refactor: replace orchestrator with LangGraph deep-agent supervisors

- Add app/core/deep_agent.py with Home and Floating supervisor graphs
  using LangGraph create_react_agent (hierarchical pattern)
- Strip ChatAgent classes from all 4 agent files, keep @tool functions
- Rewrite output_formatter.py for event-based (token/tool_end/mutations) stream
- Update device_ws.py to use run_home_stream/run_floating_stream
- Rewrite chat.py REST route to use run_home
- Add update_core_memory tool to both supervisors
- Add langgraph>=0.3.0 to requirements.txt
- Remove orchestrator.py, execution_plan.py, agent_registry.py, plans.py
- Remove PlanAction, PlanStep, ExecutionPlan, execution_mode from schemas
- Update all affected tests to match new API
- Remove 6 deprecated test files for deleted modules
- Clean up stale docstrings referencing removed orchestrator

app/core/memory_middleware.py

@@ -43,7 +43,7 @@ _PROACTIVE_CONFIDENCE_THRESHOLD = 0.6
 
 
 class MemoryMiddleware:
-    """Enrich orchestrator context with memory and persist interactions after."""
+    """Enrich agent context with memory and persist interactions after."""
 
     def __init__(self, db: AsyncSession) -> None:
         self._db = db
@@ -51,7 +51,7 @@ class MemoryMiddleware:
     # ── Public API ────────────────────────────────────────────────────────────
 
     async def enrich_context(self, user_id: str, message: str) -> dict[str, Any]:
-        """Build memory context dict to inject into the orchestrator before LLM call.
+        """Build memory context dict to inject into the agent before LLM call.
 
         Returns a dict with keys:
           core_memory        — {key: plaintext_value, ...}