fix: implement real-time streaming for responses

- Added streaming service support to the Q&A agent for real-time token streaming.
- Updated `answer_question` method to stream responses token-by-token to the frontend.
- Modified `handle_qna_workflow` to handle both custom and values streaming modes.
- Enhanced state management to include streaming service for improved user experience.

surfsense_backend/app/agents/researcher/qna_agent/state.py

@@ -7,6 +7,8 @@ from typing import Any
 
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.services.streaming_service import StreamingService
+
 
 @dataclass
 class State:
@@ -21,6 +23,9 @@ class State:
     # Runtime context
     db_session: AsyncSession
 
+    # Streaming service for real-time token streaming
+    streaming_service: StreamingService | None = None
+
     chat_history: list[Any] | None = field(default_factory=list)
     # OUTPUT: Populated by agent nodes
     reranked_documents: list[Any] | None = None