Reflection + history management
Morriz opened this issue · comments
Hi, tnx first of all for doing what I was hoping somebody would do with a similar vision of building a meta agent framework.
How about adding some configurable reflection cycles for each agent and history management allowing to intervene anywhere to finetune steps taken and letting it continue from there?
Sorry, I was under the impression that this platform would also be able to spin up the output...I was referring to the runtime stage context