#!/usr/bin/env python3
"""Compare two versioned Alliance calibration snapshots against the G0 gold pack."""

from __future__ import annotations

import argparse
import json
import sys
from pathlib import Path
from typing import Any


REPO_ROOT = Path(__file__).resolve().parents[1]
API_ROOT = REPO_ROOT / "apps" / "api"
if str(API_ROOT) not in sys.path:
    sys.path.insert(0, str(API_ROOT))

from app.contracts.measurement import BenchmarkCase  # noqa: E402
from app.services.alliance_calibration import (  # noqa: E402
    AllianceCalibrationSnapshot,
    compare_alliance_snapshots,
    gold_reference_snapshot,
    render_alliance_comparison_markdown,
)


def _read_json(path: Path) -> Any:
    return json.loads(path.read_text(encoding="utf-8"))


def main() -> int:
    parser = argparse.ArgumentParser()
    parser.add_argument("--baseline", type=Path)
    parser.add_argument("--gold-baseline", action="store_true")
    parser.add_argument("--candidate", type=Path, required=True)
    parser.add_argument(
        "--benchmark",
        type=Path,
        default=API_ROOT / "app" / "data" / "outcome_alliance_benchmark_g0.v1.json",
    )
    parser.add_argument("--out-json", type=Path, required=True)
    parser.add_argument("--out-md", type=Path, required=True)
    parser.add_argument("--min-direction-accuracy", type=float, default=0.0)
    args = parser.parse_args()

    benchmark_payload = _read_json(args.benchmark)
    cases = tuple(
        BenchmarkCase.model_validate(item) for item in benchmark_payload["cases"]
    )
    if args.gold_baseline == (args.baseline is not None):
        parser.error("choose exactly one of --baseline or --gold-baseline")
    baseline = (
        gold_reference_snapshot(cases)
        if args.gold_baseline
        else AllianceCalibrationSnapshot.model_validate(_read_json(args.baseline))
    )
    candidate = AllianceCalibrationSnapshot.model_validate(_read_json(args.candidate))
    report = compare_alliance_snapshots(baseline, candidate, cases)
    args.out_json.parent.mkdir(parents=True, exist_ok=True)
    args.out_md.parent.mkdir(parents=True, exist_ok=True)
    args.out_json.write_text(
        json.dumps(report, ensure_ascii=False, indent=2, default=str) + "\n",
        encoding="utf-8",
    )
    args.out_md.write_text(
        render_alliance_comparison_markdown(report),
        encoding="utf-8",
    )
    accuracy = float(report["candidate"]["direction_accuracy"])
    print(
        json.dumps(
            {
                "candidate_direction_accuracy": accuracy,
                "candidate_evidence_recall": report["candidate"]["evidence_recall"],
                "candidate_missing_or_failed": report["candidate"]["missing_or_failed_count"],
                "mean_absolute_score_delta": report["drift"]["mean_absolute_score_delta"],
                "report": str(args.out_md),
            },
            ensure_ascii=False,
        )
    )
    return 0 if accuracy >= args.min_direction_accuracy else 2


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