fix(alerts): acknowledgements hold until resolve; clear after N OK; rule changes reset (#5059)
#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>
This commit is contained in:
@@ -23,6 +23,7 @@ def _rule_form(form) -> dict:
|
||||
"operator": form.get("operator", ""),
|
||||
"threshold": form.get("threshold"),
|
||||
"consecutive_failures_required": form.get("consecutive_failures_required"),
|
||||
"consecutive_ok_required": form.get("consecutive_ok_required"),
|
||||
}
|
||||
|
||||
|
||||
@@ -204,8 +205,7 @@ async def update_rule(rule_id: str):
|
||||
fields = await alert_svc.rule_fields(db, **_rule_form(form))
|
||||
except ValueError as exc:
|
||||
return str(exc), 400
|
||||
for k, v in fields.items():
|
||||
setattr(rule, k, v)
|
||||
await alert_svc.apply_rule_change(db, rule, fields)
|
||||
if apply_action:
|
||||
rule.ansible_action = ansible_action
|
||||
await log_audit(current_app, session.get("user_id"), session.get("username", ""),
|
||||
@@ -222,7 +222,7 @@ async def toggle_rule(rule_id: str):
|
||||
rule = result.scalar_one_or_none()
|
||||
if rule is None:
|
||||
return "Not found", 404
|
||||
rule.enabled = not rule.enabled
|
||||
await alert_svc.apply_rule_change(db, rule, {}, enabled=not rule.enabled)
|
||||
action = "alert_rule.enabled" if rule.enabled else "alert_rule.disabled"
|
||||
await log_audit(current_app, session.get("user_id"), session.get("username", ""),
|
||||
action, entity_type="alert_rule", entity_id=rule.name)
|
||||
|
||||
Reference in New Issue
Block a user