feat: harden generic preset, add LLM retry, and finish tooling/docs

- PatternDef.validate + Luhn-gated credit-card detection; de-overlap the
  generic phone/date/IP patterns; presets.swiss unchanged (production behavior)
- strip g/y flags from nameHint so .test() is stateless (latent footgun)
- openAICompatibleProvider: bounded retry on transient failures (network /
  timeout / 429 / 5xx), configurable via retries + retryDelayMs
- eslint + prettier + vitest coverage (97%); CI runs lint/format/coverage
- docs: README badges + new-option docs, SECURITY.md, issue/PR templates

26 tests passing; build emits ESM+CJS+types.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

README.md

@@ -1,5 +1,9 @@
 # @mobiletic/anonymizer
 
+[![CI](https://github.com/mobiletic/anonymizer/actions/workflows/ci.yml/badge.svg)](https://github.com/mobiletic/anonymizer/actions/workflows/ci.yml)
+[![npm version](https://img.shields.io/npm/v/@mobiletic/anonymizer.svg)](https://www.npmjs.com/package/@mobiletic/anonymizer)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
+
 Framework-agnostic **PII anonymization & pseudonymization** for TypeScript/JavaScript.
 
 It replaces personal data in text with stable placeholders before the text leaves your trust boundary
@@ -64,6 +68,11 @@ const { anon, mapping } = await anonymizer.anonymize('Le dossier de Alain Jaccar
 If the LLM call fails, times out, or returns an invalid shape, the anonymizer automatically falls back to
 the regex engine — it never throws on a provider failure.
 
+`openAICompatibleProvider` retries **transient** failures (network error, timeout, HTTP 429/5xx) before
+giving up; 4xx and malformed responses are not retried. Tune with `timeoutMs` (per attempt, default 3000),
+`retries` (default 1 → 2 attempts), and `retryDelayMs` (linear backoff, default 250). Worst-case latency
+is `(retries + 1) × timeoutMs`, so keep `retries` low on latency-sensitive paths.
+
 ### Streaming de-anonymization
 
 When you stream an LLM answer back to a user, restore real values without ever emitting a half-written
@@ -102,7 +111,7 @@ new Anonymizer({
 ```ts
 import { presets } from '@mobiletic/anonymizer';
 
-presets.swiss;   // AVS, IBAN CH, EMAIL, Swiss phone, DATE
+presets.swiss; // AVS, IBAN CH, EMAIL, Swiss phone, DATE
 presets.generic; // EMAIL, IBAN, credit card, IPv4, phone, DATE
 
 // Compose / extend:
@@ -112,6 +121,17 @@ const patterns = [
 ];
 ```
 
+Each pattern may carry an optional `validate(match) => boolean` second stage — a match is only redacted
+if it passes. `presets.generic` uses it for a [Luhn](https://en.wikipedia.org/wiki/Luhn_algorithm) check
+so arbitrary long digit runs aren't mistaken for credit cards:
+
+```ts
+{ tag: 'CREDIT_CARD', re: /\b\d(?:[ -]?\d){12,18}\b/g, validate: luhnValid }
+```
+
+> The `generic` preset is a **best-effort** starting point — broad patterns (phone, date, card) can
+> overlap. For production use, prefer a locale-specific preset (`presets.swiss`) or your own patterns.
+
 ### Custom LLM provider
 
 Implement `LlmProvider` to use any backend (Anthropic, a local model, a rules engine…):
@@ -121,8 +141,12 @@ import type { LlmProvider } from '@mobiletic/anonymizer';
 
 const myProvider: LlmProvider = {
   isConfigured: () => true,
-  async anonymize(text) { /* return { anon, mapping } */ },
-  async anonymizeBatch(texts, usedIds) { /* return { segments, mapping } */ },
+  async anonymize(text) {
+    /* return { anon, mapping } */
+  },
+  async anonymizeBatch(texts, usedIds) {
+    /* return { segments, mapping } */
+  },
 };
 ```