diff --git a/tools/t5_distill_args.py b/tools/t5_distill_args.py index 7a78e5fe6..5b369be2c 100644 --- a/tools/t5_distill_args.py +++ b/tools/t5_distill_args.py @@ -1,7 +1,10 @@ #!/usr/bin/env python3 """tools/t5_distill_args.py — build the R16 distill slate for a Claude wave (P31 S63 T5). -Usage: t5_distill_args.py --wave .run/t5a --wfdir [--label 'P31 S63 t5a'] [--all-arms] +Usage: t5_distill_args.py --wave .run/t5a --wfdir [--wave .run/t5b --wfdir ...] + [--label 'P31 S63'] [--all-arms] [--out ] +--wave/--wfdir may be repeated and are paired POSITIONALLY (the Nth wave with the Nth wfdir), so one +distill run can cover several waves; the slates are concatenated and de-duplicated by (binary, fn). Only BYTE-PROVEN transcripts are distilled (the distiller's contract: "the whole-binary byte-gate ACCEPTED the final draft, so the final body is ground truth"), so the slate = the wave's banked set @@ -16,39 +19,55 @@ REPO = os.path.dirname(os.path.dirname(os.path.abspath(__file__))); os.chdir(REP def main(): ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter) - ap.add_argument('--wave', required=True) - ap.add_argument('--wfdir', required=True, help="the drafting run's transcript dir (holds journal.jsonl + agent-*.jsonl)") + ap.add_argument('--wave', required=True, action='append', + help='wave dir; repeatable, paired positionally with --wfdir') + ap.add_argument('--wfdir', required=True, action='append', + help="the drafting run's transcript dir (holds journal.jsonl + agent-*.jsonl); repeatable") ap.add_argument('--label', default='', help="provenance string for the cookbook header, e.g. 'P31 S63 t5a'") ap.add_argument('--all-arms', action='store_true') ap.add_argument('--out', default='') a = ap.parse_args() - jd = json.load(open(os.path.join(a.wave, 'judge.json'))) - banked_by_arm = {arm: set(v.get('banked', [])) for arm, v in jd.get('arms', {}).items()} - banked = set().union(*banked_by_arm.values()) if banked_by_arm else set() - union = set(jd.get('union', {}).get('banked', [])) - picked = jd.get('union', {}).get('picked', {}) - jp = os.path.join(a.wfdir, 'journal.jsonl') - if not os.path.exists(jp): sys.exit('no journal.jsonl in %s' % a.wfdir) - rows = [json.loads(l) for l in open(jp) if l.strip()] - tr = {} - for r in rows: - res = r.get('result') or {} - if isinstance(res, dict) and res.get('fn'): - tr[(res['fn'], res.get('arm'))] = (os.path.join(a.wfdir, 'agent-%s.jsonl' % r['agentId']), res.get('note', '')) - out, missing = [], [] - for fn in sorted(banked): - arms = sorted(banked_by_arm) if a.all_arms else [picked.get(fn) or next(x for x in banked_by_arm if fn in banked_by_arm[x])] - for arm in arms: - if fn not in banked_by_arm.get(arm, ()): continue - hit = tr.get((fn, arm)) - if not hit or not os.path.exists(hit[0]): missing.append('%s/%s' % (arm, fn)); continue - out.append({'fn': fn, 'arm': arm, 'transcript': hit[0], 'note': hit[1]}) - print('banked %d (union-gated %d); transcripts found %d; label %r' % (len(banked), len(union), len(out), a.label)) + if len(a.wave) != len(a.wfdir): + sys.exit('REFUSED: %d --wave but %d --wfdir; they pair positionally' % (len(a.wave), len(a.wfdir))) + out, missing, seen, tot_banked, tot_union = [], [], set(), 0, 0 + for wave, wfdir in zip(a.wave, a.wfdir): + jp = os.path.join(wave, 'judge.json') + if not os.path.exists(jp): + print('SKIP %s: no judge.json (wave not gated yet)' % wave); continue + jd = json.load(open(jp)) + banked_by_arm = {arm: set(v.get('banked', [])) for arm, v in jd.get('arms', {}).items()} + banked = set().union(*banked_by_arm.values()) if banked_by_arm else set() + union = set(jd.get('union', {}).get('banked', [])) + picked = jd.get('union', {}).get('picked', {}) + tot_banked += len(banked); tot_union += len(union) + T = {t['name']: t for t in json.load(open(os.path.join(wave, 'targets.json')))} + jl = os.path.join(wfdir, 'journal.jsonl') + if not os.path.exists(jl): + sys.exit('no journal.jsonl in %s' % wfdir) + tr = {} + for line in open(jl): + if '"result"' not in line: continue + r = json.loads(line); res = r.get('result') or {} + if isinstance(res, dict) and res.get('fn'): + tr[(res['fn'], res.get('arm'))] = (os.path.join(wfdir, 'agent-%s.jsonl' % r['agentId']), res.get('note', '')) + for fn in sorted(banked): + arms = sorted(banked_by_arm) if a.all_arms else [picked.get(fn) or next(x for x in banked_by_arm if fn in banked_by_arm[x])] + for arm in arms: + if fn not in banked_by_arm.get(arm, ()): continue + key = (T.get(fn, {}).get('binary', '?'), fn, arm) + if key in seen: continue # the same fn can be drawn by two waves (R48: key by binary too) + seen.add(key) + hit = tr.get((fn, arm)) + if not hit or not os.path.exists(hit[0]): + missing.append('%s/%s/%s' % (os.path.basename(wave), arm, fn)); continue + out.append({'fn': fn, 'arm': arm, 'transcript': hit[0], 'note': hit[1]}) + print('waves %d; banked %d (union-gated %d); transcripts found %d; label %r' + % (len(a.wave), tot_banked, tot_union, len(out), a.label)) if missing: print('NO TRANSCRIPT for %d banked draft(s) — NOT distilled (R32, reported not skipped): %s' % (len(missing), ' '.join(missing[:20]))) - p = a.out or os.path.join(a.wave, 'distill_args.json') - json.dump({'targets': out, 'label': a.label or os.path.basename(a.wave.rstrip('/'))}, open(p, 'w'), indent=1) + p = a.out or os.path.join(a.wave[0], 'distill_args.json') + json.dump({'targets': out, 'label': a.label or os.path.basename(a.wave[0].rstrip('/'))}, open(p, 'w'), indent=1) print('wrote %s' % p) if __name__ == '__main__': main()