Separates cluster service config from install.

Full cloud setup test run #1 fixes.
Adds more to wild-backup.
2025-09-02 16:24:38 -07:00 · 2025-09-02 02:53:52 -07:00 · 2025-08-31 15:02:35 -07:00 · 2025-08-31 15:00:00 -07:00 · 2025-08-31 14:49:35 -07:00 · 2025-08-31 14:46:42 -07:00
47 changed files with 1304 additions and 771 deletions
--- a/apps/discourse/configmap.yaml
+++ b/apps/discourse/configmap.yaml
@@ -11,33 +11,21 @@ data:
  DISCOURSE_SITE_NAME: "{{ .apps.discourse.siteName }}"
  DISCOURSE_USERNAME: "{{ .apps.discourse.adminUsername }}"
  DISCOURSE_EMAIL: "{{ .apps.discourse.adminEmail }}"
+
  DISCOURSE_REDIS_HOST: "{{ .apps.discourse.redisHostname }}"
  DISCOURSE_REDIS_PORT_NUMBER: "6379"
+
  DISCOURSE_DATABASE_HOST: "{{ .apps.discourse.dbHostname }}"
  DISCOURSE_DATABASE_PORT_NUMBER: "5432"
  DISCOURSE_DATABASE_NAME: "{{ .apps.discourse.dbName }}"
  DISCOURSE_DATABASE_USER: "{{ .apps.discourse.dbUsername }}"

-  # DISCOURSE_SMTP_ADDRESS: "{{ .apps.discourse.smtp.host }}"
-  # DISCOURSE_SMTP_PORT: "{{ .apps.discourse.smtp.port }}"
-  # DISCOURSE_SMTP_USER_NAME: "{{ .apps.discourse.smtp.user }}"
-  # DISCOURSE_SMTP_ENABLE_START_TLS: "{{ .apps.discourse.smtp.startTls }}"
-  # DISCOURSE_SMTP_AUTHENTICATION: "login"
-
-  # Bitnami specific environment variables (diverges from the original)
-  # https://techdocs.broadcom.com/us/en/vmware-tanzu/bitnami-secure-images/bitnami-secure-images/services/bsi-app-doc/apps-containers-discourse-index.html
  DISCOURSE_SMTP_HOST: "{{ .apps.discourse.smtp.host }}"
-  DISCOURSE_SMTP_PORT_NUMBER: "{{ .apps.discourse.smtp.port }}"
+  DISCOURSE_SMTP_PORT: "{{ .apps.discourse.smtp.port }}"
  DISCOURSE_SMTP_USER: "{{ .apps.discourse.smtp.user }}"
-  DISCOURSE_SMTP_ENABLE_START_TLS: "{{ .apps.discourse.smtp.startTls }}"
-  DISCOURSE_SMTP_AUTH: "login"
  DISCOURSE_SMTP_PROTOCOL: "tls"
+  DISCOURSE_SMTP_AUTH: "login"

-  DISCOURSE_PRECOMPILE_ASSETS: "false"
-
-  # SMTP_HOST: "{{ .apps.discourse.smtp.host }}"
-  # SMTP_PORT: "{{ .apps.discourse.smtp.port }}"
-  # SMTP_USER_NAME: "{{ .apps.discourse.smtp.user }}"
-  # SMTP_TLS: "{{ .apps.discourse.smtp.tls }}"
-  # SMTP_ENABLE_START_TLS: "{{ .apps.discourse.smtp.startTls }}"
-  # SMTP_AUTHENTICATION: "login"
+  # DISCOURSE_PRECOMPILE_ASSETS: "false"
+  # DISCOURSE_SKIP_INSTALL: "no"
+  # DISCOURSE_SKIP_BOOTSTRAP: "yes"
--- a/apps/discourse/deployment.yaml
+++ b/apps/discourse/deployment.yaml
@@ -37,7 +37,7 @@ spec:
      initContainers:
      containers:
        - name: discourse
-          image: { { .apps.discourse.image } }
+          image: docker.io/bitnami/discourse:3.4.7-debian-12-r0
          imagePullPolicy: "IfNotPresent"
          securityContext:
            allowPrivilegeEscalation: false
@@ -85,7 +85,7 @@ spec:
              valueFrom:
                secretKeyRef:
                  name: discourse-secrets
-                  key: apps.discourse.redisPassword
+                  key: apps.redis.password
            - name: DISCOURSE_SECRET_KEY_BASE
              valueFrom:
                secretKeyRef:
@@ -139,7 +139,7 @@ spec:
              mountPath: /bitnami/discourse
              subPath: discourse
        - name: sidekiq
-          image: { { .apps.discourse.sidekiqImage } }
+          image: docker.io/bitnami/discourse:3.4.7-debian-12-r0
          imagePullPolicy: "IfNotPresent"
          securityContext:
            allowPrivilegeEscalation: false
@@ -182,7 +182,7 @@ spec:
              valueFrom:
                secretKeyRef:
                  name: discourse-secrets
-                  key: apps.discourse.redisPassword
+                  key: apps.redis.password
            - name: DISCOURSE_SECRET_KEY_BASE
              valueFrom:
                secretKeyRef:
--- a/apps/discourse/manifest.yaml
+++ b/apps/discourse/manifest.yaml
@@ -6,8 +6,6 @@ requires:
  - name: postgres
  - name: redis
 defaultConfig:
-  image: docker.io/bitnami/discourse:3.4.7-debian-12-r0
-  sidekiqImage: docker.io/bitnami/discourse:3.4.7-debian-12-r0
  timezone: UTC
  port: 8080
  storage: 10Gi
@@ -32,7 +30,7 @@ requiredSecrets:
  - apps.discourse.adminPassword
  - apps.discourse.dbPassword
  - apps.discourse.dbUrl
-  - apps.discourse.redisPassword
+  - apps.redis.password
  - apps.discourse.secretKeyBase
  - apps.discourse.smtpPassword
  - apps.postgres.password
--- a/apps/immich/db-init-job.yaml
+++ b/apps/immich/db-init-job.yaml
@@ -52,7 +52,7 @@ spec:
            - name: POSTGRES_ADMIN_PASSWORD
              valueFrom:
                secretKeyRef:
-                  name: postgres-secrets
+                  name: immich-secrets
                  key: apps.postgres.password
            - name: DB_HOSTNAME
              value: "{{ .apps.immich.dbHostname }}"
--- a/bin/wild-backup
+++ b/bin/wild-backup
@@ -4,6 +4,72 @@
 set -e
 set -o pipefail

+# Parse command line flags
+BACKUP_HOME=true
+BACKUP_APPS=true
+BACKUP_CLUSTER=true
+
+show_help() {
+    echo "Usage: $0 [OPTIONS]"
+    echo "Backup components of your wild-cloud infrastructure"
+    echo ""
+    echo "Options:"
+    echo "  --home-only       Backup only WC_HOME (wild-cloud configuration)"
+    echo "  --apps-only       Backup only applications (databases and PVCs)"
+    echo "  --cluster-only    Backup only Kubernetes cluster resources"
+    echo "  --no-home         Skip WC_HOME backup"
+    echo "  --no-apps         Skip application backups"
+    echo "  --no-cluster      Skip cluster resource backup"
+    echo "  -h, --help        Show this help message"
+    echo ""
+    echo "Default: Backup all components (home, apps, cluster)"
+}
+
+# Process command line arguments
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --home-only)
+            BACKUP_HOME=true
+            BACKUP_APPS=false
+            BACKUP_CLUSTER=false
+            shift
+            ;;
+        --apps-only)
+            BACKUP_HOME=false
+            BACKUP_APPS=true
+            BACKUP_CLUSTER=false
+            shift
+            ;;
+        --cluster-only)
+            BACKUP_HOME=false
+            BACKUP_APPS=false
+            BACKUP_CLUSTER=true
+            shift
+            ;;
+        --no-home)
+            BACKUP_HOME=false
+            shift
+            ;;
+        --no-apps)
+            BACKUP_APPS=false
+            shift
+            ;;
+        --no-cluster)
+            BACKUP_CLUSTER=false
+            shift
+            ;;
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1"
+            show_help
+            exit 1
+            ;;
+    esac
+done
+
 # Initialize Wild Cloud environment
 if [ -z "${WC_ROOT}" ]; then
    echo "WC_ROOT is not set."
@@ -46,18 +112,25 @@ else
    echo "Repository initialized successfully."
 fi

-# Backup entire WC_HOME.
-restic --verbose --tag wild-cloud --tag wc-home --tag "$(date +%Y-%m-%d)" backup $WC_HOME
-# TODO: Ignore wild cloud cache?
+# Backup entire WC_HOME
+if [ "$BACKUP_HOME" = true ]; then
+    echo "Backing up WC_HOME..."
+    restic --verbose --tag wild-cloud --tag wc-home --tag "$(date +%Y-%m-%d)" backup $WC_HOME
+    echo "WC_HOME backup completed."
+    # TODO: Ignore wild cloud cache?
+else
+    echo "Skipping WC_HOME backup."
+fi

 mkdir -p "$STAGING_DIR"

 # Run backup for all apps at once
-echo "Running backup for all apps..."
-wild-app-backup --all
+if [ "$BACKUP_APPS" = true ]; then
+    echo "Running backup for all apps..."
+    wild-app-backup --all

-# Upload each app's backup to restic individually  
-for app_dir in "$STAGING_DIR"/apps/*; do
+    # Upload each app's backup to restic individually  
+    for app_dir in "$STAGING_DIR"/apps/*; do
        if [ ! -d "$app_dir" ]; then
            continue
        fi
@@ -65,14 +138,108 @@ for app_dir in "$STAGING_DIR"/apps/*; do
        echo "Uploading backup for app: $app"
        restic --verbose --tag wild-cloud --tag "$app" --tag "$(date +%Y-%m-%d)" backup "$app_dir"
        echo "Backup for app '$app' completed."
-done
+    done
+else
+    echo "Skipping application backups."
+fi

-# Back up Kubernetes resources
-# kubectl get all -A -o yaml > "$BACKUP_DIR/all-resources.yaml"
-# kubectl get secrets -A -o yaml > "$BACKUP_DIR/secrets.yaml"
-# kubectl get configmaps -A -o yaml > "$BACKUP_DIR/configmaps.yaml"
+# --- etcd Backup Function ----------------------------------------------------
+backup_etcd() {
+    local cluster_backup_dir="$1"
+    local etcd_backup_file="$cluster_backup_dir/etcd-snapshot.db"
    
-# Back up persistent volumes
-# TODO: Add logic to back up persistent volume data
+    echo "Creating etcd snapshot..."
+    
+    # For Talos, we use talosctl to create etcd snapshots
+    if command -v talosctl >/dev/null 2>&1; then
+        # Try to get etcd snapshot via talosctl (works for Talos clusters)
+        local control_plane_nodes
+        control_plane_nodes=$(kubectl get nodes -l node-role.kubernetes.io/control-plane -o jsonpath='{.items[*].status.addresses[?(@.type=="InternalIP")].address}' | tr ' ' '\n' | head -1)
+        
+        if [[ -n "$control_plane_nodes" ]]; then
+            echo "Using talosctl to backup etcd from control plane node: $control_plane_nodes"
+            if talosctl --nodes "$control_plane_nodes" etcd snapshot "$etcd_backup_file"; then
+                echo "  etcd backup created: $etcd_backup_file"
+                return 0
+            else
+                echo "  talosctl etcd snapshot failed, trying alternative method..."
+            fi
+        else
+            echo "  No control plane nodes found for talosctl method"
+        fi
+    fi
+    
+    # Alternative: Try to backup via etcd pod if available
+    local etcd_pod
+    etcd_pod=$(kubectl get pods -n kube-system -l component=etcd -o jsonpath='{.items[0].metadata.name}' 2>/dev/null || true)
+    
+    if [[ -n "$etcd_pod" ]]; then
+        echo "Using etcd pod: $etcd_pod"
+        # Create snapshot using etcdctl inside the etcd pod
+        if kubectl exec -n kube-system "$etcd_pod" -- etcdctl \
+            --endpoints=https://127.0.0.1:2379 \
+            --cacert=/etc/kubernetes/pki/etcd/ca.crt \
+            --cert=/etc/kubernetes/pki/etcd/server.crt \
+            --key=/etc/kubernetes/pki/etcd/server.key \
+            snapshot save /tmp/etcd-snapshot.db; then
+            
+            # Copy snapshot out of pod
+            kubectl cp -n kube-system "$etcd_pod:/tmp/etcd-snapshot.db" "$etcd_backup_file"
+            
+            # Clean up temporary file in pod
+            kubectl exec -n kube-system "$etcd_pod" -- rm -f /tmp/etcd-snapshot.db
+            
+            echo "  etcd backup created: $etcd_backup_file"
+            return 0
+        else
+            echo "  etcd pod snapshot failed"
+        fi
+    else
+        echo "  No etcd pod found in kube-system namespace"
+    fi
+    
+    # Final fallback: Try direct etcdctl if available on local system
+    if command -v etcdctl >/dev/null 2>&1; then
+        echo "Attempting local etcdctl backup..."
+        # This would need proper certificates and endpoints configured
+        echo "  Local etcdctl backup not implemented (requires certificate configuration)"
+    fi
+    
+    echo "  Warning: Could not create etcd backup - no working method found"
+    echo "  Consider installing talosctl or ensuring etcd pods are accessible"
+    return 1
+}
+
+# Back up Kubernetes cluster resources
+if [ "$BACKUP_CLUSTER" = true ]; then
+    echo "Backing up Kubernetes cluster resources..."
+    CLUSTER_BACKUP_DIR="$STAGING_DIR/cluster"
+    
+    # Clean up any existing cluster backup files
+    if [[ -d "$CLUSTER_BACKUP_DIR" ]]; then
+        echo "Cleaning up existing cluster backup files..."
+        rm -rf "$CLUSTER_BACKUP_DIR"
+    fi
+    mkdir -p "$CLUSTER_BACKUP_DIR"
+
+    kubectl get all -A -o yaml > "$CLUSTER_BACKUP_DIR/all-resources.yaml"
+    kubectl get secrets -A -o yaml > "$CLUSTER_BACKUP_DIR/secrets.yaml"
+    kubectl get configmaps -A -o yaml > "$CLUSTER_BACKUP_DIR/configmaps.yaml"
+    kubectl get persistentvolumes -o yaml > "$CLUSTER_BACKUP_DIR/persistentvolumes.yaml"
+    kubectl get persistentvolumeclaims -A -o yaml > "$CLUSTER_BACKUP_DIR/persistentvolumeclaims.yaml"
+    kubectl get storageclasses -o yaml > "$CLUSTER_BACKUP_DIR/storageclasses.yaml"
+
+    echo "Backing up etcd..."
+    backup_etcd "$CLUSTER_BACKUP_DIR"
+
+    echo "Cluster resources backed up to $CLUSTER_BACKUP_DIR"
+
+    # Upload cluster backup to restic
+    echo "Uploading cluster backup to restic..."
+    restic --verbose --tag wild-cloud --tag cluster --tag "$(date +%Y-%m-%d)" backup "$CLUSTER_BACKUP_DIR"
+    echo "Cluster backup completed."
+else
+    echo "Skipping cluster backup."
+fi

 echo "Backup completed: $BACKUP_DIR"
--- a/bin/wild-cluster-config-generate
+++ b/bin/wild-cluster-config-generate
@@ -58,10 +58,8 @@ fi

 print_header "Talos Cluster Configuration Generation"

