fix(logging): handle ResponseCompletedEvent in anthropic_messages streaming spend log (#29394)

* fix(logging): handle ResponseCompletedEvent in anthropic_messages streaming spend log

* fix(logging): extend terminal event handling to ResponseIncompleteEvent and ResponseFailedEvent; fix return type annotation

litellm/litellm_core_utils/litellm_logging.py

@@ -3503,7 +3503,9 @@ class Logging(LiteLLMLoggingBaseClass):
         else:
             return None
 
-    def _handle_anthropic_messages_response_logging(self, result: Any) -> ModelResponse:
+    def _handle_anthropic_messages_response_logging(
+        self, result: Any
+    ) -> Union[ModelResponse, ResponsesAPIResponse]:
         """
         Handles logging for Anthropic messages responses.
 
@@ -3522,6 +3524,15 @@ class Logging(LiteLLMLoggingBaseClass):
             return result
         elif isinstance(result, ModelResponse):
             return result
+        elif isinstance(
+            result,
+            (ResponseCompletedEvent, ResponseIncompleteEvent, ResponseFailedEvent),
+        ):
+            # anthropic_messages() can route to OpenAI Responses API; in that path
+            # the assembled streaming result is one of these terminal events rather than
+            # a ModelResponse. Return the inner response so downstream handlers
+            # (_transform_usage_objects, normalize_logging_result) can process it.
+            return result.response
 
         httpx_response = self.model_call_details.get("httpx_response", None)
         if httpx_response and isinstance(httpx_response, httpx.Response):

tests/test_litellm/litellm_core_utils/test_litellm_logging.py

@@ -3114,3 +3114,44 @@ def test_get_error_information_prefers_message_attribute_over_empty_str():
     )
     assert info["error_message"] == "real failure detail"
     assert info["error_code"] == "401"
+
+
+@pytest.mark.parametrize(
+    "event_cls, event_type",
+    [
+        ("ResponseCompletedEvent", "response.completed"),
+        ("ResponseIncompleteEvent", "response.incomplete"),
+        ("ResponseFailedEvent", "response.failed"),
+    ],
+)
+def test_handle_anthropic_messages_response_logging_with_terminal_responses_api_events(
+    event_cls, event_type
+):
+    """Regression test for #28943: when anthropic_messages routes to OpenAI Responses
+    API and stream=True, success_handler receives a terminal ResponsesAPI event instead
+    of a ModelResponse. The handler must return the inner ResponsesAPIResponse rather
+    than crashing with AnthropicResponse.model_validate."""
+    import importlib
+
+    openai_types = importlib.import_module("litellm.types.llms.openai")
+    EventClass = getattr(openai_types, event_cls)
+    from litellm.types.llms.openai import ResponsesAPIResponse
+
+    logging_obj = LitellmLogging(
+        model="gpt-4o",
+        messages=[{"role": "user", "content": "hello"}],
+        stream=True,
+        call_type="anthropic_messages",
+        start_time=time.time(),
+        litellm_call_id="test-rce-123",
+        function_id="test-fn",
+    )
+
+    inner_response = ResponsesAPIResponse(
+        id="resp_test", created_at=1700000000, output=[]
+    )
+    event = EventClass(type=event_type, response=inner_response)
+
+    result = logging_obj._handle_anthropic_messages_response_logging(result=event)
+
+    assert result is inner_response