infra-lead/molecule-core
1
0
Fork 0
forked from molecule-ai/molecule-core
Code Pull Requests Activity

Merge pull request #2650 from Molecule-AI/fix/sweep-stale-e2e-port-verify-pattern

Browse Source 
ci: port DELETE-verify pattern to remaining staging e2e workflows
This commit is contained in:
Hongming Wang 2026-05-03 23:32:42 +00:00 committed by GitHub
commit f6fa3669dc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 70 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
.github/workflows/e2e-staging-canvas.yml vendored
View File

@ -184,8 +184,23 @@ jobs:
exit 0
fi
echo "Deleting orphan tenant: $slug"
curl -sS -X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
# Verify HTTP 2xx instead of `>/dev/null || true` swallowing
# failures. A 5xx or timeout previously looked identical to
# success, leaving the tenant alive for up to ~45 min until
# sweep-stale-e2e-orgs caught it. Surface failures as
# workflow warnings naming the slug. Don't `exit 1` — a single
# cleanup miss shouldn't fail-flag the canvas test when the
# actual smoke check passed; the sweeper is the safety net.
# See molecule-controlplane#420.
code=$(curl -sS -o /tmp/canvas-cleanup.out -w "%{http_code}" \
-X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
-H "Authorization: Bearer $ADMIN_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"confirm\":\"$slug\"}" >/dev/null || true
-d "{\"confirm\":\"$slug\"}" \
|| echo "000")
if [ "$code" = "200" ] || [ "$code" = "204" ]; then
echo "[teardown] deleted $slug (HTTP $code)"
else
echo "::warning::canvas teardown for $slug returned HTTP $code — sweep-stale-e2e-orgs will catch it within ~45 min. Body: $(head -c 300 /tmp/canvas-cleanup.out 2>/dev/null)"
fi
exit 0

20
.github/workflows/e2e-staging-external.yml vendored
View File

@ -153,12 +153,28 @@ jobs:
if [ -n "$orgs" ]; then
echo "Safety-net sweep: deleting leftover orgs:"
echo "$orgs"
# Per-slug verified DELETE — see molecule-controlplane#420.
# `>/dev/null 2>&1` previously hid every failure; surface
# non-2xx as workflow warnings so the run page names what
# leaked. Sweeper catches the rest within ~45 min.
leaks=()
for slug in $orgs; do
curl -sS -X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
code=$(curl -sS -o /tmp/external-cleanup.out -w "%{http_code}" \
-X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
-H "Authorization: Bearer $ADMIN_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"confirm\":\"$slug\"}" >/dev/null 2>&1
-d "{\"confirm\":\"$slug\"}" \
|| echo "000")
if [ "$code" = "200" ] || [ "$code" = "204" ]; then
echo "[teardown] deleted $slug (HTTP $code)"
else
echo "::warning::external teardown for $slug returned HTTP $code — sweep-stale-e2e-orgs will catch it within ~45 min. Body: $(head -c 300 /tmp/external-cleanup.out 2>/dev/null)"
leaks+=("$slug")
fi
done
if [ ${#leaks[@]} -gt 0 ]; then
echo "::warning::external teardown left ${#leaks[@]} leak(s): ${leaks[*]}"
fi
else
echo "Safety-net sweep: no leftover orgs to clean."
fi

20
.github/workflows/e2e-staging-saas.yml vendored
View File

@ -164,11 +164,27 @@ jobs:
and o.get('instance_status') not in ('purged',)]
print('\n'.join(candidates))
" 2>/dev/null)
# Per-slug verified DELETE (was `>/dev/null || true` — see
# molecule-controlplane#420). Surface non-2xx as a workflow
# warning naming the leaked slug; don't exit 1 (sweeper is
# the safety net within ~45 min).
leaks=()
for slug in $orgs; do
echo "Safety-net teardown: $slug"
curl -sS -X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
code=$(curl -sS -o /tmp/saas-cleanup.out -w "%{http_code}" \
-X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
-H "Authorization: Bearer $ADMIN_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"confirm\":\"$slug\"}" >/dev/null || true
-d "{\"confirm\":\"$slug\"}" \
|| echo "000")
if [ "$code" = "200" ] || [ "$code" = "204" ]; then
echo "[teardown] deleted $slug (HTTP $code)"
else
echo "::warning::saas teardown for $slug returned HTTP $code — sweep-stale-e2e-orgs will catch it within ~45 min. Body: $(head -c 300 /tmp/saas-cleanup.out 2>/dev/null)"
leaks+=("$slug")
fi
done
if [ ${#leaks[@]} -gt 0 ]; then
echo "::warning::saas teardown left ${#leaks[@]} leak(s): ${leaks[*]}"
fi
exit 0

19
.github/workflows/e2e-staging-sanity.yml vendored
View File

@ -143,10 +143,25 @@ jobs:
and o.get('status') not in ('purged',)]
print('\n'.join(candidates))
" 2>/dev/null)
# Per-slug verified DELETE — see molecule-controlplane#420.
# Failures surface as workflow warnings; the sweeper is the
# safety net within ~45 min.
leaks=()
for slug in $orgs; do
curl -sS -X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
code=$(curl -sS -o /tmp/sanity-cleanup.out -w "%{http_code}" \
-X DELETE "$MOLECULE_CP_URL/cp/admin/tenants/$slug" \
-H "Authorization: Bearer $ADMIN_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"confirm\":\"$slug\"}" >/dev/null || true
-d "{\"confirm\":\"$slug\"}" \
|| echo "000")
if [ "$code" = "200" ] || [ "$code" = "204" ]; then
echo "[teardown] deleted $slug (HTTP $code)"
else
echo "::warning::sanity teardown for $slug returned HTTP $code — sweep-stale-e2e-orgs will catch it within ~45 min. Body: $(head -c 300 /tmp/sanity-cleanup.out 2>/dev/null)"
leaks+=("$slug")
fi
done
if [ ${#leaks[@]} -gt 0 ]; then
echo "::warning::sanity teardown left ${#leaks[@]} leak(s): ${leaks[*]}"
fi
exit 0