k8s-helper-cli 0.4.3__py3-none-any.whl → 0.5.1__py3-none-any.whl

k8s_helper/__init__.py

@@ -20,7 +20,7 @@ from .utils import (
     create_service_manifest
 )
 
-__version__ = "0.4.3"
+__version__ = "0.5.1"
 __author__ = "Harshit Chatterjee"
 __email__ = "harshitchatterjee50@gmail.com"
 

k8s_helper/cli.py

@@ -1359,6 +1359,7 @@ def setup_monitoring(
     namespace: str = typer.Option("monitoring", "--namespace", "-n", help="Namespace for monitoring stack"),
     grafana_service_type: str = typer.Option("NodePort", "--service-type", "-t", help="Grafana service type: NodePort, LoadBalancer, ClusterIP"),
     import_dashboard: bool = typer.Option(True, "--import-dashboard/--no-dashboard", help="Import default Kubernetes dashboard"),
+    install_kube_state_metrics: bool = typer.Option(True, "--install-kube-state-metrics/--no-kube-state-metrics", help="Install kube-state-metrics for cluster metrics"),
     wait: bool = typer.Option(True, "--wait/--no-wait", help="Wait for deployments to be ready"),
     show_info: bool = typer.Option(True, "--show-info/--no-show-info", help="Show monitoring stack information after setup")
 ):
@@ -1377,12 +1378,17 @@ def setup_monitoring(
     if import_dashboard:
         console.print("📊 Will import default Kubernetes dashboard")
     
+    if install_kube_state_metrics:
+        console.print("📈 Will install kube-state-metrics for cluster metrics")
+    
     # Show what will be deployed
     console.print("\n📋 Components to deploy:")
     console.print("   • Prometheus server with cluster monitoring configuration")
     console.print("   • Grafana with admin credentials (admin/admin123)")
     console.print("   • ServiceAccount and RBAC for Prometheus")
     console.print("   • ConfigMaps for Prometheus configuration")
+    if install_kube_state_metrics:
+        console.print("   • kube-state-metrics for cluster metrics (via Helm or manual)")
     if import_dashboard:
         console.print("   • Default Kubernetes metrics dashboard")
     
@@ -1394,7 +1400,8 @@ def setup_monitoring(
                 namespace=namespace,
                 grafana_service_type=grafana_service_type,
                 import_dashboard=import_dashboard,
-                wait_for_ready=wait
+                wait_for_ready=wait,
+                install_kube_state_metrics=install_kube_state_metrics
             )
         
         if result['success']:
@@ -1429,6 +1436,22 @@ def setup_monitoring(
             else:
                 console.print("❌ Grafana: Failed to deploy")
             
+            # Show kube-state-metrics status
+            if install_kube_state_metrics and 'kube_state_metrics' in result:
+                ksm = result['kube_state_metrics']
+                if ksm.get('installed'):
+                    method = ksm.get('method', 'unknown')
+                    if method == 'helm':
+                        console.print("✅ kube-state-metrics: Deployed via Helm")
+                    elif method == 'manual':
+                        console.print("✅ kube-state-metrics: Deployed via manual YAML")
+                    elif method == 'existing':
+                        console.print("✅ kube-state-metrics: Already deployed")
+                else:
+                    console.print(f"❌ kube-state-metrics: Failed to deploy")
+                    if ksm.get('error'):
+                        console.print(f"   Error: {ksm['error']}")
+            
             if show_info:
                 # Get and display monitoring information
                 with console.status("Retrieving monitoring stack information..."):
@@ -1863,5 +1886,217 @@ def update_prometheus_target(
         console.print(f"❌ Error updating Prometheus target: {e}")
 
