【后端】

新增：服务器离线告警连续失败检测机制（避免临时网络波动误报）
    - 数据库：deploy_server_monitor 表增加 status 字段记录采集状态（SUCCESS/FAILURE）
    - 框架层：新增 StatusEnum 通用状态枚举类，MonitorMetricEnum 增加 SERVER_STATUS 监控类型
    - 实体层：ServerMonitor 实体增加 status 字段用于标识采集状态
    - Repository：IServerMonitorRepository 增加 findRecentMonitorRecords 方法查询最近N条监控记录
    - Service：IServerMonitorService 增加 saveMonitorRecord（保存单条记录）和 countConsecutiveFailures（统计连续失败次数）方法
    - 告警服务：IServerAlertService 增加 checkServerStatusAlert（检查状态告警）和 resolveServerStatusAlert（解除状态告警）方法
    - 告警实现：ServerAlertServiceImpl 实现服务器状态告警的创建、级别升级（WARNING→CRITICAL）、自动解除逻辑
    - 调度器：ServerMonitorScheduler 集成连续失败检测，连接成功时插入SUCCESS记录并解除告警，连接失败时插入FAILURE记录并触发告警检测
    - 数据初始化：增加全局服务器状态告警规则（连续3次失败触发警告，5次触发严重并标记离线）

优化：统一监控告警通知模板，简化配置参数
    - ServerMonitorNotificationConfig 删除 serverOfflineTemplateId 字段，所有监控告警（CPU/内存/磁盘/网络/服务器状态）统一使用 resourceAlertTemplateId
    - ServerMonitorScheduler.collectServerMetrics 方法删除 serverOfflineTemplateId 参数
    - ServerAlertServiceImpl.sendServerStatusNotification 改用统一的资源告警模板，模板参数与其他监控告警保持一致

修复：删除冗余代码和未使用的类
    - 删除 CollectionStatusEnum.java（已被 StatusEnum 取代）
    - 删除 ServerMonitorScheduler.sendServerOfflineNotification 方法（改由 ServerAlertService 统一处理）

优化：告警通知模板支持百分比和次数两种单位
    - 通知模板使用 FreeMarker 条件判断，根据 alertType 自动显示"连续失败X次"或"使用率X%"
    - 严重级别告警显示红色并提示"请立即处理"，警告级别提示"请注意观察"

    【前端】
修复：告警规则表单规则范围下拉框无法滚动选择问题（移除嵌套滚动容器干扰）
优化：规则范围选择器升级为带搜索的Popover组件（支持按服务器名称/IP搜索，固定高度可滚动）
优化：规则范围数据加载从分页接口改为列表接口

backend/src/main/java/com/qqchen/deploy/backend/deploy/dto/ServerMonitorNotificationConfig.java

@@ -20,12 +20,8 @@ public class ServerMonitorNotificationConfig {
     private Long notificationChannelId;
 
     /**
-     * 服务器离线通知模板ID
+     * 资源告警通知模板ID
-     */
+     * 用于所有监控告警（CPU、内存、磁盘、网络、服务器状态）
-    private Long serverOfflineTemplateId;
-
-    /**
-     * 资源预警通知模板ID
      */
     private Long resourceAlertTemplateId;
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/entity/ServerMonitor.java

@@ -1,5 +1,6 @@
 package com.qqchen.deploy.backend.deploy.entity;
 
+import com.qqchen.deploy.backend.framework.enums.StatusEnum;
 import jakarta.persistence.*;
 import lombok.AllArgsConstructor;
 import lombok.Data;
@@ -73,4 +74,11 @@ public class ServerMonitor {
      */
     @Column(name = "collect_time", nullable = false)
     private LocalDateTime collectTime;
+
+    /**
+     * 采集状态
+     */
+    @Enumerated(EnumType.STRING)
+    @Column(name = "status", nullable = false, length = 20)
+    private StatusEnum status = StatusEnum.SUCCESS;
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/repository/IServerAlertLogRepository.java

@@ -4,6 +4,7 @@ import com.qqchen.deploy.backend.deploy.entity.ServerAlertLog;
 import com.qqchen.deploy.backend.framework.enums.MonitorMetricEnum;
 import com.qqchen.deploy.backend.framework.enums.ServerAlertStatusEnum;
 import org.springframework.data.jpa.repository.JpaRepository;
+import org.springframework.data.jpa.repository.Modifying;
 import org.springframework.data.jpa.repository.Query;
 import org.springframework.data.repository.query.Param;
 import org.springframework.stereotype.Repository;
@@ -44,4 +45,11 @@ public interface IServerAlertLogRepository extends JpaRepository<ServerAlertLog,
         @Param("ruleId") Long ruleId,
         @Param("alertType") MonitorMetricEnum alertType
     );
+
+    /**
+     * 删除指定服务器的所有告警记录
+     */
+    @Modifying
+    @Query("DELETE FROM ServerAlertLog l WHERE l.serverId = :serverId")
+    int deleteByServerId(@Param("serverId") Long serverId);
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/repository/IServerAlertRuleRepository.java

@@ -2,6 +2,9 @@ package com.qqchen.deploy.backend.deploy.repository;
 
 import com.qqchen.deploy.backend.deploy.entity.ServerAlertRule;
 import com.qqchen.deploy.backend.framework.repository.IBaseRepository;
+import org.springframework.data.jpa.repository.Modifying;
+import org.springframework.data.jpa.repository.Query;
+import org.springframework.data.repository.query.Param;
 import org.springframework.stereotype.Repository;
 
 /**
@@ -9,4 +12,11 @@ import org.springframework.stereotype.Repository;
  */
 @Repository
 public interface IServerAlertRuleRepository extends IBaseRepository<ServerAlertRule, Long> {
+
+    /**
+     * 删除指定服务器的所有告警规则
+     */
+    @Modifying
+    @Query("DELETE FROM ServerAlertRule r WHERE r.serverId = :serverId")
+    int deleteByServerId(@Param("serverId") Long serverId);
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/repository/IServerMonitorRepository.java

@@ -33,4 +33,18 @@ public interface IServerMonitorRepository extends JpaRepository<ServerMonitor, L
     @Modifying
     @Query("DELETE FROM ServerMonitor m WHERE m.collectTime < :beforeTime")
     int deleteByCollectTimeBefore(@Param("beforeTime") LocalDateTime beforeTime);
+
+    /**
+     * 删除指定服务器的所有监控记录
+     */
+    @Modifying
+    @Query("DELETE FROM ServerMonitor m WHERE m.serverId = :serverId")
+    int deleteByServerId(@Param("serverId") Long serverId);
+
+    /**
+     * 查询指定服务器最近N条监控记录（按时间倒序）
+     * 用于统计连续失败次数
+     */
+    @Query("SELECT m FROM ServerMonitor m WHERE m.serverId = :serverId ORDER BY m.collectTime DESC")
+    List<ServerMonitor> findRecentMonitorRecords(@Param("serverId") Long serverId, org.springframework.data.domain.Pageable pageable);
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/scheduler/ServerMonitorScheduler.java

@@ -69,22 +69,19 @@ public class ServerMonitorScheduler {
      * 此方法由定时任务管理系统调用
      *
      * @param notificationChannelId   通知渠道ID（可选，为null则不发送通知）
-     * @param serverOfflineTemplateId 服务器离线通知模板ID（可选）
+     * @param resourceAlertTemplateId 资源告警通知模板ID（可选，用于所有监控告警）
-     * @param resourceAlertTemplateId 资源告警通知模板ID（可选）
      */
     public void collectServerMetrics(Long notificationChannelId,
-                                     Long serverOfflineTemplateId,
                                      Long resourceAlertTemplateId) {
         // 构建通知配置对象
         ServerMonitorNotificationConfig config = null;
         if (notificationChannelId != null) {
             config = new ServerMonitorNotificationConfig();
             config.setNotificationChannelId(notificationChannelId);
-            config.setServerOfflineTemplateId(serverOfflineTemplateId);
             config.setResourceAlertTemplateId(resourceAlertTemplateId);
 
