"""Recover eval records a run's log emitted but its loss-series artefact dropped.

Written because the seed-1 pilot's LossLog callback filtered on `"loss" in logs`,
which excludes every eval record (Trainer emits `eval_loss` with no `loss` key).
The data was never lost -- it was printed and not collected -- so it is parsed
back out of the log rather than re-run. Idempotent: existing eval points are not
duplicated.
"""
import ast, json, re, sys
from pathlib import Path

log, series = Path(sys.argv[1]), Path(sys.argv[2])
s = json.loads(series.read_text())
have = {p["step"] for p in s if "eval_loss" in p}
found = []
for m in re.finditer(r"\{[^{}]*'eval_loss'[^{}]*\}", log.read_text(errors="replace")):
    try:
        d = ast.literal_eval(m.group(0))
    except Exception:
        continue
    d = {k: (float(v) if isinstance(v, str) and re.fullmatch(r"-?[\d.eE+]+", v) else v)
         for k, v in d.items()}
    found.append(d)
# Trainer logs eval without a step field; epoch is present, so derive step order.
added = 0
for i, d in enumerate(found):
    if d.get("epoch") is None:
        continue
    step = d.get("step")
    if step is None:
        after = [p["step"] for p in s if "loss" in p and p.get("epoch", 0) <= d["epoch"]]
        step = max(after) if after else 0
    if step in have:
        continue
    s.append({"step": step, **d}); have.add(step); added += 1
s.sort(key=lambda p: (p["step"], "eval_loss" in p))
series.write_text(json.dumps(s, indent=1))
print(f"  recovered {added} eval records from {log.name} ({len(found)} found in log)")