I wonder are there linters to detect those types of mistakes for SQLAlchemy. Even though I'm aware of such pitfalls, it's nice if linters can catch them cause I'm not confident to cache them all the time during code review.

Some linters like pyright can identify dangerous defaults in function call, like `def hello(x=[]): pass` (mutable values shouldn't be a default). Linter plugins for widely-used and critical libraries like SQLAlchemy are nice to have.

The mutable-default-arguments issue is easy for a third-party to linter to catch because it doesn't require any specific knowledge about primary keys and databases. Are there static typing plugins for other common packages that would catch issues like this?

I personally use pylint, which I've found to be the most aggressive python linter.

Yea, more of an issue of how this python library can cause misunderstandings, and ChatGPT failing in the same misunderstanding that would have been made by an engineer who lacks experience in that library.

This mistake would have happened even if they did not use ChatGPT.

Ah, but it’s not a characteristic of SQLAlchemy tho. It’s how Python evaluates statements. Both Peewee and the Django ORM work on the same principle with default values.

The intent is to pass a callable, not to call a function and populate an argument with what it returns.

Correct, it's not specific to sqlalchemy - I'm just saying I notice this a lot with sqlalchemy. Probably because it was the first significant bug I had to figure out how to fix when I introduced it in one of my first apps. I guess we never forget the first time we shot ourselves in the foot.

Depending on your viewpoint, ORM are by nature a mistake.

The time people spend learning the quirks of an ORM is much better put into learning SQL.

Honestly same can be said about a lot of frameworks. You will pry my vanilla JS debugged with print statements hand-coded in vi from these hands only when they're cold and dead.

Yeah, I have a workflow where I inject JavaScript into arbitrary webpages and store the results. There’s no substitute for vanilla js knowledge when you’re in the weeds.

That explains where ChatGpt is getting that from. I guess it is only as smart as the average coder.