admin/ClaudeCode-Roblox-Studio-MCP
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit: Add documentation and gitignore

Browse Source 
🤖 Generated with Claude Code

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Claude
2025-12-07 13:14:00 +04:00
Unverified
parent 8bf0eb2be0
commit 11aa5a444a
4 changed files with 446 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

121
.gitignore vendored Normal file
View File

@@ -0,0 +1,121 @@
# Windows
Thumbs.db
ehthumbs.db
Desktop.ini
# Windows Installer files
*.cab
*.msi
*.msix
*.msm
*.msp
# Windows shortcuts
*.lnk
# Windows cache directories
[.cache]/
[.local]/
[.temp]/
[.tmp]/
# Windows application data
AppData/
Local Settings/
NTUSER*
ntuser*
# Development tools
.vscode/
.android/
.gradle/
.emulator_console_auth_token
expo/
.bun/
.claude/
.claude-server-commander/
.codex/
.config/
.docker/
.gemini/
.gitconfig/
.gitlab/
.kilocode/
.lmstudio/
.lmstudio-home-pointer/
.marscode/
.mult-fetch-mcp-server/
.pm2/
.qwen/
.sbx-denybin/
.ssh/
.trae/
.trae-aicc/
.trae-cn/
.wslconfig
# Python
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
env/
venv/
ENV/
env.bak/
venv.bak/
# Node.js
node_modules/
npm-debug.log*
yarn-debug.log*
yarn-error.log*
# Logs
*.log
logs/
# Temporary files
*.tmp
*.temp
*.bak
*~
# OS generated files
.DS_Store
.DS_Store?
._*
.Spotlight-V100
.Trashes
ehthumbs.db
Thumbs.db
# Large binaries
*.exe
*.zip
*.tar.gz
*.rar
# Database files
*.db
*.sqlite
*.sqlite3
# IDE files
.idea/
*.swp
*.swo
*~
# Build outputs
build/
dist/
out/
# Environment files
.env
.env.local
.env.development.local
.env.test.local
.env.production.local

103
README.md Normal file
View File

@@ -0,0 +1,103 @@
# Claude Code PowerShell Python App
A sophisticated PowerShell wrapper application that provides coding assistance in the style of Claude Code, using Qwen3-Coder models with support for both LM Studio server and direct model loading.
## Files Created
- `lm_studio_client.py` - Enhanced Python client script with Qwen3-Coder features
- `lm_studio.ps1` - PowerShell wrapper script
- `README.md` - This documentation
## Prerequisites
1. Python 3.7+ installed and in PATH
2. For LM Studio: LM Studio running with server enabled on http://127.0.0.1:1234
3. For Qwen direct: transformers and torch libraries
4. Python requests library (auto-installed by script)
5. Optional: Flask for web interface
## Usage
### PowerShell Commands:
**List available models (LM Studio only):**
```powershell
.\lm_studio.ps1 -ListModels
```
**Single prompt:**
```powershell
.\lm_studio.ps1 -Prompt "Write a Python function to sort a list"
```
**Interactive chat mode:**
```powershell
.\lm_studio.ps1 -Interactive
```
**With specific language focus:**
```powershell
.\lm_studio.ps1 -Interactive -Language python
```
**Using Qwen direct model:**
```powershell
.\lm_studio.ps1 -Client qwen -Prompt "Hello"
```
**Fill-in-the-middle code completion:**
```powershell
.\lm_studio.ps1 -Client qwen -FimPrefix "def sort_list(arr):" -FimSuffix "return sorted_arr"
```
**Start web interface:**
```powershell
.\lm_studio.ps1 -Web -Port 8080
```
**Start terminal user interface:**
```powershell
.\lm_studio.ps1 -Tui
```
### Direct Python Usage:
```bash
python lm_studio_client.py --help
python lm_studio_client.py --client qwen --prompt "Create a REST API"
python lm_studio_client.py --interactive
python lm_studio_client.py --client qwen --fim-prefix "def hello():" --fim-suffix "print('world')"
python lm_studio_client.py --web --port 5000
python lm_studio_client.py --tui
```
## Features
- **Dual Client Support**: LM Studio server or direct Qwen3-Coder model loading
- **Interactive Chat**: Real-time conversation with the AI coding assistant
- **Terminal User Interface**: Curses-based TUI for interactive chat
- **Fill-in-the-Middle**: Advanced code completion for partial code snippets
- **Language-Specific Assistance**: Focus on specific programming languages
- **Web Interface**: Modern web UI with tabs for different features
- **Model Selection**: Choose from available models
- **Auto-Dependency Installation**: Automatically installs required Python packages
- **Error Handling**: Robust error handling and validation
## Qwen3-Coder Features
- **Agentic Coding**: Advanced coding capabilities with tool use
- **Long Context**: Support for up to 256K tokens
- **358 Programming Languages**: Comprehensive language support
- **Fill-in-the-Middle**: Specialized code completion
- **Function Calling**: Tool integration capabilities
## Setup
1. For LM Studio: Ensure LM Studio is running with server enabled
2. For Qwen direct: Install transformers: `pip install transformers torch`
3. For web interface: Install Flask: `pip install flask`
4. Run the PowerShell script from the same directory
5. The script will auto-install required Python dependencies
## Web Interface
The web interface provides three main tabs:
- **Chat**: Interactive conversation with the AI
- **Fill-in-the-Middle**: Code completion for partial snippets
- **Code Assistant**: Generate code from descriptions
Access at `http://localhost:5000` (or custom port)

