## Features
- **Fetch**: add Ollama Cloud web fetch provider
- **Gemini / Antigravity**: add Gemini 3.8 Flash support and bump IDE fingerprint to 2.11.0
- **Claude**: add Claude Fable 5.1 support (adaptive thinking with `output_config.effort`), bump Claude Code fingerprint to 2.1.258 for new-model access
- **Providers**: add client-side status filter (All / Active / Inactive / No connection) on the Providers dashboard; add max height and scroll for connection list
- **Providers & Models**: streamline tokenrouter model catalog down to 22 flagship/newest models and add missing provider icons; refresh Codebuddy-CN catalog (add hy4-preview/hy3/glm-5.3/kimi-k3-1, drop EOL glm-5.0/glm-4.7)
- **Models**: capability toggles (vision, reasoning) when adding custom models with upsert and live caps refresh
- **CLI tools**: support saving and managing custom API key presets
- **Quota**: add usage and rate-limit tracking for Groq via `x-ratelimit-*` headers
- **i18n**: complete Indonesian translation (1391 keys)
## Fixes
- **Security**: close SSRF guard bypasses in `ssrfGuard.js` (alternate IPv6 encodings, hostname trailing dots, wildcard DNS resolution check, safe redirect handling) (#3714)
- **Model markers**: strip the `[1m]` context marker Claude Code appends to model names (`claude-opus-5[1m]`) preventing model resolution failures (#3690)
- **Claude**: drop `server_tool_use` blocks carrying foreign IDs to avoid Anthropic 400 rejections; never anchor cache breakpoints on `defer_loading` tools (#3567)
- **Antigravity**: strike-break optimistic quota readings that keep 429ing by blocking the connection+model pair for 15m after 3 strikes (#3681); preserve client identity on model catalog requests (#3414)
- **Auth**: protect root `/responses` rewrite requiring API key validation in dashboardGuard
- **Chat & Docker**: return 503 Service Unavailable when all credentials are rate-limited; explicitly bundle `node-machine-id` into standalone Docker runtime image
- **OpenCode**: route Muse Spark models to `/zen/v1/responses` and declare vision support; filter inactive free model
- **Kiro**: preserve inline images as OpenAI-compatible `image_url` parts in OpenAI MITM; remove redundant top-level `systemPrompt` from payload
- **Usage**: read Responses-shape `cached_tokens` in `extractUsageFromResponse` for non-streaming traffic
- **Models**: support single model lookup with provider-prefixed IDs (e.g. `cc/claude-sonnet-5`)
- **Translator**: route Gemini thinking through `reasoning_effort` on OpenAI-compatible wire; convert `prefixItems` and ensure array items in Gemini schema sanitizer
- **UI**: apply persisted theme before first paint to prevent flash on reload; translate combo vision adapter label
## Features
- **Search**: new web search providers — Antigravity (Google Search grounding
on the existing OAuth account pool, citations keyed and merged by URL) and
Xquik (X search with `x-api-key` auth, cursor pagination, credit-based
usage), both on `POST /v1/search`. Based on #3437 by @Nautilaceae
- **Search**: ollama-search and zai-search borrow a chat provider's API key
instead of requiring their own connection, driven by a new
`credentialFallback` registry field. zai-search later folded into the `glm`
provider itself so the web search page shows the shared connection
- **Models**: daily background sync of model capabilities from models.dev —
modalities keyed by model id (majority of sources must declare one),
context/output limits keyed by provider + model, strictly additive and
sitting below the hand-written tables. ETag + mtime cache, 60s startup
delay, `MODEL_CATALOG_SYNC=off` to disable
- **Models**: add GLM-5.3-Flash (1M context, natively multimodal), DeepSeek
V4 Vision, Grok 4.5/4.6 (500k context); correct glm-4.6v/4.5v video input
and output limits, backfill glm-4.6v on glm-cn
- **Usage**: show the Zed plan quota on the dashboard — plan, edit
predictions, hosted model requests and billing-cycle reset; unlimited rows
render as "N used · Unlimited"
- **Usage**: track GPT-5.3-Codex-Spark quota windows (spark_session /
spark_weekly) from the Codex usage response (#3431)
- **Antigravity**: quota-aware routing — on 409/429 fetch live quota for the
exact per-model resetAt and skip only the exhausted account/model pair;
