sanitizer strict |
||
|
dependabot[bot]
|
8bd0e7b6bf |
deps: bump the production group across 1 directory with 21 updates (#10403)
Bumps the production group with 20 updates in the / directory: | Package | From | To | | --- | --- | --- | | [@aws-sdk/client-bedrock-runtime](https://github.com/aws/aws-sdk-js-v3/tree/HEAD/clients/client-bedrock-runtime) | `3.1096.0` | `3.1107.0` | | [@toon-format/toon](https://github.com/toon-format/toon) | `4.1.0` | `4.1.1` | | [axios](https://github.com/axios/axios) | `1.18.1` | `1.19.0` | | [cron-parser](https://github.com/harrisiirak/cron-parser) | `5.7.0` | `5.8.1` | | [csv-stringify](https://github.com/adaltas/node-csv/tree/HEAD/packages/csv-stringify) | `6.8.1` | `6.8.3` | | [fumadocs-core](https://github.com/fuma-nama/fumadocs) | `16.13.0` | `16.14.3` | | [fumadocs-ui](https://github.com/fuma-nama/fumadocs) | `16.13.0` | `16.14.3` | | [jose](https://github.com/panva/jose) | `6.2.4` | `6.2.8` | | [js-yaml](https://github.com/nodeca/js-yaml) | `5.2.2` | `5.2.3` | | [marked](https://github.com/markedjs/marked) | `18.0.7` | `18.0.9` | | [material-symbols](https://github.com/marella/material-symbols/tree/HEAD/material-symbols) | `0.45.9` | `0.45.10` | | [next](https://github.com/vercel/next.js) | `16.2.12` | `16.3.0` | | [next-intl](https://github.com/amannn/next-intl) | `4.13.4` | `4.13.6` | | [playwright](https://github.com/microsoft/playwright) | `1.61.1` | `1.62.1` | | [smol-toml](https://github.com/squirrelchat/smol-toml) | `1.7.1` | `1.7.2` | | [tsx](https://github.com/privatenumber/tsx) | `4.23.1` | `4.23.12` | | [turndown](https://github.com/mixmark-io/turndown) | `7.2.0` | `7.2.4` | | [ws](https://github.com/websockets/ws) | `8.21.1` | `8.21.3` | | [onnxruntime-node](https://github.com/Microsoft/onnxruntime) | `1.24.3` | `1.27.0` | | [wreq-js](https://github.com/sqdshguy/wreq-js) | `2.3.1` | `3.0.0` | Updates `@aws-sdk/client-bedrock-runtime` from 3.1096.0 to 3.1107.0 - [Release notes](https://github.com/aws/aws-sdk-js-v3/releases) - [Changelog](https://github.com/aws/aws-sdk-js-v3/blob/main/clients/client-bedrock-runtime/CHANGELOG.md) - [Commits](https://github.com/aws/aws-sdk-js-v3/commits/v3.1107.0/clients/client-bedrock-runtime) Updates `@toon-format/toon` from 4.1.0 to 4.1.1 - [Release notes](https://github.com/toon-format/toon/releases) - [Commits](https://github.com/toon-format/toon/compare/v4.1.0...v4.1.1) Updates `axios` from 1.18.1 to 1.19.0 - [Release notes](https://github.com/axios/axios/releases) - [Changelog](https://github.com/axios/axios/blob/v1.x/CHANGELOG.md) - [Commits](https://github.com/axios/axios/compare/v1.18.1...v1.19.0) Updates `cron-parser` from 5.7.0 to 5.8.1 - [Release notes](https://github.com/harrisiirak/cron-parser/releases) - [Changelog](https://github.com/harrisiirak/cron-parser/blob/master/CHANGELOG.md) - [Commits](https://github.com/harrisiirak/cron-parser/compare/v5.7.0...v5.8.1) Updates `csv-stringify` from 6.8.1 to 6.8.3 - [Changelog](https://github.com/adaltas/node-csv/blob/master/packages/csv-stringify/CHANGELOG.md) - [Commits](https://github.com/adaltas/node-csv/commits/csv-stringify@6.8.3/packages/csv-stringify) Updates `fumadocs-core` from 16.13.0 to 16.14.3 - [Release notes](https://github.com/fuma-nama/fumadocs/releases) - [Commits](https://github.com/fuma-nama/fumadocs/compare/fumadocs@16.13.0...fumadocs@16.14.3) Updates `fumadocs-ui` from 16.13.0 to 16.14.3 - [Release notes](https://github.com/fuma-nama/fumadocs/releases) - [Commits](https://github.com/fuma-nama/fumadocs/compare/fumadocs@16.13.0...fumadocs@16.14.3) Updates `jose` from 6.2.4 to 6.2.8 - [Release notes](https://github.com/panva/jose/releases) - [Changelog](https://github.com/panva/jose/blob/main/CHANGELOG.md) - [Commits](https://github.com/panva/jose/compare/v6.2.4...v6.2.8) Updates `js-yaml` from 5.2.2 to 5.2.3 - [Changelog](https://github.com/nodeca/js-yaml/blob/master/CHANGELOG.md) - [Commits](https://github.com/nodeca/js-yaml/compare/5.2.2...5.2.3) Updates `lucide-react` from 1.27.0 to 1.31.0 - [Release notes](https://github.com/lucide-icons/lucide/releases) - [Commits](https://github.com/lucide-icons/lucide/commits/1.31.0/packages/lucide-react) Updates `marked` from 18.0.7 to 18.0.9 - [Release notes](https://github.com/markedjs/marked/releases) - [Commits](https://github.com/markedjs/marked/compare/v18.0.7...v18.0.9) Updates `material-symbols` from 0.45.9 to 0.45.10 - [Release notes](https://github.com/marella/material-symbols/releases) - [Commits](https://github.com/marella/material-symbols/commits/v0.45.10/material-symbols) Updates `next` from 16.2.12 to 16.3.0 - [Release