-# Ensure required directories exist
-NODE_SETUP_DIR="${WC_HOME}/setup/cluster-nodes"
-
 # Check if generated directory already exists and has content
+NODE_SETUP_DIR="${WC_HOME}/setup/cluster-nodes"
 if [ -d "${NODE_SETUP_DIR}/generated" ] && [ "$(ls -A "${NODE_SETUP_DIR}/generated" 2>/dev/null)" ] && [ "$FORCE" = false ]; then
    print_success "Cluster configuration already exists in ${NODE_SETUP_DIR}/generated/"
    print_info "Skipping cluster configuration generation"
@@ -77,8 +75,6 @@ if [ -d "${NODE_SETUP_DIR}/generated" ]; then
    rm -rf "${NODE_SETUP_DIR}/generated"
 fi
 mkdir -p "${NODE_SETUP_DIR}/generated"
-talosctl gen secrets
-print_info "New secrets will be generated in ${NODE_SETUP_DIR}/generated/"

 # Ensure we have the configuration we need.     

@@ -94,9 +90,8 @@ print_info "Cluster name: $CLUSTER_NAME"
 print_info "Control plane endpoint: https://$VIP:6443"

 cd "${NODE_SETUP_DIR}/generated"
+talosctl gen secrets
 talosctl gen config --with-secrets secrets.yaml "$CLUSTER_NAME" "https://$VIP:6443"
 cd - >/dev/null

-# Verify generated files
-
 print_success "Cluster configuration generation completed!"
--- a/bin/wild-cluster-node-boot-assets-download
+++ b/bin/wild-cluster-node-boot-assets-download
@@ -51,76 +51,32 @@ else
    init_wild_env
 fi

-# Check for required configuration
-if [ -z "$(wild-config "cluster.nodes.talos.version")" ] || [ -z "$(wild-config "cluster.nodes.talos.schematicId")" ]; then
-    print_header "Talos Configuration Required"
-    print_error "Missing required Talos configuration"
-    print_info "Please run 'wild-setup' first to configure your cluster"
-    print_info "Or set the required configuration manually:"
-    print_info "  wild-config-set cluster.nodes.talos.version v1.10.4"
-    print_info "  wild-config-set cluster.nodes.talos.schematicId YOUR_SCHEMATIC_ID"
-    exit 1
-fi
-
 # =============================================================================
 # INSTALLER IMAGE GENERATION AND ASSET DOWNLOADING
 # =============================================================================

-print_header "Talos Installer Image Generation and Asset Download"
+print_header "Talos asset download"

-# Get Talos version and schematic ID from config
-TALOS_VERSION=$(wild-config cluster.nodes.talos.version)
-SCHEMATIC_ID=$(wild-config cluster.nodes.talos.schematicId)
+# Talos version
+prompt_if_unset_config "cluster.nodes.talos.version" "Talos version" "v1.11.0"
+TALOS_VERSION=$(wild-config "cluster.nodes.talos.version")
+
+# Talos schematic ID
+prompt_if_unset_config "cluster.nodes.talos.schematicId" "Talos schematic ID" "56774e0894c8a3a3a9834a2aea65f24163cacf9506abbcbdc3ba135eaca4953f"
+SCHEMATIC_ID=$(wild-config "cluster.nodes.talos.schematicId")

 print_info "Creating custom Talos installer image..."
 print_info "Talos version: $TALOS_VERSION"
-
-# Validate schematic ID
-if [ -z "$SCHEMATIC_ID" ] || [ "$SCHEMATIC_ID" = "null" ]; then
-    print_error "No schematic ID found in config.yaml"
-    print_info "Please run 'wild-setup' first to configure your cluster"
-    exit 1
-fi
-
 print_info "Schematic ID: $SCHEMATIC_ID"
-
-if [ -f "${WC_HOME}/config.yaml" ] && yq eval '.cluster.nodes.talos.schematic.customization.systemExtensions.officialExtensions' "${WC_HOME}/config.yaml" >/dev/null 2>&1; then
-    echo ""
-    print_info "Schematic includes:"
-    yq eval '.cluster.nodes.talos.schematic.customization.systemExtensions.officialExtensions[]' "${WC_HOME}/config.yaml" | sed 's/^/  - /' || true
-    echo ""
-fi
-
-# Generate installer image URL
 INSTALLER_URL="factory.talos.dev/metal-installer/$SCHEMATIC_ID:$TALOS_VERSION"
-
-print_success "Custom installer image URL generated!"
-echo ""
 print_info "Installer URL: $INSTALLER_URL"

+
 # =============================================================================
 # ASSET DOWNLOADING AND CACHING
 # =============================================================================

-print_header "Downloading and Caching PXE Boot Assets"
-
-# Create cache directories organized by schematic ID
-CACHE_DIR="${WC_HOME}/.wildcloud"
-SCHEMATIC_CACHE_DIR="${CACHE_DIR}/node-boot-assets/${SCHEMATIC_ID}"
-PXE_CACHE_DIR="${SCHEMATIC_CACHE_DIR}/pxe"
-IPXE_CACHE_DIR="${SCHEMATIC_CACHE_DIR}/ipxe"
-ISO_CACHE_DIR="${SCHEMATIC_CACHE_DIR}/iso"
-mkdir -p "$PXE_CACHE_DIR/amd64"
-mkdir -p "$IPXE_CACHE_DIR"
-mkdir -p "$ISO_CACHE_DIR"
-
-# Download Talos kernel and initramfs for PXE boot
-print_info "Downloading Talos PXE assets..."
-KERNEL_URL="https://pxe.factory.talos.dev/image/${SCHEMATIC_ID}/${TALOS_VERSION}/kernel-amd64"
-INITRAMFS_URL="https://pxe.factory.talos.dev/image/${SCHEMATIC_ID}/${TALOS_VERSION}/initramfs-amd64.xz"
-
-KERNEL_PATH="${PXE_CACHE_DIR}/amd64/vmlinuz"
-INITRAMFS_PATH="${PXE_CACHE_DIR}/amd64/initramfs.xz"
+print_header "Downloading and caching boot assets"

 # Function to download with progress
 download_asset() {
@@ -129,17 +85,19 @@ download_asset() {
    local description="$3"
    
    if [ -f "$path" ]; then
-        print_info "$description already cached at $path"
+        print_success "$description already cached at $path"
        return 0
    fi
    
    print_info "Downloading $description..."
    print_info "URL: $url"
    
-    if command -v wget >/dev/null 2>&1; then
-        wget --progress=bar:force -O "$path" "$url"
-    elif command -v curl >/dev/null 2>&1; then
-        curl -L --progress-bar -o "$path" "$url"
+    if command -v curl >/dev/null 2>&1; then
+        curl -L -o "$path" "$url" \
+            --progress-bar \
+            --write-out "✓ Downloaded %{size_download} bytes at %{speed_download} B/s\n"
+    elif command -v wget >/dev/null 2>&1; then
+        wget --progress=bar:force:noscroll -O "$path" "$url"
    else
        print_error "Neither wget nor curl is available for downloading"
        return 1
@@ -153,42 +111,51 @@ download_asset() {
    fi
    
    print_success "$description downloaded successfully"
+    echo
 }

-# Download Talos PXE assets
+CACHE_DIR="${WC_HOME}/.wildcloud"
+SCHEMATIC_CACHE_DIR="${CACHE_DIR}/node-boot-assets/${SCHEMATIC_ID}"
+PXE_CACHE_DIR="${SCHEMATIC_CACHE_DIR}/pxe"
+IPXE_CACHE_DIR="${SCHEMATIC_CACHE_DIR}/ipxe"
+ISO_CACHE_DIR="${SCHEMATIC_CACHE_DIR}/iso"
+mkdir -p "$PXE_CACHE_DIR/amd64"
+mkdir -p "$IPXE_CACHE_DIR"
+mkdir -p "$ISO_CACHE_DIR"
+
+# Download Talos kernel and initramfs for PXE boot
+KERNEL_URL="https://pxe.factory.talos.dev/image/${SCHEMATIC_ID}/${TALOS_VERSION}/kernel-amd64"
+KERNEL_PATH="${PXE_CACHE_DIR}/amd64/vmlinuz"
 download_asset "$KERNEL_URL" "$KERNEL_PATH" "Talos kernel"
+
+INITRAMFS_URL="https://pxe.factory.talos.dev/image/${SCHEMATIC_ID}/${TALOS_VERSION}/initramfs-amd64.xz"
+INITRAMFS_PATH="${PXE_CACHE_DIR}/amd64/initramfs.xz"
 download_asset "$INITRAMFS_URL" "$INITRAMFS_PATH" "Talos initramfs"

 # Download iPXE bootloader files
-print_info "Downloading iPXE bootloader assets..."
 download_asset "http://boot.ipxe.org/ipxe.efi" "${IPXE_CACHE_DIR}/ipxe.efi" "iPXE EFI bootloader"
 download_asset "http://boot.ipxe.org/undionly.kpxe" "${IPXE_CACHE_DIR}/undionly.kpxe" "iPXE BIOS bootloader"
 download_asset "http://boot.ipxe.org/arm64-efi/ipxe.efi" "${IPXE_CACHE_DIR}/ipxe-arm64.efi" "iPXE ARM64 EFI bootloader"

 # Download Talos ISO
-print_info "Downloading Talos ISO..."
 ISO_URL="https://factory.talos.dev/image/${SCHEMATIC_ID}/${TALOS_VERSION}/metal-amd64.iso"
-ISO_FILENAME="talos-${TALOS_VERSION}-metal-amd64.iso"
-ISO_PATH="${ISO_CACHE_DIR}/${ISO_FILENAME}"
+ISO_PATH="${ISO_CACHE_DIR}/talos-${TALOS_VERSION}-metal-amd64.iso"
 download_asset "$ISO_URL" "$ISO_PATH" "Talos ISO"

-echo ""
-print_success "All assets downloaded and cached!"
-echo ""
-print_info "Cached assets for schematic $SCHEMATIC_ID:"
-echo "  Talos kernel:     $KERNEL_PATH"
-echo "  Talos initramfs:  $INITRAMFS_PATH"
-echo "  Talos ISO:        $ISO_PATH"
-echo "  iPXE EFI:         ${IPXE_CACHE_DIR}/ipxe.efi"
-echo "  iPXE BIOS:        ${IPXE_CACHE_DIR}/undionly.kpxe"
-echo "  iPXE ARM64:       ${IPXE_CACHE_DIR}/ipxe-arm64.efi"
+print_header "Summary"
+print_success "Cached assets for schematic $SCHEMATIC_ID:"
+echo "- Talos kernel:     $KERNEL_PATH"
+echo "- Talos initramfs:  $INITRAMFS_PATH"
+echo "- Talos ISO:        $ISO_PATH"
+echo "- iPXE EFI:         ${IPXE_CACHE_DIR}/ipxe.efi"
+echo "- iPXE BIOS:        ${IPXE_CACHE_DIR}/undionly.kpxe"
+echo "- iPXE ARM64:       ${IPXE_CACHE_DIR}/ipxe-arm64.efi"
 echo ""
 print_info "Cache location: $SCHEMATIC_CACHE_DIR"
 echo ""
 print_info "Use these assets for:"
-echo "  - PXE boot: Use kernel and initramfs from cache"
-echo "  - USB creation: Use ISO file for dd or imaging tools"
+echo "- PXE boot: Use kernel and initramfs from cache"
+echo "- USB creation: Use ISO file for dd or imaging tools"
 echo "  Example: sudo dd if=$ISO_PATH of=/dev/sdX bs=4M status=progress"
-echo "  - Custom installer: https://$INSTALLER_URL"
+echo "- Custom installer: https://$INSTALLER_URL"
 echo ""
-print_success "Installer image generation and asset caching completed!"
--- a/bin/wild-cluster-node-up
+++ b/bin/wild-cluster-node-up
@@ -96,7 +96,7 @@ else
    init_wild_env
 fi

