Commit Graph

26 Commits

Author SHA1 Message Date
catlog22
8d178feaac feat: 增强计划验证和上下文收集功能,支持自动执行和用户交互选择 2026-01-28 00:12:15 +08:00
catlog22
b3c47294e7 Enhance workflow commands and context management
- Updated `plan.md` to include new fields in context-package.json: prioritized_context, user_intent, priority_tiers, dependency_order, and sorting_rationale.
- Added validation for the existence of the prioritized_context field in context-package.json.
- Modified user decision flow in task generation to present action choices after planning completion.
- Improved context-gathering process in `context-gather.md` to integrate user intent and prioritize context based on user goals.
- Revised conflict-resolution documentation to require planning notes records after conflict analysis.
- Streamlined task generation in `task-generate-agent.md` to utilize pre-sorted context without redundant sorting.
- Removed unused settings persistence functions and corresponding tests from `claude-cli-tools.ts` and `settings-persistence.test.ts`.
2026-01-28 00:02:45 +08:00
catlog22
a293a01d85 feat: add --yes flag for auto-confirmation across multiple workflows
- Enhanced lite-execute, lite-fix, lite-lite-lite, lite-plan, multi-cli-plan, plan, replan, session complete, session solidify, and various UI design commands to support a --yes or -y flag for skipping user confirmations and auto-selecting defaults.
- Updated argument hints and examples to reflect new auto mode functionality.
- Implemented auto mode defaults for confirmation, execution methods, and code review options.
- Improved error handling and validation in command parsing and execution processes.
2026-01-24 09:23:24 +08:00
catlog22
5b5dc85677 refactor(cli): change from env var injection to direct prompt concatenation
- Replace $PROTO/$TMPL environment variable injection with systemRules/roles direct concatenation
- Append rules to END of prompt instead of prepending
- Change prompt field name from RULES to CONSTRAINTS in all prompts
- Default to universal-rigorous-style template when --rule not specified
- Update all .claude documentation, agents, commands, and skills
- Add streaming_content type support for Gemini delta messages

Breaking: Prompts now use CONSTRAINTS field instead of RULES
2026-01-17 21:30:05 +08:00
catlog22
f14418603a feat(cli): 添加 --rule 选项支持模板自动发现
重构 ccw cli 模板系统:

- 新增 template-discovery.ts 模块,支持扁平化模板自动发现
- 添加 --rule <template> 选项,自动加载 protocol 和 template
- 模板目录从嵌套结构 (prompts/category/file.txt) 迁移到扁平结构 (prompts/category-function.txt)
- 更新所有 agent/command 文件,使用 $PROTO $TMPL 环境变量替代 $(cat ...) 模式
- 支持模糊匹配:--rule 02-review-architecture 可匹配 analysis-review-architecture.txt

其他更新:
- Dashboard: 添加 Claude Manager 和 Issue Manager 页面
- Codex-lens: 增强 chain_search 和 clustering 模块

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-17 19:20:24 +08:00
catlog22
1cf0d92ec2 feat: 更新冲突解决文档和模式,增加输出模式和策略要求,优化JSON架构 2025-12-26 15:40:40 +08:00
catlog22
8dd4a513c8 Refactor CLI command usage from ccw cli exec to ccw cli -p for improved prompt handling
- Updated command patterns across documentation and templates to reflect the new CLI syntax.
- Enhanced CLI tool implementation to support reading prompts from files and multi-line inputs.
- Modified core components and views to ensure compatibility with the new command structure.
- Adjusted help messages and internationalization strings to align with the updated command format.
- Improved error handling and user notifications in the CLI execution flow.
2025-12-18 14:12:45 +08:00
catlog22
4329bd8e80 fix: Add run_in_background=false to all agent Task invocations
Ensure all agent executions wait for results before proceeding.
Modified 20 workflow command files with 32 Task call updates.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-18 10:00:22 +08:00
catlog22
3da0ef2adb Add comprehensive tests for query parsing and Reciprocal Rank Fusion
- Implemented tests for the QueryParser class, covering various identifier splitting methods (CamelCase, snake_case, kebab-case), OR expansion, and FTS5 operator preservation.
- Added parameterized tests to validate expected token outputs for different query formats.
- Created edge case tests to ensure robustness against unusual input scenarios.
- Developed tests for the Reciprocal Rank Fusion (RRF) algorithm, including score computation, weight handling, and result ranking across multiple sources.
- Included tests for normalization of BM25 scores and tagging search results with source metadata.
2025-12-16 10:20:19 +08:00
catlog22
25ac862f46 feat(ccw): migrate backend to TypeScript
- Convert 40 JS files to TypeScript (CLI, tools, core, MCP server)
- Add Zod for runtime parameter validation
- Add type definitions in src/types/
- Keep src/templates/ as JavaScript (dashboard frontend)
- Update bin entries to use dist/
- Add tsconfig.json with strict mode
- Add backward-compatible exports for tests
- All 39 tests passing

