WarpCode

🚀 Warp through development cycles with automated BDD and Claude Coder 🚀

A Python CLI tool that orchestrates Claude Code to automatically implement BDD scenarios with zero human intervention, real-time monitoring, and robust fake implementation detection.

✨ Key Features

• 🔄 Fully Automated BDD Development - Zero human intervention once started
• 📞 Conversation Continuity - Claude maintains context across iterations with -c flag support
• 📊 Real-time OpenTelemetry Monitoring - Live Claude activity tracking with OTEL events
• 🔍 Reality Validation - Comprehensive fake implementation detection and prevention
• 🤖 Claude Integration - Automated Claude Code execution with enhanced debugging
• 🧪 BDD Test Management - Behave integration with intelligent pass/fail parsing
• 📈 Code Quality Assurance - Radon integration for complexity monitoring
• 🎨 Beautiful CLI - Rich console output with real-time progress indicators

🚀 Quick Start

Installation

pip install warpcode

Basic Usage

# Run WarpCode with interactive setup
warpcode

# Or use the shorter alias
warp

# Enable debug mode for comprehensive Claude activity visibility
WARPCODE_DEBUG=1 warpcode

# Enable verbose output to see all Claude interactions
WARPCODE_VERBOSE=1 warpcode

📊 Real-time Monitoring

WarpCode provides multiple levels of monitoring:

1. Live Activity Dashboard

Real-time display showing:

• Current BDD test status
• Claude conversation state
• Active tool executions
• Reality validation results

2. OpenTelemetry Integration

Captures and displays:

• claude_code.user_prompt - When prompts are sent
• claude_code.tool_result - Tool execution results
• claude_code.api_request - API calls with token counts
• claude_code.tool_decision - Permission decisions

3. Debug Modes

# Show full Claude command execution details
export WARPCODE_DEBUG=1

# Display all Claude output in real-time
export WARPCODE_VERBOSE=1

# Both modes together for maximum visibility
export WARPCODE_DEBUG=1 WARPCODE_VERBOSE=1

🔍 Reality Validation

WarpCode prevents fake implementations through:

• Pattern Detection - Scans for HTML mocks, hardcoded responses, simulation code
• Behavioral Testing - Verifies tests actually depend on implementation files
• Subprocess Validation - Ensures proper error handling in system calls
• Mock File Detection - Identifies files with excessive hardcoded content
• Conversation Reset - Clears Claude state when fake patterns are detected

🎯 Architecture Overview

┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐
│   Environment   │    │   Orchestrator   │    │  Claude Code    │
│    Manager      │◄──►│     Loop         │◄──►│   Interface     │
└─────────────────┘    └──────────────────┘    └─────────────────┘
         │                        │                       │
         ▼                        ▼                       ▼
┌─────────────────┐    ┌──────────────────┐    ┌─────────────────┐
│   BDD Runner    │    │   Scoreboard     │    │   Reality       │
│   (Behave)      │    │    Manager       │    │   Validator     │
└─────────────────┘    └──────────────────┘    └─────────────────┘
         │                        │                       │
         └────────────────────────┼───────────────────────┘
                                 ▼
                    ┌──────────────────┐
                    │ Activity Dashboard│
                    │ (Real-time UI)   │
                    └──────────────────┘

📁 Project Structure

your-project/
├── features/                    # BDD feature files
│   ├── environment.py          # Behave configuration
│   ├── steps/                  # Step definitions
│   └── *.feature              # Gherkin scenarios
├── scoreboards/                # Real-time status JSON files
│   ├── master_status.json     # Overall orchestration state
│   ├── bdd_status.json        # Test execution results
│   ├── claude_status.json     # Claude activity tracking
│   └── validation_*.json      # Reality validation reports
├── venv/                      # Virtual environment
├── behave.ini                 # Behave configuration
└── .warpcode_conversation_id  # Claude conversation state

