36 Pull requests opened by 14 people

• Issue 3924 Fix MethodToolCallback enum argument handling

  #3933 opened Jul 28, 2025

• Bump postgresql JDBC driver from 42.7.5 to 42.7.7

  #3934 opened Jul 29, 2025

• Fix typos in comments and improve documentation

  #3936 opened Jul 29, 2025

• Issue: 3930, Fix MessageChatMemoryAdvisor to handle message updates correctly

  #3940 opened Jul 29, 2025

• Tool filtering as ToolCallingChatOption

  #3941 opened Jul 29, 2025

• test: Add comprehensive test coverage for `MariaDBFilterExpressionConverter`

  #3943 opened Jul 29, 2025

• Issue 3890 Tool call results returned via ChatResponse lack identification metadata

  #3944 opened Jul 29, 2025

• Support custom HTTP headers for MCP SSE transport

  #3949 opened Jul 31, 2025

• test: Add additional test coverage for `OpenSearchAiSearchFilterExpressionConverter`

  #3950 opened Jul 31, 2025

• Don't log AWS SDK stack trace, updates documentation

  #3952 opened Jul 31, 2025

• Issue 3938 Improve MCP SSE URL configuration documentation and examples

  #3953 opened Jul 31, 2025

• test: Add comprehensive test coverage for `Neo4jVectorFilterExpressionConverter`

  #3957 opened Jul 31, 2025

• test: Enhance `OpenAiChatOptions` test coverage

  #3959 opened Jul 31, 2025

• Improved documentation for the `call()` method in `chatclient.adoc`

  #3963 opened Aug 1, 2025

• test: Enhance `MistralAiChatOptions` test coverage with comprehensive edge cases

  #3968 opened Aug 1, 2025

• Update Ollama API to latest version

  #3969 opened Aug 1, 2025

• Issue 3884 Improve tool parameter conversion error messages

  #3970 opened Aug 1, 2025

• Enhance AnthropicChatOptions test coverage

  #3973 opened Aug 2, 2025

• Keep the same pass check behavior for Evaluator

  #3975 opened Aug 2, 2025

• Use `Optional` to check null.

  #3976 opened Aug 2, 2025

• Polish empty check of UsageCalculator.

  #3977 opened Aug 2, 2025

• Lambda can be replaced with method reference

  #3978 opened Aug 2, 2025

• Replace instanceof check and cast with `instanceof Foo foo`

  #3979 opened Aug 2, 2025

• Use `metadata` instead of `properties` on UserMessage.

  #3980 opened Aug 2, 2025

• changes

  #3984 opened Aug 3, 2025

• test: Enhance test cases for `VectorStoreChatMemoryAdvisor` builder

  #3985 opened Aug 3, 2025

• test: add comprehensive edge case tests for `QdrantVectorStore.Builder`

  #3986 opened Aug 3, 2025

• test: Add tests for `MistralAiRuntimeHints`

  #3987 opened Aug 3, 2025

• feat: Add `metadata` support to `PromptUserSpec` and `PromptSystemSpec` in ChatClient

  #3989 opened Aug 4, 2025

• Upgrade io.modelcontextprotocol 0.11.0-SNAPSHOT -> 0.11.0

  #3990 opened Aug 4, 2025

• test: Enhanced test coverage for `AnthropicRuntimeHintsTests`

  #3992 opened Aug 4, 2025

• Fix bug in example code in documentation

  #3993 opened Aug 4, 2025

• Autoconfigure MCP Client with and async HTTP request customizer

  #3994 opened Aug 4, 2025

• test: Enhanced test coverage for `AzureOpenAiRuntimeHintsTests`

  #3995 opened Aug 4, 2025

• deps: Update Protobuf Java 3.25.2 to 3.25.8 to fix CVE-2024-7254

  #3996 opened Aug 4, 2025

• test: Enhanced test coverage for `OpenAiRuntimeHintsTests`

  #3997 opened Aug 4, 2025

3 Issues closed by 3 people

• 使用deepseek-r1 不支持流式响应吗

  #3964 closed Aug 4, 2025

• ChatClient structured output - No access to metadata/token usage with .entity()

  #3895 closed Jul 29, 2025

• An error occurred when using the TransformersEmbeddingModel: requestOptions cannot be null.

