Harden production workflows and agent admission

server/monlet_server/api/system_summary.py

@@ -0,0 +1,43 @@
+from datetime import UTC, datetime
+
+from fastapi import APIRouter, Depends
+from sqlalchemy import func, select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from ..db import get_session
+from ..models import Agent, Check, Incident
+from ..schemas import SystemSummaryResponse
+
+router = APIRouter()
+
+
+@router.get("/system-summary", response_model=SystemSummaryResponse)
+async def system_summary(session: AsyncSession = Depends(get_session)) -> SystemSummaryResponse:
+    agents_rows = (
+        await session.execute(
+            select(Agent.status, func.count())
+            .where(Agent.accepted_key_hash.is_not(None))
+            .group_by(Agent.status)
+        )
+    ).all()
+    checks_rows = (
+        await session.execute(select(Check.status, func.count()).group_by(Check.status))
+    ).all()
+    open_incidents = (
+        await session.execute(
+            select(func.count()).select_from(Incident).where(Incident.state == "open")
+        )
+    ).scalar_one()
+
+    agents = {status: count for status, count in agents_rows}
+    checks = {status: count for status, count in checks_rows}
+    return SystemSummaryResponse(
+        agents_online=agents.get("alive", 0),
+        agents_offline=agents.get("stale", 0) + agents.get("dead", 0),
+        checks_ok=checks.get("ok", 0),
+        checks_warning=checks.get("warning", 0),
+        checks_critical=checks.get("critical", 0),
+        checks_unknown=checks.get("unknown", 0),
+        open_incidents=open_incidents,
+        generated_at=datetime.now(UTC),
+    )