Reorganized for new stable/waypoint versioning design.

cert-manager/versions/v1/README.md

@@ -0,0 +1,20 @@
+# cert-manager
+
+X.509 certificate management for Kubernetes using Let's Encrypt.
+
+## Upstream
+
+The `upstream/cert-manager.yaml` file is downloaded from the official cert-manager release:
+
+- Source: https://github.com/cert-manager/cert-manager/releases/download/v1.17.2/cert-manager.yaml
+- Version: v1.17.2
+
+To update, download the new version and replace the file.
+
+## DNS Configuration
+
+The upstream cert-manager deployment is patched via kustomize overlay (`upstream/kustomization.yaml`) to use external DNS resolvers (1.1.1.1, 8.8.8.8) instead of cluster DNS. This is required for ACME DNS-01 challenge verification.
+
+## Maintenance
+
+The `scripts/repair-certificates.sh` script can fix stuck certificates, orphaned ACME orders, and Cloudflare DNS cleanup errors. Run it manually when certificate issuance has issues.

cert-manager/versions/v1/internal-wildcard-certificate.yaml

@@ -0,0 +1,19 @@
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: wildcard-internal-wild-cloud
+  namespace: cert-manager
+spec:
+  secretName: wildcard-internal-wild-cloud-tls
+  dnsNames:
+    - "*.{{ .internalDomain }}"
+    - "{{ .internalDomain }}"
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+  duration: 2160h # 90 days
+  renewBefore: 360h # 15 days
+  privateKey:
+    algorithm: RSA
+    size: 2048

cert-manager/versions/v1/kustomization.yaml

@@ -0,0 +1,9 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+- namespace.yaml
+- letsencrypt-staging-dns01.yaml
+- letsencrypt-prod-dns01.yaml
+- internal-wildcard-certificate.yaml
+- wildcard-certificate.yaml

cert-manager/versions/v1/letsencrypt-prod-dns01.yaml

@@ -0,0 +1,25 @@
+---
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: letsencrypt-prod
+spec:
+  acme:
+    email: {{ .email }}
+    privateKeySecretRef:
+      name: letsencrypt-prod
+    server: https://acme-v02.api.letsencrypt.org/directory
+    solvers:
+    # DNS-01 solver for wildcard certificates
+    - dns01:
+        cloudflare:
+          apiTokenSecretRef:
+            name: cloudflare-api-token
+            key: api-token
+      selector:
+        dnsZones:
+        - "{{ .cloudflareDomain }}"
+    # Keep the HTTP-01 solver for non-wildcard certificates
+    - http01:
+        ingress:
+          class: traefik

cert-manager/versions/v1/letsencrypt-staging-dns01.yaml

@@ -0,0 +1,25 @@
+---
+apiVersion: cert-manager.io/v1
+kind: ClusterIssuer
+metadata:
+  name: letsencrypt-staging
+spec:
+  acme:
+    email: {{ .email }}
+    privateKeySecretRef:
+      name: letsencrypt-staging
+    server: https://acme-staging-v02.api.letsencrypt.org/directory
+    solvers:
+    # DNS-01 solver for wildcard certificates
+    - dns01:
+        cloudflare:
+          apiTokenSecretRef:
+            name: cloudflare-api-token
+            key: api-token
+      selector:
+        dnsZones:
+        - "{{ .cloudflareDomain }}"
+    # Keep the HTTP-01 solver for non-wildcard certificates
+    - http01:
+        ingress:
+          class: traefik

cert-manager/versions/v1/manifest.yaml

@@ -0,0 +1,26 @@
+version: v1.17.2
+requires:
+  - name: traefik
+defaultConfig:
+  namespace: cert-manager
+  cloudDomain: "{{ .cloud.domain }}"
+  internalDomain: "{{ .cloud.internalDomain }}"
+  email: "{{ .operator.email }}"
+  cloudflareDomain: "{{ .cloud.baseDomain }}"
+scripts:
+  - name: repair-certificates
+    path: scripts/repair-certificates.sh
+    description: Fix stuck certificates, orphaned ACME orders, and Cloudflare DNS cleanup errors
+defaultSecrets:
+  - key: cloudflareToken
+deploy:
+  phases:
+    - path: upstream
+      waitFor:
+        name: cert-manager-webhook
+        timeout: "120s"
+    - path: .
+  createSecrets:
+    - name: cloudflare-api-token
+      entries:
+        api-token: cloudflareToken

cert-manager/versions/v1/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: "{{ .namespace }}"

