Skip to content

Add Responses API support#1263

Draft
blairhudson wants to merge 1 commit intoml-explore:mainfrom
blairhudson:responses
Draft

Add Responses API support#1263
blairhudson wants to merge 1 commit intoml-explore:mainfrom
blairhudson:responses

Conversation

@blairhudson
Copy link
Copy Markdown

@blairhudson blairhudson commented May 9, 2026

Summary

  • Add OpenResponses-compatible /v1/responses, streaming, WebSocket, and compaction support.
  • Add server tests and docs for Responses API behavior.

Related to #815

Try it:

uv tool install "git+https://github.com/blairhudson/mlx-lm.git@responses"
mlx_lm.server --model mlx-community/Qwen1.5-0.5B-Chat-4bit --port 8080

@blairhudson
Copy link
Copy Markdown
Author

@angeloskath would love your directional review of this draft please and if you're onboard what you'd need to see to be confident in adding Responses API support

@reneleonhardt
Copy link
Copy Markdown

Thank you for your work! ❤️

900 lines for 1 endpoint (and /compact) sounds a bit much, how much will the test coverage be decreased?

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.

2 participants