Spring AI 1.1.0-M4 Release Notes

🎯 Highlights

This release includes 27 new features, 35 bug fixes, 15 documentation improvements, 41 other improvements.

⚠️ Upgrading Notes

Migrate from the deprecated public constructor to the builder pattern when creating QuestionAnswerAdvisor instances adf4efe

📢 Noteworthy

Two commits related to MCP ObjectMapper factory and JSON schema upgrade were reverted to maintain stability. 132d50b
Updated OpenAI moderation integration from deprecated text-moderation-latest to the new omni-moderation-latest model, including integration test updates #4722
Updated Anthropic integration tests to remove usage of deprecated model versions 9e78796
The public constructor of QuestionAnswerAdvisor is now deprecated in favor of using the builder pattern for improved API design adf4efe

⭐ New Features

Advisors now support configurable observations, providing better control over observability behavior in AI workflows. 3cf3db1
Chat client now logs completion data and makes response text available in the Observation Context for improved monitoring and debugging. 13de219
Added support for Oracle JDBC in ChatMemoryRepository, enabling Oracle database backends for conversation memory storage 30af4e8
Added support for recursive advisor execution, enabling advisors to call other advisors in a chain. Includes two new built-in advisors to facilitate advanced use cases. 323c590
Introduced H2ChatMemoryRepositoryDialect to enable H2 database support for JDBC-based chat memory storage. 0b0024e
Added Oracle and SQLite database dialect support for JDBC chat memory, expanding database compatibility options. 673f483
Expanded OpenAI integration to support more transcription and text-to-speech (TTS) models, providing greater flexibility for audio processing. bdb7ea5
Enhanced TextSplitter functionality to preserve document properties and track metadata through text splitting operations, improving RAG pipeline capabilities. b452e89
Added support for Anthropic's Citations API, enabling retrieval of source citations in model responses e91eda9
Added support for Mistral AI's codestral embedding model for code-focused embedding generation ea48e17
Added usage field to ChatCompletionChunk for ZhipuAI to track token consumption during streaming operations d619727
Added additional timeout configuration options for AWS Bedrock to provide more granular control over request timeouts 34fc691
Added User-Agent header with 'spring-ai' value to OpenAI API client for better request identification and tracking 62fc70f
Enables prompt caching functionality for AWS Bedrock Converse API to improve performance and reduce costs by caching frequently used prompts. 58cf35e
Adds approximate k-nearest neighbor search capabilities to the OpenSearch vector store integration for improved query performance on large datasets. 5df83cb
Introduces new testing utilities to simplify Spring AI test configuration and improve developer experience when writing tests. 8b9f730
Introduced a unified request context API for Model Context Protocol (MCP) integration with enhanced documentation 3e6084c
Added Builder class to FactCheckingEvaluator for more convenient and flexible configuration #4652
Added tool choice capability for Anthropic chat model allowing better control over function calling behavior #4637
Applications can now provide custom RouterFunction implementations for enhanced routing control b99f26d
Enhanced MimeTypeDetector to handle URLs with query parameters and added comprehensive edge case validation tests 3f79373
Added STErrorListener bridge to SLF4J for improved error logging and diagnostics 940bcf3
Enhanced filter expression parsing to support long integer values, expanding query capabilities in vector store operations 107ab68
Introduces builder pattern support for ToolResponseMessage, improving API usability and message construction 2ded9cd
Added builder pattern support for ZhiPuAiAssistantMessage class with corresponding unit tests for improved API usability 01082b8
Added builder pattern support for DeepSeekAssistantMessage class with corresponding unit tests for improved API usability 7d0aff0
Added support for OpenAI's File API, enabling file uploads and management capabilities for OpenAI models 087393b

