Wanleung's Workshop

Independent research, structured debate and a moderator help specialist agents expose disagreements before the pipeline acts.

REST endpoints, streaming events and MCP tools turn the agent pipeline into a service that other applications can call.

A small deployment interface lets the same validation pipeline run in Docker, a virtual machine, or without a deployment backend.

Adding Prometheus metrics and expanding test coverage made pipeline failures visible and gave each reliability fix evidence behind it.

Original Article was published on Medium:...

原文原刊於Medium: https://medium.com/hong-kong-linux-user-group/how-to-type-chinese-cangjie-quick-on-pop-os-24-04-with-the-cosmic-desktop-178627ac335f好多朋友升級到Pop!_OS...

In short: A coding rule from a 1990s university computer science class — where the hard constraint was the size of a CRT screen — turned out to be one of the most practical pieces of advice I’ve ever...

https://www.youtube.com/watch?v=LKHf54jqwvABecause of AI, I could finally complete this song.The Lyrics I had written for some years but I couldn't complete the whole song because lack of melody...

Code: github.com/wanleung/ai-dev-teamIn short: The pipeline’s own AI agents opened a pull request with 7 critical bugs — code that couldn’t run at all. This post dissects exactly why it happened and...

As the system grew, every new pipeline type — bug fixes, documentation, features — needed its own Python script and GitHub Actions workflow. This post covers how all of them were unified into a single watcher process where a GitHub label determines which pipeline runs. Adding a new pipeline now means writing one YAML file.