MultiAgentHooksConfig

Defined in the Feature Configs module.

AI Agent Configuration for multi-agent orchestration hooks/callbacks. Consolidates: completion_checker, on_task_start, on_task_complete

Properties

on_task_start

Optional[Callable[[Task, int], None]]

Called before each task starts. Signature: (task, task_id). task_id is the integer assigned by AgentTeam to this task in the run.

on_task_complete

Optional[Callable[[Task, TaskOutput], None]]

Called after each task finishes. Signature: (task, task_output). task_output is the TaskOutput produced by the agent for this task.

completion_checker

Optional[Callable]

Custom function to decide whether the team’s run has finished. Overrides AgentTeam.default_completion_checker.

Internal & Generic Methods

to_dict: Convert to dictionary.

Usage

AgentManager(
        agents=[...],
        hooks=MultiAgentHooksConfig(
            on_task_start=my_start_callback,
            on_task_complete=my_complete_callback,
            completion_checker=my_checker,
        )
    )

Source

View on GitHub

praisonaiagents/config/feature_configs.py at line 781

Agents Concept

Single Agent Guide

Multi-Agent Guide

Agent Configuration

Auto Agents

Multi Agent Execution Config • AI Agent SDK

Multi Agent Memory Config • AI Agent SDK

​MultiAgentHooksConfig

​Properties

​Usage

​Source