Skip to content

Conversation

fede03billy
Copy link

What's added:

  • recognise "openai" in client factory
  • send tools as {type:"function", function:{…}}
  • re-inject <tool_call>{…}</tool_call> into content for legacy parser
  • auto-append matching role:"tool" messages after each execution
  • default model → gpt-4.1, tool_choice="auto"

Fixes the 400 error “tool_calls must be followed by tool messages” and keeps old models/vLLM working unchanged.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant