linshenkx/prompt-optimizer · error · EvaluationValidationError

Evaluation mode configuration must not be empty.

Error message

Evaluation mode configuration must not be empty.

What it means

Catch-all OptimizationError thrown at the end of optimizePrompt: any error raised inside the method (validation, model lookup, template resolution, LLM call, response validation) is re-wrapped as 'Optimization failed: <original message>'. The original message is embedded, so the underlying cause is discoverable from the string.

Source

Thrown at packages/core/src/services/evaluation/service.ts:458

      callbacks.onError(
        new EvaluationExecutionError(
          this.formatExecutionErrorMessage(error),
          error instanceof Error ? error : undefined
        )
      );
    }
  }

  /**
   * 验证评估请求
   */
  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.'

View on GitHub (pinned to 3e677b1d9f)

Solutions

1. Parse the suffix after 'Optimization failed: ' to get the real cause (e.g. '401 Unauthorized' means check API key; timeout means retry).
2. Enable request/transport logging on the LLM service to see the raw failure.
3. Fix the root cause per the embedded message: credentials, connectivity, model availability, or template config.
4. Avoid catching and stringifying errors yourself — check for typed errors (OptimizationError preserves only the message here) and log full context.

Example fix

// before
try { await promptService.optimizePrompt(req); }
catch (e) { console.error(String(e)); }

// after
try { await promptService.optimizePrompt(req); }
catch (e) {
  const cause = e instanceof Error && e.message.startsWith('Optimization failed:')
    ? e.message.slice('Optimization failed:'.length).trim()
    : String(e);
  console.error('Root cause:', cause);
}

if (!providerConfig.apiKey) throw new Error('Missing API key');
if (!(await modelManager.getModel(req.modelKey))) throw new Error('Model not found');

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(/^Optimization failed:\s*/, '');
}

try { return await svc.optimizePrompt(req); }
catch (e) { const cause = rootCause(e); if (/401|unauthorized/i.test(cause)) refreshCredentials(); else if (/timeout|network/i.test(cause)) return retry(); else throw e; }

When it happens

Trigger: Any failure inside optimizePrompt that isn't rethrown with its own type — LLM provider network error, timeout, image-understanding service missing, template errors — all surface as this wrapped message.

Common situations: API key invalid/expired causing provider 401, network offline, template manager not initialized, rate limits — anything mid-pipeline; developers lose the error class because it's flattened into a message string.

Related errors

• Workspace prompt must not be empty.
• Evaluation model key must not be empty.
• Iteration requirement must not be empty.
• ${label} promptText must not be empty.
• Failed to add favorite: ${errorMessage}

AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27). Data as JSON: /api/errors/91c4ad0b06fe88fc. Report an issue: GitHub.