 
+# ======================
+# HELM-BASED MONITORING COMMANDS
+# ======================
+@app.command()
+def setup_monitoring_stack(
+    namespace: str = typer.Option("monitoring", "--namespace", "-n", help="Namespace for monitoring stack"),
+    grafana_service_type: str = typer.Option("NodePort", "--service-type", "-t", help="Grafana service type: NodePort, LoadBalancer, ClusterIP"),
+    prometheus_storage_size: str = typer.Option("10Gi", "--prometheus-storage", help="Prometheus storage size"),
+    grafana_storage_size: str = typer.Option("5Gi", "--grafana-storage", help="Grafana storage size"),
+    wait: bool = typer.Option(True, "--wait/--no-wait", help="Wait for deployments to be ready"),
+    install_ingress: bool = typer.Option(False, "--install-ingress", help="Install ingress for external access")
+):
+    """Deploy monitoring stack using official Helm charts (Prometheus + Grafana)"""
+    
+    # Validate service type
+    valid_service_types = ["NodePort", "LoadBalancer", "ClusterIP"]
+    if grafana_service_type not in valid_service_types:
+        console.print(f"❌ Invalid service type: {grafana_service_type}")
+        console.print(f"💡 Valid options: {', '.join(valid_service_types)}")
+        return
+    
+    console.print(f"🚀 Setting up Helm-based monitoring stack in namespace: {namespace}")
+    console.print(f"🔧 Grafana service type: {grafana_service_type}")
+    console.print(f"💾 Prometheus storage: {prometheus_storage_size}")
+    console.print(f"💾 Grafana storage: {grafana_storage_size}")
+    
+    # Show what will be deployed
+    console.print("\n📋 Components to deploy via Helm:")
+    console.print("   • Prometheus Operator (kube-prometheus-stack)")
+    console.print("   • Grafana with persistent storage")
+    console.print("   • AlertManager for alerts")
+    console.print("   • Node Exporter for node metrics")
+    console.print("   • kube-state-metrics for cluster state")
+    console.print("   • Prometheus rules and dashboards")
+    if install_ingress:
+        console.print("   • Ingress for external access")
+    
+    try:
+        client = K8sClient()
+        
+        with console.status("Deploying Helm monitoring stack..."):
+            result = client.setup_helm_monitoring(
+                namespace=namespace,
+                grafana_service_type=grafana_service_type,
+                prometheus_storage_size=prometheus_storage_size,
+                grafana_storage_size=grafana_storage_size,
+                wait_for_ready=wait,
+                install_ingress=install_ingress
+            )
+        
+        if result['success']:
+            console.print("✅ Helm monitoring stack deployed successfully!")
+            
+            # Show deployment summary
+            console.print(f"\n📋 Deployment Summary:")
+            console.print(f"📍 Namespace: {result['namespace']}")
+            console.print(f"🎯 Helm Release: {result['release_name']}")
+            
+            if result.get('prometheus', {}).get('deployed'):
+                console.print("✅ Prometheus Operator: Deployed")
+            else:
+                console.print("❌ Prometheus Operator: Failed to deploy")
+            
+            if result.get('grafana', {}).get('deployed'):
+                console.print("✅ Grafana: Deployed")
+                if result['grafana'].get('admin_password'):
+                    console.print(f"🔑 Grafana admin password: {result['grafana']['admin_password']}")
+                else:
+                    console.print("🔑 Grafana admin password: admin")
+            else:
+                console.print("❌ Grafana: Failed to deploy")
+            
+            # Show access information
+            console.print(f"\n🔗 Access Information:")
+            
+            if result.get('grafana_url'):
+                console.print(f"🔗 Grafana URL: [blue]{result['grafana_url']}[/blue]")
+            else:
+                console.print(f"💡 Grafana: kubectl port-forward -n {namespace} svc/kube-prometheus-stack-grafana 3000:80")
+            
+            if result.get('prometheus_url'):
+                console.print(f"🔗 Prometheus URL: [blue]{result['prometheus_url']}[/blue]")
+            else:
+                console.print(f"💡 Prometheus: kubectl port-forward -n {namespace} svc/kube-prometheus-stack-prometheus 9090:9090")
+            
+            if result.get('alertmanager_url'):
+                console.print(f"🔗 AlertManager URL: [blue]{result['alertmanager_url']}[/blue]")
+            else:
+                console.print(f"💡 AlertManager: kubectl port-forward -n {namespace} svc/kube-prometheus-stack-alertmanager 9093:9093")
+            
+            # Show next steps
+            console.print(f"\n🚀 Next Steps:")
+            console.print(f"   1. Access Grafana with admin/admin (or password shown above)")
+            console.print(f"   2. Explore pre-configured dashboards")
+            console.print(f"   3. Set up custom alerts in AlertManager")
+            console.print(f"   4. Add custom Prometheus targets if needed")
+            console.print(f"\n💡 Useful commands:")
+            console.print(f"   • Check status: k8s-helper monitoring-stack-status -n {namespace}")
+            console.print(f"   • List dashboards: kubectl get configmaps -n {namespace} | grep dashboard")
+            console.print(f"   • View Helm release: helm list -n {namespace}")
+            
+        else:
+            console.print(f"❌ Failed to deploy Helm monitoring stack: {result.get('error', 'Unknown error')}")
+            
+            console.print("\n🛠️  Troubleshooting:")
+            console.print("   • Ensure Helm is installed: helm version")
+            console.print("   • Check cluster connectivity: kubectl get nodes")
+            console.print("   • Verify namespace permissions")
+            console.print(f"   • View Helm status: helm status -n {namespace} kube-prometheus-stack")
+    
+    except Exception as e:
+        console.print(f"❌ Error setting up Helm monitoring: {e}")
+        console.print("\n🛠️  Troubleshooting:")
+        console.print("   • Ensure Helm is installed and configured")
+        console.print("   • Check if kubectl is configured correctly")
+        console.print("   • Verify you have cluster admin permissions")
+
+
+@app.command()
+def monitoring_stack_status(
+    namespace: str = typer.Option("monitoring", "--namespace", "-n", help="Monitoring namespace"),
+    output: str = output_option
+):
+    """Show status of Helm-based monitoring stack"""
+    try:
+        client = K8sClient()
+        
+        with console.status("Checking Helm monitoring stack status..."):
+            info = client.get_helm_monitoring_info(namespace)
+        
+        if 'error' in info:
+            console.print(f"❌ Error getting monitoring status: {info['error']}")
+            return
+        
+        if output == "table":
+            # Helm release info
+            console.print(f"🎯 Helm Release: {info.get('release_name', 'kube-prometheus-stack')}")
+            console.print(f"📊 Release Status: {info.get('release_status', 'Unknown')}")
+            console.print(f"📅 Last Deployed: {info.get('last_deployed', 'Unknown')}")
+            
+            # Overview table
+            table = Table(title=f"Monitoring Stack Status - {namespace}")
+            table.add_column("Component", style="cyan")
+            table.add_column("Status", style="green")
+            table.add_column("URL", style="blue")
+            
+            # Components status
+            components = ['prometheus', 'grafana', 'alertmanager']
+            for component in components:
+                if component in info:
+                    comp_info = info[component]
+                    status = "🟢 Running" if comp_info.get('running') else "🔴 Not Running"
+                    url = comp_info.get('url', 'Port-forward required')
+                    table.add_row(component.capitalize(), status, url)
+            
+            console.print(table)
+            
+            # Show pod status
+            if info.get('pods'):
+                pod_table = Table(title="Pod Status")
+                pod_table.add_column("Pod", style="cyan")
+                pod_table.add_column("Status", style="green")
+                pod_table.add_column("Ready", style="blue")
+                
+                for pod in info['pods']:
+                    pod_table.add_row(
+                        pod['name'],
+                        pod['status'],
+                        f"{pod['ready']}/{pod['total']}"
+                    )
+                
+                console.print(pod_table)
+        
+        elif output == "json":
+            console.print(format_json_output(info))
+        elif output == "yaml":
+            console.print(format_yaml_output(info))
+    
+    except Exception as e:
+        console.print(f"❌ Error checking Helm monitoring status: {e}")
+
+
+@app.command()
+def delete_monitoring_stack(
+    namespace: str = typer.Option("monitoring", "--namespace", "-n", help="Monitoring namespace"),
+    release_name: str = typer.Option("kube-prometheus-stack", "--release-name", help="Helm release name"),
+    force: bool = typer.Option(False, "--force", help="Skip confirmation prompt")
+):
+    """Delete Helm-based monitoring stack"""
+    if not force:
+        if not typer.confirm(f"Are you sure you want to delete the Helm monitoring stack '{release_name}' in namespace '{namespace}'?"):
+            console.print("❌ Operation cancelled")
+            return
+    
+    try:
+        client = K8sClient()
+        
+        console.print(f"🗑️  Deleting Helm monitoring stack: {release_name}")
+        
+        with console.status("Uninstalling Helm release..."):
+            result = client.delete_helm_monitoring(namespace, release_name)
+        
+        if result['success']:
+            console.print(f"✅ Helm monitoring stack '{release_name}' deleted successfully")
+            console.print(f"📋 Cleaned up {result.get('resources_deleted', 0)} resources")
+        else:
+            console.print(f"❌ Failed to delete Helm monitoring stack: {result.get('error', 'Unknown error')}")
+    
+    except Exception as e:
+        console.print(f"❌ Error deleting Helm monitoring: {e}")
+
+
 if __name__ == "__main__":
     app()

k8s_helper/core.py

@@ -1683,10 +1683,346 @@ class K8sClient:
     # ======================
     # MONITORING OPERATIONS
     # ======================
+    
+    def _check_helm_available(self) -> bool:
+        """Check if Helm is available in the system"""
+        import subprocess
+        try:
+            result = subprocess.run(['helm', 'version', '--short'], 
+                                  capture_output=True, text=True, timeout=10)
+            return result.returncode == 0
+        except (subprocess.TimeoutExpired, FileNotFoundError):
+            return False
+    
+    def _install_kube_state_metrics(self, namespace: str) -> Dict[str, Any]:
+        """Install kube-state-metrics using Helm if available, or manual YAML if not"""
+        import subprocess
+        
+        result = {
+            'installed': False,
+            'method': None,
+            'error': None
+        }
+        
+        # Check if kube-state-metrics is already running
+        try:
+            deployments = self.apps_v1.list_deployment_for_all_namespaces()
+            for deployment in deployments.items:
+                if 'kube-state-metrics' in deployment.metadata.name:
+                    print(f"✅ kube-state-metrics already deployed in namespace: {deployment.metadata.namespace}")
+                    result['installed'] = True
+                    result['method'] = 'existing'
+                    return result
+        except Exception as e:
+            print(f"⚠️  Warning: Could not check existing deployments: {e}")
+        
+        # Try Helm installation first
+        if self._check_helm_available():
+            try:
+                print("📦 Installing kube-state-metrics using Helm...")
+                
+                # Add prometheus-community repo if not exists
+                subprocess.run(['helm', 'repo', 'add', 'prometheus-community', 
+                              'https://prometheus-community.github.io/helm-charts'], 
+                              capture_output=True, text=True, timeout=30)
+                
+                # Update repo
+                subprocess.run(['helm', 'repo', 'update'], 
+                              capture_output=True, text=True, timeout=30)
+                
+                # Install kube-state-metrics
+                helm_cmd = [
+                    'helm', 'install', 'kube-state-metrics',
+                    'prometheus-community/kube-state-metrics',
+                    '--namespace', namespace,
+                    '--create-namespace',
+                    '--set', 'service.port=8080',
+                    '--set', 'service.targetPort=8080'
+                ]
+                
+                helm_result = subprocess.run(helm_cmd, capture_output=True, text=True, timeout=120)
+                
+                if helm_result.returncode == 0:
+                    print("✅ kube-state-metrics installed successfully via Helm")
+                    result['installed'] = True
+                    result['method'] = 'helm'
+                    return result
+                else:
+                    print(f"⚠️  Helm installation failed: {helm_result.stderr}")
+                    
+            except subprocess.TimeoutExpired:
+                print("⚠️  Helm installation timed out, falling back to manual installation")
+            except Exception as e:
+                print(f"⚠️  Helm installation failed: {e}, falling back to manual installation")
+        
+        # Fallback to manual YAML installation
+        try:
+            print("📦 Installing kube-state-metrics using manual YAML...")
+            
+            # Create ServiceAccount
+            service_account = client.V1ServiceAccount(
+                metadata=client.V1ObjectMeta(
+                    name="kube-state-metrics",
+                    namespace=namespace
+                )
+            )
+            
+            try:
+                self.core_v1.create_namespaced_service_account(namespace=namespace, body=service_account)
+                print("✅ Created ServiceAccount for kube-state-metrics")
+            except ApiException as e:
+                if e.status == 409:
+                    print("⚠️  ServiceAccount already exists")
+                else:
+                    raise e
+            
+            # Create ClusterRole
+            cluster_role = client.V1ClusterRole(
+                metadata=client.V1ObjectMeta(name="kube-state-metrics"),
+                rules=[
+                    client.V1PolicyRule(
+                        api_groups=[""],
+                        resources=["configmaps", "secrets", "nodes", "pods", "services", 
+                                 "resourcequotas", "replicationcontrollers", "limitranges", 
+                                 "persistentvolumeclaims", "persistentvolumes", "namespaces", "endpoints"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["apps"],
+                        resources=["statefulsets", "daemonsets", "deployments", "replicasets"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["batch"],
+                        resources=["cronjobs", "jobs"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["autoscaling"],
+                        resources=["horizontalpodautoscalers"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["authentication.k8s.io"],
+                        resources=["tokenreviews"],
+                        verbs=["create"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["authorization.k8s.io"],
+                        resources=["subjectaccessreviews"],
+                        verbs=["create"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["policy"],
+                        resources=["poddisruptionbudgets"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["certificates.k8s.io"],
+                        resources=["certificatesigningrequests"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["storage.k8s.io"],
+                        resources=["storageclasses", "volumeattachments"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["admissionregistration.k8s.io"],
+                        resources=["mutatingwebhookconfigurations", "validatingwebhookconfigurations"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["networking.k8s.io"],
+                        resources=["networkpolicies", "ingresses"],
+                        verbs=["list", "watch"]
+                    ),
+                    client.V1PolicyRule(
+                        api_groups=["coordination.k8s.io"],
+                        resources=["leases"],
+                        verbs=["list", "watch"]
+                    )
+                ]
+            )
+            
+            # Create ClusterRole
+            rbac_v1 = client.RbacAuthorizationV1Api()
+            try:
+                rbac_v1.create_cluster_role(body=cluster_role)
+                print("✅ Created ClusterRole for kube-state-metrics")
+            except ApiException as e:
+                if e.status == 409:
+                    print("⚠️  ClusterRole already exists")
+                else:
+                    raise e
+            
+            # Create ClusterRoleBinding
+            # Create subject with version compatibility
+            try:
+                # Try V1Subject first (older versions)
+                subject = client.V1Subject(
+                    kind="ServiceAccount",
