Adds reliability checks to cert-manager, externaldns, and traefik setup.

setup/cluster-services/cert-manager/configure.sh

@@ -7,4 +7,5 @@ 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_config "cluster.certManager.cloudflare.zoneID" "Enter Cloudflare zone ID (for DNS challenges - improves reliability)" ""
 prompt_if_unset_secret "cloudflare.token" "Enter Cloudflare API token (for DNS challenges)" ""

setup/cluster-services/cert-manager/install.sh

@@ -16,42 +16,88 @@ CERT_MANAGER_DIR="${CLUSTER_SETUP_DIR}/cert-manager"
 
 print_header "Setting up cert-manager"
 
-# Templates should already be compiled by wild-cluster-services-generate
-echo "Using pre-compiled cert-manager templates..."
+# Check Traefik dependency
+print_info "Verifying Traefik is ready (required for cert-manager)..."
+kubectl wait --for=condition=Available deployment/traefik -n traefik --timeout=60s 2>/dev/null || {
+    print_warning "Traefik not ready, but continuing with cert-manager installation"
+    print_info "Note: cert-manager may not work properly without Traefik"
+}
+
+# Templates should already be compiled by wild-cluster-services-configure
+print_info "Using pre-compiled cert-manager templates..."
 if [ ! -d "${CERT_MANAGER_DIR}/kustomize" ]; then
-    echo "Error: Compiled templates not found. Run 'wild-cluster-services-generate' first."
+    print_error "Compiled templates not found. Run 'wild-cluster-services-configure' first."
     exit 1
 fi
 
-echo "Setting up cert-manager..."
+print_info "Setting up cert-manager..."
 
-# Install cert-manager using the official installation method 
+# Install cert-manager using the official installation method
 # This installs CRDs, controllers, and webhook components
-echo "Installing cert-manager components..."
+print_info "Installing cert-manager components..."
 # Using stable URL for cert-manager installation
 kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.13.1/cert-manager.yaml || \
   kubectl apply -f https://github.com/jetstack/cert-manager/releases/download/v1.13.1/cert-manager.yaml
 
 # Wait for cert-manager to be ready
-echo "Waiting for cert-manager to be ready..."
+print_info "Waiting for cert-manager to be ready..."
 kubectl wait --for=condition=Available deployment/cert-manager -n cert-manager --timeout=120s
 kubectl wait --for=condition=Available deployment/cert-manager-cainjector -n cert-manager --timeout=120s
 kubectl wait --for=condition=Available deployment/cert-manager-webhook -n cert-manager --timeout=120s
 
-# Add delay to allow webhook to be fully ready
-echo "Waiting additional time for cert-manager webhook to be fully operational..."
-sleep 30
+# Ensure webhook is fully operational
+print_info "Verifying cert-manager webhook is fully operational..."
+until kubectl get validatingwebhookconfigurations cert-manager-webhook &>/dev/null; do
+    print_info "Waiting for cert-manager webhook to register..."
+    sleep 5
+done
+
+# Test webhook connectivity before proceeding
+print_info "Testing webhook connectivity..."
+kubectl auth can-i create certificates.cert-manager.io --as=system:serviceaccount:cert-manager:cert-manager
+
 
