feat(plugins): Traefik problems first, UniFi/SNMP/fleet on shared shapes, audit names its entities, templates on tokens (#5126)
CI / lint (push) Successful in 2s
CI / integration (push) Successful in 1m5s
CI / unit (push) Successful in 1m19s
CI / publish (push) Successful in 57s

Traefik: routers are graded from their latest scrape (router_state: crit on
any real 5xx share, warn on p95 past the latency critical cutoff or a high
4xx share). Failing and slow routers lead as cards that say why; healthy
ones fold into one table that stays open or shut across polls. Proxy
counts are stat tiles; certificates are graded by Settings -> Thresholds
(tls_days).

UniFi: WAN health is a stat strip (latency graded by the thresholds),
devices carry status dots, event categories and firewall actions are
badges, the alarm count reuses .count-badge (renamed from .nav-count).
SNMP: each device wears a status badge and its readings are stat tiles.

Agent fleet: the table comes first, with a Status column (Reporting /
Silent / Never reported, by the host page's stale_after_seconds), silent
agents first, hosts linked, last seen as |ago.

Audit: entries name their entity (one query per type, steward/audit/
service.py) and link it; something deleted since keeps the name its entry
recorded and says "(deleted)".

Tokens: charts read colours through chart-colors.js (stewardColor resolves
a token to the rgb the browser computed; Chart.js defaults take the page's
text and border colours), so host, history, Traefik and SNMP charts drop
their hex. Template hex colours reach 0 (HEX_CEILING = 0), the last rgba
pills go, and heavy weights (600/700/bold, 60 of them) become 500, the
house pair being 400/500; a guard keeps templates there.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-06 18:25:09 -04:00
co-authored by Claude Opus 5.5
parent c2a79c8bb0
commit 414c942cbf
60 changed files with 686 additions and 391 deletions
+24 -3
View File
@@ -359,6 +359,28 @@ async def agent_source():
return Response(body, mimetype="text/x-python")
_FLEET_ORDER = {"stale": 0, "pending": 1, "up": 2}
def fleet_state(reg, now: datetime, stale_after: int) -> str:
"""An agent as the fleet table shows it: "up" while it reports, "stale"
once its last report is older than stale_after, "pending" if it never has."""
if reg.last_seen_at is None:
return "pending"
return "stale" if (now - reg.last_seen_at).total_seconds() > stale_after else "up"
def fleet_rows(regs, hosts_by_id: dict, now: datetime, stale_after: int) -> list[dict]:
"""The fleet table: silent agents first, then never-reported, then live,
each by host name."""
rows = []
for r in regs:
host = hosts_by_id.get(r.host_id)
rows.append({"reg": r, "host": host, "name": host.name if host else r.host_id,
"state": fleet_state(r, now, stale_after)})
return sorted(rows, key=lambda x: (_FLEET_ORDER[x["state"]], x["name"].lower()))
def _stale_after_seconds() -> int:
return int(
current_app.config.get("PLUGINS", {})
@@ -803,11 +825,10 @@ async def fleet():
managed_key_set = bool(
(current_app.config.get("ANSIBLE", {}).get("ssh_public_key") or "").strip())
now, stale_after = datetime.now(timezone.utc), _stale_after_seconds()
return await render_template(
"settings_list.html",
registrations=[
{"reg": r, "host": hosts_by_id.get(r.host_id)} for r in regs
],
registrations=fleet_rows(regs, hosts_by_id, now, stale_after),
new_token=new_token,
