From 13b05af06e20b84158d41511efee690868dce288 Mon Sep 17 00:00:00 2001
From: yucheng <yucheng@berri.ai>
Date: Sat, 19 Sep 2026 16:34:53 +0000
Subject: [PATCH] fix(proxy): validate responses input after prompt template
 expansion

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 .../proxy/response_api_endpoints/endpoints.py |  2 +-
 .../response_api_endpoints/test_endpoints.py  | 68 ++++++++++++++++++-
 2 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/litellm/proxy/response_api_endpoints/endpoints.py b/litellm/proxy/response_api_endpoints/endpoints.py
index a680e445a2c..73ab7e5213f 100644
--- a/litellm/proxy/response_api_endpoints/endpoints.py
+++ b/litellm/proxy/response_api_endpoints/endpoints.py
@@ -281,7 +281,6 @@ async def responses_api(
         # instead of a polling ID that immediately fails in the background task.
         processor = ProxyBaseLLMRequestProcessing(data=data)
         try:
-            raise_if_required_body_param_missing(route_type="aresponses", data=data)
             data, _logging_obj = await processor.common_processing_pre_call_logic(
                 request=request,
                 general_settings=general_settings,
@@ -298,6 +297,7 @@ async def responses_api(
                 route_type="aresponses",
                 llm_router=llm_router,
             )
+            raise_if_required_body_param_missing(route_type="aresponses", data=data)
         except Exception as e:
             raise await processor._handle_llm_api_exception(
                 e=e,
diff --git a/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py b/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py
index 751d4753608..f7abb209015 100644
--- a/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py
+++ b/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py
@@ -181,11 +181,77 @@ async def test_responses_api_background_polling_rejects_missing_input():
 
     assert exc_info.value.code == "400"
     assert exc_info.value.param == "input"
-    processor.common_processing_pre_call_logic.assert_not_awaited()
+    processor.common_processing_pre_call_logic.assert_awaited_once()
     mock_background_streaming_task.assert_not_called()
     mock_create_initial_state.assert_not_awaited()
 
 
+@pytest.mark.asyncio
+async def test_responses_api_background_polling_accepts_input_from_prompt_template():
+    from fastapi import Response as FastAPIResponse
+    from starlette.requests import Request
+
+    from litellm.proxy._types import UserAPIKeyAuth
+    from litellm.proxy.response_api_endpoints.endpoints import responses_api
+
+    processor = MagicMock()
+    processor.common_processing_pre_call_logic = AsyncMock(
+        return_value=({"model": "gpt-4o", "input": "hello from prompt"}, MagicMock())
+    )
+    initial_state = MagicMock()
+
+    async def receive():
+        return {
+            "type": "http.request",
+            "body": b'{"model":"gpt-4o","prompt_id":"greeting","background":true}',
+            "more_body": False,
+        }
+
+    request = Request(
+        {
+            "type": "http",
+            "method": "POST",
+            "path": "/v1/responses",
+            "headers": [(b"content-type", b"application/json")],
+        },
+        receive,
+    )
+
+    with (
+        patch(  # test-quality-ok: endpoint constructs the processor directly
+            "litellm.proxy.response_api_endpoints.endpoints.ProxyBaseLLMRequestProcessing",
+            return_value=processor,
+        ),
+        patch(  # test-quality-ok: polling decision is imported inside the endpoint
+            "litellm.proxy.response_polling.polling_handler.should_use_polling_for_request",
+            return_value=True,
+        ),
+        patch(  # test-quality-ok: background task is imported inside the endpoint
+            "litellm.proxy.response_polling.background_streaming.background_streaming_task",
+            new_callable=AsyncMock,
+        ),
+        patch(  # test-quality-ok: avoid scheduling a background task in this unit test
+            "litellm.proxy.response_api_endpoints.endpoints.asyncio.create_task",
+        ),
+        patch(  # test-quality-ok: polling handler is imported inside the endpoint
+            "litellm.proxy.response_polling.polling_handler.ResponsePollingHandler.create_initial_state",
+            new_callable=AsyncMock,
+        ) as mock_create_initial_state,
+    ):
+        mock_create_initial_state.return_value = initial_state
+        result = await responses_api(
+            request=request,
+            fastapi_response=FastAPIResponse(),
+            user_api_key_dict=UserAPIKeyAuth(api_key="sk-test"),
+        )
+
+    assert result is initial_state
+    processor.common_processing_pre_call_logic.assert_awaited_once()
+    mock_create_initial_state.assert_awaited_once()
+    request_data = mock_create_initial_state.await_args.kwargs["request_data"]
+    assert request_data["input"] == "hello from prompt"
+
+
 class TestResponsesAPIEndpoints(unittest.TestCase):
     @pytest.mark.asyncio
     @patch("litellm.proxy.proxy_server.llm_router")