-
Notifications
You must be signed in to change notification settings - Fork 991
feat(ai): Add thinking levels parameter #9424
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: main
Are you sure you want to change the base?
Conversation
🦋 Changeset detectedLatest commit: 87464b7 The changes in this PR will be included in the next version bump. This PR includes changesets to release 2 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
Summary of ChangesHello @hsubox76, 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 enhances the AI model configuration by introducing a Highlights
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
|
Changeset File Check ✅
|
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 introduces the thinkingLevel parameter to the thinkingConfig, providing users with presets to control the model's thinking process. The changes include updates to the ThinkingConfig interface, new type definitions for ThinkingLevel, and comprehensive documentation updates. A key addition is the client-side validation that prevents thinkingLevel and thinkingBudget from being set simultaneously, which is a great way to prevent invalid configurations. The associated test case for this validation is also well-implemented. Overall, the changes are solid. I have one minor suggestion to improve the readability of the validation logic.
| function validateGenerationConfig(generationConfig: GenerationConfig): void { | ||
| if ( | ||
| // != allows for null and undefined. 0 is considered "set" by the model | ||
| generationConfig.thinkingConfig?.thinkingBudget != null && | ||
| generationConfig.thinkingConfig.thinkingLevel | ||
| ) { | ||
| throw new AIError( | ||
| AIErrorCode.UNSUPPORTED, | ||
| `Cannot set both thinkingBudget and thinkingLevel in a config.` | ||
| ); | ||
| } | ||
| } |
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.
While the current logic is correct due to && short-circuiting, it's a bit subtle. Accessing generationConfig.thinkingConfig.thinkingLevel could be misinterpreted as unsafe if one overlooks the short-circuiting behavior. Refactoring to first check for thinkingConfig's existence improves readability and maintainability.
| function validateGenerationConfig(generationConfig: GenerationConfig): void { | |
| if ( | |
| // != allows for null and undefined. 0 is considered "set" by the model | |
| generationConfig.thinkingConfig?.thinkingBudget != null && | |
| generationConfig.thinkingConfig.thinkingLevel | |
| ) { | |
| throw new AIError( | |
| AIErrorCode.UNSUPPORTED, | |
| `Cannot set both thinkingBudget and thinkingLevel in a config.` | |
| ); | |
| } | |
| } | |
| function validateGenerationConfig(generationConfig: GenerationConfig): void { | |
| const { thinkingConfig } = generationConfig; | |
| if ( | |
| thinkingConfig && | |
| // != allows for null and undefined. 0 is considered "set" by the model | |
| thinkingConfig.thinkingBudget != null && | |
| thinkingConfig.thinkingLevel | |
| ) { | |
| throw new AIError( | |
| AIErrorCode.UNSUPPORTED, | |
| `Cannot set both thinkingBudget and thinkingLevel in a config.` | |
| ); | |
| } | |
| } |
Size Report 1Affected Products
Test Logs |
Size Analysis Report 1Affected Products
Test Logs |
Add thinking levels feature.
API proposal (internal): https://docs.google.com/document/d/16cdWurhdLDuNIDj0eJWNnL00any0tL_DjI-lAg7miP8/edit?tab=t.0
Added the param, plus an error if both thinkingLevel and thinkingBudget are set. This validation function may be used in the future to validate other common config issues.
Docs notes: