✨ Quality: Improve test coverage - useAIPrompt

[galiprandi]

💡 What: This improvement adds 13 new test cases to lib/hooks/useAIPrompt.test.ts, targeting previously uncovered branches in the useAIPrompt hook.

🎯 Why: The useAIPrompt hook had several untested logic paths, particularly around multimodal content type inference and defensive checks for browser-specific AI APIs.

📊 Impact:

• Statement coverage for useAIPrompt.ts increased from 77.86% to 99.23%.
• Branch coverage increased from 52.21% to 92.03%.
• Ensures the hook robustly handles various input types (AudioBuffer, visual elements), correctly cleans up internal state on unmount, and gracefully handles model initialization failures.

✅ Verification:

• Ran pnpm test lib/hooks/useAIPrompt.test.ts (all 26 tests passed).
• Ran pnpm test:coverage to verify the improvement.
• Ran pnpm lint to ensure no regression in code quality.

---

PR created automatically by Jules for task 3194697612275854990 started by @galiprandi

[google-labs-jules]

👋 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!

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

---

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