From 25e51c5b30d987044089194b06ef85cf3fbc19b1 Mon Sep 17 00:00:00 2001 From: sora <2075279110@qq.com> Date: Mon, 14 Sep 2026 03:48:01 +0000 Subject: [PATCH] Scoring milestones: only when no live bar The bar's 'scoring N/164' counter and 21 milestone log lines were both active on terminals -- the lines are noise there. Emit them only for pipes/redirects where no bar exists (every ~10% now). Co-Authored-By: Claude --- evalharness/cli.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/evalharness/cli.py b/evalharness/cli.py index 40dfd34..1064197 100644 --- a/evalharness/cli.py +++ b/evalharness/cli.py @@ -720,11 +720,13 @@ def _cmd_eval_run(args) -> int: for minutes with zero feedback otherwise (bar sits at 'generating 100%' and looks hung).""" if _reporter is not None: + # live terminal: the bar carries the counter -- log + # lines here are pure noise (21 lines per bench) _reporter.set_phase(f'scoring {done}/{total_s}') - # milestone lines: FIRST completion reports immediately - # (docker-slow runs otherwise look frozen for minutes), - # then every ~5% - step = max(1, total_s // 20) if total_s else 1 + return + # pipes/redirects (no live bar): milestone lines instead, + # first completion immediately then every ~10% + step = max(1, total_s // 10) if total_s else 1 if _cb and (done == 1 or done % step == 0 or done == total_s): _cb(f'Scoring {done}/{total_s} samples')