Add temporal-spring-ai module by donald-pinckney · Pull Request #2829 · temporalio/sdk-java

donald-pinckney · 2026-04-06T20:49:20Z

Summary

Adds temporal-spring-ai module that integrates Spring AI with Temporal workflows, making AI model calls, tool execution, vector store operations, embeddings, and MCP tool calls durable Temporal primitives.

Design

The core problem

Spring AI's ChatModel.call() does two things in one method: it calls the LLM and executes any tools the LLM requests, looping until the model returns a final text response. In a Temporal workflow, these need to happen in different execution contexts:

LLM calls must run as activities (network I/O, retryable, durable)
Tool execution must run in the workflow (so tools can themselves be activities, sideEffects, or other Temporal primitives)

How ActivityChatModel solves this

ActivityChatModel implements Spring AI's ChatModel interface with the same recursive call() → internalCall() pattern used by OpenAiChatModel and other Spring AI implementations. The difference is what happens inside:

Model call: converts the prompt to serializable ChatModelTypes, sends it to ChatModelActivity (a Temporal activity), gets back the response
Tool check: if the model requested tool calls, ToolCallingManager.executeToolCalls() runs the tools — these are our ActivityToolCallback, SideEffectToolCallback, etc. which execute as Temporal activities or Workflow.sideEffect()
Loop: sends tool results back to the model (recursive internalCall()) until the model returns a final response

The activity-side ChatModelActivityImpl sets internalToolExecutionEnabled(false) so the actual LLM provider (OpenAI, Anthropic, etc.) only returns tool call requests without executing them — execution happens back in the workflow.

Tool classification

Tools passed to TemporalChatClient.builder().defaultTools() are automatically classified:

Type	Detection	Execution	Use case
Activity stub	`instanceof ActivityInvocationHandler`	Temporal activity	Network I/O, external APIs
Local activity stub	`instanceof LocalActivityInvocationHandler`	Temporal local activity	Fast local operations
`@DeterministicTool`	Annotation	Direct call in workflow	Pure functions (string ops, math)
`@SideEffectTool`	Annotation	`Workflow.sideEffect()`	Timestamps, UUIDs, random values
Nexus service stub	`instanceof NexusServiceInvocationHandler`	Nexus operation	Cross-namespace calls

Conditional auto-configuration

Optional integrations only load when their dependencies are on the classpath, matching Spring AI's own approach (where RAG, MCP, etc. are separate opt-in starters):

Auto-config class	Condition	Plugin	Registers
`SpringAiTemporalAutoConfiguration`	`ChatModel` + `Worker`	`SpringAiPlugin`	`ChatModelActivity`, `ExecuteToolLocalActivity`
`SpringAiVectorStoreAutoConfiguration`	`VectorStore` bean	`VectorStorePlugin`	`VectorStoreActivity`
`SpringAiEmbeddingAutoConfiguration`	`EmbeddingModel` bean	`EmbeddingModelPlugin`	`EmbeddingModelActivity`
`SpringAiMcpAutoConfiguration`	`McpSyncClient` class	`McpPlugin`	`McpClientActivity`

Test plan

Unit tests: type conversion — ChatModelActivityImplTest (10 tests)
Unit tests: tool detection — TemporalToolUtilTest (22 tests)
Unit tests: plugin registration — SpringAiPluginTest (9 tests)
Replay tests: workflow determinism via WorkflowReplayer — WorkflowDeterminismTest (2 tests)
Verify all 5 samples boot against Temporal dev server

🤖 Generated with Claude Code

donald-pinckney

Self-review: temporal-spring-ai plugin

What's done well

Determinism architecture is sound. The core design — routing all non-deterministic operations (LLM calls, vector store ops, embeddings, MCP tools) through Temporal activities — is exactly right. The three-tier tool system (@DeterministicTool for pure functions, @SideEffectTool for cheap non-determinism, activity stubs for durable I/O) maps cleanly onto Temporal's primitives.

Tool execution stays in the workflow. ChatModelActivityImpl sets internalToolExecutionEnabled(false) and only passes tool definitions to the model. The actual tool dispatch happens back in the workflow via ToolCallingManager, which means tool calls respect their Temporal wrapping (activity, sideEffect, etc.).

SideEffectToolCallback correctly wraps each call in Workflow.sideEffect(), recording the result in history on first execution and replaying the stored value.

