"""Tests for the multi-model reconciliation in judge_screenshot.combine()."""

import os
import sys

_TOOLS = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, _TOOLS)
for _sub in ("review", "gen", "unreal", "blender", "input"):
    sys.path.insert(0, os.path.join(_TOOLS, _sub))


import unittest

from judge_screenshot import combine


class CombineTests(unittest.TestCase):
    def test_agreement_takes_the_verdict_and_mean_confidence(self):
        result = combine([
            {"model": "a", "verdict": "yes", "confidence": 0.8, "reason": "ok"},
            {"model": "b", "verdict": "yes", "confidence": 0.6, "reason": "fine"},
        ])
        self.assertEqual(result["verdict"], "yes")
        self.assertAlmostEqual(result["confidence"], 0.7)

    def test_disagreement_becomes_uncertain_and_keeps_both_reasons(self):
        result = combine([
            {"model": "a", "verdict": "yes", "confidence": 0.9, "reason": "looks right"},
            {"model": "b", "verdict": "no", "confidence": 0.4, "reason": "missing banner"},
        ])
        self.assertEqual(result["verdict"], "uncertain")
        self.assertAlmostEqual(result["confidence"], 0.4)
        self.assertIn("a=yes", result["reason"])
        self.assertIn("b=no", result["reason"])

    def test_unknown_verdicts_are_ignored(self):
        result = combine([
            {"model": "a", "verdict": "no", "confidence": 0.5, "reason": "x"},
            {"model": "b", "verdict": "garbage", "confidence": 0.9, "reason": "y"},
        ])
        self.assertEqual(result["verdict"], "no")

    def test_no_usable_verdicts(self):
        result = combine([{"model": "a", "verdict": "garbage"}])
        self.assertEqual(result["verdict"], "unknown")


if __name__ == "__main__":
    unittest.main()