🪲 Bug Fixes

Resolved integration test failures in the Elasticsearch module. a572009
Corrected broken documentation link in Google GenAI integration guide bb91c5f
Resolved issues with streaming responses in Azure OpenAI chat model integration 50db344
Corrected message ordering issues affecting MySQL and MariaDB databases in JDBC-based chat memory storage d2492a6
Fixed issue where MCP tool callback providers were incorrectly injected into the tool callback resolver febf86c
Updated and improved the FactCheckingEvaluator for better accuracy and reliability in fact-checking operations. e81cd08
Corrects the SYSTEM_ONLY cache strategy implementation to properly handle caching behavior without explicit configuration requirements. 38ea4ff
Resolves multiple streaming issues including correct finish reason handling when stop reason is not tool_use, proper finish reason population for non-tool_use cases, and ensures multiple tool calls are correctly output in ChatResponse. a897177
Updates the CONVERSATION_HISTORY cache strategy to follow Anthropic's recommended incremental caching pattern for optimal performance. 8327c0f
Fixed auto-configuration to properly scan for @McpToolListChanged and related MCP annotations 0fdb911
Fixed exception handling in DeepSeekStreamFunctionCallingHelper when toolCalls() returns an empty list instead of null, correcting a flawed ternary expression 68d176f via #4586
Fixed handling of candidates containing both text and tool calls in VertexAiGeminiChatModel 8e8654e via #4596
Removed @ImportAutoConfiguration from AzureOpenAiChatAutoConfiguration to fix configuration issues d9c9d30 via #4634
Fixed PDF document grouping to properly respect the pagesPerDocument configuration setting aeb9f8a
Corrected the keep_alive parameter format for Ollama embedding requests f32b122
Resolved issue where OllamaApi bean was not properly registered in the Spring context 1b69fd5
Fixed potential NullPointerException in the getDefaultUsage method of AnthropicChatModel a7582f0
Cleaned up redundant annotation configuration in auto-configuration classes 369db3c
Corrects auto-configuration issues in the ElevenLabs model provider integration 133eb40
Resolves auto-configuration problems in the ZhiPuAI model provider integration 5bf0e37
Addresses auto-configuration issues in AWS Bedrock Converse proxy integration f8c7644
Corrects visibility scope issues with the ConnectionDetails class to prevent exposure outside its defined scope b4392c5
Resolves issues in the StreamableMcpAnnotationsManualIT integration test bd51e34
Corrected Javadoc documentation for the CosmosDBChatMemory class #4572
Resolved auto-configuration issues for the DeepSeek model provider f7d8f0f
Resolved auto-configuration issues for the MiniMax model provider b26b2c6
Resolved auto-configuration issues for the Oracle Cloud Infrastructure (OCI) GenAI model provider edb036d
Resolved auto-configuration issues for MistralAI model integration ad69fd7
Corrected integration test failures for Google GenAI model provider 26bab76
Resolved auto-configuration issues for Google GenAI model integration 86f013d
Resolved auto-configuration issues for OpenAI model integration 0ae56f7
Resolved auto-configuration issues for Anthropic model integration 110605f
Fixed autoconfiguration ordering to ensure MCP Tools are configured before ChatClient, preventing initialization issues #4553
Resolved multiple VertexAI autoconfiguration issues including import corrections and configuration setup problems 9e0e3cd, d9f5f09
Fixed required field handling for proper validation and configuration #4547

📓 Documentation

Enhanced documentation and examples for configuring MCP Server-Sent Events (SSE) URLs. 357190d
Removed misleading documentation about activation order for MCP clients #4665
Corrected documentation that had reversed descriptions for retrieval query and document concepts 0ee96f1
Updated documentation to clarify that PgVector schema initialization requires explicit opt-in configuration. 6854e3e
Documented that Spring Boot Actuator is required for observability features to function properly abb0b89
Replaced README.md with package-info.java in converter package for better JavaDoc integration cb4af07
Corrects typographical errors in project documentation. 8620c20
Converted documentation format to AsciiDoc for improved documentation tooling d7977aa
Added documentation for the toolChoice property in Anthropic model configuration ffe11b4
Corrected typo in documentation 935ef80
Removed obsolete semicolon from documentation b2dd1c9
Fixed incorrect configuration property key in ZhipuAI documentation 1780e88
Added comprehensive documentation for the OpenAI File API integration 3b98b94
Corrected the @SInCE version annotation in Mistral AI OCR documentation 0e1885f
Updated documentation to reflect deprecation of legacy function-related configuration options in chat models #4541

