Release v1.7.14

Overview

This release improves Acceptance Criteria (AC) scoping guidelines to optimize for autonomous LLM implementation in CI/CD environments. The changes focus on clarifying what should and shouldn't be included in ACs to maximize automation ROI.

What's Changed

🎯 Improved AC Scoping Guidelines

acceptance-test-generator.md (English & Japanese)

• Simplified "Out of Scope" section into 3 clear categories:
  • External Dependencies: Test contracts/interfaces instead of real API calls
  • Non-Deterministic in CI: Avoid performance metrics and load testing
  • Implementation Details: Focus on user-observable behavior, not internal structure
• Removed redundant "Security and Performance Requirements Processing" section
• Added Action guideline: Clear instructions on handling excluded items in ACs

technical-designer.md (English & Japanese)

• Added "AC Scoping for Autonomous Implementation" section:
  • Include (High automation ROI):
    • Business logic correctness (calculations, state transitions, data transformations)
    • Data integrity and persistence behavior
    • User-visible functionality completeness
    • Error handling behavior (what user sees/experiences)
  • Exclude (Low ROI in LLM/CI/CD environment):
    • External service real connections → Use contract/interface verification
    • Performance metrics → Non-deterministic in CI, defer to load testing
    • Implementation details → Focus on observable behavior
    • UI layout specifics → Focus on information availability, not presentation
  • Principle: AC = User-observable behavior verifiable in isolated CI environment

Benefits

For AC Authors

• Clearer guidelines on what to include/exclude in acceptance criteria
• Reduced ambiguity when writing requirements for autonomous implementation
• Better alignment with CI/CD testing capabilities

For Test Generators

• Improved accuracy when transforming ACs into test cases
• Reduced confusion about scope boundaries
• Better test quality by focusing on high-value verification points

For Autonomous Implementation

• Higher success rate for LLM-based implementations
• More reliable CI/CD pipelines with deterministic tests
• Better ROI on automated testing efforts

Rationale

Why This Change?

1. Observable Behavior Focus: ACs should specify what users see/experience, not implementation details
2. CI/CD Optimization: Exclude non-deterministic tests that fail in automated environments
3. Automation ROI: Concentrate testing effort on business logic and data integrity
4. LLM Capability Alignment: Match AC scope to what autonomous agents can effectively verify

What Problem Does This Solve?

Previous AC guidelines led to "ideal quality assurance" criteria that were:

• Difficult to implement autonomously by LLMs
• Non-deterministic in CI/CD environments
• Low ROI for automated testing
• Mixed implementation details with user-observable behavior

Technical Details

Files Modified

• .claude/agents-en/acceptance-test-generator.md
• .claude/agents-ja/acceptance-test-generator.md
• .claude/agents-en/technical-designer.md
• .claude/agents-ja/technical-designer.md
• package.json (version bump)
• package-lock.json (version bump)

---

Full Changelog: v1.7.13...v1.7.14