feat(ui): host page leads with its alerts; old readings say how old (#5210)
CI / lint (push) Successful in 2s
CI / integration (push) Successful in 50s
CI / unit (push) Successful in 1m20s
CI / publish (push) Successful in 1m13s

#5210 "Problems first, with since-time, across every list" (milestone 477),
second batch.

- Host page: an "Alerts on this host" strip first (rules on its agent
  series, its containers or its monitors: alert_svc.watches_host); its
  monitors problems first with "Down 12m · reason"; Docker above Ansible.
- Uptime page and widget: worst 24h uptime first, then 7d and 30d; hosts
  with no uptime yet last.
- Agent panel and fleet widget: last seen as "3m ago", not a clock time.
- SNMP: a device is "Reachable" only while it answered within the last 3
  polls; older readings say "No answer" with their age, and every device
  says when it was last read (was: reachable whenever any reading existed).
- Traefik: a router missing from 3 scrapes in a row is listed apart as no
  longer reported, by when it was last seen, instead of keeping its last
  state (a removed router stayed Failing).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-07 00:02:20 -04:00
co-authored by Claude Opus 5.5
parent 5a14e7c693
commit 8e890c6914
15 changed files with 231 additions and 31 deletions
+31 -6
View File
@@ -13,10 +13,32 @@ from steward.models.metrics import PluginMetric
snmp_bp = Blueprint("snmp", __name__, template_folder="templates")
async def _latest_readings(db, device_names: list[str]) -> dict[str, dict[str, float]]:
"""Return {device_name: {label: latest_value}} for all configured devices."""
async def _latest_readings(db, device_names: list[str]) -> dict[str, dict]:
"""{device_name: {"readings": {label: latest_value}, "at": newest reading's
time}} for the devices that have any readings."""
latest = await latest_by_resource(db, "snmp", device_names)
return {name: {m: r.value for m, r in metrics.items()} for name, metrics in latest.items()}
return {name: {"readings": {m: r.value for m, r in metrics.items()},
"at": max(r.recorded_at for r in metrics.values())}
for name, metrics in latest.items() if metrics}
# A device whose newest reading is older than this many poll intervals is not
# shown as reachable: the poller has stopped getting answers from it.
STALE_POLLS = 3
def _device_state(entry: dict | None, poll_seconds: int, now: datetime) -> dict:
"""What the page says about a device's readings: {"readings", "at",
"reach"}, reach being "up" (answered within STALE_POLLS polls), "stale"
(has readings, but none recent) or "pending" (never answered)."""
if not entry:
return {"readings": {}, "at": None, "reach": "pending"}
fresh = (now - entry["at"]).total_seconds() <= STALE_POLLS * max(int(poll_seconds), 1)
return {**entry, "reach": "up" if fresh else "stale"}
def _poll_seconds() -> int:
return int(current_app.config["PLUGINS"]["snmp"].get("poll_interval_seconds", 60))
async def _history(db, device_name: str, hours: int = 24) -> dict[str, list]:
@@ -49,6 +71,7 @@ async def index():
async with current_app.db_sessionmaker() as db:
latest = await _latest_readings(db, device_names)
now = datetime.now(timezone.utc)
# Merge config + latest readings for the template
devices = []
@@ -58,7 +81,7 @@ async def index():
"name": name,
"host": cfg.get("host", ""),
"oids": cfg.get("oids", []),
"readings": latest.get(name, {}),
**_device_state(latest.get(name), _poll_seconds(), now),
})
poll_interval = current_app.config.get("MONITORS_POLL_INTERVAL", 60)
@@ -124,12 +147,13 @@ async def host_panel(host_id: str):
return ""
names = [d.get("name") or d.get("host", "?") for d in matched]
latest = await _latest_readings(db, names)
now = datetime.now(timezone.utc)
devices = [{
"name": d.get("name") or d.get("host", "?"),
"host": d.get("host", ""),
"oids": d.get("oids", []),
"readings": latest.get(d.get("name") or d.get("host", "?"), {}),
**_device_state(latest.get(d.get("name") or d.get("host", "?")), _poll_seconds(), now),
"bound": bool(str(d.get("host_id", "")).strip()
or str(d.get("steward_host", "")).strip()),
} for d in matched]
@@ -144,6 +168,7 @@ async def widget():
async with current_app.db_sessionmaker() as db:
latest = await _latest_readings(db, device_names[:10])
now = datetime.now(timezone.utc)
devices = []
for cfg in devices_cfg[:10]:
@@ -151,7 +176,7 @@ async def widget():
devices.append({
"name": name,
"oids": cfg.get("oids", []),
"readings": latest.get(name, {}),
**_device_state(latest.get(name), _poll_seconds(), now),
})
return await render_template("snmp/widget.html",