feat(ci): Add HA support for node failures

Modified CI/CD workflows to gracefully handle Proxmox node failures:

CI Workflow (ci.yml):
- Terraform Plan only runs on main branch (faster CI on feature branches)
- Plan failures on unavailable nodes don't block validation
- Added warning message when plan fails

Deploy Workflow (deploy.yml):
- Added continue-on-error to all deploy jobs (pve1, pve2, pve3)
- Modified cluster validation to require 2/3 nodes (quorum)
- Enhanced deployment summary with success counter
- Exit codes: 0 if >=2 nodes, 1 if 1 node, 1 if 0 nodes

This ensures the infrastructure remains operational even when one
Proxmox node is down, maintaining HA principles.

.forgejo/workflows/ci.yml

@@ -35,7 +35,7 @@ jobs:
           done
 
       - name: Terraform Plan
-        if: github.event_name == 'push'
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
         run: |
           for dir in terraform/pve*; do
             if [ -d "$dir" ]; then
@@ -44,7 +44,7 @@ jobs:
                 cd "$dir" && \
                 cp ../terraform.tfvars.example terraform.tfvars && \
                 tofu init && \
-                tofu plan -out="tfplan-$(basename $dir)"
+                tofu plan -out="tfplan-$(basename $dir)" || echo "WARNING: Plan failed for $(basename $dir) - node may be unavailable"
               )
             fi
           done

.forgejo/workflows/deploy.yml

@@ -17,6 +17,7 @@ jobs:
     name: Deploy on pve1
     runs-on: self-hosted
     needs: ci
+    continue-on-error: true
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -45,6 +46,7 @@ jobs:
     name: Deploy on pve2
     runs-on: self-hosted
     needs: ci
+    continue-on-error: true
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -73,6 +75,7 @@ jobs:
     name: Deploy on pve3
     runs-on: self-hosted
     needs: ci
+    continue-on-error: true
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -102,7 +105,14 @@ jobs:
     name: Validate K3s Cluster
     runs-on: self-hosted
     needs: [deploy-pve1, deploy-pve2, deploy-pve3]
-    if: github.ref == 'refs/heads/main' && needs.deploy-pve1.result == 'success' && needs.deploy-pve2.result == 'success' && needs.deploy-pve3.result == 'success'
+    if: |
+      always() &&
+      github.ref == 'refs/heads/main' &&
+      (
+        (needs.deploy-pve1.result == 'success' && needs.deploy-pve2.result == 'success') ||
+        (needs.deploy-pve1.result == 'success' && needs.deploy-pve3.result == 'success') ||
+        (needs.deploy-pve2.result == 'success' && needs.deploy-pve3.result == 'success')
+      )
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -124,8 +134,28 @@ jobs:
     steps:
       - name: Deployment Summary
         run: |
-          echo "Deployment completed!"
-          echo "pve1 status: ${{ needs.deploy-pve1.result }}"
-          echo "pve2 status: ${{ needs.deploy-pve2.result }}"
-          echo "pve3 status: ${{ needs.deploy-pve3.result }}"
-          echo "Validation: ${{ needs.validate-cluster.result }}"
+          echo "=== Deployment Summary ==="
+          echo "pve1 (k3s-server-1): ${{ needs.deploy-pve1.result }}"
+          echo "pve2 (k3s-server-2): ${{ needs.deploy-pve2.result }}"
+          echo "pve3 (etcd-witness):  ${{ needs.deploy-pve3.result }}"
+          echo "Cluster validation:  ${{ needs.validate-cluster.result }}"
+          echo ""
+
+          # Count successful deployments
+          success_count=0
+          [ "${{ needs.deploy-pve1.result }}" == "success" ] && ((success_count++))
+          [ "${{ needs.deploy-pve2.result }}" == "success" ] && ((success_count++))
+          [ "${{ needs.deploy-pve3.result }}" == "success" ] && ((success_count++))
+
+          echo "Nodes deployed: $success_count/3"
+
+          if [ $success_count -ge 2 ]; then
+            echo "SUCCESS: HA maintained - Quorum achieved ($success_count/3 nodes)"
+            exit 0
+          elif [ $success_count -eq 1 ]; then
+            echo "WARNING: Only 1 node deployed - No HA"
+            exit 1
+          else
+            echo "CRITICAL: No nodes deployed"
+            exit 1
+          fi