-            log.debug("开始采集服务器监控数据: channelId={}, offlineTemplateId={}, alertTemplateId={}",
+            log.debug("开始采集服务器监控数据: channelId={}, alertTemplateId={}",
-                notificationChannelId, serverOfflineTemplateId, resourceAlertTemplateId);
+                notificationChannelId, resourceAlertTemplateId);
         } else {
             log.debug("开始采集服务器监控数据（不发送通知）");
         }
@@ -201,30 +198,88 @@ public class ServerMonitorScheduler {
                 passphrase
             );
             
-            // 3. 连接成功，更新服务器状态
+            // 3. 连接成功，插入成功记录
+            ServerMonitor successRecord = ServerMonitor.builder()
+                .serverId(server.getId())
+                .status(com.qqchen.deploy.backend.framework.enums.StatusEnum.SUCCESS)
+                .collectTime(LocalDateTime.now())
+                .build();
+            monitorService.saveMonitorRecord(successRecord);
+            
+            // 4. 解除服务器状态告警（如果存在）
+            try {
+                alertService.resolveServerStatusAlert(server.getId());
+            } catch (Exception e) {
+                log.warn("解除服务器状态告警失败: serverId={}", server.getId(), e);
+            }
+            
+            // 5. 更新服务器状态为ONLINE
+            if (server.getStatus() == ServerStatusEnum.OFFLINE) {
+                server.setStatus(ServerStatusEnum.ONLINE);
+                server.setLastConnectTime(LocalDateTime.now());
+                serverRepository.save(server);
+                log.info("✓ 服务器已恢复在线: {} ({})", server.getServerName(), server.getHostIp());
+            } else {
                 server.setStatus(ServerStatusEnum.ONLINE);
                 server.setLastConnectTime(LocalDateTime.now());
                 serverRepository.save(server);
-            
                 log.info("✓ 服务器连接成功: {} ({})", server.getServerName(), server.getHostIp());
+            }
             
-            // 4. 采集监控数据（复用同一个SSH连接）
+            // 6. 采集监控数据（复用同一个SSH连接）
             return collectServerMonitorData(server, sshClient, sshService);
             
         } catch (Exception e) {
-            // 连接失败，更新服务器状态为离线
+            // 连接失败，插入失败记录
+            ServerMonitor failureRecord = ServerMonitor.builder()
+                .serverId(server.getId())
+                .status(com.qqchen.deploy.backend.framework.enums.StatusEnum.FAILURE)
+                .collectTime(LocalDateTime.now())
+                .build();
+            
+            try {
+                monitorService.saveMonitorRecord(failureRecord);
+            } catch (Exception saveError) {
+                log.error("保存失败记录异常: serverId={}", server.getId(), saveError);
+            }
+            
+            // 统计连续失败次数
+            int failureCount = 0;
+            try {
+                failureCount = monitorService.countConsecutiveFailures(server.getId(), 10);
+                log.error("✗ 服务器连接失败 [连续{}次]: {} ({}) - {}", 
+                    failureCount, server.getServerName(), server.getHostIp(), e.getMessage());
+            } catch (Exception countError) {
+                log.error("统计连续失败次数异常: serverId={}", server.getId(), countError);
                 log.error("✗ 服务器连接失败: {} ({}) - {}", 
                     server.getServerName(), server.getHostIp(), e.getMessage());
+            }
             
+            // 检查服务器状态告警（传入所有规则，避免重复查询）
+            if (failureCount > 0 && config != null) {
+                try {
+                    // 查询所有规则（在外层已查询，这里重新查询以确保最新）
+                    List<ServerAlertRule> allRules = alertRuleRepository.findAll();
+                    alertService.checkServerStatusAlert(server.getId(), failureCount, allRules, config);
+                    
+                    // 如果达到严重阈值，标记服务器为OFFLINE
+                    ServerAlertRule statusRule = allRules.stream()
+                        .filter(rule -> rule.getAlertType() == com.qqchen.deploy.backend.framework.enums.MonitorMetricEnum.SERVER_STATUS)
+                        .filter(rule -> Boolean.TRUE.equals(rule.getEnabled()))
+                        .filter(rule -> rule.getServerId() == null || server.getId().equals(rule.getServerId()))
+                        .findFirst()
+                        .orElse(null);
+                    
+                    if (statusRule != null && failureCount >= statusRule.getCriticalThreshold().intValue()) {
+                        if (server.getStatus() != ServerStatusEnum.OFFLINE) {
                             server.setStatus(ServerStatusEnum.OFFLINE);
                             serverRepository.save(server);
-            
+                            log.warn("🔴 服务器已标记为离线: {} (连续失败{}次)", 
-            // 发送离线通知
+                                server.getServerName(), failureCount);
-            if (config != null && config.getNotificationChannelId() != null && config.getServerOfflineTemplateId() != null) {
+                        }
-                try {
+                    }
-                    sendServerOfflineNotification(server, config);
+                } catch (Exception alertError) {
-                } catch (Exception notifyError) {
+                    log.error("检查服务器状态告警失败: serverId={}", server.getId(), alertError);
-                    log.error("发送服务器离线通知失败: serverId={}", server.getId(), notifyError);
                 }
             }
             
@@ -238,35 +293,6 @@ public class ServerMonitorScheduler {
         }
     }
 
-    /**
-     * 发送服务器离线通知
-     */
-    private void sendServerOfflineNotification(Server server, ServerMonitorNotificationConfig config) {
-        try {
-            // 1. 构建模板参数
-            Map<String, Object> templateParams = new HashMap<>();
-            templateParams.put("serverName", server.getServerName());
-            templateParams.put("serverIp", server.getHostIp());
-            templateParams.put("offlineTime", LocalDateTime.now().format(
-                java.time.format.DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss")));
-
-            // 2. 构建SendNotificationRequest
-            SendNotificationRequest request = new SendNotificationRequest();
-            request.setChannelId(config.getNotificationChannelId());
-            request.setNotificationTemplateId(config.getServerOfflineTemplateId());
-            request.setTemplateParams(templateParams);
-
-            // 3. 发送通知（NotificationService会自动根据渠道类型创建请求对象）
-            notificationService.send(request);
-
-            log.info("服务器离线通知已发送: serverId={}, serverName={}, ip={}",
-                server.getId(), server.getServerName(), server.getHostIp());
-        } catch (Exception e) {
-            log.error("发送服务器离线通知异常: serverId={}", server.getId(), e);
-            throw e;
-        }
-    }
-
     /**
      * 采集服务器监控数据（CPU、内存、磁盘、网络使用率）
      * 

backend/src/main/java/com/qqchen/deploy/backend/deploy/service/IServerAlertService.java

@@ -32,4 +32,23 @@ public interface IServerAlertService {
     void checkAlertRules(Long serverId, ServerMonitorDataDTO monitorData, 
                         List<ServerAlertRule> allRules,
                         ServerMonitorNotificationConfig config);
+
+    /**
+     * 检查服务器状态告警（连接失败场景）
+     * 
+     * @param serverId 服务器ID
+     * @param failureCount 连续失败次数
+     * @param allRules 所有告警规则
+     * @param config 通知配置
+     */
+    void checkServerStatusAlert(Long serverId, int failureCount, 
+                                List<ServerAlertRule> allRules,
+                                ServerMonitorNotificationConfig config);
+
+    /**
+     * 解除服务器状态告警（连接恢复场景）
+     * 
+     * @param serverId 服务器ID
+     */
+    void resolveServerStatusAlert(Long serverId);
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/service/IServerMonitorService.java

