feat: add cluster auditing, management, and upgrade scripts

scripts/fix_traefik_and_verify.py

@@ -0,0 +1,41 @@
+import paramiko
+import sys
+import time
+
+sys.stdout.reconfigure(encoding='utf-8')
+
+ssh = paramiko.SSHClient()
+ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
+ssh.connect('140.44.4.11', username='root', key_filename=r'C:\Users\Snarf\.ssh\id_ed25519_snarfnet', timeout=8)
+
+print("=== FIXING TRAEFIK CRD LABELS & ANNOTATIONS ===")
+annotate_cmd = """
+for crd in $(kubectl get crd -o name | grep 'traefik.io'); do
+  echo "Patching $crd..."
+  kubectl annotate $crd meta.helm.sh/release-name=traefik-crd meta.helm.sh/release-namespace=kube-system --overwrite
+  kubectl label $crd app.kubernetes.io/managed-by=Helm --overwrite
+done
+"""
+stdin, stdout, stderr = ssh.exec_command(annotate_cmd)
+print(stdout.read().decode())
+
+print("=== DELETING FAILED HELM INSTALL JOBS TO RETRIGGER ===")
+ssh.exec_command('kubectl delete job -n kube-system helm-install-traefik-crd helm-install-traefik')
+
+print("Waiting 15 seconds for Helm controller to reconcile...")
+time.sleep(15)
+
+print("=== CHECKING LONGHORN-MANAGER ON WRK01 ===")
+_, out, _ = ssh.exec_command('kubectl get pods -n longhorn-system -l app=longhorn-manager -o wide')
+print(out.read().decode())
+
+print("=== CHECKING ALL PODS IN KUBE-SYSTEM ===")
+_, out, _ = ssh.exec_command('kubectl get pods -n kube-system | grep traefik')
+print(out.read().decode())
+
+print("=== CHECKING ANY REMAINING CRASHING PODS ===")
+_, out, _ = ssh.exec_command('kubectl get pods -A | grep -v Running | grep -v Completed')
+print(out.read().decode())
+
+ssh.close()
+