ActivityChatModel.call() handles the tool loop correctly — it recursively calls itself when the model requests tools that don't returnDirect, maintaining proper conversation history.

Issues flagged inline below

...oral-spring-ai/src/main/java/io/temporal/springai/tool/LocalActivityToolCallbackWrapper.java

donald-pinckney · 2026-04-06T20:54:02Z

...oral-spring-ai/src/main/java/io/temporal/springai/tool/LocalActivityToolCallbackWrapper.java

+ */
+public class LocalActivityToolCallbackWrapper implements ToolCallback {
+
+  private static final Map<String, ToolCallback> CALLBACK_REGISTRY = new ConcurrentHashMap<>();


Medium severity — static registry lifecycle risk.

This static ConcurrentHashMap holds live ToolCallback references. Callbacks are removed in a finally block after the local activity completes, but if the workflow is evicted from the worker cache mid-execution (before finally runs), callbacks leak. Worth documenting or adding periodic cleanup.

Done — added javadoc documenting the eviction leak risk and pointing to getRegisteredCallbackCount() for monitoring.

Would a bounded size or TTL-based eviction strategy for the hash map make more sense, as opposed to just giving users a method to monitor the count? Even some (imo very high) limit like 10,000? Or maybe log a warning in case a user hits some huge number like that? Wdyt?

most likely not going ahead with SandboxingAdvisor, which would also kill this.

temporal-spring-ai/src/main/java/io/temporal/springai/util/TemporalStubUtil.java

temporal-spring-ai/src/main/java/io/temporal/springai/model/ActivityChatModel.java

temporal-spring-ai/src/main/java/io/temporal/springai/plugin/SpringAiPlugin.java

temporal-spring-ai/build.gradle

temporal-spring-ai/src/main/java/io/temporal/springai/model/ActivityChatModel.java

donald-pinckney

Found an additional bug during testing.

temporal-spring-ai/src/main/java/io/temporal/springai/model/ActivityChatModel.java

donald-pinckney · 2026-04-07T20:13:21Z

TASK_QUEUE.json

Obviously will delete this prior to merging ;)

Adds a new module that integrates Spring AI with Temporal workflows, enabling durable AI model calls, vector store operations, embeddings, and MCP tool execution as Temporal activities. Key components: - ActivityChatModel: ChatModel implementation backed by activities - TemporalChatClient: Temporal-aware ChatClient with tool detection - SpringAiPlugin: Auto-registers Spring AI activities with workers - Tool system: @DeterministicTool, @SideEffectTool, activity-backed tools - MCP integration: ActivityMcpClient for durable MCP tool calls Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T9: Add javadoc to LocalActivityToolCallbackWrapper explaining the leak risk when workflows are evicted from worker cache mid-execution. T11: Override stream() in ActivityChatModel to throw UnsupportedOperationException with a clear message, since streaming through Temporal activities is not supported. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T1: ChatModelActivityImplTest (10 tests) - type conversion between ChatModelTypes and Spring AI types, multi-model resolution, tool definition passthrough, model options mapping. T2: TemporalToolUtilTest (22 tests) - tool detection and conversion for @DeterministicTool, @SideEffectTool, stub type detection, error cases for unknown/null types. T3: WorkflowDeterminismTest (2 tests) - verifies workflows using ActivityChatModel with tools complete without non-determinism errors in the Temporal test environment. T4: SpringAiPluginTest (10 tests) - plugin registration with various bean combinations, multi-model support, default model resolution. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T5: Replace UUID.randomUUID() with Workflow.randomUUID() in LocalActivityToolCallbackWrapper to ensure deterministic replay. T7: Convert recursive tool call loop in ActivityChatModel.call() to iterative loop with MAX_TOOL_CALL_ITERATIONS (10) limit to prevent infinite recursion from misbehaving models. T14: Fix NPE when ChatResponse metadata is null by only calling .metadata() on the builder when metadata is non-null. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Split the monolithic SpringAiPlugin into one core plugin + three optional plugins, each with its own @ConditionalOnClass-guarded auto-configuration: - SpringAiPlugin: core chat + ExecuteToolLocalActivity (always) - VectorStorePlugin: VectorStore activity (when spring-ai-rag present) - EmbeddingModelPlugin: EmbeddingModel activity (when spring-ai-rag present) - McpPlugin: MCP activity (when spring-ai-mcp present) This fixes ClassNotFoundException when optional deps aren't on the runtime classpath. compileOnly scopes now work correctly because Spring skips loading the conditional classes entirely when the @ConditionalOnClass check fails. Also resolves T10 (unnecessary MCP reflection) — McpPlugin directly references McpClientActivityImpl instead of using Class.forName(). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Use direct instanceof checks against the SDK's internal invocation handler classes instead of string-matching on class names. Since the plugin lives in the SDK repo, any handler rename would break compilation rather than silently failing at runtime. ChildWorkflowInvocationHandler is package-private so it still uses a class name check (endsWith instead of contains for precision). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Previously the tests just ran workflows forward. Now they capture the event history after execution and replay it with WorkflowReplayer.replayWorkflowExecution(), which will throw NonDeterministicException if the workflow code generates different commands on replay. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Remove MAX_TOOL_CALL_ITERATIONS and the iterative loop. Use recursive internalCall() matching Spring AI's OpenAiChatModel pattern. Temporal's activity timeouts and workflow execution timeout already bound runaway tool loops. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tconley1428 · 2026-04-08T16:09:37Z