  #3937 closed Jul 29, 2025

18 Issues opened by 17 people

• DeepSeekChatModel: role field sent as uppercase "USER", causes 422 error

  #3988 opened Aug 4, 2025

• MCP server Error state [CLOSE_CONNECTION_NOW] reported while processing request (SSE+HTTP)

  #3983 opened Aug 3, 2025

• I Hope @Tool Support DescriptionFactory Config，To Solution Dynamic description Scene

  #3982 opened Aug 3, 2025

• spring-ai-core

  #3974 opened Aug 2, 2025

• MCP Server using STDIO - Attempting to user JSON RPC from Windows command line with partial success

  #3972 opened Aug 1, 2025

• spring-ai-autoconfigure-mcp-server什么时候支持WebFluxStreamableServer

  #3971 opened Aug 1, 2025

• 在响应的时候如何获取到记忆中的消息id

  #3967 opened Aug 1, 2025

• AWS AgentCore Module

  #3955 opened Jul 31, 2025

• How can I get the thinking content using a thinking model?

  #3954 opened Jul 31, 2025

• Exception Stracktrace Logged if `AWS_REGION` Not Set

  #3951 opened Jul 31, 2025

• Support custom HTTP headers for MCP SSE transport

  #3948 opened Jul 31, 2025

• MCP (using SSE) Connection failed when API scaled up to 2 or more.

  #3947 opened Jul 31, 2025

• Observability not effect in my code

  #3946 opened Jul 30, 2025

• The cost of reading and writing data is a bit high for the ChatMemoryRepository API

  #3945 opened Jul 29, 2025

• Update `chatclient.adoc` for `call()` return values

  #3942 opened Jul 29, 2025

• Auto-configuration dependency issues and ignoring vector databases can cause auto-configuration to not take effect

  #3939 opened Jul 29, 2025

• How can I split a usable MCP URL into the ​​baseUri​​ and ​​sseEndpoint​​ required by Spring AI's ​​HttpClientSseClientTransport​​?

  #3938 opened Jul 29, 2025

• How does the server receive identity authentication information?

  #3935 opened Jul 29, 2025

44 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Update BeanOutputConverter.java

  #3927 commented on Jul 29, 2025 • 2 new comments

• ChatModel streaming chat response data is too large.

  #3816 commented on Aug 4, 2025 • 0 new comments

• Spring AI MCP Streamable HTTP

  #3145 commented on Aug 4, 2025 • 0 new comments

• After migrating from milestones to stable, Observability stopped exposing input/output (null)

