Building AI Agents with Embabel, Spring AI and Amazon Bedrock AgentCore - Part 4 Upgrade sample application to Embabel 1.5

A developer detailed the migration of a sample AI agent application from Embabel 1.0 to Embabel 1.5.1, which supports Spring Boot 4.x and Spring AI 2.x. The upgrade required declaring the new version in pom.xml and adding a Jackson 3 mapper bean, with version 1.5.1 fixing a ClassCastException encountered with the Amazon Bedrock Converse API.

In parts 2 https://dev.to/aws-heroes/building-ai-agents-with-embabel-spring-ai-and-amazon-bedrock-agentcore-part-2-develop-agents-57nb and 3 https://dev.to/aws-heroes/building-ai-agents-with-embabel-spring-ai-and-amazon-bedrock-agentcore-part-3-develop-agents-as-2d94 , we developed our sample application https://github.com/Vadym79/amazon-bedrock-agentcore-spring-ai/tree/main/embabel-1.x-conference-app-agent-local and interacted with it via the shell and HTTP. We used Embabel version 1.0 there, which targets Spring Boot 3.x / Spring AI 1.x. Recently, the Embabel team released version 1.5 https://github.com/embabel/embabel-agent/releases/tag/v1.5.0 , which supports Spring Boot 4.x / Spring AI 2.x. In this article, we'll explain how to migrate our sample application to the Embabel 1.5.x version. You can find the final version of the application in my GitHub repository https://github.com/Vadym79/amazon-bedrock-agentcore-spring-ai/tree/main/embabel-1.5.x-conference-app-agent-local . The migration for my use case is really simple. First, in pom.xml https://github.com/Vadym79/amazon-bedrock-agentcore-spring-ai/blob/main/embabel-1.5.x-conference-app-agent-local/pom.xml we need to declare this Embabel version: <properties <java.version 25</java.version <embabel-agent.version 1.5.1</embabel-agent.version </properties Please note that we use version 1.5.1 here. With version 1.5.0, I ran into a specific problem https://github.com/embabel/embabel-agent/issues/1923 while using the Amazon Bedrock Converse API. This was due to the fact that BedrockOptionsConverter created generic ToolCallingChatOptions. Spring AI 2.0’s BedrockProxyChatModel expects BedrockChatOptions and casts the request options accordingly, causing: ClassCastException: DefaultToolCallingChatOptions cannot be cast to BedrockChatOptions . With version 1.5.1, the Embabel team fixed the problem. Next, as Spring Boot 4.x / Spring AI 2.x uses Jackson version 3 by default https://spring.io/blog/2025/10/07/introducing-jackson-3-support-in-spring , we need to declare a Jackson 3 mapper Spring bean. We do it in the Spring Boot main EmbabelConferenceApplication https://github.com/Vadym79/amazon-bedrock-agentcore-spring-ai/blob/main/embabel-1.5.x-conference-app-agent-local/src/main/java/dev/vkazulkin/EmbabelConferenceApplication.java application class of our sample application: @Bean public JsonMapper objectMapper { return new tools.jackson.databind.json.JsonMapper ; } That's it. Now you can compile, start, and interact with our sample application the same way we described in parts 2 https://dev.to/aws-heroes/building-ai-agents-with-embabel-spring-ai-and-amazon-bedrock-agentcore-part-2-develop-agents-57nb and 3 https://dev.to/aws-heroes/building-ai-agents-with-embabel-spring-ai-and-amazon-bedrock-agentcore-part-3-develop-agents-as-2d94 .