[plan] Implement tiered complexity calibration for workflow responses

[github-actions]

Objective

Introduce complexity tiers (basic/intermediate/advanced) so the agent calibrates documentation depth and feature sophistication based on request complexity.

Context

Research from #12193 shows remarkably uniform quality scores (4.8-5.0) across all 6 scenarios, suggesting the agent may not be calibrating response complexity to match request sophistication. The agent produces production-ready output consistently, but lacks differentiation between simple and complex use cases.

Approach

1. Add request complexity detection in agent instructions
2. Define three tiers:
   • Basic: Simple triggers (push, pull_request), standard tools, minimal customization
   • Intermediate: Multiple triggers, tool combinations, conditional logic
   • Advanced: Complex workflows, custom toolchains, multi-stage processes, performance optimization
3. Calibrate documentation depth, example complexity, and feature suggestions based on detected tier
4. Preserve quality standards at all tiers

Files to Modify

• .github/instructions/*.instructions.md - Add complexity detection logic
• Agent system prompts - Include tier calibration guidelines
• docs/ - Document complexity tiers for users
• AGENTS.md - Update agent development guidelines

Acceptance Criteria

• Agent detects request complexity (basic/intermediate/advanced)
• Documentation depth adjusts to match tier
• Basic requests receive focused, concise output
• Advanced requests receive comprehensive, detailed output
• Quality remains high across all tiers
• Tests validate appropriate tier selection

Reference

See discussion #12193 "Recommendations" section: "Calibrate Complexity"

AI generated by Plan Command for discussion #12193

[github-actions]

🍪 Issue Monster has assigned this to Copilot!

I've identified this issue as a good candidate for automated resolution and assigned it to the Copilot agent.

The Copilot agent will analyze the issue and create a pull request with the fix.

Om nom nom! 🍪

AI generated by Issue Monster