modify playwright

测试方案：

- lm2机器端口映射到本机：18080, 18081, 8082-8085
- 访问URL: http://localhost:18080/dashboard

![image.png](/attachments/30ed6e20-697a-4d3b-a6d3-6acccd2e9922)

![image.png](/attachments/38ef1751-0f3b-49c6-9100-f70d15617acc)

![image.png](/attachments/3be45005-9b9e-4165-8ef6-1d27405800f1)

![image.png](/attachments/eb916192-edc1-4096-8f9f-9769ab6d9039)

![image.png](/attachments/620e6efc-bd02-45ae-bba1-99a95a1b4c02)

![image.png](/attachments/986e77e7-c687-405f-a760-93282249f72f)

端到端测试通过：

![image.png](/attachments/c6e29875-4a16-4718-8b2f-368f64eb545e)

Co-authored-by: sundapeng.sdp <sundapeng@hashdata.cn>
Reviewed-on: #35
Reviewed-by: xuxt <xuxt@zgclab.edu.cn>
Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>
Reviewed-by: huhy <husteryezi@163.com>

build/build_images.sh

@@ -12,7 +12,7 @@ Options:
   --master-offline  Build master offline image (requires src/master/offline_wheels.tar.gz)
   --metric          Build metric module images (ftp, prometheus, grafana, test nodes)
   --no-cache        Build all images without using Docker layer cache
-  --only LIST       Comma-separated targets to build: core,master,metric,web,alert,all
+  --only LIST       Comma-separated targets to build: core,master,metric,web,alert,sys,all
   -h, --help        Show this help message
 
 Examples:
@@ -31,6 +31,7 @@ build_master_offline=false
 build_metric=true
 build_web=true
 build_alert=true
+build_sys=true
 no_cache=false
 
 while [[ $# -gt 0 ]]; do
@@ -62,7 +63,7 @@ while [[ $# -gt 0 ]]; do
       fi
       sel="$2"; shift 2
       # reset all, then enable selected
-      build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false
+      build_core=false; build_master=false; build_metric=false; build_web=false; build_alert=false; build_sys=false
       IFS=',' read -ra parts <<< "$sel"
       for p in "${parts[@]}"; do
         case "$p" in
@@ -71,7 +72,8 @@ while [[ $# -gt 0 ]]; do
           metric) build_metric=true ;;
           web) build_web=true ;;
           alert) build_alert=true ;;
-          all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true ;;
+          sys) build_sys=true ;;
+          all) build_core=true; build_master=true; build_metric=true; build_web=true; build_alert=true; build_sys=true ;;
           *) echo "Unknown --only target: $p" >&2; exit 1 ;;
         esac
       done
@@ -286,6 +288,42 @@ if [[ "$build_metric" == true ]]; then
   done
 fi
 
+# =======================================
+# Sys (system tests) node images
+# =======================================
+
+if [[ "$build_sys" == true ]]; then
+  echo ""
+  echo "Building Sys node images..."
+
+  sys_base_images=(
+    "ubuntu:22.04"
+    "nvidia/cuda:12.2.2-runtime-ubuntu22.04"
+  )
+
+  for base_image in "${sys_base_images[@]}"; do
+    if ! pull_base_image "$base_image"; then
+      build_failed=true
+    fi
+  done
+
+  sys_builds=(
+    "Sys Node|src/sys/build/node/Dockerfile|argus-sys-node:latest|."
+    "Sys Metric Test Node|src/sys/build/test-node/Dockerfile|argus-sys-metric-test-node:latest|."
+    "Sys Metric Test GPU Node|src/sys/build/test-gpu-node/Dockerfile|argus-sys-metric-test-gpu-node:latest|."
+  )
+
+  for build_spec in "${sys_builds[@]}"; do
+    IFS='|' read -r image_label dockerfile_path image_tag build_context <<< "$build_spec"
+    if build_image "$image_label" "$dockerfile_path" "$image_tag" "$build_context"; then
+      images_built+=("$image_tag")
+    else
+      build_failed=true
+    fi
+    echo ""
+  done
+fi
+
 # =======================================
 # Web & Alert module images
 # =======================================

src/alert/tests/.env.example

@@ -1,5 +1,5 @@
 DATA_ROOT=/home/argus/tmp/private/argus
-ARGUS_UID=1048
+ARGUS_BUILD_UID=1048
-ARGUS_GID=1048
+ARGUS_BUILD_GID=1048
 
-USE_INTRANET=false
+USE_INTRANET=false

src/alert/tests/data/alertmanager/alertmanager.yml

@@ -1,19 +0,0 @@
-global:
-  resolve_timeout: 5m
-
-route:
-  group_by: ['alertname', 'instance']   # 分组：相同 alertname + instance 的告警合并
-  group_wait: 30s        # 第一个告警后，等 30s 看是否有同组告警一起发
-  group_interval: 5m     # 同组告警变化后，至少 5 分钟再发一次
-  repeat_interval: 3h    # 相同告警，3 小时重复提醒一次
-  receiver: 'null'
-
-receivers:
-  - name: 'null'
-
-inhibit_rules:
-  - source_match:
-      severity: 'critical'     # critical 告警存在时
-    target_match:
-      severity: 'warning'      # 抑制相同 instance 的 warning 告警
-    equal: ['instance']

src/alert/tests/data/etc/alertmanager.alert.argus.com

@@ -1 +0,0 @@
-172.18.0.2

src/alert/tests/scripts/01_bootstrap.sh

@@ -1,19 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
-project_root="$(cd "$root/../../.." && pwd)"
-
-source "$project_root/scripts/common/build_user.sh"
-load_build_user
-
-# 创建新的private目录结构 (基于argus目录结构)
-echo "[INFO] Creating private directory structure for supervisor-based containers..."
-mkdir -p "$root/private/argus/alert/alertmanager"
-mkdir -p "$root/private/argus/etc/"
-
-# 设置数据目录权限
-echo "[INFO] Setting permissions for data directories..."
-chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/alert/alertmanager" 2>/dev/null || true
-chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
-
-echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"

src/alert/tests/scripts/02_up.sh

@@ -1,10 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-cd "$(dirname "$0")/.."
-compose_cmd="docker compose"
-if ! $compose_cmd version >/dev/null 2>&1; then
-  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
-    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
-fi
-$compose_cmd -p alert-mvp up -d --remove-orphans
-echo "[OK] 服务已启动：Alertmanager http://localhost:9093"

src/alert/tests/scripts/03_alertmanager_add_alert.sh

@@ -1,106 +0,0 @@
-#!/bin/bash
-set -euo pipefail
-
-# ==========================================================
-# Alertmanager 测试脚本
-# ==========================================================
-
-ALERTMANAGER_URL="http://localhost:9093"
-TEST_ALERT_NAME_CRITICAL="NodeDown"
-TEST_ALERT_NAME_WARNING="HighCPU"
-TMP_LOG="/tmp/test-alertmanager.log"
-
-# 等待参数
-am_wait_attempts=30
-am_wait_interval=2
-
-GREEN="\033[1;32m"
-RED="\033[1;31m"
-YELLOW="\033[1;33m"
-RESET="\033[0m"
-
-# ==========================================================
-# 函数定义
-# ==========================================================
-
-wait_for_alertmanager() {
-  local attempt=1
-  echo "[INFO] 等待 Alertmanager 启动中..."
-  while (( attempt <= am_wait_attempts )); do
-    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
-      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
-      return 0
-    fi
-    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
-    sleep "${am_wait_interval}"
-    (( attempt++ ))
-  done
-  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
-  return 1
-}
-
-log_step() {
-  echo -e "${YELLOW}==== $1 ====${RESET}"
-}
-
-# ==========================================================
-# 主流程
-# ==========================================================
-
-log_step "测试 Alertmanager 开始"
-echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
-
-# Step 1: 等待 Alertmanager 启动
-wait_for_alertmanager
-
-# Step 2: 触发一个critical测试告警
-echo "[INFO] 发送critical测试告警..."
-curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
-  -H "Content-Type: application/json" \
-  -d '[
-    {
-      "labels": {
-        "alertname": "'"${TEST_ALERT_NAME_CRITICAL}"'",
-        "instance": "node-1",
-        "severity": "critical"
-      },
-      "annotations": {
-        "summary": "节点 node-1 宕机"
-      }
-    }
-  ]' \
-  -o "$TMP_LOG"
-
-if [ $? -eq 0 ]; then
-  echo -e "${GREEN}[OK] 已成功发送critical测试告警${RESET}"
-else
-  echo -e "${RED}[ERROR] critical告警发送失败！${RESET}"
-  cat "$TMP_LOG"
-  exit 1
-fi
-
-# Step 3: 触发一个warning测试告警
-echo "[INFO] 发送warning测试告警..."
-curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
-  -H "Content-Type: application/json" \
-  -d '[
-    {
-      "labels": {
-        "alertname": "'"${TEST_ALERT_NAME_WARNING}"'",
-        "instance": "node-1",
-        "severity": "warning"
-      },
-      "annotations": {
-        "summary": "节点 node-1 CPU 使用率过高"
-      }
-    }
-  ]' \
-  -o "$TMP_LOG"
-
-if [ $? -eq 0 ]; then
-  echo -e "${GREEN}[OK] 已成功发送warning测试告警${RESET}"
-else
-  echo -e "${RED}[ERROR] warning告警发送失败！${RESET}"
-  cat "$TMP_LOG"
-  exit 1
-fi

