feat: initial release of @mobiletic/anonymizer

Framework-agnostic PII anonymization extracted from Mobiletic's chatbot.
Pluggable LLM detection + configurable regex fallback, deterministic
coreference, and streaming-safe de-anonymization.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mobiletic
2026-06-20 21:58:38 +01:00
commit f09b917f1a
20 changed files with 3889 additions and 0 deletions

View File

@@ -0,0 +1,58 @@
import { describe, it, expect, vi, afterEach } from 'vitest';
import { openAICompatibleProvider } from '../src/index.js';
const opts = { baseUrl: 'https://api.example.com/v1', apiKey: 'k', model: 'm' };
function mockFetchJson(content: unknown) {
return vi.fn().mockResolvedValue({
ok: true,
json: async () => ({ choices: [{ message: { content: JSON.stringify(content) } }] }),
});
}
afterEach(() => {
vi.unstubAllGlobals();
});
describe('openAICompatibleProvider', () => {
it('isConfigured() reflects whether baseUrl/apiKey/model are present', () => {
expect(openAICompatibleProvider(opts).isConfigured()).toBe(true);
expect(openAICompatibleProvider({ ...opts, apiKey: '' }).isConfigured()).toBe(false);
});
it('anonymize() parses {texte_anonymise, mapping} and posts temperature 0 + json_object', async () => {
const fetchMock = mockFetchJson({ texte_anonymise: '[EMAIL_1]', mapping: { '[EMAIL_1]': 'a@b.ch' } });
vi.stubGlobal('fetch', fetchMock);
const r = await openAICompatibleProvider(opts).anonymize('a@b.ch');
expect(r).toEqual({ anon: '[EMAIL_1]', mapping: { '[EMAIL_1]': 'a@b.ch' } });
const [url, init] = fetchMock.mock.calls[0];
expect(url).toBe('https://api.example.com/v1/chat/completions');
const body = JSON.parse(init.body);
expect(body.temperature).toBe(0);
expect(body.response_format).toEqual({ type: 'json_object' });
expect(init.headers.Authorization).toBe('Bearer k');
});
it('anonymizeBatch() returns {segments, mapping} and includes used ids in the prompt', async () => {
const fetchMock = mockFetchJson({ segments: ['[PER_2.NOM:M]'], mapping: { '[PER_2.NOM:M]': 'Bob' } });
vi.stubGlobal('fetch', fetchMock);
const r = await openAICompatibleProvider(opts).anonymizeBatch(['Bob'], ['[PER_1.NOM:M]']);
expect(r.segments).toEqual(['[PER_2.NOM:M]']);
const system = JSON.parse(fetchMock.mock.calls[0][1].body).messages[0].content;
expect(system).toContain('[PER_1.NOM:M]');
});
it('throws on a non-OK HTTP status', async () => {
vi.stubGlobal('fetch', vi.fn().mockResolvedValue({ ok: false, status: 500 }));
await expect(openAICompatibleProvider(opts).anonymize('x')).rejects.toThrow('LLM_HTTP_500');
});
it('throws on a malformed response shape', async () => {
vi.stubGlobal('fetch', mockFetchJson({ wrong: true }));
await expect(openAICompatibleProvider(opts).anonymize('x')).rejects.toThrow('LLM_BAD_SHAPE');
});
});