+                    name="kube-state-metrics",
+                    namespace=namespace
+                )
+            except AttributeError:
+                # Try RbacV1Subject (newer versions)
+                try:
+                    subject = client.RbacV1Subject(
+                        kind="ServiceAccount",
+                        name="kube-state-metrics",
+                        namespace=namespace
+                    )
+                except AttributeError:
+                    # Manual construction as fallback
+                    subject = {
+                        'kind': 'ServiceAccount',
+                        'name': 'kube-state-metrics',
+                        'namespace': namespace
+                    }
+            
+            cluster_role_binding = client.V1ClusterRoleBinding(
+                metadata=client.V1ObjectMeta(name="kube-state-metrics"),
+                subjects=[subject],
+                role_ref=client.V1RoleRef(
+                    kind="ClusterRole",
+                    name="kube-state-metrics",
+                    api_group="rbac.authorization.k8s.io"
+                )
+            )
+            
+            try:
+                rbac_v1.create_cluster_role_binding(body=cluster_role_binding)
+                print("✅ Created ClusterRoleBinding for kube-state-metrics")
+            except ApiException as e:
+                if e.status == 409:
+                    print("⚠️  ClusterRoleBinding already exists")
+                else:
+                    raise e
+            
+            # Create Deployment
+            deployment = client.V1Deployment(
+                metadata=client.V1ObjectMeta(
+                    name="kube-state-metrics",
+                    namespace=namespace,
+                    labels={"app": "kube-state-metrics"}
+                ),
+                spec=client.V1DeploymentSpec(
+                    replicas=1,
+                    selector=client.V1LabelSelector(
+                        match_labels={"app": "kube-state-metrics"}
+                    ),
+                    template=client.V1PodTemplateSpec(
+                        metadata=client.V1ObjectMeta(
+                            labels={"app": "kube-state-metrics"}
+                        ),
+                        spec=client.V1PodSpec(
+                            service_account_name="kube-state-metrics",
+                            containers=[
+                                client.V1Container(
+                                    name="kube-state-metrics",
+                                    image="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.10.1",
+                                    ports=[
+                                        client.V1ContainerPort(
+                                            name="http-metrics",
+                                            container_port=8080,
+                                            protocol="TCP"
+                                        ),
+                                        client.V1ContainerPort(
+                                            name="telemetry",
+                                            container_port=8081,
+                                            protocol="TCP"
+                                        )
+                                    ],
+                                    liveness_probe=client.V1Probe(
+                                        http_get=client.V1HTTPGetAction(
+                                            path="/healthz",
+                                            port=8080
+                                        ),
+                                        initial_delay_seconds=5,
+                                        timeout_seconds=5
+                                    ),
+                                    readiness_probe=client.V1Probe(
+                                        http_get=client.V1HTTPGetAction(
+                                            path="/",
+                                            port=8081
+                                        ),
+                                        initial_delay_seconds=5,
+                                        timeout_seconds=5
+                                    ),
+                                    security_context=client.V1SecurityContext(
+                                        allow_privilege_escalation=False,
+                                        read_only_root_filesystem=True,
+                                        run_as_non_root=True,
+                                        run_as_user=65534
+                                    )
+                                )
+                            ]
+                        )
+                    )
+                )
+            )
+            
+            try:
+                self.apps_v1.create_namespaced_deployment(namespace=namespace, body=deployment)
+                print("✅ Created Deployment for kube-state-metrics")
+            except ApiException as e:
+                if e.status == 409:
+                    print("⚠️  Deployment already exists")
+                else:
+                    raise e
+            
+            # Create Service
+            service = client.V1Service(
+                metadata=client.V1ObjectMeta(
+                    name="kube-state-metrics",
+                    namespace=namespace,
+                    labels={"app": "kube-state-metrics"}
+                ),
+                spec=client.V1ServiceSpec(
+                    selector={"app": "kube-state-metrics"},
+                    ports=[
+                        client.V1ServicePort(
+                            name="http-metrics",
+                            port=8080,
+                            target_port=8080,
+                            protocol="TCP"
+                        ),
+                        client.V1ServicePort(
+                            name="telemetry",
+                            port=8081,
+                            target_port=8081,
+                            protocol="TCP"
+                        )
+                    ],
+                    type="ClusterIP"
+                )
+            )
+            
+            try:
+                self.core_v1.create_namespaced_service(namespace=namespace, body=service)
+                print("✅ Created Service for kube-state-metrics")
+            except ApiException as e:
+                if e.status == 409:
+                    print("⚠️  Service already exists")
+                else:
+                    raise e
+            
+            result['installed'] = True
+            result['method'] = 'manual'
+            print("✅ kube-state-metrics installed successfully via manual YAML")
+            
+        except Exception as e:
+            result['error'] = str(e)
+            print(f"❌ Failed to install kube-state-metrics: {e}")
+        
+        return result
+    
     def setup_monitoring(self, namespace: str = "monitoring", 
                         grafana_service_type: str = "NodePort",
                         import_dashboard: bool = True,
-                        wait_for_ready: bool = True) -> Dict[str, Any]:
+                        wait_for_ready: bool = True,
+                        install_kube_state_metrics: bool = True) -> Dict[str, Any]:
         """Setup complete monitoring stack with Prometheus and Grafana
         