temporal-spring-ai/src/main/java/io/temporal/springai/plugin/VectorStorePlugin.java

+ * <p>This plugin is conditionally created by auto-configuration when Spring AI's {@link
+ * VectorStore} is on the classpath and a VectorStore bean is available.
+ */
+public class VectorStorePlugin extends SimplePlugin {


Is the primary reason for these being separate plugins because of spring configuration interaction? Otherwise I would think it makes more sense to have one with configurations.

it's not just Spring config interaction, it's about not forcing transitive dependencies on users. A single plugin would either need all deps as implementation or use reflection/Object types to avoid class references (fragile/yucky). Given that normal (non-Temporal) Spring AI already ships things as separate artifacts, this seemed like the most natural spring-ai-native design.

Other option is to have implementation dependencies on Spring AI's various artifacts (for MCP, RAG, etc.), which is simpler but aligns less with Spring from what I've seen. Others could weigh in here though.

To be clear, you can't just have compileOnly deps on those optional dependencies, because Spring needs to load and introspect the plugin class at startup, so any field types that don't exist at runtime cause a ClassNotFoundException.

temporal-spring-ai/src/main/java/io/temporal/springai/plugin/VectorStorePlugin.java

tconley1428 · 2026-04-08T16:15:58Z

...oral-spring-ai/src/main/java/io/temporal/springai/tool/LocalActivityToolCallbackWrapper.java

+ *
+ * @see ExecuteToolLocalActivity
+ */
+public class LocalActivityToolCallbackWrapper implements ToolCallback {


Is there a good reason we are making local activities so primary?

would be resolved following other discussion below

Copilot

Pull request overview

Adds a new temporal-spring-ai module that integrates Spring AI with Temporal by making chat model calls, tool execution, embeddings, vector store operations, and MCP tool calls durable Temporal primitives.

Changes:

Introduces ActivityChatModel + ChatModelActivity to run LLM calls as activities while executing tools deterministically in workflows.
Adds tool conversion utilities (activity/local activity/Nexus stubs, @DeterministicTool, @SideEffectTool) plus a sandboxing advisor for unsafe tools.
Adds Spring Boot auto-configuration + worker plugins for ChatModel, VectorStore, EmbeddingModel, and MCP, along with unit + replay determinism tests.

