📊 Release by the numbers

Entries by type

🏆 Top 25 contributors this cycle

By commits in ed2db6cb19..v3.8.50, author identities consolidated via .mailmap. Bots excluded.

Living section — regenerated 2026-08-12 from all cycle commits (cycle open ed2db6cb19 → tip). Bullets carry the merged PR and its author; direct pushes listed separately.

✨ New Features

• feat(search): first-class X Search provider (x-search) on… #10985

• feat(core): add Layer A capability filter at router #5696

• feat(providers): add DeepAI as paid API-key image provider #6671

• feat(providers): add Naga.ac and… #6674 — thanks @chirag127

• feat(api): add response content encoding verification —… #6736

• feat(api): add plugins marketplace install endpoint with… #6752

• feat(chatgpt-web): harden prompt-emulated… #7679 — thanks @horacecar

• docs: add management authentication terminology guide #7786

• feat(a2a): Conductor bridge — long-lived SSE consumer that… #8080

• feat(a2a): the Agent Card (/.well-known/agent.json) now… #8119

• feat(dashboard): "Conductor" panel — OmniConductor fleet… #8221

• feat(dashboard): Faro chat with voice on the Conductor panel —… #8222

• feat(a2a): inbound delegation to the OmniConductor fleet — `POST… #8223

• docs: add low-memory/small VPS optimization guide #8237

• feat(providers): add connection-level… #8369 — thanks @Benson-mk

• feat(copilot): add approval gate for runOmniRouteCli commands #8461

• feat(ci): add windows-latest leg to test-bun-sqlite job #8468

• feat(electron): Desktop app can now attach… #8799 — thanks @soulhakr

• Database The node:sqlite fallback now… #8870 — thanks @artickc

• feat(models): add exact per-model… #8908 — thanks @xz-dev

• Providers expands the Novita AI catalog… #8913 — thanks @jax-novita

• feat(providers): native xAI Agent Tools passthrough on… #8964

• feat(providers): add UnoRouter provider UnoRouter is an… #8978

• feat(sse): deprecated the legacy gemini-cli **upstream… #7034 #8980

• Add a default-off connection setting for Codex, OpenAI, and…

• Omit opaque encrypted reasoning values from persisted call logs… #9000

• feat(providers): add Regolo AI OpenAI-compatible provider #9031

• feat(db): add provider-scoped model aliases that survive… #9068

• feat(cursor): surface a dismissible dashboard banner suggesting… #9173

• feat(cursor): proactively renew Cursor sessions before their ~24h… #9173

• feat(codex): accept parenthesized… #9208 — thanks @seakleangnhak

• feat(usage): surface Claude thinking token… #9214 — thanks @luoyide

• feat(ollama): add Ollama Local embedding… #9225 — thanks @HaoNgo232

• feat(images): execute full combo strategy + fallback in… #9239

  Adds open-sse/services/imageCombo.ts that expands combo targets, filters to images-capable, executes the priority strategy with handleImageGeneration per target, and returns the first success or last failure. Route patches detect combo names before model resolution and divert to the new execution path.

• feat: make forwarded upstream response-header budget configurable… #9243

• feat(providers): filter provider detail… #9247 — thanks @RobertsXML

• feat(providers): make video_url… #9248 — thanks @HellFiveOsborn

• feat(gemini): recursive type:object injection in schema… #9268

• feat(dashboard): render a conditional "Get API key" link on the… #9270

• feat(providers): accept JSON cookie… #9284 — thanks @AIB1TAL0S

• feat(providers): support max reasoning effort for opencode-zen… #9318

• feat(providers): expanded the NanoGPT (nano-gpt.com) upstream… #9322

• feat(sse): combo system_message supports server-side… #5501

• feat(sse): template expansion… #5501 #9414 — thanks @maxmad64bis

• feat(sse): New-API/One-API/Sub2API aggregator balance detection… #9415

• feat(catalog): added opt-in settings hideAutoCombos and… #9418

• feat(opencode-plugin): added… #9473 — thanks @omniroute

• feat(providers): add native DeepSeek V4 Flash and Pro… #9485

• feat(opencode-plugin): warm catalog startup from disk snapshot +… #9490

  The config-shim hook now reads the last disk snapshot before fetching, so the provider registers immediately with the last-known-good catalog (~1-2s vs ~30s on a warm gateway). All six fetchers run concurrently via Promise.allSettled instead of sequentially. A failed refresh keeps the snapshot (no overwrite). An in-flight guard prevents concurrent refreshes for the same cache key. The features.diskCache: false opt-out disables the warm read entirely.

• feat(models): Test All's "Auto-hide failed models" no longer… #9511

• Add an advisory forgotten-sibling-tests report to pull-request… #9530

• feat(providers): add Muse Code CLI provider preset #9544

• feat(plugins): expose client request headers in plugin… #9570

• feat(plugins): add onStreamComplete built-in event exposing… #9571

  Adds a new onStreamComplete plugin event that fires after an SSE stream is fully
  consumed, carrying usage token counts and timing metrics (latency, TTFT). Built-in
  events now include onStreamComplete as a fire-and-forget lifecycle hook.

  Payload: status, usage (prompt_tokens, completion_tokens, reasoning_tokens,
  cache_read_input_tokens, cache_creation_input_tokens), timing (latencyMs, ttft),
  model, provider, errorCode.

  Non-breaking — existing onResponse hooks with { streamed: true } remain unchanged.

• feat(audio): Soniox STT + TTS provider (sx) — async… #9579

• Show cache-read and cache-write token counts in request log rows and…
  report them. (#9620)

• feat(memory): support custom OpenAI-compatible endpoints for… #9622

• feat(resilience): add an opt-in watchdog for persistently slow… #9709

• Onboarding: add an explicit, reviewable one-click setup for eligible…
  with per-provider caution links, selectable confirmation, idempotent creation, and safe partial
  retries. Existing provider connections are never changed and setup completion never enables
  providers silently. (#9752)

• feat(settings): add a dedicated Modality Bridge settings page… #9782

• feat(modality bridge): Transcribe chat audio for text-only… #9807

• feat(memory): PROVIDERS_SYSTEM_MUST_BE_FIRST (the… #6135 #7293 #9924

• feat(api): API keys can disable prompt… #10001 — thanks @shixi-li

• Add cliproxy provider exposure controls and manifest injection #7329 — thanks @KooshaPari

• feat(infra): add a systemd autostart unit for Linux #8635

• feat(db): add node sqlite adapter parity #8871 — thanks @epsilonode

• feat(alibaba): free-tier routing with live quota sync #8893 — thanks @AndrianBalanescu

• feat(oauth): add Raycast Pro provider with local auto-import #8895 — thanks @AndrianBalanescu

• feat(executors): add isolated Claude Code bridge over Devin ACP #8914 — thanks @McLuck

• feat: improve provider quota layouts #8916 — thanks @apoapostolov

• feat(mcp): add omniroute_create_combo tool #8925 — thanks @lucasmellos

• feat(ci): gate the publish on clean-install AND upgrade-over-previous #8953

• feat(providers): add Conol (conol.ai) web session provider #8974 — thanks @artickc

• Feat/combo provider wise model test #9011 — thanks @JoshimOfficial

• feat(model-alias): add runtime Model Alias Resolver middleware #9020 — thanks @Egorich-print

• feat(i18n): complete zh-CN localization for compression engines and dashboard UI #9038 — thanks @qianze0628

• feat: Cheaper Inference provider (chat + native Responses + images, sponsor rail 2nd) #9043

• feat(providers): add comprehensive support for self-hosted Firecrawl via FIRECRAWL_BASE_URL and custom base URLs #9052 — thanks @mad-gooze

• feat(dahl): add manual API key option alongside auto-generated token #9077 — thanks @pizzav-xyz

• feat(ci): G0 — reforça o trilho PR→release/ ** #9108

• feat(providers): native xAI Agent Tools passthrough for /v1/responses #9111 — thanks @VXNCXNX

• feat(.50): completa itens restantes — G13, G14, gap34, docs, R0.2 #9126

• feat(g1): rewrite combo-strategy check to runtime-import approach #9131

• feat(test:scoped): TIA-based local test runner (#8084 D1) #9143

• feat(docker): publish next from active release branches #9181 — thanks @Zartharas

• feat(usage): show Grok Build billing limits #9205 — thanks @xz-dev

• feat(models): functional gateway mirrors + fix synced-substitution #9217

• feat(admission): add adaptive overload protection for LLM routes #9262 — thanks @xz-dev

• feat(i18n): update italian translations #9280 — thanks @Gecky2102

• feat(dashboard): persist provider screen filters to URL for bookmarking #9307 — thanks @swingtempo

• feat(api-manager): add provider-level model permissions #9313 — thanks @xz-dev

• feat(warmup): proactive Claude warmup scheduler (#8848) #9449 — thanks @HouMinXi

• feat(infra): add systemd autostart unit for Linux (#8635) #9466

• feat(lib): make MODELS_DEV_SYNC_ENABLED actually control the sync #9483 — thanks @HouMinXi

• feat(radar): flag-gated signed free-model catalog overlay #9515

• feat(compression): add Russian language pack #9581 — thanks @vinogradovnet

• feat(providers): integrate wave4 free-tier gateways #9584

• feat(providers): add Zylo UnoRouter and Poolside registries #9585

• feat(providers): add FastRouter AnyAPI and ElectronHub registries #9586

• feat(providers): add LLMGateway and LLM Kiwi registries #9587

• feat(providers): add FreeInference registry #9594

• feat(radar): contributor + supporter claim buttons on the activation screen (F4/T7) #9710

• feat(radar): paste-key input on the activation screen (F4) #9758

• feat(guardrails): modality bridge core — vision mode/task-aware/cache/input_image + modalityBridge settings #9759

• feat(radar): referrals from standalone /v1/referrals feed (no 30-day delay) #9762

• feat: generic OpenAI-compatible video custom provider #9844 #9818 — thanks @oyi77

• feat(logging): make the chat-log truncation limit configurable, bumped default 128x #9863 #9738 — thanks @hartmark

• feat(logging): bump CHAT_LOG_ARRAY_TAIL_ITEMS default 24 -> 128 #9864 #9735 — thanks @hartmark

• feat(oauth): add Openference OAuth and API key provider integration #9869 #9722 — thanks @AnhLead

• feat(src): proxy-pool-toolbar-minor-improvements #9870 #9718 — thanks @AgnesRiber

• feat(resilience): expose providerQuotaOverrides via /api/resilience #9871 #9714 — thanks @herjarsa

• feat(responses): add encrypted reasoning replay opt-in #9876 #9601 — thanks @jackjinke

• feat(resilience): add per-account resilience connections view (API + dashboard) #9880 #9510 — thanks @HouMinXi

• feat(db): add a job registry for scheduled background work #9886 #9631 — thanks @HouMinXi

• feat(telegram): Mini App chat bridge — initData auth, update webhook, chat proxy #9907 #9812 — thanks @benzntech

• feat(cursor): exclusive live listing + verbatim AgentRun model ids #9911 — thanks @yansigit

• feat(usage): add Command Code quota tracking #9921 — thanks @yansigit

• feat(combo): add quota-only priority fallback #9983 — thanks @xz-dev

• feat(onboarding): add one-click free provider setup #10014

• feat(admission) — direct pushes: adaptive overload/pressure…

• feat(agentrouter) — direct pushes: support Claude and Codex…

• feat(providers) — direct pushes: ChatGPT Web session credential…

• feat(sse): honor provider-rule lock scope for agentrouter… #10419

• feat(ocr): Vertex AI DeepSeek-OCR provider #10398

• feat(providers): derive imageToText from the OCR registry +… #10400

• feat(ocr): multi-provider /v1/ocr with transformation layer… #10283

• feat(providers): declare imageToText serviceKind on major… #10275

• feat(bridge): native-vision skip guard + configurable describe… #10289

• feat(bridge): normalize images to 2048px long edge before… #10287

• feat(sse): restate agentrouter quota 403/400 as retryable 429… #10335

• feat(sse): add i-have-adhd output style to compression catalog #10271

• feat(codex): add OAuth fingerprint… #10243 — thanks @xz-dev

• feat(i18n): complete Portuguese… #10250 — thanks @DarkEsteves

• feat(providers): publish Poolside's… #10216 — thanks @pacocartones

• feat(crof): advertise reasoning… #10062 — thanks @excessivechaos

• feat(open-sse): expose… #10040 #10046 — thanks @tiangao88

• feat(dashboard): Kimi 15% first-top-up campaign — dedicated… #10240

• feat(providers): integrate audited free-tier gateways #9210

• feat(radar): OmniRoute Radar — the signed free-model… #10826
• feat(video): Video Bridge gained a full… #10483 — thanks @backryun
• feat(volcengine): Volcengine **Ark plan… #11333 — thanks @rengaryang
• feat(providers): #10722 #10184 #10174 — thanks @hgaib @megamen32 @MeRezaRezaei
• feat(providers): #9909 #10804 — thanks @yansigit @tuandinh0801
• feat(providers): tool calling for… #10948 — thanks @acc0mplish
• feat(providers): per-connection… #10885 — thanks @maxmad64bis
• feat(providers): #10226 #10195 #10942 — thanks @backryun @oyi77
• feat(providers): the web-session credential… — thanks @benzntech
• feat(sse): explicit glm-5.3-max… #11415 — thanks @phuongddx
• feat(sse): discover Anthropic partner models… #11279 — thanks @maci0
• feat(sse): opt-in… #10965 — thanks @mymusicmyspace
• feat(sse): Kimi Web token lifecycle… #10944 — thanks @MeRezaRezaei
• feat(sse): Cursor plan images through the Agent CLI… #10842 #10425
• feat(api): #10819 #10977 #10771 — thanks @RaviTharuma @maxmad64bis
• feat(api): #10568 #11076 — thanks @RaviTharuma @ntdatt812
• feat(audio): native… #11312 #11315 #10822 — thanks @RaviTharuma
• feat(gemini-web): image generation… #10494 — thanks @Abhishek4512009
• feat(cli): native Bun backend… #11039 #11168 — thanks @rqzbeh
• feat(cli): tray… #11230 #10830 #11372 — thanks @tuandinh0801 @ziuus
• feat(cli): relay-like CLI closure — a target… — thanks @backryun
• feat(dashboard): #11228 #11227 #11224 #11215 #11195 #11206 — thanks @ignamiranda
• feat(dashboard): #10263 #10900 #10520 #11196 #11329 #10354 — thanks @hartmark @swingtempo
• feat(routing): #10126 #10362 #10881 #10927 — thanks @benzntech @KaspaPulse @Egorich-print
• feat(combo): an opaque… #10730 — thanks @stanleytejakusuma
• feat(admission): #11268 #10814 #10437 — thanks @RaviTharuma @xz-dev
• feat(compression): adopts… #10647 #11318 — thanks @RaviTharuma
• feat(models): #11252 #10883 #10884 — thanks @maxmad64bis @excessivechaos
• feat(search): context7 added as a… #11140 — thanks @HouMinXi
• feat(mcp): dynamic runtime tool-schema… #11155 — thanks @rqzbeh
• feat(a2a): A2A v1.0 client compatibility —… #10839 — thanks @wpec
• feat(server): native systemd… #10662 — thanks @maxmad64bis
• feat(redis): configurable key… #11042 — thanks @MeRezaRezaei
• feat(docker): hardened Linux VPS… #10623 — thanks @freudantunes
• feat(proxy): #10876 #10342 — thanks @maxmad64bis @Gi99lin
• feat(services): sanitized CLIProxyAPI… #11314 — thanks @RaviTharuma
• feat(db): the DB health check now… #10652 — thanks @maxmad64bis
• feat(codex): sync with Codex v178 identity… #10716 — thanks @xz-dev
• feat(usage): Kimi Coding "Extra Usage" is… #10712 — thanks @xz-dev
• feat(oauth): gemini-3.7-flash models… #10305 — thanks @Chewji9875
• feat(cli-tools): Prime Agent added to… #11166 — thanks @arminanton
• feat(guardrails): a focused video-analysis mode for the vision…
• feat(ops): canary deploy path with a provenance gate, a… #10446 #10444
• feat(api): list embeddings… #11249 #11213 — thanks @rafacpti23
• feat(responses): previous_response_id… #10262 — thanks @hartmark

🐛 Bug Fixes

• fix(build): every route no longer answers HTTP… #11343 #6344 #10060
• security(search) block SSRF via /v1/search… — thanks @zmf963
• providers honor PATCH /api/providers/[id] so `omniroute… #10366
• cli route provider test commands through configured connection… #10570
• executors fix internal timeout misclassified as client… #8197
• test(combo): guard auto/best-free never leaks the combo name as a… #7754
• fix(vision-bridge): describe-model no longer returns unreachable… #8430
• fix(vision-bridge): validate fixedModel against usable credentials… #8430
• fix(vision-bridge): in the combo describe path, replace raw images… #8430
• fix(quality): add base-relative file-size check so inherited drift… #8522
• fix(ci): aggregate all fast-gates into non-fail-fast loop so one… #8542
• fix(tests): make machineId tests macOS-compatible by stubbing… #8577
• fix(scripts): replace bash 4+ readarray with compatible while-read… #8577
• fix(cli): enable systray2 on Windows for Norton-friendly tray #8609
• fix(executor): guard claude/anthropic buildHeaders against empty… #8653
• fix(providers): gate premium opencode-zen/opencode-go models… #8681
• fix(api): make /v1/models stale refresh response-safe… #8728 #8697
• fix(yuanbao-web): accept content field in SSE text events… #8739
• fix(build): remove misleading open-sse/package.json facade and add… #8781
• fix(errorClassifier): classify ChatGPT Web SENTINEL_BLOCKED 403 as… #8813
• fix(cli): fall back to node:sqlite when better-sqlite3 constructor… #8826
• fix(opencode): prefix provider id with "opencode-" for auth login… #8830
• fix(opencode-zen): add current free-tier models to registry to… #8841
• fix(api): Let image and video providers… #8843 — thanks @artickc
• fix(build): include better-sqlite3 prebuilds in standalone bun… #8847
• fix(proxy-health): include credentials in proxy health check URLs #8853
• fix(build): prepublish no… #8858 — thanks @omniroute @maisdesign
• fix(opencode): generate… #8869 — thanks @xiaoyaner0201
• fix(cli): default omitted Codex CLI… #8876 — thanks @xiaoyaner0201
• fix(proxy): isolate new proxy… #8883 — thanks @xiaoyaner0201
• fix(db): invalidate stale LKGP pins when provider connections are… #8887
• fix(tests): update stale nightly compat fixtures and goldens to… #8901
• fix(quota): Deleting a quota pool now… #8906 — thanks @xiaoyaner0201
• fix(executors): Vertex AI now routes… #8909 — thanks @wgordon17
• fix(providers): expose both OAuth… #8921 — thanks @Llliao1113
• fix(compression): drop orphan… #8946
• fix(auth): setting first dashboard login password no longer fails… #8950
• fix(github): add targetFormat to GPT-5.6 Sol/Terra/Luna models #8951
• fix(auto-update): skip synthetic Next.js standalone package.json… #8956
• fix(opencode): propagate vision capability from live catalog into… #8960
• fix(providers): switch Antigravity quota RPCs to iterate… #8965
• fix(oauth): GHE Copilot OAuth lifecycle — connecting an account…
• fix(health-check): the access-token-only… #8970 — thanks @hppsc1215
• fix(providers): copilot-m365-web enterprise turns send… #8971
• fix(ci): the reconciliation helper no longer bounds its scan… #8985
• fix(ci): fixed a live auto-update defect where **Intel Macs… #8988
• fix(sse): stripResponsesLifecycleEcho no longer strips… #8990
• fix(vertex): route Claude models to native rawPredict endpoint and… #8994
• fix(proxies): resolveProxyForConnection now returns the proxy… #8995
• fix(translator): the Responses-to-Chat promotion path called… #8997
• fix(sse): Claude reasoning-effort suffix ids…
  correctly on any provider serving a real Claude model, not just the direct Anthropic provider
  (#9006)
• fix(sse): the no-thinking (no-think/) catalog variant's…
  made it unusable outside the direct provider, both in the discovery catalog and the dashboard
  playground — is fixed (#9006)
• fix(sse): a single unrecognized model id on a Vertex connection no…
  other model on that connection for 2 minutes — Vertex 404s are now scoped to a per-model
  lockout via passthroughModels instead of a connection-wide cooldown
  (#9006)
• fix(sse): Vertex PERMISSION_DENIED 403s are now disambiguated…
  documented error format — a genuinely connection-wide cause (API disabled, project-level IAM
  denial) still cools the whole connection, while a model-specific denial locks out only that
  model (#9006)
• fix(sse): error-only streams now preserve… #9022 — thanks @shixi-li
• fix(cursor): preserve tool context across multi-turn conversations… #9029
• fix(sse): move Antigravity client system content to first user… #9030
• fix(auth): IP blacklist now blocks on direct connections via… #9033
• fix(api): use configured prefix instead of raw node UUID for… #9034
• fix(resilience): Detect and reset idle-capacity rate-limit… #9041
• fix(db): stream DB backup export instead of buffering entire file… #9045
• fix(ui): normalize Free Pool API response payload to read from… #9046
• fix(translator): pass… #9053 — thanks @ikelvingo
• fix(api/analytics): stop charging :free models at arbitrary… #9054
• fix(api): auto/* routing aliases bypass API-key… #9057
• fix(providers): anthropic strips code-execution/skills beta flag,… #9064
• fix(batches): GET /v1/batches now validates the limit query… #9073
• fix(a2a): the A2A JSON-RPC router now compares the bearer token… #9083
• fix(api/skills): the /api/skills/** routes now run caught… #9088
• fix(providers): admit audio-speech/audio-transcriptions apiType in… #9096
• fix(providers): modal.com validation returns clear error when Base… #9102
• fix(providers): GitHub Copilot no longer re-imports or routes… #9103
• fix(providers): resolve combo names in audio transcriptions route… #9134
• fix(vscode): allow built-in auto-routing models in VS Code model… #9140
• fix(background): detect Anthropic top-level system prompts for… #9142
• fix(dashboard): the provider "Auto Sync" toggle now applies to… #9149
• fix(cli): use process.execPath for macOS launchd autostart #9156
• fix(management): authorize mcp:connect-only keys on loopback/LAN… #9159
• fix(model-discovery): ingest capabilities.effort_tiers for synced… #9160
• fix(translator): Honor configured Chat… #9161 — thanks @Zartharas
• fix(translator): buffer and normalize upstream tool-call argument… #9168
• fix(cursor): the manual "Refresh" button on Cursor connections now… #9173
• fix(translator): avoid double-normalizing tool names in… #9177
• fix(dashboard): the "Default Model" of an OpenAI-compatible… #9179
• fix(db): honor the ENABLE_REQUEST_LOGS… #9187 — thanks @RobertsXML
• fix(model): normalize client… #9193 — thanks @b1nhm1nh
• fix(catalog): repair dead guard and synced-first ordering for… #9195
• fix(routing): consult customModels supportsVision flag in Combo… #9195
• fix(models): Preserve published model… #9199 — thanks @xz-dev
• fix(models): Reuse one build-local… #9199 — thanks @xz-dev
• fix(models): Resolve token limits and model… #9199 — thanks @xz-dev
• fix(models): Read and parse models.dev… #9199 — thanks @xz-dev
• fix(compression): honor the global… #9200 — thanks @joachimBrindeau
• fix(web-search): bind each search provider attempt to its… #9201
• fix(auth): make antigravity and agy equivalent in credential… #9204
• fix(cli): prefer IPv4 DNS for spawned… #9209 — thanks @dsitmilis
• fix(pricing): stop billing reasoning… #9212 — thanks @yidecode
• fix(models): /v1/models now… #4164 #9215 — thanks @nguyenha935
• fix(combo): the Combo "Add model"… #9218 — thanks @szzhoujiarui
• fix(codex): normalize additional_tools… #9219 — thanks @SalyyS1
• fix(codex): preserve quota window… #9222 — thanks @HectorBernstorff
• fix(azure): normalize GPT-5 chat… #9223 — thanks @royanrosyad85
• fix(codex): strip orphaned tool outputs… #9228 — thanks @raflyazf
• fix(i18n): completed the French UI… #9235 — thanks @alex-jordan547
• fix(nvidia): normalize tool names and… #9236 — thanks @minhnhat166
• fix(lmarena): emit Uint8Array SSE chunks instead of strings to… #9237
• fix(db): validateRegisteredKey no longer rejects the first… #9241
• fix(i18n): localized hardcoded web… #9245 — thanks @alex-jordan547
• fix(db): deleting a provider connection… #9246 — thanks @maxmad64bis
• fix(cli-tools): keep Apply enabled… #9250 — thanks @lazysaltyfish
• fix(translator): harden Claude format… #9253 — thanks @ervareza
• fix(minimax): add the required empty… #9256 — thanks @rixzkiye
• fix(resilience): Enforce RPM limits with rolling leases and… #9259
• fix(classify429): add missing have exhausted their quota… #9269
• fix(claude): remove unconditional "always" return in… #9276
• fix(qoder): include actionable CLI_QODER_BIN hint in connection… #9277
• fix(providers): the web search fallback detector in… #9279
• fix(docker): the bundled Redis sidecar no longer publishes on… #9286
• fix(credential-health): scheduler never retries failed connections… #9289
• fix(db): persist the account egress IP… #9291 — thanks @maxmad64bis
• fix(api): specialty model catalog ignores hidden OpenRouter model… #9293
• fix(mcp): break circular import between googApiKeyAuth.ts and… #9297
• fix(catalog): cache getModelsDevPricing to prevent OOM at startup #9300
• fix(providers): bump qwen-web SPA version header from 0.2.66 to… #9304
• fix(sse): broaden OMNIROUTE_SSE_COMMENTS to accept… #9305
• fix(lmarena): encode SSE stream chunks as Uint8Array to prevent… #9306
• fix(claude): reconcile compacted tool… #9308 — thanks @ryanngit
• fix(kiro): validate completed nested… #9314 — thanks @SemonCat
• fix(backend): use accumulated responseBody for provider payload in… #9315
• fix(qoder): surface qodercli stderr in error message instead of… #9319
• fix(security): require auth for /v1/models when management auth is… #9320
• fix(claude): normalize nested Claude… #9332 — thanks @AlanSyue
• fix(providers): map kimi-web/K3 to K2D5 scenario instead of OK… #9338
• fix(security): require explicit tool envelope to prevent bare JSON… #9343
• fix(api): consult LiteLLM pricing_synced layer in… #9364
• fix(providers): treat claude-web 429 as unhealthy and forward… #9406
• fix(providers): treat muse-spark-web 429 as unhealthy #9406
• fix(providers): detect expired gemini-web sessions via… #9407
• fix(providers): add tool_use block handling to claude-web stream… #9408
• fix(api): fall back to slugified provider name when prefix is… #9416
• fix(providers): Codex GPT-5.6 model metadata reports the 1M… #9431
• fix(oauth): Kiro import token endpoint no longer overwrites… #9435
• fix(sse): hoisting a mid-conversation system/developer… #9436
• fix(backend): force system MITM CA cert to 0644 on Linux… #9442
• fix(routing): a Codex-native bare model id (gpt-5.5, the… #9447
• fix(docker): ship MITM _internal/ shims and selfsigned package… #9451
• fix(cli): probe PATH for claude.exe/codex.exe on Windows before… #9454
• fix(cli): stop the supervisor before the child so omniroute stop… #9455
• fix(cli): route claude-code OAuth to the Anthropic claude… #9474
• fix(cli): re-verify running binary version after `omniroute… #9475
• fix(providers): classify 400 out of extra usage as quota_exhausted… #9486
• fix(auth): redirect active sessions from… #9491 — thanks @DaDecky
• fix(api): make the 800-message chat history cap opt-in so long… #9494
• fix(translator): preserve authentic K3 Responses reasoning by… #9496
• fix(translator): join reasoning summary segments with newline… #9500
• fix(muse-spark-web): document the ecto1: WS auth token requirement… #9502
• fix(sse): stop force-injecting advanced-tool-use beta via the… #9505
• fix(sse): stop the reasoning-token buffer from enlarging a… #9507
• fix(ci): include combo-matrix tests in test-integration job #9531
• fix(ci): tighten unit suite ceiling from 100min to 80min as a… #9532
• fix(ratelimit): added queue-wait timeout tests and… #9533
• fix(test): prevent flaky modelsDevSync timer assertions by… #9534
• fix(backend): map cache tokens in OpenAI-to-Claude non-streaming… #9536
• fix(db): add transient-error retry to corruption probe to prevent… #9541
• fix(search): mark searxng-search as fallbackOnly to prevent… #9543
• fix(providers): strip provider prefix in getModelTargetFormat to… #9545
• fix(model): add "aq" alias for amazon-q provider so parseModel… #9550
• fix(proxy): NO_PROXY now bypasses context-level proxy in… #9551
• fix(build): npm run build:cli… #8858 #9553 — thanks @omniroute
• fix(quality): #8522 #9024 #9324 #9329 #9193 #9332 #9228 #9260 #8934 #9196 #9163 #9554
• fix(build): exec native esbuild binary directly in prepublish —… #9558
• fix(mcp): the 3 audit.test.ts shutdown/fallback tests… #8959 #9559
• fix(build): lazy-resolve module-level fs paths to avoid Turbopack… #9560
• fix(sse): replace timer-based waits with polling to fix flaky… #9567
• fix(translator): restore original tool name casing in… #9568
• fix(translator): add case-insensitive fallback for upstream tool… #9575
• fix(standalone): multipart uploads (`POST… #9580
• fix(docker): standalone co-location now… #9615 — thanks @atjsh
• fix(resilience): failed connection test now sets a short cooldown… #9623
• fix(db): wire telemetry cleanup scheduler in Next.js startup path #9624
• fix(db): align domain_cost_history cleanup cutoff with millisecond… #9625
• fix(playground): surface provider model loading errors and offer… #9626
• fix(combo): distinguish pre-dispatch skips from genuine failures… #9630
• fix(build): add build-next-isolated.mjs sibling imports to… #9633
• fix(providers): new per-provider… #9675
• fix(docker): --build-arg OMNIROUTE_USE_TURBOPACK=0 now… #9695
• fix(translator): restore TitleCase tool names on the Claude →… #9713
• fix(db): clear stale combo connection pins when provider… #9719
• fix(compression): persist enableRenderers through… #9730
• Fixed GET/PUT/DELETE /api/memory/[id] always failing with a… #9737
• Replaced hand-rolled body type checks with Zod validation in… #7 #9737
• Restore Vietnamese locale parity after the entity-normalization… #9737
• fix(radar): refresh signed catalog/referral caches when… #9776
• Translator keep the Responses namespace… #9783 — thanks @VXNCXNX
• fix(api): Model catalogs no longer expose… #9788 — thanks @xz-dev
• fix(executors): preserve Command Code… #9826 — thanks @MrShitFox
• fix(executors): prevent intermittent Codex… #9828
• fix(cursor): SelectedImage uses… #9834 — thanks @yansigit
• fix(test): reconcile test expectations that drifted from the… #9874
• fix(search): nest Exa contents options (text/highlights) for… #9914
• fix(i18n): re-escape CC discovery-alias… #8747 #9917 — thanks @yansigit
• fix(encryption): name failing credential + recovery path in… #9927
• fix(executors): preserve non-strict function-tool semantics… #9931
• fix(migrations): don't abort on fresh install with only the 001… #9934
• fix(admission): per-connection… #9654 #9940 — thanks @branben
• Repair release-sweep regressions in locale and environment… #9945
• Let the release-green validator finish the test-masking gate on… #9964
• fix(chat): don't misclassify content-less thinking/redacted Claude… #9971
• fix(images): normalize terminal upstream errors via… #9981
• fix(quality): green release/v3.8.50 base-reds — sync 4 env vars… #9985
• fix(sse): replay Gemini thought_signature on the direct Claude→Gemini path #3440 #2504 — thanks @csoftware-arigpt
• fix(security): bump adm-zip >=0.6.0 + exact host matching in the mitm DNS test #7733
• fix(i18n): polish zh-CN/zh-TW translations and fix over-translation of proper nouns #8872 — thanks @ikelvingo
• fix(build): support npm v11 allowScripts for optional native deps #8877 — thanks @configurowebmax
• fix(combo): exclude hidden leaves from catalog and dispatch #8878 — thanks @ahmet-cetinkaya
• fix(antigravity): add onboardUser fallback for accounts missing Cloud Code project #8886 — thanks @HouMinXi
• fix(sse): brand-neutral keepalive frames #8888 — thanks @AndrianBalanescu
• fix(deepseek-web): enable toolCalling on all models #8889 — thanks @AndrianBalanescu
• fix(combo): fail-fast concurrency gate and execute-mode overflow #8890 — thanks @AndrianBalanescu
• fix(antigravity): quota-aware account selection and projectId persistence #8891 — thanks @AndrianBalanescu
• fix(usage): aggregate provider window costs in SQL #8892 — thanks @AndrianBalanescu
• fix(combo): least-used quota strategy and wildcard UI preservation #8894 — thanks @AndrianBalanescu
• fix(test): stop autostart tests from disabling the developer's real systemd service #8900 — thanks @nosolosoft
• fix(combos): include id column in getCombos query #8905 — thanks @HouMinXi
• fix: prevent false 'Failed to save connection' error when adding providers #8912 — thanks @ziuus
• fix: add Termux/Android support for playwright-core and better-sqlite3 #8922 — thanks @Kaedo17
• fix(i18n): localize SubscriptionTab UI strings instead of hardcoded Chinese #8930 — thanks @Hdiaktoros
• fix(kiro): keep interleaved tool results grouped without dropping assistant text (#8903) #8931 — thanks @xiaoyaner0201
• Fix custom tool output pairing during context compression #8933 — thanks @JxnLexn
• fix(routing): account for active OAuth sessions #8940 — thanks @JxnLexn
• fix(vision): prevent bridge streaming and normalize OMP effort #8945 — thanks @rinseaid
• fix(ci): stop one failing platform from taking the whole desktop channel down #8957
• fix(api): alias-backed models leak raw node UUID prefix in /v1/models (#8958) #8961 — thanks @Rahulsharma0810
• fix(sse): default OpenAI Chat Completions to non-stream when stream omitted #8976 — thanks @HouMinXi
• fix(cache): add latency marker + per-key bypass for semantic cache #8984 — thanks @HouMinXi
• fix(perplexity-web): update catalog to use 'copilot' mode and fix model IDs #8989
• fix(docker): move entrypoint script to /app to avoid tmpfs masking #8999 — thanks @yutuknown
• fix(executors): backfill missing tool message names for Kimi K3 and strict BYOK providers #9005 — thanks @Zenlyte
• fix(command-code): enable vision flags for CC models and fix vision-bridge reroute #9007 — thanks @Stazyu
• fix(sse): route Poe API-key traffic through DefaultExecutor (#8969) #9014 — thanks @Prudhvivuda
• fix(sse): preserve Gemini thought_signature on Claude Desktop tool turns #9015 — thanks @Prudhvivuda
• fix(sse): preserve Claude Code tool-name casing via Gemini/Antigravity #9016 — thanks @Prudhvivuda
• fix(dashboard): make quota providers expandable #9025 — thanks @jktan0504
• fix(chat): resolve stored combo names before image-model validation (#8986) #9027 — thanks @xiaoyaner0201
• fix(kiro): read usage from the frames Kiro actually sends #9035 — thanks @ddarkr
• fix(kiro): keep relocated tool documentation on multi-turn requests #9036 — thanks @ddarkr
• fix(vision): preserve images for text-only routes #9037 — thanks @rinseaid
• fix(db): bundle and verify the sql.js fallback #9044 — thanks @nguyenha935
• fix(open-sse): route GitHub Copilot gpt-5.6 sol/terra/luna to /responses #9050 — thanks @marchlhw
• fix: skills & memory — tool-name encoding, schema normalization, warm-cache, combo id, Ponytail catalog #9058 — thanks @Egorich-print
• fix(classify): recognize Modal 'usage limit reached' as quota exhausted #9079 — thanks @HouMinXi
• Fix/issue #8656 #9095 — thanks @infinit-X
• fix(adobe-firefly): open browser sign-in and resolve provider slug in /login #9097 — thanks @artickc
• fix(providers): make model Check/Test honor the node apiType, and show upstream model names #9099 — thanks @zhiru
• fix(audio): let the audio routes use audio-typed provider nodes, and gate remote ones behind a default-off flag #9101 — thanks @zhiru
• fix(antigravity): alias gemini-3.1-pro-high to gemini-pro-agent #9106 — thanks @HouMinXi
• fix(api): flatten single-row embedding vectors to OpenAI shape #9148 — thanks @aniketshukla1
• fix(proxy): restore connection pooling on proxy/relay paths (#9100) #9158 — thanks @oyi77
• fix(rate-limit): separate queue wait from execution timeout #9164 — thanks @Zartharas
• fix(translator): translate Codex agent messages for Chat #9171 — thanks @Gioxaa
• fix(settings): allow hidePaidModels updates #9182 — thanks @Zartharas
• fix(routing): evict affinity after terminal stream EOF #9184 — thanks @Zartharas
• fix(docker): bundle LLMLingua optional dependencies #9185 — thanks @Zartharas
• fix(health): skip disabled provider connections #9186 — thanks @Zartharas
• fix(claude): preserve standalone whitespace deltas #9189 — thanks @Zartharas
• fix(sse): evict a principal's own CCR blocks before another principal's (#9146) #9191 — thanks @fajarhide
• fix(responses): normalize terminal usage for Codex #9192
• fix(sse): back the CCR block store with a durable tier (#9061) #9198 — thanks @fajarhide
• fix(combo): recover provider circuit breaker from HALF_OPEN on success #9207 — thanks @HouMinXi
• fix(vision-bridge): improve compatibility with Anthropic image blocks and self-loop describe requests #9226 — thanks @Stazyu
• fix(images): refresh OAuth credentials and rotate accounts after 401 #9231 — thanks @Bl0ck154
• fix(ci): merge-queue tolerance for Build (advisory), drops paid-tier batching #9233 — thanks @wgordon17
• fix(token-refresh): exempt transient errors from exponential backoff #9242 — thanks @HouMinXi
• fix(resilience): count STREAM_EARLY_EOF as a provider failure in combo routing #9251 — thanks @TechNickAI
• fix(command-code): preserve literal max effort for command-code provider #9257 — thanks @Chewji9875
• fix(dashboard): open webhook wizard in edit mode #9272 — thanks @khoazero123
• fix(mcp): remove non-standard x-provider field from omniroute_test_combo body #9274 — thanks @Sam280903
• fix(routing): bare model ids route to codex first; validate synced candidates #9275
• fix(mcp): stop DB init logging from corrupting the stdio JSON-RPC stream #9281 — thanks @Sam280903
• fix(reasoning): forward Ollama Cloud thinking #9290 — thanks @xz-dev
• fix(models): reconcile active live model catalogs #9294 — thanks @Zartharas
• fix: update Baichuan website URL to baichuan-ai.com #9312 — thanks @zabrodschiipavel-sketch
• fix(agentrouter): retry on 400 content-blocked + burst guard #9323
• fix:nanogpt model discovery #9326 — thanks @TheFrenchGhosty
• fix(rate-limit): patch Bottleneck doExpire capacity leak #9328 — thanks @HouMinXi
• fix(auth): let an agy request find the connection it authorized #9340 — thanks @HouMinXi
• fix(combo): network errors must not trip provider circuit breaker #9342 — thanks @HouMinXi
• fix(antigravity): propagate switchAuth signal from 429 engine to retry guard #9351 — thanks @HouMinXi
• fix(routing): correct reset-window strategy prioritization (#9330) #9353 — thanks @Iammilansoni
• fix(sse): drop the localDb barrel imports from chat and auth #9380 — thanks @HouMinXi
• fix(providers): enforce gemini-web reasoning and tool constraints (#9356) #9397 — thanks @Iammilansoni
• fix(combo): complete #8400 — preserve full fallback order + per-model account affinity for deterministic combos #9420 — thanks @Chewji9875
• fix(translator): normalize streamed optional tool arguments #9423 — thanks @KittisakT
• fix(providers): correct Codex GPT-5.6 context limits #9432 — thanks @PixmaNts
• fix(usage): stop double-counting cache-read tokens in Command Code executor #9438 — thanks @Stazyu
• fix(deps): bumps transitive deps for 8 CVEs surfaced by vuln-ratchet #9441 — thanks @wgordon17
• fix(ui): preserve request log position #9452 — thanks @xiaoyaner0201
• fix(sse): preserve client cache boundaries when hoisting system roles #9457 — thanks @LeonG606
• fix(providers): switch minimax from claude to openai format so images work #9463
• fix(sse): take the Antigravity output ceiling from the model, not a constant #9482 — thanks @HouMinXi
• fix(docs): add required MDX frontmatter to AGENTROUTER_WAF.md #9503
• fix(quality): prune a stale entry from the ESLint suppressions baseline #9509 — thanks @HouMinXi
• fix(classify): honor upstream retry windows on Gemini free-tier 429s #9513 — thanks @shixi-li
• fix(quality): 2 production bugs + 24 unit base-reds + measured gate ceilings #9529
• fix(providers): support data URL icons #9555 — thanks @xz-dev
• fix(sse): shrink chat.ts back under the frozen file-size cap (base-red drain) #9598
• fix(ci): clear base-reds on release/v3.8.50 (migration collision + 4 masked gates) #9600
• fix(resilience): enforce RPM with rolling leases #9604
• fix(backend): stop reasoning replay placeholder from self-poisoning #9610 — thanks @stanleytejakusuma
• fix(providers): mint a Zed LLM token for zed-hosted model discovery #9628 — thanks @ARC345
• fix(test): reconcile base-drifted test expectations on release/v3.8.50 #9634 — thanks @HouMinXi
• fix(openrouter): scope model failures per-model instead of poisoning the whole connection #9635 — thanks @hartmark
• fix(radar): close the audit gaps — auth, merged feed fields, opt-in state, sidebar gate, size cap + daily scheduler #9686
• fix(ci): clear the NEW base-reds from the 08-06 merge batch (migration collision #2 + broken import) #9688
• fix(codebuddy-cn): replace agent system prompts to bypass Tencent content filter #9723 — thanks @zuckdorsey
• fix(db): resolve migration version 135 numbering collision #9745 — thanks @hartmark
• fix(ci): clear the 08-08 base-red layers — dead-code, prod crash in chat.ts, Responses payload regression, born-red stdio test, gate drifts #9757
• fix(bun): make server child and outbound fetch Bun-safe #9761 — thanks @Arul-
• fix(sse): preserve original body for semantic cache signature — fixes 0% hit rate #9775
• fix(api): validate request bodies with Zod in 4 routes — restores the t06 gate (#9737) #9779
• fix(ci): restore current release test integrity #9819
• fix(ci): close remaining release-green gaps #9835
• fix(proxy): isolate wreq TLS sessions by account #9837 — thanks @agisota
• fix(cursor): SelectedImage blobIdWithData + JPEG soft-cap prep #9840 #9834 — thanks @yansigit
• fix(executors): strip redundant oneOf matching sibling enum #9841 #9828 — thanks @larin-vas
• fix(executors): preserve Command Code usage in Responses streams #9842 #9826 — thanks @MrShitFox
• fix(responses-api): tool call after a text message collided on the same output_index #9843 #9822 — thanks @hartmark
• fix(admission): queue heavyweight chat requests before 503 busy #9845 #9816 — thanks @herjarsa
• [TS7] fix(types): accept synced catalog model rows #9846 #9798 — thanks @backryun
• [TS7] fix(types): normalize DuckDuckGo request messages #9847 #9797 — thanks @backryun
• [TS7] fix(types): expose SQLite transaction state #9848 #9796 — thanks @backryun
• [TS7] fix(types): validate default executor pool config #9849 #9795 — thanks @backryun
• [TS7] fix(types): normalize Gemini Business credentials #9851 #9792 — thanks @backryun
• [TS7] fix(types): preserve Claude thinking body contracts #9852 #9791 — thanks @backryun
• fix(response): strip internal reasoning placeholder from all reasoning fields #9853 #9790 — thanks @adevwithpurpose
• fix(api): enforce model permissions on gateway mirrors #9854 #9788 — thanks @xz-dev
• fix(sse): apply Azure param rules on azure-ai and clamp gpt-4o-mini output tokens #9855 #9787 — thanks @Michael-Rocco-Goldmann
• fix(sse): route claude discovery aliases for catalog-only providers #9856 #9777 — thanks @Michael-Rocco-Goldmann
• fix(i18n): translate validation model keys in 34 locales #9857 #9773 — thanks @Michael-Rocco-Goldmann
• [TS7] fix(skills): normalize web fetch credentials #9859 #9755 — thanks @backryun
• [TS7] fix(types): narrow DeepSeek tool calls #9860 #9751 — thanks @backryun
• fix(pricing): memoize getSyncedPricing() across catalog cache versions #9861 #9746 — thanks @chloeassistant
• fix(logging): use configurable max-depth when bounding logged tool_calls #9865 #9734 — thanks @hartmark
• fix(executors): repair DuckDuckGo AI Chat challenge solver (418 ERR_CHALLENGE) #9866 #9733 — thanks @Mynacol
• fix(compression): persist RTK renderer configuration #9867 #9730 — thanks @isaaclb98
• fix(dashboard): unregister leftover service workers in dev mode #9868 #9727 — thanks @hartmark
• fix(docker): make the webpack build-arg escape hatch actually work #9872 #9695 — thanks @HouMinXi
• fix(providers): per-provider opt-out for anonymous no-auth fallback (opencode-go/zen 401s) #9873 #9675 — thanks @chloeassistant
• fix(providers): reject the dashboard password as a connection API key #9877 #9572 — thanks @HouMinXi
• fix(settings): use provider prefixes in model overrides #9878 #9569 — thanks @xz-dev
• fix(translator): preserve Kimi K3 Responses reasoning #9879 #9556 — thanks @jackjinke
• fix(adobe-firefly): harden CDP warm, risk session, and browser sign-in #9881 #9549 — thanks @artickc
• fix: pass max reasoning effort through by default, add global model registry fallback #9883 #9612 — thanks @Momen4444
• fix(db): resolve CCR migration version collision #9884 #9618 — thanks @fenix007
• fix(compression): add Lite tool truncation toggle #9885 #9629 — thanks @xz-dev
• fix(web-tools): anchor tool contract at prompt tail + user-turn reminder for large prompts #9887 #9693 — thanks @ryan-brosas
• fix(sse): persist per-tool-call JSON escape state across SSE delta chunks #9889 #9704 — thanks @hartmark
• fix(db,combo): renumber ccr_blocks 134→139 + restore antigravity pool filter #9890 #9707 — thanks @matiasbaglieri
• fix(sse): grace period before finalizing a client disconnect as 499 #9891 #9711 — thanks @hartmark
• fix(build): standalone bundle misses LLMLingua dist + onnxruntime native binaries #9892 #9712 — thanks @hartmark
• fix(responses-api): sync reasoning-cache write index with the fixed read side #9895 #9741 — thanks @hartmark
• fix(ci): repair release lint test regressions #9896 #9813 — thanks @alex-jordan547
• fix(command-code): include tool call arguments #9897 #9821 — thanks @Chewji9875
• fix(providers): remove retired NVIDIA NIM catalog entries #9898 #9825 — thanks @Zartharas
• fix(nvidia): keep 410 failures model-scoped #9899 #9833 — thanks @Zartharas
• fix: retry CodeBuddy large-tool requests in compact form #9900 #9542 — thanks @mvanhorn
• fix(quality): clears two release/v3.8.50 base-red gates #9901 #9619 — thanks @wgordon17
• fix: resolve hollow external package directory crashes and implement … #9913 — thanks @SupremeNexas
• fix(i18n): restore Vietnamese locale parity #9925
• fix(combo): classify Cloudflare 1010 fingerprint rejection as non-auth #9929 — thanks @HouMinXi
• fix(image): return Fal images as base64 by default #9932 — thanks @rinseaid
• fix(image): support Fal reference-image edits #9933 — thanks @rinseaid
• fix(db): invalidate LKGP pins on provider connection delete #9936 — thanks @Zartharas
• fix(services): stop embedded-service supervisor retry loop when binary cannot spawn #9937 — thanks @herjarsa
• fix(backend): retain streaming usage for providers with choices:[{delta:{}}] final chunk #9938 — thanks @sadSanta-07
• fix(antigravity): ban-safety hardening — bounded onboarding retries, gate thought-signature bypass sentinel #9939 — thanks @benzntech
• fix(guardrails): vision bridge reroute/pool/self-loop fixes (auto/best-vision, claude-wire base64) #9946 — thanks @herjarsa
• fix(mcp): stop omniroute_get_health silently discarding real data #9959 — thanks @tald26
• fix(build): bump @huggingface/transformers to 4.2.0 + onnxruntime-node 1.24.3 #9962 — thanks @witt3rd
• fix(cleanup): prune mcp_tool_audit/a2a_task_events by created_at column #9963 — thanks @witt3rd
• fix(db): avoid skipping pending job registry migration 146 #9965 — thanks @Zartharas
• fix(video): support Fal-hosted Grok Imagine Video #9969 — thanks @rinseaid
• fix(i18n): escape angle brackets in denoRelayOrgDomainHint across all 43 locales #9976 — thanks @AgnesRiber
• fix(media): support Gemini Omni Flash video #9982 — thanks @rinseaid
• fix(copilot-web): restore browser authentication #9984 — thanks @backryun
• fix(opencode): fallback unsupported DeepSeek json schema output #9992 — thanks @Zartharas
• fix(translator): restore TitleCase tool names on the Claude to Gemini path #9993 — thanks @engmarcosjr
• fix(providers): scope model-level targetFormat to declaring provider catalog #9994 — thanks @Chewji9875
• fix(kimi): apply K3 effort policy to aliases #10005 — thanks @jackjinke
• fix(adobe-firefly) — direct pushes: harden credential parsing and…
• fix(combo/sse) — direct pushes: ignore benign empty error fields…
• fix(logging) — direct pushes: make stream-chunk capture and…
• fix(i18n) — direct pushes: restore/unescape HTML entities in UI…
• fix(providers) — direct pushes: repair the DeepAI registry import…
• fix(deps) — direct pushes: CVE-driven bumps (nanoid, dompurify,…
• fix(ci): pin Build (advisory) to a hosted runner with memory… #10408
• fix(providers): refresh the translate-path golden for the… #10410
• fix(sse): surface Qwen/Alibaba personal Token Plan quota in… #10290
• fix(deps): pin next to an exact version so a fresh upstream… #10340
• fix(types): restore custom model output… #10339 — thanks @backryun
• fix(sse): stop the executor-contract guard from hot-looping… #10373
• fix(types): validate nonstreaming JSON… #10258 — thanks @backryun
• fix(types): narrow refresh token rotation… #10257 — thanks @backryun
• fix(types): normalize executor result… #10256 — thanks @backryun
• fix(types): align Responses stream options #10255 — thanks @backryun
• fix(types): narrow combo credential… #10254 — thanks @backryun
• fix(compression): cap… #10118 — thanks @adevwithpurpose
• fix(ci): clear base-reds on release/v3.8.50 (round 4 #10260
• fix(sse): extract perplexity-web… #10259 — thanks @jeyhunfaslanov
• fix(mcp): persist and re-attach Gemini… #9448 — thanks @Sam280903
• fix(opencode-plugin): respect… #8982 #9316 — thanks @xiaoyaner0201
• fix(providers): raise default provider… #9283 — thanks @Sam280903
• fix(opencode-plugin): stop… #8983 #9042 — thanks @xiaoyaner0201
• fix(opencode): force CLI… #10222 — thanks @adevwithpurpose
• fix(deepseek-web): classify business… #10218 — thanks @Zartharas
• fix(combo): make failoverBeforeRetry… #10217 — thanks @hartmark
• fix(responses): preserve case-insensitive… #10177 — thanks @ddarkr
• fix(discovery): parse reasoning… #10138 — thanks @excessivechaos
• fix(combo): isolate session stickiness… #10137 — thanks @hydraxman
• fix(combo): default chaos SSE to… #10128 — thanks @herjarsa
• fix(kimi): normalize MFJS tool schemas #10079 — thanks @xz-dev
• fix(mcp): move pack validation out of… #10065 — thanks @yansigit
• fix(zed-hosted): send the provider wire… #10051 — thanks @ARC345
• fix(ci): repair and wire the two… #10050 — thanks @ARC345
• fix(reasoning): preserve and replay… #10045 — thanks @jackjinke
• fix(types): tighten chatCore helper… #10175 — thanks @backryun
• fix(cli): read the full provider… #10097 — thanks @amartinawi
• fix(cli): stop swallowing non-2xx… #10092 — thanks @amartinawi
• fix(cli): openapi… #10091 — thanks @amartinawi
• fix(cli): doctor detects prebuilt… #10090 — thanks @amartinawi
• fix(providers): kilo-gateway authType… #10086 — thanks @TengSivtean
• fix(cli): strip inline comments when… #10101 — thanks @amartinawi
• fix(logging): document… #10038 — thanks @hartmark
• fix(dashboard): expose OpenAI Responses… #10121 — thanks @hartmark
• fix(combo): clear LKGP pin when its… #10034 — thanks @hartmark
• fix(sse): provider-response summary… #10037 — thanks @hartmark
• fix(responses-api): tool call after… #10025 — thanks @hartmark
• fix(responses-api): explicit… #10041 — thanks @hartmark
• fix(kimi): recupera limite temporario… #10058 — thanks @bortolidiego
• fix(translator): preserve Responses… #10114 — thanks @mtb-ninja
• fix(providers): xai-oauth… #10165 #10170 — thanks @nordz0r
• fix(ollama-cloud): map xhigh reasoning… #10160 — thanks @Chewji9875
• fix(translator): strip Codex encrypted… #10053 — thanks @XDayonline
• fix(combo): preserve OpenCode Free oc/… #10180 — thanks @AStupidBear
• fix(sse): apply free-tier filter to… #10199 — thanks @ggdayup
• fix(providers): default missing… #10221 — thanks @jeff-alves
• fix(ci): clear base-reds on release/v3.8.50 (round 3 #10213
• fix(security): correct XML double-unescape and non-CSPRNG… #10154
• fix(docker): eliminate npm-bundled CVEs from the published… #10182
• fix(security): resolve open CodeQL alerts #10188
• fix(dashboard): retarget Kimi promo CTA to the API platform… #10200
• fix(build): repair broken production build, red lint gate and… #10198
• fix(cli): repair hollow externalized package dirs in the nested… #7346
• Electron packaged smoke test: add a cold-restart mode… #7592
• fix(usage): keep session/weekly/monthly quota windows in… #7764
• fix(images): retry Codex image generation on a sibling ChatGPT… #8307
• fix(dashboard): treat UncloseAI as a no-auth provider so the… #8864
• fix(dashboard): model-level allowed/blocked param edits now… #9013
• fix(ssrf): make getProviderOutboundGuard (used for… #9123
• fix(compression): preserve unfenced raw code (e.g. Copilot #file… #9144
• fix(api): yield the event loop during catalog builds and bulk-load… #9147
• fix(combo): recovery hint for all_targets_skipped now points at… #9303
• fix(providers): strip uniqueItems from Gemini tool schemas (Gemini… #9617
• fix(translator): convert OpenAI image_url blocks nested in… #9692
• fix(resilience): retry a retryable Codex pre-output… #9708
• fix(ratelimit): respect operator minTimeBetweenRequestsMs… #9763
• fix(test): remove live npm pack from MCP files unit… #3578 #3821
• fix(dashboard): media mini-playgrounds authenticate via session… #9935
• fix(sse): exclude search providers from credential-health… #9970
• Passthrough streaming: stop leaking upstream SSE control lines… #10017
• fix(cli): stop diagnosing every Next.js instrumentation-hook… #10028
• fix(build): stop the native… #10060 — thanks @latest
• fix(providers): the five g4f.space… #10071 — thanks @chirag127
• fix(chatgpt-web): Preserve native max… #10077 — thanks @zannen7
• Fix: wire AgentRouter's existing console balance fetcher into the… #10078
• Fix: AgentRouter's dollar balance now renders as a… #10078
• fix(sse): bridge generic openai-compatible/anthropic-compatible… #10085
• fix(domain): stop treating an unreported Antigravity quota… #10095
• fix(dashboard): remap unified Kimi Code card API-key save to the… #10096
• fix(antigravity): strip trailing model turn for native Gemini… #10104
• fix(admission): stop the adaptive latency-gradient collapse… #10111
• fix(sse): downgrade client-supplied thinking:{type:"adaptive"}… #10119
• fix(logging): move call-log artifact serialization and… #10123
• perf(logging): bound each scheduled call-log rotation pass to… #10125
• fix(streaming): start early SSE heartbeats when Responses or… #10127
• fix(combo): scope session-stickiness bindings to their owning… #10136
• fix(translator): resolve the Claude thinking output cap with… #10139
• fix(providers): correct the conol-web registry fallback-models import…
  non-existent open-sse/config/services/ and made any suite loading the provider registry fail to
  resolve (#10140)
• fix(oauth): Claude connections created via… #10144 #10143
• fix(sse): Responses-passthrough response.completed snapshots… #10156
• fix(proxy-subscriptions): allow local/loopback proxy-subscription… #10158
• fix(routing): keep approximate Combo… #10162 — thanks @xz-dev
• docs(settings): document Thinking Budget modes (passthrough vs… #10169
• fix(cli): guarantee a non-empty [STARTUP] Fatal: log line for… #10171
• fix(sse): gate structural chat admission shedding on real… #10183 #10268
• fix(guardrails): Vision Bridge handles… #10202 — thanks @Zartharas
• fix(cursor): Stop truncating pending tool calls on… #10215
• fix(responses): repair corrupted SSE deltas for non-ASCII… #10223
• fix(combo): defer the known-context-overflow hard rejection… #10225
• fix(api): deleting a… #3199 #3782 #10228 — thanks @Neuron-Mr-White
• Audio Bridge: fix production transcription self-loop uploads… #10229
• fix(api): DeepSeek V4's native… #10230 — thanks @Neuron-Mr-White
• fix(providers): FreeAIAPIKey now targets… #10233
• fix(providers): MonsterAPI's deprecation now actually applies… #10234
• fix(cliproxy): read platform/arch at runtime via… #10244
• fix(providers): compatible/custom providers… #10247 — thanks @xz-dev
• fix(models): custom model metadata and… #10248 — thanks @jackjinke
• fix(open-sse): stop concurrent requests colliding on the same… #10249
• fix(translator): Text-format tool calls emitted inline by some… #10251
• fix(dashboard): make provider card warning indicators expose the… #10261
• fix(command-code): route chat to the documented… #10265
• fix(providers): preserve validator HTTP… #10272 — thanks @Zartharas
• fix(sse): tiny-budget reasoning… #10281 — thanks @harkaranbrar7
• fix(video): stop advertising the googleflow (Veo) video provider… #10285
• fix(build): stop Turbopack from dead-code-eliminating the… #10293
• fix(ops): Docker HEALTHCHECK defaults to the lightweight… #10311
• fix(api): hash the API key before using it as the model-catalog… #10313
• fix(resilience): keep combo quality and auth failure reasons… #10314
• fix(dashboard): send periodic WS heartbeat pings so live… #10319
• fix(chat-body-admission): restore a single process-wide… #10110
• fix(providers): validate Z.ai web Local… #10329 — thanks @Zartharas
• fix(opencode-plugin): publish bare combo model ids without the… #10345
• fix(backend): log auto/<family> matched no connected models… #10346
• fix(backend): redact client IPs and account prefixes from default… #10348
• fix(github): proactive credential… #10352 — thanks @RaviTharuma
• fix(docker): warn at boot when OMNIROUTE_MEMORY_MB disagrees… #10353
• fix(providers): GitLab Duo falls back to the public Code… #10365
• fix(db): getSettings defaults… #10372 — thanks @lamchun1110
• fix(translator): Consolidate tool-name casing… #7926 #8979 #10374
• fix(responses): preserve native tool definitions for custom… #10374
• fix(dashboard): Free Tier 'used this month' now includes live… #10381
• fix(executors): OpencodeExecutor and MimocodeExecutor now… #10393
• fix(sse): the header-budget drop… #10397 — thanks @lamchun1110
• fix(sse): fail over combo streaming responses that reach… #10404
• fix(guardrails): Vision Bridge now reroutes… #10415 — thanks @rqzbeh
• fix(antigravity): geo-blocked egress… #10420 — thanks @rqzbeh
• fix(antigravity): strip competing-agent… #10420 — thanks @rqzbeh
• fix(antigravity): accounts with an empty… #10424 — thanks @rqzbeh
• fix(antigravity): Google deprecated… #10424 — thanks @rqzbeh
• fix(usage): read Gemini usageMetadata… #59 #10430 — thanks @rqzbeh
• fix(usage): surface Gemini… #10430 #10465 — thanks @rqzbeh
• fix(antigravity): automatically… #10424 #10470 — thanks @rqzbeh
• fix(mitm): forward passthrough traffic to the actual requested… #10479
• fix(docker): point the bifrost sidecar at the real… #10482
• fix(sse): stop ZWJ-obfuscating the substring "hermes" in user… #10484
• fix(memory): auto-check Qdrant health on mount and stop the… #10489
• test(compression): align source-contract tests with the merged… #10489
• fix(cli): use 127.0.0.1 for the readiness health-check poll… #10508
• fix(providers): zed-hosted OAuth now… #10517 — thanks @phatchau036
• fix(providers): allow token-backed web… #10518 — thanks @Zartharas
• fix(providers): test token-backed web… #10519 — thanks @Zartharas
• fix(compliance): redact additional… #10521 — thanks @Zartharas
• fix(providers): register a real Firefly auth probe under both the… #10522
• fix(services): isolate probeBeforeSpawn adoption tests on… #10523
• fix(sse): auto-replay a bounded multi-turn trajectory in the… #10527
• fix(network): direct (no-proxy) egress now bounds each… #10214
• fix(models): align Codex GPT-5.6 context limits with the Codex… #10530
• fix(deps): upgrade… #10536 — thanks @atjsh @tensorflow @huggingface
• fix(deepseek): Advertise none, low,… #10540 — thanks @jackjinke
• fix(a2a): use a constant-time bearer compare in… #10544
• Preserve portable plaintext reasoning by default across… #10550 #10959
• fix(dashboard): show the real model count on the "List Models"… #10553
• fix(cli): ignore the operating… #10557 #10492 — thanks @redzrush101
• fix(providers): OpenCode x-opencode-session now derives a… #10571
• fix(mcp): make GitHub skill tools discoverable through…
• fix(providers): remove 10 retired model ids from the crof seed… #10577
• fix(audio): when a prefix-matched STT provider has no… #10583
• fix(sse): resolve the short provider-alias prefix (e.g. el/)… #10586
• fix(sse): map OpenAI-compat voice names to real ElevenLabs… #10589
• fix(dashboard): route the Playground's ChatTab "Send" through the… #10592
• fix(providers): Magnific Mystic is now the canonical provider… #10594
• fix(sse): Include the redacted upstream error body in the… #10597
• fix(xai): trim Chat Completions messages and Responses… #10601
• fix(cli): derive the machine-id token correctly under plain… #10612
• fix(cli): omniroute setup --add-provider --api-key <key> no… #10613
• fix(dashboard): make /api/models agree with /v1/models on… #10615
• Combo routing: await each connection's token limit before… #10686
• fix(guardrails): resolve the public provider alias before… #10702
• fix(dashboard): filter the Modality Bridge Vision model picker to… #10703
• fix(usage): repair provider-reported input_tokens: 0 on… #10705
• fix(cli): distinguish a CLI-probe timeout from a genuinely… #10710 #10711
• fix(cli): pass --allow-scripts for the runtime's own… #10713
• fix(db): filter getProviderMetrics to providers with a live… #10714
• fix(proxy): keep password-only proxy credentials instead of… #10720
• fix(executors): the Meta AI (muse-spark-web) WebSocket… #10727
• fix(providers): copilot-m365-web chat… #10732 — thanks @acc0mplish
• fix(catalog): stop counting getTokenLimit's generic 128k… #10734
• fix(search): name /v1/search 502s with provider id and… #10735
• fix(db): pause call-log rotation and record SQLITE_CORRUPT on… #10736
• fix(compression): skip the expensive createCompressionStats… #10765
• fix(api): /api/cache/stats reported the… #9446 — thanks @Poid-ZA
• fix(logging): the app log is filterable and readable again. Entries…
• fix(analytics): Claude Code… #10774 — thanks @electrumguy
• fix(db): periodically run wal_checkpoint(TRUNCATE) so the… #10781
• fix(sse): replace LiveWS's application-only liveness check with a… #10782
• fix(open-sse): declare supportedThinkingEfforts… #10788
• fix(resilience): scope the same-account transport retry out of… #9708
• fix(opencode-plugin): respect log level… #10798 — thanks @tientien17
• fix(providers): Keep NVIDIA timeout… #10799 — thanks @Zartharas
• fix(db): disambiguate createProviderConnection's OAuth email… #10815
• fix(oauth): stop treating the Kiro profile ARN as an account… #10815
• fix(images): register OpenAI dall-e-3 in the image registry… #10832
• fix(security): Outbound URL guard now… #10843 — thanks @ntdat812
• fix(config): exclude cookie-auth image bridges (chatgpt-web,… #10848
• fix(api): POST /v1/search now replies with a named `Unknown… #10849
• fix(api): alias GET/HEAD /readyz to /healthz so… #10850
• Document the conditional management authentication and 401/403…
• fix(i18n): The "Disabled" status… #10812 #10853 — thanks @ntdat812
• fix(skills): Marketplace-installed… #10854 — thanks @kriptoburak
• fix(catalog): /v1/models no… #10831 #10857 — thanks @ntdat812
• fix(context): Base64 file payloads… #10840 #10858 — thanks @ntdat812
• fix(mcp): MCP tool calls that wait on a model provider no longer…
• fix(providers): importing models with an expired API key… #5460 #5465
• fix(api): reject a combo update that removes every model, and… #10866
• fix(proxy): proxy "Test connection" no longer reports an… #1255
• fix(cli): warn when a .env line never takes effect, and stop… #10870
• fix(db): Remove stale MiMoCode provider… #10873 — thanks @Zartharas
• fix(sse): getResetAwareProvider and the auto-combo quota… #10877
• fix(provider-health): Keep unsupported… #10878 — thanks @Zartharas
• fix(antigravity): map Gemini 3.7… #10882 — thanks @adevwithpurpose
• fix(memory): enable agent memory… #10887 — thanks @Egorich-print
• fix(perplexity-web): make the… #10902 #8634 — thanks @danscMax
• fix(providers): the loopback readiness gate no longer… #10903
• fix(relay): the Cloudflare… #4643 #1360 #6149 — thanks @evil
• fix(build): the next Docker… #10936 #10933 — thanks @arminanton
• fix(cli): always emit limit.output in generated OpenCode config… #10940
• fix(relay): the private/loopback guard the three proxy-relay… #6149
• Account rotation: make fallbackStrategy: "least-used"… #10945
• Desktop auto-update (Windows): stop the in-app updater 404ing… #10947
• Preserve explicit plaintext reasoning when a Responses… #10949 #10959
• fix(catalog): preserve provider-declared… #10953 — thanks @xz-dev
• fix(cli): combo create accepts --models and no longer creates… #10954
• fix(cli): resolve $ref path params and add PATCH combos… #10955
• fix(sse): default single-target incompatible reasoning to drop… #10959
• fix(sse): combo diagnostics no longer truncate… #10967
• fix(sse): combo terminal failures caused entirely by… #10966
• fix(search): skip catalog-default SearXNG… #10976
• fix(command-code): surface reasoning-only output as content when… #10986
• fix(ci): clear inherited release/v3.8.50 quality-gate reds… #10988
• fix(ci): clear remaining release/v3.8.50… #9147 #10501 #10988
• Static model catalog for v0-vercel-web: seed a static catalog… #10990
• fix(providers): mark the blackbox provider deprecated —… #10997
• fix(providers): validate Dify keys against its native… #11002
• fix(accounts): markCooldown now… #11008 — thanks @maxmad64bis
• fix(providers): route terminal… #11009 — thanks @maxmad64bis
• fix(codex): drop non-standard… #11014 — thanks @RaviTharuma
• fix(resilience): count heavyweight… #11015 — thanks @RaviTharuma
• fix(startup): log `Credential health… #11016 — thanks @RaviTharuma
• docs(api-keys): document that… #2289 #11017 — thanks @RaviTharuma
• fix(webhooks): remove 3 declared-but-never-emitted events…
• fix(providers): filter Perplexity model import to the Sonar… #11060
• fix(claude): restore canonical tool names… #11085 — thanks @linhdmn
• fix(resilience): filter chat connection selection by each… #11089
• fix(install): make the ONNX dependency chain optional so… #11095
• fix(providers): Reject silent validation degradation on… #11101
• Autopilot suggestion counter: the combo health autopilot… #11102
• Config audit persistence: persist the configuration audit… #11103
• fix(sse): resume mid-stream recovery after a completed tool… #11109
• fix(providers): reasoning_effort now… #11116 — thanks @maxmad64bis
• fix(sse): parallel function_call items in a Responses API… #11144
• fix(analytics): opencode-go is now… #11149 — thanks @electrumguy
• fix(dashboard): keep open-sse/config/providerRegistry.ts… #11122 #11154
• Combo create: creating a routing combo without any model is now…
• fix(resilience): a missing-model… #11165 — thanks @yourspraveen
• fix(routing): a custom… #11180 — thanks @marcs7
• fix(routing): the Routing tab's "last known good provider"… #11181
• fix(ollama): Ollama Local models are… #11271 — thanks @yourspraveen
• fix(providers): Antigravity OAuth marks connects with no Cloud… #11284
• fix(translator): preserve omitted… #11297 — thanks @ofonseca-pyming
• fix(db): group model patterns escape regex metacharacters, so… #11311
• fix(db): the upstream proxy URL check judges the host by… #11319
• fix(i18n): three pt strings had dropped their placeholders… #11325
• fix(kie): map the remaining google-imagen/* KIE… #11225 #11326
• fix(security): proxy-authorization and proxy-authenticate… #11328
• fix(video-bridge): fall back to the deterministic… #11344
• fix(translator): Codex Responses tool calls translated for… #11347
• fix(video-bridge): burn high-contrast timestamps into every… #11350
• fix(video): fingerprint protected Video Bridge bytes, coalesce… #11362
• fix(catalog): keep large /v1/models builds responsive by… #11367
• fix(video): apply the caption-frame cap after bounded visual… #11382
• Live dashboard: honour the WebSocket port reported by… #11331
• fix(dashboard): Model Database sync… #11394 — thanks @An0nym0us92
• fix(api-manager): Allowed Combos can now be restricted to zero…
• fix(build): tolerate a same-realpath symlink or stale-typed dest in the…
• fix(auto): rate-limit auto/<family> matched no connected models…
• fix(cli): drop the orphaned resolveOpencodeConfigDir… #10246 #9985
• fix(ci): make Build (advisory) produce a signal again — pinned to a…
• fix(api): hash API keys in the /v1/models catalog cache Map key so…
• fix(providers): register live OpenRouter… — thanks @RaviTharuma
• fix(translator): merge consecutive same-role contents in direct…
• fix(cli): omniroute update now finds npm… #52554 #5379 #5542 #11335
• fix(cline): Preserve client-supplied Cline task IDs and omit the…
• Hardened the Codex app-server transport after the post-merge… #11205
• fix(codex): prefer max_context_window over the context_window…
• fix(catalog): derive combo reasoning-effort tiers from the exact…
• fix(combo): evict in-memory session-stickiness bindings when a combo…
• fix(combo): resolve effort-suffixed command-code variants (e.g.…
• fix(db): the compression_run_telemetry retention sweep… #6848 #9625
• fix(compression): use pathToFileURL in compressionWorkerPool so…
• fix(db): database settings API no longer returns HTTP 500 on SQLite…
• fix(discovery): parse upstream reasoning tiers nested under…
• fix(ops): Docker HEALTHCHECK probes lightweight /healthz instead…
• fix(api): /v1/embeddings 400s for native… — thanks @RaviTharuma
• fix(sse): keep Codex/Anthropic quota headers under the upstream…
• fix(usage): z.ai/GLM coding-plan subscription keys now render their…
• fix(auth): a connection's lastError now names the real upstream…
• fix(live-ws): the Live dashboard socket can now be pointed at… #11331
• fix(sse): MiniMax music models now generate audio instead of failing…
• fix(models): honor MODELS_DEV_SYNC_ENABLED=0 as a hard kill switch…
• fix(providers): when OPENCODE_SYNTHESIZE_CLI_HEADERS=true, a… #5997
• OpenCode config merge: stop mergeOpenCodeConfig splaying a…
• fix(models): a model synced from a provider's own /models…
• fix(providers): Claude Code /… — thanks @jeff-alves
• fix(electron): desktop window stays hidden on Windows because the…
• fix(executors): OpencodeExecutor rotates (or retries once on a…
• fix(cli): recognize native… #10227 — thanks @tito13kfm
• fix(i18n): complete Vietnamese translations for recently added UI… #9985
• fix(api): repair broken @/lib/db/connections import in the… #10939
• chore(docs): regenerate PROVIDER_REFERENCE and refresh README diagram…
• chore(lint): prune ESLint suppressions orphaned on the release branch
• fix(build): #9011 #9982 #9969 #9199 #8728 #8736 #10087 #8974 #7682 #9173
• fix(security): harden three secret-leak paths surfaced by an audit…
• fix(db): the sql.js fallback now publishes the database atomically…

• fix(sse): #10441 #11152 #11151 #10475 #10980 #10805 — thanks @geek007git @maxmad64bis @HouMinXi @linhdmn @minhlongs
• fix(sse): #11043 #11110 #11129 #10330 #10806 — thanks @maxmad64bis @hartmark @xz-dev
• fix(sse): #11209 #11214 #10803 #10457 #11113 — thanks @linhdmn @Kizuno18 @HouMinXi @ggdayup
• fix(sse): #11194 #10445 #11047 #10435 #10632 #10650 #10450 #10434 #10691 #10674 — thanks @jonlwheat2-gif @killmonger2317-coder @maxmad64bis @octo-patch
• fix(sse): #11177 #10545 #10684 #10978 #10306 #10488 — thanks @rqzbeh @NahuSaruf @cryptiklemur @maxmad64bis @RaviTharuma
• fix(sse): the Adobe Firefly… #11387 #11386 — thanks @HouMinXi
• fix(providers): #11375 #11123 #11262 #11117 #11055 #10356 #10566 #10634 — thanks @ggdayup @rqzbeh @rizxfrog @backryun @RaviTharuma
• fix(providers): reasoning-effort… #11274 #11305 — thanks @linhdmn
• fix(providers): #11309 #11302 #10862 #10971 #10072 #10471 #11049 #10973 #10974 — thanks @ntdat812 @RaviTharuma @xz-dev @sha367 @maxmad64bis
• fix(resilience): #11355 #11310 #10534 #11078 #11267 #11075 #10506 #11020 — thanks @sprintberlin @SnCr90 @rqzbeh @yourspraveen @hartmark @RaviTharuma
• fix(quota): #11353 #11378 — thanks @sprintberlin @Neuron-Mr-White
• fix(combo): #11360 #10463 #10456 #11036 #10907 #10846 #10016 — thanks @sprintberlin @herjarsa @asorourx @excessivechaos @HouMinXi @fenix007
• fix(auto): #10820 #10344 #11400 #11399 — thanks @RaviTharuma @jacobsparts
• fix(routing): #11107 #11198 #11193 #10124 — thanks @SCys @pacocartones @benzntech
• fix(models): #10957 #10898 #11397 #11307 #10533 #10299 #10055 — thanks @Neuron-Mr-White @rqzbeh @marcelokarval @ekinnee @jackjinke @RaviTharuma
• fix(catalog): #10963 #10723 #11337 — thanks @xz-dev @stanleytejakusuma
• fix(pricing): #10635 #10636 #11210 — thanks @stanleytejakusuma @xyzs996
• fix(api): #10657 #10654 #10769 #10663 #10253 #10772 #10607 #10565 #11162 #11081 — thanks @maxmad64bis @HouMinXi @dpozimski @sadSanta-07 @pucedoteth @RaviTharuma @AndrianBalanescu
• fix(security): #11429 #11418 #11261 #10888 #11293 #11040 #11028 #10738 #10739 #10380 #11189 — thanks @HouMinXi @rqzbeh
• fix(authz): exact public routes are matched exactly instead of… #11417
• fix(auth): #11376 #11175 #10899 #10614 — thanks @ntdat812 @rqzbeh @MeRezaRezaei
• fix(oauth): #11141 #10725 #10620 — thanks @HouMinXi @MichaelYcJo @krishna3554
• fix(cli): #11374 #11332 #11238 #10835 #11263 — thanks @ntdat812 @pacocartones @adevwithpurpose
• fix(cli): #11173 #11079 #11054 #10572 #10468 #10447 #11264 — thanks @rqzbeh @hydraxman @xiaoyaner0201
• fix(dashboard): #11407 #11402 #11067 #11056 #10872 #10452 #10448 #10449 — thanks @jacobsparts @rqzbeh @Rahulsharma0810
• fix(live-ws): the… #11377 #11269 — thanks @ntdat812 @Minamaged18
• fix(db): #10979 #10709 #10552 #10278 #10423 #10432 — thanks @RaviTharuma @jonlwheat2-gif @excessivechaos @maxmad64bis
• fix(build): #11159 #10836 #10776 #11266 #10695 — thanks @aliyosufi @adevwithpurpose
• fix(docker): #11419 #10818 #10288 — thanks @RaviTharuma @anudeepadi
• fix(electron): the embedded server is… #10717 — thanks @echoriver89
• fix(compression): #11364 #11084 #10807 #10660 #10834 #10498 #10655 — thanks @TheDemonTuan @HouMinXi @blackwell-systems @stanleytejakusuma @adevwithpurpose @abhijeetnardele24-hash
• fix(translator): #11365 #10658 #10392 — thanks @Siva010 @giauphan
• fix(gemini): a missing items schema… #10605 — thanks @sadSanta-07
• fix(codex): #11179 #11041 #10608 #10573 #10838 #10946 — thanks @excessivechaos @jackjinke @JxnLexn @HouMinXi @YunyunZhai
• fix(opencode): #10874 #11004 #11385 #11133 #10821 #11199 — thanks @zoser69 @ntdat812 @AStupidBear @maxmad64bis @RaviTharuma @pacocartones
• fix(executors): #11158 #10402 #10694 — thanks @maxmad64bis @excessivechaos
• fix(search): #10901 #11125 #10756 #10981 #11097 — thanks @rqzbeh @RaviTharuma @Egorich-print
• fix(mcp): #11139 #10860 #10575 #10209 — thanks @HouMinXi @ntdat812 @branben @sadSanta-07
• fix(memory): a mid-conversation… #11303 #11114 — thanks @ggdayup
• fix(embeddings): an account is… #10529 #11260 — thanks @HouMinXi
• fix(video-bridge): structural segment sampling is validated, contact…
• fix(images): #10847 #10363 #10554 — thanks @RaviTharuma @tiangao88 @rinseaid
• fix(fusion): the vision-compatibility filter is applied to… #10737
• fix(proxy): #11182 #10868 #10664 #10416 — thanks @rqzbeh @ntdat812 @maxmad64bis
• fix(relay): one… #10941 #10935 #10797 — thanks @ntdat812
• fix(logging): #10770 #10331 — thanks @maxmad64bis @hartmark @benzntech
• fix(logs): #11082 #10685 — thanks @AndrianBalanescu @cryptiklemur
• fix(webhooks): three… #11050 #11130 — thanks @maxmad64bis
• fix(antigravity): #10422 #10376 #10436 — thanks @JxnLexn @Chewji9875
• fix(adobe-firefly): sessions renew through… #9255 — thanks @artickc
• fix(cline): #10279 #10706 #11132 — thanks @arafatkatze @rqzbeh
• fix(agentrouter): the protocol is inferred from the client endpoint,…
• fix(services): the… #10371 #10459 — thanks @tkgo11 @aron-intframe
• fix(monitoring): #10370 #10307 #10827 #10699 — thanks @tkgo11 @RaviTharuma
• fix(github): GitHub access tokens are… #11320 — thanks @RaviTharuma
• fix(i18n): #11339 #11322 #10546 #9721 #11208 — thanks @pacocartones @rizxfrog @dionjoshualobo
• fix(chat): the… #11304 #10394 #10438 — thanks @azzaouiomar19-sketch
• fix(providers): #11026 #10733 #10810 #10458 #11045 #10116 #10637 #11088 #10904 #10584 #10186 #11207 #10894 — thanks @sanforex24h @InkshadeWoods @Hsia97 @benzntech @MeRezaRezaei @Chewji9875 @backryun @yourspraveen @RaviTharuma @Tushar49 @rafacpti23 @rqzbeh
• fix(radar): feature availability… #10487 #10464 — thanks @backryun
• fix(usage): quota windows are ordered… #11241 — thanks @pacocartones
• fix(files): the list limit… #10673 #11059 — thanks @pacocartones
• fix(onboarding): the setup wizard… #10855 — thanks @krishna3554
• fix(settings): #10890 #10525 — thanks @rqzbeh @HouMinXi
• fix(conversations): the reconnect… #10800 — thanks @adevwithpurpose
• fix(reasoning): compatible response… #10574 — thanks @jackjinke
• fix(agent-bridge): the regenerate-cert… #10715 — thanks @ntdatt812
• fix(api-manager): empty combo restrictions… #10066 — thanks @xz-dev
• fix(db): the Database settings page no… #10558 — thanks @TechNickAI
• fix(models): health-check-excluded… #10026 — thanks @ritheshcn25
• fix(skills): the CLI skills left stale by the quota… #10698
• fix(mcp): CLI MCP call protocol issues… #10960 — thanks @YunyunZhai
• fix(dashboard): expert mode in the Combo Builder can type… #8875 #8285
• fix(sse): a combo step pinned to an explicit connection (or a… #8875
• fix(cli): the local CLI sees the full /api/monitoring/health… #11040
• fix(search): a configured search connection (Serper, Brave,… #11524
• fix(api): /v1/models no longer blocks the stale… #11551 #10198 #8728
• fix(sse): a universal handoff whose summary comes back… #11552

