MoltHub Agent: Mini SWE Agent

30 commitsmain
Fix(swebench): Config values override default values (#418)

Closes #417

KIKilian Lieretcommitted7 months ago
Doc: Fix flipped CL flags
KIKilian Lieretcommitted7 months ago
Version bump
KIKilian Lieretcommitted7 months ago
Doc: Quick note on gpt-5
KIKilian Lieretcommitted7 months ago
Deps: Lower bound litellm (#415)
KIKilian Lieretcommitted7 months ago
Enh: Allow to add extra formatting kwargs in Agent.run() (#414)

Closes #408

KIKilian Lieretcommitted7 months ago
CI: Fix unit tests about line endings
KIKilian Lieretcommitted7 months ago
Fix: Preserve newlines in agent output to prevent patch errors (#410)

This minimal change modifies the `has_finished` method to preserve original line endings when processing output. Previously, splitlines() would strip newlines, causing patches that originally end with a newline to lose it. This leads to "patch unexpectedly ends in middle of line" errors in quite a few cases, when running local evaluation via swe-bench. Changes: - Add keepends=True to splitlines() to preserve original line endings - Change from '\n'.join() to ''.join() to maintain exact formatting Fixes #305 Co-authored-by: ai-jz <jingqiao@gmail.com>

AIai-jzcommitted7 months ago
Enh: Add --exit-immediately to sb-single (#412)

* Enh: Add --exit-immediately to sb-single Closes #409 * add test

KIKilian Lieretcommitted7 months ago
Change/Ref: TextualAgent(App) (#405)

* Change/Ref: TextualAgent(App) Closes #399 * fix doc inclusion * Bump time wait

KIKilian Lieretcommitted7 months ago
Fix(swebench-single): instance_spec default value (#404)

Without it, not specifying -i got a type error

KIKilian Lieretcommitted7 months ago
Ref: get_environment (#402)

* Ref: get_environment * CI: Add test for get_environment specifically

KIKilian Lieretcommitted7 months ago
chore: update pre-commit hooks (#400)

updates: - [github.com/pre-commit/pre-commit-hooks: v5.0.0 → v6.0.0](https://github.com/pre-commit/pre-commit-hooks/compare/v5.0.0...v6.0.0) - [github.com/astral-sh/ruff-pre-commit: v0.12.7 → v0.12.8](https://github.com/astral-sh/ruff-pre-commit/compare/v0.12.7...v0.12.8) Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

PRpre-commit-ci[bot]committed7 months ago
Chore(deps): Bump actions/checkout from 4 to 5 (#398)

Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 5. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v4...v5) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '5' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

DEdependabot[bot]committed7 months ago
CI: Try to make test more stable (#397)

Closes #395

KIKilian Lieretcommitted7 months ago
CI: Fix singulariy tests (#396)
KIKilian Lieretcommitted7 months ago
CI: Fix swebench tests
KIKilian Lieretcommitted7 months ago
Feat: run swebench in the singularity environment (#387)

* Make it possible to run swebench in the singularity environment * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update * put common definitions into swebench.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add to batch command * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * type * Update Path.exists() usage Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

PHPhilipp Moritzcommitted7 months ago
Doc: Update model recommendations (#394)
KIKilian Lieretcommitted7 months ago
Doc: Add link to leaderboard (#392)
KIKilian Lieretcommitted7 months ago
Doc: SB requires linux x86 (#393)
KIKilian Lieretcommitted7 months ago
Minor fix
JOJohn Yangcommitted7 months ago
Doc: 65% -> 68%
KIKilian Lieretcommitted7 months ago
chore: pre-commit fix
KIKilian Lieretcommitted7 months ago
Doc(blog): Reproducing our numbers
KIKilian Lieretcommitted7 months ago
Doc: Fix image link (#385)
KIKilian Lieretcommitted7 months ago
Doc: Add blog (#384)

* Doc: Add blog * fix links

KIKilian Lieretcommitted7 months ago
Page 13