53
RUNNING_INSTRUCTIONS.md Normal file
View File

@@ -0,0 +1,53 @@
# Smart Calendar Project - Running Instructions
This document provides instructions on how to run the Smart Calendar Project (Reclaim.ai clone) in WSL.
## Prerequisites Installed
The following prerequisites have been installed in your WSL environment:
- Node.js and npm
- PostgreSQL database
- Database schema has been applied to the `reclaim_clone` database
- Client dependencies have been installed
## Running the Application
### 1. Start PostgreSQL (if not already running):
```bash
sudo service postgresql start
```
### 2. Start the frontend development server:
```bash
cd ~/reclaim-clone/client
npm run dev
```
The frontend will be available at http://localhost:3000
### 3. (Optional) Start the backend server:
Note: The Swift backend requires Swift to be installed in WSL, which is a more involved process. The backend would typically run on port 8080.
## Current Status
Currently, the frontend is fully set up and ready to run. The database is configured and ready for use.
To run the complete application with backend functionality, Swift would need to be installed in WSL, which requires additional steps specific to your Ubuntu version.
## Quick Start Script
You can use the provided script to quickly start the frontend:
```bash
~/start_project.sh
```
Then access the application at http://localhost:3000
## Stopping the Application
To stop the application:
1. Press Ctrl+C in the terminal where the development server is running
2. If you started PostgreSQL, you can stop it with:
```bash
sudo service postgresql stop
```