install_url=install_url,
ansible_available=ansible_available,
+13 -13
View File
@@ -54,30 +54,30 @@
interaction: { mode: "index", intersect: false },
elements: { point: { radius: 0 } },
scales: {
x: { type: "linear", ticks: { callback: (v) => fmtTime(v), maxTicksLimit: 8, color: "#8a8a92", font: { size: 10 } }, grid: { color: "#30303a" } },
y: { beginAtZero: true, max: ymax, ticks: { color: "#8a8a92", font: { size: 10 } }, grid: { color: "#30303a" } },
x: { type: "linear", ticks: { callback: (v) => fmtTime(v), maxTicksLimit: 8, font: { size: 10 } } },
y: { beginAtZero: true, max: ymax, ticks: { font: { size: 10 } } },
},
plugins: {
legend: { labels: { color: "#b8b8b0", boxWidth: 10, font: { size: 11 } } },
legend: { labels: { boxWidth: 10, font: { size: 11 } } },
tooltip: { callbacks: { title: (items) => items.length ? fmtTime(items[0].parsed.x) : "" } },
},
});
const defs = {
"chart-util": { ymax: 100, ds: [
{ key: "cpu_pct", label: "CPU %", color: "#c8a840" },
{ key: "mem_used_pct", label: "Mem %", color: "#4aa86a" },
{ key: "disk_used_pct_worst", label: "Disk % (worst)", color: "#c87840" },
{ key: "cpu_pct", label: "CPU %", color: stewardColor("--gold") },
{ key: "mem_used_pct", label: "Mem %", color: stewardColor("--green") },
{ key: "disk_used_pct_worst", label: "Disk % (worst)", color: stewardColor("--yellow") },
] },
"chart-net": { ymax: undefined, ds: [
{ key: "net_rx_bps", label: "Net RX", color: "#4aa86a" },
{ key: "net_tx_bps", label: "Net TX", color: "#c84048" },
{ key: "disk_read_bps", label: "Disk read", color: "#6aa0d0" },
{ key: "disk_write_bps", label: "Disk write", color: "#c8a840" },
{ key: "net_rx_bps", label: "Net RX", color: stewardColor("--green") },
{ key: "net_tx_bps", label: "Net TX", color: stewardColor("--red") },
{ key: "disk_read_bps", label: "Disk read", color: stewardColor("--blue") },
{ key: "disk_write_bps", label: "Disk write", color: stewardColor("--gold") },
] },
"chart-pressure": { ymax: undefined, ds: [
{ key: "load_1m", label: "Load 1m", color: "#c8a840" },
{ key: "psi_mem_some_avg10", label: "Mem PSI %", color: "#c84048" },
{ key: "temp_c_max", label: "Temp °C", color: "#c87840" },
{ key: "load_1m", label: "Load 1m", color: stewardColor("--gold") },
{ key: "psi_mem_some_avg10", label: "Mem PSI %", color: stewardColor("--red") },
{ key: "temp_c_max", label: "Temp °C", color: stewardColor("--yellow") },
] },
};
const charts = {};
+40 -36
View File
@@ -1,5 +1,5 @@
{% extends "base.html" %}
{% from "_macros.html" import crumbs %}
{% from "_macros.html" import crumbs, status_badge %}
{% block title %}Agent fleet — Steward{% endblock %}
{% block breadcrumb %}{{ crumbs([("Hosts", "/hosts/"), ("Agent fleet", "")]) }}{% endblock %}
{% block content %}
@@ -21,6 +21,45 @@
</div>
{% endif %}
<div class="card-flush" style="margin-bottom:1.5rem;">
<div class="table-wrap">
<table class="table">
<thead>
<tr>
<th>Status</th><th>Host</th><th>Last seen</th><th>Agent version</th><th>Reported IP</th><th>Distro</th>
<th class="td-actions">Actions</th>
</tr>
</thead>
<tbody>
{% for item in registrations %}
<tr>
<td>{{ status_badge(item.state, {'up': 'Reporting', 'stale': 'Silent', 'pending': 'Never reported'}[item.state]) }}</td>
<td>{% if item.host %}<a href="/hosts/{{ item.host.id }}">{{ item.host.name }}</a>{% else %}<span class="mono">{{ item.reg.host_id }}</span>{% endif %}</td>