📝 Maintenance

• refactor(providers): removed the Puter provider (id puter, alias…
• fix(types): preserve the client response format contract while… #8484
• Preserve the Responses API transform options contract under TypeScript…
• fix(types): preserved the known first-failure record while… #8484
• fix(types): reuse the validation failure predicate when… #8484
• fix(types): preserve the literal `capabilities.vision:… #9121 #8484
• chore(quality): add an RTL layout ratchet… #3541 #8828 — thanks @lukiod
• chore(sse): dropped the leftover iflow entry from the… #8966
• chore(ci): removed two fork-owned image-publish workflows that… #8967
• test(ci): fixed the intermittent spawnSync bash EPIPE failure… #8977
• refactor(providers): removed the retired GitHub Models provider… #9023
• test(sse): added the first test suite for…
  module was hotspot #7 in the coverage plan at 11.28% lines with no dedicated test; the 14 pure
  detectors are now pinned edge-to-edge (token ladders, per-domain max-not-sum scoring, and the
  min/max clamps), taking the file to ~100% line coverage. The suite also documents two quirks
  left unchanged: detectReasoningDepth scores above 0 on marker-free input via its
  always-applied message-depth bonus, and detectErrorContext returns non-integer scores because
  it never rounds (#9063)
• fix(types): preserved the Veo polling delay promise result as… #9104
• fix(types): imported compression analytics statistics from… #9105
• chore(types): align semantic cache signature inputs with the… #9117
• fix(types): narrowed non-streaming chat response metadata… #9118
• docs(readme): replace Roo Code branding with… #9229 — thanks @taltas
• chore(ci): stopped dependabot from grouping ioredis majors… #9425
• chore(tests): cleared two… #9064 #9488 — thanks @typescript-eslint
• test(cli): OpenCode plugin suite realigned to the… #9178 #9175 #9614
• Removed the unused RadarReferrals type export left by the… #9697 #9738
• Reconcile the final v3.8.50 bundle-size and file-size ratchets… #9839
• chore(quality): expand all file-size baselines by +30% ahead of… #9950
• fix(quality): tighten eslintWarnings baseline 5000->0 to match the…
• [v3.8.50] feat: add RTL layout compatibility CSS (fixes #7680) #7987 — thanks @Dingding-leo
• [v3.8.50] feat(devin-desktop): replace public Windsurf provider #8228 — thanks @backryun
• [v3.8.50] feat(ci): extend i18n glossary-consistency gate to ko #8244 — thanks @MichaelYcJo
• [v3.8.50] test(tail): realign 3 stale base-red guards + note 2 env-only false positives (slice 6) #8263
• [v3.8.50] feat(ui): add global model search to Combo builder #8285 — thanks @corefusiion
• [v3.8.50] feat: extract CloakBrowser/browser-pool into optional plugin package #8299 — thanks @oyi77
• [v3.8.50] fix(i18n): clean up and naturalize Spanish translations #8339 — thanks @Dragost
• [v3.8.50] fix(compression): bound session-dedup suffix-block scan to prevent OOM #8438 — thanks @adrianojiu
• [v3.8.50] Fix Z.ai web browser transport and model capabilities #8451 — thanks @backryun
• [v3.8.50] feat(services): add Dario as a 5th embedded service (Claude Code toggle/failover) #8523 — thanks @seanford
• [v3.8.50] fix(adobe-firefly): live x-arp-session-id / Arkose wire (stop HTTP 408) #8571 — thanks @artickc
• [v3.8.50] fix(adobe-firefly): durable session, Chrome recovery, browser sign-in #8578 — thanks @artickc
• [v3.8.50] fix: passthrough non-standard cache token fields for DeepSeek / MiniMax / Bedrock across streaming, non-streaming, and Dashboard paths #8591 — thanks @ikelvingo
• [v3.8.50] fix: treat zero-reset Antigravity 429s as transient #8626 — thanks @costaeder
• [v3.8.50] fix: enforce OpenAI model lifecycle without silent reroutes #8627 — thanks @backryun
• [v3.8.50] fix(claude): preserve signed thinking turns during obfuscation #8629 — thanks @costaeder
• [v3.8.50] fix(antigravity): lock full quota per exact model #8630 — thanks @costaeder
• [v3.8.50] fix(errorConfig): add status 499 metadata mapping (fixes #8535) #8640 — thanks @Dingding-leo
• [v3.8.50] fix(auth): accept x-api-key without anthropic-version for claude-code user-agent (fixes #8655) #8678 — thanks @Dingding-leo
• [v3.8.50] fix(open-sse): add 'has been exhausted' to CREDITS_EXHAUSTED_SIGNALS (fixes #8631) #8704 — thanks @Dingding-leo
• [v3.8.50] fix(github): honor per-model targetFormat override for Copilot custom models #8713 — thanks @Witroch4
• [v3.8.50] fix(test): revive orphaned vitest tests and fix CI routing #8718 — thanks @MohitRawat017
• [v3.8.50] feat(providers): add support for TinyCMS Web #8736 — thanks @jhordanjw123
• [v3.8.50] feat(memory): MemoryBackend provider pattern with generic HTTP connector #8752 — thanks @oyi77
• [v3.8.50] refactor(db): add combo repository boundary #8757 — thanks @xiaoyaner0201
• [v3.8.50] fix(test): revive orphaned open-sse vitest tests #8772 — thanks @MohitRawat017
• [v3.8.50] fix(open-sse): filter non-numeric values in comboTargetLimits before min calculation #8774 — thanks @Dingding-leo
• [v3.8.50] feat(compression): add Italian (it) Caveman rule pack #8776 — thanks @Anjielon
• [v3.8.50] feat(combo): add maxContextWindow to contextRequirements (fixes #8777) #8790 — thanks @Dingding-leo
• [v3.8.50] feat(images): add POST /v1/images/upscale (Adobe Firefly Topaz + Stability + Topaz Labs) #8791 — thanks @artickc
• [v3.8.50] fix(providers): drop dead Cloudflare Workers AI free catalog IDs (#8717) #8804 — thanks @DinonowDev
• [v3.8.50] fix(sse): stop fabricating encrypted Codex reasoning summary text #8807 — thanks @Prudhvivuda
• [v3.8.50] fix(backend): update Cloudflare Workers AI model catalog & remove dead model IDs (#8717) #8808 — thanks @Dingding-leo
• [TS7] [v3.8.50] refactor(db): preserve normalized combo model types #8809 — thanks @backryun
• [v3.8.50] fix(db/apiKeys): respect provider parameter in group model permission checks (fixes #8803) #8817 — thanks @Dingding-leo
• [TS7] [v3.8.50] fix(types): preserve browser abort handling #8818 — thanks @backryun
• [v3.8.50] feat(cli): deliver the Antigravity credential straight to the remote install #8834
• [v3.8.50] docs: slim AGENTS.md #8839 — thanks @MumuTW
• docs(guides): add Antigravity (Google One AI) onboarding guide #8904 — thanks @HouMinXi
• [v3.8.50] fix(usage): reject impossible provider token counts #8927 — thanks @artickc
• Treat context metadata as a routing hint #8944 — thanks @JxnLexn
• docs(db): specify MySQL conformance semantics #8947 — thanks @rushsinging
• Add native ChatGPT Web provider for Codex clients #8949 — thanks @JxnLexn
• i18n(ru): complete Russian locale — 100% coverage #9001 — thanks @Egorich-print
• docs(troubleshooting): document the chat_admission_busy 503 and how to tune heavyweight chat concurrency #9021 — thanks @xiaoyaner0201
• Security: Update Redis to fix critical vunerability #9065 — thanks @tuxmonteiro
• [TS7] fix(types): validate chat context estimation inputs #9084 — thanks @backryun
• [TS7] fix(types): narrow stream response output #9086 — thanks @backryun
• docs: clarify free-provider model refresh outcomes #9087 — thanks @AbdullahFageeh
• [TS7] [v3.8.50] fix(types): preserve SSE tool call function shape #9090 — thanks @backryun
• [TS7] fix(types): narrow CCR store rejections #9091 — thanks @backryun
• [TS7] fix(types): preserve array-buffer response bodies #9092 — thanks @backryun
• [TS7] fix(types): narrow media generation failures #9093 — thanks @backryun
• [TS7] fix(types): preserve thinking signature recovery failure #9114 — thanks @backryun
• [TS7] fix(types): preserve Responses transform options #9119 — thanks @backryun
• [TS7] fix(types): preserve validation failure narrowing #9120 — thanks @backryun
• [TS7] fix(types): preserve client usage format contract #9122 — thanks @backryun
• [TS7] fix(types): preserve request rule input contracts #9135 — thanks @backryun
• [TS7] fix(types): simplify Codex service tier narrowing #9136 — thanks @backryun
• [TS7] fix(types): tighten extracted chatCore contracts #9137 — thanks @backryun
• [TS7] fix(types): align web executor event and model contracts #9138 — thanks @backryun
• [TS7] fix(types): align web provider support contracts #9139 — thanks @backryun
• [TS7] fix(types): type media provider request payloads #9141 — thanks @backryun
• test(dashboard): drop stale next-intl mock breaking ProviderDetailPageClient smoke #9150 — thanks @maxmad64bis
• test(mcp): guard Node 24 bundled MCP startup #9162 — thanks @Gioxaa
• test(compression): lock in stacked RTK+Caveman savings on redundant tool_result content #9278 — thanks @Sam280903
• chore: bump better-sqlite3 and add provider DB query scripts #9325 — thanks @jowimila
• test(quota): wait for the hot-path consumption instead of sleeping #9365 — thanks @HouMinXi
• refactor(sse): move the thinking-budget helpers out of base.ts #9381 — thanks @HouMinXi
• test(sse): expect the trailing period in the no-credentials message #9392 — thanks @HouMinXi
• chore(db): raise sqlite cache_size/mmap_size defaults #9467 — thanks @Poid-ZA
• [TS7] fix(types): align stream failure callback contracts #9561 — thanks @backryun
• [TS7] fix(types): narrow chatCore local contracts #9562 — thanks @backryun
• [TS7] fix(types): validate Azure OpenAI base URLs #9563 — thanks @backryun
• [TS7] fix(types): preserve sanitized tool array contracts #9564 — thanks @backryun
• [TS7] fix(types): validate Vision Bridge combo names #9565 — thanks @backryun
• [TS7] fix(types): preserve streaming PII choice keys #9566 — thanks @backryun
• [TS7] test(types): use Vitest expectations in tier resolver #9742 — thanks @backryun
• [TS7] fix(translator): preserve video URL override contracts #9747 — thanks @backryun
• [TS7] fix(codex): preserve narrowed input arrays #9748 — thanks @backryun
• [TS7] fix(kiro): complete cache-only usage totals #9753 — thanks @backryun
• chore(repo): ignore Electron build output unpacked into repo root #9858 #9770 — thanks @Michael-Rocco-Goldmann
• test(integration): add general live-test tool for the real "default" combo + rootless wire capture #9862 #9744 — thanks @hartmark
• ci(test): route orphaned Vitest tests through blocking CI #9875 #9605 — thanks @MohitRawat017
• docs(proposals): Telegram Mini App integration feasibility analysis #9906 #9810 — thanks @benzntech
• chore: ignore docker-compose.override.yml #9919 — thanks @lucasalx
• [TS7] fix(types): stabilize skill token extraction #9920 — thanks @backryun
• docs: add quickstart code examples for Python, Node.js, PHP and cURL #9922 — thanks @Hariprajwal
• [TS7] fix(types): narrow combo model collections #9972 — thanks @backryun
• [TS7] fix(types): align Claude message contracts #9973 — thanks @backryun
• [TS7] fix(types): type Copilot WebSocket construction #9974 — thanks @backryun
• [TS7] chore(types): remove orphan combo manifest metrics #9975 — thanks @backryun
• [TS7] fix(types): normalize stream usage before cost calculation #9977 — thanks @backryun
• [TS7] fix(stream): collect synthesized Responses tool events #9978 — thanks @backryun
• [TS7] fix(types): complete Responses stream failure contract #9979 — thanks @backryun
• [TS7] fix(types): narrow chat dispatch contracts #9986 — thanks @backryun
• [TS7] fix(types): narrow chatCore local contracts #9987 — thanks @backryun
• [TS7] fix(types): preserve GHE Copilot executor configuration #9988 — thanks @backryun
• [TS7] fix(types): validate Fal video result URLs #9989 — thanks @backryun
• [TS7] fix(types): narrow Claude stream deltas #9990 — thanks @backryun
• provider(agnes):refresh model catalog #9998 — thanks @backryun
• docs: fix duplicated word in MCP server audit logging section #10000 — thanks @TengSivtean
• docs: fix stale tool count (105 -> 104) in MCP server docs #10002 — thanks @TengSivtean
• Document default behavior for ToS-flagged free-tier providers #10013 — thanks @yulinlina
• [TS7] fix(tinycms): align executor and signer contracts #10087 — thanks @backryun
• [TS7] fix(types): restore provider breaker predicate import #10088 — thanks @backryun
• [TS7] ci: block new TypeScript 7 diagnostics #10134 — thanks @backryun
• chore(repo): remove tracked local artifacts #10178 — thanks @backryun
• maintenance — direct pushes (rollup): release-gate and base-red…
• deps (rollup): #9081 #9082 #9427 #9458 #9459 #9461 #9462 #9472
• docs/chore (rollup): #8954 #8991 #9059 #9194 #9258 #9508
• main-branch plumbing (rollup): #7168 #7179 #7216 #7220 #7225 #8941 #7559 #6634 #7341 #7347 #8067 #8070 #8317 #7076
• deps: bump the development group across 1… #10043 — thanks @app
• deps: bump electron from 43.2.0 to 43.3.0 in… #10042 — thanks @app
• maint(release): 45 direct pushes to the release branch with no PR…
• maint(repo): #10187 #10189 #10190 #10193 #10196 #10203 #10204 #10205 #10207 #10210 #10236 #10318
• docs(auth): distinguish dashboard sessions, oma_live_…… #7786
• docs(ops): document Kubernetes probe… #10297 — thanks @RaviTharuma
• docs(docker): spell out that :latest tracks the highest… #10317
• docs(backend): document that memory extraction, skills… #10349
• docs(docker): document default SQLite as single-replica /… #10350
• docs(backend): document that pre-write SQLite backups… #10351
• fix(tests): drain three base-reds on the release branch… #10539 #10704
• chore(security): remove the unused enforceSecrets duplicate of… #10775
• fix(quality): register GrokBuildToolCard.tsx… #10778
• docs: Custom combos are only invoked… #10779 — thanks @maxmad64bis
• chore(startup): remove src/server-init.ts (183 lines, never… #10780
• fix(quality): rebaseline file-size for 's own… #10859
• docs(openapi): document the GET and PUT operations on… #10875
• fix(quality): bump EXPECTED_FEATURE_FLAG_COUNT to 52 for 's own… #10889
• test(db): replace three empty test.skip placeholders in the… #10906
• docs(docker): document runtime RAM for coding-agent… #10982
• docs(database): align the SQLite cache guide with the 65,536… #11018
• docs(docker): document N independent… #11024 — thanks @RaviTharuma
• fix(quality): rebaseline file-size for modelCapabilities.ts… #11034
• fix(quality): register… #11053
• chore(quality): drain two release/v3.8.50 base-reds — refresh… #11160
• chore(lint): ratchet… #7879 #11247 — thanks @typescript-eslint
• fix(deps): prevent pnpm from auto-installing the… — thanks @lobehub
  @lobehub/icons, keeping six unneeded packages with incompatible or unverifiable license
  metadata out of production installs (#11342).
• ci(changelog): replace the broad removal bypass with an exact,… #11345
• docs(readme): reconcile live v3.8.50 provider, free-tier, CLI,…
  community, sponsor, acknowledgment, and SVG metrics with their audited source
  denominators, including a deduplicated OmniRoute-in-Action snapshot and distinct
  contributor rankings for merged pull requests, GitHub-attributed commits, and Git history
  (#11356).
• docs(openapi): document the conditionally… #11363
• fix(video-bridge): make opt-in segment-aware sampling use one… #11381
• docs: add an embeddings client runbook with… — thanks @RaviTharuma
• chore(ci): ignore ad-hoc BOT_TOKEN/BOT_URL in env-doc-sync…
• test(kimi): the Kimi background health sweep no longer draws… #11361
• chore(test): regenerate the provider/translate-path golden… #10531
• chore(release): resync the v3.8.50 provider and CLI catalogs,…
• fix(ci): route…
  download-failure message through sanitizeErrorMessage() instead of embedding a raw
  err.message, clearing the check:error-helper base-red on release/v3.8.50 (#9985).
• fix(ci): drain three more base-reds on release/v3.8.50 .… #9985
  219 errors locally (vs. 25 in the last CI run) — all from react-hooks/set-state-in-effect,
  react-hooks/preserve-manual-memoization, react-hooks/immutability,
  react-hooks/static-components, react-hooks/refs and react-hooks/purity, six React
  Compiler lint rules that eslint-plugin-react-hooks v7 turns on by default and that were
  never frozen in config/quality/eslint-suppressions.json after the dependency bump. Froze
  the pre-existing violations for those six rules via ESLint's native
  --suppress-rule/--suppressions-location mechanism (the same pattern already used for
  @next/next/no-location-assign-relative-destination) — no application code changed, no rule
  disabled, only genuinely-new violations stay blocking. check:dead-code was at 418 against a
  415 baseline: removed the unused src/lib/quota/providerCapabilities.ts file and the unused
  ProviderQuotaMonitor interface in providerQuotaTelemetry.ts (both dead since PR #10148,
  2026-08-18, confirmed via grep/knip cross-reference), landing at 416; the residual +1 could
  not be attributed to a single recent commit after checking every dead-list entry touched
  since the 2026-08-14 baseline measurement, so it is rebaselined with the investigation
  recorded in quality-baseline.json. tests/unit/autoCombo/tieredRotation.test.ts's
  "rotates across all 43 Cerebras connection IDs" case was hitting vitest's 5000ms default
  timeout on a 200-iteration synchronous selectProvider() loop under shared-devbox
  contention (load average 40-60+ observed) — widened its explicit timeout to 20000ms; the
  assertion itself is unchanged.
• fix(tests): drain two base-reds on the release branch —… #10491
• fix(tests): realign the two stream-utils passthrough… #10017 #10473
• fix(tests): drain several base-reds on release/v3.8.50 that… #9985
  of the same pattern — a legitimate product change landed without updating the test that
  asserted the old behavior: tests/unit/glm-provider-model-import-route.test.ts (12 tests)
  and tests/unit/model-sync-route.test.ts (2 tests) predate #10603's "upstream model sync is
  opt-in and manual overrides are preserved" change; tests/unit/antigravity-model-aliases.test.ts
  predated #10537 retiring the collapsed gemini-3.7-flash alias in favor of its three tiered
  ids. Also fixes a real data drift in open-sse/config/freeModelCatalog.data.ts (the qwen-web
  free-catalog entry still pointed at the retired qwen3.8-max-preview id instead of the
  current qwen3.8-max), corrects the zh-TW providers.autoFetchModelsTooltip string to the
  glossary-canonical 快取 instead of 緩存, and removes an unused default export from
  src/lib/oauth/providers/zed-hosted.ts (the named export already covers every consumer) to
  shave one symbol off the check:dead-code ratchet regression.
• chore(release): synchronize migration-count documentation and…
• fix(i18n): translate the 14 providers.harImport* keys into… #11069