Breaking changes: None (backward compatible)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-13 10:43:15 +08:00
catlog22
811382775d feat: Implement fuzzy search functionality in smart-search.js
- Added buildFuzzyRegex function for approximate matching.
- Enhanced buildRipgrepCommand to support fuzzy parameter.
- Updated executeAutoMode to handle fuzzy search case.
- Implemented executeFuzzyMode for executing fuzzy search using ripgrep.
- Refactored import and export parsing functions for better modularity.
- Improved dependency graph building and circular dependency detection.
- Added caching mechanism for dependency graph to optimize performance.
2025-12-11 23:28:35 +08:00
catlog22
57a86ab36f feat: Add parallel explore agents to context-gather workflow
- context-gather.md: Add Step 2 with complexity assessment (Low/Medium/High)
  and parallel cli-explore-agent execution (1-4 agents based on complexity)
- context-search-agent.md: Add Track 0 for exploration aggregation with
  exploration_results schema including all_patterns and all_integration_points
- conflict-resolution.md: Consume exploration_results for enhanced conflict
  detection with pre-identified conflict indicators
- task-generate-agent.md: Use exploration critical_files for focus_paths
  and all_patterns/all_integration_points for implementation guidance

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-28 23:08:20 +08:00
catlog22
2a11d5f190 refactor: Add tree-style execution flow diagrams to all workflow commands
Added tree-style execution process diagrams using ASCII art (├─, └─, │) to 34 workflow command files across three directories for improved readability and execution flow clarity.

## Changes by Directory

### workflow/ root (17 files)
- lite-plan.md, lite-execute.md, lite-fix.md
- plan.md, execute.md, replan.md
- status.md, review.md, review-fix.md
- review-session-cycle.md, review-module-cycle.md
- session commands (start, complete, resume, list)
- tdd-plan.md, tdd-verify.md, test-cycle-execute.md, test-gen.md, test-fix-gen.md

### workflow/ui-design/ (10 files)
- layout-extract.md, animation-extract.md, style-extract.md
- generate.md, import-from-code.md, codify-style.md
- imitate-auto.md, explore-auto.md
- reference-page-generator.md, design-sync.md

### workflow/tools/ (8 files)
- conflict-resolution.md, task-generate-agent.md, context-gather.md
- tdd-coverage-analysis.md, task-generate-tdd.md
- test-task-generate.md, test-concept-enhanced.md, test-context-gather.md

## Diagram Features
- Input parsing with flag enumeration
- Decision branching with conditional paths
- Phase/step hierarchy with clear nesting
- Mode detection and validation flows

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-27 16:13:30 +08:00
catlog22
4bb4bdc124 refactor: migrate agents to path-based context loading
- Update action-planning-agent and task-generate-agent to load context
  via file paths instead of embedded context packages
- Streamline test-cycle-execute workflow execution
- Remove redundant content from conflict-resolution and context-gather
- Update SKILL.md and tdd-plan documentation
2025-11-23 22:06:13 +08:00
catlog22
c3818fdb79 Refactor workflow file paths from .workflow/sessions/ to .workflow/active/ for improved session management and consistency across commands. Updated documentation and command references to reflect the new directory structure, ensuring all relevant commands and outputs are correctly aligned with the active session model. 2025-11-20 09:40:58 +08:00
catlog22
89a61acb71 Refactor workflow output paths to use a standardized sessions directory structure
- Updated output paths in various command files to reflect the new structure: `.workflow/sessions/{session_id}/` instead of `.workflow/{session_id}/`.
- Adjusted documentation and code comments to ensure consistency across all agents and commands.
- Ensured that all references to session-related files are correctly pointing to the new directory format.
2025-11-19 23:04:10 +08:00
catlog22
19ebb2dc82 fix(workflow): complete path migration and enhance session:complete
Comprehensive update to eliminate all old path references and implement transactional archival in session:complete.

