Files
FabledSteward/steward/templates/alerts/rules_form.html
T
bvandeusen 4771d17f6d
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 8s
CI / integration (push) Failing after 2m16s
feat(alerts): run an Ansible playbook on alert firing (task 250)
Rebuilds the deleted NUT/UPS automation as a general alert action: any metric
can drive a playbook run on transition-to-firing.

- models/alerts.py + migration 0014: AlertRule.ansible_action (JSON, admin-only,
  reuses the #546 param shape); AlertEvent.ansible_run_id links a firing event to
  the run it triggered
- core/alerts.py: pure alert_extra_vars() injects steward_alert_* context; on
  ('firing', event) with an action set, schedule _run_ansible_action (deferred
  after commit, same pattern as notifications) — fires once per transition,
  consecutive_failures_required is the debounce; system-triggered AnsibleRun
- alerts/routes.py: admin-only parse/validate of the action (source must be
  configured, playbook must exist); operators keep editing rules, action preserved
- rules_form.html: admin-only 'On firing -> run a playbook' section
- tests: unit for alert_extra_vars; integration drives record_metric to firing
  and asserts a system AnsibleRun ran the playbook with the injected var and the
  event linked to it

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 14:22:29 -04:00

190 lines
9.8 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{% extends "base.html" %}
{% block title %}{% if rule %}Edit Rule{% else %}New Alert Rule{% endif %} — Steward{% endblock %}
{% block content %}
<div style="max-width:600px;margin:2rem auto;">
<h1 class="page-title">{% if rule %}Edit Rule{% else %}New Alert Rule{% endif %}</h1>
<div class="card">
<form method="post" action="{% if rule %}/alerts/rules/{{ rule.id }}{% else %}/alerts/rules{% endif %}">
<div class="form-group">
<label>Rule Name</label>
<input type="text" name="name" required autofocus
value="{{ rule.name if rule else '' }}"
placeholder="e.g. Home server down">
</div>
{# ── Source module ───────────────────────────────────────────────────── #}
<div class="form-group">
<label>Source</label>
<select name="source_module" required
hx-get="/alerts/api/rule_fields"
hx-trigger="change"
hx-target="#rule-fields"
hx-include="[name='source_module']">
{% for src in source_modules %}
<option value="{{ src }}" {% if src == initial_source %}selected{% endif %}>
{{ src }}
</option>
{% endfor %}
</select>
</div>
{# ── Dynamic resource + metric ────────────────────────────────────────── #}
<div id="rule-fields">
{# Inline the same partial logic so the page is fully usable without JS #}
<div class="form-group">
<label>Resource Name</label>
{% if resources %}
<select name="resource_name" required>
{% if not (rule and rule.resource_name) %}<option value="" disabled selected>— pick a resource —</option>{% endif %}
{% for r in resources %}
<option value="{{ r }}" {% if rule and r == rule.resource_name %}selected{% endif %}>{{ r }}</option>
{% endfor %}
</select>
{% else %}
<select name="resource_name" required disabled>
<option value="">No data yet — run monitors first</option>
</select>
<p style="font-size:0.78rem;color:var(--text-muted);margin-top:0.25rem;">
Resource names populate from live metric data. Start the scheduler and try again.
</p>
{% endif %}
</div>
<div class="form-group">
<label>Metric Name</label>
<select name="metric_name" required>
{% if not (rule and rule.metric_name) %}<option value="" disabled selected>— pick a metric —</option>{% endif %}
{% for m in metrics %}
<option value="{{ m }}" {% if rule and m == rule.metric_name %}selected{% endif %}>{{ m }}</option>
{% endfor %}
</select>
</div>
</div>
{# ── Condition ───────────────────────────────────────────────────────── #}
<div style="display:grid;grid-template-columns:1fr 1fr;gap:1rem;">
<div class="form-group">
<label>Operator</label>
<select name="operator">
{% for val, label in operators %}
<option value="{{ val }}" {% if rule and rule.operator.value == val %}selected{% endif %}>
{{ label }}
</option>
{% endfor %}
</select>
</div>
<div class="form-group">
<label>Threshold</label>
<input type="number" name="threshold" step="any" required
value="{{ rule.threshold if rule else '' }}"
placeholder="0.5">
</div>
</div>
<div class="form-group">
<label>Consecutive failures before FIRING</label>
<input type="number" name="consecutive_failures_required" min="1"
value="{{ rule.consecutive_failures_required if rule else 1 }}">
</div>
{# ── Metric reference ────────────────────────────────────────────────── #}
