feat: 监控告警体系统一重构 + 自动化任务调度引擎 + 监控大屏拆分

告警中心
- 新增统一告警(alert_unified)、监控告警规则(monitor_alert_rule)、指标目录(alert_metric_catalog)
- 通知策略与消息分发(alert_notify_policy/dispatch/message)、静默规则
- 告警引擎按阈值/SNMP 拆分(alert_engine_monitor/snmp)

监控采集
- SNMP 常量/模板与历史指标(snmp templates/constants、snmp_metrics_history、snmp_collect)
- 中间件监控 Redis 采集与种子(middleware_monitor_redis/seed)
- 站点探测 pkg(siteprobe) + 站点视图(site_view)

自动化任务
- cron 调度器(cronscheduler)、脚本运行器(scriptrunner)、系统任务(systask)及运行记录(cron_job_run、system_task)

审计与凭证
- 审计设置(audit_setting) + 历史清理(auditcleaner)

前端
- 监控页面(host/middleware/site/snmp)拆分为子模块并大屏化
- 告警中心多 Tab(规则/指标目录/通知策略/静默)、任务管理组件重构、Agent CLI Markdown 渲染
- 移除旧脚本卡片/详情/日志组件,统一为 ScriptTable/ScriptCodeEditor/TerminalOutput

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
LoganandClaude committed 2026-07-01 23:44:45 +08:00
1 parent 092d0e4b9e
commit 471353e3d7
190 files changed
+16640 -3484

No files matched your search

+29 -2
View File
@@ -97,16 +97,44 @@ func (h *DashboardHandler) GetStats(c *gin.Context) {
h.db.Model(&model.KubernetesCluster{}).Where("status = ?", "warning").Count(&k8sStats.Warning)
h.db.Model(&model.KubernetesCluster{}).Where("status = ?", "error").Count(&k8sStats.Error)
var totalNodes, totalPods, totalServices int64
var totalNodes, totalPods, totalServices, totalIngresses, totalDeployments int64
h.db.Model(&model.KubernetesNode{}).Count(&totalNodes)
h.db.Model(&model.KubernetesPod{}).Count(&totalPods)
h.db.Model(&model.KubernetesService{}).Count(&totalServices)
h.db.Model(&model.KubernetesIngress{}).Count(&totalIngresses)
h.db.Model(&model.KubernetesDeployment{}).Count(&totalDeployments)
k8sStats.TotalNodes = totalNodes
k8sStats.TotalPods = totalPods
k8sStats.TotalServices = totalServices
k8sStats.TotalIngresses = totalIngresses
k8sStats.TotalDeployments = totalDeployments
stats.K8sStats = k8sStats
today := time.Now().Format("2006-01-02")
// 自动化运维统计 // Logan.Li
var automationStats model.AutomationStats
h.db.Model(&model.CronJob{}).Count(&automationStats.CronJobCount)
h.db.Model(&model.Script{}).Count(&automationStats.ScriptCount)
h.db.Model(&model.TaskExecution{}).Where("DATE(created_at) = ?", today).Count(&automationStats.TodayExecutions)
var successExec, totalExec int64
h.db.Model(&model.TaskExecution{}).Where("status = ?", "success").Count(&successExec)
h.db.Model(&model.TaskExecution{}).Count(&totalExec)
if totalExec > 0 {
automationStats.SuccessRate = math.Round(float64(successExec)/float64(totalExec)*10000) / 100
}
stats.AutomationStats = automationStats
// 运维概览:拨测 / 中间件 / SNMP // Logan.Li
var opsStats model.OpsOverviewStats
h.db.Model(&model.Domain{}).Count(&opsStats.DomainCount)
h.db.Model(&model.SiteTask{}).Count(&opsStats.SiteTaskCount)
h.db.Model(&model.MonitorTarget{}).Where("description IN ?", []string{"redis", "mysql"}).Count(&opsStats.MiddlewareCount)
h.db.Model(&model.SNMPDevice{}).Count(&opsStats.SnmpDeviceCount)
h.db.Model(&model.MonitorTarget{}).Count(&opsStats.MonitorTargetCount)
stats.OpsStats = opsStats
// 告警统计
var alertStats model.AlertStats
h.db.Model(&model.AlertEvent{}).Count(&alertStats.Total)
@@ -117,7 +145,6 @@ func (h *DashboardHandler) GetStats(c *gin.Context) {
h.db.Model(&model.AlertEvent{}).Where("severity = ?", "info").Count(&alertStats.Info)
// 今日告警
today := time.Now().Format("2006-01-02")
h.db.Model(&model.AlertEvent{}).Where("DATE(created_at) = ?", today).Count(&alertStats.TodayCount)
// 本周告警