Skip to content

Print known/supported models when provider configuration fails with "The requested model is not supported." error #2545

@erawhctim

Description

@erawhctim

Please explain the motivation behind the feature request.
Sometimes its hard to know the exact value to enter for a given provider's supported AI models. For example, when using GH Copilot, their docs list out the "marketing names" of the supported models, but Goose expects a different set of Strings to identify the models.

For example, if I want to use "Claude 3.7 Sonnet", I have to configure the provider in Goose with the value claude-3-7-sonnet instead.

Image

It's not impossible to figure that out, but providing more detail in the configuration in Goose could help onboard new users and eliminate some friction getting things installed and running.

Describe the solution you'd like
It would be nice if Goose could print out all the supported model Strings for a given provider if the configuration process fails with a 400 error/"The requested model is not supported." error.

The downside is I'm not sure if there's a consistent error status code or message to key off of that denotes this specific error scenario. It might be hard to generalize across all providers.

Describe alternatives you've considered
Looking up the model names in the goose source 🙂 (not too hard)

Additional context
Add any other context or screenshots about the feature request here.

  • I have verified this does not duplicate an existing feature request

Metadata

Metadata

Assignees

Labels

enhancementNew feature or requestonboardingSetup/configuration/first-time user experiencep2Priority 2 - Medium

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions