Skip to main content

AI-powered git commit message and changelog generator

Project description

Git-LLM-Tool

Python Version License: MIT Code Style: Black

AI-powered git commit message and changelog generator using LLM APIs.

Table of Contents

Features

  • 🤖 Smart Commit Messages: Automatically generate commit messages from git diff using AI
  • 📝 Changelog Generation: Generate structured changelogs from git history
  • 🔧 Multiple LLM Providers: Support for OpenAI, Anthropic Claude, Google Gemini, and Azure OpenAI
  • ⚙️ Hierarchical Configuration: Project-level and global configuration support
  • 🎯 Jira Integration: Automatic ticket detection and work hours tracking
  • 🌐 Multi-language Support: Generate messages in different languages
  • ✏️ Editor Integration: Configurable editor support for reviewing commit messages
  • 🚀 Easy Setup: Simple installation and configuration

Installation

From PyPI (Coming Soon)

pip install git-llm-tool

From Source

git clone https://github.com/your-username/git-llm-tool.git
cd git-llm-tool
poetry install

Quick Start

1. Initialize Configuration

git-llm config init

2. Configure Your API Key

Choose one of the supported providers:

# OpenAI
git-llm config set llm.api_keys.openai sk-your-openai-key-here

# Anthropic Claude
git-llm config set llm.api_keys.anthropic sk-ant-your-key-here

# Google Gemini
git-llm config set llm.api_keys.google your-gemini-key-here

# Azure OpenAI
git-llm config set llm.api_keys.azure_openai your-azure-key
git-llm config set llm.azure_openai.endpoint https://your-resource.openai.azure.com/
git-llm config set llm.azure_openai.deployment_name gpt-4o

3. Generate Commit Messages

# Stage your changes
git add .

# Generate and review commit message (opens editor)
git-llm commit

# Or apply directly without review
git-llm commit --apply

4. Generate Changelogs

# Generate changelog from last tag to HEAD
git-llm changelog

# Generate changelog for specific range
git-llm changelog --from v1.0.0 --to v2.0.0

Configuration

Configuration Hierarchy

The tool uses a hierarchical configuration system (highest to lowest priority):

  1. CLI flags (highest priority)
  2. Project config .git-llm-tool.yaml
  3. Global config ~/.git-llm-tool/config.yaml
  4. Environment variables
  5. Default values

Configuration Options

LLM Settings

# Set default model
git-llm config set llm.default_model gpt-4o

# Set output language (en, zh, ja, etc.)
git-llm config set llm.language en

# API Keys
git-llm config set llm.api_keys.openai sk-your-key
git-llm config set llm.api_keys.anthropic sk-ant-your-key
git-llm config set llm.api_keys.google your-key

# Azure OpenAI specific settings
git-llm config set llm.azure_openai.endpoint https://your-resource.openai.azure.com/
git-llm config set llm.azure_openai.api_version 2024-12-01-preview
git-llm config set llm.azure_openai.deployment_name gpt-4o

Editor Configuration

# Set preferred editor for commit message review
git-llm config set editor.preferred_editor vi
git-llm config set editor.preferred_editor nano
git-llm config set editor.preferred_editor "code --wait"  # VS Code
git-llm config set editor.preferred_editor "subl --wait"  # Sublime Text

Editor Priority (highest to lowest):

  1. editor.preferred_editor config
  2. git config core.editor
  3. Environment variables (GIT_EDITOR, VISUAL, EDITOR)
  4. System defaults (nano, vim, vi)

Jira Integration

# Enable Jira integration
git-llm config set jira.enabled true

# Set branch regex pattern for ticket extraction
git-llm config set jira.branch_regex '^(feat|fix|chore)\/([A-Z]+-\d+)\/.+$'

Example Configuration File

Global config (~/.git-llm-tool/config.yaml):

llm:
  default_model: 'gpt-4o'
  language: 'en'
  api_keys:
    openai: 'sk-your-openai-key'
    anthropic: 'sk-ant-your-key'
    google: 'your-gemini-key'
  azure_openai:
    endpoint: 'https://your-resource.openai.azure.com/'
    api_version: '2024-12-01-preview'
    deployment_name: 'gpt-4o'

editor:
  preferred_editor: 'vi'

jira:
  enabled: true
  branch_regex: '^(feat|fix|chore)\/([A-Z]+-\d+)\/.+$'

View Configuration

# View all configuration
git-llm config get

# View specific setting
git-llm config get llm.default_model
git-llm config get editor.preferred_editor

CLI Commands Reference

Commit Command

git-llm commit [OPTIONS]

Options:
  -a, --apply          Apply commit message directly without opening editor
  -m, --model TEXT     Override LLM model (e.g., gpt-4, claude-3-sonnet)
  -l, --language TEXT  Override output language (e.g., en, zh, ja)
  -v, --verbose        Enable verbose output
  --help               Show help message

Changelog Command

git-llm changelog [OPTIONS]

