7ba684a1da
Roster named the permissions page, the hive's topology file and the swarm's list of agents without saying which. The page and its links are renamed; the implementation docs and UI text follow separately.
1.6 KiB
Agent permissions
Agents are a flat set: no agent manages another by position. The
manage_root_agent permission is the one grant that reaches another agent.
The hive's list of agents
Which agents exist is the swarm's to decide:
which agents exist. Each hive also
keeps a small file of its own, topology.json, with the agents this hive has
state or config for. You never edit it: the hive rebuilds it from what it sees
locally, so a hand edit is overwritten, and one that doesn't parse stops the
rebuild until you fix it. It matters for one thing, covered next.
Who may reach whose state
An agent holding no permission sees its own directories and nothing else. An
agent holding manage_root_agent gets every other agent's state directory on
this hive mounted read-write at /agents/<name>/state, never config or
harness. It's the only grant that reaches another agent's state. Ruth, the
root agent, holds it (the swarm creates her from the ruth archetype, see
which agents exist). The mounts
follow the hive's list: an empty file means no mounts until the next rebuild.
The manager is a normal agent
ruth differs from other agents in her name and in that grant. Her
permissions, prompt and tools work as for every agent, and destroying her is as
final as for any other.
How the hive reads and rebuilds the file, the wire protocol and the prompt blocks:
roster.md. The operator/agent
trust boundary is a separate axis: boundary.md.