feat: Add e2e-test-generator agent for integration test skeleton generation #56
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ration - Created new e2e-test-generator agent that generates it.todo skeletons from Design Doc ACs - Updated sub-agents orchestration flow to include e2e-test-generator after technical-designer - Enhanced information handoff between agents to ensure test skeleton info reaches work-planner - Modified task-executor and quality-fixer for better escalation handling - Updated work-planner to incorporate integration test skeleton information into plans - Added simplified escalation conditions in sub-agents.md for clearer agent communication - Updated README.ja.md to document the new e2e-test-generator agent - Bumped version to 1.7.0 This enhancement ensures integration tests are created early in the development flow, preventing the "works in isolation but fails in integration" issue. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
shinpr
changed the title
- Restored critical self-contained execution constraint in quality-fixer.md
("Do not return fix instructions, execute all fixes autonomously")
- Simplified task selection logic in task-executor.md
(Removed bash command example to prevent mechanical execution)
- Changed "Phase 4" to "最終Phase" in template for flexible phase numbering
(Supports variable phase counts from 3-6 while maintaining "Phase" keyword for compatibility)
These refinements ensure better AI execution accuracy and maintain system flexibility.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
Based on real project feedback from tacoms-ai-bot implementation: - Enhanced test design information handling with metadata support - Added dual implementation strategies (TDD vs implementation-first) - Improved task decomposition with quantitative progress tracking - Refined test categorization (setup/functional/non-functional/risk-based) - Strengthened traceability between ACs and test cases These changes reflect lessons learned from actual development cycles, particularly in handling complex test suites and measuring progress. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
- Remove unnecessary heading levels from agent specifications - Add E2E test generation workflow to plan command - Improve agent orchestration flow clarity 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
… AI execution accuracy - Strengthen quality-fixer agent with comprehensive validation workflows and error handling patterns - Add structured task decomposition and progress tracking to task-executor agent - Improve technical-designer with clearer ADR decision-making process - Enhance work-planner with Design Doc integration and phase-based planning - Update documentation templates with E2E verification procedures and Design Doc alignment - Add e2e-test-generator agent for automated integration test skeleton creation - Refine sub-agent documentation with clearer usage patterns and capabilities These changes improve AI execution accuracy through better structured guidance, clearer completion criteria, and enhanced error prevention patterns. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This enhancement ensures integration tests are created early in the development flow, preventing the "works in isolation but fails in integration" issue.
🤖 Generated with Claude Code