chore: normalize formatting (2-space → tabs) in stream-error-patterns files

Re-tab only — no logic changes. Follows the repo's tab-based formatting
for these files, matching the CommandCode executor/translator style.

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>

.env.example

@@ -14,10 +14,6 @@ NODE_ENV=production
 API_KEY_SECRET=endpoint-proxy-api-key-secret
 MACHINE_ID_SALT=endpoint-proxy-salt
 ENABLE_REQUEST_LOGS=false
-# Console verbosity: DEBUG | INFO | WARN | ERROR. Default INFO. In production set
-# ERROR to only print important errors (hides ▶ POST / 📊 DONE / [COMBO] / [CHAT]).
-# Can also be changed at runtime from dashboard Settings → Logging.
-# LOG_LEVEL=ERROR
 OBSERVABILITY_ENABLED=true
 AUTH_COOKIE_SECURE=false
 REQUIRE_API_KEY=false

.gitignore

@@ -1,4 +1,5 @@
 # See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
 # dependencies
 /node_modules
 /.pnp
@@ -8,8 +9,10 @@
 !.yarn/plugins
 !.yarn/releases
 !.yarn/versions
+
 # testing
 /coverage
+
 # next.js
 /.next/
 /.next-cli-build/
@@ -19,22 +22,28 @@ product
 # production
 /build
 .idea/
+
 # misc
 .DS_Store
 *.pem
+
 # debug
 npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
 .pnpm-debug.log*
+
 # env files (can opt-in for committing if needed)
 .env*
 !.env.example
+
 # vercel
 .vercel
+
 # typescript
 *.tsbuildinfo
 next-env.d.ts
+
 .bin/*
 data/
 logs/*
@@ -52,18 +61,23 @@ Thanks.md
 PUBLIC.en.md
 PR/*
 package-lock.json
+
+
 #Ignore vscode AI rules
 .github/instructions/codacy.instructions.md
 README1.md
 deploy*.sh
 ecosystem.config.*
+
 scripts/agSniffer/*
 gitbooks/*
 gitbook/README.md
+
 # Refactor backup reference (do not bundle/lint)
 open-sse.old/
 .graphifyignore
 graphify-out/*
+
 # Local-only working dirs (notes, vendored repos, scripts, skills)
 .claude/
 .docs/
@@ -72,8 +86,6 @@ graphify-out/*
 .codegraph/
 .PR/
 .next-analyze/*
+
 # CommandCode CLI local state (auth/taste/projects)
 .commandcode/
-
-# Pi subagent run artifacts
-.pi-subagents/

CHANGELOG.md

@@ -1,172 +1,17 @@
-# v0.5.55 (2026-08-14)
+# Unreleased
 
 ## Features
-- **Auth**: native SAML 2.0 SSO alongside OIDC — AuthnRequest generation, ACS
-  assertion handling, SP metadata export, admin config test, replay-protected
-  via a `saml_state` cookie matched against `InResponseTo`
-- **Providers**: add Alibaba Token Plan (`token-plan.ap-southeast-1`) — the
-  fourth Alibaba key type, Singapore-only and OpenAI-compatible transport only
-- **Providers**: add `glm-5.3` to GLM Coding and GLM (China)
-- **Providers**: Kimchi accepts API keys as well as OAuth (dual auth), with a
-  working Test Connection for both modes
-- **Antigravity**: add Gemini 3.7 Flash and its tiered high/medium/low variants
-  (also in the Gemini registry) with pricing and quota tracking
-- **TTS**: add Fish Audio — model id travels in an HTTP `model` header, voice
-  is a `reference_id` (preset or cloned voice model)
-- **OpenCode-Go**: route by request format via declared transports instead of
-  forcing every client into `/messages` — Codex/OpenAI clients no longer pay a
-  lossy Responses→OpenAI→Claude double translation. Per-model `supportedFormats`
-  guard; the bespoke executor is gone (its shared `_lastModel` cache could cross
-  auth headers between concurrent requests)
-- **Usage**: dedup + cache Claude quota calls (120s TTL keyed by access token,
-  in-flight promise dedup, last-good read on soft failure) to stop multiple
-  tabs tripping 429; manual refresh (↻) sends `force=1` to bypass the cache
+
+- **Stream error patterns**: per-provider `streamErrorPatterns` setting (UI: provider page → Stream Error Patterns) — HTTP-200 streams whose first bytes match configured patterns (plain text or `/regex/`) are treated as failed requests: fallback works for non-streaming and early stream errors, and late streaming errors are logged as FAILED. Zero overhead when unconfigured.
 
 ## Fixes
-- **Docker**: ship `sql.js` in the image so the pure-JS DB fallback can start —
-  file tracing carried the package's JS without `dist/sql-wasm.wasm`, so a
-  container with no native driver aborted with ENOENT and never got a database
-  (#3248)
-- **Usage**: read Gemini `usageMetadata` out of the antigravity `{ response }`
-  envelope — every non-streaming antigravity request logged `IN 0 | OUT 0`
-  (#3260)
-- **Claude**: re-anchor passthrough cache breakpoints — the client's own
-  `cache_control` markers point at pre-normalization offsets, so the tail was
-  re-cached every request. Last system block and last tool pinned at 1h TTL,
-  last assistant turn at 5m, mid-conversation system messages folded into the
-  neighbouring user turn instead of hoisted into `body.system`
-- **Combos**: detect images from Hermes and attachment payloads (`images[]`,
-  `experimental_attachments`, message-level `image_url`/`audio_url`, inline
-  `data:` URIs) so the Vision Adapter auto-switch fires for Hermes/Ollama/
-  Vercel AI SDK shapes
-- **Kiro**: intercept chat via `x-amz-target` — Kiro IDE 1.0.228+ moved
-  `GenerateAssistantResponse` to `POST /` + header, bypassing MITM. Also emit
-  the now-mandatory initial-response frame and map the `auto` model slot
-- **Kiro**: report real output tokens and stop discarding usable turns
-- **Qoder**: detect billing blocks at stream start and return a synthetic 403
-  so combo/account fallback triggers instead of leaking the error into chat
-- **Antigravity**: strip competitive system prompts (Zed IDE's Claude-agent
-  prompt) that Antigravity flags with a 429 Quota Exhausted
-- **OpenCode**: send the official client fingerprint on free-tier requests so
-  the Console stops classifying traffic as unidentified and rate-limiting it;
-  session id resolves conversation-stable to preserve prompt caching
-- **Responses**: don't close the message on an empty `tool_calls` array — some
-  providers attach one to every chunk, and the truthy check ended the message
-  on the first content token (#3234)
-- **Translator**: preserve `prompt_cache_key` when converting chat to responses
-- **Models**: expose snake_case token limits on `/v1/models`
-- **Combos**: strip `stream_options` from the Fusion panel fan-out to avoid a
-  DeepSeek 400 (#3024); raise the dashboard model-test probe budget to 1024 and
-  soft-pass reasoning-only responses (#3010)
-- **Headroom**: the toggle reflects the `headroomEnabled` setting even when the
-  proxy is down — it previously showed OFF while the engine kept calling
-  `/v1/compress`; proxy status stays visible via the status chip
-- **Hermes**: add the `api_key` parameter to the model block in YAML config
-- **Providers**: add llm7 to provider test support
 
-## Docs
-- **i18n**: add Spanish, French, and Brazilian Portuguese README translations
-
-## Security
-- **Real IP**: `x-9r-real-ip` and the Host fallback were trusted from
-  client-controlled headers whenever `custom-server.js` was not in the request
-  path (`npm run start`, `start:bun`), letting a remote caller pose as local to
-  skip API key auth and reach `LOCAL_ONLY_PATHS` (`/api/mcp/*`,
-  `/api/tunnel/enable`, `/api/auth/reset-password`). The server now stamps a
-  per-process `x-9r-peer-token` on every request it sanitizes and only trusts
-  `x-9r-real-ip` behind it — falling back to Host in development and failing
-  closed in production (GHSA-pjm4-8fpg-f9p6). Also fixes IPv6 loopback
-  detection (`::1`, `::ffff:127.0.0.1`) and routes `npm run start` /
-  `start:bun` through `custom-server.js`
-- **Search**: `resolveBaseUrl()` rejects client-supplied non-public baseUrls
-  (SSRF guard on `/v1/search`)
-- **Login**: fresh-install remote login with the default password returns 403
-  without issuing a JWT
-- **Usage**: `/api/usage/request-details` redacts request/response payloads
-
-# v0.5.50 (2026-08-05)
-
-## Features
-- **Providers**: add TokenRouter (300+ models via OpenAI-compatible gateway) with
-  exact per-model pricing for 110 models and `reasoning_effort` thinking config
-- **Providers**: add Self-hosted STT / TTS / Embedding — point 9Router at your own
-  OpenAI-compatible speech and embedding servers (whisper.cpp, faster-whisper,
-  Kokoro-FastAPI, llama-server, vLLM, Infinity). Unlike the named cloud providers
-  these read `baseUrl` per connection, so one provider can front several machines
-- **Combos**: default-enable vision/audio capacity adapter (auto-routes to a
-  vision/audio-capable model when the target lacks that capability, falling back
-  to `oc/mimo-v2.5-free`), wired into chat handler routing
-- **Endpoint**: auto-provision a "Default Key" for first-time users so `/v1`
-  works without a manual dashboard step
-- **Codex**: support GPT-5.6 Max/Ultra reasoning-level overrides (cx/ routes only)
-- **Qoder**: support PAT (Personal Access Token) connections end-to-end, alongside
-  OAuth device flow
-- **CLI tools**: add OpenDesign (manalkaff/opendesign) support
-- **Headroom**: report effective payload savings (tool schema/history bytes broken
-  out, byte-savings % reflects actual outbound reduction)
-- **Ollama**: Cloud quota tracker (session + weekly) + proactive background OAuth
-  token refresh scheduler for all providers
-
-## Fixes
-- **Providers**: remove Qwen (OAuth flow stopped working reliably)
-- **Passthrough**: detect codex-tui/Codex Desktop as native Codex client — they
-  were falling through to the translator and losing fields like `reasoning.summary`
-- **OAuth**: scope antigravity header fixes to loadCodeAssist/onboardUser only
-- **OAuth**: keep `open` external in the build so xAI/Grok token refresh works on
-  Windows
-- **OAuth**: declare missing `searchParams` in register-session handler (was a
-  500 instead of JSON on error)
-- **DB**: `ENABLE_REQUEST_LOGS` env var now overrides the UI setting correctly;
-  observability defaults to off (opt-in)
-- **Translator**: preserve Codex Responses Lite tool use across chat-native
-  OpenAI-compatible providers
-- **Translator**: don't drop image-only user messages in `prepareClaudeRequest`
-- **Translator**: drop JSON Schema keywords Gemini rejects (`uniqueItems`,
-  `contains`, `multipleOf`, `unevaluatedProperties`, `unevaluatedItems`,
-  `contentSchema`)
-- **Claude**: remove global header cache that leaked one client's identity
-  headers onto another client/account sharing the server; gate `anthropic-beta`
-  by model instead
-- **Antigravity**: drop retired Gemini 3.0 quota tiers, show Gemini 3.6 Flash
-  usage bars
-- **Cloudflare AI**: declare API key authentication (dashboard showed "No
-  connections" despite an active key)
-- **GitHub Copilot**: hold monthly-exhausted accounts until UTC month reset
-  instead of only cooling down 120s
-- **CodeBuddy**: dodge Tencent CN content filter, add usage tracking, normalize
-  codebuddy-intl messages
-- **Usage**: stop losing cached prompt tokens in the forced-SSE→JSON path
-- **Grok CLI**: display the public subscription tier from the OAuth token claim
-- **Providers**: count apikey connections for Ollama free-tier card; free-tier/
-  apikey providers without `authModes` now default to apikey (were treated
-  oauth-only)
-- **Build**: include static/public assets in standalone output (login page hung
-  on 404s when run via PM2)
-- **Server**: support IntelliJ IDEA OpenAI-compatible clients over HTTP (h2c
-  upgrade handling)
-- **Auth**: redirect already-logged-in sessions away from `/login`
-- **CLI tools**: enable Apply button for dynamic OpenAI/Anthropic-compatible
-  provider connections
-- **CLI**: include complete API artifacts in the CLI package
-- **TTS**: a bare self-hosted model name is the MODEL, not the voice — `kokoro`
-  was parsed as a voice against a default model, 404ing or synthesising with the
-  wrong one
-- **Embeddings**: self-hosted embeddings no longer fall back to `api.openai.com`
-  when a connection has no `baseUrl` — that silently sent the input text and API
-  key to OpenAI under a provider named "Self-hosted"
-- **Embeddings**: an adapter that rejects a misconfigured connection now returns
-  400 with the reason instead of escaping the handler uncaught
-- **Embeddings**: bound the upstream fetch with `FETCH_CONNECT_TIMEOUT_MS` — an
-  endpoint that drops packets never returns headers, so the request previously
-  hung indefinitely
-
-## Docs
-- **i18n**: fix port typo, add RTK Token Saver feature descriptions
+- **CommandCode**: in-stream `{"type":"error"}` events now emit OpenAI error chunks + an executor early-peek → 502 fallback instead of fake success content (`[CommandCode error: ...]`).
 
 # v0.5.45 (2026-07-30)
 
 ## Features
-- **TTS**: add Xiaomi MiMo text-to-speech (preset voices 冰糖/茉莉/苏打/白桦/Mia/Chloe/Milo/Dean, style control, language hint dropdown with Auto-detect, i18n for Style label/placeholder)
+
 - **Providers**: add Poolside (OpenAI-compatible)
 - **Providers**: add api-airforce, baidu, bazaarlink, bluesminds, kilo-gateway, llm7, morph, sambanova, tencent
 - **OAuth**: zed / trae / windsurf providers + harden callback proxies
@@ -179,6 +24,7 @@
 - **Usage**: SuperGrok weekly pool via gRPC-web
 
 ## Fixes
+
 - **Refresh**: rotate `refresh_token` between retry attempts
 - **Kiro**: canonicalize tool history and route API keys correctly
 - **Kiro**: normalize dashboard thinking intensity models
@@ -193,18 +39,21 @@
 - **Dashboard**: flex quota rows, thin global scrollbars, no hidden-row overflow
 
 ## Docs
+
 - **i18n**: expand pt-BR translation to 986 terms
 - README: Indonesian translation
 
 # v0.5.40 (2026-07-20)
 
 ## Features
+
 - **i18n**: add Khmer (km) translations
 - **CLI tools**: configure Grok Build subagent models
 - **Kimi**: merge OAuth into dual-auth provider, add K3 / K2.7 models
 - **Dashboard**: ProviderTopology flow animation
 
 ## Fixes
+
 - **DB**: resolve better-sqlite3 parameter binding crash
 - **Translator**: pass `service_tier` through OpenAI → Responses conversion
 - **Kiro**: map GPT-5.6 reasoning effort fields
@@ -215,10 +64,10 @@
 - **Cursor**: HTTP/2 AgentService support + version bump 3.12.17
 - **Dashboard**: cut duplicate API/icon spam, lazy-load provider assets
 
-
 # v0.5.35 (2026-07-16)
 
 ## Features
+
 - **xAI**: Grok Imagine video generation (`/v1/videos`) + CLI
 - **CLI tools**: Grok Build setup — choose separate main/general-purpose/explore/plan models and preserve each model's context window
 - **GitHub Copilot**: route Claude models through Copilot's native `/v1/messages`
@@ -229,6 +78,7 @@
 - **i18n**: Thai (th) + Persian (fa) translations / README
 
 ## Fixes
+
 - **Providers**: bulk-add API keys no longer overwrite existing keys (gap-fill `Key N`)
 - **Anthropic**: lowercase `anthropic-version` header to prevent duplication on `/v1/messages`
 - **Alicode-intl**: use DashScope compatible-mode endpoint so standard keys work
@@ -241,14 +91,17 @@
 - **Translator**: strip `client_metadata` when converting openai-responses → openai
 
 ## Improvements
+
 - **Perf**: skip inactive background services on startup
 
 ## Docs
+
 - README: Persian YouTube tutorial
 
 # v0.5.30 (2026-07-10)
 
 ## Features
+
 - **Perplexity**: add Agent API provider (#2492)
 - **Grok CLI**: add Grok CLI / Grok Build provider with OAuth device-code flow (#2502)
 - **Featherless**: add OpenAI-compatible provider presets
@@ -260,6 +113,7 @@
 - **Proxy-Pools**: auto-rotate strategy for no-auth providers (#2409)
 
 ## Fixes
+
 - **Cloudflare-AI**: support accountId in bulk key import (#2449)
 - **DB**: backup on schema change, MCP child cleanup, codex models, usage providers OOM
 - **Codex**: avoid bare-email OAuth dedup (#2477)
@@ -276,6 +130,7 @@
 - **Pricing**: update Claude/Codex model rates and add new models
 
 ## Improvements
+
 - **i18n(zh-CN)**: complete Chinese translations for all UI strings (#2436)
 - **API**: caching for tunnel and version status endpoints
 - **Perf**: faster dev startup and lighter bundle
@@ -283,12 +138,14 @@
 # v0.5.20 (2026-07-07)
 
 ## Features
+
 - **Thinking**: per-model thinking level picker on provider page — appends `(level)` suffix to copied model names for forced reasoning effort across all formats (openai, claude, gemini, deepseek, kimi, qwen, zai, minimax, hunyuan, step)
 - **RTK**: add JS-native git-log filter (#2423)
 - **Caveman**: add targeted upstream-aligned style rules (#2424)
 - **i18n**: add Farsi (fa) language support (#2385)
 
 ## Fixes
+
 - **Thinking**: strip `(level)` suffix from upstream `body.model` so providers no longer reject requests
 - **Translator**: preserve developer instructions in openai-responses conversion (#2434)
 - **count_tokens**: count structured Anthropic blocks (#2419)
@@ -302,12 +159,14 @@
 # v0.5.18 (2026-07-03)
 
 ## Features
+
 - **Usage**: track cached tokens + correct input/output/cache cost (#2209) — hodtien
 - **Codex**: show reset credit expiry details (#2290) — Rafli Ahmad Zulfikar
 - **NVIDIA**: add new models and capabilities — decolua
 - **ClinePass**: add provider support — sternelee
 
 ## Fixes
+
 - **Usage**: dedupe streaming request-details log entries — Qin Li
 - **Claude**: drop foreign thinking signatures in passthrough — decolua
 - Prevent non-SSE stream pipe crash and cross-IdP account overwrites (#2244) — KunN-21
@@ -324,11 +183,13 @@
 # v0.5.15 (2026-06-29)
 
 ## Features
+
 - Add Kimchi OAuth provider — Nant361
 - Refine Qwen vision/video + thinking model patterns — decolua
 - Opt-in Codex auto-ping quota keep-alive — Emirhan
 
 ## Fixes
+
 - **Responses**: handle response.done terminal events (#2142) — rifuki
 - **Headroom**: skip unsafe responses tool history (#2132) — Sutarto Jordan Chrisfivo
 - **Translator**: map mid-conversation system message to user (claude→openai) — decolua
@@ -345,6 +206,7 @@
 # v0.5.12 (2026-06-26)
 
 ## Features
+
 - Add token-saver dashboard page — decolua
 - Add bulk delete for provider connections — teddytkz
 - Resolve GitHub Copilot model catalog from upstream — caiqinzhou
@@ -353,6 +215,7 @@
 - Overhaul Blackbox provider catalog + WebUI test support — suryacagur
 
 ## Fixes
+
 - Provider thinking compatibility (DeepSeek/Gemini) — Mink Nguyen
 - Stop double-counting streaming usage at source — decolua
 - Usage logging dedupe to reduce stats churn — Mink Nguyen
@@ -381,11 +244,13 @@
 # v0.5.8 (2026-06-21)
 
 ## Features
+
 - **Antigravity**: native image generation support (image models tagged kind:image, hiển thị trong media-providers UI)
 - **CodeBuddy CN**: API key auth + credit quota tracker
 - **CodeBuddy CN**: short model prefix alias "cbcn"
 
 ## Fixes
+
 - **MiniMax-M3**: enable vision capability
 - **Headroom**: support Docker sidecar proxy
 - **Antigravity**: image executor fixes
@@ -399,12 +264,14 @@
 # v0.5.6 (2026-06-20)
 
 ## Features
+
 - **Ponytail**: minimalist code generation feature
 - **Headroom**: proxy lifecycle management + dashboard UI (one-click start/stop, install detection, status probing, token saver, claude↔openai shape conversion)
 - **CodeBuddy CN**: new OAuth provider (copilot.tencent.com) — 15-model catalog, /v2 inference, forced streaming, OpenAI-style reasoning
 - **OpenCode-Go**: align models with official endpoints; route Qwen 3.7 MiniMax via /v1/messages, GLM/Kimi/DeepSeek/MiMo via /chat/completions
 
 ## Fixes
+
 - **Anthropic-compatible validation**: use POST /v1/messages (GET /models not spec, false "invalid" for valid keys)
 - **CLI tools**: tolerate JSONC configs in all 8 settings routes (opencode, openclaw, kilo, droid, cowork, copilot, claude, cline)
 - **Gemini/Antigravity**: preserve 'pattern' in tool schema translation (glob/grep)
@@ -415,6 +282,7 @@
 # v0.5.4 (2026-06-18)
 
 ## Fixes
+
 - **Kiro**: honor thinking effort budgets
 - **AG/Kiro/Xiaomi**: provider fixes
 - **Combo/Fusion**: flatten tool history in panel calls to prevent 503
@@ -424,6 +292,7 @@
 # v0.5.2 (2026-06-17)
 
 ## Features
+
 - **Combo Fusion strategy** — fans the prompt out to all member models in parallel, then a configurable judge model synthesizes one final answer (quorum-grace, anonymized sources, graceful degradation)
 - **Per-combo strategy selector** — pick `fallback` / `round-robin` / `fusion` / `capacity` per combo (replaces the old round-robin toggle), with a judge picker for fusion
 - **Capacity auto-switch** — reorders models per request so images/PDFs route to capable models first
@@ -431,6 +300,7 @@
 - **Claude auto-ping** — warms the 5h quota window right after reset so a fresh window starts immediately (per-connection toggle)
 
 ## Fixes
+
 - **Claude 429**: stop hammering the OAuth usage endpoint — cache resetAt, throttle quota refresh to 3 min, cool down after a 429 (chat unaffected)
 - **Usage logs always empty**: missing `await` on `getAdapter()` in `getRecentLogs` made `/api/usage/logs` & `/api/usage/request-logs` return nothing
 - **Executors**: strip params unsupported by the provider/model (drops deprecated `temperature` for claude-opus-4 → Anthropic 400)
@@ -442,11 +312,13 @@
 - **Security**: SSRF hardening on web fetch
 
 ## Internal
+
 - Large **open-sse / translator refactor** (~40 commits): unified provider/model registry (LiteLLM-style `models[]` + `kind` field, 100 co-located registry files), single-sourced media/OAuth/refresh/token URLs, registry-based dispatch for usage & token-refresh, DRY translator concerns (buildUsage, encodeDataUri, finishReasonMap, chunkBuilder, reasoningDelta…), ESM-safe registry init, large-file splits, dead-code removal, and golden/no-regression test gates
 
 # v0.4.80 (2026-06-13)
 
 ## Features
+
 - Vercel AI Gateway: support embeddings, images and credit usage (#1183)
 - Add MiMo Free no-auth provider (#1789)
 - Vertex: support ADC `authorized_user` credential
@@ -455,6 +327,7 @@
 - Kiro: enable multi-endpoint failover for GenerateAssistantResponse (#1722)
 
 ## Fixes
+
 - Security: re-auth on DB export/import + SSRF guard on web fetch
 - Auth: real client IP rate-limiting + remote default-password guard
 - Cerebras/Mistral: strip unsupported `client_metadata` from downstream requests (#1742)
@@ -473,11 +346,13 @@
 - Dashboard: show provider node name instead of connection name in topology (#1770) + show explicit `kind="llm"` combos on combos page (#1684)
 
 ## Docs
+
 - README: add Indonesian 9Router tutorial video (#1709)
 
 # v0.4.71 (2026-06-06)
 
 ## Features
+
 - Caveman: add wenyan classical Chinese levels and sync upstream prompts; locale-based visibility on endpoint page
 - i18n: endpoint exposure notice across multiple languages + Russian README
 - Antigravity: add gemini-3.5-flash-extra-low (Low) model
@@ -486,6 +361,7 @@
 - MiniMax: add MiniMax-M3 + update Quota Tracker coding/CN (#1631)
 
 ## Fixes
+
 - Codex: harden streaming timeouts (stall/connect raised to 60s, configurable per-provider), accept `response.done` event, and always emit a terminal `response.failed` + `[DONE]` for Responses passthrough when a stream closes, stalls, or aborts before a terminal event — prevents codex clients from hanging (#1648, #1680, #1688, #1618)
 - Codex: durable OAuth refresh lifecycle (#1664)
 - Tunnel: skip virtual interfaces to prevent false netchange watchdog
@@ -499,21 +375,25 @@
 - Model-test: route image/STT probes to their real endpoints, harden STT ping; add opencode-go + xiaomi-tokenplan to connection test (#1576, #1628)
 
 ## Improvements
+
 - Dashboard: reorganize menu actions across sidebar/header/profile
 - Translator: add data-driven coverage, bug-exposing cases, and real provider smoke tests
 
 # v0.4.66 (2026-05-29)
 
 ## Features
+
 - Add Qoder provider: device-flow OAuth, COSY signing, WAF-bypass body encoding, live model catalog, dashboard quota tracker, 11 models (#1372)
 - Add new models: Claude Opus 4.8 (Claude Code), GPT 5.4 Mini (Codex)
 
 ## Fixes
+
 - DeepSeek thinking mode: echo `reasoning_content` back on follow-up/tool-call turns so OpenCode-free and custom providers no longer 400 with "reasoning_content must be passed back" (#1543)
 - Reasoning injector: match deepseek/kimi model ids case-insensitively (covers custom providers using capitalized model names)
 - OpenCode suggested-models: include free models without the `-free` suffix, e.g. `big-pickle` (#1535)
 
 ## Improvements
+
 - Codex: trim sunset models, keep gpt-5.5 / gpt-5.4 / gpt-5.3-codex family, add gpt-5.4-mini
 - volcengine-ark: refresh model list (add DeepSeek-V4-Flash/Pro, drop EOL entries)
 - Lower stream stall timeout 35s → 30s for faster hang detection
@@ -521,15 +401,18 @@
 # v0.4.63 (2026-05-26)
 
 ## Fixes
+
 - GitHub Copilot: never route Gemini/Claude models to the `/responses` endpoint; prevents misleading "does not support Responses API" 400s (#1062)
 - proxyFetch: restore missing `Readable` import causing runtime `ReferenceError` in DNS-bypass fetch path
 
 ## Improvements
+
 - Lower stream stall timeout from 60s → 35s for faster hang detection
 
 # v0.4.62 (2026-05-26)
 
 ## Fixes
+
 - Codex: auto-retry when upstream drops mid-stream (no more hangs)
 - Codex: fix random 400/404 errors, tool-calling failures, and unstable prompt cache
 - MITM: support Antigravity 2.x
@@ -541,25 +424,30 @@
 - Gemini CLI: reuse stored OAuth project IDs for quota checks and show clearer setup guidance when the project is missing (#1271, #1428)
 
 ## Features
+
 - Add Cloudflare Workers proxy deployer and pool integration (#1360)
 - Add Deno Deploy relays support and improved proxy pools dashboard layout (#1437)
 
 ## Improvements
+
 - Refactor Tunnel into dedicated Cloudflare and Tailscale manager modules
 - Refactor tokenRefresh service with in-flight dedup to prevent refresh_token_reused errors
 
 # v0.4.59 (2026-05-21)
 
 ## Fixes
+
 - OAuth: fix login flow on Windows
 
 # v0.4.58 (2026-05-21)
 
 ## Features
+
 - xAI Grok provider (OAuth, API key, image)
 - Provider limits: paginated accounts with page size controls
 
 ## Fixes
+
 - Tailscale: fix connection status on Windows (#1300)
 - Tunnel: fix false "checking" when tunnel URL is reachable
 - Stream: fix pipe errors on client disconnect/abort
@@ -567,11 +455,13 @@
 # v0.4.55 (2026-05-18)
 
 ## Features
+
 - Xiaomi MiMo Token Plan: region selector (Singapore / China / Europe) — keys are cluster-specific
 - Antigravity: risk confirmation dialog before first connection
 - Gemini CLI: surface upstream retry delay on 429 errors
 
 ## Fixes
+
 - MITM: cannot kill process on macOS under sudo (lsof not found in PATH)
 - Stream: false-positive stall timeout on Claude reasoning / Kiro responses
 - Tunnel: cannot re-enable after disable (stuck state)
@@ -580,16 +470,19 @@
 - Antigravity OAuth: metadata now matches the official client
 
 ## Improvements
+
 - Gemini CLI: bump engine to 0.34.0
 - Re-hide `qwen` (OAuth EOL) and `iflow` (not ready) providers
 
 # v0.4.52 (2026-05-17)
 
 ## Features
+
 - Add Vercel AI Gateway provider support (#1183)
 - rtk: Kiro format tool result compression — handle conversationState.history & currentMessage, preserve error results, ~13.6% savings (#1194)
 
 ## Fixes
+
 - openclaw: normalize agent.model object form `{primary, fallbacks}` before .startsWith → fix TypeError & 'not configured' status (#1216)
 - Usage Details pagination: stay inside mobile viewport <640px (#1218)
 - Fix test model error
@@ -599,6 +492,7 @@
 # v0.4.50 (2026-05-16)
 
 ## Fixes
+
 - Fix duplicate tray icon on macOS when hiding to tray
 - Fix tray not showing in background mode on macOS
 - Fix hide to tray broken on Windows/Linux
@@ -607,11 +501,13 @@
 # v0.4.49 (2026-05-16)
 
 ## Features
+
 - Add Kiro provider support: full request/response translation, live model listing, reasoning content support
 - Add `buildOutput` RTK filter with autodetect for npm/yarn/cargo build logs
 - Add MITM warning notification in tray and dashboard
 
 ## Improvements
+
 - Add modalities (input/output) to model configuration for OpenCode
 - Fix tray hide-to-tray: keep current process alive instead of spawning detached child (fixes macOS NSStatusItem ghost icon)
 - Fix tray kill: graceful shutdown with SIGTERM/SIGKILL escalation
@@ -620,9 +516,11 @@
 - Update i18n across 32 languages
 
 ## Fixes
+
 - Fix model check (test-models) blocked by dashboardGuard: pass machineId-based CLI token in internal self-calls
 
 # v0.4.46 (2026-05-15)
 
 ## Breaking Changes
+
 - Tunnel public URL changed — old tunnel links no longer work, please reconnect to get the new URL

Dockerfile

@@ -37,9 +37,6 @@ COPY --from=builder /app/src/mitm ./src/mitm
 COPY --from=builder /app/node_modules/node-forge ./node_modules/node-forge
 # Ensure `next` is available at runtime in case tracing did not include it.
 COPY --from=builder /app/node_modules/next ./node_modules/next
-# sql.js loads dist/sql-wasm.wasm by path at runtime; tracing only follows JS imports,
-# so the last-resort DB driver would abort with ENOENT on the missing binary.
-COPY --from=builder /app/node_modules/sql.js ./node_modules/sql.js
 
 RUN mkdir -p /app/data && chown -R node:node /app && \
   mkdir -p /app/data-home && chown node:node /app/data-home && \

README.md

@@ -17,7 +17,7 @@
 
 [🚀 Quick Start](#-quick-start) • [💡 Features](#-key-features) • [📖 Setup](#-setup-guide) • [🌐 Website](https://9router.com)
 
-[🇧🇷 Português (Brasil)](./i18n/README.pt-BR.md) • [🇻🇳 Tiếng Việt](./i18n/README.vi.md) • [🇨🇳 中文](./i18n/README.zh-CN.md) • [🇯🇵 日本語](./i18n/README.ja-JP.md) • [🇷🇺 Русский](./i18n/README.ru.md) • [🇹🇭 ไทย](./i18n/README.th.md) • [🇮🇷 فارسی](./i18n/README.fa_IR.md) • [🇮🇩 Indonesia](./i18n/README.id-ID.md) • [🇪🇸 Español](./i18n/README.es.md) • [🇫🇷 Français](./i18n/README.fr.md)
+[🇻🇳 Tiếng Việt](./i18n/README.vi.md) • [🇨🇳 中文](./i18n/README.zh-CN.md) • [🇯🇵 日本語](./i18n/README.ja-JP.md) • [🇷🇺 Русский](./i18n/README.ru.md) • [🇹🇭 ไทย](./i18n/README.th.md) • [🇮🇷 فارسی](./i18n/README.fa_IR.md) • [🇮🇩 Indonesia](./i18n/README.id-ID.md)
 
 </div>
 
@@ -285,32 +285,6 @@ Default URLs:
         <b>Kilo Code</b>
       </td>
     </tr>
-    <tr>
-      <td align="center" width="120">
-        <img src="./public/providers/opendesign.png" width="60" alt="OpenDesign"/><br/>
-        <b>OpenDesign</b>
-      </td>
-      <td align="center" width="120">
-        <img src="./public/providers/jcode.png" width="60" alt="jcode"/><br/>
-        <b>jcode</b>
-      </td>
-      <td align="center" width="120">
-        <img src="./public/providers/grok-cli.png" width="60" alt="Grok Build"/><br/>
-        <b>Grok Build</b>
-      </td>
-      <td align="center" width="120">
-        <img src="./public/providers/devin-cli.png" width="60" alt="Devin CLI"/><br/>
-        <b>Devin CLI</b>
-      </td>
-      <td align="center" width="120">
-        <img src="./public/providers/deepseek-tui.png" width="60" alt="DeepSeek TUI"/><br/>
-        <b>DeepSeek TUI</b>
-      </td>
-      <td align="center" width="120">
-        <img src="./public/providers/qwen.png" width="60" alt="Qwen Code"/><br/>
-        <b>Qwen Code</b>
-      </td>
-    </tr>
   </table>
 </div>
 
@@ -467,46 +441,6 @@ Default URLs:
   <p><i>...and 20+ more providers including Nebius, Chutes, Hyperbolic, and custom OpenAI/Anthropic compatible endpoints</i></p>
 </div>
 
-### 🏠 Self-hosted Providers
-
-For speech and embeddings served from **your own** machine — whisper.cpp,
-faster-whisper, Speaches, Kokoro-FastAPI, openedai-speech, llama.cpp/llama-server,
-vLLM, Infinity, text-embeddings-inference, or anything else that speaks the OpenAI
-shape.
-
-| Provider | Endpoint used | Typical server |
-| --- | --- | --- |
-| **Self-hosted STT** | `/v1/audio/transcriptions` | whisper.cpp, faster-whisper |
-| **Self-hosted TTS** | `/v1/audio/speech` | Kokoro-FastAPI, openedai-speech |
-| **Self-hosted Embedding** | `/v1/embeddings` | llama-server, vLLM, Infinity |
-
-Every other speech provider is a named cloud service with a fixed endpoint. These
-three read their address from **each connection**, so one provider can front
-several machines and load-balance across them like any other.
-
-Set it on the connection as `providerSpecificData.baseUrl`:
-
-| Provider | Give it | Result |
-| --- | --- | --- |
-| Self-hosted STT | the full URL — `http://host:8080/v1/audio/transcriptions` | used as-is |
-| Self-hosted TTS | the server root — `http://host:8880` | `+ /v1/audio/speech` |
-| Self-hosted Embedding | the **OpenAI base**, `/v1` included — `http://host:8080/v1` | `+ /embeddings` |
-
-> **Mind the `/v1` on embeddings.** The adapter appends `/embeddings`, so
-> `http://host:8080` resolves to `http://host:8080/embeddings` and misses the
-> OpenAI route — llama-server answers **501**. Give it the same base URL an OpenAI
-> client would use. A full `.../v1/embeddings` is also accepted, so a value pasted
-> from a `curl` example works too.
-
-The API key is not checked by most local servers, but the field must be non-empty:
-it is what gives the connection a credentials record, and `baseUrl` lives there.
-Any placeholder works.
-
-Self-hosted Embedding has **no cloud fallback by design** — a connection saved
-without a `baseUrl` is reported as a configuration error rather than quietly
-falling back to `api.openai.com`, which would send your input text and API key to
-a third party under a provider named "Self-hosted".
-
 ---
 
 ## 💡 Key Features

cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "9router",
-  "version": "0.5.55",
+  "version": "0.5.45",
   "description": "9Router CLI - Start and manage 9Router server",
   "bin": {
     "9router": "./cli.js"

cli/scripts/build-cli.js

@@ -81,96 +81,28 @@ function copyRecursive(src, dest) {
   }
 }
 
-function resolveStandaloneBuild(appDir, buildDistDir) {
-  const legacyStandaloneRoot = path.join(appDir, ".next", "standalone");
-  const resolvedStandaloneRoot = path.join(buildDistDir, "standalone");
-  let standaloneRoot = fs.existsSync(resolvedStandaloneRoot)
-    ? resolvedStandaloneRoot
-    : legacyStandaloneRoot;
+console.log("📦 Building 9Router CLI package with Next.js...\n");
 
-  // Next.js 16 nests standalone output under the project name when
-  // NEXT_TRACING_ROOT_MODE=workspace, e.g. standalone/9router/server.js.
-  const pkgName = path.basename(appDir);
-  const nestedRoot = path.join(standaloneRoot, pkgName);
-  if (fs.existsSync(path.join(nestedRoot, "server.js")) && !fs.existsSync(path.join(standaloneRoot, "server.js"))) {
-    console.log(`ℹ️  Detected nested standalone output: ${pkgName}/`);
-    standaloneRoot = nestedRoot;
-  }
+fs.mkdirSync(buildHomeDir, { recursive: true });
+fs.mkdirSync(path.join(buildHomeDir, "AppData", "Roaming"), { recursive: true });
+fs.mkdirSync(path.join(buildHomeDir, "AppData", "Local"), { recursive: true });
 
-  const standaloneApp = fs.existsSync(path.join(standaloneRoot, "server.js"))
-    ? standaloneRoot
-    : path.join(standaloneRoot, "app");
-  if (!fs.existsSync(standaloneApp)) {
-    throw new Error(
-      "Next.js standalone build not found under .next/standalone; " +
-      "expected either .next/standalone/server.js or .next/standalone/app/",
-    );
-  }
-
-  return { standaloneApp, standaloneRoot };
-}
-
-function copyStandaloneBuild(appDir, buildDistDir, cliAppDir) {
-  const { standaloneApp, standaloneRoot } = resolveStandaloneBuild(appDir, buildDistDir);
-  copyRecursive(standaloneApp, cliAppDir);
-
-  // Older nested-app layout stores traced node_modules at standalone root.
-  const standaloneNodeModules = path.join(standaloneRoot, "node_modules");
-  if (standaloneApp !== standaloneRoot && fs.existsSync(standaloneNodeModules)) {
-    copyRecursive(standaloneNodeModules, path.join(cliAppDir, "node_modules"));
-  }
-}
-
-function mergeServerArtifacts(buildDistDir, cliAppDir) {
-  const serverSrc = path.join(buildDistDir, "server");
-  const serverDest = path.join(cliAppDir, buildDistDirName, "server");
-  if (!fs.existsSync(serverSrc)) {
-    throw new Error(`Complete Next.js server build not found: ${serverSrc}`);
-  }
-  copyRecursive(serverSrc, serverDest);
-}
-
-function assertRequiredApiArtifacts(cliAppDir) {
-  const requiredArtifacts = [
-    "app/api/v1/chat/completions/route.js",
-    "app/api/v1/messages/route.js",
-  ];
-  const serverDir = path.join(cliAppDir, buildDistDirName, "server");
-  const missingArtifacts = requiredArtifacts
-    .map((artifact) => path.join(serverDir, artifact))
-    .filter((artifact) => !fs.existsSync(artifact));
-
-  if (missingArtifacts.length > 0) {
-    throw new Error(
-      `Required CLI API route artifact${missingArtifacts.length === 1 ? " is" : "s are"} missing:\n` +
-      missingArtifacts.join("\n"),
-    );
-  }
-}
-
-function buildCliPackage() {
-  console.log("📦 Building 9Router CLI package with Next.js...\n");
-
-  fs.mkdirSync(buildHomeDir, { recursive: true });
-  fs.mkdirSync(path.join(buildHomeDir, "AppData", "Roaming"), { recursive: true });
-  fs.mkdirSync(path.join(buildHomeDir, "AppData", "Local"), { recursive: true });
-
-  // Step 0: Sync version from app/cli/package.json to app/package.json
-  console.log("0️⃣  Syncing version to app/package.json...");
-  const cliPkg = JSON.parse(fs.readFileSync(path.join(cliDir, "package.json"), "utf8"));
-  const appPkgPath = path.join(appDir, "package.json");
-  const appPkg = JSON.parse(fs.readFileSync(appPkgPath, "utf8"));
-  if (appPkg.version !== cliPkg.version) {
+// Step 0: Sync version from app/cli/package.json to app/package.json
+console.log("0️⃣  Syncing version to app/package.json...");
+const cliPkg = JSON.parse(fs.readFileSync(path.join(cliDir, "package.json"), "utf8"));
+const appPkgPath = path.join(appDir, "package.json");
+const appPkg = JSON.parse(fs.readFileSync(appPkgPath, "utf8"));
+if (appPkg.version !== cliPkg.version) {
   appPkg.version = cliPkg.version;
   fs.writeFileSync(appPkgPath, JSON.stringify(appPkg, null, 2) + "\n");
   console.log(`✅ Version synced: ${cliPkg.version}\n`);
-  } else {
+} else {
   console.log(`✅ Version already synced: ${cliPkg.version}\n`);
-  }
+}
 
-  // Step 1: Build app with Next.js (workspace tracing root → traced node_modules in standalone).
-  console.log("1️⃣  Building Next.js app...");
-  try {
+// Step 1: Build app with Next.js (workspace tracing root → traced node_modules in standalone).
+console.log("1️⃣  Building Next.js app...");
+try {
   execSync("npm run build", {
     stdio: "inherit",
     cwd: appDir,
@@ -185,48 +117,65 @@ function buildCliPackage() {
     }
   });
   console.log("✅ Next.js build completed\n");
-  } catch (error) {
+} catch (error) {
   console.error("❌ Next.js build failed");
   process.exit(1);
-  }
+}
 
-  // Step 2: Clean old app/cli/app if exists
-  console.log("2️⃣  Cleaning old app/cli/app...");
-  if (fs.existsSync(cliAppDir)) {
+// Step 2: Clean old app/cli/app if exists
+console.log("2️⃣  Cleaning old app/cli/app...");
+if (fs.existsSync(cliAppDir)) {
   fs.rmSync(cliAppDir, { recursive: true, force: true });
-  }
-  console.log("✅ Cleaned\n");
+}
+console.log("✅ Cleaned\n");
 
-  // Step 3: Copy Next.js standalone build to app/cli/app.
-  // Newer Next.js standalone output writes server.js/package.json plus .next/, src/, and
-  // node_modules/ directly under .next/standalone. Older builds may still use a nested app/.
-  console.log("3️⃣  Copying Next.js standalone build to app/cli/app...");
-  try {
-    copyStandaloneBuild(appDir, buildDistDir, cliAppDir);
-  } catch (error) {
+// Step 3: Copy Next.js standalone build to app/cli/app.
+// Newer Next.js standalone output writes server.js/package.json plus .next/, src/, and
+// node_modules/ directly under .next/standalone. Older builds may still use a nested app/.
+console.log("3️⃣  Copying Next.js standalone build to app/cli/app...");
+const standaloneRoot = path.join(appDir, ".next", "standalone");
+const standaloneRootResolved = path.join(buildDistDir, "standalone");
+let standaloneRootToUse = fs.existsSync(standaloneRootResolved) ? standaloneRootResolved : standaloneRoot;
+// Next.js 16 nests standalone output under the project name when NEXT_TRACING_ROOT_MODE=workspace
+// e.g. .next-cli-build/standalone/9router/server.js
+const pkgName = path.basename(appDir);
+const nestedRoot = path.join(standaloneRootToUse, pkgName);
+if (fs.existsSync(path.join(nestedRoot, "server.js")) && !fs.existsSync(path.join(standaloneRootToUse, "server.js"))) {
+  console.log(`ℹ️  Detected nested standalone output: ${pkgName}/`);
+  standaloneRootToUse = nestedRoot;
+}
+const standaloneApp = fs.existsSync(path.join(standaloneRootToUse, "server.js"))
+  ? standaloneRootToUse
+  : path.join(standaloneRootToUse, "app");
+if (!fs.existsSync(standaloneApp)) {
   console.error("❌ Next.js standalone build not found under .next/standalone");
   console.error("Expected either .next/standalone/server.js or .next/standalone/app/");
   process.exit(1);
-  }
-  console.log("✅ Copied standalone build\n");
+}
+copyRecursive(standaloneApp, cliAppDir);
 
-  // Step 3a: Copy custom server (injects real socket IP, strips spoofable XFF).
-  const customServerSrc = path.join(appDir, "custom-server.js");
-  if (fs.existsSync(customServerSrc)) {
+// Older nested-app layout stores traced node_modules at standalone root.
+const standaloneNodeModules = path.join(standaloneRootToUse, "node_modules");
+if (standaloneApp !== standaloneRootToUse && fs.existsSync(standaloneNodeModules)) {
+  copyRecursive(standaloneNodeModules, path.join(cliAppDir, "node_modules"));
+}
+console.log("✅ Copied standalone build\n");
+
+// Step 3a: Copy custom server (injects real socket IP, strips spoofable XFF).
+const customServerSrc = path.join(appDir, "custom-server.js");
+if (fs.existsSync(customServerSrc)) {
   fs.copyFileSync(customServerSrc, path.join(cliAppDir, "custom-server.js"));
   console.log("✅ Copied custom-server.js\n");
-  } else {
-    console.error("❌ custom-server.js not found — without it no request can be proven local,");
-    console.error("   so the packaged CLI would demand an API key for its own dashboard and /v1.");
-    process.exit(1);
-  }
+} else {
+  console.warn("⚠️  custom-server.js not found — server will run without real-IP injection\n");
+}
 
-  // Step 3b: Ensure sql.js (pure JS fallback) bundled in app/cli/app/node_modules.
-  // Strip better-sqlite3 (native) — it lives in ~/.9router/runtime to avoid
-  // Windows EBUSY during global CLI updates. node:sqlite (Node ≥22.5) is also
-  // available as a no-install middle tier.
-  console.log("3️⃣ b Configuring SQLite drivers...");
-  function ensureModuleInBundle(pkg) {
+// Step 3b: Ensure sql.js (pure JS fallback) bundled in app/cli/app/node_modules.
+// Strip better-sqlite3 (native) — it lives in ~/.9router/runtime to avoid
+// Windows EBUSY during global CLI updates. node:sqlite (Node ≥22.5) is also
+// available as a no-install middle tier.
+console.log("3️⃣ b Configuring SQLite drivers...");
+function ensureModuleInBundle(pkg) {
   const dest = path.join(cliAppDir, "node_modules", pkg);
   if (fs.existsSync(dest)) {
     console.log(`✅ ${pkg} already bundled`);
@@ -244,111 +193,89 @@ function buildCliPackage() {
   fs.mkdirSync(path.dirname(dest), { recursive: true });
   copyRecursive(src, dest);
   console.log(`✅ Bundled ${pkg}`);
-  }
-  ensureModuleInBundle("sql.js");
-  // `open` is external (see serverExternalPackages in next.config.mjs), so it must exist in
-  // the bundle's node_modules or every importer throws MODULE_NOT_FOUND at runtime. Output
-  // tracing normally copies it; this is the same belt-and-braces guard used for sql.js.
-  ensureModuleInBundle("open");
-  const betterDir = path.join(cliAppDir, "node_modules", "better-sqlite3");
-  if (fs.existsSync(betterDir)) {
+}
+ensureModuleInBundle("sql.js");
+const betterDir = path.join(cliAppDir, "node_modules", "better-sqlite3");
+if (fs.existsSync(betterDir)) {
   fs.rmSync(betterDir, { recursive: true, force: true });
   console.log("✅ Stripped better-sqlite3 (lives in ~/.9router/runtime)");
-  }
-  console.log("");
+}
+console.log("");
 
-  // Step 4: Copy static files
-  console.log("4️⃣  Copying static files...");
-  const staticSrc = path.join(appDir, ".next", "static");
-  const staticSrcResolved = path.join(buildDistDir, "static");
-  const staticDest = path.join(cliAppDir, buildDistDirName, "static");
-  if (fs.existsSync(staticSrcResolved) || fs.existsSync(staticSrc)) {
+// Step 4: Copy static files
+console.log("4️⃣  Copying static files...");
+const staticSrc = path.join(appDir, ".next", "static");
+const staticSrcResolved = path.join(buildDistDir, "static");
+const staticDest = path.join(cliAppDir, buildDistDirName, "static");
+if (fs.existsSync(staticSrcResolved) || fs.existsSync(staticSrc)) {
   copyRecursive(fs.existsSync(staticSrcResolved) ? staticSrcResolved : staticSrc, staticDest);
   console.log("✅ Copied static files\n");
-  } else {
+} else {
   console.log("⏭️  No static files found\n");
-  }
+}
 
-  // Step 5: Copy public folder if exists
-  console.log("5️⃣  Copying public folder...");
-  const publicSrc = path.join(appDir, "public");
-  const publicDest = path.join(cliAppDir, "public");
-  if (fs.existsSync(publicSrc)) {
+// Step 5: Copy public folder if exists
+console.log("5️⃣  Copying public folder...");
+const publicSrc = path.join(appDir, "public");
+const publicDest = path.join(cliAppDir, "public");
+if (fs.existsSync(publicSrc)) {
   copyRecursive(publicSrc, publicDest);
   console.log("✅ Copied public folder\n");
-  } else {
+} else {
   console.log("⏭️  No public folder found\n");
-  }
+}
 
-  // Step 6: Copy vendor-chunks (required for production)
-  console.log("6️⃣  Copying vendor-chunks...");
-  const vendorChunksSrc = path.join(appDir, ".next", "server", "vendor-chunks");
-  const vendorChunksSrcResolved = path.join(buildDistDir, "server", "vendor-chunks");
-  const vendorChunksDest = path.join(cliAppDir, buildDistDirName, "server", "vendor-chunks");
-  if (fs.existsSync(vendorChunksSrcResolved) || fs.existsSync(vendorChunksSrc)) {
+// Step 6: Copy vendor-chunks (required for production)
+console.log("6️⃣  Copying vendor-chunks...");
+const vendorChunksSrc = path.join(appDir, ".next", "server", "vendor-chunks");
+const vendorChunksSrcResolved = path.join(buildDistDir, "server", "vendor-chunks");
+const vendorChunksDest = path.join(cliAppDir, buildDistDirName, "server", "vendor-chunks");
+if (fs.existsSync(vendorChunksSrcResolved) || fs.existsSync(vendorChunksSrc)) {
   copyRecursive(fs.existsSync(vendorChunksSrcResolved) ? vendorChunksSrcResolved : vendorChunksSrc, vendorChunksDest);
   console.log("✅ Copied vendor-chunks\n");
-  } else {
+} else {
   console.log("⏭️  No vendor-chunks found\n");
-  }
+}
 
-  // Step 6b: Merge the complete generated server tree. Next.js standalone output
-  // is trace-pruned and can omit route modules or chunks loaded dynamically.
-  console.log("6️⃣ b Copying complete server artifacts...");
-  mergeServerArtifacts(buildDistDir, cliAppDir);
-  assertRequiredApiArtifacts(cliAppDir);
-  console.log("✅ Copied complete server artifacts\n");
-
-  // Step 7: Copy MITM server files (not bundled by Next.js standalone)
-  console.log("7️⃣  Copying MITM server files...");
-  const mitmSrc = path.join(appDir, "src", "mitm");
-  const mitmDest = path.join(cliAppDir, "src", "mitm");
-  if (fs.existsSync(mitmSrc)) {
+// Step 7: Copy MITM server files (not bundled by Next.js standalone)
+console.log("7️⃣  Copying MITM server files...");
+const mitmSrc = path.join(appDir, "src", "mitm");
+const mitmDest = path.join(cliAppDir, "src", "mitm");
+if (fs.existsSync(mitmSrc)) {
   copyRecursive(mitmSrc, mitmDest);
   console.log("✅ Copied MITM files\n");
-  } else {
+} else {
   console.log("⏭️  No MITM files found\n");
-  }
+}
 
-  // Step 7b: Copy standalone updater (headless Node process for install progress)
-  console.log("7️⃣ b Copying updater files...");
-  const updaterSrc = path.join(appDir, "src", "lib", "updater");
-  const updaterDest = path.join(cliAppDir, "src", "lib", "updater");
-  if (fs.existsSync(updaterSrc)) {
+// Step 7b: Copy standalone updater (headless Node process for install progress)
+console.log("7️⃣ b Copying updater files...");
+const updaterSrc = path.join(appDir, "src", "lib", "updater");
+const updaterDest = path.join(cliAppDir, "src", "lib", "updater");
+if (fs.existsSync(updaterSrc)) {
   copyRecursive(updaterSrc, updaterDest);
   console.log("✅ Copied updater files\n");
-  } else {
+} else {
   console.log("⏭️  No updater files found\n");
-  }
+}
 
-  // Step 8: Build MITM server (config driven - see app/cli/scripts/buildMitm.js)
-  console.log("8️⃣  Building MITM server...");
-  try {
+// Step 8: Build MITM server (config driven - see app/cli/scripts/buildMitm.js)
+console.log("8️⃣  Building MITM server...");
+try {
   execSync("node scripts/buildMitm.js", { stdio: "inherit", cwd: cliDir });
   console.log("✅ MITM server build completed\n");
-  } catch (error) {
+} catch (error) {
   console.error("❌ MITM build failed");
   process.exit(1);
-  }
+}
 
-  console.log("✨ CLI package build completed!");
-  console.log(`📁 Output: ${cliAppDir}`);
+console.log("✨ CLI package build completed!");
+console.log(`📁 Output: ${cliAppDir}`);
 
-  try {
+try {
   const { execSync: exec } = require("child_process");
   const size = exec(`du -sh "${cliAppDir}"`, { encoding: "utf8" }).trim();
   console.log(`📊 Package size: ${size.split("\t")[0]}`);
-  } catch (e) {
+} catch (e) {
   // Silent fail on size check
-  }
-}
-
-module.exports = {
-  assertRequiredApiArtifacts,
-  copyStandaloneBuild,
-  mergeServerArtifacts,
-};
-
-if (require.main === module) {
-  buildCliPackage();
 }

cli/src/cli/menus/providers.js

@@ -53,9 +53,6 @@ const PROVIDER_MODELS = {
     { id: "glm-4.7" },
   ],
   ag: [
-    { id: "gemini-3.7-flash-high" },
-    { id: "gemini-3.7-flash-medium" },
-    { id: "gemini-3.7-flash-low" },
     { id: "gemini-3.6-flash-high" },
     { id: "gemini-3.6-flash-medium" },
     { id: "gemini-3.6-flash-low" },

custom-server.js

@@ -1,51 +1,7 @@
 const http = require("http");
-const path = require("path");
-const fs = require("fs");
-const crypto = require("crypto");
-const { pathToFileURL } = require("url");
 
 const origCreate = http.createServer.bind(http);
 
-// Per-process secret proving x-9r-real-ip was stamped below rather than sent by the client.
-// A bare `next start` / `next dev` never loads this file, so it cannot produce a matching
-// header even though the env var is inherited by child processes. Named like x-9r-cli-token
-// so the request-detail header sanitizer redacts it too.
-const PEER_TOKEN = crypto.randomBytes(24).toString("hex");
-process.env.NINEROUTER_PEER_TOKEN = PEER_TOKEN;
-
-let backgroundRefreshStarted = false;
-
-function startBackgroundTokenRefreshFromCustomServer() {
-  if (backgroundRefreshStarted) return;
-  backgroundRefreshStarted = true;
-  // Prefer source path (repo / standalone that still has src). Fail-open if missing
-  // — initializeApp also starts the same scheduler when the Next app boots.
-  const modPath = path.join(__dirname, "src", "sse", "services", "backgroundTokenRefresh.js");
-  import(pathToFileURL(modPath).href)
-    .then((m) => {
-      try {
-        m.startBackgroundTokenRefresh();
-      } catch (e) {
-        console.error("[BackgroundTokenRefresh] start failed:", e && e.message ? e.message : e);
-      }
-      const stop = () => {
-        try {
-          m.stopBackgroundTokenRefresh();
-        } catch {
-          /* ignore */
-        }
-      };
-      process.once("SIGINT", stop);
-      process.once("SIGTERM", stop);
-    })
-    .catch((e) => {
-      // Expected in published CLI standalone (src/ not on disk). App bootstrap covers it.
-      if (process.env.DEBUG_BACKGROUND_TOKEN_REFRESH) {
-        console.error("[BackgroundTokenRefresh] import failed:", e && e.message ? e.message : e);
-      }
-    });
-}
-
 // Wrap Next standalone HTTP server: derive client IP from the TCP socket
 // (unspoofable) and strip client-supplied forwarding headers so downstream
 // rate-limiting keys on the real peer address instead of attacker-controlled XFF.
@@ -66,74 +22,11 @@ http.createServer = (...args) => {
     delete req.headers["x-9r-real-ip"];
     delete req.headers["x-forwarded-for"];
     delete req.headers["x-9r-via-proxy"];
-    delete req.headers["x-9r-peer-token"];
     req.headers["x-9r-real-ip"] = ip;
-    req.headers["x-9r-peer-token"] = PEER_TOKEN;
     if (viaProxy) req.headers["x-9r-via-proxy"] = "1";
     return handler(req, res);
   };
-  const server = origCreate(...rest, wrapped);
-  server.once("listening", () => {
-    startBackgroundTokenRefreshFromCustomServer();
-  });
-  const origEmit = server.emit;
-  // JBR 25 sends h2c upgrades that the HTTP/1.1 server would otherwise close.
-  server.emit = function (event, ...eventArgs) {
-    const [req, socket, head] = eventArgs;
-    if (event !== "upgrade" || String(req.headers.upgrade || "").toLowerCase() !== "h2c") {
-      return origEmit.call(this, event, ...eventArgs);
-    }
-
-    const contentLength = Number(req.headers["content-length"] || 0);
-    if (!Number.isSafeInteger(contentLength) || contentLength < 0) {
-      socket.destroy();
-      return true;
-    }
-    const chunks = [head];
-    let received = head.length;
-    const serve = () => {
-      // Replay the upgraded request through the existing HTTP/1.1 handler.
-      const replay = new http.IncomingMessage(socket);
-      Object.assign(replay, { method: req.method, url: req.url, headers: req.headers, complete: true });
-      if (received) replay.push(Buffer.concat(chunks, received).subarray(0, contentLength));
-      replay.push(null);
-      const res = new http.ServerResponse(replay);
-      res.shouldKeepAlive = false;
-      res.assignSocket(socket);
-      res.once("finish", () => socket.end());
-      Promise.resolve().then(() => wrapped(replay, res)).catch((error) => {
-        console.error("Failed to downgrade h2c request", error);
-        socket.destroy();
-      });
-    };
-    if (received >= contentLength) serve();
-    else {
-      socket.on("data", function readBody(chunk) {
-        chunks.push(chunk);
-        received += chunk.length;
-        if (received < contentLength) return;
-        socket.off("data", readBody);
-        serve();
-      });
-      socket.resume();
-    }
-    delete req.headers.upgrade;
-    delete req.headers["http2-settings"];
-    req.headers.connection = "close";
-    return true;
-  };
-  return server;
+  return origCreate(...rest, wrapped);
 };
 
-if (require.main === module) {
-  const standalone = path.join(__dirname, "server.js");
-  if (fs.existsSync(standalone)) {
-    require(standalone);
-  } else {
-    // Repo checkout has no standalone build next to us. `next start` builds its HTTP
-    // server in-process, so the wrapper above still sanitizes every request.
-    const nextBin = require.resolve("next/dist/bin/next");
-    process.argv = [process.argv[0], nextBin, "start", ...process.argv.slice(2)];
-    require(nextBin);
-  }
-}
+require("./server.js");

docs/superpowers/plans/2026-08-02-gpt-5-6-codex-reasoning-overrides.md

@@ -1,328 +0,0 @@
-# GPT-5.6 Codex Reasoning Overrides Implementation Plan
-
-> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
-
-**Goal:** Preserve Codex-advertised Max and Ultra overrides for GPT-5.6 Sol and Terra, preserve Max for Luna, and convert Luna Ultra to Max without changing Kiro or generic OpenAI-format behavior.
-
-**Architecture:** Keep the supported reasoning matrix in the existing `getThinkingLevels(provider, model)` resolver and reuse that result in both translation and Codex executor normalization. The dashboard already consumes this resolver, so no UI component change is required. Unsupported top-end levels remain safely normalized, with Luna Ultra selecting Luna's supported Max level.
-
-**Tech Stack:** JavaScript ES modules, Next.js, Vitest, Codex Responses transport.
-
-## Global Constraints
-
-- Apply the new overrides only to the OpenAI Codex provider (`codex`, exposed as `cx/`).
-- Sol and Terra support `max` and `ultra`; Luna supports `max` but not `ultra`.
-- Convert Luna `ultra` requests to `max` in both translated and native passthrough request paths.
-- Preserve existing Kiro and generic OpenAI-compatible normalization.
-- Do not add runtime model-catalog fetching, dependencies, pricing changes, or unrelated refactors.
-- Write each behavior test first and observe the expected failure before changing production code.
-
----
-
-### Task 1: Provider-scoped GPT-5.6 level matrix
-
-**Files:**
-- Modify: `tests/unit/thinking-levels-gpt56-sol.test.js`
-- Modify: `open-sse/providers/thinkingLevels.js`
-
-**Interfaces:**
-- Consumes: `getThinkingLevels(provider, model)` and existing capability metadata.
-- Produces: `getThinkingLevels(provider, model): string[] | null` with Codex-only GPT-5.6 level overrides.
-
-- [ ] **Step 1: Replace the Sol-only assertions with the complete behavior matrix**
-
-Use literal expected arrays so each model/provider contract is independently checked:
-
-```js
-it.each([
-  ["gpt-5.6-sol", ["none", "minimal", "low", "medium", "high", "xhigh", "max", "ultra"]],
-  ["gpt-5.6-terra", ["none", "minimal", "low", "medium", "high", "xhigh", "max", "ultra"]],
-  ["gpt-5.6-luna", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]],
-  ["gpt-5.6-sol-review", ["none", "minimal", "low", "medium", "high", "xhigh", "max", "ultra"]],
-  ["gpt-5.6-terra-review", ["none", "minimal", "low", "medium", "high", "xhigh", "max", "ultra"]],
-  ["gpt-5.6-luna-review", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]],
-])("returns Codex levels for %s", (model, expected) => {
-  expect(getThinkingLevels("codex", model)).toEqual(expected);
-});
-
-it("does not expose Codex-only GPT-5.6 overrides on Kiro", () => {
-  expect(getThinkingLevels("kiro", "gpt-5.6-sol")).toEqual([
-    "none", "minimal", "low", "medium", "high", "xhigh",
-  ]);
-});
-```
-
-Keep the older Codex-model assertion to protect the existing `gpt-5.3-codex` behavior.
-
-- [ ] **Step 2: Run the level test and verify it fails for the missing matrix/provider scoping**
-
-Run:
-
-```bash
-npx vitest run tests/unit/thinking-levels-gpt56-sol.test.js
-```
-
-Expected: FAIL because Sol lacks Ultra, Terra/Luna lack Max, and Kiro currently inherits Sol Max.
-
-- [ ] **Step 3: Add provider-aware pattern matching and the three Codex model rules**
-
-Update `PATTERN_THINKING` entries to accept an optional `provider` field and match it in `getThinkingLevels`:
-
-```js
-const CODEX_GPT_5_6_LEVELS = ["none", "minimal", "low", "medium", "high", "xhigh", "max"];
-
-const PATTERN_THINKING = [
-  { provider: "codex", pattern: "*gpt-5.6-sol*", levels: [...CODEX_GPT_5_6_LEVELS, "ultra"] },
-  { provider: "codex", pattern: "*gpt-5.6-terra*", levels: [...CODEX_GPT_5_6_LEVELS, "ultra"] },
-  { provider: "codex", pattern: "*gpt-5.6-luna*", levels: CODEX_GPT_5_6_LEVELS },
-  { pattern: "*codex*", levels: ["low", "medium", "high", "xhigh"] },
-];
-
-const hit = PATTERN_THINKING.find((entry) =>
-  (!entry.provider || entry.provider === provider) && matchPattern(entry.pattern, model)
-);
-```
-
-- [ ] **Step 4: Re-run the level test and verify it passes**
-
-Run:
-
-```bash
-npx vitest run tests/unit/thinking-levels-gpt56-sol.test.js
-```
-
-Expected: 1 test file passed with no failures.
-
-- [ ] **Step 5: Commit the capability matrix**
-
-```bash
-git add open-sse/providers/thinkingLevels.js tests/unit/thinking-levels-gpt56-sol.test.js
-git commit -m "feat(codex): expose GPT-5.6 reasoning overrides"
-```
-
-### Task 2: Model-aware shared thinking translation
-
-**Files:**
-- Modify: `tests/translator/thinking-unified.test.js`
-- Modify: `open-sse/translator/concerns/thinkingUnified.js`
-
-**Interfaces:**
-- Consumes: `getThinkingLevels(provider, cleanModel): string[] | null` from Task 1.
-- Produces: `parseSuffix(model)` support for `ultra` and `applyThinking(...)` output that preserves supported Codex levels.
-
-- [ ] **Step 1: Add failing suffix and translation tests**
-
-Add a literal parser assertion:
-
-```js
-expect(parseSuffix("gpt-5.6-sol(ultra)")).toEqual({
-  cleanModel: "gpt-5.6-sol",
-  override: { mode: "level", level: "ultra" },
-});
-```
-
-Add table-driven Codex assertions using direct request fields:
-
-```js
-it.each([
-  ["gpt-5.6-sol", "max", "max"],
-  ["gpt-5.6-sol", "ultra", "ultra"],
-  ["gpt-5.6-terra", "max", "max"],
-  ["gpt-5.6-terra", "ultra", "ultra"],
-  ["gpt-5.6-luna", "max", "max"],
-  ["gpt-5.6-luna", "ultra", "max"],
-])("normalizes Codex %s effort %s to %s", (model, effort, expected) => {
-  const out = apply("openai-responses", model, { reasoning: { effort } }, "codex");
-  expect(out.reasoning_effort).toBe(expected);
-});
-```
-
-Add a parenthesized override assertion and Kiro isolation assertion:
-
-```js
-expect(apply("openai-responses", "gpt-5.6-sol(ultra)", {}, "codex").reasoning_effort).toBe("ultra");
-expect(apply("openai", "gpt-5.6-sol", { reasoning_effort: "max" }, "kiro").reasoning_effort).toBe("xhigh");
-```
-
-- [ ] **Step 2: Run the translator test and verify it fails for Ultra parsing and preserved Max/Ultra**
-
-Run:
-
-```bash
-npx vitest run tests/translator/thinking-unified.test.js
-```
-
-Expected: FAIL because Ultra suffixes are ignored and OpenAI translation clamps Max to XHigh.
-
-- [ ] **Step 3: Implement supported-level normalization in the shared translator**
-
-Import `getThinkingLevels`. Recognize `ultra` explicitly in `parseSuffix` without adding it to the budget map. Resolve supported levels once in `applyThinking` and pass them to `applyFormat`.
-
-Use this normalization rule for the OpenAI format:
-
-```js
-function normalizeOpenAILevel(level, supportedLevels) {
-  if (level !== "max" && level !== "ultra") return level;
-  if (supportedLevels?.includes(level)) return level;
-  if (level === "ultra" && supportedLevels?.includes("max")) return "max";
-  return "xhigh";
-}
-```
-
-Keep `none`, automatic effort, budget conversion, and every non-OpenAI format unchanged.
-
-- [ ] **Step 4: Re-run the translator and generic OpenAI clamp tests**
-
-Run:
-
-```bash
-npx vitest run tests/translator/thinking-unified.test.js tests/unit/thinking-effort-openai-max-clamp.test.js
-```
-
-Expected: 2 test files passed; generic OpenAI Max still becomes XHigh.
-
-- [ ] **Step 5: Commit shared translation support**
-
-```bash
-git add open-sse/translator/concerns/thinkingUnified.js tests/translator/thinking-unified.test.js
-git commit -m "feat(codex): preserve supported reasoning efforts"
-```
-
-### Task 3: Codex native passthrough normalization
-
-**Files:**
-- Modify: `tests/unit/codex-fast-capacity.test.js`
-- Modify: `open-sse/executors/codex.js`
-
-**Interfaces:**
-- Consumes: `getThinkingLevels("codex", upstreamModel): string[] | null` from Task 1.
-- Produces: `CodexExecutor.transformRequest(...)` payloads with model-supported upstream `reasoning.effort` values.
-
-- [ ] **Step 1: Add failing Codex executor behavior tests**
-
-Add a separate `describe("Codex reasoning normalization", ...)` block with real `transformRequest` calls:
-
-```js
-it.each([
-  ["gpt-5.6-sol", "max", "max"],
-  ["gpt-5.6-sol", "ultra", "ultra"],
-  ["gpt-5.6-terra", "max", "max"],
-  ["gpt-5.6-terra", "ultra", "ultra"],
-  ["gpt-5.6-luna", "max", "max"],
-  ["gpt-5.6-luna", "ultra", "max"],
-])("normalizes %s effort %s to %s", (model, effort, expected) => {
-  const body = new CodexExecutor().transformRequest(model, {
-    model,
-    input: "hi",
-    reasoning: { effort },
-  }, true, {});
-  expect(body.reasoning.effort).toBe(expected);
-});
-
-it("resolves review models before applying the reasoning matrix", () => {
-  const body = new CodexExecutor().transformRequest("gpt-5.6-terra-review", {
-    model: "gpt-5.6-terra-review",
-    input: "hi",
-    reasoning_effort: "ultra",
-  }, true, {});
-  expect(body.model).toBe("gpt-5.6-terra");
-  expect(body.reasoning.effort).toBe("ultra");
-});
-```
-
-Keep the existing GPT-5.5 Max-to-XHigh fast-tier test.
-
-- [ ] **Step 2: Run the executor test and verify supported values fail by being clamped**
-
-Run:
-
-```bash
-npx vitest run tests/unit/codex-fast-capacity.test.js
-```
-
-Expected: FAIL because current normalization maps supported Max to XHigh and does not map Luna Ultra to Max.
-
-- [ ] **Step 3: Make Codex normalization model-aware**
-
-Import `getThinkingLevels` and replace the global Max clamp with:
-
-```js
-function normalizeReasoningEffort(model, value) {
-  const supportedLevels = getThinkingLevels("codex", model);
-  if (supportedLevels?.includes(value)) return value;
-  if (value === "ultra" && supportedLevels?.includes("max")) return "max";
-  if (value === "max" || value === "ultra") return "xhigh";
-  return value;
-}
-```
-
-Call it only after `body.model` has resolved review aliases to their upstream base model. Pass `body.model` for both `reasoning_effort` and existing `reasoning.effort` request shapes.
-
-- [ ] **Step 4: Re-run the executor and focused feature suites**
-
-Run:
-
-```bash
-npx vitest run tests/unit/codex-fast-capacity.test.js tests/unit/thinking-levels-gpt56-sol.test.js tests/translator/thinking-unified.test.js tests/unit/thinking-effort-openai-max-clamp.test.js
-```
-
-Expected: 4 test files passed with no failures.
-
-- [ ] **Step 5: Commit native Codex normalization**
-
-```bash
-git add open-sse/executors/codex.js tests/unit/codex-fast-capacity.test.js
-git commit -m "feat(codex): forward GPT-5.6 max and ultra efforts"
-```
-
-### Task 4: Full verification and pull request
-
-**Files:**
-- Verify all changed production, test, design, and plan files.
-
-**Interfaces:**
-- Consumes: completed Tasks 1-3.
-- Produces: verified branch pushed to `origin` and a pull request targeting `decolua/9router:master`.
-
-- [ ] **Step 1: Run all focused regression tests**
-
-```bash
-npx vitest run tests/unit/thinking-levels-gpt56-sol.test.js tests/translator/thinking-unified.test.js tests/unit/thinking-effort-openai-max-clamp.test.js tests/unit/codex-fast-capacity.test.js
-```
-
-Expected: all selected test files and tests pass.
-
-- [ ] **Step 2: Run the complete unit test suite**
-
-```bash
-npx vitest run tests/unit tests/translator
-```
-
-Expected: all test files pass with zero failed tests.
-
-- [ ] **Step 3: Run the production build**
-
-```bash
-npm run build
-```
-
-Expected: Next.js production build exits with status 0.
-
-- [ ] **Step 4: Verify repository hygiene and requirement coverage**
-
-```bash
-git diff --check upstream/master...HEAD
-git status --short --branch
-git log --oneline upstream/master..HEAD
-```
-
-Expected: no whitespace errors, no uncommitted source changes, and only scoped feature commits.
-
-- [ ] **Step 5: Push the feature branch and open the pull request**
-
-```bash
-git push -u origin codex/gpt-5-6-reasoning-overrides
-gh pr create --repo decolua/9router --base master --head seakleangnhak:codex/gpt-5-6-reasoning-overrides --title "feat(codex): support GPT-5.6 Max and Ultra overrides" --body $'## Summary\n- expose Max and Ultra for Codex GPT-5.6 Sol and Terra\n- expose Max for Codex GPT-5.6 Luna and normalize Luna Ultra to Max\n- keep Kiro and generic OpenAI-compatible reasoning behavior unchanged\n\n## Verification\n- `npx vitest run tests/unit tests/translator`\n- `npm run build`'
-```
-
-The pull request body must summarize the Codex-only support matrix, Luna Ultra-to-Max fallback, Kiro isolation, and fresh test/build evidence.

docs/superpowers/specs/2026-08-02-gpt-5-6-codex-reasoning-overrides-design.md

@@ -1,122 +0,0 @@
-# GPT-5.6 Codex Reasoning Overrides Design
-
-## Goal
-
-Expose and preserve the reasoning levels currently advertised by the OpenAI
-Codex model catalog for GPT-5.6 Sol, Terra, and Luna when they are routed
-through the `codex` provider (`cx/`).
-
-The supported override matrix is:
-
-| Model family | Max | Ultra |
-| --- | --- | --- |
-| GPT-5.6 Sol | Yes | Yes |
-| GPT-5.6 Terra | Yes | Yes |
-| GPT-5.6 Luna | Yes | No |
-
-The same matrix applies to 9router's virtual `-review` variants because they
-resolve to the corresponding upstream base model.
-
-## Scope
-
-This change is limited to OpenAI Codex (`cx/`) routes. Kiro (`kr/`) and other
-OpenAI-format providers retain their existing reasoning-level behavior even
-when they expose models with the same GPT-5.6 names.
-
-The change covers the complete local request path:
-
-1. The provider page advertises only the levels supported by each Codex model.
-2. A copied model suffix such as `gpt-5.6-sol(ultra)` is parsed as a reasoning
-   override.
-3. The shared thinking translator preserves a supported Codex override while
-   retaining the existing `xhigh` fallback for unsupported OpenAI levels.
-4. The Codex executor sends supported `max` and `ultra` values unchanged to the
-   upstream Codex Responses endpoint.
-
-## Current Behavior
-
-`gpt-5.6-luna` and the other GPT-5.6 models already exist in the Codex model
-registry. The capability picker has a global Sol-only `max` pattern, which also
-affects providers such as Kiro unintentionally. The shared OpenAI translator
-and Codex executor then convert `max` to `xhigh`, so the advertised override is
-not preserved end to end. `ultra` is not recognized as a model suffix.
-
-## Design
-
-### Provider-scoped level resolution
-
-Extend the existing model-pattern overrides in
-`open-sse/providers/thinkingLevels.js` with an optional provider constraint.
-Add three Codex-only GPT-5.6 patterns in most-specific order:
-
-- Sol: existing levels plus `max` and `ultra`.
-- Terra: existing levels plus `max` and `ultra`.
-- Luna: existing levels plus `max`.
-
-Matching remains wildcard-based so virtual `-review` variants inherit the
-base model's levels. Provider matching prevents these overrides from changing
-Kiro or other providers.
-
-### Shared translation
-
-Teach the suffix parser to recognize `ultra` as a discrete level without
-assigning it a synthetic token budget. When applying the OpenAI wire format,
-reuse the resolved per-provider model levels:
-
-- Preserve `max` or `ultra` when the target provider/model explicitly supports
-  the requested level.
-- Convert `ultra` to `max` for GPT-5.6 Luna, preserving the highest level Luna
-  supports.
-- Convert other unsupported `max` or `ultra` requests to `xhigh`, preserving
-  the existing safe fallback for generic OpenAI-compatible providers.
-- Leave all existing lower levels and `none` handling unchanged.
-
-This keeps one capability source for the dashboard and translation behavior
-instead of duplicating the GPT-5.6 matrix.
-
-### Codex executor
-
-Make Codex reasoning normalization model-aware. After virtual review models
-are resolved to their upstream base model, preserve a requested level when
-the Codex capability resolver lists it. Continue converting unsupported
-`max` or `ultra` values to `xhigh`, except that Luna converts `ultra` to its
-supported `max` level.
-
-Do not add `max` to the executor's legacy hyphen-suffix parser because
-`gpt-5.1-codex-max` is an actual model identifier. Dashboard overrides use the
-existing parenthesized suffix and the shared translator removes that suffix
-before executor dispatch.
-
-## Error and Compatibility Behavior
-
-- `cx/gpt-5.6-luna(ultra)` becomes `max` rather than sending an unsupported
-  level upstream.
-- Non-GPT-5.6 Codex models retain their current supported levels and fallback
-  behavior.
-- Kiro GPT-5.6 routes no longer inherit the Codex Sol-only picker override and
-  continue using Kiro's existing effort normalization.
-- Direct request fields and parenthesized model overrides follow the same
-  model-aware rules.
-
-## Testing
-
-Use test-driven development with focused unit coverage:
-
-1. Level resolver tests for Sol, Terra, Luna, their review variants, an older
-   Codex model, and Kiro isolation.
-2. Shared translator tests proving `max` and `ultra` survive only for supported
-   Codex model/provider combinations, Luna `ultra` becomes `max`, and other
-   unsupported combinations become `xhigh`.
-3. Codex executor tests proving native and translated request shapes preserve
-   supported values after upstream model resolution.
-4. Existing thinking translation and Codex executor suites to guard generic
-   OpenAI clamping and fast-tier behavior.
-5. Project lint/build checks in proportion to the changed JavaScript modules.
-
-## Non-goals
-
-- Runtime fetching or caching of the Codex model catalog.
-- Adding these levels to Kiro or another provider.
-- Changing model pricing, quotas, defaults, or service tiers.
-- Adding Codex Ultra's multi-agent orchestration behavior inside 9router;
-  9router only forwards the catalog-advertised reasoning override.

i18n/README.vi.md

@@ -1,15 +1,21 @@
+Dưới đây là bản dịch tiếng Việt của tài liệu Markdown, giữ nguyên toàn bộ cú pháp và cấu trúc kỹ thuật.
+
 <div align="center">
   <img src="../images/9router.png?1" alt="Bảng điều khiển 9Router" width="800"/>
   
-  # 9Router - Free AI Router & Token Saver
+  # 9Router - Free AI Router
   
-  **Không bao giờ ngừng code. Tiết kiệm 20-40% token với RTK + tự động dự phòng sang các mô hình AI MIỄN PHÍ & giá rẻ.**
+  **Không bao giờ ngừng code. Tự động định tuyến tới các mô hình AI MIỄN PHÍ & giá rẻ với cơ chế dự phòng thông minh.**
   
-  **Kết nối tất cả công cụ AI Code (Claude Code, Codex, Cursor, Cline, Copilot, Antigravity...) tới 40+ Nhà cung cấp AI & 100+ Mô hình.**
+  **Nhà cung cấp AI Miễn cho OpenClaw.**
+  
+  <p align="center">
+    <img src="../public/providers/openclaw.png" alt="OpenClaw" width="80"/>
+  </p>
   
   [![npm](https://img.shields.io/npm/v/9router.svg)](https://www.npmjs.com/package/9router)
   [![Downloads](https://img.shields.io/npm/dm/9router.svg)](https://www.npmjs.com/package/9router)
-  [![License](https://github.com/decolua/9router/blob/main/LICENSE)](https://github.com/decolua/9router/blob/main/LICENSE)
+  [![License](https://img.shields.io/npm/l/9router.svg)](https://github.com/decolua/9router/blob/main/LICENSE)
   
   [🚀 Bắt đầu nhanh](#-quick-start) • [💡 Tính năng](#-key-features) • [📖 Cài đặt](#-setup-guide) • [🌐 Website](https://9router.com)
 </div>
@@ -18,21 +24,19 @@
 
 ## 🤔 Tại sao chọn 9Router?
 
-**Ngừng lãng phí tiền bạc, token và không bao giờ lo chạm giới hạn (rate limit):**
+**Ngừng lãng phí tiền bạc và gặp phải giới hạn:**
 
 - ❌ Hạn mức gói đăng ký hết hạn mỗi tháng mà không dùng hết
-- ❌ Giới hạn tốc độ (rate limit) làm gián đoạn công việc mid-coding
-- ❌ Kết quả của công cụ (git diff, grep, ls...) ngốn rất nhiều token
-- ❌ Chi phí API đắt đỏ ($20-50/tháng cho từng nhà cung cấp)
-- ❌ Phải chuyển đổi thủ công giữa các nhà cung cấp AI
+- ❌ Giới hạn tốc độ (rate limit) ngăn bạn giữaừng khi code
+- ❌ Các API đắt đỏ ($20-50/tháng cho mỗi nhà cung cấp)
+- ❌ Phải chuyển đổi thủ công giữa các nhà cung cấp
 
 **9Router giải quyết vấn đề này:**
 
-- ✅ **RTK Token Saver** - Tự động nén nội dung `tool_result`, tiết kiệm 20-40% token trên mỗi request
-- ✅ **Tối đa hóa gói đăng ký** - Theo dõi hạn mức, tận dụng triệt để trước khi reset
-- ✅ **Tự động dự phòng (Auto Fallback)** - Gói đăng ký → Giá rẻ → Miễn phí, không lo downtime
-- ✅ **Đa tài khoản (Multi-account)** - Xoay vòng (round-robin) các tài khoản cho mỗi nhà cung cấp
-- ✅ **Phổ quát (Universal)** - Hoạt động với Claude Code, Codex, Cursor, Cline, Antigravity và mọi công cụ CLI
+- ✅ **Tối đa hóa gói đăng ký** - Theo dõi hạn mức, sử dụng từng bit trước khi reset
+- ✅ **Tự động dự phòng** - Gói đăng ký → Giá rẻ → Miễn phí, thời gian chết bằng không
+- ✅ **Đa tài khoản** - Vòng tròn (round-robin) các tài khoản của mỗi nhà cung cấp
+- ✅ **Phổ quát** - Hoạt động với Claude Code, Codex, Gemini CLI, Cursor, Cline, bất kỳ công cụ CLI nào
 
 ---
 
@@ -40,26 +44,25 @@
 
 ```
 ┌─────────────┐
-│  Công cụ    │  (Claude Code, Codex, OpenClaw, Cursor, Cline, Antigravity...)
-│  CLI AI     │
+│  Your CLI   │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
+│   Tool      │
 └──────┬──────┘
        │ http://localhost:20128/v1
        ↓
-┌─────────────────────────────────────────────┐
+┌────────────────────────────────────────┐
 │           9Router (Smart Router)        │
-│  • RTK Token Saver (nén tool_result token) │
-│  • Dịch chuyển định dạng (OpenAI ↔ Claude) │
-│  • Quota tracking (theo dõi hạn mức)       │
-│  • Tự động làm mới OAuth Token             │
-└──────┬──────────────────────────────────────┘
+│  • Format translation (OpenAI ↔ Claude) │
+│  • Quota tracking                       │
+│  • Auto token refresh                   │
+└──────┬──────────────────────────────────┘
        │
-       ├─→ [Tier 1: GÓI ĐĂNG KÝ] Claude Code, Codex, GitHub Copilot
-       │   ↓ hết hạn mức quota
-       ├─→ [Tier 2: GIÁ RẺ] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ chạm ngân sách
-       └─→ [Tier 3: MIỄN PHÍ] Kiro AI, OpenCode Free, Vertex AI ($300 credits)
+       ├─→ [Tier 1: SUBSCRIPTION] Claude Code, Codex, Gemini CLI
+       │   ↓ quota exhausted
+       ├─→ [Tier 2: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
+       │   budget limit
+       └─→ [Tier 3: FREE] iFlow, Qwen, Kiro (unlimited)
 
-Kết quả: Không bao giờ ngừng code, chi phí tối thiểu + tiết kiệm 20-40% token qua RTK
+Result: Never stop coding, minimal cost
 ```
 
 ---
@@ -73,26 +76,26 @@ npm install -g 9router
 9router
 ```
 
-🎉 Bảng điều khiển (Dashboard) sẽ tự động mở tại `http://localhost:20128`
+🎉 Bảng điều khiển mở tại `http://localhost:20128`
 
 **2. Kết nối nhà cung cấp MIỄN PHÍ (không cần đăng ký):**
 
-Bảng điều khiển → Providers → Kết nối **Kiro AI** (~50 credits/tháng miễn phí: Claude 4.5 + GLM-5 + MiniMax) hoặc **OpenCode Free** (không cần auth) → Xong!
+Bảng điều khiển → Providers -> Kết nối **ude Code** hoặc **Antigravity** -> Đăng nhập OAuth -> Xong!
 
 **3. Sử dụng trong công cụ CLI của bạn:**
 
 ```
-Cài đặt Claude Code/Codex/OpenClaw/Cursor/Cline/Antigravity:
+Cài đặt Claude Code/Codex/Gemini CLI/OpenClaw/Cursor/Cline:
   Endpoint: http://localhost:20128/v1
   API Key: [sao chép từ bảng điều khiển]
-  Model: kr/claude-sonnet-4.5
+  Model: if/kimi-k2-thinking
 ```
 
-**Thế là xong!** Bắt đầu code ngay với các mô hình AI MIỄN PHÍ.
+**Xong rồi!** Bắt đầu code với các mô hình AI MIỄN PHÍ.
 
-**Phương án khác: chạy từ mã nguồn (repository này):**
+**Phương án khác: chạy từ nguồn (k lưu trữ này):**
 
-Gói kho lưu trữ này là riêng tư (`9router-app`), vì vậy việc chạy từ nguồn/Docker là cách phát triển cục bộ mặc định.
+Gói kho lưu trữ này là riêng tư (`9router-app`), vì vậy việc thực thi nguồn/Docker là đường dẫn phát triển cục bộ dự kiến.
 
 ```bash
 cp .env.example .env
@@ -108,12 +111,11 @@ PORT=20128 HOSTNAME=0.0.0.0 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run
 ```
 
 URL mặc định:
-- Bảng điều khiển Dashboard: `http://localhost:20128/dashboard`
+- Bảng điều khiển: `http://localhost:20128/dashboard`
 - API tương thích OpenAI: `http://localhost:20128/v1`
 
 ---
 
-
 ## 🎥 Hướng dẫn Video
 
 <div align="center">

i18n/README.zh-CN.md

@@ -42,26 +42,25 @@
 
 ```
 ┌─────────────┐
-│  Your CLI   │  (Claude Code, Codex, OpenClaw, Cursor, Cline, Antigravity...)
+│  Your CLI   │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
 │   Tool      │
 └──────┬──────┘
-       │ http://localhost:20128/v1
+       │ http://localhost:201281
        ↓
-┌─────────────────────────────────────────────┐
+┌─────────────────────────────────────────┐
 │           9Router (Smart Router)        │
-│  • RTK Token Saver (节省 20-40% Token)      │
-│  • 格式转换 (OpenAI ↔ Claude)               │
-│  • 配额追踪 (Quota tracking)                │
-│  • 自动刷新 OAuth Token                     │
-└──────┬──────────────────────────────────────┘
+│  • Format translation (OpenAI ↔ Claude) │
+│  • Quota tracking                       │
+│  • Auto token refresh                   │
+└──────┬──────────────────────────────────┘
        │
-       ├─→ [Tier 1: 订阅] Claude Code, Codex, GitHub Copilot
-       │   ↓ 配额用尽
-       ├─→ [Tier 2: 低价] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ 触及预算上限
-       └─→ [Tier 3: 免费] Kiro AI, OpenCode Free, Vertex AI ($300 credits)
+       ├─→ [Tier 1: SUBSCRIPTION] Claude Code, Codex, Gemini CLI
+       │   ↓ quota exhausted
+       ├─→ [Tier 2: CHEAP] GLM ($0.6/1M), MiniMax ($0.2/1M)
+       │   ↓ budget limit
+       └─→ [Tier 3: FREE] iFlow, Qwen, Kiro (unlimited)
 
