fix: use session_service and memory_service from invocation context #2890
Conversation
Signed-off-by: Eitan Yarmush <[email protected]>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @EItanya, 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 an issue where the AgentTool was hardcoding the use of in-memory session and memory services. The changes ensure that these services are now correctly retrieved from the invocation context, aligning with the intended design for service provision.
Highlights
- Service Resolution: The AgentTool now correctly resolves session_service and memory_service from the tool_context._invocation_context instead of instantiating InMemorySessionService and InMemoryMemoryService directly.
- Code Clean-up: Removed the unnecessary import of InMemorySessionService and standardized string literal quoting from single to double quotes across the file.
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. ↩
|
Response from ADK Triaging Agent Hello @EItanya, thank you for creating this PR! To help us review this PR more efficiently, could you please provide the following information based on our contribution guidelines:
You can find more details in our contribution guidelines. Thank you! |
There was a problem hiding this comment.
Code Review
This pull request refactors AgentTool to correctly use the session_service and memory_service from the invocation context, rather than instantiating its own InMemory versions. This is a significant improvement that ensures the tool operates within the correct application context. The changes are well-aligned with the pull request's goal. I've added one comment with a suggestion for a future refactoring to improve encapsulation, but it's not a blocker for this change. The rest of the changes are stylistic and improve code consistency.
| session_service=tool_context._invocation_context.session_service, | ||
| memory_service=tool_context._invocation_context.memory_service, |
There was a problem hiding this comment.
While this change correctly sources the services from the invocation context, it relies on accessing the protected member _invocation_context. This pattern appears elsewhere in the codebase, but it breaks encapsulation and makes the public API of ToolContext less clear.
For better maintainability and a cleaner design, consider exposing these services as public properties on ToolContext. This would be a good opportunity for future refactoring.
Example of what could be added to ToolContext:
@property
def session_service(self) -> BaseSessionService:
return self._invocation_context.session_service
@property
def memory_service(self) -> Optional[BaseMemoryService]:
return self._invocation_context.memory_serviceWith this change, the code here would become tool_context.session_service and tool_context.memory_service, which is much cleaner.
| @@ -53,10 +53,10 @@ def __init__(self, agent: BaseAgent, skip_summarization: bool = False): | |||
|
|
|||
| super().__init__(name=agent.name, description=agent.description) | |||
|
|
|||
| @model_validator(mode='before') | |||
| @model_validator(mode="before") | |||
There was a problem hiding this comment.
you might want to revert the style changes (unless they are coming from ruff and not your personal settings :)
Currently when creating an AgentTool it automatically decides to use the
InMemorySessionService, however, this should come from the incocation context.