FabledSteward/plugins/traefik/templates/traefik/rows.html

{# traefik/rows.html — HTMX fragment for the Traefik page: the verdict (swapped
   into #traefik-verdict above the request chart, #5710), routers that need
   attention (routes.router_state), their metric anomalies, the proxy's own
   figures, the healthy routers folded into one table (one over a cutoff but
   within its normal says so, #5741), then certificates by soonest expiry. #}
{% from "_macros.html" import stat_tile, status_badge %}

{# ── Verdict: what needs a look and since when, then the counts ─────────── #}
{% set shown = 3 %}
<p class="page-verdict" id="traefik-verdict" hx-swap-oob="true">
  {%- if problems %}<strong class="tone-{{ problems[0].state }}">{{ problems|length }} router{{ "s" if problems|length != 1 }} need{{ "s" if problems|length == 1 }} a look</strong>
  {%- for r in problems[:shown] %}{{ ":" if loop.first else ";" }} <span style="word-break:break-all;">{{ r.name }}</span>, {{ r.why }}
    {%- if r.since_before %}, all of the last {{ current_range }}{% elif r.since %}, started {{ r.since|ago }}{% endif %}
  {%- endfor %}
  {%- if problems|length > shown %}; {{ problems|length - shown }} more below{% endif %}.
  {%- if healthy %} {{ healthy|length }} healthy.{% endif %}
  {%- elif healthy %}<strong class="tone-ok">All {{ healthy|length }} router{{ "s" if healthy|length != 1 }} healthy</strong>
  {%- else %}<span class="tone-muted">No routers reported yet.</span>
  {%- endif %}
  {%- if gone %} <span class="tone-muted">{{ gone|length }} no longer reported.</span>{% endif %}
</p>

{# ── The proxy's own figures: shown even before any router reports ───────── #}
{% macro proxy_figures() %}
{% if global_stat and (global_stat.config_last_reload_at or global_stat.open_conns_total is not none
                       or global_stat.process_memory_bytes is not none) %}
<div class="stat-strip">
  {% if global_stat.config_last_reload_at %}
  {{ stat_tile("Config reloaded", global_stat.config_last_reload_at|ago,
               hint=(global_stat.config_reloads_total|int ~ " reloads") if global_stat.config_reloads_total is not none else none) }}
  {% endif %}
  {% if global_stat.open_conns_total is not none %}{{ stat_tile("Open connections", global_stat.open_conns_total|int) }}{% endif %}
  {% if global_stat.process_memory_bytes is not none %}{{ stat_tile("Memory", global_stat.process_memory_bytes|bytes) }}{% endif %}
</div>
{% endif %}
{% endmacro %}

{# A router that has answered nothing since Steward started has no latency yet. #}
{% macro ms(v) %}{% if v is none %}—{% else %}{{ "%.0f"|format(v) }} ms{% endif %}{% endmacro %}
{% macro latency_cell(v) %}<td{% if v is not none %} class="tone-{{ status_info(status_class(v, 'latency'))[0] }}"{% endif %}>{{ ms(v) }}</td>{% endmacro %}