-结果：永不停歇的编程体验，最低成本 + 通过 RTK 节省 20-40% Token
+Result: Never stop coding, minimal cost
 ```
 
 ---

next.config.mjs

@@ -13,14 +13,7 @@ const proxyClientMaxBodySize = process.env.NINEROUTER_PROXY_CLIENT_MAX_BODY_SIZE
 const nextConfig = {
   distDir: process.env.NEXT_DIST_DIR || ".next",
   output: "standalone",
-  // `open` must stay external. It derives its own directory from `import.meta.url`, and
-  // webpack replaces that with the absolute path of the BUILD machine as a string literal.
-  // A release built on macOS therefore ships `file:///Users/.../open/index.js`, which
-  // `fileURLToPath` rejects on Windows ("File URL path must be absolute" — no drive
-  // letter). That throw happens at module scope, so every consumer of `open` dies on
-  // import — including xAI/Grok token refresh, which loads the OAuth service that imports
-  // it. Keeping it external preserves the real `import.meta.url` at runtime.
-  serverExternalPackages: ["better-sqlite3", "sql.js", "node:sqlite", "bun:sqlite", "open"],
+  serverExternalPackages: ["better-sqlite3", "sql.js", "node:sqlite", "bun:sqlite"],
   turbopack: {
     root: tracingRoot
   },

open-sse/AGENTS.md

@@ -37,3 +37,7 @@ Provider-agnostic SSE engine: one OpenAI-style request → any provider (LLM cha
 - `registry/index.js` is an auto-generated static import list; regenerate it (don't hand-edit) after adding a `registry/{id}.js`. REGISTRY_TEMPLATE is excluded by design.
 - Special binary/protobuf formats (kiro EventStream, cursor protobuf, commandcode NDJSON) don't round-trip through OpenAI — handle in their executor.
 - `rtk/` + `headroom.js` mutate the request body in-place and are **fail-open**: any error returns null and leaves the body untouched — never throw out of them. RTK skips `is_error`/`status:"error"` tool results to preserve traces.
+- **HTTP 200 in-stream errors**: some upstreams signal failure INSIDE a 200 stream (AI SDK v5 `{"type":"error"}` events, error text in content). HTTP-level success checks miss these → no fallback, `Status: success` in logs. Three hook points + one config escape hatch:
+  1. **Translator** — never map an error event to content. Emit an OpenAI-shaped `chunk.error = { message, type }` + terminal chunk (`translator/response/commandcode-to-openai.js` is the worked example). Downstream `parseSSEToOpenAIResponse` already detects `chunk?.error`.
+  2. **Executor early-peek** — for streaming fallback, read the first events BEFORE returning the response; an error → non-ok Response (`executors/commandcode.js` `peekForUpstreamError`).
+  3. **Config escape hatch (no code)** — per-provider `streamErrorPatterns` setting (UI: provider page → Stream Error Patterns). Patterns matched against the first ~8KB of the stream and the assembled non-streaming content; see `utils/streamErrorPeek.js` + `utils/streamErrorPatterns.js`.

open-sse/config/appConstants.js

@@ -156,13 +156,6 @@ export const LOAD_CODE_ASSIST_HEADERS = {
   "Client-Metadata": JSON.stringify({ ideType: IDE_TYPE.ANTIGRAVITY, platform: getPlatformEnum(), pluginType: PLUGIN_TYPE.GEMINI }),
 };
 
-// Real Antigravity IDE doesn't send X-Goog-Api-Client/Client-Metadata on loadCodeAssist/onboardUser —
-// Google's backend fingerprints those and silently refuses to provision a cloudaicompanionProject.
-export const ANTIGRAVITY_LOAD_CODE_ASSIST_HEADERS = {
-  "Content-Type": "application/json",
-  "User-Agent": ANTIGRAVITY_IDE_USER_AGENT,
-};
-
 export const LOAD_CODE_ASSIST_METADATA = {
   ideType: IDE_TYPE.ANTIGRAVITY,
   platform: getPlatformEnum(),
@@ -183,6 +176,7 @@ export const OAUTH_ENDPOINTS = {
   google:    { token: "https://oauth2.googleapis.com/token", auth: "https://accounts.google.com/o/oauth2/auth" },
   openai:    { token: PROVIDER_OAUTH["codex"]?.tokenUrl, auth: PROVIDER_OAUTH["codex"]?.authorizeUrl },
   anthropic: { token: PROVIDER_OAUTH["claude"]?.tokenUrl, auth: "https://api.anthropic.com/v1/oauth/authorize" }, // ≠ claude.authorizeUrl (claude.ai login) — keep
+  qwen:      { token: PROVIDER_OAUTH["qwen"]?.tokenUrl, auth: PROVIDER_OAUTH["qwen"]?.deviceCodeUrl },
   iflow:     { token: PROVIDER_OAUTH["iflow"]?.tokenUrl, auth: PROVIDER_OAUTH["iflow"]?.authorizeUrl },
   github:    { token: PROVIDER_OAUTH["github"]?.tokenUrl, auth: PROVIDER_OAUTH["github"]?.authorizeUrl, deviceCode: PROVIDER_OAUTH["github"]?.deviceCodeUrl },
 };

open-sse/config/providerModels.js

@@ -2,7 +2,7 @@ import { PROVIDERS } from "./providers.js";
 import REGISTRY from "../providers/registry/index.js";
 // PROVIDER_MODELS now built from providers/registry (transport + models co-located)
 import { PROVIDER_MODELS } from "../providers/index.js";
-import { modelQuotaFamily, modelStrip, modelTargetFormat, modelSupportedFormats, normalizeModelId } from "../providers/models/schema.js";
+import { modelQuotaFamily, modelStrip, modelTargetFormat, normalizeModelId } from "../providers/models/schema.js";
 import { CODEX_REVIEW_SUFFIX } from "../providers/models/helpers.js";
 export { PROVIDER_MODELS };
 
@@ -54,14 +54,6 @@ export function getModelTargetFormat(aliasOrId, modelId) {
   return modelTargetFormat(findModel(models, modelId, aliasOrId));
 }
 
-// Declared upstream formats for a model (registry `supportedFormats`). Drives the
-// per-model guard on the sourceFormat-matched transport; null when undeclared.
-export function getModelSupportedFormats(aliasOrId, modelId) {
-  const models = PROVIDER_MODELS[aliasOrId];
-  if (!models) return null;
-  return modelSupportedFormats(findModel(models, modelId, aliasOrId));
-}
-
 export function getModelType(aliasOrId, modelId) {
   const models = PROVIDER_MODELS[aliasOrId];
   if (!models) return null;

open-sse/config/ttsModels.js

@@ -33,21 +33,6 @@ const GEMINI_VOICES = [
   "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat",
 ].map((id) => ({ id, name: id, type: "tts" }));
 
-// Xiaomi MiMo preset voices (from https://mimo.mi.com/docs/zh-CN/quick-start/usage-guide/audio/speech-synthesis-v2.5).
-// Voice id is passed via `audio.voice`; `mimo_default` = default (冰糖 on CN cluster, Mia elsewhere).
-// Voices are language-independent — the spoken language is a separate hint, not bound to the voice.
-const MIMO_VOICES = [
-  { id: "mimo_default", name: "mimo_default" },
-  { id: "冰糖",           name: "冰糖" },
-  { id: "茉莉",           name: "茉莉" },
-  { id: "苏打",           name: "苏打" },
-  { id: "白桦",           name: "白桦" },
-  { id: "Mia",           name: "Mia" },
-  { id: "Chloe",         name: "Chloe" },
-  { id: "Milo",          name: "Milo" },
-  { id: "Dean",          name: "Dean" },
-].map((v) => ({ type: "tts", ...v }));
-
 // ── TTS Config (config-driven, single source of truth) ─────────────────────
 export const TTS_MODELS_CONFIG = {
   openai: {
@@ -122,14 +107,6 @@ export const TTS_MODELS_CONFIG = {
     },
     allVoices: GEMINI_VOICES,
   },
-  "xiaomi-mimo": {
-    models: [
-      { id: "mimo-v2.5-tts", name: "MiMo V2.5 TTS", type: "tts" },
-    ],
-    voices: {
-      "mimo-v2.5-tts": MIMO_VOICES,
-    },
-  },
 };
 
 // ── Helper: get voices for a specific model ────────────────────────────────

open-sse/executors/antigravity.js

@@ -245,18 +245,6 @@ export class AntigravityExecutor extends BaseExecutor {
     // Strip tools/toolConfig (handled separately) and blacklisted fields that Google rejects
     const { tools: _originalTools, toolConfig: _originalToolConfig, ...requestWithoutTools } = body.request || {};
     stripBlacklisted(requestWithoutTools);
-    
-    // Rewrite competitive system prompts (e.g. Zed IDE's Claude prompt) to prevent Antigravity from 
-    // flagging the request and immediately blocking it with a 429 Quota Exhausted response.
-    if (requestWithoutTools.systemInstruction?.parts) {
-      const oldText = "You are a Claude agent, built on Anthropic's Claude Agent SDK.";
-      for (const part of requestWithoutTools.systemInstruction.parts) {
-        if (typeof part.text === "string" && part.text.includes(oldText)) {
-          part.text = part.text.split(oldText).join("");
-        }
-      }
-    }
-
     const generationConfig = { ...(requestWithoutTools.generationConfig || {}) };
     if (generationConfig.maxOutputTokens > MAX_ANTIGRAVITY_OUTPUT_TOKENS) {
       generationConfig.maxOutputTokens = MAX_ANTIGRAVITY_OUTPUT_TOKENS;

open-sse/executors/base.js

@@ -2,8 +2,8 @@ import { HTTP_STATUS, RETRY_CONFIG, DEFAULT_RETRY_CONFIG, resolveRetryEntry, FET
 import { shouldRefreshCredentials } from "../services/oauthCredentialManager.js";
 import { proxyAwareFetch } from "../utils/proxyFetch.js";
 import { dbg } from "../utils/debugLog.js";
+import { resolveProviderTimeoutMs } from "../services/providerTimeout.js";
 import { ANTHROPIC_API_VERSION, OPENAI_COMPAT_BASE, ANTHROPIC_COMPAT_BASE } from "../providers/shared.js";
-import { resolveOpenAICompatibleApiType } from "../services/provider.js";
 
 /**
  * BaseExecutor - Base class for provider executors
@@ -31,7 +31,7 @@ export class BaseExecutor {
     if (this.provider?.startsWith?.("openai-compatible-")) {
       const baseUrl = credentials?.providerSpecificData?.baseUrl || OPENAI_COMPAT_BASE;
       const normalized = baseUrl.replace(/\/$/, "");
-      const path = resolveOpenAICompatibleApiType(this.provider, credentials) === "responses" ? "/responses" : "/chat/completions";
+      const path = this.provider.includes("responses") ? "/responses" : "/chat/completions";
       return `${normalized}${path}`;
     }
     if (this.provider?.startsWith?.("anthropic-compatible-")) {
@@ -127,19 +127,20 @@ export class BaseExecutor {
     for (let urlIndex = 0; urlIndex < fallbackCount; urlIndex++) {
       const url = this.buildUrl(model, stream, urlIndex, credentials);
       const transformedBody = this.transformRequest(model, body, stream, credentials);
-      const headers = this.buildHeaders(credentials, stream, url, model);
+      const headers = this.buildHeaders(credentials, stream, url);
 
       if (!retryAttemptsByUrl[urlIndex]) retryAttemptsByUrl[urlIndex] = 0;
 
       // Abort if upstream doesn't return response headers within connection timeout
       const connectCtrl = new AbortController();
-      const timeoutMs = this.config?.timeoutMs || FETCH_CONNECT_TIMEOUT_MS;
+      const timeoutMs = await resolveProviderTimeoutMs(this.provider, this.config?.timeoutMs, FETCH_CONNECT_TIMEOUT_MS);
       const connectTimer = setTimeout(() => connectCtrl.abort(new Error("fetch connect timeout")), timeoutMs);
       const mergedSignal = signal ? AbortSignal.any([signal, connectCtrl.signal]) : connectCtrl.signal;
+      let fetchT0 = 0;
 
       try {
         const bodyStr = JSON.stringify(transformedBody);
-        const fetchT0 = Date.now();
+        fetchT0 = Date.now();
         dbg("FETCH", `${this.provider.toUpperCase()} → ${url} | body=${bodyStr.length}B | connectTimeout=${timeoutMs}ms`);
         const response = await proxyAwareFetch(url, {
           method: "POST",
@@ -165,6 +166,11 @@ export class BaseExecutor {
         clearTimeout(connectTimer);
         lastError = error;
         const isConnectTimeout = connectCtrl.signal.aborted && error.name === "AbortError";
+        // Error diagnostic — only logs on actual upstream failure. Distinguishes
+        // undici connect timeout (UND_ERR_CONNECT_TIMEOUT), DNS (ENOTFOUND),
+        // refused (ECONNREFUSED) vs our own connectCtrl abort (AbortError).
+        const cause = error?.cause || {};
+        console.log(`[FETCH-DIAG] ${this.provider} fetch error | name=${error.name} | code=${error.code ?? cause?.code ?? "none"} | msg=${String(error.message).slice(0, 120)} | connectTimeout=${timeoutMs}ms | elapsed=${Date.now() - fetchT0}ms`);
         dbg("FETCH", `${this.provider.toUpperCase()} ✖ ${error.name}: ${error.message}${isConnectTimeout ? " (connect timeout)" : ""}`);
         // Connect timeout is internal — convert to retryable network error, don't propagate AbortError
         if (error.name === "AbortError" && !isConnectTimeout) throw error;

open-sse/executors/codebuddy-cn.js

@@ -18,35 +18,6 @@ export class CodeBuddyExecutor extends DefaultExecutor {
     const transformed = super.transformRequest(model, body, stream, credentials);
     transformed.stream = true;
 
-    // Tencent's content filter flags CLI agent system prompts ("You are Claude
-    // Code, Anthropic's official CLI...") as prompt injection / sensitive content
-    // and rejects the whole request. Detect agent system prompts (length catch-all
-    // + identity-marker regex) and replace them with a neutral one, while leaving
-    // legitimate user system prompts untouched. content may be a string or typed
-    // blocks ([{type:"text",text}]) depending on the incoming client format, so
-    // flatten before matching and preserve the original shape on replacement.
-    const NEUTRAL_PROMPT = "You are a helpful AI assistant that helps with software engineering tasks.";
-    const AGENT_PATTERN = /you are claude code|claude.?code.+official.+cli|anthropic.+official.+cli|anxthxropic.+official.+cli|you are (?:cursor|windsurf|cline|aider|continue|copilot|cody)|you are an? (?:ai )?(?:coding |code )?agent|cc_entrypoint\s*=\s*(?:cli|vscode|jetbrains|gui)|claude.?code.+issues|give feedback.+claude.?code|you are .{0,30}(?:powerful )?ai agent|orchestration capabilities|OhMyOpenCode|<agent-identity>|<Role>|<Behavior_Instructions>/i;
-    const flatten = (content) =>
-      typeof content === "string"
-        ? content
-        : Array.isArray(content)
-          ? content.map((b) => (b && typeof b.text === "string" ? b.text : "")).join("\n")
-          : "";
-    if (Array.isArray(transformed.messages)) {
-      transformed.messages = transformed.messages.map((message) => {
-        if (!message || message.role !== "system") return message;
-        const text = flatten(message.content);
-        if (!text) return message;
-        if (text.length > 2000 || AGENT_PATTERN.test(text)) {
-          return typeof message.content === "string"
-            ? { ...message, content: NEUTRAL_PROMPT }
-            : { ...message, content: [{ type: "text", text: NEUTRAL_PROMPT }] };
-        }
-        return message;
-      });
-    }
-
     // CodeBuddy only surfaces model reasoning when the request carries the CLI's
     // OpenAI-style params: reasoning_effort + reasoning_summary:"auto". 9router's
     // thinking pipeline sets reasoning_effort only when the client asks, and never

open-sse/executors/codebuddy-intl.js

@@ -23,20 +23,6 @@ export class CodeBuddyIntlExecutor extends DefaultExecutor {
     } else if (eff) {
       transformed.reasoning_summary = "auto";
     }
-
-    // CodeBuddy rejects plain OpenAI shape (11101 invalid request): needs a
-    // leading system prompt + user content as typed blocks, not a bare string.
-    const source = Array.isArray(transformed.messages) ? transformed.messages : [];
-    transformed.messages = [{ role: "system", content: "You are CodeBuddy Code." }];
-    for (const message of source) {
-      if (!message || typeof message !== "object" || ["system", "developer"].includes(message.role)) continue;
-      if (message.role === "user" && typeof message.content === "string") {
-        transformed.messages.push({ ...message, content: [{ type: "text", text: message.content }] });
-      } else {
-        transformed.messages.push({ ...message });
-      }
-    }
-
     return transformed;
   }
 }

open-sse/executors/codex.js

@@ -8,7 +8,6 @@ import {
 import { normalizeResponsesInput } from "../translator/formats/responsesApi.js";
 import { fetchImageAsBase64 } from "../translator/concerns/image.js";
 import { getModelUpstreamId } from "../config/providerModels.js";
-import { getThinkingLevels } from "../providers/thinkingLevels.js";
 import { DEFAULT_RETRY_CONFIG, HTTP_STATUS, resolveRetryEntry } from "../config/runtimeConfig.js";
 import { dbg } from "../utils/debugLog.js";
 import { resolveSessionId } from "../utils/sessionManager.js";
@@ -125,12 +124,8 @@ function resolveCacheSessionId(body, credentials) {
   });
 }
 
-function normalizeReasoningEffort(model, value) {
-  const supportedLevels = getThinkingLevels("codex", model);
-  if (supportedLevels?.includes(value)) return value;
-  if (value === "ultra" && supportedLevels?.includes("max")) return "max";
-  if (value === "max" || value === "ultra") return "xhigh";
-  return value;
+function normalizeReasoningEffort(value) {
+  return value === "max" ? "xhigh" : value;
 }
 
 function findNestedMessage(value, depth = 0) {
@@ -445,10 +440,10 @@ export class CodexExecutor extends BaseExecutor {
 
     // Priority: explicit reasoning.effort > reasoning_effort param > model suffix > default (medium)
     if (!body.reasoning) {
-      const effort = normalizeReasoningEffort(body.model, body.reasoning_effort || modelEffort || 'low');
+      const effort = normalizeReasoningEffort(body.reasoning_effort || modelEffort || 'low');
       body.reasoning = { effort, summary: "auto" };
     } else {
-      body.reasoning.effort = normalizeReasoningEffort(body.model, body.reasoning.effort);
+      body.reasoning.effort = normalizeReasoningEffort(body.reasoning.effort);
       if (!body.reasoning.summary) body.reasoning.summary = "auto";
     }
     delete body.reasoning_effort;

open-sse/executors/commandcode.js

@@ -1,6 +1,7 @@
 import { randomUUID } from "crypto";
 import { BaseExecutor } from "./base.js";
 import { PROVIDERS } from "../config/providers.js";
+import { HTTP_STATUS } from "../config/runtimeConfig.js";
 import { commandCodeToOpenAIResponse } from "../translator/response/commandcode-to-openai.js";
 import { SSE_DONE } from "../utils/sseConstants.js";
 
@@ -14,13 +15,19 @@ import { SSE_DONE } from "../utils/sseConstants.js";
  * We translate each event to an OpenAI chat.completion.chunk and emit it as SSE so
  * both the streaming and non-streaming (forced SSE → JSON) downstream handlers in
  * 9router can consume it without further format translation.
+ *
+ * Terminal upstream failures arrive as `{"type":"error"}` events inside the HTTP
+ * 200 stream, so a plain `response.ok` check cannot see them. We peek the first
+ * events before committing the response (see peekForUpstreamError) so a stream
+ * that starts with an error fails fast — the normal `!response.ok` path then
+ * triggers account/model fallback instead of streaming fake success content.
  */
 export class CommandCodeExecutor extends BaseExecutor {
 	constructor() {
 		super("commandcode", PROVIDERS.commandcode);
 	}
 
-  transformRequest(model, body, stream, credentials) {
+	transformRequest(_model, body, _stream, _credentials) {
 		body.stream = true;
 		return body;
 	}
@@ -42,11 +49,195 @@ export class CommandCodeExecutor extends BaseExecutor {
 	async execute(opts) {
 		const result = await super.execute(opts);
 		if (!result?.response?.ok || !result.response.body) return result;
-    result.response = wrapNdjsonAsOpenAISse(result.response, opts.model);
+		result.response = await peekForUpstreamError(result.response, opts.model, {
+			signal: opts.signal,
+		});
 		return result;
 	}
 }
 
+// How long to hold the response open while peeking the first upstream events.
+// An upstream error event ("Network connection lost") is emitted at stream
+// start, so the peek is fast; the bound just prevents a slow-started stream
+// from being held hostage. Env: COMMANDCODE_PEEK_TIMEOUT_MS.
+const PEEK_TIMEOUT_MS = (() => {
+	const raw = process.env.COMMANDCODE_PEEK_TIMEOUT_MS;
+	const n = raw ? parseInt(raw, 10) : NaN;
+	return Number.isFinite(n) && n > 0 ? n : 10 * 1000;
+})();
+
+// Event types that count as "the stream has started producing". Everything
+// else (start, start-step, reasoning-start, text-start, ...) is metadata and
+// does not end the peek.
+const MEANINGFUL_EVENT_TYPES = new Set([
+	"text-delta",
+	"reasoning-delta",
+	"tool-input-start",
+	"tool-input-delta",
+	"tool-input-end",
+	"tool-call",
+	"finish-step",
+	"finish",
+]);
+
+function makeAbortError(reason) {
+	const error = new Error(reason?.message || reason || "Request aborted");
+	error.name = "AbortError";
+	return error;
+}
+
+function tryParseEvent(line) {
+	const trimmed = line.trim();
+	if (!trimmed) return null;
+	const json = trimmed.startsWith("data:") ? trimmed.slice(5).trim() : trimmed;
+	if (!json || json === "[DONE]") return null;
+	try {
+		return JSON.parse(json);
+	} catch {
+		return null;
+	}
+}
+
+function formatErrorValue(errVal) {
+	const errStr =
+		typeof errVal === "string"
+			? errVal
+			: typeof errVal?.message === "string"
+				? errVal.message
+				: JSON.stringify(errVal);
+	const errType =
+		typeof errVal === "string"
+			? "upstream_error"
+			: errVal?.type || "upstream_error";
+	return { message: errStr, type: errType };
+}
+
+/**
+ * Read the first upstream events before committing the response.
+ *
+ * - `{"type":"error"}` as the first meaningful event → return a 502 Response so
+ *   chatCore's `!response.ok` path parses the error and triggers fallback.
+ * - Otherwise → re-emit the buffered bytes + the rest of the stream through the
+ *   normal NDJSON → OpenAI SSE wrapper and return it untouched in spirit.
+ *
+ * Bounded by `timeoutMs` (default PEEK_TIMEOUT_MS): if no meaningful event
+ * arrives in time, or the request signal aborts, we commit whatever we have and
+ * let the regular stream pipeline (stall detection, abort handling) take over.
+ */
+export async function peekForUpstreamError(
+	originalResponse,
+	model,
+	{ signal = null, timeoutMs = PEEK_TIMEOUT_MS } = {},
+) {
+	const reader = originalResponse.body.getReader();
+	const decoder = new TextDecoder();
+	const abortController = new AbortController();
+	const forwardAbort = () => abortController.abort(signal?.reason);
+	if (signal?.aborted) abortController.abort(signal?.reason);
+	else if (signal)
+		signal.addEventListener("abort", forwardAbort, { once: true });
+
+	// Raw bytes for lossless re-emission; decoded text is only used for line
+	// parsing / error detection. Never re-encode decoded text: TextDecoder
+	// holds a split multi-byte char internally and flush() would replace it
+	// with U+FFFD, corrupting the stream.
+	const rawChunks = [];
+	let peeked = "";
+	let errorEvent = null;
+	let committed = false;
+
+	const readWithTimeout = (ms) => {
+		if (abortController.signal.aborted) {
+			return Promise.reject(makeAbortError(abortController.signal.reason));
+		}
+		const timeoutPromise = new Promise((_, reject) => {
+			const t = setTimeout(() => reject(new Error("peek timeout")), ms);
+			t.unref?.();
+		});
+		const abortPromise = new Promise((_, reject) => {
+			abortController.signal.addEventListener(
+				"abort",
+				() => reject(makeAbortError(abortController.signal.reason)),
+				{ once: true },
+			);
+		});
+		return Promise.race([reader.read(), timeoutPromise, abortPromise]);
+	};
+
+	try {
+		const deadline = Date.now() + timeoutMs;
+		while (!errorEvent && !committed && Date.now() < deadline) {
+			const { done, value } = await readWithTimeout(
+				Math.max(deadline - Date.now(), 1),
+			);
+			if (done) break;
+			rawChunks.push(value);
+			peeked += decoder.decode(value, { stream: true });
+			const lines = peeked.split("\n");
+			// The last segment may be a partial line — only parse complete ones.
+			for (const line of lines.slice(0, -1)) {
+				const event = tryParseEvent(line);
+				if (!event?.type) continue;
+				if (event.type === "error") {
+					errorEvent = event;
+					break;
+				}
+				if (MEANINGFUL_EVENT_TYPES.has(event.type)) {
+					committed = true;
+					break;
+				}
+			}
+		}
+	} catch {
+		// timeout / abort / read failure during the peek → commit whatever we have;
+		// the downstream stream pipeline (stall detection, abort handling) takes over.
+	}
+
+	if (signal) signal.removeEventListener("abort", forwardAbort);
+
+	if (errorEvent) {
+		await reader.cancel("commandcode early error detected").catch(() => {});
+		const { message, type } = formatErrorValue(
+			errorEvent.error ?? errorEvent.message ?? "unknown",
+		);
+		return new Response(JSON.stringify({ error: { message, type } }), {
+			status: HTTP_STATUS.BAD_GATEWAY,
+			statusText: message.slice(0, 200),
+			headers: { "Content-Type": "application/json" },
+		});
+	}
+
+	const remaining = new ReadableStream({
+		start(controller) {
+			(async () => {
+				try {
+					// Re-emit RAW bytes (never re-encoded decoded text) so split
+					// multi-byte UTF-8 sequences survive the peek untouched.
+					for (const c of rawChunks) controller.enqueue(c);
+					while (true) {
+						const { done, value } = await reader.read();
+						if (done) break;
+						controller.enqueue(value);
+					}
+					controller.close();
+				} catch (err) {
+					controller.error(err);
+				}
+			})();
+		},
+		cancel() {
+			reader.cancel("commandcode stream cancelled").catch(() => {});
+		},
+	});
+
+	const combined = new Response(remaining, {
+		status: originalResponse.status,
+		statusText: originalResponse.statusText,
+		headers: originalResponse.headers,
+	});
+	return wrapNdjsonAsOpenAISse(combined, model);
+}
+
 function wrapNdjsonAsOpenAISse(originalResponse, model) {
 	const decoder = new TextDecoder();
 	const encoder = new TextEncoder();

open-sse/executors/default.js

@@ -1,9 +1,9 @@
 import { BaseExecutor } from "./base.js";
 import { PROVIDERS, PROVIDER_OAUTH } from "../config/providers.js";
-import { ANTHROPIC_API_VERSION, OPENAI_COMPAT_BASE, ANTHROPIC_COMPAT_BASE, selectAnthropicBeta } from "../providers/shared.js";
-import { resolveOpenAICompatibleApiType } from "../services/provider.js";
+import { ANTHROPIC_API_VERSION, OPENAI_COMPAT_BASE, ANTHROPIC_COMPAT_BASE } from "../providers/shared.js";
 import { OAUTH_ENDPOINTS, buildKimiHeaders } from "../config/appConstants.js";
 import { buildClineHeaders } from "../shared/clineAuth.js";
+import { getCachedClaudeHeaders } from "../utils/claudeHeaderCache.js";
 import { proxyAwareFetch } from "../utils/proxyFetch.js";
 import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
 import { stripUnsupportedParams } from "../translator/concerns/paramSupport.js";
@@ -42,6 +42,21 @@ const HEADER_HOOKS = {
   kimiHeaders: (h, c) => Object.assign(h, buildKimiHeaders(c?.providerSpecificData?.deviceId)),
   clineHeaders: (h, c) => Object.assign(h, buildClineHeaders(c.apiKey || c.accessToken)),
   kilocodeOrg: (h, c) => { if (c.providerSpecificData?.orgId) h["X-Kilocode-OrganizationID"] = c.providerSpecificData.orgId; },
+  claudeOverlay: (h) => {
+    const cached = getCachedClaudeHeaders();
+    if (!cached) return;
+    for (const lcKey of Object.keys(cached)) {
+      const titleKey = lcKey.replace(/(^|-)([a-z])/g, (_, sep, ch) => sep + ch.toUpperCase());
+      if (lcKey === "anthropic-beta") {
+        const staticBetaStr = h[titleKey] || h[lcKey] || "";
+        const flags = new Set(staticBetaStr.split(",").map(f => f.trim()).filter(Boolean));
+        for (const f of cached[lcKey].split(",").map(f => f.trim()).filter(Boolean)) flags.add(f);
+        cached[lcKey] = Array.from(flags).join(",");
+      }
+      if (titleKey !== lcKey && h[titleKey] !== undefined) delete h[titleKey];
+    }
+    Object.assign(h, cached);
+  },
 };
 
 // Config-driven OAuth refresh grants — derived from registry oauth.refresh.
@@ -110,7 +125,7 @@ export class DefaultExecutor extends BaseExecutor {
     if (this.provider?.startsWith?.("openai-compatible-")) {
       const baseUrl = credentials?.providerSpecificData?.baseUrl || OPENAI_COMPAT_BASE;
       const normalized = baseUrl.replace(/\/$/, "");
-      const path = resolveOpenAICompatibleApiType(this.provider, credentials) === "responses" ? "/responses" : "/chat/completions";
+      const path = this.provider.includes("responses") ? "/responses" : "/chat/completions";
       return `${normalized}${path}`;
     }
     if (this.provider?.startsWith?.("anthropic-compatible-")) {
@@ -146,18 +161,14 @@ export class DefaultExecutor extends BaseExecutor {
     return BEARER;
   }
 
-  buildHeaders(credentials, stream = true, url, model) {
+  buildHeaders(credentials, stream = true) {
     const rt = credentials?.runtimeTransport;
     const headers = { "Content-Type": "application/json", ...(rt ? rt.headers : this.config.headers) };
     const desc = rt?.auth || AUTH_DESCRIPTORS[this.provider] || this.resolveAuthDescriptor();
-    // Hooks run BEFORE auth so dynamic overlays can't clobber the token.
+    // Hooks run BEFORE auth so dynamic overlays (claude cached headers) can't clobber the token.
     for (const hook of desc.hooks || []) HEADER_HOOKS[hook]?.(headers, credentials);
     applyAuth(headers, desc, credentials);
 
-    if (this.provider === "claude" && model) {
-      headers["Anthropic-Beta"] = selectAnthropicBeta(model);
-    }
-
     // Strip first-party Claude Code identity headers for non-Anthropic anthropic-compatible upstreams
     if (this.provider?.startsWith?.("anthropic-compatible-")) {
       const baseUrl = credentials?.providerSpecificData?.baseUrl || "";
@@ -211,6 +222,7 @@ export class DefaultExecutor extends BaseExecutor {
     const refreshers = {
       claude: () => this.refreshFromGrant(credentials, proxyOptions),
       codex: () => this.refreshFromGrant(credentials, proxyOptions),
+      qwen: () => this.refreshWithForm(OAUTH_ENDPOINTS.qwen.token, { grant_type: "refresh_token", refresh_token: credentials.refreshToken, client_id: PROVIDERS.qwen.clientId }, proxyOptions),
       iflow: () => this.refreshIflow(credentials.refreshToken, proxyOptions),
       gemini: () => this.refreshFromGrant(credentials, proxyOptions),
       kiro: () => this.refreshKiro(credentials.refreshToken, proxyOptions),

open-sse/executors/index.js

@@ -9,7 +9,9 @@ import { KimchiExecutor } from "./kimchi.js";
 import { CodexExecutor } from "./codex.js";
 import { CursorExecutor } from "./cursor.js";
 import { VertexExecutor } from "./vertex.js";
+import { QwenExecutor } from "./qwen.js";
 import { OpenCodeExecutor } from "./opencode.js";
+import { OpenCodeGoExecutor } from "./opencode-go.js";
 import { GrokWebExecutor } from "./grok-web.js";
 import { GrokCliExecutor } from "./grok-cli.js";
 import { PerplexityWebExecutor } from "./perplexity-web.js";
@@ -39,7 +41,9 @@ const executors = {
   cu: new CursorExecutor(), // Alias for cursor
   vertex: new VertexExecutor("vertex"),
   "vertex-partner": new VertexExecutor("vertex-partner"),
+  qwen: new QwenExecutor(),
   opencode: new OpenCodeExecutor(),
+  "opencode-go": new OpenCodeGoExecutor(),
   "grok-web": new GrokWebExecutor(),
   "grok-cli": new GrokCliExecutor(),
   gcli: new GrokCliExecutor(), // Alias
@@ -83,7 +87,9 @@ export { CodexExecutor } from "./codex.js";
 export { CursorExecutor } from "./cursor.js";
 export { VertexExecutor } from "./vertex.js";
 export { DefaultExecutor } from "./default.js";
+export { QwenExecutor } from "./qwen.js";
 export { OpenCodeExecutor } from "./opencode.js";
+export { OpenCodeGoExecutor } from "./opencode-go.js";
 export { GrokWebExecutor } from "./grok-web.js";
 export { GrokCliExecutor } from "./grok-cli.js";
 export { PerplexityWebExecutor } from "./perplexity-web.js";

open-sse/executors/kiro.js

@@ -144,12 +144,6 @@ function normalizeStopReason(value) {
   return reason || null;
 }
 
-// Of the reasons stopDisposition() folds into "terminal_incomplete", only these
-// mean "usable as far as it got, then the budget ran out" -- the case
-// finish_reason "length" exists for. cancelled / pause_turn are abandoned turns
-// whose partial content must stay private, so they are deliberately absent.
-const KIRO_TRUNCATION_STOP_REASONS = new Set(["model_context_window_exceeded", "max_tokens"]);
-
 function stopDisposition(stopReason, hasToolCalls) {
   if (["malformed_model_output", "invalid_model_output"].includes(stopReason)) return "retryable_protocol_failure";
   if (["cancelled", "pause_turn", "model_context_window_exceeded"].includes(stopReason)) return "terminal_incomplete";
@@ -717,12 +711,7 @@ export class KiroExecutor extends BaseExecutor {
     };
     const emitTools = (controller) => {
       for (const tool of state.tools.values()) {
-        // Validate per tool, not per turn: one unusable fragment used to throw out
-        // of emitTools and take every other complete tool call in the same turn
-        // with it, which the client saw as a turn that answered nothing.
-        let input;
-        try {
-          input = parsedToolInput(tool);
+        const input = parsedToolInput(tool);
         if (tool.name === "tool_call") {
           if (typeof input.name !== "string" || !input.name.trim()) {
             throw new Error("Invalid Kiro tool_call payload: missing nested MCP tool name");
@@ -731,12 +720,6 @@ export class KiroExecutor extends BaseExecutor {
             throw new Error("Invalid Kiro tool_call payload: missing nested MCP tool arguments");
           }
         }
-        } catch (error) {
-          state.droppedTools = (state.droppedTools || 0) + 1;
-          state.toolValidationError ||= error.message;
-          console.error(`[Kiro] dropping unusable tool call ${tool.id} (${tool.name}): ${error.message}`);
-          continue;
-        }
         const index = state.toolCounter++;
         emitDelta(controller, {
           tool_calls: [{
@@ -746,26 +729,14 @@ export class KiroExecutor extends BaseExecutor {
             function: { name: tool.name, arguments: "" }
           }]
         });
-        const serializedInput = JSON.stringify(input);
         emitDelta(controller, {
-          tool_calls: [{ index, function: { arguments: serializedInput } }]
+          tool_calls: [{ index, function: { arguments: JSON.stringify(input) } }]
         });
-        // Tool arguments are billed output like any other completion bytes. They
-        // were never added to totalContentLength, so the /4 estimator in finish()
-        // reported OUT 0 -- or the Math.max floor of 1 -- for every turn whose
-        // entire answer was a tool call.
-        state.totalContentLength += tool.name.length + serializedInput.length;
         state.hasToolCalls = true;
       }
       state.tools.clear();
       state.bufferedToolBytes = 0;
-      // A declared tool turn that emitted no usable call is only fatal when the
-      // turn produced nothing else. Throwing unconditionally here escaped
-      // emitTools() with provenance "invalid_tool_call", which the integrity gate
-      // re-derived into a repair retry -- discarding text the client had already
-      // been promised.
-      if (state.stopReason === "tool_use" && !state.hasToolCalls &&
-          !state.hasText && !state.hasReasoning && !state.hasCode) {
+      if (state.stopReason === "tool_use" && !state.hasToolCalls) {
         throw new Error("Kiro tool_use stop reason did not include a complete tool call");
       }
     };
@@ -825,6 +796,7 @@ export class KiroExecutor extends BaseExecutor {
         emitDelta(controller, { content: event.payload.content });
       } else if (eventType === "toolUseEvent") {
         state.sawToolUse = true;
+        if (state.toolValidationError) return true;
         const values = Array.isArray(event.payload) ? event.payload : [event.payload];
         if (!values[0]) throw new Error("Kiro toolUseEvent is empty");
         for (const value of values) {
@@ -952,10 +924,9 @@ export class KiroExecutor extends BaseExecutor {
         } catch (error) {
           const bufferExceeded = error.code === "KIRO_BUFFER_EXCEEDED";
           if (!bufferExceeded) {
-            // Keep whatever is already buffered: the rejected fragment belongs to
-            // one tool, and clearing the map dropped the complete calls too.
             state.toolValidationError ||= error.message;
-            console.error(`[Kiro] tool fragment rejected, keeping ${state.tools.size} buffered tool(s): ${error.message}`);
+            state.tools.clear();
+            state.bufferedToolBytes = 0;
             continue;
           }
           fail(
@@ -987,16 +958,7 @@ export class KiroExecutor extends BaseExecutor {
       }
       state.transportState = "clean_eof";
       const declaredDisposition = stopDisposition(state.stopReason, state.sawToolUse);
-      // model_context_window_exceeded / max_tokens map to terminal_incomplete. When
-      // they arrive after the model already streamed content, fail() threw away a
-      // complete-enough answer; a truncated turn is what finish_reason "length" is
-      // for. chunkIndex > 0 means at least one delta already reached the client.
-      const declaredTruncatedAfterOutput = declaredDisposition === "terminal_incomplete" &&
-        KIRO_TRUNCATION_STOP_REASONS.has(state.stopReason) && state.chunkIndex > 0;
-      if (declaredTruncatedAfterOutput) {
-        console.error(`[Kiro] truncated after ${state.chunkIndex} chunk(s) (stop_reason=${state.stopReason}); keeping output`);
-      }
-      if (!declaredTruncatedAfterOutput && ["retryable_protocol_failure", "terminal_incomplete", "terminal_refusal", "unknown_failure"].includes(declaredDisposition)) {
+      if (["retryable_protocol_failure", "terminal_incomplete", "terminal_refusal", "unknown_failure"].includes(declaredDisposition)) {
         const code = declaredDisposition === "retryable_protocol_failure"
           ? "kiro_retryable_protocol_failure"
           : declaredDisposition === "terminal_refusal"
@@ -1013,6 +975,16 @@ export class KiroExecutor extends BaseExecutor {
         );
         return;
       }
+      if (state.toolValidationError) {
+        fail(
+          controller,
+          "invalid_tool_call",
+          "invalid_kiro_tool_call",
+          state.toolValidationError,
+          { transport_state: state.transportState, stop_disposition: "retryable_protocol_failure" }
+        );
+        return;
+      }
       try {
         emitTools(controller);
       } catch (error) {
@@ -1025,22 +997,6 @@ export class KiroExecutor extends BaseExecutor {
         );
         return;
       }
-      // Fail only when the turn has nothing usable left. emitTools() validates
-      // per tool and drops just the unusable ones, so this has to run AFTER it:
-      // before, the rejected tool was still buffered and tools.size was never 0.
-      // A turn that also produced text keeps that text -- the dropped call is
-      // logged, not fatal.
-      if (state.toolValidationError && !state.hasToolCalls &&
-          !state.hasText && !state.hasReasoning && !state.hasCode) {
-        fail(
-          controller,
-          "invalid_tool_call",
-          "invalid_kiro_tool_call",
-          state.toolValidationError,
-          { transport_state: state.transportState, stop_disposition: "retryable_protocol_failure" }
-        );
-        return;
-      }
 
       const hasOutput = state.hasText || state.hasReasoning || state.hasCode || state.hasToolCalls;
       if (!hasOutput && !state.explicitStop) {
@@ -1055,13 +1011,7 @@ export class KiroExecutor extends BaseExecutor {
       }
 
       const disposition = stopDisposition(state.stopReason, state.hasToolCalls);
-      // Same reasoning as declaredTruncatedAfterOutput above.
-      const truncatedAfterOutput = disposition === "terminal_incomplete" &&
-        KIRO_TRUNCATION_STOP_REASONS.has(state.stopReason) && state.chunkIndex > 0;
-      if (truncatedAfterOutput) {
-        console.error(`[Kiro] truncated after ${state.chunkIndex} chunk(s) (stop_reason=${state.stopReason}); closing as length`);
-      }
-      if (!truncatedAfterOutput && ["retryable_protocol_failure", "terminal_incomplete", "terminal_refusal", "unknown_failure"].includes(disposition)) {
+      if (["retryable_protocol_failure", "terminal_incomplete", "terminal_refusal", "unknown_failure"].includes(disposition)) {
         const code = disposition === "retryable_protocol_failure"
           ? "kiro_retryable_protocol_failure"
           : disposition === "terminal_refusal"
@@ -1091,9 +1041,7 @@ export class KiroExecutor extends BaseExecutor {
           total_tokens: prompt + completion
         };
       }
-      const finishReason = truncatedAfterOutput
-        ? "length"
-        : state.hasToolCalls
+      const finishReason = state.hasToolCalls
         ? "tool_calls"
         : disposition === "length"
           ? "length"
@@ -1104,11 +1052,7 @@ export class KiroExecutor extends BaseExecutor {
       options.onTerminalState?.(diagnostics({
         terminal_provenance: state.terminalProvenance || "clean_eventstream_eof",
         transport_state: state.transportState,
-        // Report what this exit actually did, not the raw disposition. The
-        // integrity gate re-derives its verdict from stop_disposition, so
-        // reporting "terminal_incomplete" for a turn we deliberately kept made
-        // it discard the very bytes we just released to the client.
-        stop_disposition: truncatedAfterOutput ? "length" : disposition
+        stop_disposition: disposition
       }));
     };
 

open-sse/executors/opencode-go.js

@@ -0,0 +1,49 @@
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS } from "../config/providers.js";
+import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
+import { ANTHROPIC_API_VERSION } from "../providers/shared.js";
+
+// Models that use /zen/go/v1/messages (Anthropic/Claude format + x-api-key auth)
+const MESSAGES_FORMAT_MODELS = new Set([
+  "minimax-m3",
+  "minimax-m2.7",
+  "minimax-m2.5",
+  "qwen3.7-max",
+  "qwen3.7-plus",
+  "qwen3.6-plus",
+]);
+
+const BASE = "https://opencode.ai/zen/go/v1";
+
+export class OpenCodeGoExecutor extends BaseExecutor {
+  constructor() {
+    super("opencode-go", PROVIDERS["opencode-go"]);
+  }
+
+  // buildUrl runs before buildHeaders in BaseExecutor.execute, cache model here
+  buildUrl(model) {
+    this._lastModel = model;
+    return MESSAGES_FORMAT_MODELS.has(model)
+      ? `${BASE}/messages`
+      : `${BASE}/chat/completions`;
+  }
+
+  buildHeaders(credentials, stream = true) {
+    const key = credentials?.apiKey || credentials?.accessToken;
+    const headers = { "Content-Type": "application/json" };
+
+    if (MESSAGES_FORMAT_MODELS.has(this._lastModel)) {
+      headers["x-api-key"] = key;
+      headers["anthropic-version"] = ANTHROPIC_API_VERSION;
+    } else {
+      headers["Authorization"] = `Bearer ${key}`;
+    }
+
+    if (stream) headers["Accept"] = "text/event-stream";
+    return headers;
+  }
+
+  transformRequest(model, body) {
+    return injectReasoningContent({ provider: this.provider, model, body });
+  }
+}

open-sse/executors/opencode.js

@@ -1,43 +1,16 @@
-import crypto from "crypto";
 import { BaseExecutor } from "./base.js";
 import { PROVIDERS } from "../config/providers.js";
 import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
-import { resolveSessionId } from "../utils/sessionManager.js";
 
-const OPENCODE_UA = "opencode";
+// Models that use /zen/v1/messages (claude format)
 const MESSAGES_MODELS = new Set();
 
-function generateRequestId() {
-  return `msg_${crypto.randomUUID().replace(/-/g, "")}`;
-}
-
-function generateSessionId() {
-  return `ses_${crypto.randomUUID().replace(/-/g, "")}`;
-}
-
-// Normalize any resolved id into opencode's ses_ format (stable per-conversation)
-function toOpencodeSession(id) {
-  const stripped = String(id || "").replace(/^ses_/, "").replace(/-/g, "");
-  return stripped ? `ses_${stripped}` : null;
-}
-
-function resolveOpencodeSession(body, credentials) {
-  return toOpencodeSession(resolveSessionId({
-    headers: credentials?.rawHeaders,
-    body,
-    connectionId: credentials?.connectionId,
-    scope: "opencode",
-  }));
-}
-
 export class OpenCodeExecutor extends BaseExecutor {
   constructor() {
     super("opencode", PROVIDERS.opencode);
-    this._currentSessionId = null;
   }
 
-  transformRequest(model, body, stream, credentials) {
-    this._currentSessionId = resolveOpencodeSession(body, credentials);
+  transformRequest(model, body) {
     return injectReasoningContent({ provider: this.provider, model, body });
   }
 
@@ -48,23 +21,12 @@ export class OpenCodeExecutor extends BaseExecutor {
       : `${base}/zen/v1/chat/completions`;
   }
 
-  buildHeaders(credentials, stream = true) {
-    const raw = credentials?.rawHeaders || {};
-    const lower = {};
-    for (const [k, v] of Object.entries(raw)) lower[k.toLowerCase()] = v;
-
-    const downstreamUa = lower["user-agent"] || "";
-    const isOpencodeDownstream = downstreamUa.toLowerCase().includes("opencode");
-
+  buildHeaders() {
     return {
       "Content-Type": "application/json",
       "Authorization": "Bearer public",
-      "User-Agent": isOpencodeDownstream ? downstreamUa : OPENCODE_UA,
-      "x-opencode-client": lower["x-opencode-client"] || "desktop",
-      "x-opencode-session": lower["x-opencode-session"] || this._currentSessionId || generateSessionId(),
-      "x-opencode-request": lower["x-opencode-request"] || generateRequestId(),
-      "x-opencode-project": lower["x-opencode-project"] || "global",
-      "Accept": stream ? "text/event-stream" : "*/*",
+      "x-opencode-client": "desktop",
+      "Accept": "text/event-stream"
     };
   }
 }

open-sse/executors/qoder.js

@@ -30,13 +30,16 @@ import { PROVIDERS } from "../config/providers.js";
 import { proxyAwareFetch } from "../utils/proxyFetch.js";
 import { SSE_DONE } from "../utils/sseConstants.js";
 import { FETCH_CONNECT_TIMEOUT_MS } from "../config/runtimeConfig.js";
+import { resolveProviderTimeoutMs } from "../services/providerTimeout.js";
 import {
   QODER_CHAT_URL_ENCODED,
-  QODER_CHAT_BASE_ALT,
-  QODER_CHAT_SIG_PATH,
+  QODER_JOB_TOKEN_EXCHANGE_URL,
+  QODER_USERINFO_URL,
   QODER_MODEL_MAP,
+  QODER_IDE_VERSION,
+  QODER_CLIENT_TYPE,
 } from "../shared/qoder/constants.js";
-import { getQoderModelConfig, resolveQoderModels, isQoderPat, resolveQoderCredentials } from "../services/qoderModels.js";
+import { getQoderModelConfig, resolveQoderModels } from "../services/qoderModels.js";
 
 /**
  * Hoist role:"system" messages out of the messages array (Qoder rejects
@@ -215,52 +218,6 @@ async function buildQoderRequestBody({ model, body, credentials, log, proxyOptio
   };
 }
 
-/**
- * Check if a qoder error message indicates a billing/quota block.
- * Signatures: code 112 (quota exhausted), code 10605 (queue throttle), pricingUrl field.
- */
-function isBillingBlock(inner) {
-  if (!inner || typeof inner !== "string") return false;
-  const lowerMsg = inner.toLowerCase();
-  // Match: {"code":"112",...}, {"code":"10605",...}, or pricingUrl field
-  return /\"code\"\s*:\s*\"(112|10605)\"/.test(inner) || lowerMsg.includes("pricingurl");
-}
-
-/**
- * Peek the first SSE frame to detect billing errors before piping.
- * Returns { isBilling, statusVal, message, consumed } — `consumed` is every
- * byte read so far (including the peeked line) so the caller can re-process
- * it and nothing is dropped from the stream.
- */
-async function peekFirstQoderFrame(reader, decoder) {
-  let consumed = "";
-  while (true) {
-    const { done, value } = await reader.read();
-    if (done) return { isBilling: false, consumed, upstreamDone: true };
-
-    consumed += decoder.decode(value, { stream: true });
-    const nl = consumed.indexOf("\n");
-    if (nl === -1) continue; // need a full line first
-
-    const line = consumed.slice(0, nl).replace(/\r$/, "").trim();
-    if (!line.startsWith("data:")) continue;
-
-    const data = line.slice(5).trimStart();
-    if (data === "[DONE]") return { isBilling: false, consumed };
-
-    let envelope;
-    try { envelope = JSON.parse(data); } catch { return { isBilling: false, consumed }; }
-
-    const statusVal = typeof envelope.statusCodeValue === "number" ? envelope.statusCodeValue : 200;
-    const inner = typeof envelope.body === "string" ? envelope.body : "";
-
-    if (statusVal !== 200 && isBillingBlock(inner)) {
-      return { isBilling: true, statusVal, message: inner || `qoder billing block (${statusVal})` };
-    }
-    return { isBilling: false, consumed };
-  }
-}
-
 /**
  * Wrap the upstream's `{statusCodeValue, body}` SSE envelope into plain
  * OpenAI SSE chunks the rest of the chatCore pipeline understands.
@@ -275,33 +232,15 @@ async function peekFirstQoderFrame(reader, decoder) {
  * [DONE]/error frame (agent keepalive). Non-streaming clients drain via
  * response.text() which hangs until the socket closes — so on terminal
  * events we cancel the upstream reader and close our stream immediately.
- *
- * NEW: Peek first frame to detect billing blocks (code 112/10605/pricingUrl).
