test_authority_separation_is_cross_level_invariant (test_capability_lab.CapabilityLabTests.test_authority_separation_is_cross_level_invariant) ... ok
test_case_count_covers_architecture_dimensions (test_capability_lab.CapabilityLabTests.test_case_count_covers_architecture_dimensions) ... ok
test_chat_json_parser_accepts_wrapped_json (test_capability_lab.CapabilityLabTests.test_chat_json_parser_accepts_wrapped_json) ... ok
test_prompt_contains_candidate_tokens_but_not_answer_label (test_capability_lab.CapabilityLabTests.test_prompt_contains_candidate_tokens_but_not_answer_label) ... ok
test_reports_are_written (test_capability_lab.CapabilityLabTests.test_reports_are_written) ... ok
test_scripted_l2_certifies_l2 (test_capability_lab.CapabilityLabTests.test_scripted_l2_certifies_l2) ... ok
test_scripted_l5_certifies_l5 (test_capability_lab.CapabilityLabTests.test_scripted_l5_certifies_l5) ... ok
test_scripted_l9_passes_all_and_certifies_l9 (test_capability_lab.CapabilityLabTests.test_scripted_l9_passes_all_and_certifies_l9) ... ok
test_detects_critical_regression (test_regression.RegressionTests.test_detects_critical_regression) ... ok
test_regression_outputs_are_written (test_regression.RegressionTests.test_regression_outputs_are_written) ... ok
test_same_run_has_no_regression (test_regression.RegressionTests.test_same_run_has_no_regression) ... ok
test_capability_gate_separates_level_from_authority (test_runtime.RuntimeTests.test_capability_gate_separates_level_from_authority) ... ok
test_crystal_becomes_stale_after_source_head_changes (test_runtime.RuntimeTests.test_crystal_becomes_stale_after_source_head_changes) ... ok
test_exact_head_conflict_requires_rebase (test_runtime.RuntimeTests.test_exact_head_conflict_requires_rebase) ... ok
test_historical_record_survives_semantic_refutation (test_runtime.RuntimeTests.test_historical_record_survives_semantic_refutation) ... ok
test_hyperlink_path_requires_reopen_and_reaches_raw (test_runtime.RuntimeTests.test_hyperlink_path_requires_reopen_and_reaches_raw) ... ok
test_working_state_preserves_do_not_redo_and_next_entry (test_runtime.RuntimeTests.test_working_state_preserves_do_not_redo_and_next_entry) ... ok
test_benchmark_aggregates_synthetic_token_telemetry (test_telemetry.TelemetryTests.test_benchmark_aggregates_synthetic_token_telemetry) ... ok
test_offline_tournament_certifies_reference_levels (test_tournament.TournamentTests.test_offline_tournament_certifies_reference_levels) ... ok
test_replay_manifest_has_prompt_hashes (test_tournament.TournamentTests.test_replay_manifest_has_prompt_hashes) ... ok
test_safety_first_ranking_places_safe_l9_above_unsafe_l9 (test_tournament.TournamentTests.test_safety_first_ranking_places_safe_l9_above_unsafe_l9) ... ok
test_same_seed_same_case_order (test_tournament.TournamentTests.test_same_seed_same_case_order) ... ok
test_suite_hash_is_stable (test_tournament.TournamentTests.test_suite_hash_is_stable) ... ok
test_tournament_writes_csv_matrices (test_tournament.TournamentTests.test_tournament_writes_csv_matrices) ... ok

----------------------------------------------------------------------
Ran 24 tests in 0.032s

OK
