[FEATURE] Add --validate flag to check agent health

[jwesleye]

Feature Description

Run health checks on an agent before starting chat (dependencies, API keys, imports).

Problem/Motivation

I often discover issues (missing dependencies, invalid API keys, import errors) only after starting the agent.

Proposed Solution

chat_loop myagent --validate
# ✓ Dependencies installed
# ✓ API keys present
# ✓ Agent imports successfully
# ✗ Tool 'search_web' missing API key

Benefits

• Catch configuration issues early
• Useful in CI/CD pipelines
• Better onboarding experience

Priority

• Critical
• High
• Medium
• Low

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity.
It will be closed in 14 days if no further activity occurs.

If this issue is still relevant, please:

• Comment to keep it open
• Remove the "status: stale" label
• Provide additional information or updates

Thank you for your contributions!

[jwesleye]

Closing as out of scope for this AWS Strands CLI tool.

This project is focused on providing a simple, straightforward interface for AWS Strands agents. Advanced developer tooling adds complexity that doesn't serve the core use case of interactive agent conversations.

For these needs, we recommend:

• Debug/logging: Use Python's standard logging or AWS Strands' built-in debugging
• Agent validation: Test agents directly before using with chat loop
• Configuration: Edit ~/.chatrc directly (simple YAML file)
• Dry-run/testing: Use agents in test mode independently

Keeping the scope focused on being a great chat interface for AWS Strands agents.

Thank you for the suggestion!