[
  "tests/test_environment.py::TestReset::test_all_canonical_tasks_load",
  "tests/test_environment.py::TestReset::test_reset_clean_state",
  "tests/test_environment.py::TestReset::test_reset_has_available_actions",
  "tests/test_environment.py::TestReset::test_reset_provides_goal",
  "tests/test_environment.py::TestReset::test_reset_provides_suggested_actions",
  "tests/test_environment.py::TestReset::test_reset_returns_observation",
  "tests/test_environment.py::TestReset::test_reset_sequential_tasks",
  "tests/test_environment.py::TestState::test_state_accessible",
  "tests/test_environment.py::TestState::test_state_tracks_actions",
  "tests/test_environment.py::TestStep::test_findings_accumulate",
  "tests/test_environment.py::TestStep::test_investigation_action",
  "tests/test_environment.py::TestStep::test_repeated_action_penalty",
  "tests/test_environment.py::TestStep::test_step_decrements_remaining",
  "tests/test_environment.py::TestStep::test_suggested_actions_update_after_step",
  "tests/test_environment.py::TestSubmission::test_correct_resolution",
  "tests/test_environment.py::TestSubmission::test_missing_fields_returns_error",
  "tests/test_environment.py::TestSubmission::test_wrong_decision_lower_score",
  "tests/test_environment.py::TestTaskDiversity::test_scores_in_valid_range",
  "tests/test_grader.py::TestExplanationScoring::test_empty_explanation",
  "tests/test_grader.py::TestExplanationScoring::test_explanation_with_numbers",
  "tests/test_grader.py::TestExplanationScoring::test_good_explanation",
  "tests/test_grader.py::TestExplanationScoring::test_vague_explanation_scores_low",
  "tests/test_grader.py::TestGradeEpisode::test_all_rubric_dimensions_present",
  "tests/test_grader.py::TestGradeEpisode::test_no_decision_scores_zero",
  "tests/test_grader.py::TestGradeEpisode::test_partial_decision_credit",
  "tests/test_grader.py::TestGradeEpisode::test_perfect_score",
  "tests/test_grader.py::TestGradeEpisode::test_score_in_bounds",
  "tests/test_grader.py::TestGradeEpisode::test_wrong_decision_zero_decision_score",
  "tests/test_models.py::TestAction::test_minimal_action",
  "tests/test_models.py::TestAction::test_resolution_action",
  "tests/test_models.py::TestBusinessEntities::test_company_policy_defaults",
  "tests/test_models.py::TestBusinessEntities::test_invoice_creation",
  "tests/test_models.py::TestEnums::test_action_types_count",
  "tests/test_models.py::TestEnums::test_decision_types",
  "tests/test_models.py::TestEnums::test_difficulty_levels",
  "tests/test_models.py::TestEnums::test_exception_types_include_key_variants",
  "tests/test_models.py::TestEnums::test_task_ids_minimum_12_canonical",
  "tests/test_models.py::TestEnums::test_task_ids_minimum_6_canonical",
  "tests/test_models.py::TestGraderResult::test_score_bounds",
  "tests/test_models.py::TestGraderResult::test_valid_score",
  "tests/test_models.py::TestObservation::test_defaults",
  "tests/test_models.py::TestObservation::test_populated",
  "tests/test_models.py::TestState::test_defaults",
  "tests/test_models.py::TestState::test_mutation"
]