Need help : Schema nesting depth error when using Gemini models via @ai-sdk/openai package

[Nilesh9106]

When using the Portkey OpenAI-compatible gateway to call Gemini models, complex JSON schemas trigger a Google API error: "A schema in GenerationConfig in the request exceeds the maximum allowed nesting depth."
The schema provided has 4 levels of nesting . While this is technically within Gemini's limit, the OpenAI-to-Gemini translation layer in Portkey likely wraps the schema in additional object properties. This same code works fine when used @ai-sdk/google package.

I am not able to use the gemini model because of this, I cant use portkey for some of the model and direct provider for some of the models. either use portkey for all or dont use.

Relevant Code Snippet

// This configuration fails via Portkey's OpenAI wrapper
const model = createOpenAI({
  baseURL: 'https://api.portkey.ai',
  apiKey: config.portkey.apiKey,
  headers: { 'x-portkey-metadata': metadata },
})(`${config.portkey.googleProvider}/${modelName}`);

const schema = z.object({
  tasks: z.array( // Level 1
    z.object({
      title: z.string(),
      stories: z.array( // Level 2
        z.object({
          title: z.string(),
          acceptance_criteria: z.array(z.string()), // Level 3/4
          figma_frame_image_urls: z.array(z.string()), // Level 3/4
        }),
      ),
    }),
  ),
});

// Error occurs here
const { object } = await generateObject({
  model,
  schema,
  prompt: "...",
});

[aniruddhaadak80]

This feels like one of those cases where an OpenAI-compatible surface is close enough for simple calls but not neutral for advanced structured generation. If Portkey adds wrapper fields or transforms the schema before it reaches Gemini, the effective nesting depth can exceed what your original zod schema suggests.nnIt would help if the team exposed the translated payload or documented provider-specific schema limits after transformation. Without that, users cannot tell whether they need to flatten the schema, switch SDKs, or avoid the compatibility layer for this class of request.