agent-isolation-through-namespace-and-relay
IN derived (depth 1)
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
Summary
When beliefs are imported from an external agent, they get two layers of protection. First, every imported belief ID is prefixed with the agent's name, so two agents can use the same internal names without clashing. Second, each agent gets a paired on/off switch — flip it off and all of that agent's imported beliefs retract cleanly, without disturbing anything from other agents or the local system. This design also carefully avoids wiring the "on" switch into belief justifications directly, which would have created a backdoor that prevents individual beliefs from ever being retracted on their own.
Justifications
SL — Namespace handles identity isolation; relay handles truth-value isolation — both are required for full agent independence
Antecedents (all must be IN):
- import-agent-namespace-prefix — Every node imported from agent X gets the ID prefix `X:`, including infrastructure nodes `X:active` and `X:inactive`, ensuring zero collision with local or other-agent beliefs
- agent-cascades-are-isolated-by-namespace — Retracting one agent's active premise does not affect other agents' beliefs, because each agent's imported beliefs reference only their own `inactive` node in their outlist
- active-inactive-relay-pair — 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
- active-not-in-antecedents — The `active` premise is deliberately excluded from imported beliefs' antecedents; if it were an antecedent, it would provide a second always-valid justification path that defeats per-belief retraction semantics
Dependents
These beliefs depend on this one:
- agent-isolation-spans-identity-and-authorization — Agent beliefs are isolated through two independent containment mechanisms at different system levels: namespace prefixing with relay pairs provides identity-level isolation (preventing ID collisions and enabling per-agent lifecycle control via kill-switch), while transitive subset-gated access tags provide authorization-level isolation (controlling per-caller visibility with tag inheritance).
- agent-subsystem-is-self-contained — The agent subsystem provides complete lifecycle management: import handles mixed truth states and topological cycles, namespace/relay pairs provide isolation and kill-switches, and all defeat operations are reversible for agent reactivation.