From c89f5ae7731af27dfdf6895ad04167b435e01910 Mon Sep 17 00:00:00 2001
From: rcourtman <courtmanr@gmail.com>
Date: Wed, 12 Nov 2025 13:24:54 +0000
Subject: [PATCH] Re-enable validation with Docker image pull retry logic

Added exponential backoff retry logic to handle Docker Hub CDN
propagation delays (2-5 minutes after push).

Validation workflow now:
- Retries Docker image pull up to 10 times
- Uses exponential backoff: 30s, 60s, 120s, 120s...
- Total timeout: ~10 minutes max
- Continues with asset-only validation if image unavailable

This keeps validation enabled (important for quality) while
fixing the race condition that caused consistent failures.

Related to #695
---
 .github/workflows/release.yml                 | 27 +++++-------
 .github/workflows/validate-release-assets.yml | 44 ++++++++++++++-----
 2 files changed, 44 insertions(+), 27 deletions(-)

diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 7fa5367..112fa77 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -436,20 +436,13 @@ jobs:
           echo "Review the draft release and publish when ready."
           echo ""
 
-  # Validation disabled - was causing race conditions with Docker image propagation
-  # The release workflow already has comprehensive checks:
-  # - Version guard
-  # - Preflight tests (backend + frontend + linting)
-  # - Docker image builds
-  # - Release asset creation with checksums
-  # Manual validation can be done after draft release creation if needed
-  # validate-release-assets:
-  #   needs: create-release
-  #   uses: ./.github/workflows/validate-release-assets.yml
-  #   secrets: inherit
-  #   with:
-  #     tag: ${{ needs.create-release.outputs.tag }}
-  #     version: ${{ inputs.version }}
-  #     release_id: ${{ needs.create-release.outputs.release_id }}
-  #     draft: true
-  #     target_commitish: ${{ needs.create-release.outputs.target_commitish }}
+  validate-release-assets:
+    needs: create-release
+    uses: ./.github/workflows/validate-release-assets.yml
+    secrets: inherit
+    with:
+      tag: ${{ needs.create-release.outputs.tag }}
+      version: ${{ inputs.version }}
+      release_id: ${{ needs.create-release.outputs.release_id }}
+      draft: true
+      target_commitish: ${{ needs.create-release.outputs.target_commitish }}
diff --git a/.github/workflows/validate-release-assets.yml b/.github/workflows/validate-release-assets.yml
index 2b6b861..c4a8f42 100644
--- a/.github/workflows/validate-release-assets.yml
+++ b/.github/workflows/validate-release-assets.yml
@@ -157,23 +157,47 @@ jobs:
         if: steps.context.outputs.should_run == 'true'
         run: docker --version
 
-      - name: Pull Docker image (if available)
+      - name: Pull Docker image (with retry logic)
         if: steps.context.outputs.should_run == 'true'
         id: docker
         continue-on-error: true
         run: |
           IMAGE="rcourtman/pulse:${{ steps.context.outputs.tag }}"
           echo "Attempting to pull Docker image: $IMAGE"
+          echo "Docker Hub CDN propagation can take 2-5 minutes after push..."
+          echo ""
 
-          if docker pull "$IMAGE" 2>/dev/null; then
-            echo "✓ Docker image available: $IMAGE"
-            echo "image_available=true" >> $GITHUB_OUTPUT
-            echo "image=$IMAGE" >> $GITHUB_OUTPUT
-          else
-            echo "⚠️  Docker image not yet available: $IMAGE"
-            echo "⚠️  Will skip Docker image validation"
-            echo "image_available=false" >> $GITHUB_OUTPUT
-          fi
+          # Retry logic: 10 attempts with exponential backoff
+          # Total time: ~10 minutes max
+          MAX_ATTEMPTS=10
+          ATTEMPT=1
+          WAIT_TIME=30
+
+          while [ $ATTEMPT -le $MAX_ATTEMPTS ]; do
+            echo "Attempt $ATTEMPT/$MAX_ATTEMPTS: Pulling image..."
+
+            if docker pull "$IMAGE" 2>/dev/null; then
+              echo "✓ Docker image available: $IMAGE"
+              echo "image_available=true" >> $GITHUB_OUTPUT
+              echo "image=$IMAGE" >> $GITHUB_OUTPUT
+              exit 0
+            fi
+
+            if [ $ATTEMPT -lt $MAX_ATTEMPTS ]; then
+              echo "⚠️  Image not yet available, waiting ${WAIT_TIME}s before retry..."
+              sleep $WAIT_TIME
+              WAIT_TIME=$((WAIT_TIME * 2))  # Exponential backoff
+              if [ $WAIT_TIME -gt 120 ]; then
+                WAIT_TIME=120  # Cap at 2 minutes
+              fi
+            fi
+
+            ATTEMPT=$((ATTEMPT + 1))
+          done
+
+          echo "⚠️  Docker image not available after $MAX_ATTEMPTS attempts"
+          echo "⚠️  Will skip Docker image validation"
+          echo "image_available=false" >> $GITHUB_OUTPUT
 
       - name: Run validation script
         if: steps.context.outputs.should_run == 'true'