Add --eval no-pii named evaluator

[hidai25]

Summary

Add a built-in evaluator that checks whether the agent's response leaks PII (names, emails, phone numbers, SSNs). Activated with --eval no-pii.

What it should do

Use regex patterns to detect common PII in the agent's response. No LLM needed — this should be fully deterministic and fast.

PII patterns to detect (minimum)

• Email addresses
• Phone numbers (US formats)
• Social Security Numbers
• Credit card numbers

How to implement

• Add evalview/evaluators/pii_evaluator.py
• Follow the pattern of existing evaluators in evalview/evaluators/
• Hook it into the --eval flag in evalview/cli.py

Acceptance criteria

• evalview run --eval no-pii works without a rubric in the YAML
• Test fails when agent response contains an email address or phone number
• Test passes when response is PII-free

Good first issue notes

No LLM required — pure regex. Well-isolated, single file to create. Great starting point for understanding the evaluator pattern.