fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

litellm/proxy/common_request_processing.py

@@ -1949,12 +1949,26 @@ class ProxyBaseLLMRequestProcessing:
                 code=status.HTTP_400_BAD_REQUEST,
                 headers=headers,
             )
+        # Extract status_code from the exception if it carries one.
+        # Provider exceptions (NotFoundError, BadRequestError, GeminiError,
+        # VertexAIError, etc.) all have a status_code attribute reflecting
+        # the upstream API response. Use it to return the correct HTTP code
+        # instead of defaulting to 500.
+        _exc_status_code = getattr(e, "status_code", None)
+        if (
+            _exc_status_code is not None
+            and isinstance(_exc_status_code, int)
+            and 400 <= _exc_status_code <= 599
+        ):
+            _code = _exc_status_code
+        else:
+            _code = status.HTTP_500_INTERNAL_SERVER_ERROR
         raise ProxyException(
             message=getattr(e, "message", error_msg),
             type=getattr(e, "type", "None"),
             param=getattr(e, "param", "None"),
             openai_code=getattr(e, "code", None),
-            code=getattr(e, "status_code", 500),
+            code=_code,
             provider_specific_fields=getattr(e, "provider_specific_fields", None),
             headers=headers,
         )

tests/test_litellm/proxy/test_common_request_processing.py

@@ -2269,6 +2269,36 @@ class TestHandleLLMApiExceptionDictDetail:
         assert proxy_exc.message == "Content blocked by guardrail"
         assert proxy_exc.provider_specific_fields is None
 
+    async def test_not_found_error_preserves_404(self):
+        """NotFoundError with status_code=404 should map to ProxyException code=404."""
+        from litellm.exceptions import NotFoundError
+
+        exc = NotFoundError(
+            message="Model gemini-3.1-flash-lite-preview not found",
+            model="gemini-3.1-flash-lite-preview",
+            llm_provider="gemini",
+        )
+        proxy_exc = await self._invoke(exc)
+        assert proxy_exc.code == "404"
+        assert "NotFoundError" in proxy_exc.message
+
+    async def test_exception_with_status_code_propagates(self):
+        """Exception with a statically-set status_code should propagate it."""
+        from litellm.llms.vertex_ai.common_utils import VertexAIError
+
+        exc = VertexAIError(
+            status_code=429,
+            message="Rate limit exceeded",
+        )
+        proxy_exc = await self._invoke(exc)
+        assert proxy_exc.code == "429"
+
+    async def test_exception_without_status_code_defaults_to_500(self):
+        """Exception with no status_code attribute defaults to 500."""
+        exc = ValueError("Something broke")
+        proxy_exc = await self._invoke(exc)
+        assert proxy_exc.code == "500"
+
 
 class TestAsyncStreamingDataGeneratorFastPath:
     """Fast/slow path branching in async_streaming_data_generator."""