Skip to content

Conversation

@eliasecchig
Copy link
Collaborator

Summary

  • Restrict session type selection for cloud_run deployment to only adk_base and agentic_rag agents
  • Other agents now default to in_memory sessions when using cloud_run
  • Show warning if user explicitly specifies a non-in_memory session type for unsupported agents

Changes

  • Added session_type_supported_agents tuple to define which agents support session type selection
  • Restructured cloud_run session type logic to check agent eligibility
  • Added warning message for users who specify session type on unsupported agents

Test plan

  • Tested adk_base with --session-type cloud_sql → works correctly
  • Tested agentic_rag with --session-type cloud_sql → works correctly
  • Tested adk_live with --session-type cloud_sql → shows warning, uses in_memory
  • Tested langgraph_base with --session-type cloud_sql → shows warning, uses in_memory

Limit session type selection for cloud_run deployment to only adk_base
and agentic_rag agents. Other agents now default to in_memory sessions
with a warning if the user explicitly specifies a different session type.
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @eliasecchig, 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 refines the session type selection mechanism for cloud_run deployments within the agent creation CLI. It ensures that only designated agents (adk_base and agentic_rag) can utilize advanced session types, while all other agents will automatically default to in_memory sessions. This change also introduces a user-friendly warning system to guide users who attempt to configure unsupported session types, thereby enhancing clarity and preventing potential misconfigurations during deployment.

Highlights

  • Session Type Restriction: Restricted session type selection for cloud_run deployments to only adk_base and agentic_rag agents.
  • Default Session Type: Agents other than adk_base and agentic_rag will now default to in_memory sessions when deployed to cloud_run.
  • User Warning: A warning message is now displayed if a user explicitly specifies a non-in_memory session type for agents that do not support it.

🧠 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.

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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a 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 effectively restricts session type selection for cloud_run deployments to specific agents, defaulting to in-memory sessions for others and providing a helpful warning. The implementation is clear and correct. My review includes suggestions to improve maintainability by refactoring a hardcoded list into a module-level constant and to enhance robustness by adding unit tests for the new logic.

requires_session = config.get("settings", {}).get("requires_session", False)

# Session type selection is only available for these agents on cloud_run
session_type_supported_agents = ("adk_base", "agentic_rag")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better maintainability and to follow common Python conventions for constants, consider defining this as a module-level constant (e.g., SESSION_TYPE_SUPPORTED_AGENTS) at the top of the file. This makes it easier to find and modify the list of supported agents in the future.

@eliasecchig eliasecchig merged commit 9dfe266 into main Dec 22, 2025
32 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant