An improved copy: the function (or a teacher model) runs on rows with known
answers, and the runs the metric accepts become worked examples, whole turns
included (reasoning, tool calls). Labeled rows fill the rest, up to
maxLabeled. The function is unchanged.
An improved copy: the function (or a teacher model) runs on rows with known answers, and the runs the metric accepts become worked examples, whole turns included (reasoning, tool calls). Labeled rows fill the rest, up to
maxLabeled. The function is unchanged.