Reviewed changes

Copilot reviewed 45 out of 45 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
temporal-spring-ai/src/main/java/io/temporal/springai/model/ActivityChatModel.java	Workflow-safe `ChatModel` that delegates model calls to a Temporal activity and loops for tool execution.
temporal-spring-ai/src/main/java/io/temporal/springai/activity/ChatModelActivity.java	Activity interface for invoking Spring AI chat models durably.
temporal-spring-ai/src/main/java/io/temporal/springai/activity/ChatModelActivityImpl.java	Activity implementation converting between serializable types and Spring AI prompt/response types.
temporal-spring-ai/src/main/java/io/temporal/springai/model/ChatModelTypes.java	Serializable request/response/message/tool types for activity communication.
temporal-spring-ai/src/main/java/io/temporal/springai/chat/TemporalChatClient.java	`ChatClient` builder that auto-converts Temporal primitives into Spring AI tool callbacks.
temporal-spring-ai/src/main/java/io/temporal/springai/util/TemporalToolUtil.java	Converts provided tool objects into appropriate `ToolCallback` implementations.
temporal-spring-ai/src/main/java/io/temporal/springai/util/TemporalStubUtil.java	Detects Temporal stub types via proxy invocation handlers.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/DeterministicTool.java	Annotation marking tools safe to execute directly in workflows.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/SideEffectTool.java	Annotation marking tools to be executed via `Workflow.sideEffect()`.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/SideEffectToolCallback.java	Wrapper executing tool callbacks inside `Workflow.sideEffect()` for determinism.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/ActivityToolUtil.java	Extracts Spring AI tool definitions from activity interfaces/stubs.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/ActivityToolCallback.java	Marker wrapper for callbacks backed by Temporal activity stubs.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/NexusToolUtil.java	Extracts Spring AI tool definitions from Nexus service stubs.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/NexusToolCallback.java	Marker wrapper for callbacks backed by Nexus service stubs.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/ExecuteToolLocalActivity.java	Local-activity interface used to execute otherwise-unsafe tool callbacks deterministically.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/ExecuteToolLocalActivityImpl.java	Local-activity implementation that looks up and executes registered callbacks.
temporal-spring-ai/src/main/java/io/temporal/springai/tool/LocalActivityToolCallbackWrapper.java	Wraps arbitrary callbacks into a local activity using a static callback registry.
temporal-spring-ai/src/main/java/io/temporal/springai/advisor/SandboxingAdvisor.java	Advisor that wraps non-Temporal-safe tool callbacks in local activities with warnings.
temporal-spring-ai/src/main/java/io/temporal/springai/plugin/SpringAiPlugin.java	Core worker plugin registering ChatModel + tool-execution local activity.
temporal-spring-ai/src/main/java/io/temporal/springai/plugin/VectorStorePlugin.java	Optional worker plugin registering VectorStore activity.
temporal-spring-ai/src/main/java/io/temporal/springai/plugin/EmbeddingModelPlugin.java	Optional worker plugin registering EmbeddingModel activity.
temporal-spring-ai/src/main/java/io/temporal/springai/plugin/McpPlugin.java	Optional worker plugin registering MCP client activity (supports deferred registration).
temporal-spring-ai/src/main/java/io/temporal/springai/activity/VectorStoreActivity.java	Activity interface for vector store operations.
temporal-spring-ai/src/main/java/io/temporal/springai/activity/VectorStoreActivityImpl.java	Vector store activity implementation + type conversions.
temporal-spring-ai/src/main/java/io/temporal/springai/model/VectorStoreTypes.java	Serializable types for VectorStore activity calls.
temporal-spring-ai/src/main/java/io/temporal/springai/activity/EmbeddingModelActivity.java	Activity interface for embedding operations.
temporal-spring-ai/src/main/java/io/temporal/springai/activity/EmbeddingModelActivityImpl.java	Embedding activity implementation + conversions.
temporal-spring-ai/src/main/java/io/temporal/springai/model/EmbeddingModelTypes.java	Serializable types for EmbeddingModel activity calls.
temporal-spring-ai/src/main/java/io/temporal/springai/mcp/McpClientActivity.java	Activity interface for MCP client operations.
temporal-spring-ai/src/main/java/io/temporal/springai/mcp/McpClientActivityImpl.java	MCP activity implementation delegating to Spring AI MCP sync clients.
temporal-spring-ai/src/main/java/io/temporal/springai/mcp/ActivityMcpClient.java	Workflow-side wrapper around MCP activities (cached lookups).
temporal-spring-ai/src/main/java/io/temporal/springai/mcp/McpToolCallback.java	ToolCallback implementation that calls MCP tools through activities.
temporal-spring-ai/src/main/java/io/temporal/springai/autoconfigure/SpringAiTemporalAutoConfiguration.java	Core Spring Boot auto-config producing the main Spring AI plugin bean.
temporal-spring-ai/src/main/java/io/temporal/springai/autoconfigure/SpringAiVectorStoreAutoConfiguration.java	Conditional auto-config for vector store plugin.
temporal-spring-ai/src/main/java/io/temporal/springai/autoconfigure/SpringAiEmbeddingAutoConfiguration.java	Conditional auto-config for embedding plugin.
temporal-spring-ai/src/main/java/io/temporal/springai/autoconfigure/SpringAiMcpAutoConfiguration.java	Conditional auto-config for MCP plugin.
temporal-spring-ai/src/main/resources/META-INF/spring/org.springframework.boot.autoconfigure.AutoConfiguration.imports	Registers the module’s Spring Boot auto-configurations.
temporal-spring-ai/src/test/java/io/temporal/springai/activity/ChatModelActivityImplTest.java	Unit tests for serializable type conversions and tool-call preservation.
temporal-spring-ai/src/test/java/io/temporal/springai/util/TemporalToolUtilTest.java	Unit tests for tool detection/conversion and stub detection utilities.
temporal-spring-ai/src/test/java/io/temporal/springai/plugin/SpringAiPluginTest.java	Unit tests for plugin registration behavior.
temporal-spring-ai/src/test/java/io/temporal/springai/WorkflowDeterminismTest.java	Replay test intended to validate determinism via captured history replay.
temporal-spring-ai/build.gradle	New module build with Java 17 target and Spring AI dependencies.
temporal-bom/build.gradle	Adds `temporal-spring-ai` to the BOM.
settings.gradle	Includes the new `temporal-spring-ai` module in the build.
TASK_QUEUE.json	Task tracking artifact for the module work items.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

