Commit Graph

251 Commits

Author SHA1 Message Date
catlog22
81e1d3e940 docs: update README for v4.0.1 with intelligent page inference
Updates:
- Version badge: v3.5.0 → v4.0.1
- What's New: Highlight intelligent page inference and agent mode
- Phase 2 examples: Show simplified commands with page inference
- UI Design Commands: Update all command examples and descriptions
- Command table: Update descriptions with v4.0 features

Key changes:
- Simplest command: /workflow:design:auto --prompt "Modern blog with home and article pages"
- All parameters now optional with smart defaults
- Agent mode examples with --use-agent flag
- Dual input sources (images + text prompts)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-07 22:04:24 +08:00
catlog22
451b1a762e feat: intelligent page inference from prompt (v4.0.1)
Features:
- --pages parameter now optional with smart inference
- Auto-extract page names from prompt text
  Example: "blog with home, article pages" → ["home", "article"]
- Fallback to synthesis-specification.md in integrated mode
- Default to ["home"] if nothing specified

Changes:
- auto.md: Add Phase 0 page inference logic, update examples
- ui-generate.md: Add page inference in Phase 1, update examples
- CHANGELOG.md: Add v4.0.1 release notes with page inference

Benefits:
- Simplest command: /workflow:design:auto --prompt "Modern blog with home and article pages"
- No need to manually specify --pages in most cases
- More natural and intuitive user experience

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

Co-Authored-By: Claude <noreply@anthropic.com>
v4.0.1
2025-10-07 22:00:56 +08:00
catlog22
59b4b57537 chore: remove backward compatibility mention in auto.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-07 21:54:54 +08:00
catlog22
e31b93340d refactor: v4.0.0 breaking changes - remove backward compatibility
BREAKING CHANGES:
- Old command format no longer supported
- --session now optional (enables standalone mode)
- --images optional with default "design-refs/*"
- Removed --style-overrides (use --prompt instead)
- Only --pages is required

Migration required from v3.5.0 to v4.0.0
See CHANGELOG.md for migration guide

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

Co-Authored-By: Claude <noreply@anthropic.com>
v4.0.0
2025-10-07 21:52:54 +08:00
catlog22
7e75cf8425 feat: enhance UI design workflow with agent mode and flexible inputs (v3.5.1)
Features:
- Unified variant control: --variants parameter controls both style cards and UI prototypes
- Agent creative exploration: --use-agent enables parallel generation of diverse designs
- Dual mode support: standalone (no --session) and integrated (with --session)
- Dual input sources: --images, --prompt, or hybrid (both)
- Command simplification: most parameters now optional with smart defaults

Changes:
- auto.md: Added --variants, --use-agent, --prompt; dual mode detection
- style-extract.md: Agent mode, text input, parallel variant generation
- ui-generate.md: Agent mode, layout diversity, simplified execution
- CHANGELOG.md: Complete v3.5.1 release notes

Backward compatible: All existing commands continue to work

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-07 21:46:45 +08:00
catlog22
bd9278bb02 feat: enhance workflow with CCW-aware IMPL_PLAN.md templates
- Add concept-verify and action-plan-verify quality gate commands
- Enhance IMPL_PLAN.md with CCW Workflow Context section
- Add Artifact Usage Strategy for clear CCW artifact hierarchy
- Update frontmatter with context_package, verification_history, phase_progression
- Synchronize enhancements across task-generate, task-generate-agent, task-generate-tdd
- Update synthesis, plan, and tdd-plan commands with verification guidance

Makes CCW's multi-phase workflow and intelligent context gathering visible in generated documentation.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-07 20:58:11 +08:00
catlog22
51bd51ea60 refactor: optimize docs workflow with lightweight planning strategy
**Core Changes**:
- Shift from heavy analysis in planning to targeted analysis in execution
- Reduce main process context by collecting only metadata (paths, structure)
- Simplify pre_analysis steps to be more declarative

**docs.md optimizations**:
- Phase 2: Lightweight metadata collection (get_modules_by_depth.sh + Code Index MCP)
- Planning phase now collects only paths and structure, not file content
- IMPL-001: Simplified to 2 pre_analysis steps (structure + tech stack from config files only)
- IMPL-002: Removed system_context loading, single focused analysis step
- IMPL-N (API): Replace rg with mcp__code-index__search_code_advanced for better structure

