refactor web pagination and add partitioned events, flap/timeout showcase agents

This commit is contained in:
Stanislav Rossovskii
2026-05-27 18:23:31 +04:00
parent d5f312f200
commit a2e88b4e76
46 changed files with 1600 additions and 742 deletions

View File

@@ -5,7 +5,7 @@ import pytest
from sqlalchemy import func, select, update
from sqlalchemy.ext.asyncio import async_sessionmaker
from monlet_server.models import Agent, Event, Incident, NotificationOutbox
from monlet_server.models import Agent, Check, Event, Incident, NotificationOutbox
from monlet_server.services.detector import LIVENESS_CHECK_ID, _tick
from monlet_server.settings import reset_settings_cache
@@ -82,22 +82,75 @@ async def test_detector_transitions(app_client, auth_headers, engine, session):
@pytest.mark.asyncio
async def test_detector_prunes_bounded_history(
app_client, auth_headers, engine, session, monkeypatch
):
monkeypatch.setenv("MONLET_EVENTS_RETENTION_MAX_ROWS", "2")
async def test_detector_owns_liveness_check_and_events(app_client, auth_headers, engine, session):
await app_client.post(
"/api/v1/heartbeat", json=make_heartbeat("agent-flap"), headers=auth_headers
)
sm = async_sessionmaker(engine, expire_on_commit=False)
# Tick 1: alive → Check exists with status=ok, one event.
await _tick(sm)
session.expire_all()
check = (
await session.execute(
select(Check).where(Check.agent_id == "agent-flap", Check.check_id == LIVENESS_CHECK_ID)
)
).scalar_one()
assert check.status == "ok"
n_events = (
await session.execute(
select(func.count())
.select_from(Event)
.where(Event.agent_id == "agent-flap", Event.check_id == LIVENESS_CHECK_ID)
)
).scalar_one()
assert n_events == 1
# Tick 2: still alive → no new event.
await _tick(sm)
session.expire_all()
n_events = (
await session.execute(
select(func.count())
.select_from(Event)
.where(Event.agent_id == "agent-flap", Event.check_id == LIVENESS_CHECK_ID)
)
).scalar_one()
assert n_events == 1
# Push agent into dead → transition event written, Check updates.
await session.execute(
update(Agent)
.where(Agent.agent_id == "agent-flap")
.values(last_seen_at=datetime.now(UTC) - timedelta(minutes=10))
)
await session.commit()
await _tick(sm)
session.expire_all()
check = (
await session.execute(
select(Check).where(Check.agent_id == "agent-flap", Check.check_id == LIVENESS_CHECK_ID)
)
).scalar_one()
assert check.status == "critical"
n_events = (
await session.execute(
select(func.count())
.select_from(Event)
.where(Event.agent_id == "agent-flap", Event.check_id == LIVENESS_CHECK_ID)
)
).scalar_one()
assert n_events == 2
@pytest.mark.asyncio
async def test_detector_prunes_outbox(app_client, auth_headers, engine, session, monkeypatch):
monkeypatch.setenv("MONLET_OUTBOX_RETENTION_MAX_ROWS", "2")
reset_settings_cache()
try:
await app_client.post(
"/api/v1/heartbeat", json=make_heartbeat("agent-prune"), headers=auth_headers
)
events = [make_event(check_id="prune_check") for _ in range(5)]
await app_client.post(
"/api/v1/events",
json={"agent_id": "agent-prune", "events": events},
headers=auth_headers,
)
critical = make_event(check_id="critical_prune", status="critical", exit_code=2)
await app_client.post(
"/api/v1/events",
@@ -129,7 +182,6 @@ async def test_detector_prunes_bounded_history(
sm = async_sessionmaker(engine, expire_on_commit=False)
await _tick(sm)
assert (await session.execute(select(func.count()).select_from(Event))).scalar_one() == 2
terminal_outbox = (
await session.execute(
select(func.count())