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

internal/providers/provider.go

@@ -10,4 +10,5 @@ type Provider interface {
 	Name() string
 	ChatCompletion(ctx context.Context, req *models.UnifiedRequest) (*models.ChatCompletionResponse, error)
 	ChatCompletionStream(ctx context.Context, req *models.UnifiedRequest) (<-chan *models.ChatCompletionStreamResponse, error)
+	ImageGeneration(ctx context.Context, req *models.ImageGenerationRequest) (*models.ImageGenerationResponse, error)
 }