- * If detected, return 403 response so chatCore marks connection unavailable
- * and triggers combo fallback instead of leaking error text into chat.
  */
-async function wrapQoderSSE(response, model) {
+function wrapQoderSSE(response, model) {
   if (!response.ok || !response.body) return response;
 
   const decoder = new TextDecoder();
-  const reader = response.body.getReader();
-
-  // Peek first frame to detect billing block
-  const peek = await peekFirstQoderFrame(reader, decoder);
-  if (peek?.isBilling) {
-    // Billing block detected — return 403 so chatCore fails this connection
-    await reader.cancel().catch(() => {});
-    return new Response(
-      JSON.stringify({ error: { message: peek.message, code: peek.statusVal } }),
-      { status: 403, headers: { "Content-Type": "application/json" } }
-    );
-  }
-
-  // Normal flow: re-process every byte the peek consumed, then continue.
-  let buffer = peek.consumed || "";
-  const upstreamDrained = peek.upstreamDone === true;
   const encoder = new TextEncoder();
+  let buffer = "";
   let doneEmitted = false;
+  const reader = response.body.getReader();
 
   // Process one already-extracted SSE line (no trailing newline).
   const processLine = (line, controller) => {
@@ -351,28 +290,7 @@ async function wrapQoderSSE(response, model) {
     // enqueueing would never be re-invoked, hanging consumers like .text().
     async start(controller) {
       try {
-        // Drain whatever the peek already pulled off the socket first.
-        let nlSeed;
-        while ((nlSeed = buffer.indexOf("\n")) !== -1) {
-          const line = buffer.slice(0, nlSeed);
-          buffer = buffer.slice(nlSeed + 1);
-          processLine(line, controller);
-          if (doneEmitted) {
-            await reader.cancel().catch(() => {});
-            controller.close();
-            return;
-          }
-        }
-        if (upstreamDrained) {
-          // Peek hit end-of-stream: flush any trailing partial line.
-          buffer += decoder.decode();
-          if (buffer.length > 0) {
-            processLine(buffer, controller);
-            buffer = "";
-          }
-        }
-
-        while (!doneEmitted && !upstreamDrained) {
+        while (!doneEmitted) {
           const { done, value } = await reader.read();
           if (done) {
             buffer += decoder.decode();
@@ -425,18 +343,98 @@ async function wrapQoderSSE(response, model) {
   });
 }
 
+// ── PAT (Personal Access Token) → job-token exchange ───────────────────────
+// PATs (pt-...) cannot sign COSY requests directly. Exchange them for a
+// short-lived job token (jt-...) via /api/v1/jobToken/exchange (plain JSON,
+// not COSY-signed), then resolve the userId from userinfo. Mirrors the
+// official qodercli flow. Cached per-PAT until near-expiry.
+const PAT_PREFIX = "pt-";
+const PAT_REFRESH_BUFFER_MS = 5 * 60 * 1000;
+const patJobCache = new Map();
+
+export function isQoderPat(token) {
+  return typeof token === "string" && token.startsWith(PAT_PREFIX);
+}
+
+async function exchangeJobToken(pat, proxyOptions = null, signal = null) {
+  const res = await proxyAwareFetch(
+    QODER_JOB_TOKEN_EXCHANGE_URL,
+    {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+        Accept: "application/json",
+        "User-Agent": "qodercli/1.0.0",
+        "Cosy-Version": QODER_IDE_VERSION,
+        "Cosy-ClientType": QODER_CLIENT_TYPE,
+      },
+      body: JSON.stringify({ personal_token: pat }),
+      signal,
+    },
+    proxyOptions,
+  );
+  if (!res.ok) {
+    const text = await res.text().catch(() => "");
+    throw new Error(`qoder PAT exchange failed: ${res.status} ${text.slice(0, 200)}`);
+  }
+  const data = await res.json();
+  if (!data.token) throw new Error("qoder PAT exchange returned no job token");
+
+  let expiresAt = Date.now() + 24 * 60 * 60 * 1000;
+  if (data.expires_at) {
+    const parsed = Date.parse(data.expires_at);
+    if (!Number.isNaN(parsed)) expiresAt = parsed;
+  } else if (typeof data.expires_in === "number" && data.expires_in > 0) {
+    expiresAt = Date.now() + data.expires_in;
+  }
+  return { jobToken: data.token, jobRefreshToken: data.refresh_token || "", expiresAt };
+}
+
+async function fetchUserIdForJobToken(jobToken, proxyOptions = null, signal = null) {
+  try {
+    const res = await proxyAwareFetch(
+      QODER_USERINFO_URL,
+      {
+        method: "GET",
+        headers: {
+          Authorization: `Bearer ${jobToken}`,
+          Accept: "application/json",
+          "User-Agent": "qodercli/1.0.0",
+        },
+        signal,
+      },
+      proxyOptions,
+    );
+    if (!res.ok) return "";
+    const info = await res.json().catch(() => ({}));
+    return info.id || info.userId || info.user_id || "";
+  } catch {
+    return "";
+  }
+}
+
+/**
+ * Exchange a PAT for a job token + userId, caching until near-expiry so repeat
+ * chat requests don't re-exchange. Returns { accessToken, userId }.
+ */
+async function resolvePatCredential(pat, proxyOptions = null, signal = null) {
+  const cached = patJobCache.get(pat);
+  if (cached && cached.expiresAt - Date.now() > PAT_REFRESH_BUFFER_MS) {
+    return cached;
+  }
+  const { jobToken, expiresAt } = await exchangeJobToken(pat, proxyOptions, signal);
+  const userId = await fetchUserIdForJobToken(jobToken, proxyOptions, signal);
+  const entry = { accessToken: jobToken, userId, expiresAt };
+  patJobCache.set(pat, entry);
+  return entry;
+}
+
 export class QoderExecutor extends BaseExecutor {
   constructor() {
     super("qoder", PROVIDERS.qoder);
   }
 
-  buildUrl(credentials) {
-    // Job-token (jt-...) traffic must hit api2.qoder.sh — api3 rejects jt-
-    // with "Login expired" (403). Device tokens (dt-...) stay on api3.
-    const raw = credentials?.apiKey || credentials?.accessToken;
-    if (typeof raw === "string" && !raw.startsWith("pt-") && (raw.startsWith("jt-") || (credentials?.accessToken || "").startsWith("jt-"))) {
-      return `${QODER_CHAT_BASE_ALT}/algo${QODER_CHAT_SIG_PATH}?FetchKeys=llm_model_result&AgentId=agent_common&Encode=1`;
-    }
+  buildUrl() {
     return QODER_CHAT_URL_ENCODED;
   }
 
@@ -446,24 +444,36 @@ export class QoderExecutor extends BaseExecutor {
   //   - COSY headers built from the *encoded* body bytes
   //   - response stream re-wrapped from {statusCodeValue, body} to OpenAI SSE
   async execute({ model, body, stream, credentials, signal, log, proxyOptions = null }) {
+    const url = this.buildUrl();
+
     // PAT (pt-...) → exchange for short-lived job token + resolve userId so
     // downstream COSY signing + catalog fetch work. Device tokens (dt-...) and
     // job tokens (jt-...) skip this and are used directly.
     const rawToken = credentials?.apiKey || credentials?.accessToken;
     if (isQoderPat(rawToken)) {
       try {
-        credentials = await resolveQoderCredentials(credentials, proxyOptions, signal);
+        const resolved = await resolvePatCredential(rawToken, proxyOptions, signal);
+        credentials = {
+          ...credentials,
+          accessToken: resolved.accessToken,
+          apiKey: undefined,
+          providerSpecificData: {
+            authMethod: "pat",
+            ...(credentials?.providerSpecificData || {}),
+            userId: resolved.userId || credentials?.providerSpecificData?.userId || "",
+            machineId: credentials?.providerSpecificData?.machineId || "",
+          },
+        };
       } catch (err) {
         log?.error?.("QODER", `PAT exchange failed: ${err.message}`);
         const fakeResp = new Response(
           JSON.stringify({ error: { message: `qoder PAT exchange failed: ${err.message}` } }),
           { status: 401, headers: { "Content-Type": "application/json" } },
         );
-        return { response: fakeResp, url: this.buildUrl(credentials), headers: {}, transformedBody: body };
+        return { response: fakeResp, url, headers: {}, transformedBody: body };
       }
     }
 
-    const url = this.buildUrl(credentials);
     const psd = credentials?.providerSpecificData || {};
     if (!psd.userId) {
       // No user id → no way to sign. Surface a 401 so the dashboard nudges
@@ -536,7 +546,7 @@ export class QoderExecutor extends BaseExecutor {
     };
 
     // Abort if upstream doesn't return response headers within connect timeout.
-    const timeoutMs = this.config?.timeoutMs || FETCH_CONNECT_TIMEOUT_MS;
+    const timeoutMs = await resolveProviderTimeoutMs(this.provider, this.config?.timeoutMs, FETCH_CONNECT_TIMEOUT_MS);
     const connectCtrl = new AbortController();
     const connectTimer = setTimeout(() => connectCtrl.abort(new Error("fetch connect timeout")), timeoutMs);
     const mergedSignal = signal ? AbortSignal.any([signal, connectCtrl.signal]) : connectCtrl.signal;
@@ -557,7 +567,7 @@ export class QoderExecutor extends BaseExecutor {
       return { response, url, headers, transformedBody: payload };
     }
 
-    const wrapped = await wrapQoderSSE(response, `qoder/${qoderKey}`);
+    const wrapped = wrapQoderSSE(response, `qoder/${qoderKey}`);
     return { response: wrapped, url, headers, transformedBody: payload };
   }
 
@@ -581,5 +591,6 @@ export const __test__ = {
   normalizeMessages,
   wrapQoderSSE,
   buildQoderRequestBody,
-  isBillingBlock,
+  isQoderPat,
+  resolvePatCredential,
 };

open-sse/executors/qwen.js

@@ -0,0 +1,129 @@
+import { DefaultExecutor } from "./default.js";
+import { PROVIDERS } from "../config/providers.js";
+import { OAUTH_ENDPOINTS } from "../config/appConstants.js";
+
+/** portal.qwen.ai — static fingerprint matching stable Qwen Code release */
+const QWEN_USER_AGENT = "QwenCode/0.12.3 (linux; x64)";
+const QWEN_STAINLESS = {
+  os: "Linux",
+  arch: "x64",
+  lang: "js",
+  runtime: "node",
+  runtimeVersion: "v18.19.1",
+  packageVersion: "5.11.0",
+  retryCount: "1"
+};
+const QWEN_DEFAULT_SYSTEM_MESSAGE = {
+  role: "system",
+  content: [{ type: "text", text: "", cache_control: { type: "ephemeral" } }]
+};
+
+function ensureQwenSystemMessage(body) {
+  if (!body || typeof body !== "object") return body;
+  const next = { ...body };
+  if (Array.isArray(next.messages)) {
+    next.messages = [QWEN_DEFAULT_SYSTEM_MESSAGE, ...next.messages];
+  } else {
+    next.messages = [QWEN_DEFAULT_SYSTEM_MESSAGE];
+  }
+  return next;
+}
+
+function isQwenThinkingActive(body) {
+  const thinking = body?.thinking;
+  if (thinking === true || body?.enable_thinking === true) return true;
+  return typeof thinking === "object" && thinking !== null && !Array.isArray(thinking) && thinking.type === "enabled";
+}
+
+// Qwen rejects tool_choice="required" or object forms when thinking is active; neutralize to "auto".
+function sanitizeQwenThinkingToolChoice(body) {
+  if (!isQwenThinkingActive(body)) return body;
+  const tc = body.tool_choice;
+  const incompatible = tc === "required" || (typeof tc === "object" && tc !== null);
+  if (!incompatible) return body;
+  return { ...body, tool_choice: "auto" };
+}
+
+function buildQwenUpstreamHeaders(credentials, stream = true) {
+  const token = credentials?.apiKey || credentials?.accessToken || "";
+  const headers = {
+    "Content-Type": "application/json",
+    Authorization: `Bearer ${token}`,
+    "User-Agent": QWEN_USER_AGENT,
+    "X-DashScope-AuthType": "qwen-oauth",
+    "X-DashScope-CacheControl": "enable",
+    "X-DashScope-UserAgent": QWEN_USER_AGENT,
+    "X-Stainless-Arch": QWEN_STAINLESS.arch,
+    "X-Stainless-Lang": QWEN_STAINLESS.lang,
+    "X-Stainless-Os": QWEN_STAINLESS.os,
+    "X-Stainless-Package-Version": QWEN_STAINLESS.packageVersion,
+    "X-Stainless-Retry-Count": QWEN_STAINLESS.retryCount,
+    "X-Stainless-Runtime": QWEN_STAINLESS.runtime,
+    "X-Stainless-Runtime-Version": QWEN_STAINLESS.runtimeVersion,
+    Connection: "keep-alive",
+    "Accept-Language": "*",
+    "Sec-Fetch-Mode": "cors"
+  };
+  headers.Accept = stream ? "text/event-stream" : "application/json";
+  return headers;
+}
+
+export class QwenExecutor extends DefaultExecutor {
+  constructor() {
+    super("qwen");
+  }
+
+  // Qwen tokens are bound to a resource_url returned at OAuth time.
+  // Using portal.qwen.ai when the token is issued for another shard returns 401/403.
+  buildUrl(model, stream, urlIndex = 0, credentials = null) {
+    const resourceUrl = credentials?.providerSpecificData?.resourceUrl;
+    const host = resourceUrl ? resourceUrl.replace(/^https?:\/\//, "").replace(/\/$/, "") : "portal.qwen.ai";
+    return `https://${host}/v1/chat/completions`;
+  }
+
+  buildHeaders(credentials, stream = true) {
+    return buildQwenUpstreamHeaders(credentials, stream);
+  }
+
+  transformRequest(model, body, stream, credentials) {
+    let next = body && typeof body === "object" ? { ...body } : body;
+    if (stream && next?.messages && !next.stream_options && !next.thinking && !next.enable_thinking && next.stream !== false) {
+      next.stream_options = { include_usage: true };
+    }
+    next = sanitizeQwenThinkingToolChoice(next);
+    return ensureQwenSystemMessage(next);
+  }
+
+  // Override to capture resource_url from refresh response (required for buildUrl).
+  async refreshCredentials(credentials, log) {
+    if (!credentials?.refreshToken) return null;
+    try {
+      const response = await fetch(OAUTH_ENDPOINTS.qwen.token, {
+        method: "POST",
+        headers: { "Content-Type": "application/x-www-form-urlencoded", Accept: "application/json" },
+        body: new URLSearchParams({
+          grant_type: "refresh_token",
+          refresh_token: credentials.refreshToken,
+          client_id: PROVIDERS.qwen.clientId
+        })
+      });
+      if (!response.ok) return null;
+      const tokens = await response.json();
+      log?.info?.("TOKEN", "qwen refreshed");
+      return {
+        accessToken: tokens.access_token,
+        refreshToken: tokens.refresh_token || credentials.refreshToken,
+        expiresIn: tokens.expires_in,
+        providerSpecificData: {
+          ...(credentials.providerSpecificData || {}),
+          ...(tokens.resource_url ? { resourceUrl: tokens.resource_url } : {})
+        }
+      };
+    } catch (error) {
+      log?.error?.("TOKEN", `qwen refresh error: ${error.message}`);
+      return null;
+    }
+  }
+}
+
+export default QwenExecutor;

open-sse/handlers/chatCore.js

@@ -1,33 +1,67 @@
-import { detectFormat, getTargetFormat, resolveTransport } from "../services/provider.js";
+import {
+	detectFormat,
+	getTargetFormat,
+	resolveTransport,
+} from "../services/provider.js";
 import { translateRequest } from "../translator/index.js";
-import { applyThinking, extractThinking, stripThinkingSuffix } from "../translator/concerns/thinkingUnified.js";
+import { stripThinkingSuffix } from "../translator/concerns/thinkingUnified.js";
 import { FORMATS } from "../translator/formats.js";
-import { normalizeClaudePassthrough, anchorClaudeCache } from "../translator/formats/claude.js";
+import { normalizeClaudePassthrough } from "../translator/formats/claude.js";
 import { createStreamController } from "../utils/streamHandler.js";
 import { refreshWithRetry } from "../services/tokenRefresh.js";
 import { createRequestLogger } from "../utils/requestLogger.js";
-import { getModelTargetFormat, getModelSupportedFormats, getModelStrip, getModelUpstreamId, getModelType, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
+import {
+	getModelTargetFormat,
+	getModelStrip,
+	getModelUpstreamId,
+	getModelType,
+	PROVIDER_ID_TO_ALIAS,
+} from "../config/providerModels.js";
 import { PROVIDERS } from "../config/providers.js";
-import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
+import {
+	createErrorResult,
+	parseUpstreamError,
+	formatProviderError,
+} from "../utils/error.js";
 import { HTTP_STATUS, TOKEN_SAVER_HEADER } from "../config/runtimeConfig.js";
 import { handleBypassRequest } from "../utils/bypassHandler.js";
-import { trackPendingRequest, appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
+import {
+	trackPendingRequest,
+	appendRequestLog,
+	saveRequestDetail,
+} from "@/lib/usageDb.js";
 import { getExecutor } from "../executors/index.js";
 import { supportsGrokCliReasoningEffort } from "../config/grokCli.js";
-import { buildRequestDetail, extractRequestConfig } from "./chatCore/requestDetail.js";
+import {
+	buildRequestDetail,
+	extractRequestConfig,
+} from "./chatCore/requestDetail.js";
 import { handleForcedSSEToJson } from "./chatCore/sseToJsonHandler.js";
 import { handleNonStreamingResponse } from "./chatCore/nonStreamingHandler.js";
-import { handleStreamingResponse, buildOnStreamComplete } from "./chatCore/streamingHandler.js";
-import { detectClientTool, isNativePassthrough } from "../utils/clientDetector.js";
+import {
+	handleStreamingResponse,
+	buildOnStreamComplete,
+} from "./chatCore/streamingHandler.js";
+import { maybeRejectEarlyStreamError } from "../utils/streamErrorPeek.js";
+import {
+	detectClientTool,
+	isNativePassthrough,
+} from "../utils/clientDetector.js";
 import { dedupeTools } from "../utils/toolDeduper.js";
 import { injectCaveman } from "../rtk/caveman.js";
 import { injectPonytail } from "../rtk/ponytail.js";
 import { compressMessages, formatRtkLog } from "../rtk/index.js";
-import { compressWithHeadroom, formatHeadroomLog, formatHeadroomSizeLog, isHeadroomPhantomSavings } from "../rtk/headroom.js";
+import {
+	compressWithHeadroom,
+	formatHeadroomLog,
+	formatHeadroomSizeLog,
+	isHeadroomPhantomSavings,
+} from "../rtk/headroom.js";
 import { compressWithPxpipe } from "../rtk/pxpipe.js";
 import { getCapabilitiesForModel } from "../providers/capabilities.js";
 import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
 import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
+import { extractThinking } from "../translator/concerns/thinkingUnified.js";
 import { resolveSessionId } from "../utils/sessionManager.js";
 
 /**
@@ -37,61 +71,76 @@ import { resolveSessionId } from "../utils/sessionManager.js";
  * @param {object} options.credentials - Provider credentials
  * @param {string} options.sourceFormatOverride - Override detected source format (e.g. "openai-responses")
  */
-/**
- * Remove translator-internal continuity fields from the outbound upstream
- * body. The Responses→Chat request translator stashes reasoning
- * `encrypted_content` on assistant messages so a later openai→responses
- * round-trip can restore the store=false continuity blob; that stash must
- * never reach an upstream provider. Chat-native proxies reject the unknown
- * assistant-message field and answer every turn with a literal "400" body
- * (observed with multi-turn Codex sessions via OpenAI-compatible nodes).
- */
-export function stripContinuityFields(body) {
-  if (!body || !Array.isArray(body.messages)) return body;
-  for (const msg of body.messages) {
-    if (msg && typeof msg === "object") {
-      delete msg.encrypted_content;
-      delete msg.reasoning_encrypted_content;
-    }
-  }
-  return body;
-}
-
-export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, pxpipeEnabled, pxpipeMinChars, pxpipeTimeoutMs, pxpipeTransform, onPxpipeEvent, sourceFormatOverride, providerThinking }) {
+export async function handleChatCore({
+	body,
+	modelInfo,
+	credentials,
+	log,
+	onCredentialsRefreshed,
+	onRequestSuccess,
+	onDisconnect,
+	clientRawRequest,
+	connectionId,
+	userAgent,
+	apiKey,
+	ccFilterNaming,
+	rtkEnabled,
+	headroomEnabled,
+	headroomUrl,
+	headroomCompressUserMessages,
+	cavemanEnabled,
+	cavemanLevel,
+	ponytailEnabled,
+	ponytailLevel,
+	pxpipeEnabled,
+	pxpipeMinChars,
+	pxpipeTimeoutMs,
+	pxpipeTransform,
+	onPxpipeEvent,
+	sourceFormatOverride,
+	providerThinking,
+	streamErrorPatterns,
+}) {
 	const { provider, model } = modelInfo;
 	const requestStartTime = Date.now();
 	// Stable per-session color so all lines of one CLI conversation share a tag
 	const sessionSeed = (() => {
 		try {
-      return resolveSessionId({ headers: clientRawRequest?.headers, body, connectionId, scope: provider });
+			return resolveSessionId({
+				headers: clientRawRequest?.headers,
+				body,
+				connectionId,
+				scope: provider,
+			});
 		} catch {
 			return connectionId || "";
 		}
 	})();
-  const reqTag = log?.tagForSession ? log.tagForSession(sessionSeed) : (log?.nextTag ? log.nextTag() : "");
+	const reqTag = log?.tagForSession
+		? log.tagForSession(sessionSeed)
+		: log?.nextTag
+			? log.nextTag()
+			: "";
 
 	const sourceFormat = sourceFormatOverride || detectFormat(body);
 
 	// Check for bypass patterns (warmup, skip, cc naming)
-  const bypassResponse = handleBypassRequest(body, model, userAgent, ccFilterNaming);
+	const bypassResponse = handleBypassRequest(
+		body,
+		model,
+		userAgent,
+		ccFilterNaming,
+	);
 	if (bypassResponse) return bypassResponse;
 
 	const alias = PROVIDER_ID_TO_ALIAS[provider] || provider;
 	const modelTargetFormat = getModelTargetFormat(alias, model);
-  // Multi-endpoint providers: pick transport matching sourceFormat → zero translation.
-  // Per-model guard: only use the transport when the model declares support for that
-  // sourceFormat — opencode-go models differ in endpoint support (kimi/glm only do
-  // /chat/completions), so without this guard a claude-format request would wrongly
-  // route kimi to /messages.
-  const modelSupportedFormats = getModelSupportedFormats(alias, model);
+	// Multi-endpoint providers: pick transport matching sourceFormat → zero translation
 	const runtimeTransport = resolveTransport(provider, sourceFormat);
-  // Per-model guard: when a model declares supportedFormats, only use the
-  // sourceFormat-matched transport if that format is declared (opencode-go models
-  // differ — kimi/glm only do /chat/completions). Undeclared models keep the
-  // upstream default (use the transport), preserving behavior for glm/deepseek/...
-  const useTransport = (!modelSupportedFormats || modelSupportedFormats.includes(sourceFormat)) ? runtimeTransport : null;
-  const targetFormat = modelTargetFormat || useTransport?.format || getTargetFormat(provider, credentials);
-  if (useTransport && credentials) credentials.runtimeTransport = useTransport;
+	const targetFormat =
+		modelTargetFormat || runtimeTransport?.format || getTargetFormat(provider);
+	if (runtimeTransport && credentials)
+		credentials.runtimeTransport = runtimeTransport;
 	const stripList = getModelStrip(alias, model);
 	const upstreamModel = getModelUpstreamId(alias, model);
 
@@ -109,14 +158,22 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 		}
 	}
 
-  const clientRequestedStreaming = body.stream === true || sourceFormat === FORMATS.ANTIGRAVITY || sourceFormat === FORMATS.GEMINI || sourceFormat === FORMATS.GEMINI_CLI;
+	const clientRequestedStreaming =
+		body.stream === true ||
+		sourceFormat === FORMATS.ANTIGRAVITY ||
+		sourceFormat === FORMATS.GEMINI ||
+		sourceFormat === FORMATS.GEMINI_CLI;
 	const providerRequiresStreaming = PROVIDERS[provider]?.forceStream === true;
-  let stream = providerRequiresStreaming ? true : (body.stream !== false);
+	let stream = providerRequiresStreaming ? true : body.stream !== false;
 
 	// Image generation models require non-streaming (Google v1internal:generateContent)
 	const modelType = getModelType(alias, model);
-  const isImageGenModel = modelType === "imageGen" || /image|imagen|image-generation/i.test(model);
-  if (isImageGenModel && (provider === "antigravity" || provider === "gemini-cli")) {
+	const isImageGenModel =
+		modelType === "imageGen" || /image|imagen|image-generation/i.test(model);
+	if (
+		isImageGenModel &&
+		(provider === "antigravity" || provider === "gemini-cli")
+	) {
 		stream = false;
 	}
 
@@ -131,14 +188,31 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 	const acceptHeader = clientRawRequest?.headers?.accept || "";
 	const clientPrefersJson = acceptHeader.includes("application/json");
 	const clientPrefersSSE = acceptHeader.includes("text/event-stream");
-  if (clientPrefersJson && !clientPrefersSSE && body.stream !== true && !providerRequiresStreaming) {
+	if (
+		clientPrefersJson &&
+		!clientPrefersSSE &&
+		body.stream !== true &&
+		!providerRequiresStreaming
+	) {
 		stream = false;
 	}
 
-  const reqLogger = await createRequestLogger(sourceFormat, targetFormat, model);
-  if (clientRawRequest) reqLogger.logClientRawRequest(clientRawRequest.endpoint, clientRawRequest.body, clientRawRequest.headers);
+	const reqLogger = await createRequestLogger(
+		sourceFormat,
+		targetFormat,
+		model,
+	);
+	if (clientRawRequest)
+		reqLogger.logClientRawRequest(
+			clientRawRequest.endpoint,
+			clientRawRequest.body,
+			clientRawRequest.headers,
+		);
 	reqLogger.logRawRequest(body);
-  log?.debug?.("FORMAT", `${sourceFormat} → ${targetFormat} | stream=${stream}`);
+	log?.debug?.(
+		"FORMAT",
+		`${sourceFormat} → ${targetFormat} | stream=${stream}`,
+	);
 
 	// Native passthrough: CLI tool and provider are the same ecosystem
 	// Skip all translation/normalization — only model and Bearer are swapped
@@ -152,47 +226,61 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 	if (!passthrough) {
 		const caps = getCapabilitiesForModel(provider, model);
 		if (stripUnsupportedModalities(body, sourceFormat, caps)) {
-      log?.debug?.("MODALITY", `stripped unsupported media for ${provider}/${model}`);
+			log?.debug?.(
+				"MODALITY",
+				`stripped unsupported media for ${provider}/${model}`,
+			);
 		}
 		// Convert remote image URLs to base64 for targets that can't fetch URLs.
 		try {
-      const n = await prefetchRemoteImages(body, sourceFormat, targetFormat, { signal: undefined });
-      if (n > 0) log?.debug?.("MODALITY", `prefetched ${n} remote image(s) for ${targetFormat}`);
-    } catch (e) { log?.warn?.("MODALITY", `image prefetch failed: ${e.message}`); }
+			const n = await prefetchRemoteImages(body, sourceFormat, targetFormat, {
+				signal: undefined,
+			});
+			if (n > 0)
+				log?.debug?.(
+					"MODALITY",
+					`prefetched ${n} remote image(s) for ${targetFormat}`,
+				);
+		} catch (e) {
+			log?.warn?.("MODALITY", `image prefetch failed: ${e.message}`);
+		}
 	}
 
 	let translatedBody;
 	let toolNameMap;
-  let customToolNames;
 	if (passthrough) {
-    log?.debug?.("PASSTHROUGH", `${clientTool} → ${provider} | native lossless`);
+		log?.debug?.(
+			"PASSTHROUGH",
+			`${clientTool} → ${provider} | native lossless`,
+		);
 		translatedBody = { ...body, model: stripThinkingSuffix(upstreamModel) };
-    if (provider === "codex") {
-      const suffixThinking = {};
-      applyThinking(sourceFormat, upstreamModel, suffixThinking, provider);
-      if (suffixThinking.reasoning_effort) {
-        const reasoning = translatedBody.reasoning;
-        translatedBody.reasoning = {
-          ...(reasoning && typeof reasoning === "object" && !Array.isArray(reasoning) ? reasoning : {}),
-          effort: suffixThinking.reasoning_effort,
-        };
-        delete translatedBody.reasoning_effort;
-      }
-    }
 		// Normalize newer Cowork/CC beta shapes (adaptive thinking, mid-conversation system) the API rejects
-    if (clientTool === "claude") normalizeClaudePassthrough(translatedBody, translatedBody.model);
+		if (clientTool === "claude")
+			normalizeClaudePassthrough(translatedBody, translatedBody.model);
 	} else {
-    translatedBody = translateRequest(sourceFormat, targetFormat, upstreamModel, body, stream, credentials, provider, reqLogger, stripList, connectionId, clientTool);
+		translatedBody = translateRequest(
+			sourceFormat,
+			targetFormat,
+			upstreamModel,
+			body,
+			stream,
+			credentials,
+			provider,
+			reqLogger,
+			stripList,
+			connectionId,
+			clientTool,
+		);
 		if (!translatedBody) {
 			trackPendingRequest(model, provider, connectionId, false, true);
-      return createErrorResult(HTTP_STATUS.BAD_REQUEST, `Failed to translate request for ${sourceFormat} → ${targetFormat}`);
+			return createErrorResult(
+				HTTP_STATUS.BAD_REQUEST,
+				`Failed to translate request for ${sourceFormat} → ${targetFormat}`,
+			);
 		}
 		toolNameMap = translatedBody._toolNameMap;
 		delete translatedBody._toolNameMap;
-    customToolNames = translatedBody._customToolNames;
-    delete translatedBody._customToolNames;
 		translatedBody.model = stripThinkingSuffix(upstreamModel);
-    stripContinuityFields(translatedBody);
 	}
 
 	// Dedupe duplicate built-in tools when equivalent MCP tools are present (Claude clients only).
@@ -200,7 +288,10 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 		const { tools: deduped, stripped } = dedupeTools(translatedBody.tools);
 		if (stripped.length > 0) {
 			translatedBody.tools = deduped;
-      log?.debug?.("TOOLDEDUP", `stripped ${stripped.length}: ${stripped.slice(0, 3).join(", ")}${stripped.length > 3 ? "..." : ""}`);
+			log?.debug?.(
+				"TOOLDEDUP",
+				`stripped ${stripped.length}: ${stripped.slice(0, 3).join(", ")}${stripped.length > 3 ? "..." : ""}`,
+			);
 		}
 	}
 
@@ -211,12 +302,26 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 	// Request line: one correlated summary (fmt + thinking + counts + account)
 	if (log?.line) {
 		const clientModel = clientRawRequest?.body?.model || `${provider}/${model}`;
-    const msgN = translatedBody.messages?.length || translatedBody.input?.length || translatedBody.contents?.length || body.messages?.length || body.input?.length || 0;
+		const msgN =
+			translatedBody.messages?.length ||
+			translatedBody.input?.length ||
+			translatedBody.contents?.length ||
+			body.messages?.length ||
+			body.input?.length ||
+			0;
 		const toolN = translatedBody.tools?.length || body.tools?.length || 0;
-    const fmtStr = passthrough ? `FMT: ${sourceFormat} (passthrough)` : `FMT: ${sourceFormat}→${targetFormat}`;
-    const showThinking = provider !== "grok-cli" || supportsGrokCliReasoningEffort(model);
-    const think = showThinking ? log.fmtThink?.(extractThinking(translatedBody)) : null;
-    const acc = credentials?.connectionName || credentials?.connectionId?.slice(0, 8) || "-";
+		const fmtStr = passthrough
+			? `FMT: ${sourceFormat} (passthrough)`
+			: `FMT: ${sourceFormat}→${targetFormat}`;
+		const showThinking =
+			provider !== "grok-cli" || supportsGrokCliReasoningEffort(model);
+		const think = showThinking
+			? log.fmtThink?.(extractThinking(translatedBody))
+			: null;
+		const acc =
+			credentials?.connectionName ||
+			credentials?.connectionId?.slice(0, 8) ||
+			"-";
 		const parts = [
 			`POST ${clientModel} → ${provider}/${model}`,
 			fmtStr,
@@ -231,29 +336,52 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 
 	// TTS models don't support tool messages/function calling
 	if (getModelType(alias, model) === "tts" && translatedBody.messages) {
-    translatedBody.messages = translatedBody.messages.filter(msg => msg.role !== "tool");
+		translatedBody.messages = translatedBody.messages.filter(
+			(msg) => msg.role !== "tool",
+		);
 		delete translatedBody.tools;
 	}
 
 	// Per-request opt-out: client can bypass all token savers via header
-  const tokenSaverEnabled = clientRawRequest?.headers?.[TOKEN_SAVER_HEADER]?.toLowerCase() !== "off";
+	const tokenSaverEnabled =
+		clientRawRequest?.headers?.[TOKEN_SAVER_HEADER]?.toLowerCase() !== "off";
 
 	// RTK: compress tool_result content
-  const rtkStats = compressMessages(translatedBody, tokenSaverEnabled && rtkEnabled);
+	const rtkStats = compressMessages(
+		translatedBody,
+		tokenSaverEnabled && rtkEnabled,
+	);
 	const rtkLine = formatRtkLog(rtkStats);
 	if (rtkLine) console.log(rtkLine);
 
 	// Headroom: optional external proxy compression; fail open if proxy is absent.
 	const headroomDiagnostics = {};
-  const headroomStats = await compressWithHeadroom(translatedBody, { enabled: tokenSaverEnabled && headroomEnabled, url: headroomUrl, model: upstreamModel, format: finalFormat, compressUserMessages: headroomCompressUserMessages, diagnostics: headroomDiagnostics });
+	const headroomStats = await compressWithHeadroom(translatedBody, {
+		enabled: tokenSaverEnabled && headroomEnabled,
+		url: headroomUrl,
+		model: upstreamModel,
+		format: finalFormat,
+		compressUserMessages: headroomCompressUserMessages,
+		diagnostics: headroomDiagnostics,
+	});
 	const headroomLine = formatHeadroomLog(headroomStats);
 	const headroomSizeLine = formatHeadroomSizeLog(headroomDiagnostics);
 	if (headroomLine) {
-    log?.info?.("HEADROOM", `${headroomLine}${headroomSizeLine ? ` | ${headroomSizeLine}` : ""}`);
+		log?.info?.(
+			"HEADROOM",
+			`${headroomLine}${headroomSizeLine ? ` | ${headroomSizeLine}` : ""}`,
+		);
 		if (isHeadroomPhantomSavings(headroomStats, headroomDiagnostics)) {
-      log?.warn?.("HEADROOM", `reported token delta, but outbound JSON shrank <5%; provider may bill near-original payload | ${formatHeadroomSizeLog(headroomDiagnostics)}`);
+			log?.warn?.(
+				"HEADROOM",
+				`reported token delta, but outbound JSON shrank <5%; provider may bill near-original payload | ${formatHeadroomSizeLog(headroomDiagnostics)}`,
+			);
 		}
-  } else if (tokenSaverEnabled && headroomEnabled) log?.warn?.("HEADROOM", `skipped: ${headroomDiagnostics.reason || "compression unavailable"}${headroomDiagnostics.endpoint ? ` (${headroomDiagnostics.endpoint})` : ""}`);
+	} else if (tokenSaverEnabled && headroomEnabled)
+		log?.warn?.(
+			"HEADROOM",
+			`skipped: ${headroomDiagnostics.reason || "compression unavailable"}${headroomDiagnostics.endpoint ? ` (${headroomDiagnostics.endpoint})` : ""}`,
+		);
 
 	// Token-saver flags accumulator for the single "⚙" log line below.
 	const xf = [];
@@ -274,27 +402,42 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 	let pxpipeSummary = null;
 	if (pxpipeEnabled) {
 		const pxpipeResult = await compressWithPxpipe(translatedBody, {
-      enabled: true, format: finalFormat, model: upstreamModel,
-      minChars: pxpipeMinChars, timeoutMs: pxpipeTimeoutMs, transform: pxpipeTransform,
+			enabled: true,
+			format: finalFormat,
+			model: upstreamModel,
+			minChars: pxpipeMinChars,
+			timeoutMs: pxpipeTimeoutMs,
+			transform: pxpipeTransform,
 		});
 		pxpipeSummary = pxpipeResult.summary;
 		if (pxpipeResult.body) translatedBody = pxpipeResult.body;
-    if (pxpipeSummary?.applied) xf.push(`PXPIPE:${pxpipeSummary.imageCount}img`);
-    try { onPxpipeEvent?.({ provider, model, ...pxpipeSummary }); } catch { /* stats must not break requests */ }
+		if (pxpipeSummary?.applied)
+			xf.push(`PXPIPE:${pxpipeSummary.imageCount}img`);
+		try {
+			onPxpipeEvent?.({ provider, model, ...pxpipeSummary });
+		} catch {
+			/* stats must not break requests */
+		}
 	}
 
 	if (xf.length && log?.line) log.line(reqTag, "⚙", xf.join(" · "));
 
-  // Pin cache breakpoints to the final body — every saver above can reshape
-  // system/tools/messages, and a stale anchor costs a full prefix rewrite.
-  if (passthrough && clientTool === "claude") anchorClaudeCache(translatedBody);
-
 	const executor = getExecutor(provider);
 	trackPendingRequest(model, provider, connectionId, true);
-  appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => { });
+	appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(
+		() => {},
+	);
 
-  const msgCount = translatedBody.messages?.length || translatedBody.input?.length || translatedBody.contents?.length || translatedBody.request?.contents?.length || 0;
-  log?.debug?.("REQUEST", `${provider.toUpperCase()} | ${model} | ${msgCount} msgs`);
+	const msgCount =
+		translatedBody.messages?.length ||
+		translatedBody.input?.length ||
+		translatedBody.contents?.length ||
+		translatedBody.request?.contents?.length ||
+		0;
+	log?.debug?.(
+		"REQUEST",
+		`${provider.toUpperCase()} | ${model} | ${msgCount} msgs`,
+	);
 
 	const streamController = createStreamController({
 		onDisconnect: (reason) => {
@@ -302,21 +445,35 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 			if (onDisconnect) onDisconnect(reason);
 		},
 		onError: () => trackPendingRequest(model, provider, connectionId, false),
-    log, provider, model, reqTag
+		log,
+		provider,
+		model,
+		reqTag,
 	});
 
 	const proxyOptions = {
-    connectionProxyEnabled: credentials?.providerSpecificData?.connectionProxyEnabled === true,
-    connectionProxyUrl: credentials?.providerSpecificData?.connectionProxyUrl || "",
-    connectionNoProxy: credentials?.providerSpecificData?.connectionNoProxy || "",
+		connectionProxyEnabled:
+			credentials?.providerSpecificData?.connectionProxyEnabled === true,
+		connectionProxyUrl:
+			credentials?.providerSpecificData?.connectionProxyUrl || "",
+		connectionNoProxy:
+			credentials?.providerSpecificData?.connectionNoProxy || "",
 		vercelRelayUrl: credentials?.providerSpecificData?.vercelRelayUrl || "",
 	};
 
 	if (proxyOptions.vercelRelayUrl) {
-    const connectionName = credentials?.connectionName || credentials?.connectionId || "unknown";
-    const poolId = credentials?.providerSpecificData?.connectionProxyPoolId || "none";
-    log?.info?.("PROXY", `${provider.toUpperCase()} | ${model} | conn=${connectionName} | pool=${poolId} | vercel-relay=${proxyOptions.vercelRelayUrl}`);
-  } else if (proxyOptions.connectionProxyEnabled && proxyOptions.connectionProxyUrl) {
+		const connectionName =
+			credentials?.connectionName || credentials?.connectionId || "unknown";
+		const poolId =
+			credentials?.providerSpecificData?.connectionProxyPoolId || "none";
+		log?.info?.(
+			"PROXY",
+			`${provider.toUpperCase()} | ${model} | conn=${connectionName} | pool=${poolId} | vercel-relay=${proxyOptions.vercelRelayUrl}`,
+		);
+	} else if (
+		proxyOptions.connectionProxyEnabled &&
+		proxyOptions.connectionProxyUrl
+	) {
 		let maskedProxyUrl = proxyOptions.connectionProxyUrl;
 		try {
 			const parsed = new URL(proxyOptions.connectionProxyUrl);
@@ -328,14 +485,23 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 			// Keep raw if URL parsing fails
 		}
 
-    const poolId = credentials?.providerSpecificData?.connectionProxyPoolId || "none";
-    const connectionName = credentials?.connectionName || credentials?.connectionId || "unknown";
-    log?.info?.("PROXY", `${provider.toUpperCase()} | ${model} | conn=${connectionName} | pool=${poolId} | url=${maskedProxyUrl}`);
+		const poolId =
+			credentials?.providerSpecificData?.connectionProxyPoolId || "none";
+		const connectionName =
+			credentials?.connectionName || credentials?.connectionId || "unknown";
+		log?.info?.(
+			"PROXY",
+			`${provider.toUpperCase()} | ${model} | conn=${connectionName} | pool=${poolId} | url=${maskedProxyUrl}`,
+		);
 	}
 
 	if (proxyOptions.connectionProxyEnabled && proxyOptions.connectionNoProxy) {
-    const connectionName = credentials?.connectionName || credentials?.connectionId || "unknown";
-    log?.debug?.("PROXY", `${provider.toUpperCase()} | ${model} | conn=${connectionName} | no_proxy=${proxyOptions.connectionNoProxy}`);
+		const connectionName =
+			credentials?.connectionName || credentials?.connectionId || "unknown";
+		log?.debug?.(
+			"PROXY",
+			`${provider.toUpperCase()} | ${model} | conn=${connectionName} | no_proxy=${proxyOptions.connectionNoProxy}`,
+		);
 	}
 
 	// Execute request
@@ -344,7 +510,15 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 	// exception: it is decoded by the executor into OpenAI-compatible output.
 	let providerResponseFormat = targetFormat;
 	try {
-    const result = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
+		const result = await executor.execute({
+			model,
+			body: translatedBody,
+			stream,
+			credentials,
+			signal: streamController.signal,
+			log,
+			proxyOptions,
+		});
 		providerResponse = result.response;
 		providerUrl = result.url;
 		providerHeaders = result.headers;
@@ -353,111 +527,254 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 		reqLogger.logTargetRequest(providerUrl, providerHeaders, finalBody);
 	} catch (error) {
 		trackPendingRequest(model, provider, connectionId, false, true);
-    appendRequestLog({ model, provider, connectionId, status: `FAILED ${error.name === "AbortError" ? 499 : HTTP_STATUS.BAD_GATEWAY}` }).catch(() => { });
-    saveRequestDetail(buildRequestDetail({
-      provider, model, connectionId,
+		appendRequestLog({
+			model,
+			provider,
+			connectionId,
+			status: `FAILED ${error.name === "AbortError" ? 499 : HTTP_STATUS.BAD_GATEWAY}`,
+		}).catch(() => {});
+		saveRequestDetail(
+			buildRequestDetail({
+				provider,
+				model,
+				connectionId,
 				latency: { ttft: 0, total: Date.now() - requestStartTime },
 				tokens: { prompt_tokens: 0, completion_tokens: 0 },
 				request: extractRequestConfig(body, stream),
 				providerRequest: translatedBody || null,
-      response: { error: error.message || String(error), status: error.name === "AbortError" ? 499 : 502, thinking: null },
+				response: {
+					error: error.message || String(error),
+					status: error.name === "AbortError" ? 499 : 502,
+					thinking: null,
+				},
 				pxpipe: pxpipeSummary,
-      status: "error"
-    })).catch(() => { });
+				status: "error",
+			}),
+		).catch(() => {});
 
 		if (error.name === "AbortError") {
 			streamController.handleError(error);
 			return createErrorResult(499, "Request aborted");
 		}
-    const errMsg = formatProviderError(error, provider, model, HTTP_STATUS.BAD_GATEWAY);
+		const errMsg = formatProviderError(
+			error,
+			provider,
+			model,
+			HTTP_STATUS.BAD_GATEWAY,
+		);
 		if (log?.errorLine) {
-      log.errorLine(reqTag, "✗", `ERROR 502 · ${provider}/${model} · ${Date.now() - requestStartTime}ms\n    ${errMsg}${error.stack ? `\n    ${error.stack}` : ""}`);
+			log.errorLine(
+				reqTag,
+				"✗",
+				`ERROR 502 · ${provider}/${model} · ${Date.now() - requestStartTime}ms\n    ${errMsg}${error.stack ? `\n    ${error.stack}` : ""}`,
+			);
 		}
 		return createErrorResult(HTTP_STATUS.BAD_GATEWAY, errMsg);
 	}
 
+	// Config-driven in-stream error detection: peek the first bytes of a 200
+	// stream; if a configured pattern matches, fail fast with 502 so account
+	// /combo fallback can still run before any byte reaches the client.
+	const configuredPatterns = streamErrorPatterns?.[provider];
+	if (
+		providerResponse?.ok &&
+		Array.isArray(configuredPatterns) &&
+		configuredPatterns.length > 0
+	) {
+		providerResponse = await maybeRejectEarlyStreamError(
+			providerResponse,
+			configuredPatterns,
+			{ signal: streamController.signal },
+		);
+	}
+
 	// Handle 401/403 - try token refresh (skip for noAuth providers)
-  if (!executor.noAuth && (providerResponse.status === HTTP_STATUS.UNAUTHORIZED || providerResponse.status === HTTP_STATUS.FORBIDDEN)) {
+	if (
+		!executor.noAuth &&
+		(providerResponse.status === HTTP_STATUS.UNAUTHORIZED ||
+			providerResponse.status === HTTP_STATUS.FORBIDDEN)
+	) {
 		try {
 			// Mutate credentials after each successful refresh: rotating refresh_token
 			// providers (xAI/grok-cli) issue a new RT on every refresh; without this,
 			// refreshWithRetry's 2nd/3rd attempt reuses the already-consumed RT →
 			// invalid_grant → auth_failed retryable=false.
-      const newCredentials = await refreshWithRetry(async () => {
+			const newCredentials = await refreshWithRetry(
+				async () => {
 					const result = await executor.refreshCredentials(credentials, log);
-        if (result?.refreshToken && result.refreshToken !== credentials.refreshToken) {
-          if (result.accessToken) credentials.accessToken = result.accessToken;
+					if (
+						result?.refreshToken &&
+						result.refreshToken !== credentials.refreshToken
+					) {
+						if (result.accessToken)
+							credentials.accessToken = result.accessToken;
 						credentials.refreshToken = result.refreshToken;
 					}
 					return result;
-      }, 3, log);
+				},
+				3,
+				log,
+			);
 			if (newCredentials?.accessToken || newCredentials?.copilotToken) {
-        if (log?.line) log.line(reqTag, "🔑", `TOKEN REFRESHED · ${provider}/${model}`);
+				if (log?.line)
+					log.line(reqTag, "🔑", `TOKEN REFRESHED · ${provider}/${model}`);
 				Object.assign(credentials, newCredentials);
 				if (onCredentialsRefreshed) {
-          try { await onCredentialsRefreshed(newCredentials); } catch (e) { log?.warn?.("TOKEN", `onCredentialsRefreshed failed: ${e.message}`); }
+					try {
+						await onCredentialsRefreshed(newCredentials);
+					} catch (e) {
+						log?.warn?.("TOKEN", `onCredentialsRefreshed failed: ${e.message}`);
+					}
 				}
 				try {
-          const retryResult = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
+					const retryResult = await executor.execute({
+						model,
+						body: translatedBody,
+						stream,
+						credentials,
+						signal: streamController.signal,
+						log,
+						proxyOptions,
+					});
 					if (retryResult.response.ok) {
 						providerResponse = retryResult.response;
 						providerUrl = retryResult.url;
 						providerResponseFormat = retryResult.responseFormat || targetFormat;
 					}
-        } catch { log?.warn?.("TOKEN", `${provider.toUpperCase()} | retry after refresh failed`); }
+				} catch {
+					log?.warn?.(
+						"TOKEN",
+						`${provider.toUpperCase()} | retry after refresh failed`,
+					);
+				}
 			} else {
 				log?.warn?.("TOKEN", `${provider.toUpperCase()} | refresh failed`);
 			}
 		} catch (e) {
-      log?.warn?.("TOKEN", `${provider.toUpperCase()} | refresh threw: ${e.message}`);
+			log?.warn?.(
+				"TOKEN",
+				`${provider.toUpperCase()} | refresh threw: ${e.message}`,
+			);
 		}
 	}
 
 	// Provider returned error
 	if (!providerResponse.ok) {
 		trackPendingRequest(model, provider, connectionId, false, true);
-    const { statusCode, message, resetsAtMs } = await parseUpstreamError(providerResponse, executor);
-    appendRequestLog({ model, provider, connectionId, status: `FAILED ${statusCode}` }).catch(() => { });
-    saveRequestDetail(buildRequestDetail({
-      provider, model, connectionId,
+		const { statusCode, message, resetsAtMs } = await parseUpstreamError(
+			providerResponse,
+			executor,
+		);
+		appendRequestLog({
+			model,
+			provider,
+			connectionId,
+			status: `FAILED ${statusCode}`,
+		}).catch(() => {});
+		saveRequestDetail(
+			buildRequestDetail({
+				provider,
+				model,
+				connectionId,
 				latency: { ttft: 0, total: Date.now() - requestStartTime },
 				tokens: { prompt_tokens: 0, completion_tokens: 0 },
 				request: extractRequestConfig(body, stream),
 				providerRequest: finalBody || translatedBody || null,
 				response: { error: message, status: statusCode, thinking: null },
 				pxpipe: pxpipeSummary,
-      status: "error"
-    })).catch(() => { });
+				status: "error",
+			}),
+		).catch(() => {});
 
-    const errMsg = formatProviderError(new Error(message), provider, model, statusCode);
+		const errMsg = formatProviderError(
+			new Error(message),
+			provider,
+			model,
+			statusCode,
+		);
 		if (log?.errorLine) {
 			const urlStr = providerUrl ? `\n    URL: ${providerUrl}` : "";
-      log.errorLine(reqTag, "✗", `ERROR ${statusCode} · ${provider}/${model} · ${Date.now() - requestStartTime}ms${urlStr}\n    ${errMsg}`);
+			log.errorLine(
+				reqTag,
+				"✗",
+				`ERROR ${statusCode} · ${provider}/${model} · ${Date.now() - requestStartTime}ms${urlStr}\n    ${errMsg}`,
+			);
 		}
 		reqLogger.logError(new Error(message), finalBody || translatedBody);
 		return createErrorResult(statusCode, errMsg, resetsAtMs);
 	}
 
-  const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, pxpipe: pxpipeSummary, reqTag, log };
-  const appendLog = (extra) => appendRequestLog({ model, provider, connectionId, ...extra }).catch(() => { });
-  const trackDone = () => trackPendingRequest(model, provider, connectionId, false);
+	const sharedCtx = {
+		provider,
+		model,
+		body,
+		stream,
+		translatedBody,
+		finalBody,
+		requestStartTime,
+		connectionId,
+		apiKey,
+		clientRawRequest,
+		onRequestSuccess,
+		pxpipe: pxpipeSummary,
+		reqTag,
+		log,
+		streamErrorPatterns,
+	};
+	const appendLog = (extra) =>
+		appendRequestLog({ model, provider, connectionId, ...extra }).catch(
+			() => {},
+		);
+	const trackDone = () =>
+		trackPendingRequest(model, provider, connectionId, false);
 
 	// Provider forced streaming but client wants JSON
 	if (!clientRequestedStreaming && providerRequiresStreaming) {
-    const result = await handleForcedSSEToJson({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, customToolNames, trackDone, appendLog });
-    if (result) { streamController.handleComplete(); return result; }
+		const result = await handleForcedSSEToJson({
+			...sharedCtx,
+			providerResponse,
+			sourceFormat,
+			trackDone,
