EasyInputMessage does not support content with "output_text"

[memben]

The OpenAPI raises Issue when using the pydantic model .model_dump for EasyInput Message when simulating assistant <-> user exchange, as the assistant content can only be set to "input_text"

EasyInputMessage:
      type: object
      title: Input message
      description: |
        A message input to the model with a role indicating instruction following
        hierarchy. Instructions given with the `developer` or `system` role take
        precedence over instructions given with the `user` role. Messages with the
        `assistant` role are presumed to have been generated by the model in previous
        interactions.
      properties:
        role:
          type: string
          description: |
            The role of the message input. One of `user`, `assistant`, `system`, or
            `developer`.
          enum:
            - user
            - assistant
            - system
            - developer
        content:
          description: |
            Text, image, or audio input to the model, used to generate a response.
            Can also contain previous assistant responses.
          anyOf:
            - type: string
              title: Text input
              description: |
                A text input to the model.
            - $ref: '#/components/schemas/InputMessageContentList'
        type:
          type: string
          description: |
            The type of the message input. Always `message`.
          enum:
            - message
          x-stainless-const: true
      required:
        - role
        - content

[memben]

I think the right solution would be having EasyInputMessage to be discriminated based on the role type

[memben]

reproduce, create an user and then assistant message here: https://platform.openai.com/chat/edit?models=gpt-5, generate the code here:

from openai import OpenAI
client = OpenAI()

response = client.responses.create(
  model="gpt-5",
  input=[
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "this is right"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "this is wrong"
        }
      ]
    }
  ],
  text={
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  reasoning={
    "effort": "medium",
    "summary": "auto"
  },
  tools=[],
  store=True
)

and the python sdk will start complaining (as the same goes for the Param client gen)