danny-avila/LibreChat · error · Error

Missing required field: prompt

Error message

Missing required field: prompt

What it means

Guard in FluxAPI._call() for the default `generate` action: after the list_finetunes and generate_finetuned branches are skipped, the remaining code path requires `imageData.prompt`. Distinct from the finetuned path which has its own prompt check (error 5).

Source

Thrown at api/app/clients/tools/structured/FluxAPI.js:210

  async _call(data) {
    const { action = 'generate', ...imageData } = data;

    // Use provided API key for this request if available, otherwise use default
    const requestApiKey = this.apiKey || this.getApiKey();

    // Handle list_finetunes action
    if (action === 'list_finetunes') {
      return this.getMyFinetunes(requestApiKey);
    }

    // Handle finetuned generation
    if (action === 'generate_finetuned') {
      return this.generateFinetunedImage(imageData, requestApiKey);
    }

    // For generate action, ensure prompt is provided
    if (!imageData.prompt) {
      throw new Error('Missing required field: prompt');
    }

    let payload = {
      prompt: imageData.prompt,
      prompt_upsampling: imageData.prompt_upsampling || false,
      safety_tolerance: imageData.safety_tolerance || 6,
      output_format: imageData.output_format || 'png',
    };

    // Add optional parameters if provided
    if (imageData.width) {
      payload.width = imageData.width;
    }
    if (imageData.height) {
      payload.height = imageData.height;
    }
    if (imageData.steps) {
      payload.steps = imageData.steps;

View on GitHub (pinned to 5ff282f900)

Solutions

1. Supply a non-empty `prompt` string in the tool arguments for the generate action.
2. Validate the payload before invoking the tool when prompt comes from user input.
3. Re-check the tool's JSON schema so `prompt` is required and the model is steered to emit it.
4. If the caller intended a finetuned run, set `action: 'generate_finetuned'` explicitly.

Example fix

// before
await fluxTool.invoke({ action: 'generate', width: 1024 });

// after
await fluxTool.invoke({ action: 'generate', prompt: 'a neon koi, cinematic', width: 1024 });

function buildFluxGenerateArgs(input) {
  if (typeof input.prompt !== 'string' || !input.prompt.trim()) {
    throw new Error('FluxAPI generate requires a non-empty prompt.');
  }
  return { action: 'generate', ...input };
}

function hasPrompt(arg) {
  return typeof arg?.prompt === 'string' && arg.prompt.trim().length > 0;
}

try {
  await fluxTool.invoke(args);
} catch (e) {
  if (/Missing required field: prompt/.test(e.message)) return 'A prompt is required to generate.';
  throw e;
}

When it happens

Trigger: Calling the Flux tool with `action: 'generate'` (the default when action is omitted) and a payload whose `prompt` field is missing, null, undefined, or empty string.

Common situations: The model emitted tool args without a prompt (e.g., only width/height); a programmatic caller built the payload from optional user input that was empty; action defaulted to 'generate' when the caller intended a different action; schema mismatch between the tool description and what the model produced.

Related errors

• Missing required field: prompt
• Missing required field: prompt
• Missing required field: prompt
• Missing required field: finetune_id for finetuned generation
• Invalid endpoint for finetuned generation. Must be one of: $

AI-assisted analysis of danny-avila/LibreChat@5ff282f900 (2026-08-12). Data as JSON: /api/errors/81d7a8c71f0c4299. Report an issue: GitHub.