• fix(release): #11038 #10534 #10964 #11259 #11338 — thanks @backryun @adevwithpurpose @hartmark @pacocartones
• fix(quality): #11438 #11321 — thanks @pacocartones @hartmark @adevwithpurpose @wgordon17 @backryun
• fix(tests): #11306 #10726 #11161 #11341 #11327 #11240 #11380 #10683 #10682 #10689 #11135 #10700 #10451 #11040 #11147 — thanks @MichaelYcJo @rqzbeh @hartmark @wgordon17
• fix(ci): Windows… #10453 #11301 #10828 #10325 — thanks @backryun
• perf(electron): #10390 #10367 #10382 #10359 #10327 #10328 #10324 — thanks @backryun
• perf(providers): provider schema validation is lazy and… #11334 #11220
• refactor(sse): #10633 #10910 #8367 #10201 #11051 — thanks @oyi77 @xz-dev
• refactor(dashboard): custom provider quota keys are… #11188 #11156
• chore(security): the… #10952 #10411 — thanks @arminanton @blarovse
• chore(deps): #10931 #10932 #10625 #10626 #10403 #10622 #10405 #10406 #10407 #10928 #10929 #10930
• fix(deps): #10610 #10543 — thanks @atjsh @tensorflow @jonlwheat2-gif @huggingface @dcox79
• docs: #10648 #10512 #10569 #10112 #10649 #10816 #10817 #10823 #10824 #10825 #10983 #11031 #11299 #11204 #11157 #10433
• docs(i18n): #11254 #11237 #11246 #10777 #10490 #10731 — thanks @farshidrezaei @realize000 @pandaaaa1990
• chore(repo): repository hygiene — the self-referential _tasks…
• chore(release): localized llm.txt mirrors and the v3.8.50 base…
• fix(ci): the pack-artifact provenance gate now checks… #8875 #10427
• test(dashboard): the proxy-registry e2e smoke flow opens… #8875 #9870
• test(api): the /v1/models e2e check accepts the auth… #9320 #8875
• chore(quality): refreshed the combos-page ESLint… #8875 #8285

🙌 Contributors

Thanks to everyone whose work landed in v3.8.50:

📖 Full changelog with complete descriptions: CHANGELOG.md

Export estável do catálogo OmniRoute para o Radar. Atualizado automaticamente; NÃO é um release de versão do produto.

All 1383 entries from this cycle are listed below, one line each — descriptions are
trimmed to fit GitHub's 125,000-character release body. Full wording, context and links:
CHANGELOG.md.
Living section — regenerated 2026-07-19 from all 306 cycle commits (bump 2c62333 → tip). Bullets carry the merged PR and its author; direct pushes listed separately. Finalized at the v3.8.49 release.

✨ New Features

• feat: generalize ensureThinkingBudget to all providers +… (#6979) — @rafaumeu

• feat(6922): effort-tier aliases for glm-5.2 & mimo-v2.5 on… (#6987) — @rafaumeu

• feat(providers): curated OpenRouter embeddings catalog + specialty merge… (#6994)

• feat(quota): opt-in auto-ping to keep Codex quota windows warm (#6995)

• feat(providers): add Agnes AI native provider support (#7035) — @HouMinXi

• feat(sse): allow disabling : comment heartbeats via… (#7036) — @xier2012

• feat(perf): add performance.mark/measure to SSE pipeline +… (#7045) — @oyi77

• feat(providers): add Dahl free inference provider (#7062) — @growab

• feat(ci): boot-smoke the packed npm tarball (check:pack-boot,… (#7086)

• feat(ci): hotfix fast-lane + tests-only E2E skip (WS3.1) (#7088)

• feat(ci): continuous release-green — on-push quick gate + 3x/day… (#7089)

• feat(ci): duration-balanced E2E shards via LPT bin-packing (WS4.1) (#7090)

• feat(ci): TypeScript 7 native shadow for typecheck:core (WS4.2,… (#7091)

• feat(release): npm staged publishing + pre-publish boot-smoke (WS1.3) (#7092)

• feat(release): post-publish verifier — clean-container install + boot… (#7109)

• feat(ci): Mergify merge queue + manual-train fallback runbook… (#7112)

• feat(ci): Windows leg for Electron prepare smoke (WS1.5) (#7113)

• feat(ci): Codecov patch coverage (informational) + fix missing… (#7114)

• feat(sidecar): support conditional provider manifest refresh (#7130) — @KooshaPari

• feat(homolog): real-environment E2E homologation suite (npm run… (#7133)

• feat(usage): add Codex reset credit picker (#7154) — @JxnLexn

• feat(ci): Trunk Flaky Tests uploads for vitest + Playwright E2E… (#7175)

• feat(ci): Trunk Flaky Tests upload on the fast-path vitest job… (#7205)

• feat(kiro): register GPT-5.6 Sol/Terra/Luna model family (#7209)

• feat(dashboard): show Codex plan label in provider and quota views (#7210)

• feat(dashboard): add reorder connections by availability button (#7211)

• feat(dashboard): add 180D and 365D usage/cost analytics periods (#7213)

• feat(api): add Vary: Accept-Encoding to token-authenticated /v1*… (#7217)

• feat(api): expose GET /api/usage/model-latency-stats (#7218)

• feat(dashboard): add compression-mode selector to Context & Cache combos… (#7219)

• feat(sse): route GitHub Copilot Claude models through native… (#7223)

• feat(mitm): add Antigravity reasoning-effort overrides (#7228)

• feat: replace free-text model inputs with hidePaid-aware… (#7229)

• feat: editable ComfyUI base-URL field + per-connection… (#7232)

• feat(sse): add optional-enum null-omission idiom for codex… (#7233)

• feat(sse): preserve tools/tool_choice for tool-bearing requests… (#7235)

• feat(api): accept x-goog-api-key header for client-facing auth (#7236)

• feat(sse): add native xAI Grok Imagine video generation provider (#7238)

• feat: add Type filter and easiest-first sort to Free Provider… (#7240)

• feat(cli): add Grok Build CLI tool setup (~/.grok/config.toml) (#7241)

• feat(provider): add Chenzk API OpenAI-compatible gateway (#7246)

• feat(providers): let custom connections opt into prompt-cache capability (#7257)

• feat(db): include xp_audit_log in automatic retention/prune (#7260)

• feat(api): structured X-Routing-Fallback-Reason header for relay… (#7262)

• feat(compression): support RTK TOML schema v1 filters (#7281) — @JxnLexn

• feat: add principal-scoped CCR MCP lifecycle (#7282) — @JxnLexn

• feat(morph): refresh curated models (#7314) — @backryun

• feat(issue-agent): surface RecordedTriageTimeoutError as 504 (#7315) — @KooshaPari

• feat(incident-response): structured incident response templates (#7334) — @KooshaPari

• feat(providers): add xAI OAuth PKCE provider (#7399) — @fenix007

• feat(models): advertise Claude reasoning-effort variants in /v1/models (#7497) — @thepigdestroyer

• feat(kimi): sync Code, Web, and Moonshot providers (#7531) — @backryun

• feat(resilience): guard OmniRoute peer routing loops (#7555) — @isiahw1

• feat: add Mixedbread AI as embeddings provider (#7595)

• feat(providers): add Rev AI speech-to-text provider (#7596)

• feat: add Freepik (Magnific Mystic) image generation provider (#7597)

• feat(sse): add DeepInfra as a video-generation provider (#7598)

• feat(providers): add Felo chat-aggregator provider (#7599)

• feat(sse): add Notion AI Web (Unofficial/Experimental) provider (#7600)

• feat: add FreeTheAi as OpenAI-compatible gateway provider (#7602)

• feat: add Gladia as an async speech-to-text provider (#7603)

• feat: add EdgeTTS audio-tts provider (#7605)

• feat(video): add Novita AI as video-generation provider (#7606)

• feat: add Segmind image+video provider (#7608)

• feat: add Microsoft Designer as image provider (#7609)

• feat: per-model default reasoning_effort + no-think none on… (#7631)

• feat(sse): per-model upstream header-response timeout override (#7632)

• feat(dashboard): in-product guidance for prompt compression engines (#7634)

• feat(usage): add TTFT/E2E-latency/tokens-per-second to model latency… (#7635)

• feat: import providers from CSV/JSON file (#7636)

• feat: confirm before removing a single connection (#7640)

• feat(sse): honor excluded models in no-auth auto-combo candidate… (#7646)

• feat(providers): add g4f.space no-key gateway… (#7647)

• feat: rate-limit queue admission control (maxQueueDepth + 15s… (#7649)

• feat(sse): generalize session affinity TTL to all providers (#7650)

• feat: OpenRouter quota tracking (key/credits + free-window… (#7651)

• feat(sse): quota tracking for AgentRouter, v0 (Vercel), FreeModel… (#7653)

• feat(providers): Speechmatics STT, gTTS, VibeProxy preset (#6659, #6667,… (#7655)

• feat(api): route Google AI Studio Imagen through… (#7656) — @danscMax

• feat(auth): OIDC as optional dashboard admin login gate (password… (#6973) — @mikolaj92

• feat(api): add pagination params to 8 DB modules + recharts… (#7046) — @oyi77

• feat(proxy): operator-level proxy subscriptions (Karing-style) —… (#7299) — @xier2012

• feat(grok-cli): align with official Grok Build client (#7358) — @backryun

• feat(providers): Complete GHE Copilot OAuth provider implementation (#7546) — @hppsc1215

• feat(guardrails): add CredentialMaskerGuardrail for API key/secret… (#7683) — @Securiteru

• feat(perplexity): refresh provider integrations (#7687) — @backryun

• feat(providers): notion-web live model discovery via getAvailableModels (#7696) — @artickc

• feat(providers): add proactive cf_clearance/User-Agent hint to grok-web… (#7713)

• feat: add live gRPC-web quota fetcher for grok-cli (#7714)

• feat(api): add opt-in auto-sync scheduler for free-proxy sources (#7716)

• feat(dashboard): show proxy name in badge, sort saved-proxy picker,… (#7720)

• feat(cli): add auth export command for decrypted provider… (#7724)

• feat(oauth): accept full ChatGPT session JSON for Codex manual import (#7725)

• feat(sse): add nvidia NIM local RPM budget + concurrency cap (#7726)

• feat(gemini-web): emulate OpenAI tool calling via the webTools prompt shim (#7727)

• feat(services): introduce pluggable service-provider contract, migrate… (#7730)

• feat(mitm): root-CA + per-host leaf certs for AgentBridge static… (#7731)

• feat(providers): add hailuo-web (MiniMax web) chat provider (#7734)

• feat: browser login for Grok Build provider (#7735)

• feat(routing): wire interceptFetch tool interception into the chat… (#7736)

• feat(sse): add X-OmniRoute-Decision routing trace header (#7765)

• feat(providers): zai-web live model discovery with local-catalog fallback (#7766)

• feat(api): sync upstream reasoning.supported_efforts into… (#7767)

• feat(dashboard): pin Kimi providers first in category + official… (#7775)

• feat(chaos+ponytail): parallel chaos-mode dispatch + ponytail output … (#7781) — @Moseyuh333

• feat(perf): IC2 — cache provider connections by ID + lazy-decrypt… (#7787) — @oyi77

• feat(quality): gate the free-tier headline so it can never silently… (#7798)

• feat(providers): expose an explicit tier override for any provider… (#7838)

• feat(routing): read-only auto/* candidate transparency + per-API-key… (#7839)

• feat(catalog): map unmapped free tiers, add navy + aihorde, surface… (#7840)

• feat(providers): add OpenRouter speech-to-text (audio transcription)… (#7861) — @Tasogarre

• feat(qwen): add Qwen3.8 Max Preview catalogs [Part 2/3] (#7874) — @backryun

• feat: support Bun bundled SQLite runtime (#7878) — @Arul-

• feat(providers): add 5 free-tier providers (ainative, aion, sealion,… (#7887)

• feat(vnc-session): persistent noVNC browser login for web-cookie providers (#7892) — @Capslockb

• feat(sse): add PromptQL playground provider (unofficial) (#7911) — @artickc

• feat(cline): align ClinePass catalog and request protocol (#7914) — @backryun

• feat: narrow mcp:connect scope + per-key HTTP tool-scope… (#7967)

• feat: provider tab account search + mirrored top pagination (#7968)

• feat: canonical numeric helpers + tier-1 (analytics) migration (#7969)

• feat(sse): add HyperAgent (hyperagent.com) unofficial web provider (#7994) — @artickc

• feat: copilot-m365-web tone-selected model variants (#7997)

• feat(media): Adobe Firefly image + video generation provider (#8006) — @artickc

• feat(routing): add prompt-cache affinity (#8008) — @JxnLexn

• feat(compression): select model-aware tokenizers (#8009) — @JxnLexn

• feat(compression): add Responses tool-output engine (#8010) — @JxnLexn

• feat(dashboard): Kimi sponsor banner, Kimi Coding preset, official… (#8039)

• feat(dashboard): make Codex quota card windows reflect reality (#8054) — @insoln

• feat(compression): teach the model the CCR retrieve protocol on first… (#8063)

• feat(compression): per-model/endpoint compression exclusion filter (#8064)

• feat(providers): add CLOVA Studio, InternLM and Ant Ling API-key… (#8077) — @alvaretto

• feat(codex): support reference image edits (#8122) — @xiaoyaner0201

• feat(providers): add weekly quota tracking for grok-web (#8127) — @apoapostolov

• feat(providers): add Sarvam AI, Writer Palmyra and PLaMo API-key… (#8161) — @alvaretto

• feat: native Fish Audio TTS provider on /v1/audio/speech (#8164)

• feat: zh-CN terminology glossary + consistency gate +… (#8166)

• feat(providers): add Typhoon (Thailand) and Inception Mercury diffusion… (#8170) — @alvaretto

• feat(sse): restrict auto-combo no-auth pool to allowlist… (#8183)

• feat(sre): add tcp-close-analyzer.py for debugging… (#8208) — @hartmark

• feat(settings): configurable model catalog cache TTL (#8219) — @oyi77

• feat(github-models): refresh catalog and compatibility (#8225) — @backryun

• feat(github): refresh Copilot model catalog (#8226) — @backryun

• feat: classify grok-web Cloudflare anti-bot blocks + gated… (#8241)

• feat(providers): weekly quota for xAI OAuth (Grok) (xai-oauth / xao)… (#8471) — @allanvb

• feat(sse): every completion response now carries an… — @chirag127

• feat(ws): the live-dashboard WebSocket server now auto-starts… — @ianriizky

• feat(sse): configurable per-model upstream… (#6354)

• feat(dashboard): Replace free-text model inputs in the Routing (web… (#6540)

• feat(compression): new omniglyph engine (context-as-image) — renders… (#6556 #6661)

• feat(sse): rate-limit request queue admission control —… — @chirag127

• feat(sandbox): the skill sandbox gained a container-provider… — @KooshaPari

• feat(oauth): accept the full ChatGPT session JSON (not… (#6636)

• feat(sse): add 5 no-key g4f.space gateway providers —… — @chirag127

• feat(sse): add DeepInfra as a video-generation provider… (#6653)

• feat(providers): add Freepik (Magnific Mystic) API-key… (#6654)

• feat(providers): add Rev AI speech-to-text provider… (#6655)

• feat(providers): add Segmind as an image + video generation provider… (#6656)

• feat(providers): add Gladia as an async speech-to-text… (#6657)

• feat(video): add Novita AI as a video-generation… (#6658)

• feat(providers): add Speechmatics as an STT provider — async batch… (#6659)

• feat(providers): add Mixedbread AI as an embeddings… (#6660)

• feat(providers): add Felo (felo.ai) as a free, no-signup, no-API-key… (#6666)

• feat(providers): add gTTS (Google Translate TTS) as a free, no-signup… (#6667)

• feat(sse): add EdgeTTS (Microsoft Edge "Read Aloud") as a free,… (#6668)

• feat(providers): add FreeTheAi as an OpenAI-compatible… (#6670)

• feat(sse): add Microsoft Designer as an unofficial… (#6672)

• feat(providers): add Hailuo Web (hailuo-web) — a free, _token-based… (#6673)

• feat(cli): new omniroute auth export command dumps DECRYPTED… (#6683)

• feat(mitm): the AgentBridge static MITM server (server.cjs) can… (#6684)

• fix(sse): skip thinkingConfig for Gemma models on the… — @chy1211

• feat(xai): route xAI clients to Grok's native /v1/responses… — @ryanngit

• feat(models): add a Settings → AI "Model Overrides" UI plus… — @xz-dev

• feat(api): add Vary: Accept-Encoding to token-authenticated… — @chirag127

• feat(sse): add Notion AI Web (Unofficial/Experimental)… (#6758)

• feat(dashboard): add per-routing-combo compression-mode override to the… (#6760)

• feat(resilience): operator-configurable account rotation policy — a new… — @artickc

• feat(sse): preserve tools/tool_choice for tool-bearing… — @chirag127

• chore(cursor): add Grok 4.5 effort/fast model IDs: (#6774 ). — @andrewmunsell

• feat(codex): Codex provider model discovery now fetches the live… — @JxnLexn

• feat(cursor): register the Opus 4.8, Fable 5, and Sonnet 5 model… — @andrewmunsell

• Changelog fragments (changelog.d/): PRs now add their changelog entry as a new fragment…

• feat(proxy): add a latency-optimized proxy rotation strategy that… — @iamraydoan

• feat(db): include xp_audit_log in the automatic… (#6801)

• feat(fusion): the fusion judge may now draw on its own knowledge and… — @chirag127

• feat(dashboard): search box on the Playground's raw model <select> —… (#6811)

• feat(usage): Antigravity/agy quota widget now surfaces the… (#4017 #6818)

• feat(codex): Codex CLI compatibility shim — the Responses API… (#3697 #6820)

• Z.ai Web (free web-session provider): new zai-web web-cookie provider drives the free… (#6823)

• feat(dashboard): import multiple, possibly different… (#6836)

• feat(compression): update the vendored GCF codec behind the… (#6837)

• feat(sse): OpenRouter quota tracking — a dedicated fetcher polls… (#6842)

• feat(sse): live gRPC-web quota fetcher for Grok Build (grok-cli)… (#6844)

• feat(sse): add dual-window quota tracking for the… (#6845)

• feat(sse): add a static local RPM budget (default… (#6846)

• feat(sse): add quota tracking for the agentrouter… (#6850)

• feat(providers): Add GPT-5.6 support across OpenAI API, Codex, and… (#6862) — @backryun

• chore(providers): Align emitted Claude Code identity headers, bridge… (#6862) — @backryun

• feat(api): add a structured X-Routing-Fallback-Reason… (#6872)

• feat(api): new GET /api/usage/model-latency-stats management… (#6873)

• feat(providers): add a vibeproxy-openai provider-node preset to `POST…

• feat(usage): add… (#6875)

• feat(sse): per-model default reasoning_effort… (#6879)

• feat(providers): let a custom/openai-compatible connection opt into… — @andrea-kingautomation

• feat(dashboard): add a Type filter (No Signup / OAuth Login / API Key)… (#6915)

• feat(providers): expose an editable base-URL field on the ComfyUI… (#6928)

• feat(providers): refresh the curated OpenRouter embeddings catalog… (#6976)

• feat(quota): Add opt-in auto-ping to keep Codex quota windows warm —… (#6977)

• feat(oauth): Add a one-click browser (PKCE) login for Grok Build… (#7013)

• feat(sse): Add optional-enum null-omission idiom for… (#7023)

• feat(auth): accept the x-goog-api-key header for client-facing… — @QRcode1337

• feat(sse): add a local dual-window (5h + 7d,…

• feat(api): opt-in scheduled auto-sync for free-proxy sources… — @chirag127

• feat(kiro): register the GPT-5.6 Sol/Terra/Luna model family (272k… — @SemonCat

• feat(dashboard): show the Codex subscription plan label in provider… — @CarmeloCampos

• feat(dashboard): add a "Reorder" button to provider connections that… — @fzrilsh

• feat(dashboard): add 180D and 365D periods to the Cost Explorer range… (#7213)

• feat(sse): GitHub Copilot Claude models now route through… — @yidecode

• feat(mitm): Antigravity MITM model mappings now support an optional… — @trfi

• feat(sse): add native xAI Grok Imagine video generation provider —… — @anndev-69

• feat(cli): add Grok Build CLI tool setup — writes a… — @rixzkiye

• feat(provider): add Chenzk API OpenAI-compatible gateway. (thanks… — @CahyokPutraDev99

