get_log_context

gepa.optimize_anything.get_log_context() -> LogContext

Return the active log context for the current evaluator call.

Use this to propagate oa.log() capture to child threads spawned inside your evaluator::

import threading
import gepa.optimize_anything as oa

def my_evaluator(candidate):
    ctx = oa.get_log_context()

    def worker():
        oa.set_log_context(ctx)
        oa.log("from child thread")

    t = threading.Thread(target=worker)
    t.start()
    t.join()
    oa.log("from main evaluator thread")
    return score

Raises:

Type	Description
RuntimeError	If called outside an evaluator invocation.

Source code in gepa/optimize_anything.py

def get_log_context() -> LogContext:
    """Return the active log context for the current evaluator call.

    Use this to propagate ``oa.log()`` capture to child threads spawned
    inside your evaluator::

        import threading
        import gepa.optimize_anything as oa

        def my_evaluator(candidate):
            ctx = oa.get_log_context()

            def worker():
                oa.set_log_context(ctx)
                oa.log("from child thread")

            t = threading.Thread(target=worker)
            t.start()
            t.join()
            oa.log("from main evaluator thread")
            return score

    Raises:
        RuntimeError: If called outside an evaluator invocation.
    """
    ctx = _get_log_context()
    if ctx is None:
        raise RuntimeError(
            "No active log context. get_log_context() must be called inside an evaluator passed to optimize_anything()."
        )
    return ctx