alt Hacker NewsTBH I wouldn't recommend using it for this. I'm a big believer in agent chat running outside of the VM, where you can get much better control over the chat loop. I would treat the VM as a tool the agent is using rather than the agent's environment. Like the agent is a human using a machine and watching it, rather than trying to watch it from inside the machine. Then there are great existing observability tools, my fav is langfuse.
But doesn’t this defeat the purpose?
I would actually imagine this would be useful for observably in the sense that you can fork and then kill the loop in the fork, hop into an interactive session to figure out what it’s doing, while the loop is still running in the original instance.