Commit Graph

3345 Commits

Author SHA1 Message Date
Paco Cartones
376b49d8a5 fix(ratelimit): keep operator minTime floor when relaxing on headroom (#9763) (#11086)
Validated on the combined batch board over tip c92bd40b: static gates clean (changelog, file-size 158 frozen, complexity 2626<=2774, cognitive 1183<=1223, dead-code 409<=416), typecheck:core clean, 70 focused tests green (PR suites 49/49 + auth/combo neighbors 21/21).

Operator-configured positive minTime floor now survives the plenty-of-headroom relaxation (resolveMinTime instead of a hard 0). Fixes #9763. Thank you @pacocartones!
2026-08-23 01:24:16 -03:00
Rouzbeh†
c92bd40b88 perf(proxy): implement non-blocking async proxy log batching and performance optimizations (A, B, C, D) (#11182)
Validated on the combined batch board + this branch: perf-a-b-c-d + account-fallback-service 93/93, gates + typecheck clean. Owner approved the full bundle including item A (async proxy-log batching, 1s/100-item flush with an unref'd timer — reviewed the implementation: flush helper exists for shutdown wiring, buffered logs are the accepted tradeoff). B (lazy modals), C (O(1) alias maps), D (pre-compiled regex — this is also the entire content of #11187, being closed as subsumed) ride along. Conflict with the tip was only stale provider-count docs. Thank you @rqzbeh!
2026-08-23 01:07:32 -03:00
Rouzbeh†
8fa3e314c8 fix(sse): unpin static Antigravity sessionId and add DNS retry classification (#10443) (#11177)
Validated on the combined batch board + this branch: antigravity-dynamic-session-id + proxy-fetch-dns-retry green; file-size gate green with the proxyFetch 1244 frozen entry (dated annotation for the +5 retry-classification lines, owner-authorized). Static per-account sessionId unpinning ends the concurrent-turn 429s and EmptyStreamError drops on the Hermes→Antigravity path; EAI_AGAIN/ENOTFOUND/ETIMEDOUT now classified retryable. Conflict with the tip was only stale provider-count docs. Resolves the remaining #10443 root causes. Thank you @rqzbeh!
2026-08-23 01:05:08 -03:00
Rouzbeh†
47147e0bcd fix(auth): replace router.push with window.location navigation after login (#11143) (#11175)
Validated on the combined batch board + this branch: login-11143 green. Full document navigation after login guarantees the auth_token cookie is committed before any RSC prefetch fires — no more 307 back to /login. Conflict with the tip was only stale provider-count docs. Fixes #11143. Thank you @rqzbeh!
2026-08-23 01:03:40 -03:00
Rouzbeh†
b25b2eacb3 refactor(dashboard): format custom provider quota keys into title-cased labels (#11188)
Validated on the combined batch board + this branch: dashboard-ux-operability green. Unmapped custom quota keys now render as title-cased labels instead of raw snake_case. Conflict with the tip was only stale provider-count docs. Thank you @rqzbeh!
2026-08-23 01:01:11 -03:00
Rouzbeh†
f131b64a6e fix(security): add test coverage for Tier 1 local-only route guard process-spawning endpoints (#11189)
Validated on the combined batch board (gates + typecheck clean) and this branch: security-route-guard-tiers green. Regression coverage for the Hard Rule #15/#17 contract — Tier 1 process-spawning prefixes (/api/services/, /api/mcp/, /api/cli-tools/runtime/) must stay LOCAL_ONLY before any auth check. Conflict with the tip was only stale provider-count docs. Thank you @rqzbeh!
2026-08-23 01:00:14 -03:00
backryun
79c5bdf681 fix(release): repair v3.8.50 base-red tail after latest root lift (#10964)
Merged after conflict triage: the six base-red repair files (vi.json, opencode.ts JSDoc, context-manager test, the three webhook dispatcher tests, the uncloseai orphan-test rename) were already drained on the tip by today's #11130/#11157/#11160/#11113 — those hunks resolved to the tip shape. What lands is the production-fix set: GLM transport-aware Anthropic headers, Claude Code-compatible model-listing rejection, combo live-test single-probe, zero-cost Auto-Combo interval normalization, recovery-clearing union handling, LLMLingua real-path compare, macOS netstat PID discovery, AI Horde R2 strict public-host validation. Sweep of every touched test file: 243/243 green; typecheck + file-size clean. (guide-settings-route's 4 reds reproduce on the pure tip — pre-existing drift from #11079, not from here.) Thank you @backryun!
2026-08-22 23:09:16 -03:00
Webman
2dd20331a7 feat(providers): add Logfare as a free OpenAI-compatible provider (#10644) (#10987)
