bvandeusen
af60ca446d
The fabledscryer->steward rename had only ever reached host_agent. The other five bundled plugins (http, snmp, traefik, unifi, docker) still imported `from fabledscryer.*` (package no longer exists) and read FABLEDSCRYER_* env vars — so every one of them was broken at import since the original rebrand. CI stayed green only because none are enabled by default and migrations don't import plugin modules. Now that they version in-tree, complete the rename: - fabledscryer.* -> steward.* imports across all five plugins - FABLEDSCRYER_* -> STEWARD_* in plugin migration env.py files - author/repository/homepage + user-facing 'Fabled Scryer' strings -> Steward - snmp/scheduler.py: also drop dead `now`/datetime; record_metric from steward Adds tests/test_no_legacy_names.py — fails if 'scryer'/'roundtable' ever reappear in shipped code (the drift bit twice; this stops a third time). Also clears pre-existing ruff lint debt (unused imports, semicolon statements, mid-file import) surfaced by the new lint lane. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
122 lines
4.2 KiB
Python
122 lines
4.2 KiB
Python
# plugins/http/scheduler.py
|
|
from __future__ import annotations
|
|
import asyncio
|
|
import json
|
|
import logging
|
|
from datetime import datetime, timezone
|
|
|
|
from steward.core.scheduler import ScheduledTask
|
|
from steward.core.alerts import record_metric
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def make_task(app) -> ScheduledTask:
|
|
interval = int(
|
|
app.config["PLUGINS"]["http"].get("check_interval_seconds", 60)
|
|
)
|
|
|
|
async def check():
|
|
await _do_checks(app)
|
|
|
|
return ScheduledTask(
|
|
name="http_check",
|
|
coro_factory=check,
|
|
interval_seconds=interval,
|
|
run_on_startup=True,
|
|
)
|
|
|
|
|
|
async def _do_checks(app) -> None:
|
|
from sqlalchemy import select
|
|
from .models import HttpMonitor, HttpResult
|
|
from .checker import run_check
|
|
|
|
cfg = app.config["PLUGINS"]["http"]
|
|
global_interval = int(cfg.get("check_interval_seconds", 60))
|
|
global_timeout = int(cfg.get("default_timeout_seconds", 10))
|
|
global_follow = bool(cfg.get("follow_redirects", True))
|
|
global_verify = bool(cfg.get("verify_ssl", True))
|
|
|
|
now = datetime.now(timezone.utc)
|
|
|
|
async with app.db_sessionmaker() as session:
|
|
result = await session.execute(
|
|
select(HttpMonitor).where(HttpMonitor.enabled == True) # noqa: E712
|
|
)
|
|
monitors = list(result.scalars())
|
|
|
|
# Filter to monitors whose next check time has passed
|
|
due: list[HttpMonitor] = []
|
|
for m in monitors:
|
|
effective_interval = m.check_interval_seconds or global_interval
|
|
if m.last_checked_at is None:
|
|
due.append(m)
|
|
elif (now - m.last_checked_at).total_seconds() >= effective_interval:
|
|
due.append(m)
|
|
|
|
if not due:
|
|
return
|
|
|
|
async def _check_one(monitor: HttpMonitor) -> tuple[HttpMonitor, dict]:
|
|
try:
|
|
headers = json.loads(monitor.headers_json or "{}")
|
|
except (ValueError, TypeError):
|
|
headers = {}
|
|
result = await run_check(
|
|
url=monitor.url,
|
|
method=monitor.method,
|
|
expected_status=monitor.expected_status,
|
|
content_match=monitor.content_match,
|
|
headers=headers,
|
|
timeout_seconds=monitor.timeout_seconds or global_timeout,
|
|
follow_redirects=monitor.follow_redirects if monitor.follow_redirects is not None else global_follow,
|
|
verify_ssl=monitor.verify_ssl if monitor.verify_ssl is not None else global_verify,
|
|
)
|
|
return monitor, result
|
|
|
|
pairs = await asyncio.gather(*[_check_one(m) for m in due], return_exceptions=True)
|
|
|
|
check_time = datetime.now(timezone.utc)
|
|
|
|
async with app.db_sessionmaker() as session:
|
|
async with session.begin():
|
|
for item in pairs:
|
|
if isinstance(item, Exception):
|
|
logger.error("HTTP check task error: %s", item)
|
|
continue
|
|
monitor, res = item
|
|
|
|
session.add(HttpResult(
|
|
monitor_id=monitor.id,
|
|
checked_at=check_time,
|
|
status_code=res["status_code"],
|
|
response_ms=res["response_ms"],
|
|
is_up=res["is_up"],
|
|
content_matched=res["content_matched"],
|
|
error_msg=res["error_msg"],
|
|
tls_expires_at=res["tls_expires_at"],
|
|
))
|
|
|
|
# Update monitor's last_checked_at for next-run scheduling
|
|
db_monitor = await session.get(HttpMonitor, monitor.id)
|
|
if db_monitor:
|
|
db_monitor.last_checked_at = check_time
|
|
|
|
# Alert pipeline
|
|
if res["response_ms"] is not None:
|
|
await record_metric(
|
|
session=session,
|
|
source_module="http",
|
|
resource_name=monitor.name,
|
|
metric_name="response_ms",
|
|
value=res["response_ms"],
|
|
)
|
|
await record_metric(
|
|
session=session,
|
|
source_module="http",
|
|
resource_name=monitor.name,
|
|
metric_name="is_up",
|
|
value=1.0 if res["is_up"] else 0.0,
|
|
)
|