5da508af3c
## 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
49 lines
1.7 KiB
JSON
49 lines
1.7 KiB
JSON
{
|
|
"name": "9router",
|
|
"version": "0.5.2",
|
|
"description": "9Router CLI - Start and manage 9Router server",
|
|
"bin": {
|
|
"9router": "./cli.js"
|
|
},
|
|
"files": [
|
|
"cli.js",
|
|
"src",
|
|
"hooks",
|
|
"app",
|
|
"README.md",
|
|
"LICENSE"
|
|
],
|
|
"scripts": {
|
|
"dev": "nodemon -I --watch cli.js --watch src --watch hooks --ext js,json cli.js",
|
|
"build": "node scripts/build-cli.js",
|
|
"pack:cli": "npm run build && npm pack --pack-destination ../..",
|
|
"publish:cli": "npm run build && npm publish",
|
|
"postinstall": "node hooks/postinstall.js",
|
|
"prepublishOnly": "npm run build"
|
|
},
|
|
"dependencies": {
|
|
"enquirer": "^2.4.1",
|
|
"node-forge": "^1.3.3",
|
|
"node-machine-id": "^1.1.12",
|
|
"react": "19.2.1",
|
|
"react-dom": "19.2.1"
|
|
},
|
|
"comment_sqlite": "sql.js + better-sqlite3 are NOT bundled here. They are installed into ~/.9router/runtime/node_modules by hooks/postinstall.js (and re-checked at runtime by cli.js). This avoids Windows EBUSY errors when updating the global CLI, since native .node files no longer live under the locked install dir.",
|
|
"comment_systray": "systray2 is NOT bundled here. It is lazy-installed into ~/.9router/runtime/node_modules by hooks/postinstall.js on macOS/Linux only. Windows uses PowerShell NotifyIcon (zero binary). This avoids shipping unsigned Go binaries that trigger antivirus false positives (Kaspersky). We use the systray2 fork because the legacy systray@1.0.5 ships a 2017 x86_64 binary that fails on modern macOS dyld.",
|
|
"engines": {
|
|
"node": ">=18.0.0"
|
|
},
|
|
"keywords": [
|
|
"9router",
|
|
"cli",
|
|
"proxy",
|
|
"ai",
|
|
"api"
|
|
],
|
|
"license": "MIT",
|
|
"devDependencies": {
|
|
"esbuild": "^0.25.12",
|
|
"nodemon": "^3.1.14"
|
|
}
|
|
}
|