src/alert/tests/scripts/04_query_alerts.sh

@@ -1,71 +0,0 @@
-#!/bin/bash
-set -euo pipefail
-
-# ==========================================================
-# Alertmanager 测试脚本（含启动等待）
-# ==========================================================
-
-ALERTMANAGER_URL="http://localhost:9093"
-TEST_ALERT_NAME_CRITICAL="NodeDown"
-TEST_ALERT_NAME_WARNING="HighCPU"
-TMP_LOG="/tmp/test-alertmanager.log"
-
-# 等待参数
-am_wait_attempts=30
-am_wait_interval=2
-
-GREEN="\033[1;32m"
-RED="\033[1;31m"
-YELLOW="\033[1;33m"
-RESET="\033[0m"
-
-# ==========================================================
-# 函数定义
-# ==========================================================
-
-wait_for_alertmanager() {
-  local attempt=1
-  echo "[INFO] 等待 Alertmanager 启动中..."
-  while (( attempt <= am_wait_attempts )); do
-    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
-      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
-      return 0
-    fi
-    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
-    sleep "${am_wait_interval}"
-    (( attempt++ ))
-  done
-  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
-  return 1
-}
-
-log_step() {
-  echo -e "${YELLOW}==== $1 ====${RESET}"
-}
-
-# ==========================================================
-# 主流程
-# ==========================================================
-
-log_step "查询 Alertmanager 当前告警列表开始"
-echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
-
-# Step 1: 等待 Alertmanager 启动
-wait_for_alertmanager
-
-# Step 2: 查询当前告警列表
-echo "[INFO] 查询当前告警..."
-sleep 1
-curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | jq '.' || {
-  echo -e "${RED}[WARN] 无法解析返回 JSON，请检查 jq 是否安装${RESET}"
-  curl -s "${ALERTMANAGER_URL}/api/v2/alerts"
-}
-
-# Step 3: 检查告警是否包含 NodeDown
-if curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | grep -q "${TEST_ALERT_NAME_CRITICAL}"; then
-  echo -e "${GREEN}✅ 测试通过：Alertmanager 已成功接收告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
-else
-  echo -e "${RED}❌ 测试失败：未检测到告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
-fi
-
-log_step "测试结束"

src/alert/tests/scripts/05_down.sh

@@ -1,21 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-cd "$(dirname "$0")/.."
-compose_cmd="docker compose"
-if ! $compose_cmd version >/dev/null 2>&1; then
-  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
-    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
-fi
-$compose_cmd -p alert-mvp down
-echo "[OK] 已停止所有容器"
-
-# 清理private目录内容
-echo "[INFO] 清理private目录内容..."
-cd "$(dirname "$0")/.."
-if [ -d "private" ]; then
-    # 删除private目录及其所有内容
-    rm -rf private
-    echo "[OK] 已清理private目录"
-else
-    echo "[INFO] private目录不存在，无需清理"
-fi

src/alert/tests/scripts/e2e_test.sh

@@ -1,105 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-echo "======================================="
-echo "ARGUS Alert System End-to-End Test"
-echo "======================================="
-echo ""
-
-# 记录测试开始时间
-test_start_time=$(date +%s)
-
-# 函数：等待服务就绪
-wait_for_services() {
-    echo "[INFO] Waiting for all services to be ready..."
-    local max_attempts=${SERVICE_WAIT_ATTEMPTS:-120}
-    local attempt=1
-
-    while [ $attempt -le $max_attempts ]; do
-        if curl -fs http://localhost:9093/api/v2/status >/dev/null 2>&1; then
-            echo "[OK] All services are ready!"
-            return 0
-        fi
-        echo "    Waiting for services... ($attempt/$max_attempts)"
-        sleep 5
-        ((attempt++))
-    done
-
-    echo "[ERROR] Services not ready after $max_attempts attempts"
-    return 1
-}
-
-# 函数：显示测试步骤
-show_step() {
-    echo ""
-    echo "🔄 Step $1: $2"
-    echo "----------------------------------------"
-}
-
-# 函数：验证步骤结果
-verify_step() {
-    if [ $? -eq 0 ]; then
-        echo "✅ $1 - SUCCESS"
-    else
-        echo "❌ $1 - FAILED"
-        exit 1
-    fi
-}
-
-# 开始端到端测试
-show_step "1" "Bootstrap - Initialize environment"
-./scripts/01_bootstrap.sh
-verify_step "Bootstrap"
-
-show_step "2" "Startup - Start all services"
-./scripts/02_up.sh
-verify_step "Service startup"
-
-# 等待服务完全就绪
-wait_for_services || exit 1
-
-# 发送告警数据
-show_step "3" "Add alerts - Send test alerts to Alertmanager"
-./scripts/03_alertmanager_add_alert.sh
-verify_step "Send test alerts"
-
-# 查询告警数据
-show_step "4" "Verify data - Query Alertmanager"
-./scripts/04_query_alerts.sh
-verify_step "Data verification"
-
-
-# 检查服务健康状态
-show_step "Health" "Check service health"
-echo "[INFO] Checking service health..."
-
-# 检查 Alertmanager 状态
-if curl -fs "http://localhost:9093/api/v2/status" >/dev/null 2>&1; then
-    am_status="available"
-    echo "✅ Alertmanager status: $am_status"
-else
-    am_status="unavailable"
-    echo "⚠️  Alertmanager status: $am_status"
-fi
-verify_step "Service health check"
-
-# 清理环境
-show_step "5" "Cleanup - Stop all services"
-./scripts/05_down.sh
-verify_step "Service cleanup"
-
-# 计算总测试时间
-test_end_time=$(date +%s)
-total_time=$((test_end_time - test_start_time))
-
-echo ""
-echo "======================================="
-echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
-echo "======================================="
-echo "📊 Test Summary:"
-echo "   • Total time: ${total_time}s"
-echo "   • Alertmanager status: $am_status"
-echo "   • All services started and stopped successfully"
-echo ""
-echo "✅ The ARGUS Alert system is working correctly!"
-echo ""

