Require boolean judgments and intact actor isolation guards

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0e76f-be98-7ae3-965d-e0b31290a4c4
This commit is contained in:
tegwick 2026-09-28 14:03:29 +02:00
parent 9cdade2116
commit 0f8559f442
6 changed files with 156 additions and 2 deletions

View file

@ -0,0 +1,94 @@
"""Reject invalid predicate results and broken actor isolation instrumentation."""
from dataclasses import replace
import json
import pytest
from scenarios.alice_bob_carol import build
from testdriver import Runner, Verdict
from testdriver.classification import classify
from testdriver.crystallization import assess_stability
from testdriver.oracles import Oracle
class CannotCoerce:
def __bool__(self):
raise AssertionError('oracle must not coerce predicate results')
@pytest.mark.parametrize('value', [None, 'unknown', {}, [], 0, 1, CannotCoerce()])
def test_non_boolean_predicate_results_are_inconclusive(value):
_, _, _, asset, _ = build()
for assertion in (*asset.scenario.use_case.claims, *asset.scenario.use_case.invariants):
assertion = replace(assertion, predicate=lambda snapshot: value)
judgment = Oracle().judge(assertion, {'observed': True}, 'step')
assert judgment.verdict is Verdict.INCONCLUSIVE
assert 'boolean' in judgment.detail['reason']
@pytest.mark.parametrize('value,verdict', [(True, Verdict.PASS), (False, Verdict.FAIL)])
def test_boolean_predicate_results_keep_their_meaning(value, verdict):
_, _, _, asset, _ = build()
assertion = replace(asset.scenario.use_case.claims[0], predicate=lambda snapshot: value)
assert Oracle().judge(assertion, {'observed': True}, 'step').verdict is verdict
@pytest.mark.parametrize('value', [None, 'unknown', 1])
def test_invalid_predicates_cannot_authorize_acceptance_or_crystallization(value):
packs = []
for _ in range(3):
world, driver, observer, asset, oracle = build()
case = asset.scenario.use_case
asset.scenario = replace(asset.scenario, use_case=replace(case, claims=tuple(
replace(c, predicate=lambda snapshot: value) for c in case.claims)))
result = Runner(world, driver, observer, oracle).run(asset)
assert result.verdict is Verdict.INCONCLUSIVE
packs.append(json.loads(result.evidence.to_json()))
assert not classify(packs[0], packs[1]).safe_to_accept
assert not assess_stability(packs).stable
@pytest.mark.parametrize('damage', ['shared', 'missing', 'changed', 'duplicate'])
@pytest.mark.parametrize('during_run', [False, True])
def test_corrupt_isolation_guards_stop_execution(damage, during_run):
packs = []
for _ in range(3):
world, driver, observer, asset, oracle = build()
calls = []
def corrupt():
alice, bob = world.cast['alice'], world.cast['bob']
if damage == 'shared':
alice._memory = bob._memory = {}
alice.remember('private', 'private-value')
assert bob.recall('private') == 'private-value'
elif damage == 'missing':
bob._memory.pop('__canary__')
elif damage == 'changed':
bob.remember('__canary__', 'replacement')
else:
bob.canary = alice.canary
bob.remember('__canary__', alice.canary)
class Driver:
def realize(self, actor, action):
calls.append(action.name)
result = driver.realize(actor, action)
corrupt()
return result
if not during_run:
corrupt()
result = Runner(world, Driver(), observer, oracle).run(asset)
assert result.verdict is Verdict.INCONCLUSIVE
assert len(calls) == int(during_run)
pack = json.loads(result.evidence.to_json())
guards = [o['data']['violations'] for o in pack['observations']
if o['kind'] == 'actor_isolation']
assert guards[-1]
assert 'private-value' not in result.evidence.to_json()
if damage == 'shared':
assert any('memory store' in v for v in guards[-1])
packs.append(pack)
assert not classify(packs[0], packs[1]).safe_to_accept
assert not assess_stability(packs).stable