feat: container monitoring backend core (PR-1)

- Add instance_events and health_checks tables with Alembic migration
- InstanceEventBus: typed pub/sub singleton with wildcard support
- HealthMonitor: async background loop polling containers every 15s
- SSE endpoint GET /events/stream with auth and connection limits
- Lifecycle hooks in tool_instances.py (create/start/stop/restart/delete)
- Structured JSON logging with correlation IDs
- 15 new unit tests (EventBus, HealthMonitor, MonitoringModels)

Quality gates: pytest 15 new passed, ruff clean

apps/api/src/services/event_bus.py

@@ -0,0 +1,97 @@
+"""In-memory typed event bus for instance lifecycle and health events."""
+
+import asyncio
+import inspect
+import logging
+import uuid
+from collections.abc import Awaitable, Callable
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+InstanceEventPayload = dict[str, Any]
+EventCallback = Callable[[InstanceEventPayload], Awaitable[None] | None]  # noqa: UP044
+
+
+class InstanceEventBus:
+    """Singleton in-memory event bus with typed pub/sub and exception isolation."""
+
+    _instance: "InstanceEventBus | None" = None
+    _lock: asyncio.Lock = asyncio.Lock()
+
+    def __init__(self) -> None:
+        self._subscribers: dict[str, list[tuple[str, EventCallback]]] = {}
+
+    def __new__(cls) -> "InstanceEventBus":
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+            cls._instance._subscribers = {}
+        return cls._instance
+
+    def _reset_for_testing(self) -> None:
+        """Clear all subscribers. For test use only."""
+        self._subscribers.clear()
+
+    def subscribe(
+        self,
+        event_type: str,
+        callback: EventCallback,
+    ) -> Callable[[], None]:
+        """Register a callback for an event type.
+
+        Args:
+            event_type: The event type to subscribe to.
+            callback: A sync or async callable that receives the payload.
+
+        Returns:
+            An unsubscribe function.
+        """
+        if event_type not in self._subscribers:
+            self._subscribers[event_type] = []
+        callback_id = str(uuid.uuid4())
+        self._subscribers[event_type].append((callback_id, callback))
+
+        def unsubscribe() -> None:
+            self.unsubscribe(event_type, callback_id)
+
+        return unsubscribe
+
+    def unsubscribe(self, event_type: str, callback_id: str) -> None:
+        """Remove a specific callback by ID."""
+        if event_type in self._subscribers:
+            self._subscribers[event_type] = [
+                (cid, cb)
+                for cid, cb in self._subscribers[event_type]
+                if cid != callback_id
+            ]
+            if not self._subscribers[event_type]:
+                del self._subscribers[event_type]
+
+    def unsubscribe_all(self, event_type: str) -> None:
+        """Remove all subscribers for an event type."""
+        self._subscribers.pop(event_type, None)
+
+    async def publish(self, event_type: str, payload: InstanceEventPayload) -> None:
+        """Deliver payload to all subscribers of event_type.
+
+        Also delivers to subscribers registered under the wildcard "*".
+        Exceptions from individual subscribers are caught and logged;
+        delivery continues to remaining subscribers.
+        """
+        callbacks: list[tuple[str, EventCallback]] = []
+        callbacks.extend(self._subscribers.get(event_type, []))
+        callbacks.extend(self._subscribers.get("*", []))
+
+        for _callback_id, callback in callbacks:
+            try:
+                if inspect.iscoroutinefunction(callback):
+                    await callback(payload)
+                else:
+                    callback(payload)
+            except Exception:
+                correlation_id = payload.get("correlation_id", "unknown")
+                logger.exception(
+                    "Event subscriber failed for %s",
+                    event_type,
+                    extra={"correlation_id": correlation_id},
+                )