src/alert/tests/scripts/verify_alertmanager.sh

@@ -0,0 +1,113 @@
+#!/bin/bash
+# verify_alertmanager.sh
+# 用于部署后验证 Prometheus 与 Alertmanager 通信链路是否正常
+
+set -euo pipefail
+
+#=============================
+# 基础配置
+#=============================
+PROM_URL="${PROM_URL:-http://prom.metric.argus.com:9090}"
+ALERT_URL="${ALERT_URL:-http://alertmanager.alert.argus.com:9093}"
+# TODO: 根据实际部署环境调整规则目录
+DATA_ROOT="${DATA_ROOT:-/private/argus}"
+RULE_DIR = "$DATA_ROOT/metric/prometheus/rules"
+TMP_RULE="/tmp/test_rule.yml"
+
+#=============================
+# 辅助函数
+#=============================
+GREEN="\033[32m"; RED="\033[31m"; YELLOW="\033[33m"; RESET="\033[0m"
+
+log_info()    { echo -e "${YELLOW}[INFO]${RESET} $1"; }
+log_success() { echo -e "${GREEN}[OK]${RESET} $1"; }
+log_error()   { echo -e "${RED}[ERROR]${RESET} $1"; }
+
+fail_exit() { log_error "$1"; exit 1; }
+
+#=============================
+# Step 1: 检查 Alertmanager 是否可访问
+#=============================
+log_info "检查 Alertmanager 状态..."
+if curl -sSf "${ALERT_URL}/api/v2/status" >/dev/null 2>&1; then
+  log_success "Alertmanager 服务正常 (${ALERT_URL})"
+else
+  fail_exit "无法访问 Alertmanager，请检查端口映射与容器状态。"
+fi
+
+#=============================
+# Step 2: 手动发送测试告警
+#=============================
+log_info "发送手动测试告警..."
+curl -s -XPOST "${ALERT_URL}/api/v2/alerts" -H "Content-Type: application/json" -d '[
+  {
+    "labels": {
+      "alertname": "ManualTestAlert",
+      "severity": "info"
+    },
+    "annotations": {
+      "summary": "This is a test alert from deploy verification"
+    },
+    "startsAt": "'$(date -Iseconds)'"
+  }
+]' >/dev/null && log_success "测试告警已成功发送到 Alertmanager"
+
+#=============================
+# Step 3: 检查 Prometheus 配置中是否包含 Alertmanager
+#=============================
+log_info "检查 Prometheus 是否配置了 Alertmanager..."
+if curl -s "${PROM_URL}/api/v1/status/config" | grep -q "alertmanagers"; then
+  log_success "Prometheus 已配置 Alertmanager 目标"
+else
+  fail_exit "Prometheus 未配置 Alertmanager，请检查 prometheus.yml"
+fi
+
+#=============================
+# Step 4: 创建并加载测试告警规则
+#=============================
+log_info "创建临时测试规则 ${TMP_RULE} ..."
+cat <<EOF > "${TMP_RULE}"
+groups:
+- name: deploy-verify-group
+  rules:
+  - alert: DeployVerifyAlert
+    expr: vector(1)
+    labels:
+      severity: warning
+    annotations:
+      summary: "Deployment verification alert"
+EOF
+
+mkdir -p "${RULE_DIR}"
+cp "${TMP_RULE}" "${RULE_DIR}/test_rule.yml"
+
+log_info "重载 Prometheus 以加载新规则..."
+if curl -s -X POST "${PROM_URL}/-/reload" >/dev/null; then
+  log_success "Prometheus 已重载规则"
+else
+  fail_exit "Prometheus reload 失败，请检查 API 可访问性。"
+fi
+
+#=============================
+# Step 5: 等待并验证 Alertmanager 是否收到告警
+#=============================
+log_info "等待告警触发 (约5秒)..."
+sleep 5
+
+if curl -s "${ALERT_URL}/api/v2/alerts" | grep -q "DeployVerifyAlert"; then
+  log_success "Prometheus → Alertmanager 告警链路验证成功"
+else
+  fail_exit "未在 Alertmanager 中检测到 DeployVerifyAlert，请检查网络或配置。"
+fi
+
+#=============================
+# Step 6: 清理测试规则
+#=============================
+log_info "清理临时测试规则..."
+rm -f "${RULE_DIR}/test_rule.yml" "${TMP_RULE}"
+
+curl -s -X POST "${PROM_URL}/-/reload" >/dev/null \
+  && log_success "Prometheus 已清理验证规则" \
+  || log_error "Prometheus reload 清理失败，请手动确认。"
+
+log_success "部署验证全部通过！Prometheus ↔ Alertmanager 通信正常。"

src/metric/client-plugins/all-in-one-full/config/VERSION

@@ -1 +1 @@
-1.33.0
+1.35.0

src/metric/grafana/build/dashboards/default_dashboard_by_hostname.json

@@ -581,6 +581,372 @@
       ],
       "title": "Node Process Count",
       "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "GPU Utilization (%)",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 80
+              },
+              {
+                "color": "red",
+                "value": 95
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "id": 301,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_GPU_UTIL{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 利用率 (单卡)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Memory Used (%)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "orange",
+                "value": 80
+              },
+              {
+                "color": "red",
+                "value": 95
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "id": 403,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "round(DCGM_FI_DEV_FB_USED{hostname=~\"$hostname\"} / (DCGM_FI_DEV_FB_USED{hostname=~\"$hostname\"} + DCGM_FI_DEV_FB_FREE{hostname=~\"$hostname\"}) * 100)",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 显存使用率 (单卡)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Temperature (℃)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 75
+              },
+              {
+                "color": "red",
+                "value": 85
+              }
+            ]
+          },
+          "unit": "celsius"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "id": 501,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_GPU_TEMP{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 温度（单卡）",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": true,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Power (W)",
+            "axisPlacement": "left",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "max": 300,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 200
+              },
+              {
+                "color": "red",
+                "value": 300
+              }
+            ]
+          },
+          "unit": "watt"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 32
+      },
+      "id": 502,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "DCGM_FI_DEV_POWER_USAGE{hostname=~\"$hostname\"}",
+          "legendFormat": "{{hostname}} GPU{{gpu}}",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 功率 (单卡)",
+      "type": "timeseries"
     }
   ],
   "refresh": "15s",
@@ -589,11 +955,6 @@
   "templating": {
     "list": [
       {
-        "current": {
-          "selected": true,
-          "text": "node-exporter-A1",
-          "value": "node-exporter-A1"
-        },
         "datasource": {
           "type": "prometheus"
         },
@@ -623,7 +984,7 @@
   },
   "timepicker": {},
   "timezone": "",
-  "title": "Node and GPU Metrics",
+  "title": "Node and GPU Metrics (by hostname)",
-  "uid": "node_gpu_metrics",
+  "uid": "node_gpu_metrics_by_hostname",
   "weekStart": ""
-}
+}

src/metric/grafana/build/dashboards/default_dashboard_by_instance.json

@@ -622,7 +622,7 @@
     },
     "timepicker": {},
     "timezone": "",
-    "title": "Node and GPU Metrics",
+    "title": "Node and GPU Metrics (by instance)",
-    "uid": "node_gpu_metrics",
+    "uid": "node_gpu_metrics_by_instance",
     "weekStart": ""
-  }
+  }

src/sys/build/node/Dockerfile

@@ -0,0 +1,36 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional: switch to intranet apt mirrors during build
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+      echo "Configuring intranet apt sources..." && \
+      cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+      echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+      echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+      echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Install base tools and all libs that Fluent Bit may require at runtime
+# so that start-fluent-bit.sh will NOT fallback to apt during container start.
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      ca-certificates tzdata \
+      procps iproute2 net-tools lsof \
+      libpq5 libyaml-0-2 libsasl2-2 libldap-2.5-0; \
+    rm -rf /var/lib/apt/lists/*
+
+# Keep root; compose provides entrypoint via bind mount
+USER root
+
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/build/test-gpu-node/Dockerfile

@@ -0,0 +1,34 @@
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai \
+    NVIDIA_VISIBLE_DEVICES=all \
+    NVIDIA_DRIVER_CAPABILITIES=compute,utility
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional intranet mirror for build-time apt
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+      echo "Configuring intranet apt sources..." && \
+      cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+      echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+      echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+      echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Pre-install curl and diagnostics to avoid runtime apt installs in GPU test node
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      curl ca-certificates tzdata \
+      procps iproute2 net-tools lsof; \
+    rm -rf /var/lib/apt/lists/*
+
+USER root
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/build/test-node/Dockerfile

@@ -0,0 +1,32 @@
+FROM ubuntu:22.04
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Asia/Shanghai
+
+ARG USE_INTRANET=false
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# Optional intranet mirror for build-time apt
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+      echo "Configuring intranet apt sources..." && \
+      cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+      echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+      echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+      echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Pre-install curl and common diagnostics to avoid runtime apt installs
+RUN set -eux; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+      curl ca-certificates tzdata \
+      procps iproute2 net-tools lsof; \
+    rm -rf /var/lib/apt/lists/*
+
+USER root
+CMD ["bash", "-lc", "sleep infinity"]
+

src/sys/tests/README.md

@@ -47,6 +47,8 @@
   - `./scripts/11_metric_node_install.sh` 在 CPU 节点安装并验证端点
   - `./scripts/12_metric_gpu_install.sh` 在 GPU 节点安装并等待 9100/9400 就绪（仅启用 GPU 时）
   - `./scripts/13_metric_verify.sh` 对 master/Prometheus/数据面/Grafana 做综合校验（含 GPU 时校验 dcgm 指标）
+  - `./scripts/15_alert_verify.sh` 对alertmanager进行校验
+  - `./scripts/16_web_verify.sh` 对web页面进行校验综合校验。
   - `./scripts/14_metric_cleanup.sh` 清理 FTP 产物
   - `./scripts/09_down.sh` 回收容器、网络并清理 `private*/`、`tmp/`
 
@@ -133,6 +135,13 @@
 - `09_down.sh`
   - 目的：栈销毁与环境清理；必要时使用临时容器修正属主再删除 `private*` 目录
 