+			appendLog,
+		});
+		if (result) {
+			streamController.handleComplete();
+			return result;
+		}
 	}
 
 	// True non-streaming response
 	if (!stream) {
-    const result = await handleNonStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, reqLogger, toolNameMap, customToolNames, trackDone, appendLog });
+		const result = await handleNonStreamingResponse({
+			...sharedCtx,
+			providerResponse,
+			sourceFormat,
+			targetFormat: providerResponseFormat,
+			reqLogger,
+			toolNameMap,
+			trackDone,
+			appendLog,
+		});
 		streamController.handleComplete();
 		return result;
 	}
 
 	// Streaming response
-  const { onStreamComplete, streamDetailId } = buildOnStreamComplete({ ...sharedCtx });
-  return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, userAgent, reqLogger, toolNameMap, customToolNames, streamController, onStreamComplete, streamDetailId });
+	const { onStreamComplete, streamDetailId } = buildOnStreamComplete({
+		...sharedCtx,
+	});
+	return handleStreamingResponse({
+		...sharedCtx,
+		providerResponse,
+		sourceFormat,
+		targetFormat: providerResponseFormat,
+		userAgent,
+		reqLogger,
+		toolNameMap,
+		streamController,
+		onStreamComplete,
+		streamDetailId,
+	});
 }
 
 export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {

open-sse/handlers/chatCore/nonStreamingHandler.js

@@ -9,7 +9,6 @@ import { parseSSEToOpenAIResponse } from "./sseToJsonHandler.js";
 import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine } from "./requestDetail.js";
 import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
 import { decloakToolNames } from "../../utils/claudeCloaking.js";
-import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
 
 function parseToolArguments(value) {
   if (!value) return {};
@@ -61,93 +60,11 @@ function openAICompletionToClaudeMessage(responseBody) {
   };
 }
 
-/**
- * Convert an OpenAI Chat Completions non-streaming response body into the
- * OpenAI Responses API shape. Used when a Responses-format client (e.g. Codex)
- * is routed to a Chat Completions upstream and `stream:false` — the streaming
- * path already emits Responses events, but the JSON path returned a raw
- * `chat.completion` body, so tool_calls were invisible to Responses clients.
- */
-function extractCustomToolInput(argumentsValue) {
-  const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
-  try {
-    const parsed = JSON.parse(argumentsText);
-    if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
-  } catch { /* raw freeform input */ }
-  return argumentsText;
-}
-
-function openAICompletionToResponses(responseBody, customToolNames = null) {
-  const choice = responseBody?.choices?.[0];
-  if (!choice) return responseBody;
-
-  const message = choice.message || {};
-  const output = [];
-
-  // Reasoning → a reasoning item (summary text), mirroring the streaming path.
-  const reasoning = message.reasoning_content || message.reasoning;
-  if (typeof reasoning === "string" && reasoning.length > 0) {
-    output.push({
-      type: RESPONSES_ITEM.REASONING,
-      summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
-    });
-  }
-
-  // Assistant text → a message item with output_text content.
-  const text = typeof message.content === "string" ? message.content : "";
-  if (text.length > 0) {
-    output.push({
-      type: RESPONSES_ITEM.MESSAGE,
-      role: ROLE.ASSISTANT,
-      content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
-    });
-  }
-
-  // tool_calls → function_call/custom_tool_call items (Responses-native tool shape).
-  for (const tc of message.tool_calls || []) {
-    const fn = tc.function || {};
-    const custom = customToolNames?.has(fn.name);
-    output.push({
-      type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
-      id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
-      call_id: tc.id || "",
-      name: fn.name || "",
-      ...(custom
-        ? { input: extractCustomToolInput(fn.arguments) }
-        : { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
-    });
-  }
-
-  const usage = responseBody.usage || {};
-  const status = choice.finish_reason === "tool_calls" ? "completed" : (choice.finish_reason === "stop" ? "completed" : (choice.finish_reason || "completed"));
-
-  return {
-    id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
-    object: "response",
-    created_at: responseBody.created || Math.floor(Date.now() / 1000),
-    model: responseBody.model || "unknown",
-    status,
-    background: false,
-    error: null,
-    output,
-    usage: {
-      input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
-      output_tokens: usage.completion_tokens || usage.output_tokens || 0,
-      total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
-    },
-  };
-}
-
 /**
  * Translate non-streaming response body from provider format → OpenAI format.
  */
-export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames = null) {
+export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat) {
   if (targetFormat === sourceFormat) return responseBody;
-  // Provider responded in OpenAI Chat Completions shape but the client speaks
-  // Responses API — convert so tool_calls/text surface as Responses `output`.
-  if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.OPENAI_RESPONSES) {
-    return openAICompletionToResponses(responseBody, customToolNames);
-  }
   if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.CLAUDE) {
     return openAICompletionToClaudeMessage(responseBody);
   }
@@ -281,7 +198,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
 /**
  * Handle non-streaming response from provider.
  */
-export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, trackDone, appendLog, pxpipe, reqTag, log }) {
+export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog, pxpipe, reqTag, log }) {
   trackDone();
   const contentType = providerResponse.headers.get("content-type") || "";
   let responseBody;
@@ -322,12 +239,9 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
 
   const translatedResponse = needsTranslation(targetFormat, sourceFormat)
-    ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames)
+    ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
     : responseBody;
   const isClaudeMessageResponse = sourceFormat === FORMATS.CLAUDE && translatedResponse?.type === "message";
-  // Responses-format translation produces a `object:"response"` body with no
-  // `choices`; skip the Chat-Completions-specific post-processing below for it.
-  const isResponsesResponse = sourceFormat === FORMATS.OPENAI_RESPONSES && translatedResponse?.object === "response";
 
   // Fix finish_reason for tool_calls: some providers return non-standard values (e.g. "other")
   if (translatedResponse?.choices?.[0]) {
@@ -340,13 +254,13 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   }
 
   // Ensure OpenAI-required fields
-  if (!isClaudeMessageResponse && !isResponsesResponse) {
+  if (!isClaudeMessageResponse) {
     if (!translatedResponse.object) translatedResponse.object = "chat.completion";
     if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
   }
 
   // Strip Azure-specific fields
-  if (!isClaudeMessageResponse && !isResponsesResponse) {
+  if (!isClaudeMessageResponse) {
     delete translatedResponse.prompt_filter_results;
     if (translatedResponse?.choices) {
       for (const choice of translatedResponse.choices) delete choice.content_filter_results;
@@ -360,7 +274,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   // Strip reasoning_content only when content is non-empty.
   // When content is empty (e.g. thinking models that used all tokens for reasoning),
   // reasoning_content is the only useful output and must be preserved.
-  if (!isClaudeMessageResponse && !isResponsesResponse && translatedResponse?.choices) {
+  if (!isClaudeMessageResponse && translatedResponse?.choices) {
     for (const choice of translatedResponse.choices) {
       if (choice?.message?.reasoning_content && choice.message.content) {
         delete choice.message.reasoning_content;

open-sse/handlers/chatCore/requestDetail.js

@@ -44,14 +44,13 @@ export function extractUsageFromResponse(responseBody) {
     };
   }
 
-  // Gemini format. Antigravity / gemini-cli wrap the payload in { response: {...} }.
-  const usageMetadata = responseBody.usageMetadata || responseBody.response?.usageMetadata;
-  if (usageMetadata) {
+  // Gemini format
+  if (responseBody.usageMetadata) {
     return {
-      prompt_tokens: usageMetadata.promptTokenCount || 0,
-      completion_tokens: usageMetadata.candidatesTokenCount || 0,
-      cached_tokens: usageMetadata.cachedContentTokenCount || 0,
-      reasoning_tokens: usageMetadata.thoughtsTokenCount || 0
+      prompt_tokens: responseBody.usageMetadata.promptTokenCount || 0,
+      completion_tokens: responseBody.usageMetadata.candidatesTokenCount || 0,
+      cached_tokens: responseBody.usageMetadata.cachedContentTokenCount || 0,
+      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount || 0
     };
   }
 

open-sse/handlers/chatCore/sseToJsonHandler.js

@@ -1,13 +1,19 @@
 import { convertResponsesStreamToJson } from "../../transformer/streamToJsonConverter.js";
+import { matchStreamErrorPatterns } from "../../utils/streamErrorPatterns.js";
 import { createErrorResult } from "../../utils/error.js";
 import { HTTP_STATUS } from "../../config/runtimeConfig.js";
 import { FORMATS } from "../../translator/formats.js";
 import { PROVIDERS } from "../../config/providers.js";
-import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
-import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
+import {
+	buildRequestDetail,
+	extractRequestConfig,
+	saveUsageStats,
+	formatDoneLine,
+} from "./requestDetail.js";
 
 // Responses-API providers (e.g. codex) may emit SSE without content-type + use Responses output shape
-const isResponsesProvider = (p) => PROVIDERS[p]?.format === FORMATS.OPENAI_RESPONSES;
+const isResponsesProvider = (p) =>
+	PROVIDERS[p]?.format === FORMATS.OPENAI_RESPONSES;
 import { saveRequestDetail, appendRequestLog } from "@/lib/usageDb.js";
 
 function textFromResponsesMessageItem(item) {
@@ -35,76 +41,6 @@ function pickAssistantMessageForChatCompletion(output) {
 	return { msgItem: last, textContent: textFromResponsesMessageItem(last) };
 }
 
-/**
- * Convert an OpenAI Chat Completions JSON body into the Responses API shape.
- * Inlined here (not imported from nonStreamingHandler.js) to avoid a circular
- * import. Mirrors openAICompletionToResponses in nonStreamingHandler.js.
- */
-function extractCustomToolInput(argumentsValue) {
-  const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
-  try {
-    const parsed = JSON.parse(argumentsText);
-    if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
-  } catch { /* raw freeform input */ }
-  return argumentsText;
-}
-
-function chatCompletionToResponses(responseBody, customToolNames = null) {
-  const choice = responseBody?.choices?.[0];
-  if (!choice) return responseBody;
-
-  const message = choice.message || {};
-  const output = [];
-
-  const reasoning = message.reasoning_content || message.reasoning;
-  if (typeof reasoning === "string" && reasoning.length > 0) {
-    output.push({
-      type: RESPONSES_ITEM.REASONING,
-      summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
-    });
-  }
-
-  const text = typeof message.content === "string" ? message.content : "";
-  if (text.length > 0) {
-    output.push({
-      type: RESPONSES_ITEM.MESSAGE,
-      role: ROLE.ASSISTANT,
-      content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
-    });
-  }
-
-  for (const tc of message.tool_calls || []) {
-    const fn = tc.function || {};
-    const custom = customToolNames?.has(fn.name);
-    output.push({
-      type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
-      id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
-      call_id: tc.id || "",
-      name: fn.name || "",
-      ...(custom
-        ? { input: extractCustomToolInput(fn.arguments) }
-        : { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
-    });
-  }
-
-  const usage = responseBody.usage || {};
-  return {
-    id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
-    object: "response",
-    created_at: responseBody.created || Math.floor(Date.now() / 1000),
-    model: responseBody.model || "unknown",
-    status: "completed",
-    background: false,
-    error: null,
-    output,
-    usage: {
-      input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
-      output_tokens: usage.completion_tokens || usage.output_tokens || 0,
-      total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
-    },
-  };
-}
-
 /**
  * Parse OpenAI-style SSE text into a single chat completion JSON.
  * Used when provider forces streaming but client wants non-streaming.
@@ -122,7 +58,9 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
 			const chunk = JSON.parse(payload);
 			if (chunk?.error) streamError = chunk.error;
 			else chunks.push(chunk);
-    } catch { /* ignore malformed lines */ }
+		} catch {
+			/* ignore malformed lines */
+		}
 	}
 
 	if (streamError) return { error: streamError };
@@ -138,8 +76,13 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
 	for (const chunk of chunks) {
 		const choice = chunk?.choices?.[0];
 		const delta = choice?.delta || {};
-    if (typeof delta.content === "string" && delta.content.length > 0) contentParts.push(delta.content);
-    if (typeof delta.reasoning_content === "string" && delta.reasoning_content.length > 0) reasoningParts.push(delta.reasoning_content);
+		if (typeof delta.content === "string" && delta.content.length > 0)
+			contentParts.push(delta.content);
+		if (
+			typeof delta.reasoning_content === "string" &&
+			delta.reasoning_content.length > 0
+		)
+			reasoningParts.push(delta.reasoning_content);
 		if (choice?.finish_reason) finishReason = choice.finish_reason;
 		if (chunk?.usage && typeof chunk.usage === "object") usage = chunk.usage;
 
@@ -148,20 +91,31 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
 			for (const tc of delta.tool_calls) {
 				const idx = tc.index ?? 0;
 				if (!toolCallMap.has(idx)) {
-          toolCallMap.set(idx, { id: tc.id || "", type: "function", function: { name: "", arguments: "" } });
+					toolCallMap.set(idx, {
+						id: tc.id || "",
+						type: "function",
+						function: { name: "", arguments: "" },
+					});
 				}
 				const existing = toolCallMap.get(idx);
 				if (tc.id) existing.id = tc.id;
 				if (tc.function?.name) existing.function.name += tc.function.name;
-        if (tc.function?.arguments) existing.function.arguments += tc.function.arguments;
+				if (tc.function?.arguments)
+					existing.function.arguments += tc.function.arguments;
 			}
 		}
 	}
 
-  const message = { role: "assistant", content: contentParts.join("") || (toolCallMap.size > 0 ? null : "") };
-  if (reasoningParts.length > 0) message.reasoning_content = reasoningParts.join("");
+	const message = {
+		role: "assistant",
+		content: contentParts.join("") || (toolCallMap.size > 0 ? null : ""),
+	};
+	if (reasoningParts.length > 0)
+		message.reasoning_content = reasoningParts.join("");
 	if (toolCallMap.size > 0) {
-    message.tool_calls = [...toolCallMap.entries()].sort((a, b) => a[0] - b[0]).map(([, tc]) => tc);
+		message.tool_calls = [...toolCallMap.entries()]
+			.sort((a, b) => a[0] - b[0])
+			.map(([, tc]) => tc);
 	}
 
 	const result = {
@@ -169,7 +123,7 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
 		object: "chat.completion",
 		created: first.created || Math.floor(Date.now() / 1000),
 		model: first.model || fallbackModel || "unknown",
-    choices: [{ index: 0, message, finish_reason: finishReason }]
+		choices: [{ index: 0, message, finish_reason: finishReason }],
 	};
 	if (usage) result.usage = usage;
 	return result;
@@ -179,112 +133,201 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
  * Handle case: provider forced streaming but client wants JSON.
  * Supports both Codex/Responses API SSE and standard Chat Completions SSE.
  */
-export async function handleForcedSSEToJson({ providerResponse, sourceFormat, targetFormat, provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, customToolNames, trackDone, appendLog, reqTag, log }) {
+export async function handleForcedSSEToJson({
+	providerResponse,
+	sourceFormat,
+	provider,
+	model,
+	body,
+	stream,
+	translatedBody,
+	finalBody,
+	requestStartTime,
+	connectionId,
+	apiKey,
+	clientRawRequest,
+	onRequestSuccess,
+	trackDone,
+	appendLog,
+	reqTag,
+	log,
+	streamErrorPatterns,
+}) {
 	const contentType = providerResponse.headers.get("content-type") || "";
-  const isSSE = contentType.includes("text/event-stream") || (contentType === "" && isResponsesProvider(provider));
+	const isSSE =
+		contentType.includes("text/event-stream") ||
+		(contentType === "" && isResponsesProvider(provider));
 	if (!isSSE) return null; // not handled here
 
 	trackDone();
 
 	const ctx = {
-    provider, model, connectionId,
+		provider,
+		model,
+		connectionId,
 		request: extractRequestConfig(body, stream),
-    providerRequest: finalBody || translatedBody || null
+		providerRequest: finalBody || translatedBody || null,
 	};
 
 	// Codex/Responses API SSE path
-  // Branch on the UPSTREAM format (targetFormat = format we spoke to the provider in),
-  // not the client format: a Responses-API client behind a chat-native forced-streaming
-  // provider still receives chat SSE chunks, which must go through the standard path.
-  const isCodexResponsesApi = isResponsesProvider(provider) || targetFormat === FORMATS.OPENAI_RESPONSES;
+	const isCodexResponsesApi =
+		isResponsesProvider(provider) || sourceFormat === FORMATS.OPENAI_RESPONSES;
 	if (isCodexResponsesApi) {
 		try {
-      const jsonResponse = await convertResponsesStreamToJson(providerResponse.body);
+			const jsonResponse = await convertResponsesStreamToJson(
+				providerResponse.body,
+			);
 			if (onRequestSuccess) await onRequestSuccess();
 
 			const usage = jsonResponse.usage || {};
 			appendLog({ tokens: usage, status: "200 OK" });
-      saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
-      if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
+			saveUsageStats({
+				provider,
+				model,
+				tokens: usage,
+				connectionId,
+				apiKey,
+				endpoint: clientRawRequest?.endpoint,
+				silent: true,
+			});
+			if (log?.line)
+				log.line(
+					reqTag,
+					"📊",
+					formatDoneLine({
+						usage,
+						latency: { total: Date.now() - requestStartTime },
+					}),
+				);
 
-      // Same cache-inclusive total for the recorded detail, so the DB and the
-      // client-facing usage can never disagree.
-      const inTokensForLog = (usage.input_tokens || 0)
-        + (usage.cache_read_input_tokens || usage.cached_tokens || 0)
-        + (usage.cache_creation_input_tokens || 0);
-      const { msgItem, textContent } = pickAssistantMessageForChatCompletion(jsonResponse.output);
+			const { msgItem, textContent } = pickAssistantMessageForChatCompletion(
+				jsonResponse.output,
+			);
 			const totalLatency = Date.now() - requestStartTime;
 
-      saveRequestDetail(buildRequestDetail({
+			saveRequestDetail(
+				buildRequestDetail(
+					{
 						...ctx,
 						latency: { ttft: totalLatency, total: totalLatency },
-        tokens: { prompt_tokens: inTokensForLog, completion_tokens: usage.output_tokens || 0 },
-        response: { content: textContent, thinking: null, finish_reason: jsonResponse.status || "unknown" },
-        status: "success"
-      }, { endpoint: clientRawRequest?.endpoint || null })).catch(() => {});
+						tokens: {
+							prompt_tokens: usage.input_tokens || 0,
+							completion_tokens: usage.output_tokens || 0,
+						},
+						response: {
+							content: textContent,
+							thinking: null,
+							finish_reason: jsonResponse.status || "unknown",
+						},
+						status: "success",
+					},
+					{ endpoint: clientRawRequest?.endpoint || null },
+				),
+			).catch(() => {});
 
 			// Client is Responses API → return as-is
 			if (sourceFormat === FORMATS.OPENAI_RESPONSES) {
-        return { success: true, response: new Response(JSON.stringify(jsonResponse), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
+				return {
+					success: true,
+					response: new Response(JSON.stringify(jsonResponse), {
+						headers: {
+							"Content-Type": "application/json",
+							"Access-Control-Allow-Origin": "*",
+						},
+					}),
+				};
 			}
 
-      // Build client-format response.
-      // input_tokens EXCLUDES cached tokens on cache-capable upstreams, so summing
-      // only input+output under-reports prompt_tokens — measured: 2012 reported
-      // where the real prompt was ~5344 with 5332 served from cache. Fold the cache
-      // counters in, and keep them visible in prompt_tokens_details so a client can
-      // tell a cache hit from a small prompt.
-      const cacheRead = usage.cache_read_input_tokens || usage.cached_tokens || 0;
-      const cacheCreate = usage.cache_creation_input_tokens || 0;
-      const inTokens = (usage.input_tokens || 0) + cacheRead + cacheCreate;
+			// Build client-format response
+			const inTokens = usage.input_tokens || 0;
 			const outTokens = usage.output_tokens || 0;
-      const cacheDetails = (cacheRead > 0 || cacheCreate > 0)
-        ? { prompt_tokens_details: {
-              ...(cacheRead > 0 ? { cached_tokens: cacheRead } : {}),
-              ...(cacheCreate > 0 ? { cache_creation_tokens: cacheCreate } : {}) } }
-        : {};
 			let finalResp;
 
 			// Extract tool calls from Responses API output (function_call items)
-      const funcCallItems = (jsonResponse.output || []).filter(item => item.type === "function_call");
+			const funcCallItems = (jsonResponse.output || []).filter(
+				(item) => item.type === "function_call",
+			);
 			const toolCalls = funcCallItems.map((item, idx) => ({
 				id: item.call_id || `call_${item.name}_${Date.now()}_${idx}`,
 				type: "function",
 				function: {
 					name: item.name,
-          arguments: typeof item.arguments === "string" ? item.arguments : JSON.stringify(item.arguments || {})
-        }
+					arguments:
+						typeof item.arguments === "string"
+							? item.arguments
+							: JSON.stringify(item.arguments || {}),
+				},
 			}));
 			const hasToolCalls = toolCalls.length > 0;
 
-      if (sourceFormat === FORMATS.ANTIGRAVITY || sourceFormat === FORMATS.GEMINI || sourceFormat === FORMATS.GEMINI_CLI) {
+			if (
+				sourceFormat === FORMATS.ANTIGRAVITY ||
+				sourceFormat === FORMATS.GEMINI ||
+				sourceFormat === FORMATS.GEMINI_CLI
+			) {
 				finalResp = {
 					response: {
-            candidates: [{ content: { role: "model", parts: [{ text: textContent || "" }] }, finishReason: "STOP", index: 0 }],
-            usageMetadata: { promptTokenCount: inTokens, candidatesTokenCount: outTokens, totalTokenCount: inTokens + outTokens },
+						candidates: [
+							{
+								content: {
+									role: "model",
+									parts: [{ text: textContent || "" }],
+								},
+								finishReason: "STOP",
+								index: 0,
+							},
+						],
+						usageMetadata: {
+							promptTokenCount: inTokens,
+							candidatesTokenCount: outTokens,
+							totalTokenCount: inTokens + outTokens,
+						},
 						modelVersion: model,
-            responseId: jsonResponse.id || `resp_${Date.now()}`
-          }
+						responseId: jsonResponse.id || `resp_${Date.now()}`,
+					},
 				};
 			} else {
-        const message = { role: "assistant", content: textContent || (hasToolCalls ? null : "") };
+				const message = {
+					role: "assistant",
+					content: textContent || (hasToolCalls ? null : ""),
+				};
 				if (hasToolCalls) message.tool_calls = toolCalls;
-        const responseDone = jsonResponse.status === "completed" || jsonResponse.status === "done";
-        const finishReason = hasToolCalls ? "tool_calls" : (responseDone ? "stop" : (jsonResponse.status || "stop"));
+				const responseDone =
+					jsonResponse.status === "completed" || jsonResponse.status === "done";
+				const finishReason = hasToolCalls
+					? "tool_calls"
+					: responseDone
+						? "stop"
+						: jsonResponse.status || "stop";
 				finalResp = {
 					id: jsonResponse.id || `chatcmpl-${Date.now()}`,
 					object: "chat.completion",
 					created: jsonResponse.created_at || Math.floor(Date.now() / 1000),
 					model: jsonResponse.model || model,
 					choices: [{ index: 0, message, finish_reason: finishReason }],
-          usage: { prompt_tokens: inTokens, completion_tokens: outTokens, total_tokens: inTokens + outTokens, ...cacheDetails }
+					usage: {
+						prompt_tokens: inTokens,
+						completion_tokens: outTokens,
+						total_tokens: inTokens + outTokens,
+					},
 				};
 			}
 
-      return { success: true, response: new Response(JSON.stringify(finalResp), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
+			return {
+				success: true,
+				response: new Response(JSON.stringify(finalResp), {
+					headers: {
+						"Content-Type": "application/json",
+						"Access-Control-Allow-Origin": "*",
+					},
+				}),
+			};
 		} catch (err) {
 			console.error("[ChatCore] Responses API SSE→JSON failed:", err);
-      return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Failed to convert streaming response to JSON");
+			return createErrorResult(
+				HTTP_STATUS.BAD_GATEWAY,
+				"Failed to convert streaming response to JSON",
+			);
 		}
 	}
 
@@ -292,11 +335,29 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, ta
 	try {
 		const sseText = await providerResponse.text();
 		const parsed = parseSSEToOpenAIResponse(sseText, model);
-    if (!parsed) return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Invalid SSE response for non-streaming request");
+		if (!parsed)
+			return createErrorResult(
+				HTTP_STATUS.BAD_GATEWAY,
+				"Invalid SSE response for non-streaming request",
+			);
 		if (parsed.error) {
 			return createErrorResult(
 				HTTP_STATUS.BAD_GATEWAY,
-        parsed.error.message || "Upstream SSE stream failed"
+				parsed.error.message || "Upstream SSE stream failed",
+			);
+		}
+
+		// Config-driven in-stream error detection: the request "succeeded" at the
+		// HTTP level, but the content signals an upstream failure — treat it as an
+		// error so account/combo fallback and FAILED logging kick in.
+		const matchedPattern = matchStreamErrorPatterns(
+			streamErrorPatterns?.[provider],
+			parsed.choices?.[0]?.message?.content || "",
+		);
+		if (matchedPattern) {
+			return createErrorResult(
+				HTTP_STATUS.BAD_GATEWAY,
+				`Stream error pattern matched: ${matchedPattern}`,
 			);
 		}
 
@@ -304,30 +365,42 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, ta
 
 		const usage = parsed.usage || {};
 		appendLog({ tokens: usage, status: "200 OK" });
-    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
-    if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
+		saveUsageStats({
+			provider,
+			model,
+			tokens: usage,
+			connectionId,
+			apiKey,
+			endpoint: clientRawRequest?.endpoint,
+			silent: true,
+		});
+		if (log?.line)
+			log.line(
+				reqTag,
+				"📊",
+				formatDoneLine({
+					usage,
+					latency: { total: Date.now() - requestStartTime },
+				}),
+			);
 
 		const totalLatency = Date.now() - requestStartTime;
-    saveRequestDetail(buildRequestDetail({
+		saveRequestDetail(
+			buildRequestDetail(
+				{
 					...ctx,
 					latency: { ttft: totalLatency, total: totalLatency },
 					tokens: usage,
 					response: {
 						content: parsed.choices?.[0]?.message?.content || null,
 						thinking: parsed.choices?.[0]?.message?.reasoning_content || null,
-        finish_reason: parsed.choices?.[0]?.finish_reason || "unknown"
+						finish_reason: parsed.choices?.[0]?.finish_reason || "unknown",
 					},
-      status: "success"
-    }, { endpoint: clientRawRequest?.endpoint || null })).catch(() => {});
-
-    // Re-attach usage explicitly. This handler already HAS the correct usage — it is
-    // the same object written to the usage DB, and for a cached Claude request that DB
-    // row reads cache_read_input_tokens: 11022 — yet the client was observed receiving
-    // no usage field at all (verified 2026-08-04 with a fingerprinted payload matched
-    // on both sides). Whatever drops it between assembly and serialisation, the client
-    // must not be left unable to account for its own token spend: a caller cannot tell
-    // a 90%-cached request from a cheap one without this.
-    if (usage && Object.keys(usage).length > 0) parsed.usage = usage;
+					status: "success",
+				},
+				{ endpoint: clientRawRequest?.endpoint || null },
+			),
+		).catch(() => {});
 
 		// Strip reasoning_content only when content is non-empty.
 		// When content is empty (e.g. thinking models that used all tokens for reasoning),
@@ -341,19 +414,20 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, ta
 			}
 		}
 
-    // A Responses-format client (e.g. Codex) forced this provider to stream,
-    // but wants JSON back. parseSSEToOpenAIResponse yields a Chat Completions
-    // body; convert it to the Responses `output` shape so tool_calls are not
-    // lost on the non-streaming return path. Inlined (not imported from
-    // nonStreamingHandler.js) to avoid a circular import: nonStreamingHandler
-    // already imports parseSSEToOpenAIResponse from this module.
-    const finalBody = sourceFormat === FORMATS.OPENAI_RESPONSES
-      ? chatCompletionToResponses(parsed, customToolNames)
-      : parsed;
-
-    return { success: true, response: new Response(JSON.stringify(finalBody), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
+		return {
+			success: true,
+			response: new Response(JSON.stringify(parsed), {
+				headers: {
+					"Content-Type": "application/json",
+					"Access-Control-Allow-Origin": "*",
+				},
+			}),
+		};
 	} catch (err) {
 		console.error("[ChatCore] Chat Completions SSE→JSON failed:", err);
-    return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Failed to convert streaming response to JSON");
+		return createErrorResult(
+			HTTP_STATUS.BAD_GATEWAY,
+			"Failed to convert streaming response to JSON",
+		);
 	}
 }

open-sse/handlers/chatCore/streamingHandler.js

@@ -1,11 +1,20 @@
 import { FORMATS } from "../../translator/formats.js";
 import { needsTranslation } from "../../translator/index.js";
-import { createSSETransformStreamWithLogger, createPassthroughStreamWithLogger } from "../../utils/stream.js";
+import {
+	createSSETransformStreamWithLogger,
+	createPassthroughStreamWithLogger,
+} from "../../utils/stream.js";
 import { pipeWithDisconnect } from "../../utils/streamHandler.js";
 import { PROVIDERS } from "../../config/providers.js";
 import { STREAM_STALL_TIMEOUT_MS } from "../../config/runtimeConfig.js";
 import { buildAbortedResponsesTerminalBytes } from "../../utils/responsesStreamHelpers.js";
-import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
+import {
+	buildRequestDetail,
+	extractRequestConfig,
+	saveUsageStats,
+	formatDoneLine,
+} from "./requestDetail.js";
+import { streamStatusForContent } from "../../utils/streamErrorPatterns.js";
 import { saveRequestDetail } from "@/lib/usageDb.js";
 import { SSE_HEADERS_CORS as SSE_HEADERS } from "../../utils/sseConstants.js";
 
@@ -22,33 +31,108 @@ const CODEX_SOURCE_TO_TARGET = {
 /**
  * Determine which SSE transform stream to use based on provider/format.
  */
-function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, customToolNames, model, connectionId, body, onStreamComplete, apiKey }) {
-  const isDroidCLI = userAgent?.toLowerCase().includes("droid") || userAgent?.toLowerCase().includes("codex-cli");
+function buildTransformStream({
+	provider,
+	sourceFormat,
+	targetFormat,
+	userAgent,
+	reqLogger,
+	toolNameMap,
+	model,
+	connectionId,
+	body,
+	onStreamComplete,
+	apiKey,
+}) {
+	const isDroidCLI =
+		userAgent?.toLowerCase().includes("droid") ||
+		userAgent?.toLowerCase().includes("codex-cli");
 	// Responses-API providers (e.g. codex) emit Responses SSE → translate into client format
-  const isResponsesProvider = PROVIDERS[provider]?.format === FORMATS.OPENAI_RESPONSES;
-  const needsCodexTranslation = isResponsesProvider && targetFormat === FORMATS.OPENAI_RESPONSES && !isDroidCLI;
+	const isResponsesProvider =
+		PROVIDERS[provider]?.format === FORMATS.OPENAI_RESPONSES;
+	const needsCodexTranslation =
+		isResponsesProvider &&
+		targetFormat === FORMATS.OPENAI_RESPONSES &&
+		!isDroidCLI;
 
 	if (needsCodexTranslation) {
 		const codexTarget = CODEX_SOURCE_TO_TARGET[sourceFormat] || FORMATS.OPENAI;
-    return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey, customToolNames);
+		return createSSETransformStreamWithLogger(
+			FORMATS.OPENAI_RESPONSES,
+			codexTarget,
+			provider,
+			reqLogger,
+			toolNameMap,
+			model,
+			connectionId,
+			body,
+			onStreamComplete,
+			apiKey,
+		);
 	}
 
 	if (needsTranslation(targetFormat, sourceFormat)) {
-    return createSSETransformStreamWithLogger(targetFormat, sourceFormat, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey, customToolNames);
+		return createSSETransformStreamWithLogger(
+			targetFormat,
+			sourceFormat,
+			provider,
+			reqLogger,
+			toolNameMap,
+			model,
+			connectionId,
+			body,
+			onStreamComplete,
+			apiKey,
+		);
 	}
 
-  return createPassthroughStreamWithLogger(provider, reqLogger, model, connectionId, body, onStreamComplete, apiKey);
+	return createPassthroughStreamWithLogger(
+		provider,
+		reqLogger,
+		model,
+		connectionId,
+		body,
+		onStreamComplete,
+		apiKey,
+	);
 }
 
 /**
  * Handle streaming response — pipe provider SSE through transform stream to client.
  */
-export async function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, streamController, onStreamComplete, streamDetailId, pxpipe, reqTag, log }) {
+export async function handleStreamingResponse({
+	providerResponse,
+	provider,
+	model,
+	sourceFormat,
+	targetFormat,
+	userAgent,
+	body,
+	stream,
+	translatedBody,
+	finalBody,
+	requestStartTime,
+	connectionId,
+	apiKey,
+	clientRawRequest,
+	onRequestSuccess,
+	reqLogger,
+	toolNameMap,
+	streamController,
+	onStreamComplete,
+	streamDetailId,
+	pxpipe,
+	reqTag,
+	log,
+}) {
 	if (onRequestSuccess) {
 		Promise.resolve()
 			.then(onRequestSuccess)
-      .catch(err => {
-        console.error("[ChatCore] onRequestSuccess failed:", err?.message || err);
+			.catch((err) => {
+				console.error(
+					"[ChatCore] onRequestSuccess failed:",
+					err?.message || err,
+				);
 			});
 	}
 
@@ -59,84 +143,192 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
 	// return a clean JSON error instead. The message is stripped of HTML tags
 	// and clamped so untrusted upstream text never reaches the client verbatim
 	// (the UI may render error.message as HTML).
-  const upstreamContentType = (providerResponse.headers.get('content-type') || '').toLowerCase();
-  if (upstreamContentType && !upstreamContentType.includes('text/event-stream') && !upstreamContentType.includes('application/json')) {
-    const bodyText = await providerResponse.text().catch(() => '');
+	const upstreamContentType = (
+		providerResponse.headers.get("content-type") || ""
+	).toLowerCase();
+	if (
+		upstreamContentType &&
+		!upstreamContentType.includes("text/event-stream") &&
+		!upstreamContentType.includes("application/json")
+	) {
+		const bodyText = await providerResponse.text().catch(() => "");
 		const titleMatch = bodyText.match(/<title>([^<]+)<\/title>/i);
-    const sanitizedTitle = (titleMatch?.[1] || '').replace(/<[^>]*>/g, '').replace(/[\r\n]+/g, ' ').trim().slice(0, 160);
-    const shortMsg = sanitizedTitle
-      || (bodyText.length < 200 ? bodyText.replace(/<[^>]*>/g, '').trim().slice(0, 160) : `Upstream returned non-SSE response (${upstreamContentType})`);
+		const sanitizedTitle = (titleMatch?.[1] || "")
+			.replace(/<[^>]*>/g, "")
+			.replace(/[\r\n]+/g, " ")
+			.trim()
+			.slice(0, 160);
+		const shortMsg =
+			sanitizedTitle ||
+			(bodyText.length < 200
+				? bodyText
+						.replace(/<[^>]*>/g, "")
+						.trim()
+						.slice(0, 160)
+				: `Upstream returned non-SSE response (${upstreamContentType})`);
 		const status = providerResponse.status || 502;
-    if (log?.errorLine) log.errorLine(reqTag, "✗", `BLOCKED ${status} · ${provider}/${model} · non-SSE (${upstreamContentType})\n    ${shortMsg}`);
-    else console.warn(`[STREAM] ${provider} | ${model} | blocked pipe: ${shortMsg} [${status}]`);
+		if (log?.errorLine)
+			log.errorLine(
+				reqTag,
+				"✗",
+				`BLOCKED ${status} · ${provider}/${model} · non-SSE (${upstreamContentType})\n    ${shortMsg}`,
+			);
+		else
+			console.warn(
+				`[STREAM] ${provider} | ${model} | blocked pipe: ${shortMsg} [${status}]`,
+			);
 		streamController?.handleError?.(new Error(`upstream non-SSE: ${status}`));
 		return {
 			success: false,
-      response: new Response(JSON.stringify({ error: { message: `[${status}]: ${shortMsg}` } }), {
+			response: new Response(
+				JSON.stringify({ error: { message: `[${status}]: ${shortMsg}` } }),
+				{
 					status,
-        headers: { 'Content-Type': 'application/json', 'Access-Control-Allow-Origin': '*' },
-      }),
+					headers: {
+						"Content-Type": "application/json",
+						"Access-Control-Allow-Origin": "*",
+					},
+				},
+			),
 		};
 	}
 
-  const transformStream = buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, customToolNames, model, connectionId, body, onStreamComplete, apiKey });
+	const transformStream = buildTransformStream({
+		provider,
+		sourceFormat,
+		targetFormat,
+		userAgent,
+		reqLogger,
+		toolNameMap,
+		model,
+		connectionId,
+		body,
+		onStreamComplete,
+		apiKey,
+	});
 
 	// Responses passthrough: synthesize response.failed + [DONE] if the stream aborts/stalls before a terminal event
-  const isResponsesPassthrough = sourceFormat === FORMATS.OPENAI_RESPONSES && targetFormat === FORMATS.OPENAI_RESPONSES;
-  const onAbortTerminal = isResponsesPassthrough ? buildAbortedResponsesTerminalBytes : null;
-  const stallTimeoutMs = PROVIDERS[provider]?.stallTimeoutMs || STREAM_STALL_TIMEOUT_MS;
-  const transformedBody = pipeWithDisconnect(providerResponse, transformStream, streamController, onAbortTerminal, stallTimeoutMs);
+	const isResponsesPassthrough =
+		sourceFormat === FORMATS.OPENAI_RESPONSES &&
+		targetFormat === FORMATS.OPENAI_RESPONSES;
+	const onAbortTerminal = isResponsesPassthrough
+		? buildAbortedResponsesTerminalBytes
+		: null;
+	const stallTimeoutMs =
+		PROVIDERS[provider]?.stallTimeoutMs || STREAM_STALL_TIMEOUT_MS;
+	const transformedBody = pipeWithDisconnect(
+		providerResponse,
+		transformStream,
+		streamController,
+		onAbortTerminal,
+		stallTimeoutMs,
+	);
 
-  saveRequestDetail(buildRequestDetail({
-    provider, model, connectionId,
+	saveRequestDetail(
+		buildRequestDetail(
+			{
+				provider,
+				model,
+				connectionId,
 				latency: { ttft: 0, total: Date.now() - requestStartTime },
 				tokens: { prompt_tokens: 0, completion_tokens: 0 },
 				request: extractRequestConfig(body, stream),
 				providerRequest: finalBody || translatedBody || null,
 				providerResponse: "[Streaming - raw response not captured]",
-    response: { content: "[Streaming in progress...]", thinking: null, type: "streaming" },
+				response: {
+					content: "[Streaming in progress...]",
+					thinking: null,
+					type: "streaming",
+				},
 				pxpipe,
-    status: "success"
-  }, { id: streamDetailId })).catch(err => {
-    console.error("[RequestDetail] Failed to save streaming request:", err.message);
+				status: "success",
+			},
+			{ id: streamDetailId },
+		),
+	).catch((err) => {
+		console.error(
+			"[RequestDetail] Failed to save streaming request:",
+			err.message,
+		);
 	});
 
 	return {
 		success: true,
-    response: new Response(transformedBody, { headers: SSE_HEADERS })
+		response: new Response(transformedBody, { headers: SSE_HEADERS }),
 	};
 }
 
 /**
  * Build onStreamComplete callback for streaming usage tracking.
  */
-export function buildOnStreamComplete({ provider, model, connectionId, apiKey, requestStartTime, body, stream, finalBody, translatedBody, clientRawRequest, pxpipe, reqTag, log }) {
+export function buildOnStreamComplete({
+	provider,
+	model,
+	connectionId,
+	apiKey,
+	requestStartTime,
+	body,
+	stream,
+	finalBody,
+	translatedBody,
+	clientRawRequest,
+	pxpipe,
+	reqTag,
+	log,
+	streamErrorPatterns,
+}) {
 	const streamDetailId = `${Date.now()}-${Math.random().toString(36).slice(2, 11)}`;
 
 	const onStreamComplete = (contentObj, usage, ttftAt) => {
 		const latency = {
 			ttft: ttftAt ? ttftAt - requestStartTime : Date.now() - requestStartTime,
-      total: Date.now() - requestStartTime
+			total: Date.now() - requestStartTime,
 		};
 		const safeContent = contentObj?.content || "[Empty streaming response]";
 		const safeThinking = contentObj?.thinking || null;
 
-    saveRequestDetail(buildRequestDetail({
-      provider, model, connectionId,
+		saveRequestDetail(
+			buildRequestDetail(
+				{
+					provider,
+					model,
+					connectionId,
 					latency,
 					tokens: usage || { prompt_tokens: 0, completion_tokens: 0 },
 					request: extractRequestConfig(body, stream),
 					providerRequest: finalBody || translatedBody || null,
 					providerResponse: safeContent,
-      response: { content: safeContent, thinking: safeThinking, type: "streaming" },
+					response: {
+						content: safeContent,
+						thinking: safeThinking,
+						type: "streaming",
+					},
 					pxpipe,
-      status: "success"
-    }, { id: streamDetailId })).catch(err => {
-      console.error("[RequestDetail] Failed to update streaming content:", err.message);
+					status: streamStatusForContent(
+						streamErrorPatterns?.[provider],
+						safeContent,
+					),
+				},
+				{ id: streamDetailId },
+			),
+		).catch((err) => {
+			console.error(
+				"[RequestDetail] Failed to update streaming content:",
+				err.message,
+			);
 		});
 
 		// Persist stream usage to DB (no console line; the "📊 done" line below is authoritative)
-    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, label: "STREAM USAGE", silent: true });
+		saveUsageStats({
+			provider,
+			model,
+			tokens: usage,
+			connectionId,
+			apiKey,
+			endpoint: clientRawRequest?.endpoint,
+			label: "STREAM USAGE",
+			silent: true,
+		});
 		if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency }));
 	};
 

open-sse/handlers/embeddingProviders/index.js

@@ -2,7 +2,6 @@
 import createOpenAIEmbeddingAdapter from "./openai.js";
 import gemini from "./gemini.js";
 import openaiCompatNode from "./openaiCompatNode.js";
-import selfhostedEmbedding from "./selfhostedEmbedding.js";
 
 const OPENAI_COMPAT_PROVIDERS = [
   "openai", "openrouter", "mistral", "voyage-ai", "fireworks",
@@ -14,12 +13,6 @@ const ADAPTERS = {
   ...Object.fromEntries(OPENAI_COMPAT_PROVIDERS.map((id) => [id, createOpenAIEmbeddingAdapter(id)])),
   gemini,
   google_ai_studio: gemini,
-  // Self-hosted reads creds.providerSpecificData.baseUrl (one provider, many
-  // servers) — but via its OWN adapter, not openaiCompatNode: that one falls back
-  // to api.openai.com when no baseUrl is set, which under a provider called
-  // "Self-hosted Embedding" means silently shipping the input and API key to
-  // OpenAI. selfhostedEmbedding refuses instead.
-  "selfhosted-embedding": selfhostedEmbedding,
 };
 
 export function getEmbeddingAdapter(provider) {

open-sse/handlers/embeddingProviders/selfhostedEmbedding.js

@@ -1,46 +0,0 @@
-// Self-hosted embeddings — like openaiCompatNode, but the baseUrl is REQUIRED.
-//
-// openaiCompatNode falls back to https://api.openai.com/v1 when a connection
-// carries no providerSpecificData.baseUrl. For a custom NODE that default is
-// defensible: the node was created by pointing at some OpenAI-compatible URL, and
-// OpenAI is the archetype. For a provider whose entire purpose is "my own
-// server", it is actively harmful — a connection saved without a baseUrl sends
-// the INPUT TEXT and the API KEY to OpenAI, silently, under a provider named
-// "Self-hosted Embedding".
-//
-// Observed exactly that with a placeholder connection (2026-08-04):
-//
-//   [selfhosted-embedding/embedding] [401]: Incorrect API key provided: abc.
-//   You can find your API key at https://platform.openai.com/account/api-keys.
-//
-// The key "abc" was typed as a throwaway for a LOCAL server and left the network.
-// A self-hosted provider must never have a cloud fallback, so this one refuses
-// instead: no baseUrl means a configuration error, reported as such.
-import createOpenAIEmbeddingAdapter from "./openai.js";
-
-const baseAdapter = createOpenAIEmbeddingAdapter("openai");
-
-export class MissingBaseUrlError extends Error {
-  constructor() {
-    super(
-      "Self-hosted Embedding needs an endpoint: set this connection's baseUrl to " +
-        "the OpenAI base URL of your server, e.g. http://host:8080/v1 (note the /v1 — " +
-        "\"/embeddings\" is appended to it). Refusing to fall back to api.openai.com, " +
-        "which would send your input and API key to OpenAI."
-    );
-    this.name = "MissingBaseUrlError";
-    this.isConfigError = true;
-  }
-}
-
-export default {
-  ...baseAdapter,
-  buildUrl: (_model, creds) => {
-    const rawBaseUrl = creds?.providerSpecificData?.baseUrl;
-    if (!rawBaseUrl || !String(rawBaseUrl).trim()) throw new MissingBaseUrlError();
-    // Accept either the OpenAI base or a full embeddings URL, so a value pasted
-    // from a curl example works as well as one typed from the help text.
-    const baseUrl = String(rawBaseUrl).trim().replace(/\/$/, "").replace(/\/embeddings$/, "");
-    return `${baseUrl}/embeddings`;
-  },
-};

open-sse/handlers/embeddingsCore.js

@@ -1,5 +1,5 @@
 import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
-import { HTTP_STATUS, FETCH_CONNECT_TIMEOUT_MS } from "../config/runtimeConfig.js";
+import { HTTP_STATUS } from "../config/runtimeConfig.js";
 import { getExecutor } from "../executors/index.js";
 import { refreshWithRetry } from "../services/tokenRefresh.js";
 import { getEmbeddingAdapter } from "./embeddingProviders/index.js";
@@ -38,24 +38,13 @@ export async function handleEmbeddingsCore({
   }
 
   const ctx = { input };
-  // buildUrl/buildHeaders/buildBody were called bare. An adapter that rejects a
-  // misconfigured connection — selfhosted-embedding throws when no baseUrl is set
-  // rather than silently falling back to api.openai.com — would have escaped this
-  // function uncaught, surfacing as a 500 or a request that never settles. A
-  // configuration mistake is a 400 with the reason in it.
-  let url, headers, requestBody;
-  try {
-    url = adapter.buildUrl(model, credentials, ctx);
-    headers = adapter.buildHeaders(credentials, ctx);
-    requestBody = adapter.buildBody(model, {
+  const url = adapter.buildUrl(model, credentials, ctx);
+  const headers = adapter.buildHeaders(credentials, ctx);
+  const requestBody = adapter.buildBody(model, {
     input,
     encoding_format: body.encoding_format || "float",
     dimensions: body.dimensions,
   });
-  } catch (error) {
-    log?.debug?.("EMBEDDINGS", `Request build failed: ${error.message}`);
-    return createErrorResult(HTTP_STATUS.BAD_REQUEST, `[${provider}/${model}] ${error.message}`);
-  }
 
   log?.debug?.("EMBEDDINGS", `${provider.toUpperCase()} | ${model} | input_type=${Array.isArray(input) ? `array[${input.length}]` : "string"}`);
 
@@ -65,9 +54,6 @@ export async function handleEmbeddingsCore({
       method: "POST",
       headers,
       body: JSON.stringify(requestBody),
-      ...(typeof AbortSignal?.timeout === "function"
-        ? { signal: AbortSignal.timeout(FETCH_CONNECT_TIMEOUT_MS) }
-        : {}),
     });
   } catch (error) {
     const errMsg = formatProviderError(error, provider, model, HTTP_STATUS.BAD_GATEWAY);

open-sse/handlers/imageGenerationCore.js

@@ -96,7 +96,7 @@ export async function handleImageGenerationCore({
   let requestBody;
 
   try {
-    url = adapter.buildUrl(model, credentials);
+    url = adapter.buildUrl(model, credentials, body);
     requestBody = await adapter.buildBody(model, body);
     headers = adapter.buildHeaders(credentials, requestBody, model, body);
   } catch (error) {
@@ -140,7 +140,7 @@ export async function handleImageGenerationCore({
       try {
         const retryBody = await adapter.buildBody(model, body);
