In my experience, if you just ask an LLM to write tests, it'll write you a ton of boilerplate happy path tests that aren't wrong, per se, they're just pointless (one fun one in react is 'the component renders').

How do you plan to handle this?

I really wonder if Claude Code and other agents keep track of these dependencies at all (I know that VS Code exposes its internal testing tools to agents, and use Anthropic and OpenAI tools with them).