From 10cb1c215295ccf39e10323ce34ad48b2acf7545 Mon Sep 17 00:00:00 2001 From: hermes-bot Date: Tue, 27 Oct 2026 07:26:13 +0000 Subject: [PATCH 1/2] fix(wiki): wiki-sync retries while the wiki pod restarts The wiki Deployment uses Recreate, so during an image rollout the Service has no ready endpoint for ~10 s. wiki-sync-29884710 started 06:30:00Z, 4 s before the new pod was Ready, failed with curl (7) and fired KubeJobFailed. Retry up to 6 times, 10 s apart, on connection refused too, bounded to 120 s from the first attempt so a long sync that fails is not repeated. Refs #1461 --- kubernetes/apps/wiki/cronjobs.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kubernetes/apps/wiki/cronjobs.yaml b/kubernetes/apps/wiki/cronjobs.yaml index feb7ab5c..8c6669e4 100644 --- a/kubernetes/apps/wiki/cronjobs.yaml +++ b/kubernetes/apps/wiki/cronjobs.yaml @@ -72,7 +72,7 @@ spec: command: - sh - -c - - 'curl -fsS --max-time 1700 -X POST -H "X-Api-Key: $API_KEY" http://wiki.ai.svc.cluster.local:8080/api/v1/sync' + - 'curl -fsS --retry 6 --retry-delay 10 --retry-connrefused --retry-max-time 120 --max-time 1700 -X POST -H "X-Api-Key: $API_KEY" http://wiki.ai.svc.cluster.local:8080/api/v1/sync' env: - name: API_KEY valueFrom: -- 2.54.0 From be4e605d65f06c29a22c73d714872ba4ff40a222 Mon Sep 17 00:00:00 2001 From: hermes-bot Date: Tue, 27 Oct 2026 07:27:46 +0000 Subject: [PATCH 2/2] fix(wiki): wiki-sync retry window covers the full 120 s Six retries at a fixed 10 s delay stopped after about 60 s, so --retry-max-time 120 never bound. Twelve retries let the 120 s cap be the limit, covering a Recreate rollout slowed by an image pull. Retrying on 5xx is safe: POST /api/v1/sync is serialized by SyncCoordinator and re-syncs the same state, the same as a webhook landing mid-sync. --retry-max-time 120 keeps a long sync that fails late from being repeated. --- kubernetes/apps/wiki/cronjobs.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kubernetes/apps/wiki/cronjobs.yaml b/kubernetes/apps/wiki/cronjobs.yaml index 8c6669e4..1c00168d 100644 --- a/kubernetes/apps/wiki/cronjobs.yaml +++ b/kubernetes/apps/wiki/cronjobs.yaml @@ -72,7 +72,7 @@ spec: command: - sh - -c - - 'curl -fsS --retry 6 --retry-delay 10 --retry-connrefused --retry-max-time 120 --max-time 1700 -X POST -H "X-Api-Key: $API_KEY" http://wiki.ai.svc.cluster.local:8080/api/v1/sync' + - 'curl -fsS --retry 12 --retry-delay 10 --retry-connrefused --retry-max-time 120 --max-time 1700 -X POST -H "X-Api-Key: $API_KEY" http://wiki.ai.svc.cluster.local:8080/api/v1/sync' env: - name: API_KEY valueFrom: -- 2.54.0