fix(anthropic): pass logging_obj to client.post for litellm_overhead_time_ms (#24071)

When LITELLM_DETAILED_TIMING=true, litellm_overhead_time_ms was null for
Anthropic because the handler did not pass logging_obj to client.post(),
so track_llm_api_timing could not set llm_api_duration_ms. Pass
logging_obj=logging_obj at all four post() call sites (make_call,
make_sync_call, acompletion, completion). Add test to ensure make_call
passes logging_obj to client.post.

Made-with: Cursor

litellm/llms/anthropic/chat/handler.py

@@ -89,7 +89,12 @@ async def make_call(
 
     try:
         response = await client.post(
-            api_base, headers=headers, data=data, stream=True, timeout=timeout
+            api_base,
+            headers=headers,
+            data=data,
+            stream=True,
+            timeout=timeout,
+            logging_obj=logging_obj,
         )
     except httpx.HTTPStatusError as e:
         error_headers = getattr(e, "headers", None)
@@ -142,7 +147,12 @@ def make_sync_call(
 
     try:
         response = client.post(
-            api_base, headers=headers, data=data, stream=True, timeout=timeout
+            api_base,
+            headers=headers,
+            data=data,
+            stream=True,
+            timeout=timeout,
+            logging_obj=logging_obj,
         )
     except httpx.HTTPStatusError as e:
         error_headers = getattr(e, "headers", None)
@@ -266,7 +276,11 @@ class AnthropicChatCompletion(BaseLLM):
 
         try:
             response = await async_handler.post(
-                api_base, headers=headers, json=data, timeout=timeout
+                api_base,
+                headers=headers,
+                json=data,
+                timeout=timeout,
+                logging_obj=logging_obj,
             )
         except Exception as e:
             ## LOGGING
@@ -469,6 +483,7 @@ class AnthropicChatCompletion(BaseLLM):
                         headers=headers,
                         data=json.dumps(data),
                         timeout=timeout,
+                        logging_obj=logging_obj,
                     )
                 except Exception as e:
                     status_code = getattr(e, "status_code", 500)

tests/test_litellm/llms/anthropic/chat/test_anthropic_chat_handler.py

@@ -1,7 +1,9 @@
-from unittest.mock import MagicMock
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
 
 from litellm.constants import RESPONSE_FORMAT_TOOL_NAME
-from litellm.llms.anthropic.chat.handler import ModelResponseIterator
+from litellm.llms.anthropic.chat.handler import ModelResponseIterator, make_call
 from litellm.types.llms.openai import (
     ChatCompletionToolCallChunk,
     ChatCompletionToolCallFunctionChunk,
@@ -9,6 +11,33 @@ from litellm.types.llms.openai import (
 from litellm.types.responses.main import OutputCodeInterpreterCall
 
 
+@pytest.mark.asyncio
+async def test_make_call_passes_logging_obj_to_client_post():
+    """make_call must pass logging_obj to client.post so track_llm_api_timing can set llm_api_duration_ms for litellm_overhead_time_ms."""
+    mock_client = AsyncMock()
+    mock_response = MagicMock()
+    mock_response.aiter_lines = MagicMock(return_value=iter([b'data: {"type":"message_start"}\n', b'data: {"type":"message_delta"}\n']))
+    mock_client.post.return_value = mock_response
+
+    logging_obj = MagicMock()
+
+    await make_call(
+        client=mock_client,
+        api_base="https://api.anthropic.com/v1/messages",
+        headers={},
+        data="{}",
+        model="claude-3-5-haiku",
+        messages=[{"role": "user", "content": "Hi"}],
+        logging_obj=logging_obj,
+        timeout=60.0,
+        json_mode=False,
+    )
+
+    mock_client.post.assert_called_once()
+    call_kwargs = mock_client.post.call_args[1]
+    assert call_kwargs.get("logging_obj") is logging_obj
+
+
 def test_redacted_thinking_content_block_delta():
     chunk = {
         "type": "content_block_start",