         Args:
@@ -1694,6 +2030,7 @@ class K8sClient:
             grafana_service_type: Service type for Grafana (NodePort, LoadBalancer, ClusterIP)
             import_dashboard: Whether to import default Kubernetes dashboard
             wait_for_ready: Whether to wait for deployments to be ready
+            install_kube_state_metrics: Whether to install kube-state-metrics for cluster metrics
             
         Returns:
             Dictionary with deployment info, URLs, and credentials
@@ -1702,6 +2039,7 @@ class K8sClient:
             'namespace': namespace,
             'prometheus': {},
             'grafana': {},
+            'kube_state_metrics': {},
             'success': False,
             'error': None
         }
@@ -1710,6 +2048,12 @@ class K8sClient:
             # Create monitoring namespace
             self._create_monitoring_namespace(namespace)
             
+            # Install kube-state-metrics if requested
+            if install_kube_state_metrics:
+                print("📊 Installing kube-state-metrics for cluster metrics...")
+                ksm_result = self._install_kube_state_metrics(namespace)
+                result['kube_state_metrics'] = ksm_result
+            
             # Deploy Prometheus
             prometheus_result = self._deploy_prometheus(namespace)
             result['prometheus'] = prometheus_result
@@ -1762,7 +2106,7 @@ class K8sClient:
         """Deploy Prometheus to the cluster"""
         result = {'deployed': False, 'service_name': 'prometheus-service'}
         
-        # Prometheus ConfigMap
+        # Prometheus ConfigMap with kube-state-metrics support
         prometheus_config = """
 global:
   scrape_interval: 15s
@@ -1790,6 +2134,29 @@ scrape_configs:
     - action: labelmap
       regex: __meta_kubernetes_node_label_(.+)
 
+  - job_name: 'kubernetes-cadvisor'
+    kubernetes_sd_configs:
+    - role: node
+    scheme: https
+    tls_config:
+      ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+    bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+    relabel_configs:
+    - action: labelmap
+      regex: __meta_kubernetes_node_label_(.+)
+    - target_label: __address__
+      replacement: kubernetes.default.svc:443
+    - source_labels: [__meta_kubernetes_node_name]
+      regex: (.+)
+      target_label: __metrics_path__
+      replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
+
+  - job_name: 'kube-state-metrics'
+    static_configs:
+    - targets: ['kube-state-metrics.{}:8080']
+    metrics_path: /metrics
+    scrape_interval: 30s
+
   - job_name: 'kubernetes-pods'
     kubernetes_sd_configs:
     - role: pod
@@ -1814,7 +2181,36 @@ scrape_configs:
     - source_labels: [__meta_kubernetes_pod_name]
       action: replace
       target_label: kubernetes_pod_name
-"""
+
+  - job_name: 'kubernetes-service-endpoints'
+    kubernetes_sd_configs:
+    - role: endpoints
+    relabel_configs:
+    - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+      action: keep
+      regex: true
+    - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+      action: replace
+      target_label: __scheme__
+      regex: (https?)
+    - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+      action: replace
+      target_label: __metrics_path__
+      regex: (.+)
+    - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+      action: replace
+      target_label: __address__
+      regex: ([^:]+)(?::\\d+)?;(\\d+)
+      replacement: $1:$2
+    - action: labelmap
+      regex: __meta_kubernetes_service_label_(.+)
+    - source_labels: [__meta_kubernetes_namespace]
+      action: replace
+      target_label: kubernetes_namespace
+    - source_labels: [__meta_kubernetes_service_name]
+      action: replace
+      target_label: kubernetes_name
+""".format(namespace)
         
