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

+25 -31
View File
@@ -16,6 +16,7 @@ import (
"ezops/model"
"github.com/gin-gonic/gin"
"gorm.io/gorm"
)
// 通知渠道 CRUD(AlertHandler 方法接收者,与 alert.go 同包共享) // Logan.Li
@@ -198,7 +199,7 @@ func (h *AlertHandler) TestNotifyChannel(c *gin.Context) {
switch channel.Type {
case "feishu":
err := sendFeishuTest(channel.Config)
err := sendFeishuTest(h.db, channel.Config)
if err != nil {
status = "error"
message = "飞书通知发送失败: " + err.Error()
@@ -226,8 +227,8 @@ func (h *AlertHandler) TestNotifyChannel(c *gin.Context) {
// ==================== 飞书 Webhook 发送逻辑 ====================
// sendFeishuTest 发送飞书测试通知
func sendFeishuTest(configJSON string) error {
// sendFeishuTest 发送飞书测试通知 // Logan.Li
func sendFeishuTest(db *gorm.DB, configJSON string) error {
var cfg model.FeishuWebhookConfig
if err := json.Unmarshal([]byte(configJSON), &cfg); err != nil {
return fmt.Errorf("解析配置失败: %w", err)
@@ -239,11 +240,11 @@ func sendFeishuTest(configJSON string) error {
title := "✅ AIOps 告警测试通知"
content := fmt.Sprintf("**测试时间**:%s\\n**来源**:AIOps 智能运维平台\\n**状态**:连通性测试成功 🎉", time.Now().Format("2006-01-02 15:04:05"))
return sendFeishuCard(cfg.URL, cfg.Secret, title, content, "green")
return sendFeishuCard(cfg.URL, cfg.Secret, title, content, "green", buildNotifyFooter(db))
}
// sendFeishuAlert 发送飞书告警通知
func sendFeishuAlert(configJSON, title, content, severity string) error {
// sendFeishuAlert 发送飞书告警通知 // Logan.Li
func sendFeishuAlert(db *gorm.DB, configJSON, title, content, severity string) error {
var cfg model.FeishuWebhookConfig
if err := json.Unmarshal([]byte(configJSON), &cfg); err != nil {
return fmt.Errorf("解析配置失败: %w", err)
@@ -267,11 +268,15 @@ func sendFeishuAlert(configJSON, title, content, severity string) error {
}
title = emoji + " " + title
return sendFeishuCard(cfg.URL, cfg.Secret, title, content, color)
footer := defaultNotifyFooterTemplate
if db != nil {
footer = buildNotifyFooter(db)
}
return sendFeishuCard(cfg.URL, cfg.Secret, title, content, color, footer)
}
// sendFeishuRecovery 发送飞书恢复通知
func sendFeishuRecovery(configJSON, title, content string) error {
// sendFeishuRecovery 发送飞书恢复通知 // Logan.Li
func sendFeishuRecovery(db *gorm.DB, configJSON, title, content string) error {
var cfg model.FeishuWebhookConfig
if err := json.Unmarshal([]byte(configJSON), &cfg); err != nil {
return fmt.Errorf("解析配置失败: %w", err)
@@ -281,11 +286,15 @@ func sendFeishuRecovery(configJSON, title, content string) error {
}
title = "✅ " + title
return sendFeishuCard(cfg.URL, cfg.Secret, title, content, "green")
footer := buildNotifyFooter(db)
return sendFeishuCard(cfg.URL, cfg.Secret, title, content, "green", footer)
}
// sendFeishuCard 发送飞书交互卡片消息
func sendFeishuCard(webhookURL, secret, title, content, color string) error {
// sendFeishuCard 发送飞书交互卡片消息 // Logan.Li
func sendFeishuCard(webhookURL, secret, title, content, color, footer string) error {
if footer == "" {
footer = fmt.Sprintf("%s | %s", time.Now().Format("2006-01-02 15:04:05"), defaultNotifyPlatformName)
}
// 解析 content 中的字段(格式: 多行 key: value)
lines := splitLines(content)
var fields []map[string]interface{}
@@ -339,7 +348,7 @@ func sendFeishuCard(webhookURL, secret, title, content, color string) error {
"elements": []map[string]interface{}{
{
"tag": "plain_text",
"content": fmt.Sprintf("⏰ %s | AIOps 智能运维平台", time.Now().Format("2006-01-02 15:04:05")),
"content": footer,
},
},
},
@@ -438,9 +447,9 @@ func (h *AlertHandler) NotifyAlert(ruleName, hostname, metric, severity, message
for _, ch := range channels {
switch ch.Type {
case "feishu":
title := buildAlertTitle(ruleName, hostname, metric, severity)
title := buildNotifyTitle(h.db, ruleName, hostname, metric, severity)
content := buildAlertContent(ruleName, hostname, metric, severity, message, value, threshold)
if err := sendFeishuAlert(ch.Config, title, content, severity); err != nil {
if err := sendFeishuAlert(h.db, ch.Config, title, content, severity); err != nil {
fmt.Printf("[AlertNotify] 飞书通知失败 (渠道:%s): %v\n", ch.Name, err)
}
}
@@ -458,26 +467,11 @@ func (h *AlertHandler) NotifyRecovery(ruleName, hostname, metric, message string
title := fmt.Sprintf("%s — 已恢复正常", ruleName)
content := fmt.Sprintf("**告警已恢复**\\n\\n主机:%s\\n指标:%s\\n详情:%s\\n恢复时间:%s",
hostname, metric, message, time.Now().Format("2006-01-02 15:04:05"))
if err := sendFeishuRecovery(ch.Config, title, content); err != nil {
if err := sendFeishuRecovery(h.db, ch.Config, title, content); err != nil {
fmt.Printf("[AlertNotify] 飞书恢复通知失败 (渠道:%s): %v\n", ch.Name, err)
}
}
}
}
func buildAlertTitle(ruleName, hostname, metric, severity string) string {
sevLabel := "严重告警"
if severity == "warning" {
sevLabel = "警告"
} else if severity == "info" {
sevLabel = "信息"
}
return fmt.Sprintf("[%s] %s — %s (%s)", sevLabel, ruleName, hostname, metric)
}
func buildAlertContent(ruleName, hostname, metric, severity, message string, value, threshold float64) string {
return fmt.Sprintf(
"**规则名称:** %s\\n**目标主机:** %s\\n**指标类型:** %s\\n**告警级别:** %s\\n**当前值:** %.2f\\n**阈值:** %.2f\\n**详细信息:** %s\\n**触发时间:** %s",
ruleName, hostname, metric, severity, value, threshold, message, time.Now().Format("2006-01-02 15:04:05"),
)
}