Initialize ai agents documentation

[T4rk1n]

Add claude/ai agents documentation for the project.

[github-actions]

Thank you for your contribution to Dash! 🎉

This PR is exempt from requiring a linked issue due to its labels.

[AnnMarieW]

Who is the audience for the docs? Is it MCP/LLM runtime docs?

The COMMANDS.md TESTING.md and RENDERER.md seems like it's more relevant to a dash contributor.

How was the file generated? The TROUBLESHOOTING.md looks shallow and some of it is incorrect, for example:

"Circular dependency detected"
Cause: Callback output is also its own input (directly or indirectly).

Solution: Restructure callbacks to break the cycle. Use State instead of Input where possible, or split into multiple callbacks.

[T4rk1n]

Who is the audience for the docs? Is it MCP/LLM runtime docs?

It's AI generated and for AI agents like claude. It is meant to describe the project context. The TESTING describe how dash_duo works since it's part of the framework. If it's useful to a dash contributor then I think it's doing a good job.

The TROUBLESHOOTING part I was not really sure, it was a suggestion from claude to add it. If you notice incorrect info please add in a review.

[AnnMarieW]

OK - I thought this was docs for the MCP server. For dash contributors, this looks good. Not sure how useful the troubleshooing part is for this use-case.

[KoolADE85]

similar to the "Quick Reference" I don't think we should have duplicate examples.