feat: add letta-style memory tools with request/user debug tracing

app/api/routes/device_ws.py

@@ -223,10 +223,11 @@ async def _handle_home_request(
     # ── Memory: enrich context before LLM call ────────────────────────
     async with async_session() as db:
         memory = MemoryMiddleware(db)
-        memory_context = await memory.enrich_context(user_id, message)
+        memory_context = await memory.enrich_context(user_id, message, trace_id=request_id)
 
     context: dict = {
         "conversation_history": frame.get("conversation_history", []),
+        "_debug": {"request_id": request_id, "session_id": session_id, "user_id": user_id},
         **memory_context,
     }
 
@@ -253,7 +254,7 @@ async def _handle_home_request(
     async with async_session() as db:
         memory = MemoryMiddleware(db)
         await memory.store_episode(
-            user_id, session_id, message, "".join(response_chunks)
+            user_id, session_id, message, "".join(response_chunks), trace_id=request_id
         )
 
 
@@ -271,9 +272,13 @@ async def _handle_floating_request(
     # ── Memory: enrich context before LLM call ────────────────────────
     async with async_session() as db:
         memory = MemoryMiddleware(db)
-        memory_context = await memory.enrich_context(user_id, message)
+        memory_context = await memory.enrich_context(user_id, message, trace_id=request_id)
 
-    context: dict = {"scope": scope, **memory_context}
+    context: dict = {
+        "scope": scope,
+        "_debug": {"request_id": request_id, "session_id": session_id, "user_id": user_id},
+        **memory_context,
+    }
 
     executor = await _make_ws_executor(websocket, user_id)
     set_client_executor(executor)
@@ -297,7 +302,7 @@ async def _handle_floating_request(
     async with async_session() as db:
         memory = MemoryMiddleware(db)
         await memory.store_episode(
-            user_id, session_id, message, "".join(response_chunks)
+            user_id, session_id, message, "".join(response_chunks), trace_id=request_id
         )