notes](https://github.com/vercel/next.js/releases) - [Commits](https://github.com/vercel/next.js/compare/v16.2.12...v16.3.0) Updates `next-intl` from 4.13.4 to 4.13.6 - [Release notes](https://github.com/amannn/next-intl/releases) - [Changelog](https://github.com/amannn/next-intl/blob/main/CHANGELOG.md) - [Commits](https://github.com/amannn/next-intl/compare/v4.13.4...v4.13.6) Updates `playwright` from 1.61.1 to 1.62.1 - [Release notes](https://github.com/microsoft/playwright/releases) - [Commits](https://github.com/microsoft/playwright/compare/v1.61.1...v1.62.1) Updates `smol-toml` from 1.7.1 to 1.7.2 - [Release notes](https://github.com/squirrelchat/smol-toml/releases) - [Commits](https://github.com/squirrelchat/smol-toml/compare/v1.7.1...v1.7.2) Updates `tsx` from 4.23.1 to 4.23.12 - [Release notes](https://github.com/privatenumber/tsx/releases) - [Changelog](https://github.com/privatenumber/tsx/blob/master/release.config.cjs) - [Commits](https://github.com/privatenumber/tsx/compare/v4.23.1...v4.23.12) Updates `turndown` from 7.2.0 to 7.2.4 - [Release notes](https://github.com/mixmark-io/turndown/releases) - [Commits](https://github.com/mixmark-io/turndown/compare/v7.2.0...v7.2.4) Updates `ws` from 8.21.1 to 8.21.3 - [Release notes](https://github.com/websockets/ws/releases) - [Commits](https://github.com/websockets/ws/compare/8.21.1...8.21.3) Updates `onnxruntime-node` from 1.24.3 to 1.27.0 - [Release notes](https://github.com/Microsoft/onnxruntime/releases) - [Changelog](https://github.com/microsoft/onnxruntime/blob/main/docs/ReleaseNotesWorkflow.md) - [Commits](https://github.com/Microsoft/onnxruntime/compare/v1.24.3...v1.27.0) Updates `wreq-js` from 2.3.1 to 3.0.0 - [Release notes](https://github.com/sqdshguy/wreq-js/releases) - [Commits](https://github.com/sqdshguy/wreq-js/compare/v2.3.1...v3.0.0) --- updated-dependencies: - dependency-name: "@aws-sdk/client-bedrock-runtime" dependency-version: 3.1107.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: "@toon-format/toon" dependency-version: 4.1.1 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: axios dependency-version: 1.19.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: cron-parser dependency-version: 5.8.1 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: csv-stringify dependency-version: 6.8.3 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: fumadocs-core dependency-version: 16.14.3 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: fumadocs-ui dependency-version: 16.14.3 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: jose dependency-version: 6.2.8 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: js-yaml dependency-version: 5.2.3 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: lucide-react dependency-version: 1.31.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: marked dependency-version: 18.0.9 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: material-symbols dependency-version: 0.45.10 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: next dependency-version: 16.3.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: next-intl dependency-version: 4.13.6 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: playwright dependency-version: 1.62.1 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: smol-toml dependency-version: 1.7.2 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: tsx dependency-version: 4.23.12 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: turndown dependency-version: 7.2.4 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: ws dependency-version: 8.21.3 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: production - dependency-name: onnxruntime-node dependency-version: 1.27.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: production - dependency-name: wreq-js dependency-version: 3.0.0 dependency-type: direct:production update-type: version-update:semver-major dependency-group: production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
backryun
|
6b85413b87 |
perf(electron): build the Next standalone once and hydrate natives per leg (#10321 stage 8) (#10390)
The desktop release matrix ran the full Next.js standalone build on all four legs (windows, macos-intel, macos-arm64, linux), duplicating the platform-neutral majority of that work four times and re-exposing every leg to the hosted-runner RAM class of failure that took the linux leg out of v3.8.49. - scripts/build/standaloneTarball.mjs: deterministic, dependency-free tar.gz writer/reader (uid/gid/mtime pinned, sorted entries, symlink + exec-bit preservation; GNU-tar interop covered by tests). - scripts/build/standaloneManifest.mjs: byte-level manifest of .build/next (sha256 + size + symlink target per entry, plus the archive's own digest) catching artifact-transfer corruption before extraction and re-verifying the restored tree byte-for-byte, smuggling included. - scripts/build/standaloneBundle.mjs: pack / restore / hydrate CLI over the two modules above. - scripts/build/hydrateNativeDeps.mjs: swaps install-machine-forked native optionals (@img/sharp-*, @ngrok/ngrok-*, fsevents) from the leg's own npm ci into the restored tree, then verifies the bundled-native closure (koffi triplets, better-sqlite3 prebuilds, wreq-js, onnxruntime with its documented darwin-x64 exemption) services the leg's platform/arch before packaging starts. - .github/workflows/electron-release.yml: new web-build job builds the standalone once on ubuntu with webpack and uploads the bundle; legs download, restore, and hydrate it, skipping the per-leg build. The legacy per-leg build remains as a rollback path via the ELECTRON_SHARED_STANDALONE workflow_dispatch input, and legs fail closed if web-build ran and failed. Regression tests cover archive roundtrip, byte determinism, manifest tamper/smuggle detection, forked-native swaps, and native-closure serviceability. |
||
|
Diego Rodrigues de Sa e Souza
|
e1739fc71d |
fix(security): sanitize test regex and annotate CodeQL hash false-positives (#10380)
* fix(security): sanitize test regex and annotate CodeQL hash false-positives tests/unit/early-sse-route-intent.test.ts built a RegExp from a hardcoded string but only escaped `?`/`.`, missing `\` — js/incomplete-sanitization (#816). Not exploitable (fixed literal input) but the escaping was genuinely incomplete; now escapes backslash too. reasoningCache.ts::buildAssistantMessageCacheKey and codexIdentity.ts's two UUID derivation helpers hash a cache-scope/account-seed with SHA-256 to produce a lookup key / deterministic ID — not a stored, verified password. CodeQL's js/insufficient-password-hash overfires on any hash of a secret-like variable, the same false-positive class already annotated at src/lib/db/apiKeys.ts:624. Added matching lgtm/nosemgrep annotations and inline rationale so the intent is clear to reviewers and future scans. Refs #815 #816 #817 #818 * fix(security): keep only the regex sanitization; drop non-functional CodeQL annotations The lgtm[]/nosemgrep: comments in codexIdentity.ts and reasoningCache.ts use formats GitHub Actions CodeQL does not honor, and shifting those sha256 lines re-attributed the already-dismissed base alerts to this PR as two new CodeQL findings. Revert those two annotation-only files to base so the existing dismissals apply; retain the real fix (escaping backslash in the test regex), which resolves the open js/incomplete-sanitization alert. --------- Co-authored-by: Xiangzhe <bakryun0718@proton.me> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Ravi Tharuma
|
4c7b902257 |
fix(ops): Docker HEALTHCHECK probes /healthz not deep monitoring (#10307)
* fix(deps): bump nanoid, dompurify for 2 new Dependabot alerts (#189, #190) Bumps: nanoid ^3.3.17 (was transitive, now overridden), dompurify ^3.4.13 (with monaco-editor scoped override). Closes Dependabot #189, #190. Remaining #182-#188 (js-yaml + mermaid) already closed by #9651 merge — awaiting Dependabot re-scan. npm audit → 0 vulnerabilities. * fix(repo): harden .gitignore to also ignore a _tasks symlink (/_tasks) _tasks is a SEPARATE nested git repo (gitignored). The pattern _tasks/ (trailing slash) ignores only a directory, not a SYMLINK named _tasks. A self-referential _tasks symlink can slip in via git add -A and, once pulled, checkout materializes it over the real _tasks repo (destroying plans/specs/hands-off). Anchored /_tasks ignores the symlink too, preventing re-capture. * Hide health-check excluded models from /v1/models catalog (#10026) Mirror the request-time exclusion rule (provider_specific_data.excludedModels) in the unified catalog builder: a model is hidden when its provider has connections but none of them is eligible for it. Applied across the PROVIDER_MODELS, synced, custom, alias-backed, and managed-fallback loops so ghost models no longer appear as available. Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> * fix(models): memoize getModelsDevPricing (event loop / healthz) (#10055) * fix(models): memoize getModelsDevPricing for /v1/models catalog resolveCatalogPricing called getModelsDevPricing once per model while building GET /v1/models. Each call re-scanned models_dev_pricing and JSON.parsed every row (~10k SQL scans + multi-GB parse work), pegging the event loop so even /healthz timed out (#9685, #10052). Memoize the parsed map until saveModelsDevPricing / clearModelsDevPricing and add a unit test for invalidation. Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> * fix(db): invalidate modelsDevPricing cache on DB reset (#10055) Copilot review fixes: 1. Register invalidateModelsDevPricingCache() with DB state reset system so resetDbInstance() clears the process-local memo, preventing stale pricing data from surviving across DB reset/restore operations. 2. Add test assertion verifying DB reset bypasses the memo (Copilot #10055). The process-local memo at modelsDevSync.ts:204 caches getModelsDevPricing() results until saveModelsDevPricing()/clearModelsDevPricing() to avoid re-scanning all pricing rows on every /v1/models request. Without this hook, backup restore and test DB resets would serve stale cached data from the previous connection. Tests: npm run test:unit:serial -- tests/unit/modelsDevSync-extended.test.ts --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> * fix(ops): Docker HEALTHCHECK probes /healthz not deep monitoring /api/monitoring/health does a SQLite ping and more. When the event loop is busy the official image HEALTHCHECK (5s timeout) marks the container Unhealthy and orchestrators restart the only replica mid-session. * fix(ops): keep healthcheck PR scoped to the /healthz probe Drop the stray catalog ghost-model exclusion that leaked into this branch from main (already covered upstream). Restore catalog.ts to the release version so the PR contains only the Docker HEALTHCHECK /healthz fix, its tests, and the changelog entry. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Signed-off-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> Co-authored-by: ritheshcn25 <rithesh.chandran@snb.ca> Co-authored-by: ritheshcn25 <ritheshcn25@users.noreply.github.com> Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> |
||
|
Ravi Tharuma
|
326d0e81cb |
docs(ops): k8s probe recommendations (TCP liveness, HTTP /healthz readiness) (#10297)
* docs(ops): recommend TCP liveness and HTTP /healthz readiness for k8s Stock Docker HEALTHCHECK hits /api/monitoring/health (deep). Orchestrators should not use that path for kubelet liveness. Document /healthz vs deep health, note same-process event-loop limits, and link related issues. * docs: add changelog fragment for #10297 --------- Co-authored-by: Ravi Tharuma <RaviTharuma@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Paco Cartones
|
d010a9979f |
fix(providers): repoint freeaiapikey to its live API host and resync its catalog (#10233)
* fix(providers): point freeaiapikey at the api. host it moved to Every /v1 route on the freeaiapikey.com apex host answers HTTP 410 with type "endpoint_moved", and the body names its own replacement: "This API endpoint has moved. Please update your base_url to https://api.freeaiapikey.com/v1 - the old endpoint on freeaiapikey.com no longer works." Probed 2026-08-13 with paired controls so a network fault could not be read as an upstream verdict: GET https://freeaiapikey.com/v1/models -> 410 GET https://freeaiapikey.com/v1/chat/completions -> 410 GET https://api.freeaiapikey.com/v1/models -> 200 GET https://api.freeaiapikey.com/v1/chat/completions -> 405 (POST-only) GET https://api.openai.com/v1/models -> 401 (control: reachable) GET https://<nonexistent-domain>/v1/models -> 000 (control: unreachable) Every request through this provider therefore fails today. Repoint baseUrl and modelsUrl at the host upstream names. * fix(providers): resync the freeaiapikey catalog with its live model list GET https://api.freeaiapikey.com/v1/models (200, probed 2026-08-13) serves 10 models. The registry declared 7, four of which upstream does not serve at all: openai/gpt-5, openai/gpt-5.2-codex, Alibaba/qwen3.5, Alibaba/qwen3-vl:235b. Seven live models were missing: openai/gpt-5.4, openai/gpt-5.5, openai/gpt-5.6-sol, anthropic/claude-opus-4.7, anthropic/claude-opus-4.8, anthropic/claude-sonnet-5, anthropic/claude-opus-5. The four phantom ids are selectable in the dashboard and can only ever fail upstream; the seven real ones are unreachable through the static catalog. On context windows: the /v1/models response carries only id/object/created/ owned_by, so upstream publishes no window at all. The models added here therefore declare no contextLength and inherit the entry's existing defaultContextLength (128000) instead of a fabricated number. The two pre-existing contextLength values are left untouched for the same reason - this sweep neither confirms nor refutes them, and rewriting them would be guesswork in the other direction. * chore(changelog): name the fragment after the real PR number * chore(changelog): substitute the PRNUM placeholder in the fragment body --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
