Skip to content

Conversation

@dsfaccini
Copy link
Collaborator

@dsfaccini dsfaccini commented Dec 9, 2025

system_prompt and instructions do provide different behaviors, so I didn't replace all instances, but I tried replacing all that weren't specifically targeting that difference

@github-actions
Copy link

github-actions bot commented Dec 9, 2025

Docs Preview

commit: cdf6ed4
Preview URL: https://7b594f96-pydantic-ai-previews.pydantic.workers.dev

provider = OpenAIProvider(api_key=openai_api_key)
m = OpenAIResponsesModel('gpt-5', provider=provider)
settings = OpenAIResponsesModelSettings(openai_reasoning_effort='high', openai_reasoning_summary='detailed')
agent = Agent(m, system_prompt='You are a helpful assistant.', model_settings=settings)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If we're going to edit tests that have cassettes, we should re-record the cassettes.

Note that I'd be OK only updating this in the docs (for now).

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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants