Add Parallel as an additional backend for browser #219
Conversation
anshultomar746
commented
Oct 22, 2025
anshultomar746
commented
- Added parallel search and extract functionalities as an additional browser backend
- Added unit tests
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| if "results" in data: | ||
| titles_and_urls = [ | ||
| (result["title"], result["url"], " ".join(result.get("excerpts", []))) | ||
| for result in data["results"] | ||
| ] |
There was a problem hiding this comment.
The new ParallelBackend.search builds the HTML result list with " ".join(result.get("excerpts", [])). When the API returns "excerpts": null (the documented shape allows null when no excerpt is available), the key exists so dict.get yields None, causing join() to raise a TypeError and the browser tool crashes for those queries. Consider normalizing with result.get("excerpts") or [] or coercing to an empty list before joining.
Useful? React with 👍 / 👎.
1 participant
