"""Adapt the lv-hemingway arms for voice_distance.py, and refuse if its reference is empty.

voice_distance.py expects:
  - files matching voice.<arm>.jsonl in the eval dir
  - a `continuation` field per record (gen_beats_chat writes `raw`)
  - a `seed` field (present)
  - the control arm's NAME to contain the substring "unadapted" -- it picks the
    control by that substring, so `base` alone would leave the control
    unidentified and the whole vs-control table would silently be empty.
  - a reference built from corpus records whose split == "val"
"""
import json, sys
from collections import Counter
from pathlib import Path

CORP = Path("/home/infra-ops/lv-hemingway/corpus-renamed/copies")
EVAL = Path("/home/infra-ops/r49-runs/hemingway-eval")

c = Counter()
n = 0
for p in sorted(CORP.glob("*.jsonl")):
    for line in p.read_text(encoding="utf-8").splitlines():
        if not line.strip():
            continue
        r = json.loads(line)
        n += 1
        c[r.get("split")] += 1
print(f"corpus records: {n}  split values: {dict(c)}")
if c.get("val", 0) == 0:
    print("== REFUSING: no split=val records; voice_distance would build an EMPTY reference")
    print("   and every delta_cb would be meaningless rather than absent.")
    sys.exit(1)

NAMES = {"base": "base-unadapted", "ckpt1750": "ckpt1750", "ckpt850": "ckpt850"}
for src_arm, out_arm in NAMES.items():
    src = EVAL / f"beats5.{src_arm}.jsonl"
    if not src.exists():
        print(f"== missing {src}")
        sys.exit(1)
    rows = [json.loads(l) for l in src.read_text(encoding="utf-8").splitlines() if l.strip()]
    out = EVAL / f"voice.{out_arm}.jsonl"
    with out.open("w", encoding="utf-8") as fh:
        for r in rows:
            fh.write(json.dumps({"id": r["id"], "seed": r["seed"],
                                 "continuation": r["raw"]}, ensure_ascii=False) + "\n")
    print(f"  {src.name} -> {out.name}  ({len(rows)} records)")
print("ready")