"""Minimal OptimalStopControl threshold calibration — valid-window grid search.

This repo found OptimalStopControl thresholds overfit the valid window (valid
+7.5% → test −17.7% on one calibration). This script runs a small grid over
(entry_pct, exit_pct, max_hold_days) on the VALID window, reports per-config
excess return + turnover, and warns when the best valid config is a spike.

Reference repo impl: tac-qlib/examples/run_optstop_compare.py.

    python examples/run_optstop_compare.py --universe AAPL,MSFT,QQQ
"""

from __future__ import annotations

import argparse
import itertools
import os

import pandas as pd


GRID = {
    "entry_pct": [0.7, 0.85, 0.95],
    "exit_pct": [0.5, 0.7],
    "max_hold_days": [5, 10],
}


def evaluate_config(lake_root: str, universe: list[str], window: tuple, config: dict) -> dict:
    """Simplified stand-in: train the RankIC model, backtest OptimalStopControl
    on `window`, return (ann_excess_return, turnover, max_drawdown).

    The real repo impl calls qlib.backtest with the strategy and reads
    report_normal.csv + risk.csv. Keep the interface here so the grid loop is
    reusable.
    """
    # placeholder — plug in the real backtest here
    return {"ann_excess": 0.0, "turnover": 0.0, "max_dd": 0.0}


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--lake-root", default=os.environ.get("TAC_LAKE_DIR", ""))
    ap.add_argument("--universe", default="AAPL,MSFT,QQQ,IVV,SMH,TLT")
    args = ap.parse_args()
    universe = [s.strip().upper() for s in args.universe.split(",")]
    valid = ("2026-06-01", "2026-06-30")
    test = ("2026-07-01", "2026-08-06")

    keys = list(GRID)
    results = []
    for combo in itertools.product(*[GRID[k] for k in keys]):
        config = dict(zip(keys, combo))
        v = evaluate_config(args.lake_root, universe, valid, config)
        t = evaluate_config(args.lake_root, universe, test, config)
        results.append({**config, "valid_excess": v["ann_excess"], "test_excess": t["ann_excess"]})

    df = pd.DataFrame(results).sort_values("valid_excess", ascending=False)
    print(df.head(10).to_string(index=False))
    # Overfit check: how far is the best-valid config from the median test config?
    med = df["test_excess"].median()
    best = df.iloc[0]
    print(f"\nmedian test excess: {med:+.3f} | best-valid test excess: {best['test_excess']:+.3f}")
    if abs(best["test_excess"] - med) > 0.10:
        print("WARNING: best-valid config is an outlier on test — likely overfit, prefer robust defaults")


if __name__ == "__main__":
    main()