feat: migrate chat orchestration to deep langgraph workers

app/api/routes/chat.py

@@ -9,7 +9,7 @@ from fastapi import APIRouter, Depends
 from fastapi.responses import JSONResponse
 
 from app.api.deps import get_current_user
-from app.core.orchestrator import orchestrate
+from app.core.deep_agent import run_home
 from app.schemas import ChatRequest, UserProfile
 
 router = APIRouter(prefix="/chat", tags=["chat"])
@@ -20,10 +20,10 @@ async def chat(
     body: ChatRequest,
     current_user: UserProfile = Depends(get_current_user),
 ) -> JSONResponse:
-    """Route a chat message through the orchestrator.
-
-    Returns ``ChatResponse`` for ``execution_mode='direct'``,
-    or ``ExecutionPlan`` for ``execution_mode='plan'``.
-    """
-    result = await orchestrate(body)
-    return JSONResponse(content=result.model_dump())
+    """REST fallback for home chat when websocket streaming is unavailable."""
+    response = await run_home(
+        user_id=current_user.id,
+        message=body.message,
+        context=body.context.model_dump(),
+    )
+    return JSONResponse(content={"response": response})

app/api/routes/device_ws.py

@@ -41,10 +41,10 @@ from sqlalchemy import update
 
 from app.config.settings import settings
 from app.core.agent_runner import trigger_pending_runs
+from app.core.deep_agent import run_floating_stream, run_home_stream
 from app.core.device_manager import device_manager
 from app.core.memory_middleware import MemoryMiddleware
-from app.core.orchestrator import orchestrate_v3_stream
-from app.core.output_formatter import HomeFormatter, FloatingFormatter
+from app.core.output_formatter import StreamFormatter
 from app.core.ws_context import clear_client_executor, set_client_executor
 from app.db import async_session
 from app.models import AgentRunLog
@@ -233,19 +233,10 @@ async def _handle_home_request(
     executor = await _make_ws_executor(websocket, user_id)
     set_client_executor(executor)
     response_chunks: list[str] = []
-    agent_holder: list = []
     try:
-        token_stream = orchestrate_v3_stream(
-            user_id, message, context, agent_holder=agent_holder
-        )
-        formatter = HomeFormatter(request_id=request_id, tool_results=[])
-        async for ws_frame in formatter.format(token_stream):
-            # Inject mutations from agent tool_results into stream_end
-            if ws_frame.type == "stream_end" and agent_holder:  # type: ignore[union-attr]
-                ws_frame.mutations = [  # type: ignore[union-attr]
-                    {"action": r["action"], "table": r["table"], "data": r["data"]}
-                    for r in getattr(agent_holder[0], "tool_results", [])
-                ]
+        event_stream = run_home_stream(user_id, message, context)
+        formatter = StreamFormatter(request_id=request_id)
+        async for ws_frame in formatter.format(event_stream):
             await websocket.send_text(ws_frame.model_dump_json())
             # Collect text chunks to build the full response for episode storage
             if ws_frame.type == "stream_text":  # type: ignore[union-attr]
@@ -287,18 +278,10 @@ async def _handle_floating_request(
     executor = await _make_ws_executor(websocket, user_id)
     set_client_executor(executor)
     response_chunks: list[str] = []
-    agent_holder: list = []
     try:
-        token_stream = orchestrate_v3_stream(
-            user_id, message, context, agent_holder=agent_holder
-        )
-        formatter = FloatingFormatter(request_id=request_id)
-        async for ws_frame in formatter.format(token_stream):
-            if ws_frame.type == "stream_end" and agent_holder:  # type: ignore[union-attr]
-                ws_frame.mutations = [  # type: ignore[union-attr]
-                    {"action": r["action"], "table": r["table"], "data": r["data"]}
-                    for r in getattr(agent_holder[0], "tool_results", [])
-                ]
+        event_stream = run_floating_stream(user_id, message, context)
+        formatter = StreamFormatter(request_id=request_id)
+        async for ws_frame in formatter.format(event_stream):
             await websocket.send_text(ws_frame.model_dump_json())
             if ws_frame.type == "stream_text":  # type: ignore[union-attr]
                 response_chunks.append(ws_frame.chunk)  # type: ignore[union-attr]

app/api/routes/plans.py

@@ -1,37 +0,0 @@
-"""Plans routes: GET /plans/playbook and GET /plans/playbook/{plan_id}."""
-
-from __future__ import annotations
-
-from fastapi import APIRouter, Depends, HTTPException, status
-
-from app.api.deps import get_current_user
-from app.core.execution_plan import plan_cache
-from app.schemas import ExecutionPlan, UserProfile
-
-router = APIRouter(prefix="/plans", tags=["plans"])
-
-
-@router.get("/playbook", response_model=list[ExecutionPlan])
-async def list_playbooks(
-    current_user: UserProfile = Depends(get_current_user),
-) -> list[ExecutionPlan]:
-    """Return all cached execution plan playbooks for the authenticated user.
-
-    TODO(Step11): filter by tier — power+ plans gated behind batch_builder feature.
-    """
-    return plan_cache.get_all_playbooks()
-
-
-@router.get("/playbook/{plan_id}", response_model=ExecutionPlan)
-async def get_playbook(
-    plan_id: str,
-    current_user: UserProfile = Depends(get_current_user),
-) -> ExecutionPlan:
-    """Return a specific execution plan playbook by ID."""
-    plan = plan_cache.get_plan(plan_id)
-    if plan is None:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=f"Plan not found: {plan_id}",
-        )
-    return plan