Nick Hale

Closing this out. The story-book example has significantly changed since this issue was created. It's now a standalone app with a different architecture.

Closing this out as we now have a suite of unit, smoke, and e2e tests that run on PRs and merge to main.

Our smoke tests do this to some extent now. While it's doesn't exactly have "first-class gptscript support", it does use `gpt4-o` to perform fuzzy equality on the output and tool...

As of today, `sys.ls` exists, but `sys.mkdir` and `sys.readdir` do not.