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

说明与用途

shadow-debugger 通过本地或云端 LLM 实现 Python 应用的非阻塞错误诊断，生成 Markdown 报告且不影响响应延迟。

问题

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.

结果

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.

工作流

• 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/

证据

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.

来源

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

来源

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

来源