Function fetch_model_catalog 

pub async fn fetch_model_catalog(
    base_url: &str,
    token: &str,
) -> Result<ModelCatalog, CompletionError>

Fetches a [ModelCatalog] from the Gateway’s /models endpoint.

base_url is the root of the Gateway’s OpenAI-compatible API, for example http://127.0.0.1:8081/v1. The request sends token as a bearer token.

Errors

Returns a CompletionError. Its kind is:

• Transport or Timeout when the HTTP request or a response read fails;
• the kind classify_http_failure picks for the response when the Gateway returns a status outside the 2xx range;
• MalformedResponse when the body is not a valid model list.