Skip to content

feat(ai): implicit caching feature#9462

Merged
hsubox76 merged 4 commits intomainfrom
ch-implicit-caching
Jan 29, 2026
Merged

feat(ai): implicit caching feature#9462
hsubox76 merged 4 commits intomainfrom
ch-implicit-caching

Conversation

@hsubox76
Copy link
Contributor

@hsubox76 hsubox76 commented Jan 21, 2026

API proposal (internal link): go/ai-logic-implicit-caching

Copied docs comments from API proposal.

This provides two more params on UsageMetadata that contain data related to any usage of the implicit caching feature.

@changeset-bot
Copy link

changeset-bot bot commented Jan 21, 2026 •
edited
Loading

🦋 Changeset detected

Latest commit: 107ba25

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 2 packages
Name Type
@firebase/ai Minor
firebase Minor

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

@github-actions
Copy link
Contributor

github-actions bot commented Jan 21, 2026

Vertex AI Mock Responses Check ⚠️

A newer major version of the mock responses for Vertex AI unit tests is available. update_vertexai_responses.sh should be updated to clone the latest version of the responses: v16.0

@gemini-code-assist
Copy link
Contributor

gemini-code-assist bot commented Jan 21, 2026

Summary of Changes

Hello @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 UsageMetadata interface within the AI module by incorporating new metrics related to an implicit caching feature. The additions of cachedContentTokenCount and cacheTokensDetails will allow developers to gain a deeper understanding of how the caching mechanism is being utilized, providing granular data on cached content by token count and modality. This improvement aims to offer better observability and facilitate optimization of AI model interactions.

Highlights

  • New Usage Metadata Fields: Introduced two new optional fields, cachedContentTokenCount and cacheTokensDetails, to the UsageMetadata interface. These fields provide insights into the usage of the implicit caching feature.
  • Documentation Updates: Updated API review files and devsite documentation to reflect the new UsageMetadata fields, including their descriptions and TypeScript signatures.
  • Changelog Entry: Added a changeset entry indicating a minor version bump for @firebase/ai due to these new feature additions.

🧠 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. ↩

@github-actions
Copy link
Contributor

github-actions bot commented Jan 21, 2026 •
edited
Loading

Changeset File Check ✅

  • No modified packages are missing from the changeset file.
  • No changeset formatting errors detected.

gemini-code-assist[bot]
gemini-code-assist bot reviewed Jan 21, 2026
View reviewed changes
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 introduces an implicit caching feature by adding two new optional parameters, cachedContentTokenCount and cacheTokensDetails, to the UsageMetadata interface. The changes are consistently applied across the type definitions, API documentation, and a new changeset file. My review focuses on the clarity and correctness of the new API surface. I've identified a minor ambiguity in the documentation for cachedContentTokenCount that could be misleading for developers.

@hsubox76 hsubox76 marked this pull request as ready for review January 21, 2026 19:22
@hsubox76 hsubox76 requested review from a team as code owners January 21, 2026 19:22
rachelsaunders
rachelsaunders requested changes Jan 26, 2026
View reviewed changes
hsubox76 and others added 2 commits January 26, 2026 09:50
@hsubox76 @rachelsaunders
Update packages/ai/src/types/responses.ts
c72bba5 
Co-authored-by: rachelsaunders <52258509+rachelsaunders@users.noreply.github.com>
@hsubox76
update docs
107ba25
@hsubox76 hsubox76 merged commit 2e74329 into main Jan 29, 2026
40 of 44 checks passed
@hsubox76 hsubox76 deleted the ch-implicit-caching branch January 29, 2026 19:22
@google-oss-bot google-oss-bot mentioned this pull request Feb 3, 2026
Merged
maneesht pushed a commit that referenced this pull request Feb 6, 2026
@hsubox76 @maneesht
feat(ai): implicit caching feature (#9462)
6739726
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@DellaBitta DellaBitta DellaBitta approved these changes

@rachelsaunders rachelsaunders rachelsaunders approved these changes

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@hsubox76 @DellaBitta @rachelsaunders