temporal-spring-ai/src/main/java/io/temporal/springai/model/ActivityChatModel.java

temporal-spring-ai/src/main/java/io/temporal/springai/util/TemporalToolUtil.java

...g-ai/src/main/java/io/temporal/springai/autoconfigure/SpringAiTemporalAutoConfiguration.java

temporal-spring-ai/src/test/java/io/temporal/springai/WorkflowDeterminismTest.java

DABH

Looks like a ton of progress in the right direction! 🚀 Just a few questions/comments (on top of what others have already pointed out). Take them or leave them :)

temporal-spring-ai/build.gradle

DABH · 2026-04-08T19:53:21Z

temporal-spring-ai/build.gradle

+description = '''Temporal Java SDK Spring AI Plugin'''
+
+ext {
+    springAiVersion = '1.1.0'


Probably clarify in the docs/readme the compatibility matrix for the module? (So - maybe not in this PR - but at least in the forthcoming docs PR)

Good call — will add a compatibility matrix to the module README. Tracking as a follow-up task.

🤖 Generated with Claude Code

DABH · 2026-04-08T19:55:02Z

...oral-spring-ai/src/main/java/io/temporal/springai/tool/LocalActivityToolCallbackWrapper.java

+ */
+public class LocalActivityToolCallbackWrapper implements ToolCallback {
+
+  private static final Map<String, ToolCallback> CALLBACK_REGISTRY = new ConcurrentHashMap<>();


Would a bounded size or TTL-based eviction strategy for the hash map make more sense, as opposed to just giving users a method to monitor the count? Even some (imo very high) limit like 10,000? Or maybe log a warning in case a user hits some huge number like that? Wdyt?

DABH · 2026-04-08T19:56:44Z

temporal-spring-ai/src/main/java/io/temporal/springai/advisor/SandboxingAdvisor.java

+ * @see io.temporal.springai.tool.SideEffectTool
+ * @see LocalActivityToolCallbackWrapper
+ */
+public class SandboxingAdvisor implements CallAdvisor {


If you do go ahead with this route, it looks like tests are lacking at the moment, is there a meaningful way to explicitly test adviseCall?

most likely not going ahead with SandboxingAdvisor

DABH · 2026-04-08T20:36:17Z

temporal-spring-ai/src/main/java/io/temporal/springai/mcp/ActivityMcpClient.java

+    if (serverCapabilities == null) {
+      serverCapabilities = activity.getServerCapabilities();
+    }
+    return serverCapabilities;


Does it make sense to cache this in terms of replayability? If the workflow is replayed in some way where the activity's server capabilities have changed, we'd get a stale value? Is that a realistic thing we need to worry about?

This doesn't matter in terms of replayability. In fact, this cache won't be hit (initially) during replay, but Temporal itself will return the cached getServerCapabilities activity result.

When this cache will be hit is during multiple calls to getServerCapabilities throughout the life of the workflow: in those cases we don't do the whole activity and thus MCP remote call, we just return the cached thing.

IMO its pretty common practice to cache server capabilities with MCP, and it would be I think a bit confusing if the MCP client were able to react to new capabilities during the execution of a workflow, but not during later replay of a workflow.

temporal-spring-ai/src/main/java/io/temporal/springai/mcp/McpClientActivityImpl.java

DABH · 2026-04-08T20:38:10Z

...oral-spring-ai/src/main/java/io/temporal/springai/tool/LocalActivityToolCallbackWrapper.java

+    // Note: ToolContext cannot be passed through the activity, so we ignore it here.
+    // If context is needed, consider using activity parameters or workflow state.


