SendPolicyProtocol
Defined in the protocols module.AI Agent Protocol for authorising agent-initiated proactive sends. Implementations decide whether an agent may deliver to a model-chosen
target. The hook is evaluated inside the send_message path before
the messenger dispatches, so a denied send returns a clean, model-readable
:class:DeliveryResult (ok=False) rather than delivering.
A concrete, config-driven implementation (:class:SendPolicy) is provided
for the common allow/deny case; richer back-ends may live in plugins.
Methods
evaluate()
Return a :class:
SendDecision for the requested target.Source
View on GitHub
praisonaiagents/gateway/protocols.py at line 2814