{% macro router_card(r) %}
<div class="card">
    <div class="host-health-head">
      {{ status_badge(r.state, "Failing" if r.state == 'crit' else "Warning") }}
      <h3 class="section-title" style="margin:0;word-break:break-all;">{{ r.name }}</h3>
    </div>
    <p class="problem-detail" style="margin-bottom:0.5rem;">{% if r.meaning %}<strong>{{ r.meaning.label }}</strong>: {% endif %}{{ r.why }}
      {%- if r.since_before %}, all of the last {{ current_range }}{% elif r.since %}, started {{ r.since|ago }}{% endif %}</p>
    {% if r.codes %}
    <p class="field-hint" style="margin:0 0 0.5rem;">Last 15 min:
      {% for code, n in r.codes[:5] %}<span class="tone-{{ 'crit' if code[:1] == '5' else 'warn' }}">{{ code }}</span> ×{{ "{:,}".format(n) }}{{ ", " if not loop.last }}{% endfor %}
      {%- if r.codes|length > 5 %}, {{ r.codes|length - 5 }} more code{{ "s" if r.codes|length - 5 != 1 }}{% endif %}</p>
    {% elif codes_known %}
    <p class="field-hint" style="margin:0 0 0.5rem;">No 4xx or 5xx responses in the last 15 min.</p>
    {% else %}
    <p class="field-hint" style="margin:0 0 0.5rem;">Status codes not recorded yet: Steward keeps them from this version on.</p>
    {% endif %}
    {% if r.meaning %}
    {# What it means and the one next step (#5712; plugins/traefik/meaning.py). #}
    <p style="margin:0 0 0.3rem;font-size:0.85rem;">{{ r.meaning.meaning }} <span class="tone-muted">{{ r.meaning.likely }}</span></p>
    <p class="field-hint" style="margin:0 0 0.5rem;">Next:
      {%- if r.meaning.action == 'act' %}
        {%- if r.service %} <a href="/plugins/docker/service/{{ r.service|urlencode }}">{{ r.service }}: its tasks and logs →</a>
        {%- else %} look at the app's container and logs under <a href="/plugins/docker/swarm">Docker → Swarm</a>; Steward can't tell which service serves this router.
        {%- endif %}
      {%- else %} if this is normal for this router, raise the 4xx cutoff in <a href="/settings/thresholds/#traefik">Settings → Thresholds</a>. It is one cutoff for every router
        {%- if not r.normed %}; once Steward has learned this router's normal for the hour, it flags only departures from it{% endif %}.
      {%- endif %}</p>
    {% endif %}
    <table class="table" style="font-size:0.85rem;">
        <tr><td class="field-hint">Req/s</td><td>{{ "%.2f"|format(r.latest.request_rate) }}</td><td>{{ r.sparkline_req|safe }}</td></tr>
        <tr><td class="field-hint">Bandwidth</td><td>{{ r.latest.response_bytes_rate|rate }}</td><td>{{ r.sparkline_bytes|safe }}</td></tr>
        <tr><td class="field-hint">p95</td>{{ latency_cell(r.latest.latency_p95_ms) }}<td>{{ r.sparkline_p95|safe }}</td></tr>
        <tr><td class="field-hint">p99</td><td>{{ ms(r.latest.latency_p99_ms) }}</td><td></td></tr>
        <tr><td class="field-hint">4xx</td><td class="{{ 'tone-warn' if r.latest.error_rate_4xx_pct > error_4xx else '' }}">{{ "%.1f"|format(r.latest.error_rate_4xx_pct) }}%</td><td>{{ r.sparkline_4xx|safe }}</td></tr>
        <tr><td class="field-hint">5xx</td><td class="{{ 'tone-crit' if r.latest.error_rate_5xx_pct > error_5xx else '' }}">{{ "%.1f"|format(r.latest.error_rate_5xx_pct) }}%</td><td>{{ r.sparkline_5xx|safe }}</td></tr>
    </table>
    <div class="field-hint" style="margin-top:0.5rem;">Last scraped {{ r.latest.scraped_at|ago }}</div>
</div>
{% endmacro %}

{% if problems or healthy or gone or certs or old_certs %}
{# ── Routers that need attention ─────────────────────────────────────────── #}
{% if problems %}
{# A grid, not CSS columns: a column box drops its last card's bottom margin,
   which left the cards touching the section below (#5214). #}
<div class="node-grid" style="margin-bottom:1rem;">
  {% for r in problems %}{{ router_card(r) }}{% endfor %}
</div>
{% endif %}

{# A router's 4xx share or p95 out of its own normal (#5741), and the last
   30 days' anomalies, to review here. #}
{% include "_anomaly_card.html" %}

