Skip to content

Conversation

@dsfaccini
Copy link
Contributor

@dsfaccini dsfaccini commented Nov 28, 2025

No description provided.

@dsfaccini
Copy link
Contributor Author

there's a flaky outlines test breaking CI :(

openai_names = [f'openai:{n}' for n in get_model_names(OpenAIModelName)]
bedrock_names = [f'bedrock:{n}' for n in get_model_names(BedrockModelName)]
deepseek_names = ['deepseek:deepseek-chat', 'deepseek:deepseek-reasoner']
gateway_names = [
Copy link
Collaborator

Choose a reason for hiding this comment

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

I realize you couldn't see this comment in a private Slack channel, but I responded to Samuel (and he agreed):

Agreed, but if we add just a few per provider, people are definitely gonna ask us “but why not this other one?”, so maybe just include them all?

So we should NOT hard-code this, but dynamically build this based on the known model names of the providers that are known to work with gateway/{provider}

openai_names = [f'openai:{n}' for n in get_model_names(OpenAIModelName)]
bedrock_names = [f'bedrock:{n}' for n in get_model_names(BedrockModelName)]
deepseek_names = ['deepseek:deepseek-chat', 'deepseek:deepseek-reasoner']
gateway_names = (
Copy link
Collaborator

Choose a reason for hiding this comment

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

Could we use the pydantic_ai.providers.gateway.UpstreamProvider type (possibly needs splitting up into 2 so that we don't include the APi types here), and then use those names as keys into a dict of things like {'openai': OpenAIModelName}? That way when we update it in the gateway file, this list will update too

Copy link
Contributor Author

Choose a reason for hiding this comment

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

will check it out

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.

2 participants