Urgent.News

What's breaking now, across thousands of outlets.

More in AI

LLM streaming fallback: after the first token, the client owns the failure

A model gateway can switch providers cleanly until it has sent something to your client. After that point, every option changes an answer someone has already started reading.

  • After the first token, client owns streaming failure
  • Document gateway boundary, handle retries accordingly
  • Streaming unsuitable for tool calls, test against contract

More from Thursday 5 November →