A clean way to separate each agent’s workspace and runtime
A needs a clear way to manage each agent’s and runtime. The gives the agent a place to create files and do its work. The runtime gives the agent an environment where it can actually run commands.
In this design, the is first, and the runtime is started after that. This creates separate lifecycle states, including an agent that has never been set up and an agent that was set up before but later had its removed while its record and identifier remain.
Key points
- Each agent gets a separate and runtime.
- The is where the agent stores files and works.
- The runtime is where the agent actually runs commands.
- The must be before the runtime starts.
- An agent can keep its record and identifier even after its is removed.