[0xbadcafebee]

Call me crazy, but wouldn't 15 minutes on GLM 5.1 produce a working implementation? I haven't looked at the code, but a non-production-grade Go implementation can't be that complicated.

Edit: Minio is written in Go, and is AGPL3... fork it (publicly), strip out the parts you don't want, run it locally.

[Havoc]

I did exactly that. 15 mins for initial implementation was about right. And it seemed fine at first glance.

Then I decided to run the Ceph S3 test suite against it. So many issues. Think it passed 3 tests on first run out of I think about a hundred. Took another couple of hours to get it to a state that is even vaguely passable for non production use.

Got something vaguely workable but even after many hours I can’t say I super trust it

> implementation can't be that complicated.

S3 has a fair bit of bloat in spec that nobody seems to use and it’s not clearly delineated which is core and what’s ahem optional. I ended up relying on the LLM to figure out what’s core and that ended up missing stuff too so that needed a couple of feature iterations too

[0xbadcafebee]

Would you be willing to share the result on the web somewhere? Would save a few tokens (and hours) for others who end up doing the same