> But by having 155 lines of source code and through continuous use of the sdk, I haven't experienced any problems
The number of lines of code being 155 lines is not an excuse to have zero tests, especially in an SDK and it doesn't mean it works.
It only means you know it 'works' on your machine and it may not work on someone else's or in another scenario.
> Actually this comment just gave me the idea of creating a file of codesys doing just this in its own repo!
Well, you've just proven my point.
The tests should be written first before you write the actual code and to just write them after the fact defeats the entire purpose of knowing what to test for and then assuming that it 'works'.
yea this boilerplate is super simple and effective. It's essentially mimicing how I use claude code and cursor, but with low level control.
A very cool thing I'm working on in this space is having an llm code with the codesys sdk, then run the code.
So imagine cursor coding a codesys file instead of doing the task directly so that it instead scripts claude code to do a sequence of actions and allows cursor/the user to simply analyze the results.
this also enables parralel claude code sessions which is super cool!
this seems simpler and more straight forward though
reply