FabledSteward/steward/templates/settings/thresholds.html

{# steward/templates/settings/thresholds.html — tunable degraded/critical cutoffs #}
{% extends "base.html" %}
{% from "_macros.html" import crumbs %}
{% block title %}Settings — Thresholds & Retention — Steward{% endblock %}
{% block breadcrumb %}{{ crumbs([("Settings", "/settings/"), ("Thresholds & retention", "")]) }}{% endblock %}
{% block content %}
{% set active_tab = "thresholds" %}
{% include "settings/_tabs.html" %}

{% macro pair(label, warn_field, warn_key, crit_field, crit_key, unit, hint, step="1") %}
<div class="form-group" style="margin-bottom:1.1rem;">
  <label>{{ label }} <span style="color:var(--text-muted);font-size:0.8rem;">({{ unit }})</span></label>
  <div style="display:flex;gap:1.25rem;flex-wrap:wrap;margin-top:0.25rem;">
    <span style="display:flex;align-items:center;gap:0.4rem;">
      <span style="color:var(--yellow);font-size:0.8rem;font-weight:500;">warn</span>
      <input type="number" name="{{ warn_field }}" step="{{ step }}"
             value="{{ settings[warn_key] }}" style="max-width:110px;">
    </span>
    <span style="display:flex;align-items:center;gap:0.4rem;">
      <span style="color:var(--red);font-size:0.8rem;font-weight:500;">crit</span>
      <input type="number" name="{{ crit_field }}" step="{{ step }}"
             value="{{ settings[crit_key] }}" style="max-width:110px;">
    </span>
  </div>
  {% if hint %}<div style="font-size:0.78rem;color:var(--text-muted);margin-top:0.3rem;">{{ hint }}</div>{% endif %}
</div>
{% endmacro %}

<form method="post" action="/settings/thresholds/">{{ csrf_field() }}
<div class="card" style="max-width:640px;">
  <h2 class="section-title" style="margin-bottom:0.5rem;">Monitoring thresholds</h2>
  <p style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1.25rem;">
    Values at or beyond <span style="color:var(--yellow);">warn</span> show amber; at or beyond
    <span style="color:var(--red);">crit</span> show red — across dashboard widgets and host views.
    Higher is worse for everything except uptime, where the cutoffs are floors.
  </p>

  {{ pair("CPU usage",    "cpu_warn",  "thresholds.cpu_warn",  "cpu_crit",  "thresholds.cpu_crit",  "%", "Average CPU utilization per host.") }}
  {{ pair("Memory usage", "mem_warn",  "thresholds.mem_warn",  "mem_crit",  "thresholds.mem_crit",  "%", "Memory in use per host.") }}
  {{ pair("Disk usage",   "disk_warn", "thresholds.disk_warn", "disk_crit", "thresholds.disk_crit", "%", "Filesystem usage.") }}
  {{ pair("Load",         "load_warn", "thresholds.load_warn", "load_crit", "thresholds.load_crit", "% per core", "Load average normalized by core count (100% = one full core per core).") }}
  {{ pair("Temperature",  "temp_warn", "thresholds.temp_warn", "temp_crit", "thresholds.temp_crit", "°C", "Hottest reported sensor per host.") }}
  {{ pair("Ping latency", "latency_warn", "ping.threshold.good_ms", "latency_crit", "ping.threshold.warn_ms", "ms", "Round-trip time. Shared with the Ping widget's good/warn colouring.") }}
  {{ pair("Uptime / SLA", "uptime_warn", "thresholds.uptime_warn", "uptime_crit", "thresholds.uptime_crit", "%", "Lower is worse — amber below warn, red below crit.", step="0.1") }}
  {{ pair("TLS certificate expiry", "tls_warn", "thresholds.tls_warn_days", "tls_crit", "thresholds.tls_crit_days", "days left", "HTTPS monitors whose certificate expires within these many days are flagged. Lower is worse.") }}
  {{ pair("Clock drift", "clock_warn", "thresholds.clock_warn_s", "clock_crit", "thresholds.clock_crit_s", "seconds", "How far a host's clock may be from Steward's, either way, before its page and the Hosts list call it out.") }}

  <div class="form-group" style="margin-bottom:0.25rem;">
    <label>Container crash loop <span style="color:var(--text-muted);font-size:0.8rem;">(deaths per hour)</span></label>
    <div style="margin-top:0.25rem;">
      <input type="number" name="crash_loop_deaths" min="1" step="1"
             value="{{ settings['thresholds.crash_loop_deaths'] }}" style="max-width:110px;">
    </div>
    <div style="font-size:0.78rem;color:var(--text-muted);margin-top:0.3rem;">
      A container that dies (or is OOM-killed) this many times within an hour is reported as crash-looping.
    </div>
  </div>
</div>

