Download Latest Version
v1.1.0_ 10s of thousands of training trajectories source code.tar.gz (26.5 MB)
Get an email when there's a new version of SWE-agent
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2024-06-19 | 1.6 kB | |
| v0.6.1 source code.tar.gz | 2024-06-19 | 2.3 MB | |
| v0.6.1 source code.zip | 2024-06-19 | 2.4 MB | |
| Totals: 3 Items | 4.6 MB | 0 | |
This is (mostly) a patch release, in particular fixing several issues that had been introduced by the speed improvements of v0.7.0. We also solve a bug where existing linter errors in a file left SWE-agent unable to edit (because of our lint-retry-loop).
Breaking changes
- Change: sparse clone method is now correctly called "shallow" by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/591
Improved
- Enh: Show commands when encountering timeout error by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/582
- Enh: Configuration option to show time in log by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/583
- Enh: Allow to configure LONG_TIMEOUT for SWEEnv by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/584
- Enh: Always write log to traj directory by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/588
Fixed
- fix
docker.errors.NotFoundby @klieret in https://github.com/princeton-nlp/SWE-agent/pull/587 - Fix: Revert to full clone method when needed by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/589
- Fix: Refresh container_obj before querying status by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/590
- Fixed [#571] - show message that model arg is ignored in case of using Azure OpenAI by @jank in https://github.com/princeton-nlp/SWE-agent/pull/592
- Fix: Linting blocks for existing lint errors by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/593
- Fix: Process done marker not found in read with timeout by @klieret in https://github.com/princeton-nlp/SWE-agent/pull/596