fix(rollback): Add stabilization wait and retry logic for health checks

apps/demo-nginx/Jenkinsfile.rollback

@@ -225,6 +225,10 @@ pipeline {
                             --timeout=${HEALTH_CHECK_TIMEOUT}
                     """
                     
+                    // Wait a bit longer for pods to be fully ready
+                    echo "⏳ Waiting for new pods to stabilize..."
+                    sleep 10
+                    
                     echo "✅ Rollout completed"
                 }
             }
@@ -250,9 +254,27 @@ pipeline {
                             exit 1
                         fi
                         
-                        # Test health endpoint
-                        POD_NAME=\$(kubectl get pods -n ${NAMESPACE} -l app=${APP_NAME} -o jsonpath='{.items[0].metadata.name}')
-                        kubectl exec \${POD_NAME} -n ${NAMESPACE} -- wget -q -O- http://localhost/health
+                        # Verify image version on running pods
+                        DEPLOYED_IMAGE=\$(kubectl get deployment ${APP_NAME} -n ${NAMESPACE} -o jsonpath='{.spec.template.spec.containers[0].image}')
+                        echo "Deployed image: \${DEPLOYED_IMAGE}"
+                        
+                        # Get a RUNNING pod (not terminating)
+                        POD_NAME=\$(kubectl get pods -n ${NAMESPACE} -l app=${APP_NAME} --field-selector=status.phase=Running -o jsonpath='{.items[0].metadata.name}')
+                        echo "Testing pod: \${POD_NAME}"
+                        
+                        # Test health endpoint with retry
+                        for i in {1..5}; do
+                            echo "Health check attempt \$i/5..."
+                            if kubectl exec \${POD_NAME} -n ${NAMESPACE} -- wget -q -O- http://localhost/health 2>/dev/null; then
+                                echo "✅ Health check passed!"
+                                exit 0
+                            fi
+                            echo "Retrying in 5 seconds..."
+                            sleep 5
+                        done
+                        
+                        echo "❌ Health check failed after 5 attempts"
+                        exit 1
                     """
                     
                     echo "✅ Health checks passed"
@@ -308,7 +330,7 @@ pipeline {
                     1. Update deployment to target version
                     2. Update Git manifests
                     3. Wait for rollout (timeout: ${HEALTH_CHECK_TIMEOUT})
-                    ${params.SKIP_HEALTH_CHECK ? '4. (Health check skipped)' : '4. Run health checks'}
+                    ${params.SKIP_HEALTH_CHECK ? '4. (Health check skipped)' : '4. Run health checks with retry'}
                     
                     No actual changes were made.
                     """