Sometimes I start several coding agents at the same time, each working on a different task. I just let them go and don’t watch them closely.
The problem is that I may change my mind later but forget that one of the agents is still working toward the old goal. A couple of hours later, it submit a patch with all tests passing and reports that the job is done. But when I check the result, I find that it has finished implementing a plan I had already abandoned.
Has anyone else who uses multiple coding agents run into this? How do you handle agents that keep working after your plan changes? Do you cancel them manually, use a shared task list to track the current work, or simply work out during final review?
How do you distinguish between “an agent run has finished successfully” and “the actual work is done”?
Comments URL: [https://news.ycombinator.com/item?id=49409147](https://news.ycombinator.com/item?id=49409147)
Points: 1