"""Summarize a JSONL benchmark without interpreting stdout logs as results."""
import argparse
import json
import statistics
from pathlib import Path

parser = argparse.ArgumentParser()
parser.add_argument('files', nargs='+', type=Path)
args = parser.parse_args()
for path in args.files:
    rows = []
    for line in path.read_text().splitlines():
        try:
            rows.append(json.loads(line))
        except ValueError:
            continue
    short = [r for r in rows if r.get('test', '').startswith('short_')]
    summary = {'file': path.name,
               'completed': any(r.get('event') == 'BENCHMARK_PASS' for r in rows),
               'short_decode_tps_median': statistics.median(r['decode_tps_approx'] for r in short) if short else None,
               'short_ttft_s_median': statistics.median(r['ttft_s'] for r in short) if short else None,
               'all_checked_answers_correct': all(r['correct'] for r in rows if 'correct' in r),
               'long': [{k:r[k] for k in ['test','ttft_s','elapsed_s','correct']} for r in rows if r.get('test','').startswith('long_')],
               'concurrency': [r for r in rows if r.get('test') == 'concurrency_summary'],
               'prefix': [r for r in rows if r.get('test','').startswith('prefix_')]}
    print(json.dumps(summary, ensure_ascii=False, indent=2))