Merged after count reconciliation: the branch's regenerated docs claimed 57 free forever / 157 migrations from its older base; gate-verified values on the current tip are 56 free forever (Logfare carries a Free badge via gateways.ts freeNote but has no freeModelCatalog per-model entries, so the live-code counter stays at 56) and 159 migrations — the README/SVGs now match the check:docs-counts output exactly. provider-consistency OK at 267 registry / 349 canonical. logfare-registry 4/4, icon + KNOWN_PNGS + discovery-set membership all verified present. Closes #10644. Thank you @jonlwheat2-gif!
2026-08-22 23:01:04 -03:00
Ke Jin
9689dcef9f fix(reasoning): preserve mixed plaintext and drop incompatible state (#10949, #10959) (#10961)
Validated on the combined batch board + this branch: 231/231 across chatcore-translation-paths, reasoning-cache, strip-reasoning-blobs, and both Responses translator suites. Pre-merge: propagated the #11110/#11129 summary:[] defaults into five assertions here (each commented with its PR) — without it this branch red against the tip, and as a bonus the merge drains the 4 reasoning reds that were live on the tip from those merges. Plaintext now wins over a coexisting opaque companion; opaque-only drops cleanly for plaintext targets; combos keep explicit Skip. Fixes #10949 and #10959. Thank you @jackjinke!
2026-08-22 22:58:58 -03:00
Xiangzhe
c018bb41a7 fix(catalog): declare GLM reasoning effort tiers (#10963)
Merged after conflict resolution in modelMetadataRegistry.ts: the tip's effortTiers chain (declared efforts → declared tiers → undefined-if-thinking-declared → codex extension) now carries this PR's GLM guard as the final-fallback override — GLM-family models without a provider-declared contract get the authoritative empty tier list instead of generic OpenAI tiers. GLM/ZCode suites 40/40 on the resolved branch. Closes #10962. Thank you @xz-dev!
2026-08-22 22:54:49 -03:00
Bob.Hou
e52d2db449 fix(compression): CCR must not strand prompts for callers without the retrieve tool (#11084)
Validated on the combined batch board + this branch: ccr-non-mcp-full-prompt-loss + ccr-retrieval-ramp 20/20, file-size gate green with the ccr/index listing (1024, dated annotation — owner-authorized). The callerSupportsCcrRetrieve gate now skips the whole engine for callers whose tools[] cannot reach omniroute_ccr_retrieve — no more 15KB prompt arriving upstream as 112 tokens. Production-measured root cause, textbook TDD. Thank you @HouMinXi!
2026-08-22 22:53:26 -03:00
Ravi Tharuma
230017196c fix(resilience): drain heavyweight SSE on SIGTERM (#11020)
Validated on the combined batch board + this branch alone: chat-body-admission + authz/pipeline 65/65, file-size gate green with a dated frozen entry (chatBodyAdmission 1005→1009 — the +4 lease/drain wiring lines, owner-authorized rebaseline). trackRequest was never called, so SIGTERM waitForDrain saw zero in-flight and killed live SSE; leases now hold the drain counter for the stream's lifetime, and the 503 carries Retry-After. Closes #11015. Thank you @RaviTharuma!
2026-08-22 22:51:02 -03:00
Ke Jin
e73ab0040c fix(codex): make remote compaction V2 complete reliably (#11041)
Compaction-V2 output now counts as real model output (no synthetic response.failed after response.completed), the Codex SSE filter handles CRLF framing, and terminal detection runs before scan-state bounding. 88/88 stream/readiness suites on the board. Thank you @jackjinke!
2026-08-22 22:49:11 -03:00
amrx
d888f1a08b fix(combo): accept SSE comment lines (e.g. OpenRouter keep-alives) in response quality validation (#11036)
SSE comment lines (OpenRouter keep-alives) and leading whitespace no longer fail the combo quality gate's JSON fallback. First contribution — clean minimal fix with test. Thank you @asorourx, welcome aboard!
2026-08-22 22:49:08 -03:00
Diego Rodrigues de Sa e Souza
eb5797370a feat(dashboard): add CheaperInference sponsor banner and route banner links through the shortener (#11196)
- New CheaperInferenceSponsorBanner on the dashboard home, same size/shape as
  KimiSponsorBanner, no version gate (durable partnership). Uses the
  cheaperinference ProviderIcon and the brand green (#31f889) with the dark
  ink CTA (contrast, per colors.ts token).
- CTA points at https://link.omniroute.online/cheaper — the branded short
  link — so clicks land in our Kutt metrics.
- VscodeCopilotBanner CTA now points at https://link.omniroute.online/vsx
  instead of the raw Marketplace URL, for the same reason.
- i18n strings in en + pt (en is the namespace-level fallback for the other
  41 locales).
- Tests: new cheaperInferenceSponsorBanner.test.tsx (render, CTA href, dismiss
  persistence); vscodeCopilotBanner.test.tsx updated to the new CTA URL.

