Realtime API tool calls causing 500 server_error response

Hi, I’ve noticed behaviour breaking my app.

If the users first message to the realtime agent is anything longer than maybe something the length of a “hi” I keep getting this error:

type: “server_error”, code: null, message: “The server had an error while processing your request. Sorry about that! Please contact us through our help center at help.openai.com if the error persists. (include session ID in your message: sess_D5sgQNEmFTy9lf1mQnwqc). We recommend you retry your request.”

Please help.

It’s breaking the app prompting us to consider switching off our use of the model.

After more testing it looks like the problem isn’t the length of the users response.

It’s actually : the need for a tool call to be performed.

I’ve also noticed this kind of behaviour has started appearing more often, and is not tied to the first interaction between the Realtime agent and the user.

To prove this I did the following:

  • replace current orchestrator & subagent setup with a simple 1 agent setup
  • remove all tool calls

The bug never appears in this simple setup no matter how many times I try to reproduce it.

Hoping these additional details will help somebody aid me in sorting this out.

Hey @Luka_Svagusa this is definitely odd. To help us understand what’s happening, please reach out to support@openai.com and include your latest Request IDs, the exact error messages you’re seeing, and the timestamps of when the issues occurred (with timezone if possible). They’ll be in the best position to investigate further.

2 Likes

I’ve been redirected to an AI chatbot.
It’s giving general advice and not helping.

Based on experience, the team will locate your support ticket and respond to you directly. If not, you can request to speak with a member of the team.
I hope this helps.

1 Like

Sounds good, thank you.

I’ll update my post with any new happening to help out the community in case somebody runs into the same issue.

1 Like