Commit Graph

13 Commits

Author SHA1 Message Date
cexll
2c0553794a fix: Windows compatibility and flaky benchmark test
- Use cmd.exe /c to execute .bat/.cmd on Windows
- Set USERPROFILE alongside HOME for os.UserHomeDir()
- Use setTempDirEnv to set TEMP/TMP on Windows
- Replace chmod-based tests with cross-platform alternatives
- Fix concurrent speedup benchmark with fair comparison
- Add output/ to gitignore

Generated with SWE-Agent.ai

Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>
2026-01-26 21:29:54 +08:00
cexll
773f133111 chore: ignore references directory
Generated with SWE-Agent.ai

Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>
2026-01-23 12:01:04 +08:00
cexll
af1c860f54 fix: code review fixes for PR #94 - all critical and major issues resolved
This commit addresses all Critical and Major issues identified in the code review:

Critical Issues Fixed:
- #1: Test statistics data loss (utils.go:480) - Changed exit condition from || to &&
- #2: Below-target header showing "below 0%" - Added defaultCoverageTarget constant

Major Issues Fixed:
- #3: Coverage extraction not robust - Relaxed trigger conditions for various formats
- #4: 0% coverage ignored - Changed from CoverageNum>0 to Coverage!="" check
- #5: File change extraction incomplete - Support root files and @ prefix
- #6: String truncation panic risk - Added safeTruncate() with rune-based truncation
- #7: Breaking change documentation missing - Updated help text and docs
- #8: .DS_Store garbage files - Removed files and updated .gitignore
- #9: Test coverage insufficient - Added 29+ test cases in utils_test.go
- #10: Terminal escape injection risk - Added sanitizeOutput() for ANSI cleaning
- #11: Redundant code - Removed unused patterns variable

Test Results:
- All tests pass: go test ./... (34.283s)
- Test coverage: 88.4% (up from ~85%)
- New test file: codeagent-wrapper/utils_test.go
- No breaking changes to existing functionality

Files Modified:
- codeagent-wrapper/utils.go (+166 lines) - Core fixes and new functions
- codeagent-wrapper/executor.go (+111 lines) - Output format fixes
- codeagent-wrapper/main.go (+45 lines) - Configuration updates
- codeagent-wrapper/main_test.go (+40 lines) - New integration tests
- codeagent-wrapper/utils_test.go (new file) - Complete extractor tests
- docs/CODEAGENT-WRAPPER.md (+38 lines) - Documentation updates
- .gitignore (+2 lines) - Added .DS_Store patterns
- Deleted 5 .DS_Store files

Verification:
- Binary compiles successfully (v5.4.0)
- All extractors validated with real-world test cases
- Security vulnerabilities patched
- Performance maintained (90% token reduction preserved)

Related: #94

Generated with SWE-Agent.ai

Co-Authored-By: SWE-Agent.ai <noreply@swe-agent.ai>
2025-12-24 09:55:39 +08:00
swe-agent[bot]
93b72eba42 chore(v5.2.2): Bump version and clean up documentation
- Update version to 5.2.2 in README.md, README_CN.md, and codeagent-wrapper/main.go
- Remove non-existent documentation links from README.md (architecture.md, GITHUB-WORKFLOW.md, enterprise-workflow-ideas.md)
- Add coverage.out to .gitignore

Generated with swe-agent-bot

Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
2025-12-13 21:43:49 +08:00
cexll
2b8efd42a9 feat: implement modular installation system
引入模块化安装系统,支持可配置的工作流组合:

核心改进:
- .claude-plugin/marketplace.json: 移除废弃模块引用,精简插件清单
- .gitignore: 添加 Python 开发环境忽略项(.venv, __pycache__, .coverage)
- Makefile: 标记 make install 为 LEGACY,推荐使用 install.py
- install.sh: codex-wrapper 安装脚本,添加到 PATH

新架构使用 config.json 控制模块启用/禁用,支持:
- 选择性安装工作流(dev/bmad/requirements/essentials)
- 声明式操作定义(merge_dir/copy_file/run_command)
- 版本化配置管理

迁移路径: make install -> python3 install.py --install-dir ~/.claude

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-05 10:26:58 +08:00
cexll
90477abb81 update CLAUDE.md and codex skill 2025-11-29 19:11:06 +08:00
cexll
18c26a252a update doc 2025-11-18 21:12:52 +08:00
swe-agent[bot]
74b47a6f5a Merge branch 'master' of github.com:cexll/myclaude 2025-10-22 15:37:54 +08:00
swe-agent[bot]
b4a80f833a update .gitignore 2025-10-22 15:06:03 +08:00
swe-agent[bot]
cc1d22167a update 2025-10-22 14:32:19 +08:00
swe-agent[bot]
4d3789d0dc Convert requirements-clarity to plugin format with English prompts
Changes:
- Migrate from .claude/skills/ to .claude/plugins/ structure
- Add claude.json plugin metadata
- Create instructions.md with all English prompts (no Chinese)
- Update README.md for plugin distribution
- Update .gitignore to allow .claude/plugins/

Plugin structure:
- claude.json: Plugin metadata (name, version, components)
- instructions.md: Main skill prompt (100% English)
- README.md: Plugin documentation and usage guide

Maintains all functionality:
- 100-point scoring system
- Iterative clarification (≥90 threshold)
- PRD generation with 4 sections
- Auto-activation on vague requirements

Fixes #17

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-21 01:06:53 +00:00
swe-agent[bot]
9d16cb4406 Add requirements-clarity Claude Skill
- Create .claude/skills/requirements-clarity/SKILL.md (571 lines)
- Automatic activation for vague requirements
- 100-point scoring system (功能清晰度/技术具体性/实现完整性/业务背景)
- Interactive Q&A clarification process
- PRD generation with 需求描述/设计决策/验收标准/执行Phase structure
- Bilingual support (Chinese headers + mixed content)
- Create comprehensive README with testing guide and examples
- Update .gitignore to allow .claude/skills/ directory

Implements Issue #17 - Transform /clarif command into proactive Claude Skill
for automatic requirements clarification.

Generated by swe-agent
2025-10-20 15:23:20 +00:00
ben chen
e0d5b0955d Add comprehensive documentation and multi-agent workflow system
- Add English and Chinese README.md with complete project documentation
- Add agents/ directory with 7 specialized sub-agent configurations
- Add spec-execution.md and spec-workflow.md commands
- Add .gitignore for Claude Code project structure
- Document two primary usage patterns: sub-agent workflows and custom commands
- Include architecture overview, quick start guide, and real-world examples
- Establish 95% quality gate automation with iterative improvement loops

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-07-28 10:26:19 +08:00