Skip to content

chore: merge release v1.27.0 to main#4804

Merged
wuliang229 merged 4 commits intomainfrom
release/v1.27.0
Mar 12, 2026
Merged

chore: merge release v1.27.0 to main#4804
wuliang229 merged 4 commits intomainfrom
release/v1.27.0

Conversation

@Jacksunwei
Copy link
Copy Markdown
Collaborator

Syncs version bump and CHANGELOG from release v1.27.0 to main.

GWeale and others added 3 commits March 11, 2026 23:29
The `can_use_output_schema_with_tools` function now checks if a model is a LiteLlm instance by inspecting its type's Method Resolution Order, rather than directly importing `LiteLlm`

Co-authored-by: George Weale <gweale@google.com>
PiperOrigin-RevId: 882253446
Co-authored-by: Liang Wu <18244712+wuliang229@users.noreply.github.com>
@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request merges the changes from release v1.27.0 into the main branch, incorporating a wide array of new features, critical bug fixes, and significant code refactorings. The updates span across core functionalities, model integrations, tooling, observability, and optimization, enhancing the overall capabilities and stability of the system.

Highlights

  • Core Enhancements: Introduced A2A request interceptors, added UI Widget support to EventActions, enabled pluggable authentication integrations, and supported types.SchemaUnion as output schema in LLM Agents.
  • Model Capabilities: Added support for PDF documents and streaming in Anthropic LLM, and improved output schema and tool call preservation for LiteLLM models.
  • Tooling Expansion: Introduced GCS filesystem support for Skills, added various new tools like BashTool and Dataplex Catalog search, and enhanced existing BigQuery and Bigtable tools.
  • Observability Improvements: Added new OpenTelemetry span attributes for agent versions, tool definitions, and client inference operations, along with improved token usage and error code capturing.
  • Optimization Features: Introduced an adk optimize command and related infrastructure for prompt optimization.
  • A2A Integration: Implemented new A2aAgentExecutor and RemoteA2aAgent for improved Agent-to-Agent communication.
  • Bug Fixes: Addressed issues related to artifact services, LiteLLM reasoning extraction, event handling, and tool callbacks, enhancing overall stability.
  • Code Refactoring: Extracted reusable functions and renamed optimization data types for better code organization and maintainability.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog
  • .github/.release-please-manifest.json
    • Updated the project version to 1.27.0.
  • .github/release-please-config.json
    • Updated the last-release-sha to the latest release commit hash.
  • CHANGELOG.md
    • Added new release notes for version 1.27.0, detailing features, bug fixes, and code refactorings across various components.
  • src/google/adk/utils/output_schema_utils.py
    • Improved robustness of can_use_output_schema_with_tools by making LiteLlm import optional to prevent ImportError if the module is not installed.
  • src/google/adk/version.py
    • Updated the __version__ string to 1.27.0.
  • tests/unittests/utils/test_output_schema_utils.py
    • Added new test cases for can_use_output_schema_with_tools to verify behavior with and without the litellm module installed, ensuring robust handling of optional dependencies.
Activity
  • No human activity has been recorded on this pull request since its creation.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@adk-bot adk-bot added the models [Component] Issues related to model support label Mar 12, 2026
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request merges the v1.27.0 release into the main branch. The changes include version bumps in configuration files, an updated CHANGELOG, and a code improvement to handle an optional dependency gracefully. The code change in output_schema_utils.py correctly defers the import of LiteLlm and handles potential ImportError, which is well-tested. I've found a minor formatting issue in the CHANGELOG.md file that should be addressed.

@wuliang229 wuliang229 self-requested a review March 12, 2026 22:52
@wuliang229 wuliang229 merged commit abf88a9 into main Mar 12, 2026
14 checks passed
@wuliang229 wuliang229 deleted the release/v1.27.0 branch March 12, 2026 23:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

models [Component] Issues related to model support

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants