gatus: also report unhealthy Argo CD apps and CNPG clusters

gatus/backup-check.yaml

@@ -11,6 +11,8 @@
 #   younger than 26h (detached volumes are skipped; the recurring job skips
 #   them too)
 # - vault-unsealed: all Vault pods report vault-sealed=false
+# - argocd-apps: every Argo CD application is Synced and Healthy
+# - postgres: every CloudNativePG cluster is in a healthy state
 #
 # The token is generated by ESO and never leaves the cluster; Gatus reads
 # it from the same Secret.
@@ -63,6 +65,12 @@ rules:
   - apiGroups: [""]
     resources: ["pods"]
     verbs: ["list"]
+  - apiGroups: ["argoproj.io"]
+    resources: ["applications"]
+    verbs: ["list"]
+  - apiGroups: ["postgresql.cnpg.io"]
+    resources: ["clusters"]
+    verbs: ["list"]
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
@@ -170,6 +178,24 @@ data:
         return f"sealed: {', '.join(sealed)}" if sealed else None
 
 
+    def argocd():
+        bad = []
+        for a in items("/apis/argoproj.io/v1alpha1/namespaces/argocd/applications"):
+            s = a.get("status", {})
+            sync = s.get("sync", {}).get("status")
+            health = s.get("health", {}).get("status")
+            if sync != "Synced" or health != "Healthy":
+                bad.append(f"{a['metadata']['name']} {sync}/{health}")
+        return "; ".join(bad) or None
+
+
+    def postgres():
+        bad = [f"{c['metadata']['namespace']}/{c['metadata']['name']}: {c.get('status', {}).get('phase')}"
+               for c in items("/apis/postgresql.cnpg.io/v1/clusters")
+               if c.get("status", {}).get("phase") != "Cluster in healthy state"]
+        return "; ".join(bad) or None
+
+
     def push(key, error):
         query = {"success": "false" if error else "true"}
         if error:
@@ -185,6 +211,8 @@ data:
         "cluster_velero-weekly": lambda: velero("weekly-backup", 8 * 24 + 2),
         "cluster_longhorn": lambda: longhorn(26),
         "cluster_vault-unsealed": vault,
+        "cluster_argocd-apps": argocd,
+        "cluster_postgres": postgres,
     }
     failed_pushes = 0
     for key, check in checks.items():

gatus/config.yaml

@@ -169,3 +169,15 @@ external-endpoints:
     heartbeat:
       interval: 3h
     alerts: *cluster-alert
+  - name: argocd-apps
+    group: cluster
+    token: ${BACKUP_CHECK_TOKEN}
+    heartbeat:
+      interval: 3h
+    alerts: *cluster-alert
+  - name: postgres
+    group: cluster
+    token: ${BACKUP_CHECK_TOKEN}
+    heartbeat:
+      interval: 3h
+    alerts: *cluster-alert