runcell 0.1.15a9

AI Agent for Jupyter

runcell

A JupyterLab extension.

Requirements

• JupyterLab >= 4.0.0

Install

To install the extension, execute:

pip install runcell

API Key Setup

D5M AI supports multiple AI providers. You need to set up the appropriate API keys as environment variables:

Anthropic Claude

export ANTHROPIC_API_KEY="your_anthropic_api_key_here"

Google Gemini (via Google AI Studio)

export GOOGLE_API_KEY="your_google_ai_studio_api_key_here"

OpenAI

export OPENAI_API_KEY="your_openai_api_key_here"

Note: For Gemini models, make sure to use the Google AI Studio API key, not Google Cloud/Vertex AI credentials. The extension uses the gemini/ prefix format which works with Google AI Studio without requiring additional Google Cloud dependencies.

Uninstall

To remove the extension, execute:

pip uninstall runcell

Compilation System

D5M AI includes a unified compilation system for IP protection and performance optimization. The system compiles core AI modules using Nuitka while maintaining development flexibility.

Quick Start

# Compile all handlers for production
python compile_unified.py

# Test the compilation system
python test_unified_compilation.py

# Development mode (uses source code)
export D5M_ENV=development

# Production mode (uses compiled modules)
export D5M_ENV=production

For detailed information, see COMPILATION_SYSTEM.md.

Contributing

Development install

Note: You will need NodeJS to build the extension package.

The jlpm command is JupyterLab's pinned version of yarn that is installed with JupyterLab. You may use yarn or npm in lieu of jlpm below.

# Clone the repo to your local environment
# Change directory to the d5m_ai directory
# Install package in development mode
pip install -e "."
# Link your development version of the extension with JupyterLab
jupyter labextension develop . --overwrite
# Rebuild extension Typescript source after making changes
jlpm build

You can watch the source directory and run JupyterLab at the same time in different terminals to watch for changes in the extension's source and automatically rebuild the extension.

# Watch the source directory in one terminal, automatically rebuilding when needed
jlpm watch
# Run JupyterLab in another terminal
jupyter lab

With the watch command running, every saved change will immediately be built locally and available in your running JupyterLab. Refresh JupyterLab to load the change in your browser (you may need to wait several seconds for the extension to be rebuilt).

By default, the jlpm build command generates the source maps for this extension to make it easier to debug using the browser dev tools. To also generate source maps for the JupyterLab core extensions, you can run the following command:

jupyter lab build --minimize=False

Development uninstall

pip uninstall runcell

In development mode, you will also need to remove the symlink created by jupyter labextension develop command. To find its location, you can run jupyter labextension list to figure out where the labextensions folder is located. Then you can remove the symlink named runcell within that folder.

Testing the extension

Frontend tests

This extension is using Jest for JavaScript code testing.

To execute them, execute:

jlpm
jlpm test

Integration tests

This extension uses Playwright for the integration tests (aka user level tests). More precisely, the JupyterLab helper Galata is used to handle testing the extension in JupyterLab.

More information are provided within the ui-tests README.

Packaging the extension

See RELEASE

Keyboard Shortcuts

The AI chat panel can be opened using Cmd/Ctrl+L.

Development

source jupyterlab-env/bin/activate
jupyter server extension enable d5m_ai
jupyter lab