Make SillyHome startup resilient

CHANGELOG.md

@@ -1,5 +1,14 @@
 # Changelog
 
+## 0.7.15 - 2026-06-16
+- Add-on-Start ist robust gegen Home-Assistant-Core-502 beim Systemboot:
+  API und WebSocket-Listener starten trotzdem, Reconciliation/Training werden
+  im Hintergrund mit Retry nachgeholt.
+- Periodische Reconciliation und Fallback-Auswertung beenden den Dienst nicht
+  mehr bei temporären HA-Fehlern.
+- Add-on-Watchdog prüft `/health`, damit Supervisor den Dienst nach Absturz
+  wieder starten kann.
+
 ## 0.7.14 - 2026-06-16
 - Onboarding-Vorschläge laden im Dashboard nachgelagert, damit Status,
   Aktor-Auswahl und bestehende Geräte nicht auf Automation-Discovery warten.

addon/config.yaml

@@ -1,5 +1,5 @@
 name: SillyHome Next
-version: "0.7.14"
+version: "0.7.15"
 slug: sillyhome_next
 description: Lernt automatisch aus deinem Verhalten und steuert freigegebene Aktoren
 url: http://192.168.6.31:3000/pino/sillyhome-next
@@ -7,6 +7,7 @@ arch:
   - amd64
 startup: application
 boot: auto
+watchdog: http://[HOST]:[PORT:8000]/health
 init: false
 ingress: true
 ingress_port: 8000

app/main.py

@@ -43,6 +43,7 @@ class _WsStatus:
 async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     settings = app.state.settings
     client: HaClient | None = None
+    startup_task: asyncio.Task[None] | None = None
     reconcile_task: asyncio.Task[None] | None = None
     event_listener_task: asyncio.Task[None] | None = None
     fallback_task: asyncio.Task[None] | None = None
@@ -74,15 +75,17 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
             settings=settings,
         )
         app.state.ws_status = _WsStatus()
-        await asyncio.to_thread(app.state.actuator_service.reconcile_all, "startup")
+        startup_task = asyncio.create_task(_startup_reconciliation(app))
-        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:
+        if startup_task is not None:
+            startup_task.cancel()
+            with suppress(asyncio.CancelledError):
+                await startup_task
         if reconcile_task is not None:
             reconcile_task.cancel()
             with suppress(asyncio.CancelledError):
@@ -102,7 +105,7 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
 app = FastAPI(
     title="SillyHome Next API",
     description="Lokales Smart-Home-Intelligenzsystem für Home Assistant.",
-    version="0.7.14",
+    version="0.7.15",
     lifespan=lifespan,
 )
 app.state.settings = load_settings()
@@ -147,10 +150,39 @@ async def _periodic_reconciliation(app: FastAPI) -> None:
         service = getattr(app.state, "actuator_service", None)
         if not isinstance(service, ActuatorReconciliationService):
             continue
-        await asyncio.to_thread(service.reconcile_all, "scheduled")
+        try:
+            await asyncio.to_thread(service.reconcile_all, "scheduled")
+            engine = getattr(app.state, "behavior_engine", None)
+            if isinstance(engine, BehaviorEngine):
+                await asyncio.to_thread(engine.train_all)
+        except Exception:
+            logger.exception("Geplante Reconciliation fehlgeschlagen; nächster Lauf versucht es erneut.")
+
+
+async def _startup_reconciliation(app: FastAPI) -> None:
+    delay_seconds = 5
+    while True:
+        service = getattr(app.state, "actuator_service", None)
         engine = getattr(app.state, "behavior_engine", None)
-        if isinstance(engine, BehaviorEngine):
+        if not isinstance(service, ActuatorReconciliationService) or not isinstance(
+            engine,
+            BehaviorEngine,
+        ):
+            return
+        try:
+            await asyncio.to_thread(service.reconcile_all, "startup")
             await asyncio.to_thread(engine.train_all)
+            await asyncio.to_thread(engine.evaluate_all)
+            logger.info("Startup-Reconciliation erfolgreich abgeschlossen.")
+            return
+        except Exception as exc:
+            logger.warning(
+                "Startup-Reconciliation verschoben: %s. Neuer Versuch in %ss.",
+                exc,
+                delay_seconds,
+            )
+            await asyncio.sleep(delay_seconds)
+            delay_seconds = min(delay_seconds * 2, 60)
 
 
 async def _ha_event_listener(app: FastAPI, client: HaClient) -> None:
@@ -243,7 +275,11 @@ async def _ha_event_listener(app: FastAPI, client: HaClient) -> None:
                         logger.warning("Ungültige JSON-Nachricht von HA-WebSocket")
                     except Exception as exc:
                         logger.exception("Fehler bei Event-Verarbeitung: %s", exc)
-        except (websockets.exceptions.ConnectionClosed, OSError) as exc:
+        except (
+            websockets.exceptions.ConnectionClosed,
+            websockets.exceptions.InvalidStatus,
+            OSError,
+        ) as exc:
             logger.warning("WebSocket-Verbindung unterbrochen: %s. Wiederholung in 5s...", exc)
             if ws_status is not None:
                 ws_status.status = "reconnecting"
@@ -280,7 +316,10 @@ async def _fallback_prediction(app: FastAPI) -> None:
                     "Fallback-Vorhersage aktiv (WebSocket-Status: %s)",
                     ws_status.status if ws_status else "unavailable",
                 )
-                await asyncio.to_thread(engine.evaluate_all)
+                try:
+                    await asyncio.to_thread(engine.evaluate_all)
+                except Exception:
+                    logger.exception("Fallback-Vorhersage fehlgeschlagen.")
 
 
 def _load_ha_state_cache(reader: HaReader) -> dict[str, HaEntitySummary]:

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sillyhome-next"
-version = "0.7.14"
+version = "0.7.15"
 description = "Lokales Smart-Home-Intelligenzsystem für Home Assistant"
 requires-python = ">=3.11"
 dependencies = [