-
Notifications
You must be signed in to change notification settings - Fork 9.3k
fix(web-fetch): respect Content-Type header in fallback mechanism #11284
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Summary of ChangesHello @abhipatel12, 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 an issue in the Highlights
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. 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
|
There was a problem hiding this 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 correctly modifies the WebFetchTool's fallback mechanism to respect the Content-Type header, preventing the corruption of non-HTML data. The added tests effectively validate this new behavior. I've identified one high-severity issue: the Content-Type check is case-sensitive, which violates the HTTP specification. I've provided a suggestion to make the check case-insensitive to ensure robustness.
|
Size Change: +314 B (0%) Total Size: 17.8 MB ℹ️ View Unchanged
|
richieforeman
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LG
…n fallback mechanism (google-gemini#11284)
TLDR
Fixes #10728.
This PR modifies the fallback mechanism in
WebFetchToolto respect theContent-TypeHTTP header of the fetched resource. Previously,html-to-textconversion was applied unconditionally to all responses in the fallback path, which corrupted non-HTML data such as JSON APIs or raw source code files.Now,
html-to-textconversion is only applied if theContent-Typeindicates HTML or is missing. For all other content types, the raw text content is returned.Dive Deeper
packages/core/src/tools/web-fetch.ts):WebFetchToolInvocation.executeFallbackto retrieve thecontent-typeheader from thefetchWithTimeoutresponse.contentType.includes('text/html')or if it is empty string. Only in these cases ishtml-to-text.convert()called.application/json,text/plain),response.text()is used raw.packages/core/src/tools/web-fetch.test.ts):describe('execute (fallback)', ...)test block.executeFallbackmethod.text/html(verified conversion happens).application/json(verified raw text is used).text/plain(verified raw text is used).Content-Typeheader (verified conversion happens, preserving existing behavior).Reviewer Test Plan
Web fetch should still operate normally. Use natural language to guide the usage for the web fetch tool for various content type sites.
Testing Matrix
Linked issues / bugs