Architecture of hkuds/deeptutor

Input enters through two front doors: the web frontend in web, which renders screens and sends typed requests to the server, and the CLI in deeptutor_cli/__main__.py, which turns typed commands into requests and prints rich text or JSON. Requests reach the API server started from deeptutor/api/main.py. The deeptutor package assembles the application: it reads runtime settings, picks a coordination backend, and builds one container that holds the turn services, the capability registry and per-session runtime bookkeeping. The model-driven workers in deeptutor/agents take a learner's request and its settings and handle features such as chat, research, question generation, visualization and math animation. These workers return streamed results and structured output, which become the answers, quizzes and other artifacts the learner sees.

• web: 1,455 files and 243,017 lines of code
• deeptutor: 1,125 files and 263,149 lines of code
• tests: 898 files and 167,327 lines of code
• packages: 29 files and 4,996 lines of code
• deeptutor_cli: 24 files and 5,628 lines of code
• scripts: 20 files and 2,501 lines of code
• root: 5 files and 670 lines of code
• docs-for-dev: 3 files and 93 lines of code

By file count: Python 2,069 files, TypeScript 1,468 files, JavaScript 23 files, Dockerfile 1 file, Shell 1 file.

Repowise documents deeptutor in 4,658 pages generated from the source, 86 of them written explanations of the repository and its modules. Module guides include:

• deeptutor/runtime/agentic: Agentic Runtime Providers
• deeptutor/agents: Agents Overview
• deeptutor/book: Book Authoring Pipeline