         # Create ConfigMap
         configmap = client.V1ConfigMap(
@@ -2687,3 +3083,398 @@ scrape_configs:
         except Exception as e:
             print(f"⚠️  Could not restart Prometheus deployment: {e}")
             return False
+
+    # ======================
+    # HELM-BASED MONITORING METHODS
+    # ======================
+    
+    def setup_helm_monitoring(self, namespace: str = "monitoring", 
+                            grafana_service_type: str = "NodePort",
+                            prometheus_storage_size: str = "10Gi",
+                            grafana_storage_size: str = "5Gi",
+                            wait_for_ready: bool = True,
+                            install_ingress: bool = False) -> Dict:
+        """Deploy monitoring stack using official Helm charts"""
+        import subprocess
+        import tempfile
+        import os
+        
+        try:
+            # Check if Helm is available
+            try:
+                result = subprocess.run(['helm', 'version'], capture_output=True, text=True, check=True)
+            except (subprocess.CalledProcessError, FileNotFoundError):
+                return {
+                    'success': False,
+                    'error': 'Helm is not installed or not in PATH. Please install Helm first.'
+                }
+            
+            # Create namespace if it doesn't exist
+            try:
+                self.core_v1.create_namespace(
+                    body=client.V1Namespace(metadata=client.V1ObjectMeta(name=namespace))
+                )
+                print(f"✅ Created namespace: {namespace}")
+            except ApiException as e:
+                if e.status == 409:  # Already exists
+                    print(f"✅ Namespace {namespace} already exists")
+                else:
+                    print(f"⚠️  Could not create namespace: {e}")
+            
+            # Add Prometheus community Helm repository
+            print("📦 Adding Prometheus community Helm repository...")
+            try:
+                subprocess.run([
+                    'helm', 'repo', 'add', 'prometheus-community', 
+                    'https://prometheus-community.github.io/helm-charts'
+                ], check=True, capture_output=True)
+                
+                subprocess.run(['helm', 'repo', 'update'], check=True, capture_output=True)
+                print("✅ Helm repository added and updated")
+            except subprocess.CalledProcessError as e:
+                return {
+                    'success': False,
+                    'error': f'Failed to add Helm repository: {e.stderr.decode() if e.stderr else str(e)}'
+                }
+            
+            # Create Helm values file
+            helm_values = {
+                'grafana': {
+                    'enabled': True,
+                    'persistence': {
+                        'enabled': True,
+                        'size': grafana_storage_size
+                    },
+                    'service': {
+                        'type': grafana_service_type
+                    },
+                    'adminPassword': 'admin',
+                    'datasources': {
+                        'datasources.yaml': {
+                            'apiVersion': 1,
+                            'datasources': [{
+                                'name': 'Prometheus',
+                                'type': 'prometheus',
+                                'url': 'http://kube-prometheus-stack-prometheus:9090',
+                                'access': 'proxy',
+                                'isDefault': True
+                            }]
+                        }
+                    },
+                    'dashboardProviders': {
+                        'dashboardproviders.yaml': {
+                            'apiVersion': 1,
+                            'providers': [{
+                                'name': 'default',
+                                'orgId': 1,
+                                'folder': '',
+                                'type': 'file',
+                                'disableDeletion': False,
+                                'editable': True,
+                                'options': {
+                                    'path': '/var/lib/grafana/dashboards/default'
+                                }
+                            }]
+                        }
+                    },
+                    'dashboards': {
+                        'default': {
+                            'kubernetes-cluster-dashboard': {
+                                'gnetId': 7249,
+                                'revision': 1,
+                                'datasource': 'Prometheus'
+                            },
+                            'kubernetes-pod-dashboard': {
+                                'gnetId': 6417,
+                                'revision': 1,
+                                'datasource': 'Prometheus'
+                            },
+                            'node-exporter-dashboard': {
+                                'gnetId': 1860,
+                                'revision': 27,
+                                'datasource': 'Prometheus'
+                            }
+                        }
+                    }
+                },
+                'prometheus': {
+                    'enabled': True,
+                    'prometheusSpec': {
+                        'retention': '30d',
+                        'storageSpec': {
+                            'volumeClaimTemplate': {
+                                'spec': {
+                                    'accessModes': ['ReadWriteOnce'],
+                                    'resources': {
+                                        'requests': {
+                                            'storage': prometheus_storage_size
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        'serviceMonitorSelectorNilUsesHelmValues': False
+                    }
+                },
+                'alertmanager': {
+                    'enabled': True
+                },
+                'nodeExporter': {
+                    'enabled': True
+                },
+                'kubeStateMetrics': {
+                    'enabled': True
+                },
+                'defaultRules': {
+                    'create': True,
+                    'rules': {
+                        'alertmanager': True,
+                        'etcd': True,
+                        'general': True,
+                        'k8s': True,
+                        'kubeApiserver': True,
+                        'kubePrometheusNodeRecording': True,
+                        'kubernetesApps': True,
+                        'kubernetesResources': True,
+                        'kubernetesStorage': True,
+                        'kubernetesSystem': True,
+                        'network': True,
+                        'node': True,
+                        'prometheus': True,
+                        'prometheusOperator': True
+                    }
+                }
+            }
+            
+            # Add ingress if requested
+            if install_ingress:
+                helm_values['grafana']['ingress'] = {
+                    'enabled': True,
+                    'hosts': [f'grafana.{namespace}.local'],
+                    'paths': ['/']
+                }
+            
+            # Write values to temporary file
+            with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+                yaml.dump(helm_values, f, default_flow_style=False)
+                values_file = f.name
+            
+            try:
+                # Install the Helm chart
+                print("🚀 Installing kube-prometheus-stack via Helm...")
+                helm_cmd = [
+                    'helm', 'install', 'kube-prometheus-stack',
+                    'prometheus-community/kube-prometheus-stack',
+                    '--namespace', namespace,
+                    '--values', values_file
+                ]
+                
+                if wait_for_ready:
+                    helm_cmd.append('--wait')
+                    helm_cmd.extend(['--timeout', '10m'])
+                
+                result = subprocess.run(helm_cmd, capture_output=True, text=True, check=True)
+                print("✅ Helm chart installed successfully")
+                
+                # Wait a bit for pods to start
+                if wait_for_ready:
+                    print("⏳ Waiting for pods to be ready...")
+                    time.sleep(30)
+                
+                # Get service information
