Extending OpenAI Response API for Better Text Output Usability

Is there plan to extend the semantics to response API from openai? E.g. I'm using openai-agents sdk with openinference-instrumentation-openai-agents for a tool that just returns text, but the agents sdk would wrap it inside {"type": .., "text": ..., "annotation": ..} , which makes it hard to read on phoenix. I assume it's due to the response api as it matches the structure from response example on https://platform.openai.com/docs/api-reference/responses/create. I'm already using agents.OpenAIChatCompletionsModel in my code, but it looks the agents SDK converts the chat completion format to response format somehow internally.