+- `15_alert_verify.sh`
+  - 目的：验证alertmanager的可用性、Prometheus到alertmanager的连通性。
+  - 操作：在Prometheus中增加一个恒为真的告警规则，查看alertmanager是否收到该告警
+- `16_web_verify.sh`
+  - 目的：验证web页面是否可用。
+  - 使用playwright分别验证各个模块的页面是否可用，以及符合预期。
+
 ---
 
 ### 常见问题与排查

src/sys/tests/docker-compose.yml

@@ -78,7 +78,7 @@ services:
         ipv4_address: 172.31.0.4
 
   node-a:
-    image: ubuntu:22.04
+    image: argus-sys-node:latest
     container_name: argus-node-a
     hostname: dev-yyrshare-nbnyx10-cp2f-pod-0
     depends_on:
@@ -113,7 +113,7 @@ services:
       - sysnet
 
   node-b:
-    image: ubuntu:22.04
+    image: argus-sys-node:latest
     container_name: argus-node-b
     hostname: dev-yyrshare-uuuu10-ep2f-pod-0
     depends_on:
@@ -260,7 +260,7 @@ services:
         max-file: "3"
 
   test-node:
-    image: ubuntu:22.04
+    image: argus-sys-metric-test-node:latest
     container_name: argus-metric-test-node
     hostname: test-metric-node-001
     restart: unless-stopped
@@ -303,7 +303,7 @@ services:
 
   test-gpu-node:
     profiles: ["gpu"]
-    image: nvidia/cuda:12.2.2-runtime-ubuntu22.04
+    image: argus-sys-metric-test-gpu-node:latest
     container_name: argus-metric-test-gpu-node
     hostname: test-metric-gpu-node-001
     restart: unless-stopped

src/sys/tests/scripts/00_e2e_test.sh

@@ -4,6 +4,7 @@ set -euo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
 ENABLE_GPU=false
+CLEANUP=true
 
 usage() {
   cat <<'EOF'
@@ -11,6 +12,7 @@ Usage: 00_e2e_test.sh [options]
 
 Options:
   --enable-gpu   启用 GPU 相关拓扑与测试流程
+  --no-clean     跳过清理流程（不执行 14 和 09）
   -h, --help     显示帮助信息
 EOF
 }
@@ -21,6 +23,10 @@ while [[ $# -gt 0 ]]; do
       ENABLE_GPU=true
       shift
       ;;
+    --no-clean)
+      CLEANUP=false
+      shift
+      ;;
     -h|--help)
       usage
       exit 0
@@ -35,6 +41,7 @@ done
 
 export ARGUS_SYS_ENABLE_GPU=$ENABLE_GPU
 
+# 基础步骤（不包含清理与下线）
 SCRIPTS=(
   "01_bootstrap.sh"
   "02_up.sh"
@@ -48,10 +55,18 @@ SCRIPTS=(
   "11_metric_node_install.sh"
   "12_metric_gpu_install.sh"
   "13_metric_verify.sh"
-  "14_metric_cleanup.sh"
+  "15_alert_verify.sh"
-  "09_down.sh"
+  "16_web_verify.sh"
 )
 
+# 如未禁用清理，则追加清理与下线步骤（保持原有顺序）
+if [[ "$CLEANUP" == "true" ]]; then
+  SCRIPTS+=(
+    "14_metric_cleanup.sh"
+    "09_down.sh"
+  )
+fi
+
 for script in "${SCRIPTS[@]}"; do
   echo "[SYS-E2E] Running $script"
   "$SCRIPT_DIR/$script"
@@ -59,4 +74,8 @@ for script in "${SCRIPTS[@]}"; do
   echo
 done
 
-echo "[SYS-E2E] All tests completed"
+if [[ "$CLEANUP" == "true" ]]; then
+  echo "[SYS-E2E] All tests completed"
+else
+  echo "[SYS-E2E] All tests completed (cleanup skipped)"
+fi

src/sys/tests/scripts/10_metric_publish.sh

@@ -43,6 +43,29 @@ fi
 
 pushd "$PLUGIN_DIR" >/dev/null
 
+# --- Inject agent binary built in 01_bootstrap (if present) ---
+AGENT_PATH_FILE="$TEST_ROOT/tmp/agent_binary_path"
+AGENT_BIN_CANDIDATE="$REPO_ROOT/src/agent/dist/argus-agent"
+if [[ -f "$AGENT_PATH_FILE" ]]; then
+  AGENT_BIN="$(tr -d '\n' < "$AGENT_PATH_FILE")"
+else
+  AGENT_BIN="$AGENT_BIN_CANDIDATE"
+fi
+
+if [[ -x "$AGENT_BIN" ]]; then
+  echo "[SYS-METRIC] 使用 01 阶段构建的 agent: $AGENT_BIN"
+  TARGET_BIN="plugins/argus-agent/bin/argus-agent"
+  if [[ -f "$TARGET_BIN" ]]; then
+    cp -f "$AGENT_BIN" "$TARGET_BIN"
+  else
+    mkdir -p "$(dirname "$TARGET_BIN")"
+    cp "$AGENT_BIN" "$TARGET_BIN"
+  fi
+  chmod +x "$TARGET_BIN"
+else
+  echo "[SYS-METRIC] 未找到可执行的 agent 二进制（预期: $AGENT_BIN），继续使用插件目录内置版本"
+fi
+
 echo "[SYS-METRIC] Bumping metric artifact version..."
 bash scripts/version-manager.sh bump minor
 

src/sys/tests/scripts/15_alert_verify.sh

@@ -0,0 +1,103 @@
+#!/bin/bash
+# verify_alertmanager.sh
+# Verify the communication between Prometheus and Alertmanager after deployment
+
+set -euo pipefail
+
+echo "[INFO] Verifying Prometheus ↔ Alertmanager communication..."
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+TMP_DIR="$TEST_ROOT/tmp"
+mkdir -p "$TMP_DIR"
+
+PRIVATE_CORE="$TEST_ROOT/private"
+
+#=============================
+# Load environment variables
+#=============================
+if [[ -f "$TEST_ROOT/.env" ]]; then
+  set -a; source "$TEST_ROOT/.env"; set +a
+fi
+
+#=============================
+# Basic configuration
+#=============================
+PROM_URL="http://localhost:${PROMETHEUS_PORT:-9090}"
+ALERT_URL="http://localhost:${ALERTMANAGER_PORT:-9093}"
+RULE_DIR="$PRIVATE_CORE/argus/metric/prometheus/rules"
+TMP_RULE="$TMP_DIR/test_rule.yml"
+
+#=============================
+# Helper functions
+#=============================
+GREEN="\033[32m"; RED="\033[31m"; YELLOW="\033[33m"; RESET="\033[0m"
+
+log_info()    { echo -e "${YELLOW}[INFO]${RESET} $1"; }
+log_success() { echo -e "${GREEN}[OK]${RESET} $1"; }
+log_warn()    { echo -e "${YELLOW}[WARN]${RESET} $1"; }
+log_error()   { echo -e "${RED}[ERROR]${RESET} $1"; }
+
+fail_exit() { log_error "$1"; exit 1; }
+
+#=============================
+# Step 1: Check Alertmanager accessibility
+#=============================
+log_info "Checking Alertmanager status..."
+if curl -sSf "${ALERT_URL}/api/v2/status" >/dev/null 2>&1; then
+  log_success "Alertmanager is reachable at ${ALERT_URL}"
+else
+  fail_exit "Alertmanager is not reachable. Please check container or port mapping."
+fi
+
+#=============================
+# Step 2: Create and load a temporary test alert rule
+#=============================
+log_info "Creating temporary alert rule at ${TMP_RULE}..."
+cat <<EOF > "${TMP_RULE}"
+groups:
+- name: deploy-verify-group
+  rules:
+  - alert: DeployVerifyAlert
+    expr: vector(1)
+    labels:
+      severity: warning
+    annotations:
+      summary: "Deployment verification alert"
+EOF
+
+mkdir -p "${RULE_DIR}"
+cp "${TMP_RULE}" "${RULE_DIR}/test_rule.yml"
+
+log_info "Reloading Prometheus to apply the test rule..."
+if curl -s -X POST "${PROM_URL}/-/reload" >/dev/null; then
+  log_success "Prometheus successfully reloaded rules"
+else
+  fail_exit "Failed to reload Prometheus. Check API accessibility."
+fi
+
+#=============================
+# Step 3: Verify alert received by Alertmanager
+#=============================
+log_info "Waiting for alert propagation (~30 seconds)..."
+sleep 30
+
+if curl -s "${ALERT_URL}/api/v2/alerts" | grep -q "DeployVerifyAlert"; then
+  log_success "Prometheus → Alertmanager alert path verified successfully"
+else
+  fail_exit "DeployVerifyAlert not found in Alertmanager. Check configuration or network."
+fi
+
+#=============================
+# Step 4: Cleanup test rule
+#=============================
+log_info "Cleaning up temporary alert rule..."
+rm -f "${RULE_DIR}/test_rule.yml" "${TMP_RULE}"
+
+if curl -s -X POST "${PROM_URL}/-/reload" >/dev/null; then
+  log_success "Prometheus successfully reloaded after cleanup"
+else
+  log_warn "Prometheus reload after cleanup failed. Please check manually."
+fi
+
+log_success "Alertmanager verification completed successfully. Communication with Prometheus is healthy."

