bvandeusenandClaude Opus 5.5
5569f9934e
#5740 "A metric that departs from its normal is recorded as an anomaly to review, and is findable after it ends", milestone 513. - Every minute each learned key's last 15 minutes is judged against its hour's normal: above the usual hold x1.25 and by the metric's floor opens an occurrence, which ends when the level comes back. - metric_anomalies holds one row per item to review; a repeat while it still waits joins it as an occurrence (metric_anomaly_spans). - An ended row nobody reviews within anomalies.review_days (14, Settings -> Thresholds) lapses; an ongoing one never does. - Learning skips every hour an occurrence covers unless its anomaly was marked normal: no normal is learned without review. - Alerts -> Anomalies lists those to review first, then the reviewed and lapsed under day dividers; marking is operator/admin and audited. - The Overview widget and get_overview warn of open ones and count those to review; the host page shows its own; the weekly report lists the week's and the lapsed; MCP list_anomalies and review_anomaly. - Reviewed and lapsed rows are pruned at data.retention_days, and kept in backups like alert history. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
57 lines
2.3 KiB
Python
57 lines
2.3 KiB
Python
from __future__ import annotations
|
|
from quart import Blueprint, current_app, render_template, request
|
|
from sqlalchemy import func, select
|
|
|
|
from steward.alerts.service import active_alerts, alert_label
|
|
from steward.auth.middleware import require_role
|
|
from steward.core import anomalies as anom
|
|
from steward.core.status import collect_status
|
|
from steward.models.hosts import Host
|
|
from steward.models.users import UserRole
|
|
|
|
status_bp = Blueprint("status", __name__, url_prefix="/status")
|
|
|
|
|
|
def _summarize(entries) -> tuple[int, int, int]:
|
|
up = sum(1 for e in entries if e.status == "up")
|
|
down = sum(1 for e in entries if e.status == "down")
|
|
pending = sum(1 for e in entries if e.status == "pending")
|
|
return up, down, pending
|
|
|
|
|
|
@status_bp.get("/widget")
|
|
@require_role(UserRole.viewer)
|
|
async def widget():
|
|
"""HTMX dashboard 'Overview' widget — the single at-a-glance summary that
|
|
replaced the old fixed top strip: host count + monitor up/down/pending +
|
|
problem list + an alerts link."""
|
|
async with current_app.db_sessionmaker() as db:
|
|
entries = await collect_status(db)
|
|
total_hosts = (await db.execute(
|
|
select(func.count()).select_from(Host))).scalar()
|
|
alerts = await active_alerts(db)
|
|
# Metric anomalies going on now are warnings; the ones waiting for a
|
|
# review are one line linking to the list (#5740).
|
|
anomalies = await anom.views(db, await anom.open_anomalies(db))
|
|
to_review = await anom.to_review_count(db)
|
|
up, down, pending = _summarize(entries)
|
|
return await render_template(
|
|
"status/widget.html",
|
|
entries=entries, up=up, down=down, pending=pending,
|
|
total_hosts=total_hosts, alerts=overview_alerts(alerts),
|
|
anomalies=anomalies, to_review=to_review,
|
|
widget_id=request.args.get("wid", "0"),
|
|
)
|
|
|
|
|
|
def overview_alerts(alerts) -> list[dict]:
|
|
"""The Overview's alert lines: breaching or silent first, then those
|
|
someone has taken; each {rule, label, since}."""
|
|
order = {"firing": 0, "no_data": 1, "pending": 2, "acknowledged": 3}
|
|
rows = []
|
|
for state, rule in alerts:
|
|
label = alert_label(state)
|
|
since = state.no_data_since if label == "no_data" else state.last_transition_at
|
|
rows.append({"rule": rule, "label": label, "since": since})
|
|
return sorted(rows, key=lambda r: order.get(r["label"], 9))
|