<details style="margin-bottom:1rem;">
<summary style="cursor:pointer;font-size:0.82rem;color:var(--text-muted);user-select:none;">
Metric reference
</summary>
<div style="margin-top:0.75rem;display:grid;gap:0.5rem;">
{% set descs = {
"ping": [("up", "1.0 = reachable, 0.0 = unreachable"),
("response_time_ms", "round-trip latency in milliseconds")],
"dns": [("resolved", "1.0 = resolved, 0.0 = failed"),
("ip_changed", "1.0 when resolved IP differs from expected")],
"traefik": [("request_rate", "requests/sec for this router"),
("error_rate", "fraction of 5xx responses (01)"),
("latency_p50_ms", "median response time ms"),
("latency_p95_ms", "p95 response time ms"),
("latency_p99_ms", "p99 response time ms"),
("response_bytes_rate", "bytes/sec of responses"),
("cert_expiry_days", "days until TLS cert expires")],
"unifi": [("is_up", "1.0 = WAN up, 0.0 = down"),
("latency_ms", "WAN latency in ms"),
("total_clients", "number of connected clients")],
"docker": [("cpu_pct", "container CPU usage %"),
("mem_pct", "container memory usage %")],
"http": [("is_up", "1.0 = check passed, 0.0 = failed"),
("response_ms", "HTTP response time in ms")],
} %}
{% for src, pairs in descs.items() %}
<div>
<div style="font-size:0.78rem;font-weight:600;color:var(--text-dim);text-transform:uppercase;letter-spacing:0.05em;margin-bottom:0.2rem;">{{ src }}</div>
{% for metric, desc in pairs %}
<div style="display:grid;grid-template-columns:160px 1fr;gap:0.5rem;font-size:0.78rem;padding:0.15rem 0;">
<code>{{ metric }}</code>
<span style="color:var(--text-muted);">{{ desc }}</span>
</div>
{% endfor %}
</div>
{% endfor %}
</div>
</details>
{# ── Ansible action (admin only) ─────────────────────────────────────── #}
{% if session.get("user_role") == "admin" %}
{% set act = rule.ansible_action if rule and rule.ansible_action else None %}
<div style="margin:1.25rem 0;padding:1rem;border:1px solid var(--border-mid);border-radius:6px;background:var(--bg-elevated);">
<label style="display:flex;align-items:center;gap:0.5rem;font-weight:600;">
<input type="checkbox" name="ansible_enabled" {% if act %}checked{% endif %}>
On firing → run an Ansible playbook
</label>
<p style="font-size:0.78rem;color:var(--text-muted);margin:0.4rem 0 0.75rem;">
Admin only. Runs once when the alert transitions into FIRING.
<code>steward_alert_*</code> context vars (resource, metric, value…) are injected automatically.
</p>
<div class="form-group">
<label>Source</label>
<select name="ansible_source">
<option value="">— select source —</option>
{% for s in ansible_sources %}
<option value="{{ s }}" {% if act and act.source == s %}selected{% endif %}>{{ s }}</option>
{% endfor %}
</select>
</div>
<div class="form-group">
<label>Playbook <span style="color:var(--text-muted);font-weight:normal;">(path within source)</span></label>
<input type="text" name="ansible_playbook" placeholder="playbooks/shutdown.yml"
value="{{ act.playbook if act else '' }}">
</div>
<div class="form-group">
<label>Inventory <span style="color:var(--text-muted);font-weight:normal;">(path within source)</span></label>
<input type="text" name="ansible_inventory" placeholder="inventory/hosts"
value="{{ act.inventory if act else '' }}">
</div>
<div class="form-group">
<label>Extra vars <span style="color:var(--text-muted);font-weight:normal;">(optional, one key=value per line)</span></label>
<textarea name="ansible_extra_vars" rows="2"
style="width:100%;font-family:ui-monospace,monospace;font-size:0.85rem;">{{ act.extra_vars | join("\n") if act and act.extra_vars else "" }}</textarea>
</div>
<div class="form-group">
<label>Limit to host(s) <span style="color:var(--text-muted);font-weight:normal;">(optional)</span></label>
<input type="text" name="ansible_limit" value="{{ act.limit if act and act.limit else '' }}">
</div>
<div class="form-group">
<label>Tags <span style="color:var(--text-muted);font-weight:normal;">(optional)</span></label>
<input type="text" name="ansible_tags" value="{{ act.tags if act and act.tags else '' }}">
</div>
<label style="display:flex;align-items:center;gap:0.5rem;font-weight:normal;">
<input type="checkbox" name="ansible_check" {% if act and act.check %}checked{% endif %}>
Dry-run (--check --diff)
</label>
</div>
{% endif %}
<div style="display:flex;gap:1rem;margin-top:1.5rem;">
<button type="submit" class="btn">{% if rule %}Save Changes{% else %}Create Rule{% endif %}</button>
<a href="/alerts/" class="btn btn-ghost">Cancel</a>
</div>
</form>
</div>
</div>
{% endblock %}