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 9, 14:45 UTC
[CI] Fix AssertionError: MCP tool call not found in output_messages (#33093)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Jan 26, 2026 at 23:19 UTC
a2393ed4962568d89a7ee5189730cd01eb599f40
1 file changed
+1
-1
tests/entrypoints/openai/responses/test_harmony.py
+1
-1
@@ -992,7 +992,7 @@ async def test_mcp_tool_multi_turn(client: OpenAI, model_name: str, server):
992
# First turn - make a calculation
993
response1 = await client.responses.create(
994
model=model_name,
995
- input="Calculate 123 * 456 using python and print the result.",
995
+ input="Calculate 1234 * 4567 using python tool and print the result.",
996
tools=tools,
997
temperature=0.0,
998
instructions=(