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
This commit is contained in:
2026-05-28 23:09:27 +02:00
parent 0fdbef578f
commit 4a7f24348c
26 changed files with 4142 additions and 11 deletions
+30
View File
@@ -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,
)