.gitea/workflows/release.yml

@@ -115,7 +115,24 @@ jobs:
           POSTGRES_HOST=archiv-production-db-1
           EOF
 
+      - name: Validate observability compose config
+        # Dry-run: resolves all variable substitutions and reports any missing
+        # required keys before containers start. Catches undefined variables and
+        # YAML errors in config files updated by the previous step.
+        # Keep in sync with the equivalent step in nightly.yml.
+        run: |
+          docker compose \
+            -f /opt/familienarchiv/docker-compose.observability.yml \
+            --env-file /opt/familienarchiv/infra/observability/obs.env \
+            --env-file /opt/familienarchiv/obs-secrets.env \
+            config --quiet
+
       - name: Start observability stack
+        # Runs with absolute paths so bind mounts resolve to stable host paths
+        # that survive workspace wipes between runs (see ADR-016).
+        # Non-secret config from obs.env (git-tracked); secrets from obs-secrets.env
+        # (written fresh from Gitea secrets above).
+        # Keep in sync with the equivalent step in nightly.yml.
         run: |
           docker compose \
             -f /opt/familienarchiv/docker-compose.observability.yml \
@@ -123,6 +140,26 @@ jobs:
             --env-file /opt/familienarchiv/obs-secrets.env \
             up -d --wait --remove-orphans
 
+      - name: Assert observability stack health
+        # docker compose up --wait covers services WITH healthcheck directives only.
+        # obs-promtail, obs-cadvisor, obs-node-exporter, and obs-glitchtip-worker have
+        # no healthcheck — they are considered "started" as soon as the process runs.
+        # This step explicitly asserts the four healthchecked critical services are
+        # healthy before the smoke test proceeds.
+        # Keep in sync with the equivalent step in nightly.yml.
+        run: |
+          set -e
+          unhealthy=""
+          for svc in obs-loki obs-prometheus obs-grafana obs-tempo; do
+            status=$(docker inspect "$svc" --format '{{.State.Health.Status}}' 2>/dev/null || echo "missing")
+            if [ "$status" != "healthy" ]; then
+              echo "::error::$svc is not healthy (status: $status)"
+              unhealthy="$unhealthy $svc"
+            fi
+          done
+          [ -z "$unhealthy" ] || exit 1
+          echo "All critical observability services are healthy"
+
       - name: Reload Caddy
         # See nightly.yml — same rationale and mechanism: DooD job containers
         # cannot call systemctl directly; nsenter via a privileged sibling