Chewji
|
be6f18b849 |
fix(account-fallback): classify 'insufficient credits' as credits-exhausted (#10116)
* fix(account-fallback): classify 'insufficient credits' as credits-exhausted Command Code returns 400 'You have insufficient credits to make this request...' when an account's billing credits run out. The phrase was missing from CREDITS_EXHAUSTED_SIGNALS, so the error stayed unclassified (errorType=null) and the connection was never marked credits_exhausted — getProviderCredentials kept re-selecting the same dead account on every request instead of rotating to a healthy one. Add 'insufficient credits'/'insufficient credit' to the signal list (already used by antigravity429Engine.ts) so the error classifies as QUOTA_EXHAUSTED and the account is skipped on subsequent selections. * fix(account-fallback): harden insufficient-credit matching and preserve chatanywhere Add the common 'insufficient credit balance' variation to CREDITS_EXHAUSTED_SIGNALS alongside the Command Code 'insufficient credits'/'insufficient credit' signals, and restore the consolidated ChatAnywhere gateway entry that the stale snapshot removal would have deleted when merging into release/v3.8.50. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> |
||
|
SB Yoon
|
d46e8d72c9 |
feat(cli): refuse ephemeral container auto-config writes (#10057)
* feat(cli): refuse ephemeral container auto-config writes Detect containerized OmniRoute and block CLI/API config writes into throwaway homes unless a bind mount or explicit opt-in is present, and honor compose host-profile CLI_CONFIG_HOME mounts outside the container home. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(changelog): name fragment for #10057 Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: yansigit <yansigit@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
Alex
|
20fcb8d205 |
fix(affinity): evict the sticky session pin on a combo per-model timeout (#10016)
A combo target that stalls past comboTargetTimeoutMs is aborted by buildTargetTimeoutRunner, which swallows the resulting rejection behind its synthetic 524. Nothing marks the account unavailable — correctly, since a stall is not a quota/auth failure — so the #6219 eviction on the generic markAccountUnavailable -> shouldFallback path in chat.ts never ran. The session pin therefore survived its full TTL and every following request in that session was handed straight back to the account that had just stalled. Seen in production on combo "coding" [priority]: one codex account pinned for a 30-minute TTL, four consecutive requests, four 120s timeouts, "all targets exhausted" each time, while four sibling codex accounts stayed healthy and unused. Classify the abort reason (new dependency-free leaf comboAbortReasons.ts) and evict the connection-matched pin. Only a genuine per-model timeout evicts: a client disconnect or a hedge cancellation says nothing about account health, so those keep the pin and its prompt-cache locality. Eviction is best-effort and never breaks the dispatch path. The dispatch itself moves into a new seam, chatDispatch.ts, which merges the per-model abort signal into the outgoing request, runs executeChatWithBreaker, and owns the eviction on both the rejection and failed-result paths. Keeping that logic out of the frozen god-file leaves chat.ts one line SHORTER than before (1844 -> 1843). Co-authored-by: alexey.nazarov@softmg.ru <alexey.nazarov@softmg.ru> Co-authored-by: fenix007 <fenix007@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> |
||
|
SHANMUGAPRIYAN
|
579cae32b1 |
fix(sse): buffer '<think' partial so a split open tag cannot leak into content (#10441)
containsOrMayEndWithThinkOpenTag missed the 6-char partial '<think', so an open tag arriving as '<think' + '>' across SSE deltas leaked into content instead of being parsed as reasoning. Derive every proper prefix from THINK_OPEN itself so the lookahead list can never drift out of sync with the tag again. Covered by new unit tests for the partial-suffix lookahead and the split-delta buffering path. |
||
|
Rouzbeh†
|
df226e55f4 |
fix(usage): read Gemini usageMetadata out of the antigravity response envelope (#10430)
* fix(usage): read Gemini usageMetadata out of the antigravity response envelope
Port decolua/9router#59d858b: antigravity/gemini-cli wrap non-streaming
payloads in { response: {...} }, so extractUsageFromResponse only saw the
top-level usageMetadata and every non-streaming antigravity request logged
zero usage (IN 0 | OUT 0) and zeroed usage-dashboard rows. Top-level
metadata keeps priority; OpenAI/Claude branches untouched.
