shell_gpt
shell_gpt copied to clipboard
feat: add `DEFAULT_TEMPERATURE` to config
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.
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