         const retryHeaders = adapter.buildHeaders(credentials, retryBody, model, body);
-        const retryUrl = adapter.buildUrl(model, credentials);
+        const retryUrl = adapter.buildUrl(model, credentials, body);
         providerResponse = await fetch(retryUrl, {
           method: "POST",
           headers: retryHeaders,

open-sse/handlers/imageProviders/index.js

@@ -12,6 +12,7 @@ import blackForestLabs from "./blackForestLabs.js";
 import runwayml from "./runwayml.js";
 import cloudflareAi from "./cloudflareAi.js";
 import antigravity from "./antigravity.js";
+import xai from "./xai.js";
 
 const ADAPTERS = {
   openai: createOpenAIAdapter("openai"),
@@ -19,7 +20,7 @@ const ADAPTERS = {
   openrouter: createOpenAIAdapter("openrouter"),
   recraft: createOpenAIAdapter("recraft"),
   "vercel-ai-gateway": createOpenAIAdapter("vercel-ai-gateway"),
-  xai: createOpenAIAdapter("xai"),
+  xai,
   gemini,
   codex,
   sdwebui,

open-sse/handlers/imageProviders/xai.js

@@ -0,0 +1,137 @@
+// xAI Grok Imagine — text-to-image + single/multi image editing
+// Docs:
+//   https://docs.x.ai/developers/model-capabilities/images/generation
+//   https://docs.x.ai/developers/model-capabilities/images/editing
+//   https://docs.x.ai/developers/model-capabilities/images/multi-image-editing
+import { sizeToAspectRatio } from "./_base.js";
+import { PROVIDER_MEDIA } from "../../providers/index.js";
+
+const IMG_CFG = PROVIDER_MEDIA["xai"]?.imageConfig || {};
+const GENERATIONS_URL = IMG_CFG.baseUrl || "https://api.x.ai/v1/images/generations";
+const EDITS_URL = IMG_CFG.editsUrl || "https://api.x.ai/v1/images/edits";
+
+const ASPECT_RATIOS = new Set([
+  "auto",
+  "1:1",
+  "16:9",
+  "9:16",
+  "4:3",
+  "3:2",
+  "2:3",
+  "9:19.5",
+  "20:9",
+]);
+
+function hasEditInput(body) {
+  if (!body || typeof body !== "object") return false;
+  if (body.image) return true;
+  return Array.isArray(body.images) && body.images.some(Boolean);
+}
+
+/** Normalize client image input → xAI image ref object */
+function toXaiImageRef(input) {
+  if (!input) return null;
+
+  if (typeof input === "object") {
+    // Already xAI-shaped or partial
+    if (input.file_id) {
+      return {
+        type: input.type || "image_url",
+        file_id: input.file_id,
+        ...(input.url ? { url: input.url } : {}),
+      };
+    }
+    if (input.url) {
+      return { type: input.type || "image_url", url: input.url };
+    }
+    return null;
+  }
+
+  if (typeof input !== "string") return null;
+  const trimmed = input.trim();
+  if (!trimmed) return null;
+
+  // Public URL or data URI
+  if (/^https?:\/\//i.test(trimmed) || /^data:image\//i.test(trimmed)) {
+    return { type: "image_url", url: trimmed };
+  }
+
+  // Raw base64 → data URI
+  return { type: "image_url", url: `data:image/png;base64,${trimmed}` };
+}
+
+function collectImageRefs(body) {
+  const refs = [];
+  if (Array.isArray(body.images)) {
+    for (const item of body.images) {
+      const ref = toXaiImageRef(item);
+      if (ref) refs.push(ref);
+    }
+  }
+  if (body.image) {
+    const ref = toXaiImageRef(body.image);
+    if (ref) refs.push(ref);
+  }
+  // xAI multi-edit supports up to 3 source images
+  return refs.slice(0, 3);
+}
+
+function resolveAspectRatio(body) {
+  if (typeof body.aspect_ratio === "string" && body.aspect_ratio.trim()) {
+    const ratio = body.aspect_ratio.trim();
+    if (ASPECT_RATIOS.has(ratio)) return ratio;
+    // Pass through unknown ratio strings (upstream will validate)
+    return ratio;
+  }
+  // OpenAI-style size → aspect ratio (skip auto)
+  if (body.size && body.size !== "auto") {
+    return sizeToAspectRatio(body.size);
+  }
+  return undefined;
+}
+
+function resolveResolution(body) {
+  if (typeof body.resolution !== "string") return undefined;
+  const value = body.resolution.trim().toLowerCase();
+  if (!value || value === "auto") return undefined;
+  return value; // "1k" | "2k"
+}
+
+export default {
+  buildUrl: (_model, _credentials, body) => (hasEditInput(body) ? EDITS_URL : GENERATIONS_URL),
+
+  buildHeaders: (creds) => {
+    const headers = { "Content-Type": "application/json", ...(IMG_CFG.headers || {}) };
+    const key = creds?.apiKey || creds?.accessToken;
+    if (key) headers["Authorization"] = `Bearer ${key}`;
+    return headers;
+  },
+
+  buildBody: (model, body) => {
+    const req = {
+      model,
+      prompt: body.prompt,
+    };
+
+    if (body.n != null) req.n = body.n;
+    if (body.response_format) req.response_format = body.response_format;
+
+    const aspectRatio = resolveAspectRatio(body);
+    if (aspectRatio) req.aspect_ratio = aspectRatio;
+
+    const resolution = resolveResolution(body);
+    if (resolution) req.resolution = resolution;
+
+    const refs = collectImageRefs(body);
+    if (refs.length === 1) {
+      req.image = refs[0];
+    } else if (refs.length > 1) {
+      req.images = refs;
+    }
+
+    return req;
+  },
+
+  // xAI already returns OpenAI-compatible { created, data: [{ url | b64_json }] }
+  normalize: (responseBody) => responseBody,
+};

open-sse/handlers/search/callers.js

@@ -29,8 +29,6 @@
  * @property {Record<string,unknown>} [providerSpecificData]
  */
 
-import { assertPublicUrl } from "../../../src/shared/utils/ssrfGuard.js";
-
 // ── Helpers ─────────────────────────────────────────────────────────────
 
 /**
@@ -65,31 +63,12 @@ export function getProviderSetting(params, key) {
 
 /**
  * Resolve base URL with optional override from providerOptions.baseUrl.
- *
- * The override is client-controlled and therefore SSRF-hardened: only public
- * http(s) URLs are accepted (internal/private/loopback/metadata addresses are
- * rejected via assertPublicUrl). The provider's own configured baseUrl is
- * trusted as-is (admin-controlled).
- *
  * @param {SearchProviderConfig} config
  * @param {SearchRequestParams} params
  * @returns {string}
  */
 export function resolveBaseUrl(config, params) {
   const override = getProviderSetting(params, "baseUrl");
-  if (override) {
-    // SSRF guard: client-supplied base URLs must be public http(s) only.
-    let parsed;
-    try {
-      parsed = new URL(override);
-    } catch {
-      throw new Error(`Invalid baseUrl: ${override}`);
-    }
-    if (parsed.protocol !== "http:" && parsed.protocol !== "https:") {
-      throw new Error(`Invalid baseUrl protocol: ${parsed.protocol}`);
-    }
-    assertPublicUrl(override);
-  }
   return (override || config.baseUrl).replace(/\/+$/, "");
 }
 

open-sse/handlers/sttCore.js

@@ -170,17 +170,9 @@ export async function handleSttCore({ provider, model, formData, credentials, st
   const file = formData.get("file");
   if (!file) return createErrorResult(HTTP_STATUS.BAD_REQUEST, "Missing required field: file");
 
-  let cfg = sttConfig;
+  const cfg = sttConfig;
   if (!cfg) return createErrorResult(HTTP_STATUS.BAD_REQUEST, `Provider '${provider}' does not support STT`);
 
-  // Per-connection endpoint override. Registry entries carry a fixed baseUrl,
-  // which is right for a named cloud service but useless for a self-hosted one
-  // whose address only the operator knows. Opt-in: absent unless the connection
-  // sets it, so cloud providers are untouched. Mirrors the custom embedding
-  // providers, which already resolve baseUrl the same way.
-  const overrideUrl = credentials?.providerSpecificData?.baseUrl;
-  if (overrideUrl) cfg = { ...cfg, baseUrl: String(overrideUrl).replace(/\/+$/, "") };
-
   const token = cfg.authType === "none" ? null : (credentials?.apiKey || credentials?.accessToken);
   if (cfg.authType !== "none" && !token) {
     return createErrorResult(HTTP_STATUS.UNAUTHORIZED, `No credentials for STT provider: ${provider}`);

open-sse/handlers/ttsCore.js

@@ -48,16 +48,16 @@ function createTtsResponse(base64Audio, format, responseFormat) {
  *
  * @returns {Promise<{success, response, status?, error?}>}
  */
-export async function handleTtsCore({ provider, model, input, credentials, responseFormat = "mp3", language, style }) {
+export async function handleTtsCore({ provider, model, input, credentials, responseFormat = "mp3", language }) {
   if (!input?.trim()) {
     return createErrorResult(HTTP_STATUS.BAD_REQUEST, "Missing required field: input");
   }
 
   try {
-    // Special-case adapters (google-tts, edge-tts, local-device, elevenlabs, openai, openrouter, gemini, xiaomi-mimo)
+    // Special-case adapters (google-tts, edge-tts, local-device, elevenlabs, openai, openrouter, gemini)
     const adapter = getTtsAdapter(provider);
     if (adapter) {
-      const result = await adapter.synthesize(input.trim(), model, credentials, responseFormat, { language, style });
+      const result = await adapter.synthesize(input.trim(), model, credentials, responseFormat, { language });
       // Adapter may return a full {success, response} (legacy) or {base64, format}
       if (result.success !== undefined) return result;
       return createTtsResponse(result.base64, result.format, responseFormat);

open-sse/handlers/ttsProviders/genericFormats.js

@@ -51,25 +51,6 @@ async function huggingface({ baseUrl, apiKey, text, modelId }) {
   return responseToBase64(res, "wav");
 }
 
-// Fish Audio: model travels in an HTTP header, the voice is a reference_id, returns binary
-async function fishAudio({ baseUrl, apiKey, text, modelId, voiceId }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: {
-      "Content-Type": "application/json",
-      "Authorization": `Bearer ${apiKey}`,
-      "model": modelId || "s2.1-pro-free",
-    },
-    body: JSON.stringify({
-      text,
-      format: "mp3",
-      ...(voiceId ? { reference_id: voiceId } : {}),
-    }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "mp3");
-}
-
 // Inworld: Basic auth, JSON { audioContent }
 async function inworld({ baseUrl, apiKey, text, modelId, voiceId }) {
   const res = await fetch(baseUrl, {
@@ -185,5 +166,4 @@ export const FORMAT_HANDLERS = {
   tortoise,
   openai: openaiCompat,
   "minimax-tts": minimaxTts,
-  "fish-audio": fishAudio,
 };

open-sse/handlers/ttsProviders/index.js

@@ -6,8 +6,6 @@ import elevenlabs, { fetchElevenLabsVoices } from "./elevenlabs.js";
 import openai from "./openai.js";
 import openrouter from "./openrouter.js";
 import gemini, { fetchGeminiVoices } from "./gemini.js";
-import xiaomiMimo from "./xiaomi-mimo.js";
-import selfhostedTts from "./selfhostedTts.js";
 import { FORMAT_HANDLERS } from "./genericFormats.js";
 import { parseModelVoice } from "./_base.js";
 
@@ -20,8 +18,6 @@ const SPECIAL_ADAPTERS = {
   openai,
   openrouter,
   gemini,
-  "xiaomi-mimo": xiaomiMimo,
-  "selfhosted-tts": selfhostedTts,
 };
 
 export function getTtsAdapter(provider) {

open-sse/handlers/ttsProviders/selfhostedTts.js

@@ -1,69 +0,0 @@
-// Self-hosted OpenAI-compatible TTS — POST {baseUrl}/v1/audio/speech.
-//
-// A SPECIAL_ADAPTER rather than a genericFormats handler on purpose: the generic
-// dispatcher resolves baseUrl from the static registry entry
-// (`synthesizeViaConfig` reads `cfg.baseUrl`) and never looks at the connection,
-// which is exactly the limitation this provider exists to lift.
-import { Buffer } from "node:buffer";
-
-const DEFAULT_BASE_URL = "http://localhost:8880";
-const DEFAULT_MODEL = "kokoro";
-const DEFAULT_VOICE = "af_heart";
-
-export default {
-  async synthesize(text, model, credentials, responseFormat = "mp3") {
-    // Accept either providerSpecificData.baseUrl (how the custom embedding and
-    // STT providers carry it) or a bare credentials.baseUrl (how the OpenAI TTS
-    // adapter does), so a connection configured either way works.
-    const raw = credentials?.providerSpecificData?.baseUrl || credentials?.baseUrl || DEFAULT_BASE_URL;
-    // Tolerate a baseUrl given as the full endpoint or with a trailing /v1 —
-    // both are natural things to paste, and silently double-appending the path
-    // would 404 with nothing pointing at the cause.
-    const base = String(raw)
-      .replace(/\/+$/, "")
-      .replace(/\/v1\/audio\/speech$/, "")
-      .replace(/\/v1$/, "");
-
-    // The provider prefix is already stripped by getModelInfo, so `model` here is
-    // "kokoro" or "kokoro/af_heart" — NOT "selfhosted-tts/...".
-    //
-    // A bare value is the MODEL, not the voice. The OpenAI adapter reads a bare
-    // value as a voice, which is right for a service whose model is fixed
-    // ("tts-1") and whose voice varies — but wrong here, where the model is the
-    // variable part. Treating it as a voice sent voice="kokoro" upstream and
-    // Kokoro answered 400, so `selfhosted-tts/kokoro` — the obvious way to
-    // address this provider — was the one form that did not work (verified
-    // against a live Kokoro through 9router, 2026-08-03).
-    let ttsModel = DEFAULT_MODEL;
-    let voice = DEFAULT_VOICE;
-    if (model) {
-      const parts = String(model).split("/").filter(Boolean);
-      if (parts.length >= 2) {
-        ttsModel = parts[0];
-        voice = parts.slice(1).join("/");
-      } else if (parts.length === 1) {
-        ttsModel = parts[0];
-      }
-    }
-
-    const res = await fetch(`${base}/v1/audio/speech`, {
-      method: "POST",
-      headers: {
-        "Content-Type": "application/json",
-        ...(credentials?.apiKey ? { Authorization: `Bearer ${credentials.apiKey}` } : {}),
-      },
-      body: JSON.stringify({
-        model: ttsModel,
-        voice,
-        input: text,
-        response_format: responseFormat,
-      }),
-    });
-    if (!res.ok) {
-      const err = await res.json().catch(() => ({}));
-      throw new Error(err?.error?.message || `Self-hosted TTS failed: ${res.status}`);
-    }
-    const buf = await res.arrayBuffer();
-    return { base64: Buffer.from(buf).toString("base64"), format: responseFormat };
-  },
-};

open-sse/handlers/ttsProviders/xiaomi-mimo.js

@@ -1,65 +0,0 @@
-// Xiaomi MiMo TTS — via OpenAI-compatible chat completions (non-streaming).
-// Docs: https://mimo.mi.com/docs/zh-CN/quick-start/usage-guide/audio/speech-synthesis-v2.5
-// Message contract: target text in `role: assistant` content, style/voice
-// instructions in `role: user` content. Voice is selected via the top-level
-// `audio.voice` field (NOT embedded in the model name).
-import { parseModelVoice } from "./_base.js";
-
-const DEFAULT_MODEL = "mimo-v2.5-tts";
-const DEFAULT_VOICE = "mimo_default";
-
-export default {
-  synthesize(text, model, credentials, responseFormat, { style, language } = {}) {
-    if (!credentials?.apiKey) throw new Error("xiaomi-mimo API key required");
-    return synthesizeMiMo(text, model, credentials.apiKey, style, language);
-  },
-};
-
-export async function synthesizeMiMo(text, model, apiKey, style, language) {
-  const { modelId, voiceId } = parseModelVoice(model, DEFAULT_MODEL, DEFAULT_VOICE, [DEFAULT_MODEL]);
-
-  // Language and style are soft instructions → prepend as a role:user message.
-  // MiMo auto-detects the spoken language of the text; the hint only nudges it
-  // (e.g. "Speak in English.") and is independent of the chosen voice.
-  const instructions = [];
-  if (language) instructions.push(`Speak in ${language}.`);
-  if (style) instructions.push(style);
-
-  const messages = [{ role: "assistant", content: text }];
-  if (instructions.length) messages.unshift({ role: "user", content: instructions.join(" ") });
-
-  const res = await fetch("https://api.xiaomimimo.com/v1/chat/completions", {
-    method: "POST",
-    headers: {
-      "Content-Type": "application/json",
-      "Authorization": `Bearer ${apiKey}`,
-    },
-    body: JSON.stringify({
-      model: modelId,
-      stream: false,
-      messages,
-      audio: {
-        format: "wav",
-        voice: voiceId || DEFAULT_VOICE,
-      },
-    }),
-  });
-
-  const rawText = await res.text();
-  let data = {};
-  if (rawText) {
-    try { data = JSON.parse(rawText); } catch { data = {}; }
-  }
-
-  if (!res.ok) {
-    throw new Error(data?.error?.message || rawText || `MiMo TTS error (${res.status})`);
-  }
-
-  const audio = data?.choices?.[0]?.message?.audio?.data;
-  if (!audio) throw new Error(data?.error?.message || "MiMo TTS returned no audio");
-
-  return {
-    base64: audio,
-    format: data?.choices?.[0]?.message?.audio?.format || "wav",
-  };
-}

open-sse/index.js

@@ -47,6 +47,7 @@ export {
   refreshAccessToken,
   refreshClaudeOAuthToken,
   refreshGoogleToken,
+  refreshQwenToken,
   refreshCodexToken,
   refreshIflowToken,
   refreshGitHubToken,

open-sse/providers/capabilities.js

@@ -205,7 +205,6 @@ export const PATTERN_CAPABILITIES = [
 
   // ── Gemini (all 2.0+ multimodal + google_search grounding, 1M ctx) ─
   { pattern: "*gemini*image*",  caps: { vision: true, imageOutput: true, contextWindow: 1048576 } },
-  { pattern: "*gemini-3.7*",    caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65536 } },
   { pattern: "*gemini-3*pro*",  caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65535 } },
   { pattern: "*gemini-3*",      caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65536 } },
   { pattern: "*gemini-2.5*",    caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-budget", thinkingRange: { min: 0, max: 24576 }, contextWindow: 1048576, maxOutput: 65536 } },
@@ -280,7 +279,7 @@ export const PATTERN_CAPABILITIES = [
   { pattern: "*minimax*",       caps: { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 131072 } },
 
   // ── Xiaomi MiMo (vision, 1M / 262K ctx) ──────────────────────────
-  { pattern: "*mimo*v2.5*",     caps: { vision: true, audioInput: true, videoInput: true, contextWindow: 1048576, maxOutput: 131072 } },
+  { pattern: "*mimo*v2.5*",     caps: { vision: true, contextWindow: 1048576, maxOutput: 131072 } },
   { pattern: "*mimo*omni*",     caps: { vision: true, audioInput: true, contextWindow: 262144, maxOutput: 131072 } },
   { pattern: "*mimo*",          caps: { vision: true, contextWindow: 262144, maxOutput: 131072 } },
 

open-sse/providers/models/schema.js

@@ -38,11 +38,3 @@ export function modelStrip(model) {
 export function modelTargetFormat(model) {
   return model?.targetFormat || MODEL_DEFAULTS.targetFormat;
 }
-
-// Per-model declared upstream formats (e.g. ["openai", "claude"]). Guards the
-// sourceFormat-matched transport for multi-endpoint providers whose models differ
-// in endpoint support (opencode-go: kimi/glm only do /chat/completions, minimax/qwen
-// also do /messages, deepseek also does /responses).
-export function modelSupportedFormats(model) {
-  return model?.supportedFormats || null;
-}

open-sse/providers/pricing.js

@@ -57,10 +57,6 @@ export const MODEL_PRICING = {
   "o1-mini":                      { input: 3.00,  output: 12.00, cached: 1.50,  reasoning: 18.00,  cache_creation: 3.00  },
 
   // === Gemini ===
-  "gemini-3.7-flash":              { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
-  "gemini-3.7-flash-high":         { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
-  "gemini-3.7-flash-medium":       { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
-  "gemini-3.7-flash-low":          { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
   "gemini-3.6-flash":              { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
   "gemini-3.6-flash-high":         { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
   "gemini-3.6-flash-medium":       { input: 1.50,  output: 7.50,  cached: 0.15,  reasoning: 11.25,  cache_creation: 1.875 },
@@ -145,122 +141,6 @@ export const PROVIDER_PRICING = {
   gh: {
     "gpt-5.3-codex": { input: 1.75, output: 14.00, cached: 0.175, reasoning: 14.00, cache_creation: 1.75 },
   },
-  // TokenRouter — exact rates from https://api.tokenrouter.com/api/pricing ($1/1M tokens).
-  // Ratio→USD: input = model_ratio×2, output = model_ratio×completion_ratio×2.
-  // These override the canonical MODEL_PRICING/PATTERN_PRICING, whose rates often
-  // differ from TokenRouter's reseller pricing.
-  tokenrouter: {
-    "MiniMax-M3": { input: 0.3, output: 1.2, cached: 0.06, reasoning: 1.2 },
-    "anthropic/claude-fable-5": { input: 10, output: 50, cached: 1.0, cache_creation: 12.5, reasoning: 50 },
-    "anthropic/claude-haiku-4.5": { input: 1.0, output: 5.0, cached: 0.1, cache_creation: 1.25, reasoning: 5.0 },
-    "anthropic/claude-opus-4.5": { input: 5.0, output: 25.0, cached: 0.5, cache_creation: 6.25, reasoning: 25.0 },
-    "anthropic/claude-opus-4.6": { input: 5.0, output: 25.0, cached: 0.5, cache_creation: 6.25, reasoning: 25.0 },
-    "anthropic/claude-opus-4.7": { input: 5.0, output: 25.0, cached: 0.5, cache_creation: 6.25, reasoning: 25.0 },
-    "anthropic/claude-opus-4.7-fast": { input: 30, output: 150, cached: 3.0, reasoning: 150 },
-    "anthropic/claude-opus-4.8": { input: 5.0, output: 25.0, cached: 0.5, cache_creation: 6.25, reasoning: 25.0 },
-    "anthropic/claude-opus-4.8-fast": { input: 10, output: 50, cached: 1.0, cache_creation: 12.5, reasoning: 50 },
-    "anthropic/claude-opus-5": { input: 5.0, output: 25.0, cached: 0.5, cache_creation: 6.25, reasoning: 25.0 },
-    "anthropic/claude-opus-5-fast": { input: 10, output: 50, cached: 1.0, cache_creation: 12.5, reasoning: 50 },
-    "anthropic/claude-sonnet-4": { input: 3.0, output: 15.0, cached: 0.3, cache_creation: 3.75, reasoning: 15.0 },
-    "anthropic/claude-sonnet-4.5": { input: 3.0, output: 15.0, cached: 0.3, cache_creation: 3.75, reasoning: 15.0 },
-    "anthropic/claude-sonnet-4.6": { input: 3.0, output: 15.0, cached: 0.3, cache_creation: 3.75, reasoning: 15.0 },
-    "anthropic/claude-sonnet-5": { input: 2, output: 10, cached: 0.2, reasoning: 10 },
-    "claude-opus-4-8-m-aws": { input: 5.0, output: 25.0, cached: 0.5, cache_creation: 6.25, reasoning: 25.0 },
-    "deepseek/deepseek-v3.2": { input: 0.26, output: 0.38, cached: 0.13, reasoning: 0.38 },
-    "deepseek/deepseek-v4-flash": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28 },
-    "deepseek/deepseek-v4-flash-0731": { input: 0.14, output: 0.28, cached: 0.0028, reasoning: 0.28 },
-    "deepseek/deepseek-v4-pro": { input: 0.435, output: 0.87, cached: 0.003625, reasoning: 0.87 },
-    "ex/gpt-5.4": { input: 2.5, output: 15.0, cached: 0.25, reasoning: 15.0 },
-    "google/gemini-2.5-flash-image": { input: 0.3, output: 2.5, reasoning: 2.5 },
-    "google/gemini-3-flash-preview": { input: 0.5, output: 3.0, cached: 0.05, cache_creation: 0.08333, reasoning: 3.0 },
-    "google/gemini-3-pro-image-preview": { input: 2, output: 12, reasoning: 12 },
-    "google/gemini-3.1-flash-image-preview": { input: 0.5, output: 3.0, reasoning: 3.0 },
-    "google/gemini-3.1-flash-lite-image": { input: 0.25, output: 1.5, reasoning: 1.5 },
-    "google/gemini-3.1-pro-preview": { input: 2, output: 12, cached: 0.2, cache_creation: 0.375, reasoning: 12 },
-    "google/gemini-3.5-flash": { input: 1.5, output: 9.0, cached: 0.15, cache_creation: 0.08333, reasoning: 9.0 },
-    "google/gemini-3.5-flash-lite": { input: 0.3, output: 2.5, cached: 0.03, cache_creation: 0.08333, reasoning: 2.5 },
-    "google/gemini-3.6-flash": { input: 1.5, output: 7.5, cached: 0.15, cache_creation: 0.08333, reasoning: 7.5 },
-    "google/gemini-embedding-2": { input: 1.0, output: 6.0, cached: 0.1, reasoning: 6.0 },
-    "google/gemma-4-26b-a4b-it": { input: 0.06, output: 0.33, reasoning: 0.33 },
-    "kling-3.0-turbo": { input: 2.1, output: 2.1, reasoning: 2.1 },
-    "microsoft/mai-image-2.5": { input: 5.0, output: 47.0, reasoning: 47.0 },
-    "minimax/minimax-m2-her": { input: 0.3, output: 1.2, cached: 0.03, reasoning: 1.2 },
-    "minimax/minimax-m2.1": { input: 0.3, output: 1.2, cached: 0.03, reasoning: 1.2 },
-    "minimax/minimax-m2.1-highspeed": { input: 0.6, output: 2.4, cached: 0.06, reasoning: 2.4 },
-    "minimax/minimax-m2.5": { input: 0.3, output: 1.2, cached: 0.03, reasoning: 1.2 },
-    "minimax/minimax-m2.7": { input: 0.3, output: 1.2, cached: 0.06, reasoning: 1.2 },
-    "minimax/minimax-m2.7-highspeed": { input: 0.6, output: 2.4, cached: 0.06, reasoning: 2.4 },
-    "miromind/mirothinker-1-7-deepresearch": { input: 4, output: 25.0, reasoning: 25.0 },
-    "miromind/mirothinker-1-7-deepresearch-mini": { input: 1.25, output: 10.0, reasoning: 10.0 },
-    "mistralai/devstral-2512": { input: 0.4, output: 2.0, cached: 0.04, reasoning: 2.0 },
-    "mistralai/mistral-medium-3-5": { input: 1.5, output: 7.5, reasoning: 7.5 },
-    "mistralai/mistral-small-2603": { input: 0.15, output: 0.6, cached: 0.015, reasoning: 0.6 },
-    "mistralai/voxtral-small-24b-2507": { input: 0.1, output: 0.3, cached: 0.01, reasoning: 0.3 },
-    "moonshotai/kimi-k2.5": { input: 0.6, output: 3.0, cached: 0.1, reasoning: 3.0 },
-    "moonshotai/kimi-k2.6": { input: 0.95, output: 4.0, cached: 0.16, reasoning: 4.0 },
-    "moonshotai/kimi-k2.7-code": { input: 0.9286, output: 3.8571, cached: 0.1857, reasoning: 3.8571 },
-    "moonshotai/kimi-k3": { input: 3.0, output: 15.0, cached: 0.3, reasoning: 15.0 },
-    "nvidia/nemotron-3-super-120b-a12b": { input: 0.3, output: 0.9, cached: 0.1, reasoning: 0.9 },
-    "openai/gpt-4o-mini": { input: 0.15, output: 0.6, cached: 0.075, reasoning: 0.6 },
-    "openai/gpt-5": { input: 1.25, output: 10.0, cached: 0.125, reasoning: 10.0 },
-    "openai/gpt-5-image": { input: 10, output: 40, cached: 2.5, reasoning: 40 },
-    "openai/gpt-5-image-mini": { input: 2.5, output: 8.0, cached: 0.25, reasoning: 8.0 },
-    "openai/gpt-5-mini": { input: 0.25, output: 2.0, cached: 0.025, reasoning: 2.0 },
-    "openai/gpt-5.2": { input: 1.75, output: 14.0, cached: 0.175, reasoning: 14.0 },
-    "openai/gpt-5.3-codex": { input: 1.75, output: 14.0, cached: 0.175, reasoning: 14.0 },
-    "openai/gpt-5.4": { input: 2.5, output: 15.0, cached: 0.25, reasoning: 15.0 },
-    "openai/gpt-5.4-image-2": { input: 8, output: 30.0, cached: 2.0, reasoning: 30.0 },
-    "openai/gpt-5.4-mini": { input: 0.75, output: 4.5, cached: 0.075, reasoning: 4.5 },
-    "openai/gpt-5.4-nano": { input: 0.2, output: 1.25, cached: 0.02, reasoning: 1.25 },
-    "openai/gpt-5.4-pro": { input: 30, output: 180, reasoning: 180 },
-    "openai/gpt-5.5": { input: 5.0, output: 30.0, cached: 0.5, reasoning: 30.0 },
-    "openai/gpt-5.5-pro": { input: 30, output: 180, reasoning: 180 },
-    "openai/gpt-5.6-luna": { input: 0.2, output: 1.2, cached: 0.02, cache_creation: 0.25, reasoning: 1.2 },
-    "openai/gpt-5.6-sol": { input: 5.0, output: 30.0, cached: 0.5, cache_creation: 6.25, reasoning: 30.0 },
-    "openai/gpt-5.6-terra": { input: 2, output: 12, cached: 0.2, cache_creation: 2.5, reasoning: 12 },
-    "openai/gpt-audio": { input: 2.5, output: 10.0, reasoning: 10.0 },
-    "openai/gpt-audio-mini": { input: 0.6, output: 2.4, reasoning: 2.4 },
-    "openai/gpt-oss-120b": { input: 0.039, output: 0.18, reasoning: 0.18 },
-    "qwen/qwen3-coder-next": { input: 0.12, output: 0.75, cached: 0.06, reasoning: 0.75 },
-    "qwen/qwen3.5-122b-a10b": { input: 0.26, output: 2.08, reasoning: 2.08 },
-    "qwen/qwen3.5-35b-a3b": { input: 0.1625, output: 1.3, reasoning: 1.3 },
-    "qwen/qwen3.5-397b-a17b": { input: 0.39, output: 2.34, reasoning: 2.34 },
-    "qwen/qwen3.5-9b": { input: 0.1, output: 0.15, reasoning: 0.15 },
-    "qwen/qwen3.5-flash": { input: 0.1048, output: 0.4194, reasoning: 0.4194 },
-    "qwen/qwen3.5-plus-02-15": { input: 0.26, output: 1.56, reasoning: 1.56 },
-    "qwen/qwen3.6-plus": { input: 0.54, output: 3.21, reasoning: 3.21 },
-    "qwen/qwen3.7-max": { input: 1.25, output: 3.75, cached: 0.25, reasoning: 3.75 },
-    "qwen/qwen3.7-plus": { input: 0.4, output: 1.6, cached: 0.08, reasoning: 1.6 },
-    "qwen/qwen3.8-max": { input: 2, output: 6, cached: 0.25, cache_creation: 2.5, reasoning: 6 },
-    "qwen3.5-omni-plus": { input: 1.0, output: 5.7143, reasoning: 5.7143 },
-    "qwen3.6-flash": { input: 0.171, output: 1.029, cached: 0.017, cache_creation: 0.214, reasoning: 1.029 },
-    "sakana/fugu-ultra": { input: 5.0, output: 30.0, cached: 0.5, reasoning: 30.0 },
-    "seed-2-0-code-preview-260328": { input: 1.0, output: 6.0, cached: 0.2, cache_creation: 0.008333, reasoning: 6.0 },
-    "seed-2-0-lite-260428": { input: 0.5, output: 4.0, cached: 0.1, cache_creation: 0.008333, reasoning: 4.0 },
-    "seed-2-0-mini-260428": { input: 0.2, output: 0.8, cached: 0.04, cache_creation: 0.00833, reasoning: 0.8 },
-    "seed-2-0-pro-260328": { input: 1.0, output: 6.0, cached: 0.2, cache_creation: 0.008333, reasoning: 6.0 },
-    "stepfun/step-3.5-flash": { input: 0.1, output: 0.3, cached: 0.02, reasoning: 0.3 },
-    "stepfun/step-3.7-flash": { input: 0.2, output: 1.15, cached: 0.04, reasoning: 1.15 },
-    "tencent/hy3-preview": { input: 0.066, output: 0.26, cached: 0.029, reasoning: 0.26 },
-    "x-ai/grok-4.1-fast": { input: 0.2, output: 0.5, cached: 0.05, reasoning: 0.5 },
-    "x-ai/grok-4.20-beta": { input: 2, output: 6, cached: 0.2, reasoning: 6 },
-    "x-ai/grok-4.3": { input: 1.25, output: 2.5, cached: 0.2, reasoning: 2.5 },
-    "x-ai/grok-4.5": { input: 2, output: 6, cached: 0.5, reasoning: 6 },
-    "x-ai/grok-build-0.1": { input: 1.0, output: 2.0, cached: 0.2, reasoning: 2.0 },
-    "xiaomi/mimo-v2-flash": { input: 0.1, output: 0.3, cached: 0.01, reasoning: 0.3 },
-    "xiaomi/mimo-v2-omni": { input: 0.4, output: 2.0, cached: 0.08, reasoning: 2.0 },
-    "xiaomi/mimo-v2-pro": { input: 1.0, output: 3.0, cached: 0.2, reasoning: 3.0 },
-    "xiaomi/mimo-v2.5": { input: 0.4, output: 2.0, cached: 0.08, reasoning: 2.0 },
-    "xiaomi/mimo-v2.5-pro": { input: 1.0, output: 3.0, cached: 0.2, reasoning: 3.0 },
-    "z-ai/glm-4.5-air": { input: 0.13, output: 0.85, cached: 0.025, reasoning: 0.85 },
-    "z-ai/glm-4.6": { input: 0.6, output: 2.2, cached: 0.11, reasoning: 2.2 },
-    "z-ai/glm-4.6v": { input: 0.3, output: 0.9, reasoning: 0.9 },
-    "z-ai/glm-4.7": { input: 0.6, output: 2.2, cached: 0.11, reasoning: 2.2 },
-    "z-ai/glm-5": { input: 1.0, output: 3.2, cached: 0.2, reasoning: 3.2 },
-    "z-ai/glm-5-turbo": { input: 1.2, output: 4.0, cached: 0.24, reasoning: 4.0 },
-    "z-ai/glm-5.1": { input: 1.05, output: 3.5, cached: 0.525, reasoning: 3.5 },
-    "z-ai/glm-5.2": { input: 1.4, output: 4.4, cached: 0.26, reasoning: 4.4 },
-  },
 };
 
 /**

open-sse/providers/registry/alitp-intl.js

@@ -1,35 +0,0 @@
-// Token Plan — credit subscription keys on token-plan.<region>.maas.aliyuncs.com.
-// Fourth Alibaba key type: Coding Plan (alicode/alicode-intl) and Model Studio
-// (alims-intl) both reject these keys, and they reject Model Studio keys back.
-// Singapore is the only region that serves the plan; eu-central-1 answers
-// IllegalEndpoint. The Anthropic surface (/apps/anthropic/v1/messages) is not
-// authorized for this plan, so OpenAI-compatible mode is the only transport.
-export default {
-  id: "alitp-intl",
-  priority: 11,
-  alias: "alitp-intl",
-  display: {
-    name: "Alibaba Token Plan",
-    icon: "cloud",
-    color: "#FF6A00",
-    textIcon: "ATP",
-    website: "https://www.alibabacloud.com/campaign/ai-landing-page-token",
-    notice: {
-      apiKeyUrl: "https://modelstudio.console.alibabacloud.com/?apiKey=1",
-    },
-  },
-  category: "apikey",
-  transport: {
-    baseUrl: "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
-    headers: {},
-    quirks: { preserveCacheControl: true },
-  },
-  models: [
-    { id: "qwen3.8-max-preview", name: "Qwen3.8 Max Preview" },
-    { id: "qwen3.7-max", name: "Qwen3.7 Max" },
-    { id: "qwen3.7-plus", name: "Qwen3.7 Plus" },
-    { id: "qwen3.6-flash", name: "Qwen3.6 Flash" },
-    { id: "glm-5.2", name: "GLM 5.2" },
-    { id: "deepseek-v4-pro", name: "DeepSeek V4 Pro" },
-  ],
-};

open-sse/providers/registry/antigravity.js

@@ -45,9 +45,6 @@ export default {
     clientSecret: "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",
   },
   models: [
-    { id: "gemini-3.7-flash-high", name: "Gemini 3.7 Flash (High)", upstreamModelId: "gemini-3.7-flash-tiered(high)" },
-    { id: "gemini-3.7-flash-medium", name: "Gemini 3.7 Flash (Medium)", upstreamModelId: "gemini-3.7-flash-tiered(medium)" },
-    { id: "gemini-3.7-flash-low", name: "Gemini 3.7 Flash (Low)", upstreamModelId: "gemini-3.7-flash-tiered(low)" },
     { id: "gemini-3.6-flash-high", name: "Gemini 3.6 Flash (High)", upstreamModelId: "gemini-3.6-flash-tiered(high)" },
     { id: "gemini-3.6-flash-medium", name: "Gemini 3.6 Flash (Medium)", upstreamModelId: "gemini-3.6-flash-tiered(medium)" },
     { id: "gemini-3.6-flash-low", name: "Gemini 3.6 Flash (Low)", upstreamModelId: "gemini-3.6-flash-tiered(low)" },
@@ -79,7 +76,8 @@ export default {
     apiVersion: "v1internal",
     loadCodeAssistEndpoint: "https://cloudcode-pa.googleapis.com/v1internal:loadCodeAssist",
     onboardUserEndpoint: "https://cloudcode-pa.googleapis.com/v1internal:onboardUser",
-    loadCodeAssistUserAgent: ANTIGRAVITY_IDE_USER_AGENT,
+    loadCodeAssistUserAgent: "google-api-nodejs-client/9.15.1",
+    loadCodeAssistApiClient: "google-cloud-sdk vscode_cloudshelleditor/0.1",
     refreshLeadMs: 300000,
   },
   features: {

open-sse/providers/registry/claude.js

@@ -49,6 +49,9 @@ export default {
         header: "Authorization",
         scheme: "bearer",
       },
+      hooks: [
+        "claudeOverlay",
+      ],
     },
     usage: {
       oauthUrl: "https://api.anthropic.com/api/oauth/usage",

open-sse/providers/registry/cloudflare-ai.js

@@ -19,8 +19,6 @@ export default {
     },
   },
   category: "freeTier",
-  authType: "apikey",
-  authModes: ["apikey"],
   hasProviderSpecificData: true,
   transport: {
     baseUrl: "https://api.cloudflare.com/client/v4/accounts/{accountId}/ai/v1/chat/completions",

open-sse/providers/registry/codebuddy-intl.js

@@ -38,10 +38,6 @@ export default {
       header: "Authorization",
       scheme: "bearer",
     },
-    // Intl billing endpoint mirrors CN shape (data.Response.Data.Accounts[]).
-    usage: {
-      url: "https://www.codebuddy.ai/v2/billing/meter/get-user-resource",
-    },
   },
   // Same model lineup exposed by the CN gateway — intl backend is the same catalog.
   models: [

open-sse/providers/registry/commandcode.js

@@ -23,9 +23,24 @@ export default {
     format: "commandcode",
     forceStream: true,
     headers: {
-      "x-command-code-version": "0.25.7",
+      "x-command-code-version": "1.10.0",
       "x-cli-environment": "cli",
+      "User-Agent": "cli",
     },
+    // Quota/billing endpoints (same alpha API the official CLI /usage calls).
+    // whoami resolves orgId; credits+subscription+usage/summary then report the
+    // 5-hour/weekly windows, plan, and period credits. See services/usage/commandcode.js.
+    usage: {
+      baseUrl: "https://api.commandcode.ai",
+      whoamiUrl: "/alpha/whoami",
+      creditsUrl: "/alpha/billing/credits",
+      subscriptionsUrl: "/alpha/billing/subscriptions",
+      summaryUrl: "/alpha/usage/summary",
+    },
+  },
+  features: {
+    usage: true,
+    usageApikey: true,
   },
   models: [
     { id: "deepseek/deepseek-v4-pro", name: "DeepSeek V4 Pro" },

open-sse/providers/registry/fish-audio.js

@@ -1,31 +0,0 @@
-// Fish Audio TTS — the model id travels in an HTTP `model` header rather than the
-// JSON body, and the voice is a reference_id (a cloned or preset voice model).
-export default {
-  id: "fish-audio",
-  alias: "fish",
-  display: {
-    name: "Fish Audio",
-    icon: "record_voice_over",
-    color: "#1E9BF0",
-    textIcon: "FA",
-    website: "https://fish.audio",
-    notice: {
-      apiKeyUrl: "https://fish.audio/app/api-keys/",
-    },
-  },
-  category: "apikey",
-  authType: "apikey",
-  serviceKinds: ["tts"],
-  ttsConfig: {
-    baseUrl: "https://api.fish.audio/v1/tts",
-    authType: "apikey",
-    authHeader: "bearer",
-    format: "fish-audio",
-    models: [
-      { id: "s2.1-pro-free", name: "S2.1 Pro Free" },
-      { id: "s2.1-pro", name: "S2.1 Pro" },
-      { id: "s2-pro", name: "S2 Pro" },
-      { id: "s1", name: "S1" },
-    ],
-  },
-};

open-sse/providers/registry/gemini.js

@@ -36,7 +36,6 @@ export default {
     },
   },
   models: [
-    { id: "gemini-3.7-flash", name: "Gemini 3.7 Flash" },
     { id: "gemini-3.6-flash", name: "Gemini 3.6 Flash" },
     { id: "gemini-3.5-flash-lite", name: "Gemini 3.5 Flash Lite" },
     { id: "gemini-3.1-pro-preview", name: "Gemini 3.1 Pro Preview" },

open-sse/providers/registry/glm-cn.js

@@ -21,7 +21,6 @@ export default {
     },
   },
   models: [
-    { id: "glm-5.3", name: "GLM 5.3" },
     { id: "glm-5.2", name: "GLM 5.2" },
     { id: "glm-5.1", name: "GLM 5.1" },
     { id: "glm-5", name: "GLM 5" },

open-sse/providers/registry/glm.js

@@ -45,7 +45,6 @@ export default {
     },
   ],
   models: [
-    { id: "glm-5.3", name: "GLM 5.3" },
     { id: "glm-5.2", name: "GLM 5.2" },
     { id: "glm-5.1", name: "GLM 5.1" },
     { id: "glm-5", name: "GLM 5" },

open-sse/providers/registry/index.js

@@ -75,6 +75,7 @@ import p72 from "./perplexity.js";
 import p73 from "./perplexity-agent.js";
 import p74 from "./playht.js";
 import p75 from "./qoder.js";
+import p76 from "./qwen.js";
 import p77 from "./recraft.js";
 import p78 from "./runwayml.js";
 import p79 from "./sdwebui.js";
@@ -115,12 +116,6 @@ import p113 from "./morph.js";
 // import p114 from "./devin-cli.js";
 // import p104 from "./windsurf.js";
 import p115 from "./poolside.js";
-import p116 from "./tokenrouter.js";
-import p117 from "./selfhosted-stt.js";
-import p118 from "./selfhosted-tts.js";
-import p119 from "./selfhosted-embedding.js";
-import p120 from "./fish-audio.js";
-import p121 from "./alitp-intl.js";
 
 export default [
   p0,
@@ -199,6 +194,7 @@ export default [
   p73,
   p74,
   p75,
+  p76,
   p77,
   p78,
   p79,
@@ -237,10 +233,4 @@ export default [
   // p114, // devin-cli — hidden, spawns local agent with shell/fs access
   // p104, // windsurf — hidden, no tool calling
   p115,
-  p116,
-  p117,
-  p118,
-  p119,
-  p120,
-  p121,
 ];

open-sse/providers/registry/kimchi.js

@@ -14,7 +14,7 @@ export default {
     },
   },
   category: "freeTier",
-  authModes: ["oauth", "apikey"],
+  authModes: ["oauth"],
   hasOAuth: true,
   transport: {
     baseUrl: "https://llm.kimchi.dev/openai/v1/chat/completions",

open-sse/providers/registry/ollama.js

@@ -15,8 +15,6 @@ export default {
     },
   },
   category: "freeTier",
-  authType: "apikey",
-  authModes: ["apikey"],
   transport: {
     baseUrl: "https://ollama.com/api/chat",
     validateUrl: "https://ollama.com/api/tags",
@@ -34,6 +32,5 @@ export default {
   serviceKinds: ["llm"],
   features: {
     usage: true,
-    usageApikey: true,
   },
 };

open-sse/providers/registry/opencode-go.js

@@ -22,28 +22,20 @@ export default {
     baseUrl: "https://opencode.ai/zen/go/v1/chat/completions",
     headers: {},
   },
-  // Multi-endpoint: pick the transport matching the client sourceFormat to skip
-  // translation. Guarded per-model by `supportedFormats` (see chatCore) because
-  // opencode-go models differ in endpoint support.
-  transports: [
-    { format: "openai", baseUrl: "https://opencode.ai/zen/go/v1/chat/completions", auth: { combined: true, header: "Authorization", scheme: "bearer" } },
-    { format: "claude", baseUrl: "https://opencode.ai/zen/go/v1/messages", auth: { combined: true, header: "x-api-key", scheme: "raw", anthropicVersion: true } },
-    { format: "openai-responses", baseUrl: "https://opencode.ai/zen/go/v1/responses", auth: { combined: true, header: "Authorization", scheme: "bearer" } },
-  ],
   models: [
-    { id: "glm-5.2", name: "GLM 5.2", supportedFormats: ["openai"] },
-    { id: "glm-5.1", name: "GLM 5.1", supportedFormats: ["openai"] },
-    { id: "kimi-k2.7-code", name: "Kimi K2.7 Code", supportedFormats: ["openai"] },
-    { id: "kimi-k2.6", name: "Kimi K2.6", supportedFormats: ["openai"] },
-    { id: "deepseek-v4-pro", name: "DeepSeek V4 Pro", supportedFormats: ["openai", "claude", "openai-responses"] },
-    { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash", supportedFormats: ["openai", "claude", "openai-responses"] },
-    { id: "mimo-v2.5", name: "MiMo V2.5", supportedFormats: ["openai"] },
-    { id: "mimo-v2.5-pro", name: "MiMo V2.5 Pro", supportedFormats: ["openai"] },
-    { id: "minimax-m3", name: "MiniMax M3", supportedFormats: ["openai", "claude"] },
-    { id: "minimax-m2.7", name: "MiniMax M2.7", supportedFormats: ["openai", "claude"] },
-    { id: "minimax-m2.5", name: "MiniMax M2.5", supportedFormats: ["openai", "claude"] },
-    { id: "qwen3.7-max", name: "Qwen 3.7 Max", supportedFormats: ["openai", "claude"] },
-    { id: "qwen3.7-plus", name: "Qwen 3.7 Plus", supportedFormats: ["openai", "claude"] },
-    { id: "qwen3.6-plus", name: "Qwen 3.6 Plus", supportedFormats: ["openai", "claude"] },
+    { id: "glm-5.2", name: "GLM 5.2" },
+    { id: "glm-5.1", name: "GLM 5.1" },
+    { id: "kimi-k2.7-code", name: "Kimi K2.7 Code" },
+    { id: "kimi-k2.6", name: "Kimi K2.6" },
+    { id: "deepseek-v4-pro", name: "DeepSeek V4 Pro" },
+    { id: "deepseek-v4-flash", name: "DeepSeek V4 Flash" },
+    { id: "mimo-v2.5", name: "MiMo V2.5" },
+    { id: "mimo-v2.5-pro", name: "MiMo V2.5 Pro" },
+    { id: "minimax-m3", name: "MiniMax M3", targetFormat: "claude" },
+    { id: "minimax-m2.7", name: "MiniMax M2.7", targetFormat: "claude" },
+    { id: "minimax-m2.5", name: "MiniMax M2.5", targetFormat: "claude" },
+    { id: "qwen3.7-max", name: "Qwen 3.7 Max", targetFormat: "claude" },
+    { id: "qwen3.7-plus", name: "Qwen 3.7 Plus", targetFormat: "claude" },
+    { id: "qwen3.6-plus", name: "Qwen 3.6 Plus", targetFormat: "claude" },
   ],
 };

open-sse/providers/registry/qoder.js

@@ -52,7 +52,5 @@ export default {
   },
   features: {
     usage: true,
-    // PAT (apikey) connections also carry quota usage (via job-token exchange).
-    usageApikey: true,
   },
 };

open-sse/providers/registry/qwen.js

@@ -0,0 +1,33 @@
+export default {
+  id: "qwen",
+  hidden: true,
+  priority: 130,
+  alias: "qw",
+  display: {
+    name: "Qwen Code",
+    icon: "psychology",
+    color: "#10B981",
+    website: "https://chat.qwen.ai",
+    notice: {
+      signupUrl: "https://chat.qwen.ai",
+    },
+  },
+  category: "oauth",
+  transport: {
+    baseUrl: "https://portal.qwen.ai/v1/chat/completions",
+  },
+  models: [
+    { id: "qwen3-coder-plus", name: "Qwen3 Coder Plus" },
+    { id: "qwen3-coder-flash", name: "Qwen3 Coder Flash" },
+    { id: "vision-model", name: "Qwen3 Vision Model" },
+    { id: "coder-model", name: "Qwen3.6 Coder Model" },
+  ],
+  oauth: {
+    clientId: "f0304373b74a44d2b584a3fb70ca9e56",
+    deviceCodeUrl: "https://chat.qwen.ai/api/v1/oauth2/device/code",
+    tokenUrl: "https://chat.qwen.ai/api/v1/oauth2/token",
+    scope: "openid profile email model.completion",
+    codeChallengeMethod: "S256",
+    refreshLeadMs: 1200000,
+  },
+};

open-sse/providers/registry/selfhosted-embedding.js

@@ -1,73 +0,0 @@
-// Self-hosted, OpenAI-compatible embeddings (llama.cpp / llama-server, vLLM,
-// Infinity, text-embeddings-inference, ...) — the embeddings counterpart of
-// selfhosted-stt and selfhosted-tts.
-//
-// Routing a self-hosted embeddings server already WORKS today, via a custom
-// provider node: getEmbeddingAdapter() matches `openai-compatible-*` and
-// `custom-embedding-*` and returns openaiCompatNode, whose buildUrl reads
-// creds.providerSpecificData.baseUrl. What is missing is a first-class provider,
-// and the gap is visible rather than functional:
-//
-//   /v1/embeddings on such a node          -> 200, correct vectors
-//   the Embedding page in the dashboard    -> the node is not listed at all
-//
-// The page renders getProvidersByKind("embedding") plus provider nodes filtered
-// to `type === "custom-embedding"`. A node created as `openai-compatible` — the
-// natural choice when ONE endpoint serves chat and embeddings behind the same
-// front door — satisfies neither, so a working self-hosted embeddings endpoint is
-// invisible on the page whose job is to show embeddings providers. Diagnosed on a
-// deployment serving Qwen3-Embedding-8B at 4096 dimensions through exactly that
-// shape (2026-08-04).
-//
-// Declaring it as a provider with serviceKinds: ["embedding"] puts it on the page
-// beside Voyage, Jina and the rest, and keeps the per-connection baseUrl that
-// makes self-hosting possible at all.
-//
-// authType is "apikey" rather than "none" for the same reason as the STT and TTS
-// entries: it is what gives the connection a credentials record, and
-// providerSpecificData.baseUrl lives there. Local servers ignore the key itself;
-// any non-empty value works.
-export default {
-  id: "selfhosted-embedding",
-  priority: 50,
-  hasFree: true,
-  alias: "selfhosted-embedding",
-  display: {
-    name: "Self-hosted Embedding",
-    icon: "cloud",
-    color: "#ffffffff",
-    textIcon: "SE",
-    website: "https://github.com/ggml-org/llama.cpp",
-  },
-  category: "apikey",
-  auth: {
-    apiKey: {
-      // Note the /v1: the adapter appends "/embeddings" to whatever it is given,
-      // so a bare http://host:8080 resolves to http://host:8080/embeddings and
-      // misses the OpenAI route entirely. Give it the OpenAI base, the same value
-      // an OpenAI client would use. A trailing /embeddings is tolerated.
-      text: "Set providerSpecificData.baseUrl to the OpenAI base URL, e.g. http://host:8080/v1 — /embeddings is appended. The API key is not checked by local servers; any value works.",
-    },
-  },
-  // A self-hosted server serves whatever model it was started with, so the id
-  // here is a placeholder for the UI: the request passes `model` straight
-  // through, and llama-server ignores an unknown value rather than rejecting it.
-  // Dimensions are deliberately NOT declared — they are a property of the loaded
-  // weights, and asserting a number here would be a guess that silently
-  // contradicts the server.
-  models: [
-    { id: "embedding", name: "Self-hosted embedding model", kind: "embedding" },
-  ],
-  serviceKinds: ["embedding"],
-  embeddingConfig: {
-    // Declared for shape-consistency with the other embedding providers, and
-    // read by the UI — but NOT by the request path. openaiCompatNode resolves the
-    // URL purely from creds.providerSpecificData.baseUrl (falling back to
-    // api.openai.com), so unlike a fixed cloud provider this baseUrl never
-    // reaches the wire. Stated plainly because a reader would otherwise
-    // reasonably assume it is the default endpoint.
-    baseUrl: "http://localhost:8080/v1/embeddings",
-    authType: "apikey",
-    authHeader: "bearer",
-  },
-};

open-sse/providers/registry/selfhosted-stt.js

@@ -1,48 +0,0 @@
-// Self-hosted, OpenAI-compatible speech-to-text (whisper.cpp, faster-whisper,
-// Speaches, vLLM-served Whisper, ...).
-//
-// Every other STT provider here is a named cloud service with a fixed endpoint.
-// This one exists so a locally-served /v1/audio/transcriptions can be used at
-// all: set the connection's providerSpecificData.baseUrl to the full URL of the
-// endpoint, exactly as the custom embedding providers already work.
-//
-// sttCore dispatches on `format`; anything that is not one of the five named
-// cloud shapes falls through to transcribeOpenAICompatible, which POSTs the
-// standard multipart body (file, model, and optional language / prompt /
-// response_format / temperature). That is precisely what whisper.cpp's OpenAI
-// endpoint accepts.
-//
-// authType is "apikey" rather than "none" so the connection carries a
-// credentials record — which is where providerSpecificData.baseUrl lives. Local
-// servers ignore the key itself; any non-empty value works.
-export default {
-  id: "selfhosted-stt",
-  priority: 50,
-  hasFree: true,
-  alias: "selfhosted-stt",
-  display: {
-    name: "Self-hosted STT",
-    icon: "cloud",
-    color: "#ffffffff",
-    textIcon: "ST",
-    website: "https://github.com/ggml-org/whisper.cpp",
-  },
-  category: "apikey",
-  auth: {
-    apiKey: {
-      text: "Set providerSpecificData.baseUrl to the full transcriptions URL, e.g. http://host:8080/v1/audio/transcriptions. The API key is not checked by local servers; any value works.",
-    },
-  },
-  models: [
-    { id: "whisper-1", name: "Whisper (self-hosted)", params: ["language", "response_format", "temperature", "prompt"], kind: "stt" },
-  ],
-  serviceKinds: ["stt"],
-  sttConfig: {
-    // Overridden per connection by providerSpecificData.baseUrl; this default
-    // only makes the provider usable out of the box on a same-host deployment.
-    baseUrl: "http://localhost:8080/v1/audio/transcriptions",