@@ -29,4 +29,21 @@ public interface IServerMonitorService {
      * @return 最新的监控记录，如果没有则返回null
      */
     ServerMonitor getLastMonitorData(Long serverId);
+
+    /**
+     * 保存单条监控记录（包括失败记录）
+     * 
+     * @param monitor 监控记录
+     */
+    void saveMonitorRecord(ServerMonitor monitor);
+
+    /**
+     * 统计指定服务器的连续失败次数
+     * 查询最近的监控记录，从最新开始统计连续FAILURE状态的数量
+     * 
+     * @param serverId 服务器ID
+     * @param checkLimit 检查最近多少条记录（默认10条）
+     * @return 连续失败次数
+     */
+    int countConsecutiveFailures(Long serverId, int checkLimit);
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/service/impl/ServerAlertServiceImpl.java

@@ -491,4 +491,218 @@ public class ServerAlertServiceImpl implements IServerAlertService {
             throw e;
         }
     }
+
+    @Override
+    public void checkServerStatusAlert(Long serverId, int failureCount, 
+                                      List<ServerAlertRule> allRules,
+                                      ServerMonitorNotificationConfig config) {
+        // 获取SERVER_STATUS类型的有效规则（优先专属规则）
+        ServerAlertRule statusRule = getEffectiveRule(serverId, MonitorMetricEnum.SERVER_STATUS, allRules);
+        
+        if (statusRule == null) {
+            log.debug("未找到启用的服务器状态告警规则: serverId={}", serverId);
+            return;
+        }
+        
+        int warningCount = statusRule.getWarningThreshold().intValue();
+        int criticalCount = statusRule.getCriticalThreshold().intValue();
+        
+        log.debug("检查服务器状态告警: serverId={}, failureCount={}, warningCount={}, criticalCount={}", 
+            serverId, failureCount, warningCount, criticalCount);
+        
+        // 判断当前应该触发的告警级别
+        MonitorAlertLevelEnum currentLevel = null;
+        int threshold = 0;
+        
+        if (failureCount >= criticalCount) {
+            currentLevel = MonitorAlertLevelEnum.CRITICAL;
+            threshold = criticalCount;
+        } else if (failureCount >= warningCount) {
+            currentLevel = MonitorAlertLevelEnum.WARNING;
+            threshold = warningCount;
+        }
+        
+        // 查询是否已有活跃告警
+        Optional<ServerAlertLog> existingAlertOpt = alertLogRepository.findActiveOrPendingAlert(
+            serverId, statusRule.getId(), MonitorMetricEnum.SERVER_STATUS);
+        
+        if (currentLevel != null) {
+            // 需要触发告警
+            if (existingAlertOpt.isPresent()) {
+                // 已有告警，检查是否需要升级
+                ServerAlertLog existingAlert = existingAlertOpt.get();
+                if (currentLevel.ordinal() > existingAlert.getAlertLevel().ordinal()) {
+                    // 级别升级：WARNING → CRITICAL
+                    updateServerStatusAlertLevel(existingAlert, statusRule, currentLevel, 
+                        failureCount, threshold, config);
+                } else {
+                    log.debug("服务器状态告警已存在且级别未变化: serverId={}, level={}", 
+                        serverId, currentLevel);
+                }
+            } else {
+                // 创建新告警
+                createServerStatusAlert(serverId, statusRule, currentLevel, failureCount, threshold, config);
+            }
+        }
+    }
+
+    @Override
+    public void resolveServerStatusAlert(Long serverId) {
+        // 查询所有SERVER_STATUS类型的规则
+        List<ServerAlertRule> statusRules = alertRuleRepository.findAll().stream()
+            .filter(rule -> rule.getAlertType() == MonitorMetricEnum.SERVER_STATUS)
+            .collect(java.util.stream.Collectors.toList());
+        
+        for (ServerAlertRule rule : statusRules) {
+            Optional<ServerAlertLog> activeAlertOpt = alertLogRepository.findActiveOrPendingAlert(
+                serverId, rule.getId(), MonitorMetricEnum.SERVER_STATUS);
+            
+            if (activeAlertOpt.isPresent()) {
+                resolveAlert(activeAlertOpt.get());
+                log.info("✅ 服务器状态告警已解除: serverId={}, ruleId={}", serverId, rule.getId());
+            }
+        }
+    }
+
+    /**
+     * 获取有效规则（优先专属规则，其次全局规则）
+     */
+    private ServerAlertRule getEffectiveRule(Long serverId, MonitorMetricEnum alertType, 
+                                            List<ServerAlertRule> allRules) {
+        ServerAlertRule specificRule = null;
+        ServerAlertRule globalRule = null;
+        
+        for (ServerAlertRule rule : allRules) {
+            if (rule.getAlertType() != alertType || !Boolean.TRUE.equals(rule.getEnabled())) {
+                continue;
+            }
+            
+            if (serverId.equals(rule.getServerId())) {
+                specificRule = rule;
+                break; // 找到专属规则，直接返回
+            } else if (rule.getServerId() == null) {
+                globalRule = rule;
+            }
+        }
+        
+        return specificRule != null ? specificRule : globalRule;
+    }
+
+    /**
+     * 创建服务器状态告警
+     */
+    private void createServerStatusAlert(Long serverId, ServerAlertRule rule, 
+                                        MonitorAlertLevelEnum level, int failureCount, 
+                                        int threshold, ServerMonitorNotificationConfig config) {
+        Server server = serverRepository.findById(serverId).orElse(null);
+        if (server == null) {
+            log.warn("服务器不存在: serverId={}", serverId);
+            return;
+        }
+        
+        ServerAlertLog alertLog = new ServerAlertLog();
+        alertLog.setServerId(serverId);
+        alertLog.setRuleId(rule.getId());
+        alertLog.setAlertType(MonitorMetricEnum.SERVER_STATUS);
+        alertLog.setAlertLevel(level);
+        alertLog.setAlertValue(new BigDecimal(failureCount));
+        alertLog.setThresholdValue(new BigDecimal(threshold));
+        alertLog.setAlertTime(LocalDateTime.now());
+        alertLog.setStatus(ServerAlertStatusEnum.PENDING);
+        alertLog.setAlertMessage(String.format("服务器连续%d次连接失败，达到%s级别（阈值:%d次）", 
+            failureCount, level.getDescription(), threshold));
+        
+        try {
+            alertLogRepository.save(alertLog);
+            log.warn("🔔 服务器状态告警已创建: serverId={}, serverName={}, level={}, failureCount={}", 
+                serverId, server.getServerName(), level, failureCount);
+            
+            // 发送通知
+            sendServerStatusNotification(alertLog, server, config);
+        } catch (Exception e) {
+            log.error("创建服务器状态告警失败: serverId={}", serverId, e);
+        }
+    }
+
+    /**
+     * 更新服务器状态告警级别
+     */
+    private void updateServerStatusAlertLevel(ServerAlertLog alertLog, ServerAlertRule rule,
+                                             MonitorAlertLevelEnum newLevel, int failureCount, 
+                                             int threshold, ServerMonitorNotificationConfig config) {
+        Server server = serverRepository.findById(alertLog.getServerId()).orElse(null);
+        if (server == null) {
+            return;
+        }
+        
+        MonitorAlertLevelEnum oldLevel = alertLog.getAlertLevel();
+        alertLog.setAlertLevel(newLevel);
+        alertLog.setAlertValue(new BigDecimal(failureCount));
+        alertLog.setThresholdValue(new BigDecimal(threshold));
+        alertLog.setAlertMessage(String.format("服务器连续%d次连接失败，达到%s级别（阈值:%d次）", 
+            failureCount, newLevel.getDescription(), threshold));
+        
+        try {
+            alertLogRepository.save(alertLog);
+            log.warn("⬆️ 服务器状态告警级别升级: id={}, serverId={}, {} → {}, failureCount={}", 
+                alertLog.getId(), alertLog.getServerId(), oldLevel, newLevel, failureCount);
+            
+            // 重新发送通知
+            sendServerStatusNotification(alertLog, server, config);
+        } catch (Exception e) {
+            log.error("更新服务器状态告警级别失败", e);
+        }
+    }
+
+    /**
+     * 发送服务器状态通知
+     * 使用统一的资源告警模板（与CPU/内存/磁盘告警相同）
+     */
+    private void sendServerStatusNotification(ServerAlertLog alertLog, Server server, 
+                                             ServerMonitorNotificationConfig config) {
+        if (config == null || config.getNotificationChannelId() == null || 
+            config.getResourceAlertTemplateId() == null) {
+            log.debug("通知配置不完整，跳过发送服务器状态通知");
+            return;
+        }
+        
+        try {
+            // 查询规则信息
+            ServerAlertRule rule = alertRuleRepository.findById(alertLog.getRuleId()).orElse(null);
+            if (rule == null) {
+                log.warn("告警规则不存在: ruleId={}", alertLog.getRuleId());
+                return;
+            }
+            
+            // 构建模板参数（与其他监控告警保持一致）
+            Map<String, Object> templateParams = new HashMap<>();
+            templateParams.put("serverName", server.getServerName());
+            templateParams.put("ruleName", rule.getRuleName());
+            templateParams.put("alertType", rule.getAlertType().getDescription());
+            templateParams.put("resourceInfo", "服务器状态");
+            templateParams.put("alertLevel", alertLog.getAlertLevel().getDescription());
+            templateParams.put("currentValue", alertLog.getAlertValue().intValue());
+            templateParams.put("threshold", alertLog.getThresholdValue().intValue());
+            templateParams.put("alertTime", alertLog.getAlertTime().format(
+                java.time.format.DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss")));
+            
+            SendNotificationRequest request = new SendNotificationRequest();
+            request.setChannelId(config.getNotificationChannelId());
+            request.setNotificationTemplateId(config.getResourceAlertTemplateId());
+            request.setTemplateParams(templateParams);
+            
+            notificationService.send(request);
+            
+            // 更新通知状态
+            alertLog.setNotified(true);
+            alertLog.setNotifyTime(LocalDateTime.now());
+            alertLog.setStatus(ServerAlertStatusEnum.ACTIVE);
+            alertLogRepository.save(alertLog);
+            
+            log.info("✅ 服务器状态告警通知已发送: serverId={}, level={}", 
+                alertLog.getServerId(), alertLog.getAlertLevel());
+        } catch (Exception e) {
+            log.error("发送服务器状态通知异常: serverId={}", alertLog.getServerId(), e);
+        }
+    }
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/service/impl/ServerMonitorServiceImpl.java

