decolua
699edac327
## 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
9Router - FREE AI Router & Token Saver
Never stop coding. Save 20-40% tokens with RTK + auto-fallback to FREE & cheap AI models.
Connect All AI Code Tools (Claude Code, Cursor, Antigravity, Copilot, Codex, Gemini, OpenCode, Cline, OpenClaw...) to 40+ AI Providers & 100+ Models.
🤔 Why 9Router?
Stop wasting money, tokens and hitting limits:
- ❌ Subscription quota expires unused every month
- ❌ Rate limits stop you mid-coding
- ❌ Tool outputs (git diff, grep, ls...) burn tokens fast
- ❌ Expensive APIs ($20-50/month per provider)
9Router solves this:
- ✅ RTK Token Saver - Auto-compress tool_result, save 20-40% tokens
- ✅ Maximize subscriptions - Track quota, use every bit before reset
- ✅ Auto fallback - Subscription → Cheap → Free, zero downtime
- ✅ Multi-account - Round-robin between accounts per provider
- ✅ Universal - Works with any OpenAI/Claude-compatible CLI
⚡ Quick Start
Option 1 — npm (recommended for desktop):
npm install -g 9router
9router
# Or run directly with npx
npx 9router
Option 2 — Docker (server/VPS):
docker run -d --name 9router -p 20128:20128 \
-v "$HOME/.9router:/app/data" -e DATA_DIR=/app/data \
decolua/9router:latest
Published images: Docker Hub • GHCR (multi-platform amd64/arm64).
🎉 Dashboard opens at http://localhost:20128
2. Connect a FREE provider (no signup needed):
Dashboard → Providers → Connect Kiro AI (free Claude unlimited) or OpenCode Free (no auth) → Done!
3. Use in your CLI tool:
Claude Code/Codex/OpenClaw/Cursor/Cline Settings:
Endpoint: http://localhost:20128/v1
API Key: [copy from dashboard]
Model: kr/claude-sonnet-4.5
That's it! Start coding with FREE AI models.
🚀 CLI Options
9router # Start with default settings
9router --port 8080 # Custom port
9router --no-browser # Don't open browser
9router --skip-update # Skip auto-update check
9router --help # Show all options
Dashboard: http://localhost:20128/dashboard
🛠️ Supported CLI Tools
Claude-Code • OpenClaw • Codex • OpenCode • Cursor • Antigravity • Cline • Continue • Droid • Roo • Copilot • Kilo Code • Gemini CLI • Qwen Code • iFlow • Crush • Crusher • Aider
Any tool supporting OpenAI/Claude-compatible API works.
💾 Data Location
- macOS/Linux:
~/.9router/db/data.sqlite - Windows:
%APPDATA%/9router/db/data.sqlite - Docker:
/app/data/db/data.sqlite(mount$HOME/.9routerto persist)
📚 Documentation
Full docs, advanced setup, video tutorials & development guide:
- GitHub: https://github.com/decolua/9router
- Full README: https://github.com/decolua/9router/blob/main/app/README.md
- Website: https://9router.com
🙏 Acknowledgments
- CLIProxyAPI - Original Go implementation
📄 License
MIT License - see LICENSE for details.