Add prompt_id propagation in a2a-server task

[koxkox111]

Summary

Propagate prompt_id when calling CLI via a2a-server.

Details

This field is used by Google for internal purposes.

Related Issues

#14576

How to Validate

Run a2a-server, make some calls - request sent to backend should have "user_prompt_id" field populated.

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed)
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • MacOS
    • npm run
    • npx
    • Docker
    • Podman
    • Seatbelt
  • Windows
    • npm run
    • npx
    • Docker
  • Linux
    • npm run
    • npx
    • Docker

[gemini-code-assist]

Summary of Changes

Hello @koxkox111, 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 introduces the propagation of a prompt_id from the a2a-server to the CLI, a mechanism crucial for internal tracking purposes within Google. It enhances the Task class to manage and generate these unique identifiers based on user interactions, ensuring that subsequent tool calls within the same prompt context utilize the correct prompt_id.

Highlights

• Prompt ID Propagation: The system now propagates a prompt_id when the a2a-server calls the CLI, which is used for internal tracking purposes by Google.
• Task Class Enhancements: The Task class in a2a-server has been updated with currentPromptId and promptCount properties to manage and generate unique prompt identifiers.
• Dynamic Prompt ID Generation: A prompt_id is dynamically generated for each new user message, combining the session ID and an incrementing prompt count.
• Test Coverage: New unit tests have been added to task.test.ts to ensure the correct initialization and updating of currentPromptId and promptCount throughout the task lifecycle.

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 adds propagation of prompt_id for calls made via the a2a-server. The implementation introduces currentPromptId and promptCount properties to the Task class to manage a unique ID for each user message turn. However, this approach introduces a critical race condition. Storing the prompt_id as a mutable instance property on Task can lead to incorrect IDs being used when processing tool call results in a concurrent environment. My review includes a critical comment to address this by making the sendCompletedToolsToLlm function stateless with respect to prompt_id, ensuring correctness in concurrent scenarios.

[owenofbrien]

Thanks for fixing this!