Merged
Conversation
Signed-off-by: Salman Muin Kayser Chishti <13schishti@gmail.com>
PiperOrigin-RevId: 884881559
This change ensures that the OpenTelemetry context is correctly propagated across asynchronous boundaries throughout the ADK, primarily within RxJava streams.
### Key Changes
* **Context Propagation:** Replaces manual `Scope` management (which often fails in reactive code) with `.compose(Tracing.withContext(context))`. This ensures the OTel context is preserved when work moves between different threads or schedulers.
* **`Runner` Refactoring:**
* Adds a top-level `"invocation"` span to `runAsync` and `runLive` calls.
* Captures the context at entry points and propagates it through the internal execution flow (`runAsyncImpl`, `runLiveImpl`, `runAgentWithFreshSession`).
* **`BaseLlmFlow` & `Functions`:** Updates preprocessing, postprocessing, and tool execution logic to maintain context. This ensures that spans created within tools or processors are correctly parented.
* **`PluginManager`:** Ensures that plugin callbacks (like `afterRunCallback` and `onEventCallback`) execute within the captured context.
* **Testing:** Adds several unit tests across `BaseLlmFlowTest`, `FunctionsTest`, `PluginManagerTest`, and `RunnerTest` that specifically verify context propagation using `ContextKey` and `Schedulers.computation()`.
### Files Modified
* **`BaseLlmFlow.java`**, **`Functions.java`**, **`PluginManager.java`**, **`Runner.java`**: Core logic updates for context propagation.
* **`LlmAgentTest.java`**, **`BaseLlmFlowTest.java`**, **`FunctionsTest.java`**, **`PluginManagerTest.java`**, **`RunnerTest.java`**: New tests for OTel integration.
* **`BUILD` files**: Updated dependencies for OpenTelemetry APIs and SDK testing.
PiperOrigin-RevId: 884998997
InMemorySessionService sets a Session's last modified time based on when the last appended event's timestamp. The timestamp in an event is recorded in millis while the Session's timestamp is an Instant. During the transformation, Events perform this converstion using division. Before this change, the timestamp was truncated to the second, yet the code was trying to extract nanos which were always 0. This fixes that bug with a simple type change. I've also added a test to prevent regressions.
PiperOrigin-RevId: 885091550
This change introduces a new plugin for the Agent Development Kit (ADK) that logs agent execution events to BigQuery. It includes: - `BigQueryAgentAnalyticsPlugin`: A plugin that captures various agent lifecycle events (user messages, tool calls, model invocations) and sends them to BigQuery. - `BigQueryLoggerConfig`: Configuration options for the plugin, including project/dataset/table IDs, batching, and retry settings. - `BigQuerySchema`: Defines the BigQuery and Arrow schemas used for the event table. - `BatchProcessor`: Handles batching of events and writing them to BigQuery using the Storage Write API with Arrow format. - `JsonFormatter`: Utility for safely formatting JSON content for BigQuery. PiperOrigin-RevId: 885133967
PiperOrigin-RevId: 885495376
…um type for the metadata keys PiperOrigin-RevId: 885539894
PiperOrigin-RevId: 885544295
PiperOrigin-RevId: 885570460
PiperOrigin-RevId: 885587141
…ected (google#983) PiperOrigin-RevId: 885595843
fixes google#1009 PiperOrigin-RevId: 885641755
PiperOrigin-RevId: 885684062
PiperOrigin-RevId: 885777704
…ode24 PiperOrigin-RevId: 886014163
These changes are now in sync with Python ADK PiperOrigin-RevId: 886040294
… copy and add null handling for `artifactDelta` in the Builder PiperOrigin-RevId: 886130618
PiperOrigin-RevId: 886145022
PiperOrigin-RevId: 886159283
PiperOrigin-RevId: 886166671
Release-As: 1.0.0-rc.1 PiperOrigin-RevId: 886198912
PiperOrigin-RevId: 886223741
PiperOrigin-RevId: 886244600
PiperOrigin-RevId: 886245655
PiperOrigin-RevId: 886316760
PiperOrigin-RevId: 886659065
PiperOrigin-RevId: 886722180
PiperOrigin-RevId: 886723823
PiperOrigin-RevId: 886725038
…p types PiperOrigin-RevId: 886727168
…main PiperOrigin-RevId: 886751193
PiperOrigin-RevId: 886764077
Merge google#1067 🤖 I have created a release *beep* *boop* --- ### Updating meta-information for bleeding-edge SNAPSHOT release. --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). COPYBARA_INTEGRATE_REVIEW=google#1067 from google:release-please--branches--main 0b85f5b PiperOrigin-RevId: 886764460
This CL enables the simultaneous use of `output_schema` (structured output) and `tools` for models that do not natively support both features at once (specifically Gemini 1.x and 2.x on Vertex AI). ### Core Logic The CL implements a workaround for models with this limitation: 1. **Synthetic Tooling**: Instead of passing the `output_schema` directly to the model's configuration, it introduces a synthetic tool called `set_model_response`. 2. **Schema Injection**: The parameters of this tool are set to the requested `output_schema`. 3. **Instruction Prompting**: System instructions are appended, directing the model to provide its final response using this specific tool in the required format. 4. **Response Interception**: The `BaseLlmFlow` is updated to check if `set_model_response` was called. If so, it extracts the JSON arguments and converts them into a standard model response event. ### Key Changes * **`OutputSchema.java` (New)**: A new `RequestProcessor` that detects when the workaround is needed, adds the `SetModelResponseTool`, and provides utilities for extracting the structured response. * **`SetModelResponseTool.java` (New)**: A marker tool that simply returns its input arguments, used to "capture" the structured output from the model. * **`ModelNameUtils.java`**: Added logic to identify Gemini 1.x and 2.x models and determine if they can handle native `output_schema` alongside tools. * **`BaseLlmFlow.java`**: Updated the flow logic to detect the synthetic tool response and generate the final output event. * **`Basic.java`**: Updated to prevent native `outputSchema` configuration when the workaround is active. * **`SingleFlow.java`**: Registered the new `OutputSchema` processor. PiperOrigin-RevId: 886769688
…, and use JSpecify Nullable - Migrate LangChain4j to a builder pattern - Enhance token usage handling with TokenCountEstimator (from PR google#623) - Upgrade to latest version of LangChain4j - Replace javax.annotation.Nullable with org.jspecify.annotations.Nullable
PiperOrigin-RevId: 886828787
PiperOrigin-RevId: 886942637
Ensure sequential event processing and persistence in ADK Runner. This ensures that events are appended in order and returned from runAsync in order. This aligns better with the Python implementation. PiperOrigin-RevId: 886961696
PiperOrigin-RevId: 887389399
…already implemented, but adding tests from PR google#603)
PiperOrigin-RevId: 888064419
The `slf4j-simple` dependency and the exclusion of `logback-classic` are removed, allowing the default logging implementation provided by `google-adk-dev` to be used. PiperOrigin-RevId: 888114465
Resolve core/pom.xml: keep upstream BigQuery/Arrow deps and fork extras (HikariCP, DB drivers, Redis/Kafka, testcontainers, etc.). Made-with: Cursor
- BaseArtifactService.loadArtifact now uses @nullable Integer version - EventActions.stateDelta() exposed as Map; fix PostgresSessionService - PartConverter.toGenaiPart returns Part; update RequestConverter and tests - A2AMetadataKey.TYPE replaces removed PartConverter constant - Runner.runAsync(Session,...) removed; A2aService uses SessionKey - MediaSupportTest and artifact IT/unit tests updated accordingly Made-with: Cursor
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
13 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.
No description provided.