🔨 Dependency Upgrades

Upgraded Model Context Protocol SDK to version 0.15.0 and annotations library to version 0.6.0. a2d00d1
Updated JSON schema dependency versions for better consistency across modules. 53064d9
Updated jsonschema dependency to version 4.38.0 and qualified ObjectMapper in MCP module a9b0763
Updated Spring Boot dependency to version 3.5.7, bringing the latest bug fixes and improvements from the Spring Boot framework. db9ac2f
Updated Cassandra integration to leverage native QueryBuilder vector support instead of custom implementation 3fc1ed6
Updated MCP (Model Context Protocol) dependency to version 0.15.0-SN #4564
Updated mcp-annotations dependency to latest snapshot version #4555

⚡ Performance

Optimized Jackson annotation detection to return early, improving overall performance 6a34458
Added factory for standardized ObjectMapper configuration in MCP server implementations, improving consistency and performance 4273328
Optimized vector operations by eliminating unnecessary validation checks on each operation 177cd69
Improves logging performance by eliminating unnecessary string concatenation in log statements 7e563d0

🔩 Build Updates

Removed concurrency configuration from GitHub CI workflow to improve build efficiency. 0f404ff
Adjusted the frequency of scheduled CI runs for optimized resource usage. c319792
Refactored and cleaned up the parent pom.xml file f616cd9
Expanded test coverage for JsonSchemaConverter to ensure proper property handling 6593762
Added test to verify that ToolCallbackResolver doesn't inadvertently use MCP ToolCallbackProviders 68e5324
Cleaned up codebase by removing unused internal specifications, reducing maintenance burden. e0a7d74
Added comprehensive tests to ensure OpenAI API builder maintains proper immutability and configuration isolation. 062e494
Stopped using arrays as annotation attribute values where feasible in auto-configurations for cleaner code 77473d6
Refactored User-Agent header implementation in OpenAiApi with constants and additional test coverage f6ff20a
Added test coverage for OpenAiModerationProperties to improve code quality cc9c2cd
Expands test coverage for AnnotatedMethodDiscovery class to ensure reliability and maintainability. 967d00c
Improves test coverage for PostgresML embedding options to ensure proper validation and configuration handling. 838801f
Modernizes test assertions by using AssertJ's assertThatException for improved test readability and consistency. 4e0457e
Added comprehensive null parameter validation test coverage c03a5ca
Renamed classes for improved naming consistency across the codebase 2a916db
Enhanced test code quality and addressed Sonar suggestions for better maintainability fa68d1e
Modernizes codebase by adopting contemporary Java language features and idioms d3c9de1
Enhances builder class design by marking builder classes as final, preventing unintended inheritance 0403a2a
Expands test coverage with comprehensive validation tests for the MultiQueryExpander component 26c803e
Reverted Kotlin version upgrade from 2.2.20 back to 1.9.25 after Java 25 testing 37b1fd0
Added additional test coverage for edge cases in the PDF TextLine class e90f1a0
Improved and refined integration tests for the MistralAI model provider 8883689
Added extensive test suite for DefaultToolCallingManager to improve code quality and reliability d148ca2
Refactored MCP tests to leverage autoconfiguration and added ChatClient integration examples 5ab9365

🙏 Contributors

Thanks to all contributors who made this release possible:

spring-projects/spring-ai v1.1.0-M4 Spring AI 1.1.0-M4 on GitHub

Spring AI 1.1.0-M4 Release Notes

🎯 Highlights

⚠️ Upgrading Notes

📢 Noteworthy

⭐ New Features

🪲 Bug Fixes

📓 Documentation

🔨 Dependency Upgrades

⚡ Performance

🔩 Build Updates

🙏 Contributors

spring-projects/spring-ai v1.1.0-M4
Spring AI 1.1.0-M4

on GitHub