**doc-generator.md optimizations**:
- Add "Scope-Limited Analysis" philosophy
- Add "Optimized Execution Model" section
- Emphasize analysis is always limited to focus_paths to prevent context explosion

**Benefits**:
- Main process context stays minimal (no risk of overflow)
- Each task has controlled, scoped context
- Better separation: planning = metadata, execution = deep analysis
- More maintainable pre_analysis steps (less nested commands)
- Better use of MCP tools for structured data

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-06 12:19:18 +08:00
catlog22
0e16c6ba4b feat: add interactive preview system for UI prototypes
🌐 Preview Enhancement System
- Auto-generate index.html for master navigation
- Auto-generate compare.html for side-by-side comparison
- Auto-generate PREVIEW.md with setup instructions

📊 Preview Features
- Master navigation with grid layout of all prototypes
- Side-by-side comparison with iframe-based variants
- Responsive viewport toggles (Desktop/Tablet/Mobile 100%/768px/375px)
- Synchronized scrolling for layout comparison
- Dynamic page switching dropdown
- Quick links to implementation notes

🛠️ Preview Options
- Direct browser opening (simplest - double-click index.html)
- Local server (recommended - Python/Node.js/PHP/VS Code Live Server)
- Complete standalone prototypes with no external dependencies

📚 Documentation Updates
- Add detailed UI design commands section to README.md
- Add Chinese UI design commands section to README_CN.md
- Update CHANGELOG.md with comprehensive preview system documentation
- Add usage examples and preview workflow guide
- Update ui-generate.md with preview file templates

🎯 Integration
- Phase 4 in ui-generate command generates all preview files
- Updated TodoWrite to track preview file generation
- Updated output structure to show new preview files
- Enhanced "Next Steps" section with preview instructions

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-06 00:13:33 +08:00
catlog22
25951ac9b0 release: version v3.5.0 - UI Design Workflow with Triple Vision Analysis
🎨 UI Design Workflow System
- Add /workflow:design:auto semi-autonomous orchestrator with interactive checkpoints
- Add /workflow:design:style-extract with triple vision analysis (Claude + Gemini + Codex)
- Add /workflow:design:style-consolidate for token validation and style guide generation
- Add /workflow:design:ui-generate for token-driven HTML/CSS prototype generation
- Add /workflow:design:design-update for design system integration

👁️ Triple Vision Analysis
- Claude Code: Quick initial visual analysis using native Read tool
- Gemini Vision: Deep semantic understanding of design intent
- Codex Vision: Structured pattern recognition with -i parameter
- Consensus synthesis with weighted combination strategy

⏸️ Interactive Checkpoints
- Checkpoint 1: User selects style variants after extraction
- Checkpoint 2: User confirms prototypes before design update
- Pause-and-continue pattern for critical design decisions

🎯 Zero Agent Overhead
- Remove Task(conceptual-planning-agent) wrappers from design commands
- Direct bash execution for gemini-wrapper and codex commands
- Improved performance while preserving all functionality

🎨 Design Features
- OKLCH color format for perceptually uniform design tokens
- W3C Design Tokens compatibility
- WCAG 2.1 AA compliance validation
- Style override support with --style-overrides parameter
- Batch task generation with --batch-plan flag

📚 Documentation Updates
- Update README.md with Phase 2 (UI Design Refinement) section
- Update README_CN.md with Chinese design workflow documentation
- Add comprehensive CHANGELOG entry for v3.5.0
- Add 5 new /workflow:design:* commands to command reference

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

Co-Authored-By: Claude <noreply@anthropic.com>
v3.5.0
2025-10-06 00:06:20 +08:00
catlog22
a18c666f22 feat: Add style-extract and ui-generate commands for design workflow
- Implemented style-extract command to extract design styles from reference images using Gemini Vision and Codex.
- Added execution protocol detailing session validation, image analysis, and structured token generation.
- Introduced ui-generate command to create UI prototypes based on consolidated design tokens and synthesis specifications.
- Defined comprehensive execution steps for loading design systems, generating HTML/CSS prototypes, and ensuring accessibility compliance.
- Established a design-tokens-schema for consistent design token definitions across workflows, emphasizing OKLCH color format and semantic naming.
2025-10-05 23:48:11 +08:00
catlog22
ea86d5be4f refactor: optimize docs.md workflow command structure
- Simplify Pre-Planning Analysis (Phase 3) - remove heavy analysis, use lightweight check
- Add TodoWrite tracking mechanism for progress monitoring
- Add complete execution flow diagrams (Planning + Execution phases)
- Restore full JSON task templates with all 5 fields
- Fix template reference method: use $(cat template.txt) instead of "..."
- Simplify flow diagrams from ASCII boxes to arrow-based format
- Add visual status symbols (🔄) for TodoWrite tracking
- Reorganize document structure, eliminate duplicate content
- Reduce document from 726 to 590 lines (19% reduction)
- Maintain all core functionality and implementation details