<td>{% if item.reg.last_seen_at %}<span title="{{ item.reg.last_seen_at.strftime('%Y-%m-%d %H:%M:%S UTC') }}">{{ item.reg.last_seen_at|ago }}</span>{% else %}never{% endif %}</td>
<td>{{ item.reg.agent_version or "—" }}</td>
<td class="mono">{{ item.reg.host_ip or "—" }}</td>
<td>{{ item.reg.distro or "—" }}</td>
<td class="td-actions">
<form method="post" action="/plugins/host_agent/fleet/{{ item.reg.host_id }}/rotate-token"
style="display:inline;"
data-confirm="Rotate the token for {{ item.name }}? The existing agent will stop working until reinstalled with the new token.">{{ csrf_field() }}
<button type="submit" class="btn btn-ghost btn-sm">Rotate token</button>
</form>
<form method="post" action="/plugins/host_agent/fleet/{{ item.reg.host_id }}/delete"
style="display:inline;"
data-confirm="Delete the agent registration for {{ item.name }}? The agent will be unable to report metrics until re-registered.">{{ csrf_field() }}
<button type="submit" class="btn btn-danger btn-sm">Delete</button>
</form>
</td>
</tr>
{% else %}
<tr><td colspan="7" class="empty">No hosts registered. Add one below.</td></tr>
{% endfor %}
</tbody>
</table>
</div>
</div>
<div class="card">
<form method="post" action="/plugins/host_agent/fleet/add-host"
style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">{{ csrf_field() }}
@@ -137,39 +176,4 @@
{% endif %}
{% endif %}
<div class="card-flush">
<table class="table">
<thead>
<tr>
<th>Host</th><th>Reported IP</th><th>Agent version</th><th>Distro</th>
<th>Last seen</th><th class="td-actions">Actions</th>
</tr>
</thead>
<tbody>
{% for item in registrations %}
<tr>
<td>{{ item.host.name if item.host else item.reg.host_id }}</td>
<td>{{ item.reg.host_ip or "—" }}</td>
<td>{{ item.reg.agent_version or "—" }}</td>
<td>{{ item.reg.distro or "—" }}</td>
<td>{{ item.reg.last_seen_at.strftime("%Y-%m-%d %H:%M:%S") if item.reg.last_seen_at else "never" }}</td>
<td class="td-actions">
<form method="post" action="/plugins/host_agent/fleet/{{ item.reg.host_id }}/rotate-token"
style="display:inline;"
data-confirm="Rotate the token for this host? The existing agent will stop working until reinstalled with the new token.">{{ csrf_field() }}
<button type="submit" class="btn btn-ghost btn-sm">Rotate token</button>
</form>
<form method="post" action="/plugins/host_agent/fleet/{{ item.reg.host_id }}/delete"
style="display:inline;"
data-confirm="Delete this host registration? The agent will be unable to report metrics until re-registered.">{{ csrf_field() }}
<button type="submit" class="btn btn-danger btn-sm">Delete</button>
</form>
</td>
</tr>
{% else %}
<tr><td colspan="6" class="empty">No hosts registered. Add one above.</td></tr>
{% endfor %}
</tbody>
</table>
</div>
{% endblock %}
@@ -16,16 +16,14 @@
toggle that re-requests this widget without entering edit mode. #}
<div style="flex:0 0 auto;display:flex;align-items:center;gap:0.5rem;flex-wrap:wrap;font-size:0.75rem;color:var(--text-muted);margin-bottom:0.3rem;">
{% if session.user_id %}
<a href="/hosts/{{ host.id }}" style="font-weight:600;">{{ host.name }}</a>
<a href="/hosts/{{ host.id }}" style="font-weight:500;">{{ host.name }}</a>
{% else %}
<strong style="color:var(--text);">{{ host.name }}</strong>
{% endif %}
<span class="hist-range" style="margin-left:auto;display:inline-flex;border:1px solid var(--border-mid);border-radius:5px;overflow:hidden;">
<span class="hist-range" style="margin-left:auto;display:inline-flex;gap:0.25rem;">
