Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: 📒 Files selected for processing (1)
Included review availability: Your plan provides up to 1 included review per hour; 0 remain after this review. 📝 WalkthroughWalkthroughThe project catalog adds ChangesProject catalog
Priority: ⬇️ Low Estimated code review effort: 1 (Trivial) | ~2 minutes Change: Other Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
Landed on main as 402747c with you as the commit author, so it shows on your contributions. Live at https://awesomejev.com/#applications. Closing the PR rather than merging because the site's data file gets appended to nightly, which makes fork branches conflict faster than they can be reviewed. Landing the entry directly keeps your authorship without force-pushing to your fork. Thanks for the submission. |
Adds jselect with factual descriptions of their Jev decisions. Existing listings are left intact.
Maintainer submission from @keltokhy, the author of the linked MIT-licensed Python projects. These are AI-assisted projects; Codex prepared this submission and performed the source inspection and offline checks below. No independent human review or live model evaluation is claimed.
jselect
https://github.com/keltokhy/jselect
Jev judges whether each passage is useful evidence for the supplied task; local code selects verbatim passages and citations within the token budget.
Primitive: Noul. Setup and usage: jselect README. Live inference uses a configured provider and can incur charges.
Inspected public revision:
460b217110a6fa2f3546813f1dc4f77b062e82cd(2026-09-20).Offline validation:
uv run --group dev pytest -q tests/test_judge_cli.py tests/test_selection.py— 59 passed in 0.93s. These checks establish code behavior with fixtures; they do not establish model accuracy. No performance claims are included in this proposal.Catalog validation:
npm run validate.Need help on this PR? Tag
@codesmith-botwith what you need. Autofix is disabled.Summary by CodeRabbit