Changes:
- Phase 3: Lightweight docs assessment vs full pre-analysis
- Phase 4: Add TodoWrite setup with status tracking
- Task Templates: Complete JSON structures for 4 task types
- Execution Flow: Simple arrow diagrams for clarity
- TodoWrite: Visual status progression examples
- Overall: Better organized, more maintainable

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-05 22:44:23 +08:00
catlog22
fa6034bf6b refactor: enhance doc-generator agent and add error handling
- Update doc-generator agent description to emphasize intelligent autonomous execution
- Add on_error field to all flow_control pre_analysis steps
- Clarify agent role as goal-oriented worker vs script runner
- Improve error handling documentation in workflow examples

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-05 22:20:03 +08:00
catlog22
d76ccac8e4 Refactor documentation workflow and templates
- Updated `/workflow:docs` command to enhance documentation planning and orchestration.
- Introduced new parameters for tool selection and scope filtering.
- Separated documentation planning from content generation, clarifying roles of docs.md and doc-generator.md.
- Added detailed planning process phases, including session initialization, project structure analysis, and task decomposition.
- Created new templates for API, module, and project-level documentation, ensuring comprehensive coverage and consistency.
- Enhanced output structure for better organization of generated documentation.
- Implemented error handling and completion checklist for improved user experience.
2025-10-05 22:16:24 +08:00
catlog22
a03a9039d6 fix: add version tracking support to Install-Claude.sh
- Add -SourceVersion, -SourceBranch, -SourceCommit parameters
- Add create_version_json function to create version.json
- Add .qwen directory support
- Fix get_installation_mode output redirection
- Align with PowerShell version Install-Claude.ps1

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-05 22:08:53 +08:00
catlog22
677b37bfbf refactor: rename memory-gemini-bridge agent to memory-bridge
Renamed agent to be more generic and not tied to specific AI model:
- `.claude/agents/memory-gemini-bridge.md` → `.claude/agents/memory-bridge.md`
- Updated references in `/update-memory-full` command
- Updated references in `/update-memory-related` command

This improves flexibility for future multi-model support while maintaining
the same functionality for complex project documentation updates.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-05 21:25:59 +08:00
catlog22
2dbf550420 docs: clarify CLI command intent and add output routing
- **Intent Clarification**: Distinguished analysis (read-only) from execution (modifies code) commands
- **Output Routing**: Added comprehensive output destination logic for all CLI commands
- **Scratchpad Integration**: Introduced `.workflow/.scratchpad/` for non-session-specific outputs

## Analysis Commands (Read-Only)
- `/cli:analyze`, `/cli:chat`, `/cli:mode:*`: Added "Core Behavior" emphasizing read-only nature
- Added "MODE: analysis" in command templates
- Examples clearly show recommendations vs. code changes

## Execution Commands (Modifies Code)
- `/cli:execute`: Added ⚠️ warnings about code modification
- `/cli:codex-execute`: Clarified multi-stage execution with detailed output structure
- Both commands now have "Output Routing" sections

## Workflow Architecture Updates
- Added `.workflow/.scratchpad/` directory definition
- Output routing logic: session-relevant → `.chat/`, otherwise → `.scratchpad/`
- File naming pattern: `[command-type]-[brief-description]-[timestamp].md`
- Examples for both analysis and implementation commands

## Key Improvements
- Prevents confusion between analysis and implementation operations
- Solves output loss when no active session exists
- Prevents unrelated analyses from cluttering session history
- Provides centralized location for ad-hoc outputs

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-05 12:22:23 +08:00
catlog22
12034c8be5 release: version v3.4.2 - CLI documentation refactoring
Updated documentation for v3.4.2 release focusing on CLI command
documentation refactoring and single source of truth pattern.

