fixed testing of marble

Author: cemde

tests/test_benchmarks/test_multiagentbench/conftest.py

@@ -15,10 +15,11 @@
 
 import pytest
 from typing import Any, Dict, List, Optional, Sequence, Tuple
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch
 
 from conftest import DummyModelAdapter
 from maseval import AgentAdapter, Task, MessageHistory
+from maseval.benchmark.multiagentbench.environment import MultiAgentBenchEnvironment
 
 
 # =============================================================================
@@ -44,6 +45,33 @@ def ensure_marble_data():
     return ensure_marble_exists(auto_download=True)
 
 
+@pytest.fixture(autouse=True)
+def _mock_marble_environment():
+    """Mock MARBLE environment creation for all Tier 1 (offline) tests.
+
+    MultiAgentBenchEnvironment.setup_state() calls _create_marble_environment()
+    which imports marble — a vendored dependency not available in CI. This fixture
+    replaces that method with a MagicMock so structural tests can exercise the full
+    benchmark pipeline without marble installed.
+
+    Tests that need the real _create_marble_environment can override this fixture
+    with a no-op at the class or file level (standard pytest fixture scoping).
+    """
+    mock_env = MagicMock()
+    mock_env.is_done.return_value = False
+    mock_env.is_task_completed.return_value = False
+    mock_env.get_state.return_value = {}
+    mock_env._action_handlers = {}
+    mock_env.action_handler_descriptions = {}
+
+    with patch.object(
+        MultiAgentBenchEnvironment,
+        "_create_marble_environment",
+        return_value=mock_env,
+    ):
+        yield
+
+
 # =============================================================================
 # Sample Task Data
 # =============================================================================

tests/test_benchmarks/test_multiagentbench/test_environment.py

@@ -45,19 +45,6 @@ def test_init_with_bargaining_task(self, sample_bargaining_task_data: Dict[str,
 
         assert env.domain == "bargaining"
 
-    def test_init_raises_without_marble(self, sample_research_task_data: Dict[str, Any]):
-        """Constructor should raise ImportError when MARBLE is not available."""
-        marble_modules = {k: v for k, v in sys.modules.items() if "marble" in k}
-        for module_name in marble_modules:
-            sys.modules.pop(module_name, None)
-
-        try:
-            with patch.dict("sys.modules", {"marble.environments.base_env": None}):
-                with pytest.raises(ImportError, match="MARBLE is not available"):
-                    MultiAgentBenchEnvironment(task_data=sample_research_task_data)
-        finally:
-            sys.modules.update(marble_modules)
-
     def test_setup_state_extracts_domain(self, sample_research_task_data: Dict[str, Any]):
         """setup_state should extract domain from task data."""
         env = MultiAgentBenchEnvironment(task_data=sample_research_task_data)
@@ -102,8 +89,31 @@ def test_gather_config_includes_domain(self, sample_research_task_data: Dict[str
         assert config["domain"] == "research"
         assert "tool_descriptions" in config
 
+
+class TestMultiAgentBenchEnvironmentRealMarble:
+    """Tests that need the real _create_marble_environment (no mock)."""
+
+    @pytest.fixture(autouse=True)
+    def _mock_marble_environment(self):
+        """Override: let these tests use real marble imports."""
+        yield
+
+    def test_init_raises_without_marble(self, sample_research_task_data: Dict[str, Any]):
+        """Constructor should raise ImportError when MARBLE is not available."""
+        marble_modules = {k: v for k, v in sys.modules.items() if "marble" in k}
+        for module_name in marble_modules:
+            sys.modules.pop(module_name, None)
+
+        try:
+            with patch.dict("sys.modules", {"marble.environments.base_env": None}):
+                with pytest.raises(ImportError, match="MARBLE is not available"):
+                    MultiAgentBenchEnvironment(task_data=sample_research_task_data)
+        finally:
+            sys.modules.update(marble_modules)
+
+    @pytest.mark.live
     def test_marble_env_type_in_state(self, sample_research_task_data: Dict[str, Any]):
-        """setup_state should include MARBLE env type."""
+        """setup_state should include MARBLE env type (needs real marble)."""
         env = MultiAgentBenchEnvironment(task_data=sample_research_task_data)
 
         assert env.state["marble_env_type"] == "ResearchEnvironment"

tests/test_benchmarks/test_multiagentbench/test_integration_real_data.py

@@ -26,6 +26,13 @@
 
 pytestmark = [pytest.mark.live, pytest.mark.slow, pytest.mark.benchmark]
 
+
+@pytest.fixture(autouse=True)
+def _mock_marble_environment():
+    """Override: integration tests use real marble."""
+    yield
+
+
 # Domains that can be tested without external infrastructure (Docker, Minecraft Server)
 NON_INFRA_DOMAINS = sorted(VALID_DOMAINS - INFRASTRUCTURE_DOMAINS - {"minecraft", "werewolf"})