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
+2 -2
View File
@@ -4,9 +4,9 @@
<div style="display:flex;align-items:baseline;justify-content:space-between;margin-bottom:0.75rem;gap:1rem;flex-wrap:wrap;">
<h3 class="section-title" style="margin-bottom:0;">Agent</h3>
{% if reporting %}
<span style="font-size:0.78rem;color:{{ 'var(--yellow)' if stale else 'var(--green)' }};">
<span style="font-size:0.78rem;" class="tone-{{ 'warn' if stale else 'ok' }}">
{{ 'stale' if stale else 'reporting' }}{% if reg.agent_version %} · v{{ reg.agent_version }}{% endif %}
· last seen {{ reg.last_seen_at.strftime('%Y-%m-%d %H:%M') }}
· last seen {{ reg.last_seen_at|ago }}
</span>
{% elif reg %}
<span style="font-size:0.78rem;color:var(--text-muted);">pending — no check-in yet</span>
@@ -39,7 +39,7 @@
<span style="font-weight:500;font-size:0.85rem;overflow-wrap:anywhere;">{{ r.host.name }}</span>
{% endif %}
<span style="display:block;font-size:0.7rem;color:var(--text-dim);">
{{ r.reg.last_seen_at.strftime("%H:%M:%S") if r.reg.last_seen_at else "never" }}
{% if r.reg.last_seen_at %}seen {{ r.reg.last_seen_at|ago }}{% else %}never seen{% endif %}
</span>
</span>
</div>
+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",
+4 -2
View File
@@ -15,8 +15,10 @@
<span title="Explicitly bound to this host (host_id / steward_host)"
style="font-size:0.68rem;color:var(--text-muted);background:var(--bg-elevated);border:1px solid var(--border);border-radius:3px;padding:0.05rem 0.4rem;">bound</span>
{% endif %}
{% if device.readings %}
<span style="font-size:0.74rem;color:var(--green);">&#9679; reachable</span>
{% if device.reach == 'up' %}
<span style="font-size:0.74rem;" class="tone-ok">&#9679; reachable · read {{ device.at|ago }}</span>
{% elif device.reach == 'stale' %}
<span style="font-size:0.74rem;" class="tone-warn" title="The values below are from then">&#9679; no answer since {{ device.at|ago }}</span>
{% else %}
<span style="font-size:0.74rem;color:var(--text-dim);">&#9675; no data yet</span>
{% endif %}
+6 -1
View File
@@ -12,9 +12,14 @@
{% for device in devices %}
<section class="card" aria-labelledby="snmp-{{ loop.index }}">
<div class="host-health-head">
{{ status_badge('up', 'Reachable') if device.readings else status_badge('pending', 'No data yet') }}
{#- reach: answered within the last few polls (up), only long ago (stale),
or never (pending); routes._device_state. #}
{% if device.reach == 'up' %}{{ status_badge('up', 'Reachable') }}
{% elif device.reach == 'stale' %}{{ status_badge('stale', 'No answer', title="The last reading is from " ~ device.at.strftime('%Y-%m-%d %H:%M UTC') ~ "; the values below are from then") }}
{% else %}{{ status_badge('pending', 'No data yet') }}{% endif %}
<h2 id="snmp-{{ loop.index }}" class="section-title" style="margin:0;">{{ device.name }}</h2>
<span class="field-hint mono">{{ device.host }}</span>
{% if device.at %}<span class="field-hint">read {{ device.at|ago }}</span>{% endif %}
<a href="/plugins/snmp/device/{{ device.name }}" class="btn btn-sm btn-ghost" style="margin-left:auto;">History</a>
</div>
+4 -2
View File
@@ -6,8 +6,10 @@
<span style="font-size:0.82rem;font-weight:500;flex:1;min-width:0;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;">
{{ device.name }}
</span>
{% if device.readings %}
<span style="font-size:0.7rem;color:var(--green);">&#9679;</span>
{% if device.reach == 'up' %}
<span style="font-size:0.7rem;" class="tone-ok" title="Reachable · read {{ device.at.strftime('%H:%M UTC') }}">&#9679;</span>
{% elif device.reach == 'stale' %}
<span style="font-size:0.7rem;" class="tone-warn">no answer since {{ device.at|ago }}</span>
{% else %}
<span style="font-size:0.7rem;color:var(--text-dim);">&#9675;</span>
{% endif %}
+23 -2
View File
@@ -1,7 +1,7 @@
# plugins/traefik/routes.py
from __future__ import annotations
from collections import defaultdict
from datetime import datetime, timezone
from datetime import datetime, timedelta, timezone
from quart import Blueprint, current_app, render_template, request
from sqlalchemy import Integer, cast, func, select
import json
@@ -58,6 +58,24 @@ def router_state(latest, thresholds: dict) -> tuple[str, str | None]:
return "ok", None
# A router missing from this many scrapes in a row is no longer reported:
# Traefik dropped it (a removed service), so its last state is history.
GONE_AFTER_SCRAPES = 3
def gone_routers(routers: list[dict], scrape_seconds: int) -> tuple[list[dict], list[dict]]:
"""(current, gone): a router whose newest row trails the newest scrape of
any router by GONE_AFTER_SCRAPES intervals is gone, newest-seen first."""
if not routers:
return [], []
newest = max(r["latest"].scraped_at for r in routers)
cutoff = newest - timedelta(seconds=GONE_AFTER_SCRAPES * max(int(scrape_seconds), 1))
current = [r for r in routers if r["latest"].scraped_at >= cutoff]
gone = sorted((r for r in routers if r["latest"].scraped_at < cutoff),
key=lambda r: r["latest"].scraped_at, reverse=True)
return current, gone
def split_routers(routers: list[dict]) -> tuple[list[dict], list[dict]]:
"""(problems, healthy): failing routers before slow or noisy ones, each
group by name; healthy routers by name."""
@@ -171,11 +189,14 @@ async def rows():
"days_remaining": days,
})
problems, healthy = split_routers(router_data)
current, gone = gone_routers(
router_data, current_app.config["PLUGINS"]["traefik"]["scrape_interval_seconds"])
problems, healthy = split_routers(current)
return await render_template(
"traefik/rows.html",
problems=problems,
healthy=healthy,
gone=gone,
error_4xx=ERROR_4XX_PCT,
error_5xx=ERROR_5XX_PCT,
global_stat=global_stat,
+17 -1
View File
@@ -37,7 +37,7 @@
</div>
{% endmacro %}
{% if problems or healthy or certs %}
{% if problems or healthy or gone or certs %}
{# ── Routers that need attention ─────────────────────────────────────────── #}
{% if problems %}
<div style="column-width:340px;column-gap:1rem;">
@@ -67,6 +67,22 @@
</table>
</div>
</details>
{% endif %}
{# ── Routers Traefik no longer reports: their last numbers are history, not a
state, so they are listed by when they were last seen and nothing else. ── #}
{% if gone %}
<details class="card" style="margin-bottom:1rem;">
<summary class="section-title" style="cursor:pointer;">{{ gone|length }} router{{ 's' if gone|length != 1 }} no longer reported</summary>
<p class="field-hint" style="margin:0.5rem 0;">Traefik stopped reporting these, usually because the service behind them was removed.</p>
<ul class="problem-list">
{% for r in gone %}
<li><span style="word-break:break-all;">{{ r.name }}</span> <span class="problem-detail">last seen {{ r.latest.scraped_at|ago }}</span></li>
{% endfor %}
</ul>
</details>
{% endif %}
{% if healthy %}
<script>
// The fragment is re-polled; keep the healthy list as the reader left it.
(function () {