Creates a plugin flag to register a plugin with the adk api_server #2637
Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @igooch, 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 --plugin command-line option to the adk api_server command, enabling developers to register and utilize custom plugins directly without requiring a custom server entry point. This enhancement streamlines the process of integrating custom functionalities into the ADK API server.
Highlights
- CLI Enhancement: A new --plugin option is added to the adk api_server command, allowing users to specify multiple fully qualified paths to BasePlugin classes for registration.
- Dynamic Plugin Loading: The get_fast_api_app function now includes logic to dynamically import and instantiate BasePlugin classes provided via the new --plugin option.
- Runner Integration: Instantiated plugins are now passed to the AdkWebServer constructor, which then forwards them to the Runner instance, ensuring plugins are active within the server's operational flow.
- Comprehensive Unit Testing: New unit tests, specifically test_agent_run_with_plugin, have been added to validate the end-to-end functionality of plugin loading and execution within the API server.
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.
Code Review
This pull request introduces a valuable feature for registering plugins via the adk api_server CLI. The implementation is well-structured, and the addition of unit tests is commendable. My main feedback concerns a potential TypeError during plugin instantiation, which could affect usability for developers. I've provided a suggestion to make the instantiation more robust. I also have a minor suggestion to improve the test mocks for better maintainability.
| if plugins: | ||
| for plugin_path in plugins: | ||
| plugin_class = _load_plugin_class(plugin_path) | ||
| plugin_instances.append(plugin_class()) |
There was a problem hiding this comment.
The current implementation plugin_class() assumes that the plugin's __init__ method can be called without arguments. However, the BasePlugin class requires a name argument in its constructor. This will lead to a TypeError if a user creates a plugin that adheres to the BasePlugin interface without providing a default value for the name parameter.
To make this more robust and user-friendly, I suggest automatically using the plugin's class name as its name during instantiation. This provides a sensible default and avoids unexpected errors for users.
| plugin_instances.append(plugin_class()) | |
| plugin_instances.append(plugin_class(name=plugin_class.__name__)) |
| for plugin in plugin_manager.plugins: | ||
| if isinstance(plugin, MockPlugin): | ||
| # Create a mock InvocationContext for the callback | ||
| mock_invocation_context = MagicMock(spec=InvocationContext) | ||
| event = await plugin.on_event_callback( | ||
| invocation_context=mock_invocation_context, event=event | ||
| ) |
There was a problem hiding this comment.
The apply_plugin_on_event helper function inside the dummy_run_async mock is tightly coupled to MockPlugin because of the isinstance(plugin, MockPlugin) check. This makes the test mock less generic and harder to maintain if other types of mock plugins are introduced.
To improve this, you can make the logic more generic by iterating over all plugins and applying the on_event_callback if it exists, which more closely simulates the behavior of the actual PluginManager.
| for plugin in plugin_manager.plugins: | |
| if isinstance(plugin, MockPlugin): | |
| # Create a mock InvocationContext for the callback | |
| mock_invocation_context = MagicMock(spec=InvocationContext) | |
| event = await plugin.on_event_callback( | |
| invocation_context=mock_invocation_context, event=event | |
| ) | |
| for plugin in plugin_manager.plugins: | |
| if hasattr(plugin, "on_event_callback"): | |
| # Create a mock InvocationContext for the callback | |
| mock_invocation_context = MagicMock(spec=InvocationContext) | |
| result = await plugin.on_event_callback( | |
| invocation_context=mock_invocation_context, event=event | |
| ) | |
| if result is not None: | |
| event = result |
feat: Enable Plugin Registration via adk api_server CLI
This PR adds support for registering plugins directly via the
adk api_servercommand using a new--pluginoption.Main Logic Changes:
--plugintocli_api_serverinsrc/google/adk/cli/cli_tools_click.pyto accept multiple plugin import paths.src/google/adk/cli/fast_api.py, theget_fast_api_appfunction now dynamically loads and instantiates classes passed to the plugins argument.AdkWebServerconstructor, which in turn passes them to theRunnerinstance it creates insrc/google/adk/cli/adk_web_server.py.test_agent_run_with_plugintotests/unittests/cli/test_fast_api.pyto verify plugin loading and execution, using patching to mock plugin imports and services.adk api_servercommand.How to Use:
Fixes #2636