Package com.aispect.agents.security

Class ContentModerationAgent

java.lang.Object

com.aispect.agent.core.AbstractUnitAgent<Object,Object>

com.aispect.agents.security.ContentModerationAgent

All Implemented Interfaces:

AiAgentFilter, AiExceptionProxy<Object,Object>, AiExecutionProxy<Object,Object>, AiPostExecutionProxy<Object,Object>, AiPreExecutionProxy<Object>, AiUnitAgentHandler<Object,Object>

public class ContentModerationAgent
extends AbstractUnitAgent<Object,Object>

Content moderation Agent。

Intercept the request before the actual method is executed, and use AI Conduct safety checks (eg: pornography, violence, hate speech). If a violation is detected, an exception will be thrown to block the execution flow.

Constructor Summary

Constructors

Constructor	Description
ContentModerationAgent()

Method Summary

Modifier and Type	Method	Description
void	preExecute(AiInvocationContext<Object> ctx)	Parameter review is performed before the target method is executed.

Methods inherited from class com.aispect.agent.core.AbstractUnitAgent

doFilter, execute, getAiOperations, onException, postExecute, shouldProcess

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ContentModerationAgent

public ContentModerationAgent()

Method Details

preExecute

public void preExecute(AiInvocationContext<Object> ctx)
                throws AiSpectException

Parameter review is performed before the target method is executed.

Specified by:

preExecute in interface AiPreExecutionProxy<Object>

Overrides:

preExecute in class AbstractUnitAgent<Object,Object>

Parameters:

ctx - AI Execution context, containing all parameters of the target method

Throws:

AiSpectException - Thrown when unsafe content is detected AiAgentExecutionException abnormal, or in AI Another error occurred during the call