alert when a review-classifier run fails
This commit is contained in:
parent
b89ca3955a
commit
c5d601e3a2
1 changed files with 37 additions and 0 deletions
|
|
@ -1627,6 +1627,19 @@ in
|
|||
for = "0s";
|
||||
summary = "{{ $labels.hive }}/{{ $labels.agent }} could not connect to the swarm queue and its harness exited; systemd starts it again 30s later";
|
||||
})
|
||||
# `swarm-review-classifier` logs this at `warn` when a run
|
||||
# ends without a verdict (a rejected or unreadable API key,
|
||||
# a failed model call), so that PR has no classifier
|
||||
# review. The cause is in `F_ERROR`. The window is how long
|
||||
# the rule stays firing after the last failure.
|
||||
(logCountRule {
|
||||
uid = "hh-review-classifier-run-failed";
|
||||
title = "review classifier run failed";
|
||||
windowSeconds = 1800;
|
||||
expr = ''_time:30m _msg:"review classification run failed" | stats count() as failures'';
|
||||
for = "0s";
|
||||
summary = "a review-classifier run ended without a verdict, so that PR has no classifier review; the cause is in the F_ERROR field of the log line";
|
||||
})
|
||||
(logCountRule {
|
||||
uid = "hh-swarm-agent-state-publish-skipped";
|
||||
title = "swarm agent state publish skipped";
|
||||
|
|
|
|||
Loading…
Reference in a new issue