Fixing used_images usage in summary_json_system_prompt

[jamesbraza]

There were two problems being fixed here:

• The JSON sample key "used_images" didn't have a value
• "used_images" should only be present if you actually want to use this attribute, which most users won't care about

[Copilot]

Pull Request Overview

Fixes two issues with the used_images attribute in the summary_json_system_prompt: corrects incomplete JSON sample and makes the attribute optional for users who don't need image tracking.

• Separates standard and multimodal JSON prompts to handle used_images appropriately
• Updates tests to use multimodal prompt and properly handle boolean conversion
• Adds documentation for the optional multimodal prompt usage

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
src/paperqa/prompts.py	Splits prompt into standard and multimodal versions, fixing JSON format
tests/test_paperqa.py	Updates image tests to use multimodal prompt and fix boolean assertions
README.md	Documents the optional multimodal prompt configuration

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[dosubot]

Related Documentation

1 document(s) may need updating based on files changed in this PR

• Multimodal Support in PaperQA

^{How did I do? Any feedback?}  

[dosubot]

Documentation Updates

Checked 1 published document(s). No updates required.

^{How did I do? Any feedback?}