feat(providers): model-registry routing + Responses API support and streaming fallbacks for OpenAI/Gemini

src/providers/mod.rs

@@ -28,6 +28,13 @@ pub trait Provider: Send + Sync {
     /// Process a chat completion request
     async fn chat_completion(&self, request: UnifiedRequest) -> Result<ProviderResponse, AppError>;
 
+    /// Process a chat request using provider-specific "responses" style endpoint
+    /// Default implementation falls back to `chat_completion` for providers
+    /// that do not implement a dedicated responses endpoint.
+    async fn chat_responses(&self, request: UnifiedRequest) -> Result<ProviderResponse, AppError> {
+        self.chat_completion(request).await
+    }
+
     /// Process a streaming chat completion request
     async fn chat_completion_stream(
         &self,