{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreib2moramrx6ax2f4zywyawzri7x4l5txerebiibj4ryxqjkyylikq",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mej53ff2f242"
  },
  "path": "/t/realtime-api-tool-calls-causing-500-server-error-response/1373435#post_2",
  "publishedAt": "2026-02-10T12:13:40.000Z",
  "site": "https://community.openai.com",
  "textContent": "After more testing it looks like the problem isn’t the length of the users response.\n\nIt’s actually : the need for a tool call to be performed.\n\nI’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.\n\nTo prove this I did the following:\n\n  * replace current orchestrator & subagent setup with a simple 1 agent setup\n  * remove all tool calls\n\n\n\nThe bug never appears in this simple setup no matter how many times I try to reproduce it.\n\nHoping these additional details will help somebody aid me in sorting this out.",
  "title": "Realtime API tool calls causing 500 server_error response"
}