Files
bvandeusen 35f658b573
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 8s
CI / integration (push) Successful in 2m17s
CI / publish (push) Successful in 1m10s
feat(monitors): unify ping/dns/http into one Monitor entity + custom targets
Collapse the three former check types into a single core `Monitor` entity
with one management surface (/monitors), one result table (monitor_results),
and a single scheduled task. Every type can now watch a free-standing custom
destination (optional host_id) — not just a registered Host.

- models: Monitor + MonitorResult replace PingResult/DnsResult; Host loses its
  ping/dns facet columns (now Monitor rows linked by host_id).
- checks: monitors/{ping,dns,http}.py pure probes + runner.run_monitor
  dispatcher; one monitor_check scheduler with a per-monitor due-filter.
- status: single monitor_status_source replaces the three sources.
- UI: /monitors blueprint (type-aware add/edit/list/widget); host hub shows a
  host's linked monitors + "add monitor for this host"; nav + widget registry
  + alert metric catalog rewired. http plugin folded into core and removed.
- migration 0022 merges the http branch, data-migrates host facets +
  http_monitors + all three result histories, drops the old tables/columns.

Resolves the per-host ping/dns auto-attach issue (#275): monitors are now
explicit, never auto-added to every host.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016Jg27rgypiW2efULXJDtMC
2026-06-18 08:56:13 -04:00

86 lines
3.0 KiB
Python

"""Integration: unified Monitor schema + status source against live Postgres.
Validates the 0022 unification migration applied (monitors/monitor_results
exist, the old per-type tables are gone) and that monitor_status_source rolls
up MonitorResult history into a StatusEntry. Requires STEWARD_DATABASE_URL.
"""
from __future__ import annotations
import asyncio
import os
import uuid
from datetime import datetime, timezone, timedelta
import pytest
pytestmark = pytest.mark.integration
_NEEDS_DB = pytest.mark.skipif(
not os.environ.get("STEWARD_DATABASE_URL"),
reason="integration test needs a live Postgres (STEWARD_DATABASE_URL)",
)
@pytest.fixture
def app():
if not os.environ.get("STEWARD_DATABASE_URL"):
pytest.skip("needs Postgres")
from steward.app import create_app
return create_app(testing=False)
@_NEEDS_DB
def test_old_monitor_tables_dropped(app):
from sqlalchemy import text
async def _go():
async with app.db_sessionmaker() as s:
# New tables exist…
await s.execute(text("SELECT COUNT(*) FROM monitors"))
await s.execute(text("SELECT COUNT(*) FROM monitor_results"))
# …old ones are gone (regclass of a missing table is NULL).
for tbl in ("ping_results", "dns_results", "http_monitors", "http_results"):
missing = (await s.execute(
text("SELECT to_regclass(:t)"), {"t": tbl})).scalar()
assert missing is None, f"{tbl} should have been dropped"
asyncio.run(_go())
@_NEEDS_DB
def test_status_source_rolls_up_results(app):
from sqlalchemy import text
from steward.models.monitors import Monitor, MonitorResult
from steward.core.status import monitor_status_source
mid = str(uuid.uuid4())
now = datetime.now(timezone.utc)
async def _go():
async with app.db_sessionmaker() as s:
async with s.begin():
# Clean slate for a deterministic assertion.
await s.execute(text("DELETE FROM monitor_results"))
await s.execute(text("DELETE FROM monitors"))
s.add(Monitor(id=mid, name="custom-http", type="http",
target="https://example.test", host_id=None,
config_json="{}", enabled=True))
async with s.begin():
for i, up in enumerate([True, True, False, True]):
s.add(MonitorResult(
id=str(uuid.uuid4()), monitor_id=mid,
checked_at=now - timedelta(minutes=4 - i),
is_up=up, response_ms=10.0 if up else None,
))
entries = await monitor_status_source(s)
return entries
entries = asyncio.run(_go())
assert len(entries) == 1
e = entries[0]
assert e.kind == "http" and e.name == "custom-http"
assert e.target == "https://example.test"
assert e.status == "up" # latest result is up
assert len(e.heartbeat) == 4
assert e.uptime["24h"] == 75.0 # 3 of 4 up