#!/usr/bin/env python3
"""Join the live es+sandwich sweep against the deterministic round-trip
buckets → does MT round-trip drift PREDICT grounding loss?

  sweep JSONL (question=es, audit_mode, status)
     ⋈ es_roundtrip.json (es → bucket CLEAN/DRIFT/COLLAPSE)
  → crosstab bucket × audit_mode, plus the MT-engine error rate
    (the concurrency defect the fan-out surfaced) reported separately
    so it doesn't get conflated with the MT-quality signal.
"""
from __future__ import annotations

import json
import sys
from collections import Counter, defaultdict
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
RES = ROOT / "bench" / "qa_results"


def main() -> int:
    sweep_path = Path(sys.argv[1]) if len(sys.argv) > 1 else max(
        RES.glob("2026-*.jsonl"), key=lambda p: p.stat().st_mtime)
    rt = {r["es"]: r for r in json.loads((RES / "es_roundtrip.json").read_text())}
    rows = [json.loads(ln) for ln in sweep_path.read_text().splitlines() if ln.strip()]

    err = [r for r in rows if (r.get("status") or "").startswith(("err", "error"))
           or r.get("audit_mode") is None]
    ok = [r for r in rows if r not in err]
    print(f"sweep: {sweep_path.name}  rows={len(rows)}  "
          f"engine/other ERROR={len(err)} ({len(err)/max(1,len(rows)):.0%})  "
          f"scored={len(ok)}")

    ct = defaultdict(Counter)
    unmatched = 0
    for r in ok:
        b = rt.get(r["question"], {}).get("bucket")
        if b is None:
            unmatched += 1
            continue
        ct[b][r.get("audit_mode") or "?"] += 1
    print("\nbucket × audit_mode (scored rows only):")
    modes = ["STRICT", "HYBRID", "UNGROUNDED", "?"]
    print(f"  {'bucket':<9} " + " ".join(f"{m:>10}" for m in modes) + "   ground%")
    for b in ("CLEAN", "DRIFT", "COLLAPSE"):
        c = ct.get(b, Counter())
        tot = sum(c.values())
        g = c["STRICT"] + c["HYBRID"]
        print(f"  {b:<9} " + " ".join(f"{c[m]:>10}" for m in modes)
              + f"   {g}/{tot}" + (f" ({g/tot:.0%})" if tot else ""))
    if unmatched:
        print(f"  ({unmatched} scored rows had no round-trip match)")
    print("\nreading: if CLEAN grounds >> COLLAPSE, MT round-trip drift "
          "predicts grounding loss — the lever is entity-preserving MT, "
          "not the sandwich architecture.")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())