feat(openai): implement Responses API streaming and proactive routing

This commit adds support for the OpenAI Responses API in both streaming and non-streaming modes. It also implements proactive routing for gpt-5 and codex models and cleans up unused 'session' variable warnings across the dashboard source files.

src/providers/mod.rs

@@ -42,6 +42,16 @@ pub trait Provider: Send + Sync {
         request: UnifiedRequest,
     ) -> Result<BoxStream<'static, Result<ProviderStreamChunk, AppError>>, AppError>;
 
+    /// Process a streaming chat request using provider-specific "responses" style endpoint
+    /// Default implementation falls back to `chat_completion_stream` for providers
+    /// that do not implement a dedicated responses endpoint.
+    async fn chat_responses_stream(
+        &self,
+        request: UnifiedRequest,
+    ) -> Result<BoxStream<'static, Result<ProviderStreamChunk, AppError>>, AppError> {
+        self.chat_completion_stream(request).await
+    }
+
     /// Estimate token count for a request (for cost calculation)
     fn estimate_tokens(&self, request: &UnifiedRequest) -> Result<u32>;