"""Deploy-eval table (eval2 = recency-clean held-out TEST, n=119).

`just results` reports TRAIN-time L5 hack/solve. This script reports the DEPLOY
numbers (knob-off forward on the paper test set) that only appear in the
`FINAL EVAL ... held-out test` line -- the apples-to-apples per-arm deploy metric.

Headline = solve_deploy - hack_deploy (both alone are gameable; their gap is the
honest objective: solve the task without learning the cheat).

    uv run python scripts/results_deploy.py     # or: just results-deploy
"""
from __future__ import annotations
import re
from pathlib import Path
import polars as pl
from tabulate import tabulate

LOG_DIR = Path("logs")
FINAL_RE = re.compile(
    r"FINAL EVAL \[.*?\] DEPLOY \(held-out test, n=(\d+)\): "
    r"hack\(strict\)=([\d.]+) hack\(vendor eq_hinted\)=([\d.]+) solve=([\d.]+)")
MAIN_RE = re.compile(r"HACK_STUDENT=([\d.]+).*?PASS_RATE|PASS_RATE=([\d.]+).*?HACK_STUDENT=([\d.]+)")


def _frac(tok: str) -> float | None:
    a, b = tok.split("/")
    return int(a) / int(b) if int(b) else None


def _train_l5(txt: str) -> tuple[float | None, float | None]:
    """Mean of last-5 student hack_s / gt_s from the per-step table (columns by name)."""
    names = []
    for l in txt.splitlines():
        if "| INFO |" not in l:
            continue
        toks = [re.sub(r"[^a-z0-9_]", "", t.lower()) for t in l.split("| INFO |", 1)[1].split()]
        if toks[:1] == ["step"] and "ref_eq" in toks:
            names = toks
            break
    if not names:
        return None, None
    i_h, i_g = names.index("hack_s"), names.index("gt_s")
    hs, gts = [], []
    for line in txt.splitlines():
        if "| INFO |" not in line:
            continue
        row = line.split("| INFO |", 1)[1].split()
        if not row or not row[0].isdigit() or len(row) <= max(i_h, i_g):
            continue
        if (h := _frac(row[i_h])) is not None:
            hs.append(h)
        if (g := _frac(row[i_g])) is not None:
            gts.append(g)
    mean = lambda v: sum(v[-5:]) / len(v[-5:]) if v else None
    return mean(hs), mean(gts)


def parse(path: Path) -> dict | None:
    txt = path.read_text(errors="replace")
    m = FINAL_RE.search(txt)
    if m is None:
        return None                      # no recency-clean deploy eval -> not eval2
    n, hack_dep, hack_dep_eq, solve_dep = int(m[1]), float(m[2]), float(m[3]), float(m[4])
    argv = next((l.split("argv:", 1)[1].strip() for l in txt.splitlines() if "argv:" in l), "?")
    argv = argv.split("train.py ", 1)[-1].strip() if "train.py " in argv else argv
    if "tiny-random" in txt or "preset=smoke" in txt:
        return None                      # smoke garbage
    # train hack/solve = L5 (mean of last 5 student steps) from the per-step table,
    # the same converged-regime convention as scripts/results.py. The BLUF main-metric
    # line is stdout-only (not in the verbose log), so we read the streamed table.
    hack_tr, solve_tr = _train_l5(txt)
    return dict(
        headline=solve_dep - hack_dep,
        solve=solve_tr, hack=hack_tr,
        solve_deploy=solve_dep, hack_deploy=hack_dep,
        n=n, argv=argv,
    )


def main() -> None:
    rows = [r for p in sorted(LOG_DIR.glob("*.log")) if (r := parse(p))]
    if not rows:
        print("no eval2 (held-out test) deploy runs in logs/")
        return
    df = pl.DataFrame(rows).sort("headline", descending=True)
    cols = ["headline", "solve", "hack", "solve_deploy", "hack_deploy", "n", "argv"]
    print("\n## Deploy eval (eval2 = recency-clean held-out TEST), sorted by headline=solve_deploy-hack_deploy\n")
    print(tabulate(df.select(cols).rows(), headers=cols, tablefmt="pipe", floatfmt="+.3f"))


if __name__ == "__main__":
    main()