diff --git a/CHANGELOG.md b/CHANGELOG.md index 44cc94e0..a87fa3fa 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,71 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). +## [5.8.1] - 2025-01-16 + +### ⚡ Lite-Plan Workflow & CLI Tools Enhancement + +This release introduces a powerful new lightweight planning workflow with intelligent automation and optimized CLI tool usage. + +#### ✨ Added + +**Lite-Plan Workflow** (`/workflow:lite-plan`): +- ✨ **Interactive Lightweight Workflow** - Fast, in-memory planning and execution + - **Phase 1: Task Analysis & Smart Exploration** (30-90s) + - Auto-detects when codebase context is needed + - Optional `@cli-explore-agent` for code understanding + - Force exploration with `-e` or `--explore` flag + - **Phase 2: Interactive Clarification** (user-dependent) + - Ask follow-up questions based on exploration findings + - Gather missing information before planning + - **Phase 3: Adaptive Planning** (20-60s) + - Low complexity: Direct planning by Claude + - Medium/High complexity: Delegate to `@cli-planning-agent` + - **Phase 4: Three-Dimensional Multi-Select Confirmation** (user-dependent) + - ✅ **Task Approval**: Allow / Modify / Cancel (with optional supplements) + - 🔧 **Execution Method**: Agent / Provide Plan / CLI (Gemini/Qwen/Codex) + - 🔍 **Code Review**: No / Claude / Gemini / Qwen / Codex + - **Phase 5: Live Execution & Tracking** (5-120min) + - Real-time TodoWrite progress updates + - Parallel task execution for independent tasks + - Optional post-execution code review +- ✨ **Parallel Task Execution** - Identifies independent tasks for concurrent execution +- ✨ **Flexible Tool Selection** - Preset with `--tool` flag or choose during confirmation +- ✨ **No File Artifacts** - All planning stays in memory for faster workflow + +#### 🔄 Changed + +**CLI Tools Optimization**: +- 🔄 **Simplified Command Syntax** - Removed `-m` parameter requirement + - Gemini: Auto-selects `gemini-2.5-pro` (default) or `gemini-2.5-flash` + - Qwen: Auto-selects `coder-model` (default) or `vision-model` + - Codex: Auto-selects `gpt-5.1` (default), `gpt-5.1-codex`, or `gpt-5.1-codex-mini` +- 🔄 **Improved Model Selection** - Tools now auto-select best model for task +- 🔄 **Updated Documentation** - Clearer guidelines in `intelligent-tools-strategy.md` + +**Execution Workflow Enhancement**: +- 🔄 **Streamlined Phases** - Simplified execution phases with lazy loading strategy +- 🔄 **Enhanced Error Handling** - Improved error messages and recovery options +- 🔄 **Clarified Resume Mode** - Better documentation for workflow resumption + +**CLI Explore Agent**: +- 🎨 **Improved Visibility** - Changed color scheme from blue to yellow + +#### 📝 Documentation + +**Updated Files**: +- 🔄 **README.md / README_CN.md** - Added Lite-Plan workflow usage examples +- 🔄 **COMMAND_REFERENCE.md** - Added `/workflow:lite-plan` entry +- 🔄 **COMMAND_SPEC.md** - Added detailed technical specification for Lite-Plan +- 🔄 **intelligent-tools-strategy.md** - Updated model selection guidelines + +#### 🐛 Bug Fixes + +- Fixed command syntax inconsistencies in CLI tool documentation +- Improved task dependency detection for parallel execution + +--- + ## [5.5.0] - 2025-11-06 ### 🎯 Interactive Command Guide & Enhanced Documentation diff --git a/COMMAND_REFERENCE.md b/COMMAND_REFERENCE.md index c73ad5e6..5229ec42 100644 --- a/COMMAND_REFERENCE.md +++ b/COMMAND_REFERENCE.md @@ -38,6 +38,7 @@ These commands orchestrate complex, multi-phase development processes, from plan | Command | Description | |---|---| | `/workflow:plan` | Orchestrate 5-phase planning workflow with quality gate, executing commands and passing context between phases. | +| `/workflow:lite-plan` | ⚡ **NEW** Lightweight interactive planning and execution workflow with in-memory planning, smart code exploration, three-dimensional multi-select confirmation (task approval + execution method + code review), and parallel task execution support. | | `/workflow:execute` | Coordinate agents for existing workflow tasks with automatic discovery. | | `/workflow:resume` | Intelligent workflow session resumption with automatic progress analysis. | | `/workflow:review` | Optional specialized review (security, architecture, docs) for completed implementation. | diff --git a/COMMAND_SPEC.md b/COMMAND_SPEC.md index afc65819..2d5bac7b 100644 --- a/COMMAND_SPEC.md +++ b/COMMAND_SPEC.md @@ -45,6 +45,44 @@ High-level orchestrators for complex, multi-phase development processes. /workflow:plan "Create a simple Express API that returns Hello World" ``` +### **/workflow:lite-plan** ⚡ NEW + +- **Syntax**: `/workflow:lite-plan [--tool claude|gemini|qwen|codex] [-e|--explore] "task description"|file.md` +- **Parameters**: + - `--tool` (Optional, String): Preset CLI tool for execution (claude|gemini|qwen|codex). If not provided, user selects during confirmation. + - `-e, --explore` (Optional, Flag): Force code exploration phase (overrides auto-detection logic). + - `task description|file.md` (Required, String): Task description or path to .md file. +- **Responsibilities**: Lightweight interactive planning and execution workflow with 5 phases: + 1. **Task Analysis & Exploration**: Auto-detects need for codebase context, optionally launches `@cli-explore-agent` (30-90s) + 2. **Clarification**: Interactive Q&A based on exploration findings (user-dependent) + 3. **Planning**: Adaptive planning strategy - direct (Low complexity) or delegate to `@cli-planning-agent` (Medium/High complexity) (20-60s) + 4. **Three-Dimensional Confirmation**: Multi-select interaction for task approval + execution method + code review tool (user-dependent) + 5. **Execution & Tracking**: Live TodoWrite progress updates with selected method (5-120min) +- **Key Features**: + - **Smart Code Exploration**: Auto-detects when codebase context is needed (use `-e` to force) + - **In-Memory Planning**: No file artifacts generated during planning phase + - **Three-Dimensional Multi-Select**: Task approval (Allow/Modify/Cancel) + Execution method (Agent/Provide Plan/CLI) + Code review (No/Claude/Gemini/Qwen/Codex) + - **Parallel Task Execution**: Identifies independent tasks for concurrent execution + - **Flexible Execution**: Choose between Agent (@code-developer) or CLI (Gemini/Qwen/Codex) + - **Optional Post-Review**: Built-in code quality analysis with user-selectable AI tool +- **Agent Calls**: + - `@cli-explore-agent` (conditional, Phase 1) + - `@cli-planning-agent` (conditional, Phase 3 for Medium/High complexity) + - `@code-developer` (conditional, Phase 5 if Agent execution selected) +- **Skill Invocation**: None directly, but agents may invoke skills. +- **Integration**: Standalone workflow for quick tasks. Alternative to `/workflow:plan` + `/workflow:execute` pattern. +- **Example**: + ```bash + # Basic usage with auto-detection + /workflow:lite-plan "Add JWT authentication to user login" + + # Force code exploration + /workflow:lite-plan -e "Refactor logging module for better performance" + + # Preset CLI tool + /workflow:lite-plan --tool codex "Add unit tests for auth service" + ``` + ### **/workflow:execute** - **Syntax**: `/workflow:execute [--resume-session="session-id"]` diff --git a/README.md b/README.md index 143eb266..ec26e2c7 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@