## Changes

**CHANGELOG.md**:
- Added comprehensive v3.4.2 release notes
- Documented 681 lines reduction across 7 CLI command files
- Detailed removed duplicate sections and preserved unique content
- Explained single source of truth pattern with intelligent-tools-strategy.md

**README.md & README_CN.md**:
- Updated version badge from v3.4.0 to v3.4.2
- Updated "What's New" section with v3.4.2 highlights
- Documented CLI documentation refactoring benefits

## Release Summary

v3.4.2 focuses on documentation quality and maintenance optimization:
- Eliminated redundant documentation content
- Established implicit reference pattern to strategy guide
- Preserved all unique command-specific capabilities
- Reduced maintenance overhead for future updates

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

Co-Authored-By: Claude <noreply@anthropic.com>
v3.4.2
2025-10-05 10:39:53 +08:00
catlog22
467963eee2 docs: refactor CLI command docs to eliminate redundancy
Streamlined 7 CLI command documentation files by removing duplicate
content that's already comprehensively covered in intelligent-tools-strategy.md
(loaded in memory). Established single source of truth (SSOT) pattern.

Changes:
- Removed duplicate command templates (→ strategy lines 51-118)
- Removed file pattern reference lists (→ strategy lines 324-329)
- Removed complex pattern discovery steps (→ strategy lines 331-355)
- Removed MODE field definitions (→ strategy lines 128-143)
- Removed tool feature descriptions (→ strategy lines 283-322)

Files streamlined:
- analyze.md: 117→61 lines (48% reduction)
- chat.md: 118→62 lines (47% reduction)
- execute.md: 180→100 lines (44% reduction)
- codex-execute.md: 481→473 lines (2% - preserved unique content)
- mode/bug-index.md: 144→75 lines (48% reduction)
- mode/code-analysis.md: 188→76 lines (60% reduction)
- mode/plan.md: 100→76 lines (24% reduction)

Total reduction: 681 lines removed across all files

Each doc now contains only:
- Unique purpose and parameters
- Command-specific execution flow
- Practical examples
- Brief reference to intelligent-tools-strategy.md

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-05 10:35:27 +08:00
catlog22
a9d6de228e feat: 增加文件模式参考和复杂模式发现的示例,增强 CLI 命令的文档 2025-10-05 10:26:08 +08:00
catlog22
7d9adf5a55 chore: 删除 intelligent-tools-strategy.md 中的参考链接以简化文档 2025-10-05 09:08:33 +08:00
catlog22
3bf15ced59 chore: 删除 intelligent-tools-strategy.md 文件并重新创建以更新策略框架 2025-10-05 08:56:39 +08:00
catlog22
dc228411d6 chore: 删除 intelligent-tools-strategy.md 文件并更新 .gitignore 以包含 version.json 2025-10-05 08:55:22 +08:00
catlog22
7dd83f150a fix: Use commit SHA as version for development builds instead of 'latest'
**Problem**:
- version.json showed "version": "latest" for dev builds
- Non-descriptive and not useful for version tracking

**Solution**:
- Use "dev-{commit_sha}" format for development builds
- Stable releases: "3.4.1" (from tag)
- Development builds: "dev-4ec1a17" (from commit SHA)
- API failure fallback: "dev-unknown"

**Version Format Examples**:
```json
// Stable release
{"version": "3.4.1", "commit_sha": "4ec1a17"}

// Development build
{"version": "dev-4ec1a17", "commit_sha": "4ec1a17"}
```

**Benefits**:
- Clear distinction between stable and dev versions
- version field always contains meaningful information
- No more "latest" placeholder values

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 23:58:47 +08:00
catlog22
4ec1a17ef4 feat: Add commit SHA tracking to version.json for precise version identification
**Version Tracking Enhancement**:
- Add commit_sha field to version.json for distinguishing development versions
- Auto-detect commit SHA from downloaded repository using git rev-parse
- Fallback to GitHub API if git is unavailable
- Update both PowerShell and Bash installers

**version.json Structure**:
```json
{
  "version": "3.4.1",
  "commit_sha": "9a49a86",
  "installation_mode": "Global",
  "installation_path": "...",
  "installation_date_utc": "...",
  "source_branch": "main",
  "installer_version": "2.2.0"
}
```

**Benefits**:
- /version command can precisely identify installed version
- Distinguish between stable releases and development builds
- Track exact commit for debugging and support

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 23:54:00 +08:00
catlog22
9a49a86221 feat: Implement dynamic version detection and passing system
**Installation System Updates**:
- install-remote.ps1: Auto-detect version from GitHub API and pass to installer
- Install-Claude.ps1: Accept dynamic version via -SourceVersion parameter
- install-remote.sh: Synchronize version detection logic with PowerShell version
- Add installer_version field to version.json for tracking

