Add Spring AI integration documentation for Java SDK#4454
Open
donald-pinckney wants to merge 11 commits intomainfrom
Open
Add Spring AI integration documentation for Java SDK#4454donald-pinckney wants to merge 11 commits intomainfrom
donald-pinckney wants to merge 11 commits intomainfrom
Conversation
Documents the new temporal-spring-ai module that makes Spring AI model calls, tools, vector stores, embeddings, and MCP calls durable Temporal primitives.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
📖 Docs PR preview links
|
donald-pinckney
commented
Apr 20, 2026
donald-pinckney
commented
Apr 20, 2026
Bump the documented Java SDK minimum to 1.35.0 (the version where the spring-ai work landed) and add three sections that the original draft predated: - Activity options and retry behavior (#2853, #2855): defaults, the non-retryable-AI-error classification, ad-hoc forDefault(ActivityOptions), the ChatModelActivityOptions bean for configuration-driven per-model overrides, and the "default" catch-all key for compositional setups. - Provider-specific chat options (#2857): AnthropicChatOptions extended- thinking example demonstrating that subclass-specific fields survive the Activity boundary. - Media in messages (#2860): 1 MiB inline-bytes cap, URI-based alternative, io.temporal.springai.maxMediaBytes override. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Reframe the opener around Spring AI as an agent framework and the integration as making agents durable, instead of describing it mechanically as "wraps calls as Activities." Avoids overstating that "every tool" goes through an Activity — the integration explicitly supports Workflow-side tools (@SideEffectTool, plain @tool) alongside Activity and Nexus stubs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Switches six extended code samples on the spring-ai integration page from inline copies to snipsync references against samples-java markers added in temporalio/samples-java#fbae80a. Snippets pulled: - samples-java-spring-ai-chat-workflow-init - samples-java-spring-ai-activity-tool - samples-java-spring-ai-side-effect-tool - samples-java-spring-ai-plain-tool - samples-java-spring-ai-per-model-options - samples-java-spring-ai-provider-options Short single-purpose snippets (Maven dep, one-liner forDefault override, Media URI line, plugin triplet) stay inline. The daily snipsync workflow will fill the placeholders once the samples-java branch lands on master. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Contributor
Author
|
Now uses snipsync. Will wait on landing temporalio/samples-java#775 first, so the snippets are on |
Contributor
Author
|
Snipsync has been completed, and has been synced |
lennessyy
reviewed
May 4, 2026
|
|
||
| ::: | ||
|
|
||
| ## Compatibility |
Contributor
There was a problem hiding this comment.
This reads more like Prerequisites than compatibility? Let's be a bit more explicit that the user needs all these to get the integration to work
lennessyy
approved these changes
May 4, 2026
Contributor
lennessyy
left a comment
lennessyy
left a comment
There was a problem hiding this comment.
Looks good. Just a few polish suggestions
| description: Build durable AI agents in Java with the Temporal Spring AI integration. | ||
| --- | ||
|
|
||
| [Spring AI](https://docs.spring.io/spring-ai/reference/) is an agent framework for Java applications — chat clients, tool calling, vector stores, embeddings, and MCP servers, all wired through Spring Boot. The [Temporal Spring AI integration](https://central.sonatype.com/artifact/io.temporal/temporal-spring-ai) makes Spring AI agents durable: model calls run through Temporal Activities recorded in Workflow history, and tools are dispatched per their type so each kind lands in the right place in Workflow execution — Activity stubs and Nexus stubs as durable operations, `@SideEffectTool` classes wrapped in `Workflow.sideEffect`, and plain tools running directly in Workflow code. Agents retry on failure and replay deterministically without changing how you write Spring AI code. |
Contributor
There was a problem hiding this comment.
Suggested change
| [Spring AI](https://docs.spring.io/spring-ai/reference/) is an agent framework for Java applications — chat clients, tool calling, vector stores, embeddings, and MCP servers, all wired through Spring Boot. The [Temporal Spring AI integration](https://central.sonatype.com/artifact/io.temporal/temporal-spring-ai) makes Spring AI agents durable: model calls run through Temporal Activities recorded in Workflow history, and tools are dispatched per their type so each kind lands in the right place in Workflow execution — Activity stubs and Nexus stubs as durable operations, `@SideEffectTool` classes wrapped in `Workflow.sideEffect`, and plain tools running directly in Workflow code. Agents retry on failure and replay deterministically without changing how you write Spring AI code. | |
| [Spring AI](https://docs.spring.io/spring-ai/reference/) is an agent framework for Java applications — chat clients, tool calling, vector stores, embeddings, and MCP servers, all wired through Spring Boot. | |
| The [Temporal Spring AI integration](https://central.sonatype.com/artifact/io.temporal/temporal-spring-ai) makes Spring AI agents durable: model calls run through Temporal Activities recorded in Workflow history, and tools are dispatched per their type so each kind lands in the right place in Workflow execution — Activity stubs and Nexus stubs as durable operations, `@SideEffectTool` classes wrapped in `Workflow.sideEffect`, and plain tools running directly in Workflow code. Agents retry on failure and replay deterministically without changing how you write Spring AI code. |
This paragraph is a big long so could use a break here
|
|
||
| `ActivityChatModel.forDefault()` resolves to the default Spring AI `ChatModel` bean. To target a specific model in a multi-model application, pass its bean name to `ActivityChatModel.forModel("openai")`. | ||
|
|
||
| :::note |
Contributor
There was a problem hiding this comment.
Suggested change
| :::note | |
| :::note | |
our prettier config would format the next line onto the :::note line if there is no space
| Streaming responses are not currently supported. | ||
| ::: | ||
|
|
||
| ## Register tools |
Contributor
There was a problem hiding this comment.
Can we give a brief explanation of what it means to register tool and link to Spring AI docs?
|
|
||
| `ActivityChatModel.forDefault()` and `forModel(name)` build the chat Activity stub with sensible defaults: a 2-minute start-to-close timeout, 3 attempts, and `org.springframework.ai.retry.NonTransientAiException` and `java.lang.IllegalArgumentException` classified as non-retryable so a bad API key or invalid prompt fails fast. | ||
|
|
||
| Pass an `ActivityOptions` directly when you need finer control — a specific Task Queue, heartbeats, priority, or a custom `RetryOptions`: |
Contributor
There was a problem hiding this comment.
Let's add some cross links to heartbeats and priority since these aren't 101 concepts.
|
|
||
| `ActivityMcpClient` wraps a Spring AI MCP client so that remote MCP tool calls become durable Activity executions. | ||
|
|
||
| ## Learn more |
Contributor
There was a problem hiding this comment.
Suggested change
| ## Learn more | |
| ## Resources |
Resources is the standard heading we use for this type of content
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Documents the new
temporal-spring-aimodule that landed in sdk-java#2829.docs/develop/java/integrations/spring-ai.mdxwith setup, chat model usage, tool types (Activity stubs, Nexus stubs,@SideEffectTool, plain tools), and optional vector store / embedding / MCP integrations.docs/develop/java/integrations/index.mdxto split framework integrations from AI integrations (matching the Python SDK integrations layout).docs/develop/integrations.mdx.sidebars.js.Why
The Spring AI integration just merged to master on
sdk-java. Java users following the Spring Boot path need a landing page that explains how to make Spring AI calls durable through Temporal, which tool annotations to use for determinism, and what optional features auto-configure.┆Attachments: EDU-6226 Add Spring AI integration documentation for Java SDK