Update to specification from cfbce32cb0ac2a630597eb8b771691cac5b20a4b

[a2a-bot]

Commit: a2aproject/A2A@cfbce32

[gemini-code-assist]

Summary of Changes

Hello @a2a-bot, 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 brings the A2A protocol specification and its generated Python code up to date with the latest v0.3.0 version. The changes introduce enhanced clarity in field definitions, new API capabilities such as task listing and tenant-aware operations, and a more streamlined gRPC service interface. These updates are crucial for improving the protocol's robustness and expanding its functional scope.

Highlights

• Protocol Buffer Definition Updates: The core A2A protocol buffer definitions (a2a.proto) have been extensively updated. This includes renaming several fields (e.g., push_notification to push_notification_config, mime_type to media_type, content to parts), marking numerous fields as required, and introducing new fields like reference_task_ids in Message and supported_interfaces in AgentCard.
• API Endpoint and Method Changes: Several RPC methods in the A2AService have been renamed (e.g., TaskSubscription to SubscribeToTask, CreateTaskPushNotificationConfig to SetTaskPushNotificationConfig, GetAgentCard to GetExtendedAgentCard). A new ListTasks method has been added, and many API paths now include a /{tenant} segment, indicating multi-tenancy support.
• Generated Code Synchronization: The Python generated code (a2a_pb2.py, a2a_pb2.pyi, a2a_pb2_grpc.py) has been synchronized with the updated protocol buffer definitions. This includes changes to class structures, field types, method signatures, and docstrings to reflect the new specification.
• Specification Documentation Refinements: The a2a.json specification, reflected in src/a2a/types.py, has been updated to version v0.3.0. Descriptions for various id and task_id fields have been clarified, removing specific examples like '(e.g. UUID)' for a more general 'unique identifier' or 'ID'.

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. ↩

[gemini-code-assist]

Code Review

This pull request updates the A2A protocol definitions and related generated code to align with version 0.3.0 of the specification. The changes are widespread across Protobuf and Pydantic models, as well as gRPC service definitions. The update to the generate_types.sh script to support commit SHAs is a good improvement.

However, this PR appears to be incomplete and will likely break the build.

The updated gRPC definitions introduce several breaking changes, such as renaming RPC methods (e.g., CreateTaskPushNotificationConfig to SetTaskPushNotificationConfig, TaskSubscription to SubscribeToTask, and GetAgentCard to GetExtendedAgentCard). The code that consumes these definitions has not been updated accordingly.

Specifically, the following parts of the codebase need to be updated to reflect these changes:

• The gRPC server implementation in src/a2a/server/request_handlers/grpc_handler.py.
• The gRPC client transport in src/a2a/client/transports/grpc.py (and its usages in src/a2a/client/client.py).
• Associated tests, such as tests/client/transports/test_grpc_client.py and tests/server/request_handlers/test_grpc_handler.py.

Please update all usages of the generated code to be consistent with the new specification. This is a critical issue that prevents the PR from being merged.

Additionally, I've noted a minor documentation regression in the generated gRPC code, which I've commented on separately.

[gemini-code-assist]

The docstring for A2AServiceStub has been significantly shortened, removing valuable information about the service's design, its resources (AgentCard, Message, Task, etc.), and how they are used. While some other docstrings in this file have improved, this service-level docstring is now less informative. Please consider restoring the more detailed explanation from the previous version to aid developers in understanding the service. This also applies to the docstrings for A2AServiceServicer and the experimental A2AService class.