LotusGuild/gandalf
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Guard ticket creation against duplicates using event's existing ticket_id
Lint / Python (flake8) (push) Successful in 41s
Details
Lint / JS (eslint) (push) Successful in 7s
Details
Security / Python Security (bandit) (push) Successful in 40s
Details
Test / Python Tests (pytest) (push) Successful in 1m18s
Details
Lint / Notify on failure (push) Has been skipped
Details
Lint / Deploy (push) Successful in 4s
Details

Browse Source 
upsert_event now returns ticket_id (4th element) so callers can skip
ticket creation when one already exists. This prevents calling the ticket
API every poll cycle for ongoing issues while still retrying if the
previous creation attempt failed (ticket_id stays NULL until success).

Cluster events use (is_new or not ticket_id) so they too get retried
on failure rather than relying solely on is_new.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Jared Vititoe
2026-05-14 11:09:50 -04:00
parent 0975dd007a
commit 9c5a88fbce
2 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
monitor.py
+8 -8
View File
@@ -728,12 +728,12 @@ class NetworkMonitor:
db.check_suppressed(suppressions, 'interface', host, iface) or
db.check_suppressed(suppressions, 'host', host)
)
event_id, is_new, consec = db.upsert_event(
event_id, is_new, consec, ticket_id = db.upsert_event(
'interface_down', 'critical', 'prometheus',
host, iface,
f'Interface {iface} on {host} went link-down ({_now_utc()})',
)
if not sup and consec >= self.fail_thresh:
if not sup and consec >= self.fail_thresh and not ticket_id:
self._ticket_interface(event_id, host, iface, consec)
if host_has_regression:
@@ -744,13 +744,13 @@ class NetworkMonitor:
# Cluster-wide check – only genuine regressions count
if len(hosts_with_regression) >= self.cluster_thresh:
sup = db.check_suppressed(suppressions, 'all', '')
event_id, is_new, consec = db.upsert_event(
event_id, is_new, consec, ticket_id = db.upsert_event(
'cluster_network_issue', 'critical', 'prometheus',
self.cluster_name, '',
f'{len(hosts_with_regression)} hosts reporting simultaneous interface failures: '
f'{", ".join(hosts_with_regression)}',
)
if not sup and is_new:
if not sup and (is_new or not ticket_id):
title = (
f'[{self.cluster_name}][auto][production][issue][network][cluster-wide] '
f'Multiple hosts reporting interface failures'
@@ -804,12 +804,12 @@ class NetworkMonitor:
name = d['name']
if not d['connected']:
sup = db.check_suppressed(suppressions, 'unifi_device', name)
event_id, is_new, consec = db.upsert_event(
event_id, is_new, consec, ticket_id = db.upsert_event(
'unifi_device_offline', 'critical', 'unifi',
name, d.get('type', ''),
f'UniFi {name} ({d.get("ip","")}) offline ({_now_utc()})',
)
if not sup and consec >= self.fail_thresh:
if not sup and consec >= self.fail_thresh and not ticket_id:
self._ticket_unifi(event_id, d)
else:
db.resolve_event('unifi_device_offline', name, d.get('type', ''))
@@ -844,12 +844,12 @@ class NetworkMonitor:
if not reachable:
sup = db.check_suppressed(suppressions, 'host', name)
event_id, is_new, consec = db.upsert_event(
event_id, is_new, consec, ticket_id = db.upsert_event(
'host_unreachable', 'critical', 'ping',
name, ip,
f'Host {name} ({ip}) unreachable via ping ({_now_utc()})',
)
if not sup and consec >= self.fail_thresh:
if not sup and consec >= self.fail_thresh and not ticket_id:
self._ticket_unreachable(event_id, name, ip, consec)
else:
db.resolve_event('host_unreachable', name, ip)