Skip to content

Conversation

@TypeDefinition
Copy link

@TypeDefinition TypeDefinition commented Oct 27, 2025

Assistant messages must now be type output_text instead of input_text

Adding this overload allows the user to do

new Message(OpenAI.Role.Assistant, new OpenAI.Responses.TextContent(message, ResponseContentType.OutputText));

in order to create an assistant message.

@StephenHodgson
Copy link
Member

Output Text is only generated by the model.

Lets create a discussion first to understand how to best go about what it is you're trying to do, then propose changes :)

@StephenHodgson
Copy link
Member

by the way, I've got the GA refactor for realtime planned:

I know that they changed a bunch of stuff, but it shouldn't break any existing things unless you add the GA header to the requests

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Development

Successfully merging this pull request may close these issues.

2 participants