Running Agents in Parallel and Traces

[nikhil-pandey]

Please read this first

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

Question

Running agents in parallel following this example https://github.com/openai/openai-agents-python/blob/main/examples/agent_patterns/parallelization.py

    with trace("Coding Agent"):
        solutions: list[RunResult] = await asyncio.gather(
            *[Runner.run(coding_agent, prompt) for _ in range(3)]
        )

Ends up sending multiple traces but only one is populated.

Is this expected?

[rm-openai]

Not expected. Let me look into this.

[rm-openai]

@nikhil-pandey I ran this script and it only produced one trace. Do you have a script/example I can try that reproduces this error?

import asyncio

from agents import Agent, Runner, trace


async def main():
    agent = Agent(
        name="Assistant",
        instructions="You only respond in haikus.",
    )

    with trace("Hello world"):
        results = await asyncio.gather(
            *[Runner.run(agent, "Tell me about recursion in programming.") for _ in range(3)]
        )

    for result in results:
        print(result.final_output)


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

[nikhil-pandey]

Cant reproduce it anymore 🙃

[rm-openai]

Ah ok sounds good. Let me know if it happens again and I can debug (even if it reproduces intermittently, send me some code and I can poke around)