Challenges that I'm currently working on in the development of AI Agents

So here are 3 problems that I'm working to solve in the development of our agentic systems.

Any help would be truly appreciated.

1) How to prevent the agent from leaving the loop in between tool calls, saying it's "going to move on to the next step", or to ask the user for confirmation.

2) How to make the agent manage it's tokens autonomously and intelligently, by identifying and discarding messages or context that are no longer relevant.

(Important in particular for when there's this one gigantic piece of content among the messages that keeps getting sent back in each new API call, making the token count grow exponentially)

- One path that I'm exploring is to have the one task or step in a different agent, so the main agent calls the agent that executes this task, so the context stays separate.

3 - On that last note, to understand the balance between having 1 agent with a huge prompt and a lot of tasks/steps, or one "manager" agent that calls multiple small agents with small prompts and single tasks.