Co-authored-by: Xiangzhe <bakryun0718@proton.me>
2026-08-22 22:46:34 -03:00
Diego Rodrigues de Sa e Souza
3ef54fc55b feat(api): return every connection's snapshot under providers[] in om-usage json (#11192)
* feat(api): structured ?format=json for the self-service usage endpoint

GET /api/usage/om-usage already let any key read its own usage — personal
daily/weekly USD limits and the provider quota snapshot — but only as
text/plain, which a UI cannot parse safely. OmniCopilot issue #8 asks exactly
for this surface.

Adds ?format=json, returning the ApiKeyUsageLimitStatus + UsageSnapshot the
text is rendered from. Text and JSON share the same collectors
(collectUsageSnapshots, getApiKeyUsageLimitStatus), so the two can never
disagree about a number. The response is a discriminated union: a key without
allowUsageCommand (403) or an invalid key (401) returns
{ allowed:false, error:{message} }, distinct from allowed:true with empty
sections — the state a panel must render as "nothing learned yet", not a
refusal. Text form unchanged; without ?format the contract is untouched.

The endpoint was previously missing from API_REFERENCE.md; it now has a
section documenting both forms, the allowUsageCommand gate, and the
self-service auth model (caller's own key, not requireManagementAuth).

Regression guards in tests/unit/usage-command-json-format.test.ts (4 tests:
json shape, text default preserved, structured 403, sanitized 401 with no
stack trace). Existing internal-usage-command suite still 12/12.

* chore(changelog): correct the fragment to the real PR number (#11190)

* feat(api): return every connection's snapshot under providers[] in om-usage json

Closes #11191. buildUsageCommandJson picked a single snapshot via selectUsageSnapshot, so a panel could only ever show one provider. The collector already had them all — the single-pick is a presentation choice for a terminal. The JSON form now also returns the full UsageSnapshot[] alongside the selected provider, so a UI can render Codex / Claude / OpenCode side by side. The text form is untouched.

---------

Co-authored-by: Xiangzhe <bakryun0718@proton.me>
2026-08-22 22:39:56 -03:00
Diego Rodrigues de Sa e Souza
eb9fa33ee7 feat(api): structured ?format=json for the self-service usage endpoint (#11190)
* feat(api): structured ?format=json for the self-service usage endpoint

GET /api/usage/om-usage already let any key read its own usage — personal
daily/weekly USD limits and the provider quota snapshot — but only as
text/plain, which a UI cannot parse safely. OmniCopilot issue #8 asks exactly
for this surface.

Adds ?format=json, returning the ApiKeyUsageLimitStatus + UsageSnapshot the
text is rendered from. Text and JSON share the same collectors
(collectUsageSnapshots, getApiKeyUsageLimitStatus), so the two can never
disagree about a number. The response is a discriminated union: a key without
allowUsageCommand (403) or an invalid key (401) returns
{ allowed:false, error:{message} }, distinct from allowed:true with empty
sections — the state a panel must render as "nothing learned yet", not a
refusal. Text form unchanged; without ?format the contract is untouched.

The endpoint was previously missing from API_REFERENCE.md; it now has a
section documenting both forms, the allowUsageCommand gate, and the
self-service auth model (caller's own key, not requireManagementAuth).

Regression guards in tests/unit/usage-command-json-format.test.ts (4 tests:
json shape, text default preserved, structured 403, sanitized 401 with no
stack trace). Existing internal-usage-command suite still 12/12.

* chore(changelog): correct the fragment to the real PR number (#11190)

---------

Co-authored-by: Xiangzhe <bakryun0718@proton.me>
2026-08-22 22:23:17 -03:00
Dizzle
62ab93d789 fix(sse): reject a low-overlap stream-recovery continuation instead of concatenating it raw (#11152)
Merged after sibling #11151 landed: streamRecovery.ts auto-merged byte-identical to the validated combined board; the test-file conflict (both PRs added suites at the same anchor) resolved keeping all 11 tests — #11151's four clean-stop cases plus this PR's three threshold cases, with the PR's updated partial-tail fixture for the pre-existing overlap test. Full chain green: 32/32 (wiring + continuation + toolcall regression). The documented 8-char overlap threshold ends the silent mid-word gluing. Thank you @maxmad64bis!
2026-08-22 21:56:26 -03:00
Dizzle
80b8d2a8a2 fix(sse): resume stream recovery after a clean stop with reasoning-only output (#11151)
Merged after conflict resolution against the tip's #11109 (per-call tool_call tracking): scanOpenAiSseText keeps the per-call finish_reason special-case AND gains reasoningText + literal finishReason; canContinue uses the in-flight predicate with the new reasoning-only-clean-stop escape. One integration fix on the branch: the PR's hallucinatedEmptyStop referenced emittedToolCall, which #11109 had renamed — the branch now tracks emittedSawToolCall at the emitted level (any tool_call delta, complete or not), preserving the PR's don't-recover-after-tool-calls intent. Chain suites green: stream-continuation-wiring + stream-continuation + stream-recovery-toolcall 29/29. Thank you @maxmad64bis!
2026-08-22 21:54:48 -03:00
ggdayup
60f25eff98 fix(sse): merge purify_history compression notice into the leading system message (#11113)
Validated on the combined batch board: purify-system-first suite 4/4, typecheck clean. Pre-merge: file-size baseline gained a frozen entry for contextManager.ts at 1001 (+1, this PR's merge-into-leading-system branch) with a dated annotation — the gate caps unlisted files at 1000. Producer side of the live-confirmed TokenRouter 400 class: no internal path emits a mid-array system message anymore. Thank you @ggdayup — the call-log evidence made this airtight!
2026-08-22 21:53:08 -03:00
Dizzle
1058426120 fix(executors): rotate on upstream 400 empty-body rejections (opencode) (#11158)
Validated on the combined batch board over tip 92ef3c71: static gates clean (changelog, file-size, complexity 2624<=2774, cognitive 1182<=1223, dead-code 411<=416), typecheck:core clean, focused tests green.

Empty-envelope 400 (no error field, empty content, finish_reason null) now rotates/retries instead of propagating as success; 200/streaming path never buffered; real-error 400s untouched. account-rotation + new rotation suite 34/34 on the board. Thank you @maxmad64bis!
2026-08-22 21:51:22 -03:00
Dizzle
b3844550d0 fix(api): refuse creating a routing combo without any model (#11162)
Validated on the combined batch board over tip 92ef3c71: static gates clean (changelog, file-size, complexity 2624<=2774, cognitive 1182<=1223, dead-code 411<=416), typecheck:core clean, focused tests green.

