Skip to content

Conversation

dan-nicholls
Copy link

With the recent releases of the gpt-5, gpt-5-mini and gpt-5-nano models, along with the o4-mini models referenced in #692 , a custom temperature value isn't support and thus all require a temperate value of 1. Currently the application throws an error if the default 0 value is used.

This PR introduces a DEFAULT_TEMPERATURE to the config so that if you already set a default model, you then don't need to use the --temperature flag every call.

@KoenLemmen
Copy link

KoenLemmen commented Sep 8, 2025

Woudn't this also require

temperature: float = typer.Option(
        cfg.get("DEFAULT_TEMPERATURE"),
        min=0.0,
        max=2.0,
        help="Randomness of generated output.",
    ),

In app.py

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants