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
2026-05-28 23:09:27 +02:00
parent 0fdbef578f
commit 4a7f24348c
26 changed files with 4142 additions and 11 deletions
@@ -0,0 +1,122 @@
+"""add monitoring tables
+
+Revision ID: 2026_05_28_add_monitoring_tables
+Revises: 2026_05_28_drop_tool_configs_and_config_folders
+Create Date: 2026-05-28
+
+"""
+
+from collections.abc import Sequence
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision: str = "2026_05_28_add_monitoring_tables"
+down_revision: str | None = "2026_05_28_drop_tool_configs_and_config_folders"
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "instance_events",
+        sa.Column("id", sa.Uuid(), nullable=False),
+        sa.Column(
+            "instance_id",
+            sa.Uuid(),
+            nullable=False,
+        ),
+        sa.Column("event_type", sa.String(length=50), nullable=False),
+        sa.Column("status", sa.String(length=50), nullable=True),
+        sa.Column("message", sa.Text(), nullable=True),
+        sa.Column("created_by", sa.Uuid(), nullable=True),
+        sa.Column(
+            "metadata",
+            sa.JSON(),
+            nullable=False,
+            server_default="{}",
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.func.now(),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["instance_id"],
+            ["tool_instances.id"],
+            ondelete="CASCADE",
+        ),
+        sa.ForeignKeyConstraint(
+            ["created_by"],
+            ["users.id"],
+            ondelete="SET NULL",
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(
+        "idx_instance_events_instance_id",
+        "instance_events",
+        ["instance_id"],
+    )
+    op.create_index(
+        "idx_instance_events_created_at",
+        "instance_events",
+        ["created_at"],
+        postgresql_using="btree",
+    )
+    op.create_index(
+        "idx_instance_events_event_type",
+        "instance_events",
+        ["event_type"],
+    )
+
+    op.create_table(
+        "health_checks",
+        sa.Column("id", sa.Uuid(), nullable=False),
+        sa.Column(
+            "instance_id",
+            sa.Uuid(),
+            nullable=False,
+        ),
+        sa.Column("container_status", sa.String(length=50), nullable=True),
+        sa.Column("container_healthy", sa.Boolean(), nullable=True),
+        sa.Column("tunnel_healthy", sa.Boolean(), nullable=True),
+        sa.Column("exit_code", sa.Integer(), nullable=True),
+        sa.Column("probe_status", sa.String(length=50), nullable=True),
+        sa.Column("probe_output", sa.Text(), nullable=True),
+        sa.Column(
+            "checked_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.func.now(),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["instance_id"],
+            ["tool_instances.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(
+        "idx_health_checks_instance_id",
+        "health_checks",
+        ["instance_id"],
+    )
+    op.create_index(
+        "idx_health_checks_checked_at",
+        "health_checks",
+        ["checked_at"],
+        postgresql_using="btree",
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("idx_health_checks_checked_at", table_name="health_checks")
+    op.drop_index("idx_health_checks_instance_id", table_name="health_checks")
+    op.drop_table("health_checks")
+    op.drop_index("idx_instance_events_event_type", table_name="instance_events")
+    op.drop_index("idx_instance_events_created_at", table_name="instance_events")
+    op.drop_index("idx_instance_events_instance_id", table_name="instance_events")
+    op.drop_table("instance_events")