This is why I prefer to use the chatbots on a website, instead of Claude Code.
I've never used Claude Code or Cursor. All the code I got written this year was without them.
I did use Microsoft Copilot a bit when it came out, though. I prefer to see exactly what's being sent, and sorta control the KV cache. These days, these chatbots have great environments where they can install headless browsers, php, your entire thing, run end-to-end tests, and then give you a .patch or .zip file to merge over your code, or even push to github.
Incidents like this, and OpenCode changing the DX in v2, is why I'm going back to building my own. It's also fun and interesting
Im sorry, but how could this possibly be used as reason not to use an on-host harness? If you own the code, and control the supply chain, then this is not a problem- because you can read it. Weird comment.