Jev 数据隐私：官方记录说了什么，以及如何少发数据

// lib/pii-minimize.ts — redact direct identifiers before the Jev call.
// A routing decision keys off what the ticket SAYS, not who said it:
// queue "billing" does not need a name, an email, or a card number.

const PATTERNS: [RegExp, string][] = [
  [/[\w.+-]+@[\w-]+\.[\w.]+/g, '[email]'],
  [/\b(?:\d[ -]*?){13,16}\b/g, '[card]'],
  [/\+?\d[\d\s().-]{7,}\d/g, '[phone]'],
];

// Salted FNV-1a: the same customer id maps to the same stable token, so
// decisions stay correlatable in YOUR logs while the identifier itself
// never leaves your system.
function pseudonym(value: string): string {
  const input = value + (process.env.PSEUDONYM_SALT ?? '');
  let h = 2166136261;
  for (let i = 0; i < input.length; i++) {
    h ^= input.charCodeAt(i);
    h = Math.imul(h, 16777619);
  }
  return 'cust_' + (h >>> 0).toString(36);
}

export function minimizeState(state: string): string {
  let out = state.replace(/customer[ _#]?\d+/gi, (m) => pseudonym(m));
  for (const [pattern, tag] of PATTERNS) out = out.replace(pattern, tag);
  return out;
}

// Usage — one line before the existing call:
//   const state = minimizeState(rawTicketBody);
//   await evaluate({ model: 'jev-latest', state, questions });

# pii_minimize.py — redact direct identifiers before the Jev call.
import hashlib
import hmac
import os
import re

PATTERNS = [
    (re.compile(r"[\w.+-]+@[\w-]+\.[\w.]+"), "[email]"),
    (re.compile(r"\b(?:\d[ -]*?){13,16}\b"), "[card]"),
    (re.compile(r"\+?\d[\d\s().-]{7,}\d"), "[phone]"),
]
CUSTOMER = re.compile(r"customer[ _#]?\d+", re.IGNORECASE)
_SALT = os.environ.get("PSEUDONYM_SALT", "").encode()


def _pseudonym(match: re.Match) -> str:
    # Salted HMAC: the same customer id maps to the same stable token in
    # YOUR logs; the identifier itself never leaves your system.
    digest = hmac.new(_SALT, match.group(0).encode(), hashlib.sha256).hexdigest()
    return "cust_" + digest[:10]


def minimize_state(state: str) -> str:
    state = CUSTOMER.sub(_pseudonym, state)
    for pattern, tag in PATTERNS:
        state = pattern.sub(tag, state)
    return state


# Usage — one line before the existing call:
#   state = minimize_state(raw_ticket_body)
#   client.evaluate(model="jev-latest", state=state, questions=questions)