Class DebatePlanner

java.lang.Object
dev.langchain4j.agentic.patterns.debate.DebatePlanner
All Implemented Interfaces:
Planner
public class DebatePlanner extends Object implements Planner
A debate planner that orchestrates iterative adversarial rounds among debater agents.

Debaters generate independent positions in parallel, then enter critique rounds where they see each other's reasoning (via a "debateContext" scope key) and can revise their positions. Rounds continue until the ConvergenceStrategy reports convergence or maxRounds is reached, at which point the judge agent (the last registered subagent) renders a final verdict.

  • Field Details

  • Constructor Details

    • DebatePlanner

      public DebatePlanner()

    • DebatePlanner

      public DebatePlanner(int maxRounds)

    • DebatePlanner

      public DebatePlanner(ConvergenceStrategy convergenceStrategy)

    • DebatePlanner

      public DebatePlanner(int maxRounds, ConvergenceStrategy convergenceStrategy)

  • Method Details

    • init

      public void init(InitPlanningContext initPlanningContext)
      Specified by:
      init in interface Planner

    • firstAction

      public Action firstAction(PlanningContext planningContext)
      Description copied from interface: Planner
      Returns the first action to execute when the planner starts (or resumes). Defaults to delegating to Planner.nextAction(PlanningContext).
      Specified by:
      firstAction in interface Planner
      Parameters:
      planningContext - the current planning context
      Returns:
      the first action to execute

    • nextAction

      public Action nextAction(PlanningContext planningContext)
      Description copied from interface: Planner
      Determines the next action to execute based on the result of the previous agent invocation.
      Specified by:
      nextAction in interface Planner
      Parameters:
      planningContext - the current planning context, including the previous agent's result
      Returns:
      the next action to execute

    • executionState

      public Map<String,Object> executionState()
      Description copied from interface: Planner
      Returns the planner's current execution state as a map of serializable values. This state is persisted to the AgenticScope after each agent invocation, enabling the planner to resume from the correct position after a crash.

      The returned state must be such that, when passed to Planner.restoreExecutionState(Map) and Planner.firstAction(PlanningContext) is called, the planner produces the correct resume action.

      Stateless planners (e.g., parallel, conditional) can use the default empty implementation.

      Specified by:
      executionState in interface Planner
      Returns:
      a map of state entries to persist, or an empty map if no state needs saving

    • restoreExecutionState

      public void restoreExecutionState(Map<String,Object> state)
      Description copied from interface: Planner
      Restores the planner's execution state from a previously saved map. Called by the execution loop before Planner.firstAction(PlanningContext) when recovering from a persisted scope.
      Specified by:
      restoreExecutionState in interface Planner
      Parameters:
      state - the previously saved execution state

    • topology

      public AgenticSystemTopology topology()
      Description copied from interface: Planner
      Returns the topology of the agentic system managed by this planner.
      Specified by:
      topology in interface Planner
      Returns:
      the topology (defaults to AgenticSystemTopology.SEQUENCE)