-print_header "Talos Node Configuration Application"
+print_header "Talos node configuration"

 # Check if the specified node is registered
 NODE_INTERFACE=$(yq eval ".cluster.nodes.active.\"${NODE_NAME}\".interface" "${WC_HOME}/config.yaml" 2>/dev/null)
@@ -156,10 +156,7 @@ PATCH_FILE="${NODE_SETUP_DIR}/patch/${NODE_NAME}.yaml"

 # Check if patch file exists
 if [ ! -f "$PATCH_FILE" ]; then
-    print_error "Patch file not found: $PATCH_FILE"
-    print_info "Generate the patch file first:"
-    print_info "  wild-cluster-node-patch-generate $NODE_NAME"
-    exit 1
+    wild-cluster-node-patch-generate "$NODE_NAME"
 fi

 # Determine base config file
--- a/bin/wild-cluster-services-configure
+++ b/bin/wild-cluster-services-configure
@@ -0,0 +1,124 @@
+#\!/bin/bash
+
+set -e
+set -o pipefail
+
+# Usage function
+usage() {
+    echo "Usage: wild-cluster-services-configure [options] [service...]"
+    echo ""
+    echo "Compile service templates with configuration"
+    echo ""
+    echo "Arguments:"
+    echo "  service             Specific service(s) to compile (optional)"
+    echo ""
+    echo "Options:"
+    echo "  -h, --help          Show this help message"
+    echo ""
+    echo "Examples:"
+    echo "  wild-cluster-services-configure                    # Compile all services"
+    echo "  wild-cluster-services-configure metallb traefik    # Compile specific services"
+    echo ""
+    echo "Available services:"
+    echo "  metallb, longhorn, traefik, coredns, cert-manager,"
+    echo "  externaldns, kubernetes-dashboard, nfs, docker-registry"
+}
+
+# Parse arguments
+DRY_RUN=false
+LIST_SERVICES=false
+SPECIFIC_SERVICES=()
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            usage
+            exit 0
+            ;;
+        --dry-run)
+            DRY_RUN=true
+            shift
+            ;;
+        -*)
+            echo "Unknown option $1"
+            usage
+            exit 1
+            ;;
+        *)
+            SPECIFIC_SERVICES+=("$1")
+            shift
+            ;;
+    esac
+done
+
+# Initialize Wild Cloud environment
+if [ -z "${WC_ROOT}" ]; then
+    print "WC_ROOT is not set."
+    exit 1
+else
+    source "${WC_ROOT}/scripts/common.sh"
+    init_wild_env
+fi
+
+CLUSTER_SETUP_DIR="${WC_HOME}/setup/cluster-services"
+
+# Check if cluster setup directory exists
+if [ ! -d "$CLUSTER_SETUP_DIR" ]; then
+    print_error "Cluster services setup directory not found: $CLUSTER_SETUP_DIR"
+    print_info "Run 'wild-cluster-services-generate' first to generate setup files"
+    exit 1
+fi
+
+# =============================================================================
+# CLUSTER SERVICES TEMPLATE COMPILATION
+# =============================================================================
+
+print_header "Cluster services template compilation"
+
+# Get list of services to compile
+if [ ${#SPECIFIC_SERVICES[@]} -gt 0 ]; then
+    SERVICES_TO_INSTALL=("${SPECIFIC_SERVICES[@]}")
+    print_info "Compiling specific services: ${SERVICES_TO_INSTALL[*]}"
+else
+    # Compile all available services in a specific order for dependencies
+    SERVICES_TO_INSTALL=(
+        "metallb"
+        "longhorn" 
+        "traefik"
+        "coredns"
+        "cert-manager"
+        "externaldns"
+        "kubernetes-dashboard"
+        "nfs"
+        "docker-registry"
+    )
+    print_info "Installing all available services"
+fi
+
+print_info "Services to compile: ${SERVICES_TO_INSTALL[*]}"
+
+# Compile services
+cd "$CLUSTER_SETUP_DIR"
+INSTALLED_COUNT=0
+FAILED_COUNT=0
+
+for service in "${SERVICES_TO_INSTALL[@]}"; do
+    print_info "Compiling $service"
+
+    service_dir="$CLUSTER_SETUP_DIR/$service"
+    source_service_dir="$service_dir/kustomize.template"
+    dest_service_dir="$service_dir/kustomize"
+
+    # Run configuration to make sure we have the template values we need.
+    config_script="$service_dir/configure.sh"
+    if [ -f "$config_script" ]; then
+        source "$config_script"
+    fi
+
+    wild-compile-template-dir --clean "$source_service_dir" "$dest_service_dir"
+    echo ""
+done
+
+cd - >/dev/null
+
+print_success "Successfully compiled: $INSTALLED_COUNT services"
--- a/bin/wild-cluster-services-fetch
+++ b/bin/wild-cluster-services-fetch
@@ -0,0 +1,148 @@
+#\!/bin/bash
+
+set -e
+set -o pipefail
+
+# Usage function
+usage() {
+    echo "Usage: wild-cluster-services-fetch [options]"
+    echo ""
+    echo "Fetch cluster services setup files from the repository."
+    echo ""
+    echo "Arguments:"
+    echo "  service             Specific service(s) to install (optional)"
+    echo ""
+    echo "Options:"
+    echo "  -h, --help          Show this help message"
+    echo "  --force             Force fetching even if files exist"
+    echo ""
+    echo "Examples:"
+    echo "  wild-cluster-services-fetch                    # Fetch all services"
+    echo "  wild-cluster-services-fetch metallb traefik    # Fetch specific services"
+    echo ""
+    echo "Available services:"
+    echo "  metallb, longhorn, traefik, coredns, cert-manager,"
+    echo "  externaldns, kubernetes-dashboard, nfs, docker-registry"
+}
+
+# Parse arguments
+FORCE=false
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            usage
+            exit 0
+            ;;
+        --force)
+            FORCE=true
+            shift
+            ;;
+        -*)
+            echo "Unknown option $1"
+            usage
+            exit 1
+            ;;
+        *)
+            echo "Unexpected argument: $1"
+            usage
+            exit 1
+            ;;
+    esac
+done
+
+# Initialize Wild Cloud environment
+if [ -z "${WC_ROOT}" ]; then
+    print "WC_ROOT is not set."
+    exit 1
+else
+    source "${WC_ROOT}/scripts/common.sh"
+    init_wild_env
+fi
+
+print_header "Fetching cluster services templates"
+
+SOURCE_DIR="${WC_ROOT}/setup/cluster-services"
+DEST_DIR="${WC_HOME}/setup/cluster-services"
+
+# Check if source directory exists
+if [ ! -d "$SOURCE_DIR" ]; then
+    print_error "Cluster setup source directory not found: $SOURCE_DIR"
+    print_info "Make sure the wild-cloud repository is properly set up"
+    exit 1
+fi
+
+# Check if destination already exists
+if [ -d "$DEST_DIR" ] && [ "$FORCE" = false ]; then
+    print_warning "Cluster setup directory already exists: $DEST_DIR"
+    read -p "Overwrite existing files? (y/N): " -n 1 -r
+    echo
+    if [[ $REPLY =~ ^[Yy]$ ]]; then
+        FORCE=true
+    fi
+else
+    mkdir -p "$DEST_DIR"
+fi
+
+# Copy README
+if [ ! -f "${WC_HOME}/setup/README.md" ]; then
+    cp "${WC_ROOT}/setup/README.md" "${WC_HOME}/setup/README.md"
+fi
+
+# Get list of services to install
+if [ ${#SPECIFIC_SERVICES[@]} -gt 0 ]; then
+    SERVICES_TO_INSTALL=("${SPECIFIC_SERVICES[@]}")
+    print_info "Fetching specific services: ${SERVICES_TO_INSTALL[*]}"
+else
+    # Install all available services in a specific order for dependencies
+    SERVICES_TO_INSTALL=(
+        "metallb"
+        "longhorn" 
+        "traefik"
+        "coredns"
+        "cert-manager"
+        "externaldns"
+        "kubernetes-dashboard"
+        "nfs"
+        "docker-registry"
+    )
+    print_info "Fetching all available services."
+fi
+
+for service in "${SERVICES_TO_INSTALL[@]}"; do
+
+    SERVICE_SOURCE_DIR="$SOURCE_DIR/$service"
+    SERVICE_DEST_DIR="$DEST_DIR/$service"
+    TEMPLATE_SOURCE_DIR="$SERVICE_SOURCE_DIR/kustomize.template"
+    TEMPLATE_DEST_DIR="$SERVICE_DEST_DIR/kustomize.template"
+
+    if [ ! -d "$TEMPLATE_SOURCE_DIR" ]; then
+        print_error "Source directory not found: $TEMPLATE_SOURCE_DIR"
+        continue
+    fi
+
+    if $FORCE && [ -d "$TEMPLATE_DEST_DIR" ]; then
+        print_info "Removing existing $service templates in: $TEMPLATE_DEST_DIR"
+        rm -rf "$TEMPLATE_DEST_DIR"
+    elif [ -d "$TEMPLATE_DEST_DIR" ]; then
+        print_info "Files already exist for $service, skipping (use --force to overwrite)."
+        continue
+    fi
+
+    mkdir -p "$SERVICE_DEST_DIR"
+    mkdir -p "$TEMPLATE_DEST_DIR"
+    cp -f "$SERVICE_SOURCE_DIR/README.md" "$SERVICE_DEST_DIR/"
+
+    if [ -f "$SERVICE_SOURCE_DIR/configure.sh" ]; then
+        cp -f "$SERVICE_SOURCE_DIR/configure.sh" "$SERVICE_DEST_DIR/"
+    fi
+
+    if [ -f "$SERVICE_SOURCE_DIR/install.sh" ]; then
+        cp -f "$SERVICE_SOURCE_DIR/install.sh" "$SERVICE_DEST_DIR/"
+    fi
+
+    if [ -d "$TEMPLATE_SOURCE_DIR" ]; then
+        cp -r "$TEMPLATE_SOURCE_DIR/"* "$TEMPLATE_DEST_DIR/"
+    fi
+
+    print_success "Fetched $service templates."
+done
--- a/bin/wild-cluster-services-generate
+++ b/bin/wild-cluster-services-generate
@@ -1,208 +0,0 @@
-#\!/bin/bash
-
-set -e
-set -o pipefail
-
-# Usage function
-usage() {
-    echo "Usage: wild-cluster-services-generate [options]"
-    echo ""
-    echo "Generate cluster services setup files by compiling templates."
-    echo ""
-    echo "Options:"
-    echo "  -h, --help          Show this help message"
-    echo "  --force             Force regeneration even if files exist"
-    echo ""
-    echo "This script will:"
-    echo "  - Copy cluster service templates from WC_ROOT to WC_HOME"
-    echo "  - Compile all templates with current configuration"
-    echo "  - Prepare services for installation"
-    echo ""
-    echo "Requirements:"
-    echo "  - Must be run from a wild-cloud directory"
-    echo "  - Basic cluster configuration must be completed"
-    echo "  - Service configuration (DNS, storage, etc.) must be completed"
-}
-
-# Parse arguments
-FORCE=false
-while [[ $# -gt 0 ]]; do
-    case $1 in
-        -h|--help)
-            usage
-            exit 0
-            ;;
-        --force)
-            FORCE=true
-            shift
-            ;;
-        -*)
-            echo "Unknown option $1"
-            usage
-            exit 1
-            ;;
-        *)
-            echo "Unexpected argument: $1"
-            usage
-            exit 1
-            ;;
-    esac
-done
-
-# Initialize Wild Cloud environment
-if [ -z "${WC_ROOT}" ]; then
-    print "WC_ROOT is not set."
-    exit 1
-else
-    source "${WC_ROOT}/scripts/common.sh"
-    init_wild_env
-fi
-
-# =============================================================================
-# CLUSTER SERVICES SETUP GENERATION
-# =============================================================================
-
-print_header "Cluster Services Setup Generation"
-
-SOURCE_DIR="${WC_ROOT}/setup/cluster-services"
-DEST_DIR="${WC_HOME}/setup/cluster-services"
-
-# Check if source directory exists
-if [ ! -d "$SOURCE_DIR" ]; then
-    print_error "Cluster setup source directory not found: $SOURCE_DIR"
-    print_info "Make sure the wild-cloud repository is properly set up"
-    exit 1
-fi
-
-# Check if destination already exists
-if [ -d "$DEST_DIR" ] && [ "$FORCE" = false ]; then
-    print_warning "Cluster setup directory already exists: $DEST_DIR"
-    read -p "Overwrite existing files? (y/N): " -n 1 -r
-    echo
-    if [[ ! $REPLY =~ ^[Yy]$ ]]; then
-        print_info "Skipping cluster services generation"
-        exit 0
-    fi
-    print_info "Regenerating cluster setup files..."
-    rm -rf "$DEST_DIR"
-elif [ "$FORCE" = true ] && [ -d "$DEST_DIR" ]; then
-    print_info "Force regeneration enabled, removing existing files..."
-    rm -rf "$DEST_DIR"
-fi
-
-# Copy and compile cluster setup files
-print_info "Copying and compiling cluster setup files from repository..."
-mkdir -p "${WC_HOME}/setup"
-
-# Copy README if it doesn't exist
-if [ ! -f "${WC_HOME}/setup/README.md" ]; then
-    cp "${WC_ROOT}/setup/README.md" "${WC_HOME}/setup/README.md"
-fi
-
-# Create destination directory
-mkdir -p "$DEST_DIR"
-
-# First, copy root-level files from setup/cluster/ (install-all.sh, get_helm.sh, etc.)
-print_info "Copying root-level cluster setup files..."
-for item in "$SOURCE_DIR"/*; do
-    if [ -f "$item" ]; then
-        item_name=$(basename "$item")
-        print_info "  Copying: ${item_name}"
-        cp "$item" "$DEST_DIR/$item_name"
-    fi
-done
-
-# Then, process each service directory in the source
-print_info "Processing service directories..."
-for service_dir in "$SOURCE_DIR"/*; do
-    if [ ! -d "$service_dir" ]; then
-        continue
-    fi
-    
-    service_name=$(basename "$service_dir")
-    dest_service_dir="$DEST_DIR/$service_name"
-    
-    print_info "Processing service: $service_name"
-    
-    # Create destination service directory
-    mkdir -p "$dest_service_dir"
-    
-    # Copy all files except kustomize.template directory
-    for item in "$service_dir"/*; do
-        item_name=$(basename "$item")
-        
-        if [ "$item_name" = "kustomize.template" ]; then
-            # Compile kustomize.template to kustomize directory
-            if [ -d "$item" ]; then
-                print_info "  Compiling kustomize templates for $service_name"
-                wild-compile-template-dir --clean "$item" "$dest_service_dir/kustomize"
-            fi
-        else
-            # Copy other files as-is (install.sh, README.md, etc.)
-            if [ -f "$item" ]; then
-                # Compile individual template files
-                if grep -q "{{" "$item" 2>/dev/null; then
-                    print_info "  Compiling: ${item_name}"
-                    wild-compile-template < "$item" > "$dest_service_dir/$item_name"
-                else
-                    cp "$item" "$dest_service_dir/$item_name"
-                fi
-            elif [ -d "$item" ]; then
-                cp -r "$item" "$dest_service_dir/"
-            fi
-        fi
-    done
-done
-
-print_success "Cluster setup files copied and compiled"
-
-# Verify required configuration
-print_info "Verifying service configuration..."
-
-MISSING_CONFIG=()
-
-# Check essential configuration values
-if [ -z "$(wild-config cluster.name 2>/dev/null)" ]; then
-    MISSING_CONFIG+=("cluster.name")
-fi
-
-if [ -z "$(wild-config cloud.domain 2>/dev/null)" ]; then
-    MISSING_CONFIG+=("cloud.domain")
-fi
-
-if [ -z "$(wild-config cluster.ipAddressPool 2>/dev/null)" ]; then
-    MISSING_CONFIG+=("cluster.ipAddressPool")
-fi
-
-if [ -z "$(wild-config operator.email 2>/dev/null)" ]; then
-    MISSING_CONFIG+=("operator.email")
-fi
-
-if [ ${#MISSING_CONFIG[@]} -gt 0 ]; then
-    print_warning "Some required configuration values are missing:"
-    for config in "${MISSING_CONFIG[@]}"; do
-        print_warning "  - $config"
-    done
-    print_info "Run 'wild-setup' to complete the configuration"
-fi
-
-print_success "Cluster services setup generation completed!"
-echo ""
-print_info "Generated setup directory: $DEST_DIR"
-echo ""
-print_info "Available services:"
-for service_dir in "$DEST_DIR"/*; do
-    if [ -d "$service_dir" ] && [ -f "$service_dir/install.sh" ]; then
-        service_name=$(basename "$service_dir")
-        print_info "  - $service_name"
-    fi
-done
-
-echo ""
-print_info "Next steps:"
-echo "  1. Review the generated configuration files in $DEST_DIR"
-echo "  2. Make sure your cluster is running and kubectl is configured"
-echo "  3. Install services with: wild-cluster-services-up"
-echo "  4. Or install individual services by running their install.sh scripts"
-
-print_success "Ready for cluster services installation!"
--- a/bin/wild-cluster-services-up
+++ b/bin/wild-cluster-services-up
@@ -14,22 +14,15 @@ usage() {
    echo ""
    echo "Options:"
    echo "  -h, --help          Show this help message"
-    echo "  --list              List available services"
    echo "  --dry-run           Show what would be installed without running"
    echo ""
    echo "Examples:"
    echo "  wild-cluster-services-up                    # Install all services"
    echo "  wild-cluster-services-up metallb traefik    # Install specific services"
-    echo "  wild-cluster-services-up --list             # List available services"
    echo ""
-    echo "Available services (when setup files exist):"
+    echo "Available services:"
    echo "  metallb, longhorn, traefik, coredns, cert-manager,"
    echo "  externaldns, kubernetes-dashboard, nfs, docker-registry"
-    echo ""
-    echo "Requirements:"
-    echo "  - Must be run from a wild-cloud directory"
-    echo "  - Cluster services must be generated first (wild-cluster-services-generate)"
-    echo "  - Kubernetes cluster must be running and kubectl configured"
 }

