2 points | by kkm 8 hours ago
1 comments
I really like this article, agent harness knows its own state: which tool call is running, whether a sub-agent is pending, when it is finished. The API throws that away because each request looks stateless. Interesting idea.
I really like this article, agent harness knows its own state: which tool call is running, whether a sub-agent is pending, when it is finished. The API throws that away because each request looks stateless. Interesting idea.