src/sys/tests/scripts/16_web_verify.sh

@@ -0,0 +1,115 @@
+#!/usr/bin/env bash
+# verify-web-test.sh
+# Verify frontend service availability and run Playwright end-to-end tests
+
+set -euo pipefail
+
+echo '[INFO] Verifying Web frontend...'
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$TEST_ROOT/../../.." && pwd)"
+WEB_DIR="$REPO_ROOT/src/web"
+
+#=============================
+# Load environment variables
+#=============================
+if [[ -f "$TEST_ROOT/.env" ]]; then
+  set -a; source "$TEST_ROOT/.env"; set +a
+fi
+
+REPORT_DIR="$WEB_DIR/playwright-report"
+FRONTEND_URL="http://localhost:${WEB_PROXY_PORT_8080:-8080}"
+TIMEOUT=120  # max wait time (seconds) for frontend to be ready
+
+#=============================
+# Helper functions
+#=============================
+GREEN="\033[32m"; RED="\033[31m"; YELLOW="\033[33m"; RESET="\033[0m"
+
+log_info()    { echo -e "${YELLOW}[INFO]${RESET} $1"; }
+log_success() { echo -e "${GREEN}[OK]${RESET} $1"; }
+log_warn()    { echo -e "${YELLOW}[WARN]${RESET} $1"; }
+log_error()   { echo -e "${RED}[ERROR]${RESET} $1"; }
+
+fail_exit() { log_error "$1"; exit 1; }
+
+#=============================
+# Step 1: Wait for frontend service
+#=============================
+log_info "[1/4] Checking if frontend service is up (${FRONTEND_URL})..."
+
+for ((i=1; i<=TIMEOUT; i++)); do
+  STATUS_CODE=$(curl -s -o /dev/null -w "%{http_code}" "$FRONTEND_URL" || true)
+  if [[ "$STATUS_CODE" == "200" ]]; then
+    log_success "Frontend service is accessible at ${FRONTEND_URL}"
+    break
+  fi
+  sleep 2
+  if [[ $i -eq $TIMEOUT ]]; then
+    fail_exit "Timeout waiting for frontend service to become ready (${TIMEOUT}s)."
+  fi
+done
+
+#=============================
+# Step 2: Run Playwright tests
+#=============================
+log_info "[2/4] Running Playwright automated tests in headless mode..."
+
+cd "$WEB_DIR"
+
+# Ensure dependencies installed
+if [ ! -d "node_modules" ]; then
+  log_warn "Dependencies not found. Installing via npm ci..."
+  npm ci
+fi
+
+log_info "Checking Playwright browsers..."
+if [ -d "node_modules/playwright" ]; then
+    log_info "Found node_modules/playwright, checking if browsers are complete..."
+    # 使用 dry-run 确认浏览器是否完整
+    if npx playwright install --dry-run | grep -q "All required browsers are installed"; then
+        log_info "All Playwright browsers are already installed, skipping installation."
+        exit 0
+    else
+        log_info "Playwright browsers incomplete, installing..."
+    fi
+else
+    log_info "Playwright browsers not found, installing..."
+    npx playwright install --with-deps > /dev/null
+fi
+
+# Clean previous reports
+rm -rf "$REPORT_DIR"
+
+# Run Playwright tests wrapped with xvfb-run to avoid GUI
+set +e  # temporarily disable exit-on-error
+env BASE_URL="$FRONTEND_URL" xvfb-run --auto-servernum npx playwright test tests/playwright --reporter=list
+TEST_RESULT=$?
+set -e  # re-enable strict mode
+
+#=============================
+# Step 3: Check test results
+#=============================
+log_info "[3/4] Checking test results..."
+
+if [[ $TEST_RESULT -eq 0 ]]; then
+  log_success "All Playwright tests passed successfully."
+else
+  log_error "Some Playwright tests failed. Please review the test report."
+fi
+
+#=============================
+# Step 4: Report generation
+#=============================
+log_info "[4/4] Checking Playwright report..."
+
+if [[ -d "$REPORT_DIR" ]]; then
+  log_success "Test report generated at: $REPORT_DIR"
+  echo "You can view it using:"
+  echo "  npx playwright show-report"
+else
+  log_warn "Report directory not found. Check Playwright execution logs."
+fi
+
+log_success "Web frontend verify finished."

src/web/.gitignore

@@ -1,6 +1,9 @@
 # Node modules
 node_modules/
 
+# playwright report
+playwright-report/
+
 # Build output
 /dist
 /build

src/web/package-lock.json

@@ -20,6 +20,7 @@
       },
       "devDependencies": {
         "@eslint/js": "^9.33.0",
+        "@playwright/test": "^1.56.1",
         "@types/react": "^19.1.10",
         "@types/react-dom": "^19.1.7",
         "@vitejs/plugin-react": "^5.0.0",
@@ -1231,6 +1232,22 @@
         "react": "^18.x || ^19.x"
       }
     },
+    "node_modules/@playwright/test": {
+      "version": "1.56.1",
+      "resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.56.1.tgz",
+      "integrity": "sha512-vSMYtL/zOcFpvJCW71Q/OEGQb7KYBPAdKh35WNSkaZA75JlAO8ED8UN6GUNTm3drWomcbcqRPFqQbLae8yBTdg==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "dependencies": {
+        "playwright": "1.56.1"
+      },
+      "bin": {
+        "playwright": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/@rolldown/pluginutils": {
       "version": "1.0.0-beta.34",
       "resolved": "https://registry.npmjs.org/@rolldown/pluginutils/-/pluginutils-1.0.0-beta.34.tgz",
@@ -2860,6 +2877,53 @@
         "url": "https://github.com/sponsors/jonschlinkert"
       }
     },
+    "node_modules/playwright": {
+      "version": "1.56.1",
+      "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.56.1.tgz",
+      "integrity": "sha512-aFi5B0WovBHTEvpM3DzXTUaeN6eN0qWnTkKx4NQaH4Wvcmc153PdaY2UBdSYKaGYw+UyWXSVyxDUg5DoPEttjw==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "dependencies": {
+        "playwright-core": "1.56.1"
+      },
+      "bin": {
+        "playwright": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      },
+      "optionalDependencies": {
+        "fsevents": "2.3.2"
+      }
+    },
+    "node_modules/playwright-core": {
+      "version": "1.56.1",
+      "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.56.1.tgz",
+      "integrity": "sha512-hutraynyn31F+Bifme+Ps9Vq59hKuUCz7H1kDOcBs+2oGguKkWTU50bBWrtz34OUWmIwpBTWDxaRPXrIXkgvmQ==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "bin": {
+        "playwright-core": "cli.js"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/playwright/node_modules/fsevents": {
+      "version": "2.3.2",
+      "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
+      "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
+      "dev": true,
+      "hasInstallScript": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": "^8.16.0 || ^10.6.0 || >=11.0.0"
+      }
+    },
     "node_modules/postcss": {
       "version": "8.5.6",
       "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.6.tgz",

src/web/package.json

@@ -7,7 +7,9 @@
     "dev": "vite",
     "build": "vite build",
     "lint": "eslint .",
-    "preview": "vite preview"
+    "preview": "vite preview",
+    "test:web": "playwright test",
+    "test:web:report": "playwright show-report"
   },
   "dependencies": {
     "@emotion/react": "^11.14.0",
@@ -22,6 +24,7 @@
   },
   "devDependencies": {
     "@eslint/js": "^9.33.0",
+    "@playwright/test": "^1.56.1",
     "@types/react": "^19.1.10",
     "@types/react-dom": "^19.1.7",
     "@vitejs/plugin-react": "^5.0.0",

