Try ipwho.is -> ip-api.com -> ipapi.co -> ipinfo.io in order so a
rate-limited/broken provider falls through to the next; ipinfo (most
quota-bound) is last. Normalize each payload to {ip,country,region,city,org},
keep 15s timeout per endpoint, and support GEO_PROBE_URL to replace the
chain with a single custom endpoint.
Refuse re-probing failures too fast: 500/429 failures get a 2h backoff,
other errors 30m (flapping relays/quota stops hammering ipinfo every pass,
passes every 30 min instead of 15). One-line summary per pass
(geo N/M · fail: rate×a server×b) replaces the per-pool error wall.
New env POOL_GEO_PROBE_DISABLED=1 turns the feature off.
Remove [DBG:STREAM] chunk/pipe/EOF instrumentation and [DBG:SSE] flush +
fetch success lines that spam the dev console every request. Keep the stream
stall watchdog and the fetch-error (✖) diagnostics.
Unrecoverable refresh errors (invalid_grant/invalid_request) are persisted as
a refreshBlocked marker so the background scheduler stops hammering the
provider every 5 minutes and surfaces re-login required; the marker is lifted
automatically when a later refresh succeeds. Cooldown maps gained lazy pruning.
Background probe fetches ipinfo through each pool itself (provider-agnostic
transport), fills an egress IP/country cache (TTL 1h, 8-IP history) and flags
flapping relays as unstable. Periodic state sweeper (10 min) prunes expired
fitness marks, stale geo/ip-history and Freebuff session/cooldown state;
schedulers skip non-server runtimes. Unit tests for the geo cache.
Pool/IP fitness registry (globalThis-backed, provider::model scopes, 5-min
cooldown, provider::* wildcard) fed by pool-scoped failures: freebuff
limited-IP / model-locked gates and opencode free per-IP limits. chatCore
retries a failed pool via another pool without locking the account; new
Smart rotation strategy (per-connection + no-auth providers) skips unfit
pools. Proxy Fitness dashboard page: active-block table with provider/IP
filters, per-record Clear and provider-scoped Clear All; egress column via
pool geo enrichment. Unit tests for the registry.
## 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
Google fingerprints User-Agent/Client-Metadata on loadCodeAssist and
onboardUser, silently refusing to provision a cloudaicompanionProject
when they don't match the real IDE. Split antigravity's headers out of
the shared gemini-cli constants instead of overwriting them, so the fix
doesn't touch gemini-cli or any other provider.
Inspired by #3000 (thanks @stoXmod for flagging the resource-exhausted
issue), rewritten to keep gemini-cli untouched.
Adds exact per-model rates for 110 TokenRouter models (pulled from
TokenRouter's own pricing API) plus a dedicated thinkingFormat case
(reasoning_effort enum low/medium/high/xhigh/max) and the provider
logo. Provider registration itself already landed in a prior commit;
this fills in what PR #3043 added on top.
Sync alias-baseline.json and providers-baseline.json with the current
registry (poolside, tokenrouter, selfhosted-* providers already added;
stale claudeOverlay hook and Kiro X-Amz-Target header already removed).
- Endpoint page auto-creates a "Default Key" when no keys exist yet,
so /v1 works out of the box without a manual dashboard step
- Show/copy key buttons stay visible instead of opacity-0 by default
Qwen OAuth flow (portal.qwen.ai) stopped working reliably; drop the
executor, registry entry, OAuth provider/service, token refresh
profile, usage handler, and related test coverage and baselines.
- detectRequiredCapabilities: infer audioInput/videoInput from block
type and embedded mime, not just vision/pdf
- handleChat / handleSingleModelChat: augment combo and single-model
routing with capacity-adapter models when the target lacks a
required capability, wrapped with history stripping for the
adapter model's context window
- Enable vision + audioInput capacity-adapter pools by default for new
and existing users (mergeWithDefaults backward-compat)
- Fall back to oc/mimo-v2.5-free when an enabled pool has no models
configured, both in the backend resolver and the combos UI (auto
refill on removing the last model from a pool)
- Hide PDF/Video from the Vision Adapter UI (PDF never implemented,
Video lacks translator support) while keeping the settings shape
- Exclude combos from the model picker when opened from the Vision
Adapter section
- mimo-v2.5 registry entry now declares audioInput/videoInput
- Simplify combo strategy and Vision Adapter descriptions
detectClientTool only matched the legacy "codex-cli" User-Agent, so the
current codex-tui CLI and Codex Desktop (UA "Codex Desktop", originator
"codex_work_desktop") fell through to null and lost native passthrough —
their requests got re-translated, stripping/overwriting fields like
reasoning.summary instead of forwarding the client body as-is.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Add Self-hosted STT/TTS/Embedding providers that read baseUrl per connection
instead of a fixed registry endpoint, so 9Router can point at whisper.cpp,
faster-whisper, Kokoro-FastAPI, llama-server, vLLM, Infinity, and similar
OpenAI-compatible local servers.
Self-hosted Embedding refuses to run without a baseUrl rather than falling
back to api.openai.com like openaiCompatNode does, since that fallback would
silently send input text and the API key to OpenAI under a provider named
"Self-hosted". Also fixes embeddingsCore to catch adapter build errors as a
400 instead of letting them escape uncaught, and bounds the upstream fetch
with FETCH_CONNECT_TIMEOUT_MS to avoid hanging forever on a dead endpoint.
Self-hosted TTS treats a bare model value as the model rather than the voice,
since the generic OpenAI TTS convention (bare = voice) is backwards for a
provider where the model is the variable part.
