Hi Hacker News,<p>As a dev extensively using GPT-4 for coding, I've realized its effectiveness significantly increases with richer context (e.g., code samples, execution state - props to DevinAI for famously console.logging itself).<p>This inspired me to push the idea further and create CaptureFlow. This tool equips your coding LLM with a debugger-level view into your Python apps, via a simple one-line decorator.<p>Such detailed tracing improves LLM coding capabilities and opens new use cases, such as auto-bug fix and test case generation. CaptureFlow-py offers an extensible end-to-end pipeline for refactoring your code with production data samples and detailed implementation insights.<p>As a proof of concept, we've implemented an auto-exception fixing feature, which automatically submits fixes via a GitHub bot.<p>---<p>Support is limited to Only OpenAI API and GitHub API.
interesting, I wonder what are the odds of introducing new bugs like not closing connections etc. I can imagine many tests passing after such change but actual failure happening on production. Is it something embedded context can help to address?