-    authType: "apikey",
-    authHeader: "bearer",
-    format: "openai",
-  },
-};

open-sse/providers/registry/selfhosted-tts.js

@@ -1,44 +0,0 @@
-// Self-hosted, OpenAI-compatible text-to-speech (Kokoro-FastAPI, openedai-speech,
-// vLLM-served TTS, ...) — the TTS counterpart of selfhosted-stt.
-//
-// Every other self-hostable TTS provider here (coqui, tortoise) carries a FIXED
-// localhost baseUrl in its registry entry and `authType: "none"`, and the generic
-// dispatcher reads `ttsConfig.baseUrl` from that entry rather than from the
-// connection. So there was no way to point TTS at a server on another host.
-//
-// `authType: "apikey"` is what makes the override possible at all: it gives the
-// connection a credentials record, which is where providerSpecificData.baseUrl
-// lives. Local servers ignore the key; any non-empty value works.
-export default {
-  id: "selfhosted-tts",
-  priority: 50,
-  hasFree: true,
-  alias: "selfhosted-tts",
-  display: {
-    name: "Self-hosted TTS",
-    icon: "cloud",
-    color: "#ffffffff",
-    textIcon: "TT",
-    website: "https://github.com/remsky/Kokoro-FastAPI",
-  },
-  category: "apikey",
-  auth: {
-    apiKey: {
-      text: "Set providerSpecificData.baseUrl to the server root, e.g. http://host:8080 — /v1/audio/speech is appended. The API key is not checked by local servers; any value works.",
-    },
-  },
-  // Voice is selected as "<model>/<voice>", the same convention the OpenAI TTS
-  // adapter uses, so existing clients need no special casing.
-  models: [
-    { id: "kokoro", name: "Kokoro (self-hosted)", params: ["voice", "response_format", "speed"], kind: "tts" },
-  ],
-  serviceKinds: ["tts"],
-  ttsConfig: {
-    // Overridden per connection by providerSpecificData.baseUrl; this default
-    // only makes the provider usable on a same-host deployment.
-    baseUrl: "http://localhost:8880",
-    defaultModel: "kokoro",
-    authType: "apikey",
-    format: "openai-speech",
-  },
-};

open-sse/providers/registry/tokenrouter.js

@@ -1,162 +0,0 @@
-export default {
-  id: "tokenrouter",
-  alias: "tokenrouter",
-  aliases: ["tr"],
-  uiAlias: "tokenrouter",
-  display: {
-    name: "TokenRouter",
-    icon: "hub",
-    color: "#0EA5E9",
-    textIcon: "TR",
-    website: "https://www.tokenrouter.com",
-    notice: {
-      text: "OpenAI-compatible gateway. 300+ models (OpenAI, Claude, Gemini, Qwen, DeepSeek, Kimi, GLM, dsb).",
-      apiKeyUrl: "https://www.tokenrouter.com",
-    },
-  },
-  category: "apikey",
-  thinkingConfig: {
-    options: ["low", "medium", "high", "xhigh", "max"],
-    defaultMode: "high",
-  },
-  transport: {
-    baseUrl: "https://api.tokenrouter.com/v1/chat/completions",
-    validateUrl: "https://api.tokenrouter.com/v1/models",
-    thinkingFormat: "tokenrouter",
-  },
-  // Seed snapshot from live /v1/models (120 entries). Latest catalogue is
-  // fetched via modelsFetcher; other ids still accepted via passthroughModels.
-  models: [
-    { id: "MiniMax-Hailuo-2.3", name: "Minimax Hailuo 2.3", kind: "video" },
-    { id: "MiniMax-M3", name: "Minimax M3" },
-    { id: "anthropic/claude-fable-5", name: "Claude Fable 5" },
-    { id: "anthropic/claude-haiku-4.5", name: "Claude Haiku 4.5" },
-    { id: "anthropic/claude-opus-4.5", name: "Claude Opus 4.5" },
-    { id: "anthropic/claude-opus-4.6", name: "Claude Opus 4.6" },
-    { id: "anthropic/claude-opus-4.7", name: "Claude Opus 4.7" },
-    { id: "anthropic/claude-opus-4.7-fast", name: "Claude Opus 4.7 Fast" },
-    { id: "anthropic/claude-opus-4.8", name: "Claude Opus 4.8" },
-    { id: "anthropic/claude-opus-4.8-fast", name: "Claude Opus 4.8 Fast" },
-    { id: "anthropic/claude-opus-5", name: "Claude Opus 5" },
-    { id: "anthropic/claude-opus-5-fast", name: "Claude Opus 5 Fast" },
-    { id: "anthropic/claude-sonnet-4", name: "Claude Sonnet 4" },
-    { id: "anthropic/claude-sonnet-4.5", name: "Claude Sonnet 4.5" },
-    { id: "anthropic/claude-sonnet-4.6", name: "Claude Sonnet 4.6" },
-    { id: "anthropic/claude-sonnet-5", name: "Claude Sonnet 5" },
-    { id: "bytedance-seed/seedream-4.5", name: "Seedream 4.5", kind: "image" },
-    { id: "bytedance-seed/seedream-5.0-lite", name: "Seedream 5.0 Lite", kind: "image" },
-    { id: "bytedance-seed/seedream-5.0-pro", name: "Seedream 5.0 Pro", kind: "image" },
-    { id: "claude-haiku-4-5", name: "Claude Haiku 4 5" },
-    { id: "claude-opus-4-8-m-aws", name: "Claude Opus 4 8 M Aws" },
-    { id: "deepseek/deepseek-v3.2", name: "Deepseek V3.2" },
-    { id: "deepseek/deepseek-v4-flash", name: "Deepseek V4 Flash" },
-    { id: "deepseek/deepseek-v4-flash-0731", name: "Deepseek V4 Flash 0731" },
-    { id: "deepseek/deepseek-v4-pro", name: "Deepseek V4 Pro" },
-    { id: "ex/gpt-5.4", name: "Gpt 5.4" },
-    { id: "google/gemini-2.5-flash-image", name: "Gemini 2.5 Flash Image" },
-    { id: "google/gemini-3-flash-preview", name: "Gemini 3 Flash Preview" },
-    { id: "google/gemini-3-pro-image-preview", name: "Gemini 3 Pro Image Preview" },
-    { id: "google/gemini-3.1-flash-image-preview", name: "Gemini 3.1 Flash Image Preview" },
-    { id: "google/gemini-3.1-flash-lite-image", name: "Gemini 3.1 Flash Lite Image" },
-    { id: "google/gemini-3.1-pro-preview", name: "Gemini 3.1 Pro Preview" },
-    { id: "google/gemini-3.5-flash", name: "Gemini 3.5 Flash" },
-    { id: "google/gemini-3.5-flash-lite", name: "Gemini 3.5 Flash Lite" },
-    { id: "google/gemini-3.6-flash", name: "Gemini 3.6 Flash" },
-    { id: "google/gemini-embedding-2", name: "Gemini Embedding 2" },
-    { id: "google/gemma-4-26b-a4b-it", name: "Gemma 4 26B A4B It" },
-    { id: "happyhorse-1.0-t2v", name: "Happyhorse 1.0 T2V", kind: "video" },
-    { id: "kling-3.0-turbo", name: "Kling 3.0 Turbo", kind: "video" },
-    { id: "kling-v2-6", name: "Kling V2 6", kind: "video" },
-    { id: "kling-v3", name: "Kling V3", kind: "video" },
-    { id: "kling-v3-omni", name: "Kling V3 Omni", kind: "video" },
-    { id: "microsoft/mai-image-2.5", name: "Mai Image 2.5" },
-    { id: "minimax/minimax-m2-her", name: "Minimax M2 Her" },
-    { id: "minimax/minimax-m2.1", name: "Minimax M2.1" },
-    { id: "minimax/minimax-m2.1-highspeed", name: "Minimax M2.1 Highspeed" },
-    { id: "minimax/minimax-m2.5", name: "Minimax M2.5" },
-    { id: "minimax/minimax-m2.7", name: "Minimax M2.7" },
-    { id: "minimax/minimax-m2.7-highspeed", name: "Minimax M2.7 Highspeed" },
-    { id: "miromind/mirothinker-1-7-deepresearch", name: "Mirothinker 1 7 Deepresearch" },
-    { id: "miromind/mirothinker-1-7-deepresearch-mini", name: "Mirothinker 1 7 Deepresearch Mini" },
-    { id: "mistralai/devstral-2512", name: "Devstral 2512" },
-    { id: "mistralai/mistral-medium-3-5", name: "Mistral Medium 3 5" },
-    { id: "mistralai/mistral-small-2603", name: "Mistral Small 2603" },
-    { id: "mistralai/voxtral-small-24b-2507", name: "Voxtral Small 24B 2507" },
-    { id: "moonshotai/kimi-k2.5", name: "Kimi K2.5" },
-    { id: "moonshotai/kimi-k2.6", name: "Kimi K2.6" },
-    { id: "moonshotai/kimi-k2.7-code", name: "Kimi K2.7 Code" },
-    { id: "moonshotai/kimi-k3", name: "Kimi K3" },
-    { id: "moonshotai/kimi-k3-free", name: "Kimi K3 Free" },
-    { id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", name: "Nemotron 3 Nano Omni 30B A3B Reasoning:Free" },
-    { id: "nvidia/nemotron-3-super-120b-a12b", name: "Nemotron 3 Super 120B A12B" },
-    { id: "openai/gpt-4o-mini", name: "Gpt 4O Mini" },
-    { id: "openai/gpt-5", name: "Gpt 5" },
-    { id: "openai/gpt-5-image", name: "Gpt 5 Image" },
-    { id: "openai/gpt-5-image-mini", name: "Gpt 5 Image Mini" },
-    { id: "openai/gpt-5-mini", name: "Gpt 5 Mini" },
-    { id: "openai/gpt-5.2", name: "Gpt 5.2" },
-    { id: "openai/gpt-5.4", name: "Gpt 5.4" },
-    { id: "openai/gpt-5.4-image-2", name: "Gpt 5.4 Image 2", kind: "image" },
-    { id: "openai/gpt-5.4-mini", name: "Gpt 5.4 Mini" },
-    { id: "openai/gpt-5.4-nano", name: "Gpt 5.4 Nano" },
-    { id: "openai/gpt-5.4-pro", name: "Gpt 5.4 Pro" },
-    { id: "openai/gpt-5.5", name: "Gpt 5.5" },
-    { id: "openai/gpt-5.5-pro", name: "Gpt 5.5 Pro" },
-    { id: "openai/gpt-5.6-luna", name: "Gpt 5.6 Luna" },
-    { id: "openai/gpt-5.6-sol", name: "Gpt 5.6 Sol" },
-    { id: "openai/gpt-5.6-terra", name: "Gpt 5.6 Terra" },
-    { id: "openai/gpt-audio", name: "Gpt Audio", kind: "audio" },
-    { id: "openai/gpt-audio-mini", name: "Gpt Audio Mini", kind: "audio" },
-    { id: "openai/gpt-oss-120b", name: "Gpt Oss 120B" },
-    { id: "qwen/qwen3-coder-next", name: "Qwen3 Coder Next" },
-    { id: "qwen/qwen3.5-122b-a10b", name: "Qwen3.5 122B A10B" },
-    { id: "qwen/qwen3.5-35b-a3b", name: "Qwen3.5 35B A3B" },
-    { id: "qwen/qwen3.5-397b-a17b", name: "Qwen3.5 397B A17B" },
-    { id: "qwen/qwen3.5-9b", name: "Qwen3.5 9B" },
-    { id: "qwen/qwen3.5-flash", name: "Qwen3.5 Flash" },
-    { id: "qwen/qwen3.5-plus-02-15", name: "Qwen3.5 Plus 02 15" },
-    { id: "qwen/qwen3.6-plus", name: "Qwen3.6 Plus" },
-    { id: "qwen/qwen3.7-max", name: "Qwen3.7 Max" },
-    { id: "qwen/qwen3.7-plus", name: "Qwen3.7 Plus" },
-    { id: "qwen/qwen3.8-max", name: "Qwen3.8 Max" },
-    { id: "qwen3.5-omni-plus", name: "Qwen3.5 Omni Plus" },
-    { id: "qwen3.6-flash", name: "Qwen3.6 Flash" },
-    { id: "sakana/fugu-ultra", name: "Fugu Ultra" },
-    { id: "seed-2-0-code-preview-260328", name: "Seed 2 0 Code Preview 260328" },
-    { id: "seed-2-0-lite-260428", name: "Seed 2 0 Lite 260428" },
-    { id: "seed-2-0-mini-260428", name: "Seed 2 0 Mini 260428" },
-    { id: "seed-2-0-pro-260328", name: "Seed 2 0 Pro 260328" },
-    { id: "stepfun/step-3.5-flash", name: "Step 3.5 Flash" },
-    { id: "stepfun/step-3.7-flash", name: "Step 3.7 Flash" },
-    { id: "tencent/hy3-preview", name: "Hy3 Preview" },
-    { id: "x-ai/grok-4.1-fast", name: "Grok 4.1 Fast" },
-    { id: "x-ai/grok-4.20-beta", name: "Grok 4.20 Beta" },
-    { id: "x-ai/grok-4.3", name: "Grok 4.3" },
-    { id: "x-ai/grok-4.5", name: "Grok 4.5" },
-    { id: "x-ai/grok-build-0.1", name: "Grok Build 0.1" },
-    { id: "xiaomi/mimo-v2-flash", name: "Mimo V2 Flash" },
-    { id: "xiaomi/mimo-v2-omni", name: "Mimo V2 Omni" },
-    { id: "xiaomi/mimo-v2-pro", name: "Mimo V2 Pro" },
-    { id: "xiaomi/mimo-v2.5", name: "Mimo V2.5" },
-    { id: "xiaomi/mimo-v2.5-pro", name: "Mimo V2.5 Pro" },
-    { id: "z-ai/glm-4.5-air", name: "Glm 4.5 Air" },
-    { id: "z-ai/glm-4.6", name: "Glm 4.6" },
-    { id: "z-ai/glm-4.6v", name: "Glm 4.6V" },
-    { id: "z-ai/glm-4.7", name: "Glm 4.7" },
-    { id: "z-ai/glm-5", name: "Glm 5" },
-    { id: "z-ai/glm-5-turbo", name: "Glm 5 Turbo" },
-    { id: "z-ai/glm-5.1", name: "Glm 5.1" },
-    { id: "z-ai/glm-5.2", name: "Glm 5.2" },
-  ],
-  serviceKinds: ["llm", "embedding", "image"],
-  embeddingConfig: {
-    baseUrl: "https://api.tokenrouter.com/v1/embeddings",
-    authType: "apikey",
-    authHeader: "bearer",
-  },
-  imageConfig: {
-    baseUrl: "https://api.tokenrouter.com/v1/images/generations",
-  },
-  modelsFetcher: { url: "https://api.tokenrouter.com/v1/models", type: "openai" },
-  passthroughModels: true,
-};

open-sse/providers/registry/xai.js

@@ -25,17 +25,48 @@ export default {
     clientId: "b1a00492-073a-47ea-816f-4c329264a828",
     tokenUrl: "https://auth.x.ai/oauth2/token",
     refreshUrl: "https://auth.x.ai/oauth2/token",
+    // OAuth-only SuperGrok quota surfaces:
+    // - url: monthly API usage allotment (JSON)
+    // - creditsUrl: weekly SuperGrok limit (grpc-web)
+    // - settingsUrl: plan label (subscription_tier_display)
+    usage: {
+      url: "https://cli-chat-proxy.grok.com/v1/billing",
+      creditsUrl: "https://grok.com/grok_api_v2.GrokBuildBilling/GetGrokCreditsConfig",
+      settingsUrl: "https://cli-chat-proxy.grok.com/v1/settings",
+    },
   },
   models: [
     { id: "grok-4", name: "Grok 4" },
     { id: "grok-4-fast-reasoning", name: "Grok 4 Fast Reasoning" },
     { id: "grok-code-fast-1", name: "Grok Code Fast" },
     { id: "grok-3", name: "Grok 3" },
-    { id: "grok-2-image-1212", name: "Grok 2 Image", params: ["n","response_format"], kind: "image" },
-    { id: "grok-imagine-video", name: "Grok Imagine Video", params: ["duration","aspect_ratio","resolution"], kind: "video" },
+    {
+      id: "grok-imagine-image-quality",
+      name: "Grok Imagine Image Quality",
+      capabilities: ["text2img", "edit"],
+      params: ["n", "aspect_ratio", "resolution", "response_format", "size"],
+      kind: "image",
+    },
+    {
+      id: "grok-2-image-1212",
+      name: "Grok 2 Image",
+      capabilities: ["text2img", "edit"],
+      params: ["n", "aspect_ratio", "resolution", "response_format", "size"],
+      kind: "image",
+    },
+    {
+      id: "grok-imagine-video",
+      name: "Grok Imagine Video",
+      params: ["duration", "aspect_ratio", "resolution"],
+      kind: "video",
+    },
   ],
-  serviceKinds: ["llm","imageToText","webSearch","image","video"],
-  imageConfig: { baseUrl: "https://api.x.ai/v1/images/generations", bodyFields: ["model","prompt","n","response_format"] },
+  serviceKinds: ["llm", "imageToText", "webSearch", "image", "video"],
+  imageConfig: {
+    baseUrl: "https://api.x.ai/v1/images/generations",
+    editsUrl: "https://api.x.ai/v1/images/edits",
+    bodyFields: ["model", "prompt", "n", "response_format", "aspect_ratio", "resolution", "image", "images"],
+  },
   // Async video jobs (POST returns { request_id }, GET polls until done/failed).
   // Docs: https://docs.x.ai/developers/rest-api-reference/inference/videos
   videoConfig: { baseUrl: "https://api.x.ai/v1/videos" },
@@ -44,4 +75,7 @@ export default {
     endpoint: "https://api.x.ai/v1/responses",
     pricingUrl: "https://x.ai/api#pricing",
   },
+  features: {
+    usage: true,
+  },
 };

open-sse/providers/registry/xiaomi-mimo.js

@@ -15,11 +15,10 @@ export default {
     textIcon: "XM",
     website: "https://xiaomimimo.com",
     notice: {
-      apiKeyUrl: "https://platform.xiaomimimo.com/console/api-keys",
+      apiKeyUrl: "https://xiaomimimo.com",
     },
   },
   category: "apikey",
-  serviceKinds: ["llm", "tts"],
   transport: {
     baseUrl: "https://api.xiaomimimo.com/v1/chat/completions",
     validateUrl: "https://api.xiaomimimo.com/v1/models",
@@ -43,12 +42,5 @@ export default {
     { id: "mimo-v2.5", name: "MiMo V2.5" },
     { id: "mimo-v2-omni", name: "MiMo V2 Omni" },
     { id: "mimo-v2-flash", name: "MiMo V2 Flash" },
-    { id: "mimo-v2.5-tts", name: "MiMo V2.5 TTS", kind: "tts" },
   ],
-  ttsConfig: {
-    baseUrl: "https://api.xiaomimimo.com/v1/chat/completions",
-    authType: "apikey",
-    authHeader: "bearer",
-    format: "xiaomi-mimo-tts",
-  },
 };

open-sse/providers/shared.js

@@ -47,26 +47,6 @@ export const CLAUDE_CLI_SPOOF_HEADERS = {
   "X-Stainless-Timeout": "600"
 };
 
-const ANTHROPIC_BETA_BASE = [
-  "claude-code-20250219",
-  "oauth-2025-04-20",
-  "interleaved-thinking-2025-05-14",
-  "context-management-2025-06-27",
-  "prompt-caching-scope-2026-01-05",
-  "structured-outputs-2025-12-15",
-  "fast-mode-2026-02-01",
-  "redact-thinking-2026-02-12",
-  "token-efficient-tools-2026-03-28",
-];
-const ANTHROPIC_BETA_HEAVY_AGENT = ["advanced-tool-use-2025-11-20", "effort-2025-11-24"];
-
-// Heavy-agent beta flags are gated to opus/sonnet — cheaper models don't need them.
-export function selectAnthropicBeta(model = "") {
-  const flags = [...ANTHROPIC_BETA_BASE];
-  if (/^claude-(opus|sonnet)/.test(model)) flags.push(...ANTHROPIC_BETA_HEAVY_AGENT);
-  return flags.join(",");
-}
-
 // Shared baseUrls
 export const KIMI_CODING_BASE_URL = "https://api.kimi.com/coding/v1/messages";
 

open-sse/providers/thinkingLevels.js

@@ -31,13 +31,10 @@ const FORMAT_LEVELS = {
   step: L.base,
 };
 
-const CODEX_GPT_5_6_LEVELS = ["none", "minimal", "low", "medium", "high", "xhigh", "max"];
-
 // Model-name pattern overrides (glob, first match wins) — more precise than format default.
 const PATTERN_THINKING = [
-  { provider: "codex", pattern: "*gpt-5.6-sol*", levels: [...CODEX_GPT_5_6_LEVELS, "ultra"] },
-  { provider: "codex", pattern: "*gpt-5.6-terra*", levels: [...CODEX_GPT_5_6_LEVELS, "ultra"] },
-  { provider: "codex", pattern: "*gpt-5.6-luna*", levels: CODEX_GPT_5_6_LEVELS },
+  // gpt-5.6-sol accepts max (maps to xhigh on wire); live probe rejected ultra.
+  { pattern: "*gpt-5.6-sol*", levels: ["none", "minimal", "low", "medium", "high", "xhigh", "max"] },
   { pattern: "*codex*", levels: ["low", "medium", "high", "xhigh"] }, // codex cannot disable thinking
 ];
 
@@ -46,9 +43,7 @@ export function getThinkingLevels(provider, model) {
   if (provider === "kiro" && resolveKiroEffortPath(model) === null) return null;
   const caps = getCapabilitiesForModel(provider, model);
   if (!caps.reasoning) return null;
-  const hit = PATTERN_THINKING.find((entry) =>
-    (!entry.provider || entry.provider === provider) && matchPattern(entry.pattern, model)
-  );
+  const hit = PATTERN_THINKING.find((p) => matchPattern(p.pattern, model));
   let levels = hit?.levels || FORMAT_LEVELS[caps.thinkingFormat] || L.base;
   if (caps.thinkingCanDisable === false) levels = levels.filter((l) => l !== "none");
   return levels;

open-sse/rtk/headroom.js

@@ -25,17 +25,9 @@ function messagePayload(body) {
 
 function captureSizeSnapshot(body) {
   const messages = messagePayload(body);
-  const toolHistory = messages?.filter((message) =>
-    message?.role === "tool"
-    || message?.role === "function"
-    || message?.tool_calls?.length
-    || message?.content?.some?.((part) => part?.type === "tool_use" || part?.type === "tool_result")
-  ) || [];
   return {
     bodyBytes: jsonBytes(body),
     messageBytes: messages ? jsonBytes(messages) : 0,
-    toolSchemaBytes: jsonBytes(body?.tools || []),
-    toolHistoryBytes: jsonBytes(toolHistory),
   };
 }
 
@@ -344,10 +336,7 @@ export function formatHeadroomSizeLog(diagnostics) {
   const before = diagnostics?.before;
   const after = diagnostics?.after;
   if (!before || !after) return "";
-  const effective = before.bodyBytes > 0
-    ? (((before.bodyBytes - after.bodyBytes) / before.bodyBytes) * 100).toFixed(1)
-    : "0.0";
-  return `body=${before.bodyBytes}B→${after.bodyBytes}B messages=${before.messageBytes}B→${after.messageBytes}B tools=${before.toolSchemaBytes || 0}B→${after.toolSchemaBytes || 0}B toolHistory=${before.toolHistoryBytes || 0}B→${after.toolHistoryBytes || 0}B effective=${effective}%`;
+  return `body=${before.bodyBytes}B→${after.bodyBytes}B messages=${before.messageBytes}B→${after.messageBytes}B`;
 }
 
 export function isHeadroomPhantomSavings(stats, diagnostics, minShrinkRatio = 0.05) {

open-sse/services/capacityAdapter.js

@@ -1,173 +0,0 @@
-/**
- * Capacity Adapter — global fallback pools of models per input-modality capability
- * (vision / pdf / audioInput / videoInput).
- *
- * The pool models are appended as extra fallback candidates behind whatever models
- * were already going to be tried (a combo's members, or a single target model).
- * combo.js's existing reorderByCapabilities then floats a capable pool model to the
- * front only when none of the original models can handle the request — so this
- * never overrides a combo that already has a member covering the capability.
- */
-import { getCapabilitiesForModel } from "../providers/capabilities.js";
-
-const CAPABILITY_KEYS = ["vision", "pdf", "audioInput", "videoInput"];
-const HARD_CAPS = new Set(CAPABILITY_KEYS);
-const DEFAULT_FALLBACK_MODEL = "oc/mimo-v2.5-free";
-
-// Normalize a capability entry to { enabled, roundRobin, models }. Backward-compat:
-// accept the legacy array form [{model, enabled}] (treated as enabled, fallback).
-function normalizeCapEntry(entry) {
-  if (Array.isArray(entry)) {
-    return { enabled: true, roundRobin: false, models: entry.map((e) => e?.model || e).filter(Boolean) };
-  }
-  if (entry && typeof entry === "object") {
-    return {
-      enabled: entry.enabled !== false,
-      roundRobin: !!entry.roundRobin,
-      models: Array.isArray(entry.models) ? entry.models.filter(Boolean) : [],
-    };
-  }
-  return { enabled: false, roundRobin: false, models: [] };
-}
-
-// Resolve one capability's full config. Enabled pools with no models fall back
-// to DEFAULT_FALLBACK_MODEL so the toggle is never a no-op.
-export function getCapacityAdapterConfig(cap, settings) {
-  const entry = normalizeCapEntry(settings?.capacityAdapter?.[cap]);
-  if (entry.enabled && entry.models.length === 0) {
-    return { ...entry, models: [DEFAULT_FALLBACK_MODEL] };
-  }
-  return entry;
-}
-
-// Flatten enabled models across all capability pools, in priority order, deduped.
-export function getCapacityAdapterModels(settings) {
-  const seen = new Set();
-  const models = [];
-  for (const cap of CAPABILITY_KEYS) {
-    const { enabled, models: pool } = getCapacityAdapterConfig(cap, settings);
-    if (!enabled) continue;
-    for (const m of pool) {
-      if (!seen.has(m)) {
-        seen.add(m);
-        models.push(m);
-      }
-    }
-  }
-  return models;
-}
-
-// Strategy for a capability: "round-robin" when enabled+roundRobin, else "fallback".
-export function getCapacityAdapterStrategy(cap, settings) {
-  const { enabled, roundRobin } = getCapacityAdapterConfig(cap, settings);
-  return enabled && roundRobin ? "round-robin" : "fallback";
-}
-
-// Strategy from the request's required capabilities: picks the first capability
-// whose adapter pool is enabled and can satisfy a hard requirement.
-export function getActiveAdapterStrategy(requiredCapabilities, settings) {
-  const hard = [...(requiredCapabilities || [])].filter((c) => HARD_CAPS.has(c));
-  for (const cap of hard) {
-    const { enabled, models } = getCapacityAdapterConfig(cap, settings);
-    if (!enabled || models.length === 0) continue;
-    return getCapacityAdapterStrategy(cap, settings);
-  }
-  return "fallback";
-}
-
-function modelSatisfies(modelStr, requiredHard) {
-  const slash = modelStr.indexOf("/");
-  const provider = slash > 0 ? modelStr.slice(0, slash) : "";
-  const model = slash > 0 ? modelStr.slice(slash + 1) : modelStr;
-  const caps = getCapabilitiesForModel(provider, model);
-  return requiredHard.every((c) => caps[c] === true);
-}
-
-// Prepend capacity-adapter models as priority candidates when NONE of the
-// original models (combo members, or the single target model) can satisfy the
-// request's required capabilities. Adapter models go FIRST (priority); the
-// original models follow as fallback. Leaves `models` untouched when the
-// original list already covers it (combo.js's reorderByCapabilities handles
-// that case via autoSwitch).
-export function augmentModelsWithCapacityAdapter(models, requiredCapabilities, settings) {
-  const hard = [...(requiredCapabilities || [])].filter((c) => HARD_CAPS.has(c));
-  if (hard.length === 0 || !Array.isArray(models) || models.length === 0) return models;
-  if (models.some((m) => modelSatisfies(m, hard))) return models;
-
-  const pool = getCapacityAdapterModels(settings).filter((m) => !models.includes(m) && modelSatisfies(m, hard));
-  if (pool.length === 0) return models;
-  return [...pool, ...models];
-}
-
-const CHARS_PER_TOKEN = 4; // rough estimate; avoids pulling in a tokenizer dependency
-const HEAD_KEEP = 6;      // messages after system kept verbatim before dropping the middle
-
-function blockLength(content) {
-  if (typeof content === "string") return content.length;
-  if (Array.isArray(content)) {
-    return content.reduce((sum, b) => sum + (typeof b?.text === "string" ? b.text.length : 50), 0);
-  }
-  return 0;
-}
-
-// Trim history to fit a (possibly smaller) context window by dropping the MIDDLE.
-// Preserves: all system/instruction messages (head), and the trailing user run
-// carrying the media the switch happened for (tail). Older middle turns between
-// the head instructions and the current turn are dropped first.
-export function stripHistoryForContext(body, contextWindow) {
-  const key = Array.isArray(body.messages) ? "messages"
-    : Array.isArray(body.input) ? "input"
-    : Array.isArray(body.contents) ? "contents"
-    : null;
-  if (!key) return body;
-  const arr = body[key];
-  if (!arr || arr.length === 0) return body;
-
-  const isSystem = (r) => r === "system" || r === "developer";
-  const systemMsgs = arr.filter((m) => isSystem(m?.role));
-  const rest = arr.filter((m) => !isSystem(m?.role));
-  if (rest.length === 0) return body;
-
-  const isAssistant = (r) => r === "assistant" || r === "model";
-  let i = rest.length - 1;
-  while (i >= 0 && !isAssistant(rest[i]?.role)) i--;
-  const tail = rest.slice(i + 1);          // current user turn (has media) — always kept
-  const older = rest.slice(0, i + 1);      // everything before it
-  if (older.length === 0) return body;
-
-  const contentOf = (m) => m.content ?? m.parts;
-  // Cap at 80% of the adapter model's context window — leaves room for the response.
-  const budgetChars = (contextWindow || 200000) * 0.8 * CHARS_PER_TOKEN;
-
-  // Prefer keeping the first HEAD_KEEP messages (initial instructions/context) verbatim;
-  // only trim further if even that exceeds the adapter model's context window.
-  const headKept = older.slice(0, HEAD_KEEP);
-  let total = systemMsgs.concat(headKept, tail).reduce((s, m) => s + blockLength(contentOf(m)), 0);
-
-  // If head + tail overflow, drop head turns from the end (closest to middle) first.
-  let head = headKept;
-  while (total > budgetChars && head.length > 0) {
-    const dropped = head.pop();
-    total -= blockLength(contentOf(dropped));
-  }
-
-  if (head.length === older.length) return body;
-  return { ...body, [key]: [...systemMsgs, ...head, ...tail] };
-}
-
-// Wrap a handleSingleModel callback so calls to a capacity-adapter model strip
-// history to fit its context window first. No-op passthrough when the pool is empty.
-export function withCapacityAdapterStripping(handleSingleModel, adapterModels) {
-  const adapterSet = new Set(adapterModels);
-  if (adapterSet.size === 0) return handleSingleModel;
-  return (body, modelStr, ...rest) => {
-    if (adapterSet.has(modelStr)) {
-      const slash = modelStr.indexOf("/");
-      const provider = slash > 0 ? modelStr.slice(0, slash) : "";
-      const model = slash > 0 ? modelStr.slice(slash + 1) : modelStr;
-      const { contextWindow } = getCapabilitiesForModel(provider, model);
-      body = stripHistoryForContext(body, contextWindow);
-    }
-    return handleSingleModel(body, modelStr, ...rest);
-  };
-}

open-sse/services/combo.js

@@ -23,13 +23,23 @@ function flattenToolHistory(messages) {
 		.filter((msg) => msg)
 		.map((msg) => {
 			if (msg.role === "tool" || msg.role === "function") {
-        return { role: "assistant", content: `${TOOL_RESULT_PREFIX}${extractTextContent(msg.content) || String(msg.content ?? "")}]` };
+				return {
+					role: "assistant",
+					content: `${TOOL_RESULT_PREFIX}${extractTextContent(msg.content) || String(msg.content ?? "")}]`,
+				};
 			}
 			if (msg.role === "assistant" && Array.isArray(msg.tool_calls)) {
 				const { tool_calls, ...rest } = msg;
-        const names = tool_calls.map((c) => c?.function?.name || c?.name || "tool").join(", ");
-        const base = extractTextContent(rest.content) || (typeof rest.content === "string" ? rest.content : "");
-        return { ...rest, content: `${base}${base ? "\n" : ""}${TOOL_CALL_PREFIX}${names}]` };
+				const names = tool_calls
+					.map((c) => c?.function?.name || c?.name || "tool")
+					.join(", ");
+				const base =
+					extractTextContent(rest.content) ||
+					(typeof rest.content === "string" ? rest.content : "");
+				return {
+					...rest,
+					content: `${base}${base ? "\n" : ""}${TOOL_CALL_PREFIX}${names}]`,
+				};
 			}
 			if (Array.isArray(msg.content)) {
 				const hasToolUse = msg.content.some((c) => c.type === "tool_use");
@@ -41,7 +51,11 @@ function flattenToolHistory(messages) {
 					for (const block of msg.content) {
 						if (block.type === "text" && block.text) textParts.push(block.text);
 						if (block.type === "tool_use") toolNames.push(block.name || "tool");
-            if (block.type === "tool_result") toolResults.push(extractTextContent(block.content) || String(block.content ?? ""));
+						if (block.type === "tool_result")
+							toolResults.push(
+								extractTextContent(block.content) ||
+									String(block.content ?? ""),
+							);
 					}
 					const { ...rest } = msg;
 					let newContent = textParts.join("\n");
@@ -61,7 +75,13 @@ function flattenToolHistory(messages) {
 // Reorder combo models by capability fit. Stable; never drops a model (fallback intact).
 // Tier 0: satisfies all hard + all soft. Tier 1: all hard only. Tier 2: rest.
 export function reorderByCapabilities(models, required) {
-  if (!required || required.size === 0 || !Array.isArray(models) || models.length <= 1) return models;
+	if (
+		!required ||
+		required.size === 0 ||
+		!Array.isArray(models) ||
+		models.length <= 1
+	)
+		return models;
 	const hard = [...required].filter((c) => HARD_CAPS.has(c));
 	const soft = [...required].filter((c) => !HARD_CAPS.has(c));
 
@@ -106,74 +126,26 @@ export function detectRequiredCapabilities(body) {
 	const required = new Set();
 	if (!body || typeof body !== "object") return required;
 
-  const addByMime = (mime) => {
-    if (typeof mime !== "string") return;
-    if (mime.startsWith("image/")) required.add("vision");
-    else if (mime === "application/pdf") required.add("pdf");
-    else if (mime.startsWith("audio/")) required.add("audioInput");
-    else if (mime.startsWith("video/")) required.add("videoInput");
-  };
-
 	const scanBlock = (b) => {
 		if (!b || typeof b !== "object") return;
 		const t = b.type;
-    if (t === "image_url" || t === "image" || t === "input_image") required.add("vision");
-    if (t === "input_audio" || t === "audio_url" || t === "audio") required.add("audioInput");
-    if (t === "input_video" || t === "video_url" || t === "video") required.add("videoInput");
-    if (t === "file" || t === "document" || t === "input_file") {
-      // Infer modality from embedded mime when available; fall back to pdf for generic files.
-      let fmime = null;
-      if (b.input_audio?.format) fmime = `audio/${b.input_audio.format}`;
-      else if (b.file?.file_data) fmime = String(b.file.file_data).match(/^data:([^;,]+)/)?.[1];
-      else if (b.source?.media_type) fmime = b.source.media_type;
-      else if (b.source?.data) fmime = String(b.source.data).match(/^data:([^;,]+)/)?.[1];
-      if (fmime) addByMime(fmime);
-      else required.add("pdf");
-    }
+		if (t === "image_url" || t === "image" || t === "input_image")
+			required.add("vision");
+		if (t === "file" || t === "document" || t === "input_file")
+			required.add("pdf");
 		// gemini parts: inlineData/fileData carry a mime
-    addByMime(b.inlineData?.mimeType || b.fileData?.mimeType);
+		const mime = b.inlineData?.mimeType || b.fileData?.mimeType;
+		if (typeof mime === "string" && mime.startsWith("image/"))
+			required.add("vision");
+		if (mime === "application/pdf") required.add("pdf");
 	};
 
 	const scanContent = (content) => {
 		if (Array.isArray(content)) for (const b of content) scanBlock(b);
 	};
 
-  const scanMessage = (m) => {
-    if (!m || typeof m !== "object") return;
-
-    // Ollama / Hermes images array (strings or objects)
-    if (Array.isArray(m.images) && m.images.length > 0) {
-      required.add("vision");
-    }
-
-    // Vercel AI SDK / Hermes attachments / experimental_attachments
-    const attachments = m.experimental_attachments || m.attachments;
-    if (Array.isArray(attachments)) {
-      for (const att of attachments) {
-        if (!att) continue;
-        const mime = att.contentType || att.mediaType || (typeof att.url === "string" && att.url.match(/^data:([^;,]+)/)?.[1]);
-        if (mime) addByMime(mime);
-        else if (att.url || att.data) required.add("vision");
-      }
-    }
-
-    // Direct message-level modality properties
-    if (m.image_url || m.image) required.add("vision");
-    if (m.audio_url || m.audio) required.add("audioInput");
-
-    // Scan array content blocks
-    scanContent(m.content);
-
-    // Scan string content for embedded data URIs
-    if (typeof m.content === "string") {
-      if (m.content.includes("data:image/")) required.add("vision");
-      else if (m.content.includes("data:audio/")) required.add("audioInput");
-      else if (m.content.includes("data:application/pdf")) required.add("pdf");
-    }
-  };
-
 	// Modalities: current user turn only (trailing user run across each known shape).
-  for (const m of trailingUserItems(body.messages)) scanMessage(m);              // openai / claude / hermes / ollama
+	for (const m of trailingUserItems(body.messages)) scanContent(m.content); // openai / claude
 	for (const it of trailingUserItems(body.input)) scanContent(it.content); // responses
 	const contents = body.contents || body.request?.contents; // gemini / antigravity
 	for (const c of trailingUserItems(contents)) scanContent(c.parts);
@@ -213,9 +185,10 @@ export function getRotatedModels(models, comboName, strategy, stickyLimit = 1) {
 	const rotationKey = comboName || "__default__";
 	const normalizedStickyLimit = normalizeStickyLimit(stickyLimit);
 	const existingState = comboRotationState.get(rotationKey);
-  const state = typeof existingState === "number"
+	const state =
+		typeof existingState === "number"
 			? { index: existingState, consecutiveUseCount: 0 }
-    : (existingState || { index: 0, consecutiveUseCount: 0 });
+			: existingState || { index: 0, consecutiveUseCount: 0 };
 
 	const currentIndex = state.index % models.length;
 	const rotatedModels = rotateModelsFromIndex(models, currentIndex);
@@ -256,10 +229,17 @@ export function getComboModelsFromData(modelStr, combosData) {
 	if (modelStr.includes("/")) return null;
 
 	// Handle both array and object formats
-  const combos = Array.isArray(combosData) ? combosData : (combosData?.combos || []);
+	const combos = Array.isArray(combosData)
+		? combosData
+		: combosData?.combos || [];
 
-  const combo = combos.find(c => c.name === modelStr);
-  if (combo && combo.models && combo.models.length > 0) {
+	const combo = combos.find((c) => c.name === modelStr);
+	if (
+		combo &&
+		combo.enabled !== false &&
+		combo.models &&
+		combo.models.length > 0
+	) {
 		return combo.models;
 	}
 	return null;
@@ -277,9 +257,23 @@ export function getComboModelsFromData(modelStr, combosData) {
  * @param {number|string} [options.comboStickyLimit=1] - Requests per combo model before switching
  * @returns {Promise<Response>}
  */
-export async function handleComboChat({ body, models, handleSingleModel, log, comboName, comboStrategy, comboStickyLimit = 1, autoSwitch = true }) {
+export async function handleComboChat({
+	body,
+	models,
+	handleSingleModel,
+	log,
+	comboName,
+	comboStrategy,
+	comboStickyLimit = 1,
+	autoSwitch = true,
+}) {
 	// Apply rotation strategy if enabled
-  let rotatedModels = getRotatedModels(models, comboName, comboStrategy, comboStickyLimit);
+	let rotatedModels = getRotatedModels(
+		models,
+		comboName,
+		comboStrategy,
+		comboStickyLimit,
+	);
 
 	// Auto-switch: float models that satisfy the request's required capabilities to the front.
 	if (autoSwitch) {
@@ -287,7 +281,10 @@ export async function handleComboChat({ body, models, handleSingleModel, log, co
 		if (required.size > 0) {
 			const reordered = reorderByCapabilities(rotatedModels, required);
 			if (reordered[0] !== rotatedModels[0]) {
-        log.info("COMBO", `auto-switch for [${[...required].join(",")}] → ${reordered[0]}`);
+				log.info(
+					"COMBO",
+					`auto-switch for [${[...required].join(",")}] → ${reordered[0]}`,
+				);
 			}
 			rotatedModels = reordered;
 		}
@@ -299,7 +296,10 @@ export async function handleComboChat({ body, models, handleSingleModel, log, co
 
 	for (let i = 0; i < rotatedModels.length; i++) {
 		const modelStr = rotatedModels[i];
-    log.info("COMBO", `Trying model ${i + 1}/${rotatedModels.length}: ${modelStr}`);
+		log.info(
+			"COMBO",
+			`Trying model ${i + 1}/${rotatedModels.length}: ${modelStr}`,
+		);
 
 		try {
 			const result = await handleSingleModel(body, modelStr);
@@ -315,48 +315,78 @@ export async function handleComboChat({ body, models, handleSingleModel, log, co
 			let retryAfter = null;
 			try {
 				const errorBody = await result.clone().json();
-        errorText = errorBody?.error?.message || errorBody?.error || errorBody?.message || errorText;
+				errorText =
+					errorBody?.error?.message ||
+					errorBody?.error ||
+					errorBody?.message ||
+					errorText;
 				retryAfter = errorBody?.retryAfter || null;
 			} catch {
 				// Ignore JSON parse errors
 			}
 
 			// Track earliest retryAfter across all combo models
-      if (retryAfter && (!earliestRetryAfter || new Date(retryAfter) < new Date(earliestRetryAfter))) {
+			if (
+				retryAfter &&
+				(!earliestRetryAfter ||
+					new Date(retryAfter) < new Date(earliestRetryAfter))
+			) {
 				earliestRetryAfter = retryAfter;
 			}
 
 			// Normalize error text to string (Worker-safe)
 			if (typeof errorText !== "string") {
-        try { errorText = JSON.stringify(errorText); } catch { errorText = String(errorText); }
+				try {
+					errorText = JSON.stringify(errorText);
+				} catch {
+					errorText = String(errorText);
+				}
 			}
 
 			// Check if should fallback to next model
-      const { shouldFallback, cooldownMs } = checkFallbackError(result.status, errorText);
+			const { shouldFallback, cooldownMs } = checkFallbackError(
+				result.status,
+				errorText,
+			);
 
 			if (!shouldFallback) {
-        log.warn("COMBO", `Model ${modelStr} failed (no fallback)`, { status: result.status });
+				log.warn("COMBO", `Model ${modelStr} failed (no fallback)`, {
+					status: result.status,
+				});
 				return result;
 			}
 
 			// For transient errors (503/502/504), wait for cooldown before falling through
 			// so a briefly-overloaded provider gets a chance to recover rather than being
 			// skipped immediately (fixes: combo falls through on transient 503)
-      if (cooldownMs && cooldownMs > 0 && cooldownMs <= 5000 &&
-          (result.status === 503 || result.status === 502 || result.status === 504)) {
-        log.info("COMBO", `Model ${modelStr} transient ${result.status}, waiting ${cooldownMs}ms before next`);
-        await new Promise(r => setTimeout(r, cooldownMs));
+			if (
+				cooldownMs &&
+				cooldownMs > 0 &&
+				cooldownMs <= 5000 &&
+				(result.status === 503 ||
+					result.status === 502 ||
+					result.status === 504)
+			) {
+				log.info(
+					"COMBO",
+					`Model ${modelStr} transient ${result.status}, waiting ${cooldownMs}ms before next`,
+				);
+				await new Promise((r) => setTimeout(r, cooldownMs));
 			}
 
 			// Fallback to next model
 			lastError = errorText || String(result.status);
 			if (!lastStatus) lastStatus = result.status;
-      log.warn("COMBO", `Model ${modelStr} failed, trying next`, { status: result.status });
+			log.warn("COMBO", `Model ${modelStr} failed, trying next`, {
+				status: result.status,
+			});
 		} catch (error) {
 			// Catch unexpected exceptions to ensure fallback continues
 			lastError = error.message || String(error);
 			if (!lastStatus) lastStatus = 500;
-      log.warn("COMBO", `Model ${modelStr} threw error, trying next`, { error: lastError });
+			log.warn("COMBO", `Model ${modelStr} threw error, trying next`, {
+				error: lastError,
+			});
 		}
 	}
 
@@ -364,8 +394,9 @@ export async function handleComboChat({ body, models, handleSingleModel, log, co
 	// Use 503 (Service Unavailable) rather than 406 (Not Acceptable) — 406 implies
 	// the request itself is invalid, but here the providers are simply unavailable
 	// or have no active credentials. 503 is more accurate and retryable by clients.
-  const allDisabled = lastError && lastError.toLowerCase().includes("no credentials");
-  const status = allDisabled ? 503 : (lastStatus || 503);
+	const allDisabled =
+		lastError && lastError.toLowerCase().includes("no credentials");
+	const status = allDisabled ? 503 : lastStatus || 503;
 	const msg = lastError || "All combo models unavailable";
 
 	if (earliestRetryAfter) {
@@ -375,10 +406,10 @@ export async function handleComboChat({ body, models, handleSingleModel, log, co
 	}
 
 	log.warn("COMBO", `All models failed | ${msg}`);
-  return new Response(
-    JSON.stringify({ error: { message: msg } }),
-    { status, headers: { "Content-Type": "application/json" } }
-  );
+	return new Response(JSON.stringify({ error: { message: msg } }), {
+		status,
+		headers: { "Content-Type": "application/json" },
+	});
 }
 
 /**
@@ -396,7 +427,8 @@ function extractPanelText(json) {
 		const msg = choice.message ?? choice.delta ?? {};
 		const t = extractTextContent(msg.content);
 		if (t.trim()) return t;
-    if (typeof choice.text === "string" && choice.text.trim()) return choice.text;
+		if (typeof choice.text === "string" && choice.text.trim())
+			return choice.text;
 	}
 
 	// Claude messages (text blocks share OpenAI's {type:"text"} shape)
@@ -413,7 +445,9 @@ function extractPanelText(json) {
 	// OpenAI Responses API
 	if (Array.isArray(json.output)) {
 		const t = json.output
-      .flatMap((o) => (Array.isArray(o.content) ? o.content.map((c) => c?.text || "") : []))
+			.flatMap((o) =>
+				Array.isArray(o.content) ? o.content.map((c) => c?.text || "") : [],
+			)
 			.join("");
 		if (t.trim()) return t;
 	}
@@ -480,8 +514,14 @@ function withTimeout(promise, ms) {
 	return new Promise((resolve) => {
 		const t = setTimeout(() => resolve({ __timeout: true }), ms);
 		Promise.resolve(promise)
-      .then((v) => { clearTimeout(t); resolve(v); })
-      .catch((e) => { clearTimeout(t); resolve({ __error: e }); });
+			.then((v) => {
+				clearTimeout(t);
+				resolve(v);
+			})
+			.catch((e) => {
+				clearTimeout(t);
+				resolve({ __error: e });
+			});
 	});
 }
 
@@ -492,7 +532,10 @@ function withTimeout(promise, ms) {
  * still preferring a full panel when everyone is fast. Bounded by a hard timeout.
  * Returns a sparse array aligned to `calls` (undefined = not yet / dropped).
  */
-function collectPanel(calls, { minPanel, stragglerGraceMs, panelHardTimeoutMs }) {
+function collectPanel(
+	calls,
+	{ minPanel, stragglerGraceMs, panelHardTimeoutMs },
+) {
 	return new Promise((resolve) => {
 		const out = new Array(calls.length);
 		let settled = 0;
@@ -509,13 +552,18 @@ function collectPanel(calls, { minPanel, stragglerGraceMs, panelHardTimeoutMs })
 		const hardTimer = setTimeout(finish, panelHardTimeoutMs);
 		calls.forEach((p, i) => {
 			Promise.resolve(p)
-        .then((v) => { out[i] = v; })
-        .catch((e) => { out[i] = { __error: e }; })
+				.then((v) => {
+					out[i] = v;
+				})
+				.catch((e) => {
+					out[i] = { __error: e };
+				})
 				.finally(() => {
 					settled++;
 					if (out[i] && out[i].ok) ok++;
 					if (settled === calls.length) return finish();
-          if (ok >= minPanel && !graceTimer) graceTimer = setTimeout(finish, stragglerGraceMs);
+					if (ok >= minPanel && !graceTimer)
+						graceTimer = setTimeout(finish, stragglerGraceMs);
 				});
 		});
 	});
@@ -544,12 +592,20 @@ function collectPanel(calls, { minPanel, stragglerGraceMs, panelHardTimeoutMs })
  * @param {Object} [options.tuning] - Override FUSION_DEFAULTS (minPanel, grace, timeout)
  * @returns {Promise<Response>}
  */
-export async function handleFusionChat({ body, models, handleSingleModel, log, comboName, judgeModel, tuning }) {
+export async function handleFusionChat({
+	body,
+	models,
+	handleSingleModel,
+	log,
+	comboName,
+	judgeModel,
+	tuning,
+}) {
 	const panel = Array.isArray(models) ? models.filter(Boolean) : [];
 	if (panel.length === 0) {
 		return new Response(
 			JSON.stringify({ error: { message: "Fusion combo has no models" } }),
-      { status: 400, headers: { "Content-Type": "application/json" } }
+			{ status: 400, headers: { "Content-Type": "application/json" } },
 		);
 	}
 
@@ -561,13 +617,13 @@ export async function handleFusionChat({ body, models, handleSingleModel, log, c
 	const cfg = { ...FUSION_DEFAULTS, ...(tuning || {}) };
 	const minPanel = Math.min(Math.max(2, cfg.minPanel), panel.length);
 	const judge = judgeModel && judgeModel.trim() ? judgeModel.trim() : panel[0];
-  log.info("FUSION", `Combo "${comboName}" | panel=${panel.length} [${panel.join(", ")}] | judge=${judge} | quorum=${minPanel}`);
+	log.info(
+		"FUSION",
+		`Combo "${comboName}" | panel=${panel.length} [${panel.join(", ")}] | judge=${judge} | quorum=${minPanel}`,
+	);
 
 	// 1. Fan out to the panel in parallel: non-streaming, tools stripped (we want prose).
-  const { tools, tool_choice, stream_options, ...rest } = body;
-  // Fusion runs panel models non-streaming; drop stream_options too, or providers
-  // like DeepSeek reject it with "stream_options should be set along with stream = true".
-  // See issue #3024.
+	const { tools, tool_choice, ...rest } = body;
 	const panelBody = { ...rest, stream: false };
 
 	// Flatten tool turns to prose so panel models keep context without emitting tool_calls.
@@ -578,7 +634,9 @@ export async function handleFusionChat({ body, models, handleSingleModel, log, c
 	}
 
 	const t0 = Date.now();
-  const calls = panel.map((m) => withTimeout(handleSingleModel(panelBody, m, true), cfg.panelHardTimeoutMs));
+	const calls = panel.map((m) =>
+		withTimeout(handleSingleModel(panelBody, m, true), cfg.panelHardTimeoutMs),
+	);
 	const settled = await collectPanel(calls, { ...cfg, minPanel });
 	log.info("FUSION", `fan-out collected in ${Date.now() - t0}ms`);
 
@@ -587,10 +645,24 @@ export async function handleFusionChat({ body, models, handleSingleModel, log, c
 	for (let i = 0; i < settled.length; i++) {
 		const res = settled[i];
 		const model = panel[i];
-    if (!res) { log.warn("FUSION", `Panel ${model} dropped (straggler/timeout)`); continue; }
-    if (res.__timeout) { log.warn("FUSION", `Panel ${model} timed out`); continue; }
-    if (res.__error) { log.warn("FUSION", `Panel ${model} threw`, { error: res.__error?.message || String(res.__error) }); continue; }
-    if (!res.ok) { log.warn("FUSION", `Panel ${model} failed`, { status: res.status }); continue; }
+		if (!res) {
+			log.warn("FUSION", `Panel ${model} dropped (straggler/timeout)`);
+			continue;
+		}
+		if (res.__timeout) {
+			log.warn("FUSION", `Panel ${model} timed out`);
+			continue;
+		}
+		if (res.__error) {
+			log.warn("FUSION", `Panel ${model} threw`, {
+				error: res.__error?.message || String(res.__error),
+			});
+			continue;
+		}
+		if (!res.ok) {
+			log.warn("FUSION", `Panel ${model} failed`, { status: res.status });
+			continue;
+		}
 		try {
 			const json = await res.clone().json();
 			const text = extractPanelText(json);
@@ -601,7 +673,9 @@ export async function handleFusionChat({ body, models, handleSingleModel, log, c
 				log.warn("FUSION", `Panel ${model} returned empty content`);
 			}
 		} catch (e) {
-      log.warn("FUSION", `Panel ${model} unparseable`, { error: e.message || String(e) });
+			log.warn("FUSION", `Panel ${model} unparseable`, {
+				error: e.message || String(e),
+			});
 		}
 	}
 
@@ -610,11 +684,14 @@ export async function handleFusionChat({ body, models, handleSingleModel, log, c
 		log.warn("FUSION", "All panel models failed");
 		return new Response(
 			JSON.stringify({ error: { message: "All fusion panel models failed" } }),
-      { status: 503, headers: { "Content-Type": "application/json" } }
+			{ status: 503, headers: { "Content-Type": "application/json" } },
 		);
 	}
 	if (answers.length === 1) {
-    log.info("FUSION", `Only ${answers[0].model} succeeded — answering directly (no fusion)`);
+		log.info(
+			"FUSION",
+			`Only ${answers[0].model} succeeded — answering directly (no fusion)`,
+		);
 		return handleSingleModel(body, answers[0].model);
 	}
 

open-sse/services/projectId.js

@@ -7,7 +7,7 @@
  * This significantly reduces the risk of being flagged by Google's anti-abuse systems.
  */
 
-import { CLOUD_CODE_API, LOAD_CODE_ASSIST_HEADERS, ANTIGRAVITY_LOAD_CODE_ASSIST_HEADERS, LOAD_CODE_ASSIST_METADATA } from "../config/appConstants.js";
+import { CLOUD_CODE_API, LOAD_CODE_ASSIST_HEADERS, LOAD_CODE_ASSIST_METADATA } from "../config/appConstants.js";
 
 // ─── Cache ────────────────────────────────────────────────────────────────────
