#!/usr/bin/env python3
"""Run a small qualitative eval suite and write a JSON report."""

from __future__ import annotations

import argparse
import json
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / "src"))

from weather_llm.config_loader import repo_root_from
from weather_llm.eval.harness import run_eval_suite, write_report


def main() -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--model_dir", type=Path, required=True)
    ap.add_argument("--out", type=Path, default=None)
    args = ap.parse_args()
    root = repo_root_from(ROOT)
    out = args.out or (root / "outputs/eval_report.json")
    report = run_eval_suite(args.model_dir.resolve())
    write_report(out, report)
    print(json.dumps(report, indent=2, ensure_ascii=False))
    return 0 if report["passed"] == report["total"] else 1


if __name__ == "__main__":
    raise SystemExit(main())