  #3401 commented on Aug 4, 2025 • 0 new comments

• feat(redis): Add Redis-based semantic caching and chat memory implementations

  #2295 commented on Aug 3, 2025 • 0 new comments

• feat(anthropic): add support for prompt caching

  #2669 commented on Jul 29, 2025 • 0 new comments

• Create MongoDB chat memory implementation

  #2679 commented on Jul 29, 2025 • 0 new comments

• fix(redis): Implement ChatMemoryRepository interface and fix test connectivity

  #2991 commented on Aug 3, 2025 • 0 new comments

• Added support for the "think" for Ollama

  #3386 commented on Jul 29, 2025 • 0 new comments

• McpSyncServer: set immediate execution when in a servlet context

  #3794 commented on Aug 4, 2025 • 0 new comments

• feat(zhipuai): Support glm-4.1v-thinking-flash model

  #3796 commented on Jul 30, 2025 • 0 new comments

• fix: GH-3690, enhance RedisVectorStore with RedisVectorStoreBuilderCustomizer

  #3809 commented on Aug 1, 2025 • 0 new comments

• feat: MCP tools support ToolContext

  #3831 commented on Jul 30, 2025 • 0 new comments

• Add More AWS Timeout Options

  #3836 commented on Jul 31, 2025 • 0 new comments

• GH-3403: Add caching for JSON schema generation in function calling

  #3862 commented on Aug 2, 2025 • 0 new comments

• Add `KotlinModule` support for schema generation in `BeanOutputConverter`

  #3900 commented on Jul 31, 2025 • 0 new comments

• Add MCP Client tool predicate for filtering the MCP tools

  #3901 commented on Jul 29, 2025 • 0 new comments

• test: improve coverage `PgVectorEmbeddingDimensionsTests`

  #3907 commented on Aug 4, 2025 • 0 new comments

• Fixes #3824, 3849 - New Google Gen AI Embedding Module, Starters for GenAI and GenAI EMbedding Module and support for ThinkingBudget

  #3914 commented on Jul 30, 2025 • 0 new comments

• test: Add comprehensive test coverage for `PgVectorFilterExpressionConverter`

  #3916 commented on Aug 4, 2025 • 0 new comments

• test: Add comprehensive test coverage for `MongoDBAtlasFilterExpressionConverter`

  #3919 commented on Aug 4, 2025 • 0 new comments

• fix: add strict option to ChatCompletionsJsonSchemaResponseFormat (#3…

  #3931 commented on Jul 29, 2025 • 0 new comments

• Possible issue using Qwen3 models

  #2957 commented on Jul 29, 2025 • 0 new comments

• Allow defining multiple MCP servers in a single application, with parametrized paths

  #2912 commented on Jul 29, 2025 • 0 new comments

• Vector store support for S3-Vectors

  #3834 commented on Jul 29, 2025 • 0 new comments

• MethodToolCallback does not handle invalid arg gracefully

  #3924 commented on Jul 29, 2025 • 0 new comments

• MessageChatMemoryAdvisor does not handle user message modification correctly

  #3930 commented on Jul 29, 2025 • 0 new comments

• Tool call results returned via ChatResponse lack identification metadata

  #3890 commented on Jul 29, 2025 • 0 new comments

• Streaming with tools not working with Anthropic ChatClient

  #3767 commented on Jul 30, 2025 • 0 new comments

• SSE Server drops client connection at 5 min.

  #3879 commented on Jul 31, 2025 • 0 new comments

• We need the Spring AI framework to support java8 我们需要spring ai框架支持java8

  #3527 commented on Jul 31, 2025 • 0 new comments

• Vertex AI Streaming not working

  #3313 commented on Jul 31, 2025 • 0 new comments

• argument "content" is null

  #3864 commented on Aug 1, 2025 • 0 new comments

• MCPServer Redeployment causes this behavior "Error sending message: 404" in MCPClient

  #2785 commented on Aug 1, 2025 • 0 new comments

• Split OllamaOptions to Chat and Embedding specific Options

  #3926 commented on Aug 1, 2025 • 0 new comments

• When the Tool parameter is an empty string, a type conversion error occurs, reporting java.lang.NumberFormatException

  #3884 commented on Aug 1, 2025 • 0 new comments

• Add audio-related multimodal integration tests for the large model with the newly added audio input function.

  #3904 commented on Aug 2, 2025 • 0 new comments

• Use builder pattern instead of deprecated constructors in class McpToolUtils

  #3807 commented on Aug 2, 2025 • 0 new comments

• EsVectorStore Search Error

  #2322 commented on Aug 3, 2025 • 0 new comments

• MCP server: Authentication lost in tool execution

  #2506 commented on Aug 3, 2025 • 0 new comments

• Feature Request: Support for OpenAI Batch API

  #3905 commented on Aug 3, 2025 • 0 new comments

• Auto-Configuration for Multiple Beans of the Same Type

  #3518 commented on Aug 3, 2025 • 0 new comments

• Add LiteLLM support

  #2734 commented on Aug 3, 2025 • 0 new comments

• How can I capture or listen to the event when a tool is actually invoked? I would like to wrap some custom tags or markers before and after the tool execution.

  #3911 commented on Aug 4, 2025 • 0 new comments