Move dataset hydration into Python config package.#15
Conversation
…ared `dataset_config_python.hydrate` module
Summary of ChangesHello, 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 centralizes the logic for converting configuration dictionaries into Inspect AI objects by introducing a new 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. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request refactors the configuration hydration logic by moving core helper functions—including dataset building, MCP server creation, and skill tool generation—from dash_evals into the shared dataset_config_python package. Documentation and dependencies are updated to reflect this architectural shift and the planned deprecation of the Dart configuration package. Review feedback suggests minor corrections for capitalization and spelling consistency, and recommends removing redundant tests in dash_evals that now overlap with the new test suite in dataset_config_python.
| # Dataset Config management library - Dart implementation | ||
|
|
||
| > [!CAUTION] | ||
| > This library will be deprecated eventually. It almost entirely overlaps with the Python implementation, and the python lib should be considered the canonical package. No newline at end of file |
There was a problem hiding this comment.
For consistency in capitalization, could you please change python lib to Python lib?
| > This library will be deprecated eventually. It almost entirely overlaps with the Python implementation, and the python lib should be considered the canonical package. | |
| > This library will be deprecated eventually. It almost entirely overlaps with the Python implementation, and the Python lib should be considered the canonical package. |
| An Inspect AI dataset object. | ||
|
|
||
| Raises: | ||
| ValueError: If the dataset format is unrecognised or required fields |
There was a problem hiding this comment.
There's a small spelling inconsistency here. To align with the American English spelling used elsewhere in the codebase, please change unrecognised to unrecognized.
| ValueError: If the dataset format is unrecognised or required fields | |
| ValueError: If the dataset format is unrecognized or required fields |
| } | ||
| mock_ds = MagicMock(name="json_dataset_result") | ||
| with patch("dash_evals.runner.json_runner.json_dataset", return_value=mock_ds) as mock_fn: | ||
| with patch("dataset_config_python.hydrate.json_dataset", return_value=mock_ds) as mock_fn: |
There was a problem hiding this comment.
These tests for _build_dataset appear to be redundant. Since the _build_dataset function was moved to the dataset_config_python package, its tests have also been correctly added in the new packages/dataset_config_python/tests/test_hydrate.py file.
To avoid test duplication and future maintenance issues, please consider removing the TestBuildDataset* classes from this file, as they are now testing an imported function whose source is tested elsewhere.
…kage dependencies to CI workflows
1 participant
…ared
dataset_config_python.hydratemoduleIssue Link:
What is the link to the issue this cherry-pick is addressing?
https://github.com/flutter/flutter/issues/< Replace with issue link here >