Live data from Hacker News

Open Code Review – An AI-powered code review CLI tool

github.com

81–89 of 89 posts

Re: Open Code Review – An AI-powered code review CLI tool

#81
post #66

Earlier quoted context omitted.

Which LLM did you use? I assume that will make a pretty big difference.

gpt-5-mini and gpt-5.5 (had to tweak the code a bit to make it work) Surprisingly not as big of a difference as one would hope. It turns out that smarter models are more conservative. Smarter model / More thinking = slightly worse recall sometimes. I think it says more about the benchmark itself perhaps. Reviews are highly opinionated. And it could be that the smarter models are actually better, just the “golden” sta…

That must have been expensive! Thanks for running the benchmark and sharing.

I tested Coducky (my AI review macos app) on the full 50-PR Martian benchmark using qwen3.7-plus via OpenRouter as the reviewer with a lightweight pre-save precision gate with deepseek-v4-flash. The score (gpt 5.2 judge) was 43.0% precision / 35.8% recall / 39.0 F1. That puts it about inline with CodeRabbit. This cost around $7 to run the full 50 PRs.

Your post inspired me to set up a test harness for my app to continue to test model combinations. Coducky allows you to select whichever models/subscriptions you like to run reviews, but it could make sense to build a collection of model combinations that work well for this.

Re: Open Code Review – An AI-powered code review CLI tool

#83

Thank you all for the interest in Open Code Review! This project was incubated from an AI code review tool that has been widely used by developers inside Alibaba at scale. The reason we decided to open-source it is simple — we noticed that many developers in the community are either paying for similar tools or using skills to perform AI code reviews. As someone who has done deep research in this space, I think skills…

The divide and conquer strategy is not actually implemented though.

Re: Open Code Review – An AI-powered code review CLI tool

#84

A repo with the English translation of each of the rules files, using Google Translate: https://github.com/pramodbiligiri/open-code-review-rules . The original rules files (in Chinese): https://github.com/alibaba/open-code-review/tree/main/intern...

The project lead has since mainlined the translation: https://github.com/alibaba/open-code-review/commit/8c4463f65...

I wonder what it means for prompts to go from Mandarin / Cantonese to English...

Re: Open Code Review – An AI-powered code review CLI tool

#87

Ran it on a subset of 10 of the 50 PRs in this benchmark https://codereview.withmartian.com - very good recall (~74%, e.g. found a lot of the golden issues) - not so good precision (~12%, e.g. lots of false positives) - the precision causes the F1 to tank (~20%, if this stays the same on the full 50 sample it would puts it almost last, even less than Kilo+Grok)

Thank you for sharing these results and for running the evaluation! We noticed that in the version tested, there was an anomaly in a critical tool call that significantly impacted the overall performance — particularly contributing to the high false positive rate you observed. We were able to reproduce the issue on the benchmark and have since fixed it. We appreciate you taking the time to highlight this, and we look forward to seeing how it performs on the full 50-sample evaluation!

Re: Open Code Review – An AI-powered code review CLI tool

#88
post #41

Is not working with gpt5.x models (Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.) which is hardcoded. I dont know why this is on the front page. My review-with-codex skill is working just fine, consuming my usage and not API tokens.

Managed to get it to work with those actually. (Had to change the code of course)

This issue has been fixed. Welcome to use the latest version.

Re: Open Code Review – An AI-powered code review CLI tool

#89
post #83

Thank you all for the interest in Open Code Review! This project was incubated from an AI code review tool that has been widely used by developers inside Alibaba at scale. The reason we decided to open-source it is simple — we noticed that many developers in the community are either paying for similar tools or using skills to perform AI code reviews. As someone who has done deep research in this space, I think skills…

The divide and conquer strategy is not actually implemented though.

[flagged]
Post reply on HN