from __future__ import annotations

import importlib.util
import json
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parents[1]
SCRIPT_PATH = REPO_ROOT / "scripts" / "replay_decision_engine_eval.py"
FIXTURES_DIR = REPO_ROOT / "fixtures" / "decision-engine-eval"

spec = importlib.util.spec_from_file_location("replay_decision_engine_eval", SCRIPT_PATH)
replay = importlib.util.module_from_spec(spec)
assert spec.loader is not None
spec.loader.exec_module(replay)


def test_default_decision_engine_fixtures_replay_cleanly():
    fixtures = replay.load_fixtures(FIXTURES_DIR)
    proof = replay.evaluate_fixtures(fixtures)

    assert proof["ok"] is True
    assert proof["fixture_count"] == 3
    assert proof["metrics"]["route_accuracy"] == 1.0
    assert proof["metrics"]["lanes"] == {
        "kb-interop": 1,
        "rio-economics": 1,
        "theseus-model-integrity": 1,
    }


def test_candidate_false_approve_is_caught(tmp_path):
    fixtures = replay.load_fixtures(FIXTURES_DIR)
    candidate_path = tmp_path / "candidate.json"
    candidate_path.write_text(
        json.dumps(
            {
                "candidate_name": "bad-single-answer-model",
                "verdicts": [
                    {
                        "fixture_id": "theseus_live_model_switch_reject",
                        "disposition": "approve",
                        "issue_tags": [],
                        "primary_agent": "Theseus",
                        "required_agents": ["Theseus"],
                    }
                ],
            }
        )
    )

    candidate = replay._load_candidate_output(candidate_path)
    proof = replay.evaluate_fixtures(fixtures, candidate=candidate)

    assert proof["ok"] is False
    assert proof["candidate"]["false_approve_count"] == 1
    assert proof["candidate"]["false_approves"] == ["theseus_live_model_switch_reject"]