 # Parse arguments
@@ -43,10 +36,6 @@ while [[ $# -gt 0 ]]; do
            usage
            exit 0
            ;;
-        --list)
-            LIST_SERVICES=true
-            shift
-            ;;
        --dry-run)
            DRY_RUN=true
            shift
@@ -81,43 +70,11 @@ if [ ! -d "$CLUSTER_SETUP_DIR" ]; then
    exit 1
 fi

-# Function to get available services
-get_available_services() {
-    local services=()
-    for service_dir in "$CLUSTER_SETUP_DIR"/*; do
-        if [ -d "$service_dir" ] && [ -f "$service_dir/install.sh" ]; then
-            services+=($(basename "$service_dir"))
-        fi
-    done
-    echo "${services[@]}"
-}
-
-# List services if requested
-if [ "$LIST_SERVICES" = true ]; then
-    print_header "Available Cluster Services"
-    AVAILABLE_SERVICES=($(get_available_services))
-    
-    if [ ${#AVAILABLE_SERVICES[@]} -eq 0 ]; then
-        print_warning "No services found in $CLUSTER_SETUP_DIR"
-        print_info "Run 'wild-cluster-services-generate' first"
-    else
-        print_info "Services available for installation:"
-        for service in "${AVAILABLE_SERVICES[@]}"; do
-            if [ -f "$CLUSTER_SETUP_DIR/$service/install.sh" ]; then
-                print_success "  ✓ $service"
-            else
-                print_warning "  ✗ $service (install.sh missing)"
-            fi
-        done
-    fi
-    exit 0
-fi
-
 # =============================================================================
 # CLUSTER SERVICES INSTALLATION
 # =============================================================================

-print_header "Cluster Services Installation"
+print_header "Cluster services installation"

 # Check kubectl connectivity
 if [ "$DRY_RUN" = false ]; then
@@ -151,28 +108,11 @@ else
    print_info "Installing all available services"
 fi

-# Filter to only include services that actually exist
-EXISTING_SERVICES=()
-for service in "${SERVICES_TO_INSTALL[@]}"; do
-    if [ -d "$CLUSTER_SETUP_DIR/$service" ] && [ -f "$CLUSTER_SETUP_DIR/$service/install.sh" ]; then
-        EXISTING_SERVICES+=("$service")
-    elif [ ${#SPECIFIC_SERVICES[@]} -gt 0 ]; then
-        # Only warn if user specifically requested this service
-        print_warning "Service '$service' not found or missing install.sh"
-    fi
-done
-
-if [ ${#EXISTING_SERVICES[@]} -eq 0 ]; then
-    print_error "No installable services found"
-    print_info "Run 'wild-cluster-services-generate' first to generate setup files"
-    exit 1
-fi
-
-print_info "Services to install: ${EXISTING_SERVICES[*]}"
+print_info "Services to install: ${SERVICES_TO_INSTALL[*]}"

 if [ "$DRY_RUN" = true ]; then
    print_info "DRY RUN - would install the following services:"
-    for service in "${EXISTING_SERVICES[@]}"; do
+    for service in "${SERVICES_TO_INSTALL[@]}"; do
        print_info "  - $service: $CLUSTER_SETUP_DIR/$service/install.sh"
    done
    exit 0
@@ -183,7 +123,9 @@ cd "$CLUSTER_SETUP_DIR"
 INSTALLED_COUNT=0
 FAILED_COUNT=0

-for service in "${EXISTING_SERVICES[@]}"; do
+SOURCE_DIR="${WC_ROOT}/setup/cluster-services"
+
+for service in "${SERVICES_TO_INSTALL[@]}"; do
    echo ""
    print_header "Installing $service"   

@@ -206,7 +148,7 @@ cd - >/dev/null

 # Summary
 echo ""
-print_header "Installation Summary"
+print_header "Installation summary"
 print_success "Successfully installed: $INSTALLED_COUNT services"
 if [ $FAILED_COUNT -gt 0 ]; then
    print_warning "Failed to install: $FAILED_COUNT services"
@@ -219,13 +161,13 @@ if [ $INSTALLED_COUNT -gt 0 ]; then
    echo "  2. Check service status with: kubectl get services --all-namespaces"
    
    # Service-specific next steps
-    if [[ " ${EXISTING_SERVICES[*]} " =~ " kubernetes-dashboard " ]]; then
+    if [[ " ${SERVICES_TO_INSTALL[*]} " =~ " kubernetes-dashboard " ]]; then
        INTERNAL_DOMAIN=$(wild-config cloud.internalDomain 2>/dev/null || echo "your-internal-domain")
        echo "  3. Access dashboard at: https://dashboard.${INTERNAL_DOMAIN}"
        echo "  4. Get dashboard token with: ${WC_ROOT}/bin/dashboard-token"
    fi
    
-    if [[ " ${EXISTING_SERVICES[*]} " =~ " cert-manager " ]]; then
+    if [[ " ${SERVICES_TO_INSTALL[*]} " =~ " cert-manager " ]]; then
        echo "  3. Check cert-manager: kubectl get clusterissuers"
    fi
 fi
--- a/bin/wild-config-set
+++ b/bin/wild-config-set
@@ -73,11 +73,9 @@ CONFIG_FILE="${WC_HOME}/config.yaml"

 # Create config file if it doesn't exist
 if [ ! -f "${CONFIG_FILE}" ]; then
-    echo "Creating new config file at ${CONFIG_FILE}"
+    print_info "Creating new config file at ${CONFIG_FILE}"
    echo "{}" > "${CONFIG_FILE}"
 fi

 # Use yq to set the value in the YAML file
 yq eval ".${KEY_PATH} = \"${VALUE}\"" -i "${CONFIG_FILE}"
-
-echo "Set ${KEY_PATH} = ${VALUE}"
--- a/setup/cluster-services/validate-setup.sh
+++ b/setup/cluster-services/validate-setup.sh
--- a/bin/wild-setup-scaffold
+++ b/bin/wild-setup-scaffold
@@ -48,6 +48,33 @@ while [[ $# -gt 0 ]]; do
    esac
 done

+# Check if directory has any files (including hidden files, excluding . and .. and .git)
+if [ "${UPDATE}" = false ]; then
+    if [ -n "$(find . -maxdepth 1 -name ".*" -o -name "*" | grep -v "^\.$" | grep -v "^\.\.$" | grep -v "^\./\.git$" | head -1)" ]; then
+        NC='\033[0m' # No Color
+        YELLOW='\033[1;33m' # Yellow
+        echo -e "${YELLOW}WARNING:${NC} Directory is not empty."
+        read -p "Do you want to overwrite existing files? (y/N): " -n 1 -r
+        echo
+        if [[ $REPLY =~ ^[Yy]$ ]]; then
+            confirm="yes"
+        else
+            confirm="no"
+        fi
+        if [ "$confirm" != "yes" ]; then
+            echo "Aborting setup. Please run this script in an empty directory."
+            exit 1
+        fi
+    fi
+fi
+
+# Initialize .wildcloud directory if it doesn't exist.
+if [ ! -d ".wildcloud" ]; then
+    mkdir -p ".wildcloud"
+    UPDATE=true
+    echo "Created '.wildcloud' directory."
+fi
+
 # Initialize Wild Cloud environment
 if [ -z "${WC_ROOT}" ]; then
    echo "WC_ROOT is not set."
@@ -56,12 +83,10 @@ else
    source "${WC_ROOT}/scripts/common.sh"
 fi

-
-# Initialize .wildcloud directory if it doesn't exist.
-if [ ! -d ".wildcloud" ]; then
-    mkdir -p ".wildcloud"
-    UPDATE=true
-    echo "Created '.wildcloud' directory."
+# Initialize config.yaml if it doesn't exist.
+if [ ! -f "config.yaml" ]; then
+    touch "config.yaml"
+    echo "Created 'config.yaml' file."
 fi

 # =============================================================================
@@ -84,46 +109,21 @@ if [ -z "$current_cluster_name" ] || [ "$current_cluster_name" = "null" ]; then
    print_info "Set cluster name to: ${cluster_name}"
 fi

-# Check if current directory is empty for new cloud
-if [ "${UPDATE}" = false ]; then
-    # Check if directory has any files (including hidden files, excluding . and .. and .git)
-    if [ -n "$(find . -maxdepth 1 -name ".*" -o -name "*" | grep -v "^\.$" | grep -v "^\.\.$" | grep -v "^\./\.git$" | grep -v "^\./\.wildcloud$"| head -1)" ]; then
-        echo "Warning: Current directory is not empty."
-        read -p "Do you want to overwrite existing files? (y/N): " -n 1 -r
-        echo
-        if [[ $REPLY =~ ^[Yy]$ ]]; then
-            confirm="yes"
-        else
-            confirm="no"
-        fi
-        if [ "$confirm" != "yes" ]; then
-            echo "Aborting setup. Please run this script in an empty directory."
-            exit 1
-        fi
-    fi
-fi
+
+# =============================================================================
+# COPY SCAFFOLD
+# =============================================================================

 # Copy cloud files to current directory only if they do not exist.
 # Ignore files that already exist.
 SRC_DIR="${WC_ROOT}/setup/home-scaffold"
 rsync -av --ignore-existing --exclude=".git" "${SRC_DIR}/" ./ > /dev/null

-print_success "Ready for cluster setup!"

