Fix validation error when .env file contains settings from other apps.

[oscarkey]

By default Pydantic uses extra="forbid", which raises a validation error when other apps have entries in the .env file (which is a common occurence). Instead, just ignore those settings. This is recommended by the Pydantic docs:
https://docs.pydantic.dev/2.11/concepts/pydantic_settings/#dotenv-env-support

Closes #443

[gemini-code-assist]

Summary of Changes

Hello @oscarkey, 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 resolves a validation error that occurred when the application's Pydantic settings attempted to load from a .env file containing environment variables not directly relevant to the application. By configuring Pydantic to ignore unknown fields in the .env file, the change ensures smoother operation in shared development environments where .env files might contain settings for multiple services. A new test case has been added to confirm the robustness of this fix.

Highlights

• Pydantic Settings Configuration: The TabPFNSettings class's model_config has been updated to set extra="ignore" within SettingsConfigDict. This change addresses an issue where Pydantic's default extra="forbid" behavior would cause validation errors if the .env file contained variables not explicitly defined in the TabPFNSettings model, which is common when sharing .env files across multiple applications.
• New Test Case for Robustness: A new test case, test__load_settings__env_file_contains_variables_for_other_apps__does_not_crash, has been added. This test specifically verifies that the application can successfully load its settings from a .env file that includes extraneous variables (e.g., from other applications) without encountering validation failures, confirming the fix.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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. ↩

[gemini-code-assist]

Code Review

This pull request correctly addresses a validation error when the .env file contains settings for other applications by setting extra="ignore" in the Pydantic settings. The change is simple, effective, and follows the recommended practice from the Pydantic documentation. The newly added test case properly verifies this fix. I've added a couple of minor suggestions to improve the new test code for conciseness and type safety.

[LeoGrin]

bugbot run

[LeoGrin]

LGTM!

[cursor]

✅ Bugbot reviewed your changes and found no bugs!

---