Merge pull request 'fix(devops): harden staging deploy health check race' (#142) from fix/141-staging-healthcheck-retry into main

infra/staging/deploy_staging.sh

@@ -66,7 +66,31 @@ chown -R wpp:wpp "${APP_DIR}"
 runuser -u wpp -- test -w "${APP_DIR}"
 
 systemctl restart wpp-staging.service
-curl -fsS http://127.0.0.1:8000/healthz
+
+HEALTH_URL="http://127.0.0.1:8000/healthz"
+MAX_ATTEMPTS=7
+SLEEP_SECONDS=1
+ATTEMPT=1
+
+until curl -fsS "${HEALTH_URL}" >/dev/null; do
+  if [ "${ATTEMPT}" -ge "${MAX_ATTEMPTS}" ]; then
+    echo "[deploy] ERROR: health check failed after ${MAX_ATTEMPTS} attempts: ${HEALTH_URL}" >&2
+    echo "[deploy] service status (wpp-staging.service):" >&2
+    systemctl --no-pager --full status wpp-staging.service >&2 || true
+    echo "[deploy] recent service logs (wpp-staging.service):" >&2
+    journalctl --no-pager -u wpp-staging.service -n 80 >&2 || true
+    exit 1
+  fi
+
+  echo "[deploy] health check not ready (attempt ${ATTEMPT}/${MAX_ATTEMPTS}); retrying in ${SLEEP_SECONDS}s"
+  sleep "${SLEEP_SECONDS}"
+  ATTEMPT=$((ATTEMPT + 1))
+  if [ "${SLEEP_SECONDS}" -lt 8 ]; then
+    SLEEP_SECONDS=$((SLEEP_SECONDS * 2))
+  fi
+done
+
+echo "[deploy] health check passed: ${HEALTH_URL}"
 REMOTE
 
 echo "[deploy] OK: staging deploy complete for CT ${CT_ID} (${REF_NAME})"