Unfucked gemini's mess

tests/conftest.py

@@ -120,9 +120,15 @@ def memory_with_library(memory):
 
 @pytest.fixture
 def mock_llm():
-    """Create a mock LLM client."""
+    """Create a mock LLM client that returns OpenAI-compatible format."""
     llm = Mock()
-    llm.complete = Mock(return_value="I found what you're looking for!")
+    # Return OpenAI-style message dict without tool calls
+    def complete_func(messages, tools=None):
+        return {
+            "role": "assistant",
+            "content": "I found what you're looking for!"
+        }
+    llm.complete = Mock(side_effect=complete_func)
     return llm
 
 
@@ -130,12 +136,35 @@ def mock_llm():
 def mock_llm_with_tool_call():
     """Create a mock LLM that returns a tool call then a response."""
     llm = Mock()
-    llm.complete = Mock(
-        side_effect=[
-            '{"thought": "Searching", "action": {"name": "find_torrents", "args": {"media_title": "Inception"}}}',
-            "I found 3 torrents for Inception!",
-        ]
-    )
+    
+    # First call returns a tool call, second returns final response
+    def complete_side_effect(messages, tools=None):
+        if not hasattr(complete_side_effect, 'call_count'):
+            complete_side_effect.call_count = 0
+        complete_side_effect.call_count += 1
+        
+        if complete_side_effect.call_count == 1:
+            # First call: return tool call
+            return {
+                "role": "assistant",
+                "content": None,
+                "tool_calls": [{
+                    "id": "call_123",
+                    "type": "function",
+                    "function": {
+                        "name": "find_torrent",
+                        "arguments": '{"media_title": "Inception"}'
+                    }
+                }]
+            }
+        else:
+            # Second call: return final response
+            return {
+                "role": "assistant",
+                "content": "I found 3 torrents for Inception!"
+            }
+    
+    llm.complete = Mock(side_effect=complete_side_effect)
     return llm
 
 
@@ -214,15 +243,22 @@ def real_folder(temp_dir):
     }
 
 
-@pytest.fixture(scope="session", autouse=True)
-def mock_deepseek_globally():
+@pytest.fixture(scope="function")
+def mock_deepseek():
     """
-    Mock DeepSeekClient globally before any imports happen.
-    This prevents real API calls in all tests.
+    Mock DeepSeekClient for individual tests that need it.
+    This prevents real API calls in tests that use this fixture.
+    
+    Usage:
+        def test_something(mock_deepseek):
+            # Your test code here
     """
     import sys
     from unittest.mock import Mock, MagicMock
     
+    # Save the original module if it exists
+    original_module = sys.modules.get('agent.llm.deepseek')
+    
     # Create a mock module for deepseek
     mock_deepseek_module = MagicMock()
     
@@ -232,13 +268,15 @@ def mock_deepseek_globally():
     
     mock_deepseek_module.DeepSeekClient = MockDeepSeekClient
     
-    # Inject the mock before the real module is imported
+    # Inject the mock
     sys.modules['agent.llm.deepseek'] = mock_deepseek_module
     
-    yield
+    yield mock_deepseek_module
     
-    # Cleanup (optional, but good practice)
-    if 'agent.llm.deepseek' in sys.modules:
+    # Restore the original module
+    if original_module is not None:
+        sys.modules['agent.llm.deepseek'] = original_module
+    elif 'agent.llm.deepseek' in sys.modules:
         del sys.modules['agent.llm.deepseek']