linshenkx/prompt-optimizer · error · RequestConfigError

Model is not enabled

Error message

Model is not enabled

What it means

Thrown by validateRequest when modelConfig.enabled is falsy. The service only executes enabled models; a disabled config (user toggled it off, or imported with enabled:false) is rejected before any network call.

Source

Thrown at packages/core/src/services/image-understanding/service.ts:59

    if (!request || typeof request !== 'object') {
      throw new RequestConfigError('Image understanding request cannot be empty')
    }

    const modelConfig = request.modelConfig
    if (!modelConfig) {
      throw new RequestConfigError('Model config cannot be empty')
    }

    if (!modelConfig.providerMeta?.id) {
      throw new RequestConfigError('Model provider metadata cannot be empty')
    }

    if (!modelConfig.modelMeta?.id) {
      throw new RequestConfigError('Model metadata cannot be empty')
    }

    if (!modelConfig.enabled) {
      throw new RequestConfigError('Model is not enabled')
    }
  }

  private async prepareRuntimeRequest(
    request: ImageUnderstandingExecutionRequest
  ): Promise<ImageUnderstandingExecutionRequest> {
    const images = await normalizeImageInputsForLlm(request.images, this.imageInputOptions)
    return {
      ...request,
      images: images ?? request.images,
    }
  }
}

export function createImageUnderstandingService(
  options: CreateImageUnderstandingServiceOptions = {}
): IImageUnderstandingService {
  return new ImageUnderstandingService(options)

View on GitHub (pinned to 3e677b1d9f)

Solutions

1. Enable the model via the model manager / settings UI before calling understand().
2. When creating configs programmatically, set enabled: true explicitly.
3. Filter candidate models to enabled ones before building the request.

Example fix

// before
modelConfig = { providerMeta: { id: 'x' }, modelMeta: { id: 'y' }, enabled: false }
await service.understand({ modelConfig, ... })

// after
await modelManager.setEnabled('x', 'y', true)
await service.understand({ modelConfig: await modelManager.getEnabledModel('x','y'), ... })

const cfg = request.modelConfig
if (!cfg.enabled) {
  cfg.enabled = true // or pick another enabled model
}

const isEnabledModel = (c: any): boolean => Boolean(c?.enabled) && Boolean(c?.modelMeta?.id) && Boolean(c?.providerMeta?.id)

When it happens

Trigger: Calling understand/understandStream with a config whose enabled flag is false or undefined; using a model the user disabled in settings; freshly imported configs defaulting to disabled.

Common situations: UI toggle state out of sync with the code path that picks the model; importing configs where enabled was not carried over; new configs created without setting enabled: true.

Related errors

• Data must be an object
• Model config cannot be empty
• Model provider metadata cannot be empty
• Model metadata cannot be empty
• Model provider metadata cannot be empty

AI-assisted analysis of linshenkx/prompt-optimizer@3e677b1d9f (2026-08-27). Data as JSON: /api/errors/a6e1c6210df66640. Report an issue: GitHub.