* chore(changelog): fragment for #10430 antigravity usage envelope
* ci: re-run dast-smoke (Build CLI bundle runner timeout flake)
---------
Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com>
|
||
|
Rouzbeh†
|
e44a409aa9 |
fix(antigravity): classify geo-blocked egress, exclude account, real connection probe (#10420)
* fix(antigravity): classify geo-blocked egress, exclude account, real connection probe Google refuses the Cloud Code model API from unsupported egress locations with 400 FAILED_PRECONDITION "User location is not supported for the API use." Previously this surfaced as a cryptic "Antigravity upstream error (400)", never excluded the account, and the dashboard connection test stayed green because it only probed the (non-geo-restricted) OAuth userinfo endpoint. - errorClassifier: new GEO_BLOCKED type + isGeoBlockedError detection (400/403 + location-not-supported wording); non-terminal classification. - chatCore fallback: GEO_BLOCKED marks the connection and caches a 24h rate-limit-until exclusion so routing moves to other accounts instead of re-selecting the same one; never bans/expires the account. - auth: GEO_BLOCKED joins the non-terminal group (no banned/expired state). - antigravityUpstreamError: geo refusals carry an actionable message (egress location vs account problem, proxy-in-supported-region guidance). - connection test: antigravity/agy now probe the REAL streamGenerateContent surface (buildProbe), so a green tick means the model path actually works and a geo-blocked egress shows red with a clear diagnosis. * chore(changelog): fragment for #10420 antigravity geo-block resilience * chore(pr): drop prettier-version drift noise, keep only real hunks The earlier format pass (local prettier differs from the repo's pinned version) rewrapped unrelated lines in chatCore.ts and the provider test route. Restore the base formatting and re-apply only the GEO_BLOCKED fallback branch and the buildProbe connection-test changes. * fix(antigravity): strip competing-agent system prompts (429 RESOURCE_EXHAUSTED) Port decolua/9router b566b20, generalized: Antigravity flags system prompts advertising competing agents ('You are a Claude agent, built on Anthropic's Claude Agent SDK.' — Zed, Claude Code, etc.) and answers with a 429 quota error. sanitizeAntigravityGeminiRequest now strips known competitor identity sentences from systemInstruction.parts before dispatch; surrounding instruction text is untouched and non-matching prompts pass through without allocation. * chore(changelog): cover competitive prompt strip in #10420 fragment * fix(antigravity): scope GEO_BLOCKED classification to Google AI surfaces Address reviewer feedback: classifyProviderError is shared across every provider, so a lookalike 'not available in your region' body from an unrelated upstream must not receive the egress-fixable 24h exclusion treatment. Gate GEO_BLOCKED behind isGeoBlockEligibleProvider, which matches the surfaces that actually emit Google's regional-availability refusal: Cloud Code / Gemini Code Assist (antigravity, agy, cloudcode*), the Gemini Developer API (gemini, gemini-cli, vertex), plus a registry-driven fallback on executor/format. Non-Google providers fall through to their existing 400/403 classification (typically null for an unclassified 400), so a permanent block still follows its own path. * ci: re-run quality gates Trigger a fresh CI run for the PR: the previous run's 'Vitest (fast-path)' job failed in 'npm ci' because the onnxruntime-node postinstall could not download its binary from the Microsoft CDN (connect ETIMEDOUT 150.171.109.118:443). No tests ran; no code changed in this commit. * fix(antigravity): guard provider before registry lookup in geo-block gate isGeoBlockEligibleProvider passes the raw provider (string | null | undefined) to getRegistryEntry(provider: string), failing typecheck:core and the ts7-diagnostics ratchet (TS2345 at errorClassifier.ts:166). Add an explicit null guard; runtime behavior is unchanged — a falsy provider already resolved to !entry -> false. * ci: re-run quality gates (vitest npm ci onnxruntime CDN flake) --------- Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com> |