**Codex Agent Optimization** (.codex/AGENTS.md):
- Add system optimization requirements for direct binary execution
- Prioritize apply_patch tool over Python scripts for file editing
- Add Windows UTF-8 encoding configuration for Chinese character support

**Version Flow**:
1. install-remote.* detects version from GitHub API (latest release tag)
2. Passes version to Install-Claude.* via -SourceVersion/-SourceBranch
3. Installer writes accurate version to version.json

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 23:49:52 +08:00
catlog22
25a453d8f8 chore: Remove obsolete version.json file 2025-10-04 23:42:50 +08:00
catlog22
f574c0da47 feat: Add Codex CLI optimization requirements to AGENTS.md
Add system optimization section with performance and compatibility improvements:
- Direct binary execution to avoid shell wrapper overhead
- apply_patch tool priority for efficient text editing
- Windows UTF-8 encoding configuration for Chinese character support

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 23:40:34 +08:00
catlog22
5b38a63129 refactor: Remove model specification from CLI command files
Remove hardcoded model: sonnet from CLI command frontmatter to allow dynamic model selection.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 23:26:42 +08:00
catlog22
813a307c3d feat: Optimize memory-gemini-bridge agent with tool parameter support and structured context
- Add tool parameter support (gemini/qwen/codex) to memory-gemini-bridge agent
- Implement TodoWrite task tracking for all depth levels
- Simplify agent instructions with direct bash commands
- Add structured context templates for both full and related update modes
- Ensure complete module path processing with no skipping
- Improve instruction adherence with clear execution requirements

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 21:16:00 +08:00
catlog22
f1ffe9503c feat: Add .qwen directory installation support to Install-Claude.ps1
Add .qwen directory to installation script for Qwen agent support,
ensuring complete multi-tool environment setup.

Changes:
- Add .qwen directory prerequisite check
- Add .qwen source and destination paths for Global mode
- Add .qwen source and destination paths for Path mode
- Include .qwen in backup folder detection
- Merge .qwen directory contents in both Global and Path modes
- Update installation summary to include .qwen
- Update Next steps documentation to include .qwen/QWEN.md

Installation modes:
- Global: Installs .qwen to ~/.qwen
- Path: Installs .qwen to local directory

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

Co-Authored-By: Claude <noreply@anthropic.com>
v3.4.1
2025-10-04 20:47:56 +08:00
catlog22
437897faff feat: Add multi-tool support for CLAUDE.md documentation generation (v3.4.1)
Add flexible tool selection (gemini/qwen/codex) for documentation updates,
allowing users to choose the best tool for their analysis needs.

Changes:
- Add --tool parameter to /update-memory-full and /update-memory-related
- Enhance update_module_claude.sh with tool routing (gemini|qwen|codex)
- Update command documentation with tool selection examples
- Add CHANGELOG entry for v3.4.1

Tool features:
- Gemini (default): Documentation generation, pattern recognition
- Qwen: Architecture analysis, system design (direct command, no wrapper)
- Codex: Implementation validation, code quality analysis

Backward compatible: Commands default to gemini without --tool parameter

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 20:44:10 +08:00
catlog22
7f920cb33d docs: Release v3.4.0 with TDD workflow optimization and test-gen enhancements
Version Update:
- Bump version from v3.3.0 to v3.4.0

Documentation Updates (README.md & README_CN.md):
- Updated version badges to v3.4.0
- Revised What's New section highlighting:
  * TDD workflow streamlining (33% file reduction)
  * Test coverage analysis (Phase 3 integration)
  * Iterative Green Phase with test-fix-cycle
  * Manual-first fixes with optional --use-codex
  * Test-gen workflow enhancements (3 new tool commands)
  * Dynamic timeout allocation (20-120min)

Command Reference Updates:
- Updated /workflow:tdd-plan description (6 phases)
- Enhanced /workflow:test-gen with [--use-codex] flag
- Added 3 new tool commands:
  * /workflow:tools:test-context-gather
  * /workflow:tools:test-concept-enhanced
  * /workflow:tools:test-task-generate

Version Files:
- Updated .claude/version.json to 3.4.0
- Updated .claude/commands/version.md examples

