evaluate • AI Agent SDK

evaluate: Return a :class:`LifecycleCommandDecision` for “command“.

evaluate

Method

</div>

This is a method of the LifecycleCommandGuardPolicy class in the protocols module.

Return a :class:LifecycleCommandDecision for `command`.

python

def evaluate(command: str) -> LifecycleCommandDecision

ParamField str

The resolved command / scheduled-job command string (may also carry appended script text — every segment is scanned).

ResponseField LifecycleCommandDecision

An allow decision when the command is benign, or a deny decision naming the offending fragment when it would stop / restart / kill this gateway.

praisonaiagents/gateway/protocols.py at line 7109