stack-orchestrator/stack_orchestrator/deploy/k8s
Prathamesh Musale 2f99e6f7c9 so-l2l: clean orphan PVs when namespace is already gone
down() used to early-return when read_namespace returned 404,
skipping all cleanup. That left cluster-scoped PVs orphaned
after a prior 'stop --delete-namespace' (namespace cascades
delete PVCs, but PVs with Retain reclaim policy survive).

Split _delete_labeled_resources into namespaced and cluster-
scoped phases via a namespace_present flag. When the namespace
is missing, jump straight to _delete_labeled_pvs (for
--delete-volumes) and the cluster-scoped half of the wait.
_wait_for_labeled_deletions now builds its lister set based on
whether the namespace still exists.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-16 06:08:32 +00:00
..
helm Fix pyright type errors across codebase 2026-01-22 01:10:36 -05:00
__init__.py Rename app -> stack_orchestrator (#625) 2023-11-07 00:06:55 -07:00
cluster_info.py so-l2l Part B: down() deletes by stack label, keeps namespace 2026-04-15 13:17:13 +00:00
deploy_k8s.py so-l2l: clean orphan PVs when namespace is already gone 2026-04-16 06:08:32 +00:00
helpers.py Fix Kind port mappings and configmap source path resolution (#742) 2026-04-14 17:33:47 +05:30
k8s_command.py Apply pre-commit linting fixes 2026-01-21 20:58:31 -05:00