_zer0c00l_

what problem is this helper trying to solve?

I have one (at least) fundamental concern about the approach - let's say I'm building an anti-fraud system that uses AI (through API), and maybe I'm asking AI whether my user totally+fraud@gmail.com is a potential fraudster. By masking this email address I'm sabotaging my own AI prompt - the AI cannot longer reason based on the facts that 1) the email is a free public email 2) the email says 'fraud' right in your face.

I love the design, it's really cool. Do you have data that supports your hypothesis that users care about "their files leaving their computers"?

There is one potential issue with scanning the entire codebase IMHO - if the codebase is old enough, there can be old snippets of code that DON'T correspond to the current preferences anymore. So scanning the last 200 PRs and reading comments is a bit safer maybe.

This is what my vibe coded PoC did - it just used GitHub API to go through the last X merged PRs, see the diffs and all discussions and create a document based on that - the developer manifesto kind of, a set of preferences and rules for this dev team. Then, use this manifesto as context whenever reviewing new PRs

You can do this with OpenRouter though, can't you? They have a markup which is annoying, but they also have a long list of LLMs

Your example is with Codex - OpenAI could implement this easily on their end right? Every prompt of yours was an API call and they have a log, they can easily re-create a quick history of what you did/asked for before?

how does this scale - what if you have 50 Linux instances? the screenshot only has 3 or 4 so that looks good

I think CodeRabbit/others do this already? They learn from your code base/previous PRs, then use that in the future. I built a mini PoC of this a few weeks ago as well, out of curiosity