gemini-code-assist[bot] commented on PR #37166: URL: https://github.com/apache/beam/pull/37166#issuecomment-3682883684
## Summary of Changes Hello @EgbertW, I'm Gemini Code Assist[^1]! 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 significantly enhances the error handling and retry mechanisms within Apache Beam's `ElasticsearchIO` connector. It addresses a critical flaw where `ResponseException`s, often indicative of transient server or proxy issues, were not correctly identified for retries. Furthermore, it rectifies an inconsistency where the `throwWriteErrors` configuration was bypassed after retry attempts were exhausted, ensuring that users' preferences for error propagation are consistently honored. These improvements lead to a more resilient and predictable `ElasticsearchIO` behavior, especially in environments prone to temporary network or service disruptions. ### Highlights * **Corrected ResponseException Handling**: Modified `ElasticsearchIO` to correctly identify `ResponseException` as retryable by checking the exception directly (`t instanceof ResponseException`) rather than its cause (`t.getCause() instanceof ResponseException`). This ensures server-side errors (e.g., 504 Gateway Timeout) are properly retried. * **Honoring throwWriteErrors with Retries**: Ensured that the `throwWriteErrors` configuration is respected even after all retry attempts fail. Previously, exceptions were always thrown; now, if `throwWriteErrors` is `false`, the error is routed to the `FAILED_WRITES` output tag instead of being re-thrown. * **Enhanced Test Coverage for Retries**: Added a new test case, `testWriteWithClientResponseExceptionIsRetried`, to `ElasticsearchIOTest` (for both ES 8 and 9) that uses a mocked webserver to simulate HTTP 500 errors, thoroughly validating the retry logic for `ResponseException`s. * **New Mock Server Utility**: Introduced `ElasticsearchIOTestUtils.AlwaysFailServer`, a utility class that creates a simple HTTP server to return specified error codes, facilitating robust testing of error handling scenarios. 🧠**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](https://codeassist.google/code-review/login) to enable Memory in your admin console.** <details> <summary><b>Using Gemini Code Assist</b></summary> <br> The full guide for Gemini Code Assist can be found on our [documentation page](https://developers.google.com/gemini-code-assist/docs/review-github-code), here are some quick tips. <b>Invoking Gemini</b> 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. <b>Customization</b> 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](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). <b>Limitations & Feedback</b> Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: 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](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG). <b>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](https://cloud.google.com/products/gemini/code-assist).</b> </details> [^1]: Review the [Privacy Notices](https://policies.google.com/privacy), [Generative AI Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of Service](https://policies.google.com/terms), and learn how to configure Gemini Code Assist in GitHub [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). Gemini can make mistakes, so double check it and [use code with caution](https://support.google.com/legal/answer/13505487). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
