What's Changed

✨ The big news is our brand new documentation ✨

Secondly, @ollmer added a new flag --cache_task_images that will significantly speed up SWE-agent when running on the same environment/repository multiple times (no more waiting for cloning and installation!)

Breaking changes

• We have reformatted our codebase. If you create a PR based on a previous commit, make sure you install our pre-commit hook to avoid merge-conflicts because of formatting. See our docs for more information.
• Remove direct imports in __init__.py (you can no longer from sweagent import Agent by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/436

Added

• Running the web UI is now supported when running swe-agent completely in docker
• Speed up evaluation by caching task environments as docker images by @ollmer in https://github.com/princeton-nlp/SWE-agent/pull/317

Improved

• Add gpt-4o model by @raymyers in https://github.com/princeton-nlp/SWE-agent/pull/344
• Web: Allow to specify commit hash by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/358
• Add default environment_setup config by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/351
• Enh: Suppress openai logging; improve formatting of stats by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/416
• Remove signal dependency by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/428
• Do not use select if running on Windows by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/429
• Use custom Config class to support env and keys.cfg (this allows passing keys as environment variables) by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/430

Fixes

• Web: Fix script_path input by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/334
• Fix: Don't print patch msg for exit_cost patch by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/343
• Fix: Do not request job control in bash by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/345
• Fix: --base_commit not used for gh urls by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/346
• Fix: Separate data path/traj dir cause exception by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/348
• Add docker-py lower bound by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/406
• Fix: IndexError when replaying incomplete trajectories by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/410

New Contributors

• @raymyers made their first contribution in https://github.com/princeton-nlp/SWE-agent/pull/344
• @nims11 made their first contribution in https://github.com/princeton-nlp/SWE-agent/pull/332
• @khangich made their first contribution in https://github.com/princeton-nlp/SWE-agent/pull/274
• @ollmer made their first contribution in https://github.com/princeton-nlp/SWE-agent/pull/317

Full Changelog: https://github.com/princeton-nlp/SWE-agent/compare/v0.4.0...v0.5.0