bvandeusenandClaude Opus 5.5
a6c24299a2
#5059 "Alert state machine: acknowledgement holds until resolve; N consecutive OK to resolve; editing, disabling or deleting a rule resets it". - The state machine is now next_step(), a pure function of one sample. An acknowledged alert stays acknowledged while breached; before, the next breaching sample re-fired it. Firing and acknowledged alerts resolve after consecutive_ok_required OK checks in a row (new rule column, default 1; rule form, rules list and MCP create/update_alert_rule clear_after_checks). - Changing what a rule watches (source, resource, metric, operator, threshold) or disabling it resets its alert to inactive; a firing or acknowledged one records a resolved event whose new note says why, and nobody is notified. Web and MCP edits share alerts.service.apply_rule_change. - Migration 0028: consecutive_ok_required, consecutive_ok_count, alert_events.note, and metric_value nullable (a reset has no sample). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
203 lines
11 KiB
HTML
203 lines
11 KiB
HTML
{% extends "base.html" %}
|
||
{% from "_macros.html" import crumbs %}
|
||
{% block title %}{% if rule %}Edit Rule{% else %}New Alert Rule{% endif %} — Steward{% endblock %}
|
||
{% block breadcrumb %}{{ crumbs([("Alerts", "/alerts/"), ("Edit rule" if rule else "New rule", "")]) }}{% 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 %}">{{ csrf_field() }}
|
||
|
||
<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>
|
||
|
||
<div class="form-group">
|
||
<label>Consecutive OK checks before it clears</label>
|
||
<input type="number" name="consecutive_ok_required" min="1"
|
||
value="{{ rule.consecutive_ok_required if rule else 1 }}">
|
||
<p style="font-size:0.75rem;color:var(--text-muted);margin-top:0.2rem;">
|
||
A firing or acknowledged alert resolves only after this many checks in a row are back
|
||
within the threshold. An acknowledgement holds until then.</p>
|
||
</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 = {
|
||
"icmp": [("is_up", "1.0 = reachable, 0.0 = unreachable"),
|
||
("response_ms", "round-trip latency in milliseconds")],
|
||
"tcp": [("is_up", "1.0 = port open, 0.0 = unreachable"),
|
||
("response_ms", "TCP connect time in milliseconds")],
|
||
"dns": [("is_up", "1.0 = resolved (and matches expected IP), 0.0 = failed"),
|
||
("response_ms", "resolution time in milliseconds")],
|
||
"traefik": [("request_rate", "requests/sec for this router"),
|
||
("error_rate", "fraction of 5xx responses (0–1)"),
|
||
("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 %}
|