Why would model affect the ability to use tools? I just tried sonnet 4, 3.7 and gpt 4.1 without luck. Playwright opens fine from other tools where i configured it.
Someone more knowledgeable on how these LLMs are trained and fine-tuned can weigh in, but it absolutely does matter. Some models are much more "willing" to use tools (and more adept at discerning when to use them) than others.
I can't comment on why you're having this issue specifically, unfortunately.
yeah, this was not about eagerness to use a tool. It specifically listed available tools and functions and insisted it can not access this playwright related ones.
As I readily admit in my parent comment, I'm not an expert on the tool-calling mechanics. But from other threads, my understanding is it can be a manifestation of the same issue. I know that's not really helpful to you, just wanted to call out that switching models can alter this behavior.
My own "justification" is that while self-hosted is my main personal store, I maintain a paid but empty account with Bitwarden. Said empty account on their servers is to be the emergency access person for family members' personal official vaults. So, they get some money for a license out of me, without the server usage.
So that commenter must not have those generations and your comment doesn't help.
iPhone SE (1st generation) [2016] is stuck on iOS 15 but still receiving security updates, like 15.8.4 from the spring.
reply