Files
FabledSteward/steward/monitors/http.py
T
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

101 lines
3.2 KiB
Python

"""HTTP(S) check — one synthetic request, returns a normalised result dict.
Moved into core from the former http plugin (plugins/http/checker.py) when
ping/dns/http were unified under the Monitor entity.
"""
from __future__ import annotations
import asyncio
import logging
import ssl
import time
from datetime import datetime, timezone
from urllib.parse import urlparse
import httpx
logger = logging.getLogger(__name__)
async def _get_tls_expiry(hostname: str, port: int) -> datetime | None:
"""Bare TLS handshake to read the certificate's notAfter date."""
ctx = ssl.create_default_context()
try:
reader, writer = await asyncio.wait_for(
asyncio.open_connection(hostname, port, ssl=ctx),
timeout=5.0,
)
cert = writer.get_extra_info("ssl_object").getpeercert()
writer.close()
try:
await writer.wait_closed()
except Exception:
pass
exp_str = cert.get("notAfter", "")
if not exp_str:
return None
# Format: "Mar 22 12:00:00 2027 GMT"
return datetime.strptime(exp_str, "%b %d %H:%M:%S %Y %Z").replace(
tzinfo=timezone.utc
)
except Exception as exc:
logger.debug("TLS check failed for %s:%d%s", hostname, port, exc)
return None
async def http_check(
url: str,
method: str = "GET",
expected_status: int = 200,
content_match: str = "",
headers: dict | None = None,
timeout_seconds: int = 10,
follow_redirects: bool = True,
verify_ssl: bool = True,
) -> dict:
"""Perform one HTTP check. Returns the MonitorResult field dict."""
result: dict = {
"is_up": False,
"status_code": None,
"response_ms": None,
"content_matched": None,
"error_msg": None,
"tls_expires_at": None,
}
parsed = urlparse(url)
is_https = parsed.scheme.lower() == "https"
t0 = time.monotonic()
try:
async with httpx.AsyncClient(
follow_redirects=follow_redirects,
verify=verify_ssl,
timeout=timeout_seconds,
) as client:
response = await client.request(method, url, headers=headers or {})
result["response_ms"] = round((time.monotonic() - t0) * 1000, 1)
result["status_code"] = response.status_code
status_ok = response.status_code == expected_status
if content_match:
matched = content_match in response.text
result["content_matched"] = matched
result["is_up"] = status_ok and matched
else:
result["is_up"] = status_ok
except httpx.TimeoutException:
result["response_ms"] = round((time.monotonic() - t0) * 1000, 1)
result["error_msg"] = "Timeout"
except httpx.ConnectError as exc:
result["error_msg"] = f"Connection error: {exc}"
except Exception as exc:
result["error_msg"] = str(exc)[:512]
# TLS expiry — only for HTTPS once we have any response.
if is_https and result["status_code"] is not None and parsed.hostname:
port = parsed.port or 443
result["tls_expires_at"] = await _get_tls_expiry(parsed.hostname, port)
return result