test_budget_limited_and_controller_failed_states_do_not_become_passes (test_compare.ComparisonTests.test_budget_limited_and_controller_failed_states_do_not_become_passes) ... ok
test_changed_read_text_or_version_does_not_pass_target_check (test_compare.ComparisonTests.test_changed_read_text_or_version_does_not_pass_target_check) ... ok
test_exact_target_binding_maps_legacy_ids_and_refuses_changed_hash (test_compare.ComparisonTests.test_exact_target_binding_maps_legacy_ids_and_refuses_changed_hash) ... ok
test_failures_and_unsupported_incomplete_trials_are_retained (test_compare.ComparisonTests.test_failures_and_unsupported_incomplete_trials_are_retained) ... ok
test_labels_are_joined_only_after_policy_execution (test_compare.ComparisonTests.test_labels_are_joined_only_after_policy_execution) ... ok
test_missing_or_duplicate_trials_refuse_join (test_compare.ComparisonTests.test_missing_or_duplicate_trials_refuse_join) ... ok
test_same_questions_versions_corpus_and_maximum_budgets (test_compare.ComparisonTests.test_same_questions_versions_corpus_and_maximum_budgets) ... ok
test_all_limits_stop_before_denied_tool_invocation (test_limits.LimitTests.test_all_limits_stop_before_denied_tool_invocation) ... ok
test_case_and_default_k_variants_are_still_repeated_search (test_limits.LimitTests.test_case_and_default_k_variants_are_still_repeated_search) ... ok
test_cumulative_step_search_read_and_byte_limits (test_limits.LimitTests.test_cumulative_step_search_read_and_byte_limits) ... ok
test_invalid_limits_and_action_schema_fail_closed (test_limits.LimitTests.test_invalid_limits_and_action_schema_fail_closed) ... ok
test_repeated_call_is_rejected_without_second_invocation (test_limits.LimitTests.test_repeated_call_is_rejected_without_second_invocation) ... ok
test_success_records_real_validated_reads_and_actual_counters (test_limits.LimitTests.test_success_records_real_validated_reads_and_actual_counters) ... ok
test_tampered_same_size_read_is_not_accepted_as_observation (test_limits.LimitTests.test_tampered_same_size_read_is_not_accepted_as_observation) ... ok
test_tool_error_is_terminal_and_attempt_consumes_budget (test_limits.LimitTests.test_tool_error_is_terminal_and_attempt_consumes_budget) ... ok

----------------------------------------------------------------------
Ran 15 tests in 0.058s

OK