 # Setup Cloudflare API token for DNS01 challenges
-echo "Creating Cloudflare API token secret..."
+print_info "Creating Cloudflare API token secret..."
 CLOUDFLARE_API_TOKEN=$(wild-secret cloudflare.token) || exit 1
+
+# Validate Cloudflare API token permissions
+print_info "Validating Cloudflare API token permissions..."
+validate_cloudflare_token() {
+    local token="$1"
+    if ! command -v curl &>/dev/null; then
+        print_warning "curl not available, skipping token validation"
+        return 0
+    fi
+
+    print_info "Testing Cloudflare API token..."
+    local response
+    response=$(curl -s -H "Authorization: Bearer $token" \
+                   "https://api.cloudflare.com/client/v4/zones")
+
+    if echo "$response" | grep -q '"success":true'; then
+        print_success "Cloudflare API token is valid and has zone access"
+        return 0
+    else
+        print_error "Cloudflare token validation failed"
+        print_info "Response: $response"
+        print_info "Please ensure your token has Zone - Zone - Read permission"
+        return 1
+    fi
+}
+
+validate_cloudflare_token "$CLOUDFLARE_API_TOKEN" || {
+    print_error "Cloudflare token validation failed. Please check token permissions."
+    print_info "Required permissions: Zone - Zone - Read, Zone - DNS - Edit"
+    exit 1
+}
 kubectl create secret generic cloudflare-api-token \
   --namespace cert-manager \
   --from-literal=api-token="${CLOUDFLARE_API_TOKEN}" \
   --dry-run=client -o yaml | kubectl apply -f -
 
 # Configure cert-manager to use external DNS for challenge verification
-echo "Configuring cert-manager to use external DNS servers..."
+print_info "Configuring cert-manager to use external DNS servers..."
 kubectl patch deployment cert-manager -n cert-manager --patch '
 spec:
   template:
@@ -70,26 +116,39 @@ spec:
             value: "5"'
 
 # Wait for cert-manager to restart with new DNS config
-echo "Waiting for cert-manager to restart with new DNS configuration..."
+print_info "Waiting for cert-manager to restart with new DNS configuration..."
 kubectl rollout status deployment/cert-manager -n cert-manager --timeout=120s
 
 # Apply Let's Encrypt issuers and certificates using kustomize
-echo "Creating Let's Encrypt issuers and certificates..."
+print_info "Creating Let's Encrypt issuers and certificates..."
 kubectl apply -k ${CERT_MANAGER_DIR}/kustomize
 
 # Wait for issuers to be ready
-echo "Waiting for Let's Encrypt issuers to be ready..."
-sleep 10
-echo "Wildcard certificate creation initiated. This may take some time to complete depending on DNS propagation."
+print_info "Waiting for Let's Encrypt issuers to be ready..."
+kubectl wait --for=condition=Ready clusterissuer/letsencrypt-prod --timeout=60s || print_warning "Production issuer not ready, proceeding anyway..."
+kubectl wait --for=condition=Ready clusterissuer/letsencrypt-staging --timeout=60s || print_warning "Staging issuer not ready, proceeding anyway..."
+
+# Validate DNS resolution using temporary test pod
+print_info "Validating DNS resolution for ACME challenges..."
+domain=$(wild-config cluster.certManager.cloudflare.domain)
+print_info "Testing DNS resolution for domain: $domain"
+
+# Create temporary pod with DNS utilities
+kubectl run dns-test --image=busybox:1.35 --rm -i --restart=Never -n cert-manager -- \
+    nslookup -type=SOA "$domain" 1.1.1.1 &>/dev/null && \
+    print_success "DNS resolution working for ACME challenges" || \
+    print_warning "DNS resolution issues may affect ACME challenges"
+
+print_info "Wildcard certificate creation initiated. This may take some time to complete depending on DNS propagation."
 
 # Wait for the certificates to be issued (with a timeout)
-echo "Waiting for wildcard certificates to be ready (this may take several minutes)..."
+print_info "Waiting for wildcard certificates to be ready (this may take several minutes)..."
 kubectl wait --for=condition=Ready certificate wildcard-internal-wild-cloud -n cert-manager --timeout=300s || true
 kubectl wait --for=condition=Ready certificate wildcard-wild-cloud -n cert-manager --timeout=300s || true
 
-echo "cert-manager setup complete!"
+print_success "cert-manager setup complete!"
 echo ""
-echo "To verify the installation:"
-echo "  kubectl get pods -n cert-manager"
-echo "  kubectl get clusterissuers"
-echo "  kubectl get certificates -n cert-manager"
+print_info "To verify the installation:"
+print_info "  kubectl get pods -n cert-manager"
+print_info "  kubectl get clusterissuers"
+print_info "  kubectl get certificates -n cert-manager"