fix(server,sdk): a2a security schemes in agent card#1785
Conversation
Summary of ChangesHello @jezekra1, 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 refactors and standardizes the declaration of authentication security schemes within the AgentStack server and SDK, particularly for agent cards. It introduces a new Highlights
🧠 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. Using Gemini Code AssistThe 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
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 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
|
There was a problem hiding this comment.
Code Review
This pull request refactors authentication handling in the SDK to allow authentication backends to modify the agent card's security schemes, which is a solid architectural improvement. It correctly introduces an abstract base class for this purpose. However, there is a critical flaw in how the proxy server combines its own security requirements with those of the upstream agent. The current implementation incorrectly requires clients to authenticate with both the proxy and the agent simultaneously, which defeats the purpose of a proxy. I've provided a detailed comment and a code suggestion to rectify this by ensuring the proxy advertises its own authentication schemes, replacing the agent's.
76023c3 to
7ee0fce
Compare
7ee0fce to
2d46252
Compare
Signed-off-by: Radek Ježek <radek.jezek@ibm.com>
2d46252 to
c6af842
Compare
Summary
Add platform proxy auth schemes to agent card schemes:
Linked Issues
Documentation
If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.