@@ -6,8 +6,11 @@ import com.qqchen.deploy.backend.deploy.dto.ServerMonitorDataDTO;
 import com.qqchen.deploy.backend.deploy.entity.ServerMonitor;
 import com.qqchen.deploy.backend.deploy.repository.IServerMonitorRepository;
 import com.qqchen.deploy.backend.deploy.service.IServerMonitorService;
+import com.qqchen.deploy.backend.framework.enums.StatusEnum;
 import jakarta.annotation.Resource;
 import lombok.extern.slf4j.Slf4j;
+import org.springframework.data.domain.PageRequest;
+import org.springframework.data.domain.Pageable;
 import org.springframework.stereotype.Service;
 import org.springframework.transaction.annotation.Transactional;
 
@@ -80,6 +83,40 @@ public class ServerMonitorServiceImpl implements IServerMonitorService {
             .networkRx(dto.getNetworkRx())
             .networkTx(dto.getNetworkTx())
             .collectTime(dto.getCollectTime())
+            .status(StatusEnum.SUCCESS)  // 成功采集的记录
             .build();
     }
+
+    @Override
+    @Transactional
+    public void saveMonitorRecord(ServerMonitor monitor) {
+        monitorRepository.save(monitor);
+        log.debug("保存监控记录: serverId={}, status={}", monitor.getServerId(), monitor.getStatus());
+    }
+
+    @Override
+    public int countConsecutiveFailures(Long serverId, int checkLimit) {
+        // 查询最近N条记录
+        Pageable pageable = PageRequest.of(0, checkLimit);
+        List<ServerMonitor> recentRecords = monitorRepository.findRecentMonitorRecords(serverId, pageable);
+        
+        if (recentRecords == null || recentRecords.isEmpty()) {
+            log.debug("没有找到监控记录: serverId={}", serverId);
+            return 0;
+        }
+        
+        // 从最新记录开始统计连续失败次数
+        int failureCount = 0;
+        for (ServerMonitor record : recentRecords) {
+            if (StatusEnum.FAILURE.equals(record.getStatus())) {
+                failureCount++;
+            } else {
+                // 遇到成功记录，停止统计
+                break;
+            }
+        }
+        
+        log.debug("统计连续失败次数: serverId={}, count={}", serverId, failureCount);
+        return failureCount;
+    }
 }

backend/src/main/java/com/qqchen/deploy/backend/deploy/service/impl/ServerServiceImpl.java

@@ -8,6 +8,9 @@ import com.qqchen.deploy.backend.deploy.enums.ServerStatusEnum;
 import com.qqchen.deploy.backend.framework.enums.AuthTypeEnum;
 import com.qqchen.deploy.backend.deploy.query.ServerQuery;
 import com.qqchen.deploy.backend.deploy.repository.IServerRepository;
+import com.qqchen.deploy.backend.deploy.repository.IServerMonitorRepository;
+import com.qqchen.deploy.backend.deploy.repository.IServerAlertRuleRepository;
+import com.qqchen.deploy.backend.deploy.repository.IServerAlertLogRepository;
 import com.qqchen.deploy.backend.deploy.repository.ISSHAuditLogRepository;
 import com.qqchen.deploy.backend.deploy.service.IServerService;
 import com.qqchen.deploy.backend.framework.annotation.ServiceType;
@@ -43,6 +46,15 @@ public class ServerServiceImpl
     @Resource
     private ISSHAuditLogRepository sshAuditLogRepository;
     
+    @Resource
+    private IServerMonitorRepository serverMonitorRepository;
+    
+    @Resource
+    private IServerAlertRuleRepository serverAlertRuleRepository;
+    
+    @Resource
+    private IServerAlertLogRepository serverAlertLogRepository;
+
     public ServerServiceImpl(IServerRepository serverRepository) {
         this.serverRepository = serverRepository;
     }
@@ -247,6 +259,7 @@ public class ServerServiceImpl
      * @return 完整的硬件信息
      */
     @Override
+    @Transactional
     public ServerInfoDTO collectHardwareInfo(Long serverId) {
         long startTime = System.currentTimeMillis();
         ServerInfoDTO info = new ServerInfoDTO();
@@ -320,22 +333,46 @@ public class ServerServiceImpl
      * 1. 服务器：物理删除（没有@LogicDelete注解）
      * 2. 审计日志：逻辑删除（有@LogicDelete注解）
      * 3. 审计日志永久保留，仅标记deleted=true，确保审计可追溯
+     * 4. 监控记录、告警规则、告警记录：物理删除（无需保留历史）
      */
     @Override
     @Transactional
     public void delete(Long id) {
         log.info("删除服务器: serverId={}", id);
         
