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

Same contract as the lv-hemingway sibling — the arm NAMES are the only real difference,
and the control must carry the substring `unadapted` or voice_distance.py cannot identify
it and prints an empty vs-control table instead of an error.

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"
  - 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-mccarthy/corpus-renamed/copies")
EVAL = Path("/home/infra-ops/r49-runs/mccarthy-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)

# Arms are DISCOVERED, not listed. AMENDMENT 3 added two and a hardcoded dict would have
# silently dropped them from the voice table while every other axis scored them -- the arm
# would be missing rather than failing, which is the worse of the two.
found = sorted(EVAL.glob("beats5.*.jsonl"))
if not found:
    print(f"== REFUSING: no beats5.*.jsonl in {EVAL}")
    sys.exit(1)
NAMES = {}
for f in found:
    arm = f.stem.replace("beats5.", "")
    NAMES[arm] = "base-unadapted" if arm == "base" else arm
if "base-unadapted" not in NAMES.values():
    print("== REFUSING: no `base` arm, so voice_distance would have no control to compare against")
    sys.exit(1)
print(f"arms discovered: {', '.join(sorted(NAMES))}")
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")