Regarding parameter error issues

According to the source code, the corresponding model is currently called for processing using a third-party openai-compatible apikey, but the following problems occur. How should they be solved?

APICallError [AI_APICallError]: <400> InternalError.Algo.InvalidParameter: 'messages' must contain the word 'json' in some form, to use 'response_format' of type 'json_object'. at (/Users/xxx/test-py/deep-research/node_modules/@ai-sdk/provider-utils/src/response-handler.ts:59:16) at process.processTicksAndRejections (node:internal/process/task_queues:105:5) at async postToApi (/Users/xxx/test-py/deep-research/node_modules/@ai-sdk/provider-utils/src/post-to-api.ts:81:28) at async OpenAIChatLanguageModel.doGenerate (/Users/xxx/test-py/deep-research/node_modules/@ai-sdk/openai/src/openai-chat-language-model.ts:367:50) at async fn (/Users/xxx/test-py/deep-research/node_modules/ai/core/generate-object/generate-object.ts:489:32) at async (/Users/xxx/test-py/deep-research/node_modules/ai/core/telemetry/record-span.ts:18:22) at async _retryWithExponentialBackoff (/Users/xxx/test-py/deep-research/node_modules/ai/util/retry-with-exponential-backoff.ts:36:12) at async fn (/Users/xxx/test-py/deep-research/node_modules/ai/core/generate-object/generate-object.ts:457:34) at async (/Users/xxx/test-py/deep-research/node_modules/ai/core/telemetry/record-span.ts:18:22) at async generateFeedback (/Users/xxx/test-py/deep-research/src/feedback.ts:14:24) { cause: undefined,