feat(norms): hosts, containers and monitor response times are graded against their own normal (#5742)

Host CPU, memory and load per core, container CPU and memory, and every
monitor's response time learn a normal per hour (milestone 513, System 182).
A reading past its fixed cutoff but within its normal reads healthy and says
what is usual at this hour; one well out of it keeps its grade and is a
metric anomaly. Disk, a monitor down and an agent offline keep their cutoffs.

- Each normal's floor, the smallest departure that counts, is a setting:
  Settings -> Thresholds -> Normals (norms.floor.*). Defaults: host CPU 10
  points, host memory 5, load per core 10, container CPU 10 points of one
  core, container memory 5, monitor response 100 ms; Traefik's 2-point 4xx
  and 50 ms p95 floors move there from constants. learn_normal takes a
  floor function (floor_setting) read at each pass.
- learn_normal(parts=False): a host learns, its cores don't.
- Ingest records load_pct (load_1m / cores x 100), the figure pages grade.
- Shared grading: anomalies.against / graded, worst_reading(normals=),
  hosts' host_grades, docker usage(thresholds=, norms=), monitors'
  latency_grade. Applied to host vitals, the Hosts widget, MCP overview,
  Docker usage, and the monitor list, widget and page.
- The monitor and container pages list their anomalies.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

steward/templates/monitors/detail.html

@@ -1,7 +1,8 @@
 {% extends "base.html" %}
 {% from "_macros.html" import crumbs, page_header, stat_tile %}
 {# One monitor: its state and for how long, latency and uptime against
-   Settings → Thresholds, its response time over the last day, its last
+   Settings → Thresholds (latency against its own normal once it has one,
+   with its anomalies), its response time over the last day, its last
    checks, the failures behind them and how it is set up. #}
 {% block title %}{{ monitor.name }} — Monitors — Steward{% endblock %}
 {% block breadcrumb %}{{ crumbs([("Monitors", "/monitors/"), (monitor.name, "")]) }}{% endblock %}
@@ -23,7 +24,7 @@
   {% set since_hint = ((("for at least " if since_at_least else "for ") ~ (since|ago|striptags|replace(" ago", ""))) if since and state in ("up", "down", "degraded") else none) %}
   {{ stat_tile("State", status_info(state)[1], state=state, hint=since_hint) }}
   {% if latest and latest.response_ms is not none %}
-  {{ stat_tile("Latency", "%.0f ms"|format(latest.response_ms), state=status_class(latest.response_ms, "latency")) }}
+  {{ stat_tile("Latency", "%.0f ms"|format(latest.response_ms), state=latency[0], hint=latency[1]) }}
   {% endif %}
   {% for window in ("24h", "7d", "30d") %}
   {% set pct = uptime.get(window) %}
@@ -34,6 +35,8 @@
   {% endif %}
 </div>
 
+{% with back="/monitors/" ~ monitor.id, base_resource=monitor.name %}{% include "_anomaly_card.html" %}{% endwith %}
+
 {% set timed = history | selectattr("ms", "ne", none) | list %}
 {% if timed|length > 1 %}
 <section class="card" aria-labelledby="m-chart">

steward/templates/monitors/rows.html

@@ -51,7 +51,7 @@
     {% if d.state in ('down', 'paused', 'pending') %}{{ status_badge(d.state) }}
     {% elif latest.response_ms is not none %}
       {% if d.spark %}<span class="mon-spark" title="Response time over the last 30 checks">{{ d.spark|safe }}</span>{% endif %}
-      <span class="tone-{{ status_class(latest.response_ms, 'latency') }}">{{ "%.0f"|format(latest.response_ms) }} ms</span>
+      <span class="tone-{{ d.latency }}"{% if d.latency_usual %} title="{{ d.latency_usual|capitalize }}"{% endif %}>{{ "%.0f"|format(latest.response_ms) }} ms</span>
     {% elif m.type == 'dns' and latest.resolved_ip %}<span class="tone-ok">{{ latest.resolved_ip }}</span>
     {% else %}{{ status_badge('up') }}{% endif %}
   </div>

steward/templates/monitors/widget.html

@@ -26,10 +26,10 @@
       {{- status_dot(d.state) -}}
       {% if session.user_id %}<a href="/monitors/{{ m.id }}">{{ m.name }}</a>{% else %}{{ m.name }}{% endif %}
       {%- if d.state == 'down' %}<span class="w-sub tone-crit">went down {{ d.down_since|ago if d.down_since else '' }}{% if d.down_reason %} · {{ d.down_reason }}{% endif %}</span>
-      {%- elif d.state == 'degraded' %}<span class="w-sub tone-warn">{% if latest and status_class(latest.response_ms, 'latency') == 'crit' %}slow replies{% else %}checks failing now and then{% endif %}</span>
+      {%- elif d.state == 'degraded' %}<span class="w-sub tone-warn">{% if d.latency == 'crit' %}slow replies{% else %}checks failing now and then{% endif %}</span>
       {%- elif d.state == 'pending' %}<span class="w-sub">not checked yet</span>{% endif %}
     </td>
-    <td style="{{ threshold_style(latest.response_ms, 'latency') if latest and latest.is_up and latest.response_ms is not none }}">
+    <td class="{{ 'tone-' ~ d.latency if d.latency in ('warn', 'crit') }}"{% if d.latency_usual %} title="{{ d.latency_usual|capitalize }}"{% endif %}>
       {%- if latest and latest.is_up and latest.response_ms is not none %}{{ "%.0f"|format(latest.response_ms) }} ms{% else %}—{% endif -%}
     </td>
     {% for k in ("24h", "7d", "30d") %}{% set u = d.uptime.get(k) %}