[gdal-dev] Integrating AI assisted code review for PR in OSGeo/GDAL?

[Edouard Choinière]

One of my repos (MegaLinter) has the free tier of Cursor Bugbot enabled. Theres a number of PRs per month included. Appart from the PR summary added beneath (that isn’t so useful, but sometimes useful to double-check that something else isn’t squeezed in), I kinda started to like it for finding inconsistencies between files in the repo, ie, you’re changing something here, but another place (or docs) contradicts it or won’t work with the changes. It’s probably not unique to that product, I don’t even know what’s the model behind, I didn’t configure it myself.

After the limit of free reviews in the month, it’s shuts off and doesn’t annoy anyone.

For external contributors, usually they touch up once or twice their PRs with that AI review for simple mistakes and when we get to review it, there’s way less to look at.

Edouard Choinière

> Le 2 avr. 2026 à 09:42, Even Rouault <even.rouault at spatialys.com> a écrit :
> 
> Hi,
> 
> I think it could be worth to have the *possibility* of requiring an AI assisted review for pull requests, directly available from our canonical repo. I've been occasionaly experimenting Gemini Code Assist and Copilot in my personal fork. Copilot had repeated failures a few weeks ago but seems to have been fixed recently, so I've more experience with /gemini review. I find it useful and it has spotted real issues, some of them would have probably went unnoticed during classic human review, and with an acceptable rate of false positives or debatable remarks.
> 
> So my proposal would be to have the tool(s)  enabled in OSGeo/GDAL repo, *on demand* (not sure if that's possible for Copilot. Is that a setting? Although I'm not trusting github enough to be sure if we want to increase our use of it.  Gemini review is definitely on demand and an external github app we can disable in one click) for developers or reviewers that want to trigger them. I don't think having them to run systematically is a good idea, because some PRs are too trivial to get any benefit from them, and having them enabled systematically lead to noise as PR comments and notifications.
> 
> I definitely don't think those tools should replace human review. AI tools are instructed to flatter your ego and will never say your PR is a bad idea, which a human reviewer will occasionally say. Or they lack the global picture, etc. I see them as additional tools on top of our CI instrumentation and human review.
> 
> Anyone with experience in that area and thoughts?
> 
> Even
> 
> --
> http://www.spatialys.com
> My software is free, but my time generally not.
> 
>