{% macro days(label, field, key, hint) %}
<div class="form-group" style="margin-bottom:1.1rem;">
  <label>{{ label }} <span style="color:var(--text-muted);font-size:0.8rem;">(days)</span></label>
  <div style="margin-top:0.25rem;">
    <input type="number" name="{{ field }}" min="1" step="1"
           value="{{ settings[key] }}" style="max-width:110px;">
  </div>
  {% if hint %}<div style="font-size:0.78rem;color:var(--text-muted);margin-top:0.3rem;">{{ hint }}</div>{% endif %}
</div>
{% endmacro %}

<div class="card" style="max-width:640px;margin-top:1.5rem;">
  <h2 class="section-title" style="margin-bottom:0.5rem;">Docker data retention</h2>
  <p style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1.25rem;">
    Bounds how much Docker history is stored. Raw per-sample container metrics are
    kept for the raw window, then rolled up into hourly averages kept for the
    rollup window; lifecycle events are kept for the events window. Applied by the
    hourly cleanup task — a change takes effect on its next run.
  </p>

  {{ days("Raw metrics", "docker_metrics_raw_days", "docker.retention.metrics_raw_days",
          "Keep per-sample container CPU/memory points this long, then roll up to hourly.") }}
  {{ days("Rolled-up metrics", "docker_metrics_rollup_days", "docker.retention.metrics_rollup_days",
          "Keep the hourly-averaged series this long for multi-day history.") }}
  {{ days("Lifecycle events", "docker_events_days", "docker.retention.events_days",
          "Keep container start/stop/die/health history this long.") }}
</div>

<div class="card" style="max-width:640px;margin-top:1rem;">
  <h2 class="section-title" style="margin-bottom:0.5rem;">Container logs</h2>
  <p style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1.25rem;">
    The host agent tails each container's logs and pushes them here, viewable per
    container. On by default for every container; storage is bounded by a
    per-container ring (oldest lines rotate out once the age or size cap is hit,
    whichever comes first). Applied by the hourly cleanup and on ingest.
  </p>

  <div class="form-group" style="margin-bottom:1.1rem;">
    <label style="display:flex;align-items:center;gap:0.5rem;cursor:pointer;">
      <input type="checkbox" name="docker_logs_enabled" style="width:auto;"
             {% if settings["docker.logs.enabled"] %}checked{% endif %}>
      Collect container logs
    </label>
    <div style="font-size:0.78rem;color:var(--text-muted);margin-top:0.3rem;">
      Global kill-switch. When off, pushed log lines are dropped and no new logs are stored.
    </div>
  </div>

  <div class="form-group" style="margin-bottom:1.1rem;">
    <label>Exclude containers</label>
    <div style="margin-top:0.25rem;">
      <input type="text" name="docker_logs_exclude"
             value="{{ settings['docker.logs.exclude'] | join(', ') }}"
             placeholder="watchtower, some-chatty-service" style="width:100%;max-width:420px;">
    </div>
    <div style="font-size:0.78rem;color:var(--text-muted);margin-top:0.3rem;">
      Comma-separated container names whose logs are dropped on ingest (e.g. known-noisy ones).
    </div>
  </div>

  {{ days("Log retention", "docker_logs_retention_days", "docker.logs.retention_days",
          "Keep each container's log lines at most this long before rotating them out.") }}

  <div class="form-group" style="margin-bottom:0.25rem;">
    <label>Max size per container <span style="color:var(--text-muted);font-size:0.8rem;">(MB)</span></label>
    <div style="margin-top:0.25rem;">
      <input type="number" name="docker_logs_max_mb" min="1" step="1"
             value="{{ (settings['docker.logs.max_bytes_per_container'] // 1000000) or 1 }}"
             style="max-width:110px;">
    </div>
    <div style="font-size:0.78rem;color:var(--text-muted);margin-top:0.3rem;">
      Newest lines are kept up to this size per container; older lines rotate out first.
    </div>
  </div>
</div>

<div class="card" style="max-width:640px;margin-top:1rem;">
  <h2 class="section-title" style="margin-bottom:0.5rem;">Host metrics retention</h2>
  <p style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1.25rem;">
    Bounds how much host-agent metric history is stored (CPU, memory, disk, network,
    temps, …). Raw per-sample points are kept for the raw window, then rolled up
    into hourly averages kept for the rollup window. Host charts read raw for the
    recent part of a range and hourly for older data. Applied by the hourly cleanup.
  </p>

  {{ days("Raw metrics", "metrics_raw_days", "metrics.retention.raw_days",
          "Keep per-sample host metrics this long, then roll up to hourly averages.") }}
  {{ days("Rolled-up metrics", "metrics_rollup_days", "metrics.retention.rollup_days",
          "Keep the hourly-averaged series this long for multi-week history.") }}
</div>

<div style="margin-top:1rem;display:flex;align-items:center;gap:1rem;">
  <button type="submit" class="btn">Save</button>
  <span style="font-size:0.82rem;color:var(--text-muted);">Takes effect immediately — no restart.</span>
</div>
</form>
{% endblock %}