report the earliest reset when every account is blocked (#3561)
- **Antigravity**: map image `size` to the aspect-ratio model suffix (-WxH);
add the Gemini 3.7 Flash tiers to MITM defaultModels so they show up in
the dashboard model-mapping table
- **Dashboard**: bulk import Grok CLI accounts from JSON — paste an array or
drag-drop multiple .json files, all OAuth connections created in a single
call, mirroring the codex flow
- **CLI tools**: endpoint presets shared across every tool card through one
live-resyncing store, instead of per-card localStorage copies that never
saw each other's saved endpoints
- **Token Saver**: configurable compression timeout (`headroomTimeoutMs`) —
the fixed 3000 ms made busy machines time out and send inconsistently
compressed bodies, hurting prompt caching
- **i18n**: pt-BR expanded to 1132 terms
## Fixes
- **Stream**: record usage when a client closes on the terminal event — the
Responses API has no [DONE] sentinel, so codex closed the socket on
`response.completed` and cancelled the reader before flush() ran its usage
side effects; the tail now lives in a once-guarded finalizeStream(). Also
stop logging a disconnect for every completed Responses call
- **Stream**: parse the trailing NDJSON line an Ollama stream leaves behind
without a closing newline — the final chunk carrying `done_reason` and the
token counts was dropped
- **Session**: read the Claude Code session id from the
`x-claude-code-session-id` header — `metadata.user_id` is dropped by
Responses translation, splitting one conversation across several
`prompt_cache_key` values and missing the upstream prefix cache
- **Usage**: preserve nested `cached_tokens` — the top-level-only read
persisted `cached_tokens: 0` for every Responses-format provider (codex,
grok-cli, …), billing cache hits at the full input rate
- **Usage**: GLM quotas accept CREDIT_LIMIT plans and multi-interval windows
(5h session / 7d weekly) instead of overwriting a single "session" key
- **Models**: the catalog sync no longer erases its own output — deltas were
measured against the previous run's writes (the second run cut `providers`
from 20 entries to 5); one vote per provider in the modality tally, ETag
restored from file on startup, and the worker thread dropped after the
bundler rewrote its path into a module-not-found error
- **Executor**: CommandCode returns errors as a `type:"error"` event inside
an HTTP 200 NDJSON stream — peek the first events before committing, abort
and return a real 4xx/5xx so combo/account fallback triggers instead of
streaming the error text as content
- **Search**: scope failure locks on the credential-fallback path — a failing
search locked `modelLock___all` and took the shared glm key offline for
chat as well; locks are now attributed to the connection's owner and
scoped to `websearch:<provider>`
- **Providers**: connection tests get a 15s AbortSignal timeout instead of
hanging and exhausting the browser socket pool; guard undefined provider
names on the providers page
- **Antigravity**: sanitize competing-client branding via a config-driven
rule table (Zed's Claude-agent prompt, opencode → antigravity) — upstream
answers 429 Quota Exhausted. Applied in the executor so the shared
openai-to-gemini translator leaves gemini/vertex/zed untouched
- **MiniMax**: preserve images on the sourceFormat-matched OpenAI transport
— MiniMax-M3 resolved a Claude-shaped body posted to the OpenAI endpoint,
silently dropping `image_url` blocks (#3418)
- **Claude**: decloak tool names in same-format streaming passthrough —
OAuth-cloaked names (CLAUDE_TOOL_SUFFIX) leaked to the client and every
tool call was rejected as unknown
- **Tools**: default a missing `tools[].type` to "custom" on Claude-format
requests — strict Anthropic-compatible gateways (MiniMax) reject the
request with 400 otherwise
- **Translator**: zai thinkingFormat sends the top-level `reasoning_effort`
object GLM-5.2+ requires — every GLM-5.x request ran at the model default
(max); gated on GLM-5.2+ since older GLM does not read it (#2721)
- **RTK**: system prompt injection matches each target wire format
(Chat/Responses/Claude/Gemini/Kiro) and is exact-idempotent across retries,
so distinct prompts sharing a long prefix are no longer collapsed (#3202).
