feat: Implement Bible reference parsing with fuzzy matching

[google-labs-jules]

This PR introduces a robust Bible reference parser to the ScriptureBot application. It allows the bot to correctly identify and normalize Bible references from user messages, improving the reliability of passage retrieval.

Key features:

• Normalization: Converts abbreviations (e.g., "gen", "1jn") to full book names ("Genesis", "1 John").
• Fuzzy Matching: Handles typos using Levenshtein distance (e.g., "Gensis" -> "Genesis") with length-based thresholds to avoid false positives.
• Identification: Distinguishes valid references from random text (e.g., "John is here" is rejected).
• Smart Defaults:
  • Multi-chapter books default to Chapter 1 if no number is specified (e.g., "Genesis" -> "Genesis 1").
  • Single-chapter books (e.g., "Jude") are preserved as-is.
• Integration: seamlessly integrated into the GetBiblePassage flow to enhance the default message handler.

---

PR created automatically by Jules for task 7479266757348735100 started by @julwrites

[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!

---

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

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