hobokenchicken
5ee539d95c
CI / Lint (push) Has been cancelled
CI / Test (push) Has been cancelled
CI / Build (push) Has been cancelled
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
..
2026-04-26 14:45:22 -04:00
2026-03-19 14:01:59 -04:00
2026-04-26 14:48:56 -04:00
2026-04-26 14:45:22 -04:00
2026-04-27 10:06:07 -04:00
2026-04-27 10:06:07 -04:00
2026-04-27 10:06:07 -04:00
2026-04-26 14:52:10 -04:00