CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs
This tool addresses the need for unobtrusive data collection to support research on responsible AI and developer productivity, but it is incremental as it builds on existing telemetry and IDE plugin concepts.
The researchers tackled the problem of collecting detailed, real-time data on developer interactions with code generation tools without disrupting workflow by presenting CodeWatcher, a lightweight system that captures fine-grained events in VS Code, enabling continuous monitoring and post-hoc analysis of coding sessions.
Understanding how developers interact with code generation tools (CGTs) requires detailed, real-time data on programming behavior which is often difficult to collect without disrupting workflow. We present \textit{CodeWatcher}, a lightweight, unobtrusive client-server system designed to capture fine-grained interaction events from within the Visual Studio Code (VS Code) editor. \textit{CodeWatcher} logs semantically meaningful events such as insertions made by CGTs, deletions, copy-paste actions, and focus shifts, enabling continuous monitoring of developer activity without modifying user workflows. The system comprises a VS Code plugin, a Python-based RESTful API, and a MongoDB backend, all containerized for scalability and ease of deployment. By structuring and timestamping each event, \textit{CodeWatcher} enables post-hoc reconstruction of coding sessions and facilitates rich behavioral analyses, including how and when CGTs are used during development. This infrastructure is crucial for supporting research on responsible AI, developer productivity, and the human-centered evaluation of CGTs. Please find the demo, diagrams, and tool here: https://osf.io/j2kru/overview.