A minimal, production-ready client for the Hugging Face Inference API with support for code generation models, plus a reusable tools layer for Python code analysis. ├── [LLM CLIENT LAYER] ├── ...
{%- set default_system_message = '# HOW YOU SHOULD THINK AND ANSWER\n\nFirst draft your thinking process (inner monologue) until you arrive at a response. Format your response using Markdown, and use ...