• feat(dashboard): add a per-operator "hide this quota row" toggle to the… — @nguyenha935

• feat(sse): session affinity (X-Session-Id / x-codex-session-id… — @tenshiak

• feat(sse): gemini-web now honors the OpenAI tools array by… (#7286)

• feat(eval): added a router-eval harness (npm run eval:router,… — @KooshaPari

• feat(services): introduce a ServiceProviderPlugin contract… (#7333)

• feat(routing): wire interceptFetch into the chat…

• feat(dashboard): confirm before removing a single… (#7361)

• feat(providers): Add a first-class xAI OAuth PKCE provider for… (#7399) — @fenix007

• feat(dashboard): surface in-product guidance for the Settings → Prompt… (#7530)

• feat(providers): Complete GHE Copilot OAuth provider implementation with… (#7546)

• feat(providers): grok-web's add-connection dialog now… (#7567)

• feat(providers): register lmstudio in the embedding provider registry… (#7601) — @ekinnee

• feat(sse): honor a no-auth provider connection's… (#7622)

• feat(dashboard): proxy-assignment UX quality-of-life fixes — the… — @tenshiak

• feat(providers): zai-web (chat.z.ai) now wires live… — @andrea-kingautomation

• feat(perplexity): Refresh Perplexity Web model mappings and Search API… (#7687) — @backryun

• Generic OpenAI-compatible model sync now captures a… (#6879)

• feat(dashboard): Kimi (Moonshot AI) official-partnership highlight on… (#7775)

• feat(providers): let any provider connection — built-in… (#7818)

• feat(routing): add a read-only `GET… (#7819)

• feat(providers): copilot-m365-web tone-selected model… (#7872)

• feat(shared): Add canonical numeric coercion helpers (toNumber,… (#7879)

• feat(mcp): add a narrow mcp:connect API-key scope for… (#7895)

• feat(dashboard): provider tab account search… (#7937)

• feat(sse): classify grok-web Cloudflare anti-bot blocks… (#8019)

• Teach the model the CCR retrieve protocol (marker →… (#8033)

• Add a per-model/endpoint compression exclusion filter:… (#8034)

• feat(i18n): zh-CN terminology glossary + consistency gate + 提供商→提供者… (#8038)

• feat(dashboard): The Codex quota card no longer shows latent, never-used… (#8051)

• feat(providers): native Fish Audio TTS provider on… (#8099)

• feat(codex): add bounded multi-reference PNG/JPEG/WebP image editing… (#8122) — @xiaoyaner0201

• refactor(sse): classify SSE critical-path empty catches… (#8142)

• feat(db): persist caller session tag into call_logs for… (#8249)

• feat(api): quota-aware fallback routing for web-fetch… (#8297)

• feat(providers): map upstream reasoning-level metadata… (#8347)

• feat(providers): weekly quota for xAI OAuth (Grok) (xai-oauth / xao)… (#8471) — @allanvb

• feat(jobs): backup auto enable schedule is now… (#8513)

• feat(ci): automate ratchet shrink-banking so file-size/complexity… (#8612) — @MumuTW

• feat(providers): live monthly credit quota for Firecrawl (`GET… (#8759) — @allanvb

• feat(search): add Firecrawl to POST /v1/search supported providers… (#8814) — @allanvb

• feat(adobe-firefly): reference-image attach for generate + OpenAI…

• Homologation suite: new npm run homolog runs the full…

• feat(mcp): add a read-only Local Corpus context source with…

• feat(providers): notion-web live model discovery via…

• Provider connections can now be shown or hidden…

• docs(i18n): rewrite Russian README as a full native…

• Providers: adds the Xiaomi MiMo Token Plan provider and a… (#8861)

• feat(opencode-plugin): auto-discover models while running + force sync (#8101) — @RaviTharuma

• feat(combo): enforce provider and model family invariants (#8304) — @RaviTharuma

• feat(cli): replace ANTHROPIC_SMALL_FAST_MODEL with Fable default (#8343) — @leszek3737

• feat: read INITIAL_PASSWORD env var during setup (#8439) — @linhdmn

• feat(providers): add missing opencode-go reasoning effort variants (#8441) — @Prudhvivuda

• feat: add Claude Opus 5 support (#8464) — @backryun

• feat(combos): add select all / unselect all in Browse Catalog (#8526) — @JoshimOfficial

• feat(cli-tools): add all Hermes Agent auxiliary model roles (#8543) — @leszek3737

• feat(ci): block stale UI translations when an English value is… (#8574)

• feat(providers): flatten multi-turn history for gemini-web (#8607) — @Prudhvivuda

• feat(sse): relay upstream 4xx error bodies verbatim on the… (#8622)

• feat: Claude Code discovery aliases (surface non-Claude… (#8666)

• feat(dashboard): copy-paste settings.json block for Claude Code discovery (#8722)

• feat(quality): temporary relax of complexity/file-size ratchets for… (#8767)

• feat(db): let the migration runner scan extra namespaced… (#8770)

• feat(api): prompt-cache health summary endpoint and analytics tab (#8827)

⚡ Performance

• perf(db): project columns + composite index in… (#6918) — @oyi77

• perf(db): add jitter to stagger due-on-restart connections (#6919) — @oyi77

• perf(startup): warm model catalog cache at module init (#6920) — @oyi77

• perf(db): add temp_store=MEMORY pragma to SQLite init (#6921) — @oyi77

• perf(db): cap modelLockouts eviction at 1000 entries (#6923) — @oyi77

• perf: wrap ComboCard, HeroSection in React.memo (#7070) — @oyi77

• perf: Date.now hoist, hasActiveDeltaValue hoist, buffer.split… (#7066) — @oyi77

• perf(memory): mitigate event-loop starvation under 3000+ provider… (#7719) — @oyi77

• perf: reduce long-context request copies (#7862) — @RaviTharuma

• perf: lazy provider init, P2C quota cache, structuredClone… (#7893) — @oyi77

• perf(api): singleflight version lookups (#8301) — @RaviTharuma

• perf(api): skip the full catalog build for quota-exclusive keys (#8771)

🐛 Bug Fixes

• fix: add re-entrancy guard to token health check sweep (#6917) — @oyi77

• fix(grok): strip reasoningEffort for grok cli models (#6938) — @CitrusIce

• fix(6954,6953): preserve system role + strip empty-signature thinking… (#6982) — @rafaumeu

• fix(6980): classify Cloudflare AI neuron exhaustion as… (#6983) — @rafaumeu

• fix(dashboard): hide disabled provider connections from combo builder (#6984)

• fix(providers): cap grok-cli tools at 200 for cli-chat-proxy (#6986)

• fix(6848): auto-cleanup for telemetry tables causing OOM (#6988) — @rafaumeu

• fix(models): preserve direct-model combo metadata (#6993) — @JxnLexn

• fix: DDG circuit breaker + null content validation (#7001) — @rafaumeu

• fix(models): preserve chat-capable image model rows (#7004) — @xz-dev

• fix(codex): preserve GPT-5.6 reasoning contract (#7012) — @xz-dev

• fix(base-red): align least-used combo tests with executionKey usage… (#7015)

• fix: infer bare models from active synced catalogs (#7028) — @guanbear

• fix(auggie): update model registry to match v0.32.0 CLI model IDs (#7032) — @oyi77

• fix(sse): register ollama-cloud in USAGE_FETCHER_PROVIDERS (#7041) — @alltomatos

• fix(quality): read cognitiveComplexity= machine line in… (#7042) — @alltomatos

• fix(providers): sanitize Claude native output_config.effort (#7050) — @xier2012

• fix(combo): treat maxInputTokens as an input-only cap in the… (#7052) — @xier2012

• fix(antigravity): collect native part.functionCall into tool calls (#7053) — @xier2012

• fix(responses): map mid-conversation system turns to developer role (#7056) — @xier2012

• fix(combo): least-used sorts by per-account executionKey (#7059) — @xier2012

• fix(providers): AgentRouter model import applies Claude Code wire image… (#7060) — @xier2012

• fix(translator): preserve thinking.budget_tokens: 0 in Claude->Gemini (#7061) — @xier2012

• fix(cloudflare-relay): avoid invalid regex syntax in generated worker (#7063) — @SeaXen

• fix(dashboard): strip browser-extension attrs before hydration (#7073) — @MrFadiAi

• fix(relay): bound Bifrost stream lifetime (#7093) — @KooshaPari

• fix(sse): recognize xiaomi-tokenplan mimo as a thinking-mode model (#7098)

• fix(codex): strip regex lookaround from tool schema patterns (#7100)

• fix(openai): strip reasoning_effort when GPT-5.x models carry… (#7101)

• fix(compression): Headroom SmartCrusher skips developer-role messages… (#7102)

• fix(providers): surface a warning on 404 model_not_found in… (#7103)

• fix(executors): forward X-Session-ID/X-Title agent metadata headers (#7104)

• fix(cli): verify better-sqlite3 native binary is actually loadable (#7105)

• fix(sse): sanitize non-ok Antigravity streaming error body (port… (#7106)

• fix(providers): add MiniMax image-generation provider (#7108)

• fix(sse): handle space-separated arg name/value in Composer tool… (#7116)

• fix(cli): remove MITM DNS spoof entries before killing server… (#7117)

• fix(dashboard): include never-tested connections in combo builder… (#7118)

• fix(api): check Vercel SSO-protection PATCH response on relay… (#7119)

• fix(combos): reject oversized fusion panels before fan-out (port… (#7120)

• fix(combo): detect empty content_block in streaming SSE peek (#7121)

• fix(oauth): resolve Kiro AWS SSO cache client credentials by… (#7122)

• fix(tests): vitest UI suite back to green (69 fails triaged — WS6.1) (#7127)

• fix(auto): use p95 fallback in speed factors (#7128) — @KooshaPari

• fix(models): update Anthropic model contextLength to 1M (#7129) — @HouMinXi

• fix(ci): raise dast-smoke timeout 12->25min (build alone eats up… (#7139)

• fix(compression): lazy-load typescript in RTK codeStripper so prod-lean… (#7164) — @alltomatos

• fix(providers): accept m365.cloud.microsoft for copilot-m365-web token (#7166) — @xier2012

• fix(executors): disable parallel tools for Codex Responses Lite (#7171) — @fenix007

• fix(tests+providers): env-dependent tests exposed by GH-hosted runners (#6634… (#7174)

• fix(combo): reject known context overflow without exhausting… (#7177) — @JxnLexn

• fix: add static.cloudflareinsights.com to CSP script-src (#7178) — @oyi77

• fix: extend turbopack ignoreIssue suppression to compression… (#7180)

• fix: recognize Ollama Cloud session usage-limit 429 as… (#7181)

• fix: preserve relayAuth for pool-referenced relay proxies (#7182)

• fix: wire adaptive context-budget dial into settings schema… (#7183)

• fix(providers): DuckDuckGo VQD 429 misclassified as 503 (#7185)

• fix(db): cap OOM probe-failure cycle in getDbInstance() (#7186)

• fix: stop opencode-go quota lookup defaulting to Z.AI… (#7187)

• fix(providers): refresh OpenCode (oc) free-tier model catalog (#7188)

• fix: include proxyId when testing a saved registry proxy (#7189)

• fix: sanitize non-Latin1 chars in combo diagnostic headers (#7190)

• fix: raise main server keepAliveTimeout/headersTimeout above… (#7191)

• fix: route zai-web (and other registry-entry web-cookie… (#7192)

• fix(providers): reject chat requests for cloud-agent-only jules provider (#7193)

• fix: restore mobile grid-cols-1 fallback on quota page card… (#7194)

• fix: wire modelAliases fetch into HermesAgentToolCard (#7195)

• fix: surface real claude-web error body for non-SSE 400s (#7196)

• fix(dashboard): agent bridge dns toggle uses POST, not PUT (#7197)

• fix: stop duplicating text in Gemini Web streamed responses (#7198)

• fix: filter hidden custom models out of legacy combo model… (#7199)

• fix(dashboard): implement missing handleToggleSource on Free Pool tab (#7200)

• fix: honor combo-level proxy assignments from the registry (#7201)

• fix(ci): run quality gates on Mergify merge-queue draft PRs… (#7202)

• fix: add dashboard-scoped typecheck gate covering… (#7203)

• fix(guardrails/chat): stop Vision Bridge hijacking credentialed models to… (#7204) — @artickc

• fix(translator): preserve Gemini thought parts as reasoning_content on… (#7206)

• fix(translator): register openai response projection for gemini clients (#7207)

• fix(cli): fast-path --version to skip full CLI bootstrap (#7208)

• fix: honor PROVIDER_LIMITS_SYNC_SPACING_MS for local/API-key… (#7214)

• fix(api): bulk-add API keys no longer overwrite existing… (#7234)

• fix(sse): route the public OpenAI GPT-5.6 family through the… (#7242)

• fix(providers): honor configured proxy on Grok Build egress (#7244)

• fix(nvidia): expand NIM chat model catalog (#7247)

• fix(sse): reconstruct Claude-format content in synthetic bypass… (#7248)

• fix(build): isolate Windows HOME/AppData during next build (#7249)

• fix(cli): omniroute dashboard respects PORT env when --port is… (#7252)

• fix(sse): project non-streaming JSON back to the… (#7255)

• fix(combo): fall back on Responses SSE failures (#7256) — @rushsinging

• fix(routing): resolve nested combo-ref panel members in fusion… (#7259)

• fix(usage): reset logs and show provider names in analytics (#7264) — @SeaXen

• fix(sse): silence noisy proxy-failure log on caller-initiated… (#7266)

• fix(codex): normalize nested Responses output content (#7269) — @JxnLexn

• fix(combo): derive session stickiness key from Responses API… (#7277) — @alltomatos

• fix(antigravity): wrap Pro fallback chain in try/catch for timeout… (#7290) — @HouMinXi

• fix(logs): show saved provider names in request/provider log views (#7294) — @SeaXen

• fix(stream): reconcile encrypted Codex reasoning visibility without… (#7304)

• fix(build): packed tarball boot crash — server-ws timeout import… (#7308)

• fix(skills): register cli-skill-collector in the agent-skills… (#7310)

• fix(db): tolerate unavailable virtual table modules in stats (#7313) — @megamen32

• fix(router-eval): retained-optimization gate cleanup (#7318) — @KooshaPari

• fix(ci): Coverage job timeout 10->20min (lcov reporter pushed it… (#7342)

• fix(electron): normalize hashed standalone externals (#7353) — @tianrking

• fix(db): stop a 'latest' path segment from disabling backups and… (#7359) — @danscMax

• fix(branding): regenerate raster favicons — white mark was shipped… (#7390) — @vzts

• fix(test): skip real DNS writes in MITM dynamic-import test (#7398) — @HouMinXi

• fix(antigravity): streaming passthrough for non-streaming clients (#7408) — @HouMinXi

• fix(build): align engines.node with SUPPORTED_NODE_RANGE (#7490) — @alltomatos

• fix(api): await params in Agent Bridge DNS route (Next.js 16) (#7492) — @alltomatos

• fix(dashboard): show Obsidian context source card (#7500) — @DKotsyuba

• fix(ci): fetch full base history in pr-test-policy (shallow… (#7501)

• fix(sse): preserve chat quota across mixed windows (#7504) — @webmasterarbez

• fix(oauth): surface sanitized device-code error instead of a… (#7511) — @danscMax

• fix(oauth): repair qwen + codebuddy-cn device-code endpoints (#7517) — @danscMax

• fix(mitm): strip trailing assistant prefill to prevent upstream… (#7520) — @chirag127

• fix(codex): Test probe uses a ChatGPT-account-supported model (#7524)

• fix(codex): validate refresh_token on import before persisting (#7525)

• fix(codex): non-stream chat 502 'Response body is already used'… (#7526)

• fix(oauth): surface tunnel hint when Codex OAuth runs on a remote… (#7527)

• fix(sse): preserve custom tool output images (#7540) — @loulanyue

• fix(combo): failover when upstream SSE is truncated mid-lifecycle (#7545) — @Chewji9875

• fix(dashboard): prefer public endpoint URLs (#7547) — @nguyenha935

• fix(cli): refresh runtime detection accurately (#7552) — @nguyenha935

• fix(ui): improve React Flow dark theme (#7553) — @nguyenha935

• fix(i18n): treat MISSING sync placeholders as absent in EN… (#7556)

• fix(cli): Windows cert check/uninstall key off the real CA… (#7557)

• fix(sse): feed compression pipeline the authoritative vision… (#7560)

• fix(dashboard): providers model-name filter matches live/synced catalog (#7561)

• fix(db): pre-init sql.js WASM ahead of any getDbInstance()… (#7562)

• fix(dashboard): resolve costs page 500 from out-of-scope t() in… (#7564)

• fix(dashboard): surface rate-limit warning on 429 chat-probe (#7565)

• fix(sse): lazy-load playwright in claudeTurnstileSolver (#7566)

• fix(sse): combo failover for OpenAI streams truncated without… (#7568)

• fix(cli): reuse win32-aware locateCommand in tool-detector (#7569)

• fix(codex): #7536 check content-type before touching response.body… (#7570)

• fix(sse): stop dropping tool_search and leaking OpenAI-only… (#7571)

• fix(api): resolve provider display name and dedup byModel on… (#7573)

• fix(mitm): route Claude Code standalone MITM traffic (#7574) — @dongwook-chan

• fix(sse): stop per-byte enumeration of binary image bytes in log… (#7576)

• fix(sse): split effort/reasoning suffix off pinned cursor model… (#7577)

• fix(chatgpt-web): recognize update_content.messages[] celsius WS frames (#7578)

• fix(sse): 401 model-not-supported lockout + sticky… (#7580)

• fix(antigravity): allow cloudcode envelope through messages guard (#7582) — @dongwook-chan

• fix(sse): sanitize empty-signature thinking blocks + hoist… (#7583)

• fix(sse): honor per-model targetFormat override for… (#7584)

• fix(sse): clamp glm-4.6v max_tokens to the 32768 ceiling (#7585)

• fix(cli): log Codex Responses WebSocket history/usage per logical… (#7588)

• fix(providers): derive static model catalogs for search providers from… (#7589)

• fix(stream-readiness): bump timeout for heavy Claude-format reasoning replicas (#7612) — @herjarsa

• fix(translator): synthesize tool call chunks from response.completed… (#7613) — @ekinnee

• fix(embeddings): add lmstudio to embedding provider registry (#7614) — @ekinnee

• fix(combo): auto-clear stale session pins and emit recovery hints… (#7625) — @herjarsa

• fix(providers): unify connection and routing flows (#7629) — @nguyenha935

• fix(db): dedupe bulk-imported proxies by full credential tuple (#7644) — @alltomatos

• fix(api): allow text-to-image on dual-modality models + revive… (#7648) — @danscMax

• fix(stryker): add Microsoft Designer test to tap.testFiles (#7659)

• fix(dashboard): cut UI import chain from connection persist module (CI… (#7677)

• fix(perplexity-web): stop empty-content responses from live schematized SSE (#6955) — @artickc

• fix(dashboard): make quota cards container responsive (#7027) — @xz-dev

• fix(nvidia): restore GLM-5.2 reasoning on NIM (#7296) — @backryun

• fix(i18n): complete Vietnamese dashboard localization and runtime… (#7493) — @nguyenha935

• fix(providers): migrate muse-spark-web from GraphQL to WebSocket… (#7528) — @Ajeesh25353646

• fix(combo): expose computed context_length via /api/combos for… (#7633) — @herjarsa

• fix(api): enumerate tiered auto combo endpoints in… (#7662) — @ekinnee

• fix(dashboard): topology reflects connection health + clears finished… (#7672) — @danscMax

• fix(kimi-coding): capture and replay reasoning for thinking-mode turns (#7673) — @xz-dev

• fix(ci): merge-train --fast mirrors test:unit subdir allowlist (#7688)

• fix(sse): start credential-health sweep at boot so stale web… (#7689) — @danscMax

• fix(cursor): discover models via official CLI command (#7692) — @makcimbx

• fix(quota): fix antigravity/agy multi-model quota skipping in combos (#7695) — @irvandikky

• fix(usage): preserve account identity history (#7700) — @xz-dev

• fix(db): update proxies on password rotation (#7707) — @floze-the-genius

• fix(providers): correct Chutes registry baseUrl (#7708)

• fix(routing): strip prompt_cache_key for NVIDIA NIM (#7709)

• fix(providers): degrade Arena (lmarena) cookie validation redirect to… (#7710)

• fix(claude-web): unify Turnstile/executor/fast-path User-Agents behind… (#7711)

• fix(sse): authenticate CLIProxyAPI fallback/passthrough legs with… (#7712)

• fix(sse): proactively refresh Grok Build OAuth token before… (#7715)

• fix(providers): classify ambiguous Mistral 401 instead of hard auth… (#7718)

• fix(security): bump adm-zip >=0.6.0 + exact host matching in mitm DNS… (#7732)

• fix(icons): fall back to Stepfun Mono when Color component is… (#7743) — @Dan-ex-hub

• fix(stream): suppress </think> close marker for Responses API… (#7747) — @xz-dev

• fix(sse): wire settings.wildcardAliases into model resolution (#7748)

• fix(authz): classify forge/jcode CLI settings routes as LOCAL_ONLY (#7749)

• fix(routing): honor eye-icon hidden models for no-auth providers in… (#7750)

• fix(sse): persist rotated Gemini web-session cookies via… (#7751)

• fix(docs): heal release-green docs drift + eslint any-suppression… (#7755)

• fix(mcp): copy undici into dist/node_modules to prevent… (#7756)

• fix(packaging): move fumadocs-mdx to devDependencies (#7757)

• fix(ci): build API-only smoke workflows backend-only to fix… (#7758)

• fix(cli): load DATA_DIR/server.env as fallback for .env on… (#7759)

• fix(cli): split outboundUrlGuard's DB helpers so setup-opencode… (#7760)

• fix(notion-web): production-ready labels, multi-workspace, inference,… (#7768) — @artickc

• fix(kimi): expose K3 reasoning effort levels (#7776) — @xz-dev

• fix(compression): apply compression combo assignments to routing combos (#7779) — @ekinnee

• fix(i18n): regenerate Polish UI locale from English (#7782) — @leszek3737

• fix(combo): retry transient errors in pipeline strategy (#7794) — @AndrianBalanescu

• fix(quality): register nvidia-quota-phase1 and… (#7796)

• fix(stream): synthesize terminal finish_reason chunk when upstream… (#7804) — @AndrianBalanescu

• fix(plugins): 5 bugs on the plugin path (3 Windows-only, 2… (#7806) — @tmone

• fix(cli): register ESM alias resolver for @/ paths under global… (#7808) — @rafaumeu

• fix(auth): gate invalid-key check on isRequireApiKeyEnabled for… (#7810) — @AndrianBalanescu

• fix(ci): repair release regressions exposed by clean runs (#7812) — @backryun

• fix(rerank): add voyage format adapter for request/response… (#7813) — @AndrianBalanescu

• fix(antigravity): attempt onboarding when projectId is empty (#5193… (#7815) — @rafaumeu

• fix(stream): emit terminal SSE frames on mid-stream upstream failure (#7816) — @AndrianBalanescu

• fix(sse): strip orphaned tool_use before antigravity/Vertex… (#7822)

• fix(translator): sanitize tool_result.tool_use_id symmetrically with… (#7823)

• fix(oauth): require chatgptUserId agreement for Codex account dedup (#7825)

• fix(db): purge in-memory key-health state when a provider… (#7826)

• fix(compression): keep a retrievable preamble instead of a bare CCR marker (#7827)

• fix(db): log fatal boot-time SQLite driver-cascade failure… (#7828)

• fix(docker): repair tls-client-node native binary after… (#7829)

• fix(auth): restore TICK_MS in tokenHealthCheck (ReferenceError on… (#7830)

• fix(cli): fix Windows CLI detection false negatives (#7753, #7774) (#7831)

• fix(docs): document CREDENTIAL_REDACTION_ENABLED and… (#7833)

• fix(dashboard): fix collapsed quota card session/weekly order (#7834)

• fix(dashboard): mirror connection-row action-icon spacing under RTL (#7835)

• fix: avoid cmd.exe spawn on Windows by using os.hostname()… (#7841) — @tientien17

• fix(usage): harden account identity reconciliation (#7843) — @xz-dev

• fix(cli): use rundll32 instead of cmd.exe for Windows browser… (#7844) — @tientien17