+                services_info = self._get_helm_monitoring_services(namespace)
+                
+                return {
+                    'success': True,
+                    'namespace': namespace,
+                    'release_name': 'kube-prometheus-stack',
+                    'prometheus': {'deployed': True},
+                    'grafana': {
+                        'deployed': True,
+                        'admin_password': 'admin'
+                    },
+                    'grafana_url': services_info.get('grafana_url'),
+                    'prometheus_url': services_info.get('prometheus_url'),
+                    'alertmanager_url': services_info.get('alertmanager_url')
+                }
+                
+            finally:
+                # Clean up temporary file
+                os.unlink(values_file)
+                
+        except subprocess.CalledProcessError as e:
+            error_msg = e.stderr.decode() if e.stderr else str(e)
+            return {
+                'success': False,
+                'error': f'Helm installation failed: {error_msg}'
+            }
+        except Exception as e:
+            return {
+                'success': False,
+                'error': f'Failed to setup Helm monitoring: {str(e)}'
+            }
+    
+    def get_helm_monitoring_info(self, namespace: str = "monitoring") -> Dict:
+        """Get information about the Helm-based monitoring stack"""
+        import subprocess
+        
+        try:
+            # Check if Helm release exists
+            try:
+                result = subprocess.run([
+                    'helm', 'status', 'kube-prometheus-stack', 
+                    '--namespace', namespace
+                ], capture_output=True, text=True, check=True)
+                
+                # Parse Helm status
+                lines = result.stdout.split('\n')
+                release_info = {}
+                for line in lines:
+                    if 'STATUS:' in line:
+                        release_info['release_status'] = line.split('STATUS:')[1].strip()
+                    elif 'LAST DEPLOYED:' in line:
+                        release_info['last_deployed'] = line.split('LAST DEPLOYED:')[1].strip()
+                
+            except subprocess.CalledProcessError:
+                return {'error': 'Helm release not found. Use setup-helm-monitoring to deploy first.'}
+            
+            # Get services information
+            services_info = self._get_helm_monitoring_services(namespace)
+            
+            # Get pod status
+            pods_info = self._get_monitoring_pods_status(namespace)
+            
+            return {
+                'release_name': 'kube-prometheus-stack',
+                'release_status': release_info.get('release_status', 'Unknown'),
+                'last_deployed': release_info.get('last_deployed', 'Unknown'),
+                'prometheus': {
+                    'running': any(pod['name'].startswith('prometheus-kube-prometheus-stack-prometheus') 
+                                 for pod in pods_info if pod['status'] == 'Running'),
+                    'url': services_info.get('prometheus_url', 'Port-forward required')
+                },
+                'grafana': {
+                    'running': any(pod['name'].startswith('kube-prometheus-stack-grafana') 
+                                 for pod in pods_info if pod['status'] == 'Running'),
+                    'url': services_info.get('grafana_url', 'Port-forward required')
+                },
+                'alertmanager': {
+                    'running': any(pod['name'].startswith('alertmanager-kube-prometheus-stack-alertmanager') 
+                                 for pod in pods_info if pod['status'] == 'Running'),
+                    'url': services_info.get('alertmanager_url', 'Port-forward required')
+                },
+                'pods': pods_info
+            }
+            
+        except Exception as e:
+            return {'error': f'Failed to get monitoring info: {str(e)}'}
+    
+    def delete_helm_monitoring(self, namespace: str = "monitoring", 
+                             release_name: str = "kube-prometheus-stack") -> Dict:
+        """Delete Helm-based monitoring stack"""
+        import subprocess
+        
+        try:
+            # Uninstall Helm release
+            result = subprocess.run([
+                'helm', 'uninstall', release_name,
+                '--namespace', namespace
+            ], capture_output=True, text=True, check=True)
+            
+            print(f"✅ Helm release '{release_name}' uninstalled")
+            
+            # Count remaining resources (optional cleanup)
+            try:
+                # Delete PVCs that might remain
+                pvcs = self.core_v1.list_namespaced_persistent_volume_claim(namespace=namespace)
+                pvc_count = 0
+                for pvc in pvcs.items:
+                    if 'prometheus' in pvc.metadata.name or 'grafana' in pvc.metadata.name:
+                        self.core_v1.delete_namespaced_persistent_volume_claim(
+                            name=pvc.metadata.name, 
+                            namespace=namespace
+                        )
+                        pvc_count += 1
+                
+                if pvc_count > 0:
+                    print(f"✅ Cleaned up {pvc_count} persistent volume claims")
+                
+            except Exception as cleanup_error:
+                print(f"⚠️  Could not clean up some resources: {cleanup_error}")
+            
+            return {
+                'success': True,
+                'resources_deleted': pvc_count
+            }
+            
+        except subprocess.CalledProcessError as e:
+            error_msg = e.stderr.decode() if e.stderr else str(e)
+            return {
+                'success': False,
+                'error': f'Failed to uninstall Helm release: {error_msg}'
+            }
+        except Exception as e:
+            return {
+                'success': False,
+                'error': f'Failed to delete monitoring stack: {str(e)}'
+            }
+    
+    def _get_helm_monitoring_services(self, namespace: str) -> Dict:
+        """Get service URLs for Helm monitoring components"""
+        services_info = {}
+        
+        try:
+            # Get services
+            services = self.core_v1.list_namespaced_service(namespace=namespace)
+            
+            for service in services.items:
+                service_name = service.metadata.name
+                
+                if 'grafana' in service_name:
+                    url = self._get_service_url(service, namespace, 80)
+                    if url:
+                        services_info['grafana_url'] = url
+                
+                elif 'prometheus' in service_name and 'operated' not in service_name:
+                    url = self._get_service_url(service, namespace, 9090)
+                    if url:
+                        services_info['prometheus_url'] = url
+                
+                elif 'alertmanager' in service_name and 'operated' not in service_name:
+                    url = self._get_service_url(service, namespace, 9093)
+                    if url:
+                        services_info['alertmanager_url'] = url
+        
+        except Exception as e:
+            print(f"⚠️  Could not get service information: {e}")
+        
+        return services_info
+    
+    def _get_monitoring_pods_status(self, namespace: str) -> List[Dict]:
+        """Get status of monitoring pods"""
+        pods_info = []
+        
+        try:
+            pods = self.core_v1.list_namespaced_pod(namespace=namespace)
+            
+            for pod in pods.items:
+                if any(component in pod.metadata.name for component in 
+                      ['prometheus', 'grafana', 'alertmanager', 'node-exporter', 'kube-state-metrics']):
+                    
+                    ready_containers = 0
+                    total_containers = len(pod.status.container_statuses) if pod.status.container_statuses else 0
+                    
+                    if pod.status.container_statuses:
+                        ready_containers = sum(1 for cs in pod.status.container_statuses if cs.ready)
+                    
+                    pods_info.append({
+                        'name': pod.metadata.name,
+                        'status': pod.status.phase,
+                        'ready': ready_containers,
+                        'total': total_containers
+                    })
+        
+        except Exception as e:
+            print(f"⚠️  Could not get pod status: {e}")
+        
+        return pods_info

