GRM-167: fix: restrict healthcheck disk cleanup to exited/dead containers

ansible/roles/gitea_runner/molecule/template-content/verify.yml

@@ -112,6 +112,8 @@
           - "'docker network prune' in healthcheck_script.content | b64decode"
           - "'status=removing' in healthcheck_script.content | b64decode"
           - "'status=stopping' in healthcheck_script.content | b64decode"
+          - "'status=exited' in healthcheck_script.content | b64decode"
+          - "'status=dead' in healthcheck_script.content | b64decode"
           - "gitea_runner_healthcheck_disk_threshold | string in healthcheck_script.content | b64decode"
           - "gitea_runner_healthcheck_disk_critical | string in healthcheck_script.content | b64decode"
         fail_msg: "Healthcheck script template is missing expected content"

ansible/roles/gitea_runner/templates/runner-healthcheck.sh.j2

@@ -227,9 +227,12 @@ if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_critical }} ]]; then
     echo "CRITICAL: Disk usage at ${disk_pct}% (>= {{ gitea_runner_healthcheck_disk_critical }}%), full prune"
     # Critical level: remove ALL stopped containers (no age filter) and ALL
     # unused images/volumes. The until=1h gentle prune is insufficient here.
-    # Stop+rm stale non-CI containers regardless of age (failed molecule tests
-    # from the last 59 minutes also consume disk).
-    docker ps -a --format '{% raw %}{{.ID}} {{.Names}}{% endraw %}' 2>/dev/null \
+    # Implements: REQ-1 (GRM-167) — only exited/dead containers are removed.
+    # Running molecule instances are never killed: RunningFor counts creation
+    # time, so an adopted stale instance looks old; and a running container's
+    # writable layer is tiny — images/volumes are what actually fills the disk.
+    docker ps -a --filter "status=exited" --filter "status=dead" \
+        --format '{% raw %}{{.ID}} {{.Names}}{% endraw %}' 2>/dev/null \
         | grep -v 'GITEA-ACTIONS-TASK' \
         | awk '{print $1}' \
         | xargs -r docker rm -f 2>/dev/null || true
@@ -240,13 +243,16 @@ if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_critical }} ]]; then
     echo "INFO: Disk usage after full prune: ${disk_pct}%"
 elif [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
     echo "WARN: Disk usage at ${disk_pct}%, pruning runner resources (until=1h)"
-    # Force-remove stale containers (including running ones from failed molecule tests)
-    # that are older than 1 hour. "docker container prune -f" only removes stopped
-    # containers, so running containers from crashed CI jobs accumulate and consume
-    # disk/memory. Exclude CI job containers (name starts with GITEA-ACTIONS-TASK).
-    # Only remove containers older than 1 hour to avoid killing molecule test
-    # containers that CI jobs are actively using.
-    docker ps -a --format '{% raw %}{{.ID}} {{.Names}} {{.RunningFor}}{% endraw %}' 2>/dev/null \
+    # Force-remove stale stopped containers older than 1 hour.
+    # Implements: REQ-1 (GRM-167) — only exited/dead containers are removed.
+    # A running molecule instance must never be janitor-killed: RunningFor
+    # measures creation time, so a stale instance restarted by an active run
+    # looks ">1h old" and would die mid-converge ("No such container",
+    # infra nightly run 5710). Running leftovers are reused or destroyed by
+    # the next molecule create/destroy cycle.
+    # Exclude CI job containers (name starts with GITEA-ACTIONS-TASK).
+    docker ps -a --filter "status=exited" --filter "status=dead" \
+        --format '{% raw %}{{.ID}} {{.Names}} {{.RunningFor}}{% endraw %}' 2>/dev/null \
         | grep -v 'GITEA-ACTIONS-TASK' \
         | grep -E '(hour|day|week|month|year)s? ago' \
         | awk '{print $1}' \