Add retry logic to docker pull in blue-green deploy (#5197)

Handles intermittent Docker registry digest mismatch errors like:
"failed commit on ref: unexpected commit digest"

This is a known Docker/containerd issue that can occur due to:
- Registry caching
- Network/proxy issues
- Race conditions during push

Now retries up to 3 times with 5 second delays.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

scripts/deploy-blue-green.sh

@@ -48,6 +48,26 @@ get_active_instance() {
     fi
 }
 
+# Pull image with retry (handles intermittent registry/digest issues)
+pull_with_retry() {
+    local image=$1
+    local max_attempts=${2:-3}
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        log_info "Pulling image (attempt ${attempt}/${max_attempts})..."
+        if docker pull "${image}"; then
+            log_info "Image pulled successfully"
+            return 0
+        fi
+        log_warn "Pull failed, retrying in 5 seconds..."
+        sleep 5
+        attempt=$((attempt + 1))
+    done
+    log_error "Failed to pull image after ${max_attempts} attempts"
+    return 1
+}
+
 # Wait for a container to be healthy
 wait_for_healthy() {
     local container=$1
@@ -93,9 +113,11 @@ main() {
     log_info "Active instance: eagle-${active}"
     log_info "Staging instance: eagle-${staging}"
 
-    # Pull the new image
-    log_info "Pulling new image..."
-    docker pull "${new_image}"
+    # Pull the new image (with retry for intermittent registry issues)
+    if ! pull_with_retry "${new_image}" 3; then
+        log_error "Failed to pull new image, aborting deployment"
+        exit 1
+    fi
 
     # Start staging instance with new image
     log_info "Starting eagle-${staging} with new image..."