openai.BadRequestError: Error code: 400 - {'error': {'message': 'Invalid request: prompt is empty or malformed.', 'type': 'invalid_request_error', 'param': None, 'code': None}}

[aliraza108]

from openai import OpenAI
from openai.agent import Agent

client = OpenAI(api_key="sk-...") # Use your key here

Define a simple agent (no tools used)

agent = Agent(
name="TestAgent",
instructions="Answer questions as helpfully as possible.",
)

Try running the agent with an empty string (or malformed query)

response = agent.run("")
print(response)

OUTPUT:
openai.BadRequestError: Error code: 400 - {'error': {'message': 'Invalid request: prompt is empty or malformed.', 'type': 'invalid_request_error', 'param': None, 'code': None}}

[yusuf-eren]

Hi @aliraza108 , I tried to reproduce the bug but couldn't get the same response.

Here is my full code;

import asyncio
from agents import Agent, Runner

async def main():
    agent = Agent(
        name="TestAgent",
        instructions="Answer questions as helpfully as possible.",
    )

    result = await Runner.run(agent, "")
    print(result)


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

Output:

(.venv) yusuferen@Yusufs-MacBook-Pro openai-agents-python % python examples/basic/test.py
RunResult:
- Last agent: Agent(name="TestAgent", ...)
- Final output (str):
    Hello! How can I assist you today?
- 1 new item(s)
- 1 raw response(s)
- 0 input guardrail result(s)
- 0 output guardrail result(s)
(See `RunResult` for more details)

Which version do you use? And how you ran the file?

[aliraza108]

it was version error just resolved Regards, Ali Raza Abro +92-345-3808400

…

On Mon, May 19, 2025 at 9:25 PM Yusuf Eren ***@***.***> wrote: *yusuf-eren* left a comment (openai/openai-agents-python#716) <#716 (comment)> Hi @aliraza108 <https://github.com/aliraza108> , I tried to reproduce the bug but couldn't get the same response. Here is my full code; import asynciofrom agents import Agent, Runner async def main(): agent = Agent( name="TestAgent", instructions="Answer questions as helpfully as possible.", ) result = await Runner.run(agent, "") print(result) if __name__ == "__main__": asyncio.run(main()) Output: (.venv) ***@***.*** openai-agents-python % python examples/basic/test.py RunResult: - Last agent: Agent(name="TestAgent", ...) - Final output (str): Hello! How can I assist you today? - 1 new item(s) - 1 raw response(s) - 0 input guardrail result(s) - 0 output guardrail result(s) (See `RunResult` for more details) Which version do you use? And how you ran the file? — Reply to this email directly, view it on GitHub <#716 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/A4Q4HD7AZWKRYQGDOXMXAP327IAZLAVCNFSM6AAAAAB5OFX2COVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDQOJRGYYTAMRSGA> . You are receiving this because you were mentioned.Message ID: ***@***.***>