src/web/playwright.config.ts

@@ -0,0 +1,28 @@
+import { defineConfig } from '@playwright/test';
+
+export default defineConfig({
+  testDir: './tests',
+  testIgnore: ['**/src/assets/**', '**/*.png', '**/*.jpg', '**/*.svg'],
+  timeout: 60 * 1000,
+  retries: 1,
+  use: {
+    headless: true,
+    viewport: { width: 1280, height: 720 },
+    ignoreHTTPSErrors: true,
+    screenshot: 'only-on-failure',
+    video: 'retain-on-failure',
+      launchOptions: {
+          args: [
+              '--no-sandbox',
+              '--disable-gpu',
+              '--disable-dev-shm-usage',
+              '--disable-software-rasterizer',
+              '--headless=new'
+          ],
+      },
+  },
+  reporter: [
+    ['list'],
+    ['html', { open: 'never', outputFolder: 'playwright-report' }]
+  ]
+});

src/web/src/components/NodeTable.jsx

@@ -71,7 +71,7 @@ export function NodeTable({
                             size="xs"
                             variant="outline"
                             component="a"
-                            href={`${EXTERNAL_HOST.GRAFANA}/d/node_gpu_metrics/node-and-gpu-metrics?var-hostname=${encodeURIComponent(node.name)}`}
+                            href={`${EXTERNAL_HOST.GRAFANA}/d/node_gpu_metrics_by_hostname/node-and-gpu-metrics-by-hostname?var-hostname=${encodeURIComponent(node.name)}`}
                             target="_blank"
                             rel="noopener noreferrer"
                         >

src/web/src/config/entries.js

@@ -1,6 +1,5 @@
 import grafanaLogo from "../assets/grafana.png";
 import prometheusLogo from "../assets/prometheus.png";
-import esLogo from "../assets/es.png";
 import kibanaLogo from "../assets/kibana.png";
 import { EXTERNAL_HOST } from "./api";
 

src/web/tests/data/etc/web.argus.com

@@ -1 +0,0 @@
-172.18.0.3

src/web/tests/playwright/alerts.spec.ts

@@ -0,0 +1,87 @@
+import {test, expect} from "@playwright/test";
+import {BASE_URL} from './helpers/utils'
+
+test.describe("Alerts 页面功能测试", () => {
+    test.beforeEach(async ({page}) => {
+        await page.goto(`${BASE_URL}/alerts`); // 根据你实际路由调整
+    });
+
+    test("页面加载并显示告警统计", async ({page}) => {
+        await expect(page.locator("text=告警详情").first()).toBeVisible();
+        await expect(page.locator("text=总数").first()).toBeVisible();
+        await expect(page.locator("text=严重").first()).toBeVisible();
+        await expect(page.locator("text=警告").first()).toBeVisible();
+        await expect(page.locator("text=信息").first()).toBeVisible();
+    });
+
+    test("筛选功能验证", async ({ page }) => {
+        // 等待页面加载完成
+        await page.waitForSelector("table");
+
+        // ==========================
+        // 1️⃣ 选择“严重性”= critical
+        // ==========================
+        const severitySelect = page.locator('label:has-text("严重性")').locator('..').locator('input');
+        await severitySelect.click(); // 打开下拉菜单
+
+        const criticalOption = page.locator('[role="option"]:has-text("critical")');
+        await criticalOption.waitFor({ state: 'visible', timeout: 5000 });
+        await criticalOption.click();
+
+        // 验证选择已生效
+        await expect(severitySelect).toHaveValue("critical");
+
+        // ==========================
+        // 2️⃣ 选择“状态”= active
+        // ==========================
+        const stateSelect = page.locator('label:has-text("状态")').locator('..').locator('input');
+        await stateSelect.click();
+
+        const activeOption = page.locator('[role="option"]:has-text("Active")');
+        await activeOption.waitFor({ state: 'visible', timeout: 5000 });
+        await activeOption.click();
+
+        await expect(stateSelect).toHaveValue("Active");
+
+        // ==========================
+        // 4️⃣ 验证筛选结果（可选）
+        // ==========================
+        await page.waitForTimeout(1000);
+        const rows = page.locator('table tbody tr');
+        const count = await rows.count();
+        expect(count).toBeGreaterThanOrEqual(0);
+    });
+
+
+    test("排序功能", async ({page}) => {
+        const severityHeader = page.locator("th:has-text('严重性') button").first();
+        await severityHeader.click(); // 切换升序
+        await severityHeader.click(); // 切换降序
+
+        const instanceHeader = page.locator("th:has-text('节点') button").first();
+        await instanceHeader.click();
+        await instanceHeader.click();
+    });
+
+    test("分页功能", async ({page}) => {
+        const nextButton = page.locator("button:has-text('下一页')").first();
+        const prevButton = page.locator("button:has-text('上一页')").first();
+
+        if (await nextButton.isEnabled()) {
+            await nextButton.click();
+            await expect(prevButton).toBeEnabled();
+        }
+    });
+
+    test("展开更多信息行", async ({page}) => {
+        const infoIcons = page.locator("table tbody tr td [title='显示/隐藏更多信息']");
+        if (await infoIcons.count() > 0) {
+            await infoIcons.first().click();
+            // 展开的详情行应出现
+            const details = page.locator("table tbody tr >> text=alertname");
+            const detailCount = await details.count();
+            expect(detailCount).toBeGreaterThan(0);
+        }
+    });
+
+});

src/web/tests/playwright/dashboard.spec.ts

@@ -0,0 +1,52 @@
+import {test, expect} from '@playwright/test';
+import {BASE_URL} from './helpers/utils'
+
+test.describe('Dashboard 页面测试', () => {
+
+    test.beforeEach(async ({page}) => {
+        // 打开仪表盘页面
+        await page.goto(`${BASE_URL}/dashboard`, {waitUntil: 'networkidle'});
+    });
+
+    test('应能成功加载页面并显示标题', async ({page}) => {
+        await expect(page.locator('text=仪表盘').first()).toBeVisible();
+    });
+
+    test('应显示节点健康状态卡片', async ({page}) => {
+        const healthCard = page.locator('text=节点健康状态');
+        await expect(healthCard).toBeVisible();
+
+        // 检查环形图是否渲染
+        const ring = page.locator('svg'); // RingProgress 是 SVG 渲染的
+        const ringCount = await ring.count();
+        expect(ringCount).toBeGreaterThan(0);
+    });
+
+    test('应显示告警统计信息', async ({page}) => {
+        const alertCard = page.locator('text=告警统计');
+        await expect(alertCard).toBeVisible();
+
+        // 检查告警类别
+        const labels = ['总数', '严重', '警告', '信息'];
+        for (const label of labels) {
+            await expect(page.locator(`text=${label}`).first()).toBeVisible();
+        }
+    });
+
+    test('应正确渲染集群节点表格', async ({page}) => {
+        const tableHeaders = ['ID', '名称', '状态', '类型', '版本'];
+        for (const header of tableHeaders) {
+            await expect(page.locator(`th:has-text("${header}")`).first()).toBeVisible();
+        }
+
+        // 至少有一行节点数据
+        const rows = await page.locator('tbody tr').count();
+        expect(rows).toBeGreaterThan(0);
+    });
+
+    test('页面应无加载错误提示', async ({page}) => {
+        await expect(page.locator('text=加载中...')).toHaveCount(0);
+        await expect(page.locator('text=数据加载失败')).toHaveCount(0);
+    });
+
+});

src/web/tests/playwright/helpers/entrycards-helpers.ts

@@ -0,0 +1,28 @@
+import { Page, expect } from '@playwright/test';
+import type { metricsEntries } from '../../../src/config/entries';
+
+export async function testEntryCards(
+    page: Page,
+    entries: typeof metricsEntries,
+    checkLinkNavigation = false
+) {
+    for (const entry of entries) {
+        // 先根据 label 找到包含该文本的卡片
+        const card = page.locator(`.mantine-Card-root:has-text("${entry.label}")`);
+        await expect(card).toBeVisible({ timeout: 10000 });
+
+        // 检查卡片内部的链接，忽略端口号
+        const link = card.locator('a');
+        const href = await link.getAttribute('href');
+
+        // 正则：保留协议和 host，忽略端口号
+        const expectedHrefPattern = entry.href.replace(/:(\d+)/, '(:\\d+)?');
+        expect(href).toMatch(new RegExp(`^${expectedHrefPattern}$`));
+
+        // 检查图标
+        const img = card.locator('img');
+        await expect(img).toBeVisible();
+        await expect(img).toHaveAttribute('src', /(\/assets\/.+|data:image\/png;base64,)/);
+
+    }
+}

