feat(alerts): Send test on a rule checks that its alerts reach someone (#5466)
CI / lint (push) Successful in 2s
CI / integration (push) Successful in 1m9s
CI / unit (push) Successful in 1m36s
CI / publish (push) Successful in 1m6s

#5466 "Send test: check a rule's delivery from the rule". A rule's page gets
a Send test button (operator role), and MCP gets send_test_alert. Each sends
a TEST alert for that rule now, by email to everyone who gets alerts and by
webhook. The alert carries the rule's name and condition, at the latest
reading of what it watches; a rule covering hosts uses its first host. The
result for each channel shows under the button, or "Nothing is set up to
send to". Nothing fires, no event is written, and the test is audited as
alert_rule.tested. An alert with no reading now says "has no reading yet"
instead of "is None".

Docs: alerting.md also gains the burst email from #5465 "One email per burst
of alerts".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-09 08:33:32 -04:00
co-authored by Claude Opus 5.5
parent 997aa50939
commit 5ef18c992c
13 changed files with 299 additions and 7 deletions
+21 -2
View File
@@ -6,7 +6,7 @@ from datetime import datetime, timedelta, timezone
from sqlalchemy import select
from steward.alerts import service as alert_svc
from steward.mcp._context import current_caller
from steward.mcp._context import current_caller, mcp_app
from steward.models.alerts import AlertOperator, AlertRule, AlertState, MaintenanceWindow
from steward.models.users import UserRole
@@ -391,6 +391,25 @@ async def acknowledge_alert(rule: str) -> dict:
"acknowledged_at": iso(state.acknowledged_at)}
async def send_test_alert(rule: str) -> dict:
"""Send a TEST notification for a rule now, to check it reaches someone:
email to everyone who gets alerts (each in their own zone) and the
webhook, the same channels a real alert of this rule would use. Nothing
fires and the rule's history is unchanged.
rule: the rule's name or id (list_alert_rules). Returns `ok` (something
was sent and nothing failed) and one line per channel saying what
happened. Recorded in the audit log.
"""
async with db_session() as db:
r = await _rule(db, rule)
sent = await alert_svc.send_test(mcp_app(), r.id)
await audit_mcp("alert_rule.tested", "alert_rule", r.name,
{"rule_id": r.id, "ok": sent["ok"], "lines": sent["lines"]})
return {"rule_id": r.id, "rule_name": r.name, "ok": sent["ok"], "result": sent["lines"],
"email": sent["email"], "webhook": sent["webhook"]}
def _when(value: str, what: str) -> datetime:
try:
dt = datetime.fromisoformat(value.strip().replace("Z", "+00:00"))
@@ -467,7 +486,7 @@ def register(register_tool) -> None:
for fn in (list_alerts, get_alert_history, list_alert_rules, list_maintenance_windows,
get_alert_rule_options):
register_tool(fn, role=UserRole.viewer, read_only=True)
for fn in (create_alert_rule, update_alert_rule, acknowledge_alert,
for fn in (create_alert_rule, update_alert_rule, acknowledge_alert, send_test_alert,
create_maintenance_window, end_maintenance_window):
register_tool(fn, role=UserRole.operator, read_only=False)
register_tool(delete_alert_rule, role=UserRole.admin, read_only=False)