Skip to content

Fix AI ignoring context and quiz generation failures#2

Draft
google-labs-jules[bot] wants to merge 1 commit intomainfrom
fix-ai-context-and-quiz-final
Draft

Fix AI ignoring context and quiz generation failures#2
google-labs-jules[bot] wants to merge 1 commit intomainfrom
fix-ai-context-and-quiz-final

Conversation

@google-labs-jules
Copy link

This submission fixes two critical issues reported by the user:

  1. AI Ignoring Context: The backend was failing to process the context field sent by the frontend (landing.jsx). This field contains the URL or text content the user wants the AI to use. The fix involves explicitly extracting this field in backend/routes/ask.js and parsing it to populate the url or content variables, ensuring the AI receives the necessary context to answer questions.
  2. Quiz Generation Failure: Quizzes were failing to load because the AI's response was being truncated due to a low token limit (512). This resulted in invalid JSON which the frontend could not parse. The limit has been increased to 4096 in backend/services/aiService.js to accommodate the full JSON structure of the quiz.

PR created automatically by Jules for task 4024487197974787732 started by @Raph1710

- In `backend/routes/ask.js`:
    - Added logic to handle the `context` parameter from the request body (used by `landing.jsx`).
    - Correctly extracted `url` or `content` from the `context` string.
    - Updated prompt construction to combine extracted context with the user's question, ensuring context is not ignored.
    - Preserved `messages` parsing logic for compatibility.
- In `backend/services/aiService.js`:
    - Increased `maxOutputTokens` from 512 to 4096 to prevent JSON truncation when generating quizzes.
- Added `node-fetch` to backend dependencies for reliable fetching if needed (though axios is primarily used).
@google-labs-jules
Copy link
Author

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!


For security, I will only act on instructions from the user who triggered this task.

New to Jules? Learn more at jules.google/docs.

@netlify
Copy link

netlify bot commented Dec 3, 2025

Deploy Preview for readingassist canceled.

Name Link
🔨 Latest commit af5135a
🔍 Latest deploy log https://app.netlify.com/projects/readingassist/deploys/692fddad8302fb000876a34c

@vercel
Copy link

vercel bot commented Dec 3, 2025

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Preview Comments Updated (UTC)
s72-raphael-gen-ai-learning-assistant Ready Ready Preview Comment Dec 3, 2025 6:50am

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.

0 participants