Codex Responses Lite clients routed to a chat-native OpenAI-compatible
provider lost tool use in three places: non-streaming Chat responses
leaked the raw chat.completion envelope instead of Responses output
items, internal reasoning continuity fields leaked into the outbound
Chat body causing some upstreams to reject the request, and the
Responses to Chat request translator ignored additional_tools,
custom_tool_call, and custom_tool_call_output items entirely.
Also fixes apiType (chat vs responses) for openai-compatible nodes
being resolved from the immutable provider ID instead of the stored
node config, so editing a node's API Type had no runtime effect.
getAntigravityUsage filtered the fetchAvailableModels response through a
hardcoded importantModels list that only contained 3.5 Flash, silently
dropping the 3.6 Flash quota buckets so no usage bar rendered.
hasValidContent() only treated text/tool_use/tool_result blocks as valid
content, so a user message containing only an image block was filtered
out as empty. When it was the only non-system message, this left an
empty messages array and Anthropic rejected the request.
Cloudflare AI registry entry was missing authType/authModes, causing
the dashboard to report "No connections" despite an active API-key
connection. Closes#2969
Fix port 201281 -> 20128/v1 typo in README.zh-CN.md diagram, add
RTK Token Saver mention to README.vi.md/README.zh-CN.md, update
Tier 3 free providers to 2026 lineup, and drop hardcoded /tmp
node_modules path from tests/package.json and tests/README.md.
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
Adds mimo-v2.5-tts as a Media Provider TTS through the existing
OpenAI-compatible chat-completions endpoint. Voice is selected via the
top-level audio.voice field, and an optional style/language hint is
threaded through tts.js -> ttsCore.js -> the new adapter.
Map the Grok OAuth access-token tier claim to the public plan label
and prefer it over internal /user entitlement names. Fails open to
existing plan detection for opaque or malformed tokens; upstream
remains authoritative for access and quota enforcement.
Add "ultra" reasoning level for Codex GPT-5.6 Sol and Terra, and expose
Max for Luna (Luna falls back Ultra to Max since it is not supported
upstream). Scoped to cx/ routes only; Kiro and generic OpenAI routing
unchanged.
Adds a guide-type CLI Tools entry for OpenDesign, the open-sourced
claude.ai/design skills pack. It has no standalone config - it inherits
the host agent's model/provider config - so once the host (Claude Code,
Cursor, Codex, Gemini CLI, OpenCode) points at 9Router, /opendesign
sessions route through automatically.
Break out tool schema and tool-history bytes in the size snapshot and
add an effective byte-savings percentage so token-saved logs reflect
the actual outbound payload reduction, not just processed content.
The global claudeHeaderCache singleton overlaid the last-seen Claude Code
client's identity headers onto every subsequent request, leaking one
client's headers (anthropic-beta, user-agent, x-stainless-*, etc.) onto
another client/account sharing the same server. Removed the singleton and
the claudeOverlay hook entirely, falling back to static per-provider
headers. anthropic-beta is now computed per-request from the requested
model, gating heavy-agent flags (advanced-tool-use, effort) to
opus/sonnet only.
PAT-to-job-token exchange was duplicated between the executor and the model service, each with its own cache. Consolidate into qoderModels.js and have the executor import it.
Also add a qoder case to the API-key validate route - the generic OpenAI-compat probe cannot validate a PAT (needs job-token exchange + COSY signing first), so bulk-add always reported unknown for qoder keys.
Adds pt-... token auth as an alternative to OAuth device flow. A PAT can't
sign COSY requests directly, so it's exchanged for a short-lived job token
(jt-...) plus userId via openapi.qoder.sh, then used for signing.
Also fixes job-token traffic (jt-...) being rejected by api3.qoder.sh with
403 "Login expired" — the official qodercli serves jt- traffic from
api2.qoder.sh instead, so buildUrl/model-list routing now branches on it.
Quota usage and the dashboard add-key modal are updated to resolve PAT
credentials and label the field correctly, and bulk-add now validates
each key so it gets a real testStatus instead of a hardcoded "unknown".
Lock GitHub Copilot connections account-wide until 00:00 UTC on the
first of next month when the upstream 402 response indicates the
monthly additional-usage-limit was hit, instead of only cooling down
the requested model for 120s. Other GitHub 402 responses keep the
existing model-scoped cooldown.
Neutralize CLI-agent system prompts that trigger CodeBuddy CN's content filter, add usage/quota tracking for codebuddy-intl sharing CN's logic, and normalize codebuddy-intl request messages to the shape it expects.
handleForcedSSEToJson dropped cached prompt tokens in two ways: the
Responses branch summed only input_tokens, which excludes cache_read
and cache_creation on cache-capable upstreams (measured 2012 reported
vs ~5344 actual, 5332 from cache); and the Chat Completions branch
computed usage correctly but it didn't always reach the client (an
Anthropic response with cache_read_input_tokens: 11022 arrived with no
usage field at all). Now folds cache counters into prompt_tokens,
surfaces them via prompt_tokens_details, and re-attaches usage before
serialisation.
Tool schemas carrying uniqueItems, contains, multipleOf,
unevaluatedProperties, unevaluatedItems, or contentSchema get rejected
by the Gemini API with "Unknown name ...: Cannot find field", failing
the whole request. Add them to UNSUPPORTED_SCHEMA_CONSTRAINTS alongside
the existing stripped keywords (minItems, maxItems, format, ...).
MUH. IQRAM BAHRING
decolua
Dasep Moch Luay
omar-nahhas
Ubuntu
RobertsXML
nguyenha935
whale9820
cardinusantara
Sutarto Jordan Chrisfivo
huuanh20
Matt Van Horn
MiQieR
ryanngit
alfep
seakleang.nhak
Diwak4r
minhnhat166
mannnrachman
Rafi Mahardika
Muhammad Usama