Key Features in v3.4.0:
- Eliminated TDD_PLAN.md and TDD_TASK_BREAKDOWN.md (unified IMPL_PLAN.md)
- TDD workflow upgraded from 5 to 6 phases
- Built-in test-fix-cycle in IMPL tasks
- Gemini diagnosis using bug-fix.md template
- Test-gen workflow with comprehensive test generation support

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

Co-Authored-By: Claude <noreply@anthropic.com>
v3.4.0
2025-10-04 20:18:23 +08:00
catlog22
d33c69cf4d fix: Remove timeout parameters from command examples in intelligent-tools-strategy.md 2025-10-04 20:11:44 +08:00
catlog22
7047cae356 feat: Optimize TDD workflow with streamlined file structure and test-gen integration
## TDD Workflow Enhancements

### File Structure Optimization
- **Eliminated**: TDD_PLAN.md (merged into unified IMPL_PLAN.md)
- **Eliminated**: .process/TDD_TASK_BREAKDOWN.md (enhanced ANALYSIS_RESULTS.md instead)
- **Unified**: Single IMPL_PLAN.md with TDD Task Chains section
- **Result**: Reduced 2 files per TDD session (-33% file count)

### Test-Gen Integration
- Added test coverage analysis phase (Phase 3: test-context-gather)
- Integrated iterative test-fix-cycle into Green phase (IMPL tasks)
- Gemini diagnosis with bug-fix template for test failures
- Auto-revert safety mechanism (max_iterations protection)
- Manual fix by default, optional Codex automation (--use-codex flag)

### Workflow Improvements
- 6-phase TDD planning (added test coverage analysis)
- ANALYSIS_RESULTS.md enhanced with TDD breakdown structure
- IMPL tasks include test-fix-cycle configuration
- Unified IMPL_PLAN.md structure: frontmatter + TDD Task Chains + standard sections

### Configuration
- meta.max_iterations: 3 (TDD) vs 5 (test-gen)
- meta.use_codex: false (default manual fixes)
- workflow_type: "tdd" in IMPL_PLAN.md frontmatter

### Benefits
- Eliminated redundancy (2 fewer files, 1 less Gemini call)
- Context-aware TDD (not greenfield-only)
- Faster feedback (test-fix-cycle in Green phase)
- Autonomous recovery (auto-diagnose and fix)
- Backward compatible (no breaking changes)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 20:11:12 +08:00
catlog22
73bd0b2832 feat: Implement dynamic timeout allocation for CLI tools (20-120min)
- Add task complexity-based timeout allocation
- Simple tasks: 20-40min, Medium: 40-60min, Complex: 60-120min
- Codex commands use 1.5x multiplier for longer operations
- Auto-detect timeout from PURPOSE and TASK fields

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 19:37:36 +08:00
catlog22
f59b5b8102 feat: Enhance test-gen workflow with comprehensive test generation and fix cycle
- Create test-context-gather.md for MCP-based coverage analysis
  - Analyze test coverage gaps using MCP code-index tools
  - Identify files requiring tests
  - Detect test framework and conventions
  - Generate test-context-package.json with coverage data

- Create test-concept-enhanced.md for Gemini-powered test analysis
  - Analyze coverage gaps and implementation context
  - Study existing test patterns and conventions
  - Generate comprehensive test requirements
  - Design test generation strategy
  - Output TEST_ANALYSIS_RESULTS.md with test specifications

- Update test-task-generate.md to generate two tasks
  - IMPL-001: Test generation task calling @code-developer
  - IMPL-002: Test execution and fix cycle task calling @test-fix-agent
  - Use TEST_ANALYSIS_RESULTS.md for test generation requirements
  - Configure Gemini diagnosis and Codex resume mechanism for fixes

- Update test-gen.md to 5-phase workflow
  - Phase 1: Create test session
  - Phase 2: Gather test context (test-context-gather)
  - Phase 3: Analyze test requirements (test-concept-enhanced)
  - Phase 4: Generate test tasks (test-task-generate)
  - Phase 5: Return summary
  - Simplify documentation by removing redundant content
  - Maintain all original intent while improving clarity

Complete workflow: Coverage analysis → Gemini analysis → Test generation → Test execution → Fix cycle

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 19:33:28 +08:00
catlog22
7f4dfe51fd refactor: Enhance synthesis.md with comprehensive improvements
Major improvements to brainstorm synthesis specification:

1. Output Definition Unification (Critical)
   - Remove synthesis-report.md references
   - Unify to synthesis-specification.md as single output
   - Update all metadata and descriptions

