This is an MCP Server and VS Code extension which enables LLMs to interactively debug and evaluate expressions. That means it should work with various models / clients etc. It's language-agnostic, ...
When I run extension tests on GitHub actions, there's a lot of unwanted output printed. When trying to have agents run the tests, this all ends up in the context and the model sometimes attribute ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results