We use openai-agents-js (default Responses API) to run our Multi-Agent Systems (MAS). During MAS runs, we intermittently hit the following error:
{
"error": "TypeError: terminated"
}
We’ve seen this issue for a long time, but the frequency has increased significantly over the last 2 days. It happens in both streamed and non-streamed MAS runs.
We use the gpt-4.1 and gpt-5 model families across our MASes.
Full error (from our logs):
"message": "terminated",
2026-01-14 10:07:06.941 CET
"stack": "TypeError: terminated
at Fetch.onAborted (node:internal/deps/undici/undici:11322:53)
at Fetch.emit (node:events:524:28)
at Fetch.terminate (node:internal/deps/undici/undici:10480:14)
at Object.onError (node:internal/deps/undici/undici:11443:38)
at Request.onError (node:internal/deps/undici/undici:2210:31)
at Object.errorRequest (node:internal/deps/undici/undici:1707:17)
at TLSSocket.<anonymous> (node:internal/deps/undici/undici:6433:16)
at TLSSocket.emit (node:events:536:35)
at node:net:343:12
at TCP.done (node:_tls_wrap:648:7)"
Because the SDK uses the Responses API by default, this may be related to the following thread:
This issue may also be related:
And this is the corresponding “twin” issue in the openai-agents-js repository:
If there are any known incidents, rate limits, networking changes, or recommended client settings for these model families that could explain the recent increase, we’d appreciate any guidance. We’d also like to understand whether this error is caused by our system (e.g., timeouts/aborts/network/proxy behavior) or if it’s originating from the OpenAI backend.
Hey Baki, Would you be able to open a support request with us at support@openai.com. We are asking you since we will require some more details. We want you to make sure that you add your forum username and forum link into the support request and share the case id or case subject here with us so we can track it.
We want you to please provide your request id (here and in the ticket).
In Node/undici, “terminated” often wraps a more specific cause like: UND_ERR_SOCKET (other side closed) OR UND_ERR_BODY_TIMEOUT (body timeout). Can you please provide that full error stack. (IN THE TICKET)
Can you also enable SDK debug logging and share the snippet around a failure. This guide here will help. (IN THE TICKET).
Once we have these information, we can debug this further. Thank you!