Stale-backup alerts, per-server alert limits, and update runs from the Updates page

- Backups: a guest whose newest backup is older than its limit is an alert (backup kind),
  in the daily backup message, the digest and /metrics (homelab_backup_guests, ..._last_age_seconds)
- Per-server thresholds (servers.thresholds, migration 0030): offline minutes, disk percent,
  forecast window, backup age, and per-disk limits or "leave alone"; applied everywhere the
  global ones were; saving clears the alerts cache
- Update runs (update_runs, migration 0031): Update... on the Updates page puts the server under
  maintenance, runs a Semaphore playbook limited to it, waits for the host to report, and
  reports what is left and whether a restart is due; poller survives restarts
- Notification toggle for update-run results; tests and docs

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
bobbanandClaude Sonnet 5.5 committed 2026-10-18 01:25:09 +02:00
1 parent 5dc6cea69c
commit 7a5b623444
42 files changed
+7561 -57

No files matched your search

+6 -1
View File
@@ -50,6 +50,8 @@ export interface NotificationEvents {
healthAlerts: boolean;
/** A Semaphore template or Gitea repo whose latest run failed, and when it succeeds again. */
automationAlerts: boolean;
/** How an update run started from the Updates page ended: what is still waiting, whether a restart is due, or why it failed. */
updateRunResults: boolean;
/** Daily reminder while a domain registration is close to expiring or has expired. */
domainExpiryCheck: boolean;
secretCheckTime: string; // "HH:MM" — shared by the secret-expiry, Tailscale key-expiry, Docker update, and Proxmox backup checks
@@ -97,6 +99,8 @@ export interface HealthCheckSettings {
domainWarnDays: number;
/** An agent-reported disk that is on course to be full within this many days is flagged on the Alerts page. 0 turns it off. */
diskForecastDays: number;
/** A Proxmox guest whose newest backup is older than this many hours is raised as stale. 0 turns it off. */
backupStaleHours: number;
}
/** The weekly digest: one message a week through the notification channels. Off until an admin switches it on under Settings → Notifications. */
@@ -208,6 +212,7 @@ const DEFAULTS: AppSettings = {
pbsVerificationCheck: true,
healthAlerts: true,
automationAlerts: true,
updateRunResults: true,
domainExpiryCheck: true,
secretCheckTime: "08:00",
timezone: "UTC",
@@ -223,7 +228,7 @@ const DEFAULTS: AppSettings = {
inventory: { currency: "", pricePerKwh: null },
agents: { autoUpdate: false },
signIn: { roleFromGroups: false, groupsClaim: "groups", adminGroups: [], operatorGroups: [], otherwise: "viewer" },
healthChecks: { serverOfflineMinutes: 60, diskUsagePercent: 90, domainWarnDays: 30, diskForecastDays: 14 },
healthChecks: { serverOfflineMinutes: 60, diskUsagePercent: 90, domainWarnDays: 30, diskForecastDays: 14, backupStaleHours: 48 },
// Docker's default bridge (172.17.0.0/16) and the pool it hands custom networks from (172.18–31) live here, and every
// Docker host repeats them. Shown on the Consistency page, where it can be removed if 172.16/12 is used as a real LAN.
consistency: { excludedRanges: ["172.16.0.0/12"] },