a bit more progressive update and single turn

backend/main.py

@@ -2,12 +2,15 @@
 
 from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 from typing import List, Dict, Any
 import uuid
+import json
+import asyncio
 
 from . import storage
-from .council import run_full_council, generate_conversation_title
+from .council import run_full_council, generate_conversation_title, stage1_collect_responses, stage2_collect_rankings, stage3_synthesize_final, calculate_aggregate_rankings
 
 app = FastAPI(title="LLM Council API")
 
@@ -120,6 +123,77 @@ async def send_message(conversation_id: str, request: SendMessageRequest):
     }
 
 
+@app.post("/api/conversations/{conversation_id}/message/stream")
+async def send_message_stream(conversation_id: str, request: SendMessageRequest):
+    """
+    Send a message and stream the 3-stage council process.
+    Returns Server-Sent Events as each stage completes.
+    """
+    # Check if conversation exists
+    conversation = storage.get_conversation(conversation_id)
+    if conversation is None:
+        raise HTTPException(status_code=404, detail="Conversation not found")
+
+    # Check if this is the first message
+    is_first_message = len(conversation["messages"]) == 0
+
+    async def event_generator():
+        try:
+            # Add user message
+            storage.add_user_message(conversation_id, request.content)
+
+            # Start title generation in parallel (don't await yet)
+            title_task = None
+            if is_first_message:
+                title_task = asyncio.create_task(generate_conversation_title(request.content))
+
+            # Stage 1: Collect responses
+            yield f"data: {json.dumps({'type': 'stage1_start'})}\n\n"
+            stage1_results = await stage1_collect_responses(request.content)
+            yield f"data: {json.dumps({'type': 'stage1_complete', 'data': stage1_results})}\n\n"
+
+            # Stage 2: Collect rankings
+            yield f"data: {json.dumps({'type': 'stage2_start'})}\n\n"
+            stage2_results, label_to_model = await stage2_collect_rankings(request.content, stage1_results)
+            aggregate_rankings = calculate_aggregate_rankings(stage2_results, label_to_model)
+            yield f"data: {json.dumps({'type': 'stage2_complete', 'data': stage2_results, 'metadata': {'label_to_model': label_to_model, 'aggregate_rankings': aggregate_rankings}})}\n\n"
+
+            # Stage 3: Synthesize final answer
+            yield f"data: {json.dumps({'type': 'stage3_start'})}\n\n"
+            stage3_result = await stage3_synthesize_final(request.content, stage1_results, stage2_results)
+            yield f"data: {json.dumps({'type': 'stage3_complete', 'data': stage3_result})}\n\n"
+
+            # Wait for title generation if it was started
+            if title_task:
+                title = await title_task
+                storage.update_conversation_title(conversation_id, title)
+                yield f"data: {json.dumps({'type': 'title_complete', 'data': {'title': title}})}\n\n"
+
+            # Save complete assistant message
+            storage.add_assistant_message(
+                conversation_id,
+                stage1_results,
+                stage2_results,
+                stage3_result
+            )
+
+            # Send completion event
+            yield f"data: {json.dumps({'type': 'complete'})}\n\n"
+
+        except Exception as e:
+            # Send error event
+            yield f"data: {json.dumps({'type': 'error', 'message': str(e)})}\n\n"
+
+    return StreamingResponse(
+        event_generator(),
+        media_type="text/event-stream",
+        headers={
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+        }
+    )
+
+
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=8001)