feat: WebSocket-Healthcheck und Status-Tracking\n\n- Fügt _WsStatus-Klasse hinzu, die den aktuellen Verbindungsstatus verfolgt\n- Neuer Endpoint /health/websocket gibt Status zurück (connected/connecting/error)\n- Event-Listener aktualisiert den Status bei allen Zustandsänderungen\n- Fallback-Task wird korrekt im lifespan verwaltet\n- Bessere Fehlerbehandlung und Statusmeldungen\n\nImproves observability of the event-based architecture.

app/main.py

@@ -25,6 +25,17 @@ from backend.routes.ml import init_ml_routes
 
 logger = logging.getLogger(__name__)
 
+class _WsStatus:
+    """Einfacher Status-Tracker für den WebSocket-Listener.
+
+    Wird als Attribut an app.state gehängt und enthält:
+    - status: "disconnected" | "connecting" | "connected" | "error"
+    - error: str | None (Fehlermeldung bei status=error)
+    """
+    def __init__(self) -> None:
+        self.status: str = "disconnected"
+        self.error: str | None = None
+
 
 @asynccontextmanager
 async def lifespan(app: FastAPI) -> AsyncIterator[None]:
@@ -32,6 +43,7 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     client: HaClient | None = None
     reconcile_task: asyncio.Task[None] | None = None
     event_listener_task: asyncio.Task[None] | None = None
+    fallback_task: asyncio.Task[None] | None = None
     app.state.registry = ModelRegistry(settings.model_store)
     app.state.actuator_store = ActuatorStore(settings.actuator_store)
     if hasattr(app.state, "ha_reader"):
@@ -59,11 +71,13 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
             store=app.state.actuator_store,
             settings=settings,
         )
+        app.state.ws_status = _WsStatus()
         await asyncio.to_thread(app.state.actuator_service.reconcile_all, "startup")
         await asyncio.to_thread(app.state.behavior_engine.train_all)
         await asyncio.to_thread(app.state.behavior_engine.evaluate_all)
         reconcile_task = asyncio.create_task(_periodic_reconciliation(app))
         event_listener_task = asyncio.create_task(_ha_event_listener(app, client))
+        fallback_task = asyncio.create_task(_fallback_prediction(app))
     try:
         yield
     finally:
@@ -75,6 +89,10 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
             event_listener_task.cancel()
             with suppress(asyncio.CancelledError):
                 await event_listener_task
+        if fallback_task is not None:
+            fallback_task.cancel()
+            with suppress(asyncio.CancelledError):
+                await fallback_task
         if client is not None:
             client.close()
 
@@ -99,6 +117,19 @@ app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
 def health() -> dict[str, str]:
     return {"status": "ok"}
 
+@app.get("/health/websocket")
+def websocket_health() -> dict[str, object]:
+    """Gibt den aktuellen Status des WebSocket-Listeners zurück.
+
+    Antwort:
+    - status: "disconnected" | "connecting" | "connected" | "error"
+    - error: str | None (nur bei status=error)
+    """
+    ws_status = getattr(app.state, "ws_status", None)
+    if ws_status is None:
+        return {"status": "unavailable", "error": "WebSocket-Listener nicht initialisiert"}
+    return {"status": ws_status.status, "error": ws_status.error}
+
 
 @app.get("/")
 def root() -> FileResponse:
@@ -127,21 +158,34 @@ async def _ha_event_listener(app: FastAPI, client: HaClient) -> None:
     store = app.state.actuator_store
     if not isinstance(engine, BehaviorEngine) or not isinstance(store, ActuatorStore):
         logger.error("BehaviorEngine oder ActuatorStore nicht initialisiert")
+        ws_status = getattr(app.state, "ws_status", None)
+        if ws_status is not None:
+            ws_status.status = "error"
+            ws_status.error = "BehaviorEngine oder ActuatorStore nicht initialisiert"
         return
     ha_url = str(settings.ha_url).rstrip("/")
     ws_url = ha_url.replace("http://", "ws://").replace("https://", "wss://") + "/api/websocket"
     auth_token = cast(str, settings.ha_token)
+    ws_status = getattr(app.state, "ws_status", None)
+    if ws_status is not None:
+        ws_status.status = "connecting"
     while True:
         try:
             async with websockets.connect(ws_url, extra_headers={
                 "Authorization": f"Bearer {auth_token}"
             }) as websocket:
                 logger.info("WebSocket-Verbindung zu Home Assistant hergestellt")
+                if ws_status is not None:
+                    ws_status.status = "connected"
+                    ws_status.error = None
                 # Authentifizierung durchführen
                 auth_msg = await websocket.recv()
                 auth_data = json.loads(auth_msg)
                 if auth_data.get("type") != "auth_ok":
                     logger.error("WebSocket-Authentifizierung fehlgeschlagen")
+                    if ws_status is not None:
+                        ws_status.status = "error"
+                        ws_status.error = "Authentifizierung fehlgeschlagen"
                     await asyncio.sleep(5)
                     continue
                 # Auf alle State Changes subscriben
@@ -171,16 +215,33 @@ async def _ha_event_listener(app: FastAPI, client: HaClient) -> None:
                         logger.exception("Fehler bei Event-Verarbeitung: %s", exc)
         except (websockets.exceptions.ConnectionClosed, OSError) as exc:
             logger.warning("WebSocket-Verbindung unterbrochen: %s. Wiederholung in 5s...", exc)
+            if ws_status is not None:
+                ws_status.status = "reconnecting"
+                ws_status.error = str(exc)
             await asyncio.sleep(5)
         except Exception as exc:
             logger.exception("Unerwarteter Fehler im Event-Listener: %s", exc)
+            if ws_status is not None:
+                ws_status.status = "error"
+                ws_status.error = str(exc)
             await asyncio.sleep(5)
 
 
 # Fallback: periodische Vorhersage falls Event-Stream ausfällt
 async def _fallback_prediction(app: FastAPI) -> None:
+    """Periodische Vorhersage als Fallback, wenn WebSocket-Listener nicht verbunden ist.
+
+    Dies verhindert kompletten Ausfall der Vorhersagen bei Netzwerkproblemen.
+    """
     while True:
         await asyncio.sleep(app.state.settings.prediction_interval_seconds)
-        engine = getattr(app.state, "behavior_engine", None)
-        if isinstance(engine, BehaviorEngine):
-            await asyncio.to_thread(engine.evaluate_all)
+        # Nur ausführen, wenn WebSocket nicht verbunden ist
+        ws_status = getattr(app.state, "ws_status", None)
+        if ws_status is None or ws_status.status != "connected":
+            engine = getattr(app.state, "behavior_engine", None)
+            if isinstance(engine, BehaviorEngine):
+                logger.debug(
+                    "Fallback-Vorhersage aktiv (WebSocket-Status: %s)",
+                    ws_status.status if ws_status else "unavailable",
+                )
+                await asyncio.to_thread(engine.evaluate_all)