I have switched to using the PI agent to work on the game. I'm still using the Qwen3.6 model through Ollama. It seems to work a little better through Pi. I have still been trying to get it to work continuously. I tried a few extensions and finally ended up making my own that seems to do what I want.
With no extensions I was running into two problems keeping the agent working continuously. The first issue is that the agent would just stop every so often and I would have to restart it by just saying something like "Continue". I found an extension for the pi agent that would auto continue when this happens and that seemed to work fine.
That extension didn't solve the second problem that I was running into, however. Sometimes the agent would just get stuck either going through the same thoughts over and over, or just outputting something very simple, like a br tag, over and over again. To solve this I ended up making my own extension that solves both problems. I used pi to make the extension and then modified it slightly by hand.
The way my extension works is, anytime the agent stops it just sends the message "Continue". It also has a timeout that can be set to some number of seconds. I set it to 1800 sec. or 30 minutes. This means every 30 minutes the agent is stopped, and then the extension sends "Continue" and it starts working again.
This seems to keep the agent working well, and stops it often enough that it doesn't get lost thinking about something unimportant. It seems to be making progress on the game again. The game is here https://github.com/mattdyer/side-scroller. I have it writing unit tests and acceptance tests for all parts of the game. It has written a lot of code, but the game isn't playable yet.
No comments:
Post a Comment