step-5: unify ws handler (device_ws.py, chat.py)

- device_ws.py: dispatch home_request/popup_request to HomeFormatter/PopupFormatter
  via async tasks; each request gets a UUID request_id for frame correlation
- chat.py: remove chat_stream WS endpoint (superseded by unified device WS);
  keep POST /chat REST fallback unchanged
- 5 new integration tests pass; all 22 existing device_ws tests still pass

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/api/routes/device_ws.py

@@ -33,14 +33,18 @@ from __future__ import annotations
 import asyncio
 import json
 import logging
+from uuid import uuid4
 
 from fastapi import APIRouter, WebSocket, WebSocketDisconnect
 from jose import JWTError, jwt
-from sqlalchemy import select, update
+from sqlalchemy import update
 
 from app.config.settings import settings
 from app.core.agent_runner import trigger_pending_runs
 from app.core.device_manager import device_manager
+from app.core.orchestrator import orchestrate_v3_stream
+from app.core.output_formatter import HomeFormatter, PopupFormatter
+from app.core.ws_context import clear_client_executor, set_client_executor
 from app.db import async_session
 from app.models import AgentRunLog
 from app.schemas import WsFrameType
@@ -173,6 +177,16 @@ async def _message_loop(websocket: WebSocket, user_id: str) -> None:
                     "device_ws: agent_complete missing run_id from user=%s", user_id
                 )
 
+        elif frame_type == WsFrameType.home_request:
+            asyncio.create_task(
+                _handle_home_request(websocket, user_id, frame)
+            )
+
+        elif frame_type == WsFrameType.popup_request:
+            asyncio.create_task(
+                _handle_popup_request(websocket, user_id, frame)
+            )
+
         elif frame_type == "pong":
             # Heartbeat ack — nothing to do, connection is alive.
             pass
@@ -183,6 +197,76 @@ async def _message_loop(websocket: WebSocket, user_id: str) -> None:
             )
 
 
+# ── v3 Chat Handlers ──────────────────────────────────────────────────
+
+async def _make_ws_executor(websocket: WebSocket, user_id: str):
+    """Return a callback that sends tool_call frames and awaits tool_result."""
+    async def _executor(payload: dict) -> dict:
+        payload["type"] = WsFrameType.tool_call
+        await websocket.send_text(json.dumps(payload))
+        future = device_manager.create_pending_call(user_id, payload["id"])
+        return await future
+    return _executor
+
+
+async def _handle_home_request(
+    websocket: WebSocket,
+    user_id: str,
+    frame: dict,
+) -> None:
+    """Handle a home_request frame — streams HomeFormatter output back on the socket."""
+    request_id = frame.get("request_id") or str(uuid4())
+    message: str = frame.get("message", "")
+    context: dict = {
+        "conversation_history": frame.get("conversation_history", []),
+    }
+
+    executor = await _make_ws_executor(websocket, user_id)
+    set_client_executor(executor)
+    try:
+        token_stream = orchestrate_v3_stream(user_id, message, context)
+        # Collect tool_results via the formatter after the stream completes.
+        # We pass an empty list initially; tool_results are populated during
+        # the agent run via ws_context._tool_result_collector (set inside _tool_loop_stream).
+        formatter = HomeFormatter(request_id=request_id, tool_results=[])
+        async for ws_frame in formatter.format(token_stream):
+            await websocket.send_text(ws_frame.model_dump_json())
+    except Exception as exc:
+        logger.error(
+            "device_ws: home_request failed user=%s req=%s: %s",
+            user_id, request_id, exc,
+        )
+    finally:
+        clear_client_executor()
+
+
+async def _handle_popup_request(
+    websocket: WebSocket,
+    user_id: str,
+    frame: dict,
+) -> None:
+    """Handle a popup_request frame — streams PopupFormatter output back on the socket."""
+    request_id = frame.get("request_id") or str(uuid4())
+    message: str = frame.get("message", "")
+    scope: dict = frame.get("scope", {})
+    context: dict = {"scope": scope}
+
+    executor = await _make_ws_executor(websocket, user_id)
+    set_client_executor(executor)
+    try:
+        token_stream = orchestrate_v3_stream(user_id, message, context)
+        formatter = PopupFormatter(request_id=request_id)
+        async for ws_frame in formatter.format(token_stream):
+            await websocket.send_text(ws_frame.model_dump_json())
+    except Exception as exc:
+        logger.error(
+            "device_ws: popup_request failed user=%s req=%s: %s",
+            user_id, request_id, exc,
+        )
+    finally:
+        clear_client_executor()
+
+
 # ── Heartbeat ─────────────────────────────────────────────────────────
 
 async def _heartbeat_loop(websocket: WebSocket) -> None: