Thankyou and same to you. Last year for me was rough in many ways, watching a classmate from my high school go on trial for probably the world's most famous triple-murder in recent memory.
It affected me so deeply and of course I didn't understand why, so I went head first into self-discovery to try and understand it. Not sure I 100% have the answer yet but well on the way.
On the bright side, I managed to keep the weight off I had spent 4 years losing (35 kg!) and of course work is as wonderful as ever for me. So all that was good.
Happy new year all - may 2026 be better year for everyone.
No I was sharing an example of a framework that does include "a testing system that allows it to inject mouse events".
That being said mouse events and similar isn't hard to do, e.g. start with a fixed resolution (using xrandr) then xdotool or similar. Ideally if the application has accessibility feature it won't be as finicky.
My point though was just to show that testing with GUI is not infeasible.
Apparently there is even a "UI Testing for devs & agents" https://www.chromatic.com which I found via Visual TDD https://www.chromatic.com/blog/visual-test-driven-developmen... I can't recommend this but it does show even though the person I was replying with can't use Puppeteer in their context the tooling does exist and the principles would still apply.
Exactly. There's an impedance mismatch between those using the free/cheap tiers and those paying a premium, so the discussion gets squirrely because one side is talking about apples and the other oranges.
It's ultimately just a prompt, self-hosted models can use the system the same way, they just might struggle to write good SQL+vector queries to answer your questions. The prompt also works well with Codex, which has a lot of usage.
If you're not willing to pay for your own LLM usage to try a free resource offered by the author, that's up to you. But why complain to the author about it? How does your comment enrich the conversation for the rest of us?
reply