import argparse
import json
from pathlib import Path

def main():
    parser = argparse.ArgumentParser(description="Evaluate saved AI outputs offline")
    parser.add_argument("cases")
    parser.add_argument("answers")
    args = parser.parse_args()
    try:
        cases = json.loads(Path(args.cases).read_text(encoding="utf-8-sig"))
        answers = json.loads(Path(args.answers).read_text(encoding="utf-8-sig"))
        if not isinstance(cases, list) or not cases or not isinstance(answers, dict):
            raise ValueError("Use a non-empty case list and an answer object.")
        seen = set()
        results = []
        for case in cases:
            if not isinstance(case, dict):
                raise ValueError("Each case must be an object.")
            key = case.get("id")
            expected = case.get("expected")
            forbidden = case.get("forbidden", [])
            if not isinstance(key, str) or not key.strip() or key in seen:
                raise ValueError("Case IDs must be unique non-empty strings.")
            if not isinstance(expected, list) or not expected:
                raise ValueError("Each case needs expected phrases.")
            if not isinstance(forbidden, list):
                raise ValueError("Forbidden phrases must be a list.")
            if any(not isinstance(s, str) or not s.strip() for s in expected + forbidden):
                raise ValueError("Phrases must be non-empty strings.")
            seen.add(key)
            answer = answers.get(key)
            text = answer.casefold() if isinstance(answer, str) else ""
            missing = [s for s in expected if s.casefold() not in text]
            violations = [s for s in forbidden if s.casefold() in text]
            passed = isinstance(answer, str) and not missing and not violations
            results.append({"id": key, "passed": passed, "missing": missing, "forbiddenFound": violations})
    except (OSError, ValueError, TypeError, UnicodeError) as error:
        parser.exit(2, f"Invalid evaluation input: {error}\n")
    passed = sum(row["passed"] for row in results)
    print(json.dumps({"total": len(results), "passed": passed,
                      "passRate": passed / len(results), "results": results}, indent=2))
    return 0 if passed == len(results) else 1

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