Problem

We have no visibility into how GitHub Copilot CLI interacts with azd. There is no coverage for measuring LLM interactions, command discoverability, or human usability patterns.

Proposal

Add a comprehensive evaluation and testing framework at cli/azd/test/eval/ covering:

• LLM eval (how well an AI agent uses azd)
• Non-LLM unit tests (how well azd surfaces information for human and AI consumption)

See PR #7202 for implementation.