harden delivery pipeline and production runtime

app/main.py

@@ -1,4 +1,6 @@
 from contextlib import asynccontextmanager
+from collections.abc import AsyncIterator
+from typing import cast
 
 from fastapi import FastAPI
 
@@ -7,23 +9,30 @@ from app.config import load_settings
 from app.core.exception_handlers import register_exception_handlers
 from app.ha.client import HaClient, HaClientSettings
 from app.ha.reader import HaReader
+from app.ml.registry.model_registry import ModelRegistry
 from backend.routes.ml import init_ml_routes
 
 
 @asynccontextmanager
-async def lifespan(app: FastAPI):  # type: ignore[no-untyped-def]
+async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     settings = app.state.settings
+    client: HaClient | None = None
+    app.state.registry = ModelRegistry(settings.model_store)
     if hasattr(app.state, "ha_reader"):
         del app.state.ha_reader
     if settings.ha_configured:
         client = HaClient(
             settings=HaClientSettings(
-                url=settings.ha_url,
-                token=settings.ha_token,
+                url=cast(str, settings.ha_url),
+                token=cast(str, settings.ha_token),
             )
         )
         app.state.ha_reader = HaReader(client=client)
-    yield
+    try:
+        yield
+    finally:
+        if client is not None:
+            client.close()
 
 
 app = FastAPI(