feat: update beeai-framework

[Tomas2D]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @Tomas2D, 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 focuses on a comprehensive update of several Python package dependencies, including core AI frameworks, instrumentation libraries, and underlying SDKs. The updates ensure that the project leverages the latest features, bug fixes, and security improvements from these upstream libraries. Additionally, new dependencies have been introduced for specific packages to support enhanced functionalities.

Highlights

• Dependency Updates: Updated beeai-framework from 0.1.76 to 0.1.77 in pyproject.toml and uv.lock.
• Dependency Updates: Updated openinference-instrumentation-beeai from 0.1.14 to 0.1.15 in pyproject.toml and uv.lock.
• Dependency Updates: Updated a2a-sdk from 0.3.9 to 0.3.21 in uv.lock.
• Dependency Updates and Additions: Updated agentstack-sdk from 0.4.3 to 0.6.1 in uv.lock, and added new dependencies async-lru, authlib, and cachetools to it.
• Dependency Updates: Updated cachetools from 5.5.2 to 7.0.1 in uv.lock.
• Dependency Updates and Changes: Updated google-auth from 2.40.3 to 2.48.0 in uv.lock, and changed its dependency from cachetools to cryptography.
• New Package: Added authlib version 1.6.7 as a new package in uv.lock.

🧠 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

• pyproject.toml
  • Updated beeai-framework dependency version.
  • Updated openinference-instrumentation-beeai dependency version.
• uv.lock
  • Updated a2a-sdk package version.
  • Updated agentstack-sdk package version and added async-lru, authlib, cachetools as new dependencies.
  • Added authlib as a new package.
  • Updated beeai-framework package version.
  • Updated cachetools package version.
  • Updated google-auth package version and changed its dependency from cachetools to cryptography.
  • Updated openinference-instrumentation-beeai package version.

Activity

• No human activity has been recorded on this pull request yet.

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 beeai-framework and openinference-instrumentation-beeai dependencies, along with their transitive dependencies in the uv.lock file. The changes are straightforward version bumps. I've identified two areas for improvement: one regarding dependency specification best practices in pyproject.toml to make the project more lightweight, and a potential issue with the generated uv.lock file showing future timestamps for package uploads, which should be investigated.

[gemini-code-assist]

The upload-time metadata in the lock file for several packages shows future dates (e.g., 2025-12-12T17:05:31.755Z). This is highly unusual and could indicate an issue with the system clock on the machine where uv lock was run, or a potential bug in the uv tool itself. While it might not break the build, it's a significant anomaly that should be investigated to ensure the integrity of the dependency locking process and the build environment.

[gemini-code-assist]

Using [all] for beeai-framework pulls in a large number of dependencies, many of which may not be used by this starter project. This increases the installation size, time, and the potential attack surface from vulnerabilities in unused packages. Consider specifying only the extras that are actually required by the examples in this project. For instance, if only a2a and mcp features are demonstrated, you might use something like beeai-framework[a2a,mcp]>=0.1.77,<0.2.0. This would make the project more lightweight and secure.