 // connectionId -> { projectId: string, fetchedAt: number }
@@ -157,10 +157,9 @@ export function removeConnection(connectionId) {
  */
 async function fetchProjectId(accessToken, signal, provider) {
     const endpoints = CLOUD_CODE_API[provider] || CLOUD_CODE_API["gemini-cli"];
-    const headers = provider === "antigravity" ? ANTIGRAVITY_LOAD_CODE_ASSIST_HEADERS : LOAD_CODE_ASSIST_HEADERS;
     const response = await fetch(endpoints.loadCodeAssist, {
         method: "POST",
-        headers: { ...headers, "Authorization": `Bearer ${accessToken}` },
+        headers: { ...LOAD_CODE_ASSIST_HEADERS, "Authorization": `Bearer ${accessToken}` },
         body: JSON.stringify({ metadata: LOAD_CODE_ASSIST_METADATA }),
         signal
     });
@@ -187,7 +186,7 @@ async function fetchProjectId(accessToken, signal, provider) {
         }
     }
 
-    return onboardUser(accessToken, tierID, signal, endpoints, provider);
+    return onboardUser(accessToken, tierID, signal, endpoints);
 }
 
 /**
@@ -198,11 +197,10 @@ async function fetchProjectId(accessToken, signal, provider) {
  * @param {AbortSignal} externalSignal  – propagated from the connection's AbortController
  * @returns {Promise<string|null>}
  */
-async function onboardUser(accessToken, tierID, externalSignal, endpoints, provider) {
+async function onboardUser(accessToken, tierID, externalSignal, endpoints) {
     console.log(`[ProjectId] Onboarding user with tier: ${tierID}`);
 
     const reqBody = { tierId: tierID, metadata: LOAD_CODE_ASSIST_METADATA };
-    const headers = provider === "antigravity" ? ANTIGRAVITY_LOAD_CODE_ASSIST_HEADERS : LOAD_CODE_ASSIST_HEADERS;
     const MAX_ATTEMPTS = 5;
 
     for (let attempt = 1; attempt <= MAX_ATTEMPTS; attempt++) {
@@ -218,7 +216,7 @@ async function onboardUser(accessToken, tierID, externalSignal, endpoints, provi
         try {
             const response = await fetch(endpoints.onboardUser, {
                 method: "POST",
-                headers: { ...headers, "Authorization": `Bearer ${accessToken}` },
+                headers: { ...LOAD_CODE_ASSIST_HEADERS, "Authorization": `Bearer ${accessToken}` },
                 body: JSON.stringify(reqBody),
                 signal: localCtrl.signal
             });

open-sse/services/provider.js

@@ -19,15 +19,9 @@ function isAnthropicCompatible(provider) {
   return typeof provider === "string" && provider.startsWith(ANTHROPIC_COMPATIBLE_PREFIX);
 }
 
-// Resolve the API type (chat vs responses) for an openai-compatible node.
-// The stored apiType on the connection's providerSpecificData (kept in sync with
-// the node on create/update) is authoritative. Falls back to the node ID
-// substring for legacy nodes created before apiType was persisted — their IDs
-// embed the type: openai-compatible-<chat|responses>-<uuid>.
-export function resolveOpenAICompatibleApiType(provider, credentials = null) {
-  const stored = credentials?.providerSpecificData?.apiType;
-  if (stored === "chat" || stored === "responses") return stored;
-  return typeof provider === "string" && provider.includes("responses") ? "responses" : "chat";
+function getOpenAICompatibleType(provider) {
+  if (!isOpenAICompatible(provider)) return "chat";
+  return provider.includes("responses") ? "responses" : "chat";
 }
 
 // Detect request format from body structure
@@ -111,9 +105,9 @@ export function detectFormat(body) {
 }
 
 // Get provider config (internal — no external runtime consumer)
-function getProviderConfig(provider, credentials = null) {
+function getProviderConfig(provider) {
   if (isOpenAICompatible(provider)) {
-    const apiType = resolveOpenAICompatibleApiType(provider, credentials);
+    const apiType = getOpenAICompatibleType(provider);
     return {
       ...PROVIDERS.openai,
       format: apiType === "responses" ? "openai-responses" : "openai",
@@ -131,14 +125,14 @@ function getProviderConfig(provider, credentials = null) {
 }
 
 // Get target format for provider
-export function getTargetFormat(provider, credentials = null) {
+export function getTargetFormat(provider) {
   if (isOpenAICompatible(provider)) {
-    return resolveOpenAICompatibleApiType(provider, credentials) === "responses" ? "openai-responses" : "openai";
+    return getOpenAICompatibleType(provider) === "responses" ? "openai-responses" : "openai";
   }
   if (isAnthropicCompatible(provider)) {
     return "claude";
   }
-  const config = getProviderConfig(provider, credentials);
+  const config = getProviderConfig(provider);
   return config.format || "openai";
 }
 

open-sse/services/providerTimeout.js

@@ -0,0 +1,56 @@
+/**
+ * Per-provider connect timeout overrides from user settings.
+ * Settings are read from the DB lazily and cached with a short TTL
+ * so UI changes take effect without requiring a restart.
+ */
+
+let cached = {};
+let cacheTs = 0;
+const CACHE_TTL_MS = 10_000; // 10s — responsive enough for dashboard changes
+
+async function refreshCache() {
+  const now = Date.now();
+  if (now - cacheTs < CACHE_TTL_MS && Object.keys(cached).length > 0) return cached;
+
+  try {
+    const { getSettings } = await import("@/lib/localDb");
+    // Return full settings so we can read providerTimeouts + globalTimeoutMs
+    cached = await getSettings();
+    cacheTs = now;
+  } catch {
+    // If DB is unavailable, keep stale cache — don't throw on hot path
+  }
+  return cached;
+}
+
+/**
+ * Resolve the effective connect timeout for a provider.
+ * Priority: per-provider override > global default timeout (settings) > registry config > env default.
+ * @param {string} providerId
+ * @param {number} configTimeoutMs - timeoutMs from the static provider registry config
+ * @param {number} envDefaultMs - global default from env (FETCH_CONNECT_TIMEOUT_MS)
+ * @returns {number} timeout in milliseconds
+ */
+export async function resolveProviderTimeoutMs(providerId, configTimeoutMs, envDefaultMs) {
+  const overrides = await refreshCache();
+
+  // 1. Per-provider override (set in provider detail page)
+  const providerOverride = overrides.providerTimeouts?.[providerId];
+  if (providerOverride?.timeoutMs && Number.isFinite(providerOverride.timeoutMs) && providerOverride.timeoutMs > 0) {
+    return providerOverride.timeoutMs;
+  }
+
+  // 2. Global default timeout (set in Profile / Settings page)
+  const globalDefault = overrides.defaultTimeoutMs;
+  if (globalDefault && Number.isFinite(globalDefault) && globalDefault > 0) {
+    return globalDefault;
+  }
+
+  // 3. Registry per-provider config
+  if (configTimeoutMs && Number.isFinite(configTimeoutMs) && configTimeoutMs > 0) {
+    return configTimeoutMs;
+  }
+
+  // 4. Env default
+  return envDefaultMs;
+}

open-sse/services/qoderModels.js

@@ -10,12 +10,6 @@
  *
  * On any error the live cache stays empty and chatExecuteCall surfaces the
  * problem to the user as "model config not yet fetched, retry shortly".
- *
- * PAT (Personal Access Token, pt-...) connections: a PAT cannot sign COSY
- * requests directly, so we exchange it for a short-lived job token (jt-...)
- * via openapi.qoder.sh/api/v1/jobToken/exchange (plain JSON POST), then use
- * that job token for signing. Job-token traffic must hit api2.qoder.sh —
- * api3 rejects jt- with "Login expired" (403).
  */
 
 import { createHash } from "crypto";
@@ -24,30 +18,11 @@ import { proxyAwareFetch } from "../utils/proxyFetch.js";
 import { buildCosyHeaders } from "../shared/qoder/cosy.js";
 import {
   QODER_MODEL_LIST_URL,
-  QODER_CHAT_BASE_ALT,
-  QODER_JOB_TOKEN_EXCHANGE_URL,
-  QODER_USERINFO_URL,
-  QODER_IDE_VERSION,
-  QODER_CLIENT_TYPE,
 } from "../shared/qoder/constants.js";
 
 const FETCH_TIMEOUT_MS = 15_000;
 const CACHE_TTL_MS = 60 * 60 * 1000; // 1h, same as the Kiro catalog
 
-const PAT_PREFIX = "pt-";
-
-// PAT → job-token cache: a job token is short-lived (24h), so we keep it per
-// PAT and re-exchange once it is within 5 minutes of expiry.
-const PAT_REFRESH_BUFFER_MS = 5 * 60 * 1000;
-const PAT_DEFAULT_TTL_MS = 24 * 60 * 60 * 1000;
-
-export function isQoderPat(token) {
-  return typeof token === "string" && token.startsWith(PAT_PREFIX);
-}
-
-/** @type {Map<string, { accessToken: string, userId: string, expiresAt: number }>} */
-const patJobCache = new Map();
-
 /** @type {Map<string, { expiresAt: number, models: any[], rawConfigs: Map<string, object>, fetched: boolean }>} */
 const catalogCache = new Map();
 
@@ -59,109 +34,6 @@ const catalogCache = new Map();
  */
 const inflight = new Map();
 
-/**
- * Exchange a Qoder PAT (pt-...) for a short-lived job token (jt-...).
- * This endpoint is plain JSON POST — NOT COSY-signed.
- */
-async function exchangeJobToken(pat, proxyOptions = null, signal = null) {
-  const res = await proxyAwareFetch(
-    QODER_JOB_TOKEN_EXCHANGE_URL,
-    {
-      method: "POST",
-      headers: {
-        "Content-Type": "application/json",
-        Accept: "application/json",
-        "User-Agent": "qodercli/1.0.0",
-        "Cosy-Version": QODER_IDE_VERSION,
-        "Cosy-ClientType": QODER_CLIENT_TYPE,
-      },
-      body: JSON.stringify({ personal_token: pat }),
-      signal,
-    },
-    proxyOptions,
-  );
-  if (!res.ok) {
-    const text = await res.text().catch(() => "");
-    throw new Error(`qoder PAT exchange failed: ${res.status} ${text.slice(0, 200)}`);
-  }
-  const data = await res.json();
-  if (!data.token) throw new Error("qoder PAT exchange returned no job token");
-
-  let expiresAt = Date.now() + PAT_DEFAULT_TTL_MS;
-  if (data.expires_at) {
-    const parsed = Date.parse(data.expires_at);
-    if (!Number.isNaN(parsed)) expiresAt = parsed;
-  } else if (typeof data.expires_in === "number" && data.expires_in > 0) {
-    expiresAt = Date.now() + data.expires_in;
-  }
-  return { jobToken: data.token, jobRefreshToken: data.refresh_token || "", expiresAt };
-}
-
-/**
- * Resolve the Qoder userId for a job token (needed for COSY signing).
- * Returns "" on any failure — callers fall back to the stored userId.
- */
-async function fetchUserIdForJobToken(jobToken, proxyOptions = null, signal = null) {
-  try {
-    const res = await proxyAwareFetch(
-      QODER_USERINFO_URL,
-      {
-        method: "GET",
-        headers: {
-          Authorization: `Bearer ${jobToken}`,
-          Accept: "application/json",
-          "User-Agent": "qodercli/1.0.0",
-        },
-        signal,
-      },
-      proxyOptions,
-    );
-    if (!res.ok) return "";
-    const data = await res.json().catch(() => ({}));
-    return data.id || data.userId || data.user_id || "";
-  } catch {
-    return "";
-  }
-}
-
-/**
- * Resolve a PAT to a job-token credential, cached per-PAT.
- */
-async function resolvePatCredential(pat, proxyOptions = null, signal = null) {
-  const cached = patJobCache.get(pat);
-  if (cached && cached.expiresAt - Date.now() > PAT_REFRESH_BUFFER_MS) return cached;
-
-  const { jobToken, expiresAt } = await exchangeJobToken(pat, proxyOptions, signal);
-  const userId = await fetchUserIdForJobToken(jobToken, proxyOptions, signal);
-  const resolved = { accessToken: jobToken, userId, expiresAt };
-  patJobCache.set(pat, resolved);
-  return resolved;
-}
-
-/**
- * Resolve connection credentials to COSY-signable form:
- *   - PAT (pt-...) connections → exchanged to a job token (jt-...) + userId
- *   - everything else → passed through unchanged
- */
-export async function resolveQoderCredentials(credentials, proxyOptions = null, signal = null) {
-  const raw = credentials?.apiKey || credentials?.accessToken;
-  if (isQoderPat(raw)) {
-    const resolved = await resolvePatCredential(raw, proxyOptions, signal);
-    return {
-      ...credentials,
-      accessToken: resolved.accessToken,
-      apiKey: undefined,
-      providerSpecificData: {
-        authMethod: "pat",
-        ...(credentials?.providerSpecificData || {}),
-        userId: resolved.userId || credentials?.providerSpecificData?.userId || "",
-        machineId: credentials?.providerSpecificData?.machineId || "",
-      },
-    };
-  }
-  return credentials;
-}
-
 /**
  * Stable cache key per credential (so different login sessions for the same
  * account share an entry).
@@ -196,16 +68,10 @@ async function fetchQoderCatalogRaw(credentials, signal, proxyOptions = null) {
   const creds = cosyCredsFromConnection(credentials);
   if (!creds.userId || !creds.authToken) return null;
 
-  // Job-token traffic is rejected by api3 ("Login expired" 403) — the
-  // official qodercli serves it from api2 instead.
-  const modelListUrl = String(creds.authToken).startsWith("jt-")
-    ? `${QODER_CHAT_BASE_ALT}/algo/api/v2/model/list`
-    : QODER_MODEL_LIST_URL;
-
   const headers = {
     Accept: "application/json",
     "Accept-Encoding": "identity",
-    ...buildCosyHeaders(Buffer.alloc(0), modelListUrl, creds),
+    ...buildCosyHeaders(Buffer.alloc(0), QODER_MODEL_LIST_URL, creds),
   };
 
   const controller = new AbortController();
@@ -226,7 +92,7 @@ async function fetchQoderCatalogRaw(credentials, signal, proxyOptions = null) {
       }
     }
     response = await proxyAwareFetch(
-      modelListUrl,
+      QODER_MODEL_LIST_URL,
       {
         method: "GET",
         headers,
@@ -293,16 +159,11 @@ export async function getQoderModelConfig(credentials, modelKey, options = {}) {
  * one upstream request per credential.
  */
 export async function resolveQoderModels(credentials, options = {}) {
-  let resolved;
-  try {
-    resolved = await resolveQoderCredentials(credentials, options.proxyOptions, options.signal);
-  } catch (error) {
-    options.log?.warn?.("QODER", `PAT exchange failed: ${error.message}`);
-    return null;
-  }
-  if (!resolved?.accessToken || !(resolved.providerSpecificData || {}).userId) return null;
+  if (!credentials?.accessToken) return null;
+  const psd = credentials.providerSpecificData || {};
+  if (!psd.userId) return null;
 
-  const key = cacheKey(resolved);
+  const key = cacheKey(credentials);
   const now = Date.now();
   if (!options.forceRefresh) {
     const cached = catalogCache.get(key);
@@ -319,7 +180,7 @@ export async function resolveQoderModels(credentials, options = {}) {
   }
 
   const fetchPromise = (async () => {
-    const fetched = await fetchQoderCatalogRaw(resolved, options.signal, options.proxyOptions);
+    const fetched = await fetchQoderCatalogRaw(credentials, options.signal, options.proxyOptions);
     if (!fetched) return null;
     const entry = {
       expiresAt: Date.now() + CACHE_TTL_MS,

open-sse/services/tokenRefresh.js

@@ -6,6 +6,7 @@ import {
   refreshKimiToken,
   refreshClaudeOAuthToken,
   refreshGoogleToken,
+  refreshQwenToken,
   refreshCodexToken,
   refreshKiroToken,
   refreshIflowToken,
@@ -25,6 +26,7 @@ export {
   refreshKimiToken,
   refreshClaudeOAuthToken,
   refreshGoogleToken,
+  refreshQwenToken,
   refreshCodexToken,
   refreshKiroToken,
   refreshIflowToken,
@@ -135,6 +137,7 @@ const REFRESH_HANDLERS = {
   antigravity: (c, log) => refreshGoogleToken(c.refreshToken, PROVIDERS.antigravity.clientId, PROVIDERS.antigravity.clientSecret, log),
   claude: (c, log) => refreshClaudeOAuthToken(c.refreshToken, log),
   codex: (c, log) => refreshCodexToken(c.refreshToken, log),
+  qwen: (c, log) => refreshQwenToken(c.refreshToken, log),
   iflow: (c, log) => refreshIflowToken(c.refreshToken, log),
   github: (c, log) => refreshGitHubToken(c.refreshToken, log),
   kiro: (c, log) => refreshKiroToken(c.refreshToken, c.providerSpecificData, log),
@@ -202,6 +205,7 @@ export function formatProviderCredentials(provider, credentials, log) {
       };
 
     case "codex":
+    case "qwen":
     case "iflow":
     case "openai":
     case "openrouter":

open-sse/services/tokenRefresh/providers.js

@@ -40,6 +40,11 @@ const REFRESH_PROFILES = {
     url: () => OAUTH_ENDPOINTS.anthropic.token,
     dedupKey: "claude",
   },
+  qwen: {
+    url: () => OAUTH_ENDPOINTS.qwen.token,
+    dedupKey: "qwen",
+    parse: (tokens) => tokens.resource_url ? { providerSpecificData: { resourceUrl: tokens.resource_url } } : {},
+  },
   iflow: {
     url: () => OAUTH_ENDPOINTS.iflow.token,
     dedupKey: "iflow",
@@ -186,6 +191,11 @@ export async function refreshGoogleToken(refreshToken, clientId, clientSecret, l
   }, log);
 }
 
+// Qwen: form body + clientId, surfaces resource_url. Delegate to refreshAccessToken("qwen", ...).
+export async function refreshQwenToken(refreshToken, log) {
+  return refreshAccessToken("qwen", refreshToken, {}, log);
+}
+
 export function classifyOAuthRefreshError(errorText = "", status = 0) {
   let parsed = null;
   try {

open-sse/services/usage.js

@@ -10,12 +10,14 @@ import { getCodexUsage, consumeCodexRateLimitResetCredit, getCodexRateLimitReset
 export { consumeCodexRateLimitResetCredit, getCodexRateLimitResetCredits };
 import { getKiroUsage } from "./usage/kiro.js";
 import { getMiniMaxUsage } from "./usage/minimax.js";
-import { getCodeBuddyCnUsage, getCodeBuddyIntlUsage } from "./usage/codebuddy-cn.js";
+import { getCodeBuddyCnUsage } from "./usage/codebuddy-cn.js";
+import { getXaiUsage } from "./usage/xai.js";
 import { getGrokCliUsage } from "./usage/grok-cli.js";
 import { getKimiUsage } from "./usage/kimi.js";
 import { getDeepseekUsage } from "./usage/deepseek.js";
-import { resolveQoderCredentials } from "./qoderModels.js";
+import { getCommandCodeUsage } from "./usage/commandcode.js";
 import {
+  getQwenUsage,
   getIflowUsage,
   getOllamaUsage,
   getGlmUsage,
@@ -33,30 +35,27 @@ const USAGE_HANDLERS = {
   github: (c) => getGitHubUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
   "gemini-cli": (c) => getGeminiUsage(c.accessToken, c.providerDataWithProjectId, c.proxyOptions),
   antigravity: (c) => getAntigravityUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
-  claude: (c) => getClaudeUsage(c.accessToken, c.proxyOptions, { force: c.force }),
+  claude: (c) => getClaudeUsage(c.accessToken, c.proxyOptions),
   codex: (c) => getCodexUsage(c.accessToken, c.proxyOptions),
   kiro: (c) => getKiroUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
-  qoder: async (c) => {
-    // PAT (pt-...) connections must be exchanged to a job token before the
-    // quota endpoint accepts them.
-    const resolved = await resolveQoderCredentials(c, c.proxyOptions).catch(() => null);
-    return getQoderUsage(resolved?.accessToken || c.accessToken, c.proxyOptions);
-  },
+  qoder: (c) => getQoderUsage(c.accessToken, c.proxyOptions),
+  qwen: (c) => getQwenUsage(c.accessToken, c.providerSpecificData),
   iflow: (c) => getIflowUsage(c.accessToken),
-  ollama: (c) => getOllamaUsage(c.apiKey, c.providerSpecificData, c.proxyOptions),
+  ollama: (c) => getOllamaUsage(c.accessToken),
   glm: (c) => getGlmUsage(c.apiKey, c.provider, c.proxyOptions),
   "glm-cn": (c) => getGlmUsage(c.apiKey, c.provider, c.proxyOptions),
   minimax: (c) => getMiniMaxUsage(c.apiKey, c.provider, c.proxyOptions),
   "minimax-cn": (c) => getMiniMaxUsage(c.apiKey, c.provider, c.proxyOptions),
   "vercel-ai-gateway": (c) => getVercelAiGatewayUsage(c.apiKey, c.proxyOptions),
   "codebuddy-cn": (c) => getCodeBuddyCnUsage(c.accessToken, c.apiKey, c.providerSpecificData, c.proxyOptions),
-  "codebuddy-intl": (c) => getCodeBuddyIntlUsage(c.accessToken, c.apiKey, c.providerSpecificData, c.proxyOptions),
+  xai: (c) => getXaiUsage(c.accessToken, c.proxyOptions),
   "grok-cli": (c) => getGrokCliUsage(c.accessToken, c.providerSpecificData, c.proxyOptions),
   kimi: (c) => getKimiUsage(c.accessToken, c.apiKey, c.proxyOptions, c.providerSpecificData),
   deepseek: (c) => getDeepseekUsage(c.apiKey, c.proxyOptions),
+  commandcode: (c) => getCommandCodeUsage(c.apiKey, c.proxyOptions),
 };
 
-export async function getUsageForProvider(connection, proxyOptions = null, options = {}) {
+export async function getUsageForProvider(connection, proxyOptions = null) {
   const { provider, accessToken, apiKey, providerSpecificData, projectId } = connection;
   const providerDataWithProjectId = {
     ...(providerSpecificData || {}),
@@ -65,13 +64,5 @@ export async function getUsageForProvider(connection, proxyOptions = null, optio
 
   const handler = USAGE_HANDLERS[provider];
   if (!handler) return { message: `Usage API not implemented for ${provider}` };
-  return await handler({
-    provider,
-    accessToken,
-    apiKey,
-    providerSpecificData,
-    providerDataWithProjectId,
-    proxyOptions,
-    force: options.force === true,
-  });
+  return await handler({ provider, accessToken, apiKey, providerSpecificData, providerDataWithProjectId, proxyOptions });
 }

open-sse/services/usage/claude.js

@@ -19,43 +19,7 @@ const CLAUDE_CONFIG = {
 const OAUTH_429_COOLDOWN_MS = 180000;
 const oauthCooldown = new Map();
 
-// Dedup + short TTL cache per access token. Many tabs / many accounts / auto-refresh
-// all funnel through here; without this each call hits Anthropic and triggers 429.
-const USAGE_CACHE_TTL_MS = 300000;
-const usageCache = new Map(); // token -> { promise } | { result, expiresAt }
-
-export async function getClaudeUsage(accessToken, proxyOptions = null, options = {}) {
-  const force = options?.force === true;
-
-  // Serve in-flight or fresh cached result (skip on manual force)
-  if (!force && accessToken) {
-    const hit = usageCache.get(accessToken);
-    if (hit?.promise) return hit.promise;
-    if (hit && hit.expiresAt > Date.now()) return hit.result;
-  }
-
-  const stale = (!force && accessToken && usageCache.get(accessToken)?.result) || null;
-
-  const promise = (async () => {
-    const result = await fetchClaudeUsageRaw(accessToken, proxyOptions);
-    // Only cache real quota data, not soft-failure {message: ...} payloads
-    if (accessToken && result?.quotas) {
-      usageCache.set(accessToken, {
-        result,
-        expiresAt: Date.now() + USAGE_CACHE_TTL_MS,
-      });
-      return result;
-    }
-    // Soft failure (429/error): prefer the last good read over a transient error
-    if (stale) return stale;
-    return result;
-  })();
-
-  if (accessToken) usageCache.set(accessToken, { promise });
-  return promise;
-}
-
-async function fetchClaudeUsageRaw(accessToken, proxyOptions = null) {
+export async function getClaudeUsage(accessToken, proxyOptions = null) {
   try {
     // Skip OAuth usage call while this token is cooling down from a recent 429
     const cooldownUntil = oauthCooldown.get(accessToken);

open-sse/services/usage/codebuddy-cn.js

@@ -43,17 +43,17 @@ function refillCadence(acc) {
   return "Monthly";
 }
 
-async function getCodeBuddyUsage(providerId, accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
   const token = accessToken || apiKey;
   if (!token) {
-    return { message: `CodeBuddy (${providerId}) credential not available.` };
+    return { message: "CodeBuddy CN credential not available." };
   }
 
   try {
-    const response = await proxyAwareFetch(U(providerId).url, {
+    const response = await proxyAwareFetch(U(PROVIDER_ID).url, {
       method: "POST",
       headers: {
-        ...(PROVIDERS[providerId]?.headers || {}),
+        ...(PROVIDERS[PROVIDER_ID]?.headers || {}),
         Authorization: `Bearer ${token}`,
         "Content-Type": "application/json",
         Accept: "application/json",
@@ -129,18 +129,10 @@ async function getCodeBuddyUsage(providerId, accessToken, apiKey, providerSpecif
     });
 
     const basePkg = refills[0] || accounts[0] || {};
-    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy";
+    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy CN";
 
     return { plan, quotas };
   } catch (error) {
-    return { message: `CodeBuddy (${providerId}) error: ${error.message}` };
+    return { message: `CodeBuddy CN error: ${error.message}` };
   }
 }
-
-export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
-  return getCodeBuddyUsage(PROVIDER_ID, accessToken, apiKey, providerSpecificData, proxyOptions);
-}
-
-export async function getCodeBuddyIntlUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
-  return getCodeBuddyUsage("codebuddy-intl", accessToken, apiKey, providerSpecificData, proxyOptions);
-}

open-sse/services/usage/commandcode.js

@@ -0,0 +1,203 @@
+/**
+ * CommandCode usage handler
+ *
+ * Mirrors the official command-code CLI /usage command: it calls the alpha API
+ * to surface the 5-hour + weekly usage windows, the subscription plan, and the
+ * credits consumed in the current billing period.
+ *
+ *   GET /alpha/whoami                → org.id (org-scoped billing; null for personal)
+ *   GET /alpha/billing/credits       → { credits: { monthlyCredits, purchasedCredits,
+ *                                      freeCredits }, windowLimits: { fiveHour, weekly } }
+ *   GET /alpha/billing/subscriptions → { data: { planId, currentPeriodStart, ... } }
+ *   GET /alpha/usage/summary?since=  → period token/cost totals
+ *
+ * The CLI fetches whoami first (for orgId), then credits + subscription in
+ * parallel, then the summary with since = currentPeriodStart. We keep the same
+ * order/dependencies: window limits live on credits, and the plan period start
+ * determines the summary window.
+ */
+
+import { proxyAwareFetch } from "../../utils/proxyFetch.js";
+import { U, parseResetTime } from "./shared.js";
+
+const USAGE = U("commandcode");
+const BASE = USAGE.baseUrl || "https://api.commandcode.ai";
+const WHOAMI_URL = BASE + (USAGE.whoamiUrl || "/alpha/whoami");
+const CREDITS_URL = BASE + (USAGE.creditsUrl || "/alpha/billing/credits");
+const SUBSCRIPTIONS_URL =
+	BASE + (USAGE.subscriptionsUrl || "/alpha/billing/subscriptions");
+const SUMMARY_URL = BASE + (USAGE.summaryUrl || "/alpha/usage/summary");
+
+function buildHeaders(token) {
+	return {
+		Authorization: `Bearer ${token}`,
+		Accept: "application/json",
+	};
+}
+
+/** Build a normalized quota row. `unit` is "$" — the API reports currency credits. */
+function makeQuota({ used, total, resetAt, unlimited = false, unit = "$" }) {
+	const safeTotal = Math.max(0, Number(total) || 0);
+	const safeUsed = Math.max(0, Number(used) || 0);
+	if (unlimited || safeTotal === 0) {
+		return {
+			used: safeUsed,
+			total: 0,
+			remainingPercentage: unlimited ? 100 : 0,
+			resetAt: resetAt || null,
+			unit,
+			unlimited: true,
+		};
+	}
+	const remaining = Math.max(0, safeTotal - safeUsed);
+	const remainingPercentage = (remaining / safeTotal) * 100;
+	return {
+		used: safeUsed,
+		total: safeTotal,
+		remainingPercentage,
+		resetAt: resetAt || null,
+		unit,
+		unlimited: false,
+	};
+}
+
+/**
+ * @param {string} apiKey - commandcode API key (user_...)
+ * @param {object|null} proxyOptions
+ */
+export async function getCommandCodeUsage(apiKey, proxyOptions = null) {
+	if (!apiKey) {
+		return { message: "CommandCode credential not available." };
+	}
+
+	const headers = buildHeaders(apiKey);
+
+	try {
+		// whoami resolves the org id (billing is org-scoped; null for personal).
+		const whoamiRes = await proxyAwareFetch(
+			WHOAMI_URL,
+			{ method: "GET", headers },
+			proxyOptions,
+		);
+		if (whoamiRes.status === 401 || whoamiRes.status === 403) {
+			return { message: "CommandCode credential invalid or expired." };
+		}
+		if (!whoamiRes.ok) {
+			return { message: `CommandCode whoami API error (${whoamiRes.status}).` };
+		}
+		const whoami = await whoamiRes.json().catch(() => null);
+		const orgId = whoami?.org?.id ?? null;
+
+		const orgQuery = orgId ? `?orgId=${encodeURIComponent(orgId)}` : "";
+
+		const [creditsRes, subsRes] = await Promise.all([
+			proxyAwareFetch(
+				CREDITS_URL + orgQuery,
+				{ method: "GET", headers },
+				proxyOptions,
+			),
+			proxyAwareFetch(
+				SUBSCRIPTIONS_URL + orgQuery,
+				{ method: "GET", headers },
+				proxyOptions,
+			),
+		]);
+
+		if (
+			creditsRes.status === 401 ||
+			creditsRes.status === 403 ||
+			subsRes.status === 401 ||
+			subsRes.status === 403
+		) {
+			return { message: "CommandCode credential invalid or expired." };
+		}
+		if (!creditsRes.ok) {
+			return {
+				message: `CommandCode credits API error (${creditsRes.status}).`,
+			};
+		}
+
+		const credits = await creditsRes.json().catch(() => null);
+		const subs = await subsRes.json().catch(() => null);
+
+		const subData = subs?.data;
+		const planId = subData?.planId ?? null;
+		const periodStart = subData?.currentPeriodStart ?? null;
+
+		// Summary needs `since`; the CLI falls back to first-of-month when the
+		// subscription period start is unavailable.
+		const since = periodStart || firstOfMonth();
+		const summaryRes = await proxyAwareFetch(
+			`${SUMMARY_URL}?since=${encodeURIComponent(since)}`,
+			{ method: "GET", headers },
+			proxyOptions,
+		);
+		const summary = summaryRes.ok
+			? await summaryRes.json().catch(() => null)
+			: null;
+
+		const quotas = {};
+		const windowLimits = credits?.windowLimits || {};
+
+		const fiveHour = windowLimits.fiveHour;
+		if (fiveHour && Number(fiveHour.cap) > 0) {
+			quotas["5-hour window"] = makeQuota({
+				used: fiveHour.used,
+				total: fiveHour.cap,
+				resetAt: parseResetTime(fiveHour.resetAt),
+			});
+		}
+
+		const weekly = windowLimits.weekly;
+		if (weekly && Number(weekly.cap) > 0) {
+			quotas["Weekly window"] = makeQuota({
+				used: weekly.used,
+				total: weekly.cap,
+				resetAt: parseResetTime(weekly.resetAt),
+			});
+		}
+
+		// Monthly credits consumed this billing period (from summary when present,
+		// else the credits object's monthlyCredits as a fallback).
+		const monthlyUsed =
+			typeof summary?.totalCredits === "number"
+				? summary.totalCredits
+				: typeof credits?.credits?.monthlyCredits === "number"
+					? credits.credits.monthlyCredits
+					: 0;
+
+		const monthlyTotal =
+			typeof credits?.credits?.monthlyCredits === "number"
+				? credits.credits.monthlyCredits
+				: 0;
+
+		if (monthlyTotal > 0 || monthlyUsed > 0) {
+			quotas["Monthly credits"] = makeQuota({
+				used: monthlyUsed,
+				total: monthlyTotal,
+				resetAt: periodStart ? undefined : null,
+			});
+		}
+
+		if (Object.keys(quotas).length === 0) {
+			return {
+				plan: planId || "CommandCode",
+				message: "CommandCode connected, but no quota was reported.",
+				quotas: {},
+			};
+		}
+
+		return {
+			plan: planId || "CommandCode",
+			quotas,
+			periodBasis: summary?.periodBasis || "billing-period",
+		};
+	} catch (error) {
+		return { message: `CommandCode usage error: ${error.message}` };
+	}
+}
+
+function firstOfMonth() {
+	const now = new Date();
+	return new Date(now.getFullYear(), now.getMonth(), 1).toISOString();
+}

open-sse/services/usage/google.js

@@ -161,12 +161,7 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
     if (data.models) {
       // Filter only recommended/important models (must match PROVIDER_MODELS ag ids)
       const importantModels = [
-        'gemini-3.7-flash-high',
-        'gemini-3.7-flash-medium',
-        'gemini-3.7-flash-low',
-        'gemini-3.6-flash-high',
-        'gemini-3.6-flash-medium',
-        'gemini-3.6-flash-low',
+        'gemini-3-flash-agent',
         'gemini-3.5-flash-low',
         'gemini-3.5-flash-extra-low',
         'gemini-pro-agent',
@@ -174,8 +169,10 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
         'claude-sonnet-4-6',
         'claude-opus-4-6-thinking',
         'gpt-oss-120b-medium',
+        'gemini-3-flash',
         // Image generation models
         'gemini-3.1-flash-image',
+        'gemini-3-pro-image',
       ];
 
       for (const [modelKey, info] of Object.entries(data.models)) {

open-sse/services/usage/grok-cli.js

@@ -91,24 +91,6 @@ function resolvePlan(user, config) {
   return "Grok Build";
 }
 
-// Display only; upstream remains authoritative for access and quota enforcement.
-function planFromAccessToken(accessToken) {
-  try {
-    const payload = JSON.parse(Buffer.from(accessToken.split(".")[1], "base64url"));
-    return {
-      0: "Free",
-      1: "SuperGrok",
-      2: "X Basic",
-      3: "X Premium",
-      4: "X Premium Plus",
-      5: "SuperGrok Heavy",
-      6: "SuperGrok Lite",
-    }[payload.tier] || "";
-  } catch {
-    return "";
-  }
-}
-
 function makeQuota({ used, total, resetAt, unlimited = false }) {
   const safeTotal = Math.max(0, toFiniteNumber(total, 0));
   const safeUsed = Math.max(0, toFiniteNumber(used, 0));
@@ -389,7 +371,6 @@ export async function getGrokCliUsage(accessToken, providerSpecificData = null,
     }
 
     const parsed = parseGrokCliBilling(billing, user);
-    parsed.plan = planFromAccessToken(accessToken) || parsed.plan;
 
     if (!parsed.quotas || Object.keys(parsed.quotas).length === 0) {
       // Paid SuperGrok often returns cap=0 over REST but exposes the shared

open-sse/services/usage/misc.js

@@ -1,5 +1,5 @@
 /**
- * Misc usage handlers (iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
+ * Misc usage handlers (Qwen, iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
  */
 
 import { proxyAwareFetch } from "../../utils/proxyFetch.js";
@@ -15,6 +15,23 @@ const GLM_QUOTA_URLS = {
 // Returns { balance: "95.50", total_used: "4.50" } (USD as decimal strings).
 const VERCEL_AI_GATEWAY_CREDITS_URL = U("vercel-ai-gateway").url;
 
+/**
+ * Qwen Usage
+ */
+export async function getQwenUsage(accessToken, providerSpecificData) {
+  try {
+    const resourceUrl = providerSpecificData?.resourceUrl;
+    if (!resourceUrl) {
+      return { message: "Qwen connected. No resource URL available." };
+    }
+
+    // Qwen may have usage endpoint at resource URL
+    return { message: "Qwen connected. Usage tracked per request." };
+  } catch (error) {
+    return { message: "Unable to fetch Qwen usage." };
+  }
+}
+
 /**
  * iFlow Usage
  */
@@ -29,86 +46,23 @@ export async function getIflowUsage(accessToken) {
 
 /**
  * Ollama Cloud Usage
- * GET https://ollama.com/api/usage — session (5h) + weekly (7d) `usage` is a 0..1
- *   ratio (1.0 = limit reached, e.g. weekly 100% used). No reset timestamp exposed.
- * POST https://ollama.com/api/me — plan label (fail-open).
- * Auth: Authorization: Bearer <apiKey>
+ * Ollama Cloud uses an API key from ollama.com/settings/keys
+ * and has no public usage API — free tier has light usage limits (resets every 5h & 7d).
+ * This returns an informational message with the plan details.
  */
-export async function getOllamaUsage(apiKey, providerSpecificData, proxyOptions = null) {
-  if (!apiKey) {
-    return { message: "Ollama Cloud API key not available." };
-  }
-
+export async function getOllamaUsage(accessToken, providerSpecificData) {
   try {
-    const response = await proxyAwareFetch("https://ollama.com/api/usage", {
-      headers: {
-        Authorization: `Bearer ${apiKey}`,
-        Accept: "application/json",
-      },
-    }, proxyOptions);
-
-    if (response.status === 401 || response.status === 403) {
-      return { message: "Ollama Cloud API key invalid or expired." };
-    }
-
-    if (!response.ok) {
-      return { message: `Ollama Cloud usage API error (${response.status}).` };
-    }
-
-    let data;
-    try {
-      data = await response.json();
-    } catch {
-      return { message: "Ollama Cloud usage response was not JSON." };
-    }
-
-    // Best-effort plan label from /api/me
-    const me = await proxyAwareFetch("https://ollama.com/api/me", {
-      method: "POST",
-      headers: {
-        Authorization: `Bearer ${apiKey}`,
-        Accept: "application/json",
-        "Content-Length": "0",
-      },
-    }, proxyOptions).then((r) => (r.ok ? r.json() : null)).catch(() => null);
-
-    const planRaw = typeof me?.Plan === "string" ? me.Plan : "";
-    const plan = planRaw
-      ? planRaw.charAt(0).toUpperCase() + planRaw.slice(1).toLowerCase()
-      : "Ollama Cloud";
-
-    const limits = data?.limits && typeof data.limits === "object" ? data.limits : {};
-
-    // Ollama `usage` is a 0..1 ratio (1.0 = limit reached). Convert to a 0..100
-    // bar. Do NOT set absolute `remaining` — QuotaTable reads remainingPercentage.
-    function ratioQuota(usageRatio, resetAt = null) {
-      const ratio = Math.max(0, Math.min(1, Number(usageRatio) || 0));
-      const usedPct = Math.round(ratio * 100);
-      return { used: usedPct, total: 100, remainingPercentage: 100 - usedPct, resetAt, unlimited: false };
-    }
-
-    const sessionRaw = limits.session?.usage;
-    const weeklyRaw = limits.weekly?.usage;
-    const sessionNum = Number(sessionRaw);
-    const weeklyNum = Number(weeklyRaw);
-    const hasSession = sessionRaw !== undefined && sessionRaw !== null && !Number.isNaN(sessionNum);
-    const hasWeekly = weeklyRaw !== undefined && weeklyRaw !== null && !Number.isNaN(weeklyNum);
-
-    if (!hasSession && !hasWeekly) {
+    // Ollama Cloud does not expose a public quota/usage API.
+    // The provider is configured as noAuth with a notice explaining limits.
+    // We return a graceful message so the UI shows a friendly state instead of an error.
+    const plan = providerSpecificData?.plan || "Free";
     return {
       plan,
-        message: "Ollama Cloud connected. No usage limits reported.",
-        quotas: {},
+      message: "Ollama Cloud uses a free tier with light usage limits (resets every 5h & 7d). For detailed usage tracking, visit ollama.com/settings/keys.",
+      quotas: [],
     };
-    }
-
-    const quotas = {};
-    if (hasSession) quotas["Session (5h)"] = ratioQuota(sessionNum);
-    if (hasWeekly) quotas["Weekly (7d)"] = ratioQuota(weeklyNum);
-
-    return { plan, quotas };
   } catch (error) {
-    return { message: `Ollama Cloud error: ${error.message}` };
+    return { message: "Unable to fetch Ollama Cloud usage." };
   }
 }
 

open-sse/services/usage/xai.js

@@ -0,0 +1,326 @@
+/**
+ * xAI (Grok) OAuth usage handler
+ *
+ * SuperGrok quota is split across two upstream surfaces (OAuth only):
+ *
+ * 1) Monthly / API usage allotment (JSON)
+ *    GET https://cli-chat-proxy.grok.com/v1/billing
+ *    {
+ *      "config": {
+ *        "monthlyLimit": { "val": 15000 },
+ *        "used": { "val": 733 },
+ *        "onDemandCap": { "val": 0 },
+ *        "billingPeriodStart": "...",
+ *        "billingPeriodEnd": "..."
+ *      }
+ *    }
+ *
+ * 2) Weekly SuperGrok limit (grpc-web protobuf)
+ *    POST https://grok.com/grok_api_v2.GrokBuildBilling/GetGrokCreditsConfig
+ *    Empty request frame; response message1 contains:
+ *      usedPercent (float32), window start/end timestamps, nested windows.
+ *    This is what the grok.com usage page labels "Weekly limit" / "Resets …".
+ *
+ * Plan label comes from cli-chat-proxy settings:
+ *    GET https://cli-chat-proxy.grok.com/v1/settings → subscription_tier_display
+ *
+ * Note: grok.com/rest/rate-limits is a short chat-window (e.g. 2h query count)
+ * behind Cloudflare browser cookies — not usable with pure OAuth bearer.
+ */
+
+import { proxyAwareFetch } from "../../utils/proxyFetch.js";
+import { U, parseResetTime, toFiniteNumber } from "./shared.js";
+
+// Empty grpc-web request frame: flag(0) + length(0) + no payload.
+const GRPC_WEB_EMPTY_FRAME = Buffer.from([0x00, 0x00, 0x00, 0x00, 0x00]);
+
+function moneyVal(wrapper) {
+  if (wrapper == null) return null;
+  if (typeof wrapper === "number") return toFiniteNumber(wrapper, null);
+  if (typeof wrapper === "object" && wrapper.val != null) {
+    return toFiniteNumber(wrapper.val, null);
+  }
+  return null;
+}
+
+function authHeaders(accessToken, extra = {}) {
+  return {
+    Authorization: `Bearer ${accessToken}`,
+    ...extra,
+  };
+}
+
+function readVarint(buf, offset) {
+  let val = 0;
+  let shift = 0;
+  let i = offset;
+  while (i < buf.length) {
+    const b = buf[i++];
+    val |= (b & 0x7f) << shift;
+    if ((b & 0x80) === 0) return { value: val >>> 0, offset: i };
+    shift += 7;
+    if (shift > 35) break;
+  }
+  return null;
+}
+
+/**
+ * Minimal protobuf decoder for GetGrokCreditsConfig.
+ * Only understands varint / fixed32 / fixed64 / length-delimited.
+ */
+function parseProtobufFields(buf) {
+  const fields = [];
+  let i = 0;
+  while (i < buf.length) {
+    const key = readVarint(buf, i);
+    if (!key) break;
+    i = key.offset;
+    const field = key.value >>> 3;
+    const wt = key.value & 7;
+
+    if (wt === 0) {
+      const v = readVarint(buf, i);
+      if (!v) break;
+      i = v.offset;
+      fields.push({ field, type: "varint", value: v.value });
+    } else if (wt === 1) {
+      if (i + 8 > buf.length) break;
+      fields.push({ field, type: "fixed64", value: buf.subarray(i, i + 8) });
+      i += 8;
+    } else if (wt === 5) {
+      if (i + 4 > buf.length) break;
+      fields.push({
+        field,
+        type: "fixed32",
+        value: buf.readFloatLE(i),
+      });
+      i += 4;
+    } else if (wt === 2) {
+      const ln = readVarint(buf, i);
+      if (!ln) break;
+      i = ln.offset;
+      if (i + ln.value > buf.length) break;
+      fields.push({
+        field,
+        type: "bytes",
+        value: buf.subarray(i, i + ln.value),
+      });
+      i += ln.value;
+    } else {
+      break;
+    }
+  }
+  return fields;
+}
+
+function parseTimestamp(bytes) {
+  if (!bytes || !bytes.length) return null;
+  const fields = parseProtobufFields(bytes);
+  const seconds = fields.find((f) => f.field === 1 && f.type === "varint")?.value;
+  if (!Number.isFinite(seconds) || seconds <= 0) return null;
+  return new Date(seconds * 1000).toISOString();
+}
+
+/**
+ * Parse grpc-web response bytes from GetGrokCreditsConfig.
+ * Returns { usedPercent, resetAt, periodStart } or null.
+ */
+export function parseGrokCreditsConfig(raw) {
+  if (!raw || !raw.length) return null;
+  const buf = Buffer.isBuffer(raw) ? raw : Buffer.from(raw);
+
+  // grpc-web data frame: 1-byte flag + 4-byte big-endian length + message
+  if (buf.length < 5) return null;
+  const flag = buf[0];
+  // Data frames have flag 0; ignore trailer frames (flag 0x80).
+  if (flag !== 0) return null;
+  const msgLen = buf.readUInt32BE(1);
+  if (msgLen <= 0 || 5 + msgLen > buf.length) return null;
+  const msg = buf.subarray(5, 5 + msgLen);
+
+  // Response is typically { 1: CreditsConfig }
+  const top = parseProtobufFields(msg);
+  const configBytes = top.find((f) => f.field === 1 && f.type === "bytes")?.value || msg;
+  const fields = parseProtobufFields(configBytes);
+
+  const usedPercentRaw = fields.find((f) => f.field === 1 && f.type === "fixed32")?.value;
+  const periodStart = parseTimestamp(fields.find((f) => f.field === 4 && f.type === "bytes")?.value);
+  const periodEnd = parseTimestamp(fields.find((f) => f.field === 5 && f.type === "bytes")?.value);
+
+  if (usedPercentRaw == null || !Number.isFinite(usedPercentRaw)) return null;
+
+  const usedPercent = Math.max(0, Math.min(100, usedPercentRaw));
+  return {
+    usedPercent,
+    remainingPercent: Math.max(0, 100 - usedPercent),
+    periodStart,
+    resetAt: periodEnd,
+  };
+}
+
+async function fetchBilling(accessToken, billingUrl, proxyOptions) {
+  const response = await proxyAwareFetch(billingUrl, {
+    method: "GET",
+    headers: authHeaders(accessToken, { Accept: "application/json" }),
+  }, proxyOptions);
+
+  if (response.status === 401 || response.status === 403) {
+    return { error: "auth", status: response.status };
+  }
+  if (!response.ok) {
+    return { error: "http", status: response.status };
+  }
+
+  const data = await response.json().catch(() => null);
+  if (!data || typeof data !== "object") {
+    return { error: "json" };
+  }
+  return { data };
+}
+
+async function fetchWeeklyCredits(accessToken, creditsUrl, proxyOptions) {
+  if (!creditsUrl) return null;
+  try {
+    const response = await proxyAwareFetch(creditsUrl, {
+      method: "POST",
+      headers: authHeaders(accessToken, {
+        "Content-Type": "application/grpc-web+proto",
+        "x-grpc-web": "1",
+        "x-user-agent": "connect-es/2.1.1",
+        Accept: "*/*",
+        Origin: "https://grok.com",
+        Referer: "https://grok.com/?_s=usage",
+      }),
+      body: GRPC_WEB_EMPTY_FRAME,
+    }, proxyOptions);
+
+    if (!response.ok) return null;
+    const ab = await response.arrayBuffer();
+    return parseGrokCreditsConfig(Buffer.from(ab));
+  } catch {
+    return null;
+  }
+}
+
+async function fetchPlanLabel(accessToken, settingsUrl, proxyOptions) {
+  if (!settingsUrl) return null;
+  try {
+    const response = await proxyAwareFetch(settingsUrl, {
+      method: "GET",
+      headers: authHeaders(accessToken, { Accept: "application/json" }),
+    }, proxyOptions);
+    if (!response.ok) return null;
+    const data = await response.json().catch(() => null);
+    const label = data?.subscription_tier_display;
+    return typeof label === "string" && label.trim() ? label.trim() : null;
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * @param {string} accessToken - xAI OAuth access token
+ * @param {object|null} proxyOptions
+ */
+export async function getXaiUsage(accessToken, proxyOptions = null) {
+  if (!accessToken) {
+    return { message: "xAI usage unavailable: no access token. Re-authorize the connection." };
+  }
+
+  const cfg = U("xai") || {};
+  const billingUrl = cfg.url;
+  if (!billingUrl) {
+    return { message: "xAI usage endpoint is not configured." };
+  }
+
+  try {
+    const [billingResult, weekly, planLabel] = await Promise.all([
+      fetchBilling(accessToken, billingUrl, proxyOptions),
+      fetchWeeklyCredits(accessToken, cfg.creditsUrl, proxyOptions),
+      fetchPlanLabel(accessToken, cfg.settingsUrl, proxyOptions),
+    ]);
+
+    if (billingResult.error === "auth") {
+      return { message: "xAI OAuth token expired or unauthorized. Please re-authorize." };
+    }
+
+    const quotas = {};
+    let periodStart = null;
+    let periodEnd = null;
+    let onDemandCap = 0;
+
+    if (billingResult.data) {
+      const config =
+        billingResult.data.config && typeof billingResult.data.config === "object"
+          ? billingResult.data.config
+          : billingResult.data;
+      const monthlyLimit = moneyVal(config.monthlyLimit);
+      const used = moneyVal(config.used);
+      onDemandCap = moneyVal(config.onDemandCap) ?? 0;
+      periodEnd = parseResetTime(config.billingPeriodEnd);
+      periodStart = parseResetTime(config.billingPeriodStart);
+
+      // Absolute credit counts — do NOT put remaining credits on `remaining`
+      // (QuotaTable treats remaining as a 0-100 percentage; same pitfall as Qoder).
+      if (monthlyLimit != null && monthlyLimit > 0) {
+        const usedSafe = Math.max(0, used ?? 0);
+        quotas.api_usage = {
+          used: usedSafe,
+          total: monthlyLimit,
+          remainingCredits: Math.max(0, monthlyLimit - usedSafe),
+          unit: "credits",
+          resetAt: periodEnd,
+          unlimited: false,
+        };
+      }
+
+      if (onDemandCap > 0) {
+        quotas.on_demand = {
+          used: 0,
+          total: onDemandCap,
+          remainingCredits: onDemandCap,
+          unit: "credits",
+          resetAt: periodEnd,
+          unlimited: false,
+        };
+      }
+    }
+
+    // Weekly SuperGrok window — percentage-based like Claude/Codex windows.
+    if (weekly) {
+      quotas.weekly = {
+        used: weekly.usedPercent,
+        total: 100,
+        remaining: weekly.remainingPercent,
+        remainingPercentage: weekly.remainingPercent,
+        resetAt: weekly.resetAt || null,
+        unlimited: false,
+      };
+      if (!periodStart && weekly.periodStart) periodStart = weekly.periodStart;
+    }
+
+    if (Object.keys(quotas).length === 0) {
+      const statusHint =
+        billingResult.error === "http"
+          ? ` Billing API temporarily unavailable (${billingResult.status}).`
+          : "";
+      return {
+        plan: planLabel || "xAI",
+        message: `xAI connected. No quota allotment reported for this account.${statusHint}`,
+        periodStart,
+        periodEnd,
+        quotas: {},
+      };
+    }
+
+    return {
+      plan: planLabel || "xAI",
+      periodStart,
+      periodEnd,
+      onDemandCap,
+      quotas,
+    };
+  } catch (error) {
+    return { message: `xAI connected. Unable to fetch billing: ${error.message}` };
+  }
+}

open-sse/shared/qoder/constants.js

@@ -11,9 +11,6 @@
 export const QODER_OPENAPI_BASE = "https://openapi.qoder.sh";
 export const QODER_CENTER_BASE = "https://center.qoder.sh";
 export const QODER_CHAT_BASE = "https://api3.qoder.sh";
-// Job-token (jt-...) traffic is rejected by api3 with "Login expired" (403);
-// the official qodercli serves it from api2 instead.
-export const QODER_CHAT_BASE_ALT = "https://api2.qoder.sh";
 
 export const QODER_LOGIN_URL = "https://qoder.com/device/selectAccounts";