{k8s_helper_cli-0.4.3.dist-info → k8s_helper_cli-0.5.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: k8s-helper-cli
-Version: 0.4.3
+Version: 0.5.1
 Summary: A simplified Python wrapper for common Kubernetes operations
 Author-email: Harshit Chatterjee <harshitchatterjee50@gmail.com>
 License-Expression: MIT

k8s_helper_cli-0.5.1.dist-info/RECORD

@@ -0,0 +1,11 @@
+k8s_helper/__init__.py,sha256=Rm3LMlyreNv628XF3jVu7wszfxHHL0JWZKzmHFmq_D0,2666
+k8s_helper/cli.py,sha256=U4oPgjykRmkBvPli7jZLVvZrb13L6-wjV0hd-RQZN9g,92124
+k8s_helper/config.py,sha256=P7YdfyvCHprrNs2J9DRb3RrClylfTTh5hfTtDzLug0A,6867
+k8s_helper/core.py,sha256=P6nvVPuW44Jdvkm572__d4nycLin6cl8obZ-XqzuTY4,147614
+k8s_helper/utils.py,sha256=wYgTd5ktyuI-EiVcfW7FrxA7MzXY5odrEKQgmMVdueY,9496
+k8s_helper_cli-0.5.1.dist-info/licenses/LICENSE,sha256=tXPvVl3gLVc6e0qCEoLH9KjeA7z4JVL78UybpvGtBCw,1096
+k8s_helper_cli-0.5.1.dist-info/METADATA,sha256=Z2Il7mbkN4p29oc_83mIjxD3l13IPTihkzo5d0JPIT4,30789
+k8s_helper_cli-0.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+k8s_helper_cli-0.5.1.dist-info/entry_points.txt,sha256=IoCMWUZ6mn90LwzQzEy5YkWOwvogDdZ6ycqUWAzCFTQ,50
+k8s_helper_cli-0.5.1.dist-info/top_level.txt,sha256=x9A1jflyer-z2cFnkqk5B42juoH2q0fy5hkT9upsTG8,11
+k8s_helper_cli-0.5.1.dist-info/RECORD,,

k8s_helper_cli-0.4.3.dist-info/RECORD

@@ -1,11 +0,0 @@
-k8s_helper/__init__.py,sha256=8xOzKrONciTYSjLyhDKR4cQs5wVVtW0UZll7TnsTpqQ,2666
-k8s_helper/cli.py,sha256=g0hzBHaROOT0gbKN5xu5GeC-aqbIyXpl3U-xx7vNWEU,80259
-k8s_helper/config.py,sha256=P7YdfyvCHprrNs2J9DRb3RrClylfTTh5hfTtDzLug0A,6867
-k8s_helper/core.py,sha256=R0_EDqVGFWQCpu5YuWC4abLLWIqjFtpn6KHgGD_Wues,112490
-k8s_helper/utils.py,sha256=wYgTd5ktyuI-EiVcfW7FrxA7MzXY5odrEKQgmMVdueY,9496
-k8s_helper_cli-0.4.3.dist-info/licenses/LICENSE,sha256=tXPvVl3gLVc6e0qCEoLH9KjeA7z4JVL78UybpvGtBCw,1096
-k8s_helper_cli-0.4.3.dist-info/METADATA,sha256=-uygNSjY9k0yhuw6KPwft5Uu-77b0GBGCPRURlt4PEM,30789
-k8s_helper_cli-0.4.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-k8s_helper_cli-0.4.3.dist-info/entry_points.txt,sha256=IoCMWUZ6mn90LwzQzEy5YkWOwvogDdZ6ycqUWAzCFTQ,50
-k8s_helper_cli-0.4.3.dist-info/top_level.txt,sha256=x9A1jflyer-z2cFnkqk5B42juoH2q0fy5hkT9upsTG8,11
-k8s_helper_cli-0.4.3.dist-info/RECORD,,