keyv - feat: (breaking) moving to boolean return on set

[jaredwray]

Please check if the PR fulfills these requirements

• Followed the Contributing and Code of Conduct guidelines.
• Tests for the changes have been added (for bug fixes/features) with 100% code coverage.

What kind of change does this PR introduce? (Bug fix, feature, docs update, ...)
keyv - feat: (breaking) moving to boolean return on set

[gemini-code-assist]

Summary of Changes

Hello, 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 introduces a significant breaking change by standardizing the return type of the set method across all Keyv storage adapters. The primary goal is to enhance consistency and provide explicit feedback on the success or failure of a set operation, moving from ambiguous return types to a clear Promise<boolean>. This change improves the predictability and error handling capabilities for consumers of the Keyv library.

Highlights

• Breaking Change: Standardized set method return type: The set method across all Keyv storage adapters now consistently returns a Promise<boolean>, indicating the success or failure of the operation. Previously, it returned any or Promise<void> depending on the adapter.
• Improved Error Handling: All set implementations have been updated to return true on successful data storage and false if an error occurs during the operation, providing clearer feedback.
• New Build Script: A new build:sequential script was added to package.json to allow for sequential building of packages, which can be useful in certain CI/CD environments or for debugging build issues.
• Type Definition Updates: The KeyvStorageAdapter interface and specific storage type definitions were updated to reflect the new Promise<boolean> return type for the set method, including the introduction of a SetOutput type in the Etcd storage.

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.

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. ↩

[gemini-code-assist]

Code Review

This pull request standardizes the set method across multiple Keyv storage adapters (Dynamo, Etcd, Memcache, Mongo, MySQL, Postgres, Redis, SQLite, Valkey) to consistently return a Promise<boolean>, indicating the success or failure of the operation. Corresponding type definitions and test assertions were updated. A new build:sequential script was also added. The review comments suggest an improvement: the catch blocks in the set methods should emit errors for better diagnostics before returning false to maintain consistency and provide clearer feedback to users.

[chatgpt-codex-connector]

💡 Codex Review

keyv/storage/mongo/src/index.ts

Line 391 in e1bb165

return settled.map((result) => result.status === "fulfilled");

Preserve GridFS setMany failures in returned booleans

In the GridFS branch, setMany now derives success from Promise.allSettled(...).status === "fulfilled", but set() was changed to catch errors and return false instead of rejecting. That means a failed write (for example a stream error that returns false) is still treated as fulfilled and reported as true, so callers get false-positive success for entries that were not stored. This breaks per-entry result accuracy and can silently hide data-loss conditions in batch writes.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.88%. Comparing base (27e2287) to head (95f4f19).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1904   +/-   ##
=======================================
  Coverage   99.88%   99.88%           
=======================================
  Files          37       37           
  Lines        3420     3438   +18     
  Branches      560      562    +2     
=======================================
+ Hits         3416     3434   +18     
  Misses          4        4           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.