"""The classifier's safety rules, tested without calling a model.

apply_safety_rules is pure, which is why the rules that matter live there and
not in the prompt. These are the cases the Phase 8 gate cares about: 95%
classification accuracy on Procedural and Advisory, because misrouting those
two is the dangerous failure.
"""

from classifier import TIE_MARGIN, Classification, apply_safety_rules
from contracts import QuestionClass

THRESHOLD = 0.7


def classify(klass, confidence, alternatives=None, missing=None) -> Classification:
    return apply_safety_rules(
        Classification(
            question_class=klass,
            confidence=confidence,
            alternatives=alternatives or {},
            missing_context=missing or [],
        ),
        THRESHOLD,
    )


def test_confident_class_is_kept():
    assert classify(QuestionClass.HISTORICAL, 0.95).question_class is QuestionClass.HISTORICAL


def test_low_confidence_becomes_unclear():
    result = classify(QuestionClass.HISTORICAL, 0.4)
    assert result.question_class is QuestionClass.UNCLEAR
    assert "below threshold" in (result.downgraded_reason or "")


def test_low_confidence_procedural_stays_procedural():
    # Refusing to instruct is safe whether or not the label was right.
    assert classify(QuestionClass.PROCEDURAL, 0.4).question_class is QuestionClass.PROCEDURAL


def test_tie_between_historical_and_advisory_goes_advisory():
    result = classify(
        QuestionClass.HISTORICAL, 0.5, {"advisory": 0.5 - TIE_MARGIN / 2}
    )
    # Below threshold, so the tie resolves to advisory and then downgrades -
    # what matters is that it never resolves to the LESS restrictive class.
    assert result.question_class in {QuestionClass.ADVISORY, QuestionClass.UNCLEAR}


def test_tie_between_reference_and_procedural_goes_procedural():
    result = classify(QuestionClass.REFERENCE, 0.8, {"procedural": 0.75})
    assert result.question_class is QuestionClass.PROCEDURAL
    assert "more restrictive" in (result.downgraded_reason or "")


def test_clear_margin_does_not_upgrade():
    result = classify(QuestionClass.REFERENCE, 0.9, {"procedural": 0.2})
    assert result.question_class is QuestionClass.REFERENCE


def test_historical_without_a_time_window_asks_for_one():
    result = classify(QuestionClass.HISTORICAL, 0.9, missing=["time_expression"])
    assert result.question_class is QuestionClass.UNCLEAR