Function isRetryableExecError

pkg/utils/exec.go:55–93

isRetryableExecError returns true for transient infrastructure errors

(err error)

// isRetryableExecError returns true for transient infrastructure errors
func isRetryableExecError(err error) bool {
	if err == nil {
		return false
	}

	errStr := strings.ToLower(err.Error())

	// Kubernetes API proxy errors (common in AKS)
	if strings.Contains(errStr, "proxy error") ||
		strings.Contains(errStr, "error dialing backend") {
		return true
	}

	// HTTP 500 errors from API server
	if strings.Contains(errStr, "500 internal server error") ||
		strings.Contains(errStr, "internal error occurred") {
		return true
	}

	// Network connectivity issues
	if strings.Contains(errStr, "connection refused") ||
		strings.Contains(errStr, "connection reset") ||
		strings.Contains(errStr, "i/o timeout") ||
		strings.Contains(errStr, "tls handshake timeout") ||
		strings.Contains(errStr, "dial tcp") {
		return true
	}

	// Kubernetes API errors that are typically transient
	if apierrors.IsInternalError(err) ||
		apierrors.IsServerTimeout(err) ||
		apierrors.IsTimeout(err) ||
		apierrors.IsServiceUnavailable(err) ||
		apierrors.IsTooManyRequests(err) {
		return true
	}

	return false
}

// ExecCommand executes a command inside the pod, automatically retrying
// transient errors like proxy failures or network issues.