src/web/tests/playwright/helpers/testUtils.ts

@@ -0,0 +1,25 @@
+import { Page, expect } from '@playwright/test';
+import { BASE_URL } from './utils'
+/**
+ * 通用函数：验证页面导航是否正确
+ */
+export async function checkPage(page: Page, path: string, title: string) {
+  await page.goto(`${BASE_URL}`);
+  const menu = page.getByRole('link', { name: title });
+  await expect(menu).toBeVisible();
+  await menu.click();
+  await expect(page).toHaveURL(new RegExp(`${path}`));
+  await expect(page.locator('body')).toContainText(title);
+}
+
+/**
+ * 检查页面是否存在 JS 错误
+ */
+export async function noConsoleError(page: Page) {
+  const errors: string[] = [];
+  page.on('console', msg => {
+    if (msg.type() === 'error') errors.push(msg.text());
+  });
+  await page.waitForLoadState('networkidle');
+  expect(errors, `发现 JS 错误: ${errors.join(', ')}`).toHaveLength(0);
+}

src/web/tests/playwright/helpers/utils.ts

@@ -0,0 +1 @@
+export const BASE_URL = process.env.BASE_URL || "http://localhost:8080";

src/web/tests/playwright/logs.spec.ts

@@ -0,0 +1,17 @@
+import { test, expect } from '@playwright/test';
+import { logsEntries } from './test-entries';
+import { testEntryCards } from './helpers/entrycards-helpers';
+import { BASE_URL } from './helpers/utils';
+
+test.describe('Logs Page', () => {
+    test('should render all log cards', async ({ page }) => {
+        await page.goto(`${BASE_URL}/logs`);
+
+        // 等待标题可见
+        const title = page.locator('h2', { hasText: '日志详情' });
+        await expect(title).toBeVisible({ timeout: 10000 });
+
+        // 测试所有 log card
+        await testEntryCards(page, logsEntries);
+    });
+});

src/web/tests/playwright/metric.spec.ts

@@ -0,0 +1,15 @@
+import { test, expect } from '@playwright/test';
+import { metricsEntries } from './test-entries';
+import { testEntryCards } from './helpers/entrycards-helpers';
+import { BASE_URL } from './helpers/utils';
+
+test.describe('Metrics Page', () => {
+    test('should render all metric cards', async ({ page }) => {
+        await page.goto(`${BASE_URL}/metrics`);
+
+        const title = page.locator('h2', { hasText: '指标详情' });
+        await expect(title).toBeVisible({ timeout: 10000 });
+
+        await testEntryCards(page, metricsEntries);
+    });
+});

src/web/tests/playwright/node-info.spec.ts

@@ -0,0 +1,64 @@
+import {test, expect} from "@playwright/test";
+import {BASE_URL} from './helpers/utils'
+
+test.describe("节点信息页面 NodeInfo", () => {
+    test.beforeEach(async ({page}) => {
+        await page.goto(`${BASE_URL}/nodeInfo`);
+    });
+
+    test("页面标题应该正确显示", async ({page}) => {
+        const title = page.locator('h1,h2,h3:has-text("节点信息")').first();
+        await title.waitFor({timeout: 10000});
+        await expect(title).toBeVisible();
+    });
+
+    test("节点表格应该加载数据", async ({page}) => {
+        const rows = page.locator("table tbody tr");
+        await rows.first().waitFor({timeout: 10000});
+        const count = await rows.count();
+        expect(count).toBeGreaterThan(0);
+    });
+
+    test('节点详情测试', async ({page}) => {
+        const firstDetailBtn = page.locator('text=查看详情').first();
+        await firstDetailBtn.waitFor({timeout: 10000});
+        await firstDetailBtn.scrollIntoViewIfNeeded();
+        await firstDetailBtn.click({force: true});
+
+        const drawer = page.locator('role=dialog[name="节点详情"]');
+        await drawer.waitFor({timeout: 10000});
+        await expect(drawer).toBeVisible();
+        
+        for (const label of ['注册时间', '最近上报时间', '最后更新时间', '元数据信息', '健康信息', '配置信息', '标签信息']) {
+            const el = drawer.locator(`text=${label}`).first();
+            await el.waitFor({timeout: 5000});
+            await expect(el).toBeVisible();
+        }
+
+    });
+    test("每个节点的 Grafana 按钮链接正确", async ({ page }) => {
+        await page.waitForSelector("table tbody tr", { timeout: 10000 });
+
+        // 查找 Grafana 链接（根据快照，它是 link 而非 button）
+        const grafanaLinks = page.getByRole("link", { name: "Grafana" });
+        const count = await grafanaLinks.count();
+
+        // 如果没找到，保存上下文方便排查
+        if (count === 0) {
+            const html = await page.content();
+            console.error("❌ 未找到 Grafana 链接，页面 HTML 片段如下：\n", html.slice(0, 2000));
+        }
+
+        // 至少应该有一行节点
+        expect(count).toBeGreaterThan(0);
+
+        // 校验链接 href
+        for (let i = 0; i < count; i++) {
+            const link = grafanaLinks.nth(i);
+            await expect(link).toHaveAttribute(
+                "href",
+                /\/d\/node_gpu_metrics_by_hostname\/node-and-gpu-metrics-by-hostname\?var-hostname=/
+            );
+        }
+    });
+});

src/web/tests/playwright/test-entries.ts

@@ -0,0 +1,14 @@
+import { EXTERNAL_HOST } from "../../src/config/api";
+
+export const metricsEntries = [
+  { label: "Grafana", href: EXTERNAL_HOST.GRAFANA_DASHBOARD, icon: '' },
+  { label: "Prometheus", href: EXTERNAL_HOST.PROMETHEUS, icon: '' },
+];
+
+export const logsEntries = [
+  { label: "Kibana", href: EXTERNAL_HOST.KIBANA, icon: '' },
+];
+
+export const alertsEntries = [
+  { label: "Alertmanager", href: EXTERNAL_HOST.ALERTS, icon: '' },
+];

src/web/tests/playwright/web-pages.spec.ts

@@ -0,0 +1,21 @@
+import { test } from '@playwright/test';
+import { checkPage, noConsoleError } from './helpers/testUtils';
+import { BASE_URL } from './helpers/utils'
+
+const pages = [
+  { path: '/dashboard', title: '仪表盘' },
+  { path: '/nodeInfo', title: '节点信息' },
+  { path: '/metrics', title: '指标详情' },
+  { path: '/logs', title: '日志详情' },
+  { path: '/alerts', title: '告警详情' }
+];
+
+test.describe('Argus Web 页面可用性巡检', () => {
+  for (const { path, title } of pages) {
+    test(`${title} 页面加载验证`, async ({ page }) => {
+      await page.goto(`${BASE_URL}${path}`);
+      await checkPage(page, path, title);
+      await noConsoleError(page);
+    });
+  }
+});

src/web/tests/scripts/01_bootstrap.sh

@@ -1,19 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
-project_root="$(cd "$root/../../.." && pwd)"
-
-source "$project_root/scripts/common/build_user.sh"
-load_build_user
-
-# 创建新的private目录结构 (基于argus目录结构)
-echo "[INFO] Creating private directory structure for supervisor-based containers..."
-mkdir -p "$root/private/argus/web"
-mkdir -p "$root/private/argus/etc/"
-
-# 设置数据目录权限
-echo "[INFO] Setting permissions for data directories..."
-chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/web" 2>/dev/null || true
-chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
-
-echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"

src/web/tests/scripts/02_up.sh

@@ -1,10 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-cd "$(dirname "$0")/.."
-compose_cmd="docker compose"
-if ! $compose_cmd version >/dev/null 2>&1; then
-  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
-    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
-fi
-$compose_cmd -p alert-mvp up -d --remove-orphans
-echo "[OK] 服务已启动：Web Frontend http://localhost:8080"

