I built shadow-debugger: non-blocking AI error diagnosis for Python & FastAPI (works offline with Ollama)

Описание и применение

shadow-debugger позволяет быстро и без блокировки получать отчёты об ошибках в Python‑приложениях, используя локальный или облачный LLM.

Задача

When a Python app or FastAPI endpoint raises an exception or HTTP 500, the normal response is delayed while error context is sent to an LLM for analysis.

Результат

shadow-debugger enables non-blocking AI-driven error diagnosis, producing detailed Markdown reports offline or via cloud LLMs while keeping the original request latency unchanged.

Рабочий процесс

• Install shadow-debugger via pip
• Initialize shadow-debugger with provider and model
• Add middleware or decorator to the web framework
• Trigger an error in the application
• shadow-debugger captures context and sends to LLM
• LLM generates a Markdown report
• Report is written to ./shadow_reports/

Доказательства

When an exception or HTTP 500 happens, shadow-debugger captures the stack frame from your code, strips secrets from local variables and request data, and sends the context to an LLM in a background worker thread.

Источник

Your app returns its normal response right away; a few seconds later you get a Markdown postmortem in ./shadow_reports/.

Источник

It works offline with Ollama (zero external dependencies) or with Gemini, OpenAI (including OpenAI-compatible endpoints like Groq, vLLM, LM Studio), and Anthropic.

Источник