Refactor deployment workflow to improve rollout checks and update timeout settings

Author: Locatelli-Flor

.github/workflows/deploy.yml

@@ -9,7 +9,9 @@ on:
 env:
   REGISTRY: crretoxmas2024.azurecr.io
   NAMESPACE: reto-xmas-2025-goland-ia-backend
-  DEPLOY_TIMEOUT: 8m
+  ROLLOUT_TIMEOUT: 60s
+  READY_CHECK_RETRIES: 20
+  READY_CHECK_SLEEP: 15
 
 jobs:
   build-and-deploy:
@@ -27,7 +29,7 @@ jobs:
             path: ./RAGManager
             image: reto-xmas-2025-goland-ia-backend-rag-manager
             deployment: rag-manager
-    
+
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
@@ -72,47 +74,69 @@ jobs:
           api=${{ env.REGISTRY }}/${{ matrix.service.image }}:${{ github.sha }} \
           -n ${{ env.NAMESPACE }}
 
-    - name: Wait for deployment rollout
+    - name: Wait for deployment to be ready (robust)
       run: |
-        echo "Waiting for deployment rollout to complete..."
-        kubectl rollout status deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }} --timeout=${{ env.DEPLOY_TIMEOUT }}
-        kubectl get deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }}
-        kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }}
+        set -e
+
+        echo "Checking rollout status (non-blocking)..."
+        kubectl rollout status deployment/${{ matrix.service.deployment }} \
+          -n ${{ env.NAMESPACE }} \
+          --timeout=${{ env.ROLLOUT_TIMEOUT }} || true
+
+        echo "Waiting for available replicas..."
+
+        for i in $(seq 1 $READY_CHECK_RETRIES); do
+          DESIRED=$(kubectl get deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }} -o jsonpath='{.spec.replicas}')
+          AVAILABLE=$(kubectl get deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }} -o jsonpath='{.status.availableReplicas}')
+
+          echo "Attempt $i: $AVAILABLE / $DESIRED replicas available"
+
+          if [ "$AVAILABLE" = "$DESIRED" ]; then
+            echo "Deployment is ready"
+            exit 0
+          fi
 
-    - name: Verify deployment
+          sleep $READY_CHECK_SLEEP
+        done
+
+        echo "Deployment did not become ready in time"
+        kubectl describe deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }}
+        exit 1
+
+    - name: Verify pods
       if: success()
       run: |
-        echo "Deployment successful for ${{ matrix.service.name }}"
-        kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }}
+        kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }} -o wide
 
     - name: Get logs on failure
       if: failure()
       run: |
+        echo "=== Deployment ==="
+        kubectl describe deployment/${{ matrix.service.deployment }} -n ${{ env.NAMESPACE }}
+
+        echo "=== Pods ==="
+        kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }} -o wide
+
         echo "=== Pod Logs ==="
         kubectl logs -n ${{ env.NAMESPACE }} \
           -l app=${{ matrix.service.deployment }} \
           --tail=100 \
           --all-containers=true \
-          --prefix=true || echo "Could not fetch logs"
+          --prefix=true || true
 
     - name: Deployment Summary
       if: always()
       run: |
         STATUS="${{ job.status }}"
-        
+
         echo "### Deployment - ${{ matrix.service.name }}" >> $GITHUB_STEP_SUMMARY
         echo "" >> $GITHUB_STEP_SUMMARY
         echo "| Property | Value |" >> $GITHUB_STEP_SUMMARY
         echo "|----------|-------|" >> $GITHUB_STEP_SUMMARY
         echo "| Image | \`${{ env.REGISTRY }}/${{ matrix.service.image }}:${{ github.sha }}\` |" >> $GITHUB_STEP_SUMMARY
-        
-        if [ "$STATUS" == "success" ]; then
-          echo "| Status | Success |" >> $GITHUB_STEP_SUMMARY
-        else
-          echo "| Status | Failed |" >> $GITHUB_STEP_SUMMARY
-        fi
-        
+        echo "| Status | $STATUS |" >> $GITHUB_STEP_SUMMARY
         echo "" >> $GITHUB_STEP_SUMMARY
+
         echo "#### Pods:" >> $GITHUB_STEP_SUMMARY
         echo '```' >> $GITHUB_STEP_SUMMARY
         kubectl get pods -n ${{ env.NAMESPACE }} -l app=${{ matrix.service.deployment }} >> $GITHUB_STEP_SUMMARY || true
@@ -126,7 +150,7 @@ jobs:
     steps:
     - name: Success Summary
       run: |
-        echo "### ll Services Deployed!" >> $GITHUB_STEP_SUMMARY
+        echo "### All Services Deployed" >> $GITHUB_STEP_SUMMARY
         echo "" >> $GITHUB_STEP_SUMMARY
         echo "**Live URLs:**" >> $GITHUB_STEP_SUMMARY
         echo "- [DocsManager](https://goland-ia-backend-docs-manager.reto-ucu.net/docs)" >> $GITHUB_STEP_SUMMARY
@@ -142,4 +166,4 @@ jobs:
       run: |
         echo "### Deployment Failed" >> $GITHUB_STEP_SUMMARY
         echo "" >> $GITHUB_STEP_SUMMARY
-        echo "Automatic rollback initiated" >> $GITHUB_STEP_SUMMARY
+        echo "Please check deployment logs above." >> $GITHUB_STEP_SUMMARY