fix(python): caching on resource loader

[pilartomas]

Signed-off-by: Tomas Pilar thomas7pilar@gmail.com

[gemini-code-assist]

Summary of Changes

Hello @pilartomas, 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 addresses a caching issue within the Python resource loaders by migrating the underlying caching library. The primary change involves replacing cachetools with async-lru to better support asynchronous operations and improve caching behavior. This update includes modifications to project dependencies, changes to the caching decorators in relevant ResourceLoader classes, and the addition of new unit tests to ensure the updated caching mechanism functions as expected.

Highlights

• Dependency Migration: The project's dependency management files, pyproject.toml and uv.lock, have been updated to remove the cachetools library and introduce async-lru as its replacement. This ensures that the project now uses the new asynchronous caching solution.
• Caching Mechanism Update: The caching decorators in both acp_sdk/server/resources.py and acp_sdk/shared/resources.py have been switched from @cachetools.func.lfu_cache to @alru_cache(). This change directly implements the new asynchronous caching mechanism for resource loading operations.
• New Unit Tests for Caching: A new unit test file, python/tests/unit/shared/test_resources.py, has been added. This file contains tests specifically designed to validate the ResourceLoader's ability to load resources and, crucially, to confirm that its caching functionality operates correctly with the new async-lru implementation.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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]

Warning

Gemini encountered an error creating the review. You can try again by commenting /gemini review.

[grahamwhiteuk]

@pilartomas this may have introduced a package clash with beeai-framework...

  × No solution found when resolving dependencies for split (python_full_version >= '3.13'):
  ╰─▶ Because only acp-sdk<=1.0.2 is available and acp-sdk==1.0.2 depends on cachetools>=6.1.0, we can conclude that acp-sdk>=1.0.2 depends on cachetools>=6.1.0.
      And because beeai-framework>=0.1.29 depends on cachetools>=5.5.2,<6.0.0 and only the following versions of beeai-framework are available:
          beeai-framework<=0.1.29
          beeai-framework==0.1.30
          beeai-framework==0.1.31
          beeai-framework==0.1.32
          beeai-framework==0.1.33
          beeai-framework==0.1.34
          beeai-framework==0.1.35
          beeai-framework==0.1.36
      we can conclude that acp-sdk>=1.0.2 and beeai-framework>=0.1.29 are incompatible.
      And because your project depends on acp-sdk>=1.0.2 and beeai-framework>=0.1.29, we can conclude that your project's requirements are unsatisfiable.

      hint: While the active Python version is 3.11, the resolution failed for other Python versions supported by your project. Consider limiting your project's supported
      Python versions using `requires-python`.

[pilartomas]

@grahamwhiteuk thanks, the bump was not necessary, reverted in https://github.com/i-am-bee/acp/releases/tag/v1.0.3

[grahamwhiteuk]

Nice one, thanks Tomas!