linshenkx/prompt-optimizer · error · EvaluationValidationError

Workspace prompt must not be empty.

Error message

Workspace prompt must not be empty.

What it means

Catch-all OptimizationError at the end of optimizeMessage: every error thrown in the method (request validation, model lookup, template resolution, LLM call, response validation) is re-wrapped as 'Message optimization failed: <original message>'. The original cause survives only inside the message string.

Source

Thrown at packages/core/src/services/evaluation/service.ts:470

  private validateRequest(request: EvaluationRequest): void {
    if (!request.evaluationModelKey?.trim()) {
      throw new EvaluationValidationError('Evaluation model key must not be empty.');
    }

    if (!request.mode) {
      throw new EvaluationValidationError('Evaluation mode configuration must not be empty.');
    }
    if (!request.mode.functionMode) {
      throw new EvaluationValidationError('Function mode must not be empty.');
    }
    if (!request.mode.subMode) {
      throw new EvaluationValidationError('Sub mode must not be empty.');
    }

    switch (request.type) {
      case 'result':
        if (!request.target?.workspacePrompt?.trim()) {
          throw new EvaluationValidationError('Workspace prompt must not be empty.');
        }
        this.validateTestCase(request.testCase, 'Result evaluation test case');
        this.validateSnapshot(request.snapshot, 'Result evaluation snapshot');
        if (request.snapshot.testCaseId !== request.testCase.id) {
          throw new EvaluationValidationError(
            'Result evaluation snapshot testCaseId must match testCase.id.'
          );
        }
        if (this.isImageText2ImageMode(request) && !this.hasSnapshotOutputMedia(request.snapshot)) {
          throw new EvaluationValidationError(
            'Image result evaluation requires at least one output image evidence item.'
          );
        }
        break;

      case 'compare':
        if (!request.target?.workspacePrompt?.trim()) {
          throw new EvaluationValidationError('Workspace prompt must not be empty.');

View on GitHub (pinned to 3e677b1d9f)

Solutions

1. Extract the text after 'Message optimization failed: ' and fix the root cause it names (401 → credentials, timeout → retry, template/model → config).
2. Pre-validate the request (ids, messages, modelKey) so only genuine runtime failures reach this wrapper.
3. Log the full error object, not just the message, to preserve stack context.
4. Retry transient causes (network/timeout) with a single retry and backoff.

Example fix

// before
catch (e) { showError(String(e)); }

// after
catch (e) {
  const msg = e instanceof Error ? e.message : String(e);
  const cause = msg.startsWith('Message optimization failed:') ? msg.split(':').slice(1).join(':').trim() : msg;
  if (/timeout|network|fetch/i.test(cause)) return retryLater();
  showError(cause);
}

// pre-validate everything the service checks internally
const ok = req.selectedMessageId?.trim()
  && req.messages?.length
  && req.messages.some(m => m.id === req.selectedMessageId && m.content?.trim())
  && await modelManager.getModel(req.modelKey);
if (!ok) throw new Error('Request invalid');

function isOptimizationError(e: unknown): e is OptimizationError { return e instanceof OptimizationError; }
function rootCause(e: unknown): string {
  const m = e instanceof Error ? e.message : String(e);
  return m.replace(/^Message optimization failed:\s*/, '');
}

try { return await svc.optimizeMessage(req); }
catch (e) { const cause = rootCause(e); if (/timeout|network|fetch/i.test(cause)) return retryWithBackoff(req); showError(cause); }

When it happens

Trigger: Any mid-pipeline failure in the message-optimization flow — provider auth errors, network failures, empty LLM responses, missing templates — all rethrown under this wrapper.

Common situations: Invalid/expired API keys, offline clients, template manager misconfiguration, or the inner validation errors above when callers don't pre-validate; the flattened message hides the error class, complicating diagnostics.

Related errors

• Evaluation mode configuration must not be empty.
• DATA_ERROR_CODES.ELECTRON_API_UNAVAILABLE
• Data must be an object
• "data" property is missing or not an object
• Unrecognized data structure

AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27). Data as JSON: /api/errors/9cf4973c75f64fe0. Report an issue: GitHub.