-
Notifications
You must be signed in to change notification settings - Fork 1.8k
feat(agent-tool): support propagating runner plugins #2779
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @davidkl97, 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 a new feature that allows the AgentTool to propagate plugins from its parent runner context to the internal Runner instance it creates. This provides greater flexibility by enabling the AgentTool to leverage plugins defined in the broader application environment.
Highlights
- AgentTool Configuration: Added a new boolean parameter "include_plugins" to the AgentTool constructor, defaulting to "False". This parameter controls whether plugins from the parent context should be propagated.
- Plugin Propagation Logic: Modified the "run_async" method within AgentTool to conditionally retrieve plugins from the tool_context's plugin manager and pass them to the Runner instance if "include_plugins" is set to "True".
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
-
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. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request introduces the capability for an AgentTool
to propagate plugins from its parent runner's context to the sub-runner it creates. The implementation is straightforward, adding an include_plugins
flag to control this behavior. My review includes a correction for a minor typo in the documentation and a suggestion to improve encapsulation by avoiding direct access to a protected member, which would enhance long-term maintainability.
@@ -125,13 +127,15 @@ async def run_async( | |||
role='user', | |||
parts=[types.Part.from_text(text=args['request'])], | |||
) | |||
plugins = tool_context._invocation_context.plugin_manager.plugins if self.include_plugins else None |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Accessing the protected member _invocation_context
directly from tool_context
violates encapsulation and creates tight coupling. While this pattern exists elsewhere in the method, consider exposing plugin_manager
via a public property on ToolContext
to improve maintainability and adhere to the Law of Demeter.
Response from ADK Triaging Agent Hello @davidkl97, thank you for your contribution! Before we can review your PR, please address the following items based on our contribution guidelines:
This information is necessary to move forward with the review process. Thanks! |
52a0721
to
25b8dd6
Compare
Response from ADK Triaging Agent Hello @davidkl97, thank you for your contribution! I see you have already signed the CLA and associated an issue with this PR. That's great! To help us review your PR, could you please add a Thank you! |
Response from ADK Triaging Agent Hello @davidkl97, thank you for your contribution! The testing plan in your PR is a bit brief. Could you please elaborate on how you tested the new |
25b8dd6
to
3483d8d
Compare
src/google/adk/tools/agent_tool.py
Outdated
""" | ||
|
||
def __init__(self, agent: BaseAgent, skip_summarization: bool = False): | ||
def __init__(self, agent: BaseAgent, skip_summarization: bool = False, include_plugins: bool = False): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's add *, to make all future parameters keyword-only.
3483d8d
to
d8b2504
Compare
Fixes #2780
testing plan
not available as is doesn't introduce new functionality