Combo without models is now refused at the schema boundary (API 400), the CLI flags it, and openapi.yaml matches the real contract (phantom props removed). combo-* suites + cli-combo-create-models green on the board. Closes #10954. Thank you @maxmad64bis!
2026-08-22 21:51:19 -03:00
ggdayup
f3875759ac fix(memory): treat TokenRouter as system-must-be-first (live HTTP 400 confirmed) (#11114)
Validated on the combined batch board over tip 92ef3c71: static gates clean (changelog, file-size, complexity 2624<=2774, cognitive 1182<=1223, dead-code 411<=416), typecheck:core clean, focused tests green.

Companion to #11113 (consumer side): tokenrouter joins BUILTIN_PROVIDERS_SYSTEM_MUST_BE_FIRST — memory-system-first-6135 suite green. Live-confirmed 400 class documented in the body. Thank you @ggdayup!
2026-08-22 21:51:16 -03:00
Praveen K Palaniswamy
92ef3c71ea fix(resilience): honor shared-registry passthrough providers (#11071) (#11165)
Validated on a worktree over the current tip: account-fallback-service 91/91 plus the five sibling lockout suites 24/24. The measurement in the body (40 of 111 passthroughModels providers uncovered on this branch) is the clincher — one lookup via getProviderById().passthroughModels beside the existing checks, closing the #11071 remainder for shared-registry gateways (port of #11075 which had only landed on main). Thank you @yourspraveen!
2026-08-22 20:43:15 -03:00
Praveen K Palaniswamy
ce66d319b1 fix(quality): drain v3.8.50 base-reds — doc counts + orphan uncloseai test (#11160)
Validated against code before merge: 159 migration files on disk, 56 free-forever (Hack Club removal), 40 pools — counts verified, not trusted. check:docs-counts exit 0 (HARD failures drained; the 2 remaining soft executors-count notes are pre-existing on the tip) and check:test-discovery OK (orphan moved into the collected tree). These reds came from #11103/#11123 merging without the count regen — thanks for sweeping them @yourspraveen!
2026-08-22 20:41:12 -03:00
Praveen K Palaniswamy
2edb7a1fdf fix(dashboard): keep the provider registry out of node:net (#11122) (#11154)
Validated on a worktree over the current tip: the red it fixes reproduced exactly as described (media-page-client-browser-bundle red since #11122 — providerRegistry became reachable from the dashboard client bundle via node:net). Post-fix: bundle test 2/2 green, new ip-parity suite + is-local-provider 7/7, all 7 outboundUrlGuard consumer suites 76/76 (the moved normalizeHost/isPrivateHost keep their re-exports; routing behavior untouched). Thank you @yourspraveen — clean surgical extraction with a pure-JS ipVersion mirroring Node's own regexes.
2026-08-22 20:38:44 -03:00
Rouzbeh†
ec6010f018 fix(cli): resolve blank device code and undefined verification URL in oauth start (#11164) (#11173)
Cherry-picked onto the current tip (authorship preserved), noise stripped. Focused: oauth-device-flow-11164 green + 9474-claude-code-oauth-mismap neighbor suite green. Device-code endpoint is tried first, camelCase/snake_case fallbacks normalized, no more blank code / 'Visit: undefined'. Fixes #11164. Thank you @rqzbeh!
2026-08-22 20:14:26 -03:00
Rouzbeh†
d3ac1a600c refactor(dashboard): mirror check button disable state in AddApiKeyModal Enter handler (#10995) (#11156)
Cherry-picked onto the current tip (authorship preserved), generated-count noise stripped. Pre-merge: file-size baseline rebaselined 1080→1082 with dated annotation (the +2 lines are the Enter-handler isCheckDisabled mirror — owner-requested #11056 polish; rest is Prettier reflow). Gate green; vitest add-api-key-modal-enter-key 2/2 (jsdom render test). Thank you @rqzbeh!
2026-08-22 20:13:10 -03:00
Rouzbeh†
64b7389fe9 fix(tests): update translate-path golden snapshot and docs for hailuo-web (#11000) (#11161)
Cherry-picked onto the current tip (authorship preserved), noise files stripped. Pre-merge addition: regenerated the golden snapshot with UPDATE_GOLDEN=1 because the branch's snapshot predated two legitimate tip changes — the dify bare-root from #11065 and the hackclub removal from #11123. The regen'd delta contains exactly those two (audited). This also drains a live base-red: provider-translate-path-golden was failing on the pure tip. 3/3 green. Thank you @rqzbeh!
2026-08-22 20:10:24 -03:00
Harvey Doan
