From e1a25329d443d1754586c5af795c53cf4090ce27 Mon Sep 17 00:00:00 2001
From: chemavx <chemavx@git.chemavx.xyz>
Date: Thu, 9 Jul 2026 09:37:28 +0000
Subject: [PATCH] feat(monitoring): alerta Telegram para jobs fallidos de
 backup-system

Regla homelab-backup-job-failed (kube_job_status_failed{namespace="backup-system"} > 0)
en el grupo homelab-infra; cubre backup, rclone-mega-backup y backup-verify.
Aplicado con kubectl replace + rollout restart de Grafana (namespace manual).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---
 monitoring/configmap-grafana-alerting.yaml | 41 ++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/monitoring/configmap-grafana-alerting.yaml b/monitoring/configmap-grafana-alerting.yaml
index 36e772d..f111299 100644
--- a/monitoring/configmap-grafana-alerting.yaml
+++ b/monitoring/configmap-grafana-alerting.yaml
@@ -83,6 +83,47 @@ data:
                   conditions:
                     - evaluator: {params: [0], type: gt}
 
+          - uid: homelab-backup-job-failed
+            title: "Backup job fallido"
+            condition: C
+            for: 1m
+            noDataState: OK
+            execErrState: Error
+            annotations:
+              summary: "🗄️ Backup FALLIDO: {{ $labels.job_name }}\nNamespace: {{ $labels.namespace }}"
+              description: "El job {{ $labels.job_name }} del sistema de backups ha fallado. Cubre los CronJobs backup, rclone-mega-backup y backup-verify."
+            labels:
+              severity: critical
+            isPaused: false
+            data:
+              - refId: A
+                relativeTimeRange: {from: 300, to: 0}
+                datasourceUid: prometheus
+                model:
+                  editorMode: code
+                  expr: "kube_job_status_failed{namespace=\"backup-system\"}"
+                  instant: true
+                  refId: A
+              - refId: B
+                relativeTimeRange: {from: 0, to: 0}
+                datasourceUid: "-100"
+                model:
+                  type: reduce
+                  refId: B
+                  expression: A
+                  reducer: last
+                  settings:
+                    mode: ""
+              - refId: C
+                relativeTimeRange: {from: 0, to: 0}
+                datasourceUid: "-100"
+                model:
+                  type: threshold
+                  refId: C
+                  expression: B
+                  conditions:
+                    - evaluator: {params: [0], type: gt}
+
           - uid: homelab-disk-high
             title: "Disco > 80%"
             condition: C