Skip to content

Conversation

@valbeat
Copy link
Owner

@valbeat valbeat commented Aug 8, 2025

Summary

  • Add @phpstan-assert-if-false annotations to isOk() and isErr() methods
  • Use conditional return types for unwrap(), unwrapErr(), and unwrapOr() methods
  • Improve type inference and reduce PHPStan false positives

Changes

This PR enhances the PHPStan type annotations in the Result interface to provide better type safety:

1. Assertion Annotations

  • isOk(): Now asserts that $this is Err<E> when false
  • isErr(): Now asserts that $this is Ok<T> when false

2. Conditional Return Types

  • unwrap(): @return ($this is Ok<T> ? T : never)
  • unwrapErr(): @return ($this is Err<E> ? E : never)
  • unwrapOr(): @return ($this is Ok<T> ? T : U)

Benefits

  • Better type inference in conditional blocks
  • Reduced need for PHPStan ignore patterns
  • More closely aligned with Rust's Result type safety
  • Improved developer experience with more accurate type information

Test Plan

  • PHPStan analysis passes without errors
  • All existing functionality remains unchanged
  • Type annotations are properly recognized by PHPStan

Summary by CodeRabbit

  • Refactor
    • Improved type annotations for enhanced static analysis and more precise type checking in method documentation. No changes to runtime behavior.

- Add @phpstan-assert-if-false annotations to isOk() and isErr()
- Use conditional return types for unwrap(), unwrapErr(), and unwrapOr()
- These improvements enable better type inference and reduce false positives

This change makes the Result type more closely aligned with Rust's type safety
@valbeat valbeat self-assigned this Aug 8, 2025
@coderabbitai
Copy link

coderabbitai bot commented Aug 8, 2025

Note

Other AI code review bot(s) detected

CodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review.

Caution

Review failed

The pull request is closed.

Walkthrough

The Result interface was updated to include more precise PHPStan type assertions and conditional return type annotations for several methods. These changes enhance static analysis and type safety but do not affect runtime behavior or implementation.

Changes

Cohort / File(s) Change Summary
Result Interface Type Annotations
src/Result.php
Added PHPStan type assertions to isOk() and isErr(). Updated return type annotations for unwrap(), unwrapErr(), and unwrapOr() to use conditional types for improved static analysis.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Poem

In fields of types, a rabbit hops,
With PHPStan’s lens, it never stops.
"Is it Ok, or is it Err?"
Now the answer’s crystal clear!
With annotations sharp and neat,
Static checks are quite a treat.
🐇✨

Note

🔌 MCP (Model Context Protocol) integration is now available in Early Access!

Pro users can now connect to remote MCP servers under the Integrations page to get reviews and chat conversations that understand additional development context.


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 0676115 and 66a3a4a.

📒 Files selected for processing (1)
  • src/Result.php (4 hunks)
✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch feat/improve-type-annotations

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai generate unit tests to generate unit tests for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

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.

Summary of Changes

Hello @valbeat, 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!

I've enhanced the "Result" interface's PHPStan type annotations to significantly improve type safety and reduce false positives. This change refines how PHPStan understands the state of "Result" objects, leading to more accurate type inference and a better developer experience without altering any runtime behavior.

Highlights

  • Type Assertion Improvements: I've added "@phpstan-assert-if-false" annotations to the "isOk()" and "isErr()" methods. This allows PHPStan to correctly infer the type of the Result object when these methods return "false", specifically asserting "Err" when "isOk()" is false, and "Ok" when "isErr()" is false.
  • Conditional Return Types: I've updated the "unwrap()", "unwrapErr()", and "unwrapOr()" methods to use conditional return types. This provides more precise type information based on whether the Result is Ok or Err, aligning more closely with Rust's Result type safety and reducing the need for manual type casting or "@phpstan-ignore" directives.
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 or fill out our survey to provide feedback.

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.

@valbeat valbeat marked this pull request as ready for review August 8, 2025 05:07
Copilot AI review requested due to automatic review settings August 8, 2025 05:07
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 significantly improves the PHPStan type annotations for the Result interface. The use of @phpstan-assert-if-false on isOk() and isErr(), and the introduction of conditional return types for unwrap(), unwrapErr(), and unwrapOr() are excellent changes that will enhance type safety and improve the developer experience by providing more accurate type inference to static analysis tools.

The changes are correct and well-implemented. To make the interface even more robust and consistent, I'd suggest applying similar conditional return types to other methods in a follow-up effort. For instance:

  • unwrapOrElse(callable $fn) could be annotated with @return ($this is Ok<T> ? T : U).
  • match(callable $ok_fn, callable $err_fn) could be annotated with @return ($this is Ok<T> ? U : V).

Additionally, while reviewing, I noticed that the docblock for mapOr() specifies a return type of T|U, but the implementations in both Ok and Err classes always return a value of type U. Correcting this to @return U would improve the accuracy of the type hint.

Overall, this is a valuable contribution that strengthens the library's type safety. Great work!

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR enhances the PHPStan type annotations for the Result interface to provide better type safety and reduce false positives. The changes focus on improving type inference through assertion annotations and conditional return types.

  • Adds assertion annotations to isOk() and isErr() methods for better type narrowing
  • Implements conditional return types for unwrap methods to improve type inference
  • Aligns PHP implementation more closely with Rust's Result type safety patterns

@valbeat valbeat merged commit bb84cf1 into main Aug 8, 2025
2 of 3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants