[
  "tests/test_env.py::TestAllDifficulties::test_easy",
  "tests/test_env.py::TestAllDifficulties::test_hard",
  "tests/test_env.py::TestAllDifficulties::test_medium",
  "tests/test_env.py::TestEnvironmentBasics::test_episode_terminates",
  "tests/test_env.py::TestEnvironmentBasics::test_reset_returns_observation",
  "tests/test_env.py::TestEnvironmentBasics::test_state_tracking",
  "tests/test_env.py::TestEnvironmentBasics::test_step_with_correct_query",
  "tests/test_env.py::TestEnvironmentBasics::test_step_with_invalid_query",
  "tests/test_env.py::TestGrading::test_scores_in_range",
  "tests/test_env.py::TestGrading::test_varying_scores",
  "tests/test_env.py::TestTaskRegistry::test_list_tasks",
  "tests/test_env.py::TestTaskRegistry::test_minimum_3_tasks"
]