Also set the diagnostic before the silent null return on Responses
translation failure so the panel is no longer blank
- **OpenCode**: route muse-spark through /zen/v1/responses (it 500s on
chat/completions), normalizing the Chat fields the Responses API rejects
and clamping max/ultra effort to xhigh
- **CLI**: install better-sqlite3 without build tools on Node 22+ (N-API
13.0.3 ships per-platform prebuilds, `--ignore-scripts` skips the implicit
node-gyp build); Node < 22 stays on 12.6.2, working installs untouched
- **CLI tools**: send the API key Codex actually reads —
`[model_providers.9router.http_headers]` instead of auth.json (which left
every request 401 and clobbered an existing ChatGPT login); subagent model
moved to `agents.default_subagent_model`
- **OAuth**: refresh Cline tokens with the extension JSON contract
- **Dashboard**: clamp the API key mask length — keys shorter than 8 chars
threw RangeError and crashed the media-provider detail page
- **UI**: wait for the Material Symbols font itself before revealing icons —
`document.fonts.ready` resolved before the 4MB woff2 even started loading,
leaving icons blank until a second load
The runtime hook pinned better-sqlite3 12.6.2, whose prebuilds stop at
Node ABI 141 — on Node 26 the install fell back to a node-gyp source
build and failed on machines without build tools, silently degrading to
the sql.js fallback.
Node >= 22 now installs 13.0.3, which is N-API and ships per-platform
prebuilds inside the package. Two things were needed to make that
actually work:
- npm injects an implicit `node-gyp rebuild` for any package shipping a
binding.gyp, so the install still demanded build tools; `--ignore-scripts`
skips it and uses the bundled prebuild as-is.
- the binary check only looked at build/Release, which 13.x no longer
creates, so every start re-ran npm install; it now also accepts
prebuilds/<platform>-<arch>.node.
Node < 22 stays on 12.6.2 (13.x requires Node >= 22), and an existing
working install is left untouched either way.
## 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
## 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
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).
custom-server.js now generates a per-process secret at boot and stamps it
as x-9r-peer-token on every request it sanitizes. hasTrustedPeerHeaders()
(src/lib/auth/trustedPeer.js) gates trust in x-9r-real-ip on that secret;
otherwise the guard falls back to Host only in development, and fails
closed in production. Same gate on loginLimiter.getClientIp() so a spoofed
header cannot rotate the login lockout bucket.
Also: fix isLoopbackHostname for IPv6 (::1, ::ffff:127.0.0.1) which the
old split(":")[0] reduced to empty string; route npm run start /
start:bun through custom-server.js (postbuild copies it into
.next/standalone, build-cli.js fails without it) so documented deployments
keep passwordless local access.
Add gemini-3.7-flash and its tiered high/medium/low variants to the
Antigravity and Gemini registries, with matching capabilities, pricing
and Antigravity quota tracking.
extractModel now recognises gemini-3.7-flash-tiered alongside 3.6 and
derives the version from the request, so thinkingLevel still maps to the
right tiered alias.
Closes#3286Closes#3281
## 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
endpoint that drops packets never returns headers, so the request previously
hung indefinitely
Merge the complete generated .next-cli-build/server tree into the
packaged CLI after the standalone copy, since Next's standalone output
is trace-pruned and can omit route modules (e.g. /api/v1/messages) or
chunks loaded dynamically. Add a post-copy integrity check for the
required API route artifacts so an incomplete package fails during
pack:cli instead of at runtime.
Fixes#2945
`open` derives its own directory from import.meta.url at module scope.
Webpack replaces that with the build machine's absolute path as a
string literal, so a release built on macOS ships a file:///Users/...
URL that fileURLToPath rejects on Windows (no drive letter), throwing
on import. refreshXaiToken dynamic-imports the xAI OAuth service, which
imports open eagerly, so every Grok token refresh silently failed and
was swallowed by a catch that only logs a warning.
Add open to serverExternalPackages so it keeps its real import.meta.url
at runtime, and bundle it into the CLI package via ensureModuleInBundle
(same guard already used for sql.js) since externalizing it means
webpack no longer traces/copies it automatically.
