active-inactive-relay-pair
IN premise
Each imported agent gets exactly two infrastructure nodes: `agent:active` (premise, starts IN) and `agent:inactive` (derived via SL with `outlist=[active_id]`, starts OUT); every imported belief includes `inactive_id` in its outlist
Summary
When an agent is brought into the system, it gets a built-in on/off switch made of two nodes that work as a pair. The "active" node defaults to on, and the "inactive" node is its logical opposite, defaulting to off. Every belief that agent contributed is wired to depend on the inactive node being out, so if someone flips the agent to inactive, all of its beliefs automatically retract in one cascade — giving the system a clean way to silence an entire agent without deleting anything.
Dependents
These beliefs depend on this one:
- agent-isolation-through-namespace-and-relay — Agent beliefs are doubly isolated: namespace prefixing prevents ID collisions, while the active/inactive relay pair provides per-agent kill-switch semantics without cross-agent interference
Details
| Source | entries/2026/04/23/topic-multi-agent-federation.md |