Fix: Resolve flakiness in three integration tests

tests/test_litellm/integrations/test_langfuse.py

@@ -279,14 +279,16 @@ def mock_get(key, default=None):
                 "response_cost": 0.0,
             }
 
+            # Use fixed timestamps to avoid timing-related flakiness
+            fixed_time = datetime.datetime(2024, 1, 1, 12, 0, 0)
             # Call the method under test
             self.logger._log_langfuse_v2(
                 user_id="test-user",
                 metadata={},
                 litellm_params=kwargs["litellm_params"],
                 output={"role": "assistant", "content": "Response"},
-                start_time=datetime.datetime.now(),
-                end_time=datetime.datetime.now(),
+                start_time=fixed_time,
+                end_time=fixed_time + datetime.timedelta(seconds=1),
                 kwargs=kwargs,
                 optional_params=kwargs["optional_params"],
                 input={"messages": kwargs["messages"]},

tests/test_litellm/llms/watsonx/test_watsonx.py

@@ -279,7 +279,11 @@ async def test_watsonx_gpt_oss_prompt_transformation(monkeypatch):
     ), f"POST should have been called at least once, got {mock_post.call_count}"
 
     # Get the request body from the first call
-    call_args = mock_post.call_args
+    # Use call_args_list to be more robust - get the first call's arguments
+    assert len(mock_post.call_args_list) > 0, "mock_post should have at least one call"
+    call_args = mock_post.call_args_list[0]
+    assert call_args is not None, "call_args should not be None"
+    assert "data" in call_args.kwargs, "call_args.kwargs should contain 'data'"
     json_data = json.loads(call_args.kwargs["data"])
 
     print(f"\n{'='*80}")

tests/test_litellm/responses/test_no_duplicate_spend_logs.py

@@ -83,9 +83,10 @@ async def async_log_success_event(self, kwargs, response_obj, start_time, end_ti
             mock_response="Hello! I'm doing well."  # Use mock to avoid real API call
         )
 
-        # Give async logging time to complete
-        import asyncio
-        await asyncio.sleep(1)
+        # Wait for async logging to complete using the logging worker's flush method
+        # This is more reliable than sleep() which can cause race conditions
+        from litellm.litellm_core_utils.logging_worker import GLOBAL_LOGGING_WORKER
+        await GLOBAL_LOGGING_WORKER.flush()
 
         # Verify that log_success_event was called exactly once
         assert spend_logger.log_count == 1, (