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/models/__init__.py

@@ -1,6 +1,8 @@
 from src.models.base import Base
 from src.models.config_profile import ConfigProfile, ConfigProfileInclude
 from src.models.git_repository import GitRepository
+from src.models.health_check import HealthCheck
+from src.models.instance_event import InstanceEvent
 from src.models.project import Project
 from src.models.ssh_key import SSHKey
 from src.models.terminal_session import TerminalSessionModel
@@ -15,6 +17,8 @@ __all__ = [
     "ConfigProfile",
     "ConfigProfileInclude",
     "GitRepository",
+    "HealthCheck",
+    "InstanceEvent",
     "Project",
     "SSHKey",
     "TerminalSessionModel",

apps/api/src/models/health_check.py

@@ -0,0 +1,30 @@
+"""SQLAlchemy model for health check snapshots."""
+
+import uuid
+from datetime import datetime
+
+from sqlalchemy import Boolean, DateTime, ForeignKey, Integer, String, Text, Uuid, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from src.models.base import Base, UUIDPrimaryKeyMixin
+
+
+class HealthCheck(UUIDPrimaryKeyMixin, Base):
+    __tablename__ = "health_checks"
+
+    instance_id: Mapped[uuid.UUID] = mapped_column(
+        Uuid(as_uuid=True),
+        ForeignKey("tool_instances.id", ondelete="CASCADE"),
+        nullable=False,
+    )
+    container_status: Mapped[str | None] = mapped_column(String(50), nullable=True)
+    container_healthy: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
+    tunnel_healthy: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
+    exit_code: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    probe_status: Mapped[str | None] = mapped_column(String(50), nullable=True)
+    probe_output: Mapped[str | None] = mapped_column(Text, nullable=True)
+    checked_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True),
+        server_default=func.now(),
+        nullable=False,
+    )

apps/api/src/models/instance_event.py

@@ -0,0 +1,39 @@
+"""SQLAlchemy model for instance lifecycle event audit rows."""
+
+import uuid
+from datetime import datetime
+from typing import Any
+
+from sqlalchemy import DateTime, ForeignKey, JSON, String, Text, Uuid, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from src.models.base import Base, UUIDPrimaryKeyMixin
+
+
+class InstanceEvent(UUIDPrimaryKeyMixin, Base):
+    __tablename__ = "instance_events"
+
+    instance_id: Mapped[uuid.UUID] = mapped_column(
+        Uuid(as_uuid=True),
+        ForeignKey("tool_instances.id", ondelete="CASCADE"),
+        nullable=False,
+    )
+    event_type: Mapped[str] = mapped_column(String(50), nullable=False)
+    status: Mapped[str | None] = mapped_column(String(50), nullable=True)
+    message: Mapped[str | None] = mapped_column(Text, nullable=True)
+    created_by: Mapped[uuid.UUID | None] = mapped_column(
+        Uuid(as_uuid=True),
+        ForeignKey("users.id", ondelete="SET NULL"),
+        nullable=True,
+    )
+    event_metadata: Mapped[dict[str, Any]] = mapped_column(
+        "metadata",
+        JSON,
+        nullable=False,
+        default=dict,
+    )
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True),
+        server_default=func.now(),
+        nullable=False,
+    )