Phase 2: monitoring warnings, dashboard alerts & notification system

- Monitoring page: "Távoli monitoring" section showing healthcheck ping UUID
  configuration status (configured/not configured) for each of the 5 pings
- Alert manager: persistent dashboard banners on all pages generated from
  health check results, missing pings, and backup status
- Notification system: controller-side notifier sends events to hub relay,
  with cooldown tracking and event-type filtering
- Notification preferences UI: email, event checkboxes, cooldown settings
  on the settings page with test email functionality
- Settings refactored: shared settingsData() helper, NotificationPrefs
  struct with getter/setter and defaults

New files:
- controller/internal/web/alerts.go (AlertManager)
- controller/internal/notify/notifier.go (hub notification client)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-16 19:29:45 +01:00
parent ded59b687e
commit 3eee330ed5
10 changed files with 837 additions and 23 deletions
+33 -4
View File
@@ -16,6 +16,7 @@ import (
"gitea.dooplex.hu/admin/felhom-controller/internal/config"
"gitea.dooplex.hu/admin/felhom-controller/internal/metrics"
"gitea.dooplex.hu/admin/felhom-controller/internal/monitor"
"gitea.dooplex.hu/admin/felhom-controller/internal/notify"
"gitea.dooplex.hu/admin/felhom-controller/internal/report"
"gitea.dooplex.hu/admin/felhom-controller/internal/scheduler"
"gitea.dooplex.hu/admin/felhom-controller/internal/settings"
@@ -116,6 +117,12 @@ func main() {
go backupMgr.LoadSnapshotHistory()
}
// --- Initialize alert manager ---
alertMgr := web.NewAlertManager(logger)
// --- Initialize notifier ---
notifier := notify.New(cfg.Hub.URL, cfg.Hub.APIKey, cfg.Customer.ID, sett, logger)
// --- Initialize scheduler ---
sched := scheduler.New(logger)
@@ -147,16 +154,28 @@ func main() {
} else {
pinger.Ping(healthUUID, body)
}
// Refresh dashboard alerts from health report
alertMgr.Refresh(healthReport, cfg, backupMgr)
// Notify on health status changes
notifier.NotifyHealthChange(healthReport.Status, healthReport.Issues, healthReport.Warnings)
return nil
})
// Backup daily jobs
if cfg.Backup.Enabled && backupMgr != nil {
sched.Daily("db-dump", cfg.Backup.DBDumpSchedule, func(ctx context.Context) error {
return backupMgr.RunDBDumps(ctx)
err := backupMgr.RunDBDumps(ctx)
if err != nil {
notifier.NotifyDBDumpFailed("Adatbázis mentés sikertelen", err.Error())
}
return err
})
sched.Daily("backup", cfg.Backup.ResticSchedule, func(ctx context.Context) error {
return backupMgr.RunBackup(ctx)
err := backupMgr.RunBackup(ctx)
if err != nil {
notifier.NotifyBackupFailed("Biztonsági mentés sikertelen", err.Error())
}
return err
})
// Weekly integrity check — Sunday 04:00
@@ -164,7 +183,11 @@ func main() {
if time.Now().Weekday() != time.Sunday {
return nil
}
return backupMgr.RunIntegrityCheck(ctx)
err := backupMgr.RunIntegrityCheck(ctx)
if err != nil {
notifier.NotifyIntegrityFailed("Mentés integritás ellenőrzés sikertelen", err.Error())
}
return err
})
// Cache refresh: every 5 minutes
@@ -214,11 +237,17 @@ func main() {
}()
}
// Initial alert refresh (so alerts appear immediately, not after first 5min health check)
go func() {
report := monitor.RunHealthCheck(cfg, cpuCollector)
alertMgr.Refresh(report, cfg, backupMgr)
}()
// --- Initialize API router ---
apiRouter := api.NewRouter(cfg, stackMgr, syncer, cpuCollector, backupMgr, metricsStore, logger)
// --- Initialize web server ---
webServer := web.NewServer(cfg, stackMgr, cpuCollector, backupMgr, sched, sett, logger, Version)
webServer := web.NewServer(cfg, stackMgr, cpuCollector, backupMgr, sched, sett, alertMgr, notifier, logger, Version)
// --- Build HTTP mux ---
mux := http.NewServeMux()