Spring AI 2.0.0-M1 Release Notes

🎯 Highlights

Spring AI 2.0.0-M1 represents the first milestone of the 2.x series, built on Spring Boot 4.0 and Spring Framework 7.0. This major platform upgrade, contributed by Dmitry Bedrin with Paul Bakker from Netflix (#4774), brings modern Java capabilities and positions Spring AI for the next generation of AI application development.

This release includes 24 new features, 25 bug fixes, 7 documentation improvements, and 32 other improvements across 90 commits.

⏪ Breaking Changes

The main branch now requires Java 21 or higher for development and building from source. 8ca583d
The default temperature configuration has been removed from model implementations. Applications relying on default temperature values will need to explicitly configure temperature settings. ce1a7fc
The default chat model for OpenAI has been updated from the previous default to gpt-5-mini. Applications relying on the implicit default may experience different behavior. 8c093f1

⚠️ Upgrading Notes

If you're building Spring AI from source on the main branch, ensure you have Java 21 or higher installed. This does not affect users consuming Spring AI releases as a library. 8ca583d
With the removal of default temperature options, ensure your application explicitly sets temperature values in model configurations where required. ce1a7fc
If your application depends on the default OpenAI chat model, verify that gpt-5-mini meets your requirements or explicitly configure your preferred model in application properties 8c093f1

📢 Noteworthy

Spring Boot 4.0 and Spring Framework 7.0 upgrade - This release marks a major platform upgrade from Spring Boot 3.x to Spring Boot 4.0 GA and Spring Framework 7.0. Thanks to Dmitry Bedrin (@bedrin) with Paul Bakker from Netflix (@pbakker) for the comprehensive upgrade effort (#4774). This includes major version upgrades for Kotlin (2.2.21), Rest Assured (5.5.6), swagger-codegen (3.0.75), and Testcontainers (2.0.1). d5e92be, a2a5e1b
The default chat model for OpenAI integration has been updated to gpt-5-mini, reflecting the latest recommended model from OpenAI 8c093f1
Official OpenAI Java SDK integration - Added native integration with the official OpenAI Java SDK for improved compatibility and functionality 15df47d

⭐ New Features

Added Redis-based chat memory repository implementation with Spring Boot starter for persistent conversation management across sessions 95f7481
New auto-configuration starter enabling easy setup of Redis-based chat memory with minimal configuration 99b2976
Added text search capabilities, range query support, and HNSW index parameter tuning for improved vector search performance in Redis c160b9c
TokenTextSplitter now supports custom punctuation marks, allowing more flexible text segmentation for different languages and text formats 9773099
Azure Vector Store now supports custom field names, enabling integration with existing Azure AI Search indexes that use non-default field naming conventions instead of hardcoded content, embedding, and metadata fields 798ab17
New finalization hook in ToolCallAdvisor enables custom logic execution after tool call loops complete, enhancing function calling workflow control #5064
Added comprehensive Claude Skills integration including support for the Files API, enabling advanced file handling capabilities with Anthropic's Claude models. bd90625
Added support for ISNULL and ISNOTNULL filter expressions in vector store queries, enabling better null value handling in metadata filtering. 0b87c78
Added ThinkingLevel configuration option to control extended thinking capabilities in supported models, allowing fine-grained control over reasoning depth. 740a61c
Added safety ratings to response metadata for Vertex AI Gemini models, providing visibility into content safety assessments. 2710cab
Made ToolCallAdvisor extensible by introducing hook methods, allowing developers to customize tool calling behavior and implement custom logic around function execution. #5004
Added support for the latest Claude 4.5 models including Opus and Haiku variants with updated model enums and documentation 01ace16
Google GenAI integration now supports thought signatures when using Gemini 3 Pro for function calling, enabling more advanced reasoning capabilities 3cb0879
GemFire Vector Store now supports authentication via username and password credentials 839e6ed
Enhanced OpenSearch vector store to omit explicit IDs when manageDocumentIds=false, improving compatibility with AWS OpenSearch Serverless deployments. Includes additional unit and integration tests. d82eec3
Added native integration with the official OpenAI Java SDK for improved compatibility and functionality 15df47d
ChatClient now supports native structured output, enabling direct conversion of chat responses to typed objects 195c4fd
Added prompt_tokens_details tracking for ZhipuAI model and updated default chat options for tests 89a3b32
Exposed seed parameter in Vertex AI configuration for reproducible results 4f1ab6a
Added Spring Boot web and REST client dependencies explicitly to model starters for better compatibility #4949 via #4948
Introduced auto-configuration support for AWS Bedrock profiles and replaced deprecated functionality 552263d
McpClientAutoConfiguration now supports optional handlers registry, improving flexibility in MCP client configuration #4920 via #4917
ClientMcp handlers registries now support beans with unresolvable types, enhancing compatibility with various Spring configurations #4918 via #4917
New Spring Boot starter added for Azure Cosmos DB chat memory repository, enabling easier integration of chat conversation history with Cosmos DB. ef8f413

