[Pydantic AI] Add support for OpenAI GPT Image 2 model

### Question Hello, this is question/feature request to add support for new `gpt-image-2` model from OpenAI: https://developers.openai.com/api/docs/models/gpt-image-2 - Are there any plans or ongoing work to add support for the new model? - Is there a way/hack to use it today? I've tried to run the code like this, but it doesn't work: ```python from pydantic_ai import Agent, BinaryImage agent = Agent('openai:gpt-image-2', output_type=BinaryImage) agent.model.profile.supports_image_output = True # manually setting support for image output result = agent.run_sync('Generate an image of an axolotl.') ``` This results in error on the server side, so I'm assuming request content is unexpected for OpenAI ``` pydantic_ai.exceptions.ModelHTTPError: status_code: 500, model_name: gpt-image-2, body: {'message': 'The server had an error while processing your request. Sorry about that!', 'type': 'server_error', 'param': None, 'code': None} ``` Would appreciate any information or help! ### Addit