-        // 1. 逻辑删除关联的SSH审计日志（保留历史记录）
+        // 1. 物理删除关联的告警记录（需要先删除，因为它依赖告警规则）
+        try {
+            int alertLogCount = serverAlertLogRepository.deleteByServerId(id);
+            log.info("已删除服务器关联的告警记录: serverId={}, count={}", id, alertLogCount);
+        } catch (Exception e) {
+            log.warn("删除服务器关联的告警记录失败: serverId={}, error={}", id, e.getMessage());
+        }
+        
+        // 2. 物理删除关联的告警规则
+        try {
+            int alertRuleCount = serverAlertRuleRepository.deleteByServerId(id);
+            log.info("已删除服务器关联的告警规则: serverId={}, count={}", id, alertRuleCount);
+        } catch (Exception e) {
+            log.warn("删除服务器关联的告警规则失败: serverId={}, error={}", id, e.getMessage());
+        }
+        
+        // 3. 物理删除关联的监控记录
+        try {
+            int monitorCount = serverMonitorRepository.deleteByServerId(id);
+            log.info("已删除服务器关联的监控记录: serverId={}, count={}", id, monitorCount);
+        } catch (Exception e) {
+            log.warn("删除服务器关联的监控记录失败: serverId={}, error={}", id, e.getMessage());
+        }
+        
+        // 4. 逻辑删除关联的SSH审计日志（保留历史记录）
         try {
             sshAuditLogRepository.deleteByServerId(id);
             log.info("已逻辑删除服务器关联的SSH审计日志: serverId={}", id);
         } catch (Exception e) {
             log.warn("逻辑删除服务器关联的SSH审计日志失败: serverId={}, error={}", id, e.getMessage());
-            // 继续执行，即使审计日志删除失败也要删除服务器
         }
         
-        // 2. 物理删除服务器
+        // 5. 物理删除服务器
         super.delete(id);
         log.info("服务器删除成功: serverId={}", id);
     }

backend/src/main/java/com/qqchen/deploy/backend/framework/enums/MonitorMetricEnum.java

@@ -31,7 +31,14 @@ public enum MonitorMetricEnum {
     /**
      * 网络告警（MB/s）
      */
-    NETWORK("NETWORK", "网络使用率", "MB/s");
+    NETWORK("NETWORK", "网络使用率", "MB/s"),
+    
+    /**
+     * 服务器状态告警（次数）
+     * warningThreshold: 警告级别的连续失败次数
+     * criticalThreshold: 严重级别的连续失败次数（标记离线）
+     */
+    SERVER_STATUS("SERVER_STATUS", "服务器状态", "次");
     
     private final String code;
     private final String description;

backend/src/main/java/com/qqchen/deploy/backend/framework/enums/StatusEnum.java

@@ -0,0 +1,28 @@
+package com.qqchen.deploy.backend.framework.enums;
+
+import lombok.AllArgsConstructor;
+import lombok.Getter;
+
+/**
+ * 状态枚举
+ * Framework 提供的通用状态类型，适用于监控数据采集、任务执行等场景
+ *
+ * @author qqchen
+ * @since 2025-12-10
+ */
+@Getter
+@AllArgsConstructor
+public enum StatusEnum {
+    /**
+     * 成功
+     */
+    SUCCESS("SUCCESS", "成功"),
+    
+    /**
+     * 失败
+     */
+    FAILURE("FAILURE", "失败");
+    
+    private final String code;
+    private final String description;
+}

backend/src/main/resources/db/changelog/init/v1.0.0-data.sql

@@ -28,7 +28,8 @@ VALUES
 (12, NOW(), 'wangdongzhu', '$2a$10$OErv/EvBXUocMutXZJe3C.k1gq9/8rrF63pz8mWRBLoORGb/8ELIO', '王栋柱', 'wangdongzhu@iscmtech.com', NULL, 5, 1),
 (13, NOW(), 'yangzhenfu', '$2a$10$.WBc0pXTQnrDn2IUm.eRneH9jfu7TIZg2na.K3WaluvjIEts2Iasm', '杨振夫', 'yangzhenfu@iscmtech.com', '15842461837', 5, 1),
 (14, NOW(), 'songwei', '$2a$10$8ChswMOtgkvZCGsa/wvMM.wfhL5NL9uqCasyHZ6hiDG45vFu/EQRG', '宋伟', 'songwei@iscmtech.com', NULL, 5, 1),
-(15, NOW(), 'lukuan', '$2a$10$hlDCAqOWxZso7APbMClF1.Fp6xhnb8av5s.MDnC1tf0QfHfZRayNq', '路宽', 'lukuan@babyfs.cn', '13888888888', 7, 1);
+(15, NOW(), 'lukuan', '$2a$10$hlDCAqOWxZso7APbMClF1.Fp6xhnb8av5s.MDnC1tf0QfHfZRayNq', '路宽', 'lukuan@babyfs.cn', '13888888888', 7, 1),
+(16, NOW(), 'yangfan', '$2a$10$hYdpTUGG3q3Og2OA2uE39.5CnBDeUQRyqsM5OwoKUSWj2ZJUdOb0u', '杨帆', 'yangfan@iscmtech.com', NULL, 5, 1);
 
 -- 初始化系统参数
 INSERT INTO sys_param (id, create_time, code, name, value, type, description, enabled)
@@ -145,7 +146,9 @@ VALUES
 (12, 3),  -- wangdongzhu - 开发
 (13, 3),  -- yangzhenfu - 开发
 (14, 1),  -- songwei - 管理员
-(15, 3);  -- lukuan - 开发
+(15, 3),  -- lukuan - 开发
+(16, 1),  -- yangfan - 管理员
+(16, 2);  -- yangfan - 运维
 
 -- 初始化角色菜单关联
 INSERT INTO sys_role_menu (role_id, menu_id)
@@ -671,6 +674,10 @@ INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_
 INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (20, 'datax-admin', 'datax-admin', '', 0, 1, b'1', 0, 'songwei', NOW(), 'songwei', NOW(), 1, b'0');
 INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (21, 'scp-algorithm', 'scp-algorithm', '', 0, 1, b'1', 0, 'songwei', NOW(), 'songwei', NOW(), 1, b'0');
 INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (22, 'scp-forecast-model', 'scp-forecast-model', '', 2, 1, b'1', 0, 'songwei', NOW(), 'songwei', NOW(), 1, b'0');
+INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (23, 'etl-ignite-server', 'etl-ignite-server', '内存数据库', 0, 2, b'1', 0, 'admin', NOW(), 'admin', NOW(), 1, b'0');
+INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (24, 'etl-integration-ui-server', 'etl-integration-ui-server', 'UI server', 0, 2, b'1', 0, 'admin', NOW(), 'admin', NOW(), 1, b'0');
+INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (25, 'etl-executor', 'etl-executor', 'etl执行器', 0, 2, b'1', 0, 'admin', NOW(), 'admin', NOW(), 1, b'0');
+INSERT INTO `deploy-ease-platform`.`deploy_application` (`id`, `app_code`, `app_name`, `app_desc`, `language`, `application_category_id`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (26, 'etl-scheduler', 'etl-scheduler', 'etl调度器', 0, 2, b'1', 0, 'admin', NOW(), 'admin', NOW(), 1, b'0');
 
 
 INSERT INTO `deploy-ease-platform`.`deploy_environment` (`id`, `tenant_code`, `env_code`, `env_name`, `env_desc`, `enabled`, `sort`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`) VALUES (1, NULL, 'LONGI-DEV', '隆基DEV', NULL, b'1', 1, 'admin', NOW(), 'admin', NOW(), 2, b'0');
@@ -756,6 +763,11 @@ INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`,
 INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `application_id`, `environment_id`, `build_type`, `source_git_system_id`, `source_git_project_id`, `source_branch`, `target_git_system_id`, `target_git_project_id`, `target_branch`, `deploy_system_id`, `deploy_job`, `workflow_definition_id`) VALUES (81, 'songwei', NOW(), 'songwei', NOW(), 1, b'0', 3, 6, 7, 'JENKINS', 2, 300, 'feature/upgrade', NULL, NULL, NULL, 1, 'lixiang-scp-ws', 1);
 INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `application_id`, `environment_id`, `build_type`, `source_git_system_id`, `source_git_project_id`, `source_branch`, `target_git_system_id`, `target_git_project_id`, `target_branch`, `deploy_system_id`, `deploy_job`, `workflow_definition_id`) VALUES (82, 'songwei', NOW(), 'songwei', NOW(), 1, b'0', 3, 17, 7, 'JENKINS', 2, 636, 'develop', NULL, NULL, NULL, 1, 'pro-scp-xxl-job', 1);
 
+INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `application_id`, `environment_id`, `build_type`, `source_git_system_id`, `source_git_project_id`, `source_branch`, `target_git_system_id`, `target_git_project_id`, `target_branch`, `deploy_system_id`, `deploy_job`, `workflow_definition_id`) VALUES (83, 'admin', NOW(), 'admin', NOW(), 1, b'0', 5, 23, 5, 'NATIVE', 6, 7, 'release/1.0-localization', NULL, NULL, NULL, NULL, '', 2);
+INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `application_id`, `environment_id`, `build_type`, `source_git_system_id`, `source_git_project_id`, `source_branch`, `target_git_system_id`, `target_git_project_id`, `target_branch`, `deploy_system_id`, `deploy_job`, `workflow_definition_id`) VALUES (84, 'admin', NOW(), 'admin', NOW(), 1, b'0', 5, 26, 5, 'JENKINS', 6, 7, 'release/1.0-localization', NULL, NULL, NULL, NULL, '', 2);
+INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `application_id`, `environment_id`, `build_type`, `source_git_system_id`, `source_git_project_id`, `source_branch`, `target_git_system_id`, `target_git_project_id`, `target_branch`, `deploy_system_id`, `deploy_job`, `workflow_definition_id`) VALUES (85, 'admin', NOW(), 'admin', NOW(), 1, b'0', 5, 25, 5, 'NATIVE', 6, 7, 'release/1.0-localization', NULL, NULL, NULL, NULL, '', 2);
+INSERT INTO `deploy-ease-platform`.`deploy_team_application` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `application_id`, `environment_id`, `build_type`, `source_git_system_id`, `source_git_project_id`, `source_branch`, `target_git_system_id`, `target_git_project_id`, `target_branch`, `deploy_system_id`, `deploy_job`, `workflow_definition_id`) VALUES (86, 'admin', NOW(), 'admin', NOW(), 1, b'0', 5, 24, 5, 'NATIVE', 6, 7, 'release/1.0-localization', NULL, NULL, NULL, NULL, '', 2);
+
 INSERT INTO `deploy-ease-platform`.`deploy_team_environment_config` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `environment_id`, `approval_required`, `approver_user_ids`, `require_code_review`, `remark`) VALUES (8, 'admin', NOW(), 'admin', NOW(), 1, b'0', 5, 5, b'0', NULL, b'0', '');
 INSERT INTO `deploy-ease-platform`.`deploy_team_environment_config` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `environment_id`, `approval_required`, `approver_user_ids`, `require_code_review`, `remark`) VALUES (9, 'admin', NOW(), 'admin', NOW(), 1, b'0', 4, 1, b'0', NULL, b'0', '');
 INSERT INTO `deploy-ease-platform`.`deploy_team_environment_config` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `team_id`, `environment_id`, `approval_required`, `approver_user_ids`, `require_code_review`, `remark`) VALUES (10, 'admin', NOW(), 'admin', NOW(), 1, b'0', 4, 2, b'1', '[6]', b'0', '');
@@ -831,8 +843,8 @@ INSERT INTO `deploy-ease-platform`.`sys_notification_channel` (`id`, `create_by`
 INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (8, 'admin', NOW(), 'dengqichen', NOW(), 36, b'0', 'JENKINS构建状态通知', 'jenkins_build_notification', '', 'WEWORK', '## <#if environmentName??>${environmentName}</#if>环境构建通知', '>项目：<#if applicationName??><font>${applicationName}(${applicationCode})</font></#if>\r\n<#if buildStatus??>\r\n<#switch buildStatus>\r\n<#case \"SUCCESS\">\r\n>状态：<font color=\"info\">构建成功</font>\r\n<#break>\r\n<#case \"BUILDING\">\r\n>状态：<font color=\"comment\">构建中</font>\r\n<#break>\r\n<#case \"ABORTED\">\r\n>状态：<font color=\"warning\">构建被取消</font>\r\n<#break>\r\n<#default>\r\n>状态：<font color=\"warning\">构建失败</font>\r\n</#switch>\r\n</#if>\r\n<#if buildStatus?? && buildStatus != \"BUILDING\">\r\n<#if buildDurationFormatted??>\r\n>耗时：${buildDurationFormatted}\r\n</#if>\r\n<#if buildEndTime??>\r\n>时间：${buildEndTime}\r\n</#if>\r\n<#else>\r\n<#if buildStartTime??>\r\n>时间：${buildStartTime}\r\n</#if>\r\n</#if>\r\n<#if commitMessage??>\r\n>内容：\r\n<#list commitMessage?split(\'\\n\') as line>\r\n>${line}\r\n</#list>\r\n</#if>', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
 INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (9, 'admin', NOW(), 'admin', NOW(), 10, b'0', '国产化构建通知', 'localization_build_notification', '国产化模版', 'WEWORK', '## <#if environmentName??>${environmentName}</#if>环境变更通知', '>项目：<#if applicationName??><font>${applicationName}(${applicationCode})</font></#if>\r\n<#-- 通过判断HTTP节点输出是否存在来区分阶段 -->\r\n<#if sid_d7bd35dc_37cc_4868_9c8a_9c854d5d6bbf?? && sid_d7bd35dc_37cc_4868_9c8a_9c854d5d6bbf.outputs??>\r\n<#-- ========== 构建结束阶段（HTTP节点已执行）========== -->\r\n<#assign httpOutput = sid_d7bd35dc_37cc_4868_9c8a_9c854d5d6bbf.outputs>\r\n<#if httpOutput.isSuccess!false>\r\n<#if httpOutput.responseBody?? && httpOutput.responseBody.status?? && httpOutput.responseBody.status == \"success\">\r\n>状态：<font color=\"info\">构建成功</font>\r\n<#if httpOutput.responseBody.duration??>\r\n>耗时：${httpOutput.responseBody.duration}秒\r\n</#if>\r\n<#if httpOutput.responseBody.endTime??>\r\n>时间：${httpOutput.responseBody.endTime}\r\n</#if>\r\n<#else>\r\n>状态：<font color=\"warning\">构建失败</font>\r\n<#if httpOutput.responseBody?? && httpOutput.responseBody.error??>\r\n>错误：${httpOutput.responseBody.error}\r\n</#if>\r\n</#if>\r\n<#else>\r\n>状态：<font color=\"warning\">构建失败</font>\r\n<#if httpOutput.statusCode?? && httpOutput.statusCode gt 0>\r\n>HTTP状态码：${httpOutput.statusCode}\r\n<#else>\r\n>错误类型：网络连接异常\r\n</#if>\r\n<#if httpOutput.errorMessage??>\r\n>错误详情：${httpOutput.errorMessage}\r\n</#if>\r\n<#if httpOutput.responseTime??>\r\n>请求耗时：${httpOutput.responseTime}ms\r\n</#if>\r\n</#if>\r\n<#else>\r\n<#-- ========== 构建中阶段（HTTP节点未执行）========== -->\r\n>状态：<font color=\"comment\">构建中</font>\r\n<#if deployDate??>\r\n<#attempt>\r\n<#assign deployDateTime = deployDate?datetime.iso>\r\n>时间：${deployDateTime?string(\"yyyy-MM-dd HH:mm:ss\")}\r\n<#recover>\r\n>时间：${deployDate}\r\n</#attempt>\r\n</#if>\r\n</#if>\r\n>内容：<#if deployRemark??><font>${deployRemark}</font><#else>无构建内容</#if>\r\n', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
 INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (10, 'admin', NOW(), 'admin', NOW(), 3, b'0', 'Git同步检测通知', 'git_sync_code_check_notification', '', 'WEWORK', '## 代码同步检查异常', '${sid_e5f930da_062e_4819_b976_8d8172c7f14a.outputs.checkDetail}', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
-INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (11, 'admin', NOW(), 'dengqichen', NOW(), 5, b'0', '服务器阈值预警通知', 'server_threshold_warning_notification', '', 'WEWORK', '## 服务器（${resourceInfo}）${alertLevel}通知', '> 服务器：${serverName}\r\n> 告警规则：${ruleName}-${alertType}\r\n> 当前值：<font color=\"warning\">${currentValue}%</font>，阈值：${threshold}%\r\n> 告警时间：${alertTime}\r\n\r\n请及时处理告警信息！', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
+INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (11, 'admin', NOW(), 'admin', NOW(), 8, b'0', '服务器阈值预警通知', 'server_threshold_warning_notification', '', 'WEWORK', '> 服务器：**${serverName}**', '> 规则：${ruleName}（${alertType}）\r\n<#if alertType == \"服务器状态\">\r\n> 状态：<font color=\"warning\">连续失败 ${currentValue} 次</font>，阈值 ${threshold} 次\r\n<#else>\r\n> 使用率：<font color=\"warning\">${currentValue}%</font>，阈值 ${threshold}%\r\n</#if>\r\n<#if alertLevel == \"严重\">\r\n> 级别：<font color=\"warning\">🔴 严重</font>\r\n<#else>\r\n> 级别：⚠️ 警告\r\n</#if>\r\n> 时间：${alertTime}\r\n<#if alertLevel == \"严重\">\r\n<font color=\"warning\">**⚠️ 请立即处理告警信息！**</font>\r\n<#else>\r\n请注意观察，及时处理告警信息。\r\n</#if>', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
-INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (12, 'admin', NOW(), 'dengqichen', NOW(), 2, b'0', '服务器离线预警', 'server_offline_warning_notification', '', 'WEWORK', '## 服务器离线通知', '> 服务器名称：${serverName}\r\n\r\n**离线详情**\r\n> 检测时间：${offlineTime}\r\n> 状态：<font color=\"warning\">服务器无法访问</font>\r\n\r\n请立即处理服务器离线问题！', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
+INSERT INTO `deploy-ease-platform`.`sys_notification_template` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `name`, `code`, `description`, `channel_type`, `title_template`, `content_template`, `enabled`, `template_config`) VALUES (12, 'admin', NOW(), 'admin', NOW(), 4, b'1', '服务器离线预警', 'server_offline_warning_notification', '', 'WEWORK', '## 服务器离线告警', '> 检测服务器名称为：${serverName}，当前处于离线状态\r\n> 检测时间：${offlineTime}\r\n\r\n请确认是否存在服务器问题', b'1', '{\"channelType\": \"WEWORK\", \"messageType\": \"MARKDOWN\"}');
 
