Files
FabledSteward/steward/monitors/service.py
T
bvandeusenandClaude Opus 5.5 312ea95bcf
CI / lint (push) Successful in 2s
CI / integration (push) Successful in 35s
CI / unit (push) Successful in 59s
CI / publish (push) Successful in 56s
refactor: move host, docker, alert and monitor queries into service modules
MCP-3 of milestone 461 "MCP server: Steward as an LLM-inspectable,
LLM-operable hub". The /mcp tools run outside Quart's request pipeline, so
the queries they share with the pages now live in plain functions that take
an open session:

- steward/hosts/service.py: uptime, status, monitors, agent metrics,
  agent overview (stale threshold passed in, not read from current_app),
  CPU sparks.
- plugins/docker/service.py: bucket, container_history, host_map,
  list_containers, container_events, query_logs.
- steward/alerts/service.py: active_alerts (also used by core/reports),
  list_rules, list_maintenance_windows.
- steward/monitors/service.py: monitor_rows (was routes._rows_data).

Routes are repointed and render the same data. One behavior fix rides
along: the container-log search now escapes % and _ so they match
literally instead of acting as LIKE wildcards.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 07:29:21 -04:00

53 lines
2.1 KiB
Python

"""Monitor queries shared by the monitors pages and the MCP tools.
Each function takes an open session, with no Quart request context, so the
routes and the /mcp tools (which run outside Quart's pipeline) call the same
code.
"""
from __future__ import annotations
from datetime import datetime, timezone
from sqlalchemy import select
from steward.core.status import _heartbeat_title, _last_n_results, _uptime_by_monitor
from steward.core.time_range import parse_range
from steward.models.monitors import Monitor
async def monitor_rows(db, range_key: str):
"""Per-monitor state: latest result, heartbeat strip, uptime and TLS days.
Returns (rows, up, down, pending, range_key). `range_key` picks the uptime
window surfaced (24h/7d/30d; anything else falls back to 24h) and comes
back normalised.
"""
_since, range_key = parse_range(range_key)
monitors = list((await db.execute(select(Monitor).order_by(Monitor.name))).scalars())
ids = [m.id for m in monitors]
recent = await _last_n_results(db, ids)
uptime = await _uptime_by_monitor(db, ids)
# Map the selected range to the uptime bucket we surface in the list.
bucket = {"24h": "24h", "7d": "7d", "30d": "30d"}.get(range_key, "24h")
now = datetime.now(timezone.utc)
data = []
for m in monitors:
rows = recent.get(m.id, [])
latest = rows[-1] if rows else None
tls_days = None
if latest and latest.tls_expires_at:
tls_days = (latest.tls_expires_at - now).total_seconds() / 86400.0
data.append({
"monitor": m,
"latest": latest,
"heartbeat": [{"state": "up" if r.is_up else "down",
"title": _heartbeat_title(m.type, r)} for r in rows],
"uptime_pct": uptime.get(m.id, {}).get(bucket),
"tls_days": tls_days,
})
up = sum(1 for d in data if d["latest"] and d["latest"].is_up)
down = sum(1 for d in data if d["latest"] and not d["latest"].is_up)
pending = sum(1 for d in data if not d["latest"])
return data, up, down, pending, range_key