-
Notifications
You must be signed in to change notification settings - Fork 8k
Switch utility calls to use the gemini-2.5-flash-lite model #5193
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
Conversation
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 @mrcabbage972, 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 primarily focuses on optimizing the application's use of Google's Gemini models by switching certain internal utilities from the gemini-2.5-flash
model to the gemini-2.5-flash-lite
model. This change aims to leverage a potentially more efficient or cost-effective model for tasks such as code correction and tool output summarization.
Highlights
- Core Model Configuration: A minor formatting adjustment was made in
packages/core/src/config/models.ts
by adding a blank line. This file defines the various Gemini model constants. - Edit Corrector Model Update: The
editCorrector
utility, located inpackages/core/src/utils/editCorrector.ts
, has been updated to useDEFAULT_GEMINI_FLASH_LITE_MODEL
instead ofDEFAULT_GEMINI_FLASH_MODEL
for itsEditModel
constant. This means the code correction functionality will now leverage the 'flash-lite' model. - Summarizer Model Update: The
summarizer
utility, specifically thesummarizeToolOutput
function inpackages/core/src/utils/summarizer.ts
, now utilizesDEFAULT_GEMINI_FLASH_LITE_MODEL
for its operations, replacing the previousDEFAULT_GEMINI_FLASH_MODEL
. This change applies the 'flash-lite' model to the tool output summarization process.
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 or fill out our survey to provide feedback.
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 switches the model from gemini-2.5-flash
to gemini-2.5-flash-lite
in editCorrector
and summarizer
. The changes are straightforward. However, the switch appears to be incomplete, as some fallback logic in client.ts
still references the old gemini-2.5-flash
model. I've left a comment with more details. Addressing this will ensure consistent model usage across the application.
Code Coverage Summary
CLI Package - Full Text Report
Core Package - Full Text Report
For detailed HTML reports, please see the 'coverage-reports-22.x-ubuntu-latest' artifact from the main CI run. |
@@ -7,4 +7,5 @@ | |||
export const DEFAULT_GEMINI_MODEL = 'gemini-2.5-pro'; | |||
export const DEFAULT_GEMINI_FLASH_MODEL = 'gemini-2.5-flash'; | |||
export const DEFAULT_GEMINI_FLASH_LITE_MODEL = 'gemini-2.5-flash-lite'; | |||
|
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.
remove?
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
…emini#5193) Co-authored-by: Anjali Sridhar <[email protected]>
TLDR
Switching the following utility calls to use the gemini-2.5-flash-lite model:
Dive Deeper
The goal was to switch utility calls to use a cheaper model.
An evaluation of the change on the full SWE-bench Lite dataset (300 instances) has shown no degradation versus the baseline.
Reviewer Test Plan
Testing Matrix
Linked issues / bugs