Should we warn users about this?

also would go away

temporal-spring-ai/src/main/java/io/temporal/springai/model/ChatModelTypes.java

temporal-spring-ai/src/main/java/io/temporal/springai/activity/EmbeddingModelActivityImpl.java

Replace VectorStorePlugin and EmbeddingModelPlugin subclasses with SimplePlugin.newBuilder().registerActivitiesImplementations() in the auto-config classes. These plugins are trivial activity registrations that don't need custom subclasses when the builder already supports this. SpringAiPlugin stays as a subclass (has getter API for chat models). McpPlugin stays as a subclass (needs SmartInitializingSingleton for deferred registration). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Remove all completed/reverted tasks. Add T15 for the tool execution model change discussed in PR review (run plain tools in workflow context by default, remove @DeterministicTool and SandboxingAdvisor). Blocked on finalizing review discussion. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T16-T21: fixes (NPE guard, error message, multi-ChatModel bug, replay test, duplicate MCP names, embedding boxing) T22-T24: design discussions to have with Don (starter artifact, MCP caching, Object vs String) T25-T27: replies (docs, SandboxingAdvisor tests, ToolContext drop — last two likely moot if T15 lands) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

temporal-spring-ai/src/main/java/io/temporal/springai/plugin/SpringAiPlugin.java

...i/src/main/java/io/temporal/springai/autoconfigure/SpringAiVectorStoreAutoConfiguration.java

@primary

Multiple ChatModel beans without @primary caused startup failure. ObjectProvider.getIfAvailable() returns null gracefully instead. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ToolCallingStubChatModel returns a tool call request on first call, then final text after receiving the tool response. This verifies the full model -> tool -> model loop replays deterministically. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Avoids boxing 1536+ Double objects per embedding. float[] matches Spring AI's native embedding representation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

@primary

getIfAvailable() still throws NoUniqueBeanDefinitionException when multiple beans exist without @primary. getIfUnique() returns null in that case, which is what we want — SpringAiPlugin falls back to the first entry in the map. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

…sses Use SimplePlugin's builder constructor (super(Builder)) so the classes are named and user-creatable (new VectorStorePlugin(vectorStore)) while still using the builder internally rather than overriding initializeWorker. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

…lActivity Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Spring AI's Content.getText() returns String. We always cast to String on both sides. Object type gave false flexibility that would ClassCastException at runtime. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Edge CI sets edgeDepsTest which compiles temporal-sdk targeting Java 21. Our module hardcoded Java 17, causing Gradle to reject the dependency at resolution time. Now uses 21 when edgeDepsTest is set, 17 otherwise. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Docker CI runs Java 11 which can't compile --release 17. Conditionally exclude the module from settings.gradle and BOM when the build JDK is below 17. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Tools passed to defaultTools() that aren't activity stubs, nexus stubs, or @SideEffectTool now execute directly in workflow context. The user is responsible for determinism — they can call activities, sideEffect, child workflows, etc. from within their tool methods. Removed: - @DeterministicTool annotation (plain tools are the default now) - SandboxingAdvisor (no more automatic wrapping) - LocalActivityToolCallbackWrapper, ExecuteToolLocalActivity, ExecuteToolLocalActivityImpl (only used by SandboxingAdvisor) - ExecuteToolLocalActivity registration from SpringAiPlugin This matches how other Temporal AI integrations handle tools. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

donald-pinckney mentioned this pull request Apr 6, 2026

Add Spring AI samples temporalio/samples-java#775

Draft

5 tasks

donald-pinckney commented Apr 6, 2026

View reviewed changes

donald-pinckney force-pushed the d/20260406-164203 branch from f210b63 to 35e9b29 Compare April 6, 2026 21:25

donald-pinckney commented Apr 6, 2026

View reviewed changes

temporal-spring-ai/src/main/java/io/temporal/springai/model/ActivityChatModel.java Outdated Show resolved Hide resolved

donald-pinckney force-pushed the d/20260406-164203 branch 2 times, most recently from 6b01988 to 4fd80ec Compare April 7, 2026 20:12

donald-pinckney commented Apr 7, 2026

View reviewed changes

TASK_QUEUE.json

Copy link
Copy Markdown

Contributor Author

donald-pinckney Apr 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Obviously will delete this prior to merging ;)

donald-pinckney force-pushed the d/20260406-164203 branch from ee8e3c0 to 2a40064 Compare April 8, 2026 15:46

donald-pinckney and others added 15 commits April 8, 2026 11:49

Update TASK_QUEUE.json: T1-T4, T9, T11 completed

b62adfa

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Add T14 (NPE bug) to TASK_QUEUE.json

e538674

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Update TASK_QUEUE.json: T5, T6, T7, T10, T14 completed

58804ad

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Update TASK_QUEUE.json: T12 completed

f4b1028

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Update TASK_QUEUE.json: T8 completed

0cc143e

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Simplify stream() exception message

8ba4eb0

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Fix javadoc reference for publishToMavenLocal

969aabd

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

donald-pinckney force-pushed the d/20260406-164203 branch from 2a40064 to 969aabd Compare April 8, 2026 15:49

donald-pinckney marked this pull request as ready for review April 8, 2026 15:50

donald-pinckney requested a review from a team as a code owner April 8, 2026 15:50

donald-pinckney mentioned this pull request Apr 8, 2026

Migrate demos 2-4 to new temporal-spring-ai plugin temporal-community/springio-agents-springai-temporal#1

Open

tconley1428 reviewed Apr 8, 2026

View reviewed changes

temporal-spring-ai/src/main/java/io/temporal/springai/plugin/VectorStorePlugin.java Outdated Show resolved Hide resolved

tconley1428 reviewed Apr 8, 2026

View reviewed changes

Copilot started reviewing on behalf of brianstrauch April 8, 2026 19:43 View session

Copilot AI reviewed Apr 8, 2026

View reviewed changes

DABH requested changes Apr 8, 2026

View reviewed changes

donald-pinckney and others added 6 commits April 9, 2026 17:24

Add link to proposed design for T15

336cc7b

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T16: Guard assistantMessage.getMedia() against null

32e6f99

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T17: Include Nexus stubs in unrecognized tool type error message

d9b5002

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tconley1428 reviewed Apr 9, 2026

View reviewed changes

temporal-spring-ai/src/main/java/io/temporal/springai/plugin/SpringAiPlugin.java Outdated Show resolved Hide resolved

tconley1428 reviewed Apr 9, 2026

View reviewed changes

...i/src/main/java/io/temporal/springai/autoconfigure/SpringAiVectorStoreAutoConfiguration.java Outdated Show resolved Hide resolved

donald-pinckney and others added 19 commits April 10, 2026 08:45

T18: Use ObjectProvider to fix NoUniqueBeanDefinitionException

bec50f8

Multiple ChatModel beans without @primary caused startup failure. ObjectProvider.getIfAvailable() returns null gracefully instead. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T20: Handle duplicate MCP client names with clear error

6c3a107

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T21: Use float[] instead of List<Double> in EmbeddingModelTypes

4e6003d

Avoids boxing 1536+ Double objects per embedding. float[] matches Spring AI's native embedding representation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Add T28: Restore plugin classes as public API per tconley review

52c6d4b

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Clean up TASK_QUEUE: remove completed, mark superseded

01fec57

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T23: Resolved — MCP capability caching is correct

bc6275f

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T24: Change from discussion to fix — rawContent should be String

60f2941

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T22: Defer starter artifact to after PR merge

528e538

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T25: Replied to DABH about docs. Added T29 for README follow-up.

d58700f

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T29: Bump to high priority, do in this PR

4e600da

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T15: Also remove LocalActivityToolCallbackWrapper and ExecuteToolLoca…

e19463b

…lActivity Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T29: Add README with compatibility matrix and quick start

70c8594

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

T31: Skip temporal-spring-ai on JDK < 17

42f46d6

Docker CI runs Java 11 which can't compile --release 17. Conditionally exclude the module from settings.gradle and BOM when the build JDK is below 17. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

		// Note: ToolContext cannot be passed through the activity, so we ignore it here.
		// If context is needed, consider using activity parameters or workflow state.

Conversation

donald-pinckney commented Apr 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Design

The core problem

How ActivityChatModel solves this

Tool classification

Conditional auto-configuration

Related

Test plan

Uh oh!

donald-pinckney left a comment

Choose a reason for hiding this comment

Self-review: temporal-spring-ai plugin

What's done well

Issues flagged inline below

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

donald-pinckney left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

DABH left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

donald-pinckney commented Apr 6, 2026 •

edited

Loading