Tags: thosvesta/9router
Tags
- **Perplexity**: add Agent API provider (decolua#2492) - **Grok CLI**: add Grok CLI / Grok Build provider with OAuth device-code flow (decolua#2502) - **Featherless**: add OpenAI-compatible provider presets - **SearXNG**: configure endpoint via SEARXNG_URL env (decolua#2499) - **Providers**: add max thinking level for gpt-5.6-sol (decolua#2500) - **Headroom**: add extras detection and install UI (decolua#2403) - **Headroom**: activate/uninstall extras + fix interpreter detection - **PXPipe**: PXPIPE token saver — multimodal prompt compression (decolua#2465) - **Proxy-Pools**: auto-rotate strategy for no-auth providers (decolua#2409) - **Cloudflare-AI**: support accountId in bulk key import (decolua#2449) - **DB**: backup on schema change, MCP child cleanup, codex models, usage providers OOM - **Codex**: avoid bare-email OAuth dedup (decolua#2477) - **CLI**: allow staged app bundle builds (decolua#2479) - **Headroom**: compress Kiro conversation state (decolua#2488) - **Gemini-CLI**: raise output floor for thinking and add validated toolConfig (decolua#2486) - **GitHub**: label Copilot profiles by account identity (decolua#2498) - **OpenAI-to-Claude**: unwrap bare {function:{…}} tools without parent type (decolua#2473) - **Translator**: clamp thinking effort max->xhigh for OpenAI format (decolua#2466) - **RTK/find**: detect and group Windows backslash-style find output (decolua#2448) - **Codex**: handle fast tier and capacity SSE (decolua#2452) - **Volcengine-ark**: clamp Kimi max_tokens to 32768 endpoint cap - **Antigravity**: align provider fingerprint with IDE Desktop 2.1.1 (decolua#2389) - **Pricing**: update Claude/Codex model rates and add new models - **i18n(zh-CN)**: complete Chinese translations for all UI strings (decolua#2436) - **API**: caching for tunnel and version status endpoints - **Perf**: faster dev startup and lighter bundle
PreviousNext