genai-toolbox/docs/en/samples/pre_post_processing/js.md

title, type, weight, description

title	type	weight	description
(JS) Pre and post processing	docs	5	How to add pre and post processing to your JS toolbox applications.

Prerequisites

This tutorial assumes that you have set up a basic toolbox application as described in the local quickstart.

This guide demonstrates how to implement these patterns in your Toolbox applications.

Implementation

{{< tabpane persist=header >}} {{% tab header="ADK" text=true %}} The following example demonstrates how to use the beforeToolCallback and afterToolCallback hooks in the ADK LlmAgent to implement pre and post processing logic. Specifically, it shows how to intercept tool calls to enforce business policies (blocking invalid actions) and enrich tool outputs (adding loyalty points) before they return to the model.

{{< include "js/adk/agent.js" >}}

{{% /tab %}} {{% tab header="Langchain" text=true %}} The following example demonstrates how to use ToolboxClient with LangChain's middleware to implement pre and post processing for tool calls.

{{< include "js/langchain/agent.js" >}}

For more information, see the LangChain Middleware documentation. You can also add model-level (wrap_model) and agent-level (before_agent, after_agent) hooks to intercept messages at different stages of the execution loop. See the LangChain Middleware documentation for details on these additional hook types. {{% /tab %}} {{< /tabpane >}}