• fix: add native lifecycle-aware health endpoint (#7852) — @RaviTharuma

• fix: reserve chat admission before body parsing (#7853) — @RaviTharuma

• fix: bound quadratic session-dedup memory growth (#7855) — @RaviTharuma

• fix(compression): enable OmniGlyph for Claude Fable 5 (#7863) — @enjoyer-hub

• fix(notion-web): add browser fingerprint headers to reduce Cloudflare… (#7864) — @HassiyYT

• fix(mitm): gate Agent Bridge Repair on sudo password (#7865) — @skutanjir

• fix(rerank): honor the connection's pinned proxy on rerank calls (#7867)

• fix(compression): skip CCR on tool outputs to preserve agent loop (#7869) — @herjarsa

• fix(vision-bridge): reroute auto/ prefix to vision model when images present (#7871) — @herjarsa

• fix(opencode-plugin): support separate management read token (#7885) — @RaviTharuma

• fix(sse): CC bridge loses OpenAI-format image input… (#7888)

• fix(combo): strip boolean reasoning field for opencode-go providers (#7891) — @AndrianBalanescu

• fix(notion-web): accept OpenAI content-parts arrays in transcript (#7896) — @artickc

• fix(notion-web): reuse threadId across OpenAI multi-turn (no new chat… (#7900) — @artickc

• fix(gemini): strip OpenAI "strict" tool-schema keyword for… (#7901) — @Witroch4

• fix(antigravity): collect native functionCall parts in SSE collector (#7902) — @Witroch4

• fix(sse): recover invalid Anthropic thinking signatures once (#7906) — @insoln

• fix(resilience): don't cool down accounts or trip the breaker on client… (#7908) — @insoln

• fix(dashboard): preserve quota cutoff drafts (#7909) — @hydraxman

• fix(providers): treat public-host 302 as valid in Gemini Web connection… (#7917)

• fix(providers): read reasoning_text in Claude-format response translator (#7919)

• fix(dashboard): safely render structured error objects in Request Logs… (#7920)

• fix(dashboard): repair monaco deep import broken by 0.56 exports map (#7922)

• fix(autostart): adopt 9Router VBS startup to suppress console flash on… (#7925) — @tientien17

• fix(translators): normalize TitleCase tool names for non-Anthropic models (#7926) — @nramabad

• fix(api): resolve local provider models via dashboard catalog… (#7927) — @ekinnee

• fix(auto): pool accounts by provider model (#7928) — @adrianaryaputra

• fix(perplexity-web): multi-step empty content + advanced-quota cooldown (#7930) — @artickc

• fix(ccr): resolve principal via OMNIROUTE_API_KEY env var on… (#7932) — @ekinnee

• fix(combo): context-aware fallback ignores model_context_override (#7933) — @tmone

• fix(i18n): preserve remaining Vietnamese localization (#7935) — @nguyenha935

• fix(mitm): gate Agent Bridge DNS and Trust Cert on sudo password (#7939) — @skutanjir

• fix(providers): route iflytek/sparkdesk to Spark's OpenAI-compatible… (#7942) — @FenjuFu

• fix(sse): preserve parallel_tool_calls for GPT-5.6 delegation… (#7957)

• fix(providers): copilot-m365-web fails loudly on empty turns +… (#7958)

• fix(providers): treat unreliable web-cookie /models probe status as… (#7959)

• fix(api): add amazon-q to the static model catalog (#7960)

• fix: parse Gemini 429 RetryInfo.retryDelay for model lockout (#7961)

• fix(quality): tolerate ESLint's trailing unpruned-suppressions text… (#7962)

• fix(cli): translate missing sqlite bindings error into actionable… (#7963)

• fix(cli): spawn opencode.cmd shim with shell:true on win32 (#7964)

• fix(dashboard): correct block-extra-Claude-usage toggle copy to match… (#7965)

• fix(api): classify /api/acp/agents as loopback-only (#7966)

• fix(auth): restore configurable HEALTHCHECK_BATCH_SIZE dropped by… (#7970)

• fix(test): widen ratelimit-admission pollUntil deadline to 10s (#7971)

• fix(pricing): clarify disabled automatic sync status (#7972) — @RaviTharuma

• fix(combo): exempt content_filter from empty-content detection (#7973) — @HouMinXi

• fix(embeddings): support secure multimodal inputs (#7978) — @RaviTharuma

• fix(resilience): cap exactCooldownMs against maxCooldownMs (#7980) — @ekinnee

• fix(electron): derive macOS Helper name from execPath to remove 2nd… (#8002)

• fix(chatcore): report string-reason client aborts as 499, not 502 (#8011) — @Long-Feeds

• fix(models): drop generic catalog siblings of specialty surfaces (#8021) — @RaviTharuma

• fix(models): stop inventing chat capabilities for specialty surfaces (#8022) — @RaviTharuma

• fix(capabilities): resolve models.dev specialty rows across provider keys (#8023) — @RaviTharuma

• fix(models): attach models.dev pricing to GET /v1/models entries (#8025) — @RaviTharuma

• fix(grok-cli): require full auth.json on OAuth paste import (#8027) — @RaviTharuma

• fix(grok-cli): sanitize function_call_output before Grok Build dispatch (#8030) — @RaviTharuma

• fix(sse): bound forwarded response headers (#8041) — @insoln

• fix(sse): replace spoofable .includes() PromptQL issuer check… (#8042)

• fix(sse): bound Codex SSE peek read with per-read timeout (#8043)

• fix(cli): stop double-prefixing combo model ids in opencode… (#8047)

• fix(antigravity): scope 404 model-not-found lockout to exact model +… (#8050) — @AndrianBalanescu

• fix: repair pre-existing red gates on the release/v3.8.49 tip (#8055)

• fix(oauth): honor connectionId on token refresh so email-less… (#8062) — @insoln

• fix: classify Google quota exhaustion responses (#8071) — @rafaumeu

• fix(providers): refresh duckduckgo-web catalog to current Duck.ai wire… (#8079)

• fix(security): decouple request PII redaction from injection mode (#8102) — @RaviTharuma

• fix(providers): discover live AGY models (#8123) — @adevwithpurpose

• fix(guardrails): align INPUT_SANITIZER request masking gate (#8124) — @RaviTharuma

• fix(providers): refresh Baidu ERNIE and Qianfan website URLs (#8128) — @TrackCrewGalore

• fix(stream): add logging to empty catch blocks in stream error… (#8143) — @chirag127

• fix(sse): stop Codex/Responses sanitizer turning system image_url… (#8147)

• fix(db): register SIGHUP handler and stop force-killing server… (#8148)

• fix(providers): add missing poe registry baseUrl entry (#8149)

• fix(routing): anchor quota cache on globalThis for cross-chunk… (#8150)

• fix(responses): close namespace round-trip for Responses-Chat… (#8151) — @RCrushMe

• fix(oauth): warn instead of silently opening unreachable localhost… (#8152)

• fix(db): stop closing the sql.js singleton in getDbInstance()… (#8153)

• fix(sse): run compression pipeline per turn in Codex Responses WS… (#8154)

• fix(cli): merge node bin dir into CLI healthcheck PATH for codex… (#8156)

• fix(sse): anonymous fingerprint fallback for keyless Pollinations… (#8157)

• fix(cli): surface the real spawn error in process supervisor (#8158)

• fix: strip internal reasoning placeholder from user-visible… (#8162) — @Dingding-leo

• fix(combos): expose synced reasoning-effort variants in Combo… (#8165) — @Dingding-leo

• fix(windows): add windowsHide to all child process spawns (#8167) — @Dingding-leo

• fix(cursor): bridge native tools to client calls (#8171) — @makcimbx

• fix(security): bound JWT-extraction regexes to prevent polynomial… (#8173)

• fix: log pending request counter decrement failures (#8179) — @rafaumeu

• fix: suppress sql.js build warning via non-analyzable… (#8184) — @rafaumeu

• fix: align INPUT_SANITIZER_ENABLED default to true across… (#8185) — @rafaumeu

• fix(combo): skip remaining same-provider targets on 401/403 auth… (#8195) — @rafaumeu

• fix(compression): make memo key model-independent for non-vision engines (#8196) — @rafaumeu

• fix(resilience): add max/step to NumberField for provider cooldown inputs (#8203) — @rafaumeu

• fix(providers): fix Azure AI Foundry multi-model discovery and… (#8206) — @not-knope

• fix(logs): stop the async-EPIPE log-flood loop at its ignition… (#8207) — @Tasogarre

• fix(sse): surface OpenRouter mid-stream error chunks instead of a… (#8210) — @hartmark

• fix(sse): Gemini malformed function-call handling + tool_choice… (#8211) — @hartmark

• fix(sse): tool-incapable provider handling (AI Horde + Responses… (#8212) — @hartmark

• fix(sse): Gemini TPM/RPD quota classification + combo… (#8213) — @hartmark

• fix(services): resolve and record a real pid when adopting a service (#8218) — @seanford

• fix(memory): resolve remote embedding dimensions for reindex (#8220) — @Prudhvivuda

• fix(dashboard): correct machine-translated Korean UI strings in ko.json (#8224) — @MichaelYcJo

• fix(devin-cli): refresh shared model catalog (#8227) — @backryun

• fix(claude-web): align session transport and fallback (#8230) — @backryun

• fix: restore OAuth auto-refresh for gemini-cli connections (#8232) — @seanford

• fix: normalize Codex URLs and dashboard regressions (#8233) — @nguyenha935

• fix(api): narrow claudeClassifierCompat auto trigger so… (#8236)

• fix(gemini): drop HARM_CATEGORY_CIVIC_INTEGRITY from the default… (#8238)

• fix(backend): word-boundary-safe tool-result truncation in lite… (#8239)

• fix(providers): filter unsupported family-fallback candidates against… (#8240)

• fix(translator): synthesize tool call chunks from response.completed… (#180 #3980)

• fix(api): Vercel Relay deploy now checks the Deployment… (#1037) — @ricatix

• fix(oauth): resolve Kiro AWS SSO cache client credentials by… — @xcrag

• fix(combo): streaming Claude responses whose content block opens… (#1382) — @heishen6

• fix(codex): strip regex pattern lookaround (lookahead/lookbehind)… (#7100) — @evinjohnn

• fix(cli): stopMitm() now removes /etc/hosts DNS-spoof entries… — @dionisius95

• fix(sse): Cursor Composer/Auto tool calls that separate the arg… — @way-art

• fix(dashboard): the "Custom Models" add/edit form now has a "Vision… — @nguyenphi37

• fix(combos): fusion combos now reject an oversized panel (>40 models… — @fontvu

• fix(providers): the OpenAI-compatible "Check" validation flow now… — @advane204f

• fix(dashboard): include never-tested custom provider connections in the… — @fajarbossit

• fix(executors): forward agent-supplied X-Session-ID/X-Title… (#7104) — @chitholian

• fix(sse): Antigravity streaming requests that hit a non-ok… — @Duongkhanhtool

• fix(providers): MiniMax Text-to-Image now works — a minimax… — @felipeleite

• fix(cli): the runtime self-heal now verifies a cached… (#2493) — @mrprohack

• fix(openai): strip reasoning_effort/reasoning for GPT-5.x models… — @techsolutionmta

• fix(providers): preserve relayAuth for… (#5716)

• fix(providers): wire the Devin cloud-agent provider… (#6142)

• fix(providers): refresh Baidu ERNIE + Qianfan provider website URLs to… (#6271) — @TrackCrewGalore

• fix(providers): honor a provider-level proxy assigned… (#6272)

• fix(api): merge tool_call continuation deltas that… (#6276)

• fix(providers): modernize the lmarena provider for the Arena.ai… (#6280) — @backryun

• fix(providers): web-provider model discovery updated — qwen-web uses… — @janeza2

• fix(logs): the request-log detail modal no longer reopens by… — @xz-dev

• fix(providers): update SenseNova Token Plan support — register the… — @xz-dev

• fix(providers): give v0-vercel-web its own alias so its… (#6343)

• fix(providers): route AgentRouter key validation… (#6377)

• fix(db): stop legacy log-archive migration from…

• fix(docs): document Turbopack build memory tradeoff and… (#6409)

• fix(compression): surface silently-dropped…

• fix(providers): honor the max_token capability… (#6524)

• fix(dashboard): the onboarding tier-flow diagram rendered broken — its… — @ianriizky

• fix(routing): the auto combo's no-auth candidate pool now honors a… (#6557)

• fix(sse): server-tool literal names (e.g. web_search) are… — @MikeTuev

• fix(sse): sanitize non-Latin1 characters before… (#6612)

• fix(api): recognize OpenRouter… (#6623)

• fix(db): share one in-flight sql.js load across… (#6628)

• fix(db): unwrap lone named-parameter objects before… (#6802)

• fix(db): break probe-failed/restore loop on large storage.sqlite: (#6632 ). — @KooshaPari

• fix(ci): exclude check-test-masking.test.ts's own… (#6634)

• fix(routing): recognize Kimi-style "exceeded model… (#6637)

• fix(cli): Claude Code installed via WinGet is now detected on… — @enjoyer-hub

• fix(providers): removed obsolete/defunct providers from the catalog… — @backryun

• fix(sse): requests rejected before handleChatCore… (#6698)

• fix(providers): reject chat-completions requests for… (#6699)

• fix(sse): unwrap bare {function:{…}} tools so OpenAI-shape… — @samir-abis

• fix(oauth): stop merging distinct Codex OAuth logins that share an… — @lucasjustinudin

• fix(codex): detect "model at capacity"/overloaded errors embedded… — @ryanngit

• fix(volcengine): clamp max_tokens to the VolcEngine Ark endpoint cap… — @whale9820

• fix(antigravity): surface aborted/malformed Gemini tool calls (e.g.… — @anhdiepmmk

• fix(routing): the reasoning-token headroom buffer clamps to the… (#6714) — @xz-dev

• fix(api): omniroute health (and health components/`health… (#6677 #6717)

• fix(startup): webpack build broke on case-insensitive filesystems… (#6718)

• fix(build): Turbopack production build emitted an "Overly broad… (#6582 #6720)

• fix(providers): Codex Desktop requests to gpt-5.3-codex-spark failed… (#6651 #6721) — @alltomatos

• fix(providers): the provider quota card's weekly/session bars re-sorted… (#6687 #6722)

• fix(i18n): pt-BR was missing 194 UI keys present in en.json — a… (#6695 #6723)

• fix(startup): omniroute --mcp crashed at Node ESM link time with… (#6559 #6725)

• fix(providers): Kiro sent the adaptive-thinking… (#6576 #6726)

• fix(translator): Cursor's local Subagent tool call is no longer… — @like3213934360-lab

• fix(translator): GLM 5.2 (and other OpenAI-compatible upstreams that… — @itiwant

• fix(resilience): OmniRoute didn't respect an exhausted Ollama Cloud (or… (#6638 #6731)

• fix(resilience): a combo step "pinned" to one fingerprint account… (#6696 #6732)

• fix(api): Responses passthrough emitted event-only SSE frames (no… (#6561 #6735)

• fix(compression): /api/compression/preview's top-level… (#6488 #6741)

• fix(resilience): account selection could pick an account already out of… (#6686 #6742)

• fix(api): reasoning_content (extended-thinking text) was… (#6662 #6743)

• fix(api): the compression config PUT schema now accepts… — @alltomatos

• fix(api): raised the provider apiKey length cap for… — @alltomatos

• fix(routing): fusion combos no longer silently drop combo-ref panel… (#6764)

• fix(ci): publish electron-updater latest*.yml… (#6766)

• fix(i18n): translate hardcoded Portuguese dashboard strings to English (#6761, #6768): (#6769 ). — @chirag127

• fix(providers): strip redundant node prefix when… (#6772)

• fix(providers): scope nvidia NIM 404s to the single… (#6773)

• fix(codex): bump the default Codex CLI client identity from… (#6780) — @quanturbo

• fix(ci): the blocking "Impacted unit tests (TIA)" step… (#6788)

• fix(translator): read PDF/video file_data attachments on the… — @Witroch4

• fix(providers): ensure DeepSeek Web SSE emits [DONE] after FINISHED: (#6791 ). — @Pitchfork-and-Torch

• fix(api): the compression config PUT schema… — @Pitchfork-and-Torch

• fix(electron): materialize Turbopack hashed-module symlinks during packaging (#6724, #6594): (#6794 ). — @huohua-dev

• fix(cursor): send the Agent CLI build id as… — @andrewmunsell

• fix(cli): waitForServer() no longer reports ready from… (#6800)

• fix(sse): de-flake timing-sensitive combo… (#6803)

• fix(codex): strip include from compact responses requests: (#6805 ). — @yinaoxiong

• fix(dashboard): surface Claude extraUsage credits in… (#6806)

• Request count by provider & date: Dashboard → Analytics now shows a dedicated table of… (#6812) — @tjengbudi

• fix(resilience): an Ollama Cloud (or any apikey-category provider)… (#3709 #6817)

• fix(providers): an explicit thinking.budget_tokens: 0 is now honored… — @alltomatos

• fix(bootstrap): filter empty process.env values before spawning… — @AndrianBalanescu

• fix(providers): classify upstream 404 responses as MODEL_NOT_FOUND… — @AndrianBalanescu

• fix(db): cap the sql.js OOM-during-probe path in… (#6632 #6835)

• fix(mcp): de-duplicate TOTAL_MCP_TOOL_COUNT by tool… (#6854)

• fix(usage): xAI's exact provider-reported cost_in_usd_ticks no… (#6856) — @KooshaPari

• fix(plugin): the @omniroute/opencode-plugin dynamic provider hook… (#6859)

• fix(sse): apply cliproxyapiModelMapping at CLIProxyAPI… (#6876)

• fix(sse): defer response.completed until a trailing… (#6906)

• fix(cli): ship head-response-guard.cjs into the standalone… (#6908)

• fix(sse): wire the shared quota-fetch throttle into… (#6911)

• fix(sse): rename client-sent max_completion_tokens to… (#6912)

• fix(providers): PROVIDER_LIMITS_SYNC_SPACING_MS now… (#6916)

• fix(sse): classify LAN embeddings providers (10/8,… (#6925)

• fix(sse): Qwen Web executor no longer sends `[object… (#6927)

• perf(api): relay chat-completions routes now thread the… (#6930)

• fix(sse): normalizeCodexMessageContentPart now… (#6932)

• fix(sse): omit removed attachments field from Muse… (#6935)

• fix(dashboard): label audio/embeddings/image compatible… (#6936)

• fix(api): model-list discovery for LAN-local… (#6939)

• fix(providers): openai->gemini transform now maps… (#4170) — @rafaumeu

• fix(sse): escape backslash before brackets in ChatGPT-web… (#6944) — @brick30llc-ctrl

• fix(oauth): tokenHealthCheck now lowercase-normalizes… (#6947)

• fix(sse): make Codex Responses tool-arg normalization… (#6951)

• fix(sse): drop internal commentary-phase Responses… (#6952)

• fix(sse): stop forwarding empty-signature thinking… (#6953)

• fix(sse): perplexity-web's default pplx-auto/pplx-sonar… — @artickc

• fix(combos): embeddings-only and rerank-only models (e.g. JinaAI,… (#6975)

• fix(combos): when 2+ distinct model ids from the same provider would… (#6957)

• fix(dashboard): the combos builder now hides provider connections the… — @attid

• fix(providers): cap grok-cli tools at 200 per request, matching xAI's… — @gitcommit90

• fix(providers): DuckDuckGo AI Chat executor propagates… (#6996)

• fix(providers): refresh OpenCode (oc) free-tier model… (#6998)

• fix(api): raise the main server's… (#7003)

• fix(compression): wire the adaptive context-budget… (#7005)

• fix(usage): stop opencode-go quota lookup from… (#7022)

• fix(providers): Auggie (Augment CLI) model registry updated to the real… — @oyi77

• fix(ci): add a dashboard-scoped typecheck gate covering… (#7033)

• fix(cli): omniroute dashboard (no --port flag) now respects… — @kaon0388v1

• fix(build): extend the Turbopack ignoreIssue… (#7051)

• fix(providers): web-cookie… (#7058)

• fix(resilience): recognize Ollama Cloud's 5-hour… (#7071)

• fix(dashboard): restore mobile single-column fallback… (#7072)

• fix(dashboard): include proxyId when testing a saved… (#7080)

• fix(sse): xiaomi-tokenplan mimo models (e.g. mimo-v2.5-pro)… (#7098) — @xxue-z

• fix(dashboard): align onboarding tier descriptions and localize the… (#7125) — @Wibias

• fix(sse): claude-web now surfaces the real upstream error body… (#7134)

• fix(db): honor combo-level proxy assignments from the… (#7149)

• fix(dashboard): wire modelAliases fetch into… (#7151)

• fix(dashboard): filter hidden custom models out of the… (#7156)

• fix(dashboard): Agent Bridge DNS toggle now sends POST… (#7157)

• fix(dashboard): implement missing handleToggleSource… (#7161)

• fix(sse): stop duplicating text in Gemini Web streamed… (#7163)

• fix(executors): Codex Responses Lite requests force serial tool calls… (#7171) — @fenix007

• fix(translator): preserve Gemini thinking-mode thought:true parts as… — @warelik

• fix(translator): register the missing OpenAI→Gemini response projection… — @warelik

• fix(cli): omniroute --version now fast-paths before the tsx/esm… — @Jordannst

• fix(ci): build dast-smoke and nightly API-only smoke… (#7226)

• api: bulk-add API keys no longer overwrite existing provider… — @asynx6

• fix(sse): feed the compression pipeline the… (#7237)

• fix(sse): route the public OpenAI GPT-5.6 family (gpt-5.6,… — @Jordannst

• fix(providers): honor a configured proxy on Grok Build egress — the… — @ryanngit

• fix(nvidia): expand NIM chat model catalog with newly-observed… — @spacesky-cell

• fix(sse): synthetic bypass responses for Claude-format clients no… — @KunN-21

• fix(build): isolate Windows HOME/AppData during next build. (thanks… — @KunN-21

• fix(dashboard): providers model-name filter now matches… (#7250)

• fix(docs): correct stale /api/version and… (#7253)

• fix(sse): project non-streaming JSON responses back to… (#7255) — @warelik

• fix(i18n): treat __MISSING__: sync-script… (#7258)

• fix(authz): classify /api/cli-tools/forge-settings and… (#7263)

• fix(sse): lazy-load playwright in claudeTurnstileSolver… (#7265)

• fix(sse): stop logging a caller-initiated request abort/timeout… — @TuyulSpam

• fix(sse): classify 401 "model X is not supported" as… (#7268)

• fix(dashboard): resolve `ReferenceError: t is not… (#7272)

• fix(cli): Windows MITM root-CA check/uninstall keyed… (#7275)

• fix(cli): reuse cliRuntime's win32-aware… (#7279)

• fix(dashboard): connection Test surfaces a rate-limit… (#7284)

• fix(sse): combo failover now detects OpenAI-shape… (#7285)

• fix(db): getDbInstance() now guarantees sql.js WASM has…

• fix(sse): split effort/reasoning suffix off pinned… (#7289)

• fix(sse): hoist client-injected system messages to… (#7293)

• fix(sse): treat Uint8Array/Buffer as opaque binary in… (#7297)

• fix(cli): load DATA_DIR/server.env as a fallback for… (#7302)

• fix(rerank): Honor the connection's pinned proxy on rerank calls, so… (#7350) — @kamenkadmitry

• fix(electron): Normalize hashed Turbopack external imports in packaged… (#7353) — @tianrking

• fix(chatgpt-web): recognize update_content.messages[]… (#7357)

• fix(sse): clamp glm-4.6v max_tokens to the 32768… (#7364)

• fix(sse): honor per-model targetFormat override for… (#7364)

• fix(sse): combo session stickiness now releases a… (#7387)

• fix(cli): log Codex Responses WebSocket history/usage… (#7388)

• fix(embeddings): remove the non-existent… — @kamenkadmitry

• fix(providers): expose a base-URL override for… (#7447)

• fix(build): align engines.node supported range… (#7446)

• fix(i18n): replace machine-bulk-filled Vietnamese UI… (#7493)

• fix(db): stop closing the single sql.js singleton… (#7494)

• fix(sse): stop stream readiness from treating a… (#7503)

• Fixed the Codex connection Test button always… (#7521)

• The Codex account import (`POST… (#7522)

• The PKCE OAuth start… (#7523)

• fix(providers): search providers now expose a static… (#7529)

• fix(sse): map tool_search to a Chat function tool… (#7532)

• fix(sse): gate verbosity/prompt_cache_key on OpenAI… (#7533)

• fix(api): Usage page "by provider" table now shows the… (#7534)

• fix(api): Usage page "model usage" table no longer… (#7535)

