The output panel shows "Request failed" after the task is completed

[ynywna]

Please read this first

• Have you read the docs?Agents SDK docs
• Have you searched for related issues? Others may have had similar requesrs

Question

The model is started using vllm, and the task uses to_input_list. After the task is completed, it still outputs Request failed.

[ynywna]

Code and Output

Code

from agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel, set_default_openai_client, trace
import asyncio

vllm_client = AsyncOpenAI(
    api_key="EMPTY",
    base_url="http://121.61.42.5:7744/v1"
)
set_default_openai_client(vllm_client)

async def conversation_agent():
    agent = Agent(
        name="ConversationAgent",
        model=OpenAIChatCompletionsModel(
            model="qwen",
            openai_client=vllm_client,
        ),
        instructions="Please answer the questions very concisely in an American context."
    )
    result = await Runner.run(agent, input="Where is Central Park located?")
    print(result.final_output)

    new_input = result.to_input_list() + [
        {"role": "user", "content": "Please describe the lifestyle in New York City."},
    ]
    result = await Runner.run(agent, input=new_input)
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(conversation_agent())

###Output:

Central Park is located in Manhattan, New York City.

New York City lifestyle is fast-paced, diverse, and energetic. It combines bustling streets, endless entertainment, world-class cuisine, and a 24-hour subway. Residents often prioritize career and social life, embracing the city’s vibrant cultural scene and varied neighborhoods.

Request failed: [Errno 101] Network is unreachable

Request failed: [Errno 101] Network is unreachable

Request failed: [Errno 101] Network is unreachable

Max retries reached, giving up on this batch.

[moseshu]

from agents import set_tracing_disabled
set_tracing_disabled(True)

or 
with trace("test"):
   await Runner.run(agent, input="Where is Central Park located?")
......

read the doc https://openai.github.io/openai-agents-python/config/

[ynywna]

Thanks, I used set_tracing_disabled(True) to solve the problem, but using trace("test") alone still causes the same issue

[litaolaile]

,i have another problem

from agents import set_tracing_disabled
set_tracing_disabled(True)

or
with trace("test"):
await Runner.run(agent, input="Where is Central Park located?")
......
read the doc https://openai.github.io/openai-agents-python/config/

[github-actions]

This issue is stale because it has been open for 7 days with no activity.