"""The classifier, measured against the labelled catalogue — and attacked.

`test_response_matrix` samples benign and hostile cases alike. The E-003 group
below does something different: it *tries to make the framework unsafe*. An
experiment that only samples cases chosen by the same person who wrote the
implementation cannot establish a safety property.
"""

from __future__ import annotations

import json

import pytest

from testdriver import Runner, Verdict
from testdriver.classification import (
    Classification, SAFE_TO_ACCEPT, classify,
)
from testdriver.provenance import InadmissibleProvenance, Provenance
from testdriver.intent import Claim
from lab.mutations import CATALOGUE
from scenarios.full_journey import build_journey, journey_lab_server
from tests.selfverification.checks import check_intent_independence


def pack_for(*mutations: str, observer_factory=None) -> dict:
    with journey_lab_server(*mutations) as (app, tokens, base_url):
        world, driver, observer, asset, oracle = build_journey(app, tokens, base_url)
        if observer_factory is not None:
            observer = observer_factory(observer)
        return json.loads(Runner(world, driver, observer, oracle).run(asset).evidence.to_json())


@pytest.fixture(scope="module")
def baseline() -> dict:
    return pack_for()


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

EXPECTED = {
    "M01": Classification.MECHANICAL_ADAPTATION,
    "M02": Classification.MECHANICAL_ADAPTATION,
    "M03": Classification.UNCHANGED,
    "M04": Classification.MECHANICAL_ADAPTATION,
    "M05": Classification.UNCHANGED,
    "M06": Classification.MECHANICAL_ADAPTATION,
    "M07": Classification.MECHANICAL_ADAPTATION,
    "M08": Classification.MECHANICAL_ADAPTATION,
    "M09": Classification.UNCHANGED,
    "M10": Classification.UNCHANGED,
    "M21": Classification.MECHANICAL_ADAPTATION,
    "M22": Classification.AMBIGUOUS,
    "M11": Classification.BEHAVIOUR_CHANGED,
    "M12": Classification.BEHAVIOUR_CHANGED,
    "M13": Classification.UNCHANGED,
    "M14": Classification.UNCHANGED,
    "M15": Classification.BEHAVIOUR_CHANGED,
    "M16": Classification.BEHAVIOUR_CHANGED,
    "M17": Classification.BEHAVIOUR_CHANGED,
    "M18": Classification.BEHAVIOUR_CHANGED,
    "M19": Classification.BEHAVIOUR_CHANGED,
    "M20": Classification.BEHAVIOUR_CHANGED,
    "M23": Classification.AMBIGUOUS,
    "M24": Classification.MECHANICAL_ADAPTATION,
}


@pytest.mark.parametrize("mutation_id", sorted(EXPECTED))
def test_response_matrix(baseline, mutation_id):
    assert classify(baseline, pack_for(mutation_id)).classification is EXPECTED[mutation_id]


def test_baseline_classifies_as_unchanged(baseline):
    assert classify(baseline, pack_for()).classification is Classification.UNCHANGED


# --- the metric that matters ----------------------------------------------


def test_false_adaptation_rate_is_zero(baseline):
    """The project's existential safety metric.

    Not "low". Zero. A non-zero result is a stop-and-redesign signal, because a
    framework that normalizes a real defect once has spent the credibility it
    exists to accumulate.
    """
    false_adaptations = [
        mutation.id for mutation in CATALOGUE
        if mutation.label == "DEFECT"
        and classify(baseline, pack_for(mutation.id)).safe_to_accept
    ]
    assert false_adaptations == []


def test_every_defect_is_escalated(baseline):
    for mutation in CATALOGUE:
        if mutation.label != "DEFECT":
            continue
        outcome = classify(baseline, pack_for(mutation.id))
        assert not outcome.safe_to_accept, f"{mutation.id}: {outcome.reason}"


def test_mechanical_changes_are_mostly_absorbed(baseline):
    """Adaptation has to be *useful*, not merely safe.

    A classifier that escalated everything would score a perfect False Adaptation
    Rate and be worthless. This asserts the other side of the trade.
    """
    mechanical = [m for m in CATALOGUE if m.label == "MECHANICAL"]
    absorbed = [
        m.id for m in mechanical
        if classify(baseline, pack_for(m.id)).safe_to_accept
    ]
    assert len(absorbed) >= len(mechanical) - 1


def test_no_classification_is_outside_the_defined_space(baseline):
    for mutation in CATALOGUE:
        outcome = classify(baseline, pack_for(mutation.id))
        assert isinstance(outcome.classification, Classification)
        assert outcome.reason


# --- E-003: attacking the boundary ---------------------------------------


def test_attack_surface_substitution(baseline):
    """M23: the control is gone from the UI; the API endpoint is still open.

    The most plausible concrete route to a false adaptation. A driver that
    'recovers' by calling the API has routed around a control, not adapted to a
    change — and would score a successful mechanical adaptation while an
    authorization control sat broken.
    """
    outcome = classify(baseline, pack_for("M23"))
    assert not outcome.safe_to_accept
    assert outcome.classification is Classification.AMBIGUOUS


def test_attack_concurrent_mechanical_and_defect(baseline):
    """Decision-table row 3. Coincidence is not exoneration.

    This is the case a naive self-healing tool gets wrong: it sees a surface
    change, explains the failure with it, and adapts.
    """
    for combination in (("M01", "M15"), ("M02", "M17"), ("M21", "M20")):
        outcome = classify(baseline, pack_for(*combination))
        assert outcome.classification is Classification.BEHAVIOUR_CHANGED
        assert not outcome.safe_to_accept
        assert "does not excuse it" in outcome.reason


def test_attack_evidence_starvation(baseline):
    """Cut the independent observation channel and the answer must be AMBIGUOUS.

    Never a pass, never an adaptation. Evidence starvation is the condition under
    which a framework is most tempted to fall back on the actor's own account of
    what happened.
    """
    class Starved:
        def __init__(self, real):
            self._real, self._calls, self.name = real, 0, real.name
            self.watches = real.watches

        def snapshot(self):
            self._calls += 1
            return self._real.snapshot() if self._calls < 2 else {}

    outcome = classify(baseline, pack_for(observer_factory=Starved))
    assert outcome.classification is Classification.AMBIGUOUS
    assert not outcome.safe_to_accept


def test_attack_provenance_laundering():
    """Intent derived from the implementation must not become a claim.

    Rejected at authoring time, and caught again in the record if it ever got
    past — belt and braces, because this one cannot be noticed by looking at
    behaviour.
    """
    with pytest.raises(InadmissibleProvenance):
        Claim("c-laundered", "whatever the system does",
              Provenance.AGENT_FROM_IMPLEMENTATION, lambda obs: True, after_step="s1")

    tampered = pack_for("M15")
    tampered["provenance_index"]["c-bob-revoked"] = "agent-from-implementation"
    assert check_intent_independence(tampered)


def test_safe_to_accept_is_a_closed_set():
    """Only two outcomes may proceed without a human. Widening this set is the
    single easiest way to destroy the safety property, so it is asserted."""
    assert SAFE_TO_ACCEPT == {
        Classification.UNCHANGED, Classification.MECHANICAL_ADAPTATION,
    }