> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Multi Agent Hooks Config • AI Agent SDK
> MultiAgentHooksConfig: Configuration for multi-agent orchestration hooks/callbacks.
# MultiAgentHooksConfig
> Defined in the [**Feature Configs**](../modules/feature_configs) module.
AI Agent
Configuration for multi-agent orchestration hooks/callbacks.
Consolidates: completion\_checker, on\_task\_start, on\_task\_complete
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8B0000', 'primaryTextColor': '#fff', 'primaryBorderColor': '#710101', 'lineColor': '#189AB4', 'secondaryColor': '#189AB4', 'tertiaryColor': '#fff' }}}%%
graph LR
input["Input Data"] --> agent["Agent: MultiAgentHooksConfig"]
agent --> output["Output Result"]
style agent fill:#8B0000,color:#fff
style input fill:#8B0000,color:#fff
style output fill:#8B0000,color:#fff
```
## Properties
Called before each task starts. Signature: `(task, task_id)`. `task_id` is the integer assigned by AgentTeam to this task in the run.
Called after each task finishes. Signature: `(task, task_output)`. `task_output` is the `TaskOutput` produced by the agent for this task.
Custom function to decide whether the team's run has finished. Overrides `AgentTeam.default_completion_checker`.
* **to\_dict**: Convert to dictionary.
## Usage
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
AgentManager(
agents=[...],
hooks=MultiAgentHooksConfig(
on_task_start=my_start_callback,
on_task_complete=my_complete_callback,
completion_checker=my_checker,
)
)
```
## Source
`praisonaiagents/config/feature_configs.py` at line 781
***
## Related Documentation