Main model hounding · Shipping Skool

Main model hounding

Is any of you having trouble where a lot of times your main agent in openclaw will not let you know what they’re doing and you have to keep asking before you’ll get a response? This has been an ongoing thing where I feel like I have to hound the agent to see or complete a task or update me if it’s done. Right now I’m using the GLM 5.1 model on Ollama cloud. This would happen to be on the ChatGPT 5.4 codex model as well. I tried to have my agent resolved these things by trying different things, but I still don’t have a working system where things just get done quickly and I don’t have to feel like the mean boss.

5 comments