c19c73fdc8 fix(claude): restore canonical tool names so Claude Code accepts tool calls (#11085)
Merged after conflict resolution validated on the combined board (50/50 casing tests green, typecheck:core clean). Two pre-merge adjustments on the branch: (1) the utilization route conflict resolved to the tip shape — its asNullableString/displayName version is newer than the branch's; (2) dropped the newly-added src/lib/db/connections.ts, orphaned once the route kept the tip shape (tip already uses getProviderConnectionById) — nothing imported it. The casing fix itself lands intact: non-streaming OpenAI→Claude conversion now restores canonical tool names, identity echoes no longer pin lowercase, and TOOL_RENAME_MAP gained the Task* tools. Fixes the live-reproduced Claude Code 'No such tool available: bash' failures. Thank you @linhdmn — outstanding repro and root-cause writeup!
2026-08-22 19:00:39 -03:00
Reza Rezaei
7360ca4242 feat(redis): add configurable key namespace prefix (#11042)
Validated on the combined board over tip 80d931ae: quota-redis-store (incl. the KEY_PREFIX derivation test), local-redis-status and rate-limiter-redis-optional green, typecheck:core clean. One pre-merge fix pushed to the branch: docs/reference/ENVIRONMENT.md gained the REDIS_KEY_PREFIX row (env-doc-sync gate requires every .env.example var documented). Board note: the redis tests leave an ioredis retry handle open and hang the runner exit locally — assertions all pass; pre-existing pattern, not from this PR. Thank you @MeRezaRezaei!
2026-08-22 18:56:45 -03:00
Reza Rezaei
e15af18d17 fix(kimi): point kimi-web to international www.kimi.ai (#11045)
Validated on the combined board over tip 80d931ae: kimi suites green (executor-kimi-web, kimi-partner-aff-links, token-health-check-kimi 33 assertions), vitest providerPageHeaderKimiPartnerLink green, typecheck:core clean. Audited the diff: only kimi-web switches to the international www.kimi.ai (Connect-RPC base, website, auth hints); kimi-coding / kimi-coding-apikey affiliate links stay on kimi.com as intended — asserted by the updated tests. Owner approved merge without the VPS smoke. Thank you @MeRezaRezaei!
2026-08-22 18:55:23 -03:00
Andrew B.
80d931ae2d fix(logs): apply filter predicates to merged in-memory call-log rows (#11082)
Validated on a combined board over tip aa128736 (incl. sibling #11081): call-logs-row-filter 4/4 green, typecheck:core clean. The merged-row predicate fix closes a real gap — in-memory (in-flight/recently-completed) rows bypassed every filter except correlationId; rowMatchesFilter() now applies search/model/provider/account/apiKey/status/combo uniformly while DB rows stay idempotent. Thank you @AndrianBalanescu!
2026-08-22 16:55:09 -03:00
Andrew B.
56540f24c5 fix(api): save call logs and add endpoint fallback for local rerank providers (#11081)
Validated on a combined board over tip aa128736: focused tests local-rerank-logging + call-logs-row-filter green (7/7 across runs), typecheck:core clean. One pre-merge fix: widened waitForCallLogSaves 5s→15s — the call-log artifact writer's fsync latency exceeds 5s under a loaded host (pre-existing call-log-save-drain flakes identically on the pure tip), so the budget was load-flaky, not the code. Local rerank now logs call entries on success and error paths like embeddings/cloud rerank, captures full request/response payloads, attaches x-omniroute-* headers, and falls back /v1/rerank→/rerank on 404. Thank you @AndrianBalanescu!
2026-08-22 16:54:17 -03:00
Rouzbeh†
aa12873686 fix(providers): remove Hack Club AI provider (#11118) (#11123)
Cherry-picked the author's cleaned single-commit head onto the current tip. One fix applied pre-merge: the removal migration collided at number 161 with today's config_audit_log migration (#11103) — renumbered to 162_remove_hackclub_provider.sql. Focused tests: remove-hackclub-11118 + provider-metrics-deleted-provider green; check:provider-consistency OK (266/348/0). Provider removal requested by Hack Club maintainers (#11118). Thank you @rqzbeh!
2026-08-22 16:26:38 -03:00
Diego Rodrigues de Sa e Souza
b2509bcd05 fix(release): drain v3.8.50 base-reds — getTokenLimit contract, vi i18n parity, eslint gate (#9985)
Discriminated against the pure base tip (all three reproduced without any PR diff): (1) getTokenLimit test aligned to the contract changes of #8228/#11034 with the bluesminds 200k pin kept as the original guard; (2) Vietnamese translations completed for harImport*/omni-webhooks (upstream already carried equivalent translations — conflict resolved to base); (3) eslint gate fixed by typing the dynamic core imports in capture-critical-db-state.test.ts (no-explicit-any). 41/41 tests green, typecheck clean, eslint exit 0.
2026-08-22 16:19:57 -03:00
Rouzbeh†
367ae2fb97 fix(search): enforce blockedProviders setting on search endpoint (#11100) (#11125)
Cherry-picked the three value commits onto the current tip, dropping the stale base-red sync commits. Focused tests: search-blocked-providers-11100 + search-registry/searxng-loopback/chat-guard/x-search suites 65/65. Fixes #11100 (endpoint half) — GET /v1/search now honors blockedProviders via getAllSearchProviders. Thank you @rqzbeh!
2026-08-22 16:13:26 -03:00
Rouzbeh†
4220c810ee fix(resilience): include RFC1918, CGNAT, and mDNS hosts in isLocalProvider (#11091) (#11122)
Cherry-picked both value commits (a1fa49a8 + a91f6e93, incl. the fail-open guard for unparseable hostnames) onto the current tip, dropping the stale base-red sync commits. Focused tests: is-local-provider-11091 + the isLocalProvider consumer suites (provider-validation-specialty, ollama-local-provider) 127/127; mutation coverage no-drift. Fixes #11091 — RFC1918/CGNAT/link-local/mDNS hosts now classify as local via the existing isPrivateHost. Thank you @rqzbeh!
2026-08-22 16:08:22 -03:00
Rouzbeh†
50fc0d7299 fix(resilience): keep Ollama model-not-found failures scoped to connection model lockout (#11071) (#11078)
Cherry-picked the value commit (2c9202e4) onto the current tip, dropping the stale base-red sync commits. Focused tests: ollama-404-model-lockout 2/2 + the five sibling lockout suites (combo-provider-cooldown-sibling, 8247-model-unhealthy, vertex-passthrough, nvidia-410, account-fallback-service) 112/112; mutation coverage no-drift. Fixes #11071 — local/self-hosted 404s now scope to model lockout per the resilience doctrine. Thank you @rqzbeh!
2026-08-22 16:06:06 -03:00
Rouzbeh†
9a67185297 fix(cli): support OpenCode V2 config format in setup-opencode (#11070) (#11079)
Cherry-picked the value commit (55da60f5) onto the current tip, dropping the stale base-red sync commits. Focused tests: opencode-v2-config-11070 + merge-provider-guard + config-dir-single-source 12/12; mutation coverage gate no-drift (new test registered in tap.testFiles by the PR itself). Fixes #11070 — setup-opencode now emits both V1 and V2 blocks. Thank you @rqzbeh!
2026-08-22 16:01:25 -03:00
Rouzbeh†
3157e8a7ad fix(providers): require API key for Pollinations and fix optional key i18n labels (#11096) (#11117)
Cherry-picked the value commit (0e918816) onto the current tip, dropping the stale base-red sync commits. Focused tests: pollinations-api-key-required 1/1 plus the whole optional-key suite 142/142 (two legacy assertions in provider-route-schemas flipped to the new key-required contract, commented with the PR). Fixes #11096 — Pollinations answers 401 anonymously now. Thank you @rqzbeh!
2026-08-22 15:59:31 -03:00
Rouzbeh†
a51b8ba563 fix(cline): use valid modelType/model format for Cline provider models (#11099) (#11132)
Cherry-picked the value commit (ac09b6b5) onto the current release tip, dropping the stale base-red sync commits that no longer apply. Focused test cline-model-format-11099 2/2 green; check:provider-consistency OK (267/348/0). Fixes #11099 — the zai→z-ai namespace typo. Thank you @rqzbeh!
2026-08-22 15:52:13 -03:00
Dizzle
5631e91f0d fix(providers): learn reasoning_effort capability from upstream 4xx instead of a hardcoded/opt-out default (#11116)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Learned reasoning_effort caps mirror the merged learnedThinkingCaps mechanism: parse the upstream 4xx enum, clamp, retry once, consult proactively — covers custom openai-compatible connections the static registry can't. 22 new test cases + full regression list green. Fixes #11111. Thank you @maxmad64bis!
2026-08-22 14:40:57 -03:00
Dizzle
1dd0173468 fix(sse): assign a stable index/id to parallel function_call items in Responses->Chat translation (#11144)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

TDD red->green: parallel function_call items now get distinct stable index/id at .added time via a per-call Map, interleaved argument deltas no longer glue, dual item_id/output_index correlation. 120-test translator suite green. Thank you @maxmad64bis!
2026-08-22 14:40:45 -03:00
Dizzle
c89fc6ba2a feat(providers): let operators add per-provider error rules via settings (#11104)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Operator-declared per-provider error rules via settings, consulted before the built-ins; the allowlist bypass is correct — declaring a rule is itself the opt-in, and no provider-specific rule is hardcoded. Thank you @maxmad64bis!
2026-08-22 14:40:35 -03:00
Dizzle
84c9dfdd2c fix(config-audit): persist config audit log to SQLite with retention (#11103)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Config-audit survives restarts with bounded growth (migration 161 + OR IGNORE seed, retention wired into runAutoCleanup); route cabling deliberately out of scope. Thank you @maxmad64bis!
2026-08-22 14:40:09 -03:00
Dizzle
f3b190ba3e fix(providers): reject silent validation degradation with 400 and rejected keys (#11101)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Strict schema + {sanitized, rejected} DB boundary — silent validation degradation now answers 400 with the offending keys. Caller audit done: only the providers write path consumes the sanitizers. Thank you @maxmad64bis!
2026-08-22 14:39:58 -03:00
Dizzle
d021423af3 fix(sse): default summary + strip malformed id on kept Responses input items (#11110)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Defaults summary and strips malformed ids on kept Responses input items — both 400s observed against live muse-spark traffic; the flipped legacy assertion is documented contract propagation. Thank you @maxmad64bis!
2026-08-22 14:39:47 -03:00
Dizzle
78b4082361 fix(autopilot): show real suggestion count and link dashboard (#11102)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Real suggestionCount replaces the conflated link count (deprecated alias kept), dashboard deep-link fixed. Thank you @maxmad64bis!
2026-08-22 14:39:22 -03:00
Dizzle
efc7134167 fix(registry): restore models[0] default + guards; note muse-spark overlay (#11051/#11049) (#11133)
Validated on the combined batch board over release/v3.8.50 tip d91238b7: static gates clean, typecheck:core clean, focused tests green.

Restores the models[0] dashboard default silently changed by #11051, with narrow guards instead of a brittle full snapshot. Thank you @maxmad64bis!
2026-08-22 14:39:12 -03:00