[FEATURE] Add --compare flag for side-by-side agent comparison

[jwesleye]

Feature Description

Send same query to multiple agents and see responses side-by-side for A/B testing.

Problem/Motivation

When evaluating different agents or models, I have to run queries multiple times and manually compare results.

Proposed Solution

chat_loop agent1 --compare agent2

# Shows both responses:
# [Agent 1]
# Response here...
# 
# [Agent 2] 
# Response here...
#
# Tokens: A1: 234, A2: 456
# Cost: A1: $0.01, A2: $0.02

Benefits

• Easy A/B testing
• Model comparison
• Quality evaluation
• Cost comparison

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-focused CLI tool.

This project is focused on providing a simple, efficient command-line interface for AWS Strands agents. Advanced features like workflow automation, collaboration tools, and complex UI enhancements would add significant complexity without serving the core use case.

We're keeping the scope focused on:

• Solid AWS Strands agent integration
• Essential CLI features (history, templates, sessions)
• Developer productivity (debugging, validation)
• Simple, maintainable codebase

Thank you for the suggestion!