||
|
Rouzbeh†
|
b75f7dde93 |
fix(guardrails): reroute zero-vision combos through the vision bridge (#10415)
* fix(guardrails): reroute zero-vision combos through the vision bridge Named combos whose model targets all lack vision support are never reroute-eligible: the bridge only attempts the describe path, and when describing cannot run or fails the raw images stay in the payload and the request dies in the combo capability filter with capability_mismatch. getComboVisionBridgeDecision now returns a "no-vision" verdict for combos with zero vision-capable targets, and preCall treats it as reroute-eligible with the same credential guards as single text-only models, falling back to describe only when no usable reroute target exists. * chore(changelog): fragment for #10415 vision bridge combo reroute * fix(guardrails): extend allNull stub fallback to no-vision combos Reviewer follow-up (#10415): the allNull stub-text fallback at the end of preCall only fired for comboVisionBridgeDecision === 'process'. In the compound-failure case for a zero-vision combo — reroute target without usable credentials AND every describe call failing — raw images were preserved and the original capability_mismatch recurred, because a no-vision combo has no target that can consume images. Include 'no-vision' in the guard: stub text is strictly better than raw bytes no combo target can consume. Adds a double-failure unit test. * ci: re-run dast-smoke (Build CLI bundle runner timeout flake) * fix(build): bound and retry the opencode-plugin npm install in prepublish The plugin's node_modules is gitignored, so every fresh CI checkout runs a full npm install inside @omniroute/opencode-plugin during build:cli. npm's unbounded fetch retries turn a stalled registry CDN connection (the recurring onnxruntime-class ETIMEDOUT flake) into a 20-30 minute hang — the DAST 'Build CLI bundle' step has been cancelled at the 30m cap repeatedly. - Bound npm fetch: --fetch-timeout 60s, 2 retries with capped backoff — a stalled connection now fails fast instead of hanging the job. - Retry the install up to 3 times with a 10s pause between attempts, so transient CDN failures recover in-build. Net effect: the step either completes (network OK) or fails quickly with a clear error (network down) — it can no longer eat the whole job budget. * ci(dast): use existing npm-ci-retry action instead of bare npm ci dast-smoke died at 'Run npm ci' with connect ETIMEDOUT to the onnxruntime-node binary CDN (Microsoft 150.171.x.x) — the same transient CDN flake class that has hit Vitest/Quality Gates before. quality.yml already wraps npm ci in ./.github/actions/npm-ci-retry (3 attempts, exponential backoff); dast-smoke was the one workflow still using a bare install. Use the existing action for consistency. * ci(quality): use the npm-ci-retry action on every install step Fast Quality Gates failed on the recurring onnxruntime-node postinstall ETIMEDOUT (Microsoft CDN 150.171.x.x) - the same transient flake that has hit Vitest and dast-smoke today. Only the Build job used the retry action; the other five jobs (Docs, Fast Quality Gates, Vitest, Unit Tests, changelog) still ran a bare install and die on any CDN hiccup. Use the existing retry action (3 attempts, exponential backoff) on every install step for consistency. --------- Co-authored-by: Rouzbeh <rqzbeh@users.noreply.github.com> |
||
|
dependabot[bot]
|
3c8432791e |
chore(deps): bump github/codeql-action/init from 4.37.4 to 4.37.6 (#10407)
Bumps [github/codeql-action/init](https://github.com/github/codeql-action) from 4.37.4 to 4.37.6.
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](
|
||
|
dependabot[bot]
|
142bd5019f |
chore(deps): bump github/codeql-action/analyze from 4.37.4 to 4.37.6 (#10406)
Bumps [github/codeql-action/analyze](https://github.com/github/codeql-action) from 4.37.4 to 4.37.6.
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](
|