Add Colang v2 example for sensitive data detection

[lapinek]

Description

This PR adds a new example configuration for sensitive_data_detection using Colang v2 flows:
examples/configs/sensitive_data_detection_v2/

It also adds the necessary global declarations to allow the rails to output redacted data (however, see the related issue below).

Related Issue(s)

• Depends on: fix: Apply guardrails transformations to LLM inputs and bot outputs. #1297

Mentions

@drazvan — it looks like you’ve contributed to this package along with [email protected]. If you could take a look, that would be great!

Checklist

• I've read the CONTRIBUTING guidelines.
• I've updated the documentation if applicable.
• I've added tests if applicable.
• @mentions of the person or team responsible for reviewing proposed changes.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (develop@0d6fa42). Learn more about missing BASE report.
⚠️ Report is 7 commits behind head on develop.

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #1301   +/-   ##
==========================================
  Coverage           ?   70.20%           
==========================================
  Files              ?      161           
  Lines              ?    16123           
  Branches           ?        0           
==========================================
  Hits               ?    11319           
  Misses             ?     4804           
  Partials           ?        0           

Flag	Coverage Δ
python	70.20% <ø> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[Copilot]

Pull Request Overview

This PR adds a new Colang v2 example configuration for sensitive data detection using Presidio, enabling redaction of sensitive information from user inputs and bot outputs. The changes include necessary global variable declarations to support the data masking functionality.

Key Changes

• Added global variable declarations ($user_message, $bot_message, $relevant_chunks) to enable proper data flow for masking operations
• Created a complete Colang v2 example configuration with input/output rails for sensitive data detection
• Fixed a typo in a comment ("RETRIVAL" → "RETRIEVAL")

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
nemoguardrails/library/sensitive_data_detection/flows.co	Added global variable declarations and fixed spelling error
examples/configs/sensitive_data_detection_v2/main.co	Core flow configuration for Colang v2 example
examples/configs/sensitive_data_detection_v2/flows.co	Input/output rail definitions for sensitive data masking
examples/configs/sensitive_data_detection_v2/config.yml	Configuration file with model settings and detection parameters
examples/configs/sensitive_data_detection_v2/README.md	Documentation for the new example configuration

---

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