🪲 Bug Fixes

Updated outdated Milvus JSON fields documentation link in MilvusFilterExpressionConverter Javadoc #5028
Resolved test issues with ChatClient tools using generic argument types 9e857ec
Updated runtime hints for AWS Bedrock integration 0427650
Enhanced error handling for JSON parsing in the MethodToolCallback class to provide better error messages and handle malformed JSON in tool/function calling scenarios. #5032 via #3924
Corrected handling of punctuation marks in the TokenTextSplitter to ensure proper text splitting behavior. e065965
Resolved issue where the extraBody parameter was not being properly included in OpenAI API requests, ensuring all custom parameters are now correctly transmitted. 264fc3b
Corrected MariaDB schema validator to properly handle escaped spaces, eliminating false positive validation errors. 9acc2d7
Resolved native compilation problems when using GraalVM with Java 22, ensuring proper native image generation for Spring AI applications. a49e159
Addressed issue-4999 by removing the use of DEFAULT_TEMPERATURE to resolve configuration issues fe9e781
Resolved issue where OpenAI GPT models running on Amazon Bedrock were returning null responses. 050b9f1
Added missing OCIGenAiInferenceClientAutoConfiguration to Spring Boot autoconfiguration imports, ensuring proper auto-configuration for Oracle Cloud Infrastructure GenAI integration. 3e0040f
Added several missing auto-configuration classes to autoconfiguration import, improving Spring Boot integration. 258b6bc
Resolved issues in OpenSearchVectorStoreIT to ensure reliable integration testing. d4b6cf2
Corrected documentation typo in DefaultChatClientUtils. 7af2593
Corrected vector indexing algorithm acronym from HSNW to HNSW (Hierarchical Navigable Small World). 186808d
Improved retry logic for Oracle Vector Store integration test container startup to reduce flaky tests 8a6e39d
Resolved issues with ElasticSearch vector store integration tests 7f30987
Resolved issues with MongoDB Atlas vector store integration tests ad07a81
Resolved issues with RedisVectorStoreObservationIT and RedisVectorStoreIT integration tests a7b837a
Restored ResourceAccessException to the retry policy to ensure proper retry handling for resource access failures. f3eb842
Resolved issues in MongoDB chat memory auto-configuration integration tests. ce7381c
Fixed issues in Docker Compose integration tests to improve test stability. d7a6435
Resolved compatibility issues with MongoDB index creation across different Spring Data MongoDB versions. e87b2ba
Corrected issues in Typesense vector store integration tests. 106778d
Refactored retry logic to centralize exception handling, improving consistency and maintainability across all AI model implementations. #4905

📓 Documentation

Added comprehensive documentation for the new Redis-based chat memory repository implementation aa74331
Enhanced ChatClient documentation to include complete coverage of all available ChatMemoryRepository implementations 0463997
Added Maven Central badge for easier discovery of latest release versions bc50b96
New documentation covering the custom punctuation marks feature in TokenTextSplitter e59be78
Documentation added for configuring custom field names when working with Azure AI Search indexes 757ed9e
Updated documentation and workflow files following the removal of the Maven toolchains plugin. d890ede
Updated Redis vector store documentation to point to the correct search query documentation 5ce998e

🔨 Dependency Upgrades

Upgraded Google Generative AI SDK from previous version to 1.30.0 abd5082
Updated Model Context Protocol (MCP) support with latest JDK and annotation versions to improve MCP integration capabilities. 28891ab, e15d318
Cleaned up duplicate dependency entry for Azure Identity in the build configuration. 0eaf938
Updated io.swagger.core.v3:swagger-annotations from version 2.2.30 to 2.2.38. e16d75a
Upgraded to Spring Boot 4.0.0 GA release a2a5e1b
Updated MCP and MCP annotations to latest versions 0bb7e5c
Upgraded spring-javaformat-maven-plugin to version 0.0.47 920e6f4
Updated to use Testcontainers dependencies from Spring Boot BOM and latest OpenSearch Testcontainers version compatible with Java 17 fbd8b7f
Updated to Spring Boot 4.0.0-RC2, bringing in the latest features and improvements from the Spring Boot 4.x line. d5e92be

🔩 Build Updates

Fixed checkstyle execution in build process 738c033
Resolved checkstyle formatting issues across codebase c5a7042
Improved CI/CD efficiency by generalizing the PR check workflow and enabling build caching 5ef6305
Optimized build cache settings for improved build performance cd76cf9
Updated build configuration to require Java 21 or higher for the main development branch. 8ca583d
Removed Maven toolchains plugin from the build configuration with corresponding documentation updates. d890ede
Modified visibility of toolCallingManager field to protected to allow better extensibility for custom implementations. ea5477e
Updated copyright year and author information in SpringAiCoreRuntimeHintsTests to reflect current maintenance. 4969dbc
Integrated Maven Build Cache plugin to improve build performance 147f85a
Updated Maven compiler configuration to avoid forking processes during compilation bd7d4cd
Disabled ErrorProne standard checks in the build configuration to address build compatibility issues. #4976
Resolved multiple build system issues to improve build reliability and consistency. 3b14b4a
Updated fast-continuous integration workflow configuration for the 1.1.x branch dc4b6ad
Integrated ErrorProne static analysis tool with Nullaway for enhanced null safety checking during builds #4903
Added Maven toolchains support for improved build consistency across different development environments d26637b
Incremented version to 2.0.0-SNAPSHOT for next development cycle. 10bc0a7
Incremented version to 1.1.1-SNAPSHOT for next development cycle. 9970432

🔐 Security

Overrode protobuf-java version in milvus-store module to address CVE-2024-7254 security vulnerability. 24795dd

🙏 Contributors

Thanks to all the community contributors who made this release possible:

spring-projects/spring-ai v2.0.0-M1 Spring AI 2.0.0-M1 on GitHub