 # =============================================================================
-# COMPLETION
+# COPY DOCS
 # =============================================================================

-print_header "Wild Cloud Scaffold Setup Complete! Welcome to Wild Cloud!"
-
-echo ""
-echo "Next steps:"
-echo "  1. Set up your Kubernetes cluster:"
-echo "     wild-setup-cluster"
-echo ""
-echo "  2. Install cluster services:"
-echo "     wild-setup-services"
-echo ""
-echo "Or run the complete setup:"
-echo "  wild-setup"
+wild-update-docs --force

+print_success "Wild Cloud initialized! Welcome to Wild Cloud!"
--- a/bin/wild-setup
+++ b/bin/wild-setup
@@ -11,14 +11,6 @@ SKIP_SERVICES=false

 while [[ $# -gt 0 ]]; do
    case $1 in
-        --skip-scaffold)
-            SKIP_SCAFFOLD=true
-            shift
-            ;;
-        --skip-docs)
-            SKIP_DOCS=true
-            shift
-            ;;
        --skip-cluster)
            SKIP_CLUSTER=true
            shift
@@ -80,55 +72,12 @@ else
 fi

 print_header "Wild Cloud Setup"
-print_info "Running complete Wild Cloud setup."
-echo ""
-
-# =============================================================================
-# WC_HOME SCAFFOLDING
-# =============================================================================
-
-if [ "${SKIP_SCAFFOLD}" = false ]; then
-    print_header "Cloud Home Setup"
-    print_info "Scaffolding your cloud home..."
-    
-    if wild-setup-scaffold; then
-        print_success "Cloud home setup completed"
-    else
-        print_error "Cloud home setup failed"
-        exit 1
-    fi
-    echo ""
-else
-    print_info "Skipping Home Setup"
-fi
-
-# =============================================================================
-# DOCS
-# =============================================================================
-
-if [ "${SKIP_DOCS}" = false ]; then
-    print_header "Cloud Docs"
-    print_info "Preparing your docs..."
-
-    if wild-setup-docs; then
-        print_success "Cloud docs setup completed"
-    else
-        print_error "Cloud docs setup failed"
-        exit 1
-    fi
-    echo ""
-else
-    print_info "Skipping Docs Setup"
-fi

 # =============================================================================
 # CLUSTER SETUP
 # =============================================================================

 if [ "${SKIP_CLUSTER}" = false ]; then
-    print_header "Cluster Setup"
-    print_info "Running wild-setup-cluster..."
-    
    if wild-setup-cluster; then
        print_success "Cluster setup completed"
    else
@@ -145,9 +94,6 @@ fi
 # =============================================================================

 if [ "${SKIP_SERVICES}" = false ]; then
-    print_header "Services Setup"
-    print_info "Running wild-setup-services..."
-    
    if wild-setup-services; then
        print_success "Services setup completed"
    else
--- a/bin/wild-setup-cluster
+++ b/bin/wild-setup-cluster
@@ -62,40 +62,6 @@ else
 fi

 print_header "Wild Cloud Cluster Setup"
-print_info "Setting up cluster infrastructure"
-echo ""
-
-# Generate initial cluster configuration
-
-if ! wild-cluster-config-generate; then
-    print_error "Failed to generate cluster configuration"
-    exit 1
-fi
-
-# Configure Talos cli with our new cluster context
-
-CLUSTER_NAME=$(wild-config "cluster.name")
-HAS_CONTEXT=$(talosctl config contexts | grep -c "$CLUSTER_NAME" || true)
-if [ "$HAS_CONTEXT" -eq 0 ]; then
-    print_info "No Talos context found for cluster $CLUSTER_NAME, creating..."
-    talosctl config merge ${WC_HOME}/setup/cluster-nodes/generated/talosconfig
-    talosctl config use "$CLUSTER_NAME"
-    print_success "Talos context for $CLUSTER_NAME created and set as current"
-fi
-
-# Talos asset download
-
-if [ "${SKIP_INSTALLER}" = false ]; then
-    print_header "Installer Image Generation"
-    
-    print_info "Running wild-cluster-node-boot-assets-download..."
-    wild-cluster-node-boot-assets-download
-    
-    print_success "Installer image generated"
-    echo ""
-else
-    print_info "Skipping: Installer Image Generation"
-fi

 # =============================================================================
 # Configuration
@@ -103,6 +69,9 @@ fi

 prompt_if_unset_config "operator.email" "Operator email address"

+prompt_if_unset_config "cluster.name" "Cluster name" "wild-cluster"
+CLUSTER_NAME=$(wild-config "cluster.name")
+
 # Configure hostname prefix for unique node names on LAN
 prompt_if_unset_config "cluster.hostnamePrefix" "Hostname prefix (optional, e.g. 'test-' for unique names on LAN)" ""
 HOSTNAME_PREFIX=$(wild-config "cluster.hostnamePrefix")
@@ -123,41 +92,41 @@ prompt_if_unset_config "cluster.ipAddressPool" "MetalLB IP address pool" "${SUBN
 ip_pool=$(wild-config "cluster.ipAddressPool")

 # Load balancer IP (automatically set to first address in the pool if not set)
-current_lb_ip=$(wild-config "cluster.loadBalancerIp")
-if [ -z "$current_lb_ip" ] || [ "$current_lb_ip" = "null" ]; then
-    lb_ip=$(echo "${ip_pool}" | cut -d'-' -f1)
-    wild-config-set "cluster.loadBalancerIp" "${lb_ip}"
-    print_info "Set load balancer IP to: ${lb_ip} (first IP in MetalLB pool)"
-fi
+default_lb_ip=$(echo "${ip_pool}" | cut -d'-' -f1)
+prompt_if_unset_config "cluster.loadBalancerIp" "Load balancer IP" "${default_lb_ip}"

 # Talos version
-prompt_if_unset_config "cluster.nodes.talos.version" "Talos version" "v1.10.4"
+prompt_if_unset_config "cluster.nodes.talos.version" "Talos version" "v1.11.0"
 talos_version=$(wild-config "cluster.nodes.talos.version")

 # Talos schematic ID
-current_schematic_id=$(wild-config "cluster.nodes.talos.schematicId")
-if [ -z "$current_schematic_id" ] || [ "$current_schematic_id" = "null" ]; then
-    echo ""
-    print_info "Get your Talos schematic ID from: https://factory.talos.dev/"
-    print_info "This customizes Talos with the drivers needed for your hardware."
-    
-    # Use current schematic ID from config as default
-    default_schematic_id=$(wild-config "cluster.nodes.talos.schematicId")
-    if [ -n "$default_schematic_id" ] && [ "$default_schematic_id" != "null" ]; then
-        print_info "Using schematic ID from config for Talos $talos_version"
-    else
-        default_schematic_id=""
-    fi
-    
-    schematic_id=$(prompt_with_default "Talos schematic ID" "${default_schematic_id}" "${current_schematic_id}")
-    wild-config-set "cluster.nodes.talos.schematicId" "${schematic_id}"
-fi
+prompt_if_unset_config "cluster.nodes.talos.schematicId" "Talos schematic ID" "56774e0894c8a3a3a9834a2aea65f24163cacf9506abbcbdc3ba135eaca4953f"
+schematic_id=$(wild-config "cluster.nodes.talos.schematicId")

 # External DNS
-cluster_name=$(wild-config "cluster.name")
-prompt_if_unset_config "cluster.externalDns.ownerId" "External DNS owner ID" "external-dns-${cluster_name}"
+prompt_if_unset_config "cluster.externalDns.ownerId" "External DNS owner ID" "external-dns-${CLUSTER_NAME}"

+# =============================================================================
+# TALOS CLUSTER CONFIGURATION
+# =============================================================================

+prompt_if_unset_config "cluster.nodes.control.vip" "Control plane virtual IP" "${SUBNET_PREFIX}.90"
+vip=$(wild-config "cluster.nodes.control.vip")
+
+# Generate initial cluster configuration
+if ! wild-cluster-config-generate; then
+    print_error "Failed to generate cluster configuration"
+    exit 1
+fi
+
+# Configure Talos cli with our new cluster context
+HAS_CONTEXT=$(talosctl config contexts | grep -c "$CLUSTER_NAME" || true)
+if [ "$HAS_CONTEXT" -eq 0 ]; then
+    print_info "No Talos context found for cluster $CLUSTER_NAME, creating..."
+    talosctl config merge ${WC_HOME}/setup/cluster-nodes/generated/talosconfig
+    talosctl config context "$CLUSTER_NAME"
+    print_success "Talos context for $CLUSTER_NAME created and set as current"
+fi

 # =============================================================================
 # Node setup
@@ -167,12 +136,6 @@ if [ "${SKIP_HARDWARE}" = false ]; then
        
    print_header "Control Plane Configuration"

-    print_info "Configure control plane nodes (you need at least 3 for HA):"
-    echo ""
-
-    prompt_if_unset_config "cluster.nodes.control.vip" "Control plane virtual IP" "${SUBNET_PREFIX}.90"
-    vip=$(wild-config "cluster.nodes.control.vip")
-
    # Automatically configure the first three IPs after VIP for control plane nodes
    vip_last_octet=$(echo "$vip" | cut -d. -f4)
    vip_prefix=$(echo "$vip" | cut -d. -f1-3)
@@ -184,7 +147,6 @@ if [ "${SKIP_HARDWARE}" = false ]; then
    for i in 1 2 3; do
        NODE_NAME="${HOSTNAME_PREFIX}control-${i}"
        TARGET_IP="${vip_prefix}.$(( vip_last_octet + i ))"
-        echo ""
        print_info "Registering control plane node: $NODE_NAME (IP: $TARGET_IP)"

        # Initialize the node in cluster.nodes.active if not already present
@@ -288,14 +250,8 @@ if [ "${SKIP_HARDWARE}" = false ]; then
            wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".disk" "$SELECTED_DISK"
            
            # Copy current Talos version and schematic ID to this node
-            current_talos_version=$(wild-config "cluster.nodes.talos.version")
-            current_schematic_id=$(wild-config "cluster.nodes.talos.schematicId")
-            if [ -n "$current_talos_version" ] && [ "$current_talos_version" != "null" ]; then
-                wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".version" "$current_talos_version"
-            fi
-            if [ -n "$current_schematic_id" ] && [ "$current_schematic_id" != "null" ]; then
-                wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".schematicId" "$current_schematic_id"
-            fi
+            wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".version" "$talos_version"
+            wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".schematicId" "$schematic_id"
  
            echo ""
            read -p "Bring node $NODE_NAME ($TARGET_IP) up now? (y/N): " -r apply_config
@@ -315,7 +271,7 @@ if [ "${SKIP_HARDWARE}" = false ]; then
                    read -p "The cluster should be bootstrapped after the first control node is ready. Is it ready?: " -r is_ready
                    if [[ $is_ready =~ ^[Yy]$ ]]; then
                        print_info "Bootstrapping control plane node $TARGET_IP..."
-                        talos config endpoint "$TARGET_IP"
+                        talosctl config endpoint "$TARGET_IP"
                        
                        # Attempt to bootstrap the cluster
                        if talosctl bootstrap --nodes "$TARGET_IP" 2>&1 | tee /tmp/bootstrap_output.log; then
@@ -425,14 +381,8 @@ if [ "${SKIP_HARDWARE}" = false ]; then
                wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".disk" "$SELECTED_DISK"
                
                # Copy current Talos version and schematic ID to this node
-                current_talos_version=$(wild-config "cluster.nodes.talos.version")
-                current_schematic_id=$(wild-config "cluster.nodes.talos.schematicId")
-                if [ -n "$current_talos_version" ] && [ "$current_talos_version" != "null" ]; then
-                    wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".version" "$current_talos_version"
-                fi
-                if [ -n "$current_schematic_id" ] && [ "$current_schematic_id" != "null" ]; then
-                    wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".schematicId" "$current_schematic_id"
-                fi
+                wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".version" "$talos_version"
+                wild-config-set "cluster.nodes.active.\"${NODE_NAME}\".schematicId" "$schematic_id"
                
                print_success "Worker node $NODE_NAME registered successfully:"
                print_info "  - Name: $NODE_NAME"
--- a/bin/wild-setup-services
+++ b/bin/wild-setup-services
@@ -65,9 +65,7 @@ if [ -z "$(wild-config "cluster.name")" ]; then
    exit 1
 fi

-print_header "Wild Cloud Services Setup"
-print_info "Installing Kubernetes cluster services"
-echo ""
+print_header "Wild Cloud services setup"

 if ! command -v kubectl >/dev/null 2>&1; then
    print_error "kubectl is not installed or not in PATH"
@@ -82,8 +80,8 @@ if ! kubectl cluster-info >/dev/null 2>&1; then
 fi

 # Generate cluster services setup files
-
-wild-cluster-services-generate --force
+wild-cluster-services-fetch
+wild-cluster-services-generate

