mirror of
https://github.com/johndoe6345789/AutoMetabuilder.git
synced 2026-04-24 13:54:59 +00:00
johndoe6345789
5187347d21
- Implement core components: CLI argument parsing, environment loading, GitHub service creation, and logging configuration. - Add support for OpenAI client setup and model resolution. - Develop SDLC context loader from GitHub and repository files. - Implement workflow context and engine builders. - Introduce major workflow packages: `game_tick_loop` and `contextual_iterative_loop`. - Update localization files with new package descriptions and labels. - Streamline web navigation by loading items from a dedicated JSON file.
AutoMetabuilder
AutoMetabuilder is an AI-powered tool designed to integrate with the metabuilder SDLC workflow.
Features
- GitHub Integration: Automatically fetches context from GitHub Issues and Pull Requests.
- SDLC Automation: Can create branches and pull requests based on the AI's decisions.
- Customizable Prompts: Loads workflow instructions from a local YAML prompt.
Configuration
The following environment variables are required:
GITHUB_TOKEN: A GitHub Personal Access Token with repository permissions.GITHUB_REPOSITORY: The full name of the repository (e.g.,owner/repo).
Usage
Run the tool using poetry:
poetry run autometabuilder
Testing
To run the unit tests:
PYTHONPATH=src pytest tests/test_main.py tests/test_metadata.py tests/test_roadmap.py
To run the Web UI tests (Playwright):
# First install browsers if you haven't already
playwright install chromium
# Run the UI tests
PYTHONPATH=src pytest tests/ui