## Part 1: Complete Path Migration (43 files)

### Files Updated
- action-plan-verify.md
- session/list.md, session/resume.md
- tdd-verify.md, tdd-plan.md, test-*.md
- All brainstorm/*.md files (13 files)
- All tools/*.md files (10 files)
- All ui-design/*.md files (10 files)
- lite-plan.md, lite-execute.md, plan.md

### Path Changes
- `.workflow/.active-*` → `find .workflow/sessions/ -name "WFS-*" -type d`
- `.workflow/WFS-{session}` → `.workflow/sessions/WFS-{session}`
- `.workflow/.archives/` → `.workflow/archives/`
- Removed all marker file operations (touch/rm .active-*)

### Verification
-  0 references to .active-* markers remain
-  0 references to direct .workflow/WFS-* paths
-  0 references to .workflow/.archives/ (dot prefix)

## Part 2: Transactional Archival Enhancement

### session/complete.md - Complete Rewrite

**New Four-Phase Architecture**:

1. **Phase 1: Pre-Archival Preparation**
   - Find active session in .workflow/sessions/
   - Check for existing .archiving marker (resume detection)
   - Create .archiving marker to prevent concurrent operations

2. **Phase 2: Agent Analysis (In-Place)**
   - Agent processes session WHILE STILL in sessions/ directory
   - Pure analysis - no file moves or manifest updates
   - Returns complete metadata package for atomic commit
   - Failure here → session remains active, safe to retry

3. **Phase 3: Atomic Commit**
   - Only executes if Phase 2 succeeds
   - Move session to archives/
   - Update manifest.json
   - Remove .archiving marker
   - All-or-nothing guarantee

4. **Phase 4: Project Registry Update**
   - Extract feature metadata and update project.json

**Key Improvements**:
- **Agent-first, move-second**: Prevents inconsistent states
- **Transactional guarantees**: All-or-nothing file operations
- **Resume capability**: .archiving marker enables safe retry
- **Error recovery**: Comprehensive failure handling documented

**Old Design Flaw (Fixed)**:
- Old: Move first → Agent processes → If agent fails, session moved but metadata incomplete
- New: Agent processes → If success, atomic commit → Guaranteed consistency

## Benefits

1. **Consistency**: All commands use identical path patterns
2. **Robustness**: Transactional archival prevents data loss
3. **Maintainability**: Single source of truth for directory structure
4. **Recoverability**: Failed operations can be safely retried
5. **Alignment**: Closer to OpenSpec's clean three-layer model

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-18 12:39:23 +08:00
catlog22
a8ab192c72 refactor: remove Related Commands section from workflow tool commands
Only orchestrator commands (plan, execute, resume, test-gen, test-fix-gen,
tdd-plan) retain Related Commands section to document workflow phases.
Tool commands (conflict-resolution, task-generate-tdd, test-task-generate,
test-concept-enhanced, test-context-gather, tdd-coverage-analysis) have
Related Commands removed to reduce documentation redundancy.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-08 17:55:55 +08:00
catlog22
0404a7eb7c docs: 增强 conflict-resolution 核心规则,禁止使用 bash 命令输出
添加核心职责规则:直接文本输出,禁止使用 bash echo/printf 命令

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-08 12:07:45 +08:00
catlog22
920b179440 docs: 更新所有命令描述并重新生成索引文件
- 更新所有69个命令文件的description字段,基于实际功能重新生成详细描述
- 重新生成5个索引文件(all-commands, by-category, by-use-case, essential-commands, command-relationships)
- 移动analyze_commands.py到scripts/目录并完善功能
- 移除临时备份文件

