test-driver/tests/test_lab_ground_truth.py

"""The lab is the measuring instrument. These tests keep it honest.

Nothing here tests the kernel's cleverness — the kernel has no classifier yet.
What is established is the **ground truth** every later measurement is taken
against: which mutations the reference scenario responds to, and how.

The response matrix below is an asserted fact, not a snapshot. If a change to the
lab or the scenario moves a cell, that is a change to the measuring instrument
and must be a deliberate, reviewed act.
"""

from __future__ import annotations

import pytest

from testdriver import Runner, Verdict
from lab.mutations import BY_ID, CATALOGUE, build_lab, expected_classification
from scenarios.alice_bob_carol import build


def run_against(*mutations: str):
    world, driver, observer, asset, oracle = build(*mutations)
    return Runner(world, driver, observer, oracle).run(asset)


# --- the catalogue itself -------------------------------------------------


def test_catalogue_is_large_enough_to_support_a_rate():
    """Six mutations cannot support precision or recall. Twenty can begin to."""
    assert len(CATALOGUE) >= 20


def test_every_mutation_is_labelled_and_reasoned():
    for mutation in CATALOGUE:
        assert mutation.label in ("MECHANICAL", "SEMANTIC", "DEFECT")
        assert mutation.rationale.strip(), f"{mutation.id} has no rationale"


def test_labels_cover_all_three_classes_with_useful_weight():
    counts = {label: 0 for label in ("MECHANICAL", "SEMANTIC", "DEFECT")}
    for mutation in CATALOGUE:
        counts[mutation.label] += 1
    assert all(count >= 4 for count in counts.values()), counts


def test_every_mutation_is_reproducible_and_version_stamped():
    for mutation in CATALOGUE:
        first, _ = build_lab(mutation.id)
        second, _ = build_lab(mutation.id)
        assert first.version == second.version == f"lab-0.2.0-{mutation.id}"
        assert first.applied_mutations == (mutation.id,)


def test_mutations_compose_and_record_both():
    """Row 3 of the decision table needs a lab carrying both at once."""
    app, _ = build_lab("M01", "M15")
    assert app.version == "lab-0.2.0-M01+M15"
    assert app.applied_mutations == ("M01", "M15")


def test_test_id_axis_is_represented():
    """H-001 must be analysable split by whether stable selectors survived."""
    preserved = [m.id for m in CATALOGUE if m.preserves_test_ids]
    dropped = [m.id for m in CATALOGUE if not m.preserves_test_ids]
    assert preserved and dropped, "both sides of the test-id axis must exist"


# --- the response matrix --------------------------------------------------

# Ground truth: what the reference scenario reports for each lab version.
# `None` means "no assertion in this scenario covers this mutation" — recorded
# honestly rather than papered over.
EXPECTED_VERDICT = {
    "M01": Verdict.PASS, "M02": Verdict.PASS, "M03": Verdict.PASS,
    "M04": Verdict.PASS, "M05": Verdict.PASS, "M06": Verdict.PASS,
    "M07": Verdict.PASS, "M08": Verdict.PASS, "M09": Verdict.PASS,
    "M10": Verdict.PASS,
    "M11": Verdict.FAIL, "M12": Verdict.FAIL,
    "M13": Verdict.PASS, "M14": Verdict.PASS,
    "M15": Verdict.FAIL, "M16": Verdict.FAIL, "M17": Verdict.FAIL,
    "M18": Verdict.FAIL, "M19": Verdict.FAIL, "M20": Verdict.FAIL,
}

# The two SEMANTIC mutations the reference scenario cannot see, and why.
KNOWN_INERT = {
    "M13": "only affects grants that omit a permission; the scenario passes READ explicitly",
    "M14": "a change of intent with no change of code; nothing observable moved",
}


def test_baseline_passes():
    assert run_against().verdict is Verdict.PASS


@pytest.mark.parametrize("mutation_id", sorted(EXPECTED_VERDICT))
def test_response_matrix_is_stable(mutation_id):
    assert run_against(mutation_id).verdict is EXPECTED_VERDICT[mutation_id]


def test_no_mechanical_mutation_changes_the_verdict():
    """Semantics are preserved, so the use case must not notice."""
    for mutation in CATALOGUE:
        if mutation.label == "MECHANICAL":
            assert run_against(mutation.id).verdict is Verdict.PASS, mutation.id


def test_every_defect_is_detected():
    """The floor of the whole project. A defect the lab cannot surface is a
    defect no later classifier can be measured against."""
    missed = [
        m.id for m in CATALOGUE
        if m.label == "DEFECT" and run_against(m.id).verdict is Verdict.PASS
    ]
    assert missed == [], f"undetected seeded defects: {missed}"


def test_inert_semantic_mutations_are_declared():
    """A mutation the scenario cannot see must be named, not silently ignored."""
    for mutation in CATALOGUE:
        if mutation.label != "SEMANTIC":
            continue
        if run_against(mutation.id).verdict is Verdict.PASS:
            assert mutation.id in KNOWN_INERT, (
                f"{mutation.id} is invisible to the reference scenario and "
                "undeclared — either cover it or record why not"
            )


def test_deferred_revoke_and_revoke_race_are_behaviourally_identical():
    """M12 (SEMANTIC) and M19 (DEFECT) must be indistinguishable from evidence.

    This is the discrimination problem in its sharpest form, and the reason
    classification cannot be a diff over observed behaviour. Both produce the
    same failure; only intent separates them, which is why claims need
    independent provenance and why ambiguity escalates to a human.
    """
    semantic = run_against("M12")
    defect = run_against("M19")
    failed = lambda r: sorted({j.assertion_id for j in r.judgments
                               if j.verdict is not Verdict.PASS})
    assert failed(semantic) == failed(defect) == ["c-bob-revoked"]
    assert expected_classification("M12") != expected_classification("M19")


def test_a_mechanical_change_shipping_with_a_defect_still_fails():
    """Decision-table row 3: coincidence is not exoneration."""
    assert run_against("M01", "M15").verdict is Verdict.FAIL