v2.0.2 — Endpoint-Aware Model Management & Bug Fixes
🐛 Bug Fixes
- #212 — API Key creation crash — Auto-generate
API_KEY_SECRETat startup (likeJWT_SECRET) to prevent HMAC crashes - #213 — Circuit breaker scope — Changed circuit breaker key from provider-level to model-level; a 429 on one account no longer blocks all accounts for the same provider
- #200 — Custom provider connection check — Added connectivity fallback for OpenAI-compatible providers (Ollama, LM Studio); if
/modelsand/chat/completionsfail, a simple HTTP ping marks the provider as connected
✨ New Features
- #204 — API Format selector — Custom models can now specify
apiFormat:chat-completions(default) orresponses(Responses API) - #205 — Combo endpoint support — Combos now accept an
endpointfield (chat|embeddings|images), enabling fallback/rotation combos for non-chat endpoints - #206 — Supported Endpoints mapping — When adding custom models, check which endpoints the model supports (💬 Chat, 📐 Embeddings, 🖼️ Images, 🔊 Audio)
- Models tagged for embeddings appear in
/v1/embeddings, models tagged for images appear in/v1/images/generations - Visual badges on model rows for non-default configurations
/v1/modelscatalog includesapi_format,type, andsupported_endpointsmetadata
Issues Closed
- #199 — proxy_ prefix (already fixed in v2.0.0)
- #198 — Rate limit configuration (already fixed in v2.0.0)
- #201 — Security concerns (answered)
Full Changelog: v2.0.0...v2.0.2
Full Changelog: v2.0.1...v2.0.2