Skip to content

Conversation

@daniel-sanche
Copy link
Contributor

@daniel-sanche daniel-sanche commented Jan 13, 2026

Kokoro tests for pipelines were previously disabled until the backend supports the feature. This branch will re-enable those tests, when the backend is ready

Aslo removing index_mode, since this feature was pushed back to a future release

@product-auto-label product-auto-label bot added size: xl Pull request size is extra large. api: firestore Issues related to the googleapis/python-firestore API. labels Jan 13, 2026
@daniel-sanche daniel-sanche changed the base branch from main to pipeline-preview-public January 13, 2026 01:07
@gemini-code-assist
Copy link

Summary of Changes

Hello @daniel-sanche, 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 re-enabling and enhancing the pipeline system tests on Kokoro, alongside integrating full support for Python 3.14. A significant portion of the changes introduces new Firestore Pipeline API features, allowing for more complex and efficient data querying and transformation directly within the client libraries. These updates ensure compatibility with the latest Python versions and expand the functional capabilities of the Firestore client.

Highlights

  • Re-enabling Pipeline System Tests: Kokoro pipeline system tests, previously disabled, have been re-enabled to run when the backend is ready to support the feature.
  • Python 3.14 Support: Added comprehensive support for Python 3.14 across various configurations, including new Kokoro configurations (common, continuous, periodic-head, periodic, presubmit) and updates to noxfile.py and setup.py.
  • New Firestore Pipeline API Features: Introduced new Firestore Pipeline API capabilities, including CloneDatabase and ExecutePipeline methods, along with a rich set of pipeline expressions and stages for advanced data transformations and queries.
  • mTLS Support Enhancements: Improved mTLS support logic within Firestore Admin and main Firestore clients, including a new _use_client_cert_effective static method and refined handling of client certificate environment variables.
  • Changelog and Documentation Updates: Updated CHANGELOG.md to reflect version 2.22.0 with new features like mTLS support, Python 3.14, and read_time parameter. Documentation files (CONTRIBUTING.rst, README.rst, docs/README.rst) were also updated to reflect Python 3.14 support and provide more detailed client information.
  • Pipeline E2E System Tests: Added extensive new system tests (pipeline_e2e/*.yaml) to cover various end-to-end scenarios for the new Firestore Pipeline features, including aggregations, array operations, date/time functions, logical operations, map manipulations, mathematical functions, string operations, and vector search.

🧠 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.

Ignored Files
  • Ignored by pattern: .github/workflows/** (4)
    • .github/workflows/lint.yml
    • .github/workflows/mypy.yml
    • .github/workflows/system_emulated.yml
    • .github/workflows/unittest.yml
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.

Copy link

@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 re-enables pipeline system tests on Kokoro by removing the IS_KOKORO_TEST flag and its usage across the test suite. The changes are straightforward and correctly remove the conditional logic that was previously skipping these tests. My review includes a couple of suggestions to clean up unused imports in the database fixtures for both test_system.py and test_system_async.py, which became redundant after the test-skipping logic was removed. This will help improve code maintainability.

@product-auto-label product-auto-label bot added size: s Pull request size is small. and removed size: xl Pull request size is extra large. labels Jan 13, 2026
@product-auto-label product-auto-label bot added size: m Pull request size is medium. and removed size: s Pull request size is small. labels Jan 13, 2026
@daniel-sanche daniel-sanche marked this pull request as ready for review January 13, 2026 17:08
@daniel-sanche daniel-sanche requested review from a team as code owners January 13, 2026 17:08
@daniel-sanche daniel-sanche assigned bhshkh and unassigned pcostell Jan 13, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

api: firestore Issues related to the googleapis/python-firestore API. size: m Pull request size is medium.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants