#!/usr/bin/env python3 """剥离 MiniMax 内联 段:B 臂 markdown 与 G 臂原始输出统一清洗(保留 raw_* 备审计)。""" import glob, json, re n = 0 for f in glob.glob('results/*/*.json'): if f.endswith('summary.json'): continue r = json.load(open(f)) for mdkey in ('markdown',): md = r.get(mdkey, '') if '' in md: r['raw_' + mdkey] = md r[mdkey] = re.sub(r'.*?\s*', '', md, flags=re.S).strip() r['think_stripped'] = True if mdkey == 'markdown': r['ok'] = bool(r[mdkey]) n += 1 for rk in ('raw_first', 'raw_repair'): rv = r.get(rk, '') if '' in rv: r[rk + '_original'] = rv r[rk] = re.sub(r'.*?\s*', '', rv, flags=re.S).strip() json.dump(r, open(f, 'w'), ensure_ascii=False, indent=1) print('cleaned', n, 'records')