{{ proxy_figures() }}

{# ── Healthy routers, folded ─────────────────────────────────────────────── #}
{% if healthy %}
<details class="card" id="traefik-healthy" style="margin-bottom:1rem;">
  <summary class="section-title" style="cursor:pointer;">{{ healthy|length }} healthy router{{ 's' if healthy|length != 1 }}</summary>
  <div class="table-wrap" style="margin-top:0.75rem;">
  <table class="table" style="font-size:0.85rem;">
    <thead><tr><th>Router</th><th>Req/s</th><th>Bandwidth</th><th>p95</th><th>4xx</th><th>5xx</th></tr></thead>
    <tbody>
    {% for r in healthy %}
    <tr>
      <td style="word-break:break-all;">{{ r.name }}{% if r.why %}<div class="field-hint">{{ r.why }}</div>{% endif %}</td>
      <td>{{ "%.2f"|format(r.latest.request_rate) }}</td>
      <td>{{ r.latest.response_bytes_rate|rate }}</td>
      {{ latency_cell(r.latest.latency_p95_ms) }}
      <td>{{ "%.1f"|format(r.latest.error_rate_4xx_pct) }}%</td>
      <td>{{ "%.1f"|format(r.latest.error_rate_5xx_pct) }}%</td>
    </tr>
    {% endfor %}
    </tbody>
  </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 () {
    var el = document.getElementById("traefik-healthy");
    if (!el) return;
    el.open = !!window.__traefikHealthyOpen;
    el.addEventListener("toggle", function () { window.__traefikHealthyOpen = el.open; });
  })();
</script>
{% endif %}

{# ── Certificates Traefik still serves, soonest expiry first; then the ones
   it no longer reports (renewed or retired), kept here but off the
   dashboard (#5254). #}
{% if certs or old_certs %}
<div class="card">
  <div class="section-title" style="margin-bottom:0.75rem;">TLS certificates</div>
  {% if certs %}
  <table class="table" style="font-size:0.85rem;">
    <thead><tr><th>Name</th><th>Routers</th><th>Expires</th><th style="text-align:right;">Left</th></tr></thead>
    <tbody>
    {% for cert in certs %}
    <tr>
      <td style="word-break:break-all;">{{ cert.cn }}{% if cert.sans %}<div class="field-hint">also {{ cert.sans|join(", ") }}</div>{% endif %}</td>
      <td class="field-hint">{% if cert.routers is none %}—{% elif cert.routers %}{{ cert.routers|join(", ") }}{% else %}not in use{% endif %}</td>
      <td class="field-hint">{{ cert.not_after.strftime("%Y-%m-%d") }}</td>
      <td style="text-align:right;white-space:nowrap;" class="tone-{{ status_info(status_class(cert.days_remaining, 'tls_days'))[0] }}">{{ cert_left(cert.days_remaining) }}</td>
    </tr>
    {% endfor %}
    </tbody>
  </table>
  {% endif %}
  {% if old_certs %}
  <details style="margin-top:0.75rem;">
    <summary class="field-hint">No longer served ({{ old_certs|length }}) — renewed or retired; Traefik stopped reporting them</summary>
    <table class="table" style="font-size:0.85rem;margin-top:0.5rem;">
      <thead><tr><th>Name</th><th>Expires</th></tr></thead>
      <tbody>
      {% for cert in old_certs %}
      <tr style="color:var(--text-muted);">
        <td style="word-break:break-all;">{{ cert.cn }}</td>
        <td class="field-hint">{{ cert.not_after.strftime("%Y-%m-%d") }}</td>
      </tr>
      {% endfor %}
      </tbody>
    </table>
  </details>
  {% endif %}
</div>
{% endif %}

{% else %}
{{ proxy_figures() }}
<div class="card">
    <p class="field-hint">No Traefik metrics yet. Configure <code>metrics_url</code> in <code>config.yaml</code> under <code>plugins.traefik</code>.</p>
</div>
{% endif %}