# Install Argo Workflows (cluster-wide)
kubectl create namespace argo
kubectl apply -n argo -f https://github.com/argoproj/argo-workflows/releases/download/v3.4.4/install.yaml

# Verify installation
kubectl get pods -n argo
# Should show argo-server and workflow-controller pods running

# argo-workflows-config.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: workflow-controller-configmap
  namespace: argo
data:
  config: |
    # Increase parallelism for production
    parallelism: 100
    # Set resource limits
    resourceRateLimit:
      limit: 10
      burst: 1
    # Configure artifact repository
    artifactRepository:
      s3:
        bucket: my-argo-artifacts
        endpoint: s3.amazonaws.com
        region: us-west-2

# Install Argo Events (cluster-wide)
kubectl create namespace argo-events
kubectl apply -f https://raw.githubusercontent.com/argoproj/argo-events/stable/manifests/install.yaml

# Verify installation
kubectl get pods -n argo-events
# Should show eventbus-controller and eventsource-controller pods running

# Install cert-manager
kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.13.0/cert-manager.yaml

# Verify installation
kubectl get pods -n cert-manager

# Install Prometheus Operator
helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
helm repo update
helm install prometheus prometheus-community/kube-prometheus-stack \
  --namespace monitoring \
  --create-namespace

# Add the KFP Operator Helm repository
helm repo add kfp-operator https://sky-uk.github.io/kfp-operator/
helm repo update

# Verify the repository
helm search repo kfp-operator

# values.yaml - Production configuration
namespace:
  create: true
  name: kfp-operator-system

manager:
  # High availability setup
  replicas: 2
  
  # Resource allocation
  resources:
    requests:
      cpu: 200m
      memory: 256Mi
    limits:
      cpu: 1000m
      memory: 1Gi
  
  # Argo Workflows configuration
  argo:
    serviceAccount:
      create: true
      name: kfp-operator-argo
    stepTimeoutSeconds:
      default: 1800    # 30 minutes
      compile: 3600    # 1 hour
    ttlStrategy:
      secondsAfterCompletion: 3600  # Clean up after 1 hour
    containerDefaults:
      resources:
        requests:
          cpu: 100m
          memory: 128Mi
        limits:
          cpu: 500m
          memory: 512Mi
  
  # Security configuration
  rbac:
    create: true
  
  # Monitoring configuration
  monitoring:
    create: true
    serviceMonitor:
      create: true  # For Prometheus Operator
  
  # Webhook configuration (production)
  multiversion:
    enabled: true
  webhookCertificates:
    provider: cert-manager  # Use cert-manager for TLS

# Enable event-driven workflows
statusFeedback:
  enabled: true

# Logging configuration
logging:
  verbosity: 1  # 0=error, 1=info, 2=debug

# Container registry configuration
containerRegistry: "your-registry.com/kfp-operator"

# Install with custom configuration
helm install kfp-operator kfp-operator/kfp-operator \
  --namespace kfp-operator-system \
  --create-namespace \
  --values values.yaml

# Verify installation
helm list -n kfp-operator-system

# Install directly from OCI registry
helm install kfp-operator \
  oci://ghcr.io/sky-uk/kfp-operator/helm/kfp-operator \
  --namespace kfp-operator-system \
  --create-namespace \
  --values values.yaml

# Clone repository and install from source
git clone https://github.com/sky-uk/kfp-operator.git
cd kfp-operator

# Install from local chart
helm install kfp-operator ./helm/kfp-operator \
  --namespace kfp-operator-system \
  --create-namespace \
  --values values.yaml

# Check operator pods
kubectl get pods -n kfp-operator-system

# Expected output:
# NAME                                           READY   STATUS    RESTARTS   AGE
# kfp-operator-controller-manager-xxx-xxx        2/2     Running   0          2m

# Check Custom Resource Definitions
kubectl get crd | grep pipelines.kubeflow.org

# Expected output:
# pipelines.pipelines.kubeflow.org
# providers.pipelines.kubeflow.org
# runconfigurations.pipelines.kubeflow.org
# runs.pipelines.kubeflow.org

# Check operator logs for any errors
kubectl logs -n kfp-operator-system deployment/kfp-operator-controller-manager

# Should show successful startup messages

# Create a test provider (adjust for your environment)
cat <<EOF | kubectl apply -f -
apiVersion: pipelines.kubeflow.org/v1alpha5
kind: Provider
metadata:
  name: test-provider
  namespace: default
spec:
  type: kfp
  kfp:
    restKfpApiUrl: "http://ml-pipeline.kubeflow.svc.cluster.local:8888"
EOF

# Check provider status
kubectl get providers
# Should show the provider with Ready status

# Custom RBAC configuration
manager:
  rbac:
    create: true
    # Additional cluster roles for multi-tenancy
    additionalClusterRoles:
      - name: kfp-operator-tenant-viewer
        rules:
          - apiGroups: ["pipelines.kubeflow.org"]
            resources: ["pipelines", "runs"]
            verbs: ["get", "list", "watch"]

# Service account configuration
manager:
  serviceAccount:
    create: true
    name: kfp-operator-controller-manager
    annotations:
      # For cloud provider integration
      iam.gke.io/gcp-service-account: kfp-operator@project.iam.gserviceaccount.com

# Enable ServiceMonitor for Prometheus
manager:
  monitoring:
    create: true
    serviceMonitor:
      create: true
      interval: 30s
      scrapeTimeout: 10s

# Download dashboard JSON
curl -o kfp-operator-dashboard.json \
  https://raw.githubusercontent.com/sky-uk/kfp-operator/master/monitoring/grafana-dashboard.json

# Import into Grafana UI or via ConfigMap

# Check CRD status
kubectl get crd | grep pipelines.kubeflow.org

# If missing, manually install
kubectl apply -f https://raw.githubusercontent.com/sky-uk/kfp-operator/master/config/crd/bases/

# Check webhook configuration
kubectl get validatingwebhookconfiguration | grep kfp-operator

# Check certificate status (if using cert-manager)
kubectl get certificates -n kfp-operator-system

# Check service account permissions
kubectl auth can-i create pipelines --as=system:serviceaccount:kfp-operator-system:kfp-operator-controller-manager

# Review RBAC configuration
kubectl get clusterroles | grep kfp-operator