src/web/tests/scripts/03_web_health_check.sh

@@ -1,93 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-WEB_URL=${WEB_URL:-"http://localhost:8080"}
-API_URL=${API_URL:-"http://master.argus.com/api/v1/master/nodes"}
-TIMEOUT=10
-
-GREEN="\033[1;32m"
-RED="\033[1;31m"
-YELLOW="\033[1;33m"
-RESET="\033[0m"
-
-echo "[info] 测试 Argus Web 前端启动状态..."
-echo "--------------------------------------------------"
-
-# 等待 web 前端可用
-attempt=1
-while (( attempt <= 10 )); do
-  if curl -fsS -m "$TIMEOUT" -o /dev/null "$WEB_URL"; then
-    echo "[ok] Web 前端已启动 (${attempt}/10)"
-    break
-  fi
-  echo "[..] 等待 Web 前端启动中 (${attempt}/10)"
-  sleep 3
-  (( attempt++ ))
-done
-
-if (( attempt > 10 )); then
-  echo "[err] Web 前端在 30 秒内未启动"
-  exit 1
-fi
-
-# 1. 检查首页可访问性
-echo "[test] 检查首页访问..."
-if curl -fsS "$WEB_URL" -m "$TIMEOUT" | grep -q "<title>"; then
-  echo -e "[${GREEN}ok${RESET}] 首页可访问"
-else
-  echo -e "[${RED}err${RESET}] 首页访问失败"
-  exit 1
-fi
-
-# 2. 检查静态资源加载
-echo "[test] 检查静态资源..."
-if curl -fsS "$WEB_URL/static/js" -m "$TIMEOUT" | grep -q "Cannot GET"; then
-  echo -e "[${YELLOW}warn${RESET}] 静态资源路径可能未正确配置"
-else
-  echo -e "[${GREEN}ok${RESET}] 静态资源服务正常"
-fi
-
-# 3. 检查前端路由兼容
-echo "[test] 检查 React Router 路由兼容..."
-if curl -fsS "$WEB_URL/dashboard" -m "$TIMEOUT" | grep -q "<title>"; then
-  echo -e "[${GREEN}ok${RESET}] React Router 路由兼容正常"
-else
-  echo -e "[${YELLOW}warn${RESET}] /dashboard 路由未正确返回 index.html"
-fi
-
-# 4. 测试 API 代理访问
-echo "[test] 检查 API 代理..."
-if curl -fsS "$API_URL" -m "$TIMEOUT" | grep -q "nodes"; then
-  echo -e "[${GREEN}ok${RESET}] API 代理成功"
-else
-  echo -e "[${YELLOW}warn${RESET}] API 代理请求失败，请检查 Nginx proxy_pass"
-fi
-
-# 5. 页面关键字验证
-echo "[test] 检查关键内容..."
-if curl -fsS "$WEB_URL" | grep -q "Argus"; then
-  echo -e "[${GREEN}ok${RESET}] 页面包含关键字 'Argus'"
-else
-  echo -e "[${YELLOW}warn${RESET}] 页面内容中未找到 'Argus'"
-fi
-
-# 6. DNS 检查
-echo "[test] 检查 DNS 解析..."
-if dig +short web.argus.com >/dev/null; then
-  echo -e "[${GREEN}ok${RESET}] 域名 web.argus.com 解析正常"
-else
-  echo -e "[${YELLOW}warn${RESET}] 域名 web.argus.com 解析失败"
-fi
-
-# 7. 响应时间测试
-echo "[test] 检查响应时间..."
-response_time=$(curl -o /dev/null -s -w "%{time_total}\n" "$WEB_URL")
-echo "[info] 响应时间: ${response_time}s"
-if (( $(echo "$response_time > 2.0" | bc -l) )); then
-  echo -e "[${YELLOW}warn${RESET}] 响应时间较慢（>2s）"
-else
-  echo -e "[${GREEN}ok${RESET}] 响应时间正常"
-fi
-
-echo "--------------------------------------------------"
-echo "[done] Web 前端测试完成 ✅"

src/web/tests/scripts/04_down.sh

@@ -1,21 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-cd "$(dirname "$0")/.."
-compose_cmd="docker compose"
-if ! $compose_cmd version >/dev/null 2>&1; then
-  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
-    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
-fi
-$compose_cmd -p alert-mvp down
-echo "[OK] 已停止所有容器"
-
-# 清理private目录内容
-echo "[INFO] 清理private目录内容..."
-cd "$(dirname "$0")/.."
-if [ -d "private" ]; then
-    # 删除private目录及其所有内容
-    rm -rf private
-    echo "[OK] 已清理private目录"
-else
-    echo "[INFO] private目录不存在，无需清理"
-fi

src/web/tests/scripts/e2e_test.sh

@@ -1,85 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-echo "======================================="
-echo "ARGUS Web System End-to-End Test"
-echo "======================================="
-echo ""
-
-# 记录测试开始时间
-test_start_time=$(date +%s)
-
-# 函数：等待服务就绪
-wait_for_services() {
-    echo "[INFO] Waiting for all services to be ready..."
-    local max_attempts=${SERVICE_WAIT_ATTEMPTS:-120}
-    local attempt=1
-
-    while [ $attempt -le $max_attempts ]; do
-        if curl -fs http://localhost:8080 >/dev/null 2>&1; then
-            echo "[OK] All services are ready!"
-            return 0
-        fi
-        echo "    Waiting for services... ($attempt/$max_attempts)"
-        sleep 5
-        ((attempt++))
-    done
-
-    echo "[ERROR] Services not ready after $max_attempts attempts"
-    return 1
-}
-
-# 函数：显示测试步骤
-show_step() {
-    echo ""
-    echo "🔄 Step $1: $2"
-    echo "----------------------------------------"
-}
-
-# 函数：验证步骤结果
-verify_step() {
-    if [ $? -eq 0 ]; then
-        echo "✅ $1 - SUCCESS"
-    else
-        echo "❌ $1 - FAILED"
-        exit 1
-    fi
-}
-
-# 开始端到端测试
-show_step "1" "Bootstrap - Initialize environment"
-./scripts/01_bootstrap.sh
-verify_step "Bootstrap"
-
-show_step "2" "Startup - Start all services"
-./scripts/02_up.sh
-verify_step "Service startup"
-
-# 等待服务完全就绪
-wait_for_services || exit 1
-
-# 测试前端页面
-show_step "3" "Web - Check frontend availability"
-./scripts/03_web_health_check.sh
-verify_step "Web frontend availability"
-
-# 清理环境
-show_step "4" "Cleanup - Stop all services"
-./scripts/04_down.sh
-verify_step "Service cleanup"
-
-# 计算总测试时间
-test_end_time=$(date +%s)
-total_time=$((test_end_time - test_start_time))
-
-echo ""
-echo "======================================="
-echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
-echo "======================================="
-echo "📊 Test Summary:"
-echo "   • Total time: ${total_time}s"
-echo "   • Alertmanager status: $am_status"
-echo "   • All services started and stopped successfully"
-echo ""
-echo "✅ The ARGUS Web system is working correctly!"
-echo ""

src/web/tests/scripts/verify-web-frontend.sh

@@ -0,0 +1,77 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# -----------------------------------------
+# Web 前端自动化验证脚本（部署后执行）
+# -----------------------------------------
+
+PROJECT_ROOT="$(dirname "$0")"
+WEB_DIR="$PROJECT_ROOT"
+REPORT_DIR="$WEB_DIR/playwright-report"
+FRONTEND_URL="http://web.argus.com:8080"
+TIMEOUT=120  # 最长等待前端启动时间（秒）
+
+echo "🔍 [1/4] 检查前端服务是否已启动 (${FRONTEND_URL}) ..."
+
+# 等待前端服务可访问
+for ((i=1; i<=$TIMEOUT; i++)); do
+  STATUS_CODE=$(curl -s -o /dev/null -w "%{http_code}" "$FRONTEND_URL" || true)
+  if [[ "$STATUS_CODE" == "200" ]]; then
+    echo "✅ 前端服务已启动并可访问"
+    break
+  fi
+  sleep 2
+  if [ $i -eq $TIMEOUT ]; then
+    echo "❌ 等待前端启动超时 (${TIMEOUT}s)"
+    exit 1
+  fi
+done
+
+# -----------------------------------------
+# 2. 执行 Playwright 测试
+# -----------------------------------------
+echo "[2/4] 执行 Playwright 自动化测试..."
+
+cd "$WEB_DIR"
+
+# 确保依赖已安装
+if [ ! -d "node_modules" ]; then
+  echo "未检测到依赖，开始安装..."
+  npm ci
+fi
+
+# 清理旧报告
+rm -rf "$REPORT_DIR"
+
+# 运行测试（带失败检测）
+set +e  # 暂时关闭自动退出，便于捕获测试结果
+npx playwright test tests/playwright --reporter=list,html
+TEST_RESULT=$?
+set -e  # 恢复严格模式
+
+# -----------------------------------------
+# 3. 检查测试结果
+# -----------------------------------------
+echo "[3/4] 检查测试结果..."
+
+if [ $TEST_RESULT -eq 0 ]; then
+  echo "[✓] 所有测试通过！"
+else
+  echo "[X] 存在测试未通过，请查看报告。"
+fi
+
+# -----------------------------------------
+# 4. 输出报告信息
+# -----------------------------------------
+echo "[4/4] 生成测试报告..."
+
+if [ -d "$REPORT_DIR" ]; then
+  echo "测试报告已生成：$REPORT_DIR"
+  echo "可执行以下命令查看详细报告："
+  echo "  npx playwright show-report"
+else
+  echo "未生成报告目录，请检查执行日志。"
+fi
+
+# 将测试结果作为退出码返回
+exit $TEST_RESULT