5 Commits

Author	SHA1	Message	Date
hobokenchicken	eb67287b56	fix: raise provider HTTP timeouts from 30s to 10min ... 30-second resty client timeout was killing long streaming responses mid-generation. Models with large output windows (e.g. deepseek-v4-pro at 384K max_tokens) routinely exceed 30s. Raised all providers to 10 minutes (Ollama already at 15min, unchanged). Circuit breaker recovery timeout raised from 30s to 5min.	2026-04-30 10:17:45 -04:00
hobokenchicken	5ee539d95c	feat: add image generation for OpenAI DALL-E and Gemini Imagen ... New `/v1/images/generations` endpoint proxies DALL-E 2/3 (OpenAI) and Imagen 3 (Gemini). Same auth/logging as chat completions. - Add ImageGenerationRequest/Response models - Extend Provider interface with ImageGeneration() - OpenAI: forward to /v1/images/generations - Gemini: call /v1beta/models/{model}:predict, map OpenAI params - Circuit breaker wraps image gen like chat completions - Model routing: dall-e* -> openai, imagen*/gemini* -> gemini - Unsupported providers (deepseek/moonshot/grok/ollama) return error - Fix pre-existing CachedContentTokenCount bug in StreamGemini	2026-04-27 10:06:07 -04:00
hobokenchicken	1f574d8134	feat: Phase 2 - reliability & observability ... - Circuit breaker: proper thresholds (3 failures, 30s timeout) - HTTP timeouts: 30s on all providers (was no timeout) - Structured logging: slog replaces fmt.Printf throughout - Stream errors: propagated as SSE error events to client - Registry fetch: retry with backoff (3 attempts) - Registry reads in dashboard protected by RWMutex	2026-04-26 14:48:56 -04:00
hobokenchicken	9b0aa4dbe8	fix: remove unused fmt import in circuit breaker provider	2026-04-09 12:19:14 -04:00
hobokenchicken	212ac14a1b	feat: implement circuit breaker, fix auth vulnerability	2026-04-09 12:17:18 -04:00