命令描述改进示例:
- workflow:plan: 增加了工具和代理的详细说明(Gemini, action-planning-agent)
- cli:execute: 说明了YOLO权限和多种执行模式
- memory:update-related: 详细说明了批处理策略和工具回退链

索引文件改进:
- usage_scenario从2种扩展到10种(更精细分类)
- command-relationships覆盖所有69个命令
- 区分built-in(内置调用)和sequential(用户顺序执行)关系

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-06 15:11:31 +08:00
catlog22
bb6f74f44b refactor: enhance conflict resolution command with modification suggestions for custom handling 2025-10-25 17:03:05 +08:00
catlog22
692a68da6f Refactor workflow tools and user interaction methods
- Updated synthesis tool to enhance user interaction with multi-select options and improved question presentation in Chinese.
- Revised conflict resolution tool to allow batch processing of conflicts, increasing the limit from 4 to 10 per round and changing user interaction from AskUserQuestion to text output.
- Added context_package_path to task generation tools for better context management.
- Improved task generation schema to include context_package_path for enhanced context delivery.
- Updated CLI templates to reflect changes in task JSON schema, ensuring context_package_path is included.
2025-10-25 14:43:55 +08:00
catlog22
7f82d0da86 refactor(conflict-resolution): transform to interactive resolution with in-place modifications
BREAKING CHANGE: Remove CONFLICT_RESOLUTION.md generation in favor of interactive user confirmation and direct file modifications

Core Changes:
- Replace markdown report generation with structured JSON output for programmatic processing
- Add interactive conflict resolution via AskUserQuestion (max 4 conflicts, 2-4 strategies each)
- Apply modifications directly to guidance-specification.md and role analyses (*.md) using Edit tool
- Update context-package.json with conflict_risk status (resolved/none/low)
- Remove Phase 3 output validation (no file generation needed)

Modified Files:
- conflict-resolution.md: Complete rewrite of agent prompt and execution flow
  - Step 4: JSON output instead of markdown generation
  - Phase 3: User confirmation via AskUserQuestion
  - Phase 4: Apply modifications using Edit tool
  - Success criteria updated for in-place modifications
- plan.md: Update Phase 3 data flow and TodoWrite pattern
  - Data flow now shows "Apply modifications via Edit tool"
  - Todo description changed to "Resolve conflicts and apply fixes"
- task-generate-agent.md: Update conflict resolution context description
  - No longer references CONFLICT_RESOLUTION.md file
  - Notes conflicts resolved in guidance-specification.md and role analyses
- task-generate.md: Comprehensive cleanup of all CONFLICT_RESOLUTION.md references
  - Remove CONFLICT_RESOLUTION.md from artifact catalog
  - Update load_planning_context step to read guidance-specification.md
  - Update task implementation logic_flow
  - Update artifact priority and integration sections
  - Update directory structure documentation

Benefits:
- Seamless workflow: conflicts detected → user confirms → applied automatically
- No intermediate files to manage
- User interaction at decision point (not after-the-fact)
- Resolved conflicts integrated directly into source artifacts
- Clear conflict_risk status tracking in context-package.json

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 17:31:19 +08:00
catlog22
2b3541941e fix(conflict-resolution): fix markdown formatting errors
Fix formatting issues:
- Line 104-117: Replace escaped backticks (\`\`\`) with proper markdown code fence (```)
- Line 158: Remove unnecessary backslash escapes from inline code
- Line 182: Fix stray backslash before backtick in prompt template

These formatting errors were causing markdown rendering issues.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 17:07:10 +08:00
catlog22
ee7ffdae67 docs: enhance workflow documentation with role analysis and conflict resolution details 2025-10-24 11:56:50 +08:00
catlog22
57fa379e45 Refactor workflow to replace synthesis-specification.md with role analysis documents
- Updated references in various workflow commands to utilize role analysis documents instead of synthesis-specification.md.
- Modified CLI templates and command references to reflect the new architecture and document structure.
- Introduced conflict-resolution command to analyze and resolve conflicts between implementation plans and existing codebase.
- Deprecated synthesis role template and provided migration guidance for transitioning to the new role analysis approach.
2025-10-24 11:08:15 +08:00