2. Execution Model Clarification (High)
   - Change "Direct Execution Only" to "Direct Execution by Main Claude"
   - Clarify: Main Claude + Read/Write/Glob + cognitive analysis
   - Emphasize avoiding context transmission loss

3. Dynamic Role Discovery (High)
   - Replace hardcoded 9-role list with runtime discovery
   - Scan .brainstorming/* directories for actual analysis.md files
   - Support flexible participation (1 to 9+ roles)
   - Update metadata to reflect dynamic role counts

4. Enhanced Document Structure (Critical)
   - Add "Key Designs & Decisions" section
     * Core architecture diagrams (Mermaid)
     * User journey maps (images)
     * Data model overview (ERD)
     * Architecture Decision Records (ADRs)

   - Add "Controversial Points & Alternatives" section
     * Document disagreements and rejected alternatives
     * Preserve decision context and rationale
     * Track dissenting roles

   - Add "Process & Collaboration Concerns" section
     * Team capability assessment
     * Process risks and mitigation
     * Collaboration patterns
     * Timeline constraints

5. Requirements Table Enhancement (Medium)
   - Add "Rationale Summary" column to all requirement tables
   - Reduce over-reliance on @ references
   - Provide immediate context for better readability

6. Responsibility Clarification
   - synthesis-specification.md: Defines "WHAT" (requirements, design)
   - IMPL_PLAN.md: Defines "HOW" (executable tasks)
   - Clear handoff between brainstorm and planning phases

7. Updated Quality Assurance Standards
   - Visual Clarity: Diagrams required
   - Decision Transparency: Alternatives documented
   - No Role Marginalization: Process roles equally visible
   - Context-Rich: Rationale included
   - Decision Traceability: @ references maintained

Related: plan.md improvements for auto-continue clarity and synthesis integration

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 16:40:06 +08:00
catlog22
9a28866837 fix: Update synthesis and plan documentation for consistency in output file naming 2025-10-04 14:36:25 +08:00
catlog22
e90c9baa13 refactor: Optimize document passing strategy in workflow
- **concept-enhanced**: Add explicit priority for source documents
  - PRIMARY: role analysis.md files (complete technical details, ADRs)
  - SECONDARY: synthesis-specification.md (integrated requirements)
  - Framework: topic-framework.md (discussion context)

- **task-generate**: Enhanced artifacts array with usage guidance
  - Add 'usage' field for each artifact type
  - Support dynamic role discovery
  - Reorder priority: synthesis (highest) → role_analysis (high) → framework (low)

- **pre_analysis**: Add explicit artifact loading instructions
  - Note when to consult role analysis (API schemas, caching configs, design tokens)
  - Load system-architect, ui-designer, product-manager analyses

- **implementation_approach**: Add clear priority instructions
  - Primary: Use synthesis-specification.md for requirements
  - Secondary: Refer to artifacts[] for technical details
  - Update logic_flow to include "Consult artifacts when needed"

- **gitignore**: Add .workflow directory to ignore list

🎯 Result: Balanced strategy - 100% fidelity in analysis phase, 78% token efficiency in planning phase, hybrid approach in execution phase

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 12:44:07 +08:00
catlog22
237a2867fb docs: Move Configuration section below Installation in README files
- Reorganize README.md and README_CN.md structure
- Move Configuration section directly after Installation for better flow
- Update MCP Tools section to "Recommended" with warning notes in both languages
- Improve user experience by placing setup instructions together

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 11:39:51 +08:00
catlog22
c8f0352ffb fix: Display timestamps in user's local timezone in installation scripts
- Convert UTC timestamps to local timezone in install-remote.ps1
- Convert UTC timestamps to local timezone in install-remote.sh
- Support cross-platform date conversion (GNU date and BSD date)
- Remove 'UTC' suffix from timestamp displays

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 09:57:46 +08:00
catlog22
48c6fa9a40 docs: Update documentation for git staging and MCP recommendations
- Add pre-execution git staging to codex-execute workflow for clear change visibility
- Update README to recommend MCP tools installation (not optional)
- Add core principle: no unsolicited reports without user permission

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 09:55:00 +08:00
catlog22
3a78dac919 release: v3.3.0 - CLI Tool Enhancements & Codex Multi-Step Execution
 Features:
- New /cli:codex-execute command for automated multi-step task execution
- Codex resume mechanism (codex exec "..." resume --last) for context continuity
- TodoWrite progress tracking for subtask execution
- Optional Git verification after each subtask (--verify-git flag)
- Automatic task JSON detection and loading
- Enhanced Codex agent configuration (.codex/AGENTS.md v2.1.0)

