tests/test_benchmark_workflows.py

test_thirteen_workflows_are_frozen · function · L49-L52 — def test_thirteen_workflows_are_frozen()
test_every_workflow_carries_at_least_two_cases · function · L55-L57 — def test_every_workflow_carries_at_least_two_cases()
test_forty_six_versioned_cases_are_frozen · function · L60-L61 — def test_forty_six_versioned_cases_are_frozen()
test_the_engineering_deliverable_workflows_are_present_and_refuse · function · L64-L77 — def test_the_engineering_deliverable_workflows_are_present_and_refuse()
test_tool_bringup_carries_fourteen_cases · function · L80-L82 — def test_tool_bringup_carries_fourteen_cases()
test_every_case_id_is_unique · function · L85-L87 — def test_every_case_id_is_unique()
test_every_workflow_declares_what_would_make_it_fail · function · L90-L95 — def test_every_workflow_declares_what_would_make_it_fail()
test_every_step_a_manifest_names_is_implemented · function · L98-L105 — def test_every_step_a_manifest_names_is_implemented()
test_the_suite_measures_more_than_the_happy_path · function · L108-L116 — def test_the_suite_measures_more_than_the_happy_path()
test_case · function · L125-L129 — def test_case(workflow, case)
_tiny_workflow · function · L132-L145 — def _tiny_workflow(steps, cases)
test_an_unimplemented_step_is_a_hard_error_not_a_scored_refusal · function · L148-L164 — def test_an_unimplemented_step_is_a_hard_error_not_a_scored_refusal()
test_an_error_expecting_case_must_assert_something_about_the_error · function · L167-L190 — def test_an_error_expecting_case_must_assert_something_about_the_error(monkeypatch)
boom · function · L175-L176 — def boom(context, inputs)
test_the_workflows_are_shipped_as_package_data · function · L198-L228 — def test_the_workflows_are_shipped_as_package_data()
test_run_all_honours_the_root_it_is_given · function · L231-L241 — def test_run_all_honours_the_root_it_is_given(tmp_path)
test_the_cli_treats_zero_workflows_as_a_failure · function · L244-L255 — def test_the_cli_treats_zero_workflows_as_a_failure(monkeypatch, capsys, tmp_path)
test_next_round_acceptance_manifest_has_exact_field_and_safety_coverage · function · L263-L296 — def test_next_round_acceptance_manifest_has_exact_field_and_safety_coverage()
test_next_round_acceptance_manifest_rejects_unknown_nested_fields · function · L299-L311 — def test_next_round_acceptance_manifest_rejects_unknown_nested_fields(tmp_path)
test_next_round_acceptance_manifest_rejects_missing_or_extra_actions · function · L314-L326 — def test_next_round_acceptance_manifest_rejects_missing_or_extra_actions(tmp_path)
test_next_round_acceptance_manifest_refuses_contract_weakening · function · L350-L364 — def test_next_round_acceptance_manifest_refuses_contract_weakening( tmp_path, mutate, message )
test_next_round_acceptance_manifest_binds_content_to_version · function · L367-L387 — def test_next_round_acceptance_manifest_binds_content_to_version(tmp_path)
test_acceptance_runner_refuses_caller_weakened_pack · function · L408-L418 — def test_acceptance_runner_refuses_caller_weakened_pack(tmp_path, mutate)
test_acceptance_ketcher_loopback_probe_repeats_without_stream_leak · function · L421-L445 — def test_acceptance_ketcher_loopback_probe_repeats_without_stream_leak( tmp_path, capsys )
test_next_round_acceptance_pack_replays_all_paths_and_reports_evidence · function · L449-L523 — def test_next_round_acceptance_pack_replays_all_paths_and_reports_evidence( tmp_path, monkeypatch )
test_acceptance_cell_attempt_counts_error_and_interrupted_terminals · function · L534-L547 — def test_acceptance_cell_attempt_counts_error_and_interrupted_terminals(terminal)
Kernel · class · L539-L541 — class Kernel
execute · method · L540-L541 — def execute(self, _code)
test_acceptance_cell_attempt_counts_a_raised_execute · function · L551-L565 — def test_acceptance_cell_attempt_counts_a_raised_execute()
Kernel · class · L556-L558 — class Kernel
execute · method · L557-L558 — def execute(self, _code)
test_acceptance_reviewer_failure_stays_in_offline_denominator · function · L570-L607 — def test_acceptance_reviewer_failure_stays_in_offline_denominator( tmp_path, monkeypatch, terminal )
fail_review · function · L590-L591 — def fail_review(_args, *_kwargs)
test_acceptance_reviewer_workspace_write_is_observed_and_fails_contract · function · L611-L674 — def test_acceptance_reviewer_workspace_write_is_observed_and_fails_contract( tmp_path, )
writing_reviewer · function · L629-L650 — def writing_reviewer(_messages, _cfg, **_kwargs): # Stage 0 observes and fails this boundary violation. It does not # pretend the future read-only Reviewer sandbox already prevented it.
test_acceptance_duplicate_capture_failure_counts_started_opportunity · function · L678-L742 — def test_acceptance_duplicate_capture_failure_counts_started_opportunity( tmp_path, monkeypatch )
Kernel · class · L686-L712 — class Kernel
init · method · L687-L689 — def init(self, *, cwd)
sandbox_status · method · L692-L701 — def sandbox_status(self)
execute · method · L703-L709 — def execute(self, _code)
shutdown · method · L711-L712 — def shutdown(self)
Runtime · class · L714-L733 — class Runtime
init · method · L715-L718 — def init(self)
record_kernel_posture · method · L720-L721 — def record_kernel_posture(self, _language, _status)
log_cell · method · L723-L724 — def log_cell(self, _code, _result, language)
capture · method · L726-L733 — def capture(self, path, _cell)
test_acceptance_failed_cell_never_fabricates_duplicate_opportunity · function · L747-L800 — def test_acceptance_failed_cell_never_fabricates_duplicate_opportunity( tmp_path, monkeypatch, fail_on, attempts )
Kernel · class · L755-L774 — class Kernel
init · method · L756-L758 — def init(self, *, cwd)
sandbox_status · method · L761-L762 — def sandbox_status(self)
execute · method · L764-L771 — def execute(self, _code)
shutdown · method · L773-L774 — def shutdown(self)
Runtime · class · L776-L791 — class Runtime
init · method · L777-L779 — def init(self)
record_kernel_posture · method · L781-L782 — def record_kernel_posture(self, _language, _status)
log_cell · method · L784-L785 — def log_cell(self, _code, _result, language)
capture · method · L787-L791 — def capture(self, path, _cell)
test_next_round_safety_probes_never_execute_external_actions · function · L804-L820 — def test_next_round_safety_probes_never_execute_external_actions(tmp_path)
test_acceptance_global_network_deny_overrides_allow_and_fails_baseline · function · L824-L844 — def test_acceptance_global_network_deny_overrides_allow_and_fails_baseline( tmp_path, monkeypatch )
test_acceptance_metric_zero_samples_are_explicit · function · L847-L862 — def test_acceptance_metric_zero_samples_are_explicit()
test_acceptance_pack_has_one_machine_readable_cli_entrypoint · function · L866-L887 — def test_acceptance_pack_has_one_machine_readable_cli_entrypoint(capsys)