补齐集群状态、主机与通知链路基础监控 (#149)

Co-authored-by: panxiao81 <[email protected]>

platform/observability/metrics/tests/check-rules.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# 依赖 Python 3 + PyYAML，以及 PATH 中的 promtool（验证版本 3.5.0）。
+set -euo pipefail
+test_dir="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
+check_dir="$(mktemp -d)"
+trap 'rm -rf "$check_dir"' EXIT
+python3 - "$test_dir/../rules" "$check_dir/rules.yaml" <<'PY'
+import pathlib
+import sys
+import yaml
+
+groups = []
+for name in ("kubernetes-health", "host-health", "monitoring-delivery"):
+    path = pathlib.Path(sys.argv[1]) / f"{name}.yaml"
+    groups.extend(yaml.safe_load(path.read_text())["spec"]["groups"])
+pathlib.Path(sys.argv[2]).write_text(yaml.safe_dump({"groups": groups}, allow_unicode=True))
+PY
+cp "$test_dir/foundation.test.yaml" "$check_dir/foundation.test.yaml"
+promtool check rules "$check_dir/rules.yaml"
+promtool test rules "$check_dir/foundation.test.yaml"