astrbot-plugin-dev

You must follow standardized architecture by implementing the correct file structure, metadata requirements, and main.py boilerplate to ensure your chatbot plugin adheres to v4.26.5+ framework standards.

To prevent memory leaks and data loss during hot-reloads, you must enforce correct resource cleanup using the terminate method and manage data persistence through the get_data_dir functionality in your plugin lifecycle.

Registering LLM tools correctly requires using the provided main.py boilerplate and adhering to API references to ensure tools are integrated without triggering common framework exceptions.

Yes, these development guidelines provide the project scaffolding and architectural constraints needed to build and deploy production-ready chatbot plugins for platforms like QQ and Telegram.

You can validate your current plugin directory structure and main.py code by running the provided validation scripts to check your project against the team's baseline architectural constraints and security standards.

Common architectural pitfalls include incorrect metadata configuration, improper Star class implementation, and failing to manage resource cleanup, which are prevented by following team-validated architectural constraints.