 # Apply cluster services to cluster

--- a/bin/wild-update-docs
+++ b/bin/wild-update-docs
@@ -4,28 +4,28 @@ set -e
 set -o pipefail

 # Parse arguments
-UPDATE=false
+FORCE=false

 while [[ $# -gt 0 ]]; do
    case $1 in
-        --update)
-            UPDATE=true
+        --force)
+            FORCE=true
            shift
            ;;
        -h|--help)
-            echo "Usage: $0 [--update]"
+            echo "Usage: $0 [--force]"
            echo ""
            echo "Copy Wild Cloud documentation to the current cloud directory."
            echo ""
            echo "Options:"
-            echo "  --update            Update existing docs (overwrite)"
+            echo "  --force            Force overwrite of existing docs"
            echo "  -h, --help          Show this help message"
            echo ""
            exit 0
            ;;
        -*)
            echo "Unknown option $1"
-            echo "Usage: $0 [--update]"
+            echo "Usage: $0 [--force]"
            exit 1
            ;;
        *)
@@ -48,21 +48,21 @@ fi
 DOCS_DEST="${WC_HOME}/docs"

 # Check if docs already exist
-if [ -d "${DOCS_DEST}" ] && [ "${UPDATE}" = false ]; then
-    echo "Documentation already exists at ${DOCS_DEST}"
+if [ -d "${DOCS_DEST}" ] && [ "${FORCE}" = false ]; then
+    print_warning "Documentation already exists at ${DOCS_DEST}"
    read -p "Do you want to update documentation files? (y/N): " -n 1 -r
    echo
    if [[ $REPLY =~ ^[Yy]$ ]]; then
-        UPDATE=true
+        FORCE=true
    else
-        echo "Skipping documentation update."
+        print_info "Skipping documentation update."
        exit 0
    fi
 fi

 # Copy docs directory from root to WC_HOME
 if [ -d "${WC_ROOT}/docs" ]; then
-    if [ "${UPDATE}" = true ] && [ -d "${DOCS_DEST}" ]; then
+    if [ "${FORCE}" = true ] && [ -d "${DOCS_DEST}" ]; then
        rm -rf "${DOCS_DEST}"
    fi
    cp -r "${WC_ROOT}/docs" "${DOCS_DEST}"
--- a/docs/MAINTENANCE.md
+++ b/docs/MAINTENANCE.md
@@ -4,7 +4,8 @@ Keep your wild cloud running smoothly.

 - [Security Best Practices](./guides/security.md)
 - [Monitoring](./guides/monitoring.md)
- [Backup and Restore](./guides/backup-and-restore.md)
+- [Making backups](./guides/making-backups.md)
+- [Restoring backups](./guides/restoring-backups.md)

 ## Upgrade

--- a/docs/guides/backup-and-restore.md
+++ b/docs/guides/backup-and-restore.md
@@ -1,3 +0,0 @@
-# Backup and Restore
-
-TBD
--- a/docs/guides/making-backups.md
+++ b/docs/guides/making-backups.md
@@ -0,0 +1,265 @@
+# Making Backups
+
+This guide covers how to create backups of your wild-cloud infrastructure using the integrated backup system.
+
+## Overview
+
+The wild-cloud backup system creates encrypted, deduplicated snapshots using restic. It backs up three main components:
+
+- **Applications**: Database dumps and persistent volume data
+- **Cluster**: Kubernetes resources and etcd state
+- **Configuration**: Wild-cloud repository and settings
+
+## Prerequisites
+
+Before making backups, ensure you have:
+
+1. **Environment configured**: Run `source env.sh` to load backup configuration
+2. **Restic repository**: Backup repository configured in `config.yaml`
+3. **Backup password**: Set in wild-cloud secrets
+4. **Staging directory**: Configured path for temporary backup files
+
+## Backup Components
+
+### Applications (`wild-app-backup`)
+
+Backs up individual applications including:
+- **Database dumps**: PostgreSQL/MySQL databases in compressed custom format
+- **PVC data**: Application files streamed directly for restic deduplication
+- **Auto-discovery**: Finds databases and PVCs based on app manifest.yaml
+
+### Cluster Resources (`wild-backup --cluster-only`)
+
+Backs up cluster-wide resources:
+- **Kubernetes resources**: All pods, services, deployments, secrets, configmaps
+- **Storage definitions**: PersistentVolumes, PVCs, StorageClasses  
+- **etcd snapshot**: Complete cluster state for disaster recovery
+
+### Configuration (`wild-backup --home-only`)
+
+Backs up wild-cloud configuration:
+- **Repository contents**: All app definitions, manifests, configurations
+- **Settings**: Wild-cloud configuration files and customizations
+
+## Making Backups
+
+### Full System Backup (Recommended)
+
+Create a complete backup of everything:
+
+```bash
+# Backup all components (apps + cluster + config)
+wild-backup
+```
+
+This is equivalent to:
+```bash
+wild-backup --home --apps --cluster
+```
+
+### Selective Backups
+
+#### Applications Only
+```bash
+# All applications
+wild-backup --apps-only
+
+# Single application  
+wild-app-backup discourse
+
+# Multiple applications
+wild-app-backup discourse gitea immich
+```
+
+#### Cluster Only
+```bash
+# Kubernetes resources + etcd
+wild-backup --cluster-only
+```
+
+#### Configuration Only
+```bash  
+# Wild-cloud repository
+wild-backup --home-only
+```
+
+### Excluding Components
+
+Skip specific components:
+
+```bash
+# Skip config, backup apps + cluster
+wild-backup --no-home
+
+# Skip applications, backup config + cluster  
+wild-backup --no-apps
+
+# Skip cluster resources, backup config + apps
+wild-backup --no-cluster
+```
+
+## Backup Process Details
+
+### Application Backup Process
+
+1. **Discovery**: Parses `manifest.yaml` to find database and PVC dependencies
+2. **Database backup**: Creates compressed custom-format dumps
+3. **PVC backup**: Streams files directly to staging for restic deduplication  
+4. **Staging**: Organizes files in clean directory structure
+5. **Upload**: Creates individual restic snapshots per application
+
+### Cluster Backup Process
+
+1. **Resource export**: Exports all Kubernetes resources to YAML
+2. **etcd snapshot**: Creates point-in-time etcd backup via talosctl
+3. **Upload**: Creates single restic snapshot for cluster state
+
+### Restic Snapshots
+
+Each backup creates tagged restic snapshots:
+
+```bash
+# View all snapshots
+restic snapshots
+
+# Filter by component
+restic snapshots --tag discourse    # Specific app
+restic snapshots --tag cluster      # Cluster resources
+restic snapshots --tag wc-home      # Wild-cloud config
+```
+
+## Where Backup Files Are Staged
+
+Before uploading to your restic repository, backup files are organized in a staging directory. This temporary area lets you see exactly what's being backed up and helps with deduplication.
+
+Here's what the staging area looks like:
+
+```
+backup-staging/
+├── apps/
+│   ├── discourse/
+│   │   ├── database_20250816T120000Z.dump
+│   │   ├── globals_20250816T120000Z.sql  
+│   │   └── discourse/
+│   │       └── data/         # All the actual files
+│   ├── gitea/
+│   │   ├── database_20250816T120000Z.dump
+│   │   └── gitea-data/
+│   │       └── data/         # Git repositories, etc.
+│   └── immich/
+│       ├── database_20250816T120000Z.dump
+│       └── immich-data/
+│           └── upload/       # Photos and videos
+└── cluster/
+    ├── all-resources.yaml    # All running services
+    ├── secrets.yaml          # Passwords and certificates
+    ├── configmaps.yaml       # Configuration data
+    └── etcd-snapshot.db      # Complete cluster state
+```
+
+This staging approach means you can examine backup contents before they're uploaded, and restic can efficiently deduplicate files that haven't changed.
+
+## Advanced Usage
+
+### Custom Backup Scripts
+
+Applications can provide custom backup logic:
+
+```bash
+# Create apps/myapp/backup.sh for custom behavior
+chmod +x apps/myapp/backup.sh
+
+# wild-app-backup will use custom script if present
+wild-app-backup myapp
+```
+
+### Monitoring Backup Status
+
+```bash
+# Check recent snapshots
+restic snapshots | head -20
+
+# Check specific app backups
+restic snapshots --tag discourse
+
+# Verify backup integrity
+restic check
+```
+
+### Backup Automation
+
+Set up automated backups with cron:
+
+```bash
+# Daily full backup at 2 AM
+0 2 * * * cd /data/repos/payne-cloud && source env.sh && wild-backup
+
+# Hourly app backups during business hours  
+0 9-17 * * * cd /data/repos/payne-cloud && source env.sh && wild-backup --apps-only
+```
+
+## Performance Considerations
+
+### Large PVCs (like Immich photos)
+
+The streaming backup approach provides:
+- **First backup**: Full transfer time (all files processed)
+- **Subsequent backups**: Only changed files processed (dramatically faster)
+- **Storage efficiency**: Restic deduplication reduces storage usage
+
+### Network Usage
+
+- **Database dumps**: Compressed at source, efficient transfer
+- **PVC data**: Uncompressed transfer, but restic handles deduplication
+- **etcd snapshots**: Small files, minimal impact
+
+## Troubleshooting
+
+### Common Issues
+
+**"No databases or PVCs found"**
+- App has no `manifest.yaml` with database dependencies
+- No PVCs with matching labels in app namespace
+- Create custom `backup.sh` script for special cases
+
+**"kubectl not found"** 
+- Ensure kubectl is installed and configured
+- Check cluster connectivity with `kubectl get nodes`
+
+**"Staging directory not set"**
+- Configure `cloud.backup.staging` in `config.yaml`
+- Ensure directory exists and is writable
+
+**"Could not create etcd backup"**
+- Ensure `talosctl` is installed for Talos clusters
+- Check control plane node connectivity
+- Verify etcd pods are accessible in kube-system namespace
+
+### Backup Verification
+
+Always verify backups periodically:
+
+```bash
+# Check restic repository integrity
+restic check
+
+# List recent snapshots
+restic snapshots --compact
+
+# Test restore to different directory
+restic restore latest --target /tmp/restore-test
+```
+
+## Security Notes
+
+- **Encryption**: All backups are encrypted with your backup password
+- **Secrets**: Kubernetes secrets are included in cluster backups
+- **Access control**: Secure your backup repository and passwords
+- **Network**: Consider bandwidth usage for large initial backups
+
+## Next Steps
+
+- [Restoring Backups](restoring-backups.md) - Learn how to restore from backups
+- Configure automated backup schedules
+- Set up backup monitoring and alerting
+- Test disaster recovery procedures
--- a/docs/guides/restoring-backups.md
+++ b/docs/guides/restoring-backups.md
@@ -0,0 +1,294 @@
+# Restoring Backups
+
+This guide will walk you through restoring your applications and cluster from wild-cloud backups. Hopefully you'll never need this, but when you do, it's critical that the process works smoothly.
+
+## Understanding Restore Types
+
+Your wild-cloud backup system can restore different types of data depending on what you need to recover:
+
+**Application restores** bring back individual applications by restoring their database contents and file storage. This is what you'll use most often - maybe you accidentally deleted something in Discourse, or Gitea got corrupted, or you want to roll back Immich to before a bad update.
+
+**Cluster restores** are for disaster recovery scenarios where you need to rebuild your entire Kubernetes cluster from scratch. This includes restoring all the cluster's configuration and even its internal state.
+
+**Configuration restores** bring back your wild-cloud repository and settings, which contain all the "recipes" for how your infrastructure should be set up.
+
+## Before You Start Restoring
+
+Make sure you have everything needed to perform restores. You need to be in your wild-cloud directory with the environment loaded (`source env.sh`). Your backup repository and password should be configured and working - you can test this by running `restic snapshots` to see your available backups.
+
+Most importantly, make sure you have kubectl access to your cluster, since restores involve creating temporary pods and manipulating storage.
+
+## Restoring Applications
+
+### Basic Application Restore
+
+The most common restore scenario is bringing back a single application. To restore the latest backup of an app:
+
+```bash
+wild-app-restore discourse
+```
+
+This restores both the database and all file storage for the discourse app. The restore system automatically figures out what the app needs based on its manifest file and what was backed up.
+
+If you want to restore from a specific backup instead of the latest:
+
+```bash
+wild-app-restore discourse abc123
+```
+
+Where `abc123` is the snapshot ID from `restic snapshots --tag discourse`.
+
+### Partial Restores
+
+Sometimes you only need to restore part of an application. Maybe the database is fine but the files got corrupted, or vice versa.
+
+To restore only the database:
+```bash
+wild-app-restore discourse --db-only
+```
+
+To restore only the file storage:
+```bash
+wild-app-restore discourse --pvc-only
+```
+
+To restore without database roles and permissions (if they're causing conflicts):
+```bash
+wild-app-restore discourse --skip-globals
+```
+
+### Finding Available Backups
+
+To see what backups are available for an app:
+```bash
+wild-app-restore discourse --list
+```
+
+This shows recent snapshots with their IDs, timestamps, and what was included.
+
+## How Application Restores Work
+
+Understanding what happens during a restore can help when things don't go as expected.
+
+### Database Restoration
+
+When restoring a database, the system first downloads the backup files from your restic repository. It then prepares the database by creating any needed roles, disconnecting existing users, and dropping/recreating the database to ensure a clean restore.
+
+For PostgreSQL databases, it uses `pg_restore` with parallel processing to speed up large database imports. For MySQL, it uses standard mysql import commands. The system also handles database ownership and permissions automatically.
+
+### File Storage Restoration
+
+File storage (PVC) restoration is more complex because it involves safely replacing files that might be actively used by running applications.
+
+First, the system creates a safety snapshot using Longhorn. This means if something goes wrong during the restore, you can get back to where you started. Then it scales your application down to zero replicas so no pods are using the storage.
+
+Next, it creates a temporary utility pod with the PVC mounted and copies all the backup files into place, preserving file permissions and structure. Once the data is restored and verified, it removes the utility pod and scales your application back up.
+
+If everything worked correctly, the safety snapshot is automatically deleted. If something went wrong, the safety snapshot is preserved so you can recover manually.
+
+## Cluster Disaster Recovery
+
+Cluster restoration is much less common but critical when you need to rebuild your entire infrastructure.
+
+### Restoring Kubernetes Resources
+
+To restore all cluster resources from a backup:
+
+```bash
+# Download cluster backup
+restic restore --tag cluster latest --target ./restore/
+
+# Apply all resources
+kubectl apply -f restore/cluster/all-resources.yaml
+```
+
+You can also restore specific types of resources:
+```bash
+kubectl apply -f restore/cluster/secrets.yaml
+kubectl apply -f restore/cluster/configmaps.yaml
+```
+
+### Restoring etcd State
+
+**Warning: This is extremely dangerous and will affect your entire cluster.**
+
+etcd restoration should only be done when rebuilding a cluster from scratch. For Talos clusters:
+
+```bash
+talosctl --nodes <control-plane-ip> etcd restore --from ./restore/cluster/etcd-snapshot.db
+```
+
+This command stops etcd, replaces its data with the backup, and restarts the cluster. Expect significant downtime while the cluster rebuilds itself.
+
+## Common Disaster Recovery Scenarios
+
+### Complete Application Loss
+
+When an entire application is gone (namespace deleted, pods corrupted, etc.):
+
+```bash
+# Make sure the namespace exists
+kubectl create namespace discourse --dry-run=client -o yaml | kubectl apply -f -
+
+# Apply the application manifests if needed
+kubectl apply -f apps/discourse/
+
+# Restore the application data
+wild-app-restore discourse
+```
+
+### Complete Cluster Rebuild
+
+When rebuilding a cluster from scratch:
+
+First, build your new cluster infrastructure and install wild-cloud components. Then configure backup access so you can reach your backup repository.
+
+Restore cluster state:
+```bash
+restic restore --tag cluster latest --target ./restore/
+# Apply etcd snapshot using appropriate method for your cluster type
+```
+
+Finally, restore all applications:
+```bash
+# See what applications are backed up
+wild-app-restore --list
+
+# Restore each application individually
+wild-app-restore discourse
+wild-app-restore gitea
+wild-app-restore immich
+```
+
+### Rolling Back After Bad Changes
+
+Sometimes you need to undo recent changes to an application:
+
+```bash
+# See available snapshots
+wild-app-restore discourse --list
+
+# Restore from before the problematic changes
+wild-app-restore discourse abc123
+```
+
+## Cross-Cluster Migration
+
+You can use backups to move applications between clusters:
+
+On the source cluster, create a fresh backup:
+```bash
+wild-app-backup discourse
+```
+
+On the target cluster, deploy the application manifests:
+```bash
+kubectl apply -f apps/discourse/
+```
+
+Then restore the data:
+```bash
+wild-app-restore discourse
+```
+
+## Verifying Successful Restores
+
+After any restore, verify that everything is working correctly.
+
+For databases, check that you can connect and see expected data:
+```bash
+kubectl exec -n postgres deploy/postgres-deployment -- \
+  psql -U postgres -d discourse -c "SELECT count(*) FROM posts;"
+```
+
+For file storage, check that files exist and applications can start:
+```bash
+kubectl get pods -n discourse
+kubectl logs -n discourse deployment/discourse
+```
+
+For web applications, test that you can access them:
+```bash
+curl -f https://discourse.example.com/latest.json
+```
+
+## When Things Go Wrong
+
+### No Snapshots Found
+
+If the restore system can't find backups for an application, check that snapshots exist:
+```bash
+restic snapshots --tag discourse
+```
+
+Make sure you're using the correct app name and that backups were actually created successfully.
+
+### Database Restore Failures
+
+Database restores can fail if the target database isn't accessible or if there are permission issues. Check that your postgres or mysql pods are running and that you can connect to them manually.
+
+Review the restore error messages carefully - they usually indicate whether the problem is with the backup file, database connectivity, or permissions.
+
+### PVC Restore Failures
+
+If PVC restoration fails, check that you have sufficient disk space and that the PVC isn't being used by other pods. The error messages will usually indicate what went wrong.
+
+Most importantly, remember that safety snapshots are preserved when PVC restores fail. You can see them with:
+```bash
+kubectl get snapshot.longhorn.io -n longhorn-system -l app=wild-app-restore
+```
+
+These snapshots let you recover to the pre-restore state if needed.
+
+### Application Won't Start After Restore
+
+If pods fail to start after restoration, check file permissions and ownership. Sometimes the restoration process doesn't perfectly preserve the exact permissions that the application expects.
+
+You can also try scaling the application to zero and back to one, which sometimes resolves transient issues:
+```bash
+kubectl scale deployment/discourse -n discourse --replicas=0
+kubectl scale deployment/discourse -n discourse --replicas=1
+```
+
+## Manual Recovery
+
+When automated restore fails, you can always fall back to manual extraction and restoration:
+
+```bash
+# Extract backup files to local directory
+restic restore --tag discourse latest --target ./manual-restore/
+
+# Manually copy database dump to postgres pod
+kubectl cp ./manual-restore/discourse/database_*.dump \
+  postgres/postgres-deployment-xxx:/tmp/
+
+# Manually restore database
+kubectl exec -n postgres deploy/postgres-deployment -- \
+  pg_restore -U postgres -d discourse /tmp/database_*.dump
+```
+
+For file restoration, you'd need to create a utility pod and manually copy files into the PVC.
+
+## Best Practices
+
+Test your restore procedures regularly in a non-production environment. It's much better to discover issues with your backup system during a planned test than during an actual emergency.
+
+Always communicate with users before performing restores, especially if they involve downtime. Document any manual steps you had to take so you can improve the automated process.
+
+After any significant restore, monitor your applications more closely than usual for a few days. Sometimes problems don't surface immediately.
+
+## Security and Access Control
+
+Restore operations are powerful and can be destructive. Make sure only trusted administrators can perform restores, and consider requiring approval or coordination before major restoration operations.
+
+Be aware that cluster restores include all secrets, so they potentially expose passwords, API keys, and certificates. Ensure your backup repository is properly secured.
+
+Remember that Longhorn safety snapshots are preserved when things go wrong. These snapshots may contain sensitive data, so clean them up appropriately once you've resolved any issues.
+
+## What's Next
+
+The best way to get comfortable with restore operations is to practice them in a safe environment. Set up a test cluster and practice restoring applications and data.
+
+Consider creating runbooks for your most likely disaster scenarios, including the specific commands and verification steps for your infrastructure.
+
+Read the [Making Backups](making-backups.md) guide to ensure you're creating the backups you'll need for successful recovery.
--- a/env.sh
+++ b/env.sh
@@ -7,27 +7,4 @@ export WC_ROOT="$(cd "$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")" && pwd)"
 # Add bin to path first so wild-config is available
 export PATH="$WC_ROOT/bin:$PATH"

-# Install kubectl
-if ! command -v kubectl &> /dev/null; then
-    echo "Error: kubectl is not installed. Installing."
-    curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
-    curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl.sha256"
-    echo "$(cat kubectl.sha256)  kubectl" | sha256sum --check
-    sudo install -o root -g root -m 0755 kubectl /usr/local/bin/kubectl
-fi
-
-# Install talosctl
-if ! command -v talosctl &> /dev/null; then
-    echo "Error: talosctl is not installed. Installing."
-    curl -sL https://talos.dev/install | sh
-fi
-
-
-# Check if gomplate is installed
-if ! command -v gomplate &> /dev/null; then
-    echo "Error: gomplate is not installed. Please install gomplate first."
-    echo "Visit: https://docs.gomplate.ca/installing/"
-    exit 1
-fi
-
 echo "Wild Cloud root ready."
--- a/scripts/common.sh
+++ b/scripts/common.sh
@@ -84,7 +84,7 @@ prompt_with_default() {
        if [ -n "${default}" ]; then
            printf "%s [default: %s]: " "${prompt}" "${default}" >&2
        else
-            printf "%s [default: empty]: " "${prompt}" >&2
+            printf "%s: " "${prompt}" >&2
        fi
        read -r result
        if [ -z "${result}" ]; then
@@ -109,16 +109,18 @@ prompt_if_unset_config() {
    local prompt="$2"
    local default="$3"

+    # Check if key exists first to avoid error messages
+    if wild-config --check "${config_path}"; then
+        # Key exists, get its value
        local current_value
        current_value=$(wild-config "${config_path}")
-
-    if [ -z "${current_value}" ] || [ "${current_value}" = "null" ]; then
+        print_info "Using existing ${config_path} = ${current_value}"
+    else
+        # Key doesn't exist, prompt for it
        local new_value
        new_value=$(prompt_with_default "${prompt}" "${default}" "")
        wild-config-set "${config_path}" "${new_value}"
        print_info "Set ${config_path} = ${new_value}"
-    else
-        print_info "Using existing ${config_path} = ${current_value}"
    fi
 }

@@ -128,16 +130,16 @@ prompt_if_unset_secret() {
    local prompt="$2"
    local default="$3"

-    local current_value
-    current_value=$(wild-secret "${secret_path}")
-
-    if [ -z "${current_value}" ] || [ "${current_value}" = "null" ]; then
+    # Check if key exists first to avoid error messages
+    if wild-secret --check "${secret_path}"; then
+        # Key exists, we don't show the value for security
+        print_info "Using existing secret ${secret_path}"
+    else
+        # Key doesn't exist, prompt for it
        local new_value
        new_value=$(prompt_with_default "${prompt}" "${default}" "")
        wild-secret-set "${secret_path}" "${new_value}"
        print_info "Set secret ${secret_path}"
-    else
-        print_info "Using existing secret ${secret_path}"
    fi
 }

@@ -168,7 +170,7 @@ init_wild_env() {
    if [ -z "${WC_ROOT}" ]; then
        echo "ERROR: WC_ROOT is not set."
        exit 1
-    else
+    fi

    # Check if WC_ROOT is a valid directory
    if [ ! -d "${WC_ROOT}" ]; then
@@ -187,6 +189,33 @@ init_wild_env() {
        echo "ERROR: This command must be run from within a wildcloud home directory."
        exit 1
    fi
+    
+    # Check kubectl
+    if ! command -v kubectl &> /dev/null; then
+        echo "Error: kubectl is not installed. Please run $WC_ROOT/scripts/install-wild-cloud-dependencies.sh."
+    fi
+
+    # Check talosctl
+    if ! command -v talosctl &> /dev/null; then
+        echo "Error: talosctl is not installed. Please run $WC_ROOT/scripts/install-wild-cloud-dependencies.sh."
+    fi
+
+    # Check gomplate
+    if ! command -v gomplate &> /dev/null; then
+        echo "Error: gomplate is not installed. Please run $WC_ROOT/scripts/install-wild-cloud-dependencies.sh."
+        exit 1
+    fi
+
+    # Check yq
+    if ! command -v yq &> /dev/null; then
+        echo "Error: yq is not installed. Please run $WC_ROOT/scripts/install-wild-cloud-dependencies.sh."
+        exit 1
+    fi
+
+    # Check restic
+    if ! command -v restic &> /dev/null; then
+        echo "Error: restic is not installed. Please run $WC_ROOT/scripts/install-wild-cloud-dependencies.sh."
+        exit 1
    fi
 }

--- a/setup/cluster-services/get_helm.sh
+++ b/setup/cluster-services/get_helm.sh
--- a/scripts/install-wild-cloud-dependencies.sh
+++ b/scripts/install-wild-cloud-dependencies.sh
@@ -1,5 +1,14 @@
 #!/bin/bash

+# Install kubectl
+if ! command -v kubectl &> /dev/null; then
+    echo "Error: kubectl is not installed. Installing."
+    curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
+    curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl.sha256"
+    echo "$(cat kubectl.sha256)  kubectl" | sha256sum --check
+    sudo install -o root -g root -m 0755 kubectl /usr/local/bin/kubectl
+fi
+
 # Install gomplate
 if command -v gomplate &> /dev/null; then
    echo "gomplate is already installed."
--- a/setup/README.md
+++ b/setup/README.md
@@ -9,11 +9,13 @@ Follow the instructions to [set up cluster nodes](./cluster-nodes/README.md).
 Set up cluster services:

 ```bash
-./setup/cluster/setup-all.sh
+wild-cluster-services-fetch
+wild-cluster-services-configure
+wild-cluster-services-up
 ```

