Annotation Interface ConditionalAgent

@Retention(RUNTIME) @Target(METHOD) public @interface ConditionalAgent
Marks a method as a definition of a conditional agent, generally used to route the agentic workflow toward one or more sub-agents according to the verification of their activation conditions. Each sub-agent has its own activation condition, a static method annotated with ActivationCondition that determines when it should be invoked.

Example: 


    public interface ExpertsAgent {

        @ConditionalAgent(outputKey = "response",
                          subAgents = { MedicalExpert.class, TechnicalExpert.class, LegalExpert.class } )
        String askExpert(@V("request") String request);

        @ActivationCondition(MedicalExpert.class)
        static boolean activateMedical(@V("category") RequestCategory category) {
            return category == RequestCategory.MEDICAL;
        }

        @ActivationCondition(TechnicalExpert.class)
        static boolean activateTechnical(@V("category") RequestCategory category) {
            return category == RequestCategory.TECHNICAL;
        }

        @ActivationCondition(LegalExpert.class)
        static boolean activateLegal(AgenticScope agenticScope) {
            return agenticScope.readState("category", RequestCategory.UNKNOWN) == RequestCategory.LEGAL;
        }
    }

  • Required Element Summary

    Required Elements
    Modifier and Type
    Required Element
    Description
    Class<?>[]
    subAgents
    Sub-agents that can be conditionally activated by this agent.

  • Optional Element Summary

    Optional Elements
    Modifier and Type
    Optional Element
    Description
    String
    description
    Description of the agent.
    String
    name
    Name of the agent.
    String
    outputKey
    Key of the output variable that will be used to store the result of the agent's invocation.
    Class<? extends TypedKey<?>>
    typedOutputKey
    Strongly typed key of the output variable that will be used to store the result of the agent's invocation.

  • Element Details

    • name

      String name
      Name of the agent. If not provided, method name will be used.
      Returns:
      name of the agent.
      Default:
      ""

    • description

      String description
      Description of the agent. It should be clear and descriptive to allow language model to understand the agent's purpose and its intended use.
      Returns:
      description of the agent.
      Default:
      ""

    • outputKey

      String outputKey
      Key of the output variable that will be used to store the result of the agent's invocation.
      Returns:
      name of the output variable.
      Default:
      ""

    • typedOutputKey

      Class<? extends TypedKey<?>> typedOutputKey
      Strongly typed key of the output variable that will be used to store the result of the agent's invocation. It enforces type safety when retrieving the output from the agent's state and can be used in alternative to the outputKey() attribute. Note that only one of those two attributes can be used at a time.
      Returns:
      class representing the typed output variable.
      Default:
      dev.langchain4j.agentic.Agent.NoTypedKey.class

    • subAgents

      Class<?>[] subAgents
      Sub-agents that can be conditionally activated by this agent.
      Returns:
      array of sub-agents.