Add gemini-3.6-flash tiered (high/medium/low) for Antigravity routing
via upstreamModelId "gemini-3.6-flash-tiered(level)" + thinkingLevel,
plus gemini-3.6-flash and gemini-3.5-flash-lite direct API models.
- getModelUpstreamId: split (level) suffix before lookup, re-append after
- Antigravity executor: preserve transformed body.model
- MITM extractModel: parse thinkingLevel for tiered model (default medium)
- Isolate Cloud Code endpoints: discovery (loadCodeAssist/onboardUser/
quota) on PROD cloudcode-pa, chat transport on daily-cloudcode-pa
to bypass prod 429
Outdated free-tier info was misleading new users. Sync corrections into
README.md and README.zh-CN.md, and force IPv4-first DNS resolution in the
CLI launcher to avoid undici IPv6 connect timeouts (502).
- Kiro AI: free tier now ~50 credits/month (was "Unlimited FREE")
- Qwen Code / Gemini CLI: free tiers discontinued in 2026
- OpenCode Free: note free model list fluctuates
- Vertex AI: Gemini API no longer uses $300 free credits since Mar 2026
- cli/cli.js: spawn server/tray with --dns-result-order=ipv4first
Bulk-add named auto-generated keys by paste-line index, blind to existing
connection names. The backend upserts apikey connections by exact name
(connectionsRepo), so a colliding generated name silently replaced an
existing key instead of inserting a new one.
Add a collision-aware planner (src/shared/utils/bulkAdd.js) that gap-fills
the smallest free "<base> <n>" against both existing connection names and
names assigned earlier in the same batch, so a generated name is never
reused and the backend always inserts. Applies to auto-named lines, custom
name|apiKey lines, and Cloudflare name|apiKey|accountId lines.
Wire the planner into AddApiKeyModal and pass existing connection names
from the provider detail page. Add unit tests covering gap-fill, custom
names, Cloudflare 3-part format, and robustness.
- Switch dev default to Turbopack (5-14x faster compile); keep webpack as dev:webpack
- Tailwind v4 source() base so JIT scans identically under both bundlers
- Lazy-load @xyflow/react via next/dynamic to keep it out of the shared bundle
- optimizePackageImports for heavy barrel imports (xyflow, dnd-kit, material-symbols, marked)
- Replace blind setTimeout waits with TCP health-check (waitServerReady)
- Run checkForUpdate in parallel instead of blocking server spawn
- Background MITM/tunnel/cloudflared kills off the critical path
Co-authored-by: Cursor <cursoragent@cursor.com>
Write the standalone app bundle and MITM bundle to NINEROUTER_CLI_APP_DIR
when set, so staged deploys can build to a separate destination before
swapping. Default output stays at cli/app when the env var is unset.
Set process DPI awareness (Per-Monitor V2 with fallbacks) and enable
WinForms visual styles before creating the tray NotifyIcon, so the
Windows context menu renders sharply on DPI-scaled displays.
Closes#2161
Co-authored-by: Cursor <cursoragent@cursor.com>
Next.js 16 nests standalone output under the project directory name
when NEXT_TRACING_ROOT_MODE=workspace (e.g. standalone/9router/server.js
instead of standalone/server.js), causing build-cli.js to fail with
"Next.js standalone build not found".
Detect nested layout with backward-compatible fallback to existing
standalone/server.js and standalone/app/ paths.
Co-authored-by: Cursor <cursoragent@cursor.com>
Build on the optional Headroom Token Saver from Carmelo Campos
(PR: feat: add optional Headroom token saver). Add managed start/stop
of the local headroom proxy from the dashboard, install detection,
status probing, and a simplified Token Saver UI.
- detect headroom CLI + python>=3.10, probe proxy /health
- spawn/stop proxy as a detached, pid-tracked process
- /api/headroom/{status,start,stop} routes, gated local-only in dashboardGuard
- one-click Start/Stop Headroom modal, no manual config needed
- claude<->openai shape conversion for /v1/compress via 9router translators
Thanks to Carmelo Campos (@carmelogunsroses) for the original Headroom integration.
