All-Hands-AI/OpenHands 0.12.0

on GitHub

What's Changed

This release contains improvements that allow OpenHands to score 53% on SWE-Bench Verified & 41.7% on SWE-Bench Lite, making it the best OSS AI SWE system now: swe-bench/experiments#97

Added

• Add function calling to CodeAct 2.1 by @xingyaoww in #4537
• Display error messages in the chat by @amanape in #4509
• Support prompt caching on the latest claude-3-5-sonnet-20241022 by @xingyaoww in #4552

Changed

• Pared down the backend logging to make it less verbose and more informative by @rbren in #4563

Fixed

• Split bash commands by the new line character by @tofarr in #4462
• Bugfix for loading the /app page directly by @rbren in #4547
• Fix for connection leak by @tofarr in #4560
• Fix for crash on some models on OpenRouter by @enyst in #4641
• Fix compatibility for models like llama on Groq that don't support vision or tools by @enyst in #4644

New Contributors

• @msehsah1 made their first contribution in #4580

Full Changelog: 0.11.0...0.12.0