fix(exceptions.py): use correct status code for content policy exceptions

Fixes https://github.com/BerriAI/litellm/issues/4941#issuecomment-2256578732

litellm/exceptions.py

@@ -122,7 +122,7 @@ class BadRequestError(openai.BadRequestError):  # type: ignore
         self.model = model
         self.llm_provider = llm_provider
         self.litellm_debug_info = litellm_debug_info
-        response = response or httpx.Response(
+        response = httpx.Response(
             status_code=self.status_code,
             request=httpx.Request(
                 method="GET", url="https://litellm.ai"
@@ -287,16 +287,13 @@ class RateLimitError(openai.RateLimitError):  # type: ignore
         self.litellm_debug_info = litellm_debug_info
         self.max_retries = max_retries
         self.num_retries = num_retries
-        if response is None:
-            self.response = httpx.Response(
-                status_code=429,
-                request=httpx.Request(
-                    method="POST",
-                    url=" https://cloud.google.com/vertex-ai/",
-                ),
-            )
-        else:
-            self.response = response
+        self.response = httpx.Response(
+            status_code=429,
+            request=httpx.Request(
+                method="POST",
+                url=" https://cloud.google.com/vertex-ai/",
+            ),
+        )
         super().__init__(
             self.message, response=self.response, body=None
         )  # Call the base class constructor with the parameters it needs
@@ -334,7 +331,7 @@ class ContextWindowExceededError(BadRequestError):  # type: ignore
         self.llm_provider = llm_provider
         self.litellm_debug_info = litellm_debug_info
         request = httpx.Request(method="POST", url="https://api.openai.com/v1")
-        self.response = response or httpx.Response(status_code=400, request=request)
+        self.response = httpx.Response(status_code=400, request=request)
         super().__init__(
             message=self.message,
             model=self.model,  # type: ignore
@@ -377,7 +374,7 @@ class RejectedRequestError(BadRequestError):  # type: ignore
         self.litellm_debug_info = litellm_debug_info
         self.request_data = request_data
         request = httpx.Request(method="POST", url="https://api.openai.com/v1")
-        response = httpx.Response(status_code=500, request=request)
+        response = httpx.Response(status_code=400, request=request)
         super().__init__(
             message=self.message,
             model=self.model,  # type: ignore
@@ -419,7 +416,7 @@ class ContentPolicyViolationError(BadRequestError):  # type: ignore
         self.llm_provider = llm_provider
         self.litellm_debug_info = litellm_debug_info
         request = httpx.Request(method="POST", url="https://api.openai.com/v1")
-        self.response = response or httpx.Response(status_code=500, request=request)
+        self.response = httpx.Response(status_code=400, request=request)
         super().__init__(
             message=self.message,
             model=self.model,  # type: ignore
@@ -463,16 +460,13 @@ class ServiceUnavailableError(openai.APIStatusError):  # type: ignore
         self.litellm_debug_info = litellm_debug_info
         self.max_retries = max_retries
         self.num_retries = num_retries
-        if response is None:
-            self.response = httpx.Response(
-                status_code=self.status_code,
-                request=httpx.Request(
-                    method="POST",
-                    url=" https://cloud.google.com/vertex-ai/",
-                ),
-            )
-        else:
-            self.response = response
+        self.response = httpx.Response(
+            status_code=self.status_code,
+            request=httpx.Request(
+                method="POST",
+                url=" https://cloud.google.com/vertex-ai/",
+            ),
+        )
         super().__init__(
             self.message, response=self.response, body=None
         )  # Call the base class constructor with the parameters it needs
@@ -512,16 +506,13 @@ class InternalServerError(openai.InternalServerError):  # type: ignore
         self.litellm_debug_info = litellm_debug_info
         self.max_retries = max_retries
         self.num_retries = num_retries
-        if response is None:
-            self.response = httpx.Response(
-                status_code=self.status_code,
-                request=httpx.Request(
-                    method="POST",
-                    url=" https://cloud.google.com/vertex-ai/",
-                ),
-            )
-        else:
-            self.response = response
+        self.response = httpx.Response(
+            status_code=self.status_code,
+            request=httpx.Request(
+                method="POST",
+                url=" https://cloud.google.com/vertex-ai/",
+            ),
+        )
         super().__init__(
             self.message, response=self.response, body=None
         )  # Call the base class constructor with the parameters it needs

litellm/main.py

@@ -500,6 +500,16 @@ def mock_completion(
                 llm_provider=getattr(mock_response, "llm_provider", custom_llm_provider or "openai"),  # type: ignore
                 model=model,
             )
+        elif isinstance(mock_response, str) and mock_response.startswith(
+            "Exception: content_filter_policy"
+        ):
+            raise litellm.MockException(
+                status_code=400,
+                message=mock_response,
+                llm_provider="azure",
+                model=model,  # type: ignore
+                request=httpx.Request(method="POST", url="https://api.openai.com/v1/"),
+            )
         time_delay = kwargs.get("mock_delay", None)
         if time_delay is not None:
             time.sleep(time_delay)

litellm/proxy/_new_secret_config.yaml

@@ -3,7 +3,7 @@ model_list:
     litellm_params:
       model: "*"
 
-litellm_settings:
-  cache: true
-  cache_params:
-    type: redis
+# litellm_settings:
+#   cache: true
+#   cache_params:
+#     type: redis