[#29] 整合metric模块端到端测试跑通；整合web/alert模块镜像构建

src/sys/tests/scripts/13_metric_verify_master.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+TMP_DIR="$TEST_ROOT/tmp/metric-verify"
+mkdir -p "$TMP_DIR"
+
+MASTER_BASE="http://localhost:32300/api/v1/master"
+HOSTNAME="${METRIC_TEST_HOSTNAME:-test-metric-node-001}"
+
+curl_json() { curl -fsS --max-time 5 "$1"; }
+
+echo "[VERIFY:MASTER] list nodes and locate target hostname=$HOSTNAME"
+ALL_NODES_JSON="$TMP_DIR/master_nodes.json"
+
+# 重试等待节点出现在 /nodes 列表（最多 120s）
+NODE_ID=""
+for attempt in {1..24}; do
+  curl_json "$MASTER_BASE/nodes" > "$ALL_NODES_JSON" || true
+  NODE_ID=$(python3 - "$ALL_NODES_JSON" "$HOSTNAME" <<'PY'
+import json,sys
+try:
+    nodes=json.load(open(sys.argv[1]))
+except Exception:
+    nodes=[]
+name=sys.argv[2]
+for n in nodes:
+    if n.get('name')==name:
+        print(n.get('id',''))
+        break
+PY
+  )
+  if [[ -n "$NODE_ID" ]]; then break; fi
+  echo "[..] waiting node to appear in /nodes ($attempt/24)"; sleep 5
+done
+
+if [[ -z "$NODE_ID" ]]; then
+  echo "[ERR] master /nodes 中未找到 $HOSTNAME（等待超时）" >&2
+  echo "[HINT] 当前 /nodes 列表如下:" >&2
+  sed -n '1,160p' "$ALL_NODES_JSON" >&2 || true
+  exit 1
+fi
+echo "[OK] node id=$NODE_ID"
+
+echo "[VERIFY:MASTER] get node detail and assert fields"
+DETAIL1_JSON="$TMP_DIR/master_node_${NODE_ID}_detail_1.json"
+curl_json "$MASTER_BASE/nodes/$NODE_ID" > "$DETAIL1_JSON"
+
+# 基础字段与健康项检查（不强制立即 online）
+python3 - "$DETAIL1_JSON" "$HOSTNAME" <<'PY'
+import json,sys,datetime
+j=json.load(open(sys.argv[1]))
+host=sys.argv[2]
+assert j.get('name')==host, f"name mismatch: {j.get('name')} != {host}"
+status=j.get('status')
+assert status in ('initialized','online','offline'), f"unexpected status: {status}"
+md=j.get('meta_data',{})
+assert md.get('hostname',j.get('name'))==host, 'meta_data.hostname mismatch'
+assert 'last_report' in j and j['last_report'], 'last_report missing'
+h=j.get('health',{})
+for key in ('metric-node-exporter','metric-fluent-bit','metric-argus-agent'):
+    if key in h:
+        assert h[key].get('status')=='healthy', f"{key} not healthy: {h[key]}"
+print('OK')
+PY
+
+# 轮询等待 last_report 前进并最终转为 online（最多 90s），容忍短暂 5xx/网络错误
+attempt=0
+T_PRE=0
+until [[ $attempt -ge 18 ]]; do
+  sleep 5
+  DETAIL_CUR="$TMP_DIR/master_node_${NODE_ID}_detail_cur.json"
+  if ! curl_json "$MASTER_BASE/nodes/$NODE_ID" > "$DETAIL_CUR" 2>/dev/null; then
+    echo "[..] retrying node detail fetch ($attempt/18)"; ((attempt++)); continue
+  fi
+  read -r STATUS_CUR T_CUR < <(python3 - "$DETAIL_CUR" <<'PY'
+import json,sys,datetime
+j=json.load(open(sys.argv[1]))
+st=j.get('status','')
+ts=j.get('last_report','')
+if ts.endswith('Z'): ts=ts.replace('Z','+00:00')
+try:
+    t=float(datetime.datetime.fromisoformat(ts).timestamp())
+except Exception:
+    t=0.0
+print(st)
+print(t)
+PY
+  )
+  if awk -v a="$T_PRE" -v b="$T_CUR" 'BEGIN{exit !(b>a)}'; then
+    T_PRE="$T_CUR"
+  fi
+  if [[ "$STATUS_CUR" == "online" ]]; then
+    echo "[OK] status online and last_report progressed"
+    break
+  fi
+  ((attempt++))
+done
+if (( attempt >= 18 )) && [[ "$STATUS_CUR" != "online" ]]; then
+  echo "[WARN] status did not reach online within timeout; continuing"
+fi
+
+echo "$NODE_ID" > "$TMP_DIR/node_id_metric"
+echo "[DONE] master verify"