169
TESTING_WSL.md Normal file
View File

@@ -0,0 +1,169 @@
# Testing the Smart Calendar Project in WSL
This document provides instructions for testing the Reclaim.ai clone (smart calendar project) in your WSL environment.
## Prerequisites Verification
1. **Verify WSL is running:**
```bash
wsl --status
```
2. **Confirm Ubuntu distribution is accessible:**
```bash
wsl -d Ubuntu --exec whoami
```
## Project Setup in WSL
1. **Enter your WSL environment:**
```bash
wsl -d Ubuntu
```
2. **Navigate to the project directory:**
```bash
cd ~/reclaim-clone
```
3. **Run the setup script to install dependencies:**
```bash
chmod +x ~/setup_in_wsl.sh
~/setup_in_wsl.sh
```
Or follow manual steps below:
4. **Install backend dependencies (Swift):**
```bash
# Update package list
sudo apt update
# Install Swift prerequisites
sudo apt install -y clang libicu-dev libxml2-dev libzip-dev libbsd-dev
# For Ubuntu 20.04 or 22.04, install Swift using these commands:
VERSION=$(lsb_release -rs)
if [[ $VERSION == "20.04" || $VERSION == "22.04" ]]; then
wget -q -O - https://swift.org/keys/all-keys.asc | gpg --dearmor | sudo tee /etc/apt/trusted.gpg.d/swift-archive.gpg
echo "deb [signed-by=/etc/apt/trusted.gpg.d/swift-archive.gpg] https://download.swift.org/ubuntu$(echo $VERSION | sed 's/\.//') stable main" | sudo tee /etc/apt/sources.list.d/swift.list
sudo apt update
sudo apt install -y swift-lang
fi
```
5. **Install frontend dependencies (Node.js & npm):**
```bash
# Install Node.js
curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
sudo apt-get install -y nodejs
```
6. **Install and configure PostgreSQL:**
```bash
# Install PostgreSQL
sudo apt update
sudo apt install -y postgresql postgresql-contrib
# Start PostgreSQL service
sudo service postgresql start
# Set up the reclaim_clone database
sudo -u postgres createuser --superuser $(whoami)
sudo -u postgres createdb reclaim_clone
sudo -u postgres psql -d reclaim_clone -f ~/reclaim-clone/database/schema.sql
```
7. **Install client dependencies:**
```bash
cd ~/reclaim-clone/client
npm install
cd ..
```
## Testing the Backend (API)
1. **Navigate to the project directory:**
```bash
cd ~/reclaim-clone
```
2. **Test the backend (API server):**
```bash
swift run
```
3. **Verify the backend is running:**
- Open another terminal tab
- Enter WSL: `wsl -d Ubuntu`
- Test the API: `curl http://localhost:8080`
- You should see a response from the server
## Testing the Frontend (Web Client)
1. **Navigate to the client directory:**
```bash
cd ~/reclaim-clone/client
```
2. **Start the development server:**
```bash
npm run dev
```
3. **Verify the frontend is running:**
- Open a browser on the Windows host
- Navigate to `http://localhost:3000`
- You should see the Reclaim.ai clone application
## Testing Full Integration
1. **Start both backend and frontend:**
- Terminal 1: `cd ~/reclaim-clone && swift run`
- Terminal 2: `cd ~/reclaim-clone/client && npm run dev`
2. **Access the application:**
- In your Windows browser, go to `http://localhost:3000`
- You should be able to use the full application with all features
## Troubleshooting
1. **If PostgreSQL service isn't starting:**
```bash
sudo service postgresql start
sudo systemctl enable postgresql
```
2. **If Swift isn't available:**
- Check Ubuntu version: `lsb_release -a`
- Visit https://www.swift.org/download/ for Ubuntu-specific installation instructions
3. **If the frontend can't connect to the backend:**
- Verify both services are running
- Check that the backend is running on port 8080
- Verify the frontend is configured to connect to the correct backend URL
4. **If you have permission issues:**
```bash
# Fix file permissions if needed
sudo chown -R $(whoami):$(whoami) ~/reclaim-clone
```
## Verification Checklist
- [ ] WSL Ubuntu is accessible
- [ ] Project files are available in `~/reclaim-clone`
- [ ] Swift is installed and accessible (`swift --version`)
- [ ] Node.js is installed and accessible (`node --version`)
- [ ] PostgreSQL is installed and running
- [ ] Backend server starts without errors
- [ ] Frontend server starts without errors
- [ ] Application is accessible via browser at `http://localhost:3000`
- [ ] All major features of the smart calendar app are functional
## Additional Notes
- The project is now fully migrated to WSL and can be developed using Linux tools
- You can access the files from Windows at `\\wsl.localhost\Ubuntu\home\{username}\reclaim-clone`
- For development, you can use VS Code with the Remote-WSL extension for a better experience
- The application supports Trello-like kanban boards, calendar integration, and multi-user system as designed