A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 7, 21:30 UTC
[CI] Skip Responses API (#34990)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Feb 23, 2026 at 10:46 UTC
d13ece38d73adeafab8f9aa60c73a46ef741f6c8
1 file changed
+4
tests/entrypoints/openai/responses/test_harmony.py
+4
@@ -906,6 +906,10 @@ async def test_function_calling_no_code_interpreter_events(
906
907
@pytest.mark.asyncio
908
@pytest.mark.parametrize("model_name", [MODEL_NAME])
909
+@pytest.mark.skip(
910
+ reason="This test is flaky in CI, needs investigation and "
911
+ "potential fixes in the code interpreter MCP implementation."
912
+)
913
async def test_mcp_code_interpreter_streaming(client: OpenAI, model_name: str, server):
914
tools = [{"type": "mcp", "server_label": "code_interpreter"}]
915
input_text = (