📚 Documentation:
- Streamlined CLI documentation (60% reduction in redundancy)
- Updated /cli:analyze, /cli:chat, /cli:execute commands
- Enhanced intelligent-tools-strategy.md with Codex resume patterns
- Unified command templates for Gemini/Qwen vs Codex
- Added Codex -i parameter documentation for image attachment

🔧 Technical:
- Multi-task prompt format (Single-Task & Multi-Task)
- Subtask coordination guidelines and best practices
- Enhanced MODE: auto with subtask execution flow
- Progress reporting for multi-step workflows

📦 Updates:
- Version bumped to 3.3.0 in README.md, README_CN.md
- Created .claude/version.json for version tracking
- Comprehensive CHANGELOG.md entry with all changes

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

Co-Authored-By: Claude <noreply@anthropic.com>
v3.3.0
2025-10-04 00:51:34 +08:00
catlog22
4b578285ea refactor: Enhance tool write protection and lower Bash requirement
- Add explicit write operation protection in intelligent-tools-strategy
  - Require MODE=write or MODE=auto for local codebase modifications
  - Default all tools to read-only analysis mode
  - Convert all Chinese text to English for consistency
- Lower Bash version requirement from 4.0 to 2.0 in Install-Claude.sh
  - Align with install-remote.sh requirements
  - Improve compatibility with older systems

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-04 00:09:17 +08:00
catlog22
5c66e268ec fix: Clarify auto-continue workflow execution model in plan command
- Replace sequential execution model with explicit auto-continue pattern
- Document that each phase returns to user before auto-continuing
- Use TodoList state for progress tracking (no external state files)
- Store parsed data (sessionId, contextPath) in memory between phases
- Clarify error handling keeps phase in_progress without proceeding

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-03 23:56:09 +08:00
catlog22
de4914f046 fix: Lower Bash version requirement from 4.0 to 2.0
Based on Gemini analysis, all script features (double brackets, local keyword,
BASH_VERSINFO array) are supported in Bash 2.0+. This change improves
compatibility with older systems while maintaining full functionality.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-03 21:23:23 +08:00
catlog22
00d1be60cb refactor: Rename DMS directory to memory and update references
- Renamed .claude/workflows/cli-templates/prompts/dms/ to memory/
- Updated all path references in update_module_claude.sh
- Updated terminology in INSTALL.md and INSTALL_CN.md
- Changed DMS system references to memory system

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-03 13:46:44 +08:00
catlog22
f549dfcc9b release: v3.2.3 - Version Management System
Add comprehensive version management and upgrade notification system:

New Features:
- Add /version command for checking installed versions
- GitHub API integration for latest release detection
- Automatic upgrade notifications and recommendations
- Version tracking in both local and global installations
- Quick version check with comprehensive status display

Documentation Updates:
- Update CHANGELOG.md with v3.2.3 release notes
- Update README.md version badge to v3.2.3
- Update README_CN.md with Chinese version documentation
- Add RELEASE_NOTES_v3.2.3.md with detailed release information
- Add /version command to command reference tables

Cleanup:
- Remove old release notes (RELEASE_NOTES_v2.0.md, RELEASE_NOTES_v3.2.1.md)

Version Files:
- Update ~/.claude/version.json to v3.2.3

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

Co-Authored-By: Claude <noreply@anthropic.com>
v3.2.3
2025-10-03 13:09:37 +08:00
catlog22
c5c36a23ea fix: Optimize version command API calls and data extraction
- Change API endpoint from /branches/main to /commits/main for reliable commit info
- Add 30-second timeout to all network calls for slow connections
- Extract release name and published date from latest release
- Extract commit message (first line only) using improved parsing
- Add commit date extraction from main branch
- Update documentation with API endpoints and timeout configuration
- Fix commit message extraction to handle JSON escape sequences

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-03 13:00:06 +08:00
catlog22
a03415bfeb feat: Add version tracking and upgrade check system
- Add /version command to check installed and latest versions
- Create version.json metadata file during installation
- Pass version and branch info from install-remote.ps1 to Install-Claude.ps1
- Support version comparison and upgrade recommendations
- Track installation mode (Global/Path) and source branch

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-03 12:46:44 +08:00