 Now make sure everything works:

 ```bash
-./setup/cluster/validate-setup.sh
+wild-health
 ```
--- a/setup/cluster-nodes/talos-schemas.yaml
+++ b/setup/cluster-nodes/talos-schemas.yaml
@@ -45,3 +45,18 @@
                - siderolabs/nvidia-open-gpu-kernel-modules-lts
                - siderolabs/nvidia-open-gpu-kernel-modules-production
                - siderolabs/util-linux-tools"
+  "56774e0894c8a3a3a9834a2aea65f24163cacf9506abbcbdc3ba135eaca4953f":
+    version: "v1.11.0"
+    architecture: "amd64"
+    secureBoot: false
+    schematic:
+      customization:
+      systemExtensions:
+          officialExtensions:
+              - siderolabs/gvisor
+              - siderolabs/intel-ucode
+              - siderolabs/iscsi-tools
+              - siderolabs/nvidia-container-toolkit-production
+              - siderolabs/nvidia-fabricmanager-production
+              - siderolabs/nvidia-open-gpu-kernel-modules-production
+              - siderolabs/util-linux-tools
--- a/setup/cluster-services/cert-manager/configure.sh
+++ b/setup/cluster-services/cert-manager/configure.sh
@@ -0,0 +1,10 @@
+#!/bin/bash
+
+print_info "Collecting cert-manager configuration..."
+
+prompt_if_unset_config "cloud.domain" "Enter main domain name" "example.com"
+domain=$(wild-config "cloud.domain")
+prompt_if_unset_config "cloud.internalDomain" "Enter internal domain name" "local.${domain}"
+prompt_if_unset_config "operator.email" "Enter operator email address (for Let's Encrypt)" ""
+prompt_if_unset_config "cluster.certManager.cloudflare.domain" "Enter Cloudflare domain (for DNS challenges)" "${domain}"
+prompt_if_unset_secret "cloudflare.token" "Enter Cloudflare API token (for DNS challenges)" ""
--- a/setup/cluster-services/cert-manager/install.sh
+++ b/setup/cluster-services/cert-manager/install.sh
@@ -16,21 +16,6 @@ CERT_MANAGER_DIR="${CLUSTER_SETUP_DIR}/cert-manager"

 print_header "Setting up cert-manager"

-# Collect required configuration variables
-print_info "Collecting cert-manager configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cloud.domain" "Enter main domain name" "example.com"
-
-# Get the domain value to use as default for internal domain
-domain=$(wild-config "cloud.domain")
-prompt_if_unset_config "cloud.internalDomain" "Enter internal domain name" "local.${domain}"
-prompt_if_unset_config "operator.email" "Enter operator email address (for Let's Encrypt)" ""
-prompt_if_unset_config "cluster.certManager.cloudflare.domain" "Enter Cloudflare domain (for DNS challenges)" "${domain}"
-prompt_if_unset_secret "cloudflare.token" "Enter Cloudflare API token (for DNS challenges)" ""
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled cert-manager templates..."
 if [ ! -d "${CERT_MANAGER_DIR}/kustomize" ]; then
--- a/setup/cluster-services/coredns/configure.sh
+++ b/setup/cluster-services/coredns/configure.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+print_info "Collecting CoreDNS configuration..."
+
+prompt_if_unset_config "cloud.internalDomain" "Enter internal domain name" "local.example.com"
+prompt_if_unset_config "cluster.loadBalancerIp" "Enter load balancer IP address" "192.168.1.240"
+prompt_if_unset_config "cloud.dns.externalResolver" "Enter external DNS resolver" "8.8.8.8"
--- a/setup/cluster-services/coredns/install.sh
+++ b/setup/cluster-services/coredns/install.sh
@@ -16,16 +16,6 @@ COREDNS_DIR="${CLUSTER_SETUP_DIR}/coredns"

 print_header "Setting up CoreDNS for k3s"

-# Collect required configuration variables
-print_info "Collecting CoreDNS configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cloud.internalDomain" "Enter internal domain name" "local.example.com"
-prompt_if_unset_config "cluster.loadBalancerIp" "Enter load balancer IP address" "192.168.1.240"
-prompt_if_unset_config "cloud.dns.externalResolver" "Enter external DNS resolver" "8.8.8.8"
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled CoreDNS templates..."
 if [ ! -d "${COREDNS_DIR}/kustomize" ]; then
--- a/setup/cluster-services/docker-registry/configure.sh
+++ b/setup/cluster-services/docker-registry/configure.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+
+print_info "Collecting Docker Registry configuration..."
+
+prompt_if_unset_config "cloud.dockerRegistryHost" "Enter Docker Registry hostname" "registry.local.example.com"
+prompt_if_unset_config "cluster.dockerRegistry.storage" "Enter Docker Registry storage size" "100Gi"
--- a/setup/cluster-services/docker-registry/install.sh
+++ b/setup/cluster-services/docker-registry/install.sh
@@ -16,15 +16,6 @@ DOCKER_REGISTRY_DIR="${CLUSTER_SETUP_DIR}/docker-registry"

 print_header "Setting up Docker Registry"

-# Collect required configuration variables
-print_info "Collecting Docker Registry configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cloud.dockerRegistryHost" "Enter Docker Registry hostname" "registry.local.example.com"
-prompt_if_unset_config "cluster.dockerRegistry.storage" "Enter Docker Registry storage size" "100Gi"
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled Docker Registry templates..."
 if [ ! -d "${DOCKER_REGISTRY_DIR}/kustomize" ]; then
--- a/setup/cluster-services/externaldns/configure.sh
+++ b/setup/cluster-services/externaldns/configure.sh
@@ -0,0 +1,3 @@
+print_info "Collecting ExternalDNS configuration..."
+
+prompt_if_unset_config "cluster.externalDns.ownerId" "Enter ExternalDNS owner ID (unique identifier for this cluster)" "wild-cloud-$(hostname -s)"
--- a/setup/cluster-services/externaldns/install.sh
+++ b/setup/cluster-services/externaldns/install.sh
@@ -16,14 +16,6 @@ EXTERNALDNS_DIR="${CLUSTER_SETUP_DIR}/externaldns"

 print_header "Setting up ExternalDNS"

-# Collect required configuration variables
-print_info "Collecting ExternalDNS configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cluster.externalDns.ownerId" "Enter ExternalDNS owner ID (unique identifier for this cluster)" "wild-cloud-$(hostname -s)"
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled ExternalDNS templates..."
 if [ ! -d "${EXTERNALDNS_DIR}/kustomize" ]; then
--- a/setup/cluster-services/install-all.sh
+++ b/setup/cluster-services/install-all.sh
@@ -1,22 +0,0 @@
-#!/bin/bash
-set -e
-
-# Navigate to script directory
-SCRIPT_PATH="$(realpath "${BASH_SOURCE[0]}")"
-SCRIPT_DIR="$(dirname "$SCRIPT_PATH")"
-cd "$SCRIPT_DIR"
-
-echo "Setting up your wild-cloud cluster services..."
-echo
-
-./metallb/install.sh
-./longhorn/install.sh
-./traefik/install.sh
-./coredns/install.sh
-./cert-manager/install.sh
-./externaldns/install.sh
-./kubernetes-dashboard/install.sh
-./nfs/install.sh
-./docker-registry/install.sh
-
-echo "Service setup complete!"
--- a/setup/cluster-services/kubernetes-dashboard/configure.sh
+++ b/setup/cluster-services/kubernetes-dashboard/configure.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+print_info "Collecting Kubernetes Dashboard configuration..."
+
+prompt_if_unset_config "cloud.internalDomain" "Enter internal domain name (for dashboard URL)" "local.example.com"
--- a/setup/cluster-services/kubernetes-dashboard/install.sh
+++ b/setup/cluster-services/kubernetes-dashboard/install.sh
@@ -16,14 +16,6 @@ KUBERNETES_DASHBOARD_DIR="${CLUSTER_SETUP_DIR}/kubernetes-dashboard"

 print_header "Setting up Kubernetes Dashboard"

-# Collect required configuration variables
-print_info "Collecting Kubernetes Dashboard configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cloud.internalDomain" "Enter internal domain name (for dashboard URL)" "local.example.com"
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled Dashboard templates..."
 if [ ! -d "${KUBERNETES_DASHBOARD_DIR}/kustomize" ]; then
--- a/setup/cluster-services/metallb/configure.sh
+++ b/setup/cluster-services/metallb/configure.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+
+print_info "Collecting MetalLB configuration..."
+
+prompt_if_unset_config "cluster.ipAddressPool" "Enter IP address pool for MetalLB (CIDR format, e.g., 192.168.1.240-192.168.1.250)" "192.168.1.240-192.168.1.250"
+prompt_if_unset_config "cluster.loadBalancerIp" "Enter load balancer IP address" "192.168.1.240"
--- a/setup/cluster-services/metallb/install.sh
+++ b/setup/cluster-services/metallb/install.sh
@@ -16,15 +16,6 @@ METALLB_DIR="${CLUSTER_SETUP_DIR}/metallb"

 print_header "Setting up MetalLB"

-# Collect required configuration variables
-print_info "Collecting MetalLB configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cluster.ipAddressPool" "Enter IP address pool for MetalLB (CIDR format, e.g., 192.168.1.240-192.168.1.250)" "192.168.1.240-192.168.1.250"
-prompt_if_unset_config "cluster.loadBalancerIp" "Enter load balancer IP address" "192.168.1.240"
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled MetalLB templates..."
 if [ ! -d "${METALLB_DIR}/kustomize" ]; then
--- a/setup/cluster-services/nfs/configure.sh
+++ b/setup/cluster-services/nfs/configure.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+print_info "Collecting NFS configuration..."
+
+prompt_if_unset_config "cloud.nfs.host" "Enter NFS server hostname or IP address" "192.168.1.100"
+prompt_if_unset_config "cloud.nfs.mediaPath" "Enter NFS export path for media storage" "/mnt/storage/media"
+prompt_if_unset_config "cloud.nfs.storageCapacity" "Enter NFS storage capacity (e.g., 1Ti, 500Gi)" "1Ti"
--- a/setup/cluster-services/nfs/install.sh
+++ b/setup/cluster-services/nfs/install.sh
@@ -16,16 +16,6 @@ NFS_DIR="${CLUSTER_SETUP_DIR}/nfs"

 print_header "Registering NFS server with Kubernetes cluster"

-# Collect required configuration variables
-print_info "Collecting NFS configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cloud.nfs.host" "Enter NFS server hostname or IP address" "192.168.1.100"
-prompt_if_unset_config "cloud.nfs.mediaPath" "Enter NFS export path for media storage" "/mnt/storage/media"
-prompt_if_unset_config "cloud.nfs.storageCapacity" "Enter NFS storage capacity (e.g., 1Ti, 500Gi)" "1Ti"
-
-print_success "Configuration collected successfully"
-
 # Templates should already be compiled by wild-cluster-services-generate
 echo "Using pre-compiled NFS templates..."
 if [ ! -d "${NFS_DIR}/kustomize" ]; then
--- a/setup/cluster-services/smtp/configure.sh
+++ b/setup/cluster-services/smtp/configure.sh
@@ -1,15 +1,4 @@
 #!/bin/bash
-set -e
-set -o pipefail
-
-# Initialize Wild Cloud environment
-if [ -z "${WC_ROOT}" ]; then
-    print "WC_ROOT is not set."
-    exit 1
-else
-    source "${WC_ROOT}/scripts/common.sh"
-    init_wild_env
-fi

 print_header "Setting up SMTP Configuration"

@@ -19,7 +8,6 @@ echo ""

 # Collect SMTP configuration
 print_info "Collecting SMTP configuration..."
-
 prompt_if_unset_config "cloud.smtp.host" "Enter SMTP host (e.g., email-smtp.us-east-2.amazonaws.com for AWS SES)" ""
 prompt_if_unset_config "cloud.smtp.port" "Enter SMTP port (usually 465 for SSL, 587 for STARTTLS)" "465"
 prompt_if_unset_config "cloud.smtp.user" "Enter SMTP username/access key" ""
@@ -47,7 +35,3 @@ echo "  User: $(wild-config cloud.smtp.user)"
 echo "  From: $(wild-config cloud.smtp.from)"
 echo "  Password: $(wild-secret cloud.smtp.password >/dev/null 2>&1 && echo "✓ Set" || echo "✗ Not set")"
 echo ""
-echo "Applications that use SMTP: ghost, gitea, and others"
-echo ""
-echo "To test SMTP configuration, deploy an app that uses email (like Ghost)"
-echo "and try the password reset or user invitation features."
--- a/setup/cluster-services/traefik/configure.sh
+++ b/setup/cluster-services/traefik/configure.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+print_info "Collecting Traefik configuration..."
+
+prompt_if_unset_config "cluster.loadBalancerIp" "Enter load balancer IP address for Traefik" "192.168.1.240"
--- a/setup/cluster-services/traefik/install.sh
+++ b/setup/cluster-services/traefik/install.sh
@@ -16,14 +16,6 @@ TRAEFIK_DIR="${CLUSTER_SETUP_DIR}/traefik"

 print_header "Setting up Traefik ingress controller"

-# Collect required configuration variables
-print_info "Collecting Traefik configuration..."
-
-# Prompt for configuration using helper functions
-prompt_if_unset_config "cluster.loadBalancerIp" "Enter load balancer IP address for Traefik" "192.168.1.240"
-
-print_success "Configuration collected successfully"
-
 # Install required CRDs first
 echo "Installing Gateway API CRDs..."
 kubectl apply -f https://github.com/kubernetes-sigs/gateway-api/releases/download/v1.0.0/standard-install.yaml
Author	SHA1	Message	Date
Paul Payne	8a569a1720	Separates cluster service config from install.	2025-09-02 16:24:38 -07:00
Paul Payne	af60d0c744	Full cloud setup test run #1 fixes.	2025-09-02 02:53:52 -07:00
Paul Payne	61460b63a3	Adds more to wild-backup.	2025-08-31 15:02:35 -07:00
Paul Payne	9f302e0e29	Update backup/restore docs.	2025-08-31 15:00:00 -07:00
Paul Payne	f83763b070	Fix immich secret key ref.	2025-08-31 14:49:35 -07:00
Paul Payne	c9ab5a31d8	Discourse app fixes.	2025-08-31 14:46:42 -07:00