 INSERT INTO `deploy-ease-platform`.`schedule_job_category` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `code`, `name`, `description`, `icon`, `color`, `enabled`, `sort`) VALUES (1, 'system', NOW(), 'system', NOW(), 1, b'0', 'DATA_CLEAN', '数据清理', '定期清理系统历史数据和临时文件', 'DeleteOutlined', '#ff4d4f', b'1', 1);
 INSERT INTO `deploy-ease-platform`.`schedule_job_category` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `code`, `name`, `description`, `icon`, `color`, `enabled`, `sort`) VALUES (2, 'system', NOW(), 'system', NOW(), 1, b'0', 'DATA_SYNC', '数据同步', '同步外部系统数据到本地', 'SyncOutlined', '#1890ff', b'1', 2);
@@ -853,8 +865,7 @@ INSERT INTO `deploy-ease-platform`.`schedule_job` (`id`, `create_by`, `create_ti
 INSERT INTO `deploy-ease-platform`.`schedule_job` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `job_name`, `job_description`, `category_id`, `bean_name`, `method_name`, `form_definition_id`, `method_params`, `cron_expression`, `status`, `concurrent`, `last_execute_time`, `next_execute_time`, `execute_count`, `success_count`, `fail_count`, `timeout_seconds`, `retry_count`, `alert_email`) VALUES (14, 'admin', NOW(), 'admin', NOW(), 27, b'0', '隆基Git仓库组同步', '定期同步Git仓库组信息，每天凌晨2点执行', 2, 'repositoryGroupServiceImpl', 'syncGroups', NULL, '{\"externalSystemId\": 4}', '0 0 3 * * ?', 'DISABLED', b'0', NOW(), NOW(), 0, 0, 0, 3600, 2, '');
 INSERT INTO `deploy-ease-platform`.`schedule_job` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `job_name`, `job_description`, `category_id`, `bean_name`, `method_name`, `form_definition_id`, `method_params`, `cron_expression`, `status`, `concurrent`, `last_execute_time`, `next_execute_time`, `execute_count`, `success_count`, `fail_count`, `timeout_seconds`, `retry_count`, `alert_email`) VALUES (15, 'admin', NOW(), 'admin', NOW(), 1212, b'0', '隆基Git项目同步', '定期同步Git项目信息，每天凌晨3点执行', 2, 'repositoryProjectServiceImpl', 'syncProjects', NULL, '{\"externalSystemId\": 4}', '0 */5 * * * ?', 'DISABLED', b'0', NOW(), NOW(), 7, 7, 0, 3600, 2, '');
 INSERT INTO `deploy-ease-platform`.`schedule_job` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `job_name`, `job_description`, `category_id`, `bean_name`, `method_name`, `form_definition_id`, `method_params`, `cron_expression`, `status`, `concurrent`, `last_execute_time`, `next_execute_time`, `execute_count`, `success_count`, `fail_count`, `timeout_seconds`, `retry_count`, `alert_email`) VALUES (16, 'admin', NOW(), 'admin', NOW(), 5727, b'0', '隆基Git分支同步', '定期同步Git仓库分支信息，每5分钟执行一次', 2, 'repositoryBranchServiceImpl', 'syncBranches', NULL, '{\"externalSystemId\": 4}', '0 */5 * * * ?', 'DISABLED', b'0', NOW(), NOW(), 7, 7, 0, 3600, 2, '');
-INSERT INTO `deploy-ease-platform`.`schedule_job` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `job_name`, `job_description`, `category_id`, `bean_name`, `method_name`, `form_definition_id`, `method_params`, `cron_expression`, `status`, `concurrent`, `last_execute_time`, `next_execute_time`, `execute_count`, `success_count`, `fail_count`, `timeout_seconds`, `retry_count`, `alert_email`) VALUES (17, 'admin', NOW(), 'admin', NOW(), 20, b'0', '服务器预警', '', 4, 'serverMonitorScheduler', 'collectServerMetrics', NULL, '{\"notificationChannelId\": 5, \"serverOfflineTemplateId\": 12, \"resourceAlertTemplateId\": 11}', '0 */5 * * * ?', 'DISABLED', b'0', NOW(), NOW(), 15, 15, 0, 300, 0, '');
+INSERT INTO `deploy-ease-platform`.`schedule_job` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `job_name`, `job_description`, `category_id`, `bean_name`, `method_name`, `form_definition_id`, `method_params`, `cron_expression`, `status`, `concurrent`, `last_execute_time`, `next_execute_time`, `execute_count`, `success_count`, `fail_count`, `timeout_seconds`, `retry_count`, `alert_email`) VALUES (17, 'admin', NOW(), 'admin', NOW(), 49, b'0', '服务器预警', '', 4, 'serverMonitorScheduler', 'collectServerMetrics', NULL, '{\"notificationChannelId\": 5, \"resourceAlertTemplateId\": 11}', '0 */5 * * * ?', 'DISABLED', b'0', NOW(), NULL, 39, 38, 1, 300, 0, '');
-
 