Options:
  --from TEXT     Starting reference (default: last tag)
  --to TEXT       Ending reference (default: HEAD)
  -o, --output TEXT  Output file (default: stdout)
  -f, --force        Force overwrite existing output file
  --help             Show help message

Config Commands

git-llm config init                    # Initialize configuration
git-llm config get [KEY]              # Get configuration value(s)
git-llm config set KEY VALUE          # Set configuration value

Environment Variables

You can also configure the tool using environment variables:

# LLM API Keys
export OPENAI_API_KEY="sk-your-openai-key"
export ANTHROPIC_API_KEY="sk-ant-your-key"
export GOOGLE_API_KEY="your-gemini-key"

# Azure OpenAI
export AZURE_OPENAI_API_KEY="your-azure-key"
export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
export AZURE_OPENAI_API_VERSION="2024-12-01-preview"
export AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o"

# Override default model
export GIT_LLM_MODEL="gpt-4o"
export GIT_LLM_LANGUAGE="en"

Usage Examples

Basic Workflow

# 1. Make changes to your code
echo "console.log('Hello World');" > app.js

# 2. Stage changes
git add app.js

# 3. Generate commit message with review
git-llm commit
# Opens your editor with AI-generated message for review

# 4. Or apply directly
git-llm commit --apply

Using Different Models

# Use specific model for this commit
git-llm commit --model claude-3-sonnet

# Use different language
git-llm commit --language zh

Project-specific Configuration

Create .git-llm-tool.yaml in your project root:

llm:
  default_model: 'claude-3-sonnet'
  language: 'zh'
editor:
  preferred_editor: 'code --wait'
jira:
  enabled: true
  branch_regex: '^(feat|fix|docs)\/([A-Z]+-\d+)\/.+$'

Supported Models

OpenAI

  • gpt-4o (recommended)
  • gpt-4o-mini
  • gpt-4-turbo
  • gpt-3.5-turbo

Anthropic Claude

  • claude-3-5-sonnet-20241022 (recommended)
  • claude-3-5-haiku-20241022
  • claude-3-opus-20240229

Google Gemini

  • gemini-1.5-pro
  • gemini-1.5-flash

Azure OpenAI

  • Any deployment of the above OpenAI models

Development

Setup Development Environment

# Clone repository
git clone https://github.com/your-username/git-llm-tool.git
cd git-llm-tool

# Install dependencies
poetry install

# Install pre-commit hooks
poetry run pre-commit install

Running Tests

# Run all tests
poetry run pytest

# Run with coverage
poetry run pytest --cov=git_llm_tool

# Run specific test file
poetry run pytest tests/test_config.py

Code Formatting

# Format code
poetry run black .
poetry run isort .

# Check formatting
poetry run black --check .
poetry run flake8 .

Building and Publishing

# Build package
poetry build

# Publish to PyPI (maintainers only)
poetry publish

Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Make your changes
  4. Add tests for new functionality
  5. Ensure all tests pass (poetry run pytest)
  6. Format code (poetry run black . && poetry run isort .)
  7. Commit your changes (git-llm commit 😉)
  8. Push to the branch (git push origin feature/amazing-feature)
  9. Open a Pull Request

Requirements

  • Python 3.12+
  • Git
  • At least one LLM provider API key

Troubleshooting

Common Issues

"No suitable editor found"

  • Set your preferred editor: git-llm config set editor.preferred_editor vi
  • Or set git editor: git config --global core.editor vi

"No staged changes found"

  • Stage your changes first: git add .

"API Error: Invalid API key"

  • Check your API key configuration: git-llm config get
  • Ensure the key is correctly set: git-llm config set llm.api_keys.openai sk-your-key

"No commits found in range"

  • Make sure you have commits in the specified range
  • Check git log: git log --oneline

License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

git_llm_tool-0.1.0.tar.gz (20.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

git_llm_tool-0.1.0-py3-none-any.whl (25.5 kB view details)

Uploaded Python 3

File details

Details for the file git_llm_tool-0.1.0.tar.gz.

File metadata

  • Download URL: git_llm_tool-0.1.0.tar.gz
  • Upload date:
  • Size: 20.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.13.5 Darwin/24.6.0

File hashes

Hashes for git_llm_tool-0.1.0.tar.gz
Algorithm Hash digest
SHA256 2bdc7a014ff16d7f6b6b31ff385d42636f80a36af0056811f89098aa9b0cd690
MD5 9b727949c091283ab51328e21b498073
BLAKE2b-256 d35d4e6070aa80231cf2c4467006108c672f11c1ae26fa37f2c82bd486c5e71b

See more details on using hashes here.

File details

Details for the file git_llm_tool-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: git_llm_tool-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 25.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.1.3 CPython/3.13.5 Darwin/24.6.0

File hashes

Hashes for git_llm_tool-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f56065102389a5680a89d5d5150e402259e29fe3137f6f0f7f1253c106d2a1ae
MD5 0ade2d067b3af98ef67c59000c8ab130
BLAKE2b-256 c23bb330985e7ed069c736e8359c15c677ccb619f35a89ce488a8ec10e9c4e56

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page