Co-authored-by: Cursor <cursoragent@cursor.com>
## Fixes
- **Kiro**: honor thinking effort budgets
- **AG/Kiro/Xiaomi**: provider fixes
- **Combo/Fusion**: flatten tool history in panel calls to prevent 503
- **LLM selector**: show custom vision models in selector and model list
- **Image**: prevent compatible nodes from shadowing provider aliases
## Fixes
- **Kiro**: honor thinking effort budgets
- **AG/Kiro/Xiaomi**: provider fixes
- **Combo/Fusion**: flatten tool history in panel calls to prevent 503
- **LLM selector**: show custom vision models in selector and model list
- **Image**: prevent compatible nodes from shadowing provider aliases
## 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
- **Kiro headless API-key auth** (`ksk_`) + direct `claude↔kiro` route that avoids the lossy OpenAI two-hop pivot
- **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)
- **Translator**: derive deterministic tool_call ids for gemini/antigravity → OpenAI so function call/response pair correctly (fixes tool-pairing 400s)
- **Antigravity**: strip `optional` from tool schemas before sending to Gemini
- **Claude-to-OpenAI**: handle OpenAI-format responses in the non-streaming path (e.g. xiaomi-tokenplan)
- **Usage views**: show edited connection names consistently across Providers & Quota Tracker
- **Security**: hardened reverse-proxy local-access trust
- **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
Features
Vercel AI Gateway: support embeddings, images and credit usage (#1183)
Add MiMo Free no-auth provider (#1789)
Vertex: support ADC authorized_user credential
Cowork: re-enable Claude Cowork with preset-only stdio MCP
Codex: bulk add accounts via JSON (#1719)
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)
SiliconFlow: update baseUrl .cn → .com + curate verified model list (#1760)
Gemini-to-OpenAI: route unsigned thought parts to reasoning_content (#1752)
Claude-to-OpenAI: strip Anthropic billing header from system prompt (#1765)
Anthropic-compatible: send Bearer auth for third-party gateways (#1795)
Usage-stats: avoid partial stats on initial SSE race (#1767)
Proxy: use export default in proxy.js for Next.js 16 middleware detection
Claude passthrough: add body normalization
GitHub Copilot: refresh missing/expired token on models discovery (#1727) + add mappable gpt-5-mini/gpt-5.4-nano slots for Copilot MITM (#1653)
Kiro: auto-resolve profileArn to prevent 403 on IDC login, enhance profile ARN resolution, update endpoint to runtime.us-east-1.kiro.dev (#1713)
Tunnel: detect system-installed Tailscale via dual-socket probe (#1723) + non-blocking probes to prevent UI freeze
CommandCode: force stream=true in transformRequest (#1706)
Qoder: increase timeouts for reasoning models and improve stream handling
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)
- Add custom-server.js: inject unspoofable socket IP, strip client XFF
(wired into Docker CMD + CLI spawn + build-cli copy)
- loginLimiter: key on trusted x-9r-real-ip, TRUST_PROXY opt-in, global fallback
- Force password change on first remote login while default is in use
- Add /api/auth/reset-password (local-only) so CLI reset writes live SQLite
- CLI settings: reset via API instead of stale db.json
- Fix OAuth modals opening duplicate browser tabs on add-connection
- Add cli:pack / cli:publish scripts
Co-authored-by: Cursor <cursoragent@cursor.com>
- Add gemini-3.5-flash-extra-low across CLI menu, provider models, usage, pricing
- Add MITM synonyms (high/medium/extra-low) and split pattern so Low no longer falls through to Medium
- Strip models/ prefix in getMappedModel for AG public name normalization
Co-authored-by: Cursor <cursoragent@cursor.com>
## 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
## 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 (updated IDE version detection and DNS/cert flow)
- Sanitize Read tool args to prevent retry loops from non-Anthropic models (#1144)
- Implement json_schema fallback for OpenAI-compatible providers without native Structured Output (#1343)
- Strip empty Read pages argument in OpenAI-to-Claude translator (#1354)
- Forward Gemini output dimensions for embeddings (#1366)
- Resolve setState-in-effect errors in dashboard components (#1362)
- Gemini CLI: reuse stored OAuth project IDs for quota checks and show clearer setup guidance when the project is missing (#1271, #1428)