• fix(codex): non-stream Codex (ChatGPT-account) chat no… (#7536)

• fix(sse): preserve input_image parts in array-valued Codex… (#7540) — @loulanyue

• fix(providers): stop reporting Arena (lmarena) cookie… (#7542)

• fix(combo): streaming combo failover now fails over when an… (#7545) — @Chewji9875

• fix(dashboard): Public and managed tunnel endpoints now take precedence… (#7547) — @nguyenha935

• fix(claude-web): unify Turnstile solver, executor and… (#7548)

• fix(cli): fall back to the node:sqlite driver cascade… (#7586)

• fix(api): expose Responses-API-format (OpenAI/Codex)… (#7587)

• grok-cli: OAuth paste-import now requires the full… (#7610)

• fix(sse): proactively refresh Grok Build's expiring… (#7610)

• grok-cli: sanitize Responses function_call_output.output values… (#7611)

• fix(translator): guard against double-emission when response.completed…

• fix(routing): strip prompt_cache_key for NVIDIA NIM —… (#7617)

• fix(routing): honor eye-icon hidden models for no-auth… (#7620)

• fix(providers): correct Chutes registry baseUrl from… (#7621)

• fix(providers): unify connection status across… (#7629)

• fix(providers): classify Mistral ambiguous 401 (quota… (#7638)

• fix(sse): route CLIProxyAPI fallback/passthrough legs… (#7645)

• fix(packaging): move fumadocs-mdx from dependencies to… (#7661)

• GET /api/combos/auto now enumerates template variants…

• fix(sse): persist rotated Gemini web-session cookies… (#7676)

• fix(dashboard): mirror connection-row action-icon… (#7680)

• fix(cli): split outboundUrlGuard.ts's DB/feature-flag… (#7682)

• fix(sse): wire settings.wildcardAliases into model… (#7693)

• fix(mcp): copy undici into dist/node_modules to prevent… (#7701)

• fix(translator): sanitize tool_result.tool_use_id symmetrically with… (#7705)

• fix(db): bulk proxy imports now update an existing proxy when… (#7707) — @floze-the-genius

• fix(oauth): stop Codex OAuth completion from collapsing… (#7737)

• fix(db): purge in-memory API-key health/rotation state… (#7740)

• perf(db): the 5 provider-connection/node call sites 's IC2… (#7787 #7744) — @oyi77

• fix(compression): CCR no longer collapses a whole… (#7746)

• fix(sse): strip orphaned tool_use blocks before… (#7752)

• fix(cli): resolve Windows CLI detection false negatives…

• fix(dashboard): keep session/weekly quota rows in a… (#7764)

• fix(db): log the fatal boot-time SQLite driver-cascade… (#7773)

• fix(sse): Claude-Code-compatible bridge (AgentRouter and any CC… (#7777) — @beingshafin

• perf(db): getProviderConnections now reads from a shared… (#7787) — @oyi77

• fix(docs): document CREDENTIAL_REDACTION_ENABLED and… (#7793)

• fix(combo): retry intermediate pipeline-strategy steps… — @AndrianBalanescu

• fix(docker): repair tls-client-node native binary after… (#7802)

• fix(runtime): Apply refreshed request-queue settings, restore… (#7812)

• fix(oauth): attempt Antigravity onboarding inline when… (#7814)

• fix(api): add amazon-q to the static model catalog so… (#7820)

• fix(sse): preserve parallel_tool_calls for GPT-5.6… (#7821)

• fix(quality): tolerate ESLint's trailing… (#7837)

• fix(test): widen ratelimit-admission pollUntil deadline… (#7842)

• fix(cli): Windows omniroute dashboard browser fallback uses… (#7844)

• fix(dashboard): Request Logs detail modal no longer… (#7845)

• fix(backend): stop buildClientRawRequest deep-cloning… (#7847)

• fix(sse): copy the combo attempt body shallowly instead… (#7847)

• fix(sse): estimate the combo fallback-compression… (#7847)

• fix(providers): Copilot reasoning_text now surfaces in… (#7856)

• fix(providers): treat a non-401/403 response from the… (#7857)

• fix(providers): copilot-m365-web now fails loudly on a…

• fix(providers): Gemini Web connection test now accepts… (#7859)

• fix(cli): translate missing better-sqlite3 native… (#7868)

• fix(auth): restore HEALTHCHECK_BATCH_SIZE env-var… (#7875)

• fix(opencode-plugin): the official @omniroute/opencode-plugin now accepts… (#7884) — @RaviTharuma

• fix(dashboard): Provider Quota cutoff inputs preserve unsaved values… (#7889)

• fix(sse): Anthropic requests that reject a completed historical… (#7906)

• Chat Core: client aborts that reject the upstream fetch with a raw…

• fix(resilience): Client-aborted requests are now treated as client… (#7907)

• fix(cli): spawn the win32 opencode.cmd shim with… (#7913)

• fix(dashboard): correct "Block extra Claude usage"… (#7918)

• fix(autostart): Windows auto-start no longer flashes a console window —… (#7925)

• fix(providers): perplexity-web now detects the… (#7930) — @artickc

• fix(sse): parse Gemini 429 RetryInfo.retryDelay /… (#7940)

• fix(electron): resolve macOS Helper by binary name to… (#7941)

• fix(providers): iFlytek Spark (iflytek, sparkdesk) now target the… (#7942) — @FenjuFu

• fix(api): classify /api/acp/agents as loopback-only… (#7948)

• fix(cli): stop double-prefixing combo model ids in the… (#7976)

• fix(providers): route noauth opencode-zen connections… (#7993)

• fix(providers): refresh duckduckgo-web free model… (#8000)

• fix(providers): repoint the zai-web executor at… (#8014)

• fix(sse): bound the Codex SSE peek/passthrough body… (#8020)

• fix(sse): replace spoofable .includes() PromptQL… (#8029)

• fix(providers): path-shaped multimodal model ids (e.g.… (#8032) — @Prudhvivuda

• fix(cli): merge Node's own bin dir into the CLI… (#8036)

• fix(sse): Bound forwarded upstream response headers so large… (#8041) — @insoln

• fix(db): register SIGHUP handler and stop force-killing… (#8045)

• fix(oauth): warn instead of silently opening an… (#8046)

• fix(sse): run the prompt-compression pipeline per turn in the… (#8052)

• fix(oauth): Refreshing the token on an email-less OAuth connection… (#8059)

• fix(routing): anchor quota routing cache on globalThis… (#8065)

• fix(providers): add the missing poe REGISTRY entry so built-in Poe… (#8082)

• fix(translator): set status: "completed" on… (#8083)

• fix(sse): give keyless Pollinations image requests the… (#8085)

• fix(sse): stop Codex/Responses sanitizer from turning… (#8089)

• fix(cli): surface the real spawn error… (#8091)

• fix(antigravity): preserve request/tool fidelity, make credits modes… (#8098) — @nguyenha935

• fix(dashboard): clamp provider-cooldown min/max ms to… (#8107)

• fix(providers): filter unsupported family-fallback… (#8134)

• fix(providers): classify HTTP 400 model-unavailable as… (#8136)

• fix(backend): word-boundary-safe tool-result truncation… (#8169)

• fix(api): narrow claudeClassifierCompat auto trigger so… (#8189)

• fix(providers): carve cookie-auth providers out of… (#8200)

• fix(gemini): drop HARM_CATEGORY_CIVIC_INTEGRITY from… (#8231)

• fix(dashboard): Normalize Codex client URLs, restore the analytics… (#8233) — @nguyenha935

• fix(providers): classify per-model-quota 403 and…

• fix(providers): reconcile Kimi K3 vision metadata when synced… (#8250) — @Prudhvivuda

• fix(providers): the Providers page Learn more button now opens the… (#8284) — @KaynXu

• fix(api): fold namespace into the flattened Chat tool… (#8295)

• fix(runtime): sanitize Muse Spark fetch failures before logging and… (#8298) — @backryun

• fix(sse): Combo middleware preserves OpenAI Responses request… (#8310) — @ridho9

• fix(api): accept the current compatible-provider… (#8326)

• fix(api): stop leaking the internal provider UUID in… (#8327)

• fix(dashboard): show custom provider_nodes providers in… (#8328)

• fix(api): stop the 2000-token safety buffer from… (#8331)

• fix(backend): keep combo routing from dispatching image… (#8332)

• fix(sse): strip third-party-agent signals from the… (#8350)

• fix(i18n): Restore brand/model proper nouns (Claude, OpenAI,… — @ikelvingo

• fix(api): estimate inline base64 image tokens instead… (#8368)

• fix(backend): stop prompt-cache affinity from silently… (#8370)

• fix(api): accept a missing status query-param on GET… (#8374)

• fix(resilience): treat an unreachable-proxy… (#8376)

• fix(backend): make disabling the global per-key proxy… (#8385)

• fix(dashboard): persist compression engine detail… (#8388)

• fix(plugins): fire registered+active plugin hooks… (#8395)

• fix(resilience): cap the connection cooldown after a… (#8396)

• fix(api): reach synced model_capabilities rows for… (#8429)

• fix(providers): stop marking a multi-quota-window… (#8431)

• fix(backend): compute AgentBridge diagnose… (#8466)

• fix(providers): OpencodeExecutor honors Extra API Keys rotation via… (#8467) — @Prudhvivuda

• fix(sse): stop combo's "all targets failed" response… (#8486)

• fix(backend): capability filters fail closed when every combo target… (#8488) — @Prudhvivuda

• fix(providers): persist a runtime-discovered… (#8491)

• fix(cli): backup create / backup auto enable —… (#8512)

• fix(dashboard): Endpoint/API base URL display honors… (#8514) — @rqzbeh

• fix(client): Absolute fetch("/api/...") and… (#8515) — @rqzbeh

• fix(cli): create ~/.cache (and set XDG_CACHE_HOME)… (#8519)

• fix(api): surface a non-blocking warning + startup scan… (#8530)

• fix(kiro): support profileless Builder ID quota, preserve CLI auth… (#8565) — @nguyenha935

• fix(test): isolate context-manager unit tests on a… (#8568)

• fix(quality): check:file-size --update now removes baseline entries… (#8589) — @MumuTW

• fix(sse): restore Task-Aware Routing config from… (#8604) — @MumuTW

• fix(sse): task-aware routing defaults use auto/* intents… (#8605) — @MumuTW

• fix(providers): keep registered OpenCode Go effort aliases in the… (#8610)

• fix(resilience): report local request-queue expirations as… (#8613)

• fix(docker): Honor OMNIROUTE_BASE_PATH behind reverse-proxy… (#8615) — @DinonowDev

• fix(resilience): recover a wedged local request limiter after an… (#8616)

• fix(providers): Kimi Coding billing-cycle quota errors now recover… (#8632) — @glazec

• fix(oauth): show GitLab Duo OAuth app / env setup instructions in… (#8688)

• fix(sse): combo compression-limit resolution falls back to… (#8716) — @DinonowDev

• fix(db): fall back to Node's built-in SQLite driver when… (#8724) — @epsilonode

• fix(resilience): keep missing request resources such as Files API ids… (#8756) — @wilsonicdev

• fix(api): GET /v1/models no longer rebuilds the whole catalog… (#6408 #8833)

• GHE Copilot: OpenAI-native models now route to <gheUrl>/responses… (#8835) — @hppsc1215

• CLI: omniroute launch no longer truncates pass-through… (#8837) — @sumanxg

• Providers: Codex GPT-5.6 Sol/Terra/Luna report the current… (#8838) — @TitoTFP

• Antigravity: a token refresh now recovers a missing projectId… (#8842) — @HouMinXi

• CI: check:tracked-artifacts raises the git ls-files… (#8844)

• OAuth: ANTIGRAVITY_OAUTH_CLIENT_TYPE=web lets a remote… (#8845) — @HouMinXi

• fix(executors): Vertex AI now routes current-generation Claude models… (#8852) — @wgordon17

• CLI: omniroute launch-codex no longer corrupts the codex… (#8856) — @sumanxg

• Providers: AGY model sync now discovers newly announced chat…

• fix(security): bound JWT-extraction regexes in…

• Fixed every non-streaming Codex (ChatGPT-account) chat…

• Logging: a broken stdout/stderr pipe no longer drives a… (#8181)

• docs: correct three stale references caught by the…

• Fix the Turbopack next build breaking with "Module…

• Fix mitm-dnsConfig unit tests failing when the suite… (#6122)

• muse-spark-web: the WebSocket 401 auth-failure message…

• Harden the Notion web provider thread-session cache…

• fix(security): OIDC login gate now requires…

• Build: the packed tarball boots again — #7191's…

• Packaging: new check:pack-boot gate packs the real npm tarball,…

• Packaging: pack-artifact closure tests now cover EVERY npm-shipped…

• fix(cli): CLI detection now refreshes stale cached results,…

• fix(docker): Podman deployment guidance now distinguishes local… (#8497)

• fix(ui): Theme React Flow controls correctly in dark mode,…

• fix(plugins): the generated plugin host script is now deleted…

• fix(compression): the Headroom SmartCrusher tabular-compaction guard now… — @SingCJ

• Skills: register cli-skill-collector in the agent-skills…

• fix(responses): Make Responses API to Chat Completions downgrades…

• fix(stream): Responses API clients (/v1/responses) no longer… (#4633)

• fix(security): bump adm-zip to ^0.6.0 (dev transitive…

• chore(deps): bump fast-uri≥3.1.3, hono≥4.12.27,…

• chore(deps): bump dompurify≥3.4.12,…

• fix(quality): register the two covering unit tests…

• fix(auth): restore the TICK_MS constant dropped by…

• fix(guardrails/chat): do not whole-request-reroute…

• Providers: yuanbao-web no longer forwards a foreign single cookie…

• Antigravity: the shared token-refresh service now recovers a missing… (#8860) — @HouMinXi

• Adobe Firefly: gpt-image requests now default detailLevel to… (#8863) — @artickc

• Combos: deleting a provider connection now clears the combo… (#8865) — @HouMinXi

• Auto routing: auto/<family> combos (auto/glm, auto/gemini,… (#8866) — @rafaeldrincon

• fix(oauth): wire Test Connection for xAI OAuth (xai-oauth /… (#8862) — @allanvb

• Logs: a failed auto/<family> request no longer writes every… (#8867) — @rafaeldrincon

• fix(usage): correct token/request counting for 30D/90D/YTD/ALL… (#7300) — @growab

• fix(notion-web): use Chrome TLS impersonation for runInferenceTranscript (#8159) — @artickc

• fix(bifrost): send v-prefixed transport version, not bare semver (#8194) — @seanford

• fix(resilience,translator): three release/v3.8.49 base-red regressions + eslint… (#8254)

• fix(sse): export PROVIDER_BREAKER_FAILURE_STATUSES — fix… (#8258)

• fix(providers): limit Gemini CLI to legacy OAuth refresh (#8275) — @backryun

• fix(cli): resolve claude.cmd on Windows in omniroute launch (#8283) — @Dingding-leo

• fix(resilience): skip terminal connections in token health check sweep (#8286) — @Dingding-leo

• fix(sanitizer): strip zero-width chars from Anthropic-native streaming… (#8287) — @Dingding-leo

• fix(i18n): re-sync and complete es-ES translations with latest… (#8289) — @Dragost

• fix(antigravity): add missing gemini-3.6-flash pricing rows to ag OAuth… (#8290) — @HouMinXi

• fix(dashboard): stop sidebar RSC prefetch storms (#8292) — @RaviTharuma

• fix(backend): add structure-aware chat admission (#8296) — @RaviTharuma

• fix(providers): adapt Kimi nonstream requests internally (#8302) — @RaviTharuma

• fix(mcp): keep POST SSE responses uncompressed (#8303) — @RaviTharuma

• fix(api): enforce image generation API key auth (#8306) — @fenix007

• fix(cpa): isolate credential-pool failures (#8308) — @RaviTharuma

• fix(sse): suppress by default on Chat Completions (#8309) — @Prudhvivuda

• fix(translator): cap thinking budget on explicit budget_tokens path (#8312) — @HouMinXi

• fix(providers): classify HTTP 400 model-unavailable as MODEL_NOT_FOUND… (#8319)

• fix(providers): carve cookie-auth providers out of terminal 401… (#8321)

• fix(api): fold namespace into the flattened Chat tool name so… (#8322)

• fix(providers): route noauth opencode-zen connections through their… (#8324)

• fix(security): remove quadratic trailing-slash trim in Alibaba… (#8333)

• fix(memory): self-heal upsertVector/deleteVector from a raced… (#8337) — @hartmark

• fix(sse): stop stripInternalReasoningPlaceholder from eating… (#8341) — @hartmark

• fix(compression): rank codex-responses in adaptive-ladder maps (#8381)

• fix(sse): gate reasoning-placeholder strip to chunks that contain… (#8382)

• fix(resilience): terminal-skip spares the recoverable GitHub Copilot… (#8389)

• fix(sse): re-export PROVIDER_BREAKER_FAILURE_STATUSES for the… (#8390)

• fix(sse): family auto-combos include any backend that serves the… (#8391)

• fix(sse): cap exact cooldowns only when synthetic — verified… (#8393)

• fix(devin-cli): update ACP JSON-RPC protocol for Devin CLI 3000.2.x… (#8425) — @MumuTW

• fix(auth): exclude local CLI providers from tokenHealthCheck… (#8426) — @MumuTW

• fix(oauth): add devin-cli and agy entries to OAUTH_TEST_CONFIG (#8427) — @MumuTW

• fix(dashboard): preserve connection health visual on last routed… (#8428) — @MumuTW

• fix(cursor): bridge native TodoWrite completions (#8432) — @makcimbx

• fix(guardrails): Vision Bridge describe-fallback ignores unreachable… (#8433) — @guhcostan

• fix(sse): record tool calls into shared state for… (#8462) — @hartmark

• fix(oauth): actionable guidance for LAN-origin loopback mismatches… (#8463)

• fix(hyperagent): sticky thread for agentic tool loops (Claude Code) (#8470) — @artickc

• fix: combo input-bound, Responses->Chat image strip,… (#8476) — @herjarsa

• fix(sse): call the real abort-signal helper in the Gemini… (#8485) — @backryun

• fix(providers): honor Extra API Keys rotation in OpencodeExecutor (#8493) — @Prudhvivuda

• fix(backend): fail closed when capability filters empty the combo pool (#8494) — @Prudhvivuda

• fix(providers): resolve native vision for path-shaped multimodal model… (#8495) — @Prudhvivuda

• fix(hyperagent): default 1M context for fable/opus/sonnet (#8496) — @artickc

• fix(notion-web): mint fresh thread for new OpenAI sessions with same… (#8511) — @artickc

• fix(db): classify compressionDetailNormalizers as db-internal in… (#8534) — @MumuTW

• fix(sse): label HTTP 499 disconnects as client_disconnected (#8552) — @DinonowDev

• fix(resilience): honor comboCooldownWait for every combo strategy (#8559) — @DinonowDev

• fix(backend): add error.code to synthOpenAIErrorChunk for guard… (#8570) — @marceli1404

• fix(video): validate Veo AI Free artifacts before success (#8581) — @brunnolouzada

• fix(routing): exclude locked-out models from auto-combo candidates (#8586) — @Prudhvivuda

• fix(api): prevent silent lost updates on concurrent settings… (#8587) — @Prudhvivuda

• fix(auto-combo): short-circuit expandAutoComboCandidatePool when… (#8598) — @mikeiagents

• fix(auth): tag internal/loopback-origin failed logins in the audit… (#8606) — @Prudhvivuda

• fix(providers): declare explicit OpenCode plugin feature-flag defaults (#8608) — @Prudhvivuda

• fix(ci): use webpack fallback for Node 26 compat build to stop… (#8611) — @Prudhvivuda

• fix(claude): classify native subscription quota 429 (#8628) — @costaeder

• fix(windows): request shell when spawning bare qoder binary name on… (#8633) — @Dingding-leo

• fix(middleware): declare withInjectionGuard's context parameter optional (#8644) — @backryun

• fix(providers): handle space-separated search queries via… (#8660) — @maxmad64bis

• fix(dashboard): broken icon allignment in SegmentedControl.tsx (#8679) — @0x2f0

• fix(providers): deprecate Monster API provider (fixes #8676) (#8691) — @Dingding-leo

• fix(quality): register the #8494 covering test in stryker… (#8692)

• fix(sse): clamp max_tokens to the model output cap on every path (#8698)

• fix(executors): pass TimeoutError reason to controller.abort() in 7… (#8699)

• fix(api): serve /v1/models stale-first and sanitize its error… (#8703)

• fix(sse): stop thrashing the provider prompt cache for… (#8705)

• fix: repair five base-red failures on release/v3.8.49 (#8706)

• fix(oauth): show GitLab Duo setup before authorize error (#8710) — @DinonowDev

• fix: hydration mismatch, duplicate React keys, and missing… (#8723) — @Mananz90

• fix(sse): hide synthetic OpenAI startup reasoning (#8729) — @rinseaid

• fix(guardrails): check feature flag helper in PIIMasker to honor DB… (#8730) — @Dingding-leo

• fix(sse): report a stream that completes without any content (#8732) — @backryun

• fix(plugins): delete the generated host script synchronously so… (#8749) — @MumuTW

• fix(sse): update ANTHROPIC_PING heartbeat data payload to… (#8762) — @Dingding-leo

• fix(cloudflare-ai): sync missing free catalog models (fixes #8725) (#8763) — @Dingding-leo

• fix(bedrock): preserve additionalModelRequestFields in converse… (#8764) — @Dingding-leo

• fix(docs): use correct kebab-case CLI flags in OpenCode guide… (#8766) — @swingtempo

• fix(db): repair the extra-migration-dirs test and env contract… (#8773)

• fix(electron): use NEXT_DIST_DIR when stripping stale native modules (#8794) — @NBN-N3

• fix(resilience): add UND_ERR_SOCKET to PROXY_UNREACHABLE_ERROR_CODES (#8795) — @Dingding-leo

• fix(combo): fail open when strict context filter empties… (#8798) — @DinonowDev

• fix(resilience): honor Cloudflare 1010 retryable:false — skip… (#8800) — @DinonowDev

• fix(dashboard): restore Usage Model Breakdown column sorting (#8802) — @DinonowDev

• fix(api): treat cx/* and codex/* as equivalent API-key model… (#8805) — @Prudhvivuda

• fix(sse): pass real response payload into plugin onResponse hooks (#8806) — @Prudhvivuda

• fix(types): export web executor types from their module (#8810) — @backryun

• fix(types): preserve reasoning policy record shapes (#8811) — @backryun

• fix(types): preserve compression detail config shapes (#8812) — @backryun

• fix(types): declare virtual chaos combo config (#8815) — @backryun

• fix(types): type memory skills injection logger (#8816) — @backryun

• fix(types): align web fallback contracts (#8819) — @backryun

• fix(types): declare idempotency input contracts (#8820) — @backryun

• fix(reasoning): sanitize streamed K3 think tags (#8821) — @rinseaid

• fix(types): normalize Kie transcription results (#8824) — @backryun

• fix(dashboard): surface quota pool delete failures instead of failing… (#8829)

• fix(autoCombo): normalize -free suffix in task fitness lookups (#8636) — @Dingding-leo

• fix(sse): split the reasoning-decision guards so the error arm… (#8641) — @backryun

• fix(openai-to-claude): skip empty reasoning_content string deltas (#8642) — @Dingding-leo

• fix(autoCombo): match longest pattern first in lookupStaticFitnessTable (#8651) — @Dingding-leo

• fix(providers): sync search query to URL query param (#8652) — @Dingding-leo

• fix(maritalk): refresh supported model catalog (#8663) — @backryun

• fix(agentSkills): scope command slice before nested subcommands to… (#8667) — @Dingding-leo

• fix(guardrails): ensure request PII masking respects DB feature flag… (#8715) — @Dingding-leo

• fix(reasoning): sanitize Kimi Code K3 think tags (#8721) — @rinseaid

• fix(sse): clamp out-of-range Gemini thinking_budget and learn the… (#8726) — @fuko2935

• fix(providers): support multi-token search in provider filter (#8731) — @Dingding-leo

• fix(api): stop JSON.stringify-ing messages before estimateTokens… (#8740)

• fix(quality): let --update remove baseline entries that already fit… (#8741) — @MumuTW

• fix: escape angle brackets in i18n messages to prevent… (#8747) — @SteeleHu

• fix(dashboard): the /home quick-start cards no longer prefetch — #8292…

• fix(dashboard): Request Logs detail no longer crashes on a structured…

• fix(dashboard): the logs detail modal stops reopening on first close…