stack-orchestrator/.pebbles
prathamesh0 1334900407
so-o2o: detect etcd image dynamically + diagnose whitelist cleanup bugs (#745)
Replaces the hardcoded `gcr.io/etcd-development/etcd:v3.5.9` in `_clean_etcd_keeping_certs` with a dynamic ref captured from the running Kind node via `crictl`, persisted to `{backup_dir}/etcd-image.txt` and reused on subsequent cleanup runs. Self-adapts to Kind upgrades, no version table to maintain.

Testing on Kind v0.32 / etcd 3.6 surfaced two additional bugs in the whitelist cleanup that this PR does **not** fix (see so-o2o comments):
(a) the restore step pipes raw protobuf values through bash `echo`, corrupting binary bytes;
(b) the whitelist omits cluster-admin RBAC, SAs, and bootstrap tokens needed by kubeadm's pre-addon health check.

Merging this narrow fix + diagnosis trail; follow-up branch will replace the etcd-surgery approach with a kubectl-level Caddy secret backup/restore.
2026-04-17 13:48:30 +05:30
..
.gitignore fix: rename registry secret to image-pull-secret 2026-03-18 15:33:11 +00:00
config.json so-m3m: add credentials-files spec key for on-disk credential injection 2026-03-18 21:55:28 +00:00
events.jsonl so-o2o: detect etcd image dynamically + diagnose whitelist cleanup bugs (#745) 2026-04-17 13:48:30 +05:30