Stop ci/site-test.sh leaking a MariaDB volume on every run

`mariadb:lts` declares VOLUME /var/lib/mysql, so every run creates an anonymous
volume — and `docker rm -f` does not remove anonymous volumes. Only
`docker rm -f -v` does.

What hid it: cleanup() removed the containers, the network and the NAMED $id-wp
volume correctly. Three of the four things the run creates. Removing three of
four is indistinguishable from removing all four unless you count, which is the
same shape as every other bug found in this kit today.

Found by the subscriptions session, which traced the Gitea runner's disk being
100% full — 26 GB in 95 volumes with 1 in use — and by woo-cache-manager from
the other end, whose push failed with `unable to create temporary object
directory`, three layers away from the cause. Measured here rather than taken
on report: a mariadb:lts container creates exactly one anonymous volume, it
survives `docker rm -f`, and it is removed by `docker rm -f -v`. This machine
was holding 133 volumes, 127 dangling, 15.2 GB reclaimable.

The fix is the -v. The rest is so it cannot come back silently:

cleanup() now asks the containers which volumes they own, via docker inspect,
BEFORE removing them, and checks afterwards that none survive. Attribution
rather than a global before/after count on purpose — several sessions share
this box and run these container pairs concurrently, so a neighbour's volume
would read as this run's leak.

The check is advisory on a run that already failed, and fatal on one that
otherwise passed: site_test_ok is set at the single point the run is known to
have succeeded. And it calls exit rather than return, because `return` from an
EXIT trap does not change the script's exit status — the warning would have
printed while the build went green, which is the failure mode this whole day
has been about.

Verified: the real site test now runs green with a volume delta of zero.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

ci/site-test.sh

@@ -27,10 +27,49 @@ PHP_VERSION="${PHP_VERSION:-8.3}"
 
 id="wpci-$$"
 net="$id-net"
+# 🔴 -v, and it is the whole bug. `mariadb:lts` declares VOLUME
+# /var/lib/mysql, so every run creates an ANONYMOUS volume, and `docker rm -f`
+# does not remove anonymous volumes — only `docker rm -f -v` does. The named
+# $id-wp below is removed correctly, which is exactly what made this function
+# look complete: removing three of the four things you created is
+# indistinguishable from removing all four unless you count.
+#
+# Measured 2026-09-17 after a sibling plugin traced it: the Gitea runner's disk
+# was 100% full, 26 GB in 95 volumes with 1 in use, and a push there failed
+# with `unable to create temporary object directory` — three layers from the
+# cause. This machine had 127 dangling volumes and 15.2 GB reclaimable.
 cleanup() {
-  docker rm -f "$id-db" "$id-cli" >/dev/null 2>&1 || true
+  # Ask the containers which volumes they own BEFORE removing them. A global
+  # before/after count would be wrong here: several sessions share this box and
+  # run these container pairs concurrently, so a neighbour's volume would read
+  # as this run's leak.
+  local owned=""
+  owned=$(docker inspect -f \
+    '{{range .Mounts}}{{if eq .Type "volume"}}{{.Name}} {{end}}{{end}}' \
+    "$id-db" "$id-cli" 2>/dev/null || true)
+
+  docker rm -f -v "$id-db" "$id-cli" >/dev/null 2>&1 || true
   docker volume rm -f "$id-wp" >/dev/null 2>&1 || true
   docker network rm "$net" >/dev/null 2>&1 || true
+
+  # Count rather than trust the flag. This is advisory on a failed run — a test
+  # that died halfway has more urgent news — but on a successful run a leftover
+  # volume is a real regression and says so.
+  local leaked=""
+  for v in $owned; do
+    docker volume inspect "$v" >/dev/null 2>&1 && leaked="$leaked $v"
+  done
+  if [ -n "$leaked" ]; then
+    echo "::warning::This run left docker volume(s) behind:$leaked — 95 of these filled the Gitea runner's disk."
+    # `return` from an EXIT trap does NOT change the script's exit status;
+    # only `exit` does. Without this the warning would print and the build
+    # would still go green, which is the failure mode of every other check
+    # this kit has had to fix tonight.
+    if [ "${site_test_ok:-0}" = 1 ]; then
+      ci_fail "The site test leaked the volume(s) above. Left alone this fills the runner's disk, and the symptom is a push failing with 'unable to create temporary object directory'."
+      exit 1
+    fi
+  fi
 }
 trap cleanup EXIT
 
@@ -144,5 +183,9 @@ else
   echo "  nothing logged at all"
 fi
 
+# Set only here, so the leak check above is advisory on a run that failed for
+# some other reason and fatal on one that otherwise passed.
+site_test_ok=1
+
 ci_step "done"
 echo "WordPress $(wp core version)$( [ "$NEEDS_WOOCOMMERCE" = yes ] && echo " + WooCommerce $(wp plugin get woocommerce --field=version)" ) on PHP $PHP_VERSION: green"