Merge remote dev branch

apps/api/src/services/health_monitor.py

@@ -15,6 +15,7 @@ from src.models.tool_instance import ToolInstance
 from src.services.correlation import get_correlation_id
 from src.services.docker import check_tunnel_health, get_container_status
 from src.services.event_bus import InstanceEventBus, InstanceEventPayload
+from src.services.notification_service import notification_service
 
 logger = logging.getLogger(__name__)
 
@@ -217,3 +218,36 @@ class HealthMonitor:
         }
 
         await self._event_bus.publish(event_type, payload)
+
+        # Create notification for instance owner (fire-and-forget)
+        if new_status == "error":
+            category = "instance"
+            severity = "error"
+            title = "Container failed"
+        else:
+            category = "health"
+            if new_status == "unhealthy":
+                severity = "warning"
+                title = "Container unhealthy"
+            else:
+                severity = "info"
+                title = "Container recovered"
+
+        try:
+            await notification_service.create_notification(
+                session=session,
+                user_id=instance.owner_id,
+                category=category,
+                severity=severity,
+                title=title,
+                message=message,
+                source_type="tool_instances",
+                source_id=instance.id,
+                metadata=metadata,
+            )
+        except Exception:
+            logger.exception(
+                "Failed to create notification for health event %s",
+                event_type,
+                extra={"correlation_id": correlation_id},
+            )

apps/api/src/services/lifecycle_hooks.py

@@ -1,5 +1,6 @@
 """Lifecycle hook helpers for instrumenting tool instance transitions."""
 
+import logging
 import uuid
 from datetime import datetime, timezone
 
@@ -9,6 +10,25 @@ from src.models.instance_event import InstanceEvent
 from src.models.tool_instance import ToolInstance
 from src.services.correlation import get_correlation_id
 from src.services.event_bus import InstanceEventBus, InstanceEventPayload
+from src.services.notification_service import notification_service
+
+logger = logging.getLogger(__name__)
+
+
+def _derive_title(event_type: str) -> str:
+    """Map lifecycle event type to a human-readable notification title."""
+    mapping = {
+        "instance.created": "Container created",
+        "instance.started": "Container started",
+        "instance.stopped": "Container stopped",
+        "instance.restarted": "Container restarted",
+        "instance.deleted": "Container deleted",
+        "instance.error": "Container error",
+    }
+    return mapping.get(
+        event_type,
+        event_type.replace("instance.", "").replace("_", " ").title(),
+    )
 
 
 def _build_payload(
@@ -96,3 +116,26 @@ async def publish_lifecycle_event(
 
     # Publish to bus
     await event_bus.publish(event_type, payload)
+
+    # Create notification for instance owner (fire-and-forget)
+    severity = "error" if event_type == "instance.error" else "info"
+    title = _derive_title(event_type)
+
+    try:
+        await notification_service.create_notification(
+            session=session,
+            user_id=instance.owner_id,
+            category="instance",
+            severity=severity,
+            title=title,
+            message=message,
+            source_type="tool_instances",
+            source_id=instance.id,
+            metadata=metadata,
+        )
+    except Exception:
+        logger.exception(
+            "Failed to create notification for lifecycle event %s",
+            event_type,
+            extra={"correlation_id": payload.get("correlation_id", "unknown")},
+        )