cert-manager/versions/v1/scripts/repair-certificates.sh

@@ -0,0 +1,89 @@
+#!/bin/bash
+# Repair stuck certificates, orphaned ACME orders, and Cloudflare DNS errors.
+# This is an operational maintenance script, not part of deployment.
+# Run manually when cert-manager has issues with certificate issuance.
+#
+# Usage: KUBECONFIG=/path/to/kubeconfig ./repair-certificates.sh
+set -e
+set -o pipefail
+
+if [ -z "${KUBECONFIG}" ]; then
+    echo "ERROR: KUBECONFIG is not set"
+    exit 1
+fi
+
+needs_restart=false
+
+echo "=== cert-manager Certificate Repair ==="
+echo ""
+
+echo "Checking for certificates with failed issuance attempts..."
+stuck_certs=$(kubectl get certificates --all-namespaces -o json 2>/dev/null | \
+    jq -r '.items[] | select(.status.conditions[]? | select(.type=="Issuing" and .status=="False" and (.message | contains("404")))) | "\(.metadata.namespace) \(.metadata.name)"')
+
+if [ -n "$stuck_certs" ]; then
+    echo "WARNING: Found certificates stuck with non-existent orders, recreating them..."
+    echo "$stuck_certs" | while read ns name; do
+        echo "Recreating certificate $ns/$name..."
+        cert_spec=$(kubectl get certificate "$name" -n "$ns" -o json | jq '.spec')
+        kubectl delete certificate "$name" -n "$ns"
+        echo "{\"apiVersion\":\"cert-manager.io/v1\",\"kind\":\"Certificate\",\"metadata\":{\"name\":\"$name\",\"namespace\":\"$ns\"},\"spec\":$cert_spec}" | kubectl apply -f -
+    done
+    needs_restart=true
+    sleep 5
+else
+    echo "No certificates stuck with failed orders"
+fi
+
+echo "Checking for orphaned ACME orders..."
+orphaned_orders=$(kubectl logs -n cert-manager deployment/cert-manager --tail=200 2>/dev/null | \
+    grep -E "failed to retrieve the ACME order.*404" 2>/dev/null | \
+    sed -n 's/.*resource_name="\([^"]*\)".*/\1/p' | \
+    sort -u || true)
+
+if [ -n "$orphaned_orders" ]; then
+    echo "WARNING: Found orphaned ACME orders from logs"
+    for order in $orphaned_orders; do
+        echo "Deleting orphaned order: $order"
+        orders_found=$(kubectl get orders --all-namespaces 2>/dev/null | grep "$order" 2>/dev/null || true)
+        if [ -n "$orders_found" ]; then
+            echo "$orders_found" | while read ns name rest; do
+                kubectl delete order "$name" -n "$ns" 2>/dev/null || true
+            done
+        fi
+    done
+    needs_restart=true
+else
+    echo "No orphaned orders found in logs"
+fi
+
+echo "Checking for Cloudflare DNS cleanup errors..."
+cloudflare_errors=$(kubectl logs -n cert-manager deployment/cert-manager --tail=200 2>/dev/null | \
+    grep -c "Error: 7003.*Could not route" 2>/dev/null || echo "0")
+
+if [ "$cloudflare_errors" -gt "0" ]; then
+    echo "WARNING: Found $cloudflare_errors Cloudflare DNS cleanup errors (stale DNS record references)"
+    echo "Deleting stuck challenges and orders to allow fresh start"
+
+    kubectl delete challenges --all -n cert-manager 2>/dev/null || true
+    kubectl delete orders --all -n cert-manager 2>/dev/null || true
+
+    needs_restart=true
+else
+    echo "No Cloudflare DNS cleanup errors"
+fi
+
+if [ "$needs_restart" = true ]; then
+    echo "Restarting cert-manager to clear internal state..."
+    kubectl rollout restart deployment cert-manager -n cert-manager
+    kubectl rollout status deployment/cert-manager -n cert-manager --timeout=120s
+    echo "Waiting for cert-manager to recreate fresh challenges..."
+    sleep 15
+else
+    echo "No restart needed - cert-manager state is clean"
+fi
+
+echo ""
+echo "Repair complete. Check certificate status with:"
+echo "  kubectl get certificates --all-namespaces"
+echo "  kubectl get clusterissuers"

cert-manager/versions/v1/upstream/kustomization.yaml

@@ -0,0 +1,30 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - cert-manager.yaml
+patches:
+  - target:
+      kind: Deployment
+      name: cert-manager
+      namespace: cert-manager
+    patch: |-
+      apiVersion: apps/v1
+      kind: Deployment
+      metadata:
+        name: cert-manager
+        namespace: cert-manager
+      spec:
+        template:
+          spec:
+            dnsPolicy: None
+            dnsConfig:
+              nameservers:
+                - "1.1.1.1"
+                - "8.8.8.8"
+              searches:
+                - cert-manager.svc.cluster.local
+                - svc.cluster.local
+                - cluster.local
+              options:
+                - name: ndots
+                  value: "5"

cert-manager/versions/v1/wildcard-certificate.yaml

@@ -0,0 +1,19 @@
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: wildcard-wild-cloud
+  namespace: cert-manager
+spec:
+  secretName: wildcard-wild-cloud-tls
+  dnsNames:
+    - "*.{{ .cloudDomain }}"
+    - "{{ .cloudDomain }}"
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+  duration: 2160h # 90 days
+  renewBefore: 360h # 15 days
+  privateKey:
+    algorithm: RSA
+    size: 2048