integration: authenticate Docker Hub pulls and retry transient errors

Anonymous Hub pulls trip the 100/6h IP cap on shared CI runners, turning
into singleton FAIL reports whenever the runner egress IP crosses the
quota. Route every pull through Docker Hub credentials when present, and
retry transient errors with backoff. tsic and hi use the same helper so
both surfaces honour ~/.docker/config.json and the GHA secrets.

cmd/hi/docker.go

@@ -14,6 +14,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/cenkalti/backoff/v5"
 	"github.com/docker/docker/api/types/container"
 	"github.com/docker/docker/api/types/image"
 	"github.com/docker/docker/api/types/mount"
@@ -522,9 +523,9 @@ func checkImageAvailableLocally(ctx context.Context, cli *client.Client, imageNa
 	return true, nil
 }
 
-// ensureImageAvailable checks if the image is available locally first, then pulls if needed.
+// ensureImageAvailable pulls imageName if missing, using Docker Hub
+// credentials and retrying transient errors.
 func ensureImageAvailable(ctx context.Context, cli *client.Client, imageName string, verbose bool) error {
-	// First check if image is available locally
 	available, err := checkImageAvailableLocally(ctx, cli, imageName)
 	if err != nil {
 		return fmt.Errorf("checking local image availability: %w", err)
@@ -538,34 +539,64 @@ func ensureImageAvailable(ctx context.Context, cli *client.Client, imageName str
 		return nil
 	}
 
-	// Image not available locally, try to pull it
 	if verbose {
 		log.Printf("Image %s not found locally, pulling...", imageName)
 	}
 
-	reader, err := cli.ImagePull(ctx, imageName, image.PullOptions{})
+	registryAuth, err := dockertestutil.RegistryAuth()
 	if err != nil {
-		return fmt.Errorf("pulling image %s: %w", imageName, err)
+		return fmt.Errorf("resolving registry auth: %w", err)
 	}
-	defer reader.Close()
 
-	if verbose {
-		_, err = io.Copy(os.Stdout, reader)
-		if err != nil {
-			return fmt.Errorf("reading pull output: %w", err)
-		}
-	} else {
-		_, err = io.Copy(io.Discard, reader)
-		if err != nil {
-			return fmt.Errorf("reading pull output: %w", err)
-		}
+	_, err = backoff.Retry(
+		ctx,
+		func() (struct{}, error) {
+			reader, pullErr := cli.ImagePull(ctx, imageName, image.PullOptions{RegistryAuth: registryAuth})
+			if pullErr != nil {
+				if isPermanentDockerPullError(pullErr) {
+					return struct{}{}, backoff.Permanent(pullErr)
+				}
 
+				return struct{}{}, fmt.Errorf("pulling image %s: %w", imageName, pullErr)
+			}
+			defer reader.Close()
+
+			sink := io.Discard
+			if verbose {
+				sink = os.Stdout
+			}
+
+			_, copyErr := io.Copy(sink, reader)
+			if copyErr != nil {
+				return struct{}{}, fmt.Errorf("reading pull output: %w", copyErr)
+			}
+
+			return struct{}{}, nil
+		},
+		backoff.WithBackOff(backoff.NewExponentialBackOff()),
+		backoff.WithMaxElapsedTime(60*time.Second),
+	)
+	if err != nil {
+		return err
+	}
+
+	if !verbose {
 		log.Printf("Image %s pulled successfully", imageName)
 	}
 
 	return nil
 }
 
+func isPermanentDockerPullError(err error) bool {
+	msg := strings.ToLower(err.Error())
+
+	return strings.Contains(msg, "manifest unknown") ||
+		strings.Contains(msg, "manifest not found") ||
+		strings.Contains(msg, "repository does not exist") ||
+		strings.Contains(msg, "name unknown") ||
+		strings.Contains(msg, "no such image")
+}
+
 // listControlFiles displays the headscale test artifacts created in the control logs directory.
 func listControlFiles(logsDir string) {
 	entries, err := os.ReadDir(logsDir)