 
 -- 全局告警规则
@@ -862,3 +873,4 @@ INSERT INTO `deploy-ease-platform`.`deploy_server_alert_rule` (`id`, `create_by`
 INSERT INTO `deploy-ease-platform`.`deploy_server_alert_rule` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `server_id`, `rule_name`, `alert_type`, `warning_threshold`, `critical_threshold`, `duration_minutes`, `enabled`, `description`) VALUES (2, NULL, NOW(), NULL, NOW(), 0, 0, NULL, '全局内存告警规则', 'MEMORY', 75.00, 90.00, 5, 1, '全局规则：内存使用率超过75%触发警告，超过90%触发严重告警');
 INSERT INTO `deploy-ease-platform`.`deploy_server_alert_rule` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `server_id`, `rule_name`, `alert_type`, `warning_threshold`, `critical_threshold`, `duration_minutes`, `enabled`, `description`) VALUES (3, NULL, NOW(), NULL, NOW(), 0, 0, NULL, '全局磁盘告警规则', 'DISK', 80.00, 90.00, 5, 1, '全局规则：磁盘使用率超过80%触发警告，超过90%触发严重告警');
 INSERT INTO `deploy-ease-platform`.`deploy_server_alert_rule` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `server_id`, `rule_name`, `alert_type`, `warning_threshold`, `critical_threshold`, `duration_minutes`, `enabled`, `description`) VALUES (4, NULL, NOW(), NULL, NOW(), 0, 0, NULL, '全局网络流量告警规则', 'NETWORK', 100.00, 200.00, 5, 0, '全局规则：网络流量超过100MB/s触发警告，超过200MB/s触发严重告警（默认禁用，需根据实际带宽调整）');
+INSERT INTO `deploy-ease-platform`.`deploy_server_alert_rule` (`id`, `create_by`, `create_time`, `update_by`, `update_time`, `version`, `deleted`, `server_id`, `rule_name`, `alert_type`, `warning_threshold`, `critical_threshold`, `duration_minutes`, `enabled`, `description`) VALUES (5, NULL, NOW(), NULL, NOW(), 0, 0, NULL, '全局服务器状态告警规则', 'SERVER_STATUS', 3.00, 5.00, 5, 1, '全局规则：连续3次检测失败触发警告，连续5次触发严重告警并标记服务器离线');

backend/src/main/resources/db/changelog/init/v1.0.0-schema.sql

@@ -1178,6 +1178,9 @@ CREATE TABLE deploy_server_monitor
     -- 采集时间
     collect_time  DATETIME NOT NULL COMMENT '采集时间',
     
+    -- 采集状态
+    status        VARCHAR(20) NOT NULL DEFAULT 'SUCCESS' COMMENT '采集状态：SUCCESS-成功, FAILURE-失败',
+    
     INDEX idx_server_time (server_id, collect_time),
     INDEX idx_collect_time (collect_time),
     CONSTRAINT fk_monitor_server FOREIGN KEY (server_id) REFERENCES deploy_server (id)

backend/src/main/resources/db/changelog/sql/20251209141300-01.sql

@@ -12,22 +12,36 @@ INSERT INTO system_release (
 )
 VALUES (
     'system', NOW(), 'system', NOW(), 1, 0,
-    1.13, 'ALL', NOW(),
+    1.15, 'ALL', NOW(),
     '【后端】
-- 日志优化：生产环境日志级别调整（空结果/开始/详细过程→DEBUG，减少冗余输出）
+新增：服务器离线告警连续失败检测机制（避免临时网络波动误报）
-- 连接池优化：HikariCP泄漏检测阈值调整为35分钟（匹配Jenkins构建轮询时长）
+    - 数据库：deploy_server_monitor 表增加 status 字段记录采集状态（SUCCESS/FAILURE）
-- SSH日志优化：SSHJ底层日志降级为WARN（屏蔽Transport/SecureRandom等无业务价值日志）
+    - 框架层：新增 StatusEnum 通用状态枚举类，MonitorMetricEnum 增加 SERVER_STATUS 监控类型
-- 监控日志优化：服务器连接成功日志提升为INFO（便于生产环境状态监控）
+    - 实体层：ServerMonitor 实体增加 status 字段用于标识采集状态
-- Liquibase优化：目录结构调整（XML/SQL分离，changes/只放XML，sql/只放SQL，避免重复执行）
+    - Repository：IServerMonitorRepository 增加 findRecentMonitorRecords 方法查询最近N条监控记录
-- Security优化：白名单配置化（SecurityConfig/JwtAuthenticationFilter统一使用配置文件管理免认证路径）
+    - Service：IServerMonitorService 增加 saveMonitorRecord（保存单条记录）和 countConsecutiveFailures（统计连续失败次数）方法
-- 系统监控：新增"系统指标"菜单（实时查看JVM、CPU、内存、线程、连接池等性能指标）
+    - 告警服务：IServerAlertService 增加 checkServerStatusAlert（检查状态告警）和 resolveServerStatusAlert（解除状态告警）方法
-- Actuator集成：开放监控端点（health/metrics/threaddump/heapdump/env/loggers，支持动态调整日志级别）
+    - 告警实现：ServerAlertServiceImpl 实现服务器状态告警的创建、级别升级（WARNING→CRITICAL）、自动解除逻辑
-- 配置管理：新增SecurityWhitelistProperties配置类（集中管理Security白名单，支持环境差异化配置）
+    - 调度器：ServerMonitorScheduler 集成连续失败检测，连接成功时插入SUCCESS记录并解除告警，连接失败时插入FAILURE记录并触发告警检测
+    - 数据初始化：增加全局服务器状态告警规则（连续3次失败触发警告，5次触发严重并标记离线）
+
+优化：统一监控告警通知模板，简化配置参数
+    - ServerMonitorNotificationConfig 删除 serverOfflineTemplateId 字段，所有监控告警（CPU/内存/磁盘/网络/服务器状态）统一使用 resourceAlertTemplateId
+    - ServerMonitorScheduler.collectServerMetrics 方法删除 serverOfflineTemplateId 参数
+    - ServerAlertServiceImpl.sendServerStatusNotification 改用统一的资源告警模板，模板参数与其他监控告警保持一致
+
+修复：删除冗余代码和未使用的类
+    - 删除 CollectionStatusEnum.java（已被 StatusEnum 取代）
+    - 删除 ServerMonitorScheduler.sendServerOfflineNotification 方法（改由 ServerAlertService 统一处理）
+
+优化：告警通知模板支持百分比和次数两种单位
+    - 通知模板使用 FreeMarker 条件判断，根据 alertType 自动显示"连续失败X次"或"使用率X%"
+    - 严重级别告警显示红色并提示"请立即处理"，警告级别提示"请注意观察"
+    
     【前端】
-- 新增：系统指标监控页面（实时监控JVM内存、CPU、线程、连接池、GC，30秒自动刷新）
+修复：告警规则表单规则范围下拉框无法滚动选择问题（移除嵌套滚动容器干扰）
-- 新增：线程分析工具（状态筛选、智能排序、堆栈展开、问题线程识别、一键导出含堆栈）
+优化：规则范围选择器升级为带搜索的Popover组件（支持按服务器名称/IP搜索，固定高度可滚动）
-- 优化：内存单位统一为GB（图表、趋势图、卡片全局一致，清理历史数据）
+优化：规则范围数据加载从分页接口改为列表接口
-- 修复：Actuator接口代理和调用方式（新增/actuator代理配置）
 ',
     0, NULL, NULL, 0
 );