{% for opt in [1, 6, 24] %}
<button type="button" onclick="histRange({{ wid|int }}, {{ opt|int }})"
style="border:0;cursor:pointer;padding:0.1rem 0.45rem;font-size:0.72rem;
background:{% if opt == hours %}var(--accent){% else %}transparent{% endif %};
color:{% if opt == hours %}#fff{% else %}var(--text-muted){% endif %};">{{ opt }}h</button>
class="range-btn{% if opt == hours %} active{% endif %}">{{ opt }}h</button>
{% endfor %}
</span>
</div>
@@ -57,9 +55,9 @@ window.histRange = function (wid, hours) {
return ("0" + d.getHours()).slice(-2) + ":" + ("0" + d.getMinutes()).slice(-2);
};
var ds = [
{ key: "cpu_pct", label: "CPU %", color: "#c8a840" },
{ key: "mem_used_pct", label: "Mem %", color: "#4aa86a" },
{ key: "disk_root", label: "Disk / %", color: "#c87840" },
{ key: "cpu_pct", label: "CPU %", color: stewardColor("--gold") },
{ key: "mem_used_pct", label: "Mem %", color: stewardColor("--green") },
{ key: "disk_root", label: "Disk / %", color: stewardColor("--yellow") },
];
new Chart(el.getContext("2d"), {
type: "line",
@@ -75,14 +73,14 @@ window.histRange = function (wid, hours) {
interaction: { mode: "index", intersect: false },
elements: { point: { radius: 0 } },
scales: {
x: { type: "linear", ticks: { callback: function (v) { return fmtTime(v); }, maxTicksLimit: 6, color: "#8a8a92", font: { size: 10 } }, grid: { color: "#30303a" } },
x: { type: "linear", ticks: { callback: function (v) { return fmtTime(v); }, maxTicksLimit: 6, font: { size: 10 } } },
// Fixed 0–{{ y_max }} ceiling (server snaps the data peak up to the next
// 10% band). Steady across refreshes — auto-scaling made the zoom jump on
// every poll — while a banded ceiling still keeps the lines filling the panel.
y: { min: 0, max: {{ y_max }}, ticks: { color: "#8a8a92", font: { size: 10 } }, grid: { color: "#30303a" } },
y: { min: 0, max: {{ y_max }}, ticks: { font: { size: 10 } } },
},
plugins: {
legend: { labels: { color: "#b8b8b0", boxWidth: 10, font: { size: 11 } } },
legend: { labels: { boxWidth: 10, font: { size: 11 } } },
tooltip: { callbacks: { title: function (items) { return items.length ? fmtTime(items[0].parsed.x) : ""; } } },
},
},
@@ -7,7 +7,7 @@
{% macro metric_cell(label, value, fmt, svg, style="", title="") %}
<div style="min-width:62px;flex:0 0 auto;" title="{{ title }}">
<div style="font-size:0.62rem;color:var(--text-dim);text-transform:uppercase;letter-spacing:0.03em;">{{ label }}</div>
<div style="font-weight:600;font-size:0.8rem;font-variant-numeric:tabular-nums;{{ style }}">
<div style="font-weight:500;font-size:0.8rem;font-variant-numeric:tabular-nums;{{ style }}">
{% if value is not none %}{{ fmt|format(value) }}{% else %}—{% endif %}
</div>
<div style="line-height:0;height:16px;">{{ svg | safe }}</div>
@@ -34,9 +34,9 @@
title="{% if stale %}stale / no recent data{% else %}warns at CPU/memory ≥90% or any disk mount ≥90% (the 'disk /' figure shows root only){% endif %}"></span>
<span style="min-width:0;">
{% if session.user_id %}
<a href="/hosts/{{ r.host.id }}" style="font-weight:600;font-size:0.85rem;overflow-wrap:anywhere;">{{ r.host.name }}</a>
<a href="/hosts/{{ r.host.id }}" style="font-weight:500;font-size:0.85rem;overflow-wrap:anywhere;">{{ r.host.name }}</a>
{% else %}
<span style="font-weight:600;font-size:0.85rem;overflow-wrap:anywhere;">{{ r.host.name }}</span>
<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" }}