🔄 How It Works

1. Smart Environment Setup - Detects existing setup, only installs missing components
2. Conversation Continuity - Loads existing Claude conversation or starts new one
3. BDD Execution - Runs behave tests with real-time progress monitoring
4. Claude Orchestration - Sends focused prompts with anti-fake enforcement
5. Reality Validation - Scans for fake patterns, validates behavioral dependencies
6. Iterative Improvement - Feeds validation failures back to enhance next iteration

📋 Requirements

• Python 3.10+
• Claude Code CLI (authenticated and available in PATH)
• Git (for project management)

🛠️ Development

# Install in development mode
git clone https://github.com/warpcodedev/warpcode
cd warpcode
pip install -e .

# Run with debug output
WARPCODE_DEBUG=1 warpcode

📝 Release Notes

v1.1.0 (Latest) - Advanced Fake Detection & Red-Green BDD

• ✅ LLM-Powered Fake Detection: Claude analyzes step files to catch sophisticated fakes
• ✅ Dual-Phase Validation: Combines regex patterns + LLM analysis for comprehensive detection
• ✅ Red-Green BDD Enforcement: Proper TDD workflow requiring tests to fail first
• ✅ Two-Phase Claude Workflow: Phase 1: Analyze fakes, Phase 2: Implement real code
• ✅ Cross-Validation System: Validates WarpCode parsing against actual behave execution
• ✅ Enhanced Behavioral Testing: File dependency tests, scenario isolation, truth verification
• ✅ Comprehensive Fake Reports: Auto-generates fakesteps.md documentation

v1.0.9 - Comprehensive Monitoring & Conversation Continuity

• ✅ Conversation Continuity: Claude maintains context with -c flag support
• ✅ Real-time OTEL Monitoring: Live OpenTelemetry event parsing and display
• ✅ Enhanced Reality Validation: Behavioral testing and fake pattern learning
• ✅ Smart Environment Setup: Prevents unnecessary re-initialization
• ✅ Comprehensive Debug Output: Full Claude activity visibility with timestamps
• ✅ Validation Feedback Loop: Failed validations inform subsequent prompts

v1.0.8 - Reality Validation Foundation

• ✅ Reality Validator: Comprehensive fake implementation detection
• ✅ Enhanced Claude Prompts: Strict anti-mock enforcement with time limits
• ✅ Improved Monitoring: Initial OpenTelemetry integration

v1.0.7 - Enhanced Dashboard & Monitoring

• ✅ Activity Dashboard: Real-time UI progress tracking
• ✅ Scoreboard Management: JSON-based status persistence
• ✅ Claude Interface: Automated execution with log monitoring

v1.0.6 - Core BDD Integration

• ✅ BDD Runner: Behave integration with result parsing
• ✅ Environment Manager: Virtual environment and dependency handling
• ✅ Basic Orchestration: Multi-iteration Claude execution loop

Earlier Versions (v1.0.0 - v1.0.5)

• Initial project setup and basic functionality

🎛️ Configuration Options

Environment Variables

WARPCODE_DEBUG=1        # Enable comprehensive debug output
WARPCODE_VERBOSE=1      # Show all Claude interactions
ANTHROPIC_API_KEY=...   # Claude API authentication

Debug Features

• Full Command Logging: See exact Claude Code CLI invocations
• Real-time Output: Live Claude response streaming with timestamps
• Conversation Tracking: Monitor conversation ID persistence
• OTEL Event Parsing: Detailed OpenTelemetry event breakdown
• Validation Reports: Comprehensive fake implementation analysis

🔗 Links

• PyPI: https://pypi.org/project/warpcode/
• GitHub: https://github.com/warpcodedev/warpcode
• Issues: https://github.com/warpcodedev/warpcode/issues
• Documentation: https://github.com/warpcodedev/warpcode#readme

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Add tests for new functionality
4. Submit a pull request

Built with ❤️ for automated BDD development

Zero human intervention. Real implementations only. Maximum development velocity.