-
Notifications
You must be signed in to change notification settings - Fork 115
[Follow Up Questions] Re-enable follow up questions module #5886
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: master
Are you sure you want to change the base?
Conversation
Summary of ChangesHello @gmechali, 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 focuses on reactivating the 'follow up questions' module by enabling its corresponding feature flag. The decision to re-enable comes after assessing the system's capacity to handle the current user load, addressing previous concerns related to excessive crawling. While a temporary disablement mechanism is in place for potential user spikes, a long-term solution for managing Gemini quota usage is being actively explored. Highlights
🧠 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 AssistThe 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
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 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
|
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 re-enables the follow_up_questions_ga feature flag. While the change is simple, it re-introduces a known risk. My review highlights that enabling this feature without first implementing a fix for the web crawler issue (which caused a previous incident) could lead to Gemini quota exhaustion. I have added a high-severity comment on the configuration change, recommending that the underlying issue be addressed before deploying this change to production.
| { | ||
| "name": "follow_up_questions_ga", | ||
| "enabled": false, | ||
| "enabled": true, |
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.
Enabling this feature flag re-introduces a risk that led to a previous incident. The feature generates hyperlinks that web crawlers can follow, potentially causing excessive calls to the Gemini API and exhausting your quota.
The pull request description mentions that a more permanent fix has been discussed. To prevent a recurrence of the incident, it is strongly recommended to implement this fix before enabling the feature in production. A robust solution would be to add a rel=\"nofollow\" attribute to the generated <a> tags in static/js/apps/explore/follow_up_questions.tsx to instruct crawlers not to follow these links.
This is a safe move as we know our current quota can handle our current user load.
We had to disable it previously due to an incident where hyperlinks gave crawlers far more explore pages to crawl.
If we have a very high user spike, we can easily turn off this feature temporarily. We have discussed a more permanent fix to address the possibility of using too much Gemini quota.