refactor: instrument body param to bubble up on exception

litellm/llms/base_llm/chat/transformation.py

@@ -51,6 +51,7 @@ class BaseLLMException(Exception):
         headers: Optional[Union[dict, httpx.Headers]] = None,
         request: Optional[httpx.Request] = None,
         response: Optional[httpx.Response] = None,
+        body: Optional[dict] = None,
     ):
         self.status_code = status_code
         self.message: str = message
@@ -67,6 +68,7 @@ class BaseLLMException(Exception):
             self.response = httpx.Response(
                 status_code=status_code, request=self.request
             )
+        self.body = body
         super().__init__(
             self.message
         )  # Call the base class constructor with the parameters it needs

litellm/llms/openai/common_utils.py

@@ -19,6 +19,7 @@ class OpenAIError(BaseLLMException):
         request: Optional[httpx.Request] = None,
         response: Optional[httpx.Response] = None,
         headers: Optional[Union[dict, httpx.Headers]] = None,
+        body: Optional[dict] = None,
     ):
         self.status_code = status_code
         self.message = message
@@ -39,6 +40,7 @@ class OpenAIError(BaseLLMException):
             headers=self.headers,
             request=self.request,
             response=self.response,
+            body=body,
         )
 
 

litellm/llms/openai/openai.py

@@ -828,13 +828,17 @@ class OpenAIChatCompletion(BaseLLM):
             except Exception as e:
                 exception_response = getattr(e, "response", None)
                 status_code = getattr(e, "status_code", 500)
+                exception_body = getattr(e, "body", None)
                 error_headers = getattr(e, "headers", None)
                 if error_headers is None and exception_response:
                     error_headers = getattr(exception_response, "headers", None)
                 message = getattr(e, "message", str(e))
 
                 raise OpenAIError(
-                    status_code=status_code, message=message, headers=error_headers
+                    status_code=status_code,
+                    message=message,
+                    headers=error_headers,
+                    body=exception_body,
                 )
 
     def streaming(

litellm/model_prices_and_context_window_backup.json

@@ -6057,26 +6057,6 @@
         "mode": "chat",
         "supports_tool_choice": true
     },
-    "jamba-large-1.6": {
-        "max_tokens": 256000,
-        "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "input_cost_per_token": 0.000002,
-        "output_cost_per_token": 0.000008,
-        "litellm_provider": "ai21",
-        "mode": "chat",
-        "supports_tool_choice": true
-    },
-    "jamba-mini-1.6": {
-        "max_tokens": 256000,
-        "max_input_tokens": 256000,
-        "max_output_tokens": 256000,
-        "input_cost_per_token": 0.0000002,
-        "output_cost_per_token": 0.0000004,
-        "litellm_provider": "ai21",
-        "mode": "chat",
-        "supports_tool_choice": true
-    },
     "jamba-1.5-mini": {
         "max_tokens": 256000,
         "max_input_tokens": 256000,
@@ -6097,6 +6077,26 @@
         "mode": "chat",
         "supports_tool_choice": true
     },
+    "jamba-large-1.6": {
+        "max_tokens": 256000,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.000008,
+        "litellm_provider": "ai21",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
+    "jamba-mini-1.6": {
+        "max_tokens": 256000,
+        "max_input_tokens": 256000,
+        "max_output_tokens": 256000,
+        "input_cost_per_token": 0.0000002,
+        "output_cost_per_token": 0.0000004,
+        "litellm_provider": "ai21",
+        "mode": "chat",
+        "supports_tool_choice": true
+    },
     "j2-mid": {
         "max_tokens": 8192,
         "max_input_tokens": 8192,

tests/llm_translation/test_openai.py

@@ -391,3 +391,34 @@ def test_openai_chat_completion_streaming_handler_reasoning_content():
     )
 
     assert response.choices[0].delta.reasoning_content == "."
+
+
+@pytest.mark.parametrize("sync_mode", [True, False])
+@pytest.mark.parametrize("stream_mode", [True, False])
+@pytest.mark.asyncio
+async def test_exception_bubbling_up(sync_mode, stream_mode):
+    """
+    make sure code, param, and type are bubbled up
+    """
+    import litellm
+
+    litellm.set_verbose = True
+    with pytest.raises(Exception) as exc_info:
+        if sync_mode:
+            litellm.completion(
+                model="gpt-4o-mini",
+                messages=[{"role": "usera", "content": "hi"}],
+                stream=stream_mode,
+                sync_stream=sync_mode,
+            )
+        else:
+            await litellm.acompletion(
+                model="gpt-4o-mini",
+                messages=[{"role": "usera", "content": "hi"}],
+                stream=stream_mode,
+                sync_stream=sync_mode,
+            )
+
+    assert exc_info.value.code == "invalid_request_error"
+    assert exc_info.value.param == "messages"
+    assert exc_info.value.type == "invalid_request_error"