[Code Quality] Add engine comparison table to help users choose AI engine

[github-actions]

Description

Users need a clear comparison of AI engines (Claude, Copilot, Codex) to make informed decisions. Currently, the documentation explains each engine separately but never compares them, leaving users uncertain about feature parity.

Affected File

docs/src/content/docs/reference/engines.md

Missing Information

Users cannot easily answer these questions:

• What features work with Claude vs Copilot?
• When should I choose Claude over Copilot?
• What am I giving up by not using Copilot?
• Are there performance differences?

Suggested Addition

Add a comparison table after the introduction section:

## Engine Comparison

| Feature | Copilot CLI | Claude | Codex |
|---------|-------------|--------|-------|
| All workflow triggers | ✅ | ✅ | ✅ |
| GitHub tools & MCP | ✅ | ✅ | ✅ |
| Safe outputs | ✅ | ✅ | ✅ |
| Custom MCP servers | ✅ | ✅ | ✅ |
| Web search (MCP) | ⚠️ Tavily MCP | ✅ Built-in + MCP | ⚠️ Tavily MCP |
| Agent sessions | ✅ | ❌ | ❌ |
| Bot assignments | ✅ | ❌ | ❌ |
| Setup complexity | PAT required | API key | API key |

### When to Choose

- **Claude**: Best for general-purpose automation, excellent reasoning, simple API key setup, production-ready
- **Copilot**: Best when you need agent sessions or Copilot bot assignments, already have Copilot subscription
- **Codex**: Alternative OpenAI-based option for users with OpenAI access

### Feature Parity

95%+ of features work identically across all engines. Only Copilot-specific bot integration features (agent sessions, bot assignments) require Copilot.

Impact

Severity: Medium
Audience: All new users, particularly non-Copilot users
Benefit:

• Reduces confusion during engine selection
• Increases confidence in Claude/Codex adoption
• Provides transparency about trade-offs

Success Criteria

• Comparison table added to engines.md
• Table shows feature parity clearly
• "When to choose" guidance provided
• Documentation builds successfully
• Table is accurate (verify against current engine capabilities)

Source

Extracted from Claude Code User Documentation Review discussion #12027

Finding: Obstacle 2 - No Side-by-Side Engine Comparison
Priority: Medium
Effort: Medium (requires verification of features)

Additional Context

The comparison table should emphasize that engines are functionally equivalent for 95% of use cases, with differences only in:

1. Copilot-specific bot features (sessions, assignments)
2. Authentication approach (PAT vs API key)
3. Native web search support (Claude has built-in)

AI generated by Discussion Task Miner - Code Quality Improvement Agent

• expires on Feb 10, 2026, 9:06 PM UTC