Remove deep ask from ag-ui server

docs/server.md

@@ -119,7 +119,7 @@ URLs are also supported - the content is fetched and converted to markdown.
 
 ## AG-UI Server
 
-The AG-UI server provides HTTP streaming of both research and deep ask graph execution using Server-Sent Events (SSE).
+The AG-UI server provides HTTP streaming of research graph execution using Server-Sent Events (SSE).
 
 ### Starting the AG-UI Server
 
@@ -131,7 +131,6 @@ This starts an HTTP server (default: http://0.0.0.0:8000) that exposes:
 
 - `GET /health` - Health check endpoint
 - `POST /v1/research/stream` - Research graph streaming endpoint
-- `POST /v1/deep-ask/stream` - Deep ask graph streaming endpoint
 
 ### Configuration
 
@@ -154,9 +153,9 @@ agui:
 - **cors_methods**: Allowed HTTP methods (default: `["GET", "POST", "OPTIONS"]`)
 - **cors_headers**: Allowed headers (default: `["*"]`)
 
-### Using the Streaming Endpoints
+### Using the Streaming Endpoint
 
-Both endpoints accept POST requests with the same AG-UI RunAgentInput format and stream AG-UI events.
+The endpoint accepts POST requests with AG-UI RunAgentInput format and streams AG-UI events.
 
 **Request format:**
 ```json
@@ -171,7 +170,7 @@ Both endpoints accept POST requests with the same AG-UI RunAgentInput format and
 }
 ```
 
-**Research endpoint example:**
+**Example:**
 ```bash
 curl -X POST http://localhost:8000/v1/research/stream \
   -H "Content-Type: application/json" \
@@ -183,24 +182,12 @@ curl -X POST http://localhost:8000/v1/research/stream \
   --no-buffer
 ```
 
-**Deep ask endpoint example:**
-```bash
-curl -X POST http://localhost:8000/v1/deep-ask/stream \
-  -H "Content-Type: application/json" \
-  -d '{
-    "state": {
-      "question": "How does haiku.rag handle document chunking?",
-      "use_citations": true
-    }
-  }' \
-  --no-buffer
-```
-
 The `--no-buffer` flag ensures curl displays events as they arrive instead of buffering them.
 
 **Note:** The `state` object can include:
 - `question`: The question to answer (required)
-- `use_citations`: Enable citations in deep ask responses (optional, deep ask only)
+- `max_iterations`: Maximum research iterations (optional, defaults to config)
+- `confidence_threshold`: Confidence threshold for early termination (optional, defaults to config)
 
 **Response:** Server-Sent Events stream with AG-UI protocol events:
 - `RUN_STARTED` - Graph execution started

haiku_rag_slim/haiku/rag/graph/agui/server.py

@@ -154,14 +154,14 @@ def format_sse_event(event: AGUIEvent) -> str:
 def create_agui_server(  # pragma: no cover
     config: "AppConfig", db_path: Path | None = None
 ) -> Starlette:
-    """Create AG-UI server with both research and deep ask endpoints.
+    """Create AG-UI server with research endpoint.
 
     Args:
-        config: Application config with research and qa settings
+        config: Application config with research settings
         db_path: Optional database path override
 
     Returns:
-        Starlette app with research and deep ask endpoints
+        Starlette app with research endpoint
     """
     from haiku.rag.client import HaikuRAG
     from haiku.rag.graph.research.dependencies import ResearchContext
@@ -189,7 +189,14 @@ def create_agui_server(  # pragma: no cover
             if messages:
                 question = messages[0].get("content", "")
         context = ResearchContext(original_question=question)
-        return ResearchState.from_config(context=context, config=config)
+        max_iterations = input_state.get("max_iterations")
+        confidence_threshold = input_state.get("confidence_threshold")
+        return ResearchState.from_config(
+            context=context,
+            config=config,
+            max_iterations=max_iterations,
+            confidence_threshold=confidence_threshold,
+        )
 
     def research_deps_factory(input_config: dict[str, Any]) -> ResearchDeps:
         effective_db_path = (
@@ -199,33 +206,7 @@ def create_agui_server(  # pragma: no cover
         )
         return ResearchDeps(client=get_client(effective_db_path))
 
-    # Deep ask graph factories (uses research graph with quick settings)
-    def deep_ask_graph_factory() -> Graph:
-        return build_research_graph(config)
-
-    def deep_ask_state_factory(input_state: dict[str, Any]) -> ResearchState:
-        question = input_state.get("question", "")
-        if not question:
-            messages = input_state.get("messages", [])
-            if messages:
-                question = messages[0].get("content", "")
-        context = ResearchContext(original_question=question)
-        return ResearchState.from_config(
-            context=context,
-            config=config,
-            max_iterations=2,
-            confidence_threshold=0.0,
-        )
-
-    def deep_ask_deps_factory(input_config: dict[str, Any]) -> ResearchDeps:
-        effective_db_path = (
-            db_path
-            or input_config.get("db_path")
-            or config.storage.data_dir / "haiku.rag.lancedb"
-        )
-        return ResearchDeps(client=get_client(effective_db_path))
-
-    # Create event stream functions for each graph type
+    # Create event stream function
     async def research_event_stream(
         input_data: RunAgentInput,
     ) -> AsyncIterator[str]:
@@ -238,18 +219,6 @@ def create_agui_server(  # pragma: no cover
             event_data = format_sse_event(event)
             yield event_data
 
-    async def deep_ask_event_stream(
-        input_data: RunAgentInput,
-    ) -> AsyncIterator[str]:
-        """Generate SSE event stream from deep ask graph execution."""
-        graph = deep_ask_graph_factory()
-        initial_state = deep_ask_state_factory(input_data.state)
-        deps = deep_ask_deps_factory(input_data.config)
-
-        async for event in stream_graph(graph, initial_state, deps):
-            event_data = format_sse_event(event)
-            yield event_data
-
     # Endpoint handlers
     async def stream_research(request: Request) -> StreamingResponse:
         """Research graph streaming endpoint."""
@@ -266,21 +235,6 @@ def create_agui_server(  # pragma: no cover
             },
         )
 
-    async def stream_deep_ask(request: Request) -> StreamingResponse:
-        """Deep ask graph streaming endpoint."""
-        body = await request.json()
-        input_data = RunAgentInput(**body)
-
-        return StreamingResponse(
-            deep_ask_event_stream(input_data),
-            media_type="text/event-stream",
-            headers={
-                "Cache-Control": "no-cache",
-                "Connection": "keep-alive",
-                "X-Accel-Buffering": "no",
-            },
-        )
-
     async def health_check(_: Request) -> JSONResponse:
         """Health check endpoint."""
         return JSONResponse({"status": "healthy"})
@@ -288,7 +242,6 @@ def create_agui_server(  # pragma: no cover
     # Define routes
     routes = [
         Route("/v1/research/stream", stream_research, methods=